diff options
1304 files changed, 12886 insertions, 7035 deletions
@@ -12,6 +12,7 @@ # Aaron Durbin <adurbin@google.com> Abel Vesa <abelvesa@kernel.org> <abel.vesa@nxp.com> +Abel Vesa <abelvesa@kernel.org> <abel.vesa@linaro.org> Abel Vesa <abelvesa@kernel.org> <abelvesa@gmail.com> Abhijeet Dharmapurikar <quic_adharmap@quicinc.com> <adharmap@codeaurora.org> Abhinav Kumar <quic_abhinavk@quicinc.com> <abhinavk@codeaurora.org> @@ -127,7 +128,8 @@ Barry Song <baohua@kernel.org> <Baohua.Song@csr.com> Barry Song <baohua@kernel.org> <barry.song@analog.com> Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com> Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com> -Bartosz Golaszewski <brgl@bgdev.pl> <bgolaszewski@baylibre.com> +Bartosz Golaszewski <brgl@kernel.org> <bartosz.golaszewski@linaro.org> +Bartosz Golaszewski <brgl@kernel.org> <bgolaszewski@baylibre.com> Ben Dooks <ben-linux@fluff.org> <ben.dooks@simtec.co.uk> Ben Dooks <ben-linux@fluff.org> <ben.dooks@sifive.com> Ben Gardner <bgardner@wabtec.com> @@ -206,6 +208,7 @@ Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch> Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com> +Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org> Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com> David Brownell <david-b@pacbell.net> David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org> @@ -415,6 +418,7 @@ Juha Yrjola <at solidboot.com> Juha Yrjola <juha.yrjola@nokia.com> Juha Yrjola <juha.yrjola@solidboot.com> Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com> +Justin Iurman <justin.iurman@gmail.com> <justin.iurman@uliege.be> Iskren Chernev <me@iskren.info> <iskren.chernev@gmail.com> Kalle Valo <kvalo@kernel.org> <kvalo@codeaurora.org> Kalle Valo <kvalo@kernel.org> <quic_kvalo@quicinc.com> @@ -471,6 +475,10 @@ Linas Vepstas <linas@austin.ibm.com> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de> Linus Lüssing <linus.luessing@c0d3.blue> <ll@simonwunderlich.de> +Linus Walleij <linusw@kernel.org> <linus.walleij@ericsson.com> +Linus Walleij <linusw@kernel.org> <linus.walleij@stericsson.com> +Linus Walleij <linusw@kernel.org> <linus.walleij@linaro.org> +Linus Walleij <linusw@kernel.org> <triad@df.lth.se> <linux-hardening@vger.kernel.org> <kernel-hardening@lists.openwall.com> Li Yang <leoyang.li@nxp.com> <leoli@freescale.com> Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> @@ -704,6 +712,8 @@ Sankeerth Billakanti <quic_sbillaka@quicinc.com> <sbillaka@codeaurora.org> Santosh Shilimkar <santosh.shilimkar@oracle.org> Santosh Shilimkar <ssantosh@kernel.org> Sarangdhar Joshi <spjoshi@codeaurora.org> +Saravana Kannan <saravanak@kernel.org> <skannan@codeaurora.org> +Saravana Kannan <saravanak@kernel.org> <saravanak@google.com> Sascha Hauer <s.hauer@pengutronix.de> Sahitya Tummala <quic_stummala@quicinc.com> <stummala@codeaurora.org> Sathishkumar Muruganandam <quic_murugana@quicinc.com> <murugana@codeaurora.org> @@ -786,6 +796,7 @@ Sven Eckelmann <sven@narfation.org> <sven.eckelmann@open-mesh.com> Sven Eckelmann <sven@narfation.org> <sven.eckelmann@openmesh.com> Sven Eckelmann <sven@narfation.org> <sven@open-mesh.com> Sven Peter <sven@kernel.org> <sven@svenpeter.dev> +Szymon Wilczek <swilczek.lx@gmail.com> <szymonwilczek@gmx.com> Takashi YOSHII <takashi.yoshii.zj@renesas.com> Tamizh Chelvam Raja <quic_tamizhr@quicinc.com> <tamizhr@codeaurora.org> Taniya Das <quic_tdas@quicinc.com> <tdas@codeaurora.org> @@ -793,6 +804,7 @@ Tanzir Hasan <tanzhasanwork@gmail.com> <tanzirh@google.com> Tejun Heo <htejun@gmail.com> Tomeu Vizoso <tomeu@tomeuvizoso.net> <tomeu.vizoso@collabora.com> Thomas Graf <tgraf@suug.ch> +Thomas Gleixner <tglx@kernel.org> <tglx@linutronix.de> Thomas Körper <socketcan@esd.eu> <thomas.koerper@esd.eu> Thomas Pedersen <twp@codeaurora.org> Thorsten Blum <thorsten.blum@linux.dev> <thorsten.blum@toblux.com> @@ -839,6 +851,7 @@ Valentin Schneider <vschneid@redhat.com> <valentin.schneider@arm.com> Veera Sundaram Sankaran <quic_veeras@quicinc.com> <veeras@codeaurora.org> Veerabhadrarao Badiganti <quic_vbadigan@quicinc.com> <vbadigan@codeaurora.org> Venkateswara Naralasetty <quic_vnaralas@quicinc.com> <vnaralas@codeaurora.org> +Viacheslav Bocharov <v@baodeep.com> <adeep@lexina.in> Vikash Garodia <vikash.garodia@oss.qualcomm.com> <vgarodia@codeaurora.org> Vikash Garodia <vikash.garodia@oss.qualcomm.com> <quic_vgarodia@quicinc.com> Vincent Mailhol <mailhol@kernel.org> <mailhol.vincent@wanadoo.fr> @@ -857,7 +870,6 @@ Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> WangYuli <wangyuli@aosc.io> <wangyl5933@chinaunicom.cn> WangYuli <wangyuli@aosc.io> <wangyuli@deepin.org> -WangYuli <wangyuli@aosc.io> <wangyuli@uniontech.com> Weiwen Hu <huweiwen@linux.alibaba.com> <sehuww@mail.scut.edu.cn> WeiXiong Liao <gmpy.liaowx@gmail.com> <liaoweixiong@allwinnertech.com> Wen Gong <quic_wgong@quicinc.com> <wgong@codeaurora.org> @@ -868,6 +880,8 @@ Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn> Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com> +Yixun Lan <dlan@kernel.org> <dlan@gentoo.org> +Yixun Lan <dlan@kernel.org> <yixun.lan@amlogic.com> Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com> Yu-Chun Lin <eleanor.lin@realtek.com> <eleanor15x@gmail.com> Yusuke Goda <goda.yusuke@renesas.com> @@ -1398,7 +1398,7 @@ D: SRM environment driver (for Alpha systems) P: 1024D/8399E1BB 250D 3BCF 7127 0D8C A444 A961 1DBD 5E75 8399 E1BB N: Thomas Gleixner -E: tglx@linutronix.de +E: tglx@kernel.org D: NAND flash hardware support, JFFS2 on NAND flash N: Jérôme Glisse @@ -2231,6 +2231,10 @@ S: Markham, Ontario S: L3R 8B2 S: Canada +N: Krzysztof Kozlowski +E: krzk@kernel.org +D: NFC network subsystem and drivers maintainer + N: Christian Krafft D: PowerPC Cell support diff --git a/Documentation/ABI/stable/sysfs-kernel-time-aux-clocks b/Documentation/ABI/stable/sysfs-kernel-time-aux-clocks index 825508f42af6..e1a894c8dd1b 100644 --- a/Documentation/ABI/stable/sysfs-kernel-time-aux-clocks +++ b/Documentation/ABI/stable/sysfs-kernel-time-aux-clocks @@ -1,5 +1,5 @@ What: /sys/kernel/time/aux_clocks/<ID>/enable Date: May 2025 -Contact: Thomas Gleixner <tglx@linutronix.de> +Contact: Thomas Gleixner <tglx@kernel.org> Description: Controls the enablement of auxiliary clock timekeepers. diff --git a/Documentation/ABI/testing/sysfs-devices-soc b/Documentation/ABI/testing/sysfs-devices-soc index 5269808ec35f..cb6776a4afe0 100644 --- a/Documentation/ABI/testing/sysfs-devices-soc +++ b/Documentation/ABI/testing/sysfs-devices-soc @@ -17,14 +17,14 @@ Date: January 2012 contact: Lee Jones <lee@kernel.org> Description: Read-only attribute common to all SoCs. Contains the SoC machine - name (e.g. Ux500). + name (e.g. DB8500). What: /sys/devices/socX/family Date: January 2012 contact: Lee Jones <lee@kernel.org> Description: Read-only attribute common to all SoCs. Contains SoC family name - (e.g. DB8500). + (e.g. ux500). On many of ARM based silicon with SMCCC v1.2+ compliant firmware this will contain the JEDEC JEP106 manufacturer’s identification diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a8d0afde7f85..1058f2a6d6a8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2917,6 +2917,41 @@ Kernel parameters for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" are exclusive, so you cannot specify multiple forms. + kfence.burst= [MM,KFENCE] The number of additional successive + allocations to be attempted through KFENCE for each + sample interval. + Format: <unsigned integer> + Default: 0 + + kfence.check_on_panic= + [MM,KFENCE] Whether to check all KFENCE-managed objects' + canaries on panic. + Format: <bool> + Default: false + + kfence.deferrable= + [MM,KFENCE] Whether to use a deferrable timer to trigger + allocations. This avoids forcing CPU wake-ups if the + system is idle, at the risk of a less predictable + sample interval. + Format: <bool> + Default: CONFIG_KFENCE_DEFERRABLE + + kfence.sample_interval= + [MM,KFENCE] KFENCE's sample interval in milliseconds. + Format: <unsigned integer> + 0 - Disable KFENCE. + >0 - Enabled KFENCE with given sample interval. + Default: CONFIG_KFENCE_SAMPLE_INTERVAL + + kfence.skip_covered_thresh= + [MM,KFENCE] If pool utilization reaches this threshold + (pool usage%), KFENCE limits currently covered + allocations of the same source from further filling + up the pool. + Format: <unsigned integer> + Default: 75 + kgdbdbgp= [KGDB,HW,EARLY] kgdb over EHCI usb debug port. Format: <Controller#>[,poll interval] The controller # is the number of the ehci usb debug diff --git a/Documentation/admin-guide/laptops/alienware-wmi.rst b/Documentation/admin-guide/laptops/alienware-wmi.rst index 27a32a8057da..e532c60db8e2 100644 --- a/Documentation/admin-guide/laptops/alienware-wmi.rst +++ b/Documentation/admin-guide/laptops/alienware-wmi.rst @@ -105,7 +105,7 @@ information. Manual fan control on the other hand, is not exposed directly by the AWCC interface. Instead it let's us control a fan `boost` value. This `boost` value -has the following aproximate behavior over the fan pwm: +has the following approximate behavior over the fan pwm: :: diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 369a738a6819..91fa4ccd326c 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -303,6 +303,14 @@ netdev_max_backlog Maximum number of packets, queued on the INPUT side, when the interface receives packets faster than kernel can process them. +qdisc_max_burst +------------------ + +Maximum number of packets that can be temporarily stored before +reaching qdisc. + +Default: 1000 + netdev_rss_key -------------- diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 4d71211fdad8..06d0ebddeefa 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -231,6 +231,8 @@ eventually gets pushed out to disk. This tunable is used to define when dirty inode is old enough to be eligible for writeback by the kernel flusher threads. And, it is also used as the interval to wakeup dirtytime_writeback thread. +Setting this to zero disables periodic dirtytime writeback. + dirty_writeback_centisecs ========================= @@ -494,6 +496,10 @@ memory allocations. The default value depends on CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT. +When CONFIG_MEM_ALLOC_PROFILING_DEBUG=y, this control is read-only to avoid +warnings produced by allocations made while profiling is disabled and freed +when it's enabled. + memory_failure_early_kill ========================= diff --git a/Documentation/arch/riscv/uabi.rst b/Documentation/arch/riscv/uabi.rst index 243e40062e34..0c5299e00762 100644 --- a/Documentation/arch/riscv/uabi.rst +++ b/Documentation/arch/riscv/uabi.rst @@ -7,7 +7,9 @@ ISA string ordering in /proc/cpuinfo ------------------------------------ The canonical order of ISA extension names in the ISA string is defined in -chapter 27 of the unprivileged specification. +Chapter 27 of the RISC-V Instruction Set Manual Volume I Unprivileged ISA +(Document Version 20191213). + The specification uses vague wording, such as should, when it comes to ordering, so for our purposes the following rules apply: diff --git a/Documentation/arch/x86/amd_hsmp.rst b/Documentation/arch/x86/amd_hsmp.rst index a094f55c10b0..8bb411f0d70d 100644 --- a/Documentation/arch/x86/amd_hsmp.rst +++ b/Documentation/arch/x86/amd_hsmp.rst @@ -14,7 +14,7 @@ set of mailbox registers. More details on the interface can be found in chapter "7 Host System Management Port (HSMP)" of the family/model PPR -Eg: https://www.amd.com/content/dam/amd/en/documents/epyc-technical-docs/programmer-references/55898_B1_pub_0_50.zip +Eg: https://docs.amd.com/v/u/en-US/55898_B1_pub_0_50 HSMP interface is supported on EPYC line of server CPUs and MI300A (APU). @@ -185,7 +185,7 @@ what happened. The transaction returns 0 on success. More details on the interface and message definitions can be found in chapter "7 Host System Management Port (HSMP)" of the respective family/model PPR -eg: https://www.amd.com/content/dam/amd/en/documents/epyc-technical-docs/programmer-references/55898_B1_pub_0_50.zip +eg: https://docs.amd.com/v/u/en-US/55898_B1_pub_0_50 User space C-APIs are made available by linking against the esmi library, which is provided by the E-SMS project https://www.amd.com/en/developer/e-sms.html. diff --git a/Documentation/arch/x86/topology.rst b/Documentation/arch/x86/topology.rst index 86bec8ac2c4d..f779a68875c5 100644 --- a/Documentation/arch/x86/topology.rst +++ b/Documentation/arch/x86/topology.rst @@ -17,7 +17,7 @@ with the generic one and look at this one in parallel for the x86 specifics. Needless to say, code should use the generic functions - this file is *only* here to *document* the inner workings of x86 topology. -Started by Thomas Gleixner <tglx@linutronix.de> and Borislav Petkov <bp@alien8.de>. +Started by Thomas Gleixner <tglx@kernel.org> and Borislav Petkov <bp@alien8.de>. The main aim of the topology facilities is to present adequate interfaces to code which needs to know/query/use the structure of the running system wrt diff --git a/Documentation/core-api/cpu_hotplug.rst b/Documentation/core-api/cpu_hotplug.rst index e1b0eeabbb5e..9b4afca9fd09 100644 --- a/Documentation/core-api/cpu_hotplug.rst +++ b/Documentation/core-api/cpu_hotplug.rst @@ -8,7 +8,7 @@ CPU hotplug in the Kernel Srivatsa Vaddagiri <vatsa@in.ibm.com>, Ashok Raj <ashok.raj@intel.com>, Joel Schopp <jschopp@austin.ibm.com>, - Thomas Gleixner <tglx@linutronix.de> + Thomas Gleixner <tglx@kernel.org> Introduction ============ diff --git a/Documentation/core-api/genericirq.rst b/Documentation/core-api/genericirq.rst index 582bde9bf5a9..b16d751d4b98 100644 --- a/Documentation/core-api/genericirq.rst +++ b/Documentation/core-api/genericirq.rst @@ -439,6 +439,6 @@ Credits The following people have contributed to this document: -1. Thomas Gleixner tglx@linutronix.de +1. Thomas Gleixner tglx@kernel.org 2. Ingo Molnar mingo@elte.hu diff --git a/Documentation/core-api/librs.rst b/Documentation/core-api/librs.rst index 6010f5bc5bf9..0d88893dbc03 100644 --- a/Documentation/core-api/librs.rst +++ b/Documentation/core-api/librs.rst @@ -209,4 +209,4 @@ testing. Thanks a lot. The following people have contributed to this document: -Thomas Gleixner\ tglx@linutronix.de +Thomas Gleixner\ tglx@kernel.org diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml index 68a2d5fecc43..336669e16d7a 100644 --- a/Documentation/devicetree/bindings/arm/fsl.yaml +++ b/Documentation/devicetree/bindings/arm/fsl.yaml @@ -1105,7 +1105,6 @@ properties: - gateworks,imx8mp-gw74xx # i.MX8MP Gateworks Board - gateworks,imx8mp-gw75xx-2x # i.MX8MP Gateworks Board - gateworks,imx8mp-gw82xx-2x # i.MX8MP Gateworks Board - - gocontroll,moduline-display # GOcontroll Moduline Display controller - prt,prt8ml # Protonic PRT8ML - skov,imx8mp-skov-basic # SKOV i.MX8MP baseboard without frontplate - skov,imx8mp-skov-revb-hdmi # SKOV i.MX8MP climate control without panel @@ -1164,6 +1163,14 @@ properties: - const: engicam,icore-mx8mp # i.MX8MP Engicam i.Core MX8M Plus SoM - const: fsl,imx8mp + - description: Ka-Ro TX8P-ML81 SoM based boards + items: + - enum: + - gocontroll,moduline-display + - gocontroll,moduline-display-106 + - const: karo,tx8p-ml81 + - const: fsl,imx8mp + - description: Kontron i.MX8MP OSM-S SoM based Boards items: - const: kontron,imx8mp-bl-osm-s # Kontron BL i.MX8MP OSM-S Board diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml index 274f590807ca..8f4bd9fb560b 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml @@ -11,7 +11,7 @@ maintainers: - Jitao shi <jitao.shi@mediatek.com> description: | - MediaTek DP and eDP are different hardwares and there are some features + MediaTek DP and eDP are different hardware and there are some features which are not supported for eDP. For example, audio is not supported for eDP. Therefore, we need to use two different compatibles to describe them. In addition, We just need to enable the power domain of DP, so the clock diff --git a/Documentation/devicetree/bindings/i2c/brcm,iproc-i2c.yaml b/Documentation/devicetree/bindings/i2c/brcm,iproc-i2c.yaml index 2aa75b7add7b..daa70a8500e9 100644 --- a/Documentation/devicetree/bindings/i2c/brcm,iproc-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/brcm,iproc-i2c.yaml @@ -16,7 +16,8 @@ properties: - brcm,iproc-nic-i2c reg: - maxItems: 1 + minItems: 1 + maxItems: 2 clock-frequency: enum: [ 100000, 400000 ] @@ -41,8 +42,15 @@ allOf: contains: const: brcm,iproc-nic-i2c then: + properties: + reg: + minItems: 2 required: - brcm,ape-hsls-addr-mask + else: + properties: + reg: + maxItems: 1 unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sa8775p-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sa8775p-rpmh.yaml index 71428d2cce18..3dbe83e2de3d 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,sa8775p-rpmh.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,sa8775p-rpmh.yaml @@ -74,6 +74,37 @@ allOf: - description: aggre UFS CARD AXI clock - description: RPMH CC IPA clock + - if: + properties: + compatible: + contains: + enum: + - qcom,sa8775p-config-noc + - qcom,sa8775p-dc-noc + - qcom,sa8775p-gem-noc + - qcom,sa8775p-gpdsp-anoc + - qcom,sa8775p-lpass-ag-noc + - qcom,sa8775p-mmss-noc + - qcom,sa8775p-nspa-noc + - qcom,sa8775p-nspb-noc + - qcom,sa8775p-pcie-anoc + - qcom,sa8775p-system-noc + then: + properties: + clocks: false + + - if: + properties: + compatible: + contains: + enum: + - qcom,sa8775p-clk-virt + - qcom,sa8775p-mc-virt + then: + properties: + reg: false + clocks: false + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/misc/pci1de4,1.yaml b/Documentation/devicetree/bindings/misc/pci1de4,1.yaml index 2f9a7a554ed8..17a8c19af8cc 100644 --- a/Documentation/devicetree/bindings/misc/pci1de4,1.yaml +++ b/Documentation/devicetree/bindings/misc/pci1de4,1.yaml @@ -25,6 +25,10 @@ properties: items: - const: pci1de4,1 + reg: + maxItems: 1 + description: The PCI Bus-Device-Function address. + '#interrupt-cells': const: 2 description: | @@ -101,6 +105,7 @@ unevaluatedProperties: false required: - compatible + - reg - '#interrupt-cells' - interrupt-controller - pci-ep-bus@1 @@ -111,8 +116,9 @@ examples: #address-cells = <3>; #size-cells = <2>; - rp1@0,0 { + dev@0,0 { compatible = "pci1de4,1"; + reg = <0x10000 0x0 0x0 0x0 0x0>; ranges = <0x01 0x00 0x00000000 0x82010000 0x00 0x00 0x00 0x400000>; #address-cells = <3>; #size-cells = <2>; diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml index 48bd11410e8c..f5068df20cfe 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -56,7 +56,7 @@ properties: clocks: minItems: 5 - maxItems: 7 + maxItems: 6 clock-names: minItems: 5 @@ -67,7 +67,6 @@ properties: - enum: [rchng, refgen] - const: pipe - const: pipediv2 - - const: phy_aux power-domains: maxItems: 1 @@ -180,6 +179,7 @@ allOf: contains: enum: - qcom,glymur-qmp-gen5x4-pcie-phy + - qcom,qcs8300-qmp-gen4x2-pcie-phy - qcom,sa8775p-qmp-gen4x2-pcie-phy - qcom,sa8775p-qmp-gen4x4-pcie-phy - qcom,sc8280xp-qmp-gen3x1-pcie-phy @@ -202,19 +202,6 @@ allOf: compatible: contains: enum: - - qcom,qcs8300-qmp-gen4x2-pcie-phy - then: - properties: - clocks: - minItems: 7 - clock-names: - minItems: 7 - - - if: - properties: - compatible: - contains: - enum: - qcom,glymur-qmp-gen5x4-pcie-phy - qcom,sm8550-qmp-gen4x2-pcie-phy - qcom,sm8650-qmp-gen4x2-pcie-phy diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada3710-xb-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/marvell,armada3710-xb-pinctrl.yaml index 51bad2e8d6f1..4f9013d36874 100644 --- a/Documentation/devicetree/bindings/pinctrl/marvell,armada3710-xb-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada3710-xb-pinctrl.yaml @@ -88,7 +88,7 @@ patternProperties: pcie1_clkreq, pcie1_wakeup, pmic0, pmic1, ptp, ptp_clk, ptp_trig, pwm0, pwm1, pwm2, pwm3, rgmii, sdio0, sdio_sb, smi, spi_cs1, spi_cs2, spi_cs3, spi_quad, uart1, uart2, - usb2_drvvbus1, usb32_drvvbus ] + usb2_drvvbus1, usb32_drvvbus0 ] function: enum: [ drvbus, emmc, gpio, i2c, jtag, led, mii, mii_err, onewire, diff --git a/Documentation/devicetree/bindings/sound/everest,es8316.yaml b/Documentation/devicetree/bindings/sound/everest,es8316.yaml index 81a0215050e0..fe5d938ca310 100644 --- a/Documentation/devicetree/bindings/sound/everest,es8316.yaml +++ b/Documentation/devicetree/bindings/sound/everest,es8316.yaml @@ -49,6 +49,10 @@ properties: items: - const: mclk + interrupts: + maxItems: 1 + description: Headphone detect interrupt + port: $ref: audio-graph-port.yaml# unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml b/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml index 3f4f59287c1c..2eb631950963 100644 --- a/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml +++ b/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml @@ -47,6 +47,12 @@ properties: reg: maxItems: 1 + clocks: + maxItems: 1 + + clock-names: + const: mclk + interrupts: maxItems: 1 description: The CODEC's interrupt output. @@ -98,6 +104,7 @@ properties: - 4 # Use GPIO2 for jack-detect - 5 # Use GPIO3 for jack-detect - 6 # Use GPIO4 for jack-detect + - 7 # Use HDA header for jack-detect realtek,jack-detect-not-inverted: description: @@ -121,6 +128,10 @@ properties: - 2 # Scale current by 1.0 - 3 # Scale current by 1.5 + port: + $ref: audio-graph-port.yaml# + unevaluatedProperties: false + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml index 32dea7392e8d..56c755c22945 100644 --- a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml +++ b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml @@ -70,6 +70,9 @@ properties: "#sound-dai-cells": const: 0 + port: + $ref: /schemas/graph.yaml#/properties/port + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/timer/mrvl,mmp-timer.yaml b/Documentation/devicetree/bindings/timer/mrvl,mmp-timer.yaml index fe6bc4173789..0643cfcc6bc7 100644 --- a/Documentation/devicetree/bindings/timer/mrvl,mmp-timer.yaml +++ b/Documentation/devicetree/bindings/timer/mrvl,mmp-timer.yaml @@ -8,7 +8,7 @@ title: Marvell MMP Timer maintainers: - Daniel Lezcano <daniel.lezcano@linaro.org> - - Thomas Gleixner <tglx@linutronix.de> + - Thomas Gleixner <tglx@kernel.org> - Rob Herring <robh@kernel.org> properties: diff --git a/Documentation/devicetree/bindings/ufs/ufs-common.yaml b/Documentation/devicetree/bindings/ufs/ufs-common.yaml index 9f04f34d8c5a..ed97f5682509 100644 --- a/Documentation/devicetree/bindings/ufs/ufs-common.yaml +++ b/Documentation/devicetree/bindings/ufs/ufs-common.yaml @@ -48,8 +48,8 @@ properties: enum: [1, 2] default: 2 description: - Number of lanes available per direction. Note that it is assume same - number of lanes is used both directions at once. + Number of lanes available per direction. Note that it is assumed that + the same number of lanes are used in both directions at once. vdd-hba-supply: description: diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml index a792434c59db..a7f58114c02e 100644 --- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml @@ -406,7 +406,6 @@ allOf: compatible: contains: enum: - - qcom,ipq5018-dwc3 - qcom,ipq6018-dwc3 - qcom,ipq8074-dwc3 - qcom,msm8953-dwc3 @@ -428,6 +427,7 @@ allOf: compatible: contains: enum: + - qcom,msm8994-dwc3 - qcom,msm8996-dwc3 - qcom,qcs404-dwc3 - qcom,sdm660-dwc3 @@ -451,6 +451,7 @@ allOf: compatible: contains: enum: + - qcom,ipq5018-dwc3 - qcom,ipq5332-dwc3 then: properties: @@ -488,7 +489,6 @@ allOf: enum: - qcom,ipq4019-dwc3 - qcom,ipq8064-dwc3 - - qcom,msm8994-dwc3 - qcom,qcs615-dwc3 - qcom,qcs8300-dwc3 - qcom,qdu1000-dwc3 diff --git a/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml index 8cee7c5582f2..7d784a648b7d 100644 --- a/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml @@ -420,7 +420,6 @@ allOf: compatible: contains: enum: - - qcom,ipq5018-dwc3 - qcom,ipq6018-dwc3 - qcom,ipq8074-dwc3 - qcom,msm8953-dwc3 @@ -443,6 +442,7 @@ allOf: compatible: contains: enum: + - qcom,msm8994-dwc3 - qcom,msm8996-dwc3 - qcom,qcs404-dwc3 - qcom,sdm660-dwc3 @@ -467,6 +467,7 @@ allOf: compatible: contains: enum: + - qcom,ipq5018-dwc3 - qcom,ipq5332-dwc3 then: properties: @@ -509,7 +510,6 @@ allOf: - qcom,ipq4019-dwc3 - qcom,ipq8064-dwc3 - qcom,kaanapali-dwc3 - - qcom,msm8994-dwc3 - qcom,qcs615-dwc3 - qcom,qcs8300-dwc3 - qcom,qdu1000-dwc3 diff --git a/Documentation/driver-api/mtdnand.rst b/Documentation/driver-api/mtdnand.rst index ce77e024c4f1..adf03983f1ba 100644 --- a/Documentation/driver-api/mtdnand.rst +++ b/Documentation/driver-api/mtdnand.rst @@ -996,11 +996,11 @@ The following people have contributed to the NAND driver: 2. David Woodhouse\ dwmw2@infradead.org -3. Thomas Gleixner\ tglx@linutronix.de +3. Thomas Gleixner\ tglx@kernel.org A lot of users have provided bugfixes, improvements and helping hands for testing. Thanks a lot. The following people have contributed to this document: -1. Thomas Gleixner\ tglx@linutronix.de +1. Thomas Gleixner\ tglx@kernel.org diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 77704fde9845..04c7691e50e0 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -416,6 +416,7 @@ lm_change yes no no lm_breaker_owns_lease: yes no no lm_lock_expirable yes no no lm_expire_lock no no yes +lm_open_conflict yes no no ====================== ============= ================= ========= buffer_head diff --git a/Documentation/misc-devices/amd-sbi.rst b/Documentation/misc-devices/amd-sbi.rst index 07ceb44fbe5e..f91ddadefe48 100644 --- a/Documentation/misc-devices/amd-sbi.rst +++ b/Documentation/misc-devices/amd-sbi.rst @@ -15,7 +15,7 @@ and SB Temperature Sensor Interface (SB-TSI)). More details on the interface can be found in chapter "5 Advanced Platform Management Link (APML)" of the family/model PPR [1]_. -.. [1] https://www.amd.com/content/dam/amd/en/documents/epyc-technical-docs/programmer-references/55898_B1_pub_0_50.zip +.. [1] https://docs.amd.com/v/u/en-US/55898_B1_pub_0_50 SBRMI device diff --git a/Documentation/mm/allocation-profiling.rst b/Documentation/mm/allocation-profiling.rst index 316311240e6a..5389d241176a 100644 --- a/Documentation/mm/allocation-profiling.rst +++ b/Documentation/mm/allocation-profiling.rst @@ -33,6 +33,16 @@ Boot parameter: sysctl: /proc/sys/vm/mem_profiling + 1: Enable memory profiling. + + 0: Disable memory profiling. + + The default value depends on CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT. + + When CONFIG_MEM_ALLOC_PROFILING_DEBUG=y, this control is read-only to avoid + warnings produced by allocations made while profiling is disabled and freed + when it's enabled. + Runtime info: /proc/allocinfo diff --git a/Documentation/netlink/specs/dev-energymodel.yaml b/Documentation/netlink/specs/dev-energymodel.yaml new file mode 100644 index 000000000000..11faabfdfbe8 --- /dev/null +++ b/Documentation/netlink/specs/dev-energymodel.yaml @@ -0,0 +1,175 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +# +# Copyright (c) 2025 Valve Corporation. +# +--- +name: dev-energymodel + +doc: | + Energy model netlink interface to notify its changes. + +protocol: genetlink + +uapi-header: linux/dev_energymodel.h + +definitions: + - + type: flags + name: perf-state-flags + entries: + - + name: perf-state-inefficient + doc: >- + The performance state is inefficient. There is in this perf-domain, + another performance state with a higher frequency but a lower or + equal power cost. + - + type: flags + name: perf-domain-flags + entries: + - + name: perf-domain-microwatts + doc: >- + The power values are in micro-Watts or some other scale. + - + name: perf-domain-skip-inefficiencies + doc: >- + Skip inefficient states when estimating energy consumption. + - + name: perf-domain-artificial + doc: >- + The power values are artificial and might be created by platform + missing real power information. + +attribute-sets: + - + name: perf-domain + doc: >- + Information on a single performance domains. + attributes: + - + name: pad + type: pad + - + name: perf-domain-id + type: u32 + doc: >- + A unique ID number for each performance domain. + - + name: flags + type: u64 + doc: >- + Bitmask of performance domain flags. + enum: perf-domain-flags + - + name: cpus + type: u64 + multi-attr: true + doc: >- + CPUs that belong to this performance domain. + - + name: perf-table + doc: >- + Performance states table. + attributes: + - + name: perf-domain-id + type: u32 + doc: >- + A unique ID number for each performance domain. + - + name: perf-state + type: nest + nested-attributes: perf-state + multi-attr: true + - + name: perf-state + doc: >- + Performance state of a performance domain. + attributes: + - + name: pad + type: pad + - + name: performance + type: u64 + doc: >- + CPU performance (capacity) at a given frequency. + - + name: frequency + type: u64 + doc: >- + The frequency in KHz, for consistency with CPUFreq. + - + name: power + type: u64 + doc: >- + The power consumed at this level (by 1 CPU or by a registered + device). It can be a total power: static and dynamic. + - + name: cost + type: u64 + doc: >- + The cost coefficient associated with this level, used during energy + calculation. Equal to: power * max_frequency / frequency. + - + name: flags + type: u64 + doc: >- + Bitmask of performance state flags. + enum: perf-state-flags + +operations: + list: + - + name: get-perf-domains + attribute-set: perf-domain + doc: Get the list of information for all performance domains. + do: + request: + attributes: + - perf-domain-id + reply: + attributes: &perf-domain-attrs + - pad + - perf-domain-id + - flags + - cpus + dump: + reply: + attributes: *perf-domain-attrs + - + name: get-perf-table + attribute-set: perf-table + doc: Get the energy model table of a performance domain. + do: + request: + attributes: + - perf-domain-id + reply: + attributes: + - perf-domain-id + - perf-state + - + name: perf-domain-created + doc: A performance domain is created. + notify: get-perf-table + mcgrp: event + - + name: perf-domain-updated + doc: A performance domain is updated. + notify: get-perf-table + mcgrp: event + - + name: perf-domain-deleted + doc: A performance domain is deleted. + attribute-set: perf-table + event: + attributes: + - perf-domain-id + mcgrp: event + +mcast-groups: + list: + - + name: event diff --git a/Documentation/netlink/specs/em.yaml b/Documentation/netlink/specs/em.yaml deleted file mode 100644 index 9905ca482325..000000000000 --- a/Documentation/netlink/specs/em.yaml +++ /dev/null @@ -1,113 +0,0 @@ -# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) - -name: em - -doc: | - Energy model netlink interface to notify its changes. - -protocol: genetlink - -uapi-header: linux/energy_model.h - -attribute-sets: - - - name: pds - attributes: - - - name: pd - type: nest - nested-attributes: pd - multi-attr: true - - - name: pd - attributes: - - - name: pad - type: pad - - - name: pd-id - type: u32 - - - name: flags - type: u64 - - - name: cpus - type: string - - - name: pd-table - attributes: - - - name: pd-id - type: u32 - - - name: ps - type: nest - nested-attributes: ps - multi-attr: true - - - name: ps - attributes: - - - name: pad - type: pad - - - name: performance - type: u64 - - - name: frequency - type: u64 - - - name: power - type: u64 - - - name: cost - type: u64 - - - name: flags - type: u64 - -operations: - list: - - - name: get-pds - attribute-set: pds - doc: Get the list of information for all performance domains. - do: - reply: - attributes: - - pd - - - name: get-pd-table - attribute-set: pd-table - doc: Get the energy model table of a performance domain. - do: - request: - attributes: - - pd-id - reply: - attributes: - - pd-id - - ps - - - name: pd-created - doc: A performance domain is created. - notify: get-pd-table - mcgrp: event - - - name: pd-updated - doc: A performance domain is updated. - notify: get-pd-table - mcgrp: event - - - name: pd-deleted - doc: A performance domain is deleted. - attribute-set: pd-table - event: - attributes: - - pd-id - mcgrp: event - -mcast-groups: - list: - - - name: event diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml index 8e7974ec453f..331f1b342b3a 100644 --- a/Documentation/netlink/specs/fou.yaml +++ b/Documentation/netlink/specs/fou.yaml @@ -39,6 +39,8 @@ attribute-sets: - name: ipproto type: u8 + checks: + min: 1 - name: type type: u8 diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 82bf5cb2617d..596c306ce52b 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -142,7 +142,7 @@ attribute-sets: name: ifindex doc: | ifindex of the netdev to which the pool belongs. - May be reported as 0 if the page pool was allocated for a netdev + May not be reported if the page pool was allocated for a netdev which got destroyed already (page pools may outlast their netdevs because they wait for all memory to be returned). type: u32 @@ -601,7 +601,9 @@ operations: name: page-pool-get doc: | Get / dump information about Page Pools. - (Only Page Pools associated with a net_device can be listed.) + Only Page Pools associated by the driver with a net_device + can be listed. ifindex will not be reported if the net_device + no longer exists. attribute-set: page-pool do: request: diff --git a/Documentation/process/conclave.rst b/Documentation/process/conclave.rst new file mode 100644 index 000000000000..6a1234f54612 --- /dev/null +++ b/Documentation/process/conclave.rst @@ -0,0 +1,41 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Linux kernel project continuity +=============================== + +The Linux kernel development project is widely distributed, with over +100 maintainers each working to keep changes moving through their own +repositories. The final step, though, is a centralized one where changes +are pulled into the mainline repository. That is normally done by Linus +Torvalds but, as was demonstrated by the 4.19 release in 2018, there are +others who can do that work when the need arises. + +Should the maintainers of that repository become unwilling or unable to +do that work going forward (including facilitating a transition), the +project will need to find one or more replacements without delay. The +process by which that will be done is listed below. $ORGANIZER is the +last Maintainer Summit organizer or the current Linux Foundation (LF) +Technical Advisory Board (TAB) Chair as a backup. + +- Within 72 hours, $ORGANIZER will open a discussion with the invitees + of the most recently concluded Maintainers Summit. A meeting of those + invitees and the TAB, either online or in-person, will be set as soon + as possible in a way that maximizes the number of people who can + participate. + +- If there has been no Maintainers Summit in the last 15 months, the set of + invitees for this meeting will be determined by the TAB. + +- The invitees to this meeting may bring in other maintainers as needed. + +- This meeting, chaired by $ORGANIZER, will consider options for the + ongoing management of the top-level kernel repository consistent with + the expectation that it maximizes the long term health of the project + and its community. + +- Within two weeks, a representative of this group will communicate to the + broader community, using the ksummit@lists.linux.dev mailing list, what + the next steps will be. + +The Linux Foundation, as guided by the TAB, will take the steps +necessary to support and implement this plan. diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index aa12f2660194..492b808a6977 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -68,6 +68,7 @@ beyond). stable-kernel-rules management-style researcher-guidelines + conclave Dealing with bugs ----------------- diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 989192421cc9..6bce4507d5d3 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -363,6 +363,18 @@ just do it. As a result, a sequence of smaller series gets merged quicker and with better review coverage. Re-posting large series also increases the mailing list traffic. +Limit patches outstanding on mailing list +----------------------------------------- + +Avoid having more than 15 patches, across all series, outstanding for +review on the mailing list for a single tree. In other words, a maximum of +15 patches under review on net, and a maximum of 15 patches under review on +net-next. + +This limit is intended to focus developer effort on testing patches before +upstream review. Aiding the quality of upstream submissions, and easing the +load on reviewers. + .. _rcs: Local variable ordering ("reverse xmas tree", "RCS") diff --git a/Documentation/process/maintainer-soc.rst b/Documentation/process/maintainer-soc.rst index 3ba886f52a51..7d6bad989ad8 100644 --- a/Documentation/process/maintainer-soc.rst +++ b/Documentation/process/maintainer-soc.rst @@ -57,8 +57,10 @@ Submitting Patches for Given SoC All typical platform related patches should be sent via SoC submaintainers (platform-specific maintainers). This includes also changes to per-platform or -shared defconfigs (scripts/get_maintainer.pl might not provide correct -addresses in such case). +shared defconfigs. Note that scripts/get_maintainer.pl might not provide +correct addresses for the shared defconfig, so ignore its output and manually +create CC-list based on MAINTAINERS file or use something like +``scripts/get_maintainer.pl -f drivers/soc/FOO/``). Submitting Patches to the Main SoC Maintainers ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -114,9 +116,9 @@ coordinating how the changes get merged through different maintainer trees. Usually the branch that includes a driver change will also include the corresponding change to the devicetree binding description, to ensure they are in fact compatible. This means that the devicetree branch can end up causing -warnings in the "make dtbs_check" step. If a devicetree change depends on +warnings in the ``make dtbs_check`` step. If a devicetree change depends on missing additions to a header file in include/dt-bindings/, it will fail the -"make dtbs" step and not get merged. +``make dtbs`` step and not get merged. There are multiple ways to deal with this: diff --git a/Documentation/translations/zh_CN/core-api/cpu_hotplug.rst b/Documentation/translations/zh_CN/core-api/cpu_hotplug.rst index bc0d7ea6d834..3447fbf0e695 100644 --- a/Documentation/translations/zh_CN/core-api/cpu_hotplug.rst +++ b/Documentation/translations/zh_CN/core-api/cpu_hotplug.rst @@ -22,7 +22,7 @@ Srivatsa Vaddagiri <vatsa@in.ibm.com>, Ashok Raj <ashok.raj@intel.com>, Joel Schopp <jschopp@austin.ibm.com>, - Thomas Gleixner <tglx@linutronix.de> + Thomas Gleixner <tglx@kernel.org> 简介 ==== diff --git a/Documentation/translations/zh_CN/core-api/genericirq.rst b/Documentation/translations/zh_CN/core-api/genericirq.rst index 05ccb954c18d..d2c1bd94bb97 100644 --- a/Documentation/translations/zh_CN/core-api/genericirq.rst +++ b/Documentation/translations/zh_CN/core-api/genericirq.rst @@ -404,6 +404,6 @@ kernel/irq/chip.c 感谢以下人士对本文档作出的贡献： -1. Thomas Gleixner tglx@linutronix.de +1. Thomas Gleixner tglx@kernel.org 2. Ingo Molnar mingo@elte.hu diff --git a/Documentation/userspace-api/media/v4l/metafmt-arm-mali-c55.rst b/Documentation/userspace-api/media/v4l/metafmt-arm-mali-c55.rst index 696e0a645a7e..f8029bcb5282 100644 --- a/Documentation/userspace-api/media/v4l/metafmt-arm-mali-c55.rst +++ b/Documentation/userspace-api/media/v4l/metafmt-arm-mali-c55.rst @@ -44,7 +44,7 @@ member and userspace must populate the type member with a value from struct v4l2_isp_params_buffer *params = (struct v4l2_isp_params_buffer *)buffer; - params->version = MALI_C55_PARAM_BUFFER_V1; + params->version = V4L2_ISP_PARAMS_VERSION_V1; params->data_size = 0; void *data = (void *)params->data; diff --git a/MAINTAINERS b/MAINTAINERS index 12f49de7fe03..0efa8cc6775b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -314,6 +314,7 @@ R: Mauro Carvalho Chehab <mchehab@kernel.org> R: Shuai Xue <xueshuai@linux.alibaba.com> L: linux-acpi@vger.kernel.org F: drivers/acpi/apei/ +F: drivers/firmware/efi/cper* ACPI COMPONENT ARCHITECTURE (ACPICA) M: "Rafael J. Wysocki" <rafael@kernel.org> @@ -1283,6 +1284,7 @@ F: include/uapi/drm/amdxdna_accel.h AMD XGBE DRIVER M: "Shyam Sundar S K" <Shyam-sundar.S-k@amd.com> +M: Raju Rangoju <Raju.Rangoju@amd.com> L: netdev@vger.kernel.org S: Maintained F: arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi @@ -2011,7 +2013,7 @@ ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) M: Arnd Bergmann <arnd@arndb.de> M: Krzysztof Kozlowski <krzk@kernel.org> M: Alexandre Belloni <alexandre.belloni@bootlin.com> -M: Linus Walleij <linus.walleij@linaro.org> +M: Linus Walleij <linusw@kernel.org> R: Drew Fustini <fustini@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: soc@lists.linux.dev @@ -2158,7 +2160,7 @@ M: Alice Ryhl <aliceryhl@google.com> L: dri-devel@lists.freedesktop.org S: Supported W: https://rust-for-linux.com/tyr-gpu-driver -W https://drm.pages.freedesktop.org/maintainer-tools/drm-rust.html +W: https://drm.pages.freedesktop.org/maintainer-tools/drm-rust.html B: https://gitlab.freedesktop.org/panfrost/linux/-/issues T: git https://gitlab.freedesktop.org/drm/rust/kernel.git F: Documentation/devicetree/bindings/gpu/arm,mali-valhall-csf.yaml @@ -3130,6 +3132,7 @@ F: drivers/*/*ma35* K: ma35d1 ARM/NUVOTON NPCM ARCHITECTURE +M: Andrew Jeffery <andrew@codeconstruct.com.au> M: Avi Fishman <avifishman70@gmail.com> M: Tomer Maimon <tmaimon77@gmail.com> M: Tali Perry <tali.perry1@gmail.com> @@ -3138,6 +3141,7 @@ R: Nancy Yuen <yuenn@google.com> R: Benjamin Fair <benjaminfair@google.com> L: openbmc@lists.ozlabs.org (moderated for non-subscribers) S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/bmc/linux.git F: Documentation/devicetree/bindings/*/*/*npcm* F: Documentation/devicetree/bindings/*/*npcm* F: Documentation/devicetree/bindings/rtc/nuvoton,nct3018y.yaml @@ -5801,7 +5805,8 @@ F: drivers/power/supply/cw2015_battery.c CEPH COMMON CODE (LIBCEPH) M: Ilya Dryomov <idryomov@gmail.com> -M: Xiubo Li <xiubli@redhat.com> +M: Alex Markuze <amarkuze@redhat.com> +M: Viacheslav Dubeyko <slava@dubeyko.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ @@ -5812,8 +5817,9 @@ F: include/linux/crush/ F: net/ceph/ CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH) -M: Xiubo Li <xiubli@redhat.com> M: Ilya Dryomov <idryomov@gmail.com> +M: Alex Markuze <amarkuze@redhat.com> +M: Viacheslav Dubeyko <slava@dubeyko.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ @@ -6172,7 +6178,7 @@ F: include/linux/clk.h CLOCKSOURCE, CLOCKEVENT DRIVERS M: Daniel Lezcano <daniel.lezcano@linaro.org> -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> L: linux-kernel@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core @@ -6417,6 +6423,7 @@ F: include/linux/blk-cgroup.h CONTROL GROUP - CPUSET M: Waiman Long <longman@redhat.com> +R: Chen Ridong <chenridong@huaweicloud.com> L: cgroups@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git @@ -6532,13 +6539,13 @@ F: rust/kernel/cpufreq.rs F: tools/testing/selftests/cpufreq/ CPU FREQUENCY DRIVERS - VIRTUAL MACHINE CPUFREQ -M: Saravana Kannan <saravanak@google.com> +M: Saravana Kannan <saravanak@kernel.org> L: linux-pm@vger.kernel.org S: Maintained F: drivers/cpufreq/virtual-cpufreq.c CPU HOTPLUG -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> M: Peter Zijlstra <peterz@infradead.org> L: linux-kernel@vger.kernel.org S: Maintained @@ -6705,6 +6712,7 @@ S: Maintained T: git https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git libcrypto-next T: git https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git libcrypto-fixes F: lib/crypto/ +F: scripts/crypto/ CRYPTO SPEED TEST COMPARE M: Wang Jinchao <wangjinchao@xfusion.com> @@ -6965,7 +6973,7 @@ F: Documentation/scsi/dc395x.rst F: drivers/scsi/dc395x.* DEBUGOBJECTS: -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/debugobjects @@ -7170,7 +7178,7 @@ F: drivers/base/devcoredump.c F: include/linux/devcoredump.h DEVICE DEPENDENCY HELPER SCRIPT -M: Saravana Kannan <saravanak@google.com> +M: Saravana Kannan <saravanak@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: scripts/dev-needs.sh @@ -8067,7 +8075,7 @@ W: https://rust-for-linux.com/nova-gpu-driver Q: https://patchwork.freedesktop.org/project/nouveau/ B: https://gitlab.freedesktop.org/drm/nova/-/issues C: irc://irc.oftc.net/nouveau -T: git https://gitlab.freedesktop.org/drm/nova.git nova-next +T: git https://gitlab.freedesktop.org/drm/rust/kernel.git drm-rust-next F: Documentation/gpu/nova/ F: drivers/gpu/nova-core/ @@ -8079,7 +8087,7 @@ W: https://rust-for-linux.com/nova-gpu-driver Q: https://patchwork.freedesktop.org/project/nouveau/ B: https://gitlab.freedesktop.org/drm/nova/-/issues C: irc://irc.oftc.net/nouveau -T: git https://gitlab.freedesktop.org/drm/nova.git nova-next +T: git https://gitlab.freedesktop.org/drm/rust/kernel.git drm-rust-next F: Documentation/gpu/nova/ F: drivers/gpu/drm/nova/ F: include/uapi/drm/nova_drm.h @@ -8357,6 +8365,7 @@ X: drivers/gpu/drm/msm/ X: drivers/gpu/drm/nova/ X: drivers/gpu/drm/radeon/ X: drivers/gpu/drm/tegra/ +X: drivers/gpu/drm/tyr/ X: drivers/gpu/drm/xe/ DRM DRIVERS AND COMMON INFRASTRUCTURE [RUST] @@ -9251,7 +9260,6 @@ F: drivers/scsi/be2iscsi/ EMULEX 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER (be2net) M: Ajit Khaparde <ajit.khaparde@broadcom.com> M: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com> -M: Somnath Kotur <somnath.kotur@broadcom.com> L: netdev@vger.kernel.org S: Maintained W: http://www.emulex.com @@ -9298,12 +9306,12 @@ M: Lukasz Luba <lukasz.luba@arm.com> M: "Rafael J. Wysocki" <rafael@kernel.org> L: linux-pm@vger.kernel.org S: Maintained -F: kernel/power/energy_model.c -F: include/linux/energy_model.h +F: Documentation/netlink/specs/dev-energymodel.yaml F: Documentation/power/energy-model.rst -F: Documentation/netlink/specs/em.yaml -F: include/uapi/linux/energy_model.h +F: include/linux/energy_model.h +F: include/uapi/linux/dev_energymodel.h F: kernel/power/em_netlink*.* +F: kernel/power/energy_model.c EPAPR HYPERVISOR BYTE CHANNEL DEVICE DRIVER M: Laurentiu Tudor <laurentiu.tudor@nxp.com> @@ -9511,6 +9519,7 @@ F: arch/arm/boot/compressed/efi-header.S F: arch/x86/platform/efi/ F: drivers/firmware/efi/ F: include/linux/efi*.h +X: drivers/firmware/efi/cper* EXTERNAL CONNECTOR SUBSYSTEM (EXTCON) M: MyungJoo Ham <myungjoo.ham@samsung.com> @@ -10367,7 +10376,7 @@ F: include/uapi/linux/fuse.h F: tools/testing/selftests/filesystems/fuse/ FUTEX SUBSYSTEM -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> M: Ingo Molnar <mingo@redhat.com> R: Peter Zijlstra <peterz@infradead.org> R: Darren Hart <dvhart@infradead.org> @@ -10511,7 +10520,7 @@ F: drivers/base/arch_topology.c F: include/linux/arch_topology.h GENERIC ENTRY CODE -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> M: Peter Zijlstra <peterz@infradead.org> M: Andy Lutomirski <luto@kernel.org> L: linux-kernel@vger.kernel.org @@ -10624,7 +10633,7 @@ F: drivers/uio/uio_pci_generic.c GENERIC VDSO LIBRARY M: Andy Lutomirski <luto@kernel.org> -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> M: Vincenzo Frascino <vincenzo.frascino@arm.com> L: linux-kernel@vger.kernel.org S: Maintained @@ -11237,7 +11246,7 @@ F: drivers/hid/hid-logitech-hidpp.c HIGH-RESOLUTION TIMERS, TIMER WHEEL, CLOCKEVENTS M: Anna-Maria Behnsen <anna-maria@linutronix.de> M: Frederic Weisbecker <frederic@kernel.org> -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core @@ -11260,7 +11269,7 @@ R: Boqun Feng <boqun.feng@gmail.com> R: FUJITA Tomonori <fujita.tomonori@gmail.com> R: Frederic Weisbecker <frederic@kernel.org> R: Lyude Paul <lyude@redhat.com> -R: Thomas Gleixner <tglx@linutronix.de> +R: Thomas Gleixner <tglx@kernel.org> R: Anna-Maria Behnsen <anna-maria@linutronix.de> R: John Stultz <jstultz@google.com> R: Stephen Boyd <sboyd@kernel.org> @@ -13162,6 +13171,7 @@ F: Documentation/devicetree/bindings/interconnect/ F: Documentation/driver-api/interconnect.rst F: drivers/interconnect/ F: include/dt-bindings/interconnect/ +F: include/linux/interconnect-clk.h F: include/linux/interconnect-provider.h F: include/linux/interconnect.h @@ -13330,7 +13340,7 @@ F: Documentation/devicetree/bindings/sound/irondevice,* F: sound/soc/codecs/sma* IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY) -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core F: Documentation/core-api/irq/irq-domain.rst @@ -13340,7 +13350,7 @@ F: kernel/irq/irqdomain.c F: kernel/irq/msi.c IRQ SUBSYSTEM -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core @@ -13353,7 +13363,7 @@ F: kernel/irq/ F: lib/group_cpus.c IRQCHIP DRIVERS -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core @@ -13959,6 +13969,7 @@ S: Maintained F: Documentation/admin-guide/mm/kho.rst F: Documentation/core-api/kho/* F: include/linux/kexec_handover.h +F: include/linux/kho/ F: kernel/liveupdate/kexec_handover* F: lib/test_kho.c F: tools/testing/selftests/kho/ @@ -14446,7 +14457,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-nonmm-unstab F: lib/* LICENSES and SPDX stuff -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> L: linux-spdx@vger.kernel.org S: Maintained @@ -14637,6 +14648,7 @@ S: Maintained F: Documentation/core-api/liveupdate.rst F: Documentation/mm/memfd_preservation.rst F: Documentation/userspace-api/liveupdate.rst +F: include/linux/kho/abi/ F: include/linux/liveupdate.h F: include/linux/liveupdate/ F: include/uapi/linux/liveupdate.h @@ -14873,6 +14885,7 @@ LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI) M: Sathya Prakash <sathya.prakash@broadcom.com> M: Sreekanth Reddy <sreekanth.reddy@broadcom.com> M: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com> +M: Ranjan Kumar <ranjan.kumar@broadcom.com> L: MPT-FusionLinux.pdl@broadcom.com L: linux-scsi@vger.kernel.org S: Supported @@ -16426,6 +16439,7 @@ MEMORY HOT(UN)PLUG M: David Hildenbrand <david@kernel.org> M: Oscar Salvador <osalvador@suse.de> L: linux-mm@kvack.org +L: linux-cxl@vger.kernel.org S: Maintained F: Documentation/admin-guide/mm/memory-hotplug.rst F: Documentation/core-api/memory-hotplug.rst @@ -16751,6 +16765,7 @@ F: tools/testing/selftests/mm/transhuge-stress.c MEMORY MANAGEMENT - USERFAULTFD M: Andrew Morton <akpm@linux-foundation.org> +M: Mike Rapoport <rppt@kernel.org> R: Peter Xu <peterx@redhat.com> L: linux-mm@kvack.org S: Maintained @@ -18279,7 +18294,7 @@ X: net/wireless/ X: tools/testing/selftests/net/can/ NETWORKING [IOAM] -M: Justin Iurman <justin.iurman@uliege.be> +M: Justin Iurman <justin.iurman@gmail.com> S: Maintained F: Documentation/networking/ioam6* F: include/linux/ioam6* @@ -18414,9 +18429,11 @@ M: Jakub Kicinski <kuba@kernel.org> M: Sabrina Dubroca <sd@queasysnail.net> L: netdev@vger.kernel.org S: Maintained +F: Documentation/networking/tls* F: include/net/tls.h F: include/uapi/linux/tls.h -F: net/tls/* +F: net/tls/ +F: tools/testing/selftests/net/tls.c NETWORKING [SOCKETS] M: Eric Dumazet <edumazet@google.com> @@ -18469,9 +18486,8 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM -M: Krzysztof Kozlowski <krzk@kernel.org> L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/net/nfc/ @@ -18568,7 +18584,7 @@ NOHZ, DYNTICKS SUPPORT M: Anna-Maria Behnsen <anna-maria@linutronix.de> M: Frederic Weisbecker <frederic@kernel.org> M: Ingo Molnar <mingo@kernel.org> -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/nohz @@ -19543,7 +19559,7 @@ F: include/linux/oa_tc6.h OPEN FIRMWARE AND FLATTENED DEVICE TREE M: Rob Herring <robh@kernel.org> -M: Saravana Kannan <saravanak@google.com> +M: Saravana Kannan <saravanak@kernel.org> L: devicetree@vger.kernel.org S: Maintained Q: http://patchwork.kernel.org/project/devicetree/list/ @@ -20753,7 +20769,7 @@ F: drivers/platform/x86/portwell-ec.c POSIX CLOCKS and TIMERS M: Anna-Maria Behnsen <anna-maria@linutronix.de> M: Frederic Weisbecker <frederic@kernel.org> -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core @@ -21088,6 +21104,10 @@ S: Maintained F: rust/helpers/pwm.c F: rust/kernel/pwm.rs +PWM SUBSYSTEM DRIVERS [RUST] +R: Michal Wilczynski <m.wilczynski@samsung.com> +F: drivers/pwm/*.rs + PXA GPIO DRIVER M: Robert Jarzmik <robert.jarzmik@free.fr> L: linux-gpio@vger.kernel.org @@ -21345,7 +21365,7 @@ F: Documentation/devicetree/bindings/net/qcom,bam-dmux.yaml F: drivers/net/wwan/qcom_bam_dmux.c QUALCOMM BLUETOOTH DRIVER -M: Bartosz Golaszewski <brgl@bgdev.pl> +M: Bartosz Golaszewski <brgl@kernel.org> L: linux-arm-msm@vger.kernel.org S: Maintained F: drivers/bluetooth/btqca.[ch] @@ -22517,7 +22537,7 @@ F: drivers/mailbox/riscv-sbi-mpxy-mbox.c F: include/linux/mailbox/riscv-rpmi-message.h RISC-V SPACEMIT SoC Support -M: Yixun Lan <dlan@gentoo.org> +M: Yixun Lan <dlan@kernel.org> L: linux-riscv@lists.infradead.org L: spacemit@lists.linux.dev S: Maintained @@ -24571,7 +24591,7 @@ F: drivers/tty/vcc.c F: include/linux/sunserialcore.h SPARSE CHECKER -M: "Luc Van Oostenryck" <luc.vanoostenryck@gmail.com> +M: Chris Li <sparse@chrisli.org> L: linux-sparse@vger.kernel.org S: Maintained W: https://sparse.docs.kernel.org/ @@ -26264,7 +26284,7 @@ F: drivers/net/wireless/ti/ TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER M: John Stultz <jstultz@google.com> -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> R: Stephen Boyd <sboyd@kernel.org> L: linux-kernel@vger.kernel.org S: Supported @@ -28195,7 +28215,7 @@ F: net/lapb/ F: net/x25/ X86 ARCHITECTURE (32-BIT AND 64-BIT) -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> M: Ingo Molnar <mingo@redhat.com> M: Borislav Petkov <bp@alien8.de> M: Dave Hansen <dave.hansen@linux.intel.com> @@ -28211,7 +28231,7 @@ F: tools/testing/selftests/x86 X86 CPUID DATABASE M: Borislav Petkov <bp@alien8.de> -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> M: x86@kernel.org R: Ahmed S. Darwish <darwi@linutronix.de> L: x86-cpuid@lists.linux.dev @@ -28227,7 +28247,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/asm F: arch/x86/entry/ X86 HARDWARE VULNERABILITIES -M: Thomas Gleixner <tglx@linutronix.de> +M: Thomas Gleixner <tglx@kernel.org> M: Borislav Petkov <bp@alien8.de> M: Peter Zijlstra <peterz@infradead.org> M: Josh Poimboeuf <jpoimboe@kernel.org> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc7 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr-ac.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr-ac.dts index 413b9255f9e3..19a8d7b07758 100644 --- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr-ac.dts +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr-ac.dts @@ -12,6 +12,17 @@ model = "Actiontec MI424WR rev A/C"; compatible = "actiontec,mi424wr-ac", "intel,ixp42x"; + /* Connect the switch to EthC */ + spi { + ethernet-switch@0 { + ethernet-ports { + ethernet-port@4 { + ethernet = <ðc>; + }; + }; + }; + }; + soc { /* EthB used for WAN */ ethernet@c8009000 { diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr-d.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr-d.dts index 3619c6411a5c..244c6ea0973f 100644 --- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr-d.dts +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr-d.dts @@ -12,6 +12,17 @@ model = "Actiontec MI424WR rev D"; compatible = "actiontec,mi424wr-d", "intel,ixp42x"; + /* Connect the switch to EthB */ + spi { + ethernet-switch@0 { + ethernet-ports { + ethernet-port@4 { + ethernet = <ðb>; + }; + }; + }; + }; + soc { /* EthB used for LAN */ ethernet@c8009000 { diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr.dtsi b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr.dtsi index 76fd97c5beb6..9b54e3c01a34 100644 --- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr.dtsi +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-actiontec-mi424wr.dtsi @@ -152,7 +152,6 @@ }; ethernet-port@4 { reg = <4>; - ethernet = <ðc>; phy-mode = "mii"; fixed-link { speed = <100>; diff --git a/arch/arm/boot/dts/microchip/lan966x-pcb8290.dts b/arch/arm/boot/dts/microchip/lan966x-pcb8290.dts index 3b7577e48b46..50bd29572f3e 100644 --- a/arch/arm/boot/dts/microchip/lan966x-pcb8290.dts +++ b/arch/arm/boot/dts/microchip/lan966x-pcb8290.dts @@ -54,6 +54,7 @@ &mdio0 { pinctrl-0 = <&miim_a_pins>; pinctrl-names = "default"; + reset-gpios = <&gpio 53 GPIO_ACTIVE_LOW>; status = "okay"; ext_phy0: ethernet-phy@7 { diff --git a/arch/arm/boot/dts/microchip/sama7d65.dtsi b/arch/arm/boot/dts/microchip/sama7d65.dtsi index cd2cf9a6f40b..868045c650a7 100644 --- a/arch/arm/boot/dts/microchip/sama7d65.dtsi +++ b/arch/arm/boot/dts/microchip/sama7d65.dtsi @@ -527,7 +527,7 @@ interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; clocks = <&pmc PMC_TYPE_PERIPHERAL 37>; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; dmas = <&dma0 AT91_XDMAC_DT_PERID(12)>, <&dma0 AT91_XDMAC_DT_PERID(11)>; dma-names = "tx", "rx"; @@ -676,7 +676,7 @@ flx9: flexcom@e2820000 { compatible = "microchip,sama7d65-flexcom", "atmel,sama5d2-flexcom"; reg = <0xe2820000 0x200>; - ranges = <0x0 0xe281c000 0x800>; + ranges = <0x0 0xe2820000 0x800>; clocks = <&pmc PMC_TYPE_PERIPHERAL 43>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts index b8048e12e3d9..5398e9067e60 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts +++ b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts @@ -248,14 +248,14 @@ linux,default-trigger = "nand-disk"; }; - ledg3: led@10 { - reg = <10>; + ledg3: led@a { + reg = <0xa>; label = "system:green3:live"; linux,default-trigger = "heartbeat"; }; - ledb3: led@11 { - reg = <11>; + ledb3: led@b { + reg = <0xb>; label = "system:blue3:cpu"; linux,default-trigger = "cpu0"; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts b/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts index 43ff5eafb2bb..91c63d1f2604 100644 --- a/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts +++ b/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts @@ -398,13 +398,13 @@ #size-cells = <0>; led-control = <0x0 0x0 0x3f83f8 0x0>; - sysled0@3 { + led@3 { reg = <3>; label = "system:green:status"; linux,default-trigger = "default-on"; }; - sysled1@4 { + led@4 { reg = <4>; label = "system:green:act"; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/nxp/imx/imx51-zii-scu2-mezz.dts b/arch/arm/boot/dts/nxp/imx/imx51-zii-scu2-mezz.dts index 26eb7a9506e4..1598bf4f4991 100644 --- a/arch/arm/boot/dts/nxp/imx/imx51-zii-scu2-mezz.dts +++ b/arch/arm/boot/dts/nxp/imx/imx51-zii-scu2-mezz.dts @@ -225,13 +225,13 @@ #size-cells = <0>; led-control = <0x0 0x0 0x3f83f8 0x0>; - sysled3: led3@3 { + sysled3: led@3 { reg = <3>; label = "system:red:power"; linux,default-trigger = "default-on"; }; - sysled4: led4@4 { + sysled4: led@4 { reg = <4>; label = "system:green:act"; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/nxp/imx/imx51-zii-scu3-esb.dts b/arch/arm/boot/dts/nxp/imx/imx51-zii-scu3-esb.dts index 19a3b142c964..c2dcfd44c445 100644 --- a/arch/arm/boot/dts/nxp/imx/imx51-zii-scu3-esb.dts +++ b/arch/arm/boot/dts/nxp/imx/imx51-zii-scu3-esb.dts @@ -153,13 +153,13 @@ #size-cells = <0>; led-control = <0x0 0x0 0x3f83f8 0x0>; - sysled3: led3@3 { + sysled3: led@3 { reg = <3>; label = "system:red:power"; linux,default-trigger = "default-on"; }; - sysled4: led4@4 { + sysled4: led@4 { reg = <4>; label = "system:green:act"; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-ba16.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-ba16.dtsi index 53013b12c2ec..02d66523668d 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-ba16.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6q-ba16.dtsi @@ -337,7 +337,7 @@ pinctrl-0 = <&pinctrl_rtc>; reg = <0x32>; interrupt-parent = <&gpio4>; - interrupts = <10 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; }; }; diff --git a/arch/arm/mach-npcm/Kconfig b/arch/arm/mach-npcm/Kconfig index 63b42a19d1b8..d933e8abb50f 100644 --- a/arch/arm/mach-npcm/Kconfig +++ b/arch/arm/mach-npcm/Kconfig @@ -30,7 +30,6 @@ config ARCH_NPCM7XX select ARM_ERRATA_764369 if SMP select ARM_ERRATA_720789 select ARM_ERRATA_754322 - select ARM_ERRATA_794072 select PL310_ERRATA_588369 select PL310_ERRATA_727915 select MFD_SYSCON diff --git a/arch/arm64/boot/dts/broadcom/Makefile b/arch/arm64/boot/dts/broadcom/Makefile index 83d45afc6588..01ecfa304184 100644 --- a/arch/arm64/boot/dts/broadcom/Makefile +++ b/arch/arm64/boot/dts/broadcom/Makefile @@ -7,15 +7,13 @@ dtb-$(CONFIG_ARCH_BCM2835) += bcm2711-rpi-400.dtb \ bcm2711-rpi-4-b.dtb \ bcm2711-rpi-cm4-io.dtb \ bcm2712-rpi-5-b.dtb \ - bcm2712-rpi-5-b-ovl-rp1.dtb \ bcm2712-d-rpi-5-b.dtb \ bcm2837-rpi-2-b.dtb \ bcm2837-rpi-3-a-plus.dtb \ bcm2837-rpi-3-b.dtb \ bcm2837-rpi-3-b-plus.dtb \ bcm2837-rpi-cm3-io3.dtb \ - bcm2837-rpi-zero-2-w.dtb \ - rp1.dtbo + bcm2837-rpi-zero-2-w.dtb subdir-y += bcmbca subdir-y += northstar2 diff --git a/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b-ovl-rp1.dts b/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b-base.dtsi index 04738bf281eb..04738bf281eb 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b-ovl-rp1.dts +++ b/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b-base.dtsi diff --git a/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts b/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts index 3e0319fdb93f..285608281446 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts +++ b/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts @@ -1,22 +1,16 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* - * bcm2712-rpi-5-b-ovl-rp1.dts is the overlay-ready DT which will make - * the RP1 driver to load the RP1 dtb overlay at runtime, while - * bcm2712-rpi-5-b.dts (this file) is the fully defined one (i.e. it - * already contains RP1 node, so no overlay is loaded nor needed). - * This file is intended to host the override nodes for the RP1 peripherals, - * e.g. to declare the phy of the ethernet interface or the custom pin setup - * for several RP1 peripherals. - * This in turn is due to the fact that there's no current generic - * infrastructure to reference nodes (i.e. the nodes in rp1-common.dtsi) that - * are not yet defined in the DT since they are loaded at runtime via overlay. + * As a loose attempt to separate RP1 customizations from SoC peripherals + * definitioni, this file is intended to host the override nodes for the RP1 + * peripherals, e.g. to declare the phy of the ethernet interface or custom + * pin setup. * All other nodes that do not have anything to do with RP1 should be added - * to the included bcm2712-rpi-5-b-ovl-rp1.dts instead. + * to the included bcm2712-rpi-5-b-base.dtsi instead. */ /dts-v1/; -#include "bcm2712-rpi-5-b-ovl-rp1.dts" +#include "bcm2712-rpi-5-b-base.dtsi" / { aliases { @@ -25,7 +19,26 @@ }; &pcie2 { - #include "rp1-nexus.dtsi" + pci@0,0 { + reg = <0x0 0x0 0x0 0x0 0x0>; + ranges; + bus-range = <0 1>; + device_type = "pci"; + #address-cells = <3>; + #size-cells = <2>; + + dev@0,0 { + compatible = "pci1de4,1"; + reg = <0x10000 0x0 0x0 0x0 0x0>; + ranges = <0x1 0x0 0x0 0x82010000 0x0 0x0 0x0 0x400000>; + interrupt-controller; + #interrupt-cells = <2>; + #address-cells = <3>; + #size-cells = <2>; + + #include "rp1-common.dtsi" + }; + }; }; &rp1_eth { diff --git a/arch/arm64/boot/dts/broadcom/rp1-nexus.dtsi b/arch/arm64/boot/dts/broadcom/rp1-nexus.dtsi deleted file mode 100644 index 0ef30d7f1c35..000000000000 --- a/arch/arm64/boot/dts/broadcom/rp1-nexus.dtsi +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) - -rp1_nexus { - compatible = "pci1de4,1"; - #address-cells = <3>; - #size-cells = <2>; - ranges = <0x01 0x00 0x00000000 - 0x02000000 0x00 0x00000000 - 0x0 0x400000>; - interrupt-controller; - #interrupt-cells = <2>; - - #include "rp1-common.dtsi" -}; diff --git a/arch/arm64/boot/dts/broadcom/rp1.dtso b/arch/arm64/boot/dts/broadcom/rp1.dtso deleted file mode 100644 index ab4f146d22c0..000000000000 --- a/arch/arm64/boot/dts/broadcom/rp1.dtso +++ /dev/null @@ -1,11 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) - -/dts-v1/; -/plugin/; - -&pcie2 { - #address-cells = <3>; - #size-cells = <2>; - - #include "rp1-nexus.dtsi" -}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 68c2e0156a5c..f8303b7e2bd2 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -113,6 +113,7 @@ ethphy0f: ethernet-phy@1 { /* SMSC LAN8740Ai */ compatible = "ethernet-phy-id0007.c110", "ethernet-phy-ieee802.3-c22"; + clocks = <&clk IMX8MP_CLK_ENET_QOS>; interrupt-parent = <&gpio3>; interrupts = <19 IRQ_TYPE_LEVEL_LOW>; pinctrl-0 = <&pinctrl_ethphy0>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81-moduline-display-106.dts b/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81-moduline-display-106.dts index 88ad422c2760..399230144ce3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81-moduline-display-106.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81-moduline-display-106.dts @@ -9,7 +9,7 @@ #include "imx8mp-tx8p-ml81.dtsi" / { - compatible = "gocontroll,moduline-display", "fsl,imx8mp"; + compatible = "gocontroll,moduline-display-106", "karo,tx8p-ml81", "fsl,imx8mp"; chassis-type = "embedded"; hardware = "Moduline Display V1.06"; model = "GOcontroll Moduline Display baseboard"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81.dtsi index fe8ba16eb40e..761ee046eb72 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81.dtsi @@ -47,6 +47,7 @@ <&clk IMX8MP_SYS_PLL2_100M>, <&clk IMX8MP_SYS_PLL2_50M>; assigned-clock-rates = <266000000>, <100000000>, <50000000>; + nvmem-cells = <ð_mac1>; phy-handle = <ðphy0>; phy-mode = "rmii"; pinctrl-0 = <&pinctrl_eqos>; @@ -75,6 +76,10 @@ }; }; +&fec { + nvmem-cells = <ð_mac2>; +}; + &gpio1 { gpio-line-names = "SODIMM_152", "SODIMM_42", diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts index 779d9f78fb81..f1b0563d3a09 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts @@ -263,6 +263,7 @@ regulator-max-microvolt = <3000000>; gpio = <&lsio_gpio4 7 GPIO_ACTIVE_HIGH>; enable-active-high; + off-on-delay-us = <4800>; }; reg_audio: regulator-audio { @@ -576,7 +577,7 @@ compatible = "isil,isl29023"; reg = <0x44>; interrupt-parent = <&lsio_gpio4>; - interrupts = <11 IRQ_TYPE_EDGE_FALLING>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; }; pressure-sensor@60 { diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi index 5f24850bf322..974e193f8dcb 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi @@ -172,25 +172,25 @@ &lpuart0 { compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart"; - dmas = <&edma2 13 0 0>, <&edma2 12 0 1>; + dmas = <&edma2 12 0 FSL_EDMA_RX>, <&edma2 13 0 0>; dma-names = "rx","tx"; }; &lpuart1 { compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart"; - dmas = <&edma2 15 0 0>, <&edma2 14 0 1>; + dmas = <&edma2 14 0 FSL_EDMA_RX>, <&edma2 15 0 0>; dma-names = "rx","tx"; }; &lpuart2 { compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart"; - dmas = <&edma2 17 0 0>, <&edma2 16 0 1>; + dmas = <&edma2 16 0 FSL_EDMA_RX>, <&edma2 17 0 0>; dma-names = "rx","tx"; }; &lpuart3 { compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart"; - dmas = <&edma2 19 0 0>, <&edma2 18 0 1>; + dmas = <&edma2 18 0 FSL_EDMA_RX>, <&edma2 19 0 0>; dma-names = "rx","tx"; }; diff --git a/arch/arm64/boot/dts/freescale/imx95-toradex-smarc.dtsi b/arch/arm64/boot/dts/freescale/imx95-toradex-smarc.dtsi index afbdadcb3686..115a16e44a99 100644 --- a/arch/arm64/boot/dts/freescale/imx95-toradex-smarc.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95-toradex-smarc.dtsi @@ -406,8 +406,6 @@ "", "", "", - "", - "", "SMARC_SDIO_WP"; }; @@ -582,7 +580,7 @@ ethphy1: ethernet-phy@1 { reg = <1>; interrupt-parent = <&som_gpio_expander_1>; - interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + interrupts = <6 IRQ_TYPE_EDGE_FALLING>; ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>; ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>; }; diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index e45014d50abe..a4d854817559 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -828,7 +828,7 @@ interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>; #address-cells = <3>; #size-cells = <0>; - clocks = <&scmi_clk IMX95_CLK_BUSAON>, + clocks = <&scmi_clk IMX95_CLK_BUSWAKEUP>, <&scmi_clk IMX95_CLK_I3C2SLOW>; clock-names = "pclk", "fast_clk"; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/mba8mx.dtsi b/arch/arm64/boot/dts/freescale/mba8mx.dtsi index 225cd2f1220b..10d5c211b1c9 100644 --- a/arch/arm64/boot/dts/freescale/mba8mx.dtsi +++ b/arch/arm64/boot/dts/freescale/mba8mx.dtsi @@ -192,7 +192,7 @@ reset-assert-us = <500000>; reset-deassert-us = <500>; interrupt-parent = <&expander2>; - interrupts = <6 IRQ_TYPE_EDGE_FALLING>; + interrupts = <6 IRQ_TYPE_LEVEL_LOW>; }; }; }; diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts index 3f13a960f34e..ed84ab92fb19 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts +++ b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts @@ -675,10 +675,7 @@ snps,lfps_filter_quirk; snps,dis_u2_susphy_quirk; snps,dis_u3_susphy_quirk; - snps,tx_de_emphasis_quirk; - snps,tx_de_emphasis = <1>; snps,dis_enblslpm_quirk; - snps,gctl-reset-quirk; usb-role-switch; role-switch-default-mode = "host"; port { diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 709da31d5785..137aa8375257 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -202,19 +202,6 @@ nvidia,outputs = <&dsia &dsib &sor0 &sor1>; nvidia,head = <0>; - - interconnects = <&mc TEGRA210_MC_DISPLAY0A &emc>, - <&mc TEGRA210_MC_DISPLAY0B &emc>, - <&mc TEGRA210_MC_DISPLAY0C &emc>, - <&mc TEGRA210_MC_DISPLAYHC &emc>, - <&mc TEGRA210_MC_DISPLAYD &emc>, - <&mc TEGRA210_MC_DISPLAYT &emc>; - interconnect-names = "wina", - "winb", - "winc", - "cursor", - "wind", - "wint"; }; dc@54240000 { @@ -230,15 +217,6 @@ nvidia,outputs = <&dsia &dsib &sor0 &sor1>; nvidia,head = <1>; - - interconnects = <&mc TEGRA210_MC_DISPLAY0AB &emc>, - <&mc TEGRA210_MC_DISPLAY0BB &emc>, - <&mc TEGRA210_MC_DISPLAY0CB &emc>, - <&mc TEGRA210_MC_DISPLAYHCB &emc>; - interconnect-names = "wina", - "winb", - "winc", - "cursor"; }; dsia: dsi@54300000 { @@ -1052,7 +1030,6 @@ #iommu-cells = <1>; #reset-cells = <1>; - #interconnect-cells = <1>; }; emc: external-memory-controller@7001b000 { @@ -1066,7 +1043,6 @@ nvidia,memory-controller = <&mc>; operating-points-v2 = <&emc_icc_dvfs_opp_table>; - #interconnect-cells = <0>; #cooling-cells = <2>; }; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index 5334adebf278..b9e0d9c7c065 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -5788,8 +5788,12 @@ clocks = <&rpmhcc RPMH_CXO_CLK>; clock-names = "xo"; - power-domains = <&rpmhpd SC8280XP_NSP>; - power-domain-names = "nsp"; + power-domains = <&rpmhpd SC8280XP_NSP>, + <&rpmhpd SC8280XP_CX>, + <&rpmhpd SC8280XP_MXC>; + power-domain-names = "nsp", + "cx", + "mxc"; memory-region = <&pil_nsp0_mem>; @@ -5919,8 +5923,12 @@ clocks = <&rpmhcc RPMH_CXO_CLK>; clock-names = "xo"; - power-domains = <&rpmhpd SC8280XP_NSP>; - power-domain-names = "nsp"; + power-domains = <&rpmhpd SC8280XP_NSP>, + <&rpmhpd SC8280XP_CX>, + <&rpmhpd SC8280XP_MXC>; + power-domain-names = "nsp", + "cx", + "mxc"; memory-region = <&pil_nsp1_mem>; diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-enchilada.dts b/arch/arm64/boot/dts/qcom/sdm845-oneplus-enchilada.dts index a259eb9d45ae..8aead6dc25e0 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-enchilada.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-enchilada.dts @@ -31,9 +31,9 @@ }; &display_panel { - status = "okay"; + compatible = "samsung,sofef00-ams628nw01", "samsung,sofef00"; - compatible = "samsung,sofef00"; + status = "okay"; }; &bq27441_fg { diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index 2ca9e50ef599..e3f93f4f412d 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -4133,8 +4133,6 @@ usb_1: usb@a600000 { compatible = "qcom,sm8550-dwc3", "qcom,snps-dwc3"; reg = <0x0 0x0a600000 0x0 0xfc100>; - #address-cells = <1>; - #size-cells = <0>; clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>, <&gcc GCC_USB30_PRIM_MASTER_CLK>, diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index 07ae74851621..f8e1950a74ac 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -5150,9 +5150,6 @@ dma-coherent; - #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; ports { diff --git a/arch/arm64/boot/dts/qcom/talos.dtsi b/arch/arm64/boot/dts/qcom/talos.dtsi index d1dbfa3bd81c..95d26e313622 100644 --- a/arch/arm64/boot/dts/qcom/talos.dtsi +++ b/arch/arm64/boot/dts/qcom/talos.dtsi @@ -1399,10 +1399,10 @@ <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>, <&gcc GCC_UFS_PHY_AHB_CLK>, <&gcc GCC_UFS_PHY_UNIPRO_CORE_CLK>, - <&gcc GCC_UFS_PHY_ICE_CORE_CLK>, <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>, - <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>; + <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>, + <&gcc GCC_UFS_PHY_ICE_CORE_CLK>; clock-names = "core_clk", "bus_aggr_clk", "iface_clk", diff --git a/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts b/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts index e5e6b800c2d1..3473db08b9b2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts @@ -199,7 +199,7 @@ compatible = "brcm,bcm43455-fmac", "brcm,bcm4329-fmac"; reg = <1>; interrupt-parent = <&gpio0>; - interrupts = <RK_PA3 GPIO_ACTIVE_HIGH>; + interrupts = <RK_PA3 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "host-wake"; pinctrl-names = "default"; pinctrl-0 = <&wifi_host_wake>; diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go3.dts b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go3.dts index 35bbaf559ca3..6b0563cb4d3a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go3.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go3.dts @@ -14,7 +14,8 @@ joystick_mux_controller: mux-controller { compatible = "gpio-mux"; - pinctrl = <&mux_en_pins>; + pinctrl-0 = <&mux_en_pins>; + pinctrl-names = "default"; #mux-control-cells = <0>; mux-gpios = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>, diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts index e7d4a2f9a95e..b2de018a7d36 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts @@ -424,9 +424,7 @@ &pcie0 { ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; - max-link-speed = <2>; num-lanes = <2>; - pinctrl-names = "default"; status = "okay"; vpcie12v-supply = <&vcc12v_dcin>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi index 8d94d9f91a5c..3a9a10f531bd 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi @@ -71,7 +71,6 @@ }; &pcie0 { - max-link-speed = <1>; num-lanes = <1>; vpcie3v3-supply = <&vcc3v3_sys>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index eaaca08a7601..810ab6ff4e67 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -969,7 +969,6 @@ }; &spi1 { - max-freq = <10000000>; status = "okay"; spiflash: flash@0 { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts index 2dca1dca20b8..5de964d369b0 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts @@ -40,13 +40,13 @@ button-up { label = "Volume Up"; linux,code = <KEY_VOLUMEUP>; - press-threshold-microvolt = <100000>; + press-threshold-microvolt = <2000>; }; button-down { label = "Volume Down"; linux,code = <KEY_VOLUMEDOWN>; - press-threshold-microvolt = <600000>; + press-threshold-microvolt = <300000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 587e89d7fc5e..8299e9d10c7c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -483,7 +483,7 @@ pinctrl-names = "default"; pinctrl-0 = <&q7_thermal_pin &bios_disable_override_hog_pin>; - gpios { + gpio-pins { bios_disable_override_hog_pin: bios-disable-override-hog-pin { rockchip,pins = <3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_down>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts index 74160cf89188..6d52e3723a4e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts @@ -529,11 +529,11 @@ rockchip,pins = <1 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>; }; - vsel1_gpio: vsel1-gpio { + vsel1_gpio: vsel1-gpio-pin { rockchip,pins = <1 RK_PC1 RK_FUNC_GPIO &pcfg_pull_down>; }; - vsel2_gpio: vsel2-gpio { + vsel2_gpio: vsel2-gpio-pin { rockchip,pins = <1 RK_PB6 RK_FUNC_GPIO &pcfg_pull_down>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5-display-vz.dtso b/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5-display-vz.dtso index 70c23e1bf14b..d1a906031912 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5-display-vz.dtso +++ b/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5-display-vz.dtso @@ -11,7 +11,6 @@ #include "rk3568-wolfvision-pf5-display.dtsi" &st7789 { - compatible = "jasonic,jt240mhqs-hwt-ek-e3", - "sitronix,st7789v"; + compatible = "jasonic,jt240mhqs-hwt-ek-e3"; rotation = <270>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts b/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts index cce34c541f7c..bb2cc2814b83 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts @@ -201,6 +201,7 @@ pinctrl-names = "default"; pinctrl-0 = <&hp_det_l>; + simple-audio-card,bitclock-master = <&masterdai>; simple-audio-card,format = "i2s"; simple-audio-card,hp-det-gpios = <&gpio2 RK_PD6 GPIO_ACTIVE_LOW>; simple-audio-card,mclk-fs = <256>; @@ -211,15 +212,16 @@ "Headphones", "HPOR", "IN1P", "Microphone Jack"; simple-audio-card,widgets = - "Headphone", "Headphone Jack", + "Headphone", "Headphones", "Microphone", "Microphone Jack"; simple-audio-card,codec { sound-dai = <&rt5616>; }; - simple-audio-card,cpu { + masterdai: simple-audio-card,cpu { sound-dai = <&sai2>; + system-clock-frequency = <12288000>; }; }; }; @@ -727,10 +729,12 @@ rt5616: audio-codec@1b { compatible = "realtek,rt5616"; reg = <0x1b>; - assigned-clocks = <&cru CLK_SAI2_MCLKOUT>; + assigned-clocks = <&cru CLK_SAI2_MCLKOUT_TO_IO>; assigned-clock-rates = <12288000>; - clocks = <&cru CLK_SAI2_MCLKOUT>; + clocks = <&cru CLK_SAI2_MCLKOUT_TO_IO>; clock-names = "mclk"; + pinctrl-0 = <&sai2m0_mclk>; + pinctrl-names = "default"; #sound-dai-cells = <0>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi index a86fc6b4e8c4..c72343e7a045 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi @@ -1261,7 +1261,7 @@ gpu: gpu@27800000 { compatible = "rockchip,rk3576-mali", "arm,mali-bifrost"; - reg = <0x0 0x27800000 0x0 0x200000>; + reg = <0x0 0x27800000 0x0 0x20000>; assigned-clocks = <&scmi_clk SCMI_CLK_GPU>; assigned-clock-rates = <198000000>; clocks = <&cru CLK_GPU>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi index 2a7921793020..7ab12d1054a7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi @@ -1200,7 +1200,7 @@ status = "disabled"; }; - rknn_mmu_1: iommu@fdac9000 { + rknn_mmu_1: iommu@fdaca000 { compatible = "rockchip,rk3588-iommu", "rockchip,rk3568-iommu"; reg = <0x0 0xfdaca000 0x0 0x100>; interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH 0>; @@ -1230,7 +1230,7 @@ status = "disabled"; }; - rknn_mmu_2: iommu@fdad9000 { + rknn_mmu_2: iommu@fdada000 { compatible = "rockchip,rk3588-iommu", "rockchip,rk3568-iommu"; reg = <0x0 0xfdada000 0x0 0x100>; interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH 0>; diff --git a/arch/arm64/boot/dts/ti/k3-am62-lp-sk-nand.dtso b/arch/arm64/boot/dts/ti/k3-am62-lp-sk-nand.dtso index 173ac60723b6..b4daa674eaa1 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-lp-sk-nand.dtso +++ b/arch/arm64/boot/dts/ti/k3-am62-lp-sk-nand.dtso @@ -14,7 +14,7 @@ }; &main_pmx0 { - gpmc0_pins_default: gpmc0-pins-default { + gpmc0_pins_default: gpmc0-default-pins { pinctrl-single,pins = < AM62X_IOPAD(0x003c, PIN_INPUT, 0) /* (K19) GPMC0_AD0 */ AM62X_IOPAD(0x0040, PIN_INPUT, 0) /* (L19) GPMC0_AD1 */ diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-peb-c-010.dtso b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-peb-c-010.dtso index 7fc73cfacadb..1176a52d560b 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-peb-c-010.dtso +++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-peb-c-010.dtso @@ -30,13 +30,10 @@ <&main_pktdma 0xc206 15>, /* egress slice 1 */ <&main_pktdma 0xc207 15>, /* egress slice 1 */ <&main_pktdma 0x4200 15>, /* ingress slice 0 */ - <&main_pktdma 0x4201 15>, /* ingress slice 1 */ - <&main_pktdma 0x4202 0>, /* mgmnt rsp slice 0 */ - <&main_pktdma 0x4203 0>; /* mgmnt rsp slice 1 */ + <&main_pktdma 0x4201 15>; /* ingress slice 1 */ dma-names = "tx0-0", "tx0-1", "tx0-2", "tx0-3", "tx1-0", "tx1-1", "tx1-2", "tx1-3", - "rx0", "rx1", - "rxmgm0", "rxmgm1"; + "rx0", "rx1"; firmware-name = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf", "ti-pruss/am65x-sr2-rtu0-prueth-fw.elf", diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso index 996c42ec4253..bea8efa3e909 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso +++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso @@ -20,13 +20,13 @@ }; &main_pmx0 { - main_gpio1_exp_header_gpio_pins_default: main-gpio1-exp-header-gpio-pins-default { + main_gpio1_exp_header_gpio_pins_default: main-gpio1-exp-header-gpio-default-pins { pinctrl-single,pins = < AM64X_IOPAD(0x0220, PIN_INPUT, 7) /* (D14) SPI1_CS1.GPIO1_48 */ >; }; - main_spi1_pins_default: main-spi1-pins-default { + main_spi1_pins_default: main-spi1-default-pins { pinctrl-single,pins = < AM64X_IOPAD(0x0224, PIN_INPUT, 0) /* (C14) SPI1_CLK */ AM64X_IOPAD(0x021C, PIN_OUTPUT, 0) /* (B14) SPI1_CS0 */ @@ -35,7 +35,7 @@ >; }; - main_uart3_pins_default: main-uart3-pins-default { + main_uart3_pins_default: main-uart3-default-pins { pinctrl-single,pins = < AM64X_IOPAD(0x0048, PIN_INPUT, 2) /* (U20) GPMC0_AD3.UART3_RXD */ AM64X_IOPAD(0x004c, PIN_OUTPUT, 2) /* (U18) GPMC0_AD4.UART3_TXD */ @@ -52,7 +52,7 @@ &main_spi1 { pinctrl-names = "default"; pinctrl-0 = <&main_spi1_pins_default>; - ti,pindir-d0-out-d1-in = <1>; + ti,pindir-d0-out-d1-in; status = "okay"; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 45288ec9eaf7..35e9eb180c9a 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -670,7 +670,6 @@ CONFIG_PINCTRL_LPASS_LPI=m CONFIG_PINCTRL_SC7280_LPASS_LPI=m CONFIG_PINCTRL_SM6115_LPASS_LPI=m CONFIG_PINCTRL_SM8250_LPASS_LPI=m -CONFIG_PINCTRL_SM8350_LPASS_LPI=m CONFIG_PINCTRL_SM8450_LPASS_LPI=m CONFIG_PINCTRL_SC8280XP_LPASS_LPI=m CONFIG_PINCTRL_SM8550_LPASS_LPI=m diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index aa91165ca140..e8a9783235cb 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -45,7 +45,7 @@ void arch_efi_call_virt_teardown(void); * switching to the EFI runtime stack. */ #define current_in_efi() \ - (!preemptible() && efi_rt_stack_top != NULL && \ + (efi_rt_stack_top != NULL && \ on_task_stack(current, READ_ONCE(efi_rt_stack_top[-1]), 1)) #define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index a1ad12c72ebf..ce516d8187b1 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -300,6 +300,8 @@ void kvm_get_kimage_voffset(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); void kvm_compute_final_ctr_el0(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); +void kvm_pan_patch_el2_entry(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst); void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr_virt, u64 elr_phys, u64 par, uintptr_t vcpu, u64 far, u64 hpfar); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index c9eab316398e..55d34192a8de 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -119,22 +119,6 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu->arch.hcr_el2; } -static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr_el2 &= ~HCR_TWE; - if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) || - vcpu->kvm->arch.vgic.nassgireq) - vcpu->arch.hcr_el2 &= ~HCR_TWI; - else - vcpu->arch.hcr_el2 |= HCR_TWI; -} - -static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr_el2 |= HCR_TWE; - vcpu->arch.hcr_el2 |= HCR_TWI; -} - static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu) { return vcpu->arch.vsesr_el2; diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index fc02de43c68d..c0ad262a8289 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -87,7 +87,15 @@ typedef u64 kvm_pte_t; #define KVM_PTE_LEAF_ATTR_HI_SW GENMASK(58, 55) -#define KVM_PTE_LEAF_ATTR_HI_S1_XN BIT(54) +#define __KVM_PTE_LEAF_ATTR_HI_S1_XN BIT(54) +#define __KVM_PTE_LEAF_ATTR_HI_S1_UXN BIT(54) +#define __KVM_PTE_LEAF_ATTR_HI_S1_PXN BIT(53) + +#define KVM_PTE_LEAF_ATTR_HI_S1_XN \ + ({ cpus_have_final_cap(ARM64_KVM_HVHE) ? \ + (__KVM_PTE_LEAF_ATTR_HI_S1_UXN | \ + __KVM_PTE_LEAF_ATTR_HI_S1_PXN) : \ + __KVM_PTE_LEAF_ATTR_HI_S1_XN; }) #define KVM_PTE_LEAF_ATTR_HI_S2_XN GENMASK(54, 53) @@ -293,8 +301,8 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end, * children. * @KVM_PGTABLE_WALK_SHARED: Indicates the page-tables may be shared * with other software walkers. - * @KVM_PGTABLE_WALK_HANDLE_FAULT: Indicates the page-table walk was - * invoked from a fault handler. + * @KVM_PGTABLE_WALK_IGNORE_EAGAIN: Don't terminate the walk early if + * the walker returns -EAGAIN. * @KVM_PGTABLE_WALK_SKIP_BBM_TLBI: Visit and update table entries * without Break-before-make's * TLB invalidation. @@ -307,7 +315,7 @@ enum kvm_pgtable_walk_flags { KVM_PGTABLE_WALK_TABLE_PRE = BIT(1), KVM_PGTABLE_WALK_TABLE_POST = BIT(2), KVM_PGTABLE_WALK_SHARED = BIT(3), - KVM_PGTABLE_WALK_HANDLE_FAULT = BIT(4), + KVM_PGTABLE_WALK_IGNORE_EAGAIN = BIT(4), KVM_PGTABLE_WALK_SKIP_BBM_TLBI = BIT(5), KVM_PGTABLE_WALK_SKIP_CMO = BIT(6), }; diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h index e65f33edf9d6..e9ce68d50ba4 100644 --- a/arch/arm64/include/asm/suspend.h +++ b/arch/arm64/include/asm/suspend.h @@ -2,7 +2,7 @@ #ifndef __ASM_SUSPEND_H #define __ASM_SUSPEND_H -#define NR_CTX_REGS 13 +#define NR_CTX_REGS 14 #define NR_CALLEE_SAVED_REGS 12 /* diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 9df51accbb02..106b15eb232a 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -91,7 +91,8 @@ */ #define pstate_field(op1, op2) ((op1) << Op1_shift | (op2) << Op2_shift) #define PSTATE_Imm_shift CRm_shift -#define SET_PSTATE(x, r) __emit_inst(0xd500401f | PSTATE_ ## r | ((!!x) << PSTATE_Imm_shift)) +#define ENCODE_PSTATE(x, r) (0xd500401f | PSTATE_ ## r | ((!!x) << PSTATE_Imm_shift)) +#define SET_PSTATE(x, r) __emit_inst(ENCODE_PSTATE(x, r)) #define PSTATE_PAN pstate_field(0, 4) #define PSTATE_UAO pstate_field(0, 3) diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 18749e9a6c2d..9717568518ba 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -402,7 +402,7 @@ int swsusp_arch_suspend(void) * Memory allocated by get_safe_page() will be dealt with by the hibernate code, * we don't need to free it here. */ -int swsusp_arch_resume(void) +int __nocfi swsusp_arch_resume(void) { int rc; void *zero_page; diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 85bc629270bd..211f0e2e55e2 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -86,6 +86,7 @@ KVM_NVHE_ALIAS(kvm_patch_vector_branch); KVM_NVHE_ALIAS(kvm_update_va_mask); KVM_NVHE_ALIAS(kvm_get_kimage_voffset); KVM_NVHE_ALIAS(kvm_compute_final_ctr_el0); +KVM_NVHE_ALIAS(kvm_pan_patch_el2_entry); KVM_NVHE_ALIAS(spectre_bhb_patch_loop_iter); KVM_NVHE_ALIAS(spectre_bhb_patch_loop_mitigation_enable); KVM_NVHE_ALIAS(spectre_bhb_patch_wa3); diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index b9bdd83fbbca..6c5ff6807d4c 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -968,20 +968,18 @@ static int sve_set_common(struct task_struct *target, vq = sve_vq_from_vl(task_get_vl(target, type)); /* Enter/exit streaming mode */ - if (system_supports_sme()) { - switch (type) { - case ARM64_VEC_SVE: - target->thread.svcr &= ~SVCR_SM_MASK; - set_tsk_thread_flag(target, TIF_SVE); - break; - case ARM64_VEC_SME: - target->thread.svcr |= SVCR_SM_MASK; - set_tsk_thread_flag(target, TIF_SME); - break; - default: - WARN_ON_ONCE(1); - return -EINVAL; - } + switch (type) { + case ARM64_VEC_SVE: + target->thread.svcr &= ~SVCR_SM_MASK; + set_tsk_thread_flag(target, TIF_SVE); + break; + case ARM64_VEC_SME: + target->thread.svcr |= SVCR_SM_MASK; + set_tsk_thread_flag(target, TIF_SME); + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; } /* Always zero V regs, FPSR, and FPCR */ diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 1110eeb21f57..08ffc5a5aea4 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -449,12 +449,28 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq)) return -EINVAL; + if (sm) { + sme_alloc(current, false); + if (!current->thread.sme_state) + return -ENOMEM; + } + sve_alloc(current, true); if (!current->thread.sve_state) { clear_thread_flag(TIF_SVE); return -ENOMEM; } + if (sm) { + current->thread.svcr |= SVCR_SM_MASK; + set_thread_flag(TIF_SME); + } else { + current->thread.svcr &= ~SVCR_SM_MASK; + set_thread_flag(TIF_SVE); + } + + current->thread.fp_type = FP_STATE_SVE; + err = __copy_from_user(current->thread.sve_state, (char __user const *)user->sve + SVE_SIG_REGS_OFFSET, @@ -462,12 +478,6 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (err) return -EFAULT; - if (flags & SVE_SIG_FLAG_SM) - current->thread.svcr |= SVCR_SM_MASK; - else - set_thread_flag(TIF_SVE); - current->thread.fp_type = FP_STATE_SVE; - err = read_fpsimd_context(&fpsimd, user); if (err) return err; @@ -576,6 +586,10 @@ static int restore_za_context(struct user_ctxs *user) if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq)) return -EINVAL; + sve_alloc(current, false); + if (!current->thread.sve_state) + return -ENOMEM; + sme_alloc(current, true); if (!current->thread.sme_state) { current->thread.svcr &= ~SVCR_ZA_MASK; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 4f80da0c0d1d..620a465248d1 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -569,6 +569,7 @@ static bool kvm_vcpu_should_clear_twi(struct kvm_vcpu *vcpu) return kvm_wfi_trap_policy == KVM_WFX_NOTRAP; return single_task_running() && + vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) || vcpu->kvm->arch.vgic.nassgireq); } diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 53bf70126f81..808d26bed182 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -403,6 +403,7 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, struct s1_walk_result *wr, u64 va) { u64 va_top, va_bottom, baddr, desc, new_desc, ipa; + struct kvm_s2_trans s2_trans = {}; int level, stride, ret; level = wi->sl; @@ -420,8 +421,6 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, ipa = baddr | index; if (wi->s2) { - struct kvm_s2_trans s2_trans = {}; - ret = kvm_walk_nested_s2(vcpu, ipa, &s2_trans); if (ret) { fail_s1_walk(wr, @@ -515,6 +514,11 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, new_desc |= PTE_AF; if (new_desc != desc) { + if (wi->s2 && !kvm_s2_trans_writable(&s2_trans)) { + fail_s1_walk(wr, ESR_ELx_FSC_PERM_L(level), true); + return -EPERM; + } + ret = kvm_swap_s1_desc(vcpu, ipa, desc, new_desc, wi); if (ret) return ret; diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index 9f4e8d68ab50..d1ccddf9e87d 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -126,7 +126,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) add x1, x1, #VCPU_CONTEXT - ALTERNATIVE(nop, SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN) + alternative_cb ARM64_ALWAYS_SYSTEM, kvm_pan_patch_el2_entry + nop + alternative_cb_end // Store the guest regs x2 and x3 stp x2, x3, [x1, #CPU_XREG_OFFSET(2)] diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index c5d5e5b86eaf..afecbdd3c1e9 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -854,7 +854,7 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code, return false; } -static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu) { /* * Check for the conditions of Cortex-A510's #2077057. When these occur diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index a7c689152f68..8ffbbce5e2ed 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -180,6 +180,9 @@ static void handle___pkvm_vcpu_load(struct kvm_cpu_context *host_ctxt) /* Propagate WFx trapping flags */ hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWE | HCR_TWI); hyp_vcpu->vcpu.arch.hcr_el2 |= hcr_el2 & (HCR_TWE | HCR_TWI); + } else { + memcpy(&hyp_vcpu->vcpu.arch.fgt, hyp_vcpu->host_vcpu->arch.fgt, + sizeof(hyp_vcpu->vcpu.arch.fgt)); } } diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 8911338961c5..12b2acfbcfd1 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -172,7 +172,6 @@ static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu) /* Trust the host for non-protected vcpu features. */ vcpu->arch.hcrx_el2 = host_vcpu->arch.hcrx_el2; - memcpy(vcpu->arch.fgt, host_vcpu->arch.fgt, sizeof(vcpu->arch.fgt)); return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index d3b9ec8a7c28..779089e42681 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -211,7 +211,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); - synchronize_vcpu_pstate(vcpu, exit_code); + synchronize_vcpu_pstate(vcpu); /* * Some guests (e.g., protected VMs) are not be allowed to run in diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 947ac1a951a5..9abc0a6cf448 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -144,7 +144,7 @@ static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker, * page table walk. */ if (r == -EAGAIN) - return !(walker->flags & KVM_PGTABLE_WALK_HANDLE_FAULT); + return walker->flags & KVM_PGTABLE_WALK_IGNORE_EAGAIN; return !r; } @@ -1262,7 +1262,8 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) { return stage2_update_leaf_attrs(pgt, addr, size, 0, KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W, - NULL, NULL, 0); + NULL, NULL, + KVM_PGTABLE_WALK_IGNORE_EAGAIN); } void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 9984c492305a..9db3f11a4754 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -536,7 +536,7 @@ static const exit_handler_fn hyp_exit_handlers[] = { static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { - synchronize_vcpu_pstate(vcpu, exit_code); + synchronize_vcpu_pstate(vcpu); /* * If we were in HYP context on entry, adjust the PSTATE view diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 48d7c372a4cd..2caa97f87890 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -497,7 +497,7 @@ static int share_pfn_hyp(u64 pfn) this->count = 1; rb_link_node(&this->node, parent, node); rb_insert_color(&this->node, &hyp_shared_pfns); - ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn, 1); + ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn); unlock: mutex_unlock(&hyp_shared_pfns_lock); @@ -523,7 +523,7 @@ static int unshare_pfn_hyp(u64 pfn) rb_erase(&this->node, &hyp_shared_pfns); kfree(this); - ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1); + ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn); unlock: mutex_unlock(&hyp_shared_pfns_lock); @@ -1563,14 +1563,12 @@ static void adjust_nested_exec_perms(struct kvm *kvm, *prot &= ~KVM_PGTABLE_PROT_PX; } -#define KVM_PGTABLE_WALK_MEMABORT_FLAGS (KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED) - static int gmem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_s2_trans *nested, struct kvm_memory_slot *memslot, bool is_perm) { bool write_fault, exec_fault, writable; - enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_MEMABORT_FLAGS; + enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt = vcpu->arch.hw_mmu->pgt; unsigned long mmu_seq; @@ -1665,7 +1663,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_pgtable *pgt; struct page *page; vm_flags_t vm_flags; - enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_MEMABORT_FLAGS; + enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED; if (fault_is_perm) fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu); @@ -1933,7 +1931,7 @@ out_unlock: /* Resolve the access fault by making the page young again. */ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { - enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED; + enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED; struct kvm_s2_mmu *mmu; trace_kvm_access_fault(fault_ipa); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index c8fd7c6a12a1..88a57ca36d96 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -4668,7 +4668,10 @@ static void perform_access(struct kvm_vcpu *vcpu, * that we don't know how to handle. This certainly qualifies * as a gross bug that should be fixed right away. */ - BUG_ON(!r->access); + if (!r->access) { + bad_trap(vcpu, params, r, "register access"); + return; + } /* Skip instruction if instructed so */ if (likely(r->access(vcpu, params, r))) diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index 91b22a014610..bf888d150dc7 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -296,3 +296,31 @@ void kvm_compute_final_ctr_el0(struct alt_instr *alt, generate_mov_q(read_sanitised_ftr_reg(SYS_CTR_EL0), origptr, updptr, nr_inst); } + +void kvm_pan_patch_el2_entry(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + /* + * If we're running at EL1 without hVHE, then SCTLR_EL2.SPAN means + * nothing to us (it is RES1), and we don't need to set PSTATE.PAN + * to anything useful. + */ + if (!is_kernel_in_hyp_mode() && !cpus_have_cap(ARM64_KVM_HVHE)) + return; + + /* + * Leap of faith: at this point, we must be running VHE one way or + * another, and FEAT_PAN is required to be implemented. If KVM + * explodes at runtime because your system does not abide by this + * requirement, call your favourite HW vendor, they have screwed up. + * + * We don't expect hVHE to access any userspace mapping, so always + * set PSTATE.PAN on enty. Same thing if we have PAN enabled on an + * EL2 kernel. Only force it to 0 if we have not configured PAN in + * the kernel (and you know this is really silly). + */ + if (cpus_have_cap(ARM64_KVM_HVHE) || IS_ENABLED(CONFIG_ARM64_PAN)) + *updptr = cpu_to_le32(ENCODE_PSTATE(1, PAN)); + else + *updptr = cpu_to_le32(ENCODE_PSTATE(0, PAN)); +} diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index f0e784b963e6..7176ff39cb87 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -171,7 +171,8 @@ static int change_memory_common(unsigned long addr, int numpages, */ area = find_vm_area((void *)addr); if (!area || - end > (unsigned long)kasan_reset_tag(area->addr) + area->size || + ((unsigned long)kasan_reset_tag((void *)end) > + (unsigned long)kasan_reset_tag(area->addr) + area->size) || ((area->flags & (VM_ALLOC | VM_ALLOW_HUGE_VMAP)) != VM_ALLOC)) return -EINVAL; @@ -184,7 +185,8 @@ static int change_memory_common(unsigned long addr, int numpages, */ if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY || pgprot_val(clear_mask) == PTE_RDONLY)) { - unsigned long idx = (start - (unsigned long)kasan_reset_tag(area->addr)) + unsigned long idx = ((unsigned long)kasan_reset_tag((void *)start) - + (unsigned long)kasan_reset_tag(area->addr)) >> PAGE_SHIFT; for (; numpages; idx++, numpages--) { ret = __change_memory_common((u64)page_address(area->pages[idx]), diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 01e868116448..5d907ce3b6d3 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -110,6 +110,10 @@ SYM_FUNC_START(cpu_do_suspend) * call stack. */ str x18, [x0, #96] +alternative_if ARM64_HAS_TCR2 + mrs x2, REG_TCR2_EL1 + str x2, [x0, #104] +alternative_else_nop_endif ret SYM_FUNC_END(cpu_do_suspend) @@ -144,6 +148,10 @@ SYM_FUNC_START(cpu_do_resume) msr tcr_el1, x8 msr vbar_el1, x9 msr mdscr_el1, x10 +alternative_if ARM64_HAS_TCR2 + ldr x2, [x0, #104] + msr REG_TCR2_EL1, x2 +alternative_else_nop_endif msr sctlr_el1, x12 set_this_cpu_offset x13 diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi index 357de4ca7555..e759fae77dcf 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi @@ -131,6 +131,7 @@ reg-names = "main", "isr0"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -149,6 +150,7 @@ reg-names = "main", "isr0"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <4>; @@ -164,6 +166,7 @@ compatible = "loongson,ls2k0500-eiointc"; reg = <0x0 0x1fe11600 0x0 0xea00>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <1>; interrupt-parent = <&cpuintc>; interrupts = <3>; diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi index 60ab425f793f..be4f7d119660 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi @@ -46,7 +46,7 @@ }; /* i2c of the dvi eeprom edid */ - i2c-gpio-0 { + i2c-0 { compatible = "i2c-gpio"; scl-gpios = <&gpio0 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; sda-gpios = <&gpio0 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; @@ -57,7 +57,7 @@ }; /* i2c of the eeprom edid */ - i2c-gpio-1 { + i2c-1 { compatible = "i2c-gpio"; scl-gpios = <&gpio0 33 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; sda-gpios = <&gpio0 32 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; @@ -114,6 +114,7 @@ <0x0 0x1fe01140 0x0 0x8>; reg-names = "main", "isr0", "isr1"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -131,6 +132,7 @@ <0x0 0x1fe01148 0x0 0x8>; reg-names = "main", "isr0", "isr1"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <3>; @@ -437,54 +439,47 @@ gmac0: ethernet@3,0 { reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, - <13 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 12 IRQ_TYPE_LEVEL_HIGH>, + <&liointc0 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; status = "disabled"; }; gmac1: ethernet@3,1 { reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, - <15 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 14 IRQ_TYPE_LEVEL_HIGH>, + <&liointc0 15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; status = "disabled"; }; ehci0: usb@4,1 { reg = <0x2100 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc1>; - interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc1 18 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; ohci0: usb@4,2 { reg = <0x2200 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc1>; - interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc1 19 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; display@6,0 { reg = <0x3000 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 28 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; hda@7,0 { reg = <0x3800 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 4 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; sata: sata@8,0 { reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 19 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi index 6c77b86ee06c..3678c084adf7 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi @@ -126,6 +126,7 @@ reg = <0x0 0x1fe01400 0x0 0x64>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -140,6 +141,7 @@ compatible = "loongson,ls2k2000-eiointc"; reg = <0x0 0x1fe01600 0x0 0xea00>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <1>; interrupt-parent = <&cpuintc>; interrupts = <3>; @@ -149,6 +151,7 @@ compatible = "loongson,pch-pic-1.0"; reg = <0x0 0x10000000 0x0 0x400>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; loongson,pic-base-vec = <0>; interrupt-parent = <&eiointc>; @@ -291,65 +294,57 @@ gmac0: ethernet@3,0 { reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, - <13 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 12 IRQ_TYPE_LEVEL_HIGH>, + <&pic 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; gmac1: ethernet@3,1 { reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, - <15 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 14 IRQ_TYPE_LEVEL_HIGH>, + <&pic 15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; gmac2: ethernet@3,2 { reg = <0x1a00 0x0 0x0 0x0 0x0>; - interrupts = <17 IRQ_TYPE_LEVEL_HIGH>, - <18 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 17 IRQ_TYPE_LEVEL_HIGH>, + <&pic 18 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; xhci0: usb@4,0 { reg = <0x2000 0x0 0x0 0x0 0x0>; - interrupts = <48 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 48 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; xhci1: usb@19,0 { reg = <0xc800 0x0 0x0 0x0 0x0>; - interrupts = <22 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 22 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; display@6,1 { reg = <0x3100 0x0 0x0 0x0 0x0>; - interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 28 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; i2s@7,0 { reg = <0x3800 0x0 0x0 0x0 0x0>; - interrupts = <78 IRQ_TYPE_LEVEL_HIGH>, - <79 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 78 IRQ_TYPE_LEVEL_HIGH>, + <&pic 79 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "tx", "rx"; - interrupt-parent = <&pic>; status = "disabled"; }; sata: sata@8,0 { reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupts = <16 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 16 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index e6b8ff61c8cc..553c4dc7a156 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -94,6 +94,12 @@ #define CPUCFG2_LSPW BIT(21) #define CPUCFG2_LAM BIT(22) #define CPUCFG2_PTW BIT(24) +#define CPUCFG2_FRECIPE BIT(25) +#define CPUCFG2_DIV32 BIT(26) +#define CPUCFG2_LAM_BH BIT(27) +#define CPUCFG2_LAMCAS BIT(28) +#define CPUCFG2_LLACQ_SCREL BIT(29) +#define CPUCFG2_SCQ BIT(30) #define LOONGARCH_CPUCFG3 0x3 #define CPUCFG3_CCDMA BIT(0) @@ -108,6 +114,7 @@ #define CPUCFG3_SPW_HG_HF BIT(11) #define CPUCFG3_RVA BIT(12) #define CPUCFG3_RVAMAX GENMASK(16, 13) +#define CPUCFG3_DBAR_HINTS BIT(17) #define CPUCFG3_ALDORDER_CAP BIT(18) /* All address load ordered, capability */ #define CPUCFG3_ASTORDER_CAP BIT(19) /* All address store ordered, capability */ #define CPUCFG3_ALDORDER_STA BIT(20) /* All address load ordered, status */ diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index aba548db2446..4eed7bc312a8 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -42,6 +42,7 @@ SYM_DATA(kernel_fsize, .long _kernel_fsize); .align 12 SYM_CODE_START(kernel_entry) # kernel entry point + UNWIND_HINT_END_OF_STACK SETUP_TWINS SETUP_MODES t0 @@ -113,6 +114,7 @@ SYM_CODE_END(kernel_entry) * function after setting up the stack and tp registers. */ SYM_CODE_START(smpboot_entry) + UNWIND_HINT_END_OF_STACK SETUP_TWINS SETUP_MODES t0 @@ -124,14 +126,6 @@ SYM_CODE_START(smpboot_entry) LONG_LI t1, CSR_STFILL csrxchg t0, t1, LOONGARCH_CSR_IMPCTL1 #endif - /* Enable PG */ - li.w t0, 0xb0 # PLV=0, IE=0, PG=1 - csrwr t0, LOONGARCH_CSR_CRMD - li.w t0, 0x04 # PLV=0, PIE=1, PWE=0 - csrwr t0, LOONGARCH_CSR_PRMD - li.w t0, 0x00 # FPE=0, SXE=0, ASXE=0, BTE=0 - csrwr t0, LOONGARCH_CSR_EUEN - la.pcrel t0, cpuboot_data ld.d sp, t0, CPU_BOOT_STACK ld.d tp, t0, CPU_BOOT_TINFO @@ -142,5 +136,3 @@ SYM_CODE_START(smpboot_entry) SYM_CODE_END(smpboot_entry) #endif /* CONFIG_SMP */ - -SYM_ENTRY(kernel_entry_end, SYM_L_GLOBAL, SYM_A_NONE) diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index d6b474ad1d5e..5729c20e5b8b 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -94,7 +94,6 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) * at the callsite, so there is no need to restore the T series regs. */ ftrace_common_return: - PTR_L ra, sp, PT_R1 PTR_L a0, sp, PT_R4 PTR_L a1, sp, PT_R5 PTR_L a2, sp, PT_R6 @@ -104,12 +103,17 @@ ftrace_common_return: PTR_L a6, sp, PT_R10 PTR_L a7, sp, PT_R11 PTR_L fp, sp, PT_R22 - PTR_L t0, sp, PT_ERA PTR_L t1, sp, PT_R13 - PTR_ADDI sp, sp, PT_SIZE bnez t1, .Ldirect + + PTR_L ra, sp, PT_R1 + PTR_L t0, sp, PT_ERA + PTR_ADDI sp, sp, PT_SIZE jr t0 .Ldirect: + PTR_L t0, sp, PT_R1 + PTR_L ra, sp, PT_ERA + PTR_ADDI sp, sp, PT_SIZE jr t1 SYM_CODE_END(ftrace_common) @@ -161,6 +165,8 @@ SYM_CODE_END(return_to_handler) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS SYM_CODE_START(ftrace_stub_direct_tramp) UNWIND_HINT_UNDEFINED - jr t0 + move t1, ra + move ra, t0 + jr t1 SYM_CODE_END(ftrace_stub_direct_tramp) #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 9d257c8519c9..e34a6fb33e11 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -626,6 +626,18 @@ static const struct loongarch_perf_event *loongarch_pmu_map_cache_event(u64 conf return pev; } +static inline bool loongarch_pmu_event_requires_counter(const struct perf_event *event) +{ + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + case PERF_TYPE_RAW: + return true; + default: + return false; + } +} + static int validate_group(struct perf_event *event) { struct cpu_hw_events fake_cpuc; @@ -633,15 +645,18 @@ static int validate_group(struct perf_event *event) memset(&fake_cpuc, 0, sizeof(fake_cpuc)); - if (loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0) + if (loongarch_pmu_event_requires_counter(leader) && + loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0) return -EINVAL; for_each_sibling_event(sibling, leader) { - if (loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0) + if (loongarch_pmu_event_requires_counter(sibling) && + loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0) return -EINVAL; } - if (loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0) + if (loongarch_pmu_event_requires_counter(event) && + loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0) return -EINVAL; return 0; diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 004b8ebf0051..5d49b742e3bf 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -535,10 +535,15 @@ out: asmlinkage void noinstr do_ade(struct pt_regs *regs) { irqentry_state_t state = irqentry_enter(regs); + unsigned int esubcode = FIELD_GET(CSR_ESTAT_ESUBCODE, regs->csr_estat); + + if ((esubcode == EXSUBCODE_ADEM) && fixup_exception(regs)) + goto out; die_if_kernel("Kernel ade access", regs); force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)regs->csr_badvaddr); +out: irqentry_exit(regs, state); } diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c index 0d5fa64a2225..8a6e3429a860 100644 --- a/arch/loongarch/kernel/unwind_orc.c +++ b/arch/loongarch/kernel/unwind_orc.c @@ -348,24 +348,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task, } EXPORT_SYMBOL_GPL(unwind_start); -static bool is_entry_func(unsigned long addr) -{ - extern u32 kernel_entry; - extern u32 kernel_entry_end; - - return addr >= (unsigned long)&kernel_entry && addr < (unsigned long)&kernel_entry_end; -} - static inline unsigned long bt_address(unsigned long ra) { extern unsigned long eentry; - if (__kernel_text_address(ra)) - return ra; - - if (__module_text_address(ra)) - return ra; - if (ra >= eentry && ra < eentry + EXCCODE_INT_END * VECSIZE) { unsigned long func; unsigned long type = (ra - eentry) / VECSIZE; @@ -383,10 +369,13 @@ static inline unsigned long bt_address(unsigned long ra) break; } - return func + offset; + ra = func + offset; } - return ra; + if (__kernel_text_address(ra)) + return ra; + + return 0; } bool unwind_next_frame(struct unwind_state *state) @@ -402,9 +391,6 @@ bool unwind_next_frame(struct unwind_state *state) /* Don't let modules unload while we're reading their ORC data. */ guard(rcu)(); - if (is_entry_func(state->pc)) - goto end; - orc = orc_find(state->pc); if (!orc) { /* @@ -512,9 +498,6 @@ bool unwind_next_frame(struct unwind_state *state) goto err; } - if (!__kernel_text_address(state->pc)) - goto err; - return true; err: diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index 29886876143f..dfaf6ccfdd8b 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -679,6 +679,7 @@ static void kvm_eiointc_destroy(struct kvm_device *dev) kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device); kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device_vext); kfree(eiointc); + kfree(dev); } static struct kvm_device_ops kvm_eiointc_dev_ops = { diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c index 05cefd29282e..1058c13dba7f 100644 --- a/arch/loongarch/kvm/intc/ipi.c +++ b/arch/loongarch/kvm/intc/ipi.c @@ -459,6 +459,7 @@ static void kvm_ipi_destroy(struct kvm_device *dev) ipi = kvm->arch.ipi; kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &ipi->device); kfree(ipi); + kfree(dev); } static struct kvm_device_ops kvm_ipi_dev_ops = { diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index a698a73de399..4addb34bf432 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -475,6 +475,7 @@ static void kvm_pch_pic_destroy(struct kvm_device *dev) /* unregister pch pic device and free it's memory */ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &s->device); kfree(s); + kfree(dev); } static struct kvm_device_ops kvm_pch_pic_dev_ops = { diff --git a/arch/loongarch/mm/cache.c b/arch/loongarch/mm/cache.c index 6be04d36ca07..496916845ff7 100644 --- a/arch/loongarch/mm/cache.c +++ b/arch/loongarch/mm/cache.c @@ -160,8 +160,8 @@ void cpu_cache_init(void) static const pgprot_t protection_map[16] = { [VM_NONE] = __pgprot(_CACHE_CC | _PAGE_USER | - _PAGE_PROTNONE | _PAGE_NO_EXEC | - _PAGE_NO_READ), + _PAGE_NO_EXEC | _PAGE_NO_READ | + (_PAGE_PROTNONE ? : _PAGE_PRESENT)), [VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC), @@ -180,8 +180,8 @@ static const pgprot_t protection_map[16] = { [VM_EXEC | VM_WRITE | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT), [VM_SHARED] = __pgprot(_CACHE_CC | _PAGE_USER | - _PAGE_PROTNONE | _PAGE_NO_EXEC | - _PAGE_NO_READ), + _PAGE_NO_EXEC | _PAGE_NO_READ | + (_PAGE_PROTNONE ? : _PAGE_PRESENT)), [VM_SHARED | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC), diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 8dc58781b8eb..d1d5a65308b9 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -139,6 +139,7 @@ static void build_prologue(struct jit_ctx *ctx) stack_adjust = round_up(stack_adjust, 16); stack_adjust += bpf_stack_adjust; + move_reg(ctx, LOONGARCH_GPR_T0, LOONGARCH_GPR_RA); /* Reserve space for the move_imm + jirl instruction */ for (i = 0; i < LOONGARCH_LONG_JUMP_NINSNS; i++) emit_insn(ctx, nop); @@ -238,7 +239,7 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call) * Call the next bpf prog and skip the first instruction * of TCC initialization. */ - emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 6); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 7); } } @@ -280,6 +281,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn) * goto out; */ tc_ninsn = insn ? ctx->offset[insn+1] - ctx->offset[insn] : ctx->offset[0]; + emit_zext_32(ctx, a2, true); + off = offsetof(struct bpf_array, map.max_entries); emit_insn(ctx, ldwu, t1, a1, off); /* bgeu $a2, $t1, jmp_offset */ @@ -950,6 +953,22 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_SP, tcc_ptr_off); } + if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + const struct btf_func_model *m; + int i; + + m = bpf_jit_find_kfunc_model(ctx->prog, insn); + if (!m) + return -EINVAL; + + for (i = 0; i < m->nr_args; i++) { + u8 reg = regmap[BPF_REG_1 + i]; + bool sign = m->arg_flags[i] & BTF_FMODEL_SIGNED_ARG; + + emit_abi_ext(ctx, reg, m->arg_size[i], sign); + } + } + move_addr(ctx, t1, func_addr); emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0); @@ -1265,7 +1284,7 @@ static int emit_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call) return 0; } - return emit_jump_and_link(&ctx, is_call ? LOONGARCH_GPR_T0 : LOONGARCH_GPR_ZERO, (u64)target); + return emit_jump_and_link(&ctx, is_call ? LOONGARCH_GPR_RA : LOONGARCH_GPR_ZERO, (u64)target); } static int emit_call(struct jit_ctx *ctx, u64 addr) @@ -1290,15 +1309,30 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t, { int ret; bool is_call; + unsigned long size = 0; + unsigned long offset = 0; + void *image = NULL; + char namebuf[KSYM_NAME_LEN]; u32 old_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP}; u32 new_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP}; /* Only poking bpf text is supported. Since kernel function entry * is set up by ftrace, we rely on ftrace to poke kernel functions. */ - if (!is_bpf_text_address((unsigned long)ip)) + if (!__bpf_address_lookup((unsigned long)ip, &size, &offset, namebuf)) return -ENOTSUPP; + image = ip - offset; + + /* zero offset means we're poking bpf prog entry */ + if (offset == 0) { + /* skip to the nop instruction in bpf prog entry: + * move t0, ra + * nop + */ + ip = image + LOONGARCH_INSN_SIZE; + } + is_call = old_t == BPF_MOD_CALL; ret = emit_jump_or_nops(old_addr, ip, old_insns, is_call); if (ret) @@ -1622,14 +1656,12 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i /* To traced function */ /* Ftrace jump skips 2 NOP instructions */ - if (is_kernel_text((unsigned long)orig_call)) + if (is_kernel_text((unsigned long)orig_call) || + is_module_text_address((unsigned long)orig_call)) orig_call += LOONGARCH_FENTRY_NBYTES; /* Direct jump skips 5 NOP instructions */ else if (is_bpf_text_address((unsigned long)orig_call)) orig_call += LOONGARCH_BPF_FENTRY_NBYTES; - /* Module tracing not supported - cause kernel lockups */ - else if (is_module_text_address((unsigned long)orig_call)) - return -ENOTSUPP; if (flags & BPF_TRAMP_F_CALL_ORIG) { move_addr(ctx, LOONGARCH_GPR_A0, (const u64)im); @@ -1722,12 +1754,16 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i emit_insn(ctx, ldd, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, 0); emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, 16); - if (flags & BPF_TRAMP_F_SKIP_FRAME) + if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* return to parent function */ - emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0); - else - /* return to traced function */ + move_reg(ctx, LOONGARCH_GPR_RA, LOONGARCH_GPR_T0); emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T0, 0); + } else { + /* return to traced function */ + move_reg(ctx, LOONGARCH_GPR_T1, LOONGARCH_GPR_RA); + move_reg(ctx, LOONGARCH_GPR_RA, LOONGARCH_GPR_T0); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T1, 0); + } } ret = ctx->idx; diff --git a/arch/loongarch/net/bpf_jit.h b/arch/loongarch/net/bpf_jit.h index 5697158fd164..75b6330030a9 100644 --- a/arch/loongarch/net/bpf_jit.h +++ b/arch/loongarch/net/bpf_jit.h @@ -88,6 +88,32 @@ static inline void emit_sext_32(struct jit_ctx *ctx, enum loongarch_gpr reg, boo emit_insn(ctx, addiw, reg, reg, 0); } +/* Emit proper extension according to ABI requirements. + * Note that it requires a value of size `size` already resides in register `reg`. + */ +static inline void emit_abi_ext(struct jit_ctx *ctx, int reg, u8 size, bool sign) +{ + /* ABI requires unsigned char/short to be zero-extended */ + if (!sign && (size == 1 || size == 2)) + return; + + switch (size) { + case 1: + emit_insn(ctx, extwb, reg, reg); + break; + case 2: + emit_insn(ctx, extwh, reg, reg); + break; + case 4: + emit_insn(ctx, addiw, reg, reg, 0); + break; + case 8: + break; + default: + pr_warn("bpf_jit: invalid size %d for extension\n", size); + } +} + static inline void move_addr(struct jit_ctx *ctx, enum loongarch_gpr rd, u64 addr) { u64 imm_11_0, imm_31_12, imm_51_32, imm_63_52; diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index a673d3d68254..8986048f9b11 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -425,6 +425,28 @@ void __init paging_init(void) static struct kcore_list kcore_kseg0; #endif +static inline void __init highmem_init(void) +{ +#ifdef CONFIG_HIGHMEM + unsigned long tmp; + + /* + * If CPU cannot support HIGHMEM discard the memory above highstart_pfn + */ + if (cpu_has_dc_aliases) { + memblock_remove(PFN_PHYS(highstart_pfn), -1); + return; + } + + for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { + struct page *page = pfn_to_page(tmp); + + if (!memblock_is_memory(PFN_PHYS(tmp))) + SetPageReserved(page); + } +#endif +} + void __init arch_mm_preinit(void) { /* @@ -435,6 +457,7 @@ void __init arch_mm_preinit(void) maar_init(); setup_zero_pages(); /* Setup zeroed pages. */ + highmem_init(); #ifdef CONFIG_64BIT if ((unsigned long) &_text > (unsigned long) CKSEG0) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 2429cb1c7baa..764001deb060 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -26,6 +26,7 @@ #include <linux/delay.h> #include <linux/processor.h> #include <linux/smp.h> +#include <linux/sys_info.h> #include <asm/interrupt.h> #include <asm/paca.h> @@ -235,7 +236,11 @@ static void watchdog_smp_panic(int cpu) pr_emerg("CPU %d TB:%lld, last SMP heartbeat TB:%lld (%lldms ago)\n", cpu, tb, last_reset, tb_to_ns(tb - last_reset) / 1000000); - if (!sysctl_hardlockup_all_cpu_backtrace) { + if (sysctl_hardlockup_all_cpu_backtrace || + (hardlockup_si_mask & SYS_INFO_ALL_BT)) { + trigger_allbutcpu_cpu_backtrace(cpu); + cpumask_clear(&wd_smp_cpus_ipi); + } else { /* * Try to trigger the stuck CPUs, unless we are going to * get a backtrace on all of them anyway. @@ -244,11 +249,9 @@ static void watchdog_smp_panic(int cpu) smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000); __cpumask_clear_cpu(c, &wd_smp_cpus_ipi); } - } else { - trigger_allbutcpu_cpu_backtrace(cpu); - cpumask_clear(&wd_smp_cpus_ipi); } + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); @@ -415,9 +418,11 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi - if (sysctl_hardlockup_all_cpu_backtrace) + if (sysctl_hardlockup_all_cpu_backtrace || + (hardlockup_si_mask & SYS_INFO_ALL_BT)) trigger_allbutcpu_cpu_backtrace(cpu); + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index e5000bef90f2..7cf9310de0ec 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -723,7 +723,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - zone_device_page_init(dpage, 0); + zone_device_page_init(dpage, &kvmppc_uvmem_pgmap, 0); return dpage; out_clear: spin_lock(&kvmppc_uvmem_bitmap_lock); diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata index aca9b0cfcfec..3c945d086c7d 100644 --- a/arch/riscv/Kconfig.errata +++ b/arch/riscv/Kconfig.errata @@ -84,6 +84,7 @@ config ERRATA_STARFIVE_JH7100 select DMA_GLOBAL_POOL select RISCV_DMA_NONCOHERENT select RISCV_NONSTANDARD_CACHE_OPS + select CACHEMAINT_FOR_DMA select SIFIVE_CCACHE default n help diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile index bfc3d0b75b9b..5301adf5f3f5 100644 --- a/arch/riscv/boot/Makefile +++ b/arch/riscv/boot/Makefile @@ -31,11 +31,7 @@ $(obj)/xipImage: vmlinux FORCE endif -ifdef CONFIG_RELOCATABLE -$(obj)/Image: vmlinux.unstripped FORCE -else $(obj)/Image: vmlinux FORCE -endif $(call if_changed,objcopy) $(obj)/Image.gz: $(obj)/Image FORCE diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig index ee18d1e333f2..544c52067dc2 100644 --- a/arch/riscv/configs/nommu_k210_defconfig +++ b/arch/riscv/configs/nommu_k210_defconfig @@ -55,7 +55,6 @@ CONFIG_DEVTMPFS_MOUNT=y # CONFIG_HW_RANDOM is not set # CONFIG_DEVMEM is not set CONFIG_I2C=y -# CONFIG_I2C_COMPAT is not set CONFIG_I2C_CHARDEV=y # CONFIG_I2C_HELPER_AUTO is not set CONFIG_I2C_DESIGNWARE_CORE=y @@ -89,7 +88,6 @@ CONFIG_PRINTK_TIME=y # CONFIG_FRAME_POINTER is not set # CONFIG_DEBUG_MISC is not set CONFIG_PANIC_ON_OOPS=y -# CONFIG_SCHED_DEBUG is not set # CONFIG_RCU_TRACE is not set # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig index e770d81b738e..4a826e30fa3e 100644 --- a/arch/riscv/configs/nommu_k210_sdcard_defconfig +++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig @@ -86,7 +86,6 @@ CONFIG_PRINTK_TIME=y # CONFIG_FRAME_POINTER is not set # CONFIG_DEBUG_MISC is not set CONFIG_PANIC_ON_OOPS=y -# CONFIG_SCHED_DEBUG is not set # CONFIG_RCU_TRACE is not set # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig index 0da5069bfbef..4c38049633b7 100644 --- a/arch/riscv/configs/nommu_virt_defconfig +++ b/arch/riscv/configs/nommu_virt_defconfig @@ -66,7 +66,6 @@ CONFIG_EXT2_FS=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_LSM="[]" CONFIG_PRINTK_TIME=y -# CONFIG_SCHED_DEBUG is not set # CONFIG_RCU_TRACE is not set # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h index 238092125c11..3c1a15be54d8 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -11,7 +11,6 @@ #endif /* _LINUX_BITOPS_H */ #include <linux/compiler.h> -#include <linux/irqflags.h> #include <asm/barrier.h> #include <asm/bitsperlong.h> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 6bb1f5bdc5d2..9acd58a67123 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -124,10 +124,6 @@ #ifdef CONFIG_64BIT #include <asm/pgtable-64.h> -#define VA_USER_SV39 (UL(1) << (VA_BITS_SV39 - 1)) -#define VA_USER_SV48 (UL(1) << (VA_BITS_SV48 - 1)) -#define VA_USER_SV57 (UL(1) << (VA_BITS_SV57 - 1)) - #define MMAP_VA_BITS_64 ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS) #define MMAP_MIN_VA_BITS_64 (VA_BITS_SV39) #define MMAP_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_VA_BITS_64) diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 36bba6720c26..11c9886c3b70 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -97,13 +97,23 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigne */ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +/* + * Use a temporary variable for the output of the asm goto to avoid a + * triggering an LLVM assertion due to sign extending the output when + * it is used in later function calls: + * https://github.com/llvm/llvm-project/issues/143795 + */ #define __get_user_asm(insn, x, ptr, label) \ +do { \ + u64 __tmp; \ asm_goto_output( \ "1:\n" \ " " insn " %0, %1\n" \ _ASM_EXTABLE_UACCESS_ERR(1b, %l2, %0) \ - : "=&r" (x) \ - : "m" (*(ptr)) : : label) + : "=&r" (__tmp) \ + : "m" (*(ptr)) : : label); \ + (x) = (__typeof__(x))(unsigned long)__tmp; \ +} while (0) #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ #define __get_user_asm(insn, x, ptr, label) \ do { \ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f60fce69b725..a01f6439d62b 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -3,12 +3,6 @@ # Makefile for the RISC-V Linux kernel # -ifdef CONFIG_FTRACE -CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) -endif CFLAGS_syscall_table.o += $(call cc-disable-warning, override-init) CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init) @@ -24,7 +18,6 @@ CFLAGS_sbi_ecall.o := -mcmodel=medany ifdef CONFIG_FTRACE CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_sbi_ecall.o = $(CC_FLAGS_FTRACE) endif ifdef CONFIG_RELOCATABLE CFLAGS_alternative.o += -fno-pie @@ -43,6 +36,14 @@ CFLAGS_sbi_ecall.o += -D__NO_FORTIFY endif endif +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_sbi_ecall.o = $(CC_FLAGS_FTRACE) +endif + always-$(KBUILD_BUILTIN) += vmlinux.lds obj-y += head.o diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c index 87d655944803..00aff669f5f2 100644 --- a/arch/riscv/kernel/cpu_ops_sbi.c +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -85,7 +85,7 @@ static void sbi_cpu_stop(void) int ret; ret = sbi_hsm_hart_stop(); - pr_crit("Unable to stop the cpu %u (%d)\n", smp_processor_id(), ret); + pr_crit("Unable to stop the cpu %d (%d)\n", smp_processor_id(), ret); } static int sbi_cpu_is_stopped(unsigned int cpuid) diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index c05b11596c19..fa591aff9d33 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -301,23 +301,22 @@ static const unsigned int riscv_a_exts[] = { RISCV_ISA_EXT_ZALRSC, }; +#define RISCV_ISA_EXT_ZKN \ + RISCV_ISA_EXT_ZBKB, \ + RISCV_ISA_EXT_ZBKC, \ + RISCV_ISA_EXT_ZBKX, \ + RISCV_ISA_EXT_ZKND, \ + RISCV_ISA_EXT_ZKNE, \ + RISCV_ISA_EXT_ZKNH + static const unsigned int riscv_zk_bundled_exts[] = { - RISCV_ISA_EXT_ZBKB, - RISCV_ISA_EXT_ZBKC, - RISCV_ISA_EXT_ZBKX, - RISCV_ISA_EXT_ZKND, - RISCV_ISA_EXT_ZKNE, + RISCV_ISA_EXT_ZKN, RISCV_ISA_EXT_ZKR, - RISCV_ISA_EXT_ZKT, + RISCV_ISA_EXT_ZKT }; static const unsigned int riscv_zkn_bundled_exts[] = { - RISCV_ISA_EXT_ZBKB, - RISCV_ISA_EXT_ZBKC, - RISCV_ISA_EXT_ZBKX, - RISCV_ISA_EXT_ZKND, - RISCV_ISA_EXT_ZKNE, - RISCV_ISA_EXT_ZKNH, + RISCV_ISA_EXT_ZKN }; static const unsigned int riscv_zks_bundled_exts[] = { diff --git a/arch/riscv/kernel/kexec_image.c b/arch/riscv/kernel/kexec_image.c index 8f2eb900910b..51dc89259f16 100644 --- a/arch/riscv/kernel/kexec_image.c +++ b/arch/riscv/kernel/kexec_image.c @@ -22,7 +22,7 @@ static int image_probe(const char *kernel_buf, unsigned long kernel_len) if (!h || kernel_len < sizeof(*h)) return -EINVAL; - /* According to Documentation/riscv/boot-image-header.rst, + /* According to Documentation/arch/riscv/boot-image-header.rst, * use "magic2" field to check when version >= 0.2. */ diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c index 24b3f57d467f..aff93090c4ef 100644 --- a/arch/riscv/kernel/suspend.c +++ b/arch/riscv/kernel/suspend.c @@ -51,10 +51,11 @@ void suspend_restore_csrs(struct suspend_context *context) #ifdef CONFIG_MMU if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) { - csr_write(CSR_STIMECMP, context->stimecmp); #if __riscv_xlen < 64 + csr_write(CSR_STIMECMP, ULONG_MAX); csr_write(CSR_STIMECMPH, context->stimecmph); #endif + csr_write(CSR_STIMECMP, context->stimecmp); } csr_write(CSR_SATP, context->satp); diff --git a/arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S b/arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S index b951d0f12482..f16deee9e091 100644 --- a/arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S +++ b/arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S @@ -181,6 +181,7 @@ SYM_FUNC_END(test_kprobes_c_bnez) #endif /* CONFIG_RISCV_ISA_C */ +.section .rodata SYM_DATA_START(test_kprobes_addresses) RISCV_PTR test_kprobes_add_addr1 RISCV_PTR test_kprobes_add_addr2 @@ -212,6 +213,7 @@ SYM_DATA_START(test_kprobes_addresses) RISCV_PTR 0 SYM_DATA_END(test_kprobes_addresses) +.section .rodata SYM_DATA_START(test_kprobes_functions) RISCV_PTR test_kprobes_add RISCV_PTR test_kprobes_jal diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 80230de167de..47afea4ff1a8 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -339,8 +339,10 @@ void do_trap_ecall_u(struct pt_regs *regs) add_random_kstack_offset(); - if (syscall >= 0 && syscall < NR_syscalls) + if (syscall >= 0 && syscall < NR_syscalls) { + syscall = array_index_nospec(syscall, NR_syscalls); syscall_handler(regs, syscall); + } /* * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c index 85a7262115e1..f36247e4c783 100644 --- a/arch/riscv/kvm/vcpu_timer.c +++ b/arch/riscv/kvm/vcpu_timer.c @@ -72,8 +72,9 @@ static int kvm_riscv_vcpu_timer_cancel(struct kvm_vcpu_timer *t) static int kvm_riscv_vcpu_update_vstimecmp(struct kvm_vcpu *vcpu, u64 ncycles) { #if defined(CONFIG_32BIT) - ncsr_write(CSR_VSTIMECMP, ncycles & 0xFFFFFFFF); + ncsr_write(CSR_VSTIMECMP, ULONG_MAX); ncsr_write(CSR_VSTIMECMPH, ncycles >> 32); + ncsr_write(CSR_VSTIMECMP, (u32)ncycles); #else ncsr_write(CSR_VSTIMECMP, ncycles); #endif @@ -307,8 +308,9 @@ void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu) return; #if defined(CONFIG_32BIT) - ncsr_write(CSR_VSTIMECMP, (u32)t->next_cycles); + ncsr_write(CSR_VSTIMECMP, ULONG_MAX); ncsr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32)); + ncsr_write(CSR_VSTIMECMP, (u32)(t->next_cycles)); #else ncsr_write(CSR_VSTIMECMP, t->next_cycles); #endif diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 5f9457e910e8..37888abee70c 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -1133,10 +1133,6 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, store_args(nr_arg_slots, args_off, ctx); - /* skip to actual body of traced function */ - if (flags & BPF_TRAMP_F_ORIG_STACK) - orig_call += RV_FENTRY_NINSNS * 4; - if (flags & BPF_TRAMP_F_CALL_ORIG) { emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx); ret = emit_call((const u64)__bpf_tramp_enter, true, ctx); @@ -1171,6 +1167,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_CALL_ORIG) { + /* skip to actual body of traced function */ + orig_call += RV_FENTRY_NINSNS * 4; restore_args(min_t(int, nr_arg_slots, RV_MAX_REG_ARGS), args_off, ctx); restore_stack_args(nr_arg_slots - RV_MAX_REG_ARGS, args_off, stk_arg_off, ctx); ret = emit_call((const u64)orig_call, true, ctx); diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index 50988022f9ea..070bc18babd0 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -137,6 +137,15 @@ SECTIONS } _end = .; + /* Sections to be discarded */ + /DISCARD/ : { + COMMON_DISCARDS + *(.eh_frame) + *(*__ksymtab*) + *(___kcrctab*) + *(.modinfo) + } + DWARF_DEBUG ELF_DETAILS @@ -161,12 +170,4 @@ SECTIONS *(.rela.*) *(.rela_*) } ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") - - /* Sections to be discarded */ - /DISCARD/ : { - COMMON_DISCARDS - *(.eh_frame) - *(*__ksymtab*) - *(___kcrctab*) - } } diff --git a/arch/s390/kernel/vdso/Makefile b/arch/s390/kernel/vdso/Makefile index 2fa12d4ac106..fece5d975eaf 100644 --- a/arch/s390/kernel/vdso/Makefile +++ b/arch/s390/kernel/vdso/Makefile @@ -28,7 +28,7 @@ KBUILD_CFLAGS_VDSO := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAG KBUILD_CFLAGS_VDSO := $(filter-out -munaligned-symbols,$(KBUILD_CFLAGS_VDSO)) KBUILD_CFLAGS_VDSO := $(filter-out -fno-asynchronous-unwind-tables,$(KBUILD_CFLAGS_VDSO)) KBUILD_CFLAGS_VDSO += -fPIC -fno-common -fno-builtin -fasynchronous-unwind-tables -KBUILD_CFLAGS_VDSO += -fno-stack-protector +KBUILD_CFLAGS_VDSO += -fno-stack-protector $(DISABLE_KSTACK_ERASE) ldflags-y := -shared -soname=linux-vdso.so.1 \ --hash-style=both --build-id=sha1 -T diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 1d2507f22437..1fbb7d46e484 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -7,7 +7,7 @@ * Heavily based on the x86 and PowerPC implementations. * * x86: - * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index a9448088e762..b290107170e9 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -181,6 +181,28 @@ static int __init ofpci_debug(char *str) __setup("ofpci_debug=", ofpci_debug); +static void of_fixup_pci_pref(struct pci_dev *dev, int index, + struct resource *res) +{ + struct pci_bus_region region; + + if (!(res->flags & IORESOURCE_MEM_64)) + return; + + if (!resource_size(res)) + return; + + pcibios_resource_to_bus(dev->bus, ®ion, res); + if (region.end <= ~((u32)0)) + return; + + if (!(res->flags & IORESOURCE_PREFETCH)) { + res->flags |= IORESOURCE_PREFETCH; + pci_info(dev, "reg 0x%x: fixup: pref added to 64-bit resource\n", + index); + } +} + static unsigned long pci_parse_of_flags(u32 addr0) { unsigned long flags = 0; @@ -244,6 +266,7 @@ static void pci_parse_of_addrs(struct platform_device *op, res->end = op_res->end; res->flags = flags; res->name = pci_name(dev); + of_fixup_pci_pref(dev, i, res); pci_info(dev, "reg 0x%x: %pR\n", i, res); } diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index cae4d33002a5..0ce4ae343531 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -6,7 +6,7 @@ * This code is based almost entirely upon the x86 perf event * code, which is: * - * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile index 3b8ae214a6a6..b2e9ec2f6901 100644 --- a/arch/x86/coco/sev/Makefile +++ b/arch/x86/coco/sev/Makefile @@ -8,3 +8,5 @@ UBSAN_SANITIZE_noinstr.o := n # GCC may fail to respect __no_sanitize_address or __no_kcsan when inlining KASAN_SANITIZE_noinstr.o := n KCSAN_SANITIZE_noinstr.o := n + +GCOV_PROFILE_noinstr.o := n diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 0c38a31d5fc7..576baa9a52c5 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1,7 +1,7 @@ /* * Performance events x86 architecture code * - * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 3161ec0a3416..ad35c546243e 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1,7 +1,7 @@ /* * Performance events x86 architecture header * - * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter @@ -1574,13 +1574,22 @@ static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period struct hw_perf_event *hwc = &event->hw; unsigned int hw_event, bts_event; - if (event->attr.freq) + /* + * Only use BTS for fixed rate period==1 events. + */ + if (event->attr.freq || period != 1) + return false; + + /* + * BTS doesn't virtualize. + */ + if (event->attr.exclude_host) return false; hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); - return hw_event == bts_event && period == 1; + return hw_event == bts_event; } static inline bool intel_pmu_has_bts(struct perf_event *event) diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h index ff5c7134a37a..acf9ffa1a171 100644 --- a/arch/x86/include/asm/kfence.h +++ b/arch/x86/include/asm/kfence.h @@ -42,10 +42,34 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) { unsigned int level; pte_t *pte = lookup_address(addr, &level); + pteval_t val; if (WARN_ON(!pte || level != PG_LEVEL_4K)) return false; + val = pte_val(*pte); + + /* + * protect requires making the page not-present. If the PTE is + * already in the right state, there's nothing to do. + */ + if (protect != !!(val & _PAGE_PRESENT)) + return true; + + /* + * Otherwise, invert the entire PTE. This avoids writing out an + * L1TF-vulnerable PTE (not present, without the high address bits + * set). + */ + set_pte(pte, __pte(~val)); + + /* + * If the page was protected (non-present) and we're making it + * present, there is no need to flush the TLB at all. + */ + if (!protect) + return true; + /* * We need to avoid IPIs, as we may get KFENCE allocations or faults * with interrupts disabled. Therefore, the below is best-effort, and @@ -53,11 +77,6 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) * lazy fault handling takes care of faults after the page is PRESENT. */ - if (protect) - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); - else - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); - /* * Flush this CPU's TLB, assuming whoever did the allocation/free is * likely to continue running on this CPU. diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 3821a985f4ff..46673530bc6f 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -258,7 +258,7 @@ static bool cpu_has_entrysign(void) if (fam == 0x1a) { if (model <= 0x2f || (0x40 <= model && model <= 0x4f) || - (0x60 <= model && model <= 0x6f)) + (0x60 <= model && model <= 0x7f)) return true; } diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 3792ab4819dc..6ebff44a3f75 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -825,7 +825,8 @@ static __init bool get_mem_config(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) return __get_mem_config_intel(&hw_res->r_resctrl); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) return __rdt_get_mem_config_amd(&hw_res->r_resctrl); return false; @@ -987,7 +988,8 @@ static __init void rdt_init_res_defs(void) { if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) rdt_init_res_defs_intel(); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) rdt_init_res_defs_amd(); } @@ -1019,8 +1021,19 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) c->x86_cache_occ_scale = ebx; c->x86_cache_mbm_width_offset = eax & 0xff; - if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset) - c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; + if (!c->x86_cache_mbm_width_offset) { + switch (c->x86_vendor) { + case X86_VENDOR_AMD: + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; + break; + case X86_VENDOR_HYGON: + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_HYGON; + break; + default: + /* Leave c->x86_cache_mbm_width_offset as 0 */ + break; + } + } } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 4a916c84a322..79c18657ede0 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -14,6 +14,9 @@ #define MBM_CNTR_WIDTH_OFFSET_AMD 20 +/* Hygon MBM counter width as an offset from MBM_CNTR_WIDTH_BASE */ +#define MBM_CNTR_WIDTH_OFFSET_HYGON 8 + #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index da233f20ae6f..608983806fd7 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -319,10 +319,29 @@ EXPORT_SYMBOL_FOR_KVM(fpu_enable_guest_xfd_features); #ifdef CONFIG_X86_64 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { + struct fpstate *fpstate = guest_fpu->fpstate; + fpregs_lock(); - guest_fpu->fpstate->xfd = xfd; - if (guest_fpu->fpstate->in_use) - xfd_update_state(guest_fpu->fpstate); + + /* + * KVM's guest ABI is that setting XFD[i]=1 *can* immediately revert the + * save state to its initial configuration. Likewise, KVM_GET_XSAVE does + * the same as XSAVE and returns XSTATE_BV[i]=0 whenever XFD[i]=1. + * + * If the guest's FPU state is in hardware, just update XFD: the XSAVE + * in fpu_swap_kvm_fpstate will clear XSTATE_BV[i] whenever XFD[i]=1. + * + * If however the guest's FPU state is NOT resident in hardware, clear + * disabled components in XSTATE_BV now, or a subsequent XRSTOR will + * attempt to load disabled components and generate #NM _in the host_. + */ + if (xfd && test_thread_flag(TIF_NEED_FPU_LOAD)) + fpstate->regs.xsave.header.xfeatures &= ~xfd; + + fpstate->xfd = xfd; + if (fpstate->in_use) + xfd_update_state(fpstate); + fpregs_unlock(); } EXPORT_SYMBOL_FOR_KVM(fpu_update_guest_xfd); @@ -431,6 +450,13 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, return -EINVAL; /* + * Disabled features must be in their initial state, otherwise XRSTOR + * causes an exception. + */ + if (WARN_ON_ONCE(ustate->xsave.header.xfeatures & kstate->xfd)) + return -EINVAL; + + /* * Nullify @vpkru to preserve its current value if PKRU's bit isn't set * in the header. KVM's odd ABI is to leave PKRU untouched in this * case (all other components are eventually re-initialized). diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index df78ddee0abb..37dc8465e0f5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -89,6 +89,7 @@ struct kvm_task_sleep_node { struct swait_queue_head wq; u32 token; int cpu; + bool dummy; }; static struct kvm_task_sleep_head { @@ -120,15 +121,26 @@ static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n) raw_spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { - /* dummy entry exist -> wake up was delivered ahead of PF */ - hlist_del(&e->link); + struct kvm_task_sleep_node *dummy = NULL; + + /* + * The entry can either be a 'dummy' entry (which is put on the + * list when wake-up happens ahead of APF handling completion) + * or a token from another task which should not be touched. + */ + if (e->dummy) { + hlist_del(&e->link); + dummy = e; + } + raw_spin_unlock(&b->lock); - kfree(e); + kfree(dummy); return false; } n->token = token; n->cpu = smp_processor_id(); + n->dummy = false; init_swait_queue_head(&n->wq); hlist_add_head(&n->link, &b->list); raw_spin_unlock(&b->lock); @@ -231,6 +243,7 @@ again: } dummy->token = token; dummy->cpu = smp_processor_id(); + dummy->dummy = true; init_swait_queue_head(&dummy->wq); hlist_add_head(&dummy->link, &b->list); dummy = NULL; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 0a2bbd674a6d..ebefb77c37bb 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2009 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * For licencing details see kernel-base/COPYING */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ff8812f3a129..63afdb6bb078 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5807,9 +5807,18 @@ static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { + union fpregs_state *xstate = (union fpregs_state *)guest_xsave->region; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; + /* + * For backwards compatibility, do not expect disabled features to be in + * their initial state. XSTATE_BV[i] must still be cleared whenever + * XFD[i]=1, or XRSTOR would cause a #NM. + */ + xstate->xsave.header.xfeatures &= ~vcpu->arch.guest_fpu.fpstate->xfd; + return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, kvm_caps.supported_xcr0, diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 998bd807fc7b..b83a06739b51 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -821,8 +821,6 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, force_sig_pkuerr((void __user *)address, pkey); else force_sig_fault(SIGSEGV, si_code, (void __user *)address); - - local_irq_disable(); } static noinline void @@ -1474,15 +1472,12 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code, do_kern_addr_fault(regs, error_code, address); } else { do_user_addr_fault(regs, error_code, address); - /* - * User address page fault handling might have reenabled - * interrupts. Fixing up all potential exit points of - * do_user_addr_fault() and its leaf functions is just not - * doable w/o creating an unholy mess or turning the code - * upside down. - */ - local_irq_disable(); } + /* + * page fault handling might have reenabled interrupts, + * make sure to disable them again. + */ + local_irq_disable(); } DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 3c306de52fd4..834641c6049a 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -115,12 +115,12 @@ void __init kernel_randomize_memory(void) /* * Adapt physical memory region size based on available memory, - * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the - * device BAR space assuming the direct map space is large enough - * for creating a ZONE_DEVICE mapping in the direct map corresponding - * to the physical BAR address. + * except when CONFIG_ZONE_DEVICE is enabled. ZONE_DEVICE wants to map + * any physical address into the direct-map. KASLR wants to reliably + * steal some physical address bits. Those design choices are in direct + * conflict. */ - if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb)) + if (!IS_ENABLED(CONFIG_ZONE_DEVICE) && (memory_tb < kaslr_regions[0].size_tb)) kaslr_regions[0].size_tb = memory_tb; /* diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index b10d4d131dce..f7546e9e8e89 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -15,7 +15,7 @@ * Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at> * * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com> - * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and + * Mostly rewritten by Thomas Gleixner <tglx@kernel.org> and * Andy Lutomirsky <luto@amacapital.net> */ #include <linux/kernel.h> diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 9fb9f3533150..6a75fe1c7a5c 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -380,7 +380,7 @@ static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from) blkg_rwstat_add_aux(&to->merged, &from->merged); blkg_rwstat_add_aux(&to->service_time, &from->service_time); blkg_rwstat_add_aux(&to->wait_time, &from->wait_time); - bfq_stat_add_aux(&from->time, &from->time); + bfq_stat_add_aux(&to->time, &from->time); bfq_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum); bfq_stat_add_aux(&to->avg_queue_size_samples, &from->avg_queue_size_samples); diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 34a498e6b2a5..355a731e2c04 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -984,7 +984,7 @@ struct bfq_group_data { * unused for the root group. Used to know whether there * are groups with more than one active @bfq_entity * (see the comments to the function - * bfq_bfqq_may_idle()). + * bfq_better_to_idle()). * @rq_pos_tree: rbtree sorted by next_request position, used when * determining if two or more queues have interleaving * requests (see bfq_find_close_cooperator()). diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c index 9850c338548d..cff025b06be1 100644 --- a/block/bio-integrity-auto.c +++ b/block/bio-integrity-auto.c @@ -140,7 +140,7 @@ bool bio_integrity_prep(struct bio *bio) return true; set_flags = false; gfp |= __GFP_ZERO; - } else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE) + } else if (bi->metadata_size > bi->pi_tuple_size) gfp |= __GFP_ZERO; break; default: diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 9b27963680dc..964eebbee14d 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -140,14 +140,21 @@ EXPORT_SYMBOL_GPL(blk_rq_integrity_map_user); bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, struct request *next) { + struct bio_integrity_payload *bip, *bip_next; + if (blk_integrity_rq(req) == 0 && blk_integrity_rq(next) == 0) return true; if (blk_integrity_rq(req) == 0 || blk_integrity_rq(next) == 0) return false; - if (bio_integrity(req->bio)->bip_flags != - bio_integrity(next->bio)->bip_flags) + bip = bio_integrity(req->bio); + bip_next = bio_integrity(next->bio); + if (bip->bip_flags != bip_next->bip_flags) + return false; + + if (bip->bip_flags & BIP_CHECK_APPTAG && + bip->app_tag != bip_next->app_tag) return false; if (req->nr_integrity_segments + next->nr_integrity_segments > @@ -163,15 +170,21 @@ bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, struct bio *bio) { + struct bio_integrity_payload *bip, *bip_bio = bio_integrity(bio); int nr_integrity_segs; - if (blk_integrity_rq(req) == 0 && bio_integrity(bio) == NULL) + if (blk_integrity_rq(req) == 0 && bip_bio == NULL) return true; - if (blk_integrity_rq(req) == 0 || bio_integrity(bio) == NULL) + if (blk_integrity_rq(req) == 0 || bip_bio == NULL) + return false; + + bip = bio_integrity(req->bio); + if (bip->bip_flags != bip_bio->bip_flags) return false; - if (bio_integrity(req->bio)->bip_flags != bio_integrity(bio)->bip_flags) + if (bip->bip_flags & BIP_CHECK_APPTAG && + bip->app_tag != bip_bio->app_tag) return false; nr_integrity_segs = blk_rq_count_integrity_sg(q, bio); diff --git a/block/blk-mq.c b/block/blk-mq.c index 1978eef95dca..968699277c3d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1480,7 +1480,7 @@ EXPORT_SYMBOL_GPL(blk_rq_is_poll); static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { - blk_hctx_poll(rq->q, rq->mq_hctx, NULL, 0); + blk_hctx_poll(rq->q, rq->mq_hctx, NULL, BLK_POLL_ONESHOT); cond_resched(); } while (!completion_done(wait)); } @@ -3721,7 +3721,7 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) struct blk_mq_hw_ctx, cpuhp_online); int ret = 0; - if (blk_mq_hctx_has_online_cpu(hctx, cpu)) + if (!hctx->nr_ctx || blk_mq_hctx_has_online_cpu(hctx, cpu)) return 0; /* @@ -4553,8 +4553,7 @@ static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, * Make sure reading the old queue_hw_ctx from other * context concurrently won't trigger uaf. */ - synchronize_rcu_expedited(); - kfree(hctxs); + kfree_rcu_mightsleep(hctxs); hctxs = new_hctxs; } diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index b538f2c0febc..a747a504fe42 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -112,29 +112,26 @@ void __rq_qos_queue_depth_changed(struct rq_qos *rqos); static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio) { - if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && - q->rq_qos) + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos) __rq_qos_cleanup(q->rq_qos, bio); } static inline void rq_qos_done(struct request_queue *q, struct request *rq) { - if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && - q->rq_qos && !blk_rq_is_passthrough(rq)) + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && + q->rq_qos && !blk_rq_is_passthrough(rq)) __rq_qos_done(q->rq_qos, rq); } static inline void rq_qos_issue(struct request_queue *q, struct request *rq) { - if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && - q->rq_qos) + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos) __rq_qos_issue(q->rq_qos, rq); } static inline void rq_qos_requeue(struct request_queue *q, struct request *rq) { - if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && - q->rq_qos) + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos) __rq_qos_requeue(q->rq_qos, rq); } @@ -162,8 +159,7 @@ static inline void rq_qos_done_bio(struct bio *bio) static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) { - if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && - q->rq_qos) { + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos) { bio_set_flag(bio, BIO_QOS_THROTTLED); __rq_qos_throttle(q->rq_qos, bio); } @@ -172,16 +168,14 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) static inline void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio) { - if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && - q->rq_qos) + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos) __rq_qos_track(q->rq_qos, rq, bio); } static inline void rq_qos_merge(struct request_queue *q, struct request *rq, struct bio *bio) { - if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && - q->rq_qos) { + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos) { bio_set_flag(bio, BIO_QOS_MERGED); __rq_qos_merge(q->rq_qos, rq, bio); } @@ -189,8 +183,7 @@ static inline void rq_qos_merge(struct request_queue *q, struct request *rq, static inline void rq_qos_queue_depth_changed(struct request_queue *q) { - if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && - q->rq_qos) + if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos) __rq_qos_queue_depth_changed(q->rq_qos); } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 1c54678fae6b..8000c94690ee 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -1957,6 +1957,7 @@ static int disk_update_zone_resources(struct gendisk *disk, disk->nr_zones = args->nr_zones; if (args->nr_conv_zones >= disk->nr_zones) { + queue_limits_cancel_update(q); pr_warn("%s: Invalid number of conventional zones %u / %u\n", disk->disk_name, args->nr_conv_zones, disk->nr_zones); ret = -ENODEV; diff --git a/crypto/authencesn.c b/crypto/authencesn.c index d1bf0fda3f2e..542a978663b9 100644 --- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -169,6 +169,9 @@ static int crypto_authenc_esn_encrypt(struct aead_request *req) struct scatterlist *src, *dst; int err; + if (assoclen < 8) + return -EINVAL; + sg_init_table(areq_ctx->src, 2); src = scatterwalk_ffwd(areq_ctx->src, req->src, assoclen); dst = src; @@ -256,6 +259,9 @@ static int crypto_authenc_esn_decrypt(struct aead_request *req) u32 tmp[2]; int err; + if (assoclen < 8) + return -EINVAL; + cryptlen -= authsize; if (req->src != dst) diff --git a/crypto/seqiv.c b/crypto/seqiv.c index 2bae99e33526..678bb4145d78 100644 --- a/crypto/seqiv.c +++ b/crypto/seqiv.c @@ -50,6 +50,7 @@ static int seqiv_aead_encrypt(struct aead_request *req) struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv); struct aead_request *subreq = aead_request_ctx(req); crypto_completion_t compl; + bool unaligned_info; void *data; u8 *info; unsigned int ivsize = 8; @@ -68,8 +69,9 @@ static int seqiv_aead_encrypt(struct aead_request *req) memcpy_sglist(req->dst, req->src, req->assoclen + req->cryptlen); - if (unlikely(!IS_ALIGNED((unsigned long)info, - crypto_aead_alignmask(geniv) + 1))) { + unaligned_info = !IS_ALIGNED((unsigned long)info, + crypto_aead_alignmask(geniv) + 1); + if (unlikely(unaligned_info)) { info = kmemdup(req->iv, ivsize, req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC); @@ -89,7 +91,7 @@ static int seqiv_aead_encrypt(struct aead_request *req) scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1); err = crypto_aead_encrypt(subreq); - if (unlikely(info != req->iv)) + if (unlikely(unaligned_info)) seqiv_aead_encrypt_complete2(req, err); return err; } diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index ad81aa03fe2f..c416942ff3e2 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -188,7 +188,7 @@ static int acpi_pci_irq_check_entry(acpi_handle handle, struct pci_dev *dev, * the IRQ value, which is hardwired to specific interrupt inputs on * the interrupt controller. */ - pr_debug("%04x:%02x:%02x[%c] -> %s[%d]\n", + pr_debug("%04x:%02x:%02x[%c] -> %s[%u]\n", entry->id.segment, entry->id.bus, entry->id.device, pin_name(entry->pin), prt->source, entry->index); @@ -384,7 +384,7 @@ static inline bool acpi_pci_irq_valid(struct pci_dev *dev, u8 pin) int acpi_pci_irq_enable(struct pci_dev *dev) { struct acpi_prt_entry *entry; - int gsi; + u32 gsi; u8 pin; int triggering = ACPI_LEVEL_SENSITIVE; /* @@ -422,18 +422,21 @@ int acpi_pci_irq_enable(struct pci_dev *dev) return 0; } + rc = -ENODEV; + if (entry) { if (entry->link) - gsi = acpi_pci_link_allocate_irq(entry->link, + rc = acpi_pci_link_allocate_irq(entry->link, entry->index, &triggering, &polarity, - &link); - else + &link, &gsi); + else { gsi = entry->index; - } else - gsi = -1; + rc = 0; + } + } - if (gsi < 0) { + if (rc < 0) { /* * No IRQ known to the ACPI subsystem - maybe the BIOS / * driver reported one, then use it. Exit in any case. diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index bed7dc85612e..b91b039a3d20 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -448,7 +448,7 @@ static int acpi_isa_irq_penalty[ACPI_MAX_ISA_IRQS] = { /* >IRQ15 */ }; -static int acpi_irq_pci_sharing_penalty(int irq) +static int acpi_irq_pci_sharing_penalty(u32 irq) { struct acpi_pci_link *link; int penalty = 0; @@ -474,7 +474,7 @@ static int acpi_irq_pci_sharing_penalty(int irq) return penalty; } -static int acpi_irq_get_penalty(int irq) +static int acpi_irq_get_penalty(u32 irq) { int penalty = 0; @@ -528,7 +528,7 @@ static int acpi_irq_balance = -1; /* 0: static, 1: balance */ static int acpi_pci_link_allocate(struct acpi_pci_link *link) { acpi_handle handle = link->device->handle; - int irq; + u32 irq; int i; if (link->irq.initialized) { @@ -598,44 +598,53 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) return 0; } -/* - * acpi_pci_link_allocate_irq - * success: return IRQ >= 0 - * failure: return -1 +/** + * acpi_pci_link_allocate_irq(): Retrieve a link device GSI + * + * @handle: Handle for the link device + * @index: GSI index + * @triggering: pointer to store the GSI trigger + * @polarity: pointer to store GSI polarity + * @name: pointer to store link device name + * @gsi: pointer to store GSI number + * + * Returns: + * 0 on success with @triggering, @polarity, @name, @gsi initialized. + * -ENODEV on failure */ int acpi_pci_link_allocate_irq(acpi_handle handle, int index, int *triggering, - int *polarity, char **name) + int *polarity, char **name, u32 *gsi) { struct acpi_device *device = acpi_fetch_acpi_dev(handle); struct acpi_pci_link *link; if (!device) { acpi_handle_err(handle, "Invalid link device\n"); - return -1; + return -ENODEV; } link = acpi_driver_data(device); if (!link) { acpi_handle_err(handle, "Invalid link context\n"); - return -1; + return -ENODEV; } /* TBD: Support multiple index (IRQ) entries per Link Device */ if (index) { acpi_handle_err(handle, "Invalid index %d\n", index); - return -1; + return -ENODEV; } mutex_lock(&acpi_link_lock); if (acpi_pci_link_allocate(link)) { mutex_unlock(&acpi_link_lock); - return -1; + return -ENODEV; } if (!link->irq.active) { mutex_unlock(&acpi_link_lock); acpi_handle_err(handle, "Link active IRQ is 0!\n"); - return -1; + return -ENODEV; } link->refcnt++; mutex_unlock(&acpi_link_lock); @@ -647,7 +656,9 @@ int acpi_pci_link_allocate_irq(acpi_handle handle, int index, int *triggering, if (name) *name = acpi_device_bid(link->device); acpi_handle_debug(handle, "Link is referenced\n"); - return link->irq.active; + *gsi = link->irq.active; + + return 0; } /* diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 6d4d06236f61..cc3c83e4cc23 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -28,6 +28,10 @@ static bool sleep_no_lps0 __read_mostly; module_param(sleep_no_lps0, bool, 0644); MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface"); +static bool check_lps0_constraints __read_mostly; +module_param(check_lps0_constraints, bool, 0644); +MODULE_PARM_DESC(check_lps0_constraints, "Check LPS0 device constraints"); + static const struct acpi_device_id lps0_device_ids[] = { {"PNP0D80", }, {"", }, @@ -515,7 +519,8 @@ static struct acpi_scan_handler lps0_handler = { static int acpi_s2idle_begin_lps0(void) { - if (pm_debug_messages_on && !lpi_constraints_table) { + if (lps0_device_handle && !sleep_no_lps0 && check_lps0_constraints && + !lpi_constraints_table) { if (acpi_s2idle_vendor_amd()) lpi_device_get_constraints_amd(); else @@ -539,7 +544,7 @@ static int acpi_s2idle_prepare_late_lps0(void) if (!lps0_device_handle || sleep_no_lps0) return 0; - if (pm_debug_messages_on) + if (check_lps0_constraints) lpi_check_constraints(); /* Screen off */ diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs index 9379038f61f5..fdd97112ef5c 100644 --- a/drivers/android/binder/page_range.rs +++ b/drivers/android/binder/page_range.rs @@ -727,8 +727,5 @@ unsafe extern "C" fn rust_shrink_free_page( drop(mm); drop(page); - // SAFETY: We just unlocked the lru lock, but it should be locked when we return. - unsafe { bindings::spin_lock(&raw mut (*lru).lock) }; - LRU_REMOVED_ENTRY } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 7a7f88b3fa2b..931d0081169b 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -2094,13 +2094,13 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ap->flags & ATA_FLAG_EM) ap->em_message_type = hpriv->em_msg_type; - ahci_mark_external_port(ap); - - ahci_update_initial_lpm_policy(ap); - /* disabled/not-implemented port */ - if (!(hpriv->port_map & (1 << i))) + if (!(hpriv->port_map & (1 << i))) { ap->ops = &ata_dummy_port_ops; + } else { + ahci_mark_external_port(ap); + ahci_update_initial_lpm_policy(ap); + } } /* apply workaround for ASUS P5W DH Deluxe mainboard */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 09d8c035fcdf..ddf9a7b28a59 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2872,7 +2872,8 @@ static void ata_dev_config_lpm(struct ata_device *dev) static void ata_dev_print_features(struct ata_device *dev) { - if (!(dev->flags & ATA_DFLAG_FEATURES_MASK)) + if (!(dev->flags & ATA_DFLAG_FEATURES_MASK) && !dev->cpr_log && + !ata_id_has_hipm(dev->id) && !ata_id_has_dipm(dev->id)) return; ata_dev_info(dev, @@ -3116,6 +3117,11 @@ int ata_dev_configure(struct ata_device *dev) ata_mode_string(xfer_mask), cdb_intr_string, atapi_an_string, dma_dir_string); + + ata_dev_config_lpm(dev); + + if (print_info) + ata_dev_print_features(dev); } /* determine max_sectors */ diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index b2817a2995d6..04e1e774645e 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -909,7 +909,7 @@ static bool ata_scsi_lpm_supported(struct ata_port *ap) struct ata_link *link; struct ata_device *dev; - if (ap->flags & ATA_FLAG_NO_LPM) + if ((ap->flags & ATA_FLAG_NO_LPM) || !ap->ops->set_lpm) return false; ata_for_each_link(link, ap, EDGE) { diff --git a/drivers/atm/he.c b/drivers/atm/he.c index ad91cc6a34fc..92a041d5387b 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -1587,7 +1587,8 @@ he_stop(struct he_dev *he_dev) he_dev->tbrq_base, he_dev->tbrq_phys); if (he_dev->tpdrq_base) - dma_free_coherent(&he_dev->pci_dev->dev, CONFIG_TBRQ_SIZE * sizeof(struct he_tbrq), + dma_free_coherent(&he_dev->pci_dev->dev, + CONFIG_TPDRQ_SIZE * sizeof(struct he_tpdrq), he_dev->tpdrq_base, he_dev->tpdrq_phys); dma_pool_destroy(he_dev->tpd_pool); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 349f31bedfa1..bea8da5f8a3a 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -548,6 +548,8 @@ static DEVICE_ATTR_RW(state_synced); static void device_unbind_cleanup(struct device *dev) { devres_release_all(dev); + if (dev->driver->p_cb.post_unbind_rust) + dev->driver->p_cb.post_unbind_rust(dev); arch_teardown_dma_ops(dev); kfree(dev->dma_range_map); dev->dma_range_map = NULL; diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index ca1c72b68f31..4134a77ae1d6 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -95,12 +95,13 @@ static int regcache_maple_write(struct regmap *map, unsigned int reg, mas_unlock(&mas); - if (ret == 0) { - kfree(lower); - kfree(upper); + if (ret) { + kfree(entry); + return ret; } - - return ret; + kfree(lower); + kfree(upper); + return 0; } static int regcache_maple_drop(struct regmap *map, unsigned int min, diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index ce9be3989a21..ae2215d4e61c 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -408,9 +408,11 @@ static void regmap_lock_hwlock_irq(void *__map) static void regmap_lock_hwlock_irqsave(void *__map) { struct regmap *map = __map; + unsigned long flags = 0; hwspin_lock_timeout_irqsave(map->hwlock, UINT_MAX, - &map->spinlock_flags); + &flags); + map->spinlock_flags = flags; } static void regmap_unlock_hwlock(void *__map) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 32a3a5b13802..bd59c0e9508b 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1225,16 +1225,28 @@ static int loop_clr_fd(struct loop_device *lo) } static int -loop_set_status(struct loop_device *lo, const struct loop_info64 *info) +loop_set_status(struct loop_device *lo, blk_mode_t mode, + struct block_device *bdev, const struct loop_info64 *info) { int err; bool partscan = false; bool size_changed = false; unsigned int memflags; + /* + * If we don't hold exclusive handle for the device, upgrade to it + * here to avoid changing device under exclusive owner. + */ + if (!(mode & BLK_OPEN_EXCL)) { + err = bd_prepare_to_claim(bdev, loop_set_status, NULL); + if (err) + goto out_reread_partitions; + } + err = mutex_lock_killable(&lo->lo_mutex); if (err) - return err; + goto out_abort_claiming; + if (lo->lo_state != Lo_bound) { err = -ENXIO; goto out_unlock; @@ -1273,6 +1285,10 @@ out_unfreeze: } out_unlock: mutex_unlock(&lo->lo_mutex); +out_abort_claiming: + if (!(mode & BLK_OPEN_EXCL)) + bd_abort_claiming(bdev, loop_set_status); +out_reread_partitions: if (partscan) loop_reread_partitions(lo); @@ -1352,7 +1368,9 @@ loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info) } static int -loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg) +loop_set_status_old(struct loop_device *lo, blk_mode_t mode, + struct block_device *bdev, + const struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; @@ -1360,17 +1378,19 @@ loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg) if (copy_from_user(&info, arg, sizeof (struct loop_info))) return -EFAULT; loop_info64_from_old(&info, &info64); - return loop_set_status(lo, &info64); + return loop_set_status(lo, mode, bdev, &info64); } static int -loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg) +loop_set_status64(struct loop_device *lo, blk_mode_t mode, + struct block_device *bdev, + const struct loop_info64 __user *arg) { struct loop_info64 info64; if (copy_from_user(&info64, arg, sizeof (struct loop_info64))) return -EFAULT; - return loop_set_status(lo, &info64); + return loop_set_status(lo, mode, bdev, &info64); } static int @@ -1549,14 +1569,14 @@ static int lo_ioctl(struct block_device *bdev, blk_mode_t mode, case LOOP_SET_STATUS: err = -EPERM; if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_status_old(lo, argp); + err = loop_set_status_old(lo, mode, bdev, argp); break; case LOOP_GET_STATUS: return loop_get_status_old(lo, argp); case LOOP_SET_STATUS64: err = -EPERM; if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_status64(lo, argp); + err = loop_set_status64(lo, mode, bdev, argp); break; case LOOP_GET_STATUS64: return loop_get_status64(lo, argp); @@ -1650,8 +1670,9 @@ loop_info64_to_compat(const struct loop_info64 *info64, } static int -loop_set_status_compat(struct loop_device *lo, - const struct compat_loop_info __user *arg) +loop_set_status_compat(struct loop_device *lo, blk_mode_t mode, + struct block_device *bdev, + const struct compat_loop_info __user *arg) { struct loop_info64 info64; int ret; @@ -1659,7 +1680,7 @@ loop_set_status_compat(struct loop_device *lo, ret = loop_info64_from_compat(arg, &info64); if (ret < 0) return ret; - return loop_set_status(lo, &info64); + return loop_set_status(lo, mode, bdev, &info64); } static int @@ -1685,7 +1706,7 @@ static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode, switch(cmd) { case LOOP_SET_STATUS: - err = loop_set_status_compat(lo, + err = loop_set_status_compat(lo, mode, bdev, (const struct compat_loop_info __user *)arg); break; case LOOP_GET_STATUS: diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index c7c0fb79a6bf..4c0632ab4e1b 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -665,12 +665,22 @@ static void nullb_add_fault_config(struct nullb_device *dev) configfs_add_default_group(&dev->init_hctx_fault_config.group, &dev->group); } +static void nullb_del_fault_config(struct nullb_device *dev) +{ + config_item_put(&dev->init_hctx_fault_config.group.cg_item); + config_item_put(&dev->requeue_config.group.cg_item); + config_item_put(&dev->timeout_config.group.cg_item); +} + #else static void nullb_add_fault_config(struct nullb_device *dev) { } +static void nullb_del_fault_config(struct nullb_device *dev) +{ +} #endif static struct @@ -702,7 +712,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item) null_del_dev(dev->nullb); mutex_unlock(&lock); } - + nullb_del_fault_config(dev); config_item_put(item); } diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index d1c354636315..8194a970f002 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1662,7 +1662,6 @@ static void destroy_sysfs(struct rnbd_clt_dev *dev, /* To avoid deadlock firstly remove itself */ sysfs_remove_file_self(&dev->kobj, sysfs_self); kobject_del(&dev->kobj); - kobject_put(&dev->kobj); } } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 49c208457198..cd1e84653002 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -237,6 +237,7 @@ struct ublk_device { bool canceling; pid_t ublksrv_tgid; struct delayed_work exit_work; + struct work_struct partition_scan_work; struct ublk_queue *queues[]; }; @@ -1582,6 +1583,27 @@ static void ublk_put_disk(struct gendisk *disk) put_device(disk_to_dev(disk)); } +static void ublk_partition_scan_work(struct work_struct *work) +{ + struct ublk_device *ub = + container_of(work, struct ublk_device, partition_scan_work); + /* Hold disk reference to prevent UAF during concurrent teardown */ + struct gendisk *disk = ublk_get_disk(ub); + + if (!disk) + return; + + if (WARN_ON_ONCE(!test_and_clear_bit(GD_SUPPRESS_PART_SCAN, + &disk->state))) + goto out; + + mutex_lock(&disk->open_mutex); + bdev_disk_changed(disk, false); + mutex_unlock(&disk->open_mutex); +out: + ublk_put_disk(disk); +} + /* * Use this function to ensure that ->canceling is consistently set for * the device and all queues. Do not set these flags directly. @@ -2026,6 +2048,7 @@ static void ublk_stop_dev(struct ublk_device *ub) mutex_lock(&ub->mutex); ublk_stop_dev_unlocked(ub); mutex_unlock(&ub->mutex); + cancel_work_sync(&ub->partition_scan_work); ublk_cancel_dev(ub); } @@ -2862,6 +2885,15 @@ static struct ublk_device *ublk_get_device_from_id(int idx) return ub; } +static bool ublk_validate_user_pid(struct ublk_device *ub, pid_t ublksrv_pid) +{ + rcu_read_lock(); + ublksrv_pid = pid_nr(find_vpid(ublksrv_pid)); + rcu_read_unlock(); + + return ub->ublksrv_tgid == ublksrv_pid; +} + static int ublk_ctrl_start_dev(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) { @@ -2930,7 +2962,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, if (wait_for_completion_interruptible(&ub->completion) != 0) return -EINTR; - if (ub->ublksrv_tgid != ublksrv_pid) + if (!ublk_validate_user_pid(ub, ublksrv_pid)) return -EINVAL; mutex_lock(&ub->mutex); @@ -2949,14 +2981,22 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, disk->fops = &ub_fops; disk->private_data = ub; - ub->dev_info.ublksrv_pid = ublksrv_pid; + ub->dev_info.ublksrv_pid = ub->ublksrv_tgid; ub->ub_disk = disk; ublk_apply_params(ub); - /* don't probe partitions if any daemon task is un-trusted */ - if (ub->unprivileged_daemons) - set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); + /* + * Suppress partition scan to avoid potential IO hang. + * + * If ublk server error occurs during partition scan, the IO may + * wait while holding ub->mutex, which can deadlock with other + * operations that need the mutex. Defer partition scan to async + * work. + * For unprivileged daemons, keep GD_SUPPRESS_PART_SCAN set + * permanently. + */ + set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); ublk_get_device(ub); ub->dev_info.state = UBLK_S_DEV_LIVE; @@ -2973,6 +3013,10 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, set_bit(UB_STATE_USED, &ub->state); + /* Schedule async partition scan for trusted daemons */ + if (!ub->unprivileged_daemons) + schedule_work(&ub->partition_scan_work); + out_put_cdev: if (ret) { ublk_detach_disk(ub); @@ -3138,6 +3182,7 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) mutex_init(&ub->mutex); spin_lock_init(&ub->lock); mutex_init(&ub->cancel_mutex); + INIT_WORK(&ub->partition_scan_work, ublk_partition_scan_work); ret = ublk_alloc_dev_number(ub, header->dev_id); if (ret < 0) @@ -3284,12 +3329,32 @@ static int ublk_ctrl_stop_dev(struct ublk_device *ub) static int ublk_ctrl_get_dev_info(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) { + struct task_struct *p; + struct pid *pid; + struct ublksrv_ctrl_dev_info dev_info; + pid_t init_ublksrv_tgid = ub->dev_info.ublksrv_pid; void __user *argp = (void __user *)(unsigned long)header->addr; if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr) return -EINVAL; - if (copy_to_user(argp, &ub->dev_info, sizeof(ub->dev_info))) + memcpy(&dev_info, &ub->dev_info, sizeof(dev_info)); + dev_info.ublksrv_pid = -1; + + if (init_ublksrv_tgid > 0) { + rcu_read_lock(); + pid = find_pid_ns(init_ublksrv_tgid, &init_pid_ns); + p = pid_task(pid, PIDTYPE_TGID); + if (p) { + int vnr = task_tgid_vnr(p); + + if (vnr) + dev_info.ublksrv_pid = vnr; + } + rcu_read_unlock(); + } + + if (copy_to_user(argp, &dev_info, sizeof(dev_info))) return -EFAULT; return 0; @@ -3434,7 +3499,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, pr_devel("%s: All FETCH_REQs received, dev id %d\n", __func__, header->dev_id); - if (ub->ublksrv_tgid != ublksrv_pid) + if (!ublk_validate_user_pid(ub, ublksrv_pid)) return -EINVAL; mutex_lock(&ub->mutex); @@ -3445,7 +3510,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, ret = -EBUSY; goto out_unlock; } - ub->dev_info.ublksrv_pid = ublksrv_pid; + ub->dev_info.ublksrv_pid = ub->ublksrv_tgid; ub->dev_info.state = UBLK_S_DEV_LIVE; pr_devel("%s: new ublksrv_pid %d, dev id %d\n", __func__, ublksrv_pid, header->dev_id); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 8ed3883ab8ee..ded09e94d296 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4052,7 +4052,7 @@ static int btusb_probe(struct usb_interface *intf, return -ENODEV; } - data = devm_kzalloc(&intf->dev, sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -4075,8 +4075,10 @@ static int btusb_probe(struct usb_interface *intf, } } - if (!data->intr_ep || !data->bulk_tx_ep || !data->bulk_rx_ep) + if (!data->intr_ep || !data->bulk_tx_ep || !data->bulk_rx_ep) { + kfree(data); return -ENODEV; + } if (id->driver_info & BTUSB_AMP) { data->cmdreq_type = USB_TYPE_CLASS | 0x01; @@ -4131,8 +4133,10 @@ static int btusb_probe(struct usb_interface *intf, data->recv_acl = hci_recv_frame; hdev = hci_alloc_dev_priv(priv_size); - if (!hdev) + if (!hdev) { + kfree(data); return -ENOMEM; + } hdev->bus = HCI_USB; hci_set_drvdata(hdev, data); @@ -4406,6 +4410,7 @@ out_free_dev: if (data->reset_gpio) gpiod_put(data->reset_gpio); hci_free_dev(hdev); + kfree(data); return err; } @@ -4454,6 +4459,7 @@ static void btusb_disconnect(struct usb_interface *intf) } hci_free_dev(hdev); + kfree(data); } #ifdef CONFIG_PM diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index d0adae3267b4..2b28515de92c 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -685,6 +685,8 @@ static int hci_uart_register_dev(struct hci_uart *hu) return err; } + set_bit(HCI_UART_PROTO_INIT, &hu->flags); + if (test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return 0; @@ -712,8 +714,6 @@ static int hci_uart_set_proto(struct hci_uart *hu, int id) hu->proto = p; - set_bit(HCI_UART_PROTO_INIT, &hu->flags); - err = hci_uart_register_dev(hu); if (err) { return err; diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 4d7cf338824a..cfc4d83c42c0 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -50,8 +50,9 @@ static int riscv_clock_next_event(unsigned long delta, if (static_branch_likely(&riscv_sstc_available)) { #if defined(CONFIG_32BIT) - csr_write(CSR_STIMECMP, next_tval & 0xFFFFFFFF); + csr_write(CSR_STIMECMP, ULONG_MAX); csr_write(CSR_STIMECMPH, next_tval >> 32); + csr_write(CSR_STIMECMP, next_tval & 0xFFFFFFFF); #else csr_write(CSR_STIMECMP, next_tval); #endif diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index 657c98cd723e..2c3eb9e89571 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -1155,7 +1155,7 @@ static int do_chaninfo_ioctl(struct comedi_device *dev, for (i = 0; i < s->n_chan; i++) { int x; - x = (dev->minor << 28) | (it->subdev << 24) | (i << 16) | + x = (it->subdev << 24) | (i << 16) | (s->range_table_list[i]->length); if (put_user(x, it->rangelist + i)) return -EFAULT; diff --git a/drivers/comedi/drivers/dmm32at.c b/drivers/comedi/drivers/dmm32at.c index 644e3b643c79..910cd24b1bed 100644 --- a/drivers/comedi/drivers/dmm32at.c +++ b/drivers/comedi/drivers/dmm32at.c @@ -330,6 +330,7 @@ static int dmm32at_ai_cmdtest(struct comedi_device *dev, static void dmm32at_setaitimer(struct comedi_device *dev, unsigned int nansec) { + unsigned long irq_flags; unsigned char lo1, lo2, hi2; unsigned short both2; @@ -342,6 +343,9 @@ static void dmm32at_setaitimer(struct comedi_device *dev, unsigned int nansec) /* set counter clocks to 10MHz, disable all aux dio */ outb(0, dev->iobase + DMM32AT_CTRDIO_CFG_REG); + /* serialize access to control register and paged registers */ + spin_lock_irqsave(&dev->spinlock, irq_flags); + /* get access to the clock regs */ outb(DMM32AT_CTRL_PAGE_8254, dev->iobase + DMM32AT_CTRL_REG); @@ -354,6 +358,8 @@ static void dmm32at_setaitimer(struct comedi_device *dev, unsigned int nansec) outb(lo2, dev->iobase + DMM32AT_CLK2); outb(hi2, dev->iobase + DMM32AT_CLK2); + spin_unlock_irqrestore(&dev->spinlock, irq_flags); + /* enable the ai conversion interrupt and the clock to start scans */ outb(DMM32AT_INTCLK_ADINT | DMM32AT_INTCLK_CLKEN | DMM32AT_INTCLK_CLKSEL, @@ -363,13 +369,19 @@ static void dmm32at_setaitimer(struct comedi_device *dev, unsigned int nansec) static int dmm32at_ai_cmd(struct comedi_device *dev, struct comedi_subdevice *s) { struct comedi_cmd *cmd = &s->async->cmd; + unsigned long irq_flags; int ret; dmm32at_ai_set_chanspec(dev, s, cmd->chanlist[0], cmd->chanlist_len); + /* serialize access to control register and paged registers */ + spin_lock_irqsave(&dev->spinlock, irq_flags); + /* reset the interrupt just in case */ outb(DMM32AT_CTRL_INTRST, dev->iobase + DMM32AT_CTRL_REG); + spin_unlock_irqrestore(&dev->spinlock, irq_flags); + /* * wait for circuit to settle * we don't have the 'insn' here but it's not needed @@ -429,8 +441,13 @@ static irqreturn_t dmm32at_isr(int irq, void *d) comedi_handle_events(dev, s); } + /* serialize access to control register and paged registers */ + spin_lock(&dev->spinlock); + /* reset the interrupt */ outb(DMM32AT_CTRL_INTRST, dev->iobase + DMM32AT_CTRL_REG); + + spin_unlock(&dev->spinlock); return IRQ_HANDLED; } @@ -481,14 +498,25 @@ static int dmm32at_ao_insn_write(struct comedi_device *dev, static int dmm32at_8255_io(struct comedi_device *dev, int dir, int port, int data, unsigned long regbase) { + unsigned long irq_flags; + int ret; + + /* serialize access to control register and paged registers */ + spin_lock_irqsave(&dev->spinlock, irq_flags); + /* get access to the DIO regs */ outb(DMM32AT_CTRL_PAGE_8255, dev->iobase + DMM32AT_CTRL_REG); if (dir) { outb(data, dev->iobase + regbase + port); - return 0; + ret = 0; + } else { + ret = inb(dev->iobase + regbase + port); } - return inb(dev->iobase + regbase + port); + + spin_unlock_irqrestore(&dev->spinlock, irq_flags); + + return ret; } /* Make sure the board is there and put it to a known state */ diff --git a/drivers/comedi/range.c b/drivers/comedi/range.c index 8f43cf88d784..5b8f662365e3 100644 --- a/drivers/comedi/range.c +++ b/drivers/comedi/range.c @@ -52,7 +52,7 @@ int do_rangeinfo_ioctl(struct comedi_device *dev, const struct comedi_lrange *lr; struct comedi_subdevice *s; - subd = (it->range_type >> 24) & 0xf; + subd = (it->range_type >> 24) & 0xff; chan = (it->range_type >> 16) & 0xff; if (!dev->attached) diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index ce81fc4e1ae7..573b2fe93253 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -1192,6 +1192,7 @@ static irqreturn_t quad8_irq_handler(int irq, void *private) { struct counter_device *counter = private; struct quad8 *const priv = counter_priv(counter); + struct device *dev = counter->parent; unsigned int status; unsigned long irq_status; unsigned long channel; @@ -1200,8 +1201,11 @@ static irqreturn_t quad8_irq_handler(int irq, void *private) int ret; ret = regmap_read(priv->map, QUAD8_INTERRUPT_STATUS, &status); - if (ret) - return ret; + if (ret) { + dev_WARN_ONCE(dev, true, + "Attempt to read Interrupt Status Register failed: %d\n", ret); + return IRQ_NONE; + } if (!status) return IRQ_NONE; @@ -1223,8 +1227,9 @@ static irqreturn_t quad8_irq_handler(int irq, void *private) break; default: /* should never reach this path */ - WARN_ONCE(true, "invalid interrupt trigger function %u configured for channel %lu\n", - flg_pins, channel); + dev_WARN_ONCE(dev, true, + "invalid interrupt trigger function %u configured for channel %lu\n", + flg_pins, channel); continue; } @@ -1232,8 +1237,11 @@ static irqreturn_t quad8_irq_handler(int irq, void *private) } ret = regmap_write(priv->map, QUAD8_CHANNEL_OPERATION, CLEAR_PENDING_INTERRUPTS); - if (ret) - return ret; + if (ret) { + dev_WARN_ONCE(dev, true, + "Attempt to clear pending interrupts by writing to Channel Operation Register failed: %d\n", ret); + return IRQ_HANDLED; + } return IRQ_HANDLED; } diff --git a/drivers/counter/interrupt-cnt.c b/drivers/counter/interrupt-cnt.c index 6c0c1d2d7027..e6100b5fb082 100644 --- a/drivers/counter/interrupt-cnt.c +++ b/drivers/counter/interrupt-cnt.c @@ -229,8 +229,7 @@ static int interrupt_cnt_probe(struct platform_device *pdev) irq_set_status_flags(priv->irq, IRQ_NOAUTOEN); ret = devm_request_irq(dev, priv->irq, interrupt_cnt_isr, - IRQF_TRIGGER_RISING | IRQF_NO_THREAD, - dev_name(dev), counter); + IRQF_TRIGGER_RISING, dev_name(dev), counter); if (ret) return ret; diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index 81e16b5a0245..b8081acba928 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -263,6 +263,7 @@ static const struct of_device_id qcom_cpufreq_ipq806x_match_list[] __maybe_unuse { .compatible = "qcom,ipq8066", .data = (const void *)QCOM_ID_IPQ8066 }, { .compatible = "qcom,ipq8068", .data = (const void *)QCOM_ID_IPQ8068 }, { .compatible = "qcom,ipq8069", .data = (const void *)QCOM_ID_IPQ8069 }, + { /* sentinel */ } }; static int qcom_cpufreq_ipq8064_name_version(struct device *cpu_dev, diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index f8bfff5dd0bd..d47bf06a90f7 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -991,7 +991,7 @@ static void qm_get_complete_eqe_num(struct hisi_qm *qm) return; poll_data = &qm->poll_data[cqn]; - while (QM_EQE_PHASE(dw0) != qm->status.eqc_phase) { + do { poll_data->qp_finish_id[eqe_num] = dw0 & QM_EQE_CQN_MASK; eqe_num++; @@ -1004,11 +1004,10 @@ static void qm_get_complete_eqe_num(struct hisi_qm *qm) qm->status.eq_head++; } - if (eqe_num == (eq_depth >> 1) - 1) - break; - dw0 = le32_to_cpu(eqe->dw0); - } + if (QM_EQE_PHASE(dw0) != qm->status.eqc_phase) + break; + } while (eqe_num < (eq_depth >> 1) - 1); poll_data->eqe_num = eqe_num; queue_work(qm->wq, &poll_data->work); diff --git a/drivers/crypto/intel/qat/qat_common/adf_aer.c b/drivers/crypto/intel/qat/qat_common/adf_aer.c index 11728cf32653..a5964fd8204c 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_aer.c +++ b/drivers/crypto/intel/qat/qat_common/adf_aer.c @@ -41,8 +41,6 @@ static pci_ers_result_t adf_error_detected(struct pci_dev *pdev, adf_error_notifier(accel_dev); adf_pf2vf_notify_fatal_error(accel_dev); adf_dev_restarting_notify(accel_dev); - adf_pf2vf_notify_restarting(accel_dev); - adf_pf2vf_wait_for_restarting_complete(accel_dev); pci_clear_master(pdev); adf_dev_down(accel_dev); diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 77ac940e3013..49bba2b9a3c4 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -75,9 +75,16 @@ EXPORT_SYMBOL_FOR_MODULES(cxl_do_xormap_calc, "cxl_translate"); static u64 cxl_apply_xor_maps(struct cxl_root_decoder *cxlrd, u64 addr) { - struct cxl_cxims_data *cximsd = cxlrd->platform_data; + int hbiw = cxlrd->cxlsd.nr_targets; + struct cxl_cxims_data *cximsd; + + /* No xormaps for host bridge interleave ways of 1 or 3 */ + if (hbiw == 1 || hbiw == 3) + return addr; + + cximsd = cxlrd->platform_data; - return cxl_do_xormap_calc(cximsd, addr, cxlrd->cxlsd.nr_targets); + return cxl_do_xormap_calc(cximsd, addr, hbiw); } struct cxl_cxims_context { diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 1c5d2022c87a..eb5a3a7640c6 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -403,7 +403,7 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, * is not set. */ if (cxled->part < 0) - for (int i = 0; cxlds->nr_partitions; i++) + for (int i = 0; i < cxlds->nr_partitions; i++) if (resource_contains(&cxlds->part[i].res, res)) { cxled->part = i; break; @@ -530,7 +530,7 @@ resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled) resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled) { - resource_size_t base = -1; + resource_size_t base = RESOURCE_SIZE_MAX; lockdep_assert_held(&cxl_rwsem.dpa); if (cxled->dpa_res) diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index fef3aa0c6680..3310dbfae9d6 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -1590,7 +1590,7 @@ static int update_decoder_targets(struct device *dev, void *data) cxlsd->target[i] = dport; dev_dbg(dev, "dport%d found in target list, index %d\n", dport->port_id, i); - return 1; + return 0; } } diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index ae899f68551f..5bd1213737fa 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -759,7 +759,7 @@ static ssize_t extended_linear_cache_size_show(struct device *dev, ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; - return sysfs_emit(buf, "%#llx\n", p->cache_size); + return sysfs_emit(buf, "%pap\n", &p->cache_size); } static DEVICE_ATTR_RO(extended_linear_cache_size); @@ -3118,7 +3118,7 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); struct cxl_region_params *p = &cxlr->params; struct cxl_endpoint_decoder *cxled = NULL; - u64 dpa_offset, hpa_offset, hpa; + u64 base, dpa_offset, hpa_offset, hpa; u16 eig = 0; u8 eiw = 0; int pos; @@ -3136,8 +3136,14 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, ways_to_eiw(p->interleave_ways, &eiw); granularity_to_eig(p->interleave_granularity, &eig); - dpa_offset = dpa - cxl_dpa_resource_start(cxled); + base = cxl_dpa_resource_start(cxled); + if (base == RESOURCE_SIZE_MAX) + return ULLONG_MAX; + + dpa_offset = dpa - base; hpa_offset = cxl_calculate_hpa_offset(dpa_offset, pos, eiw, eig); + if (hpa_offset == ULLONG_MAX) + return ULLONG_MAX; /* Apply the hpa_offset to the region base address */ hpa = hpa_offset + p->res->start + p->cache_size; @@ -3146,6 +3152,9 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, if (cxlrd->ops.hpa_to_spa) hpa = cxlrd->ops.hpa_to_spa(cxlrd, hpa); + if (hpa == ULLONG_MAX) + return ULLONG_MAX; + if (!cxl_resource_contains_addr(p->res, hpa)) { dev_dbg(&cxlr->dev, "Addr trans fail: hpa 0x%llx not in region\n", hpa); @@ -3170,7 +3179,8 @@ static int region_offset_to_dpa_result(struct cxl_region *cxlr, u64 offset, struct cxl_region_params *p = &cxlr->params; struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); struct cxl_endpoint_decoder *cxled; - u64 hpa, hpa_offset, dpa_offset; + u64 hpa_offset = offset; + u64 dpa, dpa_offset; u16 eig = 0; u8 eiw = 0; int pos; @@ -3187,10 +3197,13 @@ static int region_offset_to_dpa_result(struct cxl_region *cxlr, u64 offset, * CXL HPA is assumed to equal SPA. */ if (cxlrd->ops.spa_to_hpa) { - hpa = cxlrd->ops.spa_to_hpa(cxlrd, p->res->start + offset); - hpa_offset = hpa - p->res->start; - } else { - hpa_offset = offset; + hpa_offset = cxlrd->ops.spa_to_hpa(cxlrd, p->res->start + offset); + if (hpa_offset == ULLONG_MAX) { + dev_dbg(&cxlr->dev, "HPA not found for %pr offset %#llx\n", + p->res, offset); + return -ENXIO; + } + hpa_offset -= p->res->start; } pos = cxl_calculate_position(hpa_offset, eiw, eig); @@ -3207,8 +3220,13 @@ static int region_offset_to_dpa_result(struct cxl_region *cxlr, u64 offset, cxled = p->targets[i]; if (cxled->pos != pos) continue; + + dpa = cxl_dpa_resource_start(cxled); + if (dpa != RESOURCE_SIZE_MAX) + dpa += dpa_offset; + result->cxlmd = cxled_to_memdev(cxled); - result->dpa = cxl_dpa_resource_start(cxled) + dpa_offset; + result->dpa = dpa; return 0; } diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index 0867115aeef2..c6ae27c982f4 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -67,14 +67,16 @@ struct dev_dax_range { /** * struct dev_dax - instance data for a subdivision of a dax region, and * data while the device is activated in the driver. - * @region - parent region - * @dax_dev - core dax functionality + * @region: parent region + * @dax_dev: core dax functionality + * @align: alignment of this instance * @target_node: effective numa node if dev_dax memory range is onlined * @dyn_id: is this a dynamic or statically created instance * @id: ida allocated id when the dax_region is not static * @ida: mapping id allocator - * @dev - device core - * @pgmap - pgmap for memmap setup / lifetime (driver owned) + * @dev: device core + * @pgmap: pgmap for memmap setup / lifetime (driver owned) + * @memmap_on_memory: allow kmem to put the memmap in the memory * @nr_range: size of @ranges * @ranges: range tuples of memory used */ diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index bd49f0374291..04bbd774b3b4 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -936,6 +936,7 @@ static void admac_remove(struct platform_device *pdev) } static const struct of_device_id admac_of_match[] = { + { .compatible = "apple,t8103-admac", }, { .compatible = "apple,admac", }, { } }; diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 7d226453961f..22bb604a3f97 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -1765,6 +1765,7 @@ static int atc_alloc_chan_resources(struct dma_chan *chan) static void atc_free_chan_resources(struct dma_chan *chan) { struct at_dma_chan *atchan = to_at_dma_chan(chan); + struct at_dma_slave *atslave; BUG_ON(atc_chan_is_enabled(atchan)); @@ -1774,8 +1775,12 @@ static void atc_free_chan_resources(struct dma_chan *chan) /* * Free atslave allocated in at_dma_xlate() */ - kfree(chan->private); - chan->private = NULL; + atslave = chan->private; + if (atslave) { + put_device(atslave->dma_dev); + kfree(atslave); + chan->private = NULL; + } dev_vdbg(chan2dev(chan), "free_chan_resources: done\n"); } diff --git a/drivers/dma/bcm-sba-raid.c b/drivers/dma/bcm-sba-raid.c index 7f0e76439ce5..ed037fa883f6 100644 --- a/drivers/dma/bcm-sba-raid.c +++ b/drivers/dma/bcm-sba-raid.c @@ -1699,7 +1699,7 @@ static int sba_probe(struct platform_device *pdev) /* Prealloc channel resource */ ret = sba_prealloc_channel_resources(sba); if (ret) - goto fail_free_mchan; + goto fail_put_mbox; /* Check availability of debugfs */ if (!debugfs_initialized()) @@ -1729,6 +1729,8 @@ skip_debugfs: fail_free_resources: debugfs_remove_recursive(sba->root); sba_freeup_channel_resources(sba); +fail_put_mbox: + put_device(sba->mbox_dev); fail_free_mchan: mbox_free_channel(sba->mchan); return ret; @@ -1744,6 +1746,8 @@ static void sba_remove(struct platform_device *pdev) sba_freeup_channel_resources(sba); + put_device(sba->mbox_dev); + mbox_free_channel(sba->mchan); } diff --git a/drivers/dma/cv1800b-dmamux.c b/drivers/dma/cv1800b-dmamux.c index e900d6595617..f7a952fcbc7d 100644 --- a/drivers/dma/cv1800b-dmamux.c +++ b/drivers/dma/cv1800b-dmamux.c @@ -102,11 +102,11 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, struct llist_node *node; unsigned long flags; unsigned int chid, devid, cpuid; - int ret; + int ret = -EINVAL; if (dma_spec->args_count != DMAMUX_NCELLS) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } devid = dma_spec->args[0]; @@ -115,18 +115,18 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (devid > MAX_DMA_MAPPING_ID) { dev_err(&pdev->dev, "invalid device id: %u\n", devid); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (cpuid > MAX_DMA_CPU_ID) { dev_err(&pdev->dev, "invalid cpu id: %u\n", cpuid); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } 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"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -136,8 +136,6 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (map->peripheral == devid && map->cpu == cpuid) goto found; } - - ret = -EINVAL; goto failed; } else { node = llist_del_first(&dmamux->free_maps); @@ -171,12 +169,17 @@ found: dev_dbg(&pdev->dev, "register channel %u for req %u (cpu %u)\n", chid, devid, cpuid); + put_device(&pdev->dev); + return map; failed: spin_unlock_irqrestore(&dmamux->lock, flags); of_node_put(dma_spec->np); dev_err(&pdev->dev, "errno %d\n", ret); +err_put_pdev: + put_device(&pdev->dev); + return ERR_PTR(ret); } diff --git a/drivers/dma/dw/rzn1-dmamux.c b/drivers/dma/dw/rzn1-dmamux.c index deadf135681b..cbec277af4dd 100644 --- a/drivers/dma/dw/rzn1-dmamux.c +++ b/drivers/dma/dw/rzn1-dmamux.c @@ -90,7 +90,7 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (test_and_set_bit(map->req_idx, dmamux->used_chans)) { ret = -EBUSY; - goto free_map; + goto put_dma_spec_np; } mask = BIT(map->req_idx); @@ -103,6 +103,8 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, clear_bitmap: clear_bit(map->req_idx, dmamux->used_chans); +put_dma_spec_np: + of_node_put(dma_spec->np); free_map: kfree(map); put_device: diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index a59212758029..7137f51ff6a0 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -873,6 +873,7 @@ err_errirq: free_irq(fsl_chan->txirq, fsl_chan); err_txirq: dma_pool_destroy(fsl_chan->tcd_pool); + clk_disable_unprepare(fsl_chan->clk); return ret; } diff --git a/drivers/dma/idxd/compat.c b/drivers/dma/idxd/compat.c index eff9943f1a42..95b8ef958633 100644 --- a/drivers/dma/idxd/compat.c +++ b/drivers/dma/idxd/compat.c @@ -20,11 +20,16 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf, size_t c int rc = -ENODEV; dev = bus_find_device_by_name(bus, NULL, buf); - if (dev && dev->driver) { + if (!dev) + return -ENODEV; + + if (dev->driver) { device_driver_detach(dev); rc = count; } + put_device(dev); + return rc; } static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, 0200, NULL, unbind_store); @@ -38,9 +43,12 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t cou struct idxd_dev *idxd_dev; dev = bus_find_device_by_name(bus, NULL, buf); - if (!dev || dev->driver || drv != &dsa_drv.drv) + if (!dev) return -ENODEV; + if (dev->driver || drv != &dsa_drv.drv) + goto err_put_dev; + idxd_dev = confdev_to_idxd_dev(dev); if (is_idxd_dev(idxd_dev)) { alt_drv = driver_find("idxd", bus); @@ -53,13 +61,20 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t cou alt_drv = driver_find("user", bus); } if (!alt_drv) - return -ENODEV; + goto err_put_dev; rc = device_driver_attach(alt_drv, dev); if (rc < 0) - return rc; + goto err_put_dev; + + put_device(dev); return count; + +err_put_dev: + put_device(dev); + + return rc; } static DRIVER_ATTR_IGNORE_LOCKDEP(bind, 0200, NULL, bind_store); diff --git a/drivers/dma/lpc18xx-dmamux.c b/drivers/dma/lpc18xx-dmamux.c index 2b6436f4b193..d3ff521951b8 100644 --- a/drivers/dma/lpc18xx-dmamux.c +++ b/drivers/dma/lpc18xx-dmamux.c @@ -57,30 +57,31 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, struct lpc18xx_dmamux_data *dmamux = platform_get_drvdata(pdev); unsigned long flags; unsigned mux; + int ret = -EINVAL; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } mux = dma_spec->args[0]; if (mux >= dmamux->dma_master_requests) { dev_err(&pdev->dev, "invalid mux number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[1] > LPC18XX_DMAMUX_MAX_VAL) { dev_err(&pdev->dev, "invalid dma mux value: %d\n", dma_spec->args[1]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } /* The of_node_put() will be done in the core for the node */ 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"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -89,7 +90,8 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_err(&pdev->dev, "dma request %u busy with %u.%u\n", mux, mux, dmamux->muxes[mux].value); of_node_put(dma_spec->np); - return ERR_PTR(-EBUSY); + ret = -EBUSY; + goto err_put_pdev; } dmamux->muxes[mux].busy = true; @@ -106,7 +108,14 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_dbg(&pdev->dev, "mapping dmamux %u.%u to dma request %u\n", mux, dmamux->muxes[mux].value, mux); + put_device(&pdev->dev); + return &dmamux->muxes[mux]; + +err_put_pdev: + put_device(&pdev->dev); + + return ERR_PTR(ret); } static int lpc18xx_dmamux_probe(struct platform_device *pdev) diff --git a/drivers/dma/lpc32xx-dmamux.c b/drivers/dma/lpc32xx-dmamux.c index 351d7e23e615..33be714740dd 100644 --- a/drivers/dma/lpc32xx-dmamux.c +++ b/drivers/dma/lpc32xx-dmamux.c @@ -95,11 +95,12 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, struct lpc32xx_dmamux_data *dmamux = platform_get_drvdata(pdev); unsigned long flags; struct lpc32xx_dmamux *mux = NULL; + int ret = -EINVAL; int i; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } for (i = 0; i < ARRAY_SIZE(lpc32xx_muxes); i++) { @@ -111,20 +112,20 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, if (!mux) { dev_err(&pdev->dev, "invalid mux request number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[2] > 1) { dev_err(&pdev->dev, "invalid dma mux value: %d\n", dma_spec->args[1]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } /* The of_node_put() will be done in the core for the node */ 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"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -133,7 +134,8 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_err(dev, "dma request signal %d busy, routed to %s\n", mux->signal, mux->muxval ? mux->name_sel1 : mux->name_sel1); of_node_put(dma_spec->np); - return ERR_PTR(-EBUSY); + ret = -EBUSY; + goto err_put_pdev; } mux->busy = true; @@ -148,7 +150,14 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_dbg(dev, "dma request signal %d routed to %s\n", mux->signal, mux->muxval ? mux->name_sel1 : mux->name_sel1); + put_device(&pdev->dev); + return mux; + +err_put_pdev: + put_device(&pdev->dev); + + return ERR_PTR(ret); } static int lpc32xx_dmamux_probe(struct platform_device *pdev) diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index d07229a74886..d12e729ee12c 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -152,8 +152,8 @@ struct mmp_pdma_phy { * * Controller Configuration: * @run_bits: Control bits in DCSR register for channel start/stop - * @dma_mask: DMA addressing capability of controller. 0 to use OF/platform - * settings, or explicit mask like DMA_BIT_MASK(32/64) + * @dma_width: DMA addressing width in bits (32 or 64). Determines the + * DMA mask capability of the controller hardware. */ struct mmp_pdma_ops { /* Hardware Register Operations */ @@ -173,7 +173,7 @@ struct mmp_pdma_ops { /* Controller Configuration */ u32 run_bits; - u64 dma_mask; + u32 dma_width; }; struct mmp_pdma_device { @@ -928,6 +928,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, { struct mmp_pdma_desc_sw *sw; struct mmp_pdma_device *pdev = to_mmp_pdma_dev(chan->chan.device); + unsigned long flags; u64 curr; u32 residue = 0; bool passed = false; @@ -945,6 +946,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, else curr = pdev->ops->read_src_addr(chan->phy); + spin_lock_irqsave(&chan->desc_lock, flags); + list_for_each_entry(sw, &chan->chain_running, node) { u64 start, end; u32 len; @@ -989,6 +992,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, continue; if (sw->async_tx.cookie == cookie) { + spin_unlock_irqrestore(&chan->desc_lock, flags); return residue; } else { residue = 0; @@ -996,6 +1000,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, } } + spin_unlock_irqrestore(&chan->desc_lock, flags); + /* We should only get here in case of cyclic transactions */ return residue; } @@ -1172,7 +1178,7 @@ static const struct mmp_pdma_ops marvell_pdma_v1_ops = { .get_desc_src_addr = get_desc_src_addr_32, .get_desc_dst_addr = get_desc_dst_addr_32, .run_bits = (DCSR_RUN), - .dma_mask = 0, /* let OF/platform set DMA mask */ + .dma_width = 32, }; static const struct mmp_pdma_ops spacemit_k1_pdma_ops = { @@ -1185,7 +1191,7 @@ static const struct mmp_pdma_ops spacemit_k1_pdma_ops = { .get_desc_src_addr = get_desc_src_addr_64, .get_desc_dst_addr = get_desc_dst_addr_64, .run_bits = (DCSR_RUN | DCSR_LPAEEN), - .dma_mask = DMA_BIT_MASK(64), /* force 64-bit DMA addr capability */ + .dma_width = 64, }; static const struct of_device_id mmp_pdma_dt_ids[] = { @@ -1314,13 +1320,9 @@ static int mmp_pdma_probe(struct platform_device *op) pdev->device.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); pdev->device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR; - /* Set DMA mask based on ops->dma_mask, or OF/platform */ - if (pdev->ops->dma_mask) - dma_set_mask(pdev->dev, pdev->ops->dma_mask); - else if (pdev->dev->coherent_dma_mask) - dma_set_mask(pdev->dev, pdev->dev->coherent_dma_mask); - else - dma_set_mask(pdev->dev, DMA_BIT_MASK(64)); + /* Set DMA mask based on controller hardware capabilities */ + dma_set_mask_and_coherent(pdev->dev, + DMA_BIT_MASK(pdev->ops->dma_width)); ret = dma_async_device_register(&pdev->device); if (ret) { diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c index 66bfea1f156d..6e30f3aa401e 100644 --- a/drivers/dma/qcom/gpi.c +++ b/drivers/dma/qcom/gpi.c @@ -1605,14 +1605,16 @@ static int gpi_peripheral_config(struct dma_chan *chan, struct dma_slave_config *config) { struct gchan *gchan = to_gchan(chan); + void *new_config; if (!config->peripheral_config) return -EINVAL; - gchan->config = krealloc(gchan->config, config->peripheral_size, GFP_NOWAIT); - if (!gchan->config) + new_config = krealloc(gchan->config, config->peripheral_size, GFP_NOWAIT); + if (!new_config) return -ENOMEM; + gchan->config = new_config; memcpy(gchan->config, config->peripheral_config, config->peripheral_size); return 0; diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index 1f687b08d6b8..9e5f088355e2 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -557,11 +557,16 @@ rz_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, static int rz_dmac_terminate_all(struct dma_chan *chan) { struct rz_dmac_chan *channel = to_rz_dmac_chan(chan); + struct rz_lmdesc *lmdesc = channel->lmdesc.base; unsigned long flags; + unsigned int i; LIST_HEAD(head); rz_dmac_disable_hw(channel); spin_lock_irqsave(&channel->vc.lock, flags); + for (i = 0; i < DMAC_NR_LMDESC; i++) + lmdesc[i].header = 0; + list_splice_tail_init(&channel->ld_active, &channel->ld_free); list_splice_tail_init(&channel->ld_queue, &channel->ld_free); vchan_get_all_descriptors(&channel->vc, &head); @@ -854,6 +859,13 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac, return 0; } +static void rz_dmac_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int rz_dmac_parse_of_icu(struct device *dev, struct rz_dmac *dmac) { struct device_node *np = dev->of_node; @@ -876,6 +888,10 @@ static int rz_dmac_parse_of_icu(struct device *dev, struct rz_dmac *dmac) return -ENODEV; } + ret = devm_add_action_or_reset(dev, rz_dmac_put_device, &dmac->icu.pdev->dev); + if (ret) + return ret; + dmac_index = args.args[0]; if (dmac_index > RZV2H_MAX_DMAC_INDEX) { dev_err(dev, "DMAC index %u invalid.\n", dmac_index); @@ -1055,8 +1071,6 @@ static void rz_dmac_remove(struct platform_device *pdev) reset_control_assert(dmac->rstc); pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); - - platform_device_put(dmac->icu.pdev); } static const struct of_device_id of_rz_dmac_match[] = { diff --git a/drivers/dma/stm32/stm32-dmamux.c b/drivers/dma/stm32/stm32-dmamux.c index 8d77e2a7939a..db13498b9c9f 100644 --- a/drivers/dma/stm32/stm32-dmamux.c +++ b/drivers/dma/stm32/stm32-dmamux.c @@ -90,23 +90,25 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, struct stm32_dmamux_data *dmamux = platform_get_drvdata(pdev); struct stm32_dmamux *mux; u32 i, min, max; - int ret; + int ret = -EINVAL; unsigned long flags; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[0] > dmamux->dmamux_requests) { dev_err(&pdev->dev, "invalid mux request number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } mux = kzalloc(sizeof(*mux), GFP_KERNEL); - if (!mux) - return ERR_PTR(-ENOMEM); + if (!mux) { + ret = -ENOMEM; + goto err_put_pdev; + } spin_lock_irqsave(&dmamux->lock, flags); mux->chan_id = find_first_zero_bit(dmamux->dma_inuse, @@ -116,7 +118,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, spin_unlock_irqrestore(&dmamux->lock, flags); dev_err(&pdev->dev, "Run out of free DMA requests\n"); ret = -ENOMEM; - goto error_chan_id; + goto err_free_mux; } set_bit(mux->chan_id, dmamux->dma_inuse); spin_unlock_irqrestore(&dmamux->lock, flags); @@ -133,8 +135,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", i - 1); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - ret = -EINVAL; - goto error; + goto err_clear_inuse; } /* Set dma request */ @@ -142,7 +143,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { spin_unlock_irqrestore(&dmamux->lock, flags); - goto error; + goto err_put_dma_spec_np; } spin_unlock_irqrestore(&dmamux->lock, flags); @@ -160,13 +161,19 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, dev_dbg(&pdev->dev, "Mapping DMAMUX(%u) to DMA%u(%u)\n", mux->request, mux->master, mux->chan_id); + put_device(&pdev->dev); + return mux; -error: +err_put_dma_spec_np: + of_node_put(dma_spec->np); +err_clear_inuse: clear_bit(mux->chan_id, dmamux->dma_inuse); - -error_chan_id: +err_free_mux: kfree(mux); +err_put_pdev: + put_device(&pdev->dev); + return ERR_PTR(ret); } diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index d0e8bb27a03b..215bfef37ec6 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -429,10 +429,17 @@ static void tegra_adma_stop(struct tegra_adma_chan *tdc) return; } - kfree(tdc->desc); + vchan_terminate_vdesc(&tdc->desc->vd); tdc->desc = NULL; } +static void tegra_adma_synchronize(struct dma_chan *dc) +{ + struct tegra_adma_chan *tdc = to_tegra_adma_chan(dc); + + vchan_synchronize(&tdc->vc); +} + static void tegra_adma_start(struct tegra_adma_chan *tdc) { struct virt_dma_desc *vd = vchan_next_desc(&tdc->vc); @@ -1155,6 +1162,7 @@ static int tegra_adma_probe(struct platform_device *pdev) tdma->dma_dev.device_config = tegra_adma_slave_config; tdma->dma_dev.device_tx_status = tegra_adma_tx_status; tdma->dma_dev.device_terminate_all = tegra_adma_terminate_all; + tdma->dma_dev.device_synchronize = tegra_adma_synchronize; tdma->dma_dev.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); tdma->dma_dev.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); tdma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); diff --git a/drivers/dma/ti/dma-crossbar.c b/drivers/dma/ti/dma-crossbar.c index 7f17ee87a6dc..e04077d542d2 100644 --- a/drivers/dma/ti/dma-crossbar.c +++ b/drivers/dma/ti/dma-crossbar.c @@ -79,34 +79,35 @@ static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec, { struct platform_device *pdev = of_find_device_by_node(ofdma->of_node); struct ti_am335x_xbar_data *xbar = platform_get_drvdata(pdev); - struct ti_am335x_xbar_map *map; + struct ti_am335x_xbar_map *map = ERR_PTR(-EINVAL); if (dma_spec->args_count != 3) - return ERR_PTR(-EINVAL); + goto out_put_pdev; if (dma_spec->args[2] >= xbar->xbar_events) { dev_err(&pdev->dev, "Invalid XBAR event number: %d\n", dma_spec->args[2]); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } if (dma_spec->args[0] >= xbar->dma_requests) { dev_err(&pdev->dev, "Invalid DMA request line number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } /* The of_node_put() will be done in the core for the node */ 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"); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) { of_node_put(dma_spec->np); - return ERR_PTR(-ENOMEM); + map = ERR_PTR(-ENOMEM); + goto out_put_pdev; } map->dma_line = (u16)dma_spec->args[0]; @@ -120,6 +121,9 @@ static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec, ti_am335x_xbar_write(xbar->iomem, map->dma_line, map->mux_val); +out_put_pdev: + put_device(&pdev->dev); + return map; } @@ -241,28 +245,26 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, { struct platform_device *pdev = of_find_device_by_node(ofdma->of_node); struct ti_dra7_xbar_data *xbar = platform_get_drvdata(pdev); - struct ti_dra7_xbar_map *map; + struct ti_dra7_xbar_map *map = ERR_PTR(-EINVAL); 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); + goto out_put_pdev; } /* The of_node_put() will be done in the core for the node */ 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); + goto out_put_pdev; } map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) { of_node_put(dma_spec->np); - put_device(&pdev->dev); - return ERR_PTR(-ENOMEM); + map = ERR_PTR(-ENOMEM); + goto out_put_pdev; } mutex_lock(&xbar->mutex); @@ -273,8 +275,8 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, 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); + map = ERR_PTR(-ENOMEM); + goto out_put_pdev; } set_bit(map->xbar_out, xbar->dma_inuse); mutex_unlock(&xbar->mutex); @@ -288,6 +290,9 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, ti_dra7_xbar_write(xbar->iomem, map->xbar_out, map->xbar_in); +out_put_pdev: + put_device(&pdev->dev); + return map; } diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index 05228bf00033..624360423ef1 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -42,9 +42,9 @@ struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property) } ud = platform_get_drvdata(pdev); + put_device(&pdev->dev); if (!ud) { pr_debug("UDMA has not been probed\n"); - put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); } diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index 8c023c6e623a..73ed4b794630 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -1808,6 +1808,8 @@ static int omap_dma_probe(struct platform_device *pdev) if (rc) { pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n", rc); + if (od->ll123_supported) + dma_pool_destroy(od->desc_pool); omap_dma_free(od); return rc; } @@ -1823,6 +1825,8 @@ static int omap_dma_probe(struct platform_device *pdev) if (rc) { pr_warn("OMAP-DMA: failed to register DMA controller\n"); dma_async_device_unregister(&od->ddev); + if (od->ll123_supported) + dma_pool_destroy(od->desc_pool); omap_dma_free(od); } } diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h index 6ad08878e938..70bca92621aa 100644 --- a/drivers/dma/xilinx/xdma-regs.h +++ b/drivers/dma/xilinx/xdma-regs.h @@ -9,6 +9,7 @@ /* The length of register space exposed to host */ #define XDMA_REG_SPACE_LEN 65536 +#define XDMA_MAX_REG_OFFSET (XDMA_REG_SPACE_LEN - 4) /* * maximum number of DMA channels for each direction: diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 0d88b1a670e1..5ecf8223c112 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -38,7 +38,7 @@ static const struct regmap_config xdma_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = XDMA_REG_SPACE_LEN, + .max_register = XDMA_MAX_REG_OFFSET, }; /** diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index fabff602065f..89a8254d9cdc 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -131,6 +131,7 @@ #define XILINX_MCDMA_MAX_CHANS_PER_DEVICE 0x20 #define XILINX_DMA_MAX_CHANS_PER_DEVICE 0x2 #define XILINX_CDMA_MAX_CHANS_PER_DEVICE 0x1 +#define XILINX_DMA_DFAULT_ADDRWIDTH 0x20 #define XILINX_DMA_DMAXR_ALL_IRQ_MASK \ (XILINX_DMA_DMASR_FRM_CNT_IRQ | \ @@ -3159,7 +3160,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) struct device_node *node = pdev->dev.of_node; struct xilinx_dma_device *xdev; struct device_node *child, *np = pdev->dev.of_node; - u32 num_frames, addr_width, len_width; + u32 num_frames, addr_width = XILINX_DMA_DFAULT_ADDRWIDTH, len_width; int i, err; /* Allocate and initialize the DMA engine structure */ @@ -3235,7 +3236,9 @@ static int xilinx_dma_probe(struct platform_device *pdev) err = of_property_read_u32(node, "xlnx,addrwidth", &addr_width); if (err < 0) - dev_warn(xdev->dev, "missing xlnx,addrwidth property\n"); + dev_warn(xdev->dev, + "missing xlnx,addrwidth property, using default value %d\n", + XILINX_DMA_DFAULT_ADDRWIDTH); if (addr_width > 32) xdev->ext_addr = true; diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index a461095efd8a..8879a7235156 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -83,10 +83,8 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, if (ref->pin != pin) continue; reg = dpll_pin_registration_find(ref, ops, priv, cookie); - if (reg) { - refcount_inc(&ref->refcount); - return 0; - } + if (reg) + return -EEXIST; ref_exists = true; break; } @@ -164,10 +162,8 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, if (ref->dpll != dpll) continue; reg = dpll_pin_registration_find(ref, ops, priv, cookie); - if (reg) { - refcount_inc(&ref->refcount); - return 0; - } + if (reg) + return -EEXIST; ref_exists = true; break; } diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index afccdebf5ac1..6cade6d7ceff 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -358,10 +358,11 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) layers[1].type = EDAC_MC_LAYER_CHANNEL; layers[1].size = nr_channels; layers[1].is_virt_csrow = false; - mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, - sizeof(struct i3200_priv)); + + rc = -ENOMEM; + mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct i3200_priv)); if (!mci) - return -ENOMEM; + goto unmap; edac_dbg(3, "MC: init mci\n"); @@ -421,9 +422,9 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) return 0; fail: + edac_mc_free(mci); +unmap: iounmap(window); - if (mci) - edac_mc_free(mci); return rc; } diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c index 49ab5721aab2..292dda754c23 100644 --- a/drivers/edac/x38_edac.c +++ b/drivers/edac/x38_edac.c @@ -341,9 +341,12 @@ static int x38_probe1(struct pci_dev *pdev, int dev_idx) layers[1].type = EDAC_MC_LAYER_CHANNEL; layers[1].size = x38_channel_num; layers[1].is_virt_csrow = false; + + + rc = -ENOMEM; mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, 0); if (!mci) - return -ENOMEM; + goto unmap; edac_dbg(3, "MC: init mci\n"); @@ -403,9 +406,9 @@ static int x38_probe1(struct pci_dev *pdev, int dev_idx) return 0; fail: + edac_mc_free(mci); +unmap: iounmap(window); - if (mci) - edac_mc_free(mci); return rc; } diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 0232bd040f61..bd99802cb0ca 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -162,7 +162,7 @@ int cper_bits_to_str(char *buf, int buf_size, unsigned long bits, len -= size; str += size; } - return len - buf_size; + return buf_size - len; } EXPORT_SYMBOL_GPL(cper_bits_to_str); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 55452e61af31..17b5f3415465 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -74,10 +74,10 @@ struct mm_struct efi_mm = { .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), .user_ns = &init_user_ns, - .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, #ifdef CONFIG_SCHED_MM_CID .mm_cid.lock = __RAW_SPIN_LOCK_UNLOCKED(efi_mm.mm_cid.lock), #endif + .flexible_array = MM_STRUCT_FLEXIBLE_ARRAY_INIT, }; struct workqueue_struct *efi_rts_wq; @@ -819,6 +819,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, if (tbl) { phys_initrd_start = tbl->base; phys_initrd_size = tbl->size; + tbl->base = tbl->size = 0; early_memunmap(tbl, sizeof(*tbl)); } } diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 538f27209ce7..97780f27ce5b 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -6,6 +6,7 @@ * Copyright (c) 2007, MontaVista Software, Inc. <source@mvista.com> */ +#include <linux/cleanup.h> #include <linux/gpio/driver.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -109,6 +110,22 @@ davinci_direction_out(struct gpio_chip *chip, unsigned offset, int value) return __davinci_direction(chip, offset, true, value); } +static int davinci_get_direction(struct gpio_chip *chip, unsigned int offset) +{ + struct davinci_gpio_controller *d = gpiochip_get_data(chip); + struct davinci_gpio_regs __iomem *g; + u32 mask = __gpio_mask(offset), val; + int bank = offset / 32; + + g = d->regs[bank]; + + guard(spinlock_irqsave)(&d->lock); + + val = readl_relaxed(&g->dir); + + return (val & mask) ? GPIO_LINE_DIRECTION_IN : GPIO_LINE_DIRECTION_OUT; +} + /* * Read the pin's value (works even if it's set up as output); * returns zero/nonzero. @@ -203,6 +220,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) chips->chip.get = davinci_gpio_get; chips->chip.direction_output = davinci_direction_out; chips->chip.set = davinci_gpio_set; + chips->chip.get_direction = davinci_get_direction; chips->chip.ngpio = ngpio; chips->chip.base = -1; diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c index 5d677bcfccf2..2ad3c239367b 100644 --- a/drivers/gpio/gpio-it87.c +++ b/drivers/gpio/gpio-it87.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/cleanup.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> @@ -241,23 +242,17 @@ static int it87_gpio_direction_out(struct gpio_chip *chip, mask = 1 << (gpio_num % 8); group = (gpio_num / 8); - spin_lock(&it87_gpio->lock); + guard(spinlock)(&it87_gpio->lock); rc = superio_enter(); if (rc) - goto exit; + return rc; /* set the output enable bit */ superio_set_mask(mask, group + it87_gpio->output_base); rc = it87_gpio_set(chip, gpio_num, val); - if (rc) - goto exit; - superio_exit(); - -exit: - spin_unlock(&it87_gpio->lock); return rc; } diff --git a/drivers/gpio/gpio-mpsse.c b/drivers/gpio/gpio-mpsse.c index ace652ba4df1..12191aeb6566 100644 --- a/drivers/gpio/gpio-mpsse.c +++ b/drivers/gpio/gpio-mpsse.c @@ -548,6 +548,13 @@ static void gpio_mpsse_ida_remove(void *data) ida_free(&gpio_mpsse_ida, priv->id); } +static void gpio_mpsse_usb_put_dev(void *data) +{ + struct mpsse_priv *priv = data; + + usb_put_dev(priv->udev); +} + static int mpsse_init_valid_mask(struct gpio_chip *chip, unsigned long *valid_mask, unsigned int ngpios) @@ -592,6 +599,10 @@ static int gpio_mpsse_probe(struct usb_interface *interface, INIT_LIST_HEAD(&priv->workers); priv->udev = usb_get_dev(interface_to_usbdev(interface)); + err = devm_add_action_or_reset(dev, gpio_mpsse_usb_put_dev, priv); + if (err) + return err; + priv->intf = interface; priv->intf_id = interface->cur_altsetting->desc.bInterfaceNumber; @@ -713,7 +724,6 @@ static void gpio_mpsse_disconnect(struct usb_interface *intf) priv->intf = NULL; usb_set_intfdata(intf, NULL); - usb_put_dev(priv->udev); } static struct usb_driver gpio_mpsse_driver = { diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 0a3916cc2772..8727ae54bc57 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -943,14 +943,35 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin DECLARE_BITMAP(old_stat, MAX_LINE); DECLARE_BITMAP(cur_stat, MAX_LINE); DECLARE_BITMAP(new_stat, MAX_LINE); + DECLARE_BITMAP(int_stat, MAX_LINE); DECLARE_BITMAP(trigger, MAX_LINE); DECLARE_BITMAP(edges, MAX_LINE); int ret; + if (chip->driver_data & PCA_PCAL) { + /* Read INT_STAT before it is cleared by the input-port read. */ + ret = pca953x_read_regs(chip, PCAL953X_INT_STAT, int_stat); + if (ret) + return false; + } + ret = pca953x_read_regs(chip, chip->regs->input, cur_stat); if (ret) return false; + if (chip->driver_data & PCA_PCAL) { + /* Detect short pulses via INT_STAT. */ + bitmap_and(trigger, int_stat, chip->irq_mask, gc->ngpio); + + /* Apply filter for rising/falling edge selection. */ + bitmap_replace(new_stat, chip->irq_trig_fall, chip->irq_trig_raise, + cur_stat, gc->ngpio); + + bitmap_and(int_stat, new_stat, trigger, gc->ngpio); + } else { + bitmap_zero(int_stat, gc->ngpio); + } + /* Remove output pins from the equation */ pca953x_read_regs(chip, chip->regs->direction, reg_direction); @@ -964,7 +985,8 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin if (bitmap_empty(chip->irq_trig_level_high, gc->ngpio) && bitmap_empty(chip->irq_trig_level_low, gc->ngpio)) { - if (bitmap_empty(trigger, gc->ngpio)) + if (bitmap_empty(trigger, gc->ngpio) && + bitmap_empty(int_stat, gc->ngpio)) return false; } @@ -972,6 +994,7 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin bitmap_and(old_stat, chip->irq_trig_raise, new_stat, gc->ngpio); bitmap_or(edges, old_stat, cur_stat, gc->ngpio); bitmap_and(pending, edges, trigger, gc->ngpio); + bitmap_or(pending, pending, int_stat, gc->ngpio); bitmap_and(cur_stat, new_stat, chip->irq_trig_level_high, gc->ngpio); bitmap_and(cur_stat, cur_stat, chip->irq_mask, gc->ngpio); diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 47174eb3ba76..bae2061f15fc 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -593,6 +593,7 @@ static int rockchip_gpiolib_register(struct rockchip_pin_bank *bank) gc->ngpio = bank->nr_pins; gc->label = bank->name; gc->parent = bank->dev; + gc->can_sleep = true; ret = gpiochip_add_data(gc, bank); if (ret) { diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 3735c9fe1502..2adc3c070908 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2549,6 +2549,7 @@ static int lineinfo_changed_notify(struct notifier_block *nb, ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); if (!ctx) { pr_err("Failed to allocate memory for line info notification\n"); + fput(fp); return NOTIFY_DONE; } @@ -2696,7 +2697,7 @@ static int gpio_chrdev_open(struct inode *inode, struct file *file) cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) - return -ENODEV; + return -ENOMEM; cdev->watched_lines = bitmap_zalloc(gdev->ngpio, GFP_KERNEL); if (!cdev->watched_lines) @@ -2796,13 +2797,18 @@ int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt) return -ENOMEM; ret = cdev_device_add(&gdev->chrdev, &gdev->dev); - if (ret) + if (ret) { + destroy_workqueue(gdev->line_state_wq); return ret; + } guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); - if (!gc) + if (!gc) { + cdev_device_del(&gdev->chrdev, &gdev->dev); + destroy_workqueue(gdev->line_state_wq); return -ENODEV; + } gpiochip_dbg(gc, "added GPIO chardev (%d:%d)\n", MAJOR(devt), gdev->id); diff --git a/drivers/gpio/gpiolib-shared.c b/drivers/gpio/gpiolib-shared.c index ba4b718d40a0..9e6544203439 100644 --- a/drivers/gpio/gpiolib-shared.c +++ b/drivers/gpio/gpiolib-shared.c @@ -38,8 +38,10 @@ struct gpio_shared_ref { int dev_id; /* Protects the auxiliary device struct and the lookup table. */ struct mutex lock; + struct lock_class_key lock_key; struct auxiliary_device adev; struct gpiod_lookup_table *lookup; + bool is_reset_gpio; }; /* Represents a single GPIO pin. */ @@ -76,6 +78,60 @@ gpio_shared_find_entry(struct fwnode_handle *controller_node, return NULL; } +static struct gpio_shared_ref *gpio_shared_make_ref(struct fwnode_handle *fwnode, + const char *con_id, + enum gpiod_flags flags) +{ + char *con_id_cpy __free(kfree) = NULL; + + struct gpio_shared_ref *ref __free(kfree) = kzalloc(sizeof(*ref), GFP_KERNEL); + if (!ref) + return NULL; + + if (con_id) { + con_id_cpy = kstrdup(con_id, GFP_KERNEL); + if (!con_id_cpy) + return NULL; + } + + ref->dev_id = ida_alloc(&gpio_shared_ida, GFP_KERNEL); + if (ref->dev_id < 0) + return NULL; + + ref->flags = flags; + ref->con_id = no_free_ptr(con_id_cpy); + ref->fwnode = fwnode; + lockdep_register_key(&ref->lock_key); + mutex_init_with_key(&ref->lock, &ref->lock_key); + + return no_free_ptr(ref); +} + +static int gpio_shared_setup_reset_proxy(struct gpio_shared_entry *entry, + enum gpiod_flags flags) +{ + struct gpio_shared_ref *ref; + + list_for_each_entry(ref, &entry->refs, list) { + if (ref->is_reset_gpio) + /* Already set-up. */ + return 0; + } + + ref = gpio_shared_make_ref(NULL, "reset", flags); + if (!ref) + return -ENOMEM; + + ref->is_reset_gpio = true; + + list_add_tail(&ref->list, &entry->refs); + + pr_debug("Created a secondary shared GPIO reference for potential reset-gpio device for GPIO %u at %s\n", + entry->offset, fwnode_get_name(entry->fwnode)); + + return 0; +} + /* Handle all special nodes that we should ignore. */ static bool gpio_shared_of_node_ignore(struct device_node *node) { @@ -106,6 +162,7 @@ static int gpio_shared_of_traverse(struct device_node *curr) size_t con_id_len, suffix_len; struct fwnode_handle *fwnode; struct of_phandle_args args; + struct gpio_shared_ref *ref; struct property *prop; unsigned int offset; const char *suffix; @@ -138,6 +195,7 @@ static int gpio_shared_of_traverse(struct device_node *curr) for (i = 0; i < count; i++) { struct device_node *np __free(device_node) = NULL; + char *con_id __free(kfree) = NULL; ret = of_parse_phandle_with_args(curr, prop->name, "#gpio-cells", i, @@ -182,15 +240,6 @@ static int gpio_shared_of_traverse(struct device_node *curr) list_add_tail(&entry->list, &gpio_shared_list); } - struct gpio_shared_ref *ref __free(kfree) = - kzalloc(sizeof(*ref), GFP_KERNEL); - if (!ref) - return -ENOMEM; - - ref->fwnode = fwnode_handle_get(of_fwnode_handle(curr)); - ref->flags = args.args[1]; - mutex_init(&ref->lock); - if (strends(prop->name, "gpios")) suffix = "-gpios"; else if (strends(prop->name, "gpio")) @@ -202,27 +251,32 @@ static int gpio_shared_of_traverse(struct device_node *curr) /* We only set con_id if there's actually one. */ if (strcmp(prop->name, "gpios") && strcmp(prop->name, "gpio")) { - ref->con_id = kstrdup(prop->name, GFP_KERNEL); - if (!ref->con_id) + con_id = kstrdup(prop->name, GFP_KERNEL); + if (!con_id) return -ENOMEM; - con_id_len = strlen(ref->con_id); + con_id_len = strlen(con_id); suffix_len = strlen(suffix); - ref->con_id[con_id_len - suffix_len] = '\0'; + con_id[con_id_len - suffix_len] = '\0'; } - ref->dev_id = ida_alloc(&gpio_shared_ida, GFP_KERNEL); - if (ref->dev_id < 0) { - kfree(ref->con_id); + ref = gpio_shared_make_ref(fwnode_handle_get(of_fwnode_handle(curr)), + con_id, args.args[1]); + if (!ref) return -ENOMEM; - } if (!list_empty(&entry->refs)) pr_debug("GPIO %u at %s is shared by multiple firmware nodes\n", entry->offset, fwnode_get_name(entry->fwnode)); - list_add_tail(&no_free_ptr(ref)->list, &entry->refs); + list_add_tail(&ref->list, &entry->refs); + + if (strcmp(prop->name, "reset-gpios") == 0) { + ret = gpio_shared_setup_reset_proxy(entry, args.args[1]); + if (ret) + return ret; + } } } @@ -306,21 +360,17 @@ static bool gpio_shared_dev_is_reset_gpio(struct device *consumer, struct fwnode_handle *reset_fwnode = dev_fwnode(consumer); struct fwnode_reference_args ref_args, aux_args; struct device *parent = consumer->parent; + struct gpio_shared_ref *real_ref; bool match; int ret; + lockdep_assert_held(&ref->lock); + /* The reset-gpio device must have a parent AND a firmware node. */ if (!parent || !reset_fwnode) return false; /* - * FIXME: use device_is_compatible() once the reset-gpio drivers gains - * a compatible string which it currently does not have. - */ - if (!strstarts(dev_name(consumer), "reset.gpio.")) - return false; - - /* * Parent of the reset-gpio auxiliary device is the GPIO chip whose * fwnode we stored in the entry structure. */ @@ -328,33 +378,61 @@ static bool gpio_shared_dev_is_reset_gpio(struct device *consumer, return false; /* - * The device associated with the shared reference's firmware node is - * the consumer of the reset control exposed by the reset-gpio device. - * It must have a "reset-gpios" property that's referencing the entry's - * firmware node. - * - * The reference args must agree between the real consumer and the - * auxiliary reset-gpio device. + * Now we need to find the actual pin we want to assign to this + * reset-gpio device. To that end: iterate over the list of references + * of this entry and see if there's one, whose reset-gpios property's + * arguments match the ones from this consumer's node. */ - ret = fwnode_property_get_reference_args(ref->fwnode, "reset-gpios", - NULL, 2, 0, &ref_args); - if (ret) - return false; + list_for_each_entry(real_ref, &entry->refs, list) { + if (real_ref == ref) + continue; + + guard(mutex)(&real_ref->lock); + + if (!real_ref->fwnode) + continue; + + /* + * The device associated with the shared reference's firmware + * node is the consumer of the reset control exposed by the + * reset-gpio device. It must have a "reset-gpios" property + * that's referencing the entry's firmware node. + * + * The reference args must agree between the real consumer and + * the auxiliary reset-gpio device. + */ + ret = fwnode_property_get_reference_args(real_ref->fwnode, + "reset-gpios", + NULL, 2, 0, &ref_args); + if (ret) + continue; + + ret = fwnode_property_get_reference_args(reset_fwnode, "reset-gpios", + NULL, 2, 0, &aux_args); + if (ret) { + fwnode_handle_put(ref_args.fwnode); + continue; + } + + match = ((ref_args.fwnode == entry->fwnode) && + (aux_args.fwnode == entry->fwnode) && + (ref_args.args[0] == aux_args.args[0])); - ret = fwnode_property_get_reference_args(reset_fwnode, "reset-gpios", - NULL, 2, 0, &aux_args); - if (ret) { fwnode_handle_put(ref_args.fwnode); - return false; - } + fwnode_handle_put(aux_args.fwnode); + + if (!match) + continue; - match = ((ref_args.fwnode == entry->fwnode) && - (aux_args.fwnode == entry->fwnode) && - (ref_args.args[0] == aux_args.args[0])); + /* + * Reuse the fwnode of the real device, next time we'll use it + * in the normal path. + */ + ref->fwnode = fwnode_handle_get(reset_fwnode); + return true; + } - fwnode_handle_put(ref_args.fwnode); - fwnode_handle_put(aux_args.fwnode); - return match; + return false; } #else static bool gpio_shared_dev_is_reset_gpio(struct device *consumer, @@ -365,24 +443,33 @@ static bool gpio_shared_dev_is_reset_gpio(struct device *consumer, } #endif /* CONFIG_RESET_GPIO */ -int gpio_shared_add_proxy_lookup(struct device *consumer, unsigned long lflags) +int gpio_shared_add_proxy_lookup(struct device *consumer, const char *con_id, + unsigned long lflags) { const char *dev_id = dev_name(consumer); + struct gpiod_lookup_table *lookup; struct gpio_shared_entry *entry; struct gpio_shared_ref *ref; - struct gpiod_lookup_table *lookup __free(kfree) = - kzalloc(struct_size(lookup, table, 2), GFP_KERNEL); - if (!lookup) - return -ENOMEM; - list_for_each_entry(entry, &gpio_shared_list, list) { list_for_each_entry(ref, &entry->refs, list) { - if (!device_match_fwnode(consumer, ref->fwnode) && - !gpio_shared_dev_is_reset_gpio(consumer, entry, ref)) + guard(mutex)(&ref->lock); + + /* + * FIXME: use device_is_compatible() once the reset-gpio + * drivers gains a compatible string which it currently + * does not have. + */ + if (!ref->fwnode && strstarts(dev_name(consumer), "reset.gpio.")) { + if (!gpio_shared_dev_is_reset_gpio(consumer, entry, ref)) + continue; + } else if (!device_match_fwnode(consumer, ref->fwnode)) { continue; + } - guard(mutex)(&ref->lock); + if ((!con_id && ref->con_id) || (con_id && !ref->con_id) || + (con_id && ref->con_id && strcmp(con_id, ref->con_id) != 0)) + continue; /* We've already done that on a previous request. */ if (ref->lookup) @@ -395,6 +482,10 @@ int gpio_shared_add_proxy_lookup(struct device *consumer, unsigned long lflags) if (!key) return -ENOMEM; + lookup = kzalloc(struct_size(lookup, table, 2), GFP_KERNEL); + if (!lookup) + return -ENOMEM; + pr_debug("Adding machine lookup entry for a shared GPIO for consumer %s, with key '%s' and con_id '%s'\n", dev_id, key, ref->con_id ?: "none"); @@ -402,7 +493,7 @@ int gpio_shared_add_proxy_lookup(struct device *consumer, unsigned long lflags) lookup->table[0] = GPIO_LOOKUP(no_free_ptr(key), 0, ref->con_id, lflags); - ref->lookup = no_free_ptr(lookup); + ref->lookup = lookup; gpiod_add_lookup_table(ref->lookup); return 0; @@ -424,7 +515,7 @@ int gpio_device_setup_shared(struct gpio_device *gdev) { struct gpio_shared_entry *entry; struct gpio_shared_ref *ref; - unsigned long *flags; + struct gpio_desc *desc; int ret; list_for_each_entry(entry, &gpio_shared_list, list) { @@ -452,26 +543,31 @@ int gpio_device_setup_shared(struct gpio_device *gdev) if (list_count_nodes(&entry->refs) <= 1) continue; - flags = &gdev->descs[entry->offset].flags; + desc = &gdev->descs[entry->offset]; - __set_bit(GPIOD_FLAG_SHARED, flags); + __set_bit(GPIOD_FLAG_SHARED, &desc->flags); /* * Shared GPIOs are not requested via the normal path. Make * them inaccessible to anyone even before we register the * chip. */ - __set_bit(GPIOD_FLAG_REQUESTED, flags); + ret = gpiod_request_commit(desc, "shared"); + if (ret) + return ret; pr_debug("GPIO %u owned by %s is shared by multiple consumers\n", entry->offset, gpio_device_get_label(gdev)); list_for_each_entry(ref, &entry->refs, list) { - pr_debug("Setting up a shared GPIO entry for %s\n", - fwnode_get_name(ref->fwnode)); + pr_debug("Setting up a shared GPIO entry for %s (con_id: '%s')\n", + fwnode_get_name(ref->fwnode) ?: "(no fwnode)", + ref->con_id ?: "(none)"); ret = gpio_shared_make_adev(gdev, entry, ref); - if (ret) + if (ret) { + gpiod_free_commit(desc); return ret; + } } } @@ -487,15 +583,8 @@ void gpio_device_teardown_shared(struct gpio_device *gdev) if (!device_match_fwnode(&gdev->dev, entry->fwnode)) continue; - /* - * For some reason if we call synchronize_srcu() in GPIO core, - * descent here and take this mutex and then recursively call - * synchronize_srcu() again from gpiochip_remove() (which is - * totally fine) called after gpio_shared_remove_adev(), - * lockdep prints a false positive deadlock splat. Disable - * lockdep here. - */ - lockdep_off(); + gpiod_free_commit(&gdev->descs[entry->offset]); + list_for_each_entry(ref, &entry->refs, list) { guard(mutex)(&ref->lock); @@ -508,7 +597,6 @@ void gpio_device_teardown_shared(struct gpio_device *gdev) gpio_shared_remove_adev(&ref->adev); } - lockdep_on(); } } @@ -604,6 +692,7 @@ static void gpio_shared_drop_ref(struct gpio_shared_ref *ref) { list_del(&ref->list); mutex_destroy(&ref->lock); + lockdep_unregister_key(&ref->lock_key); kfree(ref->con_id); ida_free(&gpio_shared_ida, ref->dev_id); fwnode_handle_put(ref->fwnode); @@ -635,12 +724,38 @@ static void __init gpio_shared_teardown(void) } } +static bool gpio_shared_entry_is_really_shared(struct gpio_shared_entry *entry) +{ + size_t num_nodes = list_count_nodes(&entry->refs); + struct gpio_shared_ref *ref; + + if (num_nodes <= 1) + return false; + + if (num_nodes > 2) + return true; + + /* Exactly two references: */ + list_for_each_entry(ref, &entry->refs, list) { + /* + * Corner-case: the second reference comes from the potential + * reset-gpio instance. However, this pin is not really shared + * as it would have three references in this case. Avoid + * creating unnecessary proxies. + */ + if (ref->is_reset_gpio) + return false; + } + + return true; +} + static void gpio_shared_free_exclusive(void) { struct gpio_shared_entry *entry, *epos; list_for_each_entry_safe(entry, epos, &gpio_shared_list, list) { - if (list_count_nodes(&entry->refs) > 1) + if (gpio_shared_entry_is_really_shared(entry)) continue; gpio_shared_drop_ref(list_first_entry(&entry->refs, diff --git a/drivers/gpio/gpiolib-shared.h b/drivers/gpio/gpiolib-shared.h index 667dbdff3585..40568ef7364c 100644 --- a/drivers/gpio/gpiolib-shared.h +++ b/drivers/gpio/gpiolib-shared.h @@ -16,7 +16,8 @@ struct device; int gpio_device_setup_shared(struct gpio_device *gdev); void gpio_device_teardown_shared(struct gpio_device *gdev); -int gpio_shared_add_proxy_lookup(struct device *consumer, unsigned long lflags); +int gpio_shared_add_proxy_lookup(struct device *consumer, const char *con_id, + unsigned long lflags); #else @@ -28,6 +29,7 @@ static inline int gpio_device_setup_shared(struct gpio_device *gdev) static inline void gpio_device_teardown_shared(struct gpio_device *gdev) { } static inline int gpio_shared_add_proxy_lookup(struct device *consumer, + const char *con_id, unsigned long lflags) { return 0; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 91e0c384f34a..1578cf3a8c74 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -468,9 +468,6 @@ int gpiod_get_direction(struct gpio_desc *desc) test_bit(GPIOD_FLAG_IS_OUT, &flags)) return 0; - if (!guard.gc->get_direction) - return -ENOTSUPP; - ret = gpiochip_get_direction(guard.gc, offset); if (ret < 0) return ret; @@ -1105,6 +1102,18 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, gdev->ngpio = gc->ngpio; gdev->can_sleep = gc->can_sleep; + rwlock_init(&gdev->line_state_lock); + RAW_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier); + BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier); + + ret = init_srcu_struct(&gdev->srcu); + if (ret) + goto err_free_label; + + ret = init_srcu_struct(&gdev->desc_srcu); + if (ret) + goto err_cleanup_gdev_srcu; + scoped_guard(mutex, &gpio_devices_lock) { /* * TODO: this allocates a Linux GPIO number base in the global @@ -1119,7 +1128,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, if (base < 0) { ret = base; base = 0; - goto err_free_label; + goto err_cleanup_desc_srcu; } /* @@ -1139,22 +1148,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiodev_add_to_list_unlocked(gdev); if (ret) { gpiochip_err(gc, "GPIO integer space overlap, cannot add chip\n"); - goto err_free_label; + goto err_cleanup_desc_srcu; } } - rwlock_init(&gdev->line_state_lock); - RAW_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier); - BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier); - - ret = init_srcu_struct(&gdev->srcu); - if (ret) - goto err_remove_from_list; - - ret = init_srcu_struct(&gdev->desc_srcu); - if (ret) - goto err_cleanup_gdev_srcu; - #ifdef CONFIG_PINCTRL INIT_LIST_HEAD(&gdev->pin_ranges); #endif @@ -1164,11 +1161,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiochip_set_names(gc); if (ret) - goto err_cleanup_desc_srcu; + goto err_remove_from_list; ret = gpiochip_init_valid_mask(gc); if (ret) - goto err_cleanup_desc_srcu; + goto err_remove_from_list; for (desc_index = 0; desc_index < gc->ngpio; desc_index++) { struct gpio_desc *desc = &gdev->descs[desc_index]; @@ -1248,10 +1245,6 @@ err_remove_of_chip: of_gpiochip_remove(gc); err_free_valid_mask: gpiochip_free_valid_mask(gc); -err_cleanup_desc_srcu: - cleanup_srcu_struct(&gdev->desc_srcu); -err_cleanup_gdev_srcu: - cleanup_srcu_struct(&gdev->srcu); err_remove_from_list: scoped_guard(mutex, &gpio_devices_lock) list_del_rcu(&gdev->list); @@ -1261,6 +1254,10 @@ err_remove_from_list: gpio_device_put(gdev); goto err_print_message; } +err_cleanup_desc_srcu: + cleanup_srcu_struct(&gdev->desc_srcu); +err_cleanup_gdev_srcu: + cleanup_srcu_struct(&gdev->srcu); err_free_label: kfree_const(gdev->label); err_free_descs: @@ -2456,7 +2453,7 @@ EXPORT_SYMBOL_GPL(gpiochip_remove_pin_ranges); * on each other, and help provide better diagnostics in debugfs. * They're called even less than the "set direction" calls. */ -static int gpiod_request_commit(struct gpio_desc *desc, const char *label) +int gpiod_request_commit(struct gpio_desc *desc, const char *label) { unsigned int offset; int ret; @@ -2518,7 +2515,7 @@ int gpiod_request(struct gpio_desc *desc, const char *label) return ret; } -static void gpiod_free_commit(struct gpio_desc *desc) +void gpiod_free_commit(struct gpio_desc *desc) { unsigned long flags; @@ -4508,45 +4505,41 @@ void gpiod_remove_hogs(struct gpiod_hog *hogs) } EXPORT_SYMBOL_GPL(gpiod_remove_hogs); -static struct gpiod_lookup_table *gpiod_find_lookup_table(struct device *dev) +static bool gpiod_match_lookup_table(struct device *dev, + const struct gpiod_lookup_table *table) { const char *dev_id = dev ? dev_name(dev) : NULL; - struct gpiod_lookup_table *table; - list_for_each_entry(table, &gpio_lookup_list, list) { - if (table->dev_id && dev_id) { - /* - * Valid strings on both ends, must be identical to have - * a match - */ - if (!strcmp(table->dev_id, dev_id)) - return table; - } else { - /* - * One of the pointers is NULL, so both must be to have - * a match - */ - if (dev_id == table->dev_id) - return table; - } + lockdep_assert_held(&gpio_lookup_lock); + + if (table->dev_id && dev_id) { + /* + * Valid strings on both ends, must be identical to have + * a match + */ + if (!strcmp(table->dev_id, dev_id)) + return true; + } else { + /* + * One of the pointers is NULL, so both must be to have + * a match + */ + if (dev_id == table->dev_id) + return true; } - return NULL; + return false; } -static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id, - unsigned int idx, unsigned long *flags) +static struct gpio_desc *gpio_desc_table_match(struct device *dev, const char *con_id, + unsigned int idx, unsigned long *flags, + struct gpiod_lookup_table *table) { - struct gpio_desc *desc = ERR_PTR(-ENOENT); - struct gpiod_lookup_table *table; + struct gpio_desc *desc; struct gpiod_lookup *p; struct gpio_chip *gc; - guard(mutex)(&gpio_lookup_lock); - - table = gpiod_find_lookup_table(dev); - if (!table) - return desc; + lockdep_assert_held(&gpio_lookup_lock); for (p = &table->table[0]; p->key; p++) { /* idx must always match exactly */ @@ -4600,7 +4593,30 @@ static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id, return desc; } - return desc; + return NULL; +} + +static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id, + unsigned int idx, unsigned long *flags) +{ + struct gpiod_lookup_table *table; + struct gpio_desc *desc; + + guard(mutex)(&gpio_lookup_lock); + + list_for_each_entry(table, &gpio_lookup_list, list) { + if (!gpiod_match_lookup_table(dev, table)) + continue; + + desc = gpio_desc_table_match(dev, con_id, idx, flags, table); + if (!desc) + continue; + + /* On IS_ERR() or match. */ + return desc; + } + + return ERR_PTR(-ENOENT); } static int platform_gpio_count(struct device *dev, const char *con_id) @@ -4610,14 +4626,16 @@ static int platform_gpio_count(struct device *dev, const char *con_id) unsigned int count = 0; scoped_guard(mutex, &gpio_lookup_lock) { - table = gpiod_find_lookup_table(dev); - if (!table) - return -ENOENT; + list_for_each_entry(table, &gpio_lookup_list, list) { + if (!gpiod_match_lookup_table(dev, table)) + continue; - for (p = &table->table[0]; p->key; p++) { - if ((con_id && p->con_id && !strcmp(con_id, p->con_id)) || - (!con_id && !p->con_id)) - count++; + for (p = &table->table[0]; p->key; p++) { + if ((con_id && p->con_id && + !strcmp(con_id, p->con_id)) || + (!con_id && !p->con_id)) + count++; + } } } @@ -4696,7 +4714,8 @@ struct gpio_desc *gpiod_find_and_request(struct device *consumer, * lookup table for the proxy device as previously * we only knew the consumer's fwnode. */ - ret = gpio_shared_add_proxy_lookup(consumer, lookupflags); + ret = gpio_shared_add_proxy_lookup(consumer, con_id, + lookupflags); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index 77f6f2936dc2..3abb90385829 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -244,7 +244,9 @@ DEFINE_CLASS(gpio_chip_guard, struct gpio_desc *desc) int gpiod_request(struct gpio_desc *desc, const char *label); +int gpiod_request_commit(struct gpio_desc *desc, const char *label); void gpiod_free(struct gpio_desc *desc); +void gpiod_free_commit(struct gpio_desc *desc); static inline int gpiod_request_user(struct gpio_desc *desc, const char *label) { diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 7e6bc0b3a589..ed85d0ceee3b 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -210,7 +210,7 @@ config DRM_GPUVM config DRM_GPUSVM tristate - depends on DRM && DEVICE_PRIVATE + depends on DRM select HMM_MIRROR select MMU_NOTIFIER help diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 0e1c668b46d2..d26191717428 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -108,8 +108,10 @@ obj-$(CONFIG_DRM_EXEC) += drm_exec.o obj-$(CONFIG_DRM_GPUVM) += drm_gpuvm.o drm_gpusvm_helper-y := \ - drm_gpusvm.o\ + drm_gpusvm.o +drm_gpusvm_helper-$(CONFIG_ZONE_DEVICE) += \ drm_pagemap.o + obj-$(CONFIG_DRM_GPUSVM) += drm_gpusvm_helper.o obj-$(CONFIG_DRM_BUDDY) += drm_buddy.o diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 9f9774f58ce1..b20a06abb65d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -274,6 +274,8 @@ extern int amdgpu_rebar; extern int amdgpu_wbrf; extern int amdgpu_user_queue; +extern uint amdgpu_hdmi_hpd_debounce_delay_ms; + #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 12201b8e99b3..d2c3885de711 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3445,11 +3445,10 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev, (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SDMA)) continue; - /* skip CG for VCE/UVD/VPE, it's handled specially */ + /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN && - adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VPE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG && adev->ip_blocks[i].version->funcs->set_powergating_state) { /* enable powergating to save power */ @@ -5064,6 +5063,14 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) amdgpu_ttm_set_buffer_funcs_status(adev, false); + /* + * device went through surprise hotplug; we need to destroy topology + * before ip_fini_early to prevent kfd locking refcount issues by calling + * amdgpu_amdkfd_suspend() + */ + if (drm_dev_is_unplugged(adev_to_drm(adev))) + amdgpu_amdkfd_device_fini_sw(adev); + amdgpu_device_ip_fini_early(adev); amdgpu_irq_fini_hw(adev); @@ -5867,6 +5874,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) if (ret) goto mode1_reset_failed; + /* enable mmio access after mode 1 reset completed */ + adev->no_hw_access = false; + amdgpu_device_load_pci_state(adev->pdev); ret = amdgpu_psp_wait_for_bootloader(adev); if (ret) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index b5d34797d606..52bc04452812 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1880,7 +1880,12 @@ int amdgpu_display_get_scanout_buffer(struct drm_plane *plane, struct drm_scanout_buffer *sb) { struct amdgpu_bo *abo; - struct drm_framebuffer *fb = plane->state->fb; + struct drm_framebuffer *fb; + + if (drm_drv_uses_atomic_modeset(plane->dev)) + fb = plane->state->fb; + else + fb = plane->fb; if (!fb) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index e22cfa7c6d32..c1461317eb29 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -95,18 +95,6 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC) attach->peer2peer = false; - /* - * Disable peer-to-peer access for DCC-enabled VRAM surfaces on GFX12+. - * Such buffers cannot be safely accessed over P2P due to device-local - * compression metadata. Fallback to system-memory path instead. - * Device supports GFX12 (GC 12.x or newer) - * BO was created with the AMDGPU_GEM_CREATE_GFX12_DCC flag - * - */ - if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(12, 0, 0) && - bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC) - attach->peer2peer = false; - if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) && pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 848e6b7db482..6ccb80e2d7c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -247,6 +247,7 @@ int amdgpu_damage_clips = -1; /* auto */ int amdgpu_umsch_mm_fwlog; int amdgpu_rebar = -1; /* auto */ int amdgpu_user_queue = -1; +uint amdgpu_hdmi_hpd_debounce_delay_ms; DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, "DRM_UT_CORE", @@ -1123,6 +1124,16 @@ module_param_named(rebar, amdgpu_rebar, int, 0444); MODULE_PARM_DESC(user_queue, "Enable user queues (-1 = auto (default), 0 = disable, 1 = enable, 2 = enable UQs and disable KQs)"); module_param_named(user_queue, amdgpu_user_queue, int, 0444); +/* + * DOC: hdmi_hpd_debounce_delay_ms (uint) + * HDMI HPD disconnect debounce delay in milliseconds. + * + * Used to filter short disconnect->reconnect HPD toggles some HDMI sinks + * generate while entering/leaving power save. Set to 0 to disable by default. + */ +MODULE_PARM_DESC(hdmi_hpd_debounce_delay_ms, "HDMI HPD disconnect debounce delay in milliseconds (0 to disable (by default), 1500 is common)"); +module_param_named(hdmi_hpd_debounce_delay_ms, amdgpu_hdmi_hpd_debounce_delay_ms, uint, 0644); + /* These devices are not supported by amdgpu. * They are supported by the mach64, r128, radeon drivers */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index c7843e336310..d78d9e7fb9d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -89,6 +89,16 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring) return seq; } +static void amdgpu_fence_save_fence_wptr_start(struct amdgpu_fence *af) +{ + af->fence_wptr_start = af->ring->wptr; +} + +static void amdgpu_fence_save_fence_wptr_end(struct amdgpu_fence *af) +{ + af->fence_wptr_end = af->ring->wptr; +} + /** * amdgpu_fence_emit - emit a fence on the requested ring * @@ -116,8 +126,10 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct amdgpu_fence *af, &ring->fence_drv.lock, adev->fence_context + ring->idx, seq); + amdgpu_fence_save_fence_wptr_start(af); amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr, seq, flags | AMDGPU_FENCE_FLAG_INT); + amdgpu_fence_save_fence_wptr_end(af); amdgpu_fence_save_wptr(af); pm_runtime_get_noresume(adev_to_drm(adev)->dev); ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask]; @@ -709,6 +721,7 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) struct amdgpu_ring *ring = af->ring; unsigned long flags; u32 seq, last_seq; + bool reemitted = false; last_seq = amdgpu_fence_read(ring) & ring->fence_drv.num_fences_mask; seq = ring->fence_drv.sync_seq & ring->fence_drv.num_fences_mask; @@ -726,7 +739,9 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) if (unprocessed && !dma_fence_is_signaled_locked(unprocessed)) { fence = container_of(unprocessed, struct amdgpu_fence, base); - if (fence == af) + if (fence->reemitted > 1) + reemitted = true; + else if (fence == af) dma_fence_set_error(&fence->base, -ETIME); else if (fence->context == af->context) dma_fence_set_error(&fence->base, -ECANCELED); @@ -734,9 +749,12 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) rcu_read_unlock(); } while (last_seq != seq); spin_unlock_irqrestore(&ring->fence_drv.lock, flags); - /* signal the guilty fence */ - amdgpu_fence_write(ring, (u32)af->base.seqno); - amdgpu_fence_process(ring); + + if (reemitted) { + /* if we've already reemitted once then just cancel everything */ + amdgpu_fence_driver_force_completion(af->ring); + af->ring->ring_backup_entries_to_copy = 0; + } } void amdgpu_fence_save_wptr(struct amdgpu_fence *af) @@ -745,7 +763,7 @@ void amdgpu_fence_save_wptr(struct amdgpu_fence *af) } static void amdgpu_ring_backup_unprocessed_command(struct amdgpu_ring *ring, - u64 start_wptr, u32 end_wptr) + u64 start_wptr, u64 end_wptr) { unsigned int first_idx = start_wptr & ring->buf_mask; unsigned int last_idx = end_wptr & ring->buf_mask; @@ -784,10 +802,18 @@ void amdgpu_ring_backup_unprocessed_commands(struct amdgpu_ring *ring, /* save everything if the ring is not guilty, otherwise * just save the content from other contexts. */ - if (!guilty_fence || (fence->context != guilty_fence->context)) + if (!fence->reemitted && + (!guilty_fence || (fence->context != guilty_fence->context))) { amdgpu_ring_backup_unprocessed_command(ring, wptr, fence->wptr); + } else if (!fence->reemitted) { + /* always save the fence */ + amdgpu_ring_backup_unprocessed_command(ring, + fence->fence_wptr_start, + fence->fence_wptr_end); + } wptr = fence->wptr; + fence->reemitted++; } rcu_read_unlock(); } while (last_seq != seq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index d2237ce9da70..1485f4789440 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -375,7 +375,7 @@ void amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset, * @start_page: first page to map in the GART aperture * @num_pages: number of pages to be mapped * @flags: page table entry flags - * @dst: CPU address of the GART table + * @dst: valid CPU address of GART table, cannot be null * * Binds a BO that is allocated in VRAM to the GART page table * (all ASICs). @@ -396,7 +396,7 @@ void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa, return; for (i = 0; i < num_pages; ++i) { - amdgpu_gmc_set_pte_pde(adev, adev->gart.ptr, + amdgpu_gmc_set_pte_pde(adev, dst, start_page + i, pa + AMDGPU_GPU_PAGE_SIZE * i, flags); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 869bceb0fe2c..7e623f91f2d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -732,6 +732,12 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, return 0; if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) { + + if (!adev->gmc.gmc_funcs->flush_gpu_tlb_pasid) { + r = 0; + goto error_unlock_reset; + } + if (adev->gmc.flush_tlb_needs_extra_type_2) adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, 2, all_hub, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 586a58facca1..72ec455fa932 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -302,7 +302,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, if (job && job->vmid) amdgpu_vmid_reset(adev, ring->vm_hub, job->vmid); amdgpu_ring_undo(ring); - return r; + goto free_fence; } *f = &af->base; /* get a ref for the job */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c index 37270c4dab8d..532f83d783d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c @@ -318,12 +318,36 @@ void isp_kernel_buffer_free(void **buf_obj, u64 *gpu_addr, void **cpu_addr) } EXPORT_SYMBOL(isp_kernel_buffer_free); +static int isp_resume(struct amdgpu_ip_block *ip_block) +{ + struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_isp *isp = &adev->isp; + + if (isp->funcs->hw_resume) + return isp->funcs->hw_resume(isp); + + return -ENODEV; +} + +static int isp_suspend(struct amdgpu_ip_block *ip_block) +{ + struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_isp *isp = &adev->isp; + + if (isp->funcs->hw_suspend) + return isp->funcs->hw_suspend(isp); + + return -ENODEV; +} + static const struct amd_ip_funcs isp_ip_funcs = { .name = "isp_ip", .early_init = isp_early_init, .hw_init = isp_hw_init, .hw_fini = isp_hw_fini, .is_idle = isp_is_idle, + .suspend = isp_suspend, + .resume = isp_resume, .set_clockgating_state = isp_set_clockgating_state, .set_powergating_state = isp_set_powergating_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h index d6f4ffa4c97c..9a5d2b1dff9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h @@ -38,6 +38,8 @@ struct amdgpu_isp; struct isp_funcs { int (*hw_init)(struct amdgpu_isp *isp); int (*hw_fini)(struct amdgpu_isp *isp); + int (*hw_suspend)(struct amdgpu_isp *isp); + int (*hw_resume)(struct amdgpu_isp *isp); }; struct amdgpu_isp { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 0a0dcbf0798d..7ccb724b2488 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -217,8 +217,11 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (!entity) return 0; - return drm_sched_job_init(&(*job)->base, entity, 1, owner, - drm_client_id); + r = drm_sched_job_init(&(*job)->base, entity, 1, owner, drm_client_id); + if (!r) + return 0; + + kfree((*job)->hw_vm_fence); err_fence: kfree((*job)->hw_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 6ee77f431d56..f65edd80cabf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -201,6 +201,9 @@ static enum amd_ip_block_type type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ? AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN; break; + case AMDGPU_HW_IP_VPE: + type = AMD_IP_BLOCK_TYPE_VPE; + break; default: type = AMD_IP_BLOCK_TYPE_NUM; break; @@ -721,6 +724,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) case AMD_IP_BLOCK_TYPE_UVD: count = adev->uvd.num_uvd_inst; break; + case AMD_IP_BLOCK_TYPE_VPE: + count = adev->vpe.num_instances; + break; /* For all other IP block types not listed in the switch statement * the ip status is valid here and the instance count is one. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 7a27c6c4bb44..055437d4edf9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -144,10 +144,15 @@ struct amdgpu_fence { struct amdgpu_ring *ring; ktime_t start_timestamp; - /* wptr for the fence for resets */ + /* wptr for the total submission for resets */ u64 wptr; /* fence context for resets */ u64 context; + /* has this fence been reemitted */ + unsigned int reemitted; + /* wptr for the fence for the submission */ + u64 fence_wptr_start; + u64 fence_wptr_end; }; extern const struct drm_sched_backend_ops amdgpu_sched_ops; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 9a969175900e..58b26c78b642 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -885,12 +885,28 @@ static int amdgpu_userq_input_args_validate(struct drm_device *dev, return 0; } +bool amdgpu_userq_enabled(struct drm_device *dev) +{ + struct amdgpu_device *adev = drm_to_adev(dev); + int i; + + for (i = 0; i < AMDGPU_HW_IP_NUM; i++) { + if (adev->userq_funcs[i]) + return true; + } + + return false; +} + int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { union drm_amdgpu_userq *args = data; int r; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + if (amdgpu_userq_input_args_validate(dev, args, filp) < 0) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h index c37444427a14..b48b3bc293fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h @@ -141,6 +141,7 @@ uint64_t amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr, struct drm_file *filp); u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev); +bool amdgpu_userq_enabled(struct drm_device *dev); int amdgpu_userq_suspend(struct amdgpu_device *adev); int amdgpu_userq_resume(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index eba9fb359047..85e9edc1cb6f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -141,6 +141,8 @@ static void amdgpu_userq_walk_and_drop_fence_drv(struct xarray *xa) void amdgpu_userq_fence_driver_free(struct amdgpu_usermode_queue *userq) { + dma_fence_put(userq->last_fence); + amdgpu_userq_walk_and_drop_fence_drv(&userq->fence_drv_xa); xa_destroy(&userq->fence_drv_xa); /* Drop the fence_drv reference held by user queue */ @@ -471,6 +473,9 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, struct drm_exec exec; u64 wptr; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + num_syncobj_handles = args->num_syncobj_handles; syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles), size_mul(sizeof(u32), num_syncobj_handles)); @@ -653,6 +658,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, int r, i, rentry, wentry, cnt; struct drm_exec exec; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + num_read_bo_handles = wait_info->num_bo_read_handles; bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles), size_mul(sizeof(u32), num_read_bo_handles)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c362d4dfb5bb..a67285118c37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1069,9 +1069,7 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params, } /* Prepare a TLB flush fence to be attached to PTs */ - if (!params->unlocked && - /* SI doesn't support pasid or KIQ/MES */ - params->adev->family > AMDGPU_FAMILY_SI) { + if (!params->unlocked) { amdgpu_vm_tlb_fence_create(params->adev, vm, fence); /* Makes sure no PD/PT is freed before the flush */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index d01d2712cf57..b786967022d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -278,7 +278,6 @@ static void gfx_v12_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance, int xcc_id); static u32 gfx_v12_0_get_wgp_active_bitmap_per_sh(struct amdgpu_device *adev); -static void gfx_v12_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure); static void gfx_v12_0_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val); static int gfx_v12_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev); @@ -4634,16 +4633,6 @@ static int gfx_v12_0_ring_preempt_ib(struct amdgpu_ring *ring) return r; } -static void gfx_v12_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, - bool start, - bool secure) -{ - uint32_t v = secure ? FRAME_TMZ : 0; - - amdgpu_ring_write(ring, PACKET3(PACKET3_FRAME_CONTROL, 0)); - amdgpu_ring_write(ring, v | FRAME_CMD(start ? 0 : 1)); -} - static void gfx_v12_0_ring_emit_rreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t reg_val_offs) { @@ -5520,7 +5509,6 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_gfx = { .emit_cntxcntl = gfx_v12_0_ring_emit_cntxcntl, .init_cond_exec = gfx_v12_0_ring_emit_init_cond_exec, .preempt_ib = gfx_v12_0_ring_preempt_ib, - .emit_frame_cntl = gfx_v12_0_ring_emit_frame_cntl, .emit_wreg = gfx_v12_0_ring_emit_wreg, .emit_reg_wait = gfx_v12_0_ring_emit_reg_wait, .emit_reg_write_reg_wait = gfx_v12_0_ring_emit_reg_write_reg_wait, diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 8ad7519f7b58..f1ee3921d970 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1235,16 +1235,16 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev, *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_NC); break; case AMDGPU_VM_MTYPE_WC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC); break; case AMDGPU_VM_MTYPE_RW: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW); break; case AMDGPU_VM_MTYPE_CC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC); break; case AMDGPU_VM_MTYPE_UC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC); break; } diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index 4258d3e0b706..0002bcc6c4ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -26,6 +26,7 @@ */ #include <linux/gpio/machine.h> +#include <linux/pm_runtime.h> #include "amdgpu.h" #include "isp_v4_1_1.h" @@ -145,6 +146,9 @@ static int isp_genpd_add_device(struct device *dev, void *data) return -ENODEV; } + /* The devices will be managed by the pm ops from the parent */ + dev_pm_syscore_device(dev, true); + exit: /* Continue to add */ return 0; @@ -177,12 +181,47 @@ static int isp_genpd_remove_device(struct device *dev, void *data) drm_err(&adev->ddev, "Failed to remove dev from genpd %d\n", ret); return -ENODEV; } + dev_pm_syscore_device(dev, false); exit: /* Continue to remove */ return 0; } +static int isp_suspend_device(struct device *dev, void *data) +{ + return pm_runtime_force_suspend(dev); +} + +static int isp_resume_device(struct device *dev, void *data) +{ + return pm_runtime_force_resume(dev); +} + +static int isp_v4_1_1_hw_suspend(struct amdgpu_isp *isp) +{ + int r; + + r = device_for_each_child(isp->parent, NULL, + isp_suspend_device); + if (r) + dev_err(isp->parent, "failed to suspend hw devices (%d)\n", r); + + return r; +} + +static int isp_v4_1_1_hw_resume(struct amdgpu_isp *isp) +{ + int r; + + r = device_for_each_child(isp->parent, NULL, + isp_resume_device); + if (r) + dev_err(isp->parent, "failed to resume hw device (%d)\n", r); + + return r; +} + static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) { const struct software_node *amd_camera_node, *isp4_node; @@ -369,6 +408,8 @@ static int isp_v4_1_1_hw_fini(struct amdgpu_isp *isp) static const struct isp_funcs isp_v4_1_1_funcs = { .hw_init = isp_v4_1_1_hw_init, .hw_fini = isp_v4_1_1_hw_fini, + .hw_suspend = isp_v4_1_1_hw_suspend, + .hw_resume = isp_v4_1_1_hw_resume, }; void isp_v4_1_1_set_isp_funcs(struct amdgpu_isp *isp) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h index 27aa1a5b120f..fbb751821c69 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h @@ -120,8 +120,7 @@ static inline bool kfd_dbg_has_gws_support(struct kfd_node *dev) && dev->kfd->mec2_fw_version < 0x1b6) || (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->kfd->mec2_fw_version < 0x30) || - (KFD_GC_VERSION(dev) >= IP_VERSION(11, 0, 0) && - KFD_GC_VERSION(dev) < IP_VERSION(12, 0, 0))) + kfd_dbg_has_cwsr_workaround(dev)) return false; /* Assume debugging and cooperative launch supported otherwise. */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index d7a2e7178ea9..625ea8ab7a74 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1209,14 +1209,8 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, pr_debug_ratelimited("Evicting process pid %d queues\n", pdd->process->lead_thread->pid); - if (dqm->dev->kfd->shared_resources.enable_mes) { + if (dqm->dev->kfd->shared_resources.enable_mes) pdd->last_evict_timestamp = get_jiffies_64(); - retval = suspend_all_queues_mes(dqm); - if (retval) { - dev_err(dev, "Suspending all queues failed"); - goto out; - } - } /* Mark all queues as evicted. Deactivate all active queues on * the qpd. @@ -1246,10 +1240,6 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES : KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, USE_DEFAULT_GRACE_PERIOD); - } else { - retval = resume_all_queues_mes(dqm); - if (retval) - dev_err(dev, "Resuming all queues failed"); } out: @@ -2919,6 +2909,14 @@ static int allocate_hiq_sdma_mqd(struct device_queue_manager *dqm) return retval; } +static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, + struct kfd_mem_obj *mqd) +{ + WARN(!mqd, "No hiq sdma mqd trunk to free"); + + amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); +} + struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) { struct device_queue_manager *dqm; @@ -3042,19 +3040,14 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) return dqm; } + if (!dev->kfd->shared_resources.enable_mes) + deallocate_hiq_sdma_mqd(dev, &dqm->hiq_sdma_mqd); + out_free: kfree(dqm); return NULL; } -static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, - struct kfd_mem_obj *mqd) -{ - WARN(!mqd, "No hiq sdma mqd trunk to free"); - - amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); -} - void device_queue_manager_uninit(struct device_queue_manager *dqm) { dqm->ops.stop(dqm); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index af53e796ea1b..6ada7b4af7c6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -217,7 +217,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) page = pfn_to_page(pfn); svm_range_bo_ref(prange->svm_bo); page->zone_device_data = prange->svm_bo; - zone_device_page_init(page, 0); + zone_device_page_init(page, page_pgmap(page), 0); } static void 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 740711ac1037..1ea5a250440f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5266,6 +5266,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) struct amdgpu_dm_backlight_caps *caps; char bl_name[16]; int min, max; + int real_brightness; + int init_brightness; if (aconnector->bl_idx == -1) return; @@ -5290,6 +5292,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) } else props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL; + init_brightness = props.brightness; + if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) { drm_info(drm, "Using custom brightness curve\n"); props.scale = BACKLIGHT_SCALE_NON_LINEAR; @@ -5308,8 +5312,20 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) if (IS_ERR(dm->backlight_dev[aconnector->bl_idx])) { drm_err(drm, "DM: Backlight registration failed!\n"); dm->backlight_dev[aconnector->bl_idx] = NULL; - } else + } else { + /* + * dm->brightness[x] can be inconsistent just after startup until + * ops.get_brightness is called. + */ + real_brightness = + amdgpu_dm_backlight_ops.get_brightness(dm->backlight_dev[aconnector->bl_idx]); + + if (real_brightness != init_brightness) { + dm->actual_brightness[aconnector->bl_idx] = real_brightness; + dm->brightness[aconnector->bl_idx] = real_brightness; + } drm_dbg_driver(drm, "DM: Registered Backlight device: %s\n", bl_name); + } } static int initialize_plane(struct amdgpu_display_manager *dm, @@ -5626,7 +5642,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) if (psr_feature_enabled) { amdgpu_dm_set_psr_caps(link); - drm_info(adev_to_drm(adev), "PSR support %d, DC PSR ver %d, sink PSR ver %d DPCD caps 0x%x su_y_granularity %d\n", + drm_info(adev_to_drm(adev), "%s: PSR support %d, DC PSR ver %d, sink PSR ver %d DPCD caps 0x%x su_y_granularity %d\n", + aconnector->base.name, link->psr_settings.psr_feature_enabled, link->psr_settings.psr_version, link->dpcd_caps.psr_info.psr_version, @@ -8930,9 +8947,18 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, mutex_init(&aconnector->hpd_lock); mutex_init(&aconnector->handle_mst_msg_ready); - aconnector->hdmi_hpd_debounce_delay_ms = AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS; - INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); - aconnector->hdmi_prev_sink = NULL; + /* + * If HDMI HPD debounce delay is set, use the minimum between selected + * value and AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS + */ + if (amdgpu_hdmi_hpd_debounce_delay_ms) { + aconnector->hdmi_hpd_debounce_delay_ms = min(amdgpu_hdmi_hpd_debounce_delay_ms, + AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS); + INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); + aconnector->hdmi_prev_sink = NULL; + } else { + aconnector->hdmi_hpd_debounce_delay_ms = 0; + } /* * configure support HPD hot plug connector_>polled default value is 0 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 bd0403005f37..beb0d04d3e68 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -59,7 +59,10 @@ #define AMDGPU_HDR_MULT_DEFAULT (0x100000000LL) -#define AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS 1500 +/* + * Maximum HDMI HPD debounce delay in milliseconds + */ +#define AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS 5000 /* #include "include/amdgpu_dal_power_if.h" #include "amdgpu_dm_irq.h" diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c index d585618b8064..a2de3bba8346 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c @@ -79,7 +79,6 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr goto cleanup; list->type = ops[i]->base.id; - list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", ops[i]->base.id); i++; @@ -197,6 +196,9 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr goto cleanup; drm_colorop_set_next_property(ops[i-1], ops[i]); + + list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", ops[0]->base.id); + return 0; cleanup: diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 697e232acebf..9fcd72d87d25 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -248,8 +248,6 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work) struct vblank_control_work *vblank_work = container_of(work, struct vblank_control_work, work); struct amdgpu_display_manager *dm = vblank_work->dm; - struct amdgpu_device *adev = drm_to_adev(dm->ddev); - int r; mutex_lock(&dm->dc_lock); @@ -279,16 +277,7 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work) if (dm->active_vblank_irq_count == 0) { dc_post_update_surfaces_to_stream(dm->dc); - - r = amdgpu_dpm_pause_power_profile(adev, true); - if (r) - dev_warn(adev->dev, "failed to set default power profile mode\n"); - dc_allow_idle_optimizations(dm->dc, true); - - r = amdgpu_dpm_pause_power_profile(adev, false); - if (r) - dev_warn(adev->dev, "failed to restore the power profile mode\n"); } mutex_unlock(&dm->dc_lock); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 0a2a3f233a0e..e7b0928bd3db 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -915,13 +915,19 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev) struct amdgpu_dm_connector *amdgpu_dm_connector; const struct dc_link *dc_link; - use_polling |= connector->polled != DRM_CONNECTOR_POLL_HPD; - if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) continue; amdgpu_dm_connector = to_amdgpu_dm_connector(connector); + /* + * Analog connectors may be hot-plugged unlike other connector + * types that don't support HPD. Only poll analog connectors. + */ + use_polling |= + amdgpu_dm_connector->dc_link && + dc_connector_supports_analog(amdgpu_dm_connector->dc_link->link_id.id); + dc_link = amdgpu_dm_connector->dc_link; /* diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 2e3ee78999d9..7c4496fb4b9d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -1790,12 +1790,13 @@ dm_atomic_plane_get_property(struct drm_plane *plane, static int dm_plane_init_colorops(struct drm_plane *plane) { - struct drm_prop_enum_list pipelines[MAX_COLOR_PIPELINES]; + struct drm_prop_enum_list pipelines[MAX_COLOR_PIPELINES] = {}; struct drm_device *dev = plane->dev; struct amdgpu_device *adev = drm_to_adev(dev); struct dc *dc = adev->dm.dc; int len = 0; - int ret; + int ret = 0; + int i; if (plane->type == DRM_PLANE_TYPE_CURSOR) return 0; @@ -1806,7 +1807,7 @@ dm_plane_init_colorops(struct drm_plane *plane) if (ret) { drm_err(plane->dev, "Failed to create color pipeline for plane %d: %d\n", plane->base.id, ret); - return ret; + goto out; } len++; @@ -1814,7 +1815,11 @@ dm_plane_init_colorops(struct drm_plane *plane) drm_plane_create_color_pipeline_property(plane, pipelines, len); } - return 0; +out: + for (i = 0; i < len; i++) + kfree(pipelines[i].name); + + return ret; } #endif diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index d1471f34e419..9f11e6ca4051 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -763,14 +763,14 @@ static enum bp_result bios_parser_encoder_control( return BP_RESULT_FAILURE; return bp->cmd_tbl.dac1_encoder_control( - bp, cntl->action == ENCODER_CONTROL_ENABLE, + bp, cntl->action, cntl->pixel_clock, ATOM_DAC1_PS2); } else if (cntl->engine_id == ENGINE_ID_DACB) { if (!bp->cmd_tbl.dac2_encoder_control) return BP_RESULT_FAILURE; return bp->cmd_tbl.dac2_encoder_control( - bp, cntl->action == ENCODER_CONTROL_ENABLE, + bp, cntl->action, cntl->pixel_clock, ATOM_DAC1_PS2); } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c index 22457f417e65..76a3559f0ddc 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c @@ -1797,7 +1797,30 @@ static enum bp_result select_crtc_source_v3( ¶ms.ucEncodeMode)) return BP_RESULT_BADINPUT; - params.ucDstBpc = bp_params->bit_depth; + switch (bp_params->color_depth) { + case COLOR_DEPTH_UNDEFINED: + params.ucDstBpc = PANEL_BPC_UNDEFINE; + break; + case COLOR_DEPTH_666: + params.ucDstBpc = PANEL_6BIT_PER_COLOR; + break; + default: + case COLOR_DEPTH_888: + params.ucDstBpc = PANEL_8BIT_PER_COLOR; + break; + case COLOR_DEPTH_101010: + params.ucDstBpc = PANEL_10BIT_PER_COLOR; + break; + case COLOR_DEPTH_121212: + params.ucDstBpc = PANEL_12BIT_PER_COLOR; + break; + case COLOR_DEPTH_141414: + dm_error("14-bit color not supported by SelectCRTC_Source v3\n"); + break; + case COLOR_DEPTH_161616: + params.ucDstBpc = PANEL_16BIT_PER_COLOR; + break; + } if (EXEC_BIOS_CMD_TABLE(SelectCRTC_Source, params)) result = BP_RESULT_OK; @@ -1815,12 +1838,12 @@ static enum bp_result select_crtc_source_v3( static enum bp_result dac1_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); static enum bp_result dac2_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); @@ -1846,12 +1869,15 @@ static void init_dac_encoder_control(struct bios_parser *bp) static void dac_encoder_control_prepare_params( DAC_ENCODER_CONTROL_PS_ALLOCATION *params, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { params->ucDacStandard = dac_standard; - if (enable) + if (action == ENCODER_CONTROL_SETUP || + action == ENCODER_CONTROL_INIT) + params->ucAction = ATOM_ENCODER_INIT; + else if (action == ENCODER_CONTROL_ENABLE) params->ucAction = ATOM_ENABLE; else params->ucAction = ATOM_DISABLE; @@ -1864,7 +1890,7 @@ static void dac_encoder_control_prepare_params( static enum bp_result dac1_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { @@ -1873,7 +1899,7 @@ static enum bp_result dac1_encoder_control_v1( dac_encoder_control_prepare_params( ¶ms, - enable, + action, pixel_clock, dac_standard); @@ -1885,7 +1911,7 @@ static enum bp_result dac1_encoder_control_v1( static enum bp_result dac2_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { @@ -1894,7 +1920,7 @@ static enum bp_result dac2_encoder_control_v1( dac_encoder_control_prepare_params( ¶ms, - enable, + action, pixel_clock, dac_standard); diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.h b/drivers/gpu/drm/amd/display/dc/bios/command_table.h index e89b1ba0048b..78bdbcaa61c8 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.h @@ -57,12 +57,12 @@ struct cmd_tbl { struct bp_crtc_source_select *bp_params); enum bp_result (*dac1_encoder_control)( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); enum bp_result (*dac2_encoder_control)( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); enum bp_result (*dac1_output_control)( diff --git a/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h b/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h index b015e80672ec..fcd3ab4b0045 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h @@ -41,7 +41,7 @@ /* kHZ*/ #define DP_ADAPTOR_DVI_MAX_TMDS_CLK 165000 /* kHZ*/ -#define DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK 165000 +#define DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK 340000 struct dp_hdmi_dongle_signature_data { int8_t id[15];/* "DP-HDMI ADAPTOR"*/ diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index b357683b4255..268b5fbdb48b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -30,7 +30,11 @@ dml_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) - frame_warn_limit := 3072 + ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy) + frame_warn_limit := 4096 + else + frame_warn_limit := 3072 + endif else frame_warn_limit := 2048 endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index 8d24763938ea..1df3412be346 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -77,32 +77,14 @@ static unsigned int dscceComputeDelay( static unsigned int dscComputeDelay( enum output_format_class pixelFormat, enum output_encoder_class Output); -// Super monster function with some 45 argument static bool CalculatePrefetchSchedule( struct display_mode_lib *mode_lib, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + unsigned int k, Pipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -116,7 +98,6 @@ static bool CalculatePrefetchSchedule( unsigned int MaxNumSwathY, double PrefetchSourceLinesC, unsigned int SwathWidthC, - int BytePerPixelC, double VInitPreFillC, unsigned int MaxNumSwathC, long swath_width_luma_ub, @@ -124,9 +105,6 @@ static bool CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, - bool ProgressiveToInterlaceUnitInOPP, - double *DSTXAfterScaler, - double *DSTYAfterScaler, double *DestinationLinesForPrefetch, double *PrefetchBandwidth, double *DestinationLinesToRequestVMInVBlank, @@ -135,14 +113,7 @@ static bool CalculatePrefetchSchedule( double *VRatioPrefetchC, double *RequiredPrefetchPixDataBWLuma, double *RequiredPrefetchPixDataBWChroma, - bool *NotEnoughTimeForDynamicMetadata, - double *Tno_bw, - double *prefetch_vmrow_bw, - double *Tdmdl_vm, - double *Tdmdl, - unsigned int *VUpdateOffsetPix, - double *VUpdateWidthPix, - double *VReadyOffsetPix); + bool *NotEnoughTimeForDynamicMetadata); static double RoundToDFSGranularityUp(double Clock, double VCOSpeed); static double RoundToDFSGranularityDown(double Clock, double VCOSpeed); static void CalculateDCCConfiguration( @@ -294,62 +265,23 @@ static void CalculateDynamicMetadataParameters( static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int DPPOutputBufferPixels, - unsigned int DETBufferSizeInKByte, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool GPUVMEnable, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, double DCFCLKDeepSleep, unsigned int DPPPerPlane[], - bool DCCEnable[], double DPPCLK[], unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], - enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, - double *StutterExitWatermark, - double *StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported); + enum clock_change_support *DRAMClockChangeSupport); static void CalculateDCFCLKDeepSleep( struct display_mode_lib *mode_lib, unsigned int NumberOfActivePlanes, @@ -810,29 +742,12 @@ static unsigned int dscComputeDelay(enum output_format_class pixelFormat, enum o static bool CalculatePrefetchSchedule( struct display_mode_lib *mode_lib, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + unsigned int k, Pipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -846,7 +761,6 @@ static bool CalculatePrefetchSchedule( unsigned int MaxNumSwathY, double PrefetchSourceLinesC, unsigned int SwathWidthC, - int BytePerPixelC, double VInitPreFillC, unsigned int MaxNumSwathC, long swath_width_luma_ub, @@ -854,9 +768,6 @@ static bool CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, - bool ProgressiveToInterlaceUnitInOPP, - double *DSTXAfterScaler, - double *DSTYAfterScaler, double *DestinationLinesForPrefetch, double *PrefetchBandwidth, double *DestinationLinesToRequestVMInVBlank, @@ -865,15 +776,10 @@ static bool CalculatePrefetchSchedule( double *VRatioPrefetchC, double *RequiredPrefetchPixDataBWLuma, double *RequiredPrefetchPixDataBWChroma, - bool *NotEnoughTimeForDynamicMetadata, - double *Tno_bw, - double *prefetch_vmrow_bw, - double *Tdmdl_vm, - double *Tdmdl, - unsigned int *VUpdateOffsetPix, - double *VUpdateWidthPix, - double *VReadyOffsetPix) + bool *NotEnoughTimeForDynamicMetadata) { + struct vba_vars_st *v = &mode_lib->vba; + double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater; bool MyError = false; unsigned int DPPCycles = 0, DISPCLKCycles = 0; double DSTTotalPixelsAfterScaler = 0; @@ -905,26 +811,26 @@ static bool CalculatePrefetchSchedule( double Tdmec = 0; double Tdmsks = 0; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMInefficiencyFactor = PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly; - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMInefficiencyFactor = v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly; + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMInefficiencyFactor = 1; HostVMDynamicLevelsTrips = 0; } CalculateDynamicMetadataParameters( - MaxInterDCNTileRepeaters, + v->MaxInterDCNTileRepeaters, myPipe->DPPCLK, myPipe->DISPCLK, myPipe->DCFCLKDeepSleep, myPipe->PixelClock, myPipe->HTotal, myPipe->VBlank, - DynamicMetadataTransmittedBytes, - DynamicMetadataLinesBeforeActiveRequired, + v->DynamicMetadataTransmittedBytes[k], + v->DynamicMetadataLinesBeforeActiveRequired[k], myPipe->InterlaceEnable, - ProgressiveToInterlaceUnitInOPP, + v->ProgressiveToInterlaceUnitInOPP, &Tsetup, &Tdmbf, &Tdmec, @@ -932,16 +838,16 @@ static bool CalculatePrefetchSchedule( LineTime = myPipe->HTotal / myPipe->PixelClock; trip_to_mem = UrgentLatency; - Tvm_trips = UrgentExtraLatency + trip_to_mem * (GPUVMPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); + Tvm_trips = UrgentExtraLatency + trip_to_mem * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); - if (DynamicMetadataVMEnabled == true && GPUVMEnable == true) { - *Tdmdl = TWait + Tvm_trips + trip_to_mem; + if (v->DynamicMetadataVMEnabled == true && v->GPUVMEnable == true) { + v->Tdmdl[k] = TWait + Tvm_trips + trip_to_mem; } else { - *Tdmdl = TWait + UrgentExtraLatency; + v->Tdmdl[k] = TWait + UrgentExtraLatency; } - if (DynamicMetadataEnable == true) { - if (VStartup * LineTime < Tsetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) { + if (v->DynamicMetadataEnable[k] == true) { + if (VStartup * LineTime < Tsetup + v->Tdmdl[k] + Tdmbf + Tdmec + Tdmsks) { *NotEnoughTimeForDynamicMetadata = true; } else { *NotEnoughTimeForDynamicMetadata = false; @@ -949,39 +855,39 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", Tdmbf); dml_print("DML: Tdmec: %fus - time dio takes to transfer dmd\n", Tdmec); dml_print("DML: Tdmsks: %fus - time before active dmd must complete transmission at dio\n", Tdmsks); - dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", *Tdmdl); + dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", v->Tdmdl[k]); } } else { *NotEnoughTimeForDynamicMetadata = false; } - *Tdmdl_vm = (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true && GPUVMEnable == true ? TWait + Tvm_trips : 0); + v->Tdmdl_vm[k] = (v->DynamicMetadataEnable[k] == true && v->DynamicMetadataVMEnabled == true && v->GPUVMEnable == true ? TWait + Tvm_trips : 0); if (myPipe->ScalerEnabled) - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCL; else - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCLLBOnly; - DPPCycles = DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor; + DPPCycles = DPPCycles + myPipe->NumberOfCursors * v->DPPCLKDelayCNVCCursor; - DISPCLKCycles = DISPCLKDelaySubtotal; + DISPCLKCycles = v->DISPCLKDelaySubtotal; if (myPipe->DPPCLK == 0.0 || myPipe->DISPCLK == 0.0) return true; - *DSTXAfterScaler = DPPCycles * myPipe->PixelClock / myPipe->DPPCLK + DISPCLKCycles * myPipe->PixelClock / myPipe->DISPCLK + v->DSTXAfterScaler[k] = DPPCycles * myPipe->PixelClock / myPipe->DPPCLK + DISPCLKCycles * myPipe->PixelClock / myPipe->DISPCLK + DSCDelay; - *DSTXAfterScaler = *DSTXAfterScaler + ((myPipe->ODMCombineEnabled)?18:0) + (myPipe->DPPPerPlane - 1) * DPP_RECOUT_WIDTH; + v->DSTXAfterScaler[k] = v->DSTXAfterScaler[k] + ((myPipe->ODMCombineEnabled)?18:0) + (myPipe->DPPPerPlane - 1) * DPP_RECOUT_WIDTH; - if (OutputFormat == dm_420 || (myPipe->InterlaceEnable && ProgressiveToInterlaceUnitInOPP)) - *DSTYAfterScaler = 1; + if (v->OutputFormat[k] == dm_420 || (myPipe->InterlaceEnable && v->ProgressiveToInterlaceUnitInOPP)) + v->DSTYAfterScaler[k] = 1; else - *DSTYAfterScaler = 0; + v->DSTYAfterScaler[k] = 0; - DSTTotalPixelsAfterScaler = *DSTYAfterScaler * myPipe->HTotal + *DSTXAfterScaler; - *DSTYAfterScaler = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1); - *DSTXAfterScaler = DSTTotalPixelsAfterScaler - ((double) (*DSTYAfterScaler * myPipe->HTotal)); + DSTTotalPixelsAfterScaler = v->DSTYAfterScaler[k] * myPipe->HTotal + v->DSTXAfterScaler[k]; + v->DSTYAfterScaler[k] = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1); + v->DSTXAfterScaler[k] = DSTTotalPixelsAfterScaler - ((double) (v->DSTYAfterScaler[k] * myPipe->HTotal)); MyError = false; @@ -990,33 +896,33 @@ static bool CalculatePrefetchSchedule( Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1) / 4 * LineTime; Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1) / 4 * LineTime; - if (GPUVMEnable) { - if (GPUVMPageTableLevels >= 3) { - *Tno_bw = UrgentExtraLatency + trip_to_mem * ((GPUVMPageTableLevels - 2) - 1); + if (v->GPUVMEnable) { + if (v->GPUVMMaxPageTableLevels >= 3) { + v->Tno_bw[k] = UrgentExtraLatency + trip_to_mem * ((v->GPUVMMaxPageTableLevels - 2) - 1); } else - *Tno_bw = 0; + v->Tno_bw[k] = 0; } else if (!myPipe->DCCEnable) - *Tno_bw = LineTime; + v->Tno_bw[k] = LineTime; else - *Tno_bw = LineTime / 4; + v->Tno_bw[k] = LineTime / 4; - dst_y_prefetch_equ = VStartup - (Tsetup + dml_max(TWait + TCalc, *Tdmdl)) / LineTime - - (*DSTYAfterScaler + *DSTXAfterScaler / myPipe->HTotal); + dst_y_prefetch_equ = VStartup - (Tsetup + dml_max(TWait + TCalc, v->Tdmdl[k])) / LineTime + - (v->DSTYAfterScaler[k] + v->DSTXAfterScaler[k] / myPipe->HTotal); dst_y_prefetch_equ = dml_min(dst_y_prefetch_equ, 63.75); // limit to the reg limit of U6.2 for DST_Y_PREFETCH Lsw_oto = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC); Tsw_oto = Lsw_oto * LineTime; - prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) / Tsw_oto; + prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) / Tsw_oto; - if (GPUVMEnable == true) { - Tvm_oto = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, + if (v->GPUVMEnable == true) { + Tvm_oto = dml_max3(v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, Tvm_trips, LineTime / 4.0); } else Tvm_oto = LineTime / 4.0; - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_oto = dml_max3( (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto, LineTime - Tvm_oto, LineTime / 4); @@ -1042,10 +948,10 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", Tdmbf); dml_print("DML: Tdmec: %fus - time dio takes to transfer dmd\n", Tdmec); dml_print("DML: Tdmsks: %fus - time before active dmd must complete transmission at dio\n", Tdmsks); - dml_print("DML: Tdmdl_vm: %fus - time for vm stages of dmd \n", *Tdmdl_vm); - dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", *Tdmdl); - dml_print("DML: dst_x_after_scl: %f pixels - number of pixel clocks pipeline and buffer delay after scaler \n", *DSTXAfterScaler); - dml_print("DML: dst_y_after_scl: %d lines - number of lines of pipeline and buffer delay after scaler \n", (int)*DSTYAfterScaler); + dml_print("DML: Tdmdl_vm: %fus - time for vm stages of dmd \n", v->Tdmdl_vm[k]); + dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", v->Tdmdl[k]); + dml_print("DML: dst_x_after_scl: %f pixels - number of pixel clocks pipeline and buffer delay after scaler \n", v->DSTXAfterScaler[k]); + dml_print("DML: dst_y_after_scl: %d lines - number of lines of pipeline and buffer delay after scaler \n", (int)v->DSTYAfterScaler[k]); *PrefetchBandwidth = 0; *DestinationLinesToRequestVMInVBlank = 0; @@ -1059,26 +965,26 @@ static bool CalculatePrefetchSchedule( double PrefetchBandwidth3 = 0; double PrefetchBandwidth4 = 0; - if (Tpre_rounded - *Tno_bw > 0) + if (Tpre_rounded - v->Tno_bw[k] > 0) PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY - + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) - / (Tpre_rounded - *Tno_bw); + + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) + / (Tpre_rounded - v->Tno_bw[k]); else PrefetchBandwidth1 = 0; - if (VStartup == MaxVStartup && (PrefetchBandwidth1 > 4 * prefetch_bw_oto) && (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - *Tno_bw) > 0) { - PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor) / (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - *Tno_bw); + if (VStartup == MaxVStartup && (PrefetchBandwidth1 > 4 * prefetch_bw_oto) && (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - v->Tno_bw[k]) > 0) { + PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor) / (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - v->Tno_bw[k]); } - if (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded > 0) + if (Tpre_rounded - v->Tno_bw[k] - 2 * Tr0_trips_rounded > 0) PrefetchBandwidth2 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * - BytePerPixelC) / - (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded); + v->BytePerPixelC[k]) / + (Tpre_rounded - v->Tno_bw[k] - 2 * Tr0_trips_rounded); else PrefetchBandwidth2 = 0; @@ -1086,7 +992,7 @@ static bool CalculatePrefetchSchedule( PrefetchBandwidth3 = (2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * - swath_width_chroma_ub * BytePerPixelC) / (Tpre_rounded - + swath_width_chroma_ub * v->BytePerPixelC[k]) / (Tpre_rounded - Tvm_trips_rounded); else PrefetchBandwidth3 = 0; @@ -1096,7 +1002,7 @@ static bool CalculatePrefetchSchedule( } if (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded > 0) - PrefetchBandwidth4 = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) + PrefetchBandwidth4 = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) / (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded); else PrefetchBandwidth4 = 0; @@ -1107,7 +1013,7 @@ static bool CalculatePrefetchSchedule( bool Case3OK; if (PrefetchBandwidth1 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1 >= Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth1 >= Tr0_trips_rounded) { Case1OK = true; } else { @@ -1118,7 +1024,7 @@ static bool CalculatePrefetchSchedule( } if (PrefetchBandwidth2 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2 >= Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth2 < Tr0_trips_rounded) { Case2OK = true; } else { @@ -1129,7 +1035,7 @@ static bool CalculatePrefetchSchedule( } if (PrefetchBandwidth3 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 < Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth3 >= Tr0_trips_rounded) { Case3OK = true; } else { @@ -1152,13 +1058,13 @@ static bool CalculatePrefetchSchedule( dml_print("DML: prefetch_bw_equ: %f\n", prefetch_bw_equ); if (prefetch_bw_equ > 0) { - if (GPUVMEnable) { - Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); + if (v->GPUVMEnable) { + Tvm_equ = dml_max3(v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); } else { Tvm_equ = LineTime / 4; } - if ((GPUVMEnable || myPipe->DCCEnable)) { + if ((v->GPUVMEnable || myPipe->DCCEnable)) { Tr0_equ = dml_max4( (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips, @@ -1227,7 +1133,7 @@ static bool CalculatePrefetchSchedule( } *RequiredPrefetchPixDataBWLuma = (double) PrefetchSourceLinesY / LinesToRequestPrefetchPixelData * BytePerPixelY * swath_width_luma_ub / LineTime; - *RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData * BytePerPixelC * swath_width_chroma_ub / LineTime; + *RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData * v->BytePerPixelC[k] * swath_width_chroma_ub / LineTime; } else { MyError = true; dml_print("DML: MyErr set %s:%d\n", __FILE__, __LINE__); @@ -1243,9 +1149,9 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tr0: %fus - time to fetch first row of data pagetables and first row of meta data (done in parallel)\n", TimeForFetchingRowInVBlank); dml_print("DML: Tr1: %fus - time to fetch second row of data pagetables and second row of meta data (done in parallel)\n", TimeForFetchingRowInVBlank); dml_print("DML: Tsw: %fus = time to fetch enough pixel data and cursor data to feed the scalers init position and detile\n", (double)LinesToRequestPrefetchPixelData * LineTime); - dml_print("DML: To: %fus - time for propagation from scaler to optc\n", (*DSTYAfterScaler + ((*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime); + dml_print("DML: To: %fus - time for propagation from scaler to optc\n", (v->DSTYAfterScaler[k] + ((v->DSTXAfterScaler[k]) / (double) myPipe->HTotal)) * LineTime); dml_print("DML: Tvstartup - Tsetup - Tcalc - Twait - Tpre - To > 0\n"); - dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime - TimeForFetchingMetaPTE - 2 * TimeForFetchingRowInVBlank - (*DSTYAfterScaler + ((*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - Tsetup); + dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime - TimeForFetchingMetaPTE - 2 * TimeForFetchingRowInVBlank - (v->DSTYAfterScaler[k] + ((v->DSTXAfterScaler[k]) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - Tsetup); dml_print("DML: row_bytes = dpte_row_bytes (per_pipe) = PixelPTEBytesPerRow = : %d\n", PixelPTEBytesPerRow); } else { @@ -1276,7 +1182,7 @@ static bool CalculatePrefetchSchedule( dml_print("DML: MyErr set %s:%d\n", __FILE__, __LINE__); } - *prefetch_vmrow_bw = dml_max(prefetch_vm_bw, prefetch_row_bw); + v->prefetch_vmrow_bw[k] = dml_max(prefetch_vm_bw, prefetch_row_bw); } if (MyError) { @@ -2437,30 +2343,12 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->ErrorResult[k] = CalculatePrefetchSchedule( mode_lib, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + k, &myPipe, v->DSCDelay[k], - v->DPPCLKDelaySubtotal - + v->DPPCLKDelayCNVCFormater, - v->DPPCLKDelaySCL, - v->DPPCLKDelaySCLLBOnly, - v->DPPCLKDelayCNVCCursor, - v->DISPCLKDelaySubtotal, (unsigned int) (v->SwathWidthY[k] / v->HRatio[k]), - v->OutputFormat[k], - v->MaxInterDCNTileRepeaters, dml_min(v->VStartupLines, v->MaxVStartupLines[k]), v->MaxVStartupLines[k], - v->GPUVMMaxPageTableLevels, - v->GPUVMEnable, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->HostVMMinPageSize, - v->DynamicMetadataEnable[k], - v->DynamicMetadataVMEnabled, - v->DynamicMetadataLinesBeforeActiveRequired[k], - v->DynamicMetadataTransmittedBytes[k], v->UrgentLatency, v->UrgentExtraLatency, v->TCalc, @@ -2474,7 +2362,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->MaxNumSwathY[k], v->PrefetchSourceLinesC[k], v->SwathWidthC[k], - v->BytePerPixelC[k], v->VInitPreFillC[k], v->MaxNumSwathC[k], v->swath_width_luma_ub[k], @@ -2482,9 +2369,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, - v->ProgressiveToInterlaceUnitInOPP, - &v->DSTXAfterScaler[k], - &v->DSTYAfterScaler[k], &v->DestinationLinesForPrefetch[k], &v->PrefetchBandwidth[k], &v->DestinationLinesToRequestVMInVBlank[k], @@ -2493,14 +2377,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman &v->VRatioPrefetchC[k], &v->RequiredPrefetchPixDataBWLuma[k], &v->RequiredPrefetchPixDataBWChroma[k], - &v->NotEnoughTimeForDynamicMetadata[k], - &v->Tno_bw[k], - &v->prefetch_vmrow_bw[k], - &v->Tdmdl_vm[k], - &v->Tdmdl[k], - &v->VUpdateOffsetPix[k], - &v->VUpdateWidthPix[k], - &v->VReadyOffsetPix[k]); + &v->NotEnoughTimeForDynamicMetadata[k]); if (v->BlendingAndTiming[k] == k) { double TotalRepeaterDelayTime = v->MaxInterDCNTileRepeaters * (2 / v->DPPCLK[k] + 3 / v->DISPCLK); v->VUpdateWidthPix[k] = (14 / v->DCFCLKDeepSleep + 12 / v->DPPCLK[k] + TotalRepeaterDelayTime) * v->PixelClock[k]; @@ -2730,62 +2607,23 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, PrefetchMode, - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->DPPOutputBufferPixels, - v->DETBufferSizeInKByte[0], - v->WritebackInterfaceBufferSize, v->DCFCLK, v->ReturnBW, - v->GPUVMEnable, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgentLatency, v->UrgentExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLK, - v->FinalDRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, v->DCFCLKDeepSleep, v->DPPPerPlane, - v->DCCEnable, v->DPPCLK, v->DETBufferSizeY, v->DETBufferSizeC, v->SwathHeightY, v->SwathHeightC, - v->LBBitPerPixel, v->SwathWidthY, v->SwathWidthC, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->BytePerPixelDETY, v->BytePerPixelDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, - &DRAMClockChangeSupport, - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &v->StutterExitWatermark, - &v->StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &DRAMClockChangeSupport); for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->WritebackEnable[k] == true) { @@ -4770,29 +4608,12 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->NoTimeForPrefetch[i][j][k] = CalculatePrefetchSchedule( mode_lib, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + k, &myPipe, v->DSCDelayPerState[i][k], - v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater, - v->DPPCLKDelaySCL, - v->DPPCLKDelaySCLLBOnly, - v->DPPCLKDelayCNVCCursor, - v->DISPCLKDelaySubtotal, v->SwathWidthYThisState[k] / v->HRatio[k], - v->OutputFormat[k], - v->MaxInterDCNTileRepeaters, dml_min(v->MaxVStartup, v->MaximumVStartup[i][j][k]), v->MaximumVStartup[i][j][k], - v->GPUVMMaxPageTableLevels, - v->GPUVMEnable, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->HostVMMinPageSize, - v->DynamicMetadataEnable[k], - v->DynamicMetadataVMEnabled, - v->DynamicMetadataLinesBeforeActiveRequired[k], - v->DynamicMetadataTransmittedBytes[k], v->UrgLatency[i], v->ExtraLatency, v->TimeCalc, @@ -4806,7 +4627,6 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->MaxNumSwY[k], v->PrefetchLinesC[i][j][k], v->SwathWidthCThisState[k], - v->BytePerPixelC[k], v->PrefillC[k], v->MaxNumSwC[k], v->swath_width_luma_ub_this_state[k], @@ -4814,9 +4634,6 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, - v->ProgressiveToInterlaceUnitInOPP, - &v->DSTXAfterScaler[k], - &v->DSTYAfterScaler[k], &v->LineTimesForPrefetch[k], &v->PrefetchBW[k], &v->LinesForMetaPTE[k], @@ -4825,14 +4642,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &v->VRatioPreC[i][j][k], &v->RequiredPrefetchPixelDataBWLuma[i][j][k], &v->RequiredPrefetchPixelDataBWChroma[i][j][k], - &v->NoTimeForDynamicMetadata[i][j][k], - &v->Tno_bw[k], - &v->prefetch_vmrow_bw[k], - &v->Tdmdl_vm[k], - &v->Tdmdl[k], - &v->VUpdateOffsetPix[k], - &v->VUpdateWidthPix[k], - &v->VReadyOffsetPix[k]); + &v->NoTimeForDynamicMetadata[i][j][k]); } for (k = 0; k <= v->NumberOfActivePlanes - 1; k++) { @@ -5007,62 +4817,23 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, v->PrefetchModePerState[i][j], - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->DPPOutputBufferPixels, - v->DETBufferSizeInKByte[0], - v->WritebackInterfaceBufferSize, v->DCFCLKState[i][j], v->ReturnBWPerState[i][j], - v->GPUVMEnable, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgLatency[i], v->ExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLKPerState[i], - v->FinalDRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, v->ProjectedDCFCLKDeepSleep[i][j], v->NoOfDPPThisState, - v->DCCEnable, v->RequiredDPPCLKThisState, v->DETBufferSizeYThisState, v->DETBufferSizeCThisState, v->SwathHeightYThisState, v->SwathHeightCThisState, - v->LBBitPerPixel, v->SwathWidthYThisState, v->SwathWidthCThisState, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->BytePerPixelInDETY, v->BytePerPixelInDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, - &v->DRAMClockChangeSupport[i][j], - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &v->StutterExitWatermark, - &v->StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &v->DRAMClockChangeSupport[i][j]); } } @@ -5179,63 +4950,25 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int DPPOutputBufferPixels, - unsigned int DETBufferSizeInKByte, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool GPUVMEnable, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, double DCFCLKDeepSleep, unsigned int DPPPerPlane[], - bool DCCEnable[], double DPPCLK[], unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], - enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, - double *StutterExitWatermark, - double *StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported) + enum clock_change_support *DRAMClockChangeSupport) { + struct vba_vars_st *v = &mode_lib->vba; double EffectiveLBLatencyHidingY = 0; double EffectiveLBLatencyHidingC = 0; double LinesInDETY[DC__NUM_DPP__MAX] = { 0 }; @@ -5254,101 +4987,101 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double WritebackDRAMClockChangeLatencyHiding = 0; unsigned int k, j; - mode_lib->vba.TotalActiveDPP = 0; - mode_lib->vba.TotalDCCActiveDPP = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - mode_lib->vba.TotalActiveDPP = mode_lib->vba.TotalActiveDPP + DPPPerPlane[k]; - if (DCCEnable[k] == true) { - mode_lib->vba.TotalDCCActiveDPP = mode_lib->vba.TotalDCCActiveDPP + DPPPerPlane[k]; + v->TotalActiveDPP = 0; + v->TotalDCCActiveDPP = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + v->TotalActiveDPP = v->TotalActiveDPP + DPPPerPlane[k]; + if (v->DCCEnable[k] == true) { + v->TotalDCCActiveDPP = v->TotalDCCActiveDPP + DPPPerPlane[k]; } } - *UrgentWatermark = UrgentLatency + ExtraLatency; + v->UrgentWatermark = UrgentLatency + ExtraLatency; - *DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark; + v->DRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->UrgentWatermark; - mode_lib->vba.TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (WritebackEnable[k] == true) { - mode_lib->vba.TotalActiveWriteback = mode_lib->vba.TotalActiveWriteback + 1; + v->TotalActiveWriteback = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->WritebackEnable[k] == true) { + v->TotalActiveWriteback = v->TotalActiveWriteback + 1; } } - if (mode_lib->vba.TotalActiveWriteback <= 1) { - *WritebackUrgentWatermark = WritebackLatency; + if (v->TotalActiveWriteback <= 1) { + v->WritebackUrgentWatermark = v->WritebackLatency; } else { - *WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - if (mode_lib->vba.TotalActiveWriteback <= 1) { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency; + if (v->TotalActiveWriteback <= 1) { + v->WritebackDRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->WritebackLatency; } else { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackDRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { - mode_lib->vba.LBLatencyHidingSourceLinesY = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1); + v->LBLatencyHidingSourceLinesY = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); - mode_lib->vba.LBLatencyHidingSourceLinesC = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1); + v->LBLatencyHidingSourceLinesC = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); - EffectiveLBLatencyHidingY = mode_lib->vba.LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); - EffectiveLBLatencyHidingC = mode_lib->vba.LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); LinesInDETY[k] = (double) DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY[k] = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY[k] = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; if (BytePerPixelDETC[k] > 0) { - LinesInDETC = mode_lib->vba.DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; + LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k]; } else { LinesInDETC = 0; FullDETBufferingTimeC = 999999; } - ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY[k] - *UrgentWatermark - (HTotal[k] / PixelClock[k]) * (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) - *DRAMClockChangeWatermark; + ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY[k] - v->UrgentWatermark - (v->HTotal[k] / v->PixelClock[k]) * (v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { - ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k]; + if (v->NumberOfActivePlanes > 1) { + ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { - ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - *UrgentWatermark - (HTotal[k] / PixelClock[k]) * (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) - *DRAMClockChangeWatermark; + ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - v->UrgentWatermark - (v->HTotal[k] / v->PixelClock[k]) * (v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { - ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k]; + if (v->NumberOfActivePlanes > 1) { + ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k]; } - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); + v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); } else { - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; + v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; } - if (WritebackEnable[k] == true) { + if (v->WritebackEnable[k] == true) { - WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024 / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) { + WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024 / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2; } - if (mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) { + if (v->WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding * 2; } - WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - mode_lib->vba.WritebackDRAMClockChangeWatermark; - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = dml_min(mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k], WritebackDRAMClockChangeLatencyMargin); + WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark; + v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(v->ActiveDRAMClockChangeLatencyMargin[k], WritebackDRAMClockChangeLatencyMargin); } } - mode_lib->vba.MinActiveDRAMClockChangeMargin = 999999; + v->MinActiveDRAMClockChangeMargin = 999999; PlaneWithMinActiveDRAMClockChangeMargin = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] < mode_lib->vba.MinActiveDRAMClockChangeMargin) { - mode_lib->vba.MinActiveDRAMClockChangeMargin = mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k]; - if (BlendingAndTiming[k] == k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) { + v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k]; + if (v->BlendingAndTiming[k] == k) { PlaneWithMinActiveDRAMClockChangeMargin = k; } else { - for (j = 0; j < NumberOfActivePlanes; ++j) { - if (BlendingAndTiming[k] == j) { + for (j = 0; j < v->NumberOfActivePlanes; ++j) { + if (v->BlendingAndTiming[k] == j) { PlaneWithMinActiveDRAMClockChangeMargin = j; } } @@ -5356,40 +5089,40 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - *MinActiveDRAMClockChangeLatencySupported = mode_lib->vba.MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency; + v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->FinalDRAMClockChangeLatency; SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { - SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k]; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { + SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k]; } } - mode_lib->vba.TotalNumberOfActiveOTG = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (BlendingAndTiming[k] == k) { - mode_lib->vba.TotalNumberOfActiveOTG = mode_lib->vba.TotalNumberOfActiveOTG + 1; + v->TotalNumberOfActiveOTG = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->BlendingAndTiming[k] == k) { + v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1; } } - if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) { + if (v->MinActiveDRAMClockChangeMargin > 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; - } else if (((mode_lib->vba.SynchronizedVBlank == true || mode_lib->vba.TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0)) { + } else if (((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0)) { *DRAMClockChangeSupport = dm_dram_clock_change_vblank; } else { *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } FullDETBufferingTimeYStutterCriticalPlane = FullDETBufferingTimeY[0]; - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (FullDETBufferingTimeY[k] <= FullDETBufferingTimeYStutterCriticalPlane) { FullDETBufferingTimeYStutterCriticalPlane = FullDETBufferingTimeY[k]; - TimeToFinishSwathTransferStutterCriticalPlane = (SwathHeightY[k] - (LinesInDETY[k] - LinesInDETYRoundedDownToSwath[k])) * (HTotal[k] / PixelClock[k]) / VRatio[k]; + TimeToFinishSwathTransferStutterCriticalPlane = (SwathHeightY[k] - (LinesInDETY[k] - LinesInDETYRoundedDownToSwath[k])) * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; } } - *StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; - *StutterEnterPlusExitWatermark = dml_max(SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep, TimeToFinishSwathTransferStutterCriticalPlane); + v->StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; + v->StutterEnterPlusExitWatermark = dml_max(v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep, TimeToFinishSwathTransferStutterCriticalPlane); } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 0cdd8c74abdf..ebd74b43e935 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1610,38 +1610,12 @@ dce110_select_crtc_source(struct pipe_ctx *pipe_ctx) struct dc_bios *bios = link->ctx->dc_bios; struct bp_crtc_source_select crtc_source_select = {0}; enum engine_id engine_id = link->link_enc->preferred_engine; - uint8_t bit_depth; if (dc_is_rgb_signal(pipe_ctx->stream->signal)) engine_id = link->link_enc->analog_engine; - switch (pipe_ctx->stream->timing.display_color_depth) { - case COLOR_DEPTH_UNDEFINED: - bit_depth = 0; - break; - case COLOR_DEPTH_666: - bit_depth = 6; - break; - default: - case COLOR_DEPTH_888: - bit_depth = 8; - break; - case COLOR_DEPTH_101010: - bit_depth = 10; - break; - case COLOR_DEPTH_121212: - bit_depth = 12; - break; - case COLOR_DEPTH_141414: - bit_depth = 14; - break; - case COLOR_DEPTH_161616: - bit_depth = 16; - break; - } - crtc_source_select.controller_id = CONTROLLER_ID_D0 + pipe_ctx->stream_res.tg->inst; - crtc_source_select.bit_depth = bit_depth; + crtc_source_select.color_depth = pipe_ctx->stream->timing.display_color_depth; crtc_source_select.engine_id = engine_id; crtc_source_select.sink_signal = pipe_ctx->stream->signal; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 6d31f4967f1a..7fa6bc97a919 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -336,7 +336,7 @@ static void query_dp_dual_mode_adaptor( /* Assume we have no valid DP passive dongle connected */ *dongle = DISPLAY_DONGLE_NONE; - sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK; + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK; /* Read DP-HDMI dongle I2c (no response interpreted as DP-DVI dongle)*/ if (!i2c_read( @@ -392,6 +392,8 @@ static void query_dp_dual_mode_adaptor( } } + if (is_valid_hdmi_signature) + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK; if (is_type2_dongle) { uint32_t max_tmds_clk = @@ -932,7 +934,7 @@ static bool link_detect_dac_load_detect(struct dc_link *link) struct link_encoder *link_enc = link->link_enc; enum engine_id engine_id = link_enc->preferred_engine; enum dal_device_type device_type = DEVICE_TYPE_CRT; - enum bp_result bp_result; + enum bp_result bp_result = BP_RESULT_UNSUPPORTED; uint32_t enum_id; switch (engine_id) { @@ -946,7 +948,9 @@ static bool link_detect_dac_load_detect(struct dc_link *link) break; } - bp_result = bios->funcs->dac_load_detection(bios, engine_id, device_type, enum_id); + if (bios->funcs->dac_load_detection) + bp_result = bios->funcs->dac_load_detection(bios, engine_id, device_type, enum_id); + return bp_result == BP_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h index 973b6bdbac63..f40dc612ec73 100644 --- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h +++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h @@ -136,7 +136,7 @@ struct bp_crtc_source_select { enum engine_id engine_id; enum controller_id controller_id; enum signal_type sink_signal; - uint8_t bit_depth; + enum dc_color_depth color_depth; }; struct bp_transmitter_control { diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index 1f539cc65f41..695432d3045f 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -2273,8 +2273,6 @@ static int si_populate_smc_tdp_limits(struct amdgpu_device *adev, if (scaling_factor == 0) return -EINVAL; - memset(smc_table, 0, sizeof(SISLANDS_SMC_STATETABLE)); - ret = si_calculate_adjusted_tdp_limits(adev, false, /* ??? */ adev->pm.dpm.tdp_adjustment, @@ -2283,6 +2281,12 @@ static int si_populate_smc_tdp_limits(struct amdgpu_device *adev, if (ret) return ret; + if (adev->pdev->device == 0x6611 && adev->pdev->revision == 0x87) { + /* Workaround buggy powertune on Radeon 430 and 520. */ + tdp_limit = 32; + near_tdp_limit = 28; + } + smc_table->dpm2Params.TDPLimit = cpu_to_be32(si_scale_power_for_smc(tdp_limit, scaling_factor) * 1000); smc_table->dpm2Params.NearTDPLimit = @@ -2328,16 +2332,8 @@ static int si_populate_smc_tdp_limits_2(struct amdgpu_device *adev, if (ni_pi->enable_power_containment) { SISLANDS_SMC_STATETABLE *smc_table = &si_pi->smc_statetable; - u32 scaling_factor = si_get_smc_power_scaling_factor(adev); int ret; - memset(smc_table, 0, sizeof(SISLANDS_SMC_STATETABLE)); - - smc_table->dpm2Params.NearTDPLimit = - cpu_to_be32(si_scale_power_for_smc(adev->pm.dpm.near_tdp_limit_adjusted, scaling_factor) * 1000); - smc_table->dpm2Params.SafePowerLimit = - cpu_to_be32(si_scale_power_for_smc((adev->pm.dpm.near_tdp_limit_adjusted * SISLANDS_DPM2_TDP_SAFE_LIMIT_PERCENT) / 100, scaling_factor) * 1000); - ret = amdgpu_si_copy_bytes_to_smc(adev, (si_pi->state_table_start + offsetof(SISLANDS_SMC_STATETABLE, dpm2Params) + @@ -3473,10 +3469,15 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, (adev->pdev->revision == 0x80) || (adev->pdev->revision == 0x81) || (adev->pdev->revision == 0x83) || - (adev->pdev->revision == 0x87) || + (adev->pdev->revision == 0x87 && + adev->pdev->device != 0x6611) || (adev->pdev->device == 0x6604) || (adev->pdev->device == 0x6605)) { max_sclk = 75000; + } else if (adev->pdev->revision == 0x87 && + adev->pdev->device == 0x6611) { + /* Radeon 430 and 520 */ + max_sclk = 78000; } } @@ -7600,12 +7601,12 @@ static int si_dpm_set_interrupt_state(struct amdgpu_device *adev, case AMDGPU_IRQ_STATE_DISABLE: cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT); cg_thermal_int |= CG_THERMAL_INT__THERM_INT_MASK_HIGH_MASK; - WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int); + WREG32(mmCG_THERMAL_INT, cg_thermal_int); break; case AMDGPU_IRQ_STATE_ENABLE: cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT); cg_thermal_int &= ~CG_THERMAL_INT__THERM_INT_MASK_HIGH_MASK; - WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int); + WREG32(mmCG_THERMAL_INT, cg_thermal_int); break; default: break; @@ -7617,12 +7618,12 @@ static int si_dpm_set_interrupt_state(struct amdgpu_device *adev, case AMDGPU_IRQ_STATE_DISABLE: cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT); cg_thermal_int |= CG_THERMAL_INT__THERM_INT_MASK_LOW_MASK; - WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int); + WREG32(mmCG_THERMAL_INT, cg_thermal_int); break; case AMDGPU_IRQ_STATE_ENABLE: cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT); cg_thermal_int &= ~CG_THERMAL_INT__THERM_INT_MASK_LOW_MASK; - WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int); + WREG32(mmCG_THERMAL_INT, cg_thermal_int); break; default: break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 7c9f77124ab2..c4966dcc6875 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2455,24 +2455,21 @@ static int navi10_update_pcie_parameters(struct smu_context *smu, } for (i = 0; i < NUM_LINK_LEVELS; i++) { - if (pptable->PcieGenSpeed[i] > pcie_gen_cap || - pptable->PcieLaneCount[i] > pcie_width_cap) { - dpm_context->dpm_tables.pcie_table.pcie_gen[i] = - pptable->PcieGenSpeed[i] > pcie_gen_cap ? - pcie_gen_cap : pptable->PcieGenSpeed[i]; - dpm_context->dpm_tables.pcie_table.pcie_lane[i] = - pptable->PcieLaneCount[i] > pcie_width_cap ? - pcie_width_cap : pptable->PcieLaneCount[i]; - smu_pcie_arg = i << 16; - smu_pcie_arg |= pcie_gen_cap << 8; - smu_pcie_arg |= pcie_width_cap; - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_OverridePcieParameters, - smu_pcie_arg, - NULL); - if (ret) - break; - } + dpm_context->dpm_tables.pcie_table.pcie_gen[i] = + pptable->PcieGenSpeed[i] > pcie_gen_cap ? + pcie_gen_cap : pptable->PcieGenSpeed[i]; + dpm_context->dpm_tables.pcie_table.pcie_lane[i] = + pptable->PcieLaneCount[i] > pcie_width_cap ? + pcie_width_cap : pptable->PcieLaneCount[i]; + smu_pcie_arg = i << 16; + smu_pcie_arg |= dpm_context->dpm_tables.pcie_table.pcie_gen[i] << 8; + smu_pcie_arg |= dpm_context->dpm_tables.pcie_table.pcie_lane[i]; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_OverridePcieParameters, + smu_pcie_arg, + NULL); + if (ret) + return ret; } return ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 677781060246..eaeff6a9bc50 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2923,8 +2923,13 @@ static int smu_v13_0_0_mode1_reset(struct smu_context *smu) break; } - if (!ret) + if (!ret) { + /* disable mmio access while doing mode 1 reset*/ + smu->adev->no_hw_access = true; + /* ensure no_hw_access is globally visible before any MMIO */ + smp_mb(); msleep(SMU13_MODE1_RESET_WAIT_TIME_IN_MS); + } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 2cea688c604f..d7642d388bc3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1702,8 +1702,9 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu, table_context->power_play_table; PPTable_t *pptable = table_context->driver_pptable; CustomSkuTable_t *skutable = &pptable->CustomSkuTable; - uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; + int16_t od_percent_upper = 0, od_percent_lower = 0; uint32_t msg_limit = pptable->SkuTable.MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC]; + uint32_t power_limit; if (smu_v14_0_get_current_power_limit(smu, &power_limit)) power_limit = smu->adev->pm.ac_power ? @@ -2143,10 +2144,15 @@ static int smu_v14_0_2_mode1_reset(struct smu_context *smu) ret = smu_cmn_send_debug_smc_msg(smu, DEBUGSMC_MSG_Mode1Reset); if (!ret) { - if (amdgpu_emu_mode == 1) + if (amdgpu_emu_mode == 1) { msleep(50000); - else + } else { + /* disable mmio access while doing mode 1 reset*/ + smu->adev->no_hw_access = true; + /* ensure no_hw_access is globally visible before any MMIO */ + smp_mb(); msleep(1000); + } } return ret; diff --git a/drivers/gpu/drm/bridge/synopsys/dw-dp.c b/drivers/gpu/drm/bridge/synopsys/dw-dp.c index 82aaf74e1bc0..432342452484 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-dp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-dp.c @@ -2062,33 +2062,41 @@ struct dw_dp *dw_dp_bind(struct device *dev, struct drm_encoder *encoder, } ret = drm_bridge_attach(encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); - if (ret) + if (ret) { dev_err_probe(dev, ret, "Failed to attach bridge\n"); + goto unregister_aux; + } dw_dp_init_hw(dp); ret = phy_init(dp->phy); if (ret) { dev_err_probe(dev, ret, "phy init failed\n"); - return ERR_PTR(ret); + goto unregister_aux; } ret = devm_add_action_or_reset(dev, dw_dp_phy_exit, dp); if (ret) - return ERR_PTR(ret); + goto unregister_aux; dp->irq = platform_get_irq(pdev, 0); - if (dp->irq < 0) - return ERR_PTR(ret); + if (dp->irq < 0) { + ret = dp->irq; + goto unregister_aux; + } ret = devm_request_threaded_irq(dev, dp->irq, NULL, dw_dp_irq, IRQF_ONESHOT, dev_name(dev), dp); if (ret) { dev_err_probe(dev, ret, "failed to request irq\n"); - return ERR_PTR(ret); + goto unregister_aux; } return dp; + +unregister_aux: + drm_dp_aux_unregister(&dp->aux); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(dw_dp_bind); diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c index fe4c026280f0..60166919c5b5 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c @@ -163,6 +163,7 @@ struct dw_hdmi_qp { unsigned long ref_clk_rate; struct regmap *regm; + int main_irq; unsigned long tmds_char_rate; }; @@ -1271,6 +1272,7 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, dw_hdmi_qp_init_hw(hdmi); + hdmi->main_irq = plat_data->main_irq; ret = devm_request_threaded_irq(dev, plat_data->main_irq, dw_hdmi_qp_main_hardirq, NULL, IRQF_SHARED, dev_name(dev), hdmi); @@ -1331,9 +1333,16 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, } EXPORT_SYMBOL_GPL(dw_hdmi_qp_bind); +void dw_hdmi_qp_suspend(struct device *dev, struct dw_hdmi_qp *hdmi) +{ + disable_irq(hdmi->main_irq); +} +EXPORT_SYMBOL_GPL(dw_hdmi_qp_suspend); + void dw_hdmi_qp_resume(struct device *dev, struct dw_hdmi_qp *hdmi) { dw_hdmi_qp_init_hw(hdmi); + enable_irq(hdmi->main_irq); } EXPORT_SYMBOL_GPL(dw_hdmi_qp_resume); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 10adac9397cf..5beea645035f 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1162,8 +1162,18 @@ crtc_needs_disable(struct drm_crtc_state *old_state, new_state->self_refresh_active; } -static void -encoder_bridge_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_disable - disable bridges and encoder + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the CRTC needs + * it, disables the bridge chain all the way, then disables the encoder + * afterwards. + */ +void +drm_atomic_helper_commit_encoder_bridge_disable(struct drm_device *dev, + struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *old_conn_state, *new_conn_state; @@ -1229,9 +1239,18 @@ encoder_bridge_disable(struct drm_device *dev, struct drm_atomic_state *state) } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_disable); -static void -crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_disable - disable CRTSs + * @dev: DRM device + * @state: the driver state object + * + * Loops over all CRTCs in the current state and if the CRTC needs + * it, disables it. + */ +void +drm_atomic_helper_commit_crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state, *new_crtc_state; @@ -1282,9 +1301,18 @@ crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) drm_crtc_vblank_put(crtc); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_disable); -static void -encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_post_disable - post-disable encoder bridges + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the CRTC needs + * it, post-disables all encoder bridges. + */ +void +drm_atomic_helper_commit_encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *old_conn_state, *new_conn_state; @@ -1335,15 +1363,16 @@ encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *sta drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_post_disable); static void disable_outputs(struct drm_device *dev, struct drm_atomic_state *state) { - encoder_bridge_disable(dev, state); + drm_atomic_helper_commit_encoder_bridge_disable(dev, state); - crtc_disable(dev, state); + drm_atomic_helper_commit_encoder_bridge_post_disable(dev, state); - encoder_bridge_post_disable(dev, state); + drm_atomic_helper_commit_crtc_disable(dev, state); } /** @@ -1446,8 +1475,17 @@ void drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *stat } EXPORT_SYMBOL(drm_atomic_helper_calc_timestamping_constants); -static void -crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_set_mode - set the new mode + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the mode has + * changed, change the mode of the CRTC, then call down the bridge + * chain and change the mode in all bridges as well. + */ +void +drm_atomic_helper_commit_crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *new_crtc_state; @@ -1508,6 +1546,7 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_set_mode); /** * drm_atomic_helper_commit_modeset_disables - modeset commit to disable outputs @@ -1531,12 +1570,21 @@ void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev, drm_atomic_helper_update_legacy_modeset_state(dev, state); drm_atomic_helper_calc_timestamping_constants(state); - crtc_set_mode(dev, state); + drm_atomic_helper_commit_crtc_set_mode(dev, state); } EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_disables); -static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, - struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_writebacks - issue writebacks + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over the connectors, checks if the new state requires + * a writeback job to be issued and in that case issues an atomic + * commit on each connector. + */ +void drm_atomic_helper_commit_writebacks(struct drm_device *dev, + struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1555,9 +1603,18 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_writebacks); -static void -encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_pre_enable - pre-enable bridges + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over the connectors and if the CRTC needs it, pre-enables + * the entire bridge chain. + */ +void +drm_atomic_helper_commit_encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1588,9 +1645,18 @@ encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_pre_enable); -static void -crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_enable - enables the CRTCs + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over CRTCs in the new state, and of the CRTC needs + * it, enables it. + */ +void +drm_atomic_helper_commit_crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state; @@ -1619,9 +1685,18 @@ crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_enable); -static void -encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_enable - enables the bridges + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over all connectors in the new state, and of the CRTC needs + * it, enables the entire bridge chain. + */ +void +drm_atomic_helper_commit_encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1664,6 +1739,7 @@ encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_enable); /** * drm_atomic_helper_commit_modeset_enables - modeset commit to enable outputs @@ -1682,11 +1758,11 @@ encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, struct drm_atomic_state *state) { - encoder_bridge_pre_enable(dev, state); + drm_atomic_helper_commit_crtc_enable(dev, state); - crtc_enable(dev, state); + drm_atomic_helper_commit_encoder_bridge_pre_enable(dev, state); - encoder_bridge_enable(dev, state); + drm_atomic_helper_commit_encoder_bridge_enable(dev, state); drm_atomic_helper_commit_writebacks(dev, state); } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 4a7f72044ab8..4b47aa0dab35 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -366,6 +366,9 @@ static void drm_fb_helper_damage_work(struct work_struct *work) { struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper, damage_work); + if (helper->info->state != FBINFO_STATE_RUNNING) + return; + drm_fb_helper_fb_dirty(helper); } @@ -732,6 +735,13 @@ void drm_fb_helper_set_suspend_unlocked(struct drm_fb_helper *fb_helper, if (fb_helper->info->state != FBINFO_STATE_RUNNING) return; + /* + * Cancel pending damage work. During GPU reset, VBlank + * interrupts are disabled and drm_fb_helper_fb_dirty() + * would wait for VBlank timeout otherwise. + */ + cancel_work_sync(&fb_helper->damage_work); + console_lock(); } else { diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 93b9cff89080..f13eb5f36e8a 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -96,7 +96,8 @@ err_release: /** * drm_gem_shmem_init - Initialize an allocated object. * @dev: DRM device - * @obj: The allocated shmem GEM object. + * @shmem: The allocated shmem GEM object. + * @size: Buffer size in bytes * * Returns: * 0 on success, or a negative error code on failure. @@ -895,4 +896,4 @@ EXPORT_SYMBOL_GPL(drm_gem_shmem_prime_import_no_map); MODULE_DESCRIPTION("DRM SHMEM memory-management helpers"); MODULE_IMPORT_NS("DMA_BUF"); -MODULE_LICENSE("GPL v2"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index 8a06d296561d..0de47e83d84d 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -1602,14 +1602,48 @@ drm_gpuvm_bo_create(struct drm_gpuvm *gpuvm, } EXPORT_SYMBOL_GPL(drm_gpuvm_bo_create); +/* + * drm_gpuvm_bo_destroy_not_in_lists() - final part of drm_gpuvm_bo cleanup + * @vm_bo: the &drm_gpuvm_bo to destroy + * + * It is illegal to call this method if the @vm_bo is present in the GEMs gpuva + * list, the extobj list, or the evicted list. + * + * Note that this puts a refcount on the GEM object, which may destroy the GEM + * object if the refcount reaches zero. It's illegal for this to happen if the + * caller holds the GEMs gpuva mutex because it would free the mutex. + */ +static void +drm_gpuvm_bo_destroy_not_in_lists(struct drm_gpuvm_bo *vm_bo) +{ + struct drm_gpuvm *gpuvm = vm_bo->vm; + const struct drm_gpuvm_ops *ops = gpuvm->ops; + struct drm_gem_object *obj = vm_bo->obj; + + if (ops && ops->vm_bo_free) + ops->vm_bo_free(vm_bo); + else + kfree(vm_bo); + + drm_gpuvm_put(gpuvm); + drm_gem_object_put(obj); +} + +static void +drm_gpuvm_bo_destroy_not_in_lists_kref(struct kref *kref) +{ + struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo, + kref); + + drm_gpuvm_bo_destroy_not_in_lists(vm_bo); +} + static void drm_gpuvm_bo_destroy(struct kref *kref) { struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo, kref); struct drm_gpuvm *gpuvm = vm_bo->vm; - const struct drm_gpuvm_ops *ops = gpuvm->ops; - struct drm_gem_object *obj = vm_bo->obj; bool lock = !drm_gpuvm_resv_protected(gpuvm); if (!lock) @@ -1618,16 +1652,10 @@ drm_gpuvm_bo_destroy(struct kref *kref) drm_gpuvm_bo_list_del(vm_bo, extobj, lock); drm_gpuvm_bo_list_del(vm_bo, evict, lock); - drm_gem_gpuva_assert_lock_held(gpuvm, obj); + drm_gem_gpuva_assert_lock_held(gpuvm, vm_bo->obj); list_del(&vm_bo->list.entry.gem); - if (ops && ops->vm_bo_free) - ops->vm_bo_free(vm_bo); - else - kfree(vm_bo); - - drm_gpuvm_put(gpuvm); - drm_gem_object_put(obj); + drm_gpuvm_bo_destroy_not_in_lists(vm_bo); } /** @@ -1745,9 +1773,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_put_deferred); void drm_gpuvm_bo_deferred_cleanup(struct drm_gpuvm *gpuvm) { - const struct drm_gpuvm_ops *ops = gpuvm->ops; struct drm_gpuvm_bo *vm_bo; - struct drm_gem_object *obj; struct llist_node *bo_defer; bo_defer = llist_del_all(&gpuvm->bo_defer); @@ -1766,14 +1792,7 @@ drm_gpuvm_bo_deferred_cleanup(struct drm_gpuvm *gpuvm) while (bo_defer) { vm_bo = llist_entry(bo_defer, struct drm_gpuvm_bo, list.entry.bo_defer); bo_defer = bo_defer->next; - obj = vm_bo->obj; - if (ops && ops->vm_bo_free) - ops->vm_bo_free(vm_bo); - else - kfree(vm_bo); - - drm_gpuvm_put(gpuvm); - drm_gem_object_put(obj); + drm_gpuvm_bo_destroy_not_in_lists(vm_bo); } } EXPORT_SYMBOL_GPL(drm_gpuvm_bo_deferred_cleanup); @@ -1861,6 +1880,9 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain); * count is decreased. If not found @__vm_bo is returned without further * increase of the reference count. * + * The provided @__vm_bo must not already be in the gpuva, evict, or extobj + * lists prior to calling this method. + * * A new &drm_gpuvm_bo is added to the GEMs gpuva list. * * Returns: a pointer to the found &drm_gpuvm_bo or @__vm_bo if no existing @@ -1873,14 +1895,19 @@ drm_gpuvm_bo_obtain_prealloc(struct drm_gpuvm_bo *__vm_bo) struct drm_gem_object *obj = __vm_bo->obj; struct drm_gpuvm_bo *vm_bo; + drm_WARN_ON(gpuvm->drm, !drm_gpuvm_immediate_mode(gpuvm)); + + mutex_lock(&obj->gpuva.lock); vm_bo = drm_gpuvm_bo_find(gpuvm, obj); if (vm_bo) { - drm_gpuvm_bo_put(__vm_bo); + mutex_unlock(&obj->gpuva.lock); + kref_put(&__vm_bo->kref, drm_gpuvm_bo_destroy_not_in_lists_kref); return vm_bo; } drm_gem_gpuva_assert_lock_held(gpuvm, obj); list_add_tail(&__vm_bo->list.entry.gem, &obj->gpuva.list); + mutex_unlock(&obj->gpuva.lock); return __vm_bo; } diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 37d7cfbbb3e8..704f2f945019 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -3,6 +3,7 @@ * Copyright © 2024-2025 Intel Corporation */ +#include <linux/dma-fence.h> #include <linux/dma-mapping.h> #include <linux/migrate.h> #include <linux/pagemap.h> @@ -196,7 +197,7 @@ static void drm_pagemap_get_devmem_page(struct page *page, struct drm_pagemap_zdd *zdd) { page->zone_device_data = drm_pagemap_zdd_get(zdd); - zone_device_page_init(page, 0); + zone_device_page_init(page, page_pgmap(page), 0); } /** @@ -408,10 +409,14 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, drm_pagemap_get_devmem_page(page, zdd); } - err = ops->copy_to_devmem(pages, pagemap_addr, npages); + err = ops->copy_to_devmem(pages, pagemap_addr, npages, + devmem_allocation->pre_migrate_fence); if (err) goto err_finalize; + dma_fence_put(devmem_allocation->pre_migrate_fence); + devmem_allocation->pre_migrate_fence = NULL; + /* Upon success bind devmem allocation to range and zdd */ devmem_allocation->timeslice_expiration = get_jiffies_64() + msecs_to_jiffies(timeslice_ms); @@ -596,7 +601,7 @@ retry: for (i = 0; i < npages; ++i) pages[i] = migrate_pfn_to_page(src[i]); - err = ops->copy_to_ram(pages, pagemap_addr, npages); + err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) goto err_finalize; @@ -732,7 +737,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, for (i = 0; i < npages; ++i) pages[i] = migrate_pfn_to_page(migrate.src[i]); - err = ops->copy_to_ram(pages, pagemap_addr, npages); + err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) goto err_finalize; @@ -813,11 +818,14 @@ EXPORT_SYMBOL_GPL(drm_pagemap_pagemap_ops_get); * @ops: Pointer to the operations structure for GPU SVM device memory * @dpagemap: The struct drm_pagemap we're allocating from. * @size: Size of device memory allocation + * @pre_migrate_fence: Fence to wait for or pipeline behind before migration starts. + * (May be NULL). */ void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, struct device *dev, struct mm_struct *mm, const struct drm_pagemap_devmem_ops *ops, - struct drm_pagemap *dpagemap, size_t size) + struct drm_pagemap *dpagemap, size_t size, + struct dma_fence *pre_migrate_fence) { init_completion(&devmem_allocation->detached); devmem_allocation->dev = dev; @@ -825,6 +833,7 @@ void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, devmem_allocation->ops = ops; devmem_allocation->dpagemap = dpagemap; devmem_allocation->size = size; + devmem_allocation->pre_migrate_fence = pre_migrate_fence; } EXPORT_SYMBOL_GPL(drm_pagemap_devmem_init); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 01813e11e6c6..8e76ac8ee4e2 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1692,7 +1692,7 @@ static irqreturn_t hdmi_irq_thread(int irq, void *arg) { struct hdmi_context *hdata = arg; - mod_delayed_work(system_wq, &hdata->hotplug_work, + mod_delayed_work(system_percpu_wq, &hdata->hotplug_work, msecs_to_jiffies(HOTPLUG_DEBOUNCE_MS)); return IRQ_HANDLED; diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 76d77a736d84..4b77be94348d 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -457,27 +457,20 @@ int gud_plane_atomic_check(struct drm_plane *plane, struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state, plane); struct drm_crtc *crtc = new_plane_state->crtc; - struct drm_crtc_state *crtc_state; + struct drm_crtc_state *crtc_state = NULL; const struct drm_display_mode *mode; struct drm_framebuffer *old_fb = old_plane_state->fb; struct drm_connector_state *connector_state = NULL; struct drm_framebuffer *fb = new_plane_state->fb; - const struct drm_format_info *format = fb->format; + const struct drm_format_info *format; struct drm_connector *connector; unsigned int i, num_properties; struct gud_state_req *req; int idx, ret; size_t len; - if (drm_WARN_ON_ONCE(plane->dev, !fb)) - return -EINVAL; - - if (drm_WARN_ON_ONCE(plane->dev, !crtc)) - return -EINVAL; - - crtc_state = drm_atomic_get_new_crtc_state(state, crtc); - - mode = &crtc_state->mode; + if (crtc) + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state, DRM_PLANE_NO_SCALING, @@ -492,6 +485,9 @@ int gud_plane_atomic_check(struct drm_plane *plane, if (old_plane_state->rotation != new_plane_state->rotation) crtc_state->mode_changed = true; + mode = &crtc_state->mode; + format = fb->format; + if (old_fb && old_fb->format != format) crtc_state->mode_changed = true; @@ -598,7 +594,7 @@ void gud_plane_atomic_update(struct drm_plane *plane, struct drm_atomic_helper_damage_iter iter; int ret, idx; - if (crtc->state->mode_changed || !crtc->state->enable) { + if (!crtc || crtc->state->mode_changed || !crtc->state->enable) { cancel_work_sync(&gdrm->work); mutex_lock(&gdrm->damage_lock); if (gdrm->fb) { diff --git a/drivers/gpu/drm/i915/display/intel_color_pipeline.c b/drivers/gpu/drm/i915/display/intel_color_pipeline.c index 942d9b9c93ce..04af552b3648 100644 --- a/drivers/gpu/drm/i915/display/intel_color_pipeline.c +++ b/drivers/gpu/drm/i915/display/intel_color_pipeline.c @@ -34,11 +34,19 @@ int _intel_color_pipeline_plane_init(struct drm_plane *plane, struct drm_prop_en return ret; list->type = colorop->base.base.id; - list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", colorop->base.base.id); /* TODO: handle failures and clean up */ prev_op = &colorop->base; + colorop = intel_colorop_create(INTEL_PLANE_CB_CSC); + ret = drm_plane_colorop_ctm_3x4_init(dev, &colorop->base, plane, + DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + return ret; + + drm_colorop_set_next_property(prev_op, &colorop->base); + prev_op = &colorop->base; + if (DISPLAY_VER(display) >= 35 && intel_color_crtc_has_3dlut(display, pipe) && plane->type == DRM_PLANE_TYPE_PRIMARY) { @@ -55,15 +63,6 @@ int _intel_color_pipeline_plane_init(struct drm_plane *plane, struct drm_prop_en prev_op = &colorop->base; } - colorop = intel_colorop_create(INTEL_PLANE_CB_CSC); - ret = drm_plane_colorop_ctm_3x4_init(dev, &colorop->base, plane, - DRM_COLOROP_FLAG_ALLOW_BYPASS); - if (ret) - return ret; - - drm_colorop_set_next_property(prev_op, &colorop->base); - prev_op = &colorop->base; - colorop = intel_colorop_create(INTEL_PLANE_CB_POST_CSC_LUT); ret = drm_plane_colorop_curve_1d_lut_init(dev, &colorop->base, plane, PLANE_GAMMA_SIZE, @@ -74,6 +73,8 @@ int _intel_color_pipeline_plane_init(struct drm_plane *plane, struct drm_prop_en drm_colorop_set_next_property(prev_op, &colorop->base); + list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", list->type); + return 0; } @@ -81,9 +82,10 @@ int intel_color_pipeline_plane_init(struct drm_plane *plane, enum pipe pipe) { struct drm_device *dev = plane->dev; struct intel_display *display = to_intel_display(dev); - struct drm_prop_enum_list pipelines[MAX_COLOR_PIPELINES]; + struct drm_prop_enum_list pipelines[MAX_COLOR_PIPELINES] = {}; int len = 0; - int ret; + int ret = 0; + int i; /* Currently expose pipeline only for HDR planes */ if (!icl_is_hdr_plane(display, to_intel_plane(plane)->id)) @@ -92,8 +94,14 @@ int intel_color_pipeline_plane_init(struct drm_plane *plane, enum pipe pipe) /* Add pipeline consisting of transfer functions */ ret = _intel_color_pipeline_plane_init(plane, &pipelines[len], pipe); if (ret) - return ret; + goto out; len++; - return drm_plane_create_color_pipeline_property(plane, pipelines, len); + ret = drm_plane_create_color_pipeline_property(plane, pipelines, len); + + for (i = 0; i < len; i++) + kfree(pipelines[i].name); + +out: + return ret; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index b057c2fa03a4..d49e96f9be51 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -951,13 +951,13 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) vma = eb_lookup_vma(eb, eb->exec[i].handle); if (IS_ERR(vma)) { err = PTR_ERR(vma); - goto err; + return err; } err = eb_validate_vma(eb, &eb->exec[i], vma); if (unlikely(err)) { i915_vma_put(vma); - goto err; + return err; } err = eb_add_vma(eb, ¤t_batch, i, vma); @@ -966,19 +966,8 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) if (i915_gem_object_is_userptr(vma->obj)) { err = i915_gem_object_userptr_submit_init(vma->obj); - if (err) { - if (i + 1 < eb->buffer_count) { - /* - * Execbuffer code expects last vma entry to be NULL, - * since we already initialized this entry, - * set the next value to NULL or we mess up - * cleanup handling. - */ - eb->vma[i + 1].vma = NULL; - } - + if (err) return err; - } eb->vma[i].flags |= __EXEC_OBJECT_USERPTR_INIT; eb->args->flags |= __EXEC_USERPTR_USED; @@ -986,10 +975,6 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) } return 0; - -err: - eb->vma[i].vma = NULL; - return err; } static int eb_lock_vmas(struct i915_execbuffer *eb) @@ -3375,7 +3360,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.exec = exec; eb.vma = (struct eb_vma *)(exec + args->buffer_count + 1); - eb.vma[0].vma = NULL; + memset(eb.vma, 0, (args->buffer_count + 1) * sizeof(struct eb_vma)); + eb.batch_pool = NULL; eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS; @@ -3584,7 +3570,18 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, if (err) return err; - /* Allocate extra slots for use by the command parser */ + /* + * Allocate extra slots for use by the command parser. + * + * Note that this allocation handles two different arrays (the + * exec2_list array, and the eventual eb.vma array introduced in + * i915_gem_do_execbuffer()), that reside in virtually contiguous + * memory. Also note that the allocation intentionally doesn't fill the + * area with zeros, because the exec2_list part doesn't need to be, as + * it's immediately overwritten by user data a few lines below. + * However, the eb.vma part is explicitly zeroed later in + * i915_gem_do_execbuffer(). + */ exec2_list = kvmalloc_array(count + 2, eb_element_size(), __GFP_NOWARN | GFP_KERNEL); if (exec2_list == NULL) { diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 7582ef34bf3f..303d8d9b7775 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -686,7 +686,7 @@ static void err_print_guc_ctb(struct drm_i915_error_state_buf *m, } /* This list includes registers that are useful in debugging GuC hangs. */ -const struct { +static const struct { u32 start; u32 count; } guc_hw_reg_state[] = { diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c index 8a56952f6730..99d681413eff 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_trace.c +++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c @@ -137,6 +137,7 @@ update_logtype(struct pvr_device *pvr_dev, u32 group_mask) struct rogue_fwif_kccb_cmd cmd; int idx; int err; + int slot; if (group_mask) fw_trace->tracebuf_ctrl->log_type = ROGUE_FWIF_LOG_TYPE_TRACE | group_mask; @@ -154,8 +155,13 @@ update_logtype(struct pvr_device *pvr_dev, u32 group_mask) cmd.cmd_type = ROGUE_FWIF_KCCB_CMD_LOGTYPE_UPDATE; cmd.kccb_flags = 0; - err = pvr_kccb_send_cmd(pvr_dev, &cmd, NULL); + err = pvr_kccb_send_cmd(pvr_dev, &cmd, &slot); + if (err) + goto err_drm_dev_exit; + + err = pvr_kccb_wait_for_completion(pvr_dev, slot, HZ, NULL); +err_drm_dev_exit: drm_dev_exit(idx); err_up_read: diff --git a/drivers/gpu/drm/imagination/pvr_gem.c b/drivers/gpu/drm/imagination/pvr_gem.c index a66cf082af24..c07c9a915190 100644 --- a/drivers/gpu/drm/imagination/pvr_gem.c +++ b/drivers/gpu/drm/imagination/pvr_gem.c @@ -28,6 +28,16 @@ static void pvr_gem_object_free(struct drm_gem_object *obj) drm_gem_shmem_object_free(obj); } +static struct dma_buf *pvr_gem_export(struct drm_gem_object *obj, int flags) +{ + struct pvr_gem_object *pvr_obj = gem_to_pvr_gem(obj); + + if (pvr_obj->flags & DRM_PVR_BO_PM_FW_PROTECT) + return ERR_PTR(-EPERM); + + return drm_gem_prime_export(obj, flags); +} + static int pvr_gem_mmap(struct drm_gem_object *gem_obj, struct vm_area_struct *vma) { struct pvr_gem_object *pvr_obj = gem_to_pvr_gem(gem_obj); @@ -42,6 +52,7 @@ static int pvr_gem_mmap(struct drm_gem_object *gem_obj, struct vm_area_struct *v static const struct drm_gem_object_funcs pvr_gem_object_funcs = { .free = pvr_gem_object_free, .print_info = drm_gem_shmem_object_print_info, + .export = pvr_gem_export, .pin = drm_gem_shmem_object_pin, .unpin = drm_gem_shmem_object_unpin, .get_sg_table = drm_gem_shmem_object_get_sg_table, diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index 96188bf9274a..ad8c8b823681 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -8,7 +8,7 @@ config DRM_MEDIATEK depends on OF depends on MTK_MMSYS select DRM_CLIENT_SELECTION - select DRM_GEM_DMA_HELPER if DRM_FBDEV_EMULATION + select DRM_GEM_DMA_HELPER select DRM_KMS_HELPER select DRM_DISPLAY_HELPER select DRM_BRIDGE_CONNECTOR diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 61cab32e213a..53360b5d12ba 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -836,20 +836,6 @@ static int mtk_dpi_bridge_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) { struct mtk_dpi *dpi = bridge_to_dpi(bridge); - int ret; - - dpi->next_bridge = devm_drm_of_get_bridge(dpi->dev, dpi->dev->of_node, 1, -1); - if (IS_ERR(dpi->next_bridge)) { - ret = PTR_ERR(dpi->next_bridge); - if (ret == -EPROBE_DEFER) - return ret; - - /* Old devicetree has only one endpoint */ - dpi->next_bridge = devm_drm_of_get_bridge(dpi->dev, dpi->dev->of_node, 0, 0); - if (IS_ERR(dpi->next_bridge)) - return dev_err_probe(dpi->dev, PTR_ERR(dpi->next_bridge), - "Failed to get bridge\n"); - } return drm_bridge_attach(encoder, dpi->next_bridge, &dpi->bridge, flags); @@ -1319,6 +1305,15 @@ static int mtk_dpi_probe(struct platform_device *pdev) if (dpi->irq < 0) return dpi->irq; + dpi->next_bridge = devm_drm_of_get_bridge(dpi->dev, dpi->dev->of_node, 1, -1); + if (IS_ERR(dpi->next_bridge) && PTR_ERR(dpi->next_bridge) == -ENODEV) { + /* Old devicetree has only one endpoint */ + dpi->next_bridge = devm_drm_of_get_bridge(dpi->dev, dpi->dev->of_node, 0, 0); + } + if (IS_ERR(dpi->next_bridge)) + return dev_err_probe(dpi->dev, PTR_ERR(dpi->next_bridge), + "Failed to get bridge\n"); + platform_set_drvdata(pdev, dpi); dpi->bridge.of_node = dev->of_node; diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 0e2bcd5f67b7..d7726091819c 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1002,12 +1002,6 @@ static int mtk_dsi_host_attach(struct mipi_dsi_host *host, return PTR_ERR(dsi->next_bridge); } - /* - * set flag to request the DSI host bridge be pre-enabled before device bridge - * in the chain, so the DSI host is ready when the device bridge is pre-enabled - */ - dsi->next_bridge->pre_enable_prev_first = true; - drm_bridge_add(&dsi->bridge); ret = component_add(host->dev, &mtk_dsi_component_ops); diff --git a/drivers/gpu/drm/mediatek/mtk_gem.c b/drivers/gpu/drm/mediatek/mtk_gem.c index 024cc7e9036c..7525a9f9907a 100644 --- a/drivers/gpu/drm/mediatek/mtk_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_gem.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2015 MediaTek Inc. + * Copyright (c) 2025 Collabora Ltd. + * AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> */ #include <linux/dma-buf.h> @@ -18,24 +20,64 @@ static int mtk_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); -static const struct vm_operations_struct vm_ops = { - .open = drm_gem_vm_open, - .close = drm_gem_vm_close, -}; +static void mtk_gem_free_object(struct drm_gem_object *obj) +{ + struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(obj); + struct mtk_drm_private *priv = obj->dev->dev_private; + + if (dma_obj->sgt) + drm_prime_gem_destroy(obj, dma_obj->sgt); + else + dma_free_wc(priv->dma_dev, dma_obj->base.size, + dma_obj->vaddr, dma_obj->dma_addr); + + /* release file pointer to gem object. */ + drm_gem_object_release(obj); + + kfree(dma_obj); +} + +/* + * Allocate a sg_table for this GEM object. + * Note: Both the table's contents, and the sg_table itself must be freed by + * the caller. + * Returns a pointer to the newly allocated sg_table, or an ERR_PTR() error. + */ +static struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj) +{ + struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(obj); + struct mtk_drm_private *priv = obj->dev->dev_private; + struct sg_table *sgt; + int ret; + + sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); + if (!sgt) + return ERR_PTR(-ENOMEM); + + ret = dma_get_sgtable(priv->dma_dev, sgt, dma_obj->vaddr, + dma_obj->dma_addr, obj->size); + if (ret) { + DRM_ERROR("failed to allocate sgt, %d\n", ret); + kfree(sgt); + return ERR_PTR(ret); + } + + return sgt; +} static const struct drm_gem_object_funcs mtk_gem_object_funcs = { .free = mtk_gem_free_object, + .print_info = drm_gem_dma_object_print_info, .get_sg_table = mtk_gem_prime_get_sg_table, - .vmap = mtk_gem_prime_vmap, - .vunmap = mtk_gem_prime_vunmap, + .vmap = drm_gem_dma_object_vmap, .mmap = mtk_gem_object_mmap, - .vm_ops = &vm_ops, + .vm_ops = &drm_gem_dma_vm_ops, }; -static struct mtk_gem_obj *mtk_gem_init(struct drm_device *dev, - unsigned long size) +static struct drm_gem_dma_object *mtk_gem_init(struct drm_device *dev, + unsigned long size, bool private) { - struct mtk_gem_obj *mtk_gem_obj; + struct drm_gem_dma_object *dma_obj; int ret; size = round_up(size, PAGE_SIZE); @@ -43,86 +85,65 @@ static struct mtk_gem_obj *mtk_gem_init(struct drm_device *dev, if (size == 0) return ERR_PTR(-EINVAL); - mtk_gem_obj = kzalloc(sizeof(*mtk_gem_obj), GFP_KERNEL); - if (!mtk_gem_obj) + dma_obj = kzalloc(sizeof(*dma_obj), GFP_KERNEL); + if (!dma_obj) return ERR_PTR(-ENOMEM); - mtk_gem_obj->base.funcs = &mtk_gem_object_funcs; + dma_obj->base.funcs = &mtk_gem_object_funcs; - ret = drm_gem_object_init(dev, &mtk_gem_obj->base, size); - if (ret < 0) { + if (private) { + ret = 0; + drm_gem_private_object_init(dev, &dma_obj->base, size); + } else { + ret = drm_gem_object_init(dev, &dma_obj->base, size); + } + if (ret) { DRM_ERROR("failed to initialize gem object\n"); - kfree(mtk_gem_obj); + kfree(dma_obj); return ERR_PTR(ret); } - return mtk_gem_obj; + return dma_obj; } -struct mtk_gem_obj *mtk_gem_create(struct drm_device *dev, - size_t size, bool alloc_kmap) +static struct drm_gem_dma_object *mtk_gem_create(struct drm_device *dev, size_t size) { struct mtk_drm_private *priv = dev->dev_private; - struct mtk_gem_obj *mtk_gem; + struct drm_gem_dma_object *dma_obj; struct drm_gem_object *obj; int ret; - mtk_gem = mtk_gem_init(dev, size); - if (IS_ERR(mtk_gem)) - return ERR_CAST(mtk_gem); - - obj = &mtk_gem->base; + dma_obj = mtk_gem_init(dev, size, false); + if (IS_ERR(dma_obj)) + return ERR_CAST(dma_obj); - mtk_gem->dma_attrs = DMA_ATTR_WRITE_COMBINE; + obj = &dma_obj->base; - if (!alloc_kmap) - mtk_gem->dma_attrs |= DMA_ATTR_NO_KERNEL_MAPPING; - - mtk_gem->cookie = dma_alloc_attrs(priv->dma_dev, obj->size, - &mtk_gem->dma_addr, GFP_KERNEL, - mtk_gem->dma_attrs); - if (!mtk_gem->cookie) { + dma_obj->vaddr = dma_alloc_wc(priv->dma_dev, obj->size, + &dma_obj->dma_addr, + GFP_KERNEL | __GFP_NOWARN); + if (!dma_obj->vaddr) { DRM_ERROR("failed to allocate %zx byte dma buffer", obj->size); ret = -ENOMEM; goto err_gem_free; } - if (alloc_kmap) - mtk_gem->kvaddr = mtk_gem->cookie; - - DRM_DEBUG_DRIVER("cookie = %p dma_addr = %pad size = %zu\n", - mtk_gem->cookie, &mtk_gem->dma_addr, + DRM_DEBUG_DRIVER("vaddr = %p dma_addr = %pad size = %zu\n", + dma_obj->vaddr, &dma_obj->dma_addr, size); - return mtk_gem; + return dma_obj; err_gem_free: drm_gem_object_release(obj); - kfree(mtk_gem); + kfree(dma_obj); return ERR_PTR(ret); } -void mtk_gem_free_object(struct drm_gem_object *obj) -{ - struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj); - struct mtk_drm_private *priv = obj->dev->dev_private; - - if (mtk_gem->sg) - drm_prime_gem_destroy(obj, mtk_gem->sg); - else - dma_free_attrs(priv->dma_dev, obj->size, mtk_gem->cookie, - mtk_gem->dma_addr, mtk_gem->dma_attrs); - - /* release file pointer to gem object. */ - drm_gem_object_release(obj); - - kfree(mtk_gem); -} - int mtk_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev, struct drm_mode_create_dumb *args) { - struct mtk_gem_obj *mtk_gem; + struct drm_gem_dma_object *dma_obj; int ret; args->pitch = DIV_ROUND_UP(args->width * args->bpp, 8); @@ -135,25 +156,25 @@ int mtk_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev, args->size = args->pitch; args->size *= args->height; - mtk_gem = mtk_gem_create(dev, args->size, false); - if (IS_ERR(mtk_gem)) - return PTR_ERR(mtk_gem); + dma_obj = mtk_gem_create(dev, args->size); + if (IS_ERR(dma_obj)) + return PTR_ERR(dma_obj); /* * allocate a id of idr table where the obj is registered * and handle has the id what user can see. */ - ret = drm_gem_handle_create(file_priv, &mtk_gem->base, &args->handle); + ret = drm_gem_handle_create(file_priv, &dma_obj->base, &args->handle); if (ret) goto err_handle_create; /* drop reference from allocate - handle holds it now. */ - drm_gem_object_put(&mtk_gem->base); + drm_gem_object_put(&dma_obj->base); return 0; err_handle_create: - mtk_gem_free_object(&mtk_gem->base); + mtk_gem_free_object(&dma_obj->base); return ret; } @@ -161,129 +182,50 @@ static int mtk_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) { - int ret; - struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj); + struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(obj); struct mtk_drm_private *priv = obj->dev->dev_private; + int ret; /* * Set vm_pgoff (used as a fake buffer offset by DRM) to 0 and map the * whole buffer from the start. */ - vma->vm_pgoff = 0; + vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node); /* * dma_alloc_attrs() allocated a struct page table for mtk_gem, so clear * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap(). */ - vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); + vm_flags_mod(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP, VM_PFNMAP); + vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); - ret = dma_mmap_attrs(priv->dma_dev, vma, mtk_gem->cookie, - mtk_gem->dma_addr, obj->size, mtk_gem->dma_attrs); + ret = dma_mmap_wc(priv->dma_dev, vma, dma_obj->vaddr, + dma_obj->dma_addr, obj->size); + if (ret) + drm_gem_vm_close(vma); return ret; } -/* - * Allocate a sg_table for this GEM object. - * Note: Both the table's contents, and the sg_table itself must be freed by - * the caller. - * Returns a pointer to the newly allocated sg_table, or an ERR_PTR() error. - */ -struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj) -{ - struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj); - struct mtk_drm_private *priv = obj->dev->dev_private; - struct sg_table *sgt; - int ret; - - sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); - if (!sgt) - return ERR_PTR(-ENOMEM); - - ret = dma_get_sgtable_attrs(priv->dma_dev, sgt, mtk_gem->cookie, - mtk_gem->dma_addr, obj->size, - mtk_gem->dma_attrs); - if (ret) { - DRM_ERROR("failed to allocate sgt, %d\n", ret); - kfree(sgt); - return ERR_PTR(ret); - } - - return sgt; -} - struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev, - struct dma_buf_attachment *attach, struct sg_table *sg) + struct dma_buf_attachment *attach, struct sg_table *sgt) { - struct mtk_gem_obj *mtk_gem; + struct drm_gem_dma_object *dma_obj; /* check if the entries in the sg_table are contiguous */ - if (drm_prime_get_contiguous_size(sg) < attach->dmabuf->size) { + if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size) { DRM_ERROR("sg_table is not contiguous"); return ERR_PTR(-EINVAL); } - mtk_gem = mtk_gem_init(dev, attach->dmabuf->size); - if (IS_ERR(mtk_gem)) - return ERR_CAST(mtk_gem); - - mtk_gem->dma_addr = sg_dma_address(sg->sgl); - mtk_gem->sg = sg; - - return &mtk_gem->base; -} - -int mtk_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map) -{ - struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj); - struct sg_table *sgt = NULL; - unsigned int npages; - - if (mtk_gem->kvaddr) - goto out; - - sgt = mtk_gem_prime_get_sg_table(obj); - if (IS_ERR(sgt)) - return PTR_ERR(sgt); - - npages = obj->size >> PAGE_SHIFT; - mtk_gem->pages = kcalloc(npages, sizeof(*mtk_gem->pages), GFP_KERNEL); - if (!mtk_gem->pages) { - sg_free_table(sgt); - kfree(sgt); - return -ENOMEM; - } - - drm_prime_sg_to_page_array(sgt, mtk_gem->pages, npages); - - mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP, - pgprot_writecombine(PAGE_KERNEL)); - if (!mtk_gem->kvaddr) { - sg_free_table(sgt); - kfree(sgt); - kfree(mtk_gem->pages); - return -ENOMEM; - } - sg_free_table(sgt); - kfree(sgt); - -out: - iosys_map_set_vaddr(map, mtk_gem->kvaddr); - - return 0; -} - -void mtk_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map) -{ - struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj); - void *vaddr = map->vaddr; + dma_obj = mtk_gem_init(dev, attach->dmabuf->size, true); + if (IS_ERR(dma_obj)) + return ERR_CAST(dma_obj); - if (!mtk_gem->pages) - return; + dma_obj->dma_addr = sg_dma_address(sgt->sgl); + dma_obj->sgt = sgt; - vunmap(vaddr); - mtk_gem->kvaddr = NULL; - kfree(mtk_gem->pages); + return &dma_obj->base; } diff --git a/drivers/gpu/drm/mediatek/mtk_gem.h b/drivers/gpu/drm/mediatek/mtk_gem.h index 66e5f154f698..afebc3a970a8 100644 --- a/drivers/gpu/drm/mediatek/mtk_gem.h +++ b/drivers/gpu/drm/mediatek/mtk_gem.h @@ -7,42 +7,11 @@ #define _MTK_GEM_H_ #include <drm/drm_gem.h> +#include <drm/drm_gem_dma_helper.h> -/* - * mtk drm buffer structure. - * - * @base: a gem object. - * - a new handle to this gem object would be created - * by drm_gem_handle_create(). - * @cookie: the return value of dma_alloc_attrs(), keep it for dma_free_attrs() - * @kvaddr: kernel virtual address of gem buffer. - * @dma_addr: dma address of gem buffer. - * @dma_attrs: dma attributes of gem buffer. - * - * P.S. this object would be transferred to user as kms_bo.handle so - * user can access the buffer through kms_bo.handle. - */ -struct mtk_gem_obj { - struct drm_gem_object base; - void *cookie; - void *kvaddr; - dma_addr_t dma_addr; - unsigned long dma_attrs; - struct sg_table *sg; - struct page **pages; -}; - -#define to_mtk_gem_obj(x) container_of(x, struct mtk_gem_obj, base) - -void mtk_gem_free_object(struct drm_gem_object *gem); -struct mtk_gem_obj *mtk_gem_create(struct drm_device *dev, size_t size, - bool alloc_kmap); int mtk_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev, struct drm_mode_create_dumb *args); -struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj); struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg); -int mtk_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map); -void mtk_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map); #endif diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_common.c b/drivers/gpu/drm/mediatek/mtk_hdmi_common.c index e78eb0876f16..bd7f8c56ec9c 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_common.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_common.c @@ -303,7 +303,7 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, struct platform_device return dev_err_probe(dev, ret, "Failed to get clocks\n"); hdmi->irq = platform_get_irq(pdev, 0); - if (!hdmi->irq) + if (hdmi->irq < 0) return hdmi->irq; hdmi->regs = device_node_to_regmap(dev->of_node); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_common.h b/drivers/gpu/drm/mediatek/mtk_hdmi_common.h index de5e064585f8..7a644bbf5843 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_common.h +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_common.h @@ -168,7 +168,7 @@ struct mtk_hdmi { bool audio_enable; bool powered; bool enabled; - unsigned int irq; + int irq; enum hdmi_hpd_state hpd; hdmi_codec_plugged_cb plugged_cb; struct device *codec_dev; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c index b844e2c10f28..d937219fdb7e 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c @@ -66,11 +66,19 @@ static int mtk_ddc_check_and_rise_low_bus(struct mtk_hdmi_ddc *ddc) return 0; } -static int mtk_ddc_wr_one(struct mtk_hdmi_ddc *ddc, u16 addr_id, - u16 offset_id, u8 *wr_data) +static int mtk_ddcm_write_hdmi(struct mtk_hdmi_ddc *ddc, u16 addr_id, + u16 offset_id, u16 data_cnt, u8 *wr_data) { u32 val; - int ret; + int ret, i; + + /* Don't allow transfer with a size over than the transfer fifo size + * (16 byte) + */ + if (data_cnt > 16) { + dev_err(ddc->dev, "Invalid DDCM write request\n"); + return -EINVAL; + } /* If down, rise bus for write operation */ mtk_ddc_check_and_rise_low_bus(ddc); @@ -78,16 +86,21 @@ static int mtk_ddc_wr_one(struct mtk_hdmi_ddc *ddc, u16 addr_id, regmap_update_bits(ddc->regs, HPD_DDC_CTRL, HPD_DDC_DELAY_CNT, FIELD_PREP(HPD_DDC_DELAY_CNT, DDC2_DLY_CNT)); + /* In case there is no payload data, just do a single write for the + * address only + */ if (wr_data) { - regmap_write(ddc->regs, SI2C_CTRL, - FIELD_PREP(SI2C_ADDR, SI2C_ADDR_READ) | - FIELD_PREP(SI2C_WDATA, *wr_data) | - SI2C_WR); + /* Fill transfer fifo with payload data */ + for (i = 0; i < data_cnt; i++) { + regmap_write(ddc->regs, SI2C_CTRL, + FIELD_PREP(SI2C_ADDR, SI2C_ADDR_READ) | + FIELD_PREP(SI2C_WDATA, wr_data[i]) | + SI2C_WR); + } } - regmap_write(ddc->regs, DDC_CTRL, FIELD_PREP(DDC_CTRL_CMD, DDC_CMD_SEQ_WRITE) | - FIELD_PREP(DDC_CTRL_DIN_CNT, wr_data == NULL ? 0 : 1) | + FIELD_PREP(DDC_CTRL_DIN_CNT, wr_data == NULL ? 0 : data_cnt) | FIELD_PREP(DDC_CTRL_OFFSET, offset_id) | FIELD_PREP(DDC_CTRL_ADDR, addr_id)); usleep_range(1000, 1250); @@ -96,6 +109,11 @@ static int mtk_ddc_wr_one(struct mtk_hdmi_ddc *ddc, u16 addr_id, !(val & DDC_I2C_IN_PROG), 500, 1000); if (ret) { dev_err(ddc->dev, "DDC I2C write timeout\n"); + + /* Abort transfer if it is still in progress */ + regmap_update_bits(ddc->regs, DDC_CTRL, DDC_CTRL_CMD, + FIELD_PREP(DDC_CTRL_CMD, DDC_CMD_ABORT_XFER)); + return ret; } @@ -179,6 +197,11 @@ static int mtk_ddcm_read_hdmi(struct mtk_hdmi_ddc *ddc, u16 uc_dev, 500 * (temp_length + 5)); if (ret) { dev_err(ddc->dev, "Timeout waiting for DDC I2C\n"); + + /* Abort transfer if it is still in progress */ + regmap_update_bits(ddc->regs, DDC_CTRL, DDC_CTRL_CMD, + FIELD_PREP(DDC_CTRL_CMD, DDC_CMD_ABORT_XFER)); + return ret; } @@ -250,24 +273,9 @@ static int mtk_hdmi_fg_ddc_data_read(struct mtk_hdmi_ddc *ddc, u16 b_dev, static int mtk_hdmi_ddc_fg_data_write(struct mtk_hdmi_ddc *ddc, u16 b_dev, u8 data_addr, u16 data_cnt, u8 *pr_data) { - int i, ret; - regmap_set_bits(ddc->regs, HDCP2X_POL_CTRL, HDCP2X_DIS_POLL_EN); - /* - * In case there is no payload data, just do a single write for the - * address only - */ - if (data_cnt == 0) - return mtk_ddc_wr_one(ddc, b_dev, data_addr, NULL); - i = 0; - do { - ret = mtk_ddc_wr_one(ddc, b_dev, data_addr + i, pr_data + i); - if (ret) - return ret; - } while (++i < data_cnt); - - return 0; + return mtk_ddcm_write_hdmi(ddc, b_dev, data_addr, data_cnt, pr_data); } static int mtk_hdmi_ddc_v2_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num) diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c b/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c index c272e1e74b7d..454b8b93b834 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c @@ -1120,9 +1120,10 @@ static void mtk_hdmi_v2_hpd_disable(struct drm_bridge *bridge) mtk_hdmi_v2_disable(hdmi); } -static int mtk_hdmi_v2_hdmi_tmds_char_rate_valid(const struct drm_bridge *bridge, - const struct drm_display_mode *mode, - unsigned long long tmds_rate) +static enum drm_mode_status +mtk_hdmi_v2_hdmi_tmds_char_rate_valid(const struct drm_bridge *bridge, + const struct drm_display_mode *mode, + unsigned long long tmds_rate) { if (mode->clock < MTK_HDMI_V2_CLOCK_MIN) return MODE_CLOCK_LOW; diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index 5043e0377270..fcd10d7e8342 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -11,13 +11,13 @@ #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> +#include <drm/drm_gem_dma_helper.h> #include <drm/drm_print.h> #include <linux/align.h> #include "mtk_crtc.h" #include "mtk_ddp_comp.h" #include "mtk_drm_drv.h" -#include "mtk_gem.h" #include "mtk_plane.h" static const u64 modifiers[] = { @@ -114,8 +114,8 @@ static void mtk_plane_update_new_state(struct drm_plane_state *new_state, struct mtk_plane_state *mtk_plane_state) { struct drm_framebuffer *fb = new_state->fb; + struct drm_gem_dma_object *dma_obj; struct drm_gem_object *gem; - struct mtk_gem_obj *mtk_gem; unsigned int pitch, format; u64 modifier; dma_addr_t addr; @@ -124,8 +124,8 @@ static void mtk_plane_update_new_state(struct drm_plane_state *new_state, int offset; gem = fb->obj[0]; - mtk_gem = to_mtk_gem_obj(gem); - addr = mtk_gem->dma_addr; + dma_obj = to_drm_gem_dma_obj(gem); + addr = dma_obj->dma_addr; pitch = fb->pitches[0]; format = fb->format->format; modifier = fb->modifier; diff --git a/drivers/gpu/drm/nouveau/dispnv50/atom.h b/drivers/gpu/drm/nouveau/dispnv50/atom.h index 93f8f4f64578..b43c4f9bbcdf 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/atom.h +++ b/drivers/gpu/drm/nouveau/dispnv50/atom.h @@ -152,8 +152,21 @@ static inline struct nv50_head_atom * nv50_head_atom_get(struct drm_atomic_state *state, struct drm_crtc *crtc) { struct drm_crtc_state *statec = drm_atomic_get_crtc_state(state, crtc); + if (IS_ERR(statec)) return (void *)statec; + + return nv50_head_atom(statec); +} + +static inline struct nv50_head_atom * +nv50_head_atom_get_new(struct drm_atomic_state *state, struct drm_crtc *crtc) +{ + struct drm_crtc_state *statec = drm_atomic_get_new_crtc_state(state, crtc); + + if (!statec) + return NULL; + return nv50_head_atom(statec); } diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c index a95ee5dcc2e3..1a889139cb05 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c +++ b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c @@ -84,6 +84,7 @@ curs507a_prepare(struct nv50_wndw *wndw, struct nv50_head_atom *asyh, asyh->curs.handle = handle; asyh->curs.offset = offset; asyh->set.curs = asyh->curs.visible; + nv50_atom(asyh->state.state)->lock_core = true; } } diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c index 3dd742b4f823..e32ed1db6c56 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head.c @@ -43,6 +43,9 @@ nv50_head_flush_clr(struct nv50_head *head, union nv50_head_atom_mask clr = { .mask = asyh->clr.mask & ~(flush ? 0 : asyh->set.mask), }; + + lockdep_assert_held(&head->disp->mutex); + if (clr.crc) nv50_crc_atomic_clr(head); if (clr.olut) head->func->olut_clr(head); if (clr.core) head->func->core_clr(head); @@ -65,6 +68,8 @@ nv50_head_flush_set_wndw(struct nv50_head *head, struct nv50_head_atom *asyh) void nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh) { + lockdep_assert_held(&head->disp->mutex); + if (asyh->set.view ) head->func->view (head, asyh); if (asyh->set.mode ) head->func->mode (head, asyh); if (asyh->set.core ) head->func->core_set(head, asyh); diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index ef9e410babbf..9a2c20fce0f3 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -583,7 +583,7 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) asyw->image.offset[0] = nvbo->offset; if (wndw->func->prepare) { - asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc); + asyh = nv50_head_atom_get_new(asyw->state.state, asyw->state.crtc); if (IS_ERR(asyh)) return PTR_ERR(asyh); diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h index d1beaad0c82b..834ed6587aa5 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h @@ -1,28 +1,81 @@ /* SPDX-License-Identifier: MIT */ #ifndef __NVBIOS_CONN_H__ #define __NVBIOS_CONN_H__ + +/* + * An enumerator representing all of the possible VBIOS connector types defined + * by Nvidia at + * https://nvidia.github.io/open-gpu-doc/DCB/DCB-4.x-Specification.html. + * + * [1] Nvidia's documentation actually claims DCB_CONNECTOR_HDMI_0 is a "3-Pin + * DIN Stereo Connector". This seems very likely to be a documentation typo + * or some sort of funny historical baggage, because we've treated this + * connector type as HDMI for years without issue. + * TODO: Check with Nvidia what's actually happening here. + */ enum dcb_connector_type { - DCB_CONNECTOR_VGA = 0x00, - DCB_CONNECTOR_TV_0 = 0x10, - DCB_CONNECTOR_TV_1 = 0x11, - DCB_CONNECTOR_TV_3 = 0x13, - DCB_CONNECTOR_DVI_I = 0x30, - DCB_CONNECTOR_DVI_D = 0x31, - DCB_CONNECTOR_DMS59_0 = 0x38, - DCB_CONNECTOR_DMS59_1 = 0x39, - DCB_CONNECTOR_LVDS = 0x40, - DCB_CONNECTOR_LVDS_SPWG = 0x41, - DCB_CONNECTOR_DP = 0x46, - DCB_CONNECTOR_eDP = 0x47, - DCB_CONNECTOR_mDP = 0x48, - DCB_CONNECTOR_HDMI_0 = 0x60, - DCB_CONNECTOR_HDMI_1 = 0x61, - DCB_CONNECTOR_HDMI_C = 0x63, - DCB_CONNECTOR_DMS59_DP0 = 0x64, - DCB_CONNECTOR_DMS59_DP1 = 0x65, - DCB_CONNECTOR_WFD = 0x70, - DCB_CONNECTOR_USB_C = 0x71, - DCB_CONNECTOR_NONE = 0xff + /* Analog outputs */ + DCB_CONNECTOR_VGA = 0x00, // VGA 15-pin connector + DCB_CONNECTOR_DVI_A = 0x01, // DVI-A + DCB_CONNECTOR_POD_VGA = 0x02, // Pod - VGA 15-pin connector + DCB_CONNECTOR_TV_0 = 0x10, // TV - Composite Out + DCB_CONNECTOR_TV_1 = 0x11, // TV - S-Video Out + DCB_CONNECTOR_TV_2 = 0x12, // TV - S-Video Breakout - Composite + DCB_CONNECTOR_TV_3 = 0x13, // HDTV Component - YPrPb + DCB_CONNECTOR_TV_SCART = 0x14, // TV - SCART Connector + DCB_CONNECTOR_TV_SCART_D = 0x16, // TV - Composite SCART over D-connector + DCB_CONNECTOR_TV_DTERM = 0x17, // HDTV - D-connector (EIAJ4120) + DCB_CONNECTOR_POD_TV_3 = 0x18, // Pod - HDTV - YPrPb + DCB_CONNECTOR_POD_TV_1 = 0x19, // Pod - S-Video + DCB_CONNECTOR_POD_TV_0 = 0x1a, // Pod - Composite + + /* DVI digital outputs */ + DCB_CONNECTOR_DVI_I_TV_1 = 0x20, // DVI-I-TV-S-Video + DCB_CONNECTOR_DVI_I_TV_0 = 0x21, // DVI-I-TV-Composite + DCB_CONNECTOR_DVI_I_TV_2 = 0x22, // DVI-I-TV-S-Video Breakout-Composite + DCB_CONNECTOR_DVI_I = 0x30, // DVI-I + DCB_CONNECTOR_DVI_D = 0x31, // DVI-D + DCB_CONNECTOR_DVI_ADC = 0x32, // Apple Display Connector (ADC) + DCB_CONNECTOR_DMS59_0 = 0x38, // LFH-DVI-I-1 + DCB_CONNECTOR_DMS59_1 = 0x39, // LFH-DVI-I-2 + DCB_CONNECTOR_BNC = 0x3c, // BNC Connector [for SDI?] + + /* LVDS / TMDS digital outputs */ + DCB_CONNECTOR_LVDS = 0x40, // LVDS-SPWG-Attached [is this name correct?] + DCB_CONNECTOR_LVDS_SPWG = 0x41, // LVDS-OEM-Attached (non-removable) + DCB_CONNECTOR_LVDS_REM = 0x42, // LVDS-SPWG-Detached [following naming above] + DCB_CONNECTOR_LVDS_SPWG_REM = 0x43, // LVDS-OEM-Detached (removable) + DCB_CONNECTOR_TMDS = 0x45, // TMDS-OEM-Attached (non-removable) + + /* DP digital outputs */ + DCB_CONNECTOR_DP = 0x46, // DisplayPort External Connector + DCB_CONNECTOR_eDP = 0x47, // DisplayPort Internal Connector + DCB_CONNECTOR_mDP = 0x48, // DisplayPort (Mini) External Connector + + /* Dock outputs (not used) */ + DCB_CONNECTOR_DOCK_VGA_0 = 0x50, // VGA 15-pin if not docked + DCB_CONNECTOR_DOCK_VGA_1 = 0x51, // VGA 15-pin if docked + DCB_CONNECTOR_DOCK_DVI_I_0 = 0x52, // DVI-I if not docked + DCB_CONNECTOR_DOCK_DVI_I_1 = 0x53, // DVI-I if docked + DCB_CONNECTOR_DOCK_DVI_D_0 = 0x54, // DVI-D if not docked + DCB_CONNECTOR_DOCK_DVI_D_1 = 0x55, // DVI-D if docked + DCB_CONNECTOR_DOCK_DP_0 = 0x56, // DisplayPort if not docked + DCB_CONNECTOR_DOCK_DP_1 = 0x57, // DisplayPort if docked + DCB_CONNECTOR_DOCK_mDP_0 = 0x58, // DisplayPort (Mini) if not docked + DCB_CONNECTOR_DOCK_mDP_1 = 0x59, // DisplayPort (Mini) if docked + + /* HDMI? digital outputs */ + DCB_CONNECTOR_HDMI_0 = 0x60, // HDMI? See [1] in top-level enum comment above + DCB_CONNECTOR_HDMI_1 = 0x61, // HDMI-A connector + DCB_CONNECTOR_SPDIF = 0x62, // Audio S/PDIF connector + DCB_CONNECTOR_HDMI_C = 0x63, // HDMI-C (Mini) connector + + /* Misc. digital outputs */ + DCB_CONNECTOR_DMS59_DP0 = 0x64, // LFH-DP-1 + DCB_CONNECTOR_DMS59_DP1 = 0x65, // LFH-DP-2 + DCB_CONNECTOR_WFD = 0x70, // Virtual connector for Wifi Display (WFD) + DCB_CONNECTOR_USB_C = 0x71, // [DP over USB-C; not present in docs] + DCB_CONNECTOR_NONE = 0xff // Skip Entry }; struct nvbios_connT { diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 00515623a2cc..829c2b573971 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -352,6 +352,8 @@ nouveau_user_framebuffer_create(struct drm_device *dev, static const struct drm_mode_config_funcs nouveau_mode_config_funcs = { .fb_create = nouveau_user_framebuffer_create, + .atomic_commit = drm_atomic_helper_commit, + .atomic_check = drm_atomic_helper_check, }; diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 58071652679d..3d8031296eed 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -425,7 +425,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm, bool is_large) order = ilog2(DMEM_CHUNK_NPAGES); } - zone_device_folio_init(folio, order); + zone_device_folio_init(folio, page_pgmap(folio_page(folio, 0)), order); return page; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c index 2dab6612c4fc..23d1e5c27bb1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c @@ -191,27 +191,60 @@ nvkm_uconn_new(const struct nvkm_oclass *oclass, void *argv, u32 argc, struct nv spin_lock(&disp->client.lock); if (!conn->object.func) { switch (conn->info.type) { - case DCB_CONNECTOR_VGA : args->v0.type = NVIF_CONN_V0_VGA; break; - case DCB_CONNECTOR_TV_0 : - case DCB_CONNECTOR_TV_1 : - case DCB_CONNECTOR_TV_3 : args->v0.type = NVIF_CONN_V0_TV; break; - case DCB_CONNECTOR_DMS59_0 : - case DCB_CONNECTOR_DMS59_1 : - case DCB_CONNECTOR_DVI_I : args->v0.type = NVIF_CONN_V0_DVI_I; break; - case DCB_CONNECTOR_DVI_D : args->v0.type = NVIF_CONN_V0_DVI_D; break; - case DCB_CONNECTOR_LVDS : args->v0.type = NVIF_CONN_V0_LVDS; break; - case DCB_CONNECTOR_LVDS_SPWG: args->v0.type = NVIF_CONN_V0_LVDS_SPWG; break; - case DCB_CONNECTOR_DMS59_DP0: - case DCB_CONNECTOR_DMS59_DP1: - case DCB_CONNECTOR_DP : - case DCB_CONNECTOR_mDP : - case DCB_CONNECTOR_USB_C : args->v0.type = NVIF_CONN_V0_DP; break; - case DCB_CONNECTOR_eDP : args->v0.type = NVIF_CONN_V0_EDP; break; - case DCB_CONNECTOR_HDMI_0 : - case DCB_CONNECTOR_HDMI_1 : - case DCB_CONNECTOR_HDMI_C : args->v0.type = NVIF_CONN_V0_HDMI; break; + /* VGA */ + case DCB_CONNECTOR_DVI_A : + case DCB_CONNECTOR_POD_VGA : + case DCB_CONNECTOR_VGA : args->v0.type = NVIF_CONN_V0_VGA; break; + + /* TV */ + case DCB_CONNECTOR_TV_0 : + case DCB_CONNECTOR_TV_1 : + case DCB_CONNECTOR_TV_2 : + case DCB_CONNECTOR_TV_SCART : + case DCB_CONNECTOR_TV_SCART_D : + case DCB_CONNECTOR_TV_DTERM : + case DCB_CONNECTOR_POD_TV_3 : + case DCB_CONNECTOR_POD_TV_1 : + case DCB_CONNECTOR_POD_TV_0 : + case DCB_CONNECTOR_TV_3 : args->v0.type = NVIF_CONN_V0_TV; break; + + /* DVI */ + case DCB_CONNECTOR_DVI_I_TV_1 : + case DCB_CONNECTOR_DVI_I_TV_0 : + case DCB_CONNECTOR_DVI_I_TV_2 : + case DCB_CONNECTOR_DVI_ADC : + case DCB_CONNECTOR_DMS59_0 : + case DCB_CONNECTOR_DMS59_1 : + case DCB_CONNECTOR_DVI_I : args->v0.type = NVIF_CONN_V0_DVI_I; break; + case DCB_CONNECTOR_TMDS : + case DCB_CONNECTOR_DVI_D : args->v0.type = NVIF_CONN_V0_DVI_D; break; + + /* LVDS */ + case DCB_CONNECTOR_LVDS : args->v0.type = NVIF_CONN_V0_LVDS; break; + case DCB_CONNECTOR_LVDS_SPWG : args->v0.type = NVIF_CONN_V0_LVDS_SPWG; break; + + /* DP */ + case DCB_CONNECTOR_DMS59_DP0 : + case DCB_CONNECTOR_DMS59_DP1 : + case DCB_CONNECTOR_DP : + case DCB_CONNECTOR_mDP : + case DCB_CONNECTOR_USB_C : args->v0.type = NVIF_CONN_V0_DP; break; + case DCB_CONNECTOR_eDP : args->v0.type = NVIF_CONN_V0_EDP; break; + + /* HDMI */ + case DCB_CONNECTOR_HDMI_0 : + case DCB_CONNECTOR_HDMI_1 : + case DCB_CONNECTOR_HDMI_C : args->v0.type = NVIF_CONN_V0_HDMI; break; + + /* + * Dock & unused outputs. + * BNC, SPDIF, WFD, and detached LVDS go here. + */ default: - WARN_ON(1); + nvkm_warn(&disp->engine.subdev, + "unimplemented connector type 0x%02x\n", + conn->info.type); + args->v0.type = NVIF_CONN_V0_VGA; ret = -EINVAL; break; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c index 35d1fcef520b..c456a9626823 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c @@ -30,6 +30,9 @@ ad102_gsp = { .booter.ctor = ga102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c index 503760246660..851140e80122 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c @@ -337,18 +337,12 @@ nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp) } int -nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +nvkm_gsp_fwsec_sb_init(struct nvkm_gsp *gsp) { return nvkm_gsp_fwsec_init(gsp, &gsp->fws.falcon.sb, "fwsec-sb", NVFW_FALCON_APPIF_DMEMMAPPER_CMD_SB); } -void -nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) -{ - nvkm_falcon_fw_dtor(&gsp->fws.falcon.sb); -} - int nvkm_gsp_fwsec_frts(struct nvkm_gsp *gsp) { diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c index d201e8697226..27a13aeccd3c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c @@ -47,6 +47,9 @@ ga100_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c index 917f7e2f6c46..b6b3eb6f4c00 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c @@ -158,6 +158,9 @@ ga102_gsp_r535 = { .booter.ctor = ga102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h index 86bdd203bc10..9dd66a2e3801 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h @@ -7,9 +7,8 @@ enum nvkm_acr_lsf_id; int nvkm_gsp_fwsec_frts(struct nvkm_gsp *); -int nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *); int nvkm_gsp_fwsec_sb(struct nvkm_gsp *); -void nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *); +int nvkm_gsp_fwsec_sb_init(struct nvkm_gsp *gsp); struct nvkm_gsp_fwif { int version; @@ -52,6 +51,11 @@ struct nvkm_gsp_func { struct nvkm_falcon *, struct nvkm_falcon_fw *); } booter; + struct { + int (*ctor)(struct nvkm_gsp *); + void (*dtor)(struct nvkm_gsp *); + } fwsec_sb; + void (*dtor)(struct nvkm_gsp *); int (*oneinit)(struct nvkm_gsp *); int (*init)(struct nvkm_gsp *); @@ -67,6 +71,8 @@ extern const struct nvkm_falcon_func tu102_gsp_flcn; extern const struct nvkm_falcon_fw_func tu102_gsp_fwsec; int tu102_gsp_booter_ctor(struct nvkm_gsp *, const char *, const struct firmware *, struct nvkm_falcon *, struct nvkm_falcon_fw *); +int tu102_gsp_fwsec_sb_ctor(struct nvkm_gsp *); +void tu102_gsp_fwsec_sb_dtor(struct nvkm_gsp *); int tu102_gsp_oneinit(struct nvkm_gsp *); int tu102_gsp_init(struct nvkm_gsp *); int tu102_gsp_fini(struct nvkm_gsp *, bool suspend); @@ -91,5 +97,18 @@ int r535_gsp_fini(struct nvkm_gsp *, bool suspend); int nvkm_gsp_new_(const struct nvkm_gsp_fwif *, struct nvkm_device *, enum nvkm_subdev_type, int, struct nvkm_gsp **); +static inline int nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +{ + if (gsp->func->fwsec_sb.ctor) + return gsp->func->fwsec_sb.ctor(gsp); + return 0; +} + +static inline void nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) +{ + if (gsp->func->fwsec_sb.dtor) + gsp->func->fwsec_sb.dtor(gsp); +} + extern const struct nvkm_gsp_func gv100_gsp; #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c index 81e56da0474a..04b642a1f730 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c @@ -30,6 +30,18 @@ #include <nvfw/fw.h> #include <nvfw/hs.h> +int +tu102_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +{ + return nvkm_gsp_fwsec_sb_init(gsp); +} + +void +tu102_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) +{ + nvkm_falcon_fw_dtor(&gsp->fws.falcon.sb); +} + static int tu102_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1) { @@ -370,6 +382,9 @@ tu102_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c index 97eb046c25d0..58cf25842421 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c @@ -30,6 +30,9 @@ tu116_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index b26b682826bc..162cc58c7b8f 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -623,49 +623,6 @@ static struct panel_simple *panel_simple_probe(struct device *dev) if (IS_ERR(desc)) return ERR_CAST(desc); - panel = devm_drm_panel_alloc(dev, struct panel_simple, base, - &panel_simple_funcs, desc->connector_type); - if (IS_ERR(panel)) - return ERR_CAST(panel); - - panel->desc = desc; - - panel->supply = devm_regulator_get(dev, "power"); - if (IS_ERR(panel->supply)) - return ERR_CAST(panel->supply); - - panel->enable_gpio = devm_gpiod_get_optional(dev, "enable", - GPIOD_OUT_LOW); - if (IS_ERR(panel->enable_gpio)) - return dev_err_cast_probe(dev, panel->enable_gpio, - "failed to request GPIO\n"); - - err = of_drm_get_panel_orientation(dev->of_node, &panel->orientation); - if (err) { - dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, err); - return ERR_PTR(err); - } - - ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0); - if (ddc) { - panel->ddc = of_find_i2c_adapter_by_node(ddc); - of_node_put(ddc); - - if (!panel->ddc) - return ERR_PTR(-EPROBE_DEFER); - } - - if (!of_device_is_compatible(dev->of_node, "panel-dpi") && - !of_get_display_timing(dev->of_node, "panel-timing", &dt)) - panel_simple_parse_panel_timing_node(dev, panel, &dt); - - if (desc->connector_type == DRM_MODE_CONNECTOR_LVDS) { - /* Optional data-mapping property for overriding bus format */ - err = panel_simple_override_nondefault_lvds_datamapping(dev, panel); - if (err) - goto free_ddc; - } - connector_type = desc->connector_type; /* Catch common mistakes for panels. */ switch (connector_type) { @@ -690,8 +647,7 @@ static struct panel_simple *panel_simple_probe(struct device *dev) break; case DRM_MODE_CONNECTOR_eDP: dev_warn(dev, "eDP panels moved to panel-edp\n"); - err = -EINVAL; - goto free_ddc; + return ERR_PTR(-EINVAL); case DRM_MODE_CONNECTOR_DSI: if (desc->bpc != 6 && desc->bpc != 8) dev_warn(dev, "Expected bpc in {6,8} but got: %u\n", desc->bpc); @@ -720,6 +676,49 @@ static struct panel_simple *panel_simple_probe(struct device *dev) break; } + panel = devm_drm_panel_alloc(dev, struct panel_simple, base, + &panel_simple_funcs, connector_type); + if (IS_ERR(panel)) + return ERR_CAST(panel); + + panel->desc = desc; + + panel->supply = devm_regulator_get(dev, "power"); + if (IS_ERR(panel->supply)) + return ERR_CAST(panel->supply); + + panel->enable_gpio = devm_gpiod_get_optional(dev, "enable", + GPIOD_OUT_LOW); + if (IS_ERR(panel->enable_gpio)) + return dev_err_cast_probe(dev, panel->enable_gpio, + "failed to request GPIO\n"); + + err = of_drm_get_panel_orientation(dev->of_node, &panel->orientation); + if (err) { + dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, err); + return ERR_PTR(err); + } + + ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0); + if (ddc) { + panel->ddc = of_find_i2c_adapter_by_node(ddc); + of_node_put(ddc); + + if (!panel->ddc) + return ERR_PTR(-EPROBE_DEFER); + } + + if (!of_device_is_compatible(dev->of_node, "panel-dpi") && + !of_get_display_timing(dev->of_node, "panel-timing", &dt)) + panel_simple_parse_panel_timing_node(dev, panel, &dt); + + if (desc->connector_type == DRM_MODE_CONNECTOR_LVDS) { + /* Optional data-mapping property for overriding bus format */ + err = panel_simple_override_nondefault_lvds_datamapping(dev, panel); + if (err) + goto free_ddc; + } + dev_set_drvdata(dev, panel); /* @@ -1900,6 +1899,7 @@ static const struct panel_desc dataimage_scf0700c48ggu18 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct display_timing dlc_dlc0700yzg_1_timing = { diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index d4839d282689..f6339963e496 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -1252,17 +1252,7 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, goto err_cleanup; } - /* drm_gpuvm_bo_obtain_prealloc() will call drm_gpuvm_bo_put() on our - * pre-allocated BO if the <BO,VM> association exists. Given we - * only have one ref on preallocated_vm_bo, drm_gpuvm_bo_destroy() will - * be called immediately, and we have to hold the VM resv lock when - * calling this function. - */ - dma_resv_lock(panthor_vm_resv(vm), NULL); - mutex_lock(&bo->base.base.gpuva.lock); op_ctx->map.vm_bo = drm_gpuvm_bo_obtain_prealloc(preallocated_vm_bo); - mutex_unlock(&bo->base.base.gpuva.lock); - dma_resv_unlock(panthor_vm_resv(vm)); op_ctx->map.bo_offset = offset; diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 56ff6a3fb483..d7dc83cf7b00 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -295,7 +295,7 @@ static int pl111_amba_probe(struct amba_device *amba_dev, variant->name, priv); if (ret != 0) { dev_err(dev, "%s failed irq %d\n", __func__, ret); - return ret; + goto dev_put; } ret = pl111_modeset_init(drm); diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h index 969a8fb0ee9e..f4e71046dc91 100644 --- a/drivers/gpu/drm/radeon/pptable.h +++ b/drivers/gpu/drm/radeon/pptable.h @@ -450,7 +450,7 @@ typedef struct _ClockInfoArray{ //sizeof(ATOM_PPLIB_CLOCK_INFO) UCHAR ucEntrySize; - UCHAR clockInfo[] __counted_by(ucNumEntries); + UCHAR clockInfo[] /*__counted_by(ucNumEntries)*/; }ClockInfoArray; typedef struct _NonClockInfoArray{ diff --git a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c index c9fe6aa3e3e3..8604342f9943 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c @@ -121,7 +121,7 @@ static void dw_hdmi_qp_rockchip_encoder_enable(struct drm_encoder *encoder) struct drm_crtc *crtc = encoder->crtc; /* Unconditionally switch to TMDS as FRL is not yet supported */ - gpiod_set_value(hdmi->frl_enable_gpio, 0); + gpiod_set_value_cansleep(hdmi->frl_enable_gpio, 0); if (!crtc || !crtc->state) return; @@ -640,6 +640,15 @@ static void dw_hdmi_qp_rockchip_remove(struct platform_device *pdev) component_del(&pdev->dev, &dw_hdmi_qp_rockchip_ops); } +static int __maybe_unused dw_hdmi_qp_rockchip_suspend(struct device *dev) +{ + struct rockchip_hdmi_qp *hdmi = dev_get_drvdata(dev); + + dw_hdmi_qp_suspend(dev, hdmi->hdmi); + + return 0; +} + static int __maybe_unused dw_hdmi_qp_rockchip_resume(struct device *dev) { struct rockchip_hdmi_qp *hdmi = dev_get_drvdata(dev); @@ -655,7 +664,8 @@ static int __maybe_unused dw_hdmi_qp_rockchip_resume(struct device *dev) } static const struct dev_pm_ops dw_hdmi_qp_rockchip_pm = { - SET_SYSTEM_SLEEP_PM_OPS(NULL, dw_hdmi_qp_rockchip_resume) + SET_SYSTEM_SLEEP_PM_OPS(dw_hdmi_qp_rockchip_suspend, + dw_hdmi_qp_rockchip_resume) }; struct platform_driver dw_hdmi_qp_rockchip_pltfm_driver = { diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c index cd8380f0eddc..f3950e8476a7 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c @@ -2104,7 +2104,7 @@ static void rk3568_vop2_wait_for_port_mux_done(struct vop2 *vop2) * Spin until the previous port_mux figuration is done. */ ret = readx_poll_timeout_atomic(rk3568_vop2_read_port_mux, vop2, port_mux_sel, - port_mux_sel == vop2->old_port_sel, 0, 50 * 1000); + port_mux_sel == vop2->old_port_sel, 10, 50 * 1000); if (ret) DRM_DEV_ERROR(vop2->dev, "wait port_mux done timeout: 0x%x--0x%x\n", port_mux_sel, vop2->old_port_sel); @@ -2124,7 +2124,7 @@ static void rk3568_vop2_wait_for_layer_cfg_done(struct vop2 *vop2, u32 cfg) * Spin until the previous layer configuration is done. */ ret = readx_poll_timeout_atomic(rk3568_vop2_read_layer_cfg, vop2, atv_layer_cfg, - atv_layer_cfg == cfg, 0, 50 * 1000); + atv_layer_cfg == cfg, 10, 50 * 1000); if (ret) DRM_DEV_ERROR(vop2->dev, "wait layer cfg done timeout: 0x%x--0x%x\n", atv_layer_cfg, cfg); @@ -2144,6 +2144,7 @@ static void rk3568_vop2_setup_layer_mixer(struct vop2_video_port *vp) u8 layer_sel_id; unsigned int ofs; u32 ovl_ctrl; + u32 cfg_done; int i; struct vop2_video_port *vp0 = &vop2->vps[0]; struct vop2_video_port *vp1 = &vop2->vps[1]; @@ -2298,8 +2299,16 @@ static void rk3568_vop2_setup_layer_mixer(struct vop2_video_port *vp) rk3568_vop2_wait_for_port_mux_done(vop2); } - if (layer_sel != old_layer_sel && atv_layer_sel != old_layer_sel) - rk3568_vop2_wait_for_layer_cfg_done(vop2, vop2->old_layer_sel); + if (layer_sel != old_layer_sel && atv_layer_sel != old_layer_sel) { + cfg_done = vop2_readl(vop2, RK3568_REG_CFG_DONE); + cfg_done &= (BIT(vop2->data->nr_vps) - 1); + cfg_done &= ~BIT(vp->id); + /* + * Changes of other VPs' overlays have not taken effect + */ + if (cfg_done) + rk3568_vop2_wait_for_layer_cfg_done(vop2, vop2->old_layer_sel); + } vop2_writel(vop2, RK3568_OVL_LAYER_SEL, layer_sel); mutex_unlock(&vop2->ovl_lock); diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_helper.h b/drivers/gpu/drm/sysfb/drm_sysfb_helper.h index da670d7eeb2e..de96bfe7562c 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_helper.h +++ b/drivers/gpu/drm/sysfb/drm_sysfb_helper.h @@ -55,15 +55,6 @@ const struct drm_format_info *drm_sysfb_get_format_si(struct drm_device *dev, #endif /* - * Input parsing - */ - -int drm_sysfb_get_validated_int(struct drm_device *dev, const char *name, - u64 value, u32 max); -int drm_sysfb_get_validated_int0(struct drm_device *dev, const char *name, - u64 value, u32 max); - -/* * Display modes */ diff --git a/drivers/gpu/drm/tidss/tidss_kms.c b/drivers/gpu/drm/tidss/tidss_kms.c index 86eb5d97410b..8bb93194e5ac 100644 --- a/drivers/gpu/drm/tidss/tidss_kms.c +++ b/drivers/gpu/drm/tidss/tidss_kms.c @@ -26,9 +26,33 @@ static void tidss_atomic_commit_tail(struct drm_atomic_state *old_state) tidss_runtime_get(tidss); - drm_atomic_helper_commit_modeset_disables(ddev, old_state); - drm_atomic_helper_commit_planes(ddev, old_state, DRM_PLANE_COMMIT_ACTIVE_ONLY); - drm_atomic_helper_commit_modeset_enables(ddev, old_state); + /* + * TI's OLDI and DSI encoders need to be set up before the crtc is + * enabled. Thus drm_atomic_helper_commit_modeset_enables() and + * drm_atomic_helper_commit_modeset_disables() cannot be used here, as + * they enable the crtc before bridges' pre-enable, and disable the crtc + * after bridges' post-disable. + * + * Open code the functions here and first call the bridges' pre-enables, + * then crtc enable, then bridges' post-enable (and vice versa for + * disable). + */ + + drm_atomic_helper_commit_encoder_bridge_disable(ddev, old_state); + drm_atomic_helper_commit_crtc_disable(ddev, old_state); + drm_atomic_helper_commit_encoder_bridge_post_disable(ddev, old_state); + + drm_atomic_helper_update_legacy_modeset_state(ddev, old_state); + drm_atomic_helper_calc_timestamping_constants(old_state); + drm_atomic_helper_commit_crtc_set_mode(ddev, old_state); + + drm_atomic_helper_commit_planes(ddev, old_state, + DRM_PLANE_COMMIT_ACTIVE_ONLY); + + drm_atomic_helper_commit_encoder_bridge_pre_enable(ddev, old_state); + drm_atomic_helper_commit_crtc_enable(ddev, old_state); + drm_atomic_helper_commit_encoder_bridge_enable(ddev, old_state); + drm_atomic_helper_commit_writebacks(ddev, old_state); drm_atomic_helper_commit_hw_done(old_state); drm_atomic_helper_wait_for_flip_done(ddev, old_state); diff --git a/drivers/gpu/drm/vkms/vkms_colorop.c b/drivers/gpu/drm/vkms/vkms_colorop.c index 5c3ffc78aea0..d03a1f2e9c41 100644 --- a/drivers/gpu/drm/vkms/vkms_colorop.c +++ b/drivers/gpu/drm/vkms/vkms_colorop.c @@ -37,7 +37,6 @@ static int vkms_initialize_color_pipeline(struct drm_plane *plane, struct drm_pr goto cleanup; list->type = ops[i]->base.id; - list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", ops[i]->base.id); i++; @@ -88,6 +87,8 @@ static int vkms_initialize_color_pipeline(struct drm_plane *plane, struct drm_pr drm_colorop_set_next_property(ops[i - 1], ops[i]); + list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", ops[0]->base.id); + return 0; cleanup: @@ -103,18 +104,18 @@ cleanup: int vkms_initialize_colorops(struct drm_plane *plane) { - struct drm_prop_enum_list pipeline; - int ret; + struct drm_prop_enum_list pipeline = {}; + int ret = 0; /* Add color pipeline */ ret = vkms_initialize_color_pipeline(plane, &pipeline); if (ret) - return ret; + goto out; /* Create COLOR_PIPELINE property and attach */ ret = drm_plane_create_color_pipeline_property(plane, &pipeline, 1); - if (ret) - return ret; - return 0; + kfree(pipeline.name); +out: + return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index f031a312c783..b22887e8c881 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -32,9 +32,15 @@ #include <drm/ttm/ttm_placement.h> -static void vmw_bo_release(struct vmw_bo *vbo) +/** + * vmw_bo_free - vmw_bo destructor + * + * @bo: Pointer to the embedded struct ttm_buffer_object + */ +static void vmw_bo_free(struct ttm_buffer_object *bo) { struct vmw_resource *res; + struct vmw_bo *vbo = to_vmw_bo(&bo->base); WARN_ON(kref_read(&vbo->tbo.base.refcount) != 0); vmw_bo_unmap(vbo); @@ -62,20 +68,8 @@ static void vmw_bo_release(struct vmw_bo *vbo) } vmw_surface_unreference(&vbo->dumb_surface); } - drm_gem_object_release(&vbo->tbo.base); -} - -/** - * vmw_bo_free - vmw_bo destructor - * - * @bo: Pointer to the embedded struct ttm_buffer_object - */ -static void vmw_bo_free(struct ttm_buffer_object *bo) -{ - struct vmw_bo *vbo = to_vmw_bo(&bo->base); - WARN_ON(!RB_EMPTY_ROOT(&vbo->res_tree)); - vmw_bo_release(vbo); + drm_gem_object_release(&vbo->tbo.base); WARN_ON(vbo->dirty); kfree(vbo); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 00be92da5509..85795082fef9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -515,12 +515,12 @@ int vmw_fence_obj_unref_ioctl(struct drm_device *dev, void *data, /** * vmw_event_fence_action_seq_passed * - * @action: The struct vmw_fence_action embedded in a struct - * vmw_event_fence_action. + * @f: The struct dma_fence which provides timestamp for the action event + * @cb: The struct dma_fence_cb callback for the action event. * - * This function is called when the seqno of the fence where @action is - * attached has passed. It queues the event on the submitter's event list. - * This function is always called from atomic context. + * This function is called when the seqno of the fence has passed + * and it is always called from atomic context. + * It queues the event on the submitter's event list. */ static void vmw_event_fence_action_seq_passed(struct dma_fence *f, struct dma_fence_cb *cb) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index d32ce1cb579e..bc51b5d55e38 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -766,13 +766,15 @@ err_out: return ERR_PTR(ret); } - ttm_bo_reserve(&bo->tbo, false, false, NULL); - ret = vmw_bo_dirty_add(bo); - if (!ret && surface && surface->res.func->dirty_alloc) { - surface->res.coherent = true; - ret = surface->res.func->dirty_alloc(&surface->res); + if (bo) { + ttm_bo_reserve(&bo->tbo, false, false, NULL); + ret = vmw_bo_dirty_add(bo); + if (!ret && surface && surface->res.func->dirty_alloc) { + surface->res.coherent = true; + ret = surface->res.func->dirty_alloc(&surface->res); + } + ttm_bo_unreserve(&bo->tbo); } - ttm_bo_unreserve(&bo->tbo); return &vfb->base; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 69dfe69ce0f8..a8c8c9375d29 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -923,8 +923,10 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, ttm_bo_unreserve(&buf->tbo); res = vmw_shader_alloc(dev_priv, buf, size, 0, shader_type); - if (unlikely(ret != 0)) + if (IS_ERR(res)) { + ret = PTR_ERR(res); goto no_reserve; + } ret = vmw_cmdbuf_res_add(man, vmw_cmdbuf_res_shader, vmw_shader_key(user_key, shader_type), diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index 4b288eb3f5b0..4d7dcaff2b91 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -39,7 +39,7 @@ config DRM_XE select DRM_TTM select DRM_TTM_HELPER select DRM_EXEC - select DRM_GPUSVM if !UML && DEVICE_PRIVATE + select DRM_GPUSVM if !UML select DRM_GPUVM select DRM_SCHED select MMU_NOTIFIER @@ -80,8 +80,9 @@ config DRM_XE_GPUSVM bool "Enable CPU to GPU address mirroring" depends on DRM_XE depends on !UML - depends on DEVICE_PRIVATE + depends on ZONE_DEVICE default y + select DEVICE_PRIVATE select DRM_GPUSVM help Enable this option if you want support for CPU to GPU address diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index bf4ee976b680..71acd45aa33b 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -1055,6 +1055,7 @@ static long xe_bo_shrink_purge(struct ttm_operation_ctx *ctx, unsigned long *scanned) { struct xe_device *xe = ttm_to_xe_device(bo->bdev); + struct ttm_tt *tt = bo->ttm; long lret; /* Fake move to system, without copying data. */ @@ -1079,8 +1080,10 @@ static long xe_bo_shrink_purge(struct ttm_operation_ctx *ctx, .writeback = false, .allow_move = false}); - if (lret > 0) + if (lret > 0) { xe_ttm_tt_account_subtract(xe, bo->ttm); + update_global_total_pages(bo->bdev, -(long)tt->num_pages); + } return lret; } @@ -1166,8 +1169,10 @@ long xe_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo, if (needs_rpm) xe_pm_runtime_put(xe); - if (lret > 0) + if (lret > 0) { xe_ttm_tt_account_subtract(xe, tt); + update_global_total_pages(bo->bdev, -(long)tt->num_pages); + } out_unref: xe_bo_put(xe_bo); diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c index e91da9589c5f..63fd8bf13c70 100644 --- a/drivers/gpu/drm/xe/xe_debugfs.c +++ b/drivers/gpu/drm/xe/xe_debugfs.c @@ -256,14 +256,64 @@ static ssize_t wedged_mode_show(struct file *f, char __user *ubuf, return simple_read_from_buffer(ubuf, size, pos, buf, len); } +static int __wedged_mode_set_reset_policy(struct xe_gt *gt, enum xe_wedged_mode mode) +{ + bool enable_engine_reset; + int ret; + + enable_engine_reset = (mode != XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET); + ret = xe_guc_ads_scheduler_policy_toggle_reset(>->uc.guc.ads, + enable_engine_reset); + if (ret) + xe_gt_err(gt, "Failed to update GuC ADS scheduler policy (%pe)\n", ERR_PTR(ret)); + + return ret; +} + +static int wedged_mode_set_reset_policy(struct xe_device *xe, enum xe_wedged_mode mode) +{ + struct xe_gt *gt; + int ret; + u8 id; + + guard(xe_pm_runtime)(xe); + for_each_gt(gt, xe, id) { + ret = __wedged_mode_set_reset_policy(gt, mode); + if (ret) { + if (id > 0) { + xe->wedged.inconsistent_reset = true; + drm_err(&xe->drm, "Inconsistent reset policy state between GTs\n"); + } + return ret; + } + } + + xe->wedged.inconsistent_reset = false; + + return 0; +} + +static bool wedged_mode_needs_policy_update(struct xe_device *xe, enum xe_wedged_mode mode) +{ + if (xe->wedged.inconsistent_reset) + return true; + + if (xe->wedged.mode == mode) + return false; + + if (xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET || + mode == XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET) + return true; + + return false; +} + static ssize_t wedged_mode_set(struct file *f, const char __user *ubuf, size_t size, loff_t *pos) { struct xe_device *xe = file_inode(f)->i_private; - struct xe_gt *gt; u32 wedged_mode; ssize_t ret; - u8 id; ret = kstrtouint_from_user(ubuf, size, 0, &wedged_mode); if (ret) @@ -272,22 +322,14 @@ static ssize_t wedged_mode_set(struct file *f, const char __user *ubuf, if (wedged_mode > 2) return -EINVAL; - if (xe->wedged.mode == wedged_mode) - return size; + if (wedged_mode_needs_policy_update(xe, wedged_mode)) { + ret = wedged_mode_set_reset_policy(xe, wedged_mode); + if (ret) + return ret; + } xe->wedged.mode = wedged_mode; - xe_pm_runtime_get(xe); - for_each_gt(gt, xe, id) { - ret = xe_guc_ads_scheduler_policy_toggle_reset(>->uc.guc.ads); - if (ret) { - xe_gt_err(gt, "Failed to update GuC ADS scheduler policy. GuC may still cause engine reset even with wedged_mode=2\n"); - xe_pm_runtime_put(xe); - return -EIO; - } - } - xe_pm_runtime_put(xe); - return size; } diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 0b2fa7c56d38..047e86e22133 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -44,6 +44,22 @@ struct xe_pat_ops; struct xe_pxp; struct xe_vram_region; +/** + * enum xe_wedged_mode - possible wedged modes + * @XE_WEDGED_MODE_NEVER: Device will never be declared wedged. + * @XE_WEDGED_MODE_UPON_CRITICAL_ERROR: Device will be declared wedged only + * when critical error occurs like GT reset failure or firmware failure. + * This is the default mode. + * @XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET: Device will be declared wedged on + * any hang. In this mode, engine resets are disabled to avoid automatic + * recovery attempts. This mode is primarily intended for debugging hangs. + */ +enum xe_wedged_mode { + XE_WEDGED_MODE_NEVER = 0, + XE_WEDGED_MODE_UPON_CRITICAL_ERROR = 1, + XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET = 2, +}; + #define XE_BO_INVALID_OFFSET LONG_MAX #define GRAPHICS_VER(xe) ((xe)->info.graphics_verx100 / 100) @@ -587,6 +603,8 @@ struct xe_device { int mode; /** @wedged.method: Recovery method to be sent in the drm device wedged uevent */ unsigned long method; + /** @wedged.inconsistent_reset: Inconsistent reset policy state between GTs */ + bool inconsistent_reset; } wedged; /** @bo_device: Struct to control async free of BOs */ diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 8724f8de67e2..779d7e7e2d2e 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -328,6 +328,7 @@ struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe * @xe: Xe device. * @tile: tile which bind exec queue belongs to. * @flags: exec queue creation flags + * @user_vm: The user VM which this exec queue belongs to * @extensions: exec queue creation extensions * * Normalize bind exec queue creation. Bind exec queue is tied to migration VM @@ -341,6 +342,7 @@ struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe */ struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe, struct xe_tile *tile, + struct xe_vm *user_vm, u32 flags, u64 extensions) { struct xe_gt *gt = tile->primary_gt; @@ -377,6 +379,9 @@ struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe, xe_exec_queue_put(q); return ERR_PTR(err); } + + if (user_vm) + q->user_vm = xe_vm_get(user_vm); } return q; @@ -407,6 +412,11 @@ void xe_exec_queue_destroy(struct kref *ref) xe_exec_queue_put(eq); } + if (q->user_vm) { + xe_vm_put(q->user_vm); + q->user_vm = NULL; + } + q->ops->destroy(q); } @@ -742,6 +752,22 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, XE_IOCTL_DBG(xe, eci[0].engine_instance != 0)) return -EINVAL; + vm = xe_vm_lookup(xef, args->vm_id); + if (XE_IOCTL_DBG(xe, !vm)) + return -ENOENT; + + err = down_read_interruptible(&vm->lock); + if (err) { + xe_vm_put(vm); + return err; + } + + if (XE_IOCTL_DBG(xe, xe_vm_is_closed_or_banned(vm))) { + up_read(&vm->lock); + xe_vm_put(vm); + return -ENOENT; + } + for_each_tile(tile, xe, id) { struct xe_exec_queue *new; @@ -749,9 +775,11 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, if (id) flags |= EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD; - new = xe_exec_queue_create_bind(xe, tile, flags, + new = xe_exec_queue_create_bind(xe, tile, vm, flags, args->extensions); if (IS_ERR(new)) { + up_read(&vm->lock); + xe_vm_put(vm); err = PTR_ERR(new); if (q) goto put_exec_queue; @@ -763,6 +791,8 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, list_add_tail(&new->multi_gt_list, &q->multi_gt_link); } + up_read(&vm->lock); + xe_vm_put(vm); } else { logical_mask = calc_validate_logical_mask(xe, eci, args->width, diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h index fda4d4f9bda8..37a9da22f420 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.h +++ b/drivers/gpu/drm/xe/xe_exec_queue.h @@ -28,6 +28,7 @@ struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe u32 flags, u64 extensions); struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe, struct xe_tile *tile, + struct xe_vm *user_vm, u32 flags, u64 extensions); void xe_exec_queue_fini(struct xe_exec_queue *q); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 771ffe35cd0c..3a4263c92b3d 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -54,6 +54,12 @@ struct xe_exec_queue { struct kref refcount; /** @vm: VM (address space) for this exec queue */ struct xe_vm *vm; + /** + * @user_vm: User VM (address space) for this exec queue (bind queues + * only) + */ + struct xe_vm *user_vm; + /** @class: class of this exec queue */ enum xe_engine_class class; /** diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index ef481b334af4..793d7324a395 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -322,7 +322,7 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt) else ggtt->pt_ops = &xelp_pt_ops; - ggtt->wq = alloc_workqueue("xe-ggtt-wq", 0, WQ_MEM_RECLAIM); + ggtt->wq = alloc_workqueue("xe-ggtt-wq", WQ_MEM_RECLAIM, 0); if (!ggtt->wq) return -ENOMEM; diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h index 420b0e6089de..e8897a77ba19 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h @@ -41,10 +41,10 @@ struct xe_gt_sriov_vf_runtime { }; /** - * xe_gt_sriov_vf_migration - VF migration data. + * struct xe_gt_sriov_vf_migration - VF migration data. */ struct xe_gt_sriov_vf_migration { - /** @migration: VF migration recovery worker */ + /** @worker: VF migration recovery worker */ struct work_struct worker; /** @lock: Protects recovery_queued, teardown */ spinlock_t lock; diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c index bcb85a1bf26d..3f7f1b5602d5 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.c +++ b/drivers/gpu/drm/xe/xe_guc_ads.c @@ -983,16 +983,17 @@ static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_off /** * xe_guc_ads_scheduler_policy_toggle_reset - Toggle reset policy * @ads: Additional data structures object + * @enable_engine_reset: true to enable engine resets, false otherwise * - * This function update the GuC's engine reset policy based on wedged.mode. + * This function update the GuC's engine reset policy. * * Return: 0 on success, and negative error code otherwise. */ -int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads) +int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads, + bool enable_engine_reset) { struct guc_policies *policies; struct xe_guc *guc = ads_to_guc(ads); - struct xe_device *xe = ads_to_xe(ads); CLASS(xe_guc_buf, buf)(&guc->buf, sizeof(*policies)); if (!xe_guc_buf_is_valid(buf)) @@ -1004,10 +1005,11 @@ int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads) policies->dpc_promote_time = ads_blob_read(ads, policies.dpc_promote_time); policies->max_num_work_items = ads_blob_read(ads, policies.max_num_work_items); policies->is_valid = 1; - if (xe->wedged.mode == 2) - policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET; - else + + if (enable_engine_reset) policies->global_flags &= ~GLOBAL_POLICY_DISABLE_ENGINE_RESET; + else + policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET; return guc_ads_action_update_policies(ads, xe_guc_buf_flush(buf)); } diff --git a/drivers/gpu/drm/xe/xe_guc_ads.h b/drivers/gpu/drm/xe/xe_guc_ads.h index 2e6674c760ff..7a39f361cb17 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.h +++ b/drivers/gpu/drm/xe/xe_guc_ads.h @@ -6,6 +6,8 @@ #ifndef _XE_GUC_ADS_H_ #define _XE_GUC_ADS_H_ +#include <linux/types.h> + struct xe_guc_ads; int xe_guc_ads_init(struct xe_guc_ads *ads); @@ -13,6 +15,7 @@ int xe_guc_ads_init_post_hwconfig(struct xe_guc_ads *ads); void xe_guc_ads_populate(struct xe_guc_ads *ads); void xe_guc_ads_populate_minimal(struct xe_guc_ads *ads); void xe_guc_ads_populate_post_load(struct xe_guc_ads *ads); -int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads); +int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads, + bool enable_engine_reset); #endif diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 4ac434ad216f..a5019d1e741b 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -104,7 +104,9 @@ static void g2h_fence_cancel(struct g2h_fence *g2h_fence) { g2h_fence->cancel = true; g2h_fence->fail = true; - g2h_fence->done = true; + + /* WRITE_ONCE pairs with READ_ONCEs in guc_ct_send_recv. */ + WRITE_ONCE(g2h_fence->done, true); } static bool g2h_fence_needs_alloc(struct g2h_fence *g2h_fence) @@ -1203,10 +1205,13 @@ retry_same_fence: return ret; } - ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ); + /* READ_ONCEs pairs with WRITE_ONCEs in parse_g2h_response + * and g2h_fence_cancel. + */ + ret = wait_event_timeout(ct->g2h_fence_wq, READ_ONCE(g2h_fence.done), HZ); if (!ret) { LNL_FLUSH_WORK(&ct->g2h_worker); - if (g2h_fence.done) { + if (READ_ONCE(g2h_fence.done)) { xe_gt_warn(gt, "G2H fence %u, action %04x, done\n", g2h_fence.seqno, action[0]); ret = 1; @@ -1454,7 +1459,8 @@ static int parse_g2h_response(struct xe_guc_ct *ct, u32 *msg, u32 len) g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN); - g2h_fence->done = true; + /* WRITE_ONCE pairs with READ_ONCEs in guc_ct_send_recv. */ + WRITE_ONCE(g2h_fence->done, true); smp_mb(); wake_up_all(&ct->g2h_fence_wq); diff --git a/drivers/gpu/drm/xe/xe_late_bind_fw_types.h b/drivers/gpu/drm/xe/xe_late_bind_fw_types.h index 0f5da89ce98b..2a8a985c37e7 100644 --- a/drivers/gpu/drm/xe/xe_late_bind_fw_types.h +++ b/drivers/gpu/drm/xe/xe_late_bind_fw_types.h @@ -15,10 +15,12 @@ #define XE_LB_MAX_PAYLOAD_SIZE SZ_4K /** - * xe_late_bind_fw_id - enum to determine late binding fw index + * enum xe_late_bind_fw_id - enum to determine late binding fw index */ enum xe_late_bind_fw_id { + /** @XE_LB_FW_FAN_CONTROL: Fan control */ XE_LB_FW_FAN_CONTROL = 0, + /** @XE_LB_FW_MAX_ID: Number of IDs */ XE_LB_FW_MAX_ID }; diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index b5083c99dd50..281286f2b5f9 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -1050,6 +1050,9 @@ static ssize_t setup_utilization_wa(struct xe_lrc *lrc, { u32 *cmd = batch; + if (IS_SRIOV_VF(gt_to_xe(lrc->gt))) + return 0; + if (xe_gt_WARN_ON(lrc->gt, max_len < 12)) return -ENOSPC; diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 2184af413b91..d8ee76aab4e4 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -2062,6 +2062,7 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, unsigned long sram_offset, struct drm_pagemap_addr *sram_addr, u64 vram_addr, + struct dma_fence *deps, const enum xe_migrate_copy_dir dir) { struct xe_gt *gt = m->tile->primary_gt; @@ -2150,6 +2151,14 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, xe_sched_job_add_migrate_flush(job, MI_INVALIDATE_TLB); + if (deps && !dma_fence_is_signaled(deps)) { + dma_fence_get(deps); + err = drm_sched_job_add_dependency(&job->drm, deps); + if (err) + dma_fence_wait(deps, false); + err = 0; + } + mutex_lock(&m->job_mutex); xe_sched_job_arm(job); fence = dma_fence_get(&job->drm.s_fence->finished); @@ -2175,6 +2184,8 @@ err: * @npages: Number of pages to migrate. * @src_addr: Array of DMA information (source of migrate) * @dst_addr: Device physical address of VRAM (destination of migrate) + * @deps: struct dma_fence representing the dependencies that need + * to be signaled before migration. * * Copy from an array dma addresses to a VRAM device physical address * @@ -2184,10 +2195,11 @@ err: struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, unsigned long npages, struct drm_pagemap_addr *src_addr, - u64 dst_addr) + u64 dst_addr, + struct dma_fence *deps) { return xe_migrate_vram(m, npages * PAGE_SIZE, 0, src_addr, dst_addr, - XE_MIGRATE_COPY_TO_VRAM); + deps, XE_MIGRATE_COPY_TO_VRAM); } /** @@ -2196,6 +2208,8 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, * @npages: Number of pages to migrate. * @src_addr: Device physical address of VRAM (source of migrate) * @dst_addr: Array of DMA information (destination of migrate) + * @deps: struct dma_fence representing the dependencies that need + * to be signaled before migration. * * Copy from a VRAM device physical address to an array dma addresses * @@ -2205,10 +2219,11 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m, unsigned long npages, u64 src_addr, - struct drm_pagemap_addr *dst_addr) + struct drm_pagemap_addr *dst_addr, + struct dma_fence *deps) { return xe_migrate_vram(m, npages * PAGE_SIZE, 0, dst_addr, src_addr, - XE_MIGRATE_COPY_TO_SRAM); + deps, XE_MIGRATE_COPY_TO_SRAM); } static void xe_migrate_dma_unmap(struct xe_device *xe, @@ -2384,7 +2399,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, __fence = xe_migrate_vram(m, current_bytes, (unsigned long)buf & ~PAGE_MASK, &pagemap_addr[current_page], - vram_addr, write ? + vram_addr, NULL, write ? XE_MIGRATE_COPY_TO_VRAM : XE_MIGRATE_COPY_TO_SRAM); if (IS_ERR(__fence)) { @@ -2430,7 +2445,7 @@ void xe_migrate_job_lock(struct xe_migrate *m, struct xe_exec_queue *q) if (is_migrate) mutex_lock(&m->job_mutex); else - xe_vm_assert_held(q->vm); /* User queues VM's should be locked */ + xe_vm_assert_held(q->user_vm); /* User queues VM's should be locked */ } /** @@ -2448,7 +2463,7 @@ void xe_migrate_job_unlock(struct xe_migrate *m, struct xe_exec_queue *q) if (is_migrate) mutex_unlock(&m->job_mutex); else - xe_vm_assert_held(q->vm); /* User queues VM's should be locked */ + xe_vm_assert_held(q->user_vm); /* User queues VM's should be locked */ } #if IS_ENABLED(CONFIG_PROVE_LOCKING) diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h index 260e298e5dd7..b76441f062b4 100644 --- a/drivers/gpu/drm/xe/xe_migrate.h +++ b/drivers/gpu/drm/xe/xe_migrate.h @@ -116,12 +116,14 @@ int xe_migrate_init(struct xe_migrate *m); struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, unsigned long npages, struct drm_pagemap_addr *src_addr, - u64 dst_addr); + u64 dst_addr, + struct dma_fence *deps); struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m, unsigned long npages, u64 src_addr, - struct drm_pagemap_addr *dst_addr); + struct drm_pagemap_addr *dst_addr, + struct dma_fence *deps); struct dma_fence *xe_migrate_copy(struct xe_migrate *m, struct xe_bo *src_bo, diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c index 797a4b866226..d963231b5135 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c @@ -346,7 +346,7 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe) flags = EXEC_QUEUE_FLAG_KERNEL | EXEC_QUEUE_FLAG_PERMANENT | EXEC_QUEUE_FLAG_MIGRATE; - q = xe_exec_queue_create_bind(xe, tile, flags, 0); + q = xe_exec_queue_create_bind(xe, tile, NULL, flags, 0); if (IS_ERR(q)) { err = PTR_ERR(q); goto err_ret; diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index 55c5a0eb82e1..f97e0af6a9b0 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -476,7 +476,8 @@ static void xe_svm_copy_us_stats_incr(struct xe_gt *gt, static int xe_svm_copy(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages, const enum xe_svm_copy_dir dir) + unsigned long npages, const enum xe_svm_copy_dir dir, + struct dma_fence *pre_migrate_fence) { struct xe_vram_region *vr = NULL; struct xe_gt *gt = NULL; @@ -565,7 +566,8 @@ static int xe_svm_copy(struct page **pages, __fence = xe_migrate_from_vram(vr->migrate, i - pos + incr, vram_addr, - &pagemap_addr[pos]); + &pagemap_addr[pos], + pre_migrate_fence); } else { vm_dbg(&xe->drm, "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld", @@ -574,13 +576,14 @@ static int xe_svm_copy(struct page **pages, __fence = xe_migrate_to_vram(vr->migrate, i - pos + incr, &pagemap_addr[pos], - vram_addr); + vram_addr, + pre_migrate_fence); } if (IS_ERR(__fence)) { err = PTR_ERR(__fence); goto err_out; } - + pre_migrate_fence = NULL; dma_fence_put(fence); fence = __fence; } @@ -603,20 +606,22 @@ static int xe_svm_copy(struct page **pages, vram_addr, (u64)pagemap_addr[pos].addr, 1); __fence = xe_migrate_from_vram(vr->migrate, 1, vram_addr, - &pagemap_addr[pos]); + &pagemap_addr[pos], + pre_migrate_fence); } else { vm_dbg(&xe->drm, "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%d", (u64)pagemap_addr[pos].addr, vram_addr, 1); __fence = xe_migrate_to_vram(vr->migrate, 1, &pagemap_addr[pos], - vram_addr); + vram_addr, + pre_migrate_fence); } if (IS_ERR(__fence)) { err = PTR_ERR(__fence); goto err_out; } - + pre_migrate_fence = NULL; dma_fence_put(fence); fence = __fence; } @@ -629,6 +634,8 @@ err_out: dma_fence_wait(fence, false); dma_fence_put(fence); } + if (pre_migrate_fence) + dma_fence_wait(pre_migrate_fence, false); /* * XXX: We can't derive the GT here (or anywhere in this functions, but @@ -645,16 +652,20 @@ err_out: static int xe_svm_copy_to_devmem(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages) + unsigned long npages, + struct dma_fence *pre_migrate_fence) { - return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM); + return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM, + pre_migrate_fence); } static int xe_svm_copy_to_ram(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages) + unsigned long npages, + struct dma_fence *pre_migrate_fence) { - return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM); + return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM, + pre_migrate_fence); } static struct xe_bo *to_xe_bo(struct drm_pagemap_devmem *devmem_allocation) @@ -667,6 +678,7 @@ static void xe_svm_devmem_release(struct drm_pagemap_devmem *devmem_allocation) struct xe_bo *bo = to_xe_bo(devmem_allocation); struct xe_device *xe = xe_bo_device(bo); + dma_fence_put(devmem_allocation->pre_migrate_fence); xe_bo_put_async(bo); xe_pm_runtime_put(xe); } @@ -861,6 +873,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, unsigned long timeslice_ms) { struct xe_vram_region *vr = container_of(dpagemap, typeof(*vr), dpagemap); + struct dma_fence *pre_migrate_fence = NULL; struct xe_device *xe = vr->xe; struct device *dev = xe->drm.dev; struct drm_buddy_block *block; @@ -887,8 +900,20 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, break; } + /* Ensure that any clearing or async eviction will complete before migration. */ + if (!dma_resv_test_signaled(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL)) { + err = dma_resv_get_singleton(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL, + &pre_migrate_fence); + if (err) + dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL, + false, MAX_SCHEDULE_TIMEOUT); + else if (pre_migrate_fence) + dma_fence_enable_sw_signaling(pre_migrate_fence); + } + drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm, - &dpagemap_devmem_ops, dpagemap, end - start); + &dpagemap_devmem_ops, dpagemap, end - start, + pre_migrate_fence); blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks; list_for_each_entry(block, blocks, link) @@ -941,7 +966,7 @@ bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vm xe_assert(vm->xe, IS_DGFX(vm->xe)); if (xe_svm_range_in_vram(range)) { - drm_info(&vm->xe->drm, "Range is already in VRAM\n"); + drm_dbg(&vm->xe->drm, "Range is already in VRAM\n"); return false; } diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 79ab6c512d3e..095bb197e8b0 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1617,7 +1617,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) if (!vm->pt_root[id]) continue; - q = xe_exec_queue_create_bind(xe, tile, create_flags, 0); + q = xe_exec_queue_create_bind(xe, tile, vm, create_flags, 0); if (IS_ERR(q)) { err = PTR_ERR(q); goto err_close; @@ -3578,6 +3578,11 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) } } + if (XE_IOCTL_DBG(xe, q && vm != q->user_vm)) { + err = -EINVAL; + goto put_exec_queue; + } + /* Ensure all UNMAPs visible */ xe_svm_flush(vm); diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index ef8a5019574e..016f6786134c 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -379,7 +379,7 @@ static inline void xe_vm_set_validation_exec(struct xe_vm *vm, struct drm_exec * } /** - * xe_vm_set_validation_exec() - Accessor to read the drm_exec object + * xe_vm_validation_exec() - Accessor to read the drm_exec object * @vm: The vm we want to register a drm_exec object with. * * Return: The drm_exec object used to lock the vm's resv. The value diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig index 20d3e6d0d796..527920f9c4d3 100644 --- a/drivers/gpu/nova-core/Kconfig +++ b/drivers/gpu/nova-core/Kconfig @@ -3,7 +3,7 @@ config NOVA_CORE depends on 64BIT depends on PCI depends on RUST - depends on RUST_FW_LOADER_ABSTRACTIONS + select RUST_FW_LOADER_ABSTRACTIONS select AUXILIARY_BUS default n help diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs index 6f946d14868a..3991ccc0c10f 100644 --- a/drivers/gpu/nova-core/gsp/cmdq.rs +++ b/drivers/gpu/nova-core/gsp/cmdq.rs @@ -588,21 +588,23 @@ impl Cmdq { header.length(), ); + let payload_length = header.payload_length(); + // Check that the driver read area is large enough for the message. - if slice_1.len() + slice_2.len() < header.length() { + if slice_1.len() + slice_2.len() < payload_length { return Err(EIO); } // Cut the message slices down to the actual length of the message. - let (slice_1, slice_2) = if slice_1.len() > header.length() { - // PANIC: we checked above that `slice_1` is at least as long as `msg_header.length()`. - (slice_1.split_at(header.length()).0, &slice_2[0..0]) + let (slice_1, slice_2) = if slice_1.len() > payload_length { + // PANIC: we checked above that `slice_1` is at least as long as `payload_length`. + (slice_1.split_at(payload_length).0, &slice_2[0..0]) } else { ( slice_1, // PANIC: we checked above that `slice_1.len() + slice_2.len()` is at least as - // large as `msg_header.length()`. - slice_2.split_at(header.length() - slice_1.len()).0, + // large as `payload_length`. + slice_2.split_at(payload_length - slice_1.len()).0, ) }; diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs index abffd6beec65..caeb0d251fe5 100644 --- a/drivers/gpu/nova-core/gsp/fw.rs +++ b/drivers/gpu/nova-core/gsp/fw.rs @@ -141,8 +141,8 @@ unsafe impl AsBytes for GspFwWprMeta {} // are valid. unsafe impl FromBytes for GspFwWprMeta {} -type GspFwWprMetaBootResumeInfo = r570_144::GspFwWprMeta__bindgen_ty_1; -type GspFwWprMetaBootInfo = r570_144::GspFwWprMeta__bindgen_ty_1__bindgen_ty_1; +type GspFwWprMetaBootResumeInfo = bindings::GspFwWprMeta__bindgen_ty_1; +type GspFwWprMetaBootInfo = bindings::GspFwWprMeta__bindgen_ty_1__bindgen_ty_1; impl GspFwWprMeta { /// Fill in and return a `GspFwWprMeta` suitable for booting `gsp_firmware` using the @@ -150,8 +150,8 @@ impl GspFwWprMeta { pub(crate) fn new(gsp_firmware: &GspFirmware, fb_layout: &FbLayout) -> Self { Self(bindings::GspFwWprMeta { // CAST: we want to store the bits of `GSP_FW_WPR_META_MAGIC` unmodified. - magic: r570_144::GSP_FW_WPR_META_MAGIC as u64, - revision: u64::from(r570_144::GSP_FW_WPR_META_REVISION), + magic: bindings::GSP_FW_WPR_META_MAGIC as u64, + revision: u64::from(bindings::GSP_FW_WPR_META_REVISION), sysmemAddrOfRadix3Elf: gsp_firmware.radix3_dma_handle(), sizeOfRadix3Elf: u64::from_safe_cast(gsp_firmware.size), sysmemAddrOfBootloader: gsp_firmware.bootloader.ucode.dma_handle(), @@ -315,19 +315,19 @@ impl From<MsgFunction> for u32 { #[repr(u32)] pub(crate) enum SeqBufOpcode { // Core operation opcodes - CoreReset = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESET, - CoreResume = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME, - CoreStart = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_START, - CoreWaitForHalt = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT, + CoreReset = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESET, + CoreResume = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME, + CoreStart = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_START, + CoreWaitForHalt = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT, // Delay opcode - DelayUs = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_DELAY_US, + DelayUs = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_DELAY_US, // Register operation opcodes - RegModify = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_MODIFY, - RegPoll = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_POLL, - RegStore = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_STORE, - RegWrite = r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_WRITE, + RegModify = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_MODIFY, + RegPoll = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_POLL, + RegStore = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_STORE, + RegWrite = bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_WRITE, } impl fmt::Display for SeqBufOpcode { @@ -351,25 +351,25 @@ impl TryFrom<u32> for SeqBufOpcode { fn try_from(value: u32) -> Result<SeqBufOpcode> { match value { - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESET => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESET => { Ok(SeqBufOpcode::CoreReset) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME => { Ok(SeqBufOpcode::CoreResume) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_START => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_START => { Ok(SeqBufOpcode::CoreStart) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT => { Ok(SeqBufOpcode::CoreWaitForHalt) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_DELAY_US => Ok(SeqBufOpcode::DelayUs), - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_MODIFY => { + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_DELAY_US => Ok(SeqBufOpcode::DelayUs), + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_MODIFY => { Ok(SeqBufOpcode::RegModify) } - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_POLL => Ok(SeqBufOpcode::RegPoll), - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_STORE => Ok(SeqBufOpcode::RegStore), - r570_144::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_WRITE => Ok(SeqBufOpcode::RegWrite), + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_POLL => Ok(SeqBufOpcode::RegPoll), + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_STORE => Ok(SeqBufOpcode::RegStore), + bindings::GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_REG_WRITE => Ok(SeqBufOpcode::RegWrite), _ => Err(EINVAL), } } @@ -385,7 +385,7 @@ impl From<SeqBufOpcode> for u32 { /// Wrapper for GSP sequencer register write payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct RegWritePayload(r570_144::GSP_SEQ_BUF_PAYLOAD_REG_WRITE); +pub(crate) struct RegWritePayload(bindings::GSP_SEQ_BUF_PAYLOAD_REG_WRITE); impl RegWritePayload { /// Returns the register address. @@ -408,7 +408,7 @@ unsafe impl AsBytes for RegWritePayload {} /// Wrapper for GSP sequencer register modify payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct RegModifyPayload(r570_144::GSP_SEQ_BUF_PAYLOAD_REG_MODIFY); +pub(crate) struct RegModifyPayload(bindings::GSP_SEQ_BUF_PAYLOAD_REG_MODIFY); impl RegModifyPayload { /// Returns the register address. @@ -436,7 +436,7 @@ unsafe impl AsBytes for RegModifyPayload {} /// Wrapper for GSP sequencer register poll payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct RegPollPayload(r570_144::GSP_SEQ_BUF_PAYLOAD_REG_POLL); +pub(crate) struct RegPollPayload(bindings::GSP_SEQ_BUF_PAYLOAD_REG_POLL); impl RegPollPayload { /// Returns the register address. @@ -469,7 +469,7 @@ unsafe impl AsBytes for RegPollPayload {} /// Wrapper for GSP sequencer delay payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct DelayUsPayload(r570_144::GSP_SEQ_BUF_PAYLOAD_DELAY_US); +pub(crate) struct DelayUsPayload(bindings::GSP_SEQ_BUF_PAYLOAD_DELAY_US); impl DelayUsPayload { /// Returns the delay value in microseconds. @@ -487,7 +487,7 @@ unsafe impl AsBytes for DelayUsPayload {} /// Wrapper for GSP sequencer register store payload. #[repr(transparent)] #[derive(Copy, Clone)] -pub(crate) struct RegStorePayload(r570_144::GSP_SEQ_BUF_PAYLOAD_REG_STORE); +pub(crate) struct RegStorePayload(bindings::GSP_SEQ_BUF_PAYLOAD_REG_STORE); impl RegStorePayload { /// Returns the register address. @@ -510,7 +510,7 @@ unsafe impl AsBytes for RegStorePayload {} /// Wrapper for GSP sequencer buffer command. #[repr(transparent)] -pub(crate) struct SequencerBufferCmd(r570_144::GSP_SEQUENCER_BUFFER_CMD); +pub(crate) struct SequencerBufferCmd(bindings::GSP_SEQUENCER_BUFFER_CMD); impl SequencerBufferCmd { /// Returns the opcode as a `SeqBufOpcode` enum, or error if invalid. @@ -612,7 +612,7 @@ unsafe impl AsBytes for SequencerBufferCmd {} /// Wrapper for GSP run CPU sequencer RPC. #[repr(transparent)] -pub(crate) struct RunCpuSequencer(r570_144::rpc_run_cpu_sequencer_v17_00); +pub(crate) struct RunCpuSequencer(bindings::rpc_run_cpu_sequencer_v17_00); impl RunCpuSequencer { /// Returns the command index. @@ -797,13 +797,6 @@ impl bindings::rpc_message_header_v { } } -// SAFETY: We can't derive the Zeroable trait for this binding because the -// procedural macro doesn't support the syntax used by bindgen to create the -// __IncompleteArrayField types. So instead we implement it here, which is safe -// because these are explicitly padded structures only containing types for -// which any bit pattern, including all zeros, is valid. -unsafe impl Zeroable for bindings::rpc_message_header_v {} - /// GSP Message Element. /// /// This is essentially a message header expected to be followed by the message data. @@ -853,11 +846,16 @@ impl GspMsgElement { self.inner.checkSum = checksum; } - /// Returns the total length of the message. + /// Returns the length of the message's payload. + pub(crate) fn payload_length(&self) -> usize { + // `rpc.length` includes the length of the RPC message header. + num::u32_as_usize(self.inner.rpc.length) + .saturating_sub(size_of::<bindings::rpc_message_header_v>()) + } + + /// Returns the total length of the message, message and RPC headers included. pub(crate) fn length(&self) -> usize { - // `rpc.length` includes the length of the GspRpcHeader but not the message header. - size_of::<Self>() - size_of::<bindings::rpc_message_header_v>() - + num::u32_as_usize(self.inner.rpc.length) + size_of::<Self>() + self.payload_length() } // Returns the sequence number of the message. diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144.rs b/drivers/gpu/nova-core/gsp/fw/r570_144.rs index 048234d1a9d1..e99d315ae74c 100644 --- a/drivers/gpu/nova-core/gsp/fw/r570_144.rs +++ b/drivers/gpu/nova-core/gsp/fw/r570_144.rs @@ -24,8 +24,11 @@ unreachable_pub, unsafe_op_in_unsafe_fn )] -use kernel::{ - ffi, - prelude::Zeroable, // -}; +use kernel::ffi; +use pin_init::MaybeZeroable; + include!("r570_144/bindings.rs"); + +// SAFETY: This type has a size of zero, so its inclusion into another type should not affect their +// ability to implement `Zeroable`. +unsafe impl<T> kernel::prelude::Zeroable for __IncompleteArrayField<T> {} diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs index 5bcfbcd1ad22..6d25fe0bffa9 100644 --- a/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs +++ b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs @@ -320,11 +320,12 @@ pub const NV_VGPU_MSG_EVENT_RECOVERY_ACTION: _bindgen_ty_3 = 4130; pub const NV_VGPU_MSG_EVENT_NUM_EVENTS: _bindgen_ty_3 = 4131; pub type _bindgen_ty_3 = ffi::c_uint; #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct NV0080_CTRL_GPU_GET_SRIOV_CAPS_PARAMS { pub totalVFs: u32_, pub firstVfOffset: u32_, pub vfFeatureMask: u32_, + pub __bindgen_padding_0: [u8; 4usize], pub FirstVFBar0Address: u64_, pub FirstVFBar1Address: u64_, pub FirstVFBar2Address: u64_, @@ -340,23 +341,26 @@ pub struct NV0080_CTRL_GPU_GET_SRIOV_CAPS_PARAMS { pub bClientRmAllocatedCtxBuffer: u8_, pub bNonPowerOf2ChannelCountSupported: u8_, pub bVfResizableBAR1Supported: u8_, + pub __bindgen_padding_1: [u8; 7usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct NV2080_CTRL_BIOS_GET_SKU_INFO_PARAMS { pub BoardID: u32_, pub chipSKU: [ffi::c_char; 9usize], pub chipSKUMod: [ffi::c_char; 5usize], + pub __bindgen_padding_0: [u8; 2usize], pub skuConfigVersion: u32_, pub project: [ffi::c_char; 5usize], pub projectSKU: [ffi::c_char; 5usize], pub CDP: [ffi::c_char; 6usize], pub projectSKUMod: [ffi::c_char; 2usize], + pub __bindgen_padding_1: [u8; 2usize], pub businessCycle: u32_, } pub type NV2080_CTRL_CMD_FB_GET_FB_REGION_SURFACE_MEM_TYPE_FLAG = [u8_; 17usize]; #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct NV2080_CTRL_CMD_FB_GET_FB_REGION_FB_REGION_INFO { pub base: u64_, pub limit: u64_, @@ -368,13 +372,14 @@ pub struct NV2080_CTRL_CMD_FB_GET_FB_REGION_FB_REGION_INFO { pub blackList: NV2080_CTRL_CMD_FB_GET_FB_REGION_SURFACE_MEM_TYPE_FLAG, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct NV2080_CTRL_CMD_FB_GET_FB_REGION_INFO_PARAMS { pub numFBRegions: u32_, + pub __bindgen_padding_0: [u8; 4usize], pub fbRegion: [NV2080_CTRL_CMD_FB_GET_FB_REGION_FB_REGION_INFO; 16usize], } #[repr(C)] -#[derive(Debug, Copy, Clone)] +#[derive(Debug, Copy, Clone, MaybeZeroable)] pub struct NV2080_CTRL_GPU_GET_GID_INFO_PARAMS { pub index: u32_, pub flags: u32_, @@ -391,14 +396,14 @@ impl Default for NV2080_CTRL_GPU_GET_GID_INFO_PARAMS { } } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct DOD_METHOD_DATA { pub status: u32_, pub acpiIdListLen: u32_, pub acpiIdList: [u32_; 16usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct JT_METHOD_DATA { pub status: u32_, pub jtCaps: u32_, @@ -407,14 +412,14 @@ pub struct JT_METHOD_DATA { pub __bindgen_padding_0: u8, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct MUX_METHOD_DATA_ELEMENT { pub acpiId: u32_, pub mode: u32_, pub status: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct MUX_METHOD_DATA { pub tableLen: u32_, pub acpiIdMuxModeTable: [MUX_METHOD_DATA_ELEMENT; 16usize], @@ -422,13 +427,13 @@ pub struct MUX_METHOD_DATA { pub acpiIdMuxStateTable: [MUX_METHOD_DATA_ELEMENT; 16usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct CAPS_METHOD_DATA { pub status: u32_, pub optimusCaps: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct ACPI_METHOD_DATA { pub bValid: u8_, pub __bindgen_padding_0: [u8; 3usize], @@ -438,20 +443,20 @@ pub struct ACPI_METHOD_DATA { pub capsMethodData: CAPS_METHOD_DATA, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct VIRTUAL_DISPLAY_GET_MAX_RESOLUTION_PARAMS { pub headIndex: u32_, pub maxHResolution: u32_, pub maxVResolution: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct VIRTUAL_DISPLAY_GET_NUM_HEADS_PARAMS { pub numHeads: u32_, pub maxNumHeads: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct BUSINFO { pub deviceID: u16_, pub vendorID: u16_, @@ -461,7 +466,7 @@ pub struct BUSINFO { pub __bindgen_padding_0: u8, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_VF_INFO { pub totalVFs: u32_, pub firstVFOffset: u32_, @@ -474,34 +479,37 @@ pub struct GSP_VF_INFO { pub __bindgen_padding_0: [u8; 5usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_PCIE_CONFIG_REG { pub linkCap: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct EcidManufacturingInfo { pub ecidLow: u32_, pub ecidHigh: u32_, pub ecidExtended: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct FW_WPR_LAYOUT_OFFSET { pub nonWprHeapOffset: u64_, pub frtsOffset: u64_, } #[repr(C)] -#[derive(Debug, Copy, Clone)] +#[derive(Debug, Copy, Clone, MaybeZeroable)] pub struct GspStaticConfigInfo_t { pub grCapsBits: [u8_; 23usize], + pub __bindgen_padding_0: u8, pub gidInfo: NV2080_CTRL_GPU_GET_GID_INFO_PARAMS, pub SKUInfo: NV2080_CTRL_BIOS_GET_SKU_INFO_PARAMS, + pub __bindgen_padding_1: [u8; 4usize], pub fbRegionInfoParams: NV2080_CTRL_CMD_FB_GET_FB_REGION_INFO_PARAMS, pub sriovCaps: NV0080_CTRL_GPU_GET_SRIOV_CAPS_PARAMS, pub sriovMaxGfid: u32_, pub engineCaps: [u32_; 3usize], pub poisonFuseEnabled: u8_, + pub __bindgen_padding_2: [u8; 7usize], pub fb_length: u64_, pub fbio_mask: u64_, pub fb_bus_width: u32_, @@ -527,16 +535,20 @@ pub struct GspStaticConfigInfo_t { pub bIsMigSupported: u8_, pub RTD3GC6TotalBoardPower: u16_, pub RTD3GC6PerstDelay: u16_, + pub __bindgen_padding_3: [u8; 2usize], pub bar1PdeBase: u64_, pub bar2PdeBase: u64_, pub bVbiosValid: u8_, + pub __bindgen_padding_4: [u8; 3usize], pub vbiosSubVendor: u32_, pub vbiosSubDevice: u32_, pub bPageRetirementSupported: u8_, pub bSplitVasBetweenServerClientRm: u8_, pub bClRootportNeedsNosnoopWAR: u8_, + pub __bindgen_padding_5: u8, pub displaylessMaxHeads: VIRTUAL_DISPLAY_GET_NUM_HEADS_PARAMS, pub displaylessMaxResolution: VIRTUAL_DISPLAY_GET_MAX_RESOLUTION_PARAMS, + pub __bindgen_padding_6: [u8; 4usize], pub displaylessMaxPixels: u64_, pub hInternalClient: u32_, pub hInternalDevice: u32_, @@ -558,7 +570,7 @@ impl Default for GspStaticConfigInfo_t { } } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspSystemInfo { pub gpuPhysAddr: u64_, pub gpuPhysFbAddr: u64_, @@ -615,7 +627,7 @@ pub struct GspSystemInfo { pub hostPageSize: u64_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct MESSAGE_QUEUE_INIT_ARGUMENTS { pub sharedMemPhysAddr: u64_, pub pageTableEntryCount: u32_, @@ -624,7 +636,7 @@ pub struct MESSAGE_QUEUE_INIT_ARGUMENTS { pub statQueueOffset: u64_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SR_INIT_ARGUMENTS { pub oldLevel: u32_, pub flags: u32_, @@ -632,7 +644,7 @@ pub struct GSP_SR_INIT_ARGUMENTS { pub __bindgen_padding_0: [u8; 3usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_ARGUMENTS_CACHED { pub messageQueueInitArguments: MESSAGE_QUEUE_INIT_ARGUMENTS, pub srInitArguments: GSP_SR_INIT_ARGUMENTS, @@ -642,13 +654,13 @@ pub struct GSP_ARGUMENTS_CACHED { pub profilerArgs: GSP_ARGUMENTS_CACHED__bindgen_ty_1, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_ARGUMENTS_CACHED__bindgen_ty_1 { pub pa: u64_, pub size: u64_, } #[repr(C)] -#[derive(Copy, Clone, Zeroable)] +#[derive(Copy, Clone, MaybeZeroable)] pub union rpc_message_rpc_union_field_v03_00 { pub spare: u32_, pub cpuRmGfid: u32_, @@ -664,6 +676,7 @@ impl Default for rpc_message_rpc_union_field_v03_00 { } pub type rpc_message_rpc_union_field_v = rpc_message_rpc_union_field_v03_00; #[repr(C)] +#[derive(MaybeZeroable)] pub struct rpc_message_header_v03_00 { pub header_version: u32_, pub signature: u32_, @@ -686,7 +699,7 @@ impl Default for rpc_message_header_v03_00 { } pub type rpc_message_header_v = rpc_message_header_v03_00; #[repr(C)] -#[derive(Copy, Clone, Zeroable)] +#[derive(Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta { pub magic: u64_, pub revision: u64_, @@ -721,19 +734,19 @@ pub struct GspFwWprMeta { pub verified: u64_, } #[repr(C)] -#[derive(Copy, Clone, Zeroable)] +#[derive(Copy, Clone, MaybeZeroable)] pub union GspFwWprMeta__bindgen_ty_1 { pub __bindgen_anon_1: GspFwWprMeta__bindgen_ty_1__bindgen_ty_1, pub __bindgen_anon_2: GspFwWprMeta__bindgen_ty_1__bindgen_ty_2, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta__bindgen_ty_1__bindgen_ty_1 { pub sysmemAddrOfSignature: u64_, pub sizeOfSignature: u64_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta__bindgen_ty_1__bindgen_ty_2 { pub gspFwHeapFreeListWprOffset: u32_, pub unused0: u32_, @@ -749,13 +762,13 @@ impl Default for GspFwWprMeta__bindgen_ty_1 { } } #[repr(C)] -#[derive(Copy, Clone, Zeroable)] +#[derive(Copy, Clone, MaybeZeroable)] pub union GspFwWprMeta__bindgen_ty_2 { pub __bindgen_anon_1: GspFwWprMeta__bindgen_ty_2__bindgen_ty_1, pub __bindgen_anon_2: GspFwWprMeta__bindgen_ty_2__bindgen_ty_2, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta__bindgen_ty_2__bindgen_ty_1 { pub partitionRpcAddr: u64_, pub partitionRpcRequestOffset: u16_, @@ -767,7 +780,7 @@ pub struct GspFwWprMeta__bindgen_ty_2__bindgen_ty_1 { pub lsUcodeVersion: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GspFwWprMeta__bindgen_ty_2__bindgen_ty_2 { pub partitionRpcPadding: [u32_; 4usize], pub sysmemAddrOfCrashReportQueue: u64_, @@ -802,7 +815,7 @@ pub const LibosMemoryRegionLoc_LIBOS_MEMORY_REGION_LOC_SYSMEM: LibosMemoryRegion pub const LibosMemoryRegionLoc_LIBOS_MEMORY_REGION_LOC_FB: LibosMemoryRegionLoc = 2; pub type LibosMemoryRegionLoc = ffi::c_uint; #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct LibosMemoryRegionInitArgument { pub id8: LibosAddress, pub pa: LibosAddress, @@ -812,7 +825,7 @@ pub struct LibosMemoryRegionInitArgument { pub __bindgen_padding_0: [u8; 6usize], } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct PACKED_REGISTRY_ENTRY { pub nameOffset: u32_, pub type_: u8_, @@ -821,14 +834,14 @@ pub struct PACKED_REGISTRY_ENTRY { pub length: u32_, } #[repr(C)] -#[derive(Debug, Default)] +#[derive(Debug, Default, MaybeZeroable)] pub struct PACKED_REGISTRY_TABLE { pub size: u32_, pub numEntries: u32_, pub entries: __IncompleteArrayField<PACKED_REGISTRY_ENTRY>, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct msgqTxHeader { pub version: u32_, pub size: u32_, @@ -840,13 +853,13 @@ pub struct msgqTxHeader { pub entryOff: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone, Zeroable)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct msgqRxHeader { pub readPtr: u32_, } #[repr(C)] #[repr(align(8))] -#[derive(Zeroable)] +#[derive(MaybeZeroable)] pub struct GSP_MSG_QUEUE_ELEMENT { pub authTagBuffer: [u8_; 16usize], pub aadBuffer: [u8_; 16usize], @@ -866,7 +879,7 @@ impl Default for GSP_MSG_QUEUE_ELEMENT { } } #[repr(C)] -#[derive(Debug, Default)] +#[derive(Debug, Default, MaybeZeroable)] pub struct rpc_run_cpu_sequencer_v17_00 { pub bufferSizeDWord: u32_, pub cmdIndex: u32_, @@ -884,20 +897,20 @@ pub const GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_WAIT_FOR_HALT: GSP_SEQ_BUF_ pub const GSP_SEQ_BUF_OPCODE_GSP_SEQ_BUF_OPCODE_CORE_RESUME: GSP_SEQ_BUF_OPCODE = 8; pub type GSP_SEQ_BUF_OPCODE = ffi::c_uint; #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_REG_WRITE { pub addr: u32_, pub val: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_REG_MODIFY { pub addr: u32_, pub mask: u32_, pub val: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_REG_POLL { pub addr: u32_, pub mask: u32_, @@ -906,24 +919,24 @@ pub struct GSP_SEQ_BUF_PAYLOAD_REG_POLL { pub error: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_DELAY_US { pub val: u32_, } #[repr(C)] -#[derive(Debug, Default, Copy, Clone)] +#[derive(Debug, Default, Copy, Clone, MaybeZeroable)] pub struct GSP_SEQ_BUF_PAYLOAD_REG_STORE { pub addr: u32_, pub index: u32_, } #[repr(C)] -#[derive(Copy, Clone)] +#[derive(Copy, Clone, MaybeZeroable)] pub struct GSP_SEQUENCER_BUFFER_CMD { pub opCode: GSP_SEQ_BUF_OPCODE, pub payload: GSP_SEQUENCER_BUFFER_CMD__bindgen_ty_1, } #[repr(C)] -#[derive(Copy, Clone)] +#[derive(Copy, Clone, MaybeZeroable)] pub union GSP_SEQUENCER_BUFFER_CMD__bindgen_ty_1 { pub regWrite: GSP_SEQ_BUF_PAYLOAD_REG_WRITE, pub regModify: GSP_SEQ_BUF_PAYLOAD_REG_MODIFY, diff --git a/drivers/hid/bpf/progs/Makefile b/drivers/hid/bpf/progs/Makefile index ec1fc642fd63..66b8f38e591d 100644 --- a/drivers/hid/bpf/progs/Makefile +++ b/drivers/hid/bpf/progs/Makefile @@ -56,8 +56,10 @@ clean: %.bpf.o: %.bpf.c vmlinux.h $(BPFOBJ) | $(OUTPUT) $(call msg,BPF,$@) - $(Q)$(CLANG) -g -O2 --target=bpf -Wall -Werror $(INCLUDES) \ - -c $(filter %.c,$^) -o $@ && \ + $(Q)$(CLANG) -g -O2 --target=bpf -Wall -Werror $(INCLUDES) \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ + -c $(filter %.c,$^) -o $@ && \ $(LLVM_STRIP) -g $@ vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR) diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c index 981d1b6e9658..2003d2dcda7c 100644 --- a/drivers/hid/hid-elecom.c +++ b/drivers/hid/hid-elecom.c @@ -77,7 +77,7 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, break; case USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB: case USB_DEVICE_ID_ELECOM_M_XT3URBK_018F: - case USB_DEVICE_ID_ELECOM_M_XT3DRBK: + case USB_DEVICE_ID_ELECOM_M_XT3DRBK_00FC: case USB_DEVICE_ID_ELECOM_M_XT4DRBK: /* * Report descriptor format: @@ -102,6 +102,16 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, */ mouse_button_fixup(hdev, rdesc, *rsize, 12, 30, 14, 20, 8); break; + case USB_DEVICE_ID_ELECOM_M_XT3DRBK_018C: + /* + * Report descriptor format: + * 22: button bit count + * 30: padding bit count + * 24: button report size + * 16: button usage maximum + */ + mouse_button_fixup(hdev, rdesc, *rsize, 22, 30, 24, 16, 6); + break; case USB_DEVICE_ID_ELECOM_M_DT2DRBK: case USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C: /* @@ -122,7 +132,8 @@ static const struct hid_device_id elecom_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XGL20DLBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_018F) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK_00FC) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK_018C) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index d31711f1aaec..9c2bf584d9f6 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -317,6 +317,7 @@ #define USB_DEVICE_ID_CHICONY_ACER_SWITCH12 0x1421 #define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA 0xb824 #define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2 0xb82c +#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA3 0xb882 #define USB_VENDOR_ID_CHUNGHWAT 0x2247 #define USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH 0x0001 @@ -438,6 +439,9 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002 0xc002 +#define USB_VENDOR_ID_EDIFIER 0x2d99 +#define USB_DEVICE_ID_EDIFIER_QR30 0xa101 /* EDIFIER Hal0 2.0 SE */ + #define USB_VENDOR_ID_ELAN 0x04f3 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401 #define USB_DEVICE_ID_HP_X2 0x074d @@ -451,7 +455,8 @@ #define USB_DEVICE_ID_ELECOM_M_XGL20DLBK 0x00e6 #define USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB 0x00fb #define USB_DEVICE_ID_ELECOM_M_XT3URBK_018F 0x018f -#define USB_DEVICE_ID_ELECOM_M_XT3DRBK 0x00fc +#define USB_DEVICE_ID_ELECOM_M_XT3DRBK_00FC 0x00fc +#define USB_DEVICE_ID_ELECOM_M_XT3DRBK_018C 0x018c #define USB_DEVICE_ID_ELECOM_M_XT4DRBK 0x00fd #define USB_DEVICE_ID_ELECOM_M_DT1URBK 0x00fe #define USB_DEVICE_ID_ELECOM_M_DT1DRBK 0x00ff diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index d5011a5d0890..e871f1729d4b 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -4662,6 +4662,8 @@ static const struct hid_device_id hidpp_devices[] = { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb025) }, { /* MX Master 3S mouse over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb034) }, + { /* MX Anywhere 3S mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb037) }, { /* MX Anywhere 3SB mouse over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb038) }, {} diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 179dc316b4b5..b1c3ef129058 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -81,6 +81,7 @@ MODULE_LICENSE("GPL"); #define MT_INPUTMODE_TOUCHPAD 0x03 #define MT_BUTTONTYPE_CLICKPAD 0 +#define MT_BUTTONTYPE_PRESSUREPAD 1 enum latency_mode { HID_LATENCY_NORMAL = 0, @@ -179,6 +180,7 @@ struct mt_device { __u8 inputmode_value; /* InputMode HID feature value */ __u8 maxcontacts; bool is_buttonpad; /* is this device a button pad? */ + bool is_pressurepad; /* is this device a pressurepad? */ bool is_haptic_touchpad; /* is this device a haptic touchpad? */ bool serial_maybe; /* need to check for serial protocol */ @@ -393,6 +395,7 @@ static const struct mt_class mt_classes[] = { { .name = MT_CLS_VTL, .quirks = MT_QUIRK_ALWAYS_VALID | MT_QUIRK_CONTACT_CNT_ACCURATE | + MT_QUIRK_STICKY_FINGERS | MT_QUIRK_FORCE_GET_FEATURE, }, { .name = MT_CLS_GOOGLE, @@ -530,8 +533,14 @@ static void mt_feature_mapping(struct hid_device *hdev, } mt_get_feature(hdev, field->report); - if (field->value[usage->usage_index] == MT_BUTTONTYPE_CLICKPAD) + switch (field->value[usage->usage_index]) { + case MT_BUTTONTYPE_CLICKPAD: td->is_buttonpad = true; + break; + case MT_BUTTONTYPE_PRESSUREPAD: + td->is_pressurepad = true; + break; + } break; case 0xff0000c5: @@ -1393,6 +1402,8 @@ static int mt_touch_input_configured(struct hid_device *hdev, if (td->is_buttonpad) __set_bit(INPUT_PROP_BUTTONPAD, input->propbit); + if (td->is_pressurepad) + __set_bit(INPUT_PROP_PRESSUREPAD, input->propbit); app->pending_palm_slots = devm_kcalloc(&hi->input->dev, BITS_TO_LONGS(td->maxcontacts), diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index 128aa6abd10b..e4dfcf26b04e 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -753,11 +753,16 @@ ps_gamepad_create(struct hid_device *hdev, if (IS_ERR(gamepad)) return ERR_CAST(gamepad); + /* Set initial resting state for joysticks to 128 (center) */ input_set_abs_params(gamepad, ABS_X, 0, 255, 0, 0); + gamepad->absinfo[ABS_X].value = 128; input_set_abs_params(gamepad, ABS_Y, 0, 255, 0, 0); + gamepad->absinfo[ABS_Y].value = 128; input_set_abs_params(gamepad, ABS_Z, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_RX, 0, 255, 0, 0); + gamepad->absinfo[ABS_RX].value = 128; input_set_abs_params(gamepad, ABS_RY, 0, 255, 0, 0); + gamepad->absinfo[ABS_RY].value = 128; input_set_abs_params(gamepad, ABS_RZ, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_HAT0X, -1, 1, 0, 0); diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index c89a015686c0..11438039cdb7 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -81,6 +81,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_PS3), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER), HID_QUIRK_MULTI_INPUT | HID_QUIRK_NOGET }, + { HID_USB_DEVICE(USB_VENDOR_ID_EDIFIER, USB_DEVICE_ID_EDIFIER_QR30), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_EMS, USB_DEVICE_ID_EMS_TRIO_LINKER_PLUS_II), HID_QUIRK_MULTI_INPUT }, @@ -232,6 +233,15 @@ static const struct hid_device_id hid_quirks[] = { * used as a driver. See hid_scan_report(). */ static const struct hid_device_id hid_have_special_driver[] = { +#if IS_ENABLED(CONFIG_APPLEDISPLAY) + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9218) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9219) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x921c) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x921d) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9222) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9226) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9236) }, +#endif #if IS_ENABLED(CONFIG_HID_A4TECH) { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_WCP32PU) }, { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_X5_005D) }, @@ -412,7 +422,8 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XGL20DLBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_018F) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK_00FC) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK_018C) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) }, @@ -769,6 +780,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_BERKSHIRE, USB_DEVICE_ID_BERKSHIRE_PCWD) }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA) }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA3) }, { HID_USB_DEVICE(USB_VENDOR_ID_CIDC, 0x0103) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI470X) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI4713) }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 63f46a2e5788..5a183af3d5c6 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -286,6 +286,7 @@ static int i2c_hid_get_report(struct i2c_hid *ihid, * In addition to report data device will supply data length * in the first 2 bytes of the response, so adjust . */ + recv_len = min(recv_len, ihid->bufsize - sizeof(__le16)); error = i2c_hid_xfer(ihid, ihid->cmdbuf, length, ihid->rawbuf, recv_len + sizeof(__le16)); if (error) { diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index f37b3bc2bb7d..6d64008f2ce0 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -495,6 +495,7 @@ static int ishtp_enum_enum_devices(struct ishtp_cl *hid_ishtp_cl) int rv; /* Send HOSTIF_DM_ENUM_DEVICES */ + client_data->enum_devices_done = false; memset(&msg, 0, sizeof(struct hostif_msg)); msg.hdr.command = HOSTIF_DM_ENUM_DEVICES; rv = ishtp_cl_send(hid_ishtp_cl, (unsigned char *)&msg, diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index c6ce37244e49..c3915f3a060e 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -240,9 +240,17 @@ static int ishtp_cl_bus_match(struct device *dev, const struct device_driver *dr { struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv); + struct ishtp_fw_client *client = device->fw_client; + const struct ishtp_device_id *id; - return(device->fw_client ? guid_equal(&driver->id[0].guid, - &device->fw_client->props.protocol_name) : 0); + if (client) { + for (id = driver->id; !guid_is_null(&id->guid); id++) { + if (guid_equal(&id->guid, &client->props.protocol_name)) + return 1; + } + } + + return 0; } /** diff --git a/drivers/hid/intel-thc-hid/Kconfig b/drivers/hid/intel-thc-hid/Kconfig index 0351d1137607..9d74e53b8c62 100644 --- a/drivers/hid/intel-thc-hid/Kconfig +++ b/drivers/hid/intel-thc-hid/Kconfig @@ -7,6 +7,7 @@ menu "Intel THC HID Support" config INTEL_THC_HID tristate "Intel Touch Host Controller" depends on ACPI + select SGL_ALLOC help THC (Touch Host Controller) is the name of the IP block in PCH that interfaces with Touch Devices (ex: touchscreen, touchpad etc.). It diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c index 636a68306501..7e220a4c5ded 100644 --- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c @@ -1593,7 +1593,7 @@ int thc_i2c_set_rx_max_size(struct thc_device *dev, u32 max_rx_size) if (!max_rx_size) return -EOPNOTSUPP; - ret = regmap_read(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, &val); + ret = regmap_read(dev->thc_regmap, THC_M_PRT_SPI_ICRRD_OPCODE_OFFSET, &val); if (ret) return ret; @@ -1662,7 +1662,7 @@ int thc_i2c_set_rx_int_delay(struct thc_device *dev, u32 delay_us) if (!delay_us) return -EOPNOTSUPP; - ret = regmap_read(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, &val); + ret = regmap_read(dev->thc_regmap, THC_M_PRT_SPI_ICRRD_OPCODE_OFFSET, &val); if (ret) return ret; diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c index 82b8854843e0..6ee675e0a738 100644 --- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c @@ -232,6 +232,7 @@ static int setup_dma_buffers(struct thc_device *dev, return 0; memset(config->sgls, 0, sizeof(config->sgls)); + memset(config->sgls_nent_pages, 0, sizeof(config->sgls_nent_pages)); memset(config->sgls_nent, 0, sizeof(config->sgls_nent)); cpu_addr = dma_alloc_coherent(dev->dev, prd_tbls_size, @@ -254,6 +255,7 @@ static int setup_dma_buffers(struct thc_device *dev, } count = dma_map_sg(dev->dev, config->sgls[i], nent, dir); + config->sgls_nent_pages[i] = nent; config->sgls_nent[i] = count; } @@ -299,7 +301,7 @@ static void release_dma_buffers(struct thc_device *dev, continue; dma_unmap_sg(dev->dev, config->sgls[i], - config->sgls_nent[i], + config->sgls_nent_pages[i], config->dir); sgl_free(config->sgls[i]); @@ -573,6 +575,11 @@ static int read_dma_buffer(struct thc_device *dev, return -EINVAL; } + if (!read_config->prd_tbls || !read_config->sgls[prd_table_index]) { + dev_err_once(dev->dev, "PRD tables are not ready yet\n"); + return -EINVAL; + } + prd_tbl = &read_config->prd_tbls[prd_table_index]; mes_len = calc_message_len(prd_tbl, &nent); if (mes_len > read_config->max_packet_size) { diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h index 78917400492c..541d33995baf 100644 --- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h @@ -91,6 +91,7 @@ struct thc_prd_table { * @dir: Direction of DMA for this config * @prd_tbls: PRD tables for current DMA * @sgls: Array of pointers to scatter-gather lists + * @sgls_nent_pages: Number of pages per scatter-gather list * @sgls_nent: Actual number of entries per scatter-gather list * @prd_tbl_num: Actual number of PRD tables * @max_packet_size: Size of the buffer needed for 1 DMA message (1 PRD table) @@ -107,6 +108,7 @@ struct thc_dma_configuration { struct thc_prd_table *prd_tbls; struct scatterlist *sgls[PRD_TABLES_NUM]; + u8 sgls_nent_pages[PRD_TABLES_NUM]; u8 sgls_nent[PRD_TABLES_NUM]; u8 prd_tbl_num; diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index aac0051a2cf6..758eb21430cd 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -985,6 +985,7 @@ static int usbhid_parse(struct hid_device *hid) struct usb_device *dev = interface_to_usbdev (intf); struct hid_descriptor *hdesc; struct hid_class_descriptor *hcdesc; + __u8 fixed_opt_descriptors_size; u32 quirks = 0; unsigned int rsize = 0; char *rdesc; @@ -1015,7 +1016,21 @@ static int usbhid_parse(struct hid_device *hid) (hdesc->bNumDescriptors - 1) * sizeof(*hcdesc)) { dbg_hid("hid descriptor invalid, bLen=%hhu bNum=%hhu\n", hdesc->bLength, hdesc->bNumDescriptors); - return -EINVAL; + + /* + * Some devices may expose a wrong number of descriptors compared + * to the provided length. + * However, we ignore the optional hid class descriptors entirely + * so we can safely recompute the proper field. + */ + if (hdesc->bLength >= sizeof(*hdesc)) { + fixed_opt_descriptors_size = hdesc->bLength - sizeof(*hdesc); + + hid_warn(intf, "fixing wrong optional hid class descriptors count\n"); + hdesc->bNumDescriptors = fixed_opt_descriptors_size / sizeof(*hcdesc) + 1; + } else { + return -EINVAL; + } } hid->version = le16_to_cpu(hdesc->bcdHID); diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 0a3ab7efed46..f1c17fb60dc1 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -195,13 +195,15 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, /* * Write dump contents to the page. No need to synchronize; panic should - * be single-threaded. + * be single-threaded. Ignore failures from kmsg_dump_get_buffer() since + * panic notification should be done even if there is no message data. + * Don't assume bytes_written is set in case of failure, so initialize it. */ kmsg_dump_rewind(&iter); - kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, + bytes_written = 0; + (void)kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, &bytes_written); - if (!bytes_written) - return; + /* * P3 to contain the physical address of the panic page & P4 to * contain the size of the panic data in that page. Rest of the @@ -210,7 +212,7 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, hv_set_msr(HV_MSR_CRASH_P0, 0); hv_set_msr(HV_MSR_CRASH_P1, 0); hv_set_msr(HV_MSR_CRASH_P2, 0); - hv_set_msr(HV_MSR_CRASH_P3, virt_to_phys(hv_panic_page)); + hv_set_msr(HV_MSR_CRASH_P3, bytes_written ? virt_to_phys(hv_panic_page) : 0); hv_set_msr(HV_MSR_CRASH_P4, bytes_written); /* diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index b2862e0a317a..cdbc5f5c3215 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -375,7 +375,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) return; /* - * The cmxchg() above does an implicit memory barrier to + * The cmpxchg() above does an implicit memory barrier to * ensure the write to MessageType (ie set to * HVMSG_NONE) happens before we read the * MessagePending and EOMing. Otherwise, the EOMing diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c index 58027b23c206..63f09bb5136e 100644 --- a/drivers/hv/mshv_common.c +++ b/drivers/hv/mshv_common.c @@ -142,6 +142,7 @@ int hv_call_get_partition_property(u64 partition_id, } EXPORT_SYMBOL_GPL(hv_call_get_partition_property); +#ifdef CONFIG_X86 /* * Corresponding sleep states have to be initialized in order for a subsequent * HVCALL_ENTER_SLEEP_STATE call to succeed. Currently only S5 state as per @@ -237,3 +238,4 @@ void hv_machine_power_off(void) BUG(); } +#endif diff --git a/drivers/hv/mshv_eventfd.c b/drivers/hv/mshv_eventfd.c index d93a18f09c76..0b75ff1edb73 100644 --- a/drivers/hv/mshv_eventfd.c +++ b/drivers/hv/mshv_eventfd.c @@ -388,7 +388,7 @@ static int mshv_irqfd_assign(struct mshv_partition *pt, { struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL; struct mshv_irqfd *irqfd, *tmp; - unsigned int events; + __poll_t events; int ret; int idx; diff --git a/drivers/hv/mshv_regions.c b/drivers/hv/mshv_regions.c index 202b9d551e39..adba3564d9f1 100644 --- a/drivers/hv/mshv_regions.c +++ b/drivers/hv/mshv_regions.c @@ -20,6 +20,41 @@ #define MSHV_MAP_FAULT_IN_PAGES PTRS_PER_PMD /** + * mshv_chunk_stride - Compute stride for mapping guest memory + * @page : The page to check for huge page backing + * @gfn : Guest frame number for the mapping + * @page_count: Total number of pages in the mapping + * + * Determines the appropriate stride (in pages) for mapping guest memory. + * Uses huge page stride if the backing page is huge and the guest mapping + * is properly aligned; otherwise falls back to single page stride. + * + * Return: Stride in pages, or -EINVAL if page order is unsupported. + */ +static int mshv_chunk_stride(struct page *page, + u64 gfn, u64 page_count) +{ + unsigned int page_order; + + /* + * Use single page stride by default. For huge page stride, the + * page must be compound and point to the head of the compound + * page, and both gfn and page_count must be huge-page aligned. + */ + if (!PageCompound(page) || !PageHead(page) || + !IS_ALIGNED(gfn, PTRS_PER_PMD) || + !IS_ALIGNED(page_count, PTRS_PER_PMD)) + return 1; + + page_order = folio_order(page_folio(page)); + /* The hypervisor only supports 2M huge page */ + if (page_order != PMD_ORDER) + return -EINVAL; + + return 1 << page_order; +} + +/** * mshv_region_process_chunk - Processes a contiguous chunk of memory pages * in a region. * @region : Pointer to the memory region structure. @@ -45,25 +80,23 @@ static long mshv_region_process_chunk(struct mshv_mem_region *region, int (*handler)(struct mshv_mem_region *region, u32 flags, u64 page_offset, - u64 page_count)) + u64 page_count, + bool huge_page)) { - u64 count, stride; - unsigned int page_order; + u64 gfn = region->start_gfn + page_offset; + u64 count; struct page *page; - int ret; + int stride, ret; page = region->pages[page_offset]; if (!page) return -EINVAL; - page_order = folio_order(page_folio(page)); - /* The hypervisor only supports 4K and 2M page sizes */ - if (page_order && page_order != HPAGE_PMD_ORDER) - return -EINVAL; - - stride = 1 << page_order; + stride = mshv_chunk_stride(page, gfn, page_count); + if (stride < 0) + return stride; - /* Start at stride since the first page is validated */ + /* Start at stride since the first stride is validated */ for (count = stride; count < page_count; count += stride) { page = region->pages[page_offset + count]; @@ -71,12 +104,13 @@ static long mshv_region_process_chunk(struct mshv_mem_region *region, if (!page) break; - /* Break if page size changes */ - if (page_order != folio_order(page_folio(page))) + /* Break if stride size changes */ + if (stride != mshv_chunk_stride(page, gfn + count, + page_count - count)) break; } - ret = handler(region, flags, page_offset, count); + ret = handler(region, flags, page_offset, count, stride > 1); if (ret) return ret; @@ -108,7 +142,8 @@ static int mshv_region_process_range(struct mshv_mem_region *region, int (*handler)(struct mshv_mem_region *region, u32 flags, u64 page_offset, - u64 page_count)) + u64 page_count, + bool huge_page)) { long ret; @@ -162,11 +197,10 @@ struct mshv_mem_region *mshv_region_create(u64 guest_pfn, u64 nr_pages, static int mshv_region_chunk_share(struct mshv_mem_region *region, u32 flags, - u64 page_offset, u64 page_count) + u64 page_offset, u64 page_count, + bool huge_page) { - struct page *page = region->pages[page_offset]; - - if (PageHuge(page) || PageTransCompound(page)) + if (huge_page) flags |= HV_MODIFY_SPA_PAGE_HOST_ACCESS_LARGE_PAGE; return hv_call_modify_spa_host_access(region->partition->pt_id, @@ -188,11 +222,10 @@ int mshv_region_share(struct mshv_mem_region *region) static int mshv_region_chunk_unshare(struct mshv_mem_region *region, u32 flags, - u64 page_offset, u64 page_count) + u64 page_offset, u64 page_count, + bool huge_page) { - struct page *page = region->pages[page_offset]; - - if (PageHuge(page) || PageTransCompound(page)) + if (huge_page) flags |= HV_MODIFY_SPA_PAGE_HOST_ACCESS_LARGE_PAGE; return hv_call_modify_spa_host_access(region->partition->pt_id, @@ -212,11 +245,10 @@ int mshv_region_unshare(struct mshv_mem_region *region) static int mshv_region_chunk_remap(struct mshv_mem_region *region, u32 flags, - u64 page_offset, u64 page_count) + u64 page_offset, u64 page_count, + bool huge_page) { - struct page *page = region->pages[page_offset]; - - if (PageHuge(page) || PageTransCompound(page)) + if (huge_page) flags |= HV_MAP_GPA_LARGE_PAGE; return hv_call_map_gpa_pages(region->partition->pt_id, @@ -295,11 +327,10 @@ release_pages: static int mshv_region_chunk_unmap(struct mshv_mem_region *region, u32 flags, - u64 page_offset, u64 page_count) + u64 page_offset, u64 page_count, + bool huge_page) { - struct page *page = region->pages[page_offset]; - - if (PageHuge(page) || PageTransCompound(page)) + if (huge_page) flags |= HV_UNMAP_GPA_LARGE_PAGE; return hv_call_unmap_gpa_pages(region->partition->pt_id, @@ -494,13 +525,6 @@ static bool mshv_region_interval_invalidate(struct mmu_interval_notifier *mni, unsigned long mstart, mend; int ret = -EPERM; - if (mmu_notifier_range_blockable(range)) - mutex_lock(®ion->mutex); - else if (!mutex_trylock(®ion->mutex)) - goto out_fail; - - mmu_interval_set_seq(mni, cur_seq); - mstart = max(range->start, region->start_uaddr); mend = min(range->end, region->start_uaddr + (region->nr_pages << HV_HYP_PAGE_SHIFT)); @@ -508,10 +532,17 @@ static bool mshv_region_interval_invalidate(struct mmu_interval_notifier *mni, page_offset = HVPFN_DOWN(mstart - region->start_uaddr); page_count = HVPFN_DOWN(mend - mstart); + if (mmu_notifier_range_blockable(range)) + mutex_lock(®ion->mutex); + else if (!mutex_trylock(®ion->mutex)) + goto out_fail; + + mmu_interval_set_seq(mni, cur_seq); + ret = mshv_region_remap_pages(region, HV_MAP_GPA_NO_ACCESS, page_offset, page_count); if (ret) - goto out_fail; + goto out_unlock; mshv_region_invalidate_pages(region, page_offset, page_count); @@ -519,6 +550,8 @@ static bool mshv_region_interval_invalidate(struct mmu_interval_notifier *mni, return true; +out_unlock: + mutex_unlock(®ion->mutex); out_fail: WARN_ONCE(ret, "Failed to invalidate region %#llx-%#llx (range %#lx-%#lx, event: %u, pages %#llx-%#llx, mm: %#llx): %d\n", diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c index 1134a82c7881..681b58154d5e 100644 --- a/drivers/hv/mshv_root_main.c +++ b/drivers/hv/mshv_root_main.c @@ -611,7 +611,6 @@ mshv_partition_region_by_gfn(struct mshv_partition *partition, u64 gfn) return NULL; } -#ifdef CONFIG_X86_64 static struct mshv_mem_region * mshv_partition_region_by_gfn_get(struct mshv_partition *p, u64 gfn) { @@ -643,12 +642,17 @@ static bool mshv_handle_gpa_intercept(struct mshv_vp *vp) { struct mshv_partition *p = vp->vp_partition; struct mshv_mem_region *region; - struct hv_x64_memory_intercept_message *msg; bool ret; u64 gfn; - - msg = (struct hv_x64_memory_intercept_message *) +#if defined(CONFIG_X86_64) + struct hv_x64_memory_intercept_message *msg = + (struct hv_x64_memory_intercept_message *) + vp->vp_intercept_msg_page->u.payload; +#elif defined(CONFIG_ARM64) + struct hv_arm64_memory_intercept_message *msg = + (struct hv_arm64_memory_intercept_message *) vp->vp_intercept_msg_page->u.payload; +#endif gfn = HVPFN_DOWN(msg->guest_physical_address); @@ -666,9 +670,6 @@ static bool mshv_handle_gpa_intercept(struct mshv_vp *vp) return ret; } -#else /* CONFIG_X86_64 */ -static bool mshv_handle_gpa_intercept(struct mshv_vp *vp) { return false; } -#endif /* CONFIG_X86_64 */ static bool mshv_vp_handle_intercept(struct mshv_vp *vp) { @@ -1280,7 +1281,7 @@ mshv_map_user_memory(struct mshv_partition *partition, long ret; if (mem.flags & BIT(MSHV_SET_MEM_BIT_UNMAP) || - !access_ok((const void *)mem.userspace_addr, mem.size)) + !access_ok((const void __user *)mem.userspace_addr, mem.size)) return -EINVAL; mmap_read_lock(current->mm); diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 591b7c12aae5..2482ecf5776b 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -810,16 +810,19 @@ static int intel_th_output_open(struct inode *inode, struct file *file) int err; dev = bus_find_device_by_devt(&intel_th_bus, inode->i_rdev); - if (!dev || !dev->driver) { + if (!dev) + return -ENODEV; + + if (!dev->driver) { err = -ENODEV; - goto out_no_device; + goto err_put_dev; } thdrv = to_intel_th_driver(dev->driver); fops = fops_get(thdrv->fops); if (!fops) { err = -ENODEV; - goto out_put_device; + goto err_put_dev; } replace_fops(file, fops); @@ -829,19 +832,29 @@ static int intel_th_output_open(struct inode *inode, struct file *file) if (file->f_op->open) { err = file->f_op->open(inode, file); if (err) - goto out_put_device; + goto err_put_dev; } return 0; -out_put_device: +err_put_dev: put_device(dev); -out_no_device: + return err; } +static int intel_th_output_release(struct inode *inode, struct file *file) +{ + struct intel_th_device *thdev = file->private_data; + + put_device(&thdev->dev); + + return 0; +} + static const struct file_operations intel_th_output_fops = { .open = intel_th_output_open, + .release = intel_th_output_release, .llseek = noop_llseek, }; diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 2a0962a0b441..d882126c1778 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -593,6 +593,13 @@ static bool is_use_dma(struct lpi2c_imx_struct *lpi2c_imx, struct i2c_msg *msg) return false; /* + * A system-wide suspend or resume transition is in progress. LPI2C should use PIO to + * transfer data to avoid issue caused by no ready DMA HW resource. + */ + if (pm_suspend_in_progress()) + return false; + + /* * When the length of data is less than I2C_DMA_THRESHOLD, * cpu mode is used directly to avoid low performance. */ diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c index d42c03ef5db5..8ef6d5d1927b 100644 --- a/drivers/i2c/busses/i2c-k1.c +++ b/drivers/i2c/busses/i2c-k1.c @@ -566,7 +566,7 @@ static int spacemit_i2c_probe(struct platform_device *pdev) return dev_err_probe(dev, i2c->irq, "failed to get irq resource"); ret = devm_request_irq(i2c->dev, i2c->irq, spacemit_i2c_irq_handler, - IRQF_NO_SUSPEND | IRQF_ONESHOT, dev_name(i2c->dev), i2c); + IRQF_NO_SUSPEND, dev_name(i2c->dev), i2c); if (ret) return dev_err_probe(dev, ret, "failed to request irq"); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 3a04016db2c3..ae609bdd2ec4 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -116,6 +116,7 @@ struct geni_i2c_dev { dma_addr_t dma_addr; struct dma_chan *tx_c; struct dma_chan *rx_c; + bool no_dma; bool gpi_mode; bool abort_done; bool is_tx_multi_desc_xfer; @@ -447,7 +448,7 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, size_t len = msg->len; struct i2c_msg *cur; - dma_buf = i2c_get_dma_safe_msg_buf(msg, 32); + dma_buf = gi2c->no_dma ? NULL : i2c_get_dma_safe_msg_buf(msg, 32); if (dma_buf) geni_se_select_mode(se, GENI_SE_DMA); else @@ -486,7 +487,7 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, size_t len = msg->len; struct i2c_msg *cur; - dma_buf = i2c_get_dma_safe_msg_buf(msg, 32); + dma_buf = gi2c->no_dma ? NULL : i2c_get_dma_safe_msg_buf(msg, 32); if (dma_buf) geni_se_select_mode(se, GENI_SE_DMA); else @@ -1080,10 +1081,12 @@ static int geni_i2c_probe(struct platform_device *pdev) goto err_resources; } - if (desc && desc->no_dma_support) + if (desc && desc->no_dma_support) { fifo_disable = false; - else + gi2c->no_dma = true; + } else { fifo_disable = readl_relaxed(gi2c->se.base + GENI_IF_DISABLE_RO) & FIFO_IF_DISABLE; + } if (fifo_disable) { /* FIFO is disabled, so we can only use GPI DMA */ diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c index 3e8f126cb7f7..9e3595b3623e 100644 --- a/drivers/i2c/busses/i2c-riic.c +++ b/drivers/i2c/busses/i2c-riic.c @@ -670,12 +670,39 @@ static const struct riic_of_data riic_rz_t2h_info = { static int riic_i2c_suspend(struct device *dev) { - struct riic_dev *riic = dev_get_drvdata(dev); - int ret; + /* + * Some I2C devices may need the I2C controller to remain active + * during resume_noirq() or suspend_noirq(). If the controller is + * autosuspended, there is no way to wake it up once runtime PM is + * disabled (in suspend_late()). + * + * During system resume, the I2C controller will be available only + * after runtime PM is re-enabled (in resume_early()). However, this + * may be too late for some devices. + * + * Wake up the controller in the suspend() callback while runtime PM + * is still enabled. The I2C controller will remain available until + * the suspend_noirq() callback (pm_runtime_force_suspend()) is + * called. During resume, the I2C controller can be restored by the + * resume_noirq() callback (pm_runtime_force_resume()). + * + * Finally, the resume() callback re-enables autosuspend, ensuring + * the I2C controller remains available until the system enters + * suspend_noirq() and from resume_noirq(). + */ + return pm_runtime_resume_and_get(dev); +} - ret = pm_runtime_resume_and_get(dev); - if (ret) - return ret; +static int riic_i2c_resume(struct device *dev) +{ + pm_runtime_put_autosuspend(dev); + + return 0; +} + +static int riic_i2c_suspend_noirq(struct device *dev) +{ + struct riic_dev *riic = dev_get_drvdata(dev); i2c_mark_adapter_suspended(&riic->adapter); @@ -683,12 +710,12 @@ static int riic_i2c_suspend(struct device *dev) riic_clear_set_bit(riic, ICCR1_ICE, 0, RIIC_ICCR1); pm_runtime_mark_last_busy(dev); - pm_runtime_put_sync(dev); + pm_runtime_force_suspend(dev); return reset_control_assert(riic->rstc); } -static int riic_i2c_resume(struct device *dev) +static int riic_i2c_resume_noirq(struct device *dev) { struct riic_dev *riic = dev_get_drvdata(dev); int ret; @@ -697,6 +724,10 @@ static int riic_i2c_resume(struct device *dev) if (ret) return ret; + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + ret = riic_init_hw(riic); if (ret) { /* @@ -714,6 +745,7 @@ static int riic_i2c_resume(struct device *dev) } static const struct dev_pm_ops riic_i2c_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(riic_i2c_suspend_noirq, riic_i2c_resume_noirq) SYSTEM_SLEEP_PM_OPS(riic_i2c_suspend, riic_i2c_resume) }; diff --git a/drivers/iio/accel/adxl380.c b/drivers/iio/accel/adxl380.c index 6d5f1a0d51e9..aef5109c1ddd 100644 --- a/drivers/iio/accel/adxl380.c +++ b/drivers/iio/accel/adxl380.c @@ -1784,9 +1784,9 @@ static int adxl380_config_irq(struct iio_dev *indio_dev) st->int_map[1] = ADXL380_INT0_MAP1_REG; } else { st->irq = fwnode_irq_get_byname(dev_fwnode(st->dev), "INT1"); - if (st->irq > 0) - return dev_err_probe(st->dev, -ENODEV, - "no interrupt name specified"); + if (st->irq < 0) + return dev_err_probe(st->dev, st->irq, + "no interrupt name specified\n"); st->int_map[0] = ADXL380_INT1_MAP0_REG; st->int_map[1] = ADXL380_INT1_MAP1_REG; } diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index a7961c610ed2..1a9447c81b0f 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -517,7 +517,6 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .wai_addr = ST_SENSORS_DEFAULT_WAI_ADDRESS, .sensors_supported = { [0] = H3LIS331DL_ACCEL_DEV_NAME, - [1] = IIS328DQ_ACCEL_DEV_NAME, }, .ch = (struct iio_chan_spec *)st_accel_12bit_channels, .odr = { @@ -585,6 +584,77 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .bootime = 2, }, { + .wai = 0x32, + .wai_addr = ST_SENSORS_DEFAULT_WAI_ADDRESS, + .sensors_supported = { + [0] = IIS328DQ_ACCEL_DEV_NAME, + }, + .ch = (struct iio_chan_spec *)st_accel_12bit_channels, + .odr = { + .addr = 0x20, + .mask = 0x18, + .odr_avl = { + { .hz = 50, .value = 0x00, }, + { .hz = 100, .value = 0x01, }, + { .hz = 400, .value = 0x02, }, + { .hz = 1000, .value = 0x03, }, + }, + }, + .pw = { + .addr = 0x20, + .mask = 0x20, + .value_on = ST_SENSORS_DEFAULT_POWER_ON_VALUE, + .value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE, + }, + .enable_axis = { + .addr = ST_SENSORS_DEFAULT_AXIS_ADDR, + .mask = ST_SENSORS_DEFAULT_AXIS_MASK, + }, + .fs = { + .addr = 0x23, + .mask = 0x30, + .fs_avl = { + [0] = { + .num = ST_ACCEL_FS_AVL_100G, + .value = 0x00, + .gain = IIO_G_TO_M_S_2(980), + }, + [1] = { + .num = ST_ACCEL_FS_AVL_200G, + .value = 0x01, + .gain = IIO_G_TO_M_S_2(1950), + }, + [2] = { + .num = ST_ACCEL_FS_AVL_400G, + .value = 0x03, + .gain = IIO_G_TO_M_S_2(3910), + }, + }, + }, + .bdu = { + .addr = 0x23, + .mask = 0x80, + }, + .drdy_irq = { + .int1 = { + .addr = 0x22, + .mask = 0x02, + }, + .int2 = { + .addr = 0x22, + .mask = 0x10, + }, + .addr_ihl = 0x22, + .mask_ihl = 0x80, + }, + .sim = { + .addr = 0x23, + .value = BIT(0), + }, + .multi_read_bit = true, + .bootime = 2, + }, + { /* No WAI register present */ .sensors_supported = { [0] = LIS3L02DQ_ACCEL_DEV_NAME, diff --git a/drivers/iio/adc/ad7280a.c b/drivers/iio/adc/ad7280a.c index 50a6ff7c8b1c..ba12a3796e2b 100644 --- a/drivers/iio/adc/ad7280a.c +++ b/drivers/iio/adc/ad7280a.c @@ -1024,7 +1024,9 @@ static int ad7280_probe(struct spi_device *spi) st->spi->max_speed_hz = AD7280A_MAX_SPI_CLK_HZ; st->spi->mode = SPI_MODE_1; - spi_setup(st->spi); + ret = spi_setup(st->spi); + if (ret < 0) + return ret; st->ctrl_lb = FIELD_PREP(AD7280A_CTRL_LB_ACQ_TIME_MSK, st->acquisition_time) | FIELD_PREP(AD7280A_CTRL_LB_THERMISTOR_MSK, st->thermistor_term_en); diff --git a/drivers/iio/adc/ad7606_par.c b/drivers/iio/adc/ad7606_par.c index 634852c4bbd2..b81e707ab40c 100644 --- a/drivers/iio/adc/ad7606_par.c +++ b/drivers/iio/adc/ad7606_par.c @@ -43,7 +43,8 @@ static int ad7606_par_bus_setup_iio_backend(struct device *dev, struct iio_dev *indio_dev) { struct ad7606_state *st = iio_priv(indio_dev); - unsigned int ret, c; + unsigned int c; + int ret; struct iio_backend_data_fmt data = { .sign_extend = true, .enable = true, diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index f7a9f46ea0dc..2d8f8da3671d 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -95,7 +95,7 @@ #define CHIPID_AD9434 0x6A #define AD9434_DEF_OUTPUT_MODE 0x00 -#define AD9434_REG_VREF_MASK 0xC0 +#define AD9434_REG_VREF_MASK GENMASK(4, 0) /* * Analog Devices AD9467 16-Bit, 200/250 MSPS ADC diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index b4c36e6a7490..aa4ba3f5a506 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -2481,6 +2481,7 @@ static void at91_adc_remove(struct platform_device *pdev) struct at91_adc_state *st = iio_priv(indio_dev); iio_device_unregister(indio_dev); + cancel_work_sync(&st->touch_st.workq); at91_adc_dma_disable(st); diff --git a/drivers/iio/adc/exynos_adc.c b/drivers/iio/adc/exynos_adc.c index 1484adff00df..f2400897818c 100644 --- a/drivers/iio/adc/exynos_adc.c +++ b/drivers/iio/adc/exynos_adc.c @@ -540,15 +540,6 @@ static const struct iio_chan_spec exynos_adc_iio_channels[] = { ADC_CHANNEL(9, "adc9"), }; -static int exynos_adc_remove_devices(struct device *dev, void *c) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - - return 0; -} - static int exynos_adc_probe(struct platform_device *pdev) { struct exynos_adc *info = NULL; @@ -660,8 +651,7 @@ static int exynos_adc_probe(struct platform_device *pdev) return 0; err_of_populate: - device_for_each_child(&indio_dev->dev, NULL, - exynos_adc_remove_devices); + of_platform_depopulate(&indio_dev->dev); iio_device_unregister(indio_dev); err_irq: free_irq(info->irq, info); @@ -681,8 +671,7 @@ static void exynos_adc_remove(struct platform_device *pdev) struct iio_dev *indio_dev = platform_get_drvdata(pdev); struct exynos_adc *info = iio_priv(indio_dev); - device_for_each_child(&indio_dev->dev, NULL, - exynos_adc_remove_devices); + of_platform_depopulate(&indio_dev->dev); iio_device_unregister(indio_dev); free_irq(info->irq, info); if (info->data->exit_hw) diff --git a/drivers/iio/adc/pac1934.c b/drivers/iio/adc/pac1934.c index ec96bb0f2ed6..712b5e9caba6 100644 --- a/drivers/iio/adc/pac1934.c +++ b/drivers/iio/adc/pac1934.c @@ -665,9 +665,9 @@ static int pac1934_reg_snapshot(struct pac1934_chip_info *info, /* add the power_acc field */ curr_energy += inc; - clamp(curr_energy, PAC_193X_MIN_POWER_ACC, PAC_193X_MAX_POWER_ACC); - - reg_data->energy_sec_acc[cnt] = curr_energy; + reg_data->energy_sec_acc[cnt] = clamp(curr_energy, + PAC_193X_MIN_POWER_ACC, + PAC_193X_MAX_POWER_ACC); } offset_reg_data_p += PAC1934_VPOWER_ACC_REG_LEN; diff --git a/drivers/iio/chemical/scd4x.c b/drivers/iio/chemical/scd4x.c index 8859f89fb2a9..0fd839176e26 100644 --- a/drivers/iio/chemical/scd4x.c +++ b/drivers/iio/chemical/scd4x.c @@ -584,7 +584,7 @@ static const struct iio_chan_spec scd4x_channels[] = { .sign = 'u', .realbits = 16, .storagebits = 16, - .endianness = IIO_BE, + .endianness = IIO_CPU, }, }, { @@ -599,7 +599,7 @@ static const struct iio_chan_spec scd4x_channels[] = { .sign = 'u', .realbits = 16, .storagebits = 16, - .endianness = IIO_BE, + .endianness = IIO_CPU, }, }, { @@ -612,7 +612,7 @@ static const struct iio_chan_spec scd4x_channels[] = { .sign = 'u', .realbits = 16, .storagebits = 16, - .endianness = IIO_BE, + .endianness = IIO_CPU, }, }, }; diff --git a/drivers/iio/dac/ad3552r-hs.c b/drivers/iio/dac/ad3552r-hs.c index 41b96b48ba98..a9578afa7015 100644 --- a/drivers/iio/dac/ad3552r-hs.c +++ b/drivers/iio/dac/ad3552r-hs.c @@ -549,12 +549,15 @@ static ssize_t ad3552r_hs_write_data_source(struct file *f, guard(mutex)(&st->lock); + if (count >= sizeof(buf)) + return -ENOSPC; + ret = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, userbuf, count); if (ret < 0) return ret; - buf[count] = '\0'; + buf[ret] = '\0'; ret = match_string(dbgfs_attr_source, ARRAY_SIZE(dbgfs_attr_source), buf); diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c index d9cae9555e5d..4b18498aa074 100644 --- a/drivers/iio/dac/ad5686.c +++ b/drivers/iio/dac/ad5686.c @@ -434,6 +434,12 @@ static const struct ad5686_chip_info ad5686_chip_info_tbl[] = { .num_channels = 4, .regmap_type = AD5686_REGMAP, }, + [ID_AD5695R] = { + .channels = ad5685r_channels, + .int_vref_mv = 2500, + .num_channels = 4, + .regmap_type = AD5686_REGMAP, + }, [ID_AD5696] = { .channels = ad5686_channels, .num_channels = 4, diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c index ab1cb7b9dba4..25bd9757a594 100644 --- a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c +++ b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c @@ -960,16 +960,17 @@ int inv_icm45600_temp_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; /* * T°C = (temp / 128) + 25 - * Tm°C = 1000 * ((temp * 100 / 12800) + 25) - * scale: 100000 / 13248 = 7.8125 - * offset: 25000 + * Tm°C = ((temp + 25 * 128) / 128)) * 1000 + * Tm°C = (temp + 3200) * (1000 / 128) + * scale: 1000 / 128 = 7.8125 + * offset: 3200 */ case IIO_CHAN_INFO_SCALE: *val = 7; *val2 = 812500; return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_OFFSET: - *val = 25000; + *val = 3200; return IIO_VAL_INT; default: return -EINVAL; diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 49ac17806e72..dc78227952a7 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -101,6 +101,13 @@ static const struct iio_chan_spec st_lsm6dsx_acc_channels[] = { IIO_CHAN_SOFT_TIMESTAMP(3), }; +static const struct iio_chan_spec st_lsm6ds0_acc_channels[] = { + ST_LSM6DSX_CHANNEL(IIO_ACCEL, 0x28, IIO_MOD_X, 0), + ST_LSM6DSX_CHANNEL(IIO_ACCEL, 0x2a, IIO_MOD_Y, 1), + ST_LSM6DSX_CHANNEL(IIO_ACCEL, 0x2c, IIO_MOD_Z, 2), + IIO_CHAN_SOFT_TIMESTAMP(3), +}; + static const struct iio_chan_spec st_lsm6dsx_gyro_channels[] = { ST_LSM6DSX_CHANNEL(IIO_ANGL_VEL, 0x22, IIO_MOD_X, 0), ST_LSM6DSX_CHANNEL(IIO_ANGL_VEL, 0x24, IIO_MOD_Y, 1), @@ -142,8 +149,8 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = { }, .channels = { [ST_LSM6DSX_ID_ACC] = { - .chan = st_lsm6dsx_acc_channels, - .len = ARRAY_SIZE(st_lsm6dsx_acc_channels), + .chan = st_lsm6ds0_acc_channels, + .len = ARRAY_SIZE(st_lsm6ds0_acc_channels), }, [ST_LSM6DSX_ID_GYRO] = { .chan = st_lsm6ds0_gyro_channels, @@ -1449,8 +1456,8 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = { }, .channels = { [ST_LSM6DSX_ID_ACC] = { - .chan = st_lsm6dsx_acc_channels, - .len = ARRAY_SIZE(st_lsm6dsx_acc_channels), + .chan = st_lsm6ds0_acc_channels, + .len = ARRAY_SIZE(st_lsm6ds0_acc_channels), }, [ST_LSM6DSX_ID_GYRO] = { .chan = st_lsm6dsx_gyro_channels, diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index f69deefcfb6f..117ffad4f376 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1657,6 +1657,7 @@ static void iio_dev_release(struct device *device) mutex_destroy(&iio_dev_opaque->info_exist_lock); mutex_destroy(&iio_dev_opaque->mlock); + lockdep_unregister_key(&iio_dev_opaque->info_exist_key); lockdep_unregister_key(&iio_dev_opaque->mlock_key); ida_free(&iio_ida, iio_dev_opaque->id); @@ -1717,9 +1718,10 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv) INIT_LIST_HEAD(&iio_dev_opaque->ioctl_handlers); lockdep_register_key(&iio_dev_opaque->mlock_key); + lockdep_register_key(&iio_dev_opaque->info_exist_key); mutex_init_with_key(&iio_dev_opaque->mlock, &iio_dev_opaque->mlock_key); - mutex_init(&iio_dev_opaque->info_exist_lock); + mutex_init_with_key(&iio_dev_opaque->info_exist_lock, &iio_dev_opaque->info_exist_key); indio_dev->dev.parent = parent; indio_dev->dev.type = &iio_device_type; diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 61596cda2b65..35ba852a172a 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -80,37 +80,25 @@ static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = { .min = sizeof(struct rdma_nla_ls_gid)}, }; -static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh) +static void ib_nl_process_ip_rsep(const struct nlmsghdr *nlh) { struct nlattr *tb[LS_NLA_TYPE_MAX] = {}; + union ib_gid gid; + struct addr_req *req; + int found = 0; int ret; if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR) - return false; + return; ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh), nlmsg_len(nlh), ib_nl_addr_policy, NULL); if (ret) - return false; - - return true; -} - -static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh) -{ - const struct nlattr *head, *curr; - union ib_gid gid; - struct addr_req *req; - int len, rem; - int found = 0; - - head = (const struct nlattr *)nlmsg_data(nlh); - len = nlmsg_len(nlh); + return; - nla_for_each_attr(curr, head, len, rem) { - if (curr->nla_type == LS_NLA_TYPE_DGID) - memcpy(&gid, nla_data(curr), nla_len(curr)); - } + if (!tb[LS_NLA_TYPE_DGID]) + return; + memcpy(&gid, nla_data(tb[LS_NLA_TYPE_DGID]), sizeof(gid)); spin_lock_bh(&lock); list_for_each_entry(req, &req_list, list) { @@ -137,8 +125,7 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb, !(NETLINK_CB(skb).sk)) return -EPERM; - if (ib_nl_is_good_ip_resp(nlh)) - ib_nl_process_good_ip_rsep(nlh); + ib_nl_process_ip_rsep(nlh); return 0; } diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 95e89f5c147c..f00f1d3fbd9c 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2009,6 +2009,7 @@ static void destroy_mc(struct rdma_id_private *id_priv, ib_sa_free_multicast(mc->sa_mc); if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { + struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct net_device *ndev = NULL; @@ -2031,6 +2032,8 @@ static void destroy_mc(struct rdma_id_private *id_priv, dev_put(ndev); cancel_work_sync(&mc->iboe_join.work); + if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) + rdma_destroy_ah_attr(&event->param.ud.ah_attr); } kfree(mc); } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 13e8a1714bbd..1174ab7da629 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2881,8 +2881,10 @@ int ib_del_sub_device_and_put(struct ib_device *sub) { struct ib_device *parent = sub->parent; - if (!parent) + if (!parent) { + ib_device_put(sub); return -EOPNOTSUPP; + } mutex_lock(&parent->subdev_lock); list_del(&sub->subdev_list); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 11b1a194de44..ee390928511a 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -738,7 +738,7 @@ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, (struct in6_addr *)dgid); return 0; } else if (net_type == RDMA_NETWORK_IPV6 || - net_type == RDMA_NETWORK_IB || RDMA_NETWORK_ROCE_V1) { + net_type == RDMA_NETWORK_IB || net_type == RDMA_NETWORK_ROCE_V1) { *dgid = hdr->ibgrh.dgid; *sgid = hdr->ibgrh.sgid; return 0; diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.h b/drivers/infiniband/hw/bnxt_re/hw_counters.h index 09d371d442aa..cebec033f4a0 100644 --- a/drivers/infiniband/hw/bnxt_re/hw_counters.h +++ b/drivers/infiniband/hw/bnxt_re/hw_counters.h @@ -89,6 +89,9 @@ enum bnxt_re_hw_stats { BNXT_RE_RES_SRQ_LOAD_ERR, BNXT_RE_RES_TX_PCI_ERR, BNXT_RE_RES_RX_PCI_ERR, + BNXT_RE_REQ_CQE_ERROR, + BNXT_RE_RESP_CQE_ERROR, + BNXT_RE_RESP_REMOTE_ACCESS_ERRS, BNXT_RE_OUT_OF_SEQ_ERR, BNXT_RE_TX_ATOMIC_REQ, BNXT_RE_TX_READ_REQ, @@ -110,9 +113,6 @@ enum bnxt_re_hw_stats { BNXT_RE_TX_CNP, BNXT_RE_RX_CNP, BNXT_RE_RX_ECN, - BNXT_RE_REQ_CQE_ERROR, - BNXT_RE_RESP_CQE_ERROR, - BNXT_RE_RESP_REMOTE_ACCESS_ERRS, BNXT_RE_NUM_EXT_COUNTERS }; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index f19b55c13d58..ff91511bd338 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -2919,14 +2919,9 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, wqe.rawqp1.lflags |= SQ_SEND_RAWETH_QP1_LFLAGS_ROCE_CRC; } - switch (wr->send_flags) { - case IB_SEND_IP_CSUM: + if (wr->send_flags & IB_SEND_IP_CSUM) wqe.rawqp1.lflags |= SQ_SEND_RAWETH_QP1_LFLAGS_IP_CHKSUM; - break; - default: - break; - } fallthrough; case IB_WR_SEND_WITH_INV: rc = bnxt_re_build_send_wqe(qp, wr, &wqe); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 295a9610f3e6..4dad0cfcfa98 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -1112,7 +1112,7 @@ static int bnxt_qplib_map_creq_db(struct bnxt_qplib_rcfw *rcfw, u32 reg_offt) creq_db->dbinfo.flags = 0; creq_db->reg.bar_id = RCFW_COMM_CONS_PCI_BAR_REGION; creq_db->reg.bar_base = pci_resource_start(pdev, creq_db->reg.bar_id); - if (!creq_db->reg.bar_id) + if (!creq_db->reg.bar_base) dev_err(&pdev->dev, "QPLIB: CREQ BAR region %d resc start is 0!", creq_db->reg.bar_id); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 875d7b52c06a..4d674a3aee1a 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -64,9 +64,7 @@ static void __free_pbl(struct bnxt_qplib_res *res, struct bnxt_qplib_pbl *pbl, for (i = 0; i < pbl->pg_count; i++) { if (pbl->pg_arr[i]) dma_free_coherent(&pdev->dev, pbl->pg_size, - (void *)((unsigned long) - pbl->pg_arr[i] & - PAGE_MASK), + pbl->pg_arr[i], pbl->pg_map_arr[i]); else dev_warn(&pdev->dev, @@ -237,7 +235,7 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, if (npbl % BIT(MAX_PDL_LVL_SHIFT)) npde++; /* Alloc PDE pages */ - sginfo.pgsize = npde * pg_size; + sginfo.pgsize = npde * ROCE_PG_SIZE_4K; sginfo.npages = 1; rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_0], &sginfo); if (rc) @@ -245,7 +243,7 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, /* Alloc PBL pages */ sginfo.npages = npbl; - sginfo.pgsize = PAGE_SIZE; + sginfo.pgsize = ROCE_PG_SIZE_4K; rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_1], &sginfo); if (rc) goto fail; diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 22d3e25c3b9d..755bba8d58bb 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1320,13 +1320,9 @@ static int umem_to_page_list(struct efa_dev *dev, u32 hp_cnt, u8 hp_shift) { - u32 pages_in_hp = BIT(hp_shift - PAGE_SHIFT); struct ib_block_iter biter; unsigned int hp_idx = 0; - ibdev_dbg(&dev->ibdev, "hp_cnt[%u], pages_in_hp[%u]\n", - hp_cnt, pages_in_hp); - rdma_umem_for_each_dma_block(umem, &biter, BIT(hp_shift)) page_list[hp_idx++] = rdma_block_iter_dma_address(&biter); diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index cc2a12f735d3..13d7499131d4 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -251,7 +251,7 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event, void *ptr) { struct neighbour *neigh = ptr; - struct net_device *real_dev, *netdev = (struct net_device *)neigh->dev; + struct net_device *real_dev, *netdev; struct irdma_device *iwdev; struct ib_device *ibdev; __be32 *p; @@ -260,6 +260,7 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event, switch (event) { case NETEVENT_NEIGH_UPDATE: + netdev = neigh->dev; real_dev = rdma_vlan_dev_real_dev(netdev); if (!real_dev) real_dev = netdev; diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c index 1becc8779123..7600412b0739 100644 --- a/drivers/infiniband/hw/mana/cq.c +++ b/drivers/infiniband/hw/mana/cq.c @@ -56,6 +56,10 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, doorbell = mana_ucontext->doorbell; } else { is_rnic_cq = true; + if (attr->cqe > U32_MAX / COMP_ENTRY_SIZE / 2 + 1) { + ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe); + return -EINVAL; + } buf_size = MANA_PAGE_ALIGN(roundup_pow_of_two(attr->cqe * COMP_ENTRY_SIZE)); cq->cqe = buf_size / COMP_ENTRY_SIZE; err = mana_ib_create_kernel_queue(mdev, buf_size, GDMA_CQ, &cq->queue); diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 0195d361e5e3..0bd0902b11f7 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -64,7 +64,39 @@ static inline void rxe_reclassify_recv_socket(struct socket *sock) break; default: WARN_ON_ONCE(1); + return; } + /* + * sock_lock_init_class_and_name() calls + * sk_owner_set(sk, THIS_MODULE); in order + * to make sure the referenced global + * variables rxe_recv_slock_key and + * rxe_recv_sk_key are not removed + * before the socket is closed. + * + * However this prevents rxe_net_exit() + * from being called and 'rmmod rdma_rxe' + * is refused because of the references. + * + * For the global sockets in recv_sockets, + * we are sure that rxe_net_exit() will call + * rxe_release_udp_tunnel -> udp_tunnel_sock_release. + * + * So we don't need the additional reference to + * our own (THIS_MODULE). + */ + sk_owner_put(sk); + /* + * We also call sk_owner_clear() otherwise + * sk_owner_put(sk) in sk_prot_free will + * fail, which is called via + * sk_free -> __sk_free -> sk_destruct + * and sk_destruct calls __sk_destruct + * directly or via call_rcu() + * so sk_prot_free() might be called + * after rxe_net_exit(). + */ + sk_owner_clear(sk); #endif /* CONFIG_DEBUG_LOCK_ALLOC */ } diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c b/drivers/infiniband/sw/rxe/rxe_odp.c index ae71812bea82..c928cbf2e35f 100644 --- a/drivers/infiniband/sw/rxe/rxe_odp.c +++ b/drivers/infiniband/sw/rxe/rxe_odp.c @@ -179,8 +179,10 @@ static int rxe_odp_map_range_and_lock(struct rxe_mr *mr, u64 iova, int length, u return err; need_fault = rxe_check_pagefault(umem_odp, iova, length); - if (need_fault) + if (need_fault) { + mutex_unlock(&umem_odp->umem_mutex); return -EFAULT; + } } return 0; diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 71387811b281..2b397a544cb9 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -1464,6 +1464,7 @@ static void query_fast_reg_mode(struct rtrs_clt_path *clt_path) 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)); + max_pages_per_mr = min_not_zero((u32)max_pages_per_mr, U32_MAX); 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); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-pri.h b/drivers/infiniband/ulp/rtrs/rtrs-pri.h index ef29bd483b5a..59529d593869 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-pri.h +++ b/drivers/infiniband/ulp/rtrs/rtrs-pri.h @@ -150,7 +150,7 @@ enum rtrs_msg_types { /** * enum rtrs_msg_flags - RTRS message flags. - * @RTRS_NEED_INVAL: Send invalidation in response. + * @RTRS_MSG_NEED_INVAL_F: Send invalidation in response. * @RTRS_MSG_NEW_RKEY_F: Send refreshed rkey in response. */ enum rtrs_msg_flags { @@ -179,16 +179,19 @@ struct rtrs_sg_desc { * @recon_cnt: Reconnections counter * @sess_uuid: UUID of a session (path) * @paths_uuid: UUID of a group of sessions (paths) - * + * @first_conn: %1 if the connection request is the first for that session, + * otherwise %0 * NOTE: max size 56 bytes, see man rdma_connect(). */ struct rtrs_msg_conn_req { - /* Is set to 0 by cma.c in case of AF_IB, do not touch that. - * see https://www.spinics.net/lists/linux-rdma/msg22397.html + /** + * @__cma_version: Is set to 0 by cma.c in case of AF_IB, do not touch + * that. See https://www.spinics.net/lists/linux-rdma/msg22397.html */ u8 __cma_version; - /* On sender side that should be set to 0, or cma_save_ip_info() - * extract garbage and will fail. + /** + * @__ip_version: On sender side that should be set to 0, or + * cma_save_ip_info() extract garbage and will fail. */ u8 __ip_version; __le16 magic; @@ -199,6 +202,7 @@ struct rtrs_msg_conn_req { uuid_t sess_uuid; uuid_t paths_uuid; u8 first_conn : 1; + /* private: */ u8 reserved_bits : 7; u8 reserved[11]; }; @@ -211,6 +215,7 @@ struct rtrs_msg_conn_req { * @queue_depth: max inflight messages (queue-depth) in this session * @max_io_size: max io size server supports * @max_hdr_size: max msg header size server supports + * @flags: RTRS message flags for this message * * NOTE: size is 56 bytes, max possible is 136 bytes, see man rdma_accept(). */ @@ -222,22 +227,24 @@ struct rtrs_msg_conn_rsp { __le32 max_io_size; __le32 max_hdr_size; __le32 flags; + /* private: */ u8 reserved[36]; }; /** - * struct rtrs_msg_info_req + * struct rtrs_msg_info_req - client additional info request * @type: @RTRS_MSG_INFO_REQ * @pathname: Path name chosen by client */ struct rtrs_msg_info_req { __le16 type; u8 pathname[NAME_MAX]; + /* private: */ u8 reserved[15]; }; /** - * struct rtrs_msg_info_rsp + * struct rtrs_msg_info_rsp - server additional info response * @type: @RTRS_MSG_INFO_RSP * @sg_cnt: Number of @desc entries * @desc: RDMA buffers where the client can write to server @@ -245,12 +252,14 @@ struct rtrs_msg_info_req { struct rtrs_msg_info_rsp { __le16 type; __le16 sg_cnt; + /* private: */ u8 reserved[4]; + /* public: */ struct rtrs_sg_desc desc[]; }; /** - * struct rtrs_msg_rkey_rsp + * struct rtrs_msg_rkey_rsp - server refreshed rkey response * @type: @RTRS_MSG_RKEY_RSP * @buf_id: RDMA buf_id of the new rkey * @rkey: new remote key for RDMA buffers id from server @@ -264,6 +273,7 @@ struct rtrs_msg_rkey_rsp { /** * struct rtrs_msg_rdma_read - RDMA data transfer request from client * @type: always @RTRS_MSG_READ + * @flags: RTRS message flags (enum rtrs_msg_flags) * @usr_len: length of user payload * @sg_cnt: number of @desc entries * @desc: RDMA buffers where the server can write the result to @@ -277,7 +287,7 @@ struct rtrs_msg_rdma_read { }; /** - * struct_msg_rdma_write - Message transferred to server with RDMA-Write + * struct rtrs_msg_rdma_write - Message transferred to server with RDMA-Write * @type: always @RTRS_MSG_WRITE * @usr_len: length of user payload */ @@ -287,7 +297,7 @@ struct rtrs_msg_rdma_write { }; /** - * struct_msg_rdma_hdr - header for read or write request + * struct rtrs_msg_rdma_hdr - header for read or write request * @type: @RTRS_MSG_WRITE | @RTRS_MSG_READ */ struct rtrs_msg_rdma_hdr { diff --git a/drivers/infiniband/ulp/rtrs/rtrs.h b/drivers/infiniband/ulp/rtrs/rtrs.h index b48b53a7c143..b5bd35712de0 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs.h +++ b/drivers/infiniband/ulp/rtrs/rtrs.h @@ -24,8 +24,8 @@ struct rtrs_srv_op; /** * enum rtrs_clt_link_ev - Events about connectivity state of a client - * @RTRS_CLT_LINK_EV_RECONNECTED Client was reconnected. - * @RTRS_CLT_LINK_EV_DISCONNECTED Client was disconnected. + * @RTRS_CLT_LINK_EV_RECONNECTED: Client was reconnected. + * @RTRS_CLT_LINK_EV_DISCONNECTED: Client was disconnected. */ enum rtrs_clt_link_ev { RTRS_CLT_LINK_EV_RECONNECTED, @@ -33,7 +33,9 @@ enum rtrs_clt_link_ev { }; /** - * Source and destination address of a path to be established + * struct rtrs_addr - Source and destination address of a path to be established + * @src: source address + * @dst: destination address */ struct rtrs_addr { struct sockaddr_storage *src; @@ -41,7 +43,7 @@ struct rtrs_addr { }; /** - * rtrs_clt_ops - it holds the link event callback and private pointer. + * struct rtrs_clt_ops - it holds the link event callback and private pointer. * @priv: User supplied private data. * @link_ev: Event notification callback function for connection state changes * @priv: User supplied data that was passed to rtrs_clt_open() @@ -67,10 +69,10 @@ enum wait_type { }; /** - * enum rtrs_clt_con_type() type of ib connection to use with a given + * enum rtrs_clt_con_type - type of ib connection to use with a given * rtrs_permit - * @ADMIN_CON - use connection reserved for "service" messages - * @IO_CON - use a connection reserved for IO + * @RTRS_ADMIN_CON: use connection reserved for "service" messages + * @RTRS_IO_CON: use a connection reserved for IO */ enum rtrs_clt_con_type { RTRS_ADMIN_CON, @@ -85,7 +87,7 @@ void rtrs_clt_put_permit(struct rtrs_clt_sess *sess, struct rtrs_permit *permit); /** - * rtrs_clt_req_ops - it holds the request confirmation callback + * struct rtrs_clt_req_ops - it holds the request confirmation callback * and a private pointer. * @priv: User supplied private data. * @conf_fn: callback function to be called as confirmation @@ -105,7 +107,11 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops, int rtrs_clt_rdma_cq_direct(struct rtrs_clt_sess *clt, unsigned int index); /** - * rtrs_attrs - RTRS session attributes + * struct rtrs_attrs - RTRS session attributes + * @queue_depth: queue_depth saved from rtrs_clt_sess message + * @max_io_size: max_io_size from rtrs_clt_sess message, capped to + * @max_segments * %SZ_4K + * @max_segments: max_segments saved from rtrs_clt_sess message */ struct rtrs_attrs { u32 queue_depth; diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 654771275ce8..d2cf940b105a 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -116,6 +116,17 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_NEVER) }, { + /* + * ASUS Zenbook UX425QA_UM425QA + * Some Zenbooks report "Zenbook" with a lowercase b. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "Zenbook UX425QA_UM425QA"), + }, + .driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER) + }, + { /* ASUS ZenBook UX425UA/QA */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), @@ -1176,6 +1187,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "WUJIE Series-X5SP4NAG"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, /* * A lot of modern Clevo barebones have touchpad and/or keyboard issues * after suspend fixable with the forcenorestore quirk. diff --git a/drivers/interconnect/debugfs-client.c b/drivers/interconnect/debugfs-client.c index 778deeb4a7e8..24d7b5a57794 100644 --- a/drivers/interconnect/debugfs-client.c +++ b/drivers/interconnect/debugfs-client.c @@ -150,6 +150,11 @@ int icc_debugfs_client_init(struct dentry *icc_dir) return ret; } + src_node = devm_kstrdup(&pdev->dev, "", GFP_KERNEL); + dst_node = devm_kstrdup(&pdev->dev, "", GFP_KERNEL); + if (!src_node || !dst_node) + return -ENOMEM; + client_dir = debugfs_create_dir("test_client", icc_dir); debugfs_create_str("src_node", 0600, client_dir, &src_node); diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 5d45795c367a..7c12be1b247f 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2450,8 +2450,6 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) goto out_err; } -out_err: - iommu_completion_wait(iommu); if (FEATURE_NUM_INT_REMAP_SUP_2K(amd_iommu_efr2)) @@ -2462,6 +2460,7 @@ out_err: if (dev_is_pci(dev)) pci_prepare_ats(to_pci_dev(dev), PAGE_SHIFT); +out_err: return iommu_dev; } diff --git a/drivers/iommu/generic_pt/.kunitconfig b/drivers/iommu/generic_pt/.kunitconfig index 52ac9e661ffd..a78b295f264d 100644 --- a/drivers/iommu/generic_pt/.kunitconfig +++ b/drivers/iommu/generic_pt/.kunitconfig @@ -1,4 +1,5 @@ CONFIG_KUNIT=y +CONFIG_COMPILE_TEST=y CONFIG_GENERIC_PT=y CONFIG_DEBUG_GENERIC_PT=y CONFIG_IOMMU_PT=y @@ -11,4 +12,3 @@ CONFIG_IOMMUFD=y CONFIG_DEBUG_KERNEL=y CONFIG_FAULT_INJECTION=y CONFIG_RUNTIME_TESTING_MENU=y -CONFIG_IOMMUFD_TEST=y diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h index 3327116a441c..52ef028ed2db 100644 --- a/drivers/iommu/generic_pt/iommu_pt.h +++ b/drivers/iommu/generic_pt/iommu_pt.h @@ -645,7 +645,7 @@ static __always_inline int __do_map_single_page(struct pt_range *range, struct pt_iommu_map_args *map = arg; pts.type = pt_load_single_entry(&pts); - if (level == 0) { + if (pts.level == 0) { if (pts.type != PT_ENTRY_EMPTY) return -EADDRINUSE; pt_install_leaf_entry(&pts, map->oa, PAGE_SHIFT, diff --git a/drivers/iommu/generic_pt/pt_defs.h b/drivers/iommu/generic_pt/pt_defs.h index c25544d72f97..707b3b0282fa 100644 --- a/drivers/iommu/generic_pt/pt_defs.h +++ b/drivers/iommu/generic_pt/pt_defs.h @@ -202,7 +202,7 @@ static inline bool pt_table_install32(struct pt_state *pts, u32 table_entry) #define PT_SUPPORTED_FEATURE(feature_nr) (PT_SUPPORTED_FEATURES & BIT(feature_nr)) -static inline bool pt_feature(const struct pt_common *common, +static __always_inline bool pt_feature(const struct pt_common *common, unsigned int feature_nr) { if (PT_FORCE_ENABLED_FEATURES & BIT(feature_nr)) @@ -212,7 +212,7 @@ static inline bool pt_feature(const struct pt_common *common, return common->features & BIT(feature_nr); } -static inline bool pts_feature(const struct pt_state *pts, +static __always_inline bool pts_feature(const struct pt_state *pts, unsigned int feature_nr) { return pt_feature(pts->range->common, feature_nr); diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index e6626004b323..05d63fe92e43 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -637,7 +637,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, pte = READ_ONCE(*ptep); if (!pte) { WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN)); - return -ENOENT; + return 0; } /* If the size matches this level, we're in the right place */ diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index d236aef80a8d..e1e63c2be82b 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -3,6 +3,7 @@ * Helpers for IOMMU drivers implementing SVA */ #include <linux/mmu_context.h> +#include <linux/mmu_notifier.h> #include <linux/mutex.h> #include <linux/sched/mm.h> #include <linux/iommu.h> diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig index eae3f03629b0..455bac0351f2 100644 --- a/drivers/iommu/iommufd/Kconfig +++ b/drivers/iommu/iommufd/Kconfig @@ -41,7 +41,8 @@ config IOMMUFD_TEST depends on DEBUG_KERNEL depends on FAULT_INJECTION depends on RUNTIME_TESTING_MENU - depends on IOMMU_PT_AMDV1 + depends on IOMMU_PT_AMDV1=y || IOMMUFD=IOMMU_PT_AMDV1 + select DMA_SHARED_BUFFER select IOMMUFD_DRIVER default n help diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index ada585bfa451..2988def30972 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -709,7 +709,7 @@ static struct its_collection *its_build_mapd_cmd(struct its_node *its, struct its_cmd_block *cmd, struct its_cmd_desc *desc) { - unsigned long itt_addr; + phys_addr_t itt_addr; u8 size = ilog2(desc->its_mapd_cmd.dev->nr_ites); itt_addr = virt_to_phys(desc->its_mapd_cmd.dev->itt); @@ -879,7 +879,7 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, struct its_cmd_desc *desc) { struct its_vpe *vpe = valid_vpe(its, desc->its_vmapp_cmd.vpe); - unsigned long vpt_addr, vconf_addr; + phys_addr_t vpt_addr, vconf_addr; u64 target; bool alloc; @@ -2477,10 +2477,10 @@ retry_baser: baser->psz = psz; tmp = indirect ? GITS_LVL1_ENTRY_SIZE : esz; - pr_info("ITS@%pa: allocated %d %s @%lx (%s, esz %d, psz %dK, shr %d)\n", + pr_info("ITS@%pa: allocated %d %s @%llx (%s, esz %d, psz %dK, shr %d)\n", &its->phys_base, (int)(PAGE_ORDER_TO_SIZE(order) / (int)tmp), its_base_type_string[type], - (unsigned long)virt_to_phys(base), + (u64)virt_to_phys(base), indirect ? "indirect" : "flat", (int)esz, psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); diff --git a/drivers/irqchip/irq-gic-v5-its.c b/drivers/irqchip/irq-gic-v5-its.c index 554485f0be1f..8e22134b9f48 100644 --- a/drivers/irqchip/irq-gic-v5-its.c +++ b/drivers/irqchip/irq-gic-v5-its.c @@ -849,7 +849,7 @@ static int gicv5_its_map_event(struct gicv5_its_dev *its_dev, u16 event_id, u32 itte = gicv5_its_device_get_itte_ref(its_dev, event_id); - if (FIELD_GET(GICV5_ITTL2E_VALID, *itte)) + if (FIELD_GET(GICV5_ITTL2E_VALID, le64_to_cpu(*itte))) return -EEXIST; itt_entry = FIELD_PREP(GICV5_ITTL2E_LPI_ID, lpi) | diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c index 899a423b5da8..9b487120f011 100644 --- a/drivers/irqchip/irq-renesas-rzv2h.c +++ b/drivers/irqchip/irq-renesas-rzv2h.c @@ -328,6 +328,7 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type) u32 titsr, titsr_k, titsel_n, tien; struct rzv2h_icu_priv *priv; u32 tssr, tssr_k, tssel_n; + u32 titsr_cur, tssr_cur; unsigned int hwirq; u32 tint, sense; int tint_nr; @@ -376,12 +377,18 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type) guard(raw_spinlock)(&priv->lock); tssr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TSSR(tssr_k)); + titsr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TITSR(titsr_k)); + + tssr_cur = field_get(ICU_TSSR_TSSEL_MASK(tssel_n, priv->info->field_width), tssr); + titsr_cur = field_get(ICU_TITSR_TITSEL_MASK(titsel_n), titsr); + if (tssr_cur == tint && titsr_cur == sense) + return 0; + tssr &= ~(ICU_TSSR_TSSEL_MASK(tssel_n, priv->info->field_width) | tien); tssr |= ICU_TSSR_TSSEL_PREP(tint, tssel_n, priv->info->field_width); writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(tssr_k)); - titsr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TITSR(titsr_k)); titsr &= ~ICU_TITSR_TITSEL_MASK(titsel_n); titsr |= ICU_TITSR_TITSEL_PREP(sense, titsel_n); diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c index 7228a33f6c37..643c8e459611 100644 --- a/drivers/irqchip/irq-riscv-imsic-platform.c +++ b/drivers/irqchip/irq-riscv-imsic-platform.c @@ -158,11 +158,11 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask tmp_vec.local_id = new_vec->local_id; /* Point device to the temporary vector */ - imsic_msi_update_msg(d, &tmp_vec); + imsic_msi_update_msg(irq_get_irq_data(d->irq), &tmp_vec); } /* Point device to the new vector */ - imsic_msi_update_msg(d, new_vec); + imsic_msi_update_msg(irq_get_irq_data(d->irq), new_vec); /* Update irq descriptors with the new vector */ d->chip_data = new_vec; diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c index 385368052d5c..b6cebfee9461 100644 --- a/drivers/irqchip/irq-riscv-imsic-state.c +++ b/drivers/irqchip/irq-riscv-imsic-state.c @@ -477,6 +477,7 @@ static void __init imsic_local_cleanup(void) lpriv = per_cpu_ptr(imsic->lpriv, cpu); bitmap_free(lpriv->dirty_bitmap); + kfree(lpriv->vectors); } free_percpu(imsic->lpriv); @@ -490,8 +491,7 @@ static int __init imsic_local_init(void) int cpu, i; /* Allocate per-CPU private state */ - imsic->lpriv = __alloc_percpu(struct_size(imsic->lpriv, vectors, global->nr_ids + 1), - __alignof__(*imsic->lpriv)); + imsic->lpriv = alloc_percpu(typeof(*imsic->lpriv)); if (!imsic->lpriv) return -ENOMEM; @@ -511,6 +511,12 @@ static int __init imsic_local_init(void) timer_setup(&lpriv->timer, imsic_local_timer_callback, TIMER_PINNED); #endif + /* Allocate vector array */ + lpriv->vectors = kcalloc(global->nr_ids + 1, sizeof(*lpriv->vectors), + GFP_KERNEL); + if (!lpriv->vectors) + goto fail_local_cleanup; + /* Setup vector array */ for (i = 0; i <= global->nr_ids; i++) { vec = &lpriv->vectors[i]; diff --git a/drivers/irqchip/irq-riscv-imsic-state.h b/drivers/irqchip/irq-riscv-imsic-state.h index 6332501dcbd8..c42ee180b305 100644 --- a/drivers/irqchip/irq-riscv-imsic-state.h +++ b/drivers/irqchip/irq-riscv-imsic-state.h @@ -40,7 +40,7 @@ struct imsic_local_priv { #endif /* Local vector table */ - struct imsic_vector vectors[]; + struct imsic_vector *vectors; }; struct imsic_priv { diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index df98144a9539..33521c328a82 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -109,14 +109,14 @@ mISDN_read(struct file *filep, char __user *buf, size_t count, loff_t *off) spin_unlock_irq(&dev->lock); if (filep->f_flags & O_NONBLOCK) return -EAGAIN; - wait_event_interruptible(dev->wait, (dev->work || + wait_event_interruptible(dev->wait, (READ_ONCE(dev->work) || !list_empty(list))); if (signal_pending(current)) return -ERESTARTSYS; spin_lock_irq(&dev->lock); } if (dev->work) - dev->work = 0; + WRITE_ONCE(dev->work, 0); if (!list_empty(list)) { timer = list_first_entry(list, struct mISDNtimer, list); list_del(&timer->list); @@ -141,13 +141,16 @@ mISDN_poll(struct file *filep, poll_table *wait) if (*debug & DEBUG_TIMER) printk(KERN_DEBUG "%s(%p, %p)\n", __func__, filep, wait); if (dev) { + u32 work; + poll_wait(filep, &dev->wait, wait); mask = 0; - if (dev->work || !list_empty(&dev->expired)) + work = READ_ONCE(dev->work); + if (work || !list_empty(&dev->expired)) mask |= (EPOLLIN | EPOLLRDNORM); if (*debug & DEBUG_TIMER) printk(KERN_DEBUG "%s work(%d) empty(%d)\n", __func__, - dev->work, list_empty(&dev->expired)); + work, list_empty(&dev->expired)); } return mask; } @@ -172,7 +175,7 @@ misdn_add_timer(struct mISDNtimerdev *dev, int timeout) struct mISDNtimer *timer; if (!timeout) { - dev->work = 1; + WRITE_ONCE(dev->work, 1); wake_up_interruptible(&dev->wait); id = 0; } else { diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 885399ed0776..d34a19453560 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -560,11 +560,6 @@ int led_classdev_register_ext(struct device *parent, #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED led_cdev->brightness_hw_changed = -1; #endif - /* add to the list of leds */ - down_write(&leds_list_lock); - list_add_tail(&led_cdev->node, &leds_list); - up_write(&leds_list_lock); - if (!led_cdev->max_brightness) led_cdev->max_brightness = LED_FULL; @@ -574,6 +569,11 @@ int led_classdev_register_ext(struct device *parent, led_init_core(led_cdev); + /* add to the list of leds */ + down_write(&leds_list_lock); + list_add_tail(&led_cdev->node, &leds_list); + up_write(&leds_list_lock); + #ifdef CONFIG_LEDS_TRIGGERS led_trigger_set_default(led_cdev); #endif diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 8ccacba85547..ec9ff9715081 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -273,6 +273,8 @@ struct bcache_device { struct bio_set bio_split; + struct bio_set bio_detached; + unsigned int data_csum:1; int (*cache_miss)(struct btree *b, struct search *s, @@ -753,6 +755,13 @@ struct bbio { struct bio bio; }; +struct detached_dev_io_private { + struct bcache_device *d; + unsigned long start_time; + struct bio *orig_bio; + struct bio bio; +}; + #define BTREE_PRIO USHRT_MAX #define INITIAL_PRIO 32768U diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 82fdea7dea7a..a02aecac05cd 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1077,68 +1077,58 @@ static CLOSURE_CALLBACK(cached_dev_nodata) continue_at(cl, cached_dev_bio_complete, NULL); } -struct detached_dev_io_private { - struct bcache_device *d; - unsigned long start_time; - bio_end_io_t *bi_end_io; - void *bi_private; - struct block_device *orig_bdev; -}; - static void detached_dev_end_io(struct bio *bio) { - struct detached_dev_io_private *ddip; - - ddip = bio->bi_private; - bio->bi_end_io = ddip->bi_end_io; - bio->bi_private = ddip->bi_private; + struct detached_dev_io_private *ddip = + container_of(bio, struct detached_dev_io_private, bio); + struct bio *orig_bio = ddip->orig_bio; /* Count on the bcache device */ - bio_end_io_acct_remapped(bio, ddip->start_time, ddip->orig_bdev); + bio_end_io_acct(orig_bio, ddip->start_time); if (bio->bi_status) { - struct cached_dev *dc = container_of(ddip->d, - struct cached_dev, disk); + struct cached_dev *dc = bio->bi_private; + /* should count I/O error for backing device here */ bch_count_backing_io_errors(dc, bio); + orig_bio->bi_status = bio->bi_status; } - kfree(ddip); - bio_endio(bio); + bio_put(bio); + bio_endio(orig_bio); } -static void detached_dev_do_request(struct bcache_device *d, struct bio *bio, - struct block_device *orig_bdev, unsigned long start_time) +static void detached_dev_do_request(struct bcache_device *d, + struct bio *orig_bio, unsigned long start_time) { struct detached_dev_io_private *ddip; struct cached_dev *dc = container_of(d, struct cached_dev, disk); + struct bio *clone_bio; - /* - * no need to call closure_get(&dc->disk.cl), - * because upper layer had already opened bcache device, - * which would call closure_get(&dc->disk.cl) - */ - ddip = kzalloc(sizeof(struct detached_dev_io_private), GFP_NOIO); - if (!ddip) { - bio->bi_status = BLK_STS_RESOURCE; - bio_endio(bio); + if (bio_op(orig_bio) == REQ_OP_DISCARD && + !bdev_max_discard_sectors(dc->bdev)) { + bio_endio(orig_bio); return; } - ddip->d = d; + clone_bio = bio_alloc_clone(dc->bdev, orig_bio, GFP_NOIO, + &d->bio_detached); + if (!clone_bio) { + orig_bio->bi_status = BLK_STS_RESOURCE; + bio_endio(orig_bio); + return; + } + + ddip = container_of(clone_bio, struct detached_dev_io_private, bio); /* Count on the bcache device */ - ddip->orig_bdev = orig_bdev; + ddip->d = d; ddip->start_time = start_time; - ddip->bi_end_io = bio->bi_end_io; - ddip->bi_private = bio->bi_private; - bio->bi_end_io = detached_dev_end_io; - bio->bi_private = ddip; - - if ((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(dc->bdev)) - detached_dev_end_io(bio); - else - submit_bio_noacct(bio); + ddip->orig_bio = orig_bio; + + clone_bio->bi_end_io = detached_dev_end_io; + clone_bio->bi_private = dc; + + submit_bio_noacct(clone_bio); } static void quit_max_writeback_rate(struct cache_set *c, @@ -1214,10 +1204,10 @@ void cached_dev_submit_bio(struct bio *bio) start_time = bio_start_io_acct(bio); - bio_set_dev(bio, dc->bdev); bio->bi_iter.bi_sector += dc->sb.data_offset; if (cached_dev_get(dc)) { + bio_set_dev(bio, dc->bdev); s = search_alloc(bio, d, orig_bdev, start_time); trace_bcache_request_start(s->d, bio); @@ -1237,9 +1227,10 @@ void cached_dev_submit_bio(struct bio *bio) else cached_dev_read(dc, s); } - } else + } else { /* I/O request sent to backing device */ - detached_dev_do_request(d, bio, orig_bdev, start_time); + detached_dev_do_request(d, bio, start_time); + } } static int cached_dev_ioctl(struct bcache_device *d, blk_mode_t mode, diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index c17d4517af22..238d12ffdae8 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -887,6 +887,7 @@ static void bcache_device_free(struct bcache_device *d) } bioset_exit(&d->bio_split); + bioset_exit(&d->bio_detached); kvfree(d->full_dirty_stripes); kvfree(d->stripe_sectors_dirty); @@ -949,6 +950,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER)) goto out_ida_remove; + if (bioset_init(&d->bio_detached, 4, + offsetof(struct detached_dev_io_private, bio), + BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER)) + goto out_bioset_split_exit; + if (lim.logical_block_size > PAGE_SIZE && cached_bdev) { /* * This should only happen with BCACHE_SB_VERSION_BDEV. @@ -964,7 +970,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE); if (IS_ERR(d->disk)) - goto out_bioset_exit; + goto out_bioset_detach_exit; set_capacity(d->disk, sectors); snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx); @@ -976,7 +982,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk->private_data = d; return 0; -out_bioset_exit: +out_bioset_detach_exit: + bioset_exit(&d->bio_detached); +out_bioset_split_exit: bioset_exit(&d->bio_split); out_ida_remove: ida_free(&bcache_device_idx, idx); diff --git a/drivers/md/md.c b/drivers/md/md.c index e5922a682953..6d73f6e196a9 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1999,7 +1999,6 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc mddev->layout = le32_to_cpu(sb->layout); mddev->raid_disks = le32_to_cpu(sb->raid_disks); mddev->dev_sectors = le64_to_cpu(sb->size); - mddev->logical_block_size = le32_to_cpu(sb->logical_block_size); mddev->events = ev1; mddev->bitmap_info.offset = 0; mddev->bitmap_info.space = 0; @@ -2015,6 +2014,9 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc mddev->max_disks = (4096-256)/2; + if (!mddev->logical_block_size) + mddev->logical_block_size = le32_to_cpu(sb->logical_block_size); + if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) && mddev->bitmap_info.file == NULL) { mddev->bitmap_info.offset = @@ -3882,7 +3884,6 @@ out_free_rdev: static int analyze_sbs(struct mddev *mddev) { - int i; struct md_rdev *rdev, *freshest, *tmp; freshest = NULL; @@ -3909,11 +3910,9 @@ static int analyze_sbs(struct mddev *mddev) super_types[mddev->major_version]. validate_super(mddev, NULL/*freshest*/, freshest); - i = 0; rdev_for_each_safe(rdev, tmp, mddev) { if (mddev->max_disks && - (rdev->desc_nr >= mddev->max_disks || - i > mddev->max_disks)) { + rdev->desc_nr >= mddev->max_disks) { pr_warn("md: %s: %pg: only %d devices permitted\n", mdname(mddev), rdev->bdev, mddev->max_disks); @@ -4407,7 +4406,7 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len) if (err < 0) return err; - err = mddev_lock(mddev); + err = mddev_suspend_and_lock(mddev); if (err) return err; if (mddev->pers) @@ -4432,7 +4431,7 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len) } else mddev->raid_disks = n; out_unlock: - mddev_unlock(mddev); + mddev_unlock_and_resume(mddev); return err ? err : len; } static struct md_sysfs_entry md_raid_disks = @@ -5981,13 +5980,33 @@ lbs_store(struct mddev *mddev, const char *buf, size_t len) if (mddev->major_version == 0) return -EINVAL; - if (mddev->pers) - return -EBUSY; - err = kstrtouint(buf, 10, &lbs); if (err < 0) return -EINVAL; + if (mddev->pers) { + unsigned int curr_lbs; + + if (mddev->logical_block_size) + return -EBUSY; + /* + * To fix forward compatibility issues, LBS is not + * configured for arrays from old kernels (<=6.18) by default. + * If the user confirms no rollback to old kernels, + * enable LBS by writing current LBS — to prevent data + * loss from LBS changes. + */ + curr_lbs = queue_logical_block_size(mddev->gendisk->queue); + if (lbs != curr_lbs) + return -EINVAL; + + mddev->logical_block_size = curr_lbs; + set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); + pr_info("%s: logical block size configured successfully, array will not be assembled in old kernels (<= 6.18)\n", + mdname(mddev)); + return len; + } + err = mddev_lock(mddev); if (err) goto unlock; @@ -6163,7 +6182,27 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim, mdname(mddev)); return -EINVAL; } - mddev->logical_block_size = lim->logical_block_size; + + /* Only 1.x meta needs to set logical block size */ + if (mddev->major_version == 0) + return 0; + + /* + * Fix forward compatibility issue. Only set LBS by default for + * new arrays, mddev->events == 0 indicates the array was just + * created. When assembling an array, read LBS from the superblock + * instead — LBS is 0 in superblocks created by old kernels. + */ + if (!mddev->events) { + pr_info("%s: array will not be assembled in old kernels that lack configurable LBS support (<= 6.18)\n", + mdname(mddev)); + mddev->logical_block_size = lim->logical_block_size; + } + + if (!mddev->logical_block_size) + pr_warn("%s: echo current LBS to md/logical_block_size to prevent data loss issues from LBS changes.\n" + "\tNote: After setting, array will not be assembled in old kernels (<= 6.18)\n", + mdname(mddev)); return 0; } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e57ce3295292..8dc98f545969 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7187,12 +7187,14 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) err = mddev_suspend_and_lock(mddev); if (err) return err; + conf = mddev->private; + if (!conf) { + mddev_unlock_and_resume(mddev); + return -ENODEV; + } raid5_quiesce(mddev, true); - conf = mddev->private; - if (!conf) - err = -ENODEV; - else if (new != conf->worker_cnt_per_group) { + if (new != conf->worker_cnt_per_group) { old_groups = conf->worker_groups; if (old_groups) flush_workqueue(raid5_wq); diff --git a/drivers/media/i2c/ov02c10.c b/drivers/media/i2c/ov02c10.c index b1e540eb8326..cf93d36032e1 100644 --- a/drivers/media/i2c/ov02c10.c +++ b/drivers/media/i2c/ov02c10.c @@ -165,16 +165,12 @@ static const struct reg_sequence sensor_1928x1092_30fps_setting[] = { {0x3809, 0x88}, {0x380a, 0x04}, {0x380b, 0x44}, - {0x3810, 0x00}, - {0x3811, 0x02}, - {0x3812, 0x00}, - {0x3813, 0x02}, {0x3814, 0x01}, {0x3815, 0x01}, {0x3816, 0x01}, {0x3817, 0x01}, - {0x3820, 0xa0}, + {0x3820, 0xa8}, {0x3821, 0x00}, {0x3822, 0x80}, {0x3823, 0x08}, @@ -385,8 +381,6 @@ struct ov02c10 { struct v4l2_ctrl *vblank; struct v4l2_ctrl *hblank; struct v4l2_ctrl *exposure; - struct v4l2_ctrl *hflip; - struct v4l2_ctrl *vflip; struct clk *img_clk; struct gpio_desc *reset; @@ -465,13 +459,17 @@ static int ov02c10_set_ctrl(struct v4l2_ctrl *ctrl) break; case V4L2_CID_HFLIP: + cci_write(ov02c10->regmap, OV02C10_ISP_X_WIN_CONTROL, + ctrl->val ? 2 : 1, &ret); cci_update_bits(ov02c10->regmap, OV02C10_ROTATE_CONTROL, - BIT(3), ov02c10->hflip->val << 3, &ret); + BIT(3), ctrl->val ? 0 : BIT(3), &ret); break; case V4L2_CID_VFLIP: + cci_write(ov02c10->regmap, OV02C10_ISP_Y_WIN_CONTROL, + ctrl->val ? 2 : 1, &ret); cci_update_bits(ov02c10->regmap, OV02C10_ROTATE_CONTROL, - BIT(4), ov02c10->vflip->val << 4, &ret); + BIT(4), ctrl->val << 4, &ret); break; default: @@ -549,15 +547,11 @@ static int ov02c10_init_controls(struct ov02c10 *ov02c10) OV02C10_EXPOSURE_STEP, exposure_max); - ov02c10->hflip = v4l2_ctrl_new_std(ctrl_hdlr, &ov02c10_ctrl_ops, - V4L2_CID_HFLIP, 0, 1, 1, 0); - if (ov02c10->hflip) - ov02c10->hflip->flags |= V4L2_CTRL_FLAG_MODIFY_LAYOUT; + v4l2_ctrl_new_std(ctrl_hdlr, &ov02c10_ctrl_ops, V4L2_CID_HFLIP, + 0, 1, 1, 0); - ov02c10->vflip = v4l2_ctrl_new_std(ctrl_hdlr, &ov02c10_ctrl_ops, - V4L2_CID_VFLIP, 0, 1, 1, 0); - if (ov02c10->vflip) - ov02c10->vflip->flags |= V4L2_CTRL_FLAG_MODIFY_LAYOUT; + v4l2_ctrl_new_std(ctrl_hdlr, &ov02c10_ctrl_ops, V4L2_CID_VFLIP, + 0, 1, 1, 0); v4l2_ctrl_new_std_menu_items(ctrl_hdlr, &ov02c10_ctrl_ops, V4L2_CID_TEST_PATTERN, diff --git a/drivers/media/mc/mc-request.c b/drivers/media/mc/mc-request.c index 2ac9ac0a740b..3cca9a0c7c97 100644 --- a/drivers/media/mc/mc-request.c +++ b/drivers/media/mc/mc-request.c @@ -315,12 +315,12 @@ int media_request_alloc(struct media_device *mdev, int *alloc_fd) fd_prepare_file(fdf)->private_data = req; - *alloc_fd = fd_publish(fdf); - snprintf(req->debug_str, sizeof(req->debug_str), "%u:%d", - atomic_inc_return(&mdev->request_id), *alloc_fd); + atomic_inc_return(&mdev->request_id), fd_prepare_fd(fdf)); dev_dbg(mdev->dev, "request: allocated %s\n", req->debug_str); + *alloc_fd = fd_publish(fdf); + return 0; err_free_req: diff --git a/drivers/media/pci/intel/Kconfig b/drivers/media/pci/intel/Kconfig index d9fcddce028b..3f14ca110d06 100644 --- a/drivers/media/pci/intel/Kconfig +++ b/drivers/media/pci/intel/Kconfig @@ -6,7 +6,7 @@ source "drivers/media/pci/intel/ivsc/Kconfig" config IPU_BRIDGE tristate "Intel IPU Bridge" - depends on ACPI || COMPILE_TEST + depends on ACPI depends on I2C help The IPU bridge is a helper library for Intel IPU drivers to diff --git a/drivers/media/pci/intel/ipu-bridge.c b/drivers/media/pci/intel/ipu-bridge.c index c9827e9fe6ff..b2b710094914 100644 --- a/drivers/media/pci/intel/ipu-bridge.c +++ b/drivers/media/pci/intel/ipu-bridge.c @@ -5,6 +5,7 @@ #include <acpi/acpi_bus.h> #include <linux/cleanup.h> #include <linux/device.h> +#include <linux/dmi.h> #include <linux/i2c.h> #include <linux/mei_cl_bus.h> #include <linux/platform_device.h> @@ -98,6 +99,28 @@ static const struct ipu_sensor_config ipu_supported_sensors[] = { IPU_SENSOR_CONFIG("XMCC0003", 1, 321468000), }; +/* + * DMI matches for laptops which have their sensor mounted upside-down + * without reporting a rotation of 180° in neither the SSDB nor the _PLD. + */ +static const struct dmi_system_id upside_down_sensor_dmi_ids[] = { + { + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS 13 9350"), + }, + .driver_data = "OVTI02C1", + }, + { + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS 16 9640"), + }, + .driver_data = "OVTI02C1", + }, + {} /* Terminating entry */ +}; + static const struct ipu_property_names prop_names = { .clock_frequency = "clock-frequency", .rotation = "rotation", @@ -248,6 +271,12 @@ out_free_buff: static u32 ipu_bridge_parse_rotation(struct acpi_device *adev, struct ipu_sensor_ssdb *ssdb) { + const struct dmi_system_id *dmi_id; + + dmi_id = dmi_first_match(upside_down_sensor_dmi_ids); + if (dmi_id && acpi_dev_hid_match(adev, dmi_id->driver_data)) + return 180; + switch (ssdb->degree) { case IPU_SENSOR_ROTATION_NORMAL: return 0; diff --git a/drivers/media/platform/arm/mali-c55/mali-c55-params.c b/drivers/media/platform/arm/mali-c55/mali-c55-params.c index 082cda4f4f63..be0e909bcf29 100644 --- a/drivers/media/platform/arm/mali-c55/mali-c55-params.c +++ b/drivers/media/platform/arm/mali-c55/mali-c55-params.c @@ -582,13 +582,6 @@ static int mali_c55_params_buf_prepare(struct vb2_buffer *vb) struct mali_c55 *mali_c55 = params->mali_c55; int ret; - if (config->version != MALI_C55_PARAM_BUFFER_V1) { - dev_dbg(mali_c55->dev, - "Unsupported extensible format version: %u\n", - config->version); - return -EINVAL; - } - ret = v4l2_isp_params_validate_buffer_size(mali_c55->dev, vb, v4l2_isp_params_buffer_size(MALI_C55_PARAMS_MAX_SIZE)); if (ret) diff --git a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c index 0fbdae280fdc..6dc4b53607b4 100644 --- a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c +++ b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c @@ -96,13 +96,6 @@ #define VSRSTS_RETRIES 20 -#define RZG2L_CSI2_MIN_WIDTH 320 -#define RZG2L_CSI2_MIN_HEIGHT 240 -#define RZG2L_CSI2_MAX_WIDTH 2800 -#define RZG2L_CSI2_MAX_HEIGHT 4095 - -#define RZG2L_CSI2_DEFAULT_WIDTH RZG2L_CSI2_MIN_WIDTH -#define RZG2L_CSI2_DEFAULT_HEIGHT RZG2L_CSI2_MIN_HEIGHT #define RZG2L_CSI2_DEFAULT_FMT MEDIA_BUS_FMT_UYVY8_1X16 enum rzg2l_csi2_pads { @@ -137,6 +130,10 @@ struct rzg2l_csi2_info { int (*dphy_enable)(struct rzg2l_csi2 *csi2); int (*dphy_disable)(struct rzg2l_csi2 *csi2); bool has_system_clk; + unsigned int min_width; + unsigned int min_height; + unsigned int max_width; + unsigned int max_height; }; struct rzg2l_csi2_timings { @@ -418,6 +415,10 @@ static const struct rzg2l_csi2_info rzg2l_csi2_info = { .dphy_enable = rzg2l_csi2_dphy_enable, .dphy_disable = rzg2l_csi2_dphy_disable, .has_system_clk = true, + .min_width = 320, + .min_height = 240, + .max_width = 2800, + .max_height = 4095, }; static int rzg2l_csi2_dphy_setting(struct v4l2_subdev *sd, bool on) @@ -542,6 +543,10 @@ static const struct rzg2l_csi2_info rzv2h_csi2_info = { .dphy_enable = rzv2h_csi2_dphy_enable, .dphy_disable = rzv2h_csi2_dphy_disable, .has_system_clk = false, + .min_width = 320, + .min_height = 240, + .max_width = 4096, + .max_height = 4096, }; static int rzg2l_csi2_mipi_link_setting(struct v4l2_subdev *sd, bool on) @@ -631,6 +636,7 @@ static int rzg2l_csi2_set_format(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, struct v4l2_subdev_format *fmt) { + struct rzg2l_csi2 *csi2 = sd_to_csi2(sd); struct v4l2_mbus_framefmt *src_format; struct v4l2_mbus_framefmt *sink_format; @@ -653,9 +659,11 @@ static int rzg2l_csi2_set_format(struct v4l2_subdev *sd, sink_format->ycbcr_enc = fmt->format.ycbcr_enc; sink_format->quantization = fmt->format.quantization; sink_format->width = clamp_t(u32, fmt->format.width, - RZG2L_CSI2_MIN_WIDTH, RZG2L_CSI2_MAX_WIDTH); + csi2->info->min_width, + csi2->info->max_width); sink_format->height = clamp_t(u32, fmt->format.height, - RZG2L_CSI2_MIN_HEIGHT, RZG2L_CSI2_MAX_HEIGHT); + csi2->info->min_height, + csi2->info->max_height); fmt->format = *sink_format; /* propagate format to source pad */ @@ -668,9 +676,10 @@ static int rzg2l_csi2_init_state(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state) { struct v4l2_subdev_format fmt = { .pad = RZG2L_CSI2_SINK, }; + struct rzg2l_csi2 *csi2 = sd_to_csi2(sd); - fmt.format.width = RZG2L_CSI2_DEFAULT_WIDTH; - fmt.format.height = RZG2L_CSI2_DEFAULT_HEIGHT; + fmt.format.width = csi2->info->min_width; + fmt.format.height = csi2->info->min_height; fmt.format.field = V4L2_FIELD_NONE; fmt.format.code = RZG2L_CSI2_DEFAULT_FMT; fmt.format.colorspace = V4L2_COLORSPACE_SRGB; @@ -697,16 +706,18 @@ static int rzg2l_csi2_enum_frame_size(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_frame_size_enum *fse) { + struct rzg2l_csi2 *csi2 = sd_to_csi2(sd); + if (fse->index != 0) return -EINVAL; if (!rzg2l_csi2_code_to_fmt(fse->code)) return -EINVAL; - fse->min_width = RZG2L_CSI2_MIN_WIDTH; - fse->min_height = RZG2L_CSI2_MIN_HEIGHT; - fse->max_width = RZG2L_CSI2_MAX_WIDTH; - fse->max_height = RZG2L_CSI2_MAX_HEIGHT; + fse->min_width = csi2->info->min_width; + fse->min_height = csi2->info->min_height; + fse->max_width = csi2->info->max_width; + fse->max_height = csi2->info->max_height; return 0; } diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index a4f75dc36929..fa30899a5fa2 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -122,6 +122,8 @@ #define MEI_DEV_ID_WCL_P 0x4D70 /* Wildcat Lake P */ +#define MEI_DEV_ID_NVL_S 0x6E68 /* Nova Lake Point S */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/mei-trace.h b/drivers/misc/mei/mei-trace.h index 5312edbf5190..24fa321d88bd 100644 --- a/drivers/misc/mei/mei-trace.h +++ b/drivers/misc/mei/mei-trace.h @@ -21,18 +21,18 @@ TRACE_EVENT(mei_reg_read, TP_ARGS(dev, reg, offs, val), TP_STRUCT__entry( __string(dev, dev_name(dev)) - __field(const char *, reg) + __string(reg, reg) __field(u32, offs) __field(u32, val) ), TP_fast_assign( __assign_str(dev); - __entry->reg = reg; + __assign_str(reg); __entry->offs = offs; __entry->val = val; ), TP_printk("[%s] read %s:[%#x] = %#x", - __get_str(dev), __entry->reg, __entry->offs, __entry->val) + __get_str(dev), __get_str(reg), __entry->offs, __entry->val) ); TRACE_EVENT(mei_reg_write, @@ -40,18 +40,18 @@ TRACE_EVENT(mei_reg_write, TP_ARGS(dev, reg, offs, val), TP_STRUCT__entry( __string(dev, dev_name(dev)) - __field(const char *, reg) + __string(reg, reg) __field(u32, offs) __field(u32, val) ), TP_fast_assign( __assign_str(dev); - __entry->reg = reg; + __assign_str(reg); __entry->offs = offs; __entry->val = val; ), TP_printk("[%s] write %s[%#x] = %#x", - __get_str(dev), __entry->reg, __entry->offs, __entry->val) + __get_str(dev), __get_str(reg), __entry->offs, __entry->val) ); TRACE_EVENT(mei_pci_cfg_read, @@ -59,18 +59,18 @@ TRACE_EVENT(mei_pci_cfg_read, TP_ARGS(dev, reg, offs, val), TP_STRUCT__entry( __string(dev, dev_name(dev)) - __field(const char *, reg) + __string(reg, reg) __field(u32, offs) __field(u32, val) ), TP_fast_assign( __assign_str(dev); - __entry->reg = reg; + __assign_str(reg); __entry->offs = offs; __entry->val = val; ), TP_printk("[%s] pci cfg read %s:[%#x] = %#x", - __get_str(dev), __entry->reg, __entry->offs, __entry->val) + __get_str(dev), __get_str(reg), __entry->offs, __entry->val) ); #endif /* _MEI_TRACE_H_ */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 73cad914be9f..2a6e569558b9 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -129,6 +129,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_WCL_P, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_NVL_S, MEI_ME_PCH15_CFG)}, + /* required last entry */ {0, } }; diff --git a/drivers/misc/rp1/Kconfig b/drivers/misc/rp1/Kconfig index 5232e70d3079..2c13b3968b01 100644 --- a/drivers/misc/rp1/Kconfig +++ b/drivers/misc/rp1/Kconfig @@ -5,8 +5,7 @@ config MISC_RP1 tristate "RaspberryPi RP1 misc device" - depends on OF_IRQ && OF_OVERLAY && PCI_MSI && PCI_QUIRKS - select PCI_DYNAMIC_OF_NODES + depends on OF_IRQ && PCI_MSI help Support the RP1 peripheral chip found on Raspberry Pi 5 board. @@ -15,6 +14,3 @@ config MISC_RP1 The driver is responsible for enabling the DT node once the PCIe endpoint has been configured, and handling interrupts. - - This driver uses an overlay to load other drivers to support for - RP1 internal sub-devices. diff --git a/drivers/misc/rp1/Makefile b/drivers/misc/rp1/Makefile index 508b4cb05627..ab32b433d7ed 100644 --- a/drivers/misc/rp1/Makefile +++ b/drivers/misc/rp1/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_MISC_RP1) += rp1-pci.o -rp1-pci-objs := rp1_pci.o rp1-pci.dtbo.o +obj-$(CONFIG_MISC_RP1) += rp1_pci.o diff --git a/drivers/misc/rp1/rp1-pci.dtso b/drivers/misc/rp1/rp1-pci.dtso deleted file mode 100644 index eea826b36e02..000000000000 --- a/drivers/misc/rp1/rp1-pci.dtso +++ /dev/null @@ -1,25 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) - -/* - * The dts overlay is included from the dts directory so - * it can be possible to check it with CHECK_DTBS while - * also compile it from the driver source directory. - */ - -/dts-v1/; -/plugin/; - -/ { - fragment@0 { - target-path=""; - __overlay__ { - compatible = "pci1de4,1"; - #address-cells = <3>; - #size-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - - #include "arm64/broadcom/rp1-common.dtsi" - }; - }; -}; diff --git a/drivers/misc/rp1/rp1_pci.c b/drivers/misc/rp1/rp1_pci.c index a342bcc6164b..d210da84c30a 100644 --- a/drivers/misc/rp1/rp1_pci.c +++ b/drivers/misc/rp1/rp1_pci.c @@ -34,16 +34,11 @@ /* Interrupts */ #define RP1_INT_END 61 -/* Embedded dtbo symbols created by cmd_wrap_S_dtb in scripts/Makefile.lib */ -extern char __dtbo_rp1_pci_begin[]; -extern char __dtbo_rp1_pci_end[]; - struct rp1_dev { struct pci_dev *pdev; struct irq_domain *domain; struct irq_data *pcie_irqds[64]; void __iomem *bar1; - int ovcs_id; /* overlay changeset id */ bool level_triggered_irq[RP1_INT_END]; }; @@ -184,24 +179,13 @@ static void rp1_unregister_interrupts(struct pci_dev *pdev) static int rp1_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - u32 dtbo_size = __dtbo_rp1_pci_end - __dtbo_rp1_pci_begin; - void *dtbo_start = __dtbo_rp1_pci_begin; struct device *dev = &pdev->dev; struct device_node *rp1_node; - bool skip_ovl = true; struct rp1_dev *rp1; int err = 0; int i; - /* - * Either use rp1_nexus node if already present in DT, or - * set a flag to load it from overlay at runtime - */ - rp1_node = of_find_node_by_name(NULL, "rp1_nexus"); - if (!rp1_node) { - rp1_node = dev_of_node(dev); - skip_ovl = false; - } + rp1_node = dev_of_node(dev); if (!rp1_node) { dev_err(dev, "Missing of_node for device\n"); @@ -276,42 +260,29 @@ static int rp1_probe(struct pci_dev *pdev, const struct pci_device_id *id) rp1_chained_handle_irq, rp1); } - if (!skip_ovl) { - err = of_overlay_fdt_apply(dtbo_start, dtbo_size, &rp1->ovcs_id, - rp1_node); - if (err) - goto err_unregister_interrupts; - } - err = of_platform_default_populate(rp1_node, NULL, dev); if (err) { dev_err_probe(&pdev->dev, err, "Error populating devicetree\n"); - goto err_unload_overlay; + goto err_unregister_interrupts; } - if (skip_ovl) - of_node_put(rp1_node); + of_node_put(rp1_node); return 0; -err_unload_overlay: - of_overlay_remove(&rp1->ovcs_id); err_unregister_interrupts: rp1_unregister_interrupts(pdev); err_put_node: - if (skip_ovl) - of_node_put(rp1_node); + of_node_put(rp1_node); return err; } static void rp1_remove(struct pci_dev *pdev) { - struct rp1_dev *rp1 = pci_get_drvdata(pdev); struct device *dev = &pdev->dev; of_platform_depopulate(dev); - of_overlay_remove(&rp1->ovcs_id); rp1_unregister_interrupts(pdev); } diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index 42e7d2a2a90c..6d71355528d3 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -40,20 +40,34 @@ static int uacce_start_queue(struct uacce_queue *q) return 0; } -static int uacce_put_queue(struct uacce_queue *q) +static int uacce_stop_queue(struct uacce_queue *q) { struct uacce_device *uacce = q->uacce; - if ((q->state == UACCE_Q_STARTED) && uacce->ops->stop_queue) + if (q->state != UACCE_Q_STARTED) + return 0; + + if (uacce->ops->stop_queue) uacce->ops->stop_queue(q); - if ((q->state == UACCE_Q_INIT || q->state == UACCE_Q_STARTED) && - uacce->ops->put_queue) + q->state = UACCE_Q_INIT; + + return 0; +} + +static void uacce_put_queue(struct uacce_queue *q) +{ + struct uacce_device *uacce = q->uacce; + + uacce_stop_queue(q); + + if (q->state != UACCE_Q_INIT) + return; + + if (uacce->ops->put_queue) uacce->ops->put_queue(q); q->state = UACCE_Q_ZOMBIE; - - return 0; } static long uacce_fops_unl_ioctl(struct file *filep, @@ -80,7 +94,7 @@ static long uacce_fops_unl_ioctl(struct file *filep, ret = uacce_start_queue(q); break; case UACCE_CMD_PUT_Q: - ret = uacce_put_queue(q); + ret = uacce_stop_queue(q); break; default: if (uacce->ops->ioctl) @@ -214,8 +228,14 @@ static void uacce_vma_close(struct vm_area_struct *vma) } } +static int uacce_vma_mremap(struct vm_area_struct *area) +{ + return -EPERM; +} + static const struct vm_operations_struct uacce_vm_ops = { .close = uacce_vma_close, + .mremap = uacce_vma_mremap, }; static int uacce_fops_mmap(struct file *filep, struct vm_area_struct *vma) @@ -382,6 +402,9 @@ static ssize_t isolate_strategy_show(struct device *dev, struct device_attribute struct uacce_device *uacce = to_uacce_device(dev); u32 val; + if (!uacce->ops->isolate_err_threshold_read) + return -ENOENT; + val = uacce->ops->isolate_err_threshold_read(uacce); return sysfs_emit(buf, "%u\n", val); @@ -394,6 +417,9 @@ static ssize_t isolate_strategy_store(struct device *dev, struct device_attribut unsigned long val; int ret; + if (!uacce->ops->isolate_err_threshold_write) + return -ENOENT; + if (kstrtoul(buf, 0, &val) < 0) return -EINVAL; @@ -519,6 +545,8 @@ EXPORT_SYMBOL_GPL(uacce_alloc); */ int uacce_register(struct uacce_device *uacce) { + int ret; + if (!uacce) return -ENODEV; @@ -529,7 +557,11 @@ int uacce_register(struct uacce_device *uacce) uacce->cdev->ops = &uacce_fops; uacce->cdev->owner = THIS_MODULE; - return cdev_device_add(uacce->cdev, &uacce->dev); + ret = cdev_device_add(uacce->cdev, &uacce->dev); + if (ret) + uacce->cdev = NULL; + + return ret; } EXPORT_SYMBOL_GPL(uacce_register); diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index dc2587ff8519..4db3328f46df 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -1306,6 +1306,46 @@ out: return err; } +static int sdmmc_card_busy(struct mmc_host *mmc) +{ + struct realtek_pci_sdmmc *host = mmc_priv(mmc); + struct rtsx_pcr *pcr = host->pcr; + int err; + u8 stat; + u8 mask = SD_DAT3_STATUS | SD_DAT2_STATUS | SD_DAT1_STATUS + | SD_DAT0_STATUS; + + mutex_lock(&pcr->pcr_mutex); + + rtsx_pci_start_run(pcr); + + err = rtsx_pci_write_register(pcr, SD_BUS_STAT, + SD_CLK_TOGGLE_EN | SD_CLK_FORCE_STOP, + SD_CLK_TOGGLE_EN); + if (err) + goto out; + + mdelay(1); + + err = rtsx_pci_read_register(pcr, SD_BUS_STAT, &stat); + if (err) + goto out; + + err = rtsx_pci_write_register(pcr, SD_BUS_STAT, + SD_CLK_TOGGLE_EN | SD_CLK_FORCE_STOP, 0); +out: + mutex_unlock(&pcr->pcr_mutex); + + if (err) + return err; + + /* check if any pin between dat[0:3] is low */ + if ((stat & mask) != mask) + return 1; + else + return 0; +} + static int sdmmc_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct realtek_pci_sdmmc *host = mmc_priv(mmc); @@ -1418,6 +1458,7 @@ static const struct mmc_host_ops realtek_pci_sdmmc_ops = { .get_ro = sdmmc_get_ro, .get_cd = sdmmc_get_cd, .start_signal_voltage_switch = sdmmc_switch_voltage, + .card_busy = sdmmc_card_busy, .execute_tuning = sdmmc_execute_tuning, .init_sd_express = sdmmc_init_sd_express, }; diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index 51949cde0958..2b75a36c096b 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -739,6 +739,13 @@ static void dwcmshc_rk3568_set_clock(struct sdhci_host *host, unsigned int clock sdhci_writel(host, extra, reg); if (clock <= 52000000) { + if (host->mmc->ios.timing == MMC_TIMING_MMC_HS200 || + host->mmc->ios.timing == MMC_TIMING_MMC_HS400) { + dev_err(mmc_dev(host->mmc), + "Can't reduce the clock below 52MHz in HS200/HS400 mode"); + return; + } + /* * Disable DLL and reset both of sample and drive clock. * The bypass bit and start bit need to be set if DLL is not locked. @@ -1588,6 +1595,7 @@ static int eic7700_init(struct device *dev, struct sdhci_host *host, struct dwcm { u32 emmc_caps = MMC_CAP2_NO_SD | MMC_CAP2_NO_SDIO; unsigned int val, hsp_int_status, hsp_pwr_ctrl; + static const char * const clk_ids[] = {"axi"}; struct of_phandle_args args; struct eic7700_priv *priv; struct regmap *hsp_regmap; @@ -1605,6 +1613,11 @@ static int eic7700_init(struct device *dev, struct sdhci_host *host, struct dwcm return ret; } + ret = dwcmshc_get_enable_other_clks(mmc_dev(host->mmc), dwc_priv, + ARRAY_SIZE(clk_ids), clk_ids); + if (ret) + return ret; + ret = of_parse_phandle_with_fixed_args(dev->of_node, "eswin,hsp-sp-csr", 2, 0, &args); if (ret) { dev_err(dev, "Fail to parse 'eswin,hsp-sp-csr' phandle (%d)\n", ret); @@ -1726,6 +1739,7 @@ static const struct sdhci_ops sdhci_dwcmshc_eic7700_ops = { .set_uhs_signaling = sdhci_eic7700_set_uhs_wrapper, .set_power = sdhci_set_power_and_bus_voltage, .irq = dwcmshc_cqe_irq_handler, + .adma_write_desc = dwcmshc_adma_write_desc, .platform_execute_tuning = sdhci_eic7700_executing_tuning, }; diff --git a/drivers/mtd/nand/ecc-sw-hamming.c b/drivers/mtd/nand/ecc-sw-hamming.c index f2d0effad9d2..bc62a71f9fdd 100644 --- a/drivers/mtd/nand/ecc-sw-hamming.c +++ b/drivers/mtd/nand/ecc-sw-hamming.c @@ -8,7 +8,7 @@ * * Completely replaces the previous ECC implementation which was written by: * Steven J. Hill (sjhill@realitydiluted.com) - * Thomas Gleixner (tglx@linutronix.de) + * Thomas Gleixner (tglx@kernel.org) * * Information on how this algorithm works and how it was developed * can be found in Documentation/driver-api/mtd/nand_ecc.rst diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 70d6c2250f32..540b6baf8bb1 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -11,7 +11,7 @@ * Error correction code lifted from the old docecc code * Author: Fabrice Bellard (fabrice.bellard@netgem.com) * Copyright (C) 2000 Netgem S.A. - * converted to the generic Reed-Solomon library by Thomas Gleixner <tglx@linutronix.de> + * converted to the generic Reed-Solomon library by Thomas Gleixner <tglx@kernel.org> * * Interface to generic NAND code for M-Systems DiskOnChip devices */ diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index ad6d66309597..f2322de93ab4 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -8,7 +8,7 @@ * http://www.linux-mtd.infradead.org/doc/nand.html * * Copyright (C) 2000 Steven J. Hill (sjhill@realitydiluted.com) - * 2002-2006 Thomas Gleixner (tglx@linutronix.de) + * 2002-2006 Thomas Gleixner (tglx@kernel.org) * * Credits: * David Woodhouse for adding multichip support @@ -6594,5 +6594,5 @@ EXPORT_SYMBOL_GPL(nand_cleanup); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steven J. Hill <sjhill@realitydiluted.com>"); -MODULE_AUTHOR("Thomas Gleixner <tglx@linutronix.de>"); +MODULE_AUTHOR("Thomas Gleixner <tglx@kernel.org>"); MODULE_DESCRIPTION("Generic NAND flash driver code"); diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c index a8fba5f39f59..3050ab7e6eb6 100644 --- a/drivers/mtd/nand/raw/nand_bbt.c +++ b/drivers/mtd/nand/raw/nand_bbt.c @@ -3,7 +3,7 @@ * Overview: * Bad block table support for the NAND driver * - * Copyright © 2004 Thomas Gleixner (tglx@linutronix.de) + * Copyright © 2004 Thomas Gleixner (tglx@kernel.org) * * Description: * diff --git a/drivers/mtd/nand/raw/nand_ids.c b/drivers/mtd/nand/raw/nand_ids.c index 650351c62af6..62a8cf86d9e2 100644 --- a/drivers/mtd/nand/raw/nand_ids.c +++ b/drivers/mtd/nand/raw/nand_ids.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2002 Thomas Gleixner (tglx@linutronix.de) + * Copyright (C) 2002 Thomas Gleixner (tglx@kernel.org) */ #include <linux/sizes.h> diff --git a/drivers/mtd/nand/raw/nand_jedec.c b/drivers/mtd/nand/raw/nand_jedec.c index b3cc8f360529..89e6dd8ed1a8 100644 --- a/drivers/mtd/nand/raw/nand_jedec.c +++ b/drivers/mtd/nand/raw/nand_jedec.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2000 Steven J. Hill (sjhill@realitydiluted.com) - * 2002-2006 Thomas Gleixner (tglx@linutronix.de) + * 2002-2006 Thomas Gleixner (tglx@kernel.org) * * Credits: * David Woodhouse for adding multichip support diff --git a/drivers/mtd/nand/raw/nand_legacy.c b/drivers/mtd/nand/raw/nand_legacy.c index 743792edf98d..97700f80d5b8 100644 --- a/drivers/mtd/nand/raw/nand_legacy.c +++ b/drivers/mtd/nand/raw/nand_legacy.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2000 Steven J. Hill (sjhill@realitydiluted.com) - * 2002-2006 Thomas Gleixner (tglx@linutronix.de) + * 2002-2006 Thomas Gleixner (tglx@kernel.org) * * Credits: * David Woodhouse for adding multichip support diff --git a/drivers/mtd/nand/raw/nand_onfi.c b/drivers/mtd/nand/raw/nand_onfi.c index 861975e44b55..11954440e4de 100644 --- a/drivers/mtd/nand/raw/nand_onfi.c +++ b/drivers/mtd/nand/raw/nand_onfi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2000 Steven J. Hill (sjhill@realitydiluted.com) - * 2002-2006 Thomas Gleixner (tglx@linutronix.de) + * 2002-2006 Thomas Gleixner (tglx@kernel.org) * * Credits: * David Woodhouse for adding multichip support diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c index 13365128194d..7ad8bc04be1a 100644 --- a/drivers/mtd/nand/raw/ndfc.c +++ b/drivers/mtd/nand/raw/ndfc.c @@ -272,5 +272,5 @@ static struct platform_driver ndfc_driver = { module_platform_driver(ndfc_driver); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Thomas Gleixner <tglx@linutronix.de>"); +MODULE_AUTHOR("Thomas Gleixner <tglx@kernel.org>"); MODULE_DESCRIPTION("OF Platform driver for NDFC"); diff --git a/drivers/mtd/nand/spi/esmt.c b/drivers/mtd/nand/spi/esmt.c index e60e4ac1fd6f..3e86f346f751 100644 --- a/drivers/mtd/nand/spi/esmt.c +++ b/drivers/mtd/nand/spi/esmt.c @@ -215,7 +215,7 @@ static const struct spinand_info esmt_c8_spinand_table[] = { SPINAND_FACT_OTP_INFO(2, 0, &f50l1g41lb_fact_otp_ops)), SPINAND_INFO("F50D1G41LB", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0x11, 0x7f, - 0x7f), + 0x7f, 0x7f), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), NAND_ECCREQ(1, 512), SPINAND_INFO_OP_VARIANTS(&read_cache_variants, diff --git a/drivers/mux/mmio.c b/drivers/mux/mmio.c index e4ddb1e61923..3409af1ffb80 100644 --- a/drivers/mux/mmio.c +++ b/drivers/mux/mmio.c @@ -101,13 +101,13 @@ static int mux_mmio_probe(struct platform_device *pdev) mux_mmio = mux_chip_priv(mux_chip); mux_mmio->fields = devm_kmalloc(dev, num_fields * sizeof(*mux_mmio->fields), GFP_KERNEL); - if (IS_ERR(mux_mmio->fields)) - return PTR_ERR(mux_mmio->fields); + if (!mux_mmio->fields) + return -ENOMEM; mux_mmio->hardware_states = devm_kmalloc(dev, num_fields * sizeof(*mux_mmio->hardware_states), GFP_KERNEL); - if (IS_ERR(mux_mmio->hardware_states)) - return PTR_ERR(mux_mmio->hardware_states); + if (!mux_mmio->hardware_states) + return -ENOMEM; for (i = 0; i < num_fields; i++) { struct mux_control *mux = &mux_chip->mux[i]; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 3d56339a8a10..45bd2bb102ff 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1862,6 +1862,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, */ if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { + if (slave_dev->type != ARPHRD_ETHER && + BOND_MODE(bond) == BOND_MODE_8023AD) { + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "8023AD mode requires Ethernet devices"); + return -EINVAL; + } slave_dbg(bond_dev, slave_dev, "change device type from %d to %d\n", bond_dev->type, slave_dev->type); @@ -2196,11 +2202,6 @@ skip_mac_set: unblock_netpoll_tx(); } - /* broadcast mode uses the all_slaves to loop through slaves. */ - if (bond_mode_can_use_xmit_hash(bond) || - BOND_MODE(bond) == BOND_MODE_BROADCAST) - bond_update_slave_arr(bond, NULL); - if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { if (bond->xdp_prog) { @@ -2234,6 +2235,11 @@ skip_mac_set: bpf_prog_inc(bond->xdp_prog); } + /* broadcast mode uses the all_slaves to loop through slaves. */ + if (bond_mode_can_use_xmit_hash(bond) || + BOND_MODE(bond) == BOND_MODE_BROADCAST) + bond_update_slave_arr(bond, NULL); + bond_xdp_set_features(bond_dev); slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", @@ -3041,8 +3047,8 @@ static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 __func__, &sip); return; } - slave->last_rx = jiffies; - slave->target_last_arp_rx[i] = jiffies; + WRITE_ONCE(slave->last_rx, jiffies); + WRITE_ONCE(slave->target_last_arp_rx[i], jiffies); } static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, @@ -3261,8 +3267,8 @@ static void bond_validate_na(struct bonding *bond, struct slave *slave, __func__, saddr); return; } - slave->last_rx = jiffies; - slave->target_last_arp_rx[i] = jiffies; + WRITE_ONCE(slave->last_rx, jiffies); + WRITE_ONCE(slave->target_last_arp_rx[i], jiffies); } static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, @@ -3332,7 +3338,7 @@ int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, (slave_do_arp_validate_only(bond) && is_ipv6) || #endif !slave_do_arp_validate_only(bond)) - slave->last_rx = jiffies; + WRITE_ONCE(slave->last_rx, jiffies); return RX_HANDLER_ANOTHER; } else if (is_arp) { return bond_arp_rcv(skb, bond, slave); @@ -3400,7 +3406,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_tx, 1) && - bond_time_in_interval(bond, slave->last_rx, 1)) { + bond_time_in_interval(bond, READ_ONCE(slave->last_rx), 1)) { bond_propose_link_state(slave, BOND_LINK_UP); slave_state_changed = 1; @@ -3424,8 +3430,10 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || - !bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) { + if (!bond_time_in_interval(bond, last_tx, + bond->params.missed_max) || + !bond_time_in_interval(bond, READ_ONCE(slave->last_rx), + bond->params.missed_max)) { bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; @@ -4090,8 +4098,9 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const v case BOND_XMIT_POLICY_ENCAP23: case BOND_XMIT_POLICY_ENCAP34: memset(fk, 0, sizeof(*fk)); - return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, - fk, data, l2_proto, nhoff, hlen, 0); + return __skb_flow_dissect(dev_net(bond->dev), skb, + &flow_keys_bonding, fk, data, + l2_proto, nhoff, hlen, 0); default: break; } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 384499c869b8..f1c6e9d8f616 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1152,7 +1152,7 @@ static void _bond_options_arp_ip_target_set(struct bonding *bond, int slot, if (slot >= 0 && slot < BOND_MAX_ARP_TARGETS) { bond_for_each_slave(bond, slave, iter) - slave->target_last_arp_rx[slot] = last_rx; + WRITE_ONCE(slave->target_last_arp_rx[slot], last_rx); targets[slot] = target; } } @@ -1221,8 +1221,8 @@ static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target) bond_for_each_slave(bond, slave, iter) { targets_rx = slave->target_last_arp_rx; for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++) - targets_rx[i] = targets_rx[i+1]; - targets_rx[i] = 0; + WRITE_ONCE(targets_rx[i], READ_ONCE(targets_rx[i+1])); + WRITE_ONCE(targets_rx[i], 0); } for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++) targets[i] = targets[i+1]; @@ -1377,7 +1377,7 @@ static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) { bond_for_each_slave(bond, slave, iter) { - slave->target_last_arp_rx[slot] = last_rx; + WRITE_ONCE(slave->target_last_arp_rx[slot], last_rx); slave_set_ns_maddr(bond, slave, target, &targets[slot]); } targets[slot] = *target; diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index cfaea6178a71..e15e320db476 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menuconfig CAN_DEV - bool "CAN Device Drivers" + tristate "CAN Device Drivers" default y depends on CAN help @@ -17,7 +17,10 @@ menuconfig CAN_DEV virtual ones. If you own such devices or plan to use the virtual CAN interfaces to develop applications, say Y here. -if CAN_DEV && CAN + To compile as a module, choose M here: the module will be called + can-dev. + +if CAN_DEV config CAN_VCAN tristate "Virtual Local CAN Interface (vcan)" diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index 37e2f1a2faec..d7bc10a6b8ea 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_CAN_VCAN) += vcan.o obj-$(CONFIG_CAN_VXCAN) += vxcan.o obj-$(CONFIG_CAN_SLCAN) += slcan/ -obj-$(CONFIG_CAN_DEV) += dev/ +obj-y += dev/ obj-y += esd/ obj-y += rcar/ obj-y += rockchip/ diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index c2a3a4eef5b2..58da323f14d7 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -1099,7 +1099,7 @@ static int at91_can_probe(struct platform_device *pdev) if (IS_ERR(transceiver)) { err = PTR_ERR(transceiver); dev_err_probe(&pdev->dev, err, "failed to get phy\n"); - goto exit_iounmap; + goto exit_free; } dev->netdev_ops = &at91_netdev_ops; diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index 1e6b9e3dc2fe..0ea1ff28dfce 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -310,7 +310,7 @@ static int ctucan_set_secondary_sample_point(struct net_device *ndev) } ssp_cfg = FIELD_PREP(REG_TRV_DELAY_SSP_OFFSET, ssp_offset); - ssp_cfg |= FIELD_PREP(REG_TRV_DELAY_SSP_SRC, 0x1); + ssp_cfg |= FIELD_PREP(REG_TRV_DELAY_SSP_SRC, 0x0); } ctucan_write32(priv, CTUCANFD_TRV_DELAY, ssp_cfg); diff --git a/drivers/net/can/dev/Makefile b/drivers/net/can/dev/Makefile index 64226acf0f3d..633687d6b6c0 100644 --- a/drivers/net/can/dev/Makefile +++ b/drivers/net/can/dev/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_CAN) += can-dev.o +obj-$(CONFIG_CAN_DEV) += can-dev.o + +can-dev-y += skb.o -can-dev-$(CONFIG_CAN_DEV) += skb.o can-dev-$(CONFIG_CAN_CALC_BITTIMING) += calc_bittiming.o can-dev-$(CONFIG_CAN_NETLINK) += bittiming.o can-dev-$(CONFIG_CAN_NETLINK) += dev.o diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 091f30e94c61..769745e22a3c 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -332,6 +332,7 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, can_ml = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); can_set_ml_priv(dev, can_ml); + can_set_cap(dev, CAN_CAP_CC); if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; @@ -375,6 +376,32 @@ void can_set_default_mtu(struct net_device *dev) } } +void can_set_cap_info(struct net_device *dev) +{ + struct can_priv *priv = netdev_priv(dev); + u32 can_cap; + + if (can_dev_in_xl_only_mode(priv)) { + /* XL only mode => no CC/FD capability */ + can_cap = CAN_CAP_XL; + } else { + /* mixed mode => CC + FD/XL capability */ + can_cap = CAN_CAP_CC; + + if (priv->ctrlmode & CAN_CTRLMODE_FD) + can_cap |= CAN_CAP_FD; + + if (priv->ctrlmode & CAN_CTRLMODE_XL) + can_cap |= CAN_CAP_XL; + } + + if (priv->ctrlmode & (CAN_CTRLMODE_LISTENONLY | + CAN_CTRLMODE_RESTRICTED)) + can_cap |= CAN_CAP_RO; + + can_set_cap(dev, can_cap); +} + /* helper to define static CAN controller features at device creation time */ int can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) { @@ -390,6 +417,7 @@ int can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) /* override MTU which was set by default in can_setup()? */ can_set_default_mtu(dev); + can_set_cap_info(dev); return 0; } diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index d6b0e686fb11..0498198a4696 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -377,6 +377,7 @@ static int can_ctrlmode_changelink(struct net_device *dev, } can_set_default_mtu(dev); + can_set_cap_info(dev); return 0; } diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index de8e212a1366..4c219a5b139b 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -486,11 +486,17 @@ resubmit_urb: urb->transfer_buffer, RX_BUFFER_SIZE, ems_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 08da507faef4..8cc924c47042 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -541,13 +541,20 @@ resubmit_urb: urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + err = usb_submit_urb(urb, GFP_ATOMIC); + if (!err) + return; + + usb_unanchor_urb(urb); + if (err == -ENODEV) { for (i = 0; i < dev->net_count; i++) { if (dev->nets[i]) netif_device_detach(dev->nets[i]->netdev); } - } else if (err) { + } else { dev_err(dev->udev->dev.parent, "failed resubmitting read bulk urb: %pe\n", ERR_PTR(err)); } diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index f799233c2b72..2d248deb69dc 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1736,7 +1736,7 @@ static int es58x_alloc_rx_urbs(struct es58x_device *es58x_dev) dev_dbg(dev, "%s: Allocated %d rx URBs each of size %u\n", __func__, i, rx_buf_len); - return ret; + return 0; } /** diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index a0233e550a5a..d8b2dd74b3a1 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -610,7 +610,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) { struct gs_usb *parent = urb->context; struct gs_can *dev; - struct net_device *netdev; + struct net_device *netdev = NULL; int rc; struct net_device_stats *stats; struct gs_host_frame *hf = urb->transfer_buffer; @@ -751,7 +751,13 @@ resubmit_urb: hf, parent->hf_size_rx, gs_usb_receive_bulk_callback, parent); + usb_anchor_urb(urb, &parent->rx_submitted); + rc = usb_submit_urb(urb, GFP_ATOMIC); + if (!rc) + return; + + usb_unanchor_urb(urb); /* USB failure take down all interfaces */ if (rc == -ENODEV) { @@ -760,6 +766,9 @@ device_detach: if (parent->canch[rc]) netif_device_detach(parent->canch[rc]->netdev); } + } else if (rc != -ESHUTDOWN && net_ratelimit()) { + netdev_info(netdev, "failed to re-submit IN URB: %pe\n", + ERR_PTR(rc)); } } 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 62701ec34272..d0a2a2a33c1c 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -361,7 +361,14 @@ resubmit_urb: urb->transfer_buffer, KVASER_USB_RX_BUFFER_SIZE, kvaser_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + err = usb_submit_urb(urb, GFP_ATOMIC); + if (!err) + return; + + usb_unanchor_urb(urb); + if (err == -ENODEV) { for (i = 0; i < dev->nchannels; i++) { struct kvaser_usb_net_priv *priv; @@ -372,7 +379,7 @@ resubmit_urb: netif_device_detach(priv->netdev); } - } else if (err) { + } else { dev_err(&dev->intf->dev, "Failed resubmitting read bulk urb: %d\n", err); } diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 41c0a1c399bf..04170326dc7e 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -608,11 +608,17 @@ resubmit_urb: urb->transfer_buffer, MCBA_USB_RX_BUFF_SIZE, mcba_usb_read_bulk_callback, priv); + usb_anchor_urb(urb, &priv->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index 7449328f7cd7..3125cf59d002 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -541,11 +541,17 @@ resubmit_urb: urb->transfer_buffer, RX_BUFFER_SIZE, usb_8dev_read_bulk_callback, priv); + usb_anchor_urb(urb, &priv->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index fdc662aea279..76e6b7b5c6a1 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -130,6 +130,19 @@ static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +static void vcan_set_cap_info(struct net_device *dev) +{ + u32 can_cap = CAN_CAP_CC; + + if (dev->mtu > CAN_MTU) + can_cap |= CAN_CAP_FD; + + if (dev->mtu >= CANXL_MIN_MTU) + can_cap |= CAN_CAP_XL; + + can_set_cap(dev, can_cap); +} + static int vcan_change_mtu(struct net_device *dev, int new_mtu) { /* Do not allow changing the MTU while running */ @@ -141,6 +154,7 @@ static int vcan_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; WRITE_ONCE(dev->mtu, new_mtu); + vcan_set_cap_info(dev); return 0; } @@ -162,6 +176,7 @@ static void vcan_setup(struct net_device *dev) dev->tx_queue_len = 0; dev->flags = IFF_NOARP; can_set_ml_priv(dev, netdev_priv(dev)); + vcan_set_cap_info(dev); /* set flags according to driver capabilities */ if (echo) diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index b2c19f8c5f8e..f14c6f02b662 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -125,6 +125,19 @@ static int vxcan_get_iflink(const struct net_device *dev) return iflink; } +static void vxcan_set_cap_info(struct net_device *dev) +{ + u32 can_cap = CAN_CAP_CC; + + if (dev->mtu > CAN_MTU) + can_cap |= CAN_CAP_FD; + + if (dev->mtu >= CANXL_MIN_MTU) + can_cap |= CAN_CAP_XL; + + can_set_cap(dev, can_cap); +} + static int vxcan_change_mtu(struct net_device *dev, int new_mtu) { /* Do not allow changing the MTU while running */ @@ -136,6 +149,7 @@ static int vxcan_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; WRITE_ONCE(dev->mtu, new_mtu); + vxcan_set_cap_info(dev); return 0; } @@ -167,6 +181,7 @@ static void vxcan_setup(struct net_device *dev) can_ml = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN); can_set_ml_priv(dev, can_ml); + vxcan_set_cap_info(dev); } /* forward declaration for rtnl_create_link() */ diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index a1a177713d99..2c4131ed7e30 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -2169,6 +2169,9 @@ static int b53_fdb_copy(int port, const struct b53_arl_entry *ent, if (!ent->is_valid) return 0; + if (is_multicast_ether_addr(ent->mac)) + return 0; + if (port != ent->port) return 0; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index b4d48997bf46..09002c853b78 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3364,13 +3364,10 @@ static int mv88e6xxx_setup_upstream_port(struct mv88e6xxx_chip *chip, int port) static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) { - struct device_node *phy_handle = NULL; struct fwnode_handle *ports_fwnode; struct fwnode_handle *port_fwnode; struct dsa_switch *ds = chip->ds; struct mv88e6xxx_port *p; - struct dsa_port *dp; - int tx_amp; int err; u16 reg; u32 val; @@ -3582,23 +3579,6 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } - if (chip->info->ops->serdes_set_tx_amplitude) { - dp = dsa_to_port(ds, port); - if (dp) - phy_handle = of_parse_phandle(dp->dn, "phy-handle", 0); - - if (phy_handle && !of_property_read_u32(phy_handle, - "tx-p2p-microvolt", - &tx_amp)) - err = chip->info->ops->serdes_set_tx_amplitude(chip, - port, tx_amp); - if (phy_handle) { - of_node_put(phy_handle); - if (err) - return err; - } - } - /* Port based VLAN map: give each port the same default address * database, and allow bidirectional communication between the * CPU and DSA port(s), and the other ports. @@ -4768,7 +4748,6 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .serdes_irq_mapping = mv88e6352_serdes_irq_mapping, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, - .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, .gpio_ops = &mv88e6352_gpio_ops, .phylink_get_caps = mv88e6352_phylink_get_caps, .pcs_ops = &mv88e6352_pcs_ops, @@ -5044,7 +5023,6 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .serdes_irq_mapping = mv88e6352_serdes_irq_mapping, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, - .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, @@ -5481,7 +5459,6 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .serdes_get_stats = mv88e6352_serdes_get_stats, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, - .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, .phylink_get_caps = mv88e6352_phylink_get_caps, .pcs_ops = &mv88e6352_pcs_ops, }; diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 2f211e55cb47..e073446ee7d0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -642,10 +642,6 @@ struct mv88e6xxx_ops { void (*serdes_get_regs)(struct mv88e6xxx_chip *chip, int port, void *_p); - /* SERDES SGMII/Fiber Output Amplitude */ - int (*serdes_set_tx_amplitude)(struct mv88e6xxx_chip *chip, int port, - int val); - /* Address Translation Unit operations */ int (*atu_get_hash)(struct mv88e6xxx_chip *chip, u8 *hash); int (*atu_set_hash)(struct mv88e6xxx_chip *chip, u8 hash); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index b3330211edbc..a936ee80ce00 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -25,14 +25,6 @@ static int mv88e6352_serdes_read(struct mv88e6xxx_chip *chip, int reg, reg, val); } -static int mv88e6352_serdes_write(struct mv88e6xxx_chip *chip, int reg, - u16 val) -{ - return mv88e6xxx_phy_page_write(chip, MV88E6352_ADDR_SERDES, - MV88E6352_SERDES_PAGE_FIBER, - reg, val); -} - static int mv88e6390_serdes_read(struct mv88e6xxx_chip *chip, int lane, int device, int reg, u16 *val) { @@ -506,41 +498,3 @@ void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p) p[i] = reg; } } - -static const int mv88e6352_serdes_p2p_to_reg[] = { - /* Index of value in microvolts corresponds to the register value */ - 14000, 112000, 210000, 308000, 406000, 504000, 602000, 700000, -}; - -int mv88e6352_serdes_set_tx_amplitude(struct mv88e6xxx_chip *chip, int port, - int val) -{ - bool found = false; - u16 ctrl, reg; - int err; - int i; - - err = mv88e6352_g2_scratch_port_has_serdes(chip, port); - if (err <= 0) - return err; - - for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_p2p_to_reg); ++i) { - if (mv88e6352_serdes_p2p_to_reg[i] == val) { - reg = i; - found = true; - break; - } - } - - if (!found) - return -EINVAL; - - err = mv88e6352_serdes_read(chip, MV88E6352_SERDES_SPEC_CTRL2, &ctrl); - if (err) - return err; - - ctrl &= ~MV88E6352_SERDES_OUT_AMP_MASK; - ctrl |= reg; - - return mv88e6352_serdes_write(chip, MV88E6352_SERDES_SPEC_CTRL2, ctrl); -} diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index ad887d8601bc..17a3e85fabaa 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -29,8 +29,6 @@ struct phylink_link_state; #define MV88E6352_SERDES_INT_FIBRE_ENERGY BIT(4) #define MV88E6352_SERDES_INT_STATUS 0x13 -#define MV88E6352_SERDES_SPEC_CTRL2 0x1a -#define MV88E6352_SERDES_OUT_AMP_MASK 0x0007 #define MV88E6341_PORT5_LANE 0x15 @@ -140,9 +138,6 @@ void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); int mv88e6390_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port); void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); -int mv88e6352_serdes_set_tx_amplitude(struct mv88e6xxx_chip *chip, int port, - int val); - /* Return the (first) SERDES lane address a port is using, -errno otherwise. */ static inline int mv88e6xxx_serdes_get_lane(struct mv88e6xxx_chip *chip, int port) diff --git a/drivers/net/dsa/yt921x.c b/drivers/net/dsa/yt921x.c index 1c511f5dc6ab..7b8c1549a0fb 100644 --- a/drivers/net/dsa/yt921x.c +++ b/drivers/net/dsa/yt921x.c @@ -682,21 +682,22 @@ static int yt921x_read_mib(struct yt921x_priv *priv, int port) const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i]; u32 reg = YT921X_MIBn_DATA0(port) + desc->offset; u64 *valp = &((u64 *)mib)[i]; - u64 val = *valp; u32 val0; - u32 val1; + u64 val; res = yt921x_reg_read(priv, reg, &val0); if (res) break; if (desc->size <= 1) { - if (val < (u32)val) - /* overflow */ - val += (u64)U32_MAX + 1; - val &= ~U32_MAX; - val |= val0; + u64 old_val = *valp; + + val = (old_val & ~(u64)U32_MAX) | val0; + if (val < old_val) + val += 1ull << 32; } else { + u32 val1; + res = yt921x_reg_read(priv, reg + 4, &val1); if (res) break; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 8c9cc97efd4e..4fe4efdb3737 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -1473,7 +1473,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq, return 0; free_ring: - dma_free_coherent(&pdev->dev, + dma_free_coherent(gendev, sizeof(struct boom_rx_desc) * RX_RING_SIZE + sizeof(struct boom_tx_desc) * TX_RING_SIZE, vp->rx_ring, vp->rx_ring_dma); diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 75893c90a0a1..315d97036ac1 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -2924,19 +2924,26 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, port->id = id; eth->ports[p] = port; - err = airoha_metadata_dst_alloc(port); - if (err) - return err; + return airoha_metadata_dst_alloc(port); +} - err = register_netdev(dev); - if (err) - goto free_metadata_dst; +static int airoha_register_gdm_devices(struct airoha_eth *eth) +{ + int i; - return 0; + for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { + struct airoha_gdm_port *port = eth->ports[i]; + int err; -free_metadata_dst: - airoha_metadata_dst_free(port); - return err; + if (!port) + continue; + + err = register_netdev(port->dev); + if (err) + return err; + } + + return 0; } static int airoha_probe(struct platform_device *pdev) @@ -3027,6 +3034,10 @@ static int airoha_probe(struct platform_device *pdev) } } + err = airoha_register_gdm_devices(eth); + if (err) + goto error_napi_stop; + return 0; error_napi_stop: @@ -3040,10 +3051,12 @@ error_hw_cleanup: for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; - if (port && port->dev->reg_state == NETREG_REGISTERED) { + if (!port) + continue; + + if (port->dev->reg_state == NETREG_REGISTERED) unregister_netdev(port->dev); - airoha_metadata_dst_free(port); - } + airoha_metadata_dst_free(port); } free_netdev(eth->napi_dev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 0caabb0c3aa0..2221bafaf7c9 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -1547,13 +1547,16 @@ void airoha_ppe_deinit(struct airoha_eth *eth) { struct airoha_npu *npu; - rcu_read_lock(); - npu = rcu_dereference(eth->npu); + mutex_lock(&flow_offload_mutex); + + npu = rcu_replace_pointer(eth->npu, NULL, + lockdep_is_held(&flow_offload_mutex)); if (npu) { npu->ops.ppe_deinit(npu); airoha_npu_put(npu); } - rcu_read_unlock(); + + mutex_unlock(&flow_offload_mutex); rhashtable_destroy(ð->ppe->l2_flows); rhashtable_destroy(ð->flow_table); diff --git a/drivers/net/ethernet/amazon/ena/ena_devlink.c b/drivers/net/ethernet/amazon/ena/ena_devlink.c index ac81c24016dd..4772185e669d 100644 --- a/drivers/net/ethernet/amazon/ena/ena_devlink.c +++ b/drivers/net/ethernet/amazon/ena/ena_devlink.c @@ -53,10 +53,12 @@ void ena_devlink_disable_phc_param(struct devlink *devlink) { union devlink_param_value value; + devl_lock(devlink); value.vbool = false; devl_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, value); + devl_unlock(devlink); } static void ena_devlink_port_register(struct devlink *devlink) @@ -145,10 +147,12 @@ static int ena_devlink_configure_params(struct devlink *devlink) return rc; } + devl_lock(devlink); value.vbool = ena_phc_is_enabled(adapter); devl_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, value); + devl_unlock(devlink); return 0; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 3ddd896d6987..b5a60a048896 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1837,7 +1837,7 @@ static void xgbe_get_stats64(struct net_device *netdev, s->multicast = pstats->rxmulticastframes_g; s->rx_length_errors = pstats->rxlengtherror; s->rx_crc_errors = pstats->rxcrcerror; - s->rx_fifo_errors = pstats->rxfifooverflow; + s->rx_over_errors = pstats->rxfifooverflow; s->tx_packets = pstats->txframecount_gb; s->tx_bytes = pstats->txoctetcount_gb; @@ -2292,9 +2292,6 @@ read_again: goto read_again; if (error || packet->errors) { - if (packet->errors) - netif_err(pdata, rx_err, netdev, - "error in received packet\n"); dev_kfree_skb(skb); goto next_packet; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index a68757e8fd22..c63ddb12237e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -1928,6 +1928,7 @@ static void xgbe_set_rx_adap_mode(struct xgbe_prv_data *pdata, { if (pdata->rx_adapt_retries++ >= MAX_RX_ADAPT_RETRIES) { pdata->rx_adapt_retries = 0; + pdata->mode_set = false; return; } @@ -1974,6 +1975,7 @@ static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata) */ netif_dbg(pdata, link, pdata->netdev, "Block_lock done"); pdata->rx_adapt_done = true; + pdata->rx_adapt_retries = 0; pdata->mode_set = false; return; } diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 666522d64775..cd7dddeb91dd 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -255,14 +255,15 @@ config BNXT_HWMON devices, via the hwmon sysfs interface. config BNGE - tristate "Broadcom Ethernet device support" + tristate "Broadcom ThorUltra Ethernet device support" depends on PCI select NET_DEVLINK select PAGE_POOL + select AUXILIARY_BUS help - This driver supports Broadcom 50/100/200/400/800 gigabit Ethernet cards. - The module will be called bng_en. To compile this driver as a module, - choose M here. + This driver supports Broadcom ThorUltra 50/100/200/400/800 gigabit + Ethernet cards. The module will be called bng_en. To compile this + driver as a module, choose M here. config BCMASP tristate "Broadcom ASP 2.0 Ethernet support" diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c index fd35f4b4dc50..014340f33345 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c @@ -156,7 +156,7 @@ static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv, ASP_RX_FILTER_NET_OFFSET_L4(32), ASP_RX_FILTER_NET_OFFSET(nfilt->hw_index + 1)); - rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->port + 8) | + rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->ch) | ASP_RX_FILTER_NET_CFG_EN | ASP_RX_FILTER_NET_CFG_L2_EN | ASP_RX_FILTER_NET_CFG_L3_EN | @@ -166,7 +166,7 @@ static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv, ASP_RX_FILTER_NET_CFG_UMC(nfilt->port), ASP_RX_FILTER_NET_CFG(nfilt->hw_index)); - rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->port + 8) | + rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->ch) | ASP_RX_FILTER_NET_CFG_EN | ASP_RX_FILTER_NET_CFG_L2_EN | ASP_RX_FILTER_NET_CFG_L3_EN | @@ -714,6 +714,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf, nfilter = &priv->net_filters[open_index]; nfilter->claimed = true; nfilter->port = intf->port; + nfilter->ch = intf->channel + priv->tx_chan_offset; nfilter->hw_index = open_index; } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h index 74adfdb50e11..e238507be40a 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h @@ -348,6 +348,7 @@ struct bcmasp_net_filter { bool wake_filter; int port; + int ch; unsigned int hw_index; }; diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index b9973956c480..ceb6c11431dd 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -1261,7 +1261,7 @@ struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv, netdev_err(intf->ndev, "invalid PHY mode: %s for port %d\n", phy_modes(intf->phy_interface), intf->port); ret = -EINVAL; - goto err_free_netdev; + goto err_deregister_fixed_link; } ret = of_get_ethdev_address(ndev_dn, ndev); @@ -1286,6 +1286,9 @@ struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv, return intf; +err_deregister_fixed_link: + if (of_phy_is_fixed_link(ndev_dn)) + of_phy_deregister_fixed_link(ndev_dn); err_free_netdev: free_netdev(ndev); err: diff --git a/drivers/net/ethernet/broadcom/bnge/bnge.h b/drivers/net/ethernet/broadcom/bnge/bnge.h index 411744894349..32fc16a37d02 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge.h @@ -5,7 +5,7 @@ #define _BNGE_H_ #define DRV_NAME "bng_en" -#define DRV_SUMMARY "Broadcom 800G Ethernet Linux Driver" +#define DRV_SUMMARY "Broadcom ThorUltra NIC Ethernet Driver" #include <linux/etherdevice.h> #include <linux/bnxt/hsi.h> diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_core.c b/drivers/net/ethernet/broadcom/bnge/bnge_core.c index c94e132bebc8..b4090283df0f 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_core.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_core.c @@ -19,7 +19,7 @@ char bnge_driver_name[] = DRV_NAME; static const struct { char *name; } board_info[] = { - [BCM57708] = { "Broadcom BCM57708 50Gb/100Gb/200Gb/400Gb/800Gb Ethernet" }, + [BCM57708] = { "Broadcom BCM57708 ThorUltra 50Gb/100Gb/200Gb/400Gb/800Gb Ethernet" }, }; static const struct pci_device_id bnge_pci_tbl[] = { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index d17d0ea89c36..8419d1eb4035 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1482,9 +1482,11 @@ static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id) struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; u16 idx = agg_id & MAX_TPA_P5_MASK; - if (test_bit(idx, map->agg_idx_bmap)) - idx = find_first_zero_bit(map->agg_idx_bmap, - BNXT_AGG_IDX_BMAP_SIZE); + if (test_bit(idx, map->agg_idx_bmap)) { + idx = find_first_zero_bit(map->agg_idx_bmap, MAX_TPA_P5); + if (idx >= MAX_TPA_P5) + return INVALID_HW_RING_ID; + } __set_bit(idx, map->agg_idx_bmap); map->agg_id_tbl[agg_id] = idx; return idx; @@ -1548,6 +1550,13 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { agg_id = TPA_START_AGG_ID_P5(tpa_start); agg_id = bnxt_alloc_agg_idx(rxr, agg_id); + if (unlikely(agg_id == INVALID_HW_RING_ID)) { + netdev_warn(bp->dev, "Unable to allocate agg ID for ring %d, agg 0x%x\n", + rxr->bnapi->index, + TPA_START_AGG_ID_P5(tpa_start)); + bnxt_sched_reset_rxr(bp, rxr); + return; + } } else { agg_id = TPA_START_AGG_ID(tpa_start); } @@ -16882,12 +16891,12 @@ init_err_dl: init_err_pci_clean: bnxt_hwrm_func_drv_unrgtr(bp); - bnxt_free_hwrm_resources(bp); - bnxt_hwmon_uninit(bp); - bnxt_ethtool_free(bp); bnxt_ptp_clear(bp); kfree(bp->ptp_cfg); bp->ptp_cfg = NULL; + bnxt_free_hwrm_resources(bp); + bnxt_hwmon_uninit(bp); + bnxt_ethtool_free(bp); kfree(bp->fw_health); bp->fw_health = NULL; bnxt_cleanup_pci(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index f5f07a7e6b29..f88e7769a838 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1080,11 +1080,9 @@ struct bnxt_tpa_info { struct rx_agg_cmp *agg_arr; }; -#define BNXT_AGG_IDX_BMAP_SIZE (MAX_TPA_P5 / BITS_PER_LONG) - struct bnxt_tpa_idx_map { u16 agg_id_tbl[1024]; - unsigned long agg_idx_bmap[BNXT_AGG_IDX_BMAP_SIZE]; + DECLARE_BITMAP(agg_idx_bmap, MAX_TPA_P5); }; struct bnxt_rx_ring_info { diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index e461f5072884..6511ecd5856b 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -708,7 +708,6 @@ static void macb_mac_link_up(struct phylink_config *config, /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down * cleared the pipeline and control registers. */ - bp->macbgem_ops.mog_init_rings(bp); macb_init_buffers(bp); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) @@ -2954,6 +2953,8 @@ static int macb_open(struct net_device *dev) goto pm_exit; } + bp->macbgem_ops.mog_init_rings(bp); + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { napi_enable(&queue->napi_rx); napi_enable(&queue->napi_tx); diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index bb5d2fa15736..8ed45bceb537 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -3801,6 +3801,7 @@ int be_cmd_get_perm_mac(struct be_adapter *adapter, u8 *mac) { int status; bool pmac_valid = false; + u32 pmac_id; eth_zero_addr(mac); @@ -3813,7 +3814,7 @@ int be_cmd_get_perm_mac(struct be_adapter *adapter, u8 *mac) adapter->if_handle, 0); } else { status = be_cmd_get_mac_from_list(adapter, mac, &pmac_valid, - NULL, adapter->if_handle, 0); + &pmac_id, adapter->if_handle, 0); } return status; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 5bb31c8fab39..995c159003d7 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2141,7 +2141,7 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) struct be_aic_obj *aic; struct be_rx_obj *rxo; struct be_tx_obj *txo; - u64 rx_pkts = 0, tx_pkts = 0; + u64 rx_pkts = 0, tx_pkts = 0, pkts; ulong now; u32 pps, delta; int i; @@ -2157,15 +2157,17 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) for_all_rx_queues_on_eq(adapter, eqo, rxo, i) { do { start = u64_stats_fetch_begin(&rxo->stats.sync); - rx_pkts += rxo->stats.rx_pkts; + pkts = rxo->stats.rx_pkts; } while (u64_stats_fetch_retry(&rxo->stats.sync, start)); + rx_pkts += pkts; } for_all_tx_queues_on_eq(adapter, eqo, txo, i) { do { start = u64_stats_fetch_begin(&txo->stats.sync); - tx_pkts += txo->stats.tx_reqs; + pkts = txo->stats.tx_reqs; } while (u64_stats_fetch_retry(&txo->stats.sync, start)); + tx_pkts += pkts; } /* Skip, if wrapped around or first calculation */ diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index dce27bd67a7d..aecd40aeef9c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -79,9 +79,9 @@ struct enetc_lso_t { #define ENETC_RXB_TRUESIZE (PAGE_SIZE >> 1) #define ENETC_RXB_PAD NET_SKB_PAD /* add extra space if needed */ #define ENETC_RXB_DMA_SIZE \ - (SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD) + min(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD, 0xffff) #define ENETC_RXB_DMA_SIZE_XDP \ - (SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - XDP_PACKET_HEADROOM) + min(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - XDP_PACKET_HEADROOM, 0xffff) struct enetc_rx_swbd { dma_addr_t dma; diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c index 443983fdecd9..7fd39f895290 100644 --- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c +++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c @@ -577,11 +577,17 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv, } addr = netc_get_phy_addr(np); - if (addr <= 0) { + if (addr < 0) { dev_err(dev, "Failed to get PHY address\n"); return addr; } + /* The default value of LaBCR[MDIO_PHYAD_PRTAD] is 0, + * so no need to set the register. + */ + if (!addr) + return 0; + if (phy_mask & BIT(addr)) { dev_err(dev, "Find same PHY address in EMDIO and ENETC node\n"); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index a753265961af..797ef6899657 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1150,7 +1150,7 @@ fec_restart(struct net_device *ndev) u32 rcntl = FEC_RCR_MII; if (OPT_ARCH_HAS_MAX_FL) - rcntl |= (fep->netdev->mtu + ETH_HLEN + ETH_FCS_LEN) << 16; + rcntl |= (fep->netdev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN) << 16; if (fep->bufdesc_ex) fec_ptp_save_state(fep); @@ -1285,12 +1285,13 @@ fec_restart(struct net_device *ndev) /* When Jumbo Frame is enabled, the FIFO may not be large enough * to hold an entire frame. In such cases, if the MTU exceeds - * (PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN), configure the interface - * to operate in cut-through mode, triggered by the FIFO threshold. + * (PKT_MAXBUF_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN), configure + * the interface to operate in cut-through mode, triggered by + * the FIFO threshold. * Otherwise, enable the ENET store-and-forward mode. */ if ((fep->quirks & FEC_QUIRK_JUMBO_FRAME) && - (ndev->mtu > (PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN))) + (ndev->mtu > (PKT_MAXBUF_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN))) writel(0xF, fep->hwp + FEC_X_WMRK); else writel(FEC_TXWMRK_STRFWD, fep->hwp + FEC_X_WMRK); @@ -4037,7 +4038,7 @@ static int fec_change_mtu(struct net_device *ndev, int new_mtu) if (netif_running(ndev)) return -EBUSY; - order = get_order(new_mtu + ETH_HLEN + ETH_FCS_LEN + order = get_order(new_mtu + VLAN_ETH_HLEN + ETH_FCS_LEN + FEC_DRV_RESERVE_SPACE); fep->rx_frame_size = (PAGE_SIZE << order) - FEC_DRV_RESERVE_SPACE; fep->pagepool_order = order; @@ -4588,7 +4589,7 @@ fec_probe(struct platform_device *pdev) else fep->max_buf_size = PKT_MAXBUF_SIZE; - ndev->max_mtu = fep->max_buf_size - ETH_HLEN - ETH_FCS_LEN; + ndev->max_mtu = fep->max_buf_size - VLAN_ETH_HLEN - ETH_FCS_LEN; ret = register_netdev(ndev); if (ret) diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index affd5a6c44e7..131d1210dc4a 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1602,8 +1602,10 @@ static void ugeth_mac_config(struct phylink_config *config, unsigned int mode, pr_warn("TBI mode requires that the device tree specify a tbi-handle\n"); tbiphy = of_phy_find_device(ug_info->tbi_node); - if (!tbiphy) + if (!tbiphy) { pr_warn("Could not get TBI device\n"); + return; + } value = phy_read(tbiphy, ENET_TBI_MII_CR); value &= ~0x1000; /* Turn off autonegotiation */ diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 970d5ca8cdde..cbdf3a842cfe 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1206,6 +1206,11 @@ static inline bool gve_supports_xdp_xmit(struct gve_priv *priv) } } +static inline bool gve_is_clock_enabled(struct gve_priv *priv) +{ + return priv->nic_ts_report; +} + /* gqi napi handler defined in gve_main.c */ int gve_napi_poll(struct napi_struct *napi, int budget); diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 52500ae8348e..311b106160b2 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -938,7 +938,7 @@ static int gve_get_ts_info(struct net_device *netdev, ethtool_op_get_ts_info(netdev, info); - if (priv->nic_timestamp_supported) { + if (gve_is_clock_enabled(priv)) { info->so_timestamping |= SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index a7a088a77f37..52c5e4942cd4 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -558,7 +558,7 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) block->priv = priv; err = request_irq(priv->msix_vectors[msix_idx].vector, gve_is_gqi(priv) ? gve_intr : gve_intr_dqo, - 0, block->name, block); + IRQF_NO_AUTOEN, block->name, block); if (err) { dev_err(&priv->pdev->dev, "Failed to receive msix vector %d\n", i); @@ -680,10 +680,12 @@ static int gve_setup_device_resources(struct gve_priv *priv) } } - err = gve_init_clock(priv); - if (err) { - dev_err(&priv->pdev->dev, "Failed to init clock"); - goto abort_with_ptype_lut; + if (priv->nic_timestamp_supported) { + err = gve_init_clock(priv); + if (err) { + dev_warn(&priv->pdev->dev, "Failed to init clock, continuing without PTP support"); + err = 0; + } } err = gve_init_rss_config(priv, priv->rx_cfg.num_queues); @@ -2183,7 +2185,7 @@ static int gve_set_ts_config(struct net_device *dev, } if (kernel_config->rx_filter != HWTSTAMP_FILTER_NONE) { - if (!priv->nic_ts_report) { + if (!gve_is_clock_enabled(priv)) { NL_SET_ERR_MSG_MOD(extack, "RX timestamping is not supported"); kernel_config->rx_filter = HWTSTAMP_FILTER_NONE; diff --git a/drivers/net/ethernet/google/gve/gve_ptp.c b/drivers/net/ethernet/google/gve/gve_ptp.c index 073677d82ee8..de42fc2c19a1 100644 --- a/drivers/net/ethernet/google/gve/gve_ptp.c +++ b/drivers/net/ethernet/google/gve/gve_ptp.c @@ -70,11 +70,6 @@ static int gve_ptp_init(struct gve_priv *priv) struct gve_ptp *ptp; int err; - if (!priv->nic_timestamp_supported) { - dev_dbg(&priv->pdev->dev, "Device does not support PTP\n"); - return -EOPNOTSUPP; - } - priv->ptp = kzalloc(sizeof(*priv->ptp), GFP_KERNEL); if (!priv->ptp) return -ENOMEM; @@ -116,9 +111,6 @@ int gve_init_clock(struct gve_priv *priv) { int err; - if (!priv->nic_timestamp_supported) - return 0; - err = gve_ptp_init(priv); if (err) return err; diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index f1bd8f5d5732..63a96106a693 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -484,7 +484,7 @@ int gve_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp) { const struct gve_xdp_buff *ctx = (void *)_ctx; - if (!ctx->gve->nic_ts_report) + if (!gve_is_clock_enabled(ctx->gve)) return -ENODATA; if (!(ctx->compl_desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID)) diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c index ace9b8698021..b53b7fcdcdaf 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.c +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -112,11 +112,13 @@ void gve_add_napi(struct gve_priv *priv, int ntfy_idx, netif_napi_add_locked(priv->dev, &block->napi, gve_poll); netif_napi_set_irq_locked(&block->napi, block->irq); + enable_irq(block->irq); } void gve_remove_napi(struct gve_priv *priv, int ntfy_idx) { struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; + disable_irq(block->irq); netif_napi_del_locked(&block->napi); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 7a0654e2d3dd..7a9573dcab74 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2529,44 +2529,47 @@ static netdev_features_t hns3_features_check(struct sk_buff *skb, static void hns3_fetch_stats(struct rtnl_link_stats64 *stats, struct hns3_enet_ring *ring, bool is_tx) { + struct ring_stats ring_stats; unsigned int start; do { start = u64_stats_fetch_begin(&ring->syncp); - if (is_tx) { - stats->tx_bytes += ring->stats.tx_bytes; - stats->tx_packets += ring->stats.tx_pkts; - stats->tx_dropped += ring->stats.sw_err_cnt; - stats->tx_dropped += ring->stats.tx_vlan_err; - stats->tx_dropped += ring->stats.tx_l4_proto_err; - stats->tx_dropped += ring->stats.tx_l2l3l4_err; - stats->tx_dropped += ring->stats.tx_tso_err; - stats->tx_dropped += ring->stats.over_max_recursion; - stats->tx_dropped += ring->stats.hw_limitation; - stats->tx_dropped += ring->stats.copy_bits_err; - stats->tx_dropped += ring->stats.skb2sgl_err; - stats->tx_dropped += ring->stats.map_sg_err; - stats->tx_errors += ring->stats.sw_err_cnt; - stats->tx_errors += ring->stats.tx_vlan_err; - stats->tx_errors += ring->stats.tx_l4_proto_err; - stats->tx_errors += ring->stats.tx_l2l3l4_err; - stats->tx_errors += ring->stats.tx_tso_err; - stats->tx_errors += ring->stats.over_max_recursion; - stats->tx_errors += ring->stats.hw_limitation; - stats->tx_errors += ring->stats.copy_bits_err; - stats->tx_errors += ring->stats.skb2sgl_err; - stats->tx_errors += ring->stats.map_sg_err; - } else { - stats->rx_bytes += ring->stats.rx_bytes; - stats->rx_packets += ring->stats.rx_pkts; - stats->rx_dropped += ring->stats.l2_err; - stats->rx_errors += ring->stats.l2_err; - stats->rx_errors += ring->stats.l3l4_csum_err; - stats->rx_crc_errors += ring->stats.l2_err; - stats->multicast += ring->stats.rx_multicast; - stats->rx_length_errors += ring->stats.err_pkt_len; - } + ring_stats = ring->stats; } while (u64_stats_fetch_retry(&ring->syncp, start)); + + if (is_tx) { + stats->tx_bytes += ring_stats.tx_bytes; + stats->tx_packets += ring_stats.tx_pkts; + stats->tx_dropped += ring_stats.sw_err_cnt; + stats->tx_dropped += ring_stats.tx_vlan_err; + stats->tx_dropped += ring_stats.tx_l4_proto_err; + stats->tx_dropped += ring_stats.tx_l2l3l4_err; + stats->tx_dropped += ring_stats.tx_tso_err; + stats->tx_dropped += ring_stats.over_max_recursion; + stats->tx_dropped += ring_stats.hw_limitation; + stats->tx_dropped += ring_stats.copy_bits_err; + stats->tx_dropped += ring_stats.skb2sgl_err; + stats->tx_dropped += ring_stats.map_sg_err; + stats->tx_errors += ring_stats.sw_err_cnt; + stats->tx_errors += ring_stats.tx_vlan_err; + stats->tx_errors += ring_stats.tx_l4_proto_err; + stats->tx_errors += ring_stats.tx_l2l3l4_err; + stats->tx_errors += ring_stats.tx_tso_err; + stats->tx_errors += ring_stats.over_max_recursion; + stats->tx_errors += ring_stats.hw_limitation; + stats->tx_errors += ring_stats.copy_bits_err; + stats->tx_errors += ring_stats.skb2sgl_err; + stats->tx_errors += ring_stats.map_sg_err; + } else { + stats->rx_bytes += ring_stats.rx_bytes; + stats->rx_packets += ring_stats.rx_pkts; + stats->rx_dropped += ring_stats.l2_err; + stats->rx_errors += ring_stats.l2_err; + stats->rx_errors += ring_stats.l3l4_csum_err; + stats->rx_crc_errors += ring_stats.l2_err; + stats->multicast += ring_stats.rx_multicast; + stats->rx_length_errors += ring_stats.err_pkt_len; + } } static void hns3_nic_get_stats64(struct net_device *netdev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 9bb708fa42f2..416e02e7b995 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -731,7 +731,7 @@ struct hclge_fd_tcam_config_3_cmd { #define HCLGE_FD_AD_QID_M GENMASK(11, 2) #define HCLGE_FD_AD_USE_COUNTER_B 12 #define HCLGE_FD_AD_COUNTER_NUM_S 13 -#define HCLGE_FD_AD_COUNTER_NUM_M GENMASK(20, 13) +#define HCLGE_FD_AD_COUNTER_NUM_M GENMASK(19, 13) #define HCLGE_FD_AD_NXT_STEP_B 20 #define HCLGE_FD_AD_NXT_KEY_S 21 #define HCLGE_FD_AD_NXT_KEY_M GENMASK(25, 21) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c589baea7c77..b8e2aa19f9e6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -5690,7 +5690,7 @@ static int hclge_fd_ad_config(struct hclge_dev *hdev, u8 stage, int loc, HCLGE_FD_AD_COUNTER_NUM_S, action->counter_id); hnae3_set_bit(ad_data, HCLGE_FD_AD_NXT_STEP_B, action->use_next_stage); hnae3_set_field(ad_data, HCLGE_FD_AD_NXT_KEY_M, HCLGE_FD_AD_NXT_KEY_S, - action->counter_id); + action->next_input_key); req->ad_data = cpu_to_le64(ad_data); ret = hclge_cmd_send(&hdev->hw, &desc, 1); diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c index a69b361225e9..84bee5d6e638 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c @@ -43,21 +43,12 @@ static void qp_add_napi(struct hinic3_irq_cfg *irq_cfg) struct hinic3_nic_dev *nic_dev = netdev_priv(irq_cfg->netdev); netif_napi_add(nic_dev->netdev, &irq_cfg->napi, hinic3_poll); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi); napi_enable(&irq_cfg->napi); } static void qp_del_napi(struct hinic3_irq_cfg *irq_cfg) { napi_disable(&irq_cfg->napi); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_RX, NULL); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_TX, NULL); - netif_stop_subqueue(irq_cfg->netdev, irq_cfg->irq_id); netif_napi_del(&irq_cfg->napi); } @@ -150,6 +141,11 @@ int hinic3_qps_irq_init(struct net_device *netdev) goto err_release_irqs; } + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi); + hinic3_set_msix_auto_mask_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_SET_MSIX_AUTO_MASK); @@ -164,6 +160,10 @@ err_release_irqs: q_id--; irq_cfg = &nic_dev->q_params.irq_cfg[q_id]; qp_del_napi(irq_cfg); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, NULL); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, NULL); hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_MSIX_DISABLE); hinic3_set_msix_auto_mask_state(nic_dev->hwdev, @@ -184,6 +184,10 @@ void hinic3_qps_irq_uninit(struct net_device *netdev) for (q_id = 0; q_id < nic_dev->q_params.num_qps; q_id++) { irq_cfg = &nic_dev->q_params.irq_cfg[q_id]; qp_del_napi(irq_cfg); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, NULL); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, NULL); hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_MSIX_DISABLE); hinic3_set_msix_auto_mask_state(nic_dev->hwdev, diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 292389aceb2d..7f078ec9c14c 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -4094,7 +4094,15 @@ static bool e1000_tbi_should_accept(struct e1000_adapter *adapter, u32 length, const u8 *data) { struct e1000_hw *hw = &adapter->hw; - u8 last_byte = *(data + length - 1); + u8 last_byte; + + /* Guard against OOB on data[length - 1] */ + if (unlikely(!length)) + return false; + /* Upper bound: length must not exceed rx_buffer_len */ + if (unlikely(length > adapter->rx_buffer_len)) + return false; + last_byte = *(data + length - 1); if (TBI_ACCEPT(hw, status, errors, length, last_byte)) { unsigned long irq_flags; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index d2d03db2acec..dcb50c2e1aa2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1422,4 +1422,15 @@ static inline struct i40e_veb *i40e_pf_get_main_veb(struct i40e_pf *pf) return (pf->lan_veb != I40E_NO_VEB) ? pf->veb[pf->lan_veb] : NULL; } +static inline u32 i40e_get_max_num_descriptors(const struct i40e_pf *pf) +{ + const struct i40e_hw *hw = &pf->hw; + + switch (hw->mac.type) { + case I40E_MAC_XL710: + return I40E_MAX_NUM_DESCRIPTORS_XL710; + default: + return I40E_MAX_NUM_DESCRIPTORS; + } +} #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index f2c2646ea298..6a47ea0927e9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2013,18 +2013,6 @@ static void i40e_get_drvinfo(struct net_device *netdev, drvinfo->n_priv_flags += I40E_GL_PRIV_FLAGS_STR_LEN; } -static u32 i40e_get_max_num_descriptors(struct i40e_pf *pf) -{ - struct i40e_hw *hw = &pf->hw; - - switch (hw->mac.type) { - case I40E_MAC_XL710: - return I40E_MAX_NUM_DESCRIPTORS_XL710; - default: - return I40E_MAX_NUM_DESCRIPTORS; - } -} - static void i40e_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index d8192aa23254..0b1cc0481027 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2234,6 +2234,7 @@ static void i40e_set_rx_mode(struct net_device *netdev) vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->back->state); } + i40e_service_event_schedule(vsi->back); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 8b30a3accd31..1fa877b52f61 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -656,7 +656,7 @@ static int i40e_config_vsi_tx_queue(struct i40e_vf *vf, u16 vsi_id, /* ring_len has to be multiple of 8 */ if (!IS_ALIGNED(info->ring_len, 8) || - info->ring_len > I40E_MAX_NUM_DESCRIPTORS_XL710) { + info->ring_len > i40e_get_max_num_descriptors(pf)) { ret = -EINVAL; goto error_context; } @@ -726,7 +726,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, /* ring_len has to be multiple of 32 */ if (!IS_ALIGNED(info->ring_len, 32) || - info->ring_len > I40E_MAX_NUM_DESCRIPTORS_XL710) { + info->ring_len > i40e_get_max_num_descriptors(pf)) { ret = -EINVAL; goto error_param; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index c2fbe443ef85..4b0fc8f354bc 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1726,11 +1726,11 @@ static int iavf_config_rss_reg(struct iavf_adapter *adapter) u16 i; dw = (u32 *)adapter->rss_key; - for (i = 0; i <= adapter->rss_key_size / 4; i++) + for (i = 0; i < adapter->rss_key_size / 4; i++) wr32(hw, IAVF_VFQF_HKEY(i), dw[i]); dw = (u32 *)adapter->rss_lut; - for (i = 0; i <= adapter->rss_lut_size / 4; i++) + for (i = 0; i < adapter->rss_lut_size / 4; i++) wr32(hw, IAVF_VFQF_HLUT(i), dw[i]); iavf_flush(hw); diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index d88b7f3fd1f9..2ef39cc70c21 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -460,6 +460,7 @@ static void ice_devlink_reinit_down(struct ice_pf *pf) ice_vsi_decfg(ice_get_main_vsi(pf)); rtnl_unlock(); ice_deinit_pf(pf); + ice_deinit_hw(&pf->hw); ice_deinit_dev(pf); } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 147aaee192a7..00f75d87c73f 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -979,6 +979,7 @@ void ice_map_xdp_rings(struct ice_vsi *vsi); int ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 046bc9c65c51..785bf5cc1b25 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2251,7 +2251,7 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) /* there are some rare cases when trying to release the resource * results in an admin queue timeout, so handle them correctly */ - timeout = jiffies + 10 * ICE_CTL_Q_SQ_CMD_TIMEOUT; + timeout = jiffies + 10 * usecs_to_jiffies(ICE_CTL_Q_SQ_CMD_TIMEOUT); do { status = ice_aq_release_res(hw, res, 0, NULL); if (status != -EIO) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 969d4f8f9c02..3565a5d96c6d 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3626,11 +3626,7 @@ ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) if (!lut) return -ENOMEM; - err = ice_get_rss_key(vsi, rxfh->key); - if (err) - goto out; - - err = ice_get_rss_lut(vsi, lut, vsi->rss_table_size); + err = ice_get_rss(vsi, rxfh->key, lut, vsi->rss_table_size); if (err) goto out; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 15621707fbf8..d47af94f31a9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -398,6 +398,8 @@ static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) if (!ring_stats) goto err_out; + u64_stats_init(&ring_stats->syncp); + WRITE_ONCE(tx_ring_stats[i], ring_stats); } @@ -417,6 +419,8 @@ static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) if (!ring_stats) goto err_out; + u64_stats_init(&ring_stats->syncp); + WRITE_ONCE(rx_ring_stats[i], ring_stats); } @@ -2779,12 +2783,14 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) ASSERT_RTNL(); ice_for_each_rxq(vsi, q_idx) - netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, - &vsi->rx_rings[q_idx]->q_vector->napi); + if (vsi->rx_rings[q_idx] && vsi->rx_rings[q_idx]->q_vector) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, + &vsi->rx_rings[q_idx]->q_vector->napi); ice_for_each_txq(vsi, q_idx) - netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, - &vsi->tx_rings[q_idx]->q_vector->napi); + if (vsi->tx_rings[q_idx] && vsi->tx_rings[q_idx]->q_vector) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, + &vsi->tx_rings[q_idx]->q_vector->napi); /* Also set the interrupt number for the NAPI */ ice_for_each_q_vector(vsi, v_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; @@ -3805,22 +3811,31 @@ int ice_vsi_add_vlan_zero(struct ice_vsi *vsi) int ice_vsi_del_vlan_zero(struct ice_vsi *vsi) { struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct ice_pf *pf = vsi->back; struct ice_vlan vlan; int err; - vlan = ICE_VLAN(0, 0, 0); - err = vlan_ops->del_vlan(vsi, &vlan); - if (err && err != -EEXIST) - return err; + if (pf->lag && pf->lag->primary) { + dev_dbg(ice_pf_to_dev(pf), "Interface is primary in aggregate - not deleting prune list\n"); + } else { + vlan = ICE_VLAN(0, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + } /* in SVM both VLAN 0 filters are identical */ if (!ice_is_dvm_ena(&vsi->back->hw)) return 0; - vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); - err = vlan_ops->del_vlan(vsi, &vlan); - if (err && err != -EEXIST) - return err; + if (pf->lag && pf->lag->primary) { + dev_dbg(ice_pf_to_dev(pf), "Interface is primary in aggregate - not deleting QinQ prune list\n"); + } else { + vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + } /* when deleting the last VLAN filter, make sure to disable the VLAN * promisc mode so the filter isn't left by accident diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4bb68e7a00f5..71c6d53b461e 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4836,6 +4836,7 @@ static void ice_deinit_features(struct ice_pf *pf) ice_dpll_deinit(pf); if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) xa_destroy(&pf->eswitch.reprs); + ice_hwmon_exit(pf); } static void ice_init_wakeup(struct ice_pf *pf) @@ -5437,8 +5438,6 @@ static void ice_remove(struct pci_dev *pdev) ice_free_vfs(pf); } - ice_hwmon_exit(pf); - if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); @@ -6983,7 +6982,6 @@ void ice_update_vsi_stats(struct ice_vsi *vsi) cur_ns->rx_errors = pf->stats.crc_errors + pf->stats.illegal_bytes + pf->stats.rx_undersize + - pf->hw_csum_rx_error + pf->stats.rx_jabber + pf->stats.rx_fragments + pf->stats.rx_oversize; @@ -7989,6 +7987,34 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed) } /** + * ice_get_rss - Get RSS LUT and/or key + * @vsi: Pointer to VSI structure + * @seed: Buffer to store the key in + * @lut: Buffer to store the lookup table entries + * @lut_size: Size of buffer to store the lookup table entries + * + * Return: 0 on success, negative on failure + */ +int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) +{ + int err; + + if (seed) { + err = ice_get_rss_key(vsi, seed); + if (err) + return err; + } + + if (lut) { + err = ice_get_rss_lut(vsi, lut, lut_size); + if (err) + return err; + } + + return 0; +} + +/** * ice_set_rss_hfunc - Set RSS HASH function * @vsi: Pointer to VSI structure * @hfunc: hash function (ICE_AQ_VSI_Q_OPT_RSS_*) diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index 8cfc68cbfa06..1bf7934d4e28 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -284,8 +284,7 @@ struct idpf_port_stats { struct idpf_fsteer_fltr { struct list_head list; - u32 loc; - u32 q_index; + struct ethtool_rx_flow_spec fs; }; /** @@ -424,14 +423,12 @@ enum idpf_user_flags { * @rss_key: RSS hash key * @rss_lut_size: Size of RSS lookup table * @rss_lut: RSS lookup table - * @cached_lut: Used to restore previously init RSS lut */ struct idpf_rss_data { u16 rss_key_size; u8 *rss_key; u16 rss_lut_size; u32 *rss_lut; - u32 *cached_lut; }; /** @@ -558,6 +555,7 @@ struct idpf_vector_lifo { * @max_q: Maximum possible queues * @req_qs_chunks: Queue chunk data for requested queues * @mac_filter_list_lock: Lock to protect mac filters + * @flow_steer_list_lock: Lock to protect fsteer filters * @flags: See enum idpf_vport_config_flags */ struct idpf_vport_config { @@ -565,6 +563,7 @@ struct idpf_vport_config { struct idpf_vport_max_q max_q; struct virtchnl2_add_queues *req_qs_chunks; spinlock_t mac_filter_list_lock; + spinlock_t flow_steer_list_lock; DECLARE_BITMAP(flags, IDPF_VPORT_CONFIG_FLAGS_NBITS); }; diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index 2589e124e41c..2efa3c08aba5 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -37,6 +37,7 @@ static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, { struct idpf_netdev_priv *np = netdev_priv(netdev); struct idpf_vport_user_config_data *user_config; + struct idpf_vport_config *vport_config; struct idpf_fsteer_fltr *f; struct idpf_vport *vport; unsigned int cnt = 0; @@ -44,7 +45,8 @@ static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - user_config = &np->adapter->vport_config[np->vport_idx]->user_config; + vport_config = np->adapter->vport_config[np->vport_idx]; + user_config = &vport_config->user_config; switch (cmd->cmd) { case ETHTOOL_GRXCLSRLCNT: @@ -52,26 +54,34 @@ static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, cmd->data = idpf_fsteer_max_rules(vport); break; case ETHTOOL_GRXCLSRULE: - err = -EINVAL; + err = -ENOENT; + spin_lock_bh(&vport_config->flow_steer_list_lock); list_for_each_entry(f, &user_config->flow_steer_list, list) - if (f->loc == cmd->fs.location) { - cmd->fs.ring_cookie = f->q_index; + if (f->fs.location == cmd->fs.location) { + /* Avoid infoleak from padding: zero first, + * then assign fields + */ + memset(&cmd->fs, 0, sizeof(cmd->fs)); + cmd->fs = f->fs; err = 0; break; } + spin_unlock_bh(&vport_config->flow_steer_list_lock); break; case ETHTOOL_GRXCLSRLALL: cmd->data = idpf_fsteer_max_rules(vport); + spin_lock_bh(&vport_config->flow_steer_list_lock); list_for_each_entry(f, &user_config->flow_steer_list, list) { if (cnt == cmd->rule_cnt) { err = -EMSGSIZE; break; } - rule_locs[cnt] = f->loc; + rule_locs[cnt] = f->fs.location; cnt++; } if (!err) cmd->rule_cnt = user_config->num_fsteer_fltrs; + spin_unlock_bh(&vport_config->flow_steer_list_lock); break; default: break; @@ -168,7 +178,7 @@ static int idpf_add_flow_steer(struct net_device *netdev, struct idpf_vport *vport; u32 flow_type, q_index; u16 num_rxq; - int err; + int err = 0; vport = idpf_netdev_to_vport(netdev); vport_config = vport->adapter->vport_config[np->vport_idx]; @@ -194,6 +204,29 @@ static int idpf_add_flow_steer(struct net_device *netdev, if (!rule) return -ENOMEM; + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) { + err = -ENOMEM; + goto out_free_rule; + } + + /* detect duplicate entry and reject before adding rules */ + spin_lock_bh(&vport_config->flow_steer_list_lock); + list_for_each_entry(f, &user_config->flow_steer_list, list) { + if (f->fs.location == fsp->location) { + err = -EEXIST; + break; + } + + if (f->fs.location > fsp->location) + break; + parent = f; + } + spin_unlock_bh(&vport_config->flow_steer_list_lock); + + if (err) + goto out; + rule->vport_id = cpu_to_le32(vport->vport_id); rule->count = cpu_to_le32(1); info = &rule->rule_info[0]; @@ -232,26 +265,20 @@ static int idpf_add_flow_steer(struct net_device *netdev, goto out; } - fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); - if (!fltr) { - err = -ENOMEM; - goto out; - } - - fltr->loc = fsp->location; - fltr->q_index = q_index; - list_for_each_entry(f, &user_config->flow_steer_list, list) { - if (f->loc >= fltr->loc) - break; - parent = f; - } + /* Save a copy of the user's flow spec so ethtool can later retrieve it */ + fltr->fs = *fsp; + spin_lock_bh(&vport_config->flow_steer_list_lock); parent ? list_add(&fltr->list, &parent->list) : list_add(&fltr->list, &user_config->flow_steer_list); user_config->num_fsteer_fltrs++; + spin_unlock_bh(&vport_config->flow_steer_list_lock); + goto out_free_rule; out: + kfree(fltr); +out_free_rule: kfree(rule); return err; } @@ -302,17 +329,20 @@ static int idpf_del_flow_steer(struct net_device *netdev, goto out; } + spin_lock_bh(&vport_config->flow_steer_list_lock); list_for_each_entry_safe(f, iter, &user_config->flow_steer_list, list) { - if (f->loc == fsp->location) { + if (f->fs.location == fsp->location) { list_del(&f->list); kfree(f); user_config->num_fsteer_fltrs--; - goto out; + goto out_unlock; } } - err = -EINVAL; + err = -ENOENT; +out_unlock: + spin_unlock_bh(&vport_config->flow_steer_list_lock); out: kfree(rule); return err; @@ -381,7 +411,10 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev) * @netdev: network interface device structure * @rxfh: pointer to param struct (indir, key, hfunc) * - * Reads the indirection table directly from the hardware. Always returns 0. + * RSS LUT and Key information are read from driver's cached + * copy. When rxhash is off, rss lut will be displayed as zeros. + * + * Return: 0 on success, -errno otherwise. */ static int idpf_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) @@ -389,10 +422,13 @@ static int idpf_get_rxfh(struct net_device *netdev, struct idpf_netdev_priv *np = netdev_priv(netdev); struct idpf_rss_data *rss_data; struct idpf_adapter *adapter; + struct idpf_vport *vport; + bool rxhash_ena; int err = 0; u16 i; idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); adapter = np->adapter; @@ -402,9 +438,8 @@ static int idpf_get_rxfh(struct net_device *netdev, } rss_data = &adapter->vport_config[np->vport_idx]->user_config.rss_data; - if (!test_bit(IDPF_VPORT_UP, np->state)) - goto unlock_mutex; + rxhash_ena = idpf_is_feature_ena(vport, NETIF_F_RXHASH); rxfh->hfunc = ETH_RSS_HASH_TOP; if (rxfh->key) @@ -412,7 +447,7 @@ static int idpf_get_rxfh(struct net_device *netdev, if (rxfh->indir) { for (i = 0; i < rss_data->rss_lut_size; i++) - rxfh->indir[i] = rss_data->rss_lut[i]; + rxfh->indir[i] = rxhash_ena ? rss_data->rss_lut[i] : 0; } unlock_mutex: @@ -452,8 +487,6 @@ static int idpf_set_rxfh(struct net_device *netdev, } rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; - if (!test_bit(IDPF_VPORT_UP, np->state)) - goto unlock_mutex; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && rxfh->hfunc != ETH_RSS_HASH_TOP) { @@ -469,7 +502,8 @@ static int idpf_set_rxfh(struct net_device *netdev, rss_data->rss_lut[lut] = rxfh->indir[lut]; } - err = idpf_config_rss(vport); + if (test_bit(IDPF_VPORT_UP, np->state)) + err = idpf_config_rss(vport); unlock_mutex: idpf_vport_ctrl_unlock(netdev); diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c index 7e20a07e98e5..6dad0593f7f2 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_idc.c +++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c @@ -322,7 +322,7 @@ static void idpf_idc_vport_dev_down(struct idpf_adapter *adapter) for (i = 0; i < adapter->num_alloc_vports; i++) { struct idpf_vport *vport = adapter->vports[i]; - if (!vport) + if (!vport || !vport->vdev_info) continue; idpf_unplug_aux_dev(vport->vdev_info->adev); diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 7a7e101afeb6..131a8121839b 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -443,6 +443,29 @@ send_dealloc_vecs: } /** + * idpf_del_all_flow_steer_filters - Delete all flow steer filters in list + * @vport: main vport struct + * + * Takes flow_steer_list_lock spinlock. Deletes all filters + */ +static void idpf_del_all_flow_steer_filters(struct idpf_vport *vport) +{ + struct idpf_vport_config *vport_config; + struct idpf_fsteer_fltr *f, *ftmp; + + vport_config = vport->adapter->vport_config[vport->idx]; + + spin_lock_bh(&vport_config->flow_steer_list_lock); + list_for_each_entry_safe(f, ftmp, &vport_config->user_config.flow_steer_list, + list) { + list_del(&f->list); + kfree(f); + } + vport_config->user_config.num_fsteer_fltrs = 0; + spin_unlock_bh(&vport_config->flow_steer_list_lock); +} + +/** * idpf_find_mac_filter - Search filter list for specific mac filter * @vconfig: Vport config structure * @macaddr: The MAC address @@ -729,6 +752,65 @@ static int idpf_init_mac_addr(struct idpf_vport *vport, return 0; } +static void idpf_detach_and_close(struct idpf_adapter *adapter) +{ + int max_vports = adapter->max_vports; + + for (int i = 0; i < max_vports; i++) { + struct net_device *netdev = adapter->netdevs[i]; + + /* If the interface is in detached state, that means the + * previous reset was not handled successfully for this + * vport. + */ + if (!netif_device_present(netdev)) + continue; + + /* Hold RTNL to protect racing with callbacks */ + rtnl_lock(); + netif_device_detach(netdev); + if (netif_running(netdev)) { + set_bit(IDPF_VPORT_UP_REQUESTED, + adapter->vport_config[i]->flags); + dev_close(netdev); + } + rtnl_unlock(); + } +} + +static void idpf_attach_and_open(struct idpf_adapter *adapter) +{ + int max_vports = adapter->max_vports; + + for (int i = 0; i < max_vports; i++) { + struct idpf_vport *vport = adapter->vports[i]; + struct idpf_vport_config *vport_config; + struct net_device *netdev; + + /* In case of a critical error in the init task, the vport + * will be freed. Only continue to restore the netdevs + * if the vport is allocated. + */ + if (!vport) + continue; + + /* No need for RTNL on attach as this function is called + * following detach and dev_close(). We do take RTNL for + * dev_open() below as it can race with external callbacks + * following the call to netif_device_attach(). + */ + netdev = adapter->netdevs[i]; + netif_device_attach(netdev); + vport_config = adapter->vport_config[vport->idx]; + if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, + vport_config->flags)) { + rtnl_lock(); + dev_open(netdev, NULL); + rtnl_unlock(); + } + } +} + /** * idpf_cfg_netdev - Allocate, configure and register a netdev * @vport: main vport structure @@ -991,7 +1073,7 @@ static void idpf_vport_rel(struct idpf_vport *vport) u16 idx = vport->idx; vport_config = adapter->vport_config[vport->idx]; - idpf_deinit_rss(vport); + idpf_deinit_rss_lut(vport); rss_data = &vport_config->user_config.rss_data; kfree(rss_data->rss_key); rss_data->rss_key = NULL; @@ -1023,6 +1105,8 @@ static void idpf_vport_rel(struct idpf_vport *vport) kfree(adapter->vport_config[idx]->req_qs_chunks); adapter->vport_config[idx]->req_qs_chunks = NULL; } + kfree(vport->rx_ptype_lkup); + vport->rx_ptype_lkup = NULL; kfree(vport); adapter->num_alloc_vports--; } @@ -1041,12 +1125,15 @@ static void idpf_vport_dealloc(struct idpf_vport *vport) idpf_idc_deinit_vport_aux_device(vport->vdev_info); idpf_deinit_mac_addr(vport); - idpf_vport_stop(vport, true); - if (!test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags)) + if (!test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags)) { + idpf_vport_stop(vport, true); idpf_decfg_netdev(vport); - if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) + } + if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) { idpf_del_all_mac_filters(vport); + idpf_del_all_flow_steer_filters(vport); + } if (adapter->netdevs[i]) { struct idpf_netdev_priv *np = netdev_priv(adapter->netdevs[i]); @@ -1139,6 +1226,7 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, u16 idx = adapter->next_vport; struct idpf_vport *vport; u16 num_max_q; + int err; if (idx == IDPF_NO_FREE_SLOT) return NULL; @@ -1189,10 +1277,11 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, idpf_vport_init(vport, max_q); - /* This alloc is done separate from the LUT because it's not strictly - * dependent on how many queues we have. If we change number of queues - * and soft reset we'll need a new LUT but the key can remain the same - * for as long as the vport exists. + /* LUT and key are both initialized here. Key is not strictly dependent + * on how many queues we have. If we change number of queues and soft + * reset is initiated, LUT will be freed and a new LUT will be allocated + * as per the updated number of queues during vport bringup. However, + * the key remains the same for as long as the vport exists. */ rss_data = &adapter->vport_config[idx]->user_config.rss_data; rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL); @@ -1202,6 +1291,11 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, /* Initialize default rss key */ netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size); + /* Initialize default rss LUT */ + err = idpf_init_rss_lut(vport); + if (err) + goto free_rss_key; + /* fill vport slot in the adapter struct */ adapter->vports[idx] = vport; adapter->vport_ids[idx] = idpf_get_vport_id(vport); @@ -1212,6 +1306,8 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, return vport; +free_rss_key: + kfree(rss_data->rss_key); free_vector_idxs: kfree(vport->q_vector_idxs); free_vport: @@ -1271,7 +1367,7 @@ void idpf_mbx_task(struct work_struct *work) idpf_mb_irq_enable(adapter); else queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, - msecs_to_jiffies(300)); + usecs_to_jiffies(300)); idpf_recv_mb_msg(adapter); } @@ -1388,7 +1484,6 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); struct idpf_adapter *adapter = vport->adapter; - struct idpf_vport_config *vport_config; int err; if (test_bit(IDPF_VPORT_UP, np->state)) @@ -1429,14 +1524,14 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize queue registers for vport %u: %d\n", vport->vport_id, err); - goto queues_rel; + goto intr_deinit; } err = idpf_rx_bufs_init_all(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize RX buffers for vport %u: %d\n", vport->vport_id, err); - goto queues_rel; + goto intr_deinit; } idpf_rx_init_buf_tail(vport); @@ -1482,13 +1577,9 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) idpf_restore_features(vport); - vport_config = adapter->vport_config[vport->idx]; - if (vport_config->user_config.rss_data.rss_lut) - err = idpf_config_rss(vport); - else - err = idpf_init_rss(vport); + err = idpf_config_rss(vport); if (err) { - dev_err(&adapter->pdev->dev, "Failed to initialize RSS for vport %u: %d\n", + dev_err(&adapter->pdev->dev, "Failed to configure RSS for vport %u: %d\n", vport->vport_id, err); goto disable_vport; } @@ -1497,7 +1588,7 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) if (err) { dev_err(&adapter->pdev->dev, "Failed to complete interface up for vport %u: %d\n", vport->vport_id, err); - goto deinit_rss; + goto disable_vport; } if (rtnl) @@ -1505,8 +1596,6 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) return 0; -deinit_rss: - idpf_deinit_rss(vport); disable_vport: idpf_send_disable_vport_msg(vport); disable_queues: @@ -1544,7 +1633,6 @@ void idpf_init_task(struct work_struct *work) struct idpf_vport_config *vport_config; struct idpf_vport_max_q max_q; struct idpf_adapter *adapter; - struct idpf_netdev_priv *np; struct idpf_vport *vport; u16 num_default_vports; struct pci_dev *pdev; @@ -1579,10 +1667,15 @@ void idpf_init_task(struct work_struct *work) goto unwind_vports; } + err = idpf_send_get_rx_ptype_msg(vport); + if (err) + goto unwind_vports; + index = vport->idx; vport_config = adapter->vport_config[index]; spin_lock_init(&vport_config->mac_filter_list_lock); + spin_lock_init(&vport_config->flow_steer_list_lock); INIT_LIST_HEAD(&vport_config->user_config.mac_filter_list); INIT_LIST_HEAD(&vport_config->user_config.flow_steer_list); @@ -1590,21 +1683,11 @@ void idpf_init_task(struct work_struct *work) err = idpf_check_supported_desc_ids(vport); if (err) { dev_err(&pdev->dev, "failed to get required descriptor ids\n"); - goto cfg_netdev_err; + goto unwind_vports; } if (idpf_cfg_netdev(vport)) - goto cfg_netdev_err; - - err = idpf_send_get_rx_ptype_msg(vport); - if (err) - goto handle_err; - - /* Once state is put into DOWN, driver is ready for dev_open */ - np = netdev_priv(vport->netdev); - clear_bit(IDPF_VPORT_UP, np->state); - if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, vport_config->flags)) - idpf_vport_open(vport, true); + goto unwind_vports; /* Spawn and return 'idpf_init_task' work queue until all the * default vports are created @@ -1635,21 +1718,15 @@ void idpf_init_task(struct work_struct *work) set_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags); } - /* As all the required vports are created, clear the reset flag - * unconditionally here in case we were in reset and the link was down. - */ + /* Clear the reset and load bits as all vports are created */ clear_bit(IDPF_HR_RESET_IN_PROG, adapter->flags); + clear_bit(IDPF_HR_DRV_LOAD, adapter->flags); /* Start the statistics task now */ queue_delayed_work(adapter->stats_wq, &adapter->stats_task, msecs_to_jiffies(10 * (pdev->devfn & 0x07))); return; -handle_err: - idpf_decfg_netdev(vport); -cfg_netdev_err: - idpf_vport_rel(vport); - adapter->vports[index] = NULL; unwind_vports: if (default_vport) { for (index = 0; index < adapter->max_vports; index++) { @@ -1657,6 +1734,15 @@ unwind_vports: idpf_vport_dealloc(adapter->vports[index]); } } + /* Cleanup after vc_core_init, which has no way of knowing the + * init task failed on driver load. + */ + if (test_and_clear_bit(IDPF_HR_DRV_LOAD, adapter->flags)) { + cancel_delayed_work_sync(&adapter->serv_task); + cancel_delayed_work_sync(&adapter->mbx_task); + } + idpf_ptp_release(adapter); + clear_bit(IDPF_HR_RESET_IN_PROG, adapter->flags); } @@ -1787,27 +1873,6 @@ static int idpf_check_reset_complete(struct idpf_hw *hw, } /** - * idpf_set_vport_state - Set the vport state to be after the reset - * @adapter: Driver specific private structure - */ -static void idpf_set_vport_state(struct idpf_adapter *adapter) -{ - u16 i; - - for (i = 0; i < adapter->max_vports; i++) { - struct idpf_netdev_priv *np; - - if (!adapter->netdevs[i]) - continue; - - np = netdev_priv(adapter->netdevs[i]); - if (test_bit(IDPF_VPORT_UP, np->state)) - set_bit(IDPF_VPORT_UP_REQUESTED, - adapter->vport_config[i]->flags); - } -} - -/** * idpf_init_hard_reset - Initiate a hardware reset * @adapter: Driver specific private structure * @@ -1815,37 +1880,25 @@ static void idpf_set_vport_state(struct idpf_adapter *adapter) * reallocate. Also reinitialize the mailbox. Return 0 on success, * negative on failure. */ -static int idpf_init_hard_reset(struct idpf_adapter *adapter) +static void idpf_init_hard_reset(struct idpf_adapter *adapter) { struct idpf_reg_ops *reg_ops = &adapter->dev_ops.reg_ops; struct device *dev = &adapter->pdev->dev; - struct net_device *netdev; int err; - u16 i; + idpf_detach_and_close(adapter); mutex_lock(&adapter->vport_ctrl_lock); dev_info(dev, "Device HW Reset initiated\n"); - /* Avoid TX hangs on reset */ - for (i = 0; i < adapter->max_vports; i++) { - netdev = adapter->netdevs[i]; - if (!netdev) - continue; - - netif_carrier_off(netdev); - netif_tx_disable(netdev); - } - /* Prepare for reset */ - if (test_and_clear_bit(IDPF_HR_DRV_LOAD, adapter->flags)) { + if (test_bit(IDPF_HR_DRV_LOAD, adapter->flags)) { reg_ops->trigger_reset(adapter, IDPF_HR_DRV_LOAD); } else if (test_and_clear_bit(IDPF_HR_FUNC_RESET, adapter->flags)) { bool is_reset = idpf_is_reset_detected(adapter); idpf_idc_issue_reset_event(adapter->cdev_info); - idpf_set_vport_state(adapter); idpf_vc_core_deinit(adapter); if (!is_reset) reg_ops->trigger_reset(adapter, IDPF_HR_FUNC_RESET); @@ -1892,11 +1945,14 @@ static int idpf_init_hard_reset(struct idpf_adapter *adapter) unlock_mutex: mutex_unlock(&adapter->vport_ctrl_lock); - /* Wait until all vports are created to init RDMA CORE AUX */ - if (!err) - err = idpf_idc_init(adapter); - - return err; + /* Attempt to restore netdevs and initialize RDMA CORE AUX device, + * provided vc_core_init succeeded. It is still possible that + * vports are not allocated at this point if the init task failed. + */ + if (!err) { + idpf_attach_and_open(adapter); + idpf_idc_init(adapter); + } } /** @@ -1997,7 +2053,6 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, idpf_vport_stop(vport, false); } - idpf_deinit_rss(vport); /* We're passing in vport here because we need its wait_queue * to send a message and it should be getting all the vport * config data out of the adapter but we need to be careful not @@ -2023,6 +2078,10 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, if (err) goto err_open; + if (reset_cause == IDPF_SR_Q_CHANGE && + !netif_is_rxfh_configured(vport->netdev)) + idpf_fill_dflt_rss_lut(vport); + if (vport_is_up) err = idpf_vport_open(vport, false); @@ -2166,40 +2225,6 @@ static void idpf_set_rx_mode(struct net_device *netdev) } /** - * idpf_vport_manage_rss_lut - disable/enable RSS - * @vport: the vport being changed - * - * In the event of disable request for RSS, this function will zero out RSS - * LUT, while in the event of enable request for RSS, it will reconfigure RSS - * LUT with the default LUT configuration. - */ -static int idpf_vport_manage_rss_lut(struct idpf_vport *vport) -{ - bool ena = idpf_is_feature_ena(vport, NETIF_F_RXHASH); - struct idpf_rss_data *rss_data; - u16 idx = vport->idx; - int lut_size; - - rss_data = &vport->adapter->vport_config[idx]->user_config.rss_data; - lut_size = rss_data->rss_lut_size * sizeof(u32); - - if (ena) { - /* This will contain the default or user configured LUT */ - memcpy(rss_data->rss_lut, rss_data->cached_lut, lut_size); - } else { - /* Save a copy of the current LUT to be restored later if - * requested. - */ - memcpy(rss_data->cached_lut, rss_data->rss_lut, lut_size); - - /* Zero out the current LUT to disable */ - memset(rss_data->rss_lut, 0, lut_size); - } - - return idpf_config_rss(vport); -} - -/** * idpf_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted * @features: the feature set that the stack is suggesting @@ -2224,10 +2249,19 @@ static int idpf_set_features(struct net_device *netdev, } if (changed & NETIF_F_RXHASH) { + struct idpf_netdev_priv *np = netdev_priv(netdev); + netdev->features ^= NETIF_F_RXHASH; - err = idpf_vport_manage_rss_lut(vport); - if (err) - goto unlock_mutex; + + /* If the interface is not up when changing the rxhash, update + * to the HW is skipped. The updated LUT will be committed to + * the HW when the interface is brought up. + */ + if (test_bit(IDPF_VPORT_UP, np->state)) { + err = idpf_config_rss(vport); + if (err) + goto unlock_mutex; + } } if (changed & NETIF_F_GRO_HW) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c index 3e1052d070cf..0a8b50350b86 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c @@ -108,11 +108,11 @@ static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter, ptp_read_system_prets(sts); idpf_ptp_enable_shtime(adapter); + lo = readl(ptp->dev_clk_regs.dev_clk_ns_l); /* Read the system timestamp post PHC read */ ptp_read_system_postts(sts); - lo = readl(ptp->dev_clk_regs.dev_clk_ns_l); hi = readl(ptp->dev_clk_regs.dev_clk_ns_h); spin_unlock(&ptp->read_dev_clk_lock); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 1d91c56f7469..f58f616d87fc 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -695,9 +695,10 @@ err: static int idpf_rx_bufs_init_singleq(struct idpf_rx_queue *rxq) { struct libeth_fq fq = { - .count = rxq->desc_count, - .type = LIBETH_FQE_MTU, - .nid = idpf_q_vector_to_mem(rxq->q_vector), + .count = rxq->desc_count, + .type = LIBETH_FQE_MTU, + .buf_len = IDPF_RX_MAX_BUF_SZ, + .nid = idpf_q_vector_to_mem(rxq->q_vector), }; int ret; @@ -754,6 +755,7 @@ static int idpf_rx_bufs_init(struct idpf_buf_queue *bufq, .truesize = bufq->truesize, .count = bufq->desc_count, .type = type, + .buf_len = IDPF_RX_MAX_BUF_SZ, .hsplit = idpf_queue_has(HSPLIT_EN, bufq), .xdp = idpf_xdp_enabled(bufq->q_vector->vport), .nid = idpf_q_vector_to_mem(bufq->q_vector), @@ -3939,7 +3941,7 @@ static void idpf_update_dim_sample(struct idpf_q_vector *q_vector, static void idpf_net_dim(struct idpf_q_vector *q_vector) { struct dim_sample dim_sample = { }; - u64 packets, bytes; + u64 packets, bytes, pkts, bts; u32 i; if (!IDPF_ITR_IS_DYNAMIC(q_vector->tx_intr_mode)) @@ -3951,9 +3953,12 @@ static void idpf_net_dim(struct idpf_q_vector *q_vector) do { start = u64_stats_fetch_begin(&txq->stats_sync); - packets += u64_stats_read(&txq->q_stats.packets); - bytes += u64_stats_read(&txq->q_stats.bytes); + pkts = u64_stats_read(&txq->q_stats.packets); + bts = u64_stats_read(&txq->q_stats.bytes); } while (u64_stats_fetch_retry(&txq->stats_sync, start)); + + packets += pkts; + bytes += bts; } idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->tx_dim, @@ -3970,9 +3975,12 @@ check_rx_itr: do { start = u64_stats_fetch_begin(&rxq->stats_sync); - packets += u64_stats_read(&rxq->q_stats.packets); - bytes += u64_stats_read(&rxq->q_stats.bytes); + pkts = u64_stats_read(&rxq->q_stats.packets); + bts = u64_stats_read(&rxq->q_stats.bytes); } while (u64_stats_fetch_retry(&rxq->stats_sync, start)); + + packets += pkts; + bytes += bts; } idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->rx_dim, @@ -4641,7 +4649,7 @@ int idpf_config_rss(struct idpf_vport *vport) * idpf_fill_dflt_rss_lut - Fill the indirection table with the default values * @vport: virtual port structure */ -static void idpf_fill_dflt_rss_lut(struct idpf_vport *vport) +void idpf_fill_dflt_rss_lut(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; u16 num_active_rxq = vport->num_rxq; @@ -4650,57 +4658,47 @@ static void idpf_fill_dflt_rss_lut(struct idpf_vport *vport) rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; - for (i = 0; i < rss_data->rss_lut_size; i++) { + for (i = 0; i < rss_data->rss_lut_size; i++) rss_data->rss_lut[i] = i % num_active_rxq; - rss_data->cached_lut[i] = rss_data->rss_lut[i]; - } } /** - * idpf_init_rss - Allocate and initialize RSS resources + * idpf_init_rss_lut - Allocate and initialize RSS LUT * @vport: virtual port * - * Return 0 on success, negative on failure + * Return: 0 on success, negative on failure */ -int idpf_init_rss(struct idpf_vport *vport) +int idpf_init_rss_lut(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; struct idpf_rss_data *rss_data; - u32 lut_size; rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + if (!rss_data->rss_lut) { + u32 lut_size; - lut_size = rss_data->rss_lut_size * sizeof(u32); - rss_data->rss_lut = kzalloc(lut_size, GFP_KERNEL); - if (!rss_data->rss_lut) - return -ENOMEM; - - rss_data->cached_lut = kzalloc(lut_size, GFP_KERNEL); - if (!rss_data->cached_lut) { - kfree(rss_data->rss_lut); - rss_data->rss_lut = NULL; - - return -ENOMEM; + lut_size = rss_data->rss_lut_size * sizeof(u32); + rss_data->rss_lut = kzalloc(lut_size, GFP_KERNEL); + if (!rss_data->rss_lut) + return -ENOMEM; } /* Fill the default RSS lut values */ idpf_fill_dflt_rss_lut(vport); - return idpf_config_rss(vport); + return 0; } /** - * idpf_deinit_rss - Release RSS resources + * idpf_deinit_rss_lut - Release RSS LUT * @vport: virtual port */ -void idpf_deinit_rss(struct idpf_vport *vport) +void idpf_deinit_rss_lut(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; struct idpf_rss_data *rss_data; rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; - kfree(rss_data->cached_lut); - rss_data->cached_lut = NULL; kfree(rss_data->rss_lut); rss_data->rss_lut = NULL; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 75b977094741..423cc9486dce 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -101,6 +101,7 @@ do { \ idx = 0; \ } while (0) +#define IDPF_RX_MAX_BUF_SZ (16384 - 128) #define IDPF_RX_BUF_STRIDE 32 #define IDPF_RX_BUF_POST_STRIDE 16 #define IDPF_LOW_WATERMARK 64 @@ -1085,9 +1086,10 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector); void idpf_vport_intr_deinit(struct idpf_vport *vport); int idpf_vport_intr_init(struct idpf_vport *vport); void idpf_vport_intr_ena(struct idpf_vport *vport); +void idpf_fill_dflt_rss_lut(struct idpf_vport *vport); int idpf_config_rss(struct idpf_vport *vport); -int idpf_init_rss(struct idpf_vport *vport); -void idpf_deinit_rss(struct idpf_vport *vport); +int idpf_init_rss_lut(struct idpf_vport *vport); +void idpf_deinit_rss_lut(struct idpf_vport *vport); int idpf_rx_bufs_init_all(struct idpf_vport *vport); struct idpf_q_vector *idpf_find_rxq_vec(const struct idpf_vport *vport, diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index 44cd4b466c48..cb702eac86c8 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -1016,6 +1016,9 @@ static int idpf_send_get_lan_memory_regions(struct idpf_adapter *adapter) struct idpf_vc_xn_params xn_params = { .vc_op = VIRTCHNL2_OP_GET_LAN_MEMORY_REGIONS, .recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN, + .send_buf.iov_len = + sizeof(struct virtchnl2_get_lan_memory_regions) + + sizeof(struct virtchnl2_mem_region), .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, }; int num_regions, size; @@ -1028,6 +1031,8 @@ static int idpf_send_get_lan_memory_regions(struct idpf_adapter *adapter) return -ENOMEM; xn_params.recv_buf.iov_base = rcvd_regions; + rcvd_regions->num_memory_regions = cpu_to_le16(1); + xn_params.send_buf.iov_base = rcvd_regions; reply_sz = idpf_vc_xn_exec(adapter, &xn_params); if (reply_sz < 0) return reply_sz; @@ -2799,6 +2804,10 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport) * @vport: virtual port data structure * @get: flag to set or get rss look up table * + * When rxhash is disabled, RSS LUT will be configured with zeros. If rxhash + * is enabled, the LUT values stored in driver's soft copy will be used to setup + * the HW. + * * Returns 0 on success, negative on failure. */ int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get) @@ -2809,10 +2818,12 @@ int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get) struct idpf_rss_data *rss_data; int buf_size, lut_buf_size; ssize_t reply_sz; + bool rxhash_ena; int i; rss_data = &vport->adapter->vport_config[vport->idx]->user_config.rss_data; + rxhash_ena = idpf_is_feature_ena(vport, NETIF_F_RXHASH); buf_size = struct_size(rl, lut, rss_data->rss_lut_size); rl = kzalloc(buf_size, GFP_KERNEL); if (!rl) @@ -2834,7 +2845,8 @@ int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get) } else { rl->lut_entries = cpu_to_le16(rss_data->rss_lut_size); for (i = 0; i < rss_data->rss_lut_size; i++) - rl->lut[i] = cpu_to_le32(rss_data->rss_lut[i]); + rl->lut[i] = rxhash_ena ? + cpu_to_le32(rss_data->rss_lut[i]) : 0; xn_params.vc_op = VIRTCHNL2_OP_SET_RSS_LUT; } @@ -3565,6 +3577,7 @@ init_failed: */ void idpf_vc_core_deinit(struct idpf_adapter *adapter) { + struct idpf_hw *hw = &adapter->hw; bool remove_in_prog; if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags)) @@ -3588,6 +3601,9 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter) idpf_vport_params_buf_rel(adapter); + kfree(hw->lan_regs); + hw->lan_regs = NULL; + kfree(adapter->vports); adapter->vports = NULL; diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 498ba1522ca4..9482ab11f050 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -443,9 +443,10 @@ #define IGC_TXPBSIZE_DEFAULT ( \ IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \ IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4)) +/* TSN value following I225/I226 SW User Manual Section 7.5.4 */ #define IGC_TXPBSIZE_TSN ( \ - IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \ - IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4)) + IGC_TXPB0SIZE(5) | IGC_TXPB1SIZE(5) | IGC_TXPB2SIZE(5) | \ + IGC_TXPB3SIZE(5) | IGC_OS2BMCPBSIZE(4)) #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index e94c1922b97a..3172cdbca9cc 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1565,8 +1565,8 @@ static int igc_ethtool_set_channels(struct net_device *netdev, if (ch->other_count != NON_Q_VECTORS) return -EINVAL; - /* Do not allow channel reconfiguration when mqprio is enabled */ - if (adapter->strict_priority_enable) + /* Do not allow channel reconfiguration when any TSN qdisc is enabled */ + if (adapter->flags & IGC_FLAG_TSN_ANY_ENABLED) return -EINVAL; /* Verify the number of channels doesn't exceed hw limits */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 7aafa60ba0c8..89a321a344d2 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7759,6 +7759,11 @@ int igc_reinit_queues(struct igc_adapter *adapter) if (netif_running(netdev)) err = igc_open(netdev); + if (!err) { + /* Restore default IEEE 802.1Qbv schedule after queue reinit */ + igc_tsn_clear_schedule(adapter); + } + return err; } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index b7b46d863bee..7aae83c108fd 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -774,36 +774,43 @@ static void igc_ptp_tx_reg_to_stamp(struct igc_adapter *adapter, static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + u32 txstmpl_old; u64 regval; u32 mask; int i; + /* Establish baseline of TXSTMPL_0 before checking TXTT_0. + * This baseline is used to detect if a new timestamp arrives in + * register 0 during the hardware bug workaround below. + */ + txstmpl_old = rd32(IGC_TXSTMPL); + mask = rd32(IGC_TSYNCTXCTL) & IGC_TSYNCTXCTL_TXTT_ANY; if (mask & IGC_TSYNCTXCTL_TXTT_0) { regval = rd32(IGC_TXSTMPL); regval |= (u64)rd32(IGC_TXSTMPH) << 32; } else { - /* There's a bug in the hardware that could cause - * missing interrupts for TX timestamping. The issue - * is that for new interrupts to be triggered, the - * IGC_TXSTMPH_0 register must be read. + /* TXTT_0 not set - register 0 has no new timestamp initially. + * + * Hardware bug: Future timestamp interrupts won't fire unless + * TXSTMPH_0 is read, even if the timestamp was captured in + * registers 1-3. * - * To avoid discarding a valid timestamp that just - * happened at the "wrong" time, we need to confirm - * that there was no timestamp captured, we do that by - * assuming that no two timestamps in sequence have - * the same nanosecond value. + * Workaround: Read TXSTMPH_0 here to enable future interrupts. + * However, this read clears TXTT_0. If a timestamp arrives in + * register 0 after checking TXTT_0 but before this read, it + * would be lost. * - * So, we read the "low" register, read the "high" - * register (to latch a new timestamp) and read the - * "low" register again, if "old" and "new" versions - * of the "low" register are different, a valid - * timestamp was captured, we can read the "high" - * register again. + * To detect this race: We saved a baseline read of TXSTMPL_0 + * before TXTT_0 check. After performing the workaround read of + * TXSTMPH_0, we read TXSTMPL_0 again. Since consecutive + * timestamps never share the same nanosecond value, a change + * between the baseline and new TXSTMPL_0 indicates a timestamp + * arrived during the race window. If so, read the complete + * timestamp. */ - u32 txstmpl_old, txstmpl_new; + u32 txstmpl_new; - txstmpl_old = rd32(IGC_TXSTMPL); rd32(IGC_TXSTMPH); txstmpl_new = rd32(IGC_TXSTMPL); @@ -818,7 +825,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) done: /* Now that the problematic first register was handled, we can - * use retrieve the timestamps from the other registers + * retrieve the timestamps from the other registers * (starting from '1') with less complications. */ for (i = 1; i < IGC_MAX_TX_TSTAMP_REGS; i++) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 034618e79169..c58051e4350b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -11468,20 +11468,17 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) */ static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter) { - struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; struct ixgbe_hw *hw = &adapter->hw; - bool disable_dev; int err = -EIO; if (hw->mac.type != ixgbe_mac_e610) - goto clean_up_probe; + return err; ixgbe_get_hw_control(adapter); - mutex_init(&hw->aci.lock); err = ixgbe_get_flash_data(&adapter->hw); if (err) - goto shutdown_aci; + goto err_release_hw_control; timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); INIT_WORK(&adapter->service_task, ixgbe_recovery_service_task); @@ -11504,16 +11501,8 @@ static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter) devl_unlock(adapter->devlink); return 0; -shutdown_aci: - mutex_destroy(&adapter->hw.aci.lock); +err_release_hw_control: ixgbe_release_hw_control(adapter); -clean_up_probe: - disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); - free_netdev(netdev); - devlink_free(adapter->devlink); - pci_release_mem_regions(pdev); - if (disable_dev) - pci_disable_device(pdev); return err; } @@ -11655,8 +11644,13 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_sw_init; - if (ixgbe_check_fw_error(adapter)) - return ixgbe_recovery_probe(adapter); + if (ixgbe_check_fw_error(adapter)) { + err = ixgbe_recovery_probe(adapter); + if (err) + goto err_sw_init; + + return 0; + } if (adapter->hw.mac.type == ixgbe_mac_e610) { err = ixgbe_get_caps(&adapter->hw); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 44b201817d94..c116da7d7f18 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1389,7 +1389,7 @@ int mvpp2_ethtool_cls_rule_ins(struct mvpp2_port *port, efs->rule.flow_type = mvpp2_cls_ethtool_flow_to_type(info->fs.flow_type); if (efs->rule.flow_type < 0) { ret = efs->rule.flow_type; - goto clean_rule; + goto clean_eth_rule; } ret = mvpp2_cls_rfs_parse_rule(&efs->rule); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index bcea3fc26a8c..57db7ea2f5be 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1338,7 +1338,7 @@ int octep_device_setup(struct octep_device *oct) ret = octep_ctrl_net_init(oct); if (ret) - return ret; + goto unsupported_dev; INIT_WORK(&oct->tx_timeout_task, octep_tx_timeout_task); INIT_WORK(&oct->ctrl_mbox_task, octep_ctrl_mbox_task); diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c index 420c3f4cf741..1d9760b4b8f4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c @@ -218,7 +218,7 @@ static int octep_vf_request_irqs(struct octep_vf_device *oct) ioq_irq_err: while (i) { --i; - free_irq(oct->msix_entries[i].vector, oct); + free_irq(oct->msix_entries[i].vector, oct->ioq_vector[i]); } return -1; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 2d78e08f985f..747fbdf2a908 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1551,8 +1551,8 @@ static int rvu_get_attach_blkaddr(struct rvu *rvu, int blktype, return -ENODEV; } -static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, - int num_lfs, struct rsrc_attach *attach) +static int rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, + int num_lfs, struct rsrc_attach *attach) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct rvu_hwinfo *hw = rvu->hw; @@ -1562,21 +1562,21 @@ static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, u64 cfg; if (!num_lfs) - return; + return -EINVAL; blkaddr = rvu_get_attach_blkaddr(rvu, blktype, pcifunc, attach); if (blkaddr < 0) - return; + return -EFAULT; block = &hw->block[blkaddr]; if (!block->lf.bmap) - return; + return -ESRCH; for (slot = 0; slot < num_lfs; slot++) { /* Allocate the resource */ lf = rvu_alloc_rsrc(&block->lf); if (lf < 0) - return; + return -EFAULT; cfg = (1ULL << 63) | (pcifunc << 8) | slot; rvu_write64(rvu, blkaddr, block->lfcfg_reg | @@ -1587,6 +1587,8 @@ static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, /* Set start MSIX vector for this LF within this PF/VF */ rvu_set_msix_offset(rvu, pfvf, block, lf); } + + return 0; } static int rvu_check_rsrc_availability(struct rvu *rvu, @@ -1724,22 +1726,31 @@ int rvu_mbox_handler_attach_resources(struct rvu *rvu, int err; /* If first request, detach all existing attached resources */ - if (!attach->modify) - rvu_detach_rsrcs(rvu, NULL, pcifunc); + if (!attach->modify) { + err = rvu_detach_rsrcs(rvu, NULL, pcifunc); + if (err) + return err; + } mutex_lock(&rvu->rsrc_lock); /* Check if the request can be accommodated */ err = rvu_check_rsrc_availability(rvu, attach, pcifunc); if (err) - goto exit; + goto fail1; /* Now attach the requested resources */ - if (attach->npalf) - rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1, attach); + if (attach->npalf) { + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1, attach); + if (err) + goto fail1; + } - if (attach->nixlf) - rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1, attach); + if (attach->nixlf) { + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1, attach); + if (err) + goto fail2; + } if (attach->sso) { /* RVU func doesn't know which exact LF or slot is attached @@ -1749,33 +1760,64 @@ int rvu_mbox_handler_attach_resources(struct rvu *rvu, */ if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_SSO); - rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, - attach->sso, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, + attach->sso, attach); + if (err) + goto fail3; } if (attach->ssow) { if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_SSOW); - rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, - attach->ssow, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, + attach->ssow, attach); + if (err) + goto fail4; } if (attach->timlfs) { if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_TIM); - rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, - attach->timlfs, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, + attach->timlfs, attach); + if (err) + goto fail5; } if (attach->cptlfs) { if (attach->modify && rvu_attach_from_same_block(rvu, BLKTYPE_CPT, attach)) rvu_detach_block(rvu, pcifunc, BLKTYPE_CPT); - rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, - attach->cptlfs, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, + attach->cptlfs, attach); + if (err) + goto fail6; } -exit: + mutex_unlock(&rvu->rsrc_lock); + return 0; + +fail6: + if (attach->timlfs) + rvu_detach_block(rvu, pcifunc, BLKTYPE_TIM); + +fail5: + if (attach->ssow) + rvu_detach_block(rvu, pcifunc, BLKTYPE_SSOW); + +fail4: + if (attach->sso) + rvu_detach_block(rvu, pcifunc, BLKTYPE_SSO); + +fail3: + if (attach->nixlf) + rvu_detach_block(rvu, pcifunc, BLKTYPE_NIX); + +fail2: + if (attach->npalf) + rvu_detach_block(rvu, pcifunc, BLKTYPE_NPA); + +fail1: mutex_unlock(&rvu->rsrc_lock); return err; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 3abd750a4bd7..3d91a34f8b57 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -1222,6 +1222,9 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, u8 cgx_idx, lmac; void *cgxd; + if (!rvu->fwdata) + return LMAC_AF_ERR_FIRMWARE_DATA_NOT_MAPPED; + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) return -EPERM; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c index e4a5f9fa6fd4..bbfd8231aed5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c @@ -56,7 +56,7 @@ int rvu_sdp_init(struct rvu *rvu) struct rvu_pfvf *pfvf; u32 i = 0; - if (rvu->fwdata->channel_data.valid) { + if (rvu->fwdata && rvu->fwdata->channel_data.valid) { sdp_pf_num[0] = 0; pfvf = &rvu->pf[sdp_pf_num[0]]; pfvf->sdp_info = &rvu->fwdata->channel_data.info; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 4c7e0f345cb5..060c715ebad0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -328,7 +328,7 @@ static int cn10k_mcs_write_rx_flowid(struct otx2_nic *pfvf, req->data[0] = FIELD_PREP(MCS_TCAM0_MAC_DA_MASK, mac_da); req->mask[0] = ~0ULL; - req->mask[0] = ~MCS_TCAM0_MAC_DA_MASK; + req->mask[0] &= ~MCS_TCAM0_MAC_DA_MASK; req->data[1] = FIELD_PREP(MCS_TCAM1_ETYPE_MASK, ETH_P_MACSEC); req->mask[1] = ~0ULL; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index e616a727a3a9..8cdfc36d79d2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -940,13 +940,8 @@ static inline dma_addr_t otx2_dma_map_page(struct otx2_nic *pfvf, size_t offset, size_t size, enum dma_data_direction dir) { - dma_addr_t iova; - - iova = dma_map_page_attrs(pfvf->dev, page, + return dma_map_page_attrs(pfvf->dev, page, offset, size, dir, DMA_ATTR_SKIP_CPU_SYNC); - if (unlikely(dma_mapping_error(pfvf->dev, iova))) - return (dma_addr_t)NULL; - return iova; } static inline void otx2_dma_unmap_page(struct otx2_nic *pfvf, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index b90e23dc49de..b6449f0a9e7d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -418,6 +418,14 @@ static int otx2_set_ringparam(struct net_device *netdev, */ if (rx_count < pfvf->hw.rq_skid) rx_count = pfvf->hw.rq_skid; + + if (ring->rx_pending < 16) { + netdev_err(netdev, + "rx ring size %u invalid, min is 16\n", + ring->rx_pending); + return -EINVAL; + } + rx_count = Q_COUNT(Q_SIZE(rx_count, 3)); /* Due pipelining impact minimum 2000 unused SQ CQE's diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index a7feb4c392b3..6b2d8559f0eb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -3249,7 +3249,9 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->watchdog_timeo = OTX2_TX_TIMEOUT; netdev->netdev_ops = &otx2_netdev_ops; - netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; netdev->min_mtu = OTX2_MIN_MTU; netdev->max_mtu = otx2_get_max_mtu(pf); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index 2a4c9df4eb79..e63d95c1842f 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -387,6 +387,8 @@ struct prestera_switch *prestera_devlink_alloc(struct prestera_device *dev) dl = devlink_alloc(&prestera_dl_ops, sizeof(struct prestera_switch), dev->dev); + if (!dl) + return NULL; return devlink_priv(dl); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 36806e813c33..1301c56e20d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -613,3 +613,19 @@ void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) cq->dbg = NULL; } } + +static int vhca_id_show(struct seq_file *file, void *priv) +{ + struct mlx5_core_dev *dev = file->private; + + seq_printf(file, "0x%x\n", MLX5_CAP_GEN(dev, vhca_id)); + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(vhca_id); + +void mlx5_vhca_debugfs_init(struct mlx5_core_dev *dev) +{ + debugfs_create_file("vhca_id", 0400, dev->priv.dbg.dbg_root, dev, + &vhca_id_fops); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 64c04f52990f..781e39b5aa1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -575,3 +575,17 @@ bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev return plen && flen && flen == plen && !memcmp(fsystem_guid, psystem_guid, flen); } + +void mlx5_core_reps_aux_devs_remove(struct mlx5_core_dev *dev) +{ + struct mlx5_priv *priv = &dev->priv; + + if (priv->adev[MLX5_INTERFACE_PROTOCOL_ETH]) + device_lock_assert(&priv->adev[MLX5_INTERFACE_PROTOCOL_ETH]->adev.dev); + else + mlx5_core_err(dev, "ETH driver already removed\n"); + if (priv->adev[MLX5_INTERFACE_PROTOCOL_IB_REP]) + del_adev(&priv->adev[MLX5_INTERFACE_PROTOCOL_IB_REP]->adev); + if (priv->adev[MLX5_INTERFACE_PROTOCOL_ETH_REP]) + del_adev(&priv->adev[MLX5_INTERFACE_PROTOCOL_ETH_REP]->adev); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 262dc032e276..ff4ab4691baf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -962,7 +962,7 @@ struct mlx5e_priv { }; struct mlx5e_dev { - struct mlx5e_priv *priv; + struct net_device *netdev; struct devlink_port dl_port; }; @@ -1242,10 +1242,13 @@ struct net_device * mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile); int mlx5e_attach_netdev(struct mlx5e_priv *priv); void mlx5e_detach_netdev(struct mlx5e_priv *priv); -void mlx5e_destroy_netdev(struct mlx5e_priv *priv); -int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, - const struct mlx5e_profile *new_profile, void *new_ppriv); -void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv); +void mlx5e_destroy_netdev(struct net_device *netdev); +int mlx5e_netdev_change_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, + void *new_ppriv); +void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev); void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv); void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index a8fb4bec369c..9c7064187ed0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -430,7 +430,8 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, attrs->replay_esn.esn = sa_entry->esn_state.esn; attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb; attrs->replay_esn.overlap = sa_entry->esn_state.overlap; - if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT || + x->xso.type != XFRM_DEV_OFFLOAD_PACKET) goto skip_replay_window; switch (x->replay_esn->replay_window) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c index 38e7c77cc851..9a74438ce10a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c @@ -44,6 +44,7 @@ struct mlx5e_accel_fs_psp_prot { struct mlx5_flow_table *ft; struct mlx5_flow_group *miss_group; struct mlx5_flow_handle *miss_rule; + struct mlx5_modify_hdr *rx_modify_hdr; struct mlx5_flow_destination default_dest; struct mlx5e_psp_rx_err rx_err; u32 refcnt; @@ -286,13 +287,19 @@ out_err: return err; } -static void accel_psp_fs_rx_fs_destroy(struct mlx5e_accel_fs_psp_prot *fs_prot) +static void accel_psp_fs_rx_fs_destroy(struct mlx5e_psp_fs *fs, + struct mlx5e_accel_fs_psp_prot *fs_prot) { if (fs_prot->def_rule) { mlx5_del_flow_rules(fs_prot->def_rule); fs_prot->def_rule = NULL; } + if (fs_prot->rx_modify_hdr) { + mlx5_modify_header_dealloc(fs->mdev, fs_prot->rx_modify_hdr); + fs_prot->rx_modify_hdr = NULL; + } + if (fs_prot->miss_rule) { mlx5_del_flow_rules(fs_prot->miss_rule); fs_prot->miss_rule = NULL; @@ -396,6 +403,7 @@ static int accel_psp_fs_rx_create_ft(struct mlx5e_psp_fs *fs, modify_hdr = NULL; goto out_err; } + fs_prot->rx_modify_hdr = modify_hdr; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_CRYPTO_DECRYPT | @@ -416,7 +424,7 @@ static int accel_psp_fs_rx_create_ft(struct mlx5e_psp_fs *fs, goto out; out_err: - accel_psp_fs_rx_fs_destroy(fs_prot); + accel_psp_fs_rx_fs_destroy(fs, fs_prot); out: kvfree(flow_group_in); kvfree(spec); @@ -433,7 +441,7 @@ static int accel_psp_fs_rx_destroy(struct mlx5e_psp_fs *fs, enum accel_fs_psp_ty /* The netdev unreg already happened, so all offloaded rule are already removed */ fs_prot = &accel_psp->fs_prot[type]; - accel_psp_fs_rx_fs_destroy(fs_prot); + accel_psp_fs_rx_fs_destroy(fs, fs_prot); accel_psp_fs_rx_err_destroy_ft(fs, &fs_prot->rx_err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c index c17ea0fcd8ef..ef7f5338540f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c @@ -177,8 +177,6 @@ bool mlx5e_psp_handle_tx_skb(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct net *net = sock_net(skb->sk); - const struct ipv6hdr *ip6; - struct tcphdr *th; if (!mlx5e_psp_set_state(priv, skb, psp_st)) return true; @@ -190,11 +188,18 @@ bool mlx5e_psp_handle_tx_skb(struct net_device *netdev, return false; } if (skb_is_gso(skb)) { - ip6 = ipv6_hdr(skb); - th = inner_tcp_hdr(skb); + int len = skb_shinfo(skb)->gso_size + inner_tcp_hdrlen(skb); + struct tcphdr *th = inner_tcp_hdr(skb); - th->check = ~tcp_v6_check(skb_shinfo(skb)->gso_size + inner_tcp_hdrlen(skb), &ip6->saddr, - &ip6->daddr, 0); + if (skb->protocol == htons(ETH_P_IP)) { + const struct iphdr *ip = ip_hdr(skb); + + th->check = ~tcp_v4_check(len, ip->saddr, ip->daddr, 0); + } else { + const struct ipv6hdr *ip6 = ipv6_hdr(skb); + + th->check = ~tcp_v6_check(len, &ip6->saddr, &ip6->daddr, 0); + } } return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 07fc4d2c8fad..4b2963bbe7ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4052,6 +4052,8 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) mlx5e_queue_update_stats(priv); } + netdev_stats_to_stats64(stats, &dev->stats); + if (mlx5e_is_uplink_rep(priv)) { struct mlx5e_vport_stats *vstats = &priv->stats.vport; @@ -4068,21 +4070,21 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) mlx5e_fold_sw_stats64(priv, stats); } - stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer; - stats->rx_dropped = PPORT_2863_GET(pstats, if_in_discards); + stats->rx_missed_errors += priv->stats.qcnt.rx_out_of_buffer; + stats->rx_dropped += PPORT_2863_GET(pstats, if_in_discards); - stats->rx_length_errors = + stats->rx_length_errors += PPORT_802_3_GET(pstats, a_in_range_length_errors) + PPORT_802_3_GET(pstats, a_out_of_range_length_field) + PPORT_802_3_GET(pstats, a_frame_too_long_errors) + VNIC_ENV_GET(&priv->stats.vnic, eth_wqe_too_small); - stats->rx_crc_errors = + stats->rx_crc_errors += PPORT_802_3_GET(pstats, a_frame_check_sequence_errors); - stats->rx_frame_errors = PPORT_802_3_GET(pstats, a_alignment_errors); - stats->tx_aborted_errors = PPORT_2863_GET(pstats, if_out_discards); - stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors + - stats->rx_frame_errors; - stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors; + stats->rx_frame_errors += PPORT_802_3_GET(pstats, a_alignment_errors); + stats->tx_aborted_errors += PPORT_2863_GET(pstats, if_out_discards); + stats->rx_errors += stats->rx_length_errors + stats->rx_crc_errors + + stats->rx_frame_errors; + stats->tx_errors += stats->tx_aborted_errors + stats->tx_carrier_errors; } static void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv) @@ -6325,6 +6327,7 @@ err_free_cpumask: void mlx5e_priv_cleanup(struct mlx5e_priv *priv) { + bool destroying = test_bit(MLX5E_STATE_DESTROYING, &priv->state); int i; /* bail if change profile failed and also rollback failed */ @@ -6352,6 +6355,8 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) } memset(priv, 0, sizeof(*priv)); + if (destroying) /* restore destroying bit, to allow unload */ + set_bit(MLX5E_STATE_DESTROYING, &priv->state); } static unsigned int mlx5e_get_max_num_txqs(struct mlx5_core_dev *mdev, @@ -6584,19 +6589,28 @@ profile_cleanup: return err; } -int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, - const struct mlx5e_profile *new_profile, void *new_ppriv) +int mlx5e_netdev_change_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, + void *new_ppriv) { - const struct mlx5e_profile *orig_profile = priv->profile; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; - void *orig_ppriv = priv->ppriv; + struct mlx5e_priv *priv = netdev_priv(netdev); + const struct mlx5e_profile *orig_profile; int err, rollback_err; + void *orig_ppriv; - /* cleanup old profile */ - mlx5e_detach_netdev(priv); - priv->profile->cleanup(priv); - mlx5e_priv_cleanup(priv); + orig_profile = priv->profile; + orig_ppriv = priv->ppriv; + + /* NULL could happen if previous change_profile failed to rollback */ + if (priv->profile) { + WARN_ON_ONCE(priv->mdev != mdev); + /* cleanup old profile */ + mlx5e_detach_netdev(priv); + priv->profile->cleanup(priv); + mlx5e_priv_cleanup(priv); + } + /* priv members are not valid from this point ... */ if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); @@ -6613,23 +6627,33 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, return 0; rollback: + if (!orig_profile) { + netdev_warn(netdev, "no original profile to rollback to\n"); + priv->profile = NULL; + return err; + } + rollback_err = mlx5e_netdev_attach_profile(netdev, mdev, orig_profile, orig_ppriv); - if (rollback_err) - netdev_err(netdev, "%s: failed to rollback to orig profile, %d\n", - __func__, rollback_err); + if (rollback_err) { + netdev_err(netdev, "failed to rollback to orig profile, %d\n", + rollback_err); + priv->profile = NULL; + } return err; } -void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv) +void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev) { - mlx5e_netdev_change_profile(priv, &mlx5e_nic_profile, NULL); + mlx5e_netdev_change_profile(netdev, mdev, &mlx5e_nic_profile, NULL); } -void mlx5e_destroy_netdev(struct mlx5e_priv *priv) +void mlx5e_destroy_netdev(struct net_device *netdev) { - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); - mlx5e_priv_cleanup(priv); + if (priv->profile) + mlx5e_priv_cleanup(priv); free_netdev(netdev); } @@ -6637,8 +6661,8 @@ static int _mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; struct mlx5_core_dev *mdev = edev->mdev; struct mlx5_core_dev *pos, *to; int err, i; @@ -6684,10 +6708,11 @@ static int mlx5e_resume(struct auxiliary_device *adev) static int _mlx5e_suspend(struct auxiliary_device *adev, bool pre_netdev_reg) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5_core_dev *mdev = edev->mdev; struct mlx5_core_dev *pos; int i; @@ -6748,11 +6773,11 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_devlink_port_unregister; } SET_NETDEV_DEVLINK_PORT(netdev, &mlx5e_dev->dl_port); + mlx5e_dev->netdev = netdev; mlx5e_build_nic_netdev(netdev); priv = netdev_priv(netdev); - mlx5e_dev->priv = priv; priv->profile = profile; priv->ppriv = NULL; @@ -6785,7 +6810,7 @@ err_resume: err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); err_devlink_port_unregister: mlx5e_devlink_port_unregister(mlx5e_dev); err_devlink_unregister: @@ -6815,17 +6840,21 @@ static void _mlx5e_remove(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = edev->mdev; + mlx5_eswitch_safe_aux_devs_remove(mdev); mlx5_core_uplink_netdev_set(mdev, NULL); - mlx5e_dcbnl_delete_app(priv); + + if (priv->profile) + mlx5e_dcbnl_delete_app(priv); /* When unload driver, the netdev is in registered state * if it's from legacy mode. If from switchdev mode, it * is already unregistered before changing to NIC profile. */ - if (priv->netdev->reg_state == NETREG_REGISTERED) { - unregister_netdev(priv->netdev); + if (netdev->reg_state == NETREG_REGISTERED) { + unregister_netdev(netdev); _mlx5e_suspend(adev, false); } else { struct mlx5_core_dev *pos; @@ -6840,7 +6869,7 @@ static void _mlx5e_remove(struct auxiliary_device *adev) /* Avoid cleanup if profile rollback failed. */ if (priv->profile) priv->profile->cleanup(priv); - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); mlx5e_devlink_port_unregister(mlx5e_dev); mlx5e_destroy_devlink(mlx5e_dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index ee9595109649..6eec88fa6d10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1508,17 +1508,16 @@ mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep * { struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev; - struct mlx5e_priv *priv; int err; netdev = mlx5_uplink_netdev_get(dev); if (!netdev) return 0; - priv = netdev_priv(netdev); - rpriv->netdev = priv->netdev; - err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); + /* must not use netdev_priv(netdev), it might not be initialized yet */ + rpriv->netdev = netdev; + err = mlx5e_netdev_change_profile(netdev, dev, + &mlx5e_uplink_rep_profile, rpriv); mlx5_uplink_netdev_put(dev, netdev); return err; } @@ -1546,7 +1545,7 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_SWITCH_LEGACY)) unregister_netdev(netdev); - mlx5e_netdev_attach_nic_profile(priv); + mlx5e_netdev_attach_nic_profile(netdev, priv->mdev); } static int @@ -1612,7 +1611,7 @@ err_cleanup_profile: priv->profile->cleanup(priv); err_destroy_netdev: - mlx5e_destroy_netdev(netdev_priv(netdev)); + mlx5e_destroy_netdev(netdev); return err; } @@ -1667,7 +1666,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); free_ppriv: kvfree(ppriv); /* mlx5e_rep_priv */ } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index a2802cfc9b98..a8af84fc9763 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1608,12 +1608,13 @@ void mlx5e_stats_fec_get(struct mlx5e_priv *priv, { int mode = fec_active_mode(priv->mdev); - if (mode == MLX5E_FEC_NOFEC || - !MLX5_CAP_PCAM_FEATURE(priv->mdev, ppcnt_statistical_group)) + if (mode == MLX5E_FEC_NOFEC) return; - fec_set_corrected_bits_total(priv, fec_stats); - fec_set_block_stats(priv, mode, fec_stats); + if (MLX5_CAP_PCAM_FEATURE(priv->mdev, ppcnt_statistical_group)) { + fec_set_corrected_bits_total(priv, fec_stats); + fec_set_block_stats(priv, mode, fec_stats); + } if (MLX5_CAP_PCAM_REG(priv->mdev, pphcr)) fec_set_histograms_stats(priv, mode, hist); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index a8773b2342c2..424786f489ec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2147,11 +2147,14 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow, static void mlx5e_tc_del_fdb_peers_flow(struct mlx5e_tc_flow *flow) { + struct mlx5_devcom_comp_dev *devcom; + struct mlx5_devcom_comp_dev *pos; + struct mlx5_eswitch *peer_esw; int i; - for (i = 0; i < MLX5_MAX_PORTS; i++) { - if (i == mlx5_get_dev_index(flow->priv->mdev)) - continue; + devcom = flow->priv->mdev->priv.eswitch->devcom; + mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { + i = mlx5_get_dev_index(peer_esw->dev); mlx5e_tc_del_fdb_peer_flow(flow, i); } } @@ -5513,12 +5516,16 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags) void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw) { + struct mlx5_devcom_comp_dev *devcom; + struct mlx5_devcom_comp_dev *pos; struct mlx5e_tc_flow *flow, *tmp; + struct mlx5_eswitch *peer_esw; int i; - for (i = 0; i < MLX5_MAX_PORTS; i++) { - if (i == mlx5_get_dev_index(esw->dev)) - continue; + devcom = esw->devcom; + + mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { + i = mlx5_get_dev_index(peer_esw->dev); list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i]) mlx5e_tc_del_fdb_peers_flow(flow); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c index 1c37098e09ea..49a637829c59 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c @@ -188,7 +188,7 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, if (IS_ERR(vport->ingress.acl)) { err = PTR_ERR(vport->ingress.acl); vport->ingress.acl = NULL; - return err; + goto out; } err = esw_acl_ingress_lgcy_groups_create(esw, vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index ad1073f7b79f..714ad28e8445 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -929,6 +929,7 @@ int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_v int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev, u16 vport_num); bool mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev); +void mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } @@ -1009,9 +1010,12 @@ mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev) static inline bool mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id) { - return -EOPNOTSUPP; + return false; } +static inline void +mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev) {} + #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_ESWITCH_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index ea94a727633f..02b7e474586d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3981,6 +3981,32 @@ static bool mlx5_devlink_switchdev_active_mode_change(struct mlx5_eswitch *esw, return true; } +#define MLX5_ESW_HOLD_TIMEOUT_MS 7000 +#define MLX5_ESW_HOLD_RETRY_DELAY_MS 500 + +void mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev) +{ + unsigned long timeout; + bool hold_esw = true; + + /* Wait for any concurrent eswitch mode transition to complete. */ + if (!mlx5_esw_hold(dev)) { + timeout = jiffies + msecs_to_jiffies(MLX5_ESW_HOLD_TIMEOUT_MS); + while (!mlx5_esw_hold(dev)) { + if (!time_before(jiffies, timeout)) { + hold_esw = false; + break; + } + msleep(MLX5_ESW_HOLD_RETRY_DELAY_MS); + } + } + if (hold_esw) { + if (mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS) + mlx5_core_reps_aux_devs_remove(dev); + mlx5_esw_release(dev); + } +} + int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, struct netlink_ext_ack *extack) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index ced747bef641..c348ee62cd3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -1198,7 +1198,8 @@ int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, boo u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {}; u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {}; - if (disconnect && MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default)) + if (disconnect && + !MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default)) return -EOPNOTSUPP; MLX5_SET(set_flow_table_root_in, in, opcode, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index aee17fcf3b36..cdc99fe5c956 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -173,10 +173,15 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, } /* Handle multipath entry with lower priority value */ - if (mp->fib.mfi && mp->fib.mfi != fi && + if (mp->fib.mfi && (mp->fib.dst != fen_info->dst || mp->fib.dst_len != fen_info->dst_len) && - fi->fib_priority >= mp->fib.priority) + mp->fib.dst_len <= fen_info->dst_len && + !(mp->fib.dst_len == fen_info->dst_len && + fi->fib_priority < mp->fib.priority)) { + mlx5_core_dbg(ldev->pf[idx].dev, + "Multipath entry with lower priority was rejected\n"); return; + } nh_dev0 = mlx5_lag_get_next_fib_dev(ldev, fi, NULL); nh_dev1 = mlx5_lag_get_next_fib_dev(ldev, fi, nh_dev0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 4209da722f9a..55b4e0cceae2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1806,16 +1806,6 @@ err: return -ENOMEM; } -static int vhca_id_show(struct seq_file *file, void *priv) -{ - struct mlx5_core_dev *dev = file->private; - - seq_printf(file, "0x%x\n", MLX5_CAP_GEN(dev, vhca_id)); - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(vhca_id); - static int mlx5_notifiers_init(struct mlx5_core_dev *dev) { int err; @@ -1884,7 +1874,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev)); priv->dbg.dbg_root = debugfs_create_dir(dev_name(dev->device), mlx5_debugfs_root); - debugfs_create_file("vhca_id", 0400, priv->dbg.dbg_root, dev, &vhca_id_fops); + INIT_LIST_HEAD(&priv->traps); err = mlx5_cmd_init(dev); @@ -2022,6 +2012,8 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_init_one; } + mlx5_vhca_debugfs_init(dev); + pci_save_state(pdev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index cfebc110c02f..f2d74382fb85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -258,6 +258,7 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages); void mlx5_cmd_flush(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); +void mlx5_vhca_debugfs_init(struct mlx5_core_dev *dev); int mlx5_query_pcam_reg(struct mlx5_core_dev *dev, u32 *pcam, u8 feature_group, u8 access_reg_group); @@ -290,6 +291,7 @@ int mlx5_register_device(struct mlx5_core_dev *dev); void mlx5_unregister_device(struct mlx5_core_dev *dev); void mlx5_dev_set_lightweight(struct mlx5_core_dev *dev); bool mlx5_dev_is_lightweight(struct mlx5_core_dev *dev); +void mlx5_core_reps_aux_devs_remove(struct mlx5_core_dev *dev); void mlx5_fw_reporters_create(struct mlx5_core_dev *dev); int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 85a9e534f442..7f8bed353e67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -393,9 +393,11 @@ static int mlx5_query_mcia(struct mlx5_core_dev *dev, if (err) return err; - *status = MLX5_GET(mcia_reg, out, status); - if (*status) + if (MLX5_GET(mcia_reg, out, status)) { + if (status) + *status = MLX5_GET(mcia_reg, out, status); return -EIO; + } ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); memcpy(data, ptr, size); @@ -429,7 +431,8 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &offset); break; default: - mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id); + mlx5_core_dbg(dev, "Module ID not recognized: 0x%x\n", + module_id); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index b706f1486504..c45540fe7d9d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -76,6 +76,7 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto init_one_err; } + mlx5_vhca_debugfs_init(mdev); return 0; init_one_err: diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index efb4e412ec7e..0055c231acf6 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -481,7 +481,7 @@ static void mana_serv_reset(struct pci_dev *pdev) /* Perform PCI rescan on device if we failed on HWC */ dev_err(&pdev->dev, "MANA service: resume failed, rescanning\n"); mana_serv_rescan(pdev); - goto out; + return; } if (ret) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 08bee56aea35..c345d9b17c89 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -2307,14 +2307,16 @@ static void ocelot_set_aggr_pgids(struct ocelot *ocelot) /* Now, set PGIDs for each active LAG */ for (lag = 0; lag < ocelot->num_phys_ports; lag++) { - struct net_device *bond = ocelot->ports[lag]->bond; + struct ocelot_port *ocelot_port = ocelot->ports[lag]; int num_active_ports = 0; + struct net_device *bond; unsigned long bond_mask; u8 aggr_idx[16]; - if (!bond || (visited & BIT(lag))) + if (!ocelot_port || !ocelot_port->bond || (visited & BIT(lag))) continue; + bond = ocelot_port->bond; bond_mask = ocelot_get_bond_mask(ocelot, bond); for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) { diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 36af94a2e062..2794f75df8fc 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -1524,9 +1524,8 @@ static void rocker_world_port_post_fini(struct rocker_port *rocker_port) { struct rocker_world_ops *wops = rocker_port->rocker->wops; - if (!wops->port_post_fini) - return; - wops->port_post_fini(rocker_port); + if (wops->port_post_fini) + wops->port_post_fini(rocker_port); kfree(rocker_port->wpriv); } diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c index 6ef96292909a..3db589b90b68 100644 --- a/drivers/net/ethernet/sfc/mcdi_filters.c +++ b/drivers/net/ethernet/sfc/mcdi_filters.c @@ -2182,12 +2182,7 @@ int efx_mcdi_rx_pull_rss_context_config(struct efx_nic *efx, int efx_mcdi_rx_pull_rss_config(struct efx_nic *efx) { - int rc; - - mutex_lock(&efx->net_dev->ethtool->rss_lock); - rc = efx_mcdi_rx_pull_rss_context_config(efx, &efx->rss_context); - mutex_unlock(&efx->net_dev->ethtool->rss_lock); - return rc; + return efx_mcdi_rx_pull_rss_context_config(efx, &efx->rss_context); } void efx_mcdi_rx_restore_rss_contexts(struct efx_nic *efx) diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 9d1a83a5fa7e..d16c178d1034 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -516,15 +516,7 @@ static inline void smc_rcv(struct net_device *dev) * any other concurrent access and C would always interrupt B. But life * isn't that easy in a SMP world... */ -#define smc_special_trylock(lock, flags) \ -({ \ - int __ret; \ - local_irq_save(flags); \ - __ret = spin_trylock(lock); \ - if (!__ret) \ - local_irq_restore(flags); \ - __ret; \ -}) +#define smc_special_trylock(lock, flags) spin_trylock_irqsave(lock, flags) #define smc_special_lock(lock, flags) spin_lock_irqsave(lock, flags) #define smc_special_unlock(lock, flags) spin_unlock_irqrestore(lock, flags) #else diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c index 220eb5ce7583..88e9424d2d51 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.c +++ b/drivers/net/ethernet/spacemit/k1_emac.c @@ -1099,7 +1099,13 @@ static int emac_read_stat_cnt(struct emac_priv *priv, u8 cnt, u32 *res, 100, 10000); if (ret) { - netdev_err(priv->ndev, "Read stat timeout\n"); + /* + * This could be caused by the PHY stopping its refclk even when + * the link is up, for power saving. See also comments in + * emac_stats_update(). + */ + dev_err_ratelimited(&priv->ndev->dev, + "Read stat timeout. PHY clock stopped?\n"); return ret; } @@ -1147,17 +1153,25 @@ static void emac_stats_update(struct emac_priv *priv) assert_spin_locked(&priv->stats_lock); - if (!netif_running(priv->ndev) || !netif_device_present(priv->ndev)) { - /* Not up, don't try to update */ + /* + * We can't read statistics if the interface is not up. Also, some PHYs + * stop their reference clocks for link down power saving, which also + * causes reading statistics to time out. Don't update and don't + * reschedule in these cases. + */ + if (!netif_running(priv->ndev) || + !netif_carrier_ok(priv->ndev) || + !netif_device_present(priv->ndev)) { return; } for (i = 0; i < sizeof(priv->tx_stats) / sizeof(*tx_stats); i++) { /* - * If reading stats times out, everything is broken and there's - * nothing we can do. Reading statistics also can't return an - * error, so just return without updating and without - * rescheduling. + * If reading stats times out anyway, the stat registers will be + * stuck, and we can't really recover from that. + * + * Reading statistics also can't return an error, so just return + * without updating and without rescheduling. */ if (emac_tx_read_stat_cnt(priv, i, &res)) return; @@ -1636,6 +1650,12 @@ static void emac_adjust_link(struct net_device *dev) emac_wr(priv, MAC_GLOBAL_CONTROL, ctrl); emac_set_fc_autoneg(priv); + + /* + * Reschedule stats updates now that link is up. See comments in + * emac_stats_update(). + */ + mod_timer(&priv->stats_timer, jiffies); } phy_print_status(phydev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index da206b24aaed..3f42843cd9ed 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -89,6 +89,7 @@ MODULE_PARM_DESC(phyaddr, "Physical device address"); #define STMMAC_XDP_CONSUMED BIT(0) #define STMMAC_XDP_TX BIT(1) #define STMMAC_XDP_REDIRECT BIT(2) +#define STMMAC_XSK_CONSUMED BIT(3) static int flow_ctrl = 0xdead; module_param(flow_ctrl, int, 0644); @@ -4358,11 +4359,11 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int first_entry, tx_packets; struct stmmac_txq_stats *txq_stats; struct stmmac_tx_queue *tx_q; + bool set_ic, is_last_segment; u32 pay_len, mss, queue; int i, first_tx, nfrags; u8 proto_hdr_len, hdr; dma_addr_t des; - bool set_ic; /* Always insert VLAN tag to SKB payload for TSO frames. * @@ -4550,10 +4551,16 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) stmmac_enable_tx_timestamp(priv, first); } + /* If we only have one entry used, then the first entry is the last + * segment. + */ + is_last_segment = ((tx_q->cur_tx - first_entry) & + (priv->dma_conf.dma_tx_size - 1)) == 1; + /* Complete the first descriptor before granting the DMA */ stmmac_prepare_tso_tx_desc(priv, first, 1, proto_hdr_len, 0, 1, - tx_q->tx_skbuff_dma[first_entry].last_segment, - hdr / 4, (skb->len - proto_hdr_len)); + is_last_segment, hdr / 4, + skb->len - proto_hdr_len); /* If context desc is used to change MSS */ if (mss_desc) { @@ -5126,6 +5133,7 @@ static int stmmac_xdp_get_tx_queue(struct stmmac_priv *priv, static int stmmac_xdp_xmit_back(struct stmmac_priv *priv, struct xdp_buff *xdp) { + bool zc = !!(xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL); struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); int cpu = smp_processor_id(); struct netdev_queue *nq; @@ -5142,9 +5150,18 @@ static int stmmac_xdp_xmit_back(struct stmmac_priv *priv, /* Avoids TX time-out as we are sharing with slow path */ txq_trans_cond_update(nq); - res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, false); - if (res == STMMAC_XDP_TX) + /* For zero copy XDP_TX action, dma_map is true */ + res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, zc); + if (res == STMMAC_XDP_TX) { stmmac_flush_tx_descriptors(priv, queue); + } else if (res == STMMAC_XDP_CONSUMED && zc) { + /* xdp has been freed by xdp_convert_buff_to_frame(), + * no need to call xsk_buff_free() again, so return + * STMMAC_XSK_CONSUMED. + */ + res = STMMAC_XSK_CONSUMED; + xdp_return_frame(xdpf); + } __netif_tx_unlock(nq); @@ -5494,6 +5511,8 @@ read_again: break; case STMMAC_XDP_CONSUMED: xsk_buff_free(buf->xdp); + fallthrough; + case STMMAC_XSK_CONSUMED: rx_dropped++; break; case STMMAC_XDP_TX: diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index d138dea7d208..ec278f99d295 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -21,6 +21,7 @@ config LIBWX depends on PTP_1588_CLOCK_OPTIONAL select PAGE_POOL select DIMLIB + select PHYLINK help Common library for Wangxun(R) Ethernet drivers. @@ -29,7 +30,6 @@ config NGBE depends on PCI depends on PTP_1588_CLOCK_OPTIONAL select LIBWX - select PHYLINK help This driver supports Wangxun(R) GbE PCI Express family of adapters. @@ -48,7 +48,6 @@ config TXGBE depends on PTP_1588_CLOCK_OPTIONAL select MARVELL_10G_PHY select REGMAP - select PHYLINK select HWMON if TXGBE=y select SFP select GPIOLIB @@ -71,7 +70,6 @@ config TXGBEVF depends on PCI_MSI depends on PTP_1588_CLOCK_OPTIONAL select LIBWX - select PHYLINK help This driver supports virtual functions for SP1000A, WX1820AL, WX5XXX, WX5XXXAL. diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c index 62d7f47d4f8d..f0514251d4f3 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c @@ -70,7 +70,7 @@ int txgbe_test_hostif(struct wx *wx) buffer.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), - WX_HI_COMMAND_TIMEOUT, true); + WX_HI_COMMAND_TIMEOUT, false); } int txgbe_read_eeprom_hostif(struct wx *wx, @@ -148,7 +148,7 @@ static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int buffer.duplex = duplex; return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), - WX_HI_COMMAND_TIMEOUT, true); + WX_HI_COMMAND_TIMEOUT, false); } static void txgbe_get_link_capabilities(struct wx *wx, int *speed, diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index b9b5554ea862..5ad2673f213d 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -334,7 +334,7 @@ int fjes_hw_init(struct fjes_hw *hw) ret = fjes_hw_reset(hw); if (ret) - return ret; + goto err_iounmap; fjes_hw_set_irqmask(hw, REG_ICTL_MASK_ALL, true); @@ -347,8 +347,10 @@ int fjes_hw_init(struct fjes_hw *hw) hw->max_epid = fjes_hw_get_max_epid(hw); hw->my_epid = fjes_hw_get_my_epid(hw); - if ((hw->max_epid == 0) || (hw->my_epid >= hw->max_epid)) - return -ENXIO; + if ((hw->max_epid == 0) || (hw->my_epid >= hw->max_epid)) { + ret = -ENXIO; + goto err_iounmap; + } ret = fjes_hw_setup(hw); @@ -356,6 +358,10 @@ int fjes_hw_init(struct fjes_hw *hw) hw->hw_info.trace_size = FJES_DEBUG_BUFFER_SIZE; return ret; + +err_iounmap: + fjes_hw_iounmap(hw); + return ret; } void fjes_hw_exit(struct fjes_hw *hw) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 3d47d749ef9f..cbd52cb79268 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1750,6 +1750,9 @@ static int netvsc_set_rxfh(struct net_device *dev, rxfh->hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; + if (!ndc->rx_table_sz) + return -EOPNOTSUPP; + rndis_dev = ndev->extension; if (rxfh->indir) { for (i = 0; i < ndc->rx_table_sz; i++) diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 50de3ee204db..80f84fc87008 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -69,7 +69,6 @@ struct ipvl_dev { DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE); netdev_features_t sfeatures; u32 msg_enable; - spinlock_t addrs_lock; }; struct ipvl_addr { @@ -90,6 +89,7 @@ struct ipvl_port { struct net_device *dev; possible_net_t pnet; struct hlist_head hlhead[IPVLAN_HASH_SIZE]; + spinlock_t addrs_lock; /* guards hash-table and addrs */ struct list_head ipvlans; u16 mode; u16 flags; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 2efa3ba148aa..bdb3a46b327c 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -107,17 +107,15 @@ void ipvlan_ht_addr_del(struct ipvl_addr *addr) struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6) { - struct ipvl_addr *addr, *ret = NULL; + struct ipvl_addr *addr; - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) { - if (addr_equal(is_v6, addr, iaddr)) { - ret = addr; - break; - } + assert_spin_locked(&ipvlan->port->addrs_lock); + + list_for_each_entry(addr, &ipvlan->addrs, anode) { + if (addr_equal(is_v6, addr, iaddr)) + return addr; } - rcu_read_unlock(); - return ret; + return NULL; } bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 660f3db11766..baccdad695fd 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -75,6 +75,7 @@ static int ipvlan_port_create(struct net_device *dev) for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++) INIT_HLIST_HEAD(&port->hlhead[idx]); + spin_lock_init(&port->addrs_lock); skb_queue_head_init(&port->backlog); INIT_WORK(&port->wq, ipvlan_process_multicast); ida_init(&port->ida); @@ -181,6 +182,7 @@ static void ipvlan_uninit(struct net_device *dev) static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); + struct ipvl_port *port = ipvlan->port; struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || @@ -189,10 +191,10 @@ static int ipvlan_open(struct net_device *dev) else dev->flags &= ~IFF_NOARP; - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) + spin_lock_bh(&port->addrs_lock); + list_for_each_entry(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); - rcu_read_unlock(); + spin_unlock_bh(&port->addrs_lock); return 0; } @@ -206,10 +208,10 @@ static int ipvlan_stop(struct net_device *dev) dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) + spin_lock_bh(&ipvlan->port->addrs_lock); + list_for_each_entry(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); - rcu_read_unlock(); + spin_unlock_bh(&ipvlan->port->addrs_lock); return 0; } @@ -579,7 +581,6 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, if (!tb[IFLA_MTU]) ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); - spin_lock_init(&ipvlan->addrs_lock); /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing @@ -657,13 +658,13 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head) struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); kfree_rcu(addr, rcu); } - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); ida_free(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); @@ -817,6 +818,8 @@ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; + assert_spin_locked(&ipvlan->port->addrs_lock); + addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC); if (!addr) return -ENOMEM; @@ -847,16 +850,16 @@ static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); addr = ipvlan_find_addr(ipvlan, iaddr, is_v6); if (!addr) { - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return; } ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); kfree_rcu(addr, rcu); } @@ -878,14 +881,14 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { int ret = -EINVAL; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv6=%pI6c addr for %s intf\n", ip6_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip6_addr, true); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return ret; } @@ -924,21 +927,24 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused, struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr; struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); + int ret = NOTIFY_OK; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) { NL_SET_ERR_MSG(i6vi->extack, "Address already assigned to an ipvlan device"); - return notifier_from_errno(-EADDRINUSE); + ret = notifier_from_errno(-EADDRINUSE); } + spin_unlock_bh(&ipvlan->port->addrs_lock); break; } - return NOTIFY_OK; + return ret; } #endif @@ -946,14 +952,14 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { int ret = -EINVAL; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip4_addr, false); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return ret; } @@ -995,21 +1001,24 @@ static int ipvlan_addr4_validator_event(struct notifier_block *unused, struct in_validator_info *ivi = (struct in_validator_info *)ptr; struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); + int ret = NOTIFY_OK; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) { NL_SET_ERR_MSG(ivi->extack, "Address already assigned to an ipvlan device"); - return notifier_from_errno(-EADDRINUSE); + ret = notifier_from_errno(-EADDRINUSE); } + spin_unlock_bh(&ipvlan->port->addrs_lock); break; } - return NOTIFY_OK; + return ret; } static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 7966545512cf..b4df7e184791 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -59,7 +59,7 @@ struct macvlan_port { struct macvlan_source_entry { struct hlist_node hlist; - struct macvlan_dev *vlan; + struct macvlan_dev __rcu *vlan; unsigned char addr[6+2] __aligned(sizeof(u16)); struct rcu_head rcu; }; @@ -146,7 +146,7 @@ static struct macvlan_source_entry *macvlan_hash_lookup_source( hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(entry->addr, addr) && - entry->vlan == vlan) + rcu_access_pointer(entry->vlan) == vlan) return entry; } return NULL; @@ -168,7 +168,7 @@ static int macvlan_hash_add_source(struct macvlan_dev *vlan, return -ENOMEM; ether_addr_copy(entry->addr, addr); - entry->vlan = vlan; + RCU_INIT_POINTER(entry->vlan, vlan); h = &port->vlan_source_hash[macvlan_eth_hash(addr)]; hlist_add_head_rcu(&entry->hlist, h); vlan->macaddr_count++; @@ -187,6 +187,7 @@ static void macvlan_hash_add(struct macvlan_dev *vlan) static void macvlan_hash_del_source(struct macvlan_source_entry *entry) { + RCU_INIT_POINTER(entry->vlan, NULL); hlist_del_rcu(&entry->hlist); kfree_rcu(entry, rcu); } @@ -390,7 +391,7 @@ static void macvlan_flush_sources(struct macvlan_port *port, int i; hash_for_each_safe(port->vlan_source_hash, i, next, entry, hlist) - if (entry->vlan == vlan) + if (rcu_access_pointer(entry->vlan) == vlan) macvlan_hash_del_source(entry); vlan->macaddr_count = 0; @@ -433,9 +434,14 @@ static bool macvlan_forward_source(struct sk_buff *skb, hlist_for_each_entry_rcu(entry, h, hlist) { if (ether_addr_equal_64bits(entry->addr, addr)) { - if (entry->vlan->flags & MACVLAN_FLAG_NODST) + struct macvlan_dev *vlan = rcu_dereference(entry->vlan); + + if (!vlan) + continue; + + if (vlan->flags & MACVLAN_FLAG_NODST) consume = true; - macvlan_forward_source_one(skb, entry->vlan); + macvlan_forward_source_one(skb, vlan); } } @@ -1680,7 +1686,7 @@ static int macvlan_fill_info_macaddr(struct sk_buff *skb, struct macvlan_source_entry *entry; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { - if (entry->vlan != vlan) + if (rcu_access_pointer(entry->vlan) != vlan) continue; if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) return 1; diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index e55be6dc9ae7..d6b9004c61dc 100644 --- a/drivers/net/mdio/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c @@ -63,6 +63,13 @@ static int aspeed_mdio_op(struct mii_bus *bus, u8 st, u8 op, u8 phyad, u8 regad, iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL); + /* Workaround for read-after-write issue. + * The controller may return stale data if a read follows immediately + * after a write. A dummy read forces the hardware to update its + * internal state, ensuring that the next real read returns correct data. + */ + ioread32(ctx->base + ASPEED_MDIO_CTRL); + return readl_poll_timeout(ctx->base + ASPEED_MDIO_CTRL, ctrl, !(ctrl & ASPEED_MDIO_CTRL_FIRE), ASPEED_MDIO_INTERVAL_US, diff --git a/drivers/net/mdio/mdio-realtek-rtl9300.c b/drivers/net/mdio/mdio-realtek-rtl9300.c index 33694c3ff9a7..405a07075dd1 100644 --- a/drivers/net/mdio/mdio-realtek-rtl9300.c +++ b/drivers/net/mdio/mdio-realtek-rtl9300.c @@ -354,7 +354,6 @@ static int rtl9300_mdiobus_probe_one(struct device *dev, struct rtl9300_mdio_pri struct fwnode_handle *node) { struct rtl9300_mdio_chan *chan; - struct fwnode_handle *child; struct mii_bus *bus; u32 mdio_bus; int err; @@ -371,7 +370,7 @@ static int rtl9300_mdiobus_probe_one(struct device *dev, struct rtl9300_mdio_pri * compatible = "ethernet-phy-ieee802.3-c45". This does mean we can't * support both c45 and c22 on the same MDIO bus. */ - fwnode_for_each_child_node(node, child) + fwnode_for_each_child_node_scoped(node, child) if (fwnode_device_is_compatible(child, "ethernet-phy-ieee802.3-c45")) priv->smi_bus_is_c45[mdio_bus] = true; @@ -409,7 +408,6 @@ static int rtl9300_mdiobus_map_ports(struct device *dev) { struct rtl9300_mdio_priv *priv = dev_get_drvdata(dev); struct device *parent = dev->parent; - struct fwnode_handle *port; int err; struct fwnode_handle *ports __free(fwnode_handle) = @@ -418,7 +416,7 @@ static int rtl9300_mdiobus_map_ports(struct device *dev) return dev_err_probe(dev, -EINVAL, "%pfwP missing ethernet-ports\n", dev_fwnode(parent)); - fwnode_for_each_child_node(ports, port) { + fwnode_for_each_child_node_scoped(ports, port) { struct device_node *mdio_dn; u32 addr; u32 bus; diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 49537d3c4120..5f17f68f3c08 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -244,7 +244,9 @@ static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev, &state->state, &nsim_bpf_string_fops); debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded); + mutex_lock(&nsim_dev->progs_list_lock); list_add_tail(&state->l, &nsim_dev->bpf_bound_progs); + mutex_unlock(&nsim_dev->progs_list_lock); prog->aux->offload->dev_priv = state; @@ -273,12 +275,16 @@ static int nsim_bpf_translate(struct bpf_prog *prog) static void nsim_bpf_destroy_prog(struct bpf_prog *prog) { struct nsim_bpf_bound_prog *state; + struct nsim_dev *nsim_dev; state = prog->aux->offload->dev_priv; + nsim_dev = state->nsim_dev; WARN(state->is_loaded, "offload state destroyed while program still bound"); debugfs_remove_recursive(state->ddir); + mutex_lock(&nsim_dev->progs_list_lock); list_del(&state->l); + mutex_unlock(&nsim_dev->progs_list_lock); kfree(state); } diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index 70e8c38ddad6..d16b95304aa7 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -332,6 +332,11 @@ static ssize_t link_device_store(const struct bus_type *bus, const char *buf, si rcu_assign_pointer(nsim_a->peer, nsim_b); rcu_assign_pointer(nsim_b->peer, nsim_a); + if (netif_running(dev_a) && netif_running(dev_b)) { + netif_carrier_on(dev_a); + netif_carrier_on(dev_b); + } + out_err: put_net(ns_b); put_net(ns_a); @@ -381,6 +386,9 @@ static ssize_t unlink_device_store(const struct bus_type *bus, const char *buf, if (!peer) goto out_put_netns; + netif_carrier_off(dev); + netif_carrier_off(peer->netdev); + err = 0; RCU_INIT_POINTER(nsim->peer, NULL); RCU_INIT_POINTER(peer->peer, NULL); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 2683a989873e..dfd571b22107 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1647,6 +1647,7 @@ int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; nsim_dev->test2 = NSIM_DEV_TEST2_DEFAULT; spin_lock_init(&nsim_dev->fa_cookie_lock); + mutex_init(&nsim_dev->progs_list_lock); dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); @@ -1785,6 +1786,7 @@ void nsim_drv_remove(struct nsim_bus_dev *nsim_bus_dev) devl_unregister(devlink); kfree(nsim_dev->vfconfigs); kfree(nsim_dev->fa_cookie); + mutex_destroy(&nsim_dev->progs_list_lock); devl_unlock(devlink); devlink_free(devlink); dev_set_drvdata(&nsim_bus_dev->dev, NULL); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index d1a941e2b18f..46c67983c517 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -324,6 +324,7 @@ struct nsim_dev { u32 prog_id_gen; struct list_head bpf_bound_progs; struct list_head bpf_bound_maps; + struct mutex progs_list_lock; struct netdev_phys_item_id switch_id; struct list_head port_list; bool fw_update_status; diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c index 149ddf51d785..87df3a9dfc9b 100644 --- a/drivers/net/pcs/pcs-mtk-lynxi.c +++ b/drivers/net/pcs/pcs-mtk-lynxi.c @@ -93,12 +93,10 @@ static unsigned int mtk_pcs_lynxi_inband_caps(struct phylink_pcs *pcs, { switch (interface) { case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: case PHY_INTERFACE_MODE_SGMII: return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; - case PHY_INTERFACE_MODE_2500BASEX: - return LINK_INBAND_DISABLE; - default: return 0; } diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c index 9766dd99afaa..12ff4c1f285d 100644 --- a/drivers/net/phy/intel-xway.c +++ b/drivers/net/phy/intel-xway.c @@ -277,7 +277,7 @@ static int xway_gphy_init_leds(struct phy_device *phydev) static int xway_gphy_config_init(struct phy_device *phydev) { - struct device_node *np = phydev->mdio.dev.of_node; + struct device_node *np; int err; /* Mask all interrupts */ @@ -286,7 +286,10 @@ static int xway_gphy_config_init(struct phy_device *phydev) return err; /* Use default LED configuration if 'leds' node isn't defined */ - if (!of_get_child_by_name(np, "leds")) + np = of_get_child_by_name(phydev->mdio.dev.of_node, "leds"); + if (np) + of_node_put(np); + else xway_gphy_init_leds(phydev); /* Clear all pending interrupts */ diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c index cd09fbf92ef2..2c4bbc236202 100644 --- a/drivers/net/phy/mediatek/mtk-ge-soc.c +++ b/drivers/net/phy/mediatek/mtk-ge-soc.c @@ -1167,9 +1167,9 @@ static int mt798x_phy_calibration(struct phy_device *phydev) } buf = (u32 *)nvmem_cell_read(cell, &len); + nvmem_cell_put(cell); if (IS_ERR(buf)) return PTR_ERR(buf); - nvmem_cell_put(cell); if (!buf[0] || !buf[1] || !buf[2] || !buf[3] || len < 4 * sizeof(u32)) { phydev_err(phydev, "invalid efuse data\n"); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 05de68b9f719..8208ecbb575c 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2643,11 +2643,21 @@ static int kszphy_probe(struct phy_device *phydev) kszphy_parse_led_mode(phydev); - clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, "rmii-ref"); + clk = devm_clk_get_optional(&phydev->mdio.dev, "rmii-ref"); /* NOTE: clk may be NULL if building without CONFIG_HAVE_CLK */ if (!IS_ERR_OR_NULL(clk)) { - unsigned long rate = clk_get_rate(clk); bool rmii_ref_clk_sel_25_mhz; + unsigned long rate; + int err; + + err = clk_prepare_enable(clk); + if (err) { + phydev_err(phydev, "Failed to enable rmii-ref clock\n"); + return err; + } + + rate = clk_get_rate(clk); + clk_disable_unprepare(clk); if (type) priv->rmii_ref_clk_sel = type->has_rmii_ref_clk_sel; @@ -2665,13 +2675,12 @@ static int kszphy_probe(struct phy_device *phydev) } } else if (!clk) { /* unnamed clock from the generic ethernet-phy binding */ - clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, NULL); + clk = devm_clk_get_optional(&phydev->mdio.dev, NULL); } if (IS_ERR(clk)) return PTR_ERR(clk); - clk_disable_unprepare(clk); priv->clk = clk; if (ksz8041_fiber_mode(phydev)) diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c index 89b5b19a9bd2..42d46b5758fc 100644 --- a/drivers/net/phy/motorcomm.c +++ b/drivers/net/phy/motorcomm.c @@ -1741,10 +1741,10 @@ static int yt8521_led_hw_control_set(struct phy_device *phydev, u8 index, val |= YT8521_LED_1000_ON_EN; if (test_bit(TRIGGER_NETDEV_FULL_DUPLEX, &rules)) - val |= YT8521_LED_HDX_ON_EN; + val |= YT8521_LED_FDX_ON_EN; if (test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &rules)) - val |= YT8521_LED_FDX_ON_EN; + val |= YT8521_LED_HDX_ON_EN; if (test_bit(TRIGGER_NETDEV_TX, &rules) || test_bit(TRIGGER_NETDEV_RX, &rules)) diff --git a/drivers/net/phy/mxl-86110.c b/drivers/net/phy/mxl-86110.c index e5d137a37a1d..42a5fe3f115f 100644 --- a/drivers/net/phy/mxl-86110.c +++ b/drivers/net/phy/mxl-86110.c @@ -938,6 +938,9 @@ static struct phy_driver mxl_phy_drvs[] = { PHY_ID_MATCH_EXACT(PHY_ID_MXL86110), .name = "MXL86110 Gigabit Ethernet", .config_init = mxl86110_config_init, + .suspend = genphy_suspend, + .resume = genphy_resume, + .soft_reset = genphy_soft_reset, .get_wol = mxl86110_get_wol, .set_wol = mxl86110_set_wol, .led_brightness_set = mxl86110_led_brightness_set, diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 6166e9196364..47f095bd91ce 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -519,6 +519,8 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK_F("HALNy", "HL-GSFP", sfp_fixup_halny_gsfp), + SFP_QUIRK_F("H-COM", "SPP425H-GAB4", sfp_fixup_potron), + // HG MXPD-483II-F 2.5G supports 2500Base-X, but incorrectly reports // 2600MBd in their EERPOM SFP_QUIRK_S("HG GENUINE", "MXPD-483II", sfp_quirk_2500basex), @@ -765,7 +767,7 @@ static int sfp_smbus_byte_write(struct sfp *sfp, bool a2, u8 dev_addr, dev_addr++; } - return 0; + return data - (u8 *)buf; } static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c) diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 4d5c9ae8f221..c08a5c1bd6e4 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -878,7 +878,7 @@ static void __team_queue_override_enabled_check(struct team *team) static void team_queue_override_port_prio_changed(struct team *team, struct team_port *port) { - if (!port->queue_id || team_port_enabled(port)) + if (!port->queue_id || !team_port_enabled(port)) return; __team_queue_override_port_del(team, port); __team_queue_override_port_add(team, port); diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 7fd763917ae2..6ab3486072cb 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -335,6 +335,11 @@ int asix_read_phy_addr(struct usbnet *dev, bool internal) offset = (internal ? 1 : 0); ret = buf[offset]; + if (ret >= PHY_MAX_ADDR) { + netdev_err(dev->net, "invalid PHY address: %d\n", ret); + return -ENODEV; + } + netdev_dbg(dev->net, "%s PHY address 0x%x\n", internal ? "internal" : "external", ret); diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index f613e4bc68c8..758a423a459b 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -210,11 +210,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) ret = asix_read_phy_addr(dev, priv->use_embdphy); if (ret < 0) goto free; - if (ret >= PHY_MAX_ADDR) { - netdev_err(dev->net, "Invalid PHY address %#x\n", ret); - ret = -ENODEV; - goto free; - } + priv->phy_addr = ret; ax88172a_reset_phy(dev, priv->use_embdphy); diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 8b6d6a1b3c2e..2b4716ccf0c5 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -604,10 +604,6 @@ static const struct usb_device_id products[] = { .driver_info = (unsigned long)&dm9601_info, }, { - USB_DEVICE(0x0fe6, 0x9700), /* DM9601 USB to Fast Ethernet Adapter */ - .driver_info = (unsigned long)&dm9601_info, - }, - { USB_DEVICE(0x0a46, 0x9000), /* DM9000E */ .driver_info = (unsigned long)&dm9601_info, }, diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 81ca64debc5b..c514483134f0 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -168,6 +168,8 @@ static int update_eth_regs_async(pegasus_t *pegasus) netif_device_detach(pegasus->net); netif_err(pegasus, drv, pegasus->net, "%s returned %d\n", __func__, ret); + usb_free_urb(async_urb); + kfree(req); } return ret; } diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 278e6cb6f4d9..e40b0669d9f4 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -211,6 +211,8 @@ static int async_set_registers(rtl8150_t *dev, u16 indx, u16 size, u16 reg) if (res == -ENODEV) netif_device_detach(dev->netdev); dev_err(&dev->udev->dev, "%s failed with %d\n", __func__, res); + kfree(req); + usb_free_urb(async_urb); } return res; } diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 091bc2aca7e8..820c4c506979 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -52,7 +52,7 @@ static int sr_read_reg(struct usbnet *dev, u8 reg, u8 *value) static int sr_write_reg(struct usbnet *dev, u8 reg, u8 value) { - return usbnet_write_cmd(dev, SR_WR_REGS, SR_REQ_WR_REG, + return usbnet_write_cmd(dev, SR_WR_REG, SR_REQ_WR_REG, value, reg, NULL, 0); } @@ -65,7 +65,7 @@ static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, static void sr_write_reg_async(struct usbnet *dev, u8 reg, u8 value) { - usbnet_write_cmd_async(dev, SR_WR_REGS, SR_REQ_WR_REG, + usbnet_write_cmd_async(dev, SR_WR_REG, SR_REQ_WR_REG, value, reg, NULL, 0); } @@ -539,6 +539,11 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0fe6, 0x9700), /* SR9700 device */ .driver_info = (unsigned long)&sr9700_driver_info, }, + { + /* SR9700 with virtual driver CD-ROM - interface 0 is the CD-ROM device */ + USB_DEVICE_INTERFACE_NUMBER(0x0fe6, 0x9702, 1), + .driver_info = (unsigned long)&sr9700_driver_info, + }, {}, /* END */ }; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 1d9faa70ba3b..9280ef544bbb 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -831,7 +831,6 @@ int usbnet_stop(struct net_device *net) clear_bit(EVENT_DEV_OPEN, &dev->flags); netif_stop_queue(net); - netdev_reset_queue(net); netif_info(dev, ifdown, dev->net, "stop stats: rx/tx %lu/%lu, errs %lu/%lu\n", @@ -875,6 +874,8 @@ int usbnet_stop(struct net_device *net) timer_delete_sync(&dev->delay); cancel_work_sync(&dev->kevent); + netdev_reset_queue(net); + if (!pm) usb_autopm_put_interface(dev->intf); @@ -1820,9 +1821,12 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) if ((dev->driver_info->flags & FLAG_NOARP) != 0) net->flags |= IFF_NOARP; - /* maybe the remote can't receive an Ethernet MTU */ - if (net->mtu > (dev->hard_mtu - net->hard_header_len)) - net->mtu = dev->hard_mtu - net->hard_header_len; + if (net->max_mtu > (dev->hard_mtu - net->hard_header_len)) + net->max_mtu = dev->hard_mtu - net->hard_header_len; + + if (net->mtu > net->max_mtu) + net->mtu = net->max_mtu; + } else if (!info->in || !info->out) status = usbnet_get_endpoints(dev, udev); else { @@ -1983,6 +1987,7 @@ int usbnet_resume(struct usb_interface *intf) } else { netif_trans_update(dev->net); __skb_queue_tail(&dev->txq, skb); + netdev_sent_queue(dev->net, skb->len); } } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 14e6f2a2fb77..9982412fd7f2 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -228,16 +228,20 @@ static void veth_get_ethtool_stats(struct net_device *dev, const struct veth_rq_stats *rq_stats = &rcv_priv->rq[i].stats; const void *base = (void *)&rq_stats->vs; unsigned int start, tx_idx = idx; + u64 buf[VETH_TQ_STATS_LEN]; size_t offset; - tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; do { start = u64_stats_fetch_begin(&rq_stats->syncp); for (j = 0; j < VETH_TQ_STATS_LEN; j++) { offset = veth_tq_stats_desc[j].offset; - data[tx_idx + j] += *(u64 *)(base + offset); + buf[j] = *(u64 *)(base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); + + tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; + for (j = 0; j < VETH_TQ_STATS_LEN; j++) + data[tx_idx + j] += buf[j]; } pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1bb3aeca66c6..db88dcaefb20 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -425,9 +425,6 @@ struct virtnet_info { u16 rss_indir_table_size; u32 rss_hash_types_supported; u32 rss_hash_types_saved; - struct virtio_net_rss_config_hdr *rss_hdr; - struct virtio_net_rss_config_trailer rss_trailer; - u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE]; /* Has control virtqueue */ bool has_cvq; @@ -441,9 +438,6 @@ struct virtnet_info { /* Packet virtio header size */ u8 hdr_len; - /* Work struct for delayed refilling if we run low on memory. */ - struct delayed_work refill; - /* UDP tunnel support */ bool tx_tnl; @@ -451,12 +445,6 @@ struct virtnet_info { bool rx_tnl_csum; - /* 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; @@ -493,7 +481,16 @@ struct virtnet_info { struct failover *failover; u64 device_stats_cap; + + struct virtio_net_rss_config_hdr *rss_hdr; + + /* Must be last as it ends in a flexible-array member. */ + TRAILING_OVERLAP(struct virtio_net_rss_config_trailer, rss_trailer, hash_key_data, + u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE]; + ); }; +static_assert(offsetof(struct virtnet_info, rss_trailer.hash_key_data) == + offsetof(struct virtnet_info, rss_hash_key_data)); struct padded_vnet_hdr { struct virtio_net_hdr_v1_hash hdr; @@ -720,20 +717,6 @@ static void virtnet_rq_free_buf(struct virtnet_info *vi, put_page(virt_to_head_page(buf)); } -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 enable_rx_mode_work(struct virtnet_info *vi) { rtnl_lock(); @@ -2948,42 +2931,6 @@ static void virtnet_napi_disable(struct receive_queue *rq) napi_disable(napi); } -static void refill_work(struct work_struct *work) -{ - struct virtnet_info *vi = - container_of(work, struct virtnet_info, refill.work); - bool still_empty; - int i; - - for (i = 0; i < vi->curr_queue_pairs; i++) { - struct receive_queue *rq = &vi->rq[i]; - - /* - * When queue API support is added in the future and the call - * below becomes napi_disable_locked, this driver will need to - * be refactored. - * - * One possible solution would be to: - * - cancel refill_work with cancel_delayed_work (note: - * non-sync) - * - cancel refill_work with cancel_delayed_work_sync in - * virtnet_remove after the netdev is unregistered - * - wrap all of the work in a lock (perhaps the netdev - * instance lock) - * - check netif_running() and return early to avoid a race - */ - napi_disable(&rq->napi); - still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); - virtnet_napi_do_enable(rq->vq, &rq->napi); - - /* In theory, this can happen: if we don't get any buffers in - * we will *never* try to fill again. - */ - if (still_empty) - schedule_delayed_work(&vi->refill, HZ/2); - } -} - static int virtnet_receive_xsk_bufs(struct virtnet_info *vi, struct receive_queue *rq, int budget, @@ -3046,16 +2993,16 @@ static int virtnet_receive(struct receive_queue *rq, int budget, else packets = virtnet_receive_packets(vi, rq, budget, xdp_xmit, &stats); + u64_stats_set(&stats.packets, packets); if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) { - 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); - } + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) + /* We need to retry refilling in the next NAPI poll so + * we must return budget to make sure the NAPI is + * repolled. + */ + packets = budget; } - u64_stats_set(&stats.packets, packets); u64_stats_update_begin(&rq->stats.syncp); for (i = 0; i < ARRAY_SIZE(virtnet_rq_stats_desc); i++) { size_t offset = virtnet_rq_stats_desc[i].offset; @@ -3226,13 +3173,12 @@ 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. */ - if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) - schedule_delayed_work(&vi->refill, 0); + /* Pre-fill rq agressively, to make sure we are ready to + * get packets immediately. + */ + try_fill_recv(vi, &vi->rq[i], GFP_KERNEL); err = virtnet_enable_queue_pair(vi, i); if (err < 0) @@ -3251,9 +3197,6 @@ static int virtnet_open(struct net_device *dev) return 0; err_enable_qp: - disable_delayed_refill(vi); - cancel_delayed_work_sync(&vi->refill); - for (i--; i >= 0; i--) { virtnet_disable_queue_pair(vi, i); virtnet_cancel_dim(vi, &vi->rq[i].dim); @@ -3432,8 +3375,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static void __virtnet_rx_pause(struct virtnet_info *vi, - struct receive_queue *rq) +static void virtnet_rx_pause(struct virtnet_info *vi, + struct receive_queue *rq) { bool running = netif_running(vi->dev); @@ -3447,62 +3390,37 @@ static void virtnet_rx_pause_all(struct virtnet_info *vi) { int i; - /* - * Make sure refill_work does not run concurrently to - * avoid napi_disable race which leads to deadlock. - */ - disable_delayed_refill(vi); - cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) - __virtnet_rx_pause(vi, &vi->rq[i]); + virtnet_rx_pause(vi, &vi->rq[i]); } -static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) +static void virtnet_rx_resume(struct virtnet_info *vi, + struct receive_queue *rq, + bool refill) { - /* - * Make sure refill_work does not run concurrently to - * avoid napi_disable race which leads to deadlock. - */ - disable_delayed_refill(vi); - cancel_delayed_work_sync(&vi->refill); - __virtnet_rx_pause(vi, rq); -} - -static void __virtnet_rx_resume(struct virtnet_info *vi, - struct receive_queue *rq, - bool refill) -{ - bool running = netif_running(vi->dev); - bool schedule_refill = false; + if (netif_running(vi->dev)) { + /* Pre-fill rq agressively, to make sure we are ready to get + * packets immediately. + */ + if (refill) + try_fill_recv(vi, rq, GFP_KERNEL); - if (refill && !try_fill_recv(vi, rq, GFP_KERNEL)) - schedule_refill = true; - if (running) virtnet_napi_enable(rq); - - if (schedule_refill) - schedule_delayed_work(&vi->refill, 0); + } } static void virtnet_rx_resume_all(struct virtnet_info *vi) { int i; - enable_delayed_refill(vi); for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) - __virtnet_rx_resume(vi, &vi->rq[i], true); + virtnet_rx_resume(vi, &vi->rq[i], true); else - __virtnet_rx_resume(vi, &vi->rq[i], false); + virtnet_rx_resume(vi, &vi->rq[i], false); } } -static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) -{ - enable_delayed_refill(vi); - __virtnet_rx_resume(vi, rq, true); -} - static int virtnet_rx_resize(struct virtnet_info *vi, struct receive_queue *rq, u32 ring_num) { @@ -3516,7 +3434,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi, if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); - virtnet_rx_resume(vi, rq); + virtnet_rx_resume(vi, rq, true); return err; } @@ -3791,7 +3709,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) if (vi->has_rss && !netif_is_rxfh_configured(dev)) { old_rss_hdr = vi->rss_hdr; old_rss_trailer = vi->rss_trailer; - vi->rss_hdr = devm_kzalloc(&dev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL); + vi->rss_hdr = devm_kzalloc(&vi->vdev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL); if (!vi->rss_hdr) { vi->rss_hdr = old_rss_hdr; return -ENOMEM; @@ -3802,7 +3720,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) if (!virtnet_commit_rss_command(vi)) { /* restore ctrl_rss if commit_rss_command failed */ - devm_kfree(&dev->dev, vi->rss_hdr); + devm_kfree(&vi->vdev->dev, vi->rss_hdr); vi->rss_hdr = old_rss_hdr; vi->rss_trailer = old_rss_trailer; @@ -3810,7 +3728,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) queue_pairs); return -EINVAL; } - devm_kfree(&dev->dev, old_rss_hdr); + devm_kfree(&vi->vdev->dev, old_rss_hdr); goto succ; } @@ -3829,11 +3747,12 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) } succ: vi->curr_queue_pairs = queue_pairs; - /* virtnet_open() will refill when device is going to up. */ - spin_lock_bh(&vi->refill_lock); - if (dev->flags & IFF_UP && vi->refill_enabled) - schedule_delayed_work(&vi->refill, 0); - spin_unlock_bh(&vi->refill_lock); + if (dev->flags & IFF_UP) { + local_bh_disable(); + for (int i = 0; i < vi->curr_queue_pairs; ++i) + virtqueue_napi_schedule(&vi->rq[i].napi, vi->rq[i].vq); + local_bh_enable(); + } return 0; } @@ -3843,10 +3762,6 @@ 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); /* Prevent the config change callback from changing carrier * after close */ @@ -5802,7 +5717,6 @@ static int virtnet_restore_up(struct virtio_device *vdev) virtio_device_ready(vdev); - enable_delayed_refill(vi); enable_rx_mode_work(vi); if (netif_running(vi->dev)) { @@ -5892,7 +5806,7 @@ static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queu rq->xsk_pool = pool; - virtnet_rx_resume(vi, rq); + virtnet_rx_resume(vi, rq, true); if (pool) return 0; @@ -6559,7 +6473,6 @@ static int virtnet_alloc_queues(struct virtnet_info *vi) if (!vi->rq) goto err_rq; - INIT_DELAYED_WORK(&vi->refill, refill_work); for (i = 0; i < vi->max_queue_pairs; i++) { vi->rq[i].pages = NULL; netif_napi_add_config(vi->dev, &vi->rq[i].napi, virtnet_poll, @@ -6901,7 +6814,6 @@ static int virtnet_probe(struct virtio_device *vdev) INIT_WORK(&vi->config_work, virtnet_config_changed_work); INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work); - spin_lock_init(&vi->refill_lock); if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) { vi->mergeable_rx_bufs = true; @@ -7165,7 +7077,6 @@ free_failover: net_failover_destroy(vi->failover); free_vqs: virtio_reset_device(vdev); - cancel_delayed_work_sync(&vi->refill); free_receive_page_frags(vi); virtnet_del_vqs(vi); free: diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c index 7bbda46cfd93..82f120ee1c66 100644 --- a/drivers/net/wireless/ath/ath10k/ce.c +++ b/drivers/net/wireless/ath/ath10k/ce.c @@ -1727,8 +1727,8 @@ static void _ath10k_ce_free_pipe(struct ath10k *ar, int ce_id) (ce_state->src_ring->nentries * sizeof(struct ce_desc) + CE_DESC_RING_ALIGN), - ce_state->src_ring->base_addr_owner_space, - ce_state->src_ring->base_addr_ce_space); + ce_state->src_ring->base_addr_owner_space_unaligned, + ce_state->src_ring->base_addr_ce_space_unaligned); kfree(ce_state->src_ring); } @@ -1737,8 +1737,8 @@ static void _ath10k_ce_free_pipe(struct ath10k *ar, int ce_id) (ce_state->dest_ring->nentries * sizeof(struct ce_desc) + CE_DESC_RING_ALIGN), - ce_state->dest_ring->base_addr_owner_space, - ce_state->dest_ring->base_addr_ce_space); + ce_state->dest_ring->base_addr_owner_space_unaligned, + ce_state->dest_ring->base_addr_ce_space_unaligned); kfree(ce_state->dest_ring); } @@ -1758,8 +1758,8 @@ static void _ath10k_ce_free_pipe_64(struct ath10k *ar, int ce_id) (ce_state->src_ring->nentries * sizeof(struct ce_desc_64) + CE_DESC_RING_ALIGN), - ce_state->src_ring->base_addr_owner_space, - ce_state->src_ring->base_addr_ce_space); + ce_state->src_ring->base_addr_owner_space_unaligned, + ce_state->src_ring->base_addr_ce_space_unaligned); kfree(ce_state->src_ring); } @@ -1768,8 +1768,8 @@ static void _ath10k_ce_free_pipe_64(struct ath10k *ar, int ce_id) (ce_state->dest_ring->nentries * sizeof(struct ce_desc_64) + CE_DESC_RING_ALIGN), - ce_state->dest_ring->base_addr_owner_space, - ce_state->dest_ring->base_addr_ce_space); + ce_state->dest_ring->base_addr_owner_space_unaligned, + ce_state->dest_ring->base_addr_ce_space_unaligned); kfree(ce_state->dest_ring); } diff --git a/drivers/net/wireless/ath/ath12k/ce.c b/drivers/net/wireless/ath/ath12k/ce.c index 9a63608838ac..4aea58446838 100644 --- a/drivers/net/wireless/ath/ath12k/ce.c +++ b/drivers/net/wireless/ath/ath12k/ce.c @@ -984,8 +984,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->src_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->src_ring->base_addr_owner_space, - pipe->src_ring->base_addr_ce_space); + pipe->src_ring->base_addr_owner_space_unaligned, + pipe->src_ring->base_addr_ce_space_unaligned); kfree(pipe->src_ring); pipe->src_ring = NULL; } @@ -995,8 +995,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->dest_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->dest_ring->base_addr_owner_space, - pipe->dest_ring->base_addr_ce_space); + pipe->dest_ring->base_addr_owner_space_unaligned, + pipe->dest_ring->base_addr_ce_space_unaligned); kfree(pipe->dest_ring); pipe->dest_ring = NULL; } @@ -1007,8 +1007,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->status_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->status_ring->base_addr_owner_space, - pipe->status_ring->base_addr_ce_space); + pipe->status_ring->base_addr_owner_space_unaligned, + pipe->status_ring->base_addr_ce_space_unaligned); kfree(pipe->status_ring); pipe->status_ring = NULL; } diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index f7a2a544bef2..e0e49f782bf8 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -5495,7 +5495,8 @@ static void ath12k_mac_op_cancel_hw_scan(struct ieee80211_hw *hw, for_each_set_bit(link_id, &links_map, ATH12K_NUM_MAX_LINKS) { arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); - if (!arvif || arvif->is_started) + if (!arvif || !arvif->is_created || + arvif->ar->scan.arvif != arvif) continue; ar = arvif->ar; @@ -9172,7 +9173,10 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw, return; } } else { - link_id = 0; + if (vif->type == NL80211_IFTYPE_P2P_DEVICE) + link_id = ATH12K_FIRST_SCAN_LINK; + else + link_id = 0; } arvif = rcu_dereference(ahvif->link[link_id]); @@ -12142,6 +12146,9 @@ static void ath12k_mac_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *v if (drop) return; + for_each_ar(ah, ar, i) + wiphy_work_flush(hw->wiphy, &ar->wmi_mgmt_tx_work); + /* vif can be NULL when flush() is considered for hw */ if (!vif) { for_each_ar(ah, ar, i) @@ -12149,9 +12156,6 @@ static void ath12k_mac_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *v return; } - for_each_ar(ah, ar, i) - wiphy_work_flush(hw->wiphy, &ar->wmi_mgmt_tx_work); - ahvif = ath12k_vif_to_ahvif(vif); links = ahvif->links_map; for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { @@ -13343,7 +13347,7 @@ static int ath12k_mac_op_cancel_remain_on_channel(struct ieee80211_hw *hw, ath12k_scan_abort(ar); cancel_delayed_work_sync(&ar->scan.timeout); - wiphy_work_cancel(hw->wiphy, &ar->scan.vdev_clean_wk); + wiphy_work_flush(hw->wiphy, &ar->scan.vdev_clean_wk); return 0; } diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index be8b2943094f..3ce5fcb0e460 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -6575,16 +6575,9 @@ static int freq_to_idx(struct ath12k *ar, int freq) if (!sband) continue; - for (ch = 0; ch < sband->n_channels; ch++, idx++) { - if (sband->channels[ch].center_freq < - KHZ_TO_MHZ(ar->freq_range.start_freq) || - sband->channels[ch].center_freq > - KHZ_TO_MHZ(ar->freq_range.end_freq)) - continue; - + for (ch = 0; ch < sband->n_channels; ch++, idx++) if (sband->channels[ch].center_freq == freq) goto exit; - } } exit: diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 3391f07b01de..f8fc6f30fbe5 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1597,7 +1597,7 @@ static void _iwl_op_mode_stop(struct iwl_drv *drv) */ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context) { - unsigned int min_core, max_core, loaded_core; + int min_core, max_core, loaded_core; struct iwl_drv *drv = context; struct iwl_fw *fw = &drv->fw; const struct iwl_ucode_header *ucode; @@ -1676,7 +1676,7 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context) if (loaded_core < min_core || loaded_core > max_core) { IWL_ERR(drv, "Driver unable to support your firmware API. " - "Driver supports FW core %u..%u, firmware is %u.\n", + "Driver supports FW core %d..%d, firmware is %d.\n", min_core, max_core, loaded_core); goto try_again; } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c index ffeb37a7f830..231920425c06 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c @@ -121,6 +121,12 @@ static int iwl_mld_ptp_gettime(struct ptp_clock_info *ptp, return 0; } +static int iwl_mld_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + static int iwl_mld_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct iwl_mld *mld = container_of(ptp, struct iwl_mld, @@ -279,6 +285,7 @@ void iwl_mld_ptp_init(struct iwl_mld *mld) mld->ptp_data.ptp_clock_info.owner = THIS_MODULE; mld->ptp_data.ptp_clock_info.gettime64 = iwl_mld_ptp_gettime; + mld->ptp_data.ptp_clock_info.settime64 = iwl_mld_ptp_settime; mld->ptp_data.ptp_clock_info.max_adj = 0x7fffffff; mld->ptp_data.ptp_clock_info.adjtime = iwl_mld_ptp_adjtime; mld->ptp_data.ptp_clock_info.adjfine = iwl_mld_ptp_adjfine; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c index 06a4c9f74797..ad156b82eaa9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c @@ -220,6 +220,12 @@ static int iwl_mvm_ptp_gettime(struct ptp_clock_info *ptp, return 0; } +static int iwl_mvm_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + static int iwl_mvm_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct iwl_mvm *mvm = container_of(ptp, struct iwl_mvm, @@ -281,6 +287,7 @@ void iwl_mvm_ptp_init(struct iwl_mvm *mvm) mvm->ptp_data.ptp_clock_info.adjfine = iwl_mvm_ptp_adjfine; mvm->ptp_data.ptp_clock_info.adjtime = iwl_mvm_ptp_adjtime; mvm->ptp_data.ptp_clock_info.gettime64 = iwl_mvm_ptp_gettime; + mvm->ptp_data.ptp_clock_info.settime64 = iwl_mvm_ptp_settime; mvm->ptp_data.scaled_freq = SCALE_FACTOR; /* Give a short 'friendly name' to identify the PHC clock */ diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c index 354c5ce66045..f3397dc6c422 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c @@ -825,7 +825,7 @@ void mwifiex_update_rxreor_flags(struct mwifiex_adapter *adapter, u8 flags) static void mwifiex_update_ampdu_rxwinsize(struct mwifiex_adapter *adapter, bool coex_flag) { - u8 i; + u8 i, j; u32 rx_win_size; struct mwifiex_private *priv; @@ -863,8 +863,8 @@ static void mwifiex_update_ampdu_rxwinsize(struct mwifiex_adapter *adapter, if (rx_win_size != priv->add_ba_param.rx_win_size) { if (!priv->media_connected) continue; - for (i = 0; i < MAX_NUM_TID; i++) - mwifiex_11n_delba(priv, i); + for (j = 0; j < MAX_NUM_TID; j++) + mwifiex_11n_delba(priv, j); } } } diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index ea99167765b0..0457712286d5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -3019,7 +3019,7 @@ int mt76_connac2_load_ram(struct mt76_dev *dev, const char *fw_wm, } hdr = (const void *)(fw->data + fw->size - sizeof(*hdr)); - dev_info(dev->dev, "WM Firmware Version: %.10s, Build Time: %.15s\n", + dev_info(dev->dev, "WM Firmware Version: %.10s, Build Time: %.15s", hdr->fw_ver, hdr->build_date); ret = mt76_connac_mcu_send_ram_firmware(dev, hdr, fw->data, false); @@ -3048,7 +3048,7 @@ int mt76_connac2_load_ram(struct mt76_dev *dev, const char *fw_wm, } hdr = (const void *)(fw->data + fw->size - sizeof(*hdr)); - dev_info(dev->dev, "WA Firmware Version: %.10s, Build Time: %.15s\n", + dev_info(dev->dev, "WA Firmware Version: %.10s, Build Time: %.15s", hdr->fw_ver, hdr->build_date); ret = mt76_connac_mcu_send_ram_firmware(dev, hdr, fw->data, true); @@ -3101,7 +3101,6 @@ int mt76_connac2_load_patch(struct mt76_dev *dev, const char *fw_name) int i, ret, sem, max_len = mt76_is_sdio(dev) ? 2048 : 4096; const struct mt76_connac2_patch_hdr *hdr; const struct firmware *fw = NULL; - char build_date[17]; sem = mt76_connac_mcu_patch_sem_ctrl(dev, true); switch (sem) { @@ -3125,11 +3124,8 @@ int mt76_connac2_load_patch(struct mt76_dev *dev, const char *fw_name) } hdr = (const void *)fw->data; - strscpy(build_date, hdr->build_date, sizeof(build_date)); - build_date[16] = '\0'; - strim(build_date); - dev_info(dev->dev, "HW/SW Version: 0x%x, Build Time: %.16s\n", - be32_to_cpu(hdr->hw_sw_ver), build_date); + dev_info(dev->dev, "HW/SW Version: 0x%x, Build Time: %.16s", + be32_to_cpu(hdr->hw_sw_ver), hdr->build_date); for (i = 0; i < be32_to_cpu(hdr->desc.n_region); i++) { struct mt76_connac2_patch_sec *sec; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c index aa702ba7c9f5..d6c35e8d02a5 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c @@ -511,7 +511,8 @@ void rtl92cu_tx_fill_desc(struct ieee80211_hw *hw, if (sta) { sta_entry = (struct rtl_sta_info *)sta->drv_priv; tid = ieee80211_get_tid(hdr); - agg_state = sta_entry->tids[tid].agg.agg_state; + if (tid < MAX_TID_COUNT) + agg_state = sta_entry->tids[tid].agg.agg_state; ampdu_density = sta->deflink.ht_cap.ampdu_density; } diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c index 99d7c629eac6..e35de52d8eb4 100644 --- a/drivers/net/wireless/realtek/rtw88/sdio.c +++ b/drivers/net/wireless/realtek/rtw88/sdio.c @@ -144,8 +144,10 @@ static u32 rtw_sdio_to_io_address(struct rtw_dev *rtwdev, u32 addr, static bool rtw_sdio_use_direct_io(struct rtw_dev *rtwdev, u32 addr) { + bool might_indirect_under_power_off = rtwdev->chip->id == RTW_CHIP_TYPE_8822C; + if (!test_bit(RTW_FLAG_POWERON, rtwdev->flags) && - !rtw_sdio_is_bus_addr(addr)) + !rtw_sdio_is_bus_addr(addr) && might_indirect_under_power_off) return false; return !rtw_sdio_is_sdio30_supported(rtwdev) || diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c index 009202c627d2..3b5126ffc81a 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.c +++ b/drivers/net/wireless/realtek/rtw88/usb.c @@ -965,8 +965,7 @@ static int rtw_usb_init_rx(struct rtw_dev *rtwdev) struct sk_buff *rx_skb; int i; - rtwusb->rxwq = alloc_workqueue("rtw88_usb: rx wq", WQ_BH | WQ_UNBOUND, - 0); + rtwusb->rxwq = alloc_workqueue("rtw88_usb: rx wq", WQ_BH, 0); if (!rtwusb->rxwq) { rtw_err(rtwdev, "failed to create RX work queue\n"); return -ENOMEM; diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index f3a853edfc11..8c8e074a3a70 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -2035,6 +2035,7 @@ int rsi_mac80211_attach(struct rsi_common *common) hw->queues = MAX_HW_QUEUES; hw->extra_tx_headroom = RSI_NEEDED_HEADROOM; + hw->vif_data_size = sizeof(struct vif_priv); hw->max_rates = 1; hw->max_rate_tries = MAX_RETRIES; diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c index f76087be2f75..6241866d39df 100644 --- a/drivers/net/wireless/ti/wlcore/tx.c +++ b/drivers/net/wireless/ti/wlcore/tx.c @@ -207,6 +207,11 @@ static int wl1271_tx_allocate(struct wl1271 *wl, struct wl12xx_vif *wlvif, total_blocks = wlcore_hw_calc_tx_blocks(wl, total_len, spare_blocks); if (total_blocks <= wl->tx_blocks_available) { + if (skb_headroom(skb) < (total_len - skb->len) && + pskb_expand_head(skb, (total_len - skb->len), 0, GFP_ATOMIC)) { + wl1271_free_tx_id(wl, id); + return -EAGAIN; + } desc = skb_push(skb, total_len - skb->len); wlcore_hw_set_tx_desc_blocks(wl, desc, total_blocks, diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 551f5eb4e747..79cc63272134 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -4040,7 +4040,7 @@ mac80211_hwsim_nan_dw_start(struct hrtimer *timer) ieee80211_vif_to_wdev(data->nan_device_vif); if (data->nan_curr_dw_band == NL80211_BAND_5GHZ) - ch = ieee80211_get_channel(hw->wiphy, 5475); + ch = ieee80211_get_channel(hw->wiphy, 5745); else ch = ieee80211_get_channel(hw->wiphy, 2437); @@ -4112,14 +4112,14 @@ static int mac80211_hwsim_stop_nan(struct ieee80211_hw *hw, hrtimer_cancel(&data->nan_timer); data->nan_device_vif = NULL; - spin_lock(&hwsim_radio_lock); + spin_lock_bh(&hwsim_radio_lock); list_for_each_entry(data2, &hwsim_radios, list) { if (data2->nan_device_vif) { nan_cluster_running = true; break; } } - spin_unlock(&hwsim_radio_lock); + spin_unlock_bh(&hwsim_radio_lock); if (!nan_cluster_running) memset(hwsim_nan_cluster_id, 0, ETH_ALEN); diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.c b/drivers/net/wwan/iosm/iosm_ipc_mux.c index fc928b298a98..b846889fcb09 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.c @@ -456,6 +456,7 @@ void ipc_mux_deinit(struct iosm_mux *ipc_mux) struct sk_buff_head *free_list; union mux_msg mux_msg; struct sk_buff *skb; + int i; if (!ipc_mux->initialized) return; @@ -479,5 +480,10 @@ void ipc_mux_deinit(struct iosm_mux *ipc_mux) ipc_mux->channel->dl_pipe.is_open = false; } + if (ipc_mux->protocol != MUX_LITE) { + for (i = 0; i < IPC_MEM_MUX_IP_SESSION_ENTRIES; i++) + kfree(ipc_mux->ul_adb.pp_qlt[i]); + } + kfree(ipc_mux); } diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index 0dace12f5ad0..f8bc9a39bfa3 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -78,9 +78,8 @@ struct mhi_mbim_context { struct mbim_tx_hdr { struct usb_cdc_ncm_nth16 nth16; - - /* Must be last as it ends in a flexible-array member. */ struct usb_cdc_ncm_ndp16 ndp16; + struct usb_cdc_ncm_dpe16 dpe16[2]; } __packed; static struct mhi_mbim_link *mhi_mbim_get_link_rcu(struct mhi_mbim_context *mbim, @@ -108,20 +107,20 @@ static int mhi_mbim_get_link_mux_id(struct mhi_controller *cntrl) static struct sk_buff *mbim_tx_fixup(struct sk_buff *skb, unsigned int session, u16 tx_seq) { - DEFINE_RAW_FLEX(struct mbim_tx_hdr, mbim_hdr, ndp16.dpe16, 2); unsigned int dgram_size = skb->len; struct usb_cdc_ncm_nth16 *nth16; struct usb_cdc_ncm_ndp16 *ndp16; + struct mbim_tx_hdr *mbim_hdr; /* Only one NDP is sent, containing the IP packet (no aggregation) */ /* Ensure we have enough headroom for crafting MBIM header */ - if (skb_cow_head(skb, __struct_size(mbim_hdr))) { + if (skb_cow_head(skb, sizeof(struct mbim_tx_hdr))) { dev_kfree_skb_any(skb); return NULL; } - mbim_hdr = skb_push(skb, __struct_size(mbim_hdr)); + mbim_hdr = skb_push(skb, sizeof(struct mbim_tx_hdr)); /* Fill NTB header */ nth16 = &mbim_hdr->nth16; @@ -134,11 +133,12 @@ static struct sk_buff *mbim_tx_fixup(struct sk_buff *skb, unsigned int session, /* Fill the unique NDP */ ndp16 = &mbim_hdr->ndp16; ndp16->dwSignature = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN | (session << 24)); - ndp16->wLength = cpu_to_le16(struct_size(ndp16, dpe16, 2)); + ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16) + + sizeof(struct usb_cdc_ncm_dpe16) * 2); ndp16->wNextNdpIndex = 0; /* Datagram follows the mbim header */ - ndp16->dpe16[0].wDatagramIndex = cpu_to_le16(__struct_size(mbim_hdr)); + ndp16->dpe16[0].wDatagramIndex = cpu_to_le16(sizeof(struct mbim_tx_hdr)); ndp16->dpe16[0].wDatagramLength = cpu_to_le16(dgram_size); /* null termination */ @@ -584,8 +584,7 @@ static void mhi_mbim_setup(struct net_device *ndev) { ndev->header_ops = NULL; /* No header */ ndev->type = ARPHRD_RAWIP; - ndev->needed_headroom = - struct_size_t(struct mbim_tx_hdr, ndp16.dpe16, 2); + ndev->needed_headroom = sizeof(struct mbim_tx_hdr); ndev->hard_header_len = 0; ndev->addr_len = 0; ndev->flags = IFF_POINTOPOINT | IFF_NOARP; diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c index b76bea6ab2d7..5af90ca6e063 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c @@ -395,6 +395,7 @@ static int t7xx_dpmaif_set_frag_to_skb(const struct dpmaif_rx_queue *rxq, struct sk_buff *skb) { unsigned long long data_bus_addr, data_base_addr; + struct skb_shared_info *shinfo = skb_shinfo(skb); struct device *dev = rxq->dpmaif_ctrl->dev; struct dpmaif_bat_page *page_info; unsigned int data_len; @@ -402,18 +403,22 @@ static int t7xx_dpmaif_set_frag_to_skb(const struct dpmaif_rx_queue *rxq, page_info = rxq->bat_frag->bat_skb; page_info += t7xx_normal_pit_bid(pkt_info); - dma_unmap_page(dev, page_info->data_bus_addr, page_info->data_len, DMA_FROM_DEVICE); if (!page_info->page) return -EINVAL; + if (shinfo->nr_frags >= MAX_SKB_FRAGS) + return -EINVAL; + + dma_unmap_page(dev, page_info->data_bus_addr, page_info->data_len, DMA_FROM_DEVICE); + data_bus_addr = le32_to_cpu(pkt_info->pd.data_addr_h); data_bus_addr = (data_bus_addr << 32) + le32_to_cpu(pkt_info->pd.data_addr_l); data_base_addr = page_info->data_bus_addr; data_offset = data_bus_addr - data_base_addr; data_offset += page_info->offset; data_len = FIELD_GET(PD_PIT_DATA_LEN, le32_to_cpu(pkt_info->header)); - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page_info->page, + skb_add_rx_frag(skb, shinfo->nr_frags, page_info->page, data_offset, data_len, page_info->data_len); page_info->page = NULL; diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index 9ef8ef2d4363..b957fce83b7c 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -125,10 +125,6 @@ static ssize_t virtual_ncidev_write(struct file *file, kfree_skb(skb); return -EFAULT; } - if (strnlen(skb->data, count) != count) { - kfree_skb(skb); - return -EINVAL; - } nci_recv_frame(vdev->ndev, skb); return count; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index eb875e3db2e3..71d4bb25f7fd 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -1394,6 +1394,7 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) goto err2; } + mutex_init(&nt->link_event_lock); INIT_DELAYED_WORK(&nt->link_work, ntb_transport_link_work); INIT_WORK(&nt->link_cleanup, ntb_transport_link_cleanup_work); diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 15b3d07f8ccd..ed61b97fde59 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1704,6 +1704,7 @@ static const struct apple_nvme_hw apple_nvme_t8103_hw = { static const struct of_device_id apple_nvme_of_match[] = { { .compatible = "apple,t8015-nvme-ans2", .data = &apple_nvme_t8015_hw }, + { .compatible = "apple,t8103-nvme-ans2", .data = &apple_nvme_t8103_hw }, { .compatible = "apple,nvme-ans2", .data = &apple_nvme_t8103_hw }, {}, }; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index bc455fa98246..6948de3f438a 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3587,6 +3587,8 @@ fail_ctrl: ctrl->ctrl.opts = NULL; + if (ctrl->ctrl.admin_tagset) + nvme_remove_admin_tag_set(&ctrl->ctrl); /* initiate nvme ctrl ref counting teardown */ nvme_uninit_ctrl(&ctrl->ctrl); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 0e4caeab739c..58f3097888a7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1532,7 +1532,10 @@ static int nvme_pci_subsystem_reset(struct nvme_ctrl *ctrl) } writel(NVME_SUBSYS_RESET, dev->bar + NVME_REG_NSSR); - nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE); + + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) || + !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) + goto unlock; /* * Read controller status to flush the previous write and trigger a @@ -3999,6 +4002,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x1fa0, 0x2283), /* Wodposit WPBSNM8-256GTP */ + .driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, }, { PCI_DEVICE(0x025e, 0xf1ac), /* SOLIDIGM P44 pro SSDPFKKW020X7 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */ diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 96648ec2fadb..67c423a8b052 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -150,7 +150,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req) * code path with duplicate ctrl subsysnqn. In order to prevent that we * mask the passthru-ctrl subsysnqn with the target ctrl subsysnqn. */ - memcpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn)); + strscpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn)); /* use fabric id-ctrl values */ id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) + diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 15416ff0eac4..549a4786d1c3 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -982,6 +982,18 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len); goto err_proto; } + /* + * Ensure command data structures are initialized. We must check both + * cmd->req.sg and cmd->iov because they can have different NULL states: + * - Uninitialized commands: both NULL + * - READ commands: cmd->req.sg allocated, cmd->iov NULL + * - WRITE commands: both allocated + */ + if (unlikely(!cmd->req.sg || !cmd->iov)) { + pr_err("queue %d: H2CData PDU received for invalid command state (ttag %u)\n", + queue->idx, data->ttag); + goto err_proto; + } cmd->pdu_recv = 0; nvmet_tcp_build_pdu_iovec(cmd); queue->cmd = cmd; @@ -1992,14 +2004,13 @@ static void nvmet_tcp_listen_data_ready(struct sock *sk) trace_sk_data_ready(sk); + if (sk->sk_state != TCP_LISTEN) + return; + read_lock_bh(&sk->sk_callback_lock); port = sk->sk_user_data; - if (!port) - goto out; - - if (sk->sk_state == TCP_LISTEN) + if (port) queue_work(nvmet_wq, &port->accept_work); -out: read_unlock_bh(&sk->sk_callback_lock); } diff --git a/drivers/of/base.c b/drivers/of/base.c index 0b65039ece53..57420806c1a2 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1942,13 +1942,17 @@ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)) end--; len = end - start; - if (kstrtoint(end, 10, &id) < 0) + if (kstrtoint(end, 10, &id) < 0) { + of_node_put(np); continue; + } /* Allocate an alias_prop with enough space for the stem */ ap = dt_alloc(sizeof(*ap) + len + 1, __alignof__(*ap)); - if (!ap) + if (!ap) { + of_node_put(np); continue; + } memset(ap, 0, sizeof(*ap) + len + 1); ap->alias = start; of_alias_add(ap, np, id, start, len); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index f77cb19973a5..a6dca3a005aa 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -569,7 +569,7 @@ static int __init of_platform_default_populate_init(void) node = of_find_node_by_path("/firmware"); if (node) { - of_platform_populate(node, NULL, NULL, NULL); + of_platform_default_populate(node, NULL, NULL); of_node_put(node); } diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 388e9ec2cccf..3b773aaf9d05 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -1985,7 +1985,6 @@ static void attach_node_and_children(struct device_node *np) */ static int __init unittest_data_add(void) { - void *unittest_data; void *unittest_data_align; struct device_node *unittest_data_node = NULL, *np; /* @@ -2004,7 +2003,7 @@ static int __init unittest_data_add(void) } /* creating copy */ - unittest_data = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL); + void *unittest_data __free(kfree) = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL); if (!unittest_data) return -ENOMEM; @@ -2014,12 +2013,10 @@ static int __init unittest_data_add(void) ret = of_fdt_unflatten_tree(unittest_data_align, NULL, &unittest_data_node); if (!ret) { pr_warn("%s: unflatten testcases tree failed\n", __func__); - kfree(unittest_data); return -ENODATA; } if (!unittest_data_node) { pr_warn("%s: testcases tree is empty\n", __func__); - kfree(unittest_data); return -ENODATA; } @@ -2038,7 +2035,6 @@ static int __init unittest_data_add(void) /* attach the sub-tree to live tree */ if (!of_root) { pr_warn("%s: no live tree to attach sub-tree\n", __func__); - kfree(unittest_data); rc = -ENODEV; goto unlock; } @@ -2059,6 +2055,8 @@ static int __init unittest_data_add(void) EXPECT_END(KERN_INFO, "Duplicate name in testcase-data, renamed to \"duplicate-name#1\""); + retain_and_null_ptr(unittest_data); + unlock: of_overlay_mutex_unlock(); diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 00b0210e1f1d..e3f848ffb52a 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -225,12 +225,6 @@ config PCI_P2PDMA P2P DMA transactions must be between devices behind the same root port. - Enabling this option will reduce the entropy of x86 KASLR memory - regions. For example - on a 46 bit system, the entropy goes down - from 16 bits to 15 bits. The actual reduction in entropy depends - on the physical address bits, on processor features, kernel config - (5 level page table) and physical memory present on the system. - If unsure, say N. config PCI_LABEL diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c index 54b6a4196f17..0694084f612b 100644 --- a/drivers/pci/controller/dwc/pci-meson.c +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -37,7 +37,6 @@ #define PCIE_CFG_STATUS17 0x44 #define PM_CURRENT_STATE(x) (((x) >> 7) & 0x1) -#define WAIT_LINKUP_TIMEOUT 4000 #define PORT_CLK_RATE 100000000UL #define MAX_PAYLOAD_SIZE 256 #define MAX_READ_REQ_SIZE 256 @@ -350,40 +349,10 @@ static struct pci_ops meson_pci_ops = { static bool meson_pcie_link_up(struct dw_pcie *pci) { struct meson_pcie *mp = to_meson_pcie(pci); - struct device *dev = pci->dev; - u32 speed_okay = 0; - u32 cnt = 0; - u32 state12, state17, smlh_up, ltssm_up, rdlh_up; - - do { - state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12); - state17 = meson_cfg_readl(mp, PCIE_CFG_STATUS17); - smlh_up = IS_SMLH_LINK_UP(state12); - rdlh_up = IS_RDLH_LINK_UP(state12); - ltssm_up = IS_LTSSM_UP(state12); - - if (PM_CURRENT_STATE(state17) < PCIE_GEN3) - speed_okay = 1; - - if (smlh_up) - dev_dbg(dev, "smlh_link_up is on\n"); - if (rdlh_up) - dev_dbg(dev, "rdlh_link_up is on\n"); - if (ltssm_up) - dev_dbg(dev, "ltssm_up is on\n"); - if (speed_okay) - dev_dbg(dev, "speed_okay\n"); - - if (smlh_up && rdlh_up && ltssm_up && speed_okay) - return true; - - cnt++; - - udelay(10); - } while (cnt < WAIT_LINKUP_TIMEOUT); - - dev_err(dev, "error: wait linkup timeout\n"); - return false; + u32 state12; + + state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12); + return IS_SMLH_LINK_UP(state12) && IS_RDLH_LINK_UP(state12); } static int meson_pcie_host_init(struct dw_pcie_rp *pp) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 7b92e7a1c0d9..5a318487b2b3 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1047,7 +1047,6 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) writel(WR_NO_SNOOP_OVERRIDE_EN | RD_NO_SNOOP_OVERRIDE_EN, pcie->parf + PARF_NO_SNOOP_OVERRIDE); - qcom_pcie_clear_aspm_l0s(pcie->pci); qcom_pcie_clear_hpc(pcie->pci); return 0; @@ -1316,6 +1315,8 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp) goto err_disable_phy; } + qcom_pcie_clear_aspm_l0s(pcie->pci); + qcom_ep_reset_deassert(pcie); if (pcie->cfg->ops->config_sid) { @@ -1464,6 +1465,7 @@ static const struct qcom_pcie_cfg cfg_2_1_0 = { static const struct qcom_pcie_cfg cfg_2_3_2 = { .ops = &ops_2_3_2, + .no_l0s = true, }; static const struct qcom_pcie_cfg cfg_2_3_3 = { diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index b9c252aa6fe0..280cd50d693b 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -6308,7 +6308,6 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5020, of_pci_make_dev_node); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5021, of_pci_make_dev_node); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_REDHAT, 0x0005, of_pci_make_dev_node); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_EFAR, 0x9660, of_pci_make_dev_node); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_RPI, PCI_DEVICE_ID_RPI_RP1_C0, of_pci_make_dev_node); /* * Devices known to require a longer delay before first config space access diff --git a/drivers/pci/rebar.c b/drivers/pci/rebar.c index ecdebdeb2dff..39f8cf3b70d5 100644 --- a/drivers/pci/rebar.c +++ b/drivers/pci/rebar.c @@ -295,7 +295,6 @@ int pci_resize_resource(struct pci_dev *dev, int resno, int size, int exclude_bars) { struct pci_host_bridge *host; - int old, ret; /* Check if we must preserve the firmware's resource assignment */ host = pci_find_host_bridge(dev->bus); @@ -308,21 +307,6 @@ int pci_resize_resource(struct pci_dev *dev, int resno, int size, if (!pci_rebar_size_supported(dev, resno, size)) return -EINVAL; - old = pci_rebar_get_current_size(dev, resno); - if (old < 0) - return old; - - ret = pci_rebar_set_size(dev, resno, size); - if (ret) - return ret; - - ret = pci_do_resource_release_and_resize(dev, resno, size, exclude_bars); - if (ret) - goto error_resize; - return 0; - -error_resize: - pci_rebar_set_size(dev, resno, old); - return ret; + return pci_do_resource_release_and_resize(dev, resno, size, exclude_bars); } EXPORT_SYMBOL(pci_resize_resource); diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 6e90f46f52af..a61d38777cdc 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -2504,12 +2504,20 @@ int pci_do_resource_release_and_resize(struct pci_dev *pdev, int resno, int size struct resource *b_win, *r; LIST_HEAD(saved); unsigned int i; - int ret = 0; + int old, ret; b_win = pbus_select_window(bus, res); if (!b_win) return -EINVAL; + old = pci_rebar_get_current_size(pdev, resno); + if (old < 0) + return old; + + ret = pci_rebar_set_size(pdev, resno, size); + if (ret) + return ret; + pci_dev_for_each_resource(pdev, r, i) { if (i >= PCI_BRIDGE_RESOURCES) break; @@ -2542,7 +2550,15 @@ out: return ret; restore: - /* Revert to the old configuration */ + /* + * Revert to the old configuration. + * + * BAR Size must be restored first because it affects the read-only + * bits in BAR (the old address might not be restorable otherwise + * due to low address bits). + */ + pci_rebar_set_size(pdev, resno, old); + list_for_each_entry(dev_res, &saved, list) { struct resource *res = dev_res->res; struct pci_dev *dev = dev_res->dev; @@ -2556,8 +2572,7 @@ restore: restore_dev_resource(dev_res); - ret = pci_claim_resource(dev, i); - if (ret) + if (pci_claim_resource(dev, i)) continue; if (i < PCI_BRIDGE_RESOURCES) { diff --git a/drivers/pci/vgaarb.c b/drivers/pci/vgaarb.c index 436fa7f4c387..baa242b14099 100644 --- a/drivers/pci/vgaarb.c +++ b/drivers/pci/vgaarb.c @@ -652,13 +652,6 @@ static bool vga_is_boot_device(struct vga_device *vgadev) return true; } - /* - * Vgadev has neither IO nor MEM enabled. If we haven't found any - * other VGA devices, it is the best candidate so far. - */ - if (!boot_vga) - return true; - return false; } diff --git a/drivers/phy/broadcom/phy-bcm-ns-usb3.c b/drivers/phy/broadcom/phy-bcm-ns-usb3.c index 9f995e156f75..6e56498d0644 100644 --- a/drivers/phy/broadcom/phy-bcm-ns-usb3.c +++ b/drivers/phy/broadcom/phy-bcm-ns-usb3.c @@ -203,7 +203,7 @@ static int bcm_ns_usb3_mdio_probe(struct mdio_device *mdiodev) usb3->dev = dev; usb3->mdiodev = mdiodev; - usb3->family = (enum bcm_ns_family)device_get_match_data(dev); + usb3->family = (unsigned long)device_get_match_data(dev); syscon_np = of_parse_phandle(dev->of_node, "usb3-dmp-syscon", 0); err = of_address_to_resource(syscon_np, 0, &res); diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index 68fcc8114d75..7f5600103a00 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -89,7 +89,8 @@ static int imx8_pcie_phy_power_on(struct phy *phy) writel(imx8_phy->tx_deemph_gen2, imx8_phy->base + PCIE_PHY_TRSV_REG6); break; - case IMX8MP: /* Do nothing. */ + case IMX8MP: + reset_control_assert(imx8_phy->reset); break; } diff --git a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c index ad8a55012e42..91b3e62743d3 100644 --- a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c +++ b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c @@ -126,8 +126,6 @@ struct imx8mq_usb_phy { static void tca_blk_orientation_set(struct tca_blk *tca, enum typec_orientation orientation); -#ifdef CONFIG_TYPEC - static int tca_blk_typec_switch_set(struct typec_switch_dev *sw, enum typec_orientation orientation) { @@ -175,18 +173,6 @@ static void tca_blk_put_typec_switch(struct typec_switch_dev *sw) typec_switch_unregister(sw); } -#else - -static struct typec_switch_dev *tca_blk_get_typec_switch(struct platform_device *pdev, - struct imx8mq_usb_phy *imx_phy) -{ - return NULL; -} - -static void tca_blk_put_typec_switch(struct typec_switch_dev *sw) {} - -#endif /* CONFIG_TYPEC */ - static void tca_blk_orientation_set(struct tca_blk *tca, enum typec_orientation orientation) { @@ -504,6 +490,7 @@ static void imx8m_phy_tune(struct imx8mq_usb_phy *imx_phy) if (imx_phy->pcs_tx_swing_full != PHY_TUNE_DEFAULT) { value = readl(imx_phy->base + PHY_CTRL5); + value &= ~PHY_CTRL5_PCS_TX_SWING_FULL_MASK; value |= FIELD_PREP(PHY_CTRL5_PCS_TX_SWING_FULL_MASK, imx_phy->pcs_tx_swing_full); writel(value, imx_phy->base + PHY_CTRL5); diff --git a/drivers/phy/microchip/Kconfig b/drivers/phy/microchip/Kconfig index 2f0045e874ac..2e6d1224711e 100644 --- a/drivers/phy/microchip/Kconfig +++ b/drivers/phy/microchip/Kconfig @@ -6,7 +6,7 @@ config PHY_SPARX5_SERDES tristate "Microchip Sparx5 SerDes PHY driver" select GENERIC_PHY - depends on ARCH_SPARX5 || COMPILE_TEST + depends on ARCH_SPARX5 || ARCH_LAN969X || COMPILE_TEST depends on OF depends on HAS_IOMEM help diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index b5514a32ff8f..eb93015be841 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -1093,29 +1093,29 @@ static int qusb2_phy_probe(struct platform_device *pdev) or->hsdisc_trim.override = true; } - pm_runtime_set_active(dev); - pm_runtime_enable(dev); + dev_set_drvdata(dev, qphy); + /* - * Prevent runtime pm from being ON by default. Users can enable - * it using power/control in sysfs. + * Enable runtime PM support, but forbid it by default. + * Users can allow it again via the power/control attribute in sysfs. */ + pm_runtime_set_active(dev); pm_runtime_forbid(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; generic_phy = devm_phy_create(dev, NULL, &qusb2_phy_gen_ops); if (IS_ERR(generic_phy)) { ret = PTR_ERR(generic_phy); dev_err(dev, "failed to create phy, %d\n", ret); - pm_runtime_disable(dev); return ret; } qphy->phy = generic_phy; - dev_set_drvdata(dev, qphy); phy_set_drvdata(generic_phy, qphy); phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - pm_runtime_disable(dev); return PTR_ERR_OR_ZERO(phy_provider); } diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c index b0f23690ec30..8f4c08e599aa 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c @@ -821,17 +821,20 @@ static void rockchip_chg_detect_work(struct work_struct *work) container_of(work, struct rockchip_usb2phy_port, chg_work.work); struct rockchip_usb2phy *rphy = dev_get_drvdata(rport->phy->dev.parent); struct regmap *base = get_reg_base(rphy); - bool is_dcd, tmout, vout; + bool is_dcd, tmout, vout, vbus_attach; unsigned long delay; + vbus_attach = property_enabled(rphy->grf, &rport->port_cfg->utmi_bvalid); + dev_dbg(&rport->phy->dev, "chg detection work state = %d\n", rphy->chg_state); switch (rphy->chg_state) { case USB_CHG_STATE_UNDEFINED: - if (!rport->suspended) + if (!rport->suspended && !vbus_attach) rockchip_usb2phy_power_off(rport->phy); /* put the controller in non-driving mode */ - property_enable(base, &rphy->phy_cfg->chg_det.opmode, false); + if (!vbus_attach) + property_enable(base, &rphy->phy_cfg->chg_det.opmode, false); /* Start DCD processing stage 1 */ rockchip_chg_enable_dcd(rphy, true); rphy->chg_state = USB_CHG_STATE_WAIT_FOR_DCD; @@ -894,7 +897,8 @@ static void rockchip_chg_detect_work(struct work_struct *work) fallthrough; case USB_CHG_STATE_DETECTED: /* put the controller in normal mode */ - property_enable(base, &rphy->phy_cfg->chg_det.opmode, true); + if (!vbus_attach) + property_enable(base, &rphy->phy_cfg->chg_det.opmode, true); rockchip_usb2phy_otg_sm_work(&rport->otg_sm_work.work); dev_dbg(&rport->phy->dev, "charger = %s\n", chg_to_string(rphy->chg_type)); @@ -1491,7 +1495,7 @@ next_child: rphy); if (ret) { dev_err_probe(rphy->dev, ret, "failed to request usb2phy irq handle\n"); - goto put_child; + return ret; } } diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c index 27fe92f73f33..b44afbff8616 100644 --- a/drivers/phy/st/phy-stm32-usbphyc.c +++ b/drivers/phy/st/phy-stm32-usbphyc.c @@ -712,7 +712,7 @@ static int stm32_usbphyc_probe(struct platform_device *pdev) } ret = of_property_read_u32(child, "reg", &index); - if (ret || index > usbphyc->nphys) { + if (ret || index >= usbphyc->nphys) { dev_err(&phy->dev, "invalid reg property: %d\n", ret); if (!ret) ret = -EINVAL; diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c index e818f6c3980e..bec9616c4a2e 100644 --- a/drivers/phy/tegra/xusb-tegra186.c +++ b/drivers/phy/tegra/xusb-tegra186.c @@ -84,6 +84,7 @@ #define XUSB_PADCTL_USB2_BIAS_PAD_CTL0 0x284 #define BIAS_PAD_PD BIT(11) #define HS_SQUELCH_LEVEL(x) (((x) & 0x7) << 0) +#define HS_DISCON_LEVEL(x) (((x) & 0x7) << 3) #define XUSB_PADCTL_USB2_BIAS_PAD_CTL1 0x288 #define USB2_TRK_START_TIMER(x) (((x) & 0x7f) << 12) @@ -623,6 +624,8 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl) value &= ~BIAS_PAD_PD; value &= ~HS_SQUELCH_LEVEL(~0); value |= HS_SQUELCH_LEVEL(priv->calib.hs_squelch); + value &= ~HS_DISCON_LEVEL(~0); + value |= HS_DISCON_LEVEL(0x7); padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL0); udelay(1); diff --git a/drivers/phy/ti/phy-da8xx-usb.c b/drivers/phy/ti/phy-da8xx-usb.c index 1d81a1e6ec6b..62fa6f89c0e6 100644 --- a/drivers/phy/ti/phy-da8xx-usb.c +++ b/drivers/phy/ti/phy-da8xx-usb.c @@ -180,6 +180,7 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) struct da8xx_usb_phy_platform_data *pdata = dev->platform_data; struct device_node *node = dev->of_node; struct da8xx_usb_phy *d_phy; + int ret; d_phy = devm_kzalloc(dev, sizeof(*d_phy), GFP_KERNEL); if (!d_phy) @@ -233,8 +234,6 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) return PTR_ERR(d_phy->phy_provider); } } else { - int ret; - ret = phy_create_lookup(d_phy->usb11_phy, "usb-phy", "ohci-da8xx"); if (ret) @@ -249,7 +248,9 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) PHY_INIT_BITS, PHY_INIT_BITS); pm_runtime_set_active(dev); - devm_pm_runtime_enable(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; /* * Prevent runtime pm from being ON by default. Users can enable * it using power/control in sysfs. diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index 6cfe2538d15b..6213c2b6005a 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -512,7 +512,7 @@ static int phy_gmii_sel_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(base), "failed to get base memory resource\n"); - priv->regmap = regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg); + priv->regmap = devm_regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg); if (IS_ERR(priv->regmap)) return dev_err_probe(dev, PTR_ERR(priv->regmap), "Failed to get syscon\n"); diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index bc7f37afc48b..7b9f792acb0e 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -491,6 +491,7 @@ config PINCTRL_PIC64GX depends on ARCH_MICROCHIP || COMPILE_TEST depends on OF select GENERIC_PINCONF + select REGMAP_MMIO default y help This selects the pinctrl driver for gpio2 on pic64gx. diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8189.c b/drivers/pinctrl/mediatek/pinctrl-mt8189.c index f6a3e584588b..cd4cdff309a1 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8189.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8189.c @@ -1642,7 +1642,7 @@ static const struct mtk_pin_reg_calc mt8189_reg_cals[PINCTRL_PIN_REG_MAX] = { }; static const char * const mt8189_pinctrl_register_base_names[] = { - "base", "lm", "rb0", "rb1", "bm0", "bm1", "bm2", "lt0", "lt1", "rt", + "base", "bm0", "bm1", "bm2", "lm", "lt0", "lt1", "rb0", "rb1", "rt", }; static const struct mtk_eint_hw mt8189_eint_hw = { diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index 18295b15ecd9..4507dc8b5563 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -619,7 +619,7 @@ static int meson_gpiolib_register(struct meson_pinctrl *pc) pc->chip.set = meson_gpio_set; pc->chip.base = -1; pc->chip.ngpio = pc->data->num_pins; - pc->chip.can_sleep = false; + pc->chip.can_sleep = true; ret = gpiochip_add_data(&pc->chip, pc); if (ret) { diff --git a/drivers/pinctrl/pinctrl-th1520.c b/drivers/pinctrl/pinctrl-th1520.c index e641bad6728c..83e9c9f77370 100644 --- a/drivers/pinctrl/pinctrl-th1520.c +++ b/drivers/pinctrl/pinctrl-th1520.c @@ -287,7 +287,7 @@ static const struct pinctrl_pin_desc th1520_group3_pins[] = { TH1520_PAD(5, QSPI0_D0_MOSI, QSPI, PWM, I2S, GPIO, ____, ____, 0), TH1520_PAD(6, QSPI0_D1_MISO, QSPI, PWM, I2S, GPIO, ____, ____, 0), TH1520_PAD(7, QSPI0_D2_WP, QSPI, PWM, I2S, GPIO, ____, ____, 0), - TH1520_PAD(8, QSPI1_D3_HOLD, QSPI, ____, I2S, GPIO, ____, ____, 0), + TH1520_PAD(8, QSPI0_D3_HOLD, QSPI, ____, I2S, GPIO, ____, ____, 0), TH1520_PAD(9, I2C2_SCL, I2C, UART, ____, GPIO, ____, ____, 0), TH1520_PAD(10, I2C2_SDA, I2C, UART, ____, GPIO, ____, ____, 0), TH1520_PAD(11, I2C3_SCL, I2C, ____, ____, GPIO, ____, ____, 0), diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index c480e8b78503..f56592411cf6 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -61,13 +61,14 @@ config PINCTRL_LPASS_LPI (Low Power Island) found on the Qualcomm Technologies Inc SoCs. config PINCTRL_SC7280_LPASS_LPI - tristate "Qualcomm Technologies Inc SC7280 LPASS LPI pin controller driver" + tristate "Qualcomm Technologies Inc SC7280 and SM8350 LPASS LPI pin controller driver" depends on ARM64 || COMPILE_TEST depends on PINCTRL_LPASS_LPI help This is the pinctrl, pinmux, pinconf and gpiolib driver for the Qualcomm Technologies Inc LPASS (Low Power Audio SubSystem) LPI - (Low Power Island) found on the Qualcomm Technologies Inc SC7280 platform. + (Low Power Island) found on the Qualcomm Technologies Inc SC7280 + and SM8350 platforms. config PINCTRL_SDM660_LPASS_LPI tristate "Qualcomm Technologies Inc SDM660 LPASS LPI pin controller driver" @@ -106,16 +107,6 @@ config PINCTRL_SM8250_LPASS_LPI Qualcomm Technologies Inc LPASS (Low Power Audio SubSystem) LPI (Low Power Island) found on the Qualcomm Technologies Inc SM8250 platform. -config PINCTRL_SM8350_LPASS_LPI - tristate "Qualcomm Technologies Inc SM8350 LPASS LPI pin controller driver" - depends on ARM64 || COMPILE_TEST - depends on PINCTRL_LPASS_LPI - help - This is the pinctrl, pinmux, pinconf and gpiolib driver for the - Qualcomm Technologies Inc LPASS (Low Power Audio SubSystem) LPI - (Low Power Island) found on the Qualcomm Technologies Inc SM8350 - platform. - config PINCTRL_SM8450_LPASS_LPI tristate "Qualcomm Technologies Inc SM8450 LPASS LPI pin controller driver" depends on ARM64 || COMPILE_TEST diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile index 748b17a77b2c..4269d1781015 100644 --- a/drivers/pinctrl/qcom/Makefile +++ b/drivers/pinctrl/qcom/Makefile @@ -64,7 +64,6 @@ obj-$(CONFIG_PINCTRL_SM8150) += pinctrl-sm8150.o obj-$(CONFIG_PINCTRL_SM8250) += pinctrl-sm8250.o obj-$(CONFIG_PINCTRL_SM8250_LPASS_LPI) += pinctrl-sm8250-lpass-lpi.o obj-$(CONFIG_PINCTRL_SM8350) += pinctrl-sm8350.o -obj-$(CONFIG_PINCTRL_SM8350_LPASS_LPI) += pinctrl-sm8350-lpass-lpi.o obj-$(CONFIG_PINCTRL_SM8450) += pinctrl-sm8450.o obj-$(CONFIG_PINCTRL_SM8450_LPASS_LPI) += pinctrl-sm8450-lpass-lpi.o obj-$(CONFIG_PINCTRL_SM8550) += pinctrl-sm8550.o diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index 1c97ec44aa5f..76aed3296279 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -312,6 +312,22 @@ static const struct pinconf_ops lpi_gpio_pinconf_ops = { .pin_config_group_set = lpi_config_set, }; +static int lpi_gpio_get_direction(struct gpio_chip *chip, unsigned int pin) +{ + unsigned long config = pinconf_to_config_packed(PIN_CONFIG_LEVEL, 0); + struct lpi_pinctrl *state = gpiochip_get_data(chip); + unsigned long arg; + int ret; + + ret = lpi_config_get(state->ctrl, pin, &config); + if (ret) + return ret; + + arg = pinconf_to_config_argument(config); + + return arg ? GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN; +} + static int lpi_gpio_direction_input(struct gpio_chip *chip, unsigned int pin) { struct lpi_pinctrl *state = gpiochip_get_data(chip); @@ -409,6 +425,7 @@ static void lpi_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) #endif static const struct gpio_chip lpi_gpio_template = { + .get_direction = lpi_gpio_get_direction, .direction_input = lpi_gpio_direction_input, .direction_output = lpi_gpio_direction_output, .get = lpi_gpio_get, @@ -498,7 +515,7 @@ int lpi_pinctrl_probe(struct platform_device *pdev) pctrl->chip.base = -1; pctrl->chip.ngpio = data->npins; pctrl->chip.label = dev_name(dev); - pctrl->chip.can_sleep = false; + pctrl->chip.can_sleep = true; mutex_init(&pctrl->lock); diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c index 1161f0a91a00..750f410311a8 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c @@ -131,6 +131,9 @@ static const struct of_device_id lpi_pinctrl_of_match[] = { { .compatible = "qcom,sc7280-lpass-lpi-pinctrl", .data = &sc7280_lpi_data, + }, { + .compatible = "qcom,sm8350-lpass-lpi-pinctrl", + .data = &sc7280_lpi_data, }, { } }; diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c deleted file mode 100644 index 7b146b4acfdf..000000000000 --- a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c +++ /dev/null @@ -1,151 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2016-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2020-2023 Linaro Ltd. - */ - -#include <linux/gpio/driver.h> -#include <linux/module.h> -#include <linux/platform_device.h> - -#include "pinctrl-lpass-lpi.h" - -enum lpass_lpi_functions { - LPI_MUX_dmic1_clk, - LPI_MUX_dmic1_data, - LPI_MUX_dmic2_clk, - LPI_MUX_dmic2_data, - LPI_MUX_dmic3_clk, - LPI_MUX_dmic3_data, - LPI_MUX_i2s1_clk, - LPI_MUX_i2s1_data, - LPI_MUX_i2s1_ws, - LPI_MUX_i2s2_clk, - LPI_MUX_i2s2_data, - LPI_MUX_i2s2_ws, - LPI_MUX_qua_mi2s_data, - LPI_MUX_qua_mi2s_sclk, - LPI_MUX_qua_mi2s_ws, - LPI_MUX_swr_rx_clk, - LPI_MUX_swr_rx_data, - LPI_MUX_swr_tx_clk, - LPI_MUX_swr_tx_data, - LPI_MUX_wsa_swr_clk, - LPI_MUX_wsa_swr_data, - LPI_MUX_gpio, - LPI_MUX__, -}; - -static const struct pinctrl_pin_desc sm8350_lpi_pins[] = { - PINCTRL_PIN(0, "gpio0"), - PINCTRL_PIN(1, "gpio1"), - PINCTRL_PIN(2, "gpio2"), - PINCTRL_PIN(3, "gpio3"), - PINCTRL_PIN(4, "gpio4"), - PINCTRL_PIN(5, "gpio5"), - PINCTRL_PIN(6, "gpio6"), - PINCTRL_PIN(7, "gpio7"), - PINCTRL_PIN(8, "gpio8"), - PINCTRL_PIN(9, "gpio9"), - PINCTRL_PIN(10, "gpio10"), - PINCTRL_PIN(11, "gpio11"), - PINCTRL_PIN(12, "gpio12"), - PINCTRL_PIN(13, "gpio13"), - PINCTRL_PIN(14, "gpio14"), -}; - -static const char * const swr_tx_clk_groups[] = { "gpio0" }; -static const char * const swr_tx_data_groups[] = { "gpio1", "gpio2", "gpio5", "gpio14" }; -static const char * const swr_rx_clk_groups[] = { "gpio3" }; -static const char * const swr_rx_data_groups[] = { "gpio4", "gpio5" }; -static const char * const dmic1_clk_groups[] = { "gpio6" }; -static const char * const dmic1_data_groups[] = { "gpio7" }; -static const char * const dmic2_clk_groups[] = { "gpio8" }; -static const char * const dmic2_data_groups[] = { "gpio9" }; -static const char * const i2s2_clk_groups[] = { "gpio10" }; -static const char * const i2s2_ws_groups[] = { "gpio11" }; -static const char * const dmic3_clk_groups[] = { "gpio12" }; -static const char * const dmic3_data_groups[] = { "gpio13" }; -static const char * const qua_mi2s_sclk_groups[] = { "gpio0" }; -static const char * const qua_mi2s_ws_groups[] = { "gpio1" }; -static const char * const qua_mi2s_data_groups[] = { "gpio2", "gpio3", "gpio4" }; -static const char * const i2s1_clk_groups[] = { "gpio6" }; -static const char * const i2s1_ws_groups[] = { "gpio7" }; -static const char * const i2s1_data_groups[] = { "gpio8", "gpio9" }; -static const char * const wsa_swr_clk_groups[] = { "gpio10" }; -static const char * const wsa_swr_data_groups[] = { "gpio11" }; -static const char * const i2s2_data_groups[] = { "gpio12", "gpio12" }; - -static const struct lpi_pingroup sm8350_groups[] = { - LPI_PINGROUP(0, 0, swr_tx_clk, qua_mi2s_sclk, _, _), - LPI_PINGROUP(1, 2, swr_tx_data, qua_mi2s_ws, _, _), - LPI_PINGROUP(2, 4, swr_tx_data, qua_mi2s_data, _, _), - LPI_PINGROUP(3, 8, swr_rx_clk, qua_mi2s_data, _, _), - LPI_PINGROUP(4, 10, swr_rx_data, qua_mi2s_data, _, _), - LPI_PINGROUP(5, 12, swr_tx_data, swr_rx_data, _, _), - LPI_PINGROUP(6, LPI_NO_SLEW, dmic1_clk, i2s1_clk, _, _), - LPI_PINGROUP(7, LPI_NO_SLEW, dmic1_data, i2s1_ws, _, _), - LPI_PINGROUP(8, LPI_NO_SLEW, dmic2_clk, i2s1_data, _, _), - LPI_PINGROUP(9, LPI_NO_SLEW, dmic2_data, i2s1_data, _, _), - LPI_PINGROUP(10, 16, i2s2_clk, wsa_swr_clk, _, _), - LPI_PINGROUP(11, 18, i2s2_ws, wsa_swr_data, _, _), - LPI_PINGROUP(12, LPI_NO_SLEW, dmic3_clk, i2s2_data, _, _), - LPI_PINGROUP(13, LPI_NO_SLEW, dmic3_data, i2s2_data, _, _), - LPI_PINGROUP(14, 6, swr_tx_data, _, _, _), -}; - -static const struct lpi_function sm8350_functions[] = { - LPI_FUNCTION(dmic1_clk), - LPI_FUNCTION(dmic1_data), - LPI_FUNCTION(dmic2_clk), - LPI_FUNCTION(dmic2_data), - LPI_FUNCTION(dmic3_clk), - LPI_FUNCTION(dmic3_data), - LPI_FUNCTION(i2s1_clk), - LPI_FUNCTION(i2s1_data), - LPI_FUNCTION(i2s1_ws), - LPI_FUNCTION(i2s2_clk), - LPI_FUNCTION(i2s2_data), - LPI_FUNCTION(i2s2_ws), - LPI_FUNCTION(qua_mi2s_data), - LPI_FUNCTION(qua_mi2s_sclk), - LPI_FUNCTION(qua_mi2s_ws), - LPI_FUNCTION(swr_rx_clk), - LPI_FUNCTION(swr_rx_data), - LPI_FUNCTION(swr_tx_clk), - LPI_FUNCTION(swr_tx_data), - LPI_FUNCTION(wsa_swr_clk), - LPI_FUNCTION(wsa_swr_data), -}; - -static const struct lpi_pinctrl_variant_data sm8350_lpi_data = { - .pins = sm8350_lpi_pins, - .npins = ARRAY_SIZE(sm8350_lpi_pins), - .groups = sm8350_groups, - .ngroups = ARRAY_SIZE(sm8350_groups), - .functions = sm8350_functions, - .nfunctions = ARRAY_SIZE(sm8350_functions), -}; - -static const struct of_device_id lpi_pinctrl_of_match[] = { - { - .compatible = "qcom,sm8350-lpass-lpi-pinctrl", - .data = &sm8350_lpi_data, - }, - { } -}; -MODULE_DEVICE_TABLE(of, lpi_pinctrl_of_match); - -static struct platform_driver lpi_pinctrl_driver = { - .driver = { - .name = "qcom-sm8350-lpass-lpi-pinctrl", - .of_match_table = lpi_pinctrl_of_match, - }, - .probe = lpi_pinctrl_probe, - .remove = lpi_pinctrl_remove, -}; -module_platform_driver(lpi_pinctrl_driver); - -MODULE_AUTHOR("Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>"); -MODULE_DESCRIPTION("QTI SM8350 LPI GPIO pin control driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/platform/mellanox/mlx-platform.c b/drivers/platform/mellanox/mlx-platform.c index d0df18be93c7..efd0c074ad93 100644 --- a/drivers/platform/mellanox/mlx-platform.c +++ b/drivers/platform/mellanox/mlx-platform.c @@ -7381,7 +7381,7 @@ static int __init mlxplat_dmi_ng400_hi171_matched(const struct dmi_system_id *dm mlxplat_hotplug = &mlxplat_mlxcpld_ng800_hi171_data; mlxplat_hotplug->deferred_nr = mlxplat_msn21xx_channels[MLXPLAT_CPLD_GRP_CHNL_NUM - 1]; - mlxplat_led = &mlxplat_default_ng_led_data; + mlxplat_led = &mlxplat_xdr_led_data; mlxplat_regs_io = &mlxplat_default_ng_regs_io_data; mlxplat_fan = &mlxplat_xdr_fan_data; diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index 16a2fd9fdd9b..5ec1ad471696 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -801,18 +801,18 @@ static const struct mlxbf_pmc_events mlxbf_pmc_llt_miss_events[] = { {11, "GDC_MISS_MACHINE_CHI_TXDAT"}, {12, "GDC_MISS_MACHINE_CHI_RXDAT"}, {13, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_0"}, - {14, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_1 "}, + {14, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_1"}, {15, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_2"}, - {16, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_3 "}, - {17, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_0 "}, - {18, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_1 "}, - {19, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_2 "}, - {20, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_3 "}, + {16, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_3"}, + {17, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_0"}, + {18, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_1"}, + {19, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_2"}, + {20, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_3"}, {21, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE0_0"}, {22, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE0_1"}, {23, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE0_2"}, {24, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE0_3"}, - {25, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_0 "}, + {25, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_0"}, {26, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_1"}, {27, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_2"}, {28, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_3"}, diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index bf97381faf58..e0eaaefb13d0 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -455,6 +455,11 @@ static struct quirk_entry quirk_acer_travelmate_2490 = { .mailled = 1, }; +static struct quirk_entry quirk_acer_nitro_an515_58 = { + .predator_v4 = 1, + .pwm = 1, +}; + static struct quirk_entry quirk_acer_predator_ph315_53 = { .turbo = 1, .cpu_fans = 1, @@ -655,7 +660,7 @@ static const struct dmi_system_id acer_quirks[] __initconst = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "Nitro AN515-58"), }, - .driver_data = &quirk_acer_predator_v4, + .driver_data = &quirk_acer_nitro_an515_58, }, { .callback = dmi_matched, @@ -2065,7 +2070,8 @@ static int acer_toggle_turbo(void) WMID_gaming_set_u64(0x1, ACER_CAP_TURBO_LED); /* Set FAN mode to auto */ - WMID_gaming_set_fan_mode(ACER_WMID_FAN_MODE_AUTO); + if (has_cap(ACER_CAP_TURBO_FAN)) + WMID_gaming_set_fan_mode(ACER_WMID_FAN_MODE_AUTO); /* Set OC to normal */ if (has_cap(ACER_CAP_TURBO_OC)) { @@ -2079,7 +2085,8 @@ static int acer_toggle_turbo(void) WMID_gaming_set_u64(0x10001, ACER_CAP_TURBO_LED); /* Set FAN mode to turbo */ - WMID_gaming_set_fan_mode(ACER_WMID_FAN_MODE_TURBO); + if (has_cap(ACER_CAP_TURBO_FAN)) + WMID_gaming_set_fan_mode(ACER_WMID_FAN_MODE_TURBO); /* Set OC to turbo mode */ if (has_cap(ACER_CAP_TURBO_OC)) { diff --git a/drivers/platform/x86/amd/wbrf.c b/drivers/platform/x86/amd/wbrf.c index dd197b3aebe0..0f58d252b620 100644 --- a/drivers/platform/x86/amd/wbrf.c +++ b/drivers/platform/x86/amd/wbrf.c @@ -104,8 +104,10 @@ static int wbrf_record(struct acpi_device *adev, uint8_t action, struct wbrf_ran obj = acpi_evaluate_dsm(adev->handle, &wifi_acpi_dsm_guid, WBRF_REVISION, WBRF_RECORD, &argv4); - if (!obj) + if (!obj) { + kfree(tmp); return -EINVAL; + } if (obj->type != ACPI_TYPE_INTEGER) { ret = -EINVAL; diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h index a1bb2005c3f3..6e9703bd5017 100644 --- a/drivers/platform/x86/asus-armoury.h +++ b/drivers/platform/x86/asus-armoury.h @@ -348,6 +348,37 @@ struct power_data { static const struct dmi_system_id power_limits[] = { { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "FA401UV"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 35, + .ppt_pl2_sppt_max = 80, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 80, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 25, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 55, + .nv_tgp_max = 75, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 25, + .ppt_pl1_spl_max = 35, + .ppt_pl2_sppt_min = 31, + .ppt_pl2_sppt_max = 44, + .ppt_pl3_fppt_min = 45, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "FA401W"), }, .driver_data = &(struct power_data) { @@ -449,12 +480,27 @@ static const struct dmi_system_id power_limits[] = { .ac_data = &(struct power_limits) { .ppt_pl1_spl_min = 15, .ppt_pl1_spl_max = 80, - .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_min = 35, .ppt_pl2_sppt_max = 80, .ppt_pl3_fppt_min = 35, - .ppt_pl3_fppt_max = 80 + .ppt_pl3_fppt_max = 80, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 25, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_def = 45, + .ppt_pl1_spl_max = 65, + .ppt_pl2_sppt_min = 35, + .ppt_pl2_sppt_def = 54, + .ppt_pl2_sppt_max = 65, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, }, - .dc_data = NULL, }, }, { @@ -554,6 +600,42 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "FA608UM"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_def = 45, + .ppt_pl1_spl_max = 90, + .ppt_pl2_sppt_min = 35, + .ppt_pl2_sppt_def = 54, + .ppt_pl2_sppt_max = 90, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_def = 65, + .ppt_pl3_fppt_max = 90, + .nv_dynamic_boost_min = 10, + .nv_dynamic_boost_max = 15, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 55, + .nv_tgp_max = 100, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_def = 45, + .ppt_pl1_spl_max = 65, + .ppt_pl2_sppt_min = 35, + .ppt_pl2_sppt_def = 54, + .ppt_pl2_sppt_max = 65, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "FA608WI"), }, .driver_data = &(struct power_data) { @@ -652,6 +734,25 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "FA617XT"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_apu_sppt_min = 15, + .ppt_apu_sppt_max = 80, + .ppt_platform_sppt_min = 30, + .ppt_platform_sppt_max = 145, + }, + .dc_data = &(struct power_limits) { + .ppt_apu_sppt_min = 25, + .ppt_apu_sppt_max = 35, + .ppt_platform_sppt_min = 45, + .ppt_platform_sppt_max = 100, + }, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "FX507VI"), }, .driver_data = &(struct power_data) { @@ -792,7 +893,7 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { - DMI_MATCH(DMI_BOARD_NAME, "GA403U"), + DMI_MATCH(DMI_BOARD_NAME, "GA403UI"), }, .driver_data = &(struct power_data) { .ac_data = &(struct power_limits) { @@ -824,6 +925,134 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GA403UV"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 80, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 80, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 25, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 55, + .nv_tgp_max = 65, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 35, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 35, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GA403WM"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 80, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 80, + .nv_dynamic_boost_min = 0, + .nv_dynamic_boost_max = 15, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 55, + .nv_tgp_max = 85, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 35, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 35, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GA403WR"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 80, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 80, + .nv_dynamic_boost_min = 0, + .nv_dynamic_boost_max = 25, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 80, + .nv_tgp_max = 95, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 35, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 35, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GA403WW"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 80, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 80, + .nv_dynamic_boost_min = 0, + .nv_dynamic_boost_max = 25, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 80, + .nv_tgp_max = 95, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 35, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 35, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "GA503QR"), }, .driver_data = &(struct power_data) { @@ -952,6 +1181,35 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GU605CR"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 30, + .ppt_pl1_spl_max = 85, + .ppt_pl2_sppt_min = 38, + .ppt_pl2_sppt_max = 110, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 20, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 80, + .nv_tgp_def = 90, + .nv_tgp_max = 105, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 30, + .ppt_pl1_spl_max = 85, + .ppt_pl2_sppt_min = 38, + .ppt_pl2_sppt_max = 110, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "GU605CW"), }, .driver_data = &(struct power_data) { @@ -1077,6 +1335,33 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GV302XV"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 55, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 60, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 35, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 35, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "GV601R"), }, .driver_data = &(struct power_data) { @@ -1206,6 +1491,22 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "G513QY"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + /* Advantage Edition Laptop, no PL1 or PL2 limits */ + .ppt_apu_sppt_min = 15, + .ppt_apu_sppt_max = 100, + .ppt_platform_sppt_min = 70, + .ppt_platform_sppt_max = 190, + }, + .dc_data = NULL, + .requires_fan_curve = true, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "G513R"), }, .driver_data = &(struct power_data) { @@ -1262,6 +1563,35 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "G615LR"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 28, + .ppt_pl1_spl_def = 140, + .ppt_pl1_spl_max = 175, + .ppt_pl2_sppt_min = 28, + .ppt_pl2_sppt_max = 175, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 25, + .nv_tgp_min = 65, + .nv_tgp_max = 115, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 25, + .ppt_pl1_spl_max = 55, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 70, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "G634J"), }, .driver_data = &(struct power_data) { @@ -1428,6 +1758,64 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "G835LR"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 28, + .ppt_pl1_spl_def = 140, + .ppt_pl1_spl_max = 175, + .ppt_pl2_sppt_min = 28, + .ppt_pl2_sppt_max = 175, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 25, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 65, + .nv_tgp_max = 115, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 25, + .ppt_pl1_spl_max = 55, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 70, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "G835LW"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 28, + .ppt_pl1_spl_def = 140, + .ppt_pl1_spl_max = 175, + .ppt_pl2_sppt_min = 28, + .ppt_pl2_sppt_max = 175, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 25, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_tgp_min = 80, + .nv_tgp_max = 150, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 25, + .ppt_pl1_spl_max = 55, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 70, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "H7606W"), }, .driver_data = &(struct power_data) { diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 6a62bc5b02fd..a38a65f5c550 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -580,6 +580,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x2a, { KEY_SELECTIVE_SCREENSHOT } }, { KE_IGNORE, 0x2b, }, /* PrintScreen (also send via PS/2) on newer models */ { KE_IGNORE, 0x2c, }, /* CapsLock (also send via PS/2) on newer models */ + { KE_KEY, 0x2d, { KEY_DISPLAYTOGGLE } }, { KE_KEY, 0x30, { KEY_VOLUMEUP } }, { KE_KEY, 0x31, { KEY_VOLUMEDOWN } }, { KE_KEY, 0x32, { KEY_MUTE } }, diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 4aec7ec69250..0775fadedd10 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -4889,7 +4889,6 @@ static int asus_wmi_add(struct platform_device *pdev) asus->egpu_enable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_EGPU); asus->dgpu_disable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_DGPU); asus->kbd_rgb_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_STATE); - asus->oobe_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE); if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_MINI_LED_MODE)) asus->mini_led_dev_id = ASUS_WMI_DEVID_MINI_LED_MODE; @@ -4902,6 +4901,8 @@ static int asus_wmi_add(struct platform_device *pdev) asus->gpu_mux_dev = ASUS_WMI_DEVID_GPU_MUX_VIVO; #endif /* IS_ENABLED(CONFIG_ASUS_WMI_DEPRECATED_ATTRS) */ + asus->oobe_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE); + if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY)) asus->throttle_thermal_policy_dev = ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY; else if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY_VIVO)) diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c index 1418bd326edf..e69b50162bb1 100644 --- a/drivers/platform/x86/dell/alienware-wmi-wmax.c +++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c @@ -90,6 +90,30 @@ static struct awcc_quirks empty_quirks; static const struct dmi_system_id awcc_dmi_table[] __initconst = { { + .ident = "Alienware 16 Area-51", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware 16 Area-51"), + }, + .driver_data = &g_series_quirks, + }, + { + .ident = "Alienware 16X Aurora", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware 16X Aurora"), + }, + .driver_data = &g_series_quirks, + }, + { + .ident = "Alienware 18 Area-51", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware 18 Area-51"), + }, + .driver_data = &g_series_quirks, + }, + { .ident = "Alienware 16 Aurora", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -162,6 +186,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { .driver_data = &generic_quirks, }, { + .ident = "Alienware x16", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x16"), + }, + .driver_data = &g_series_quirks, + }, + { .ident = "Alienware x17", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), diff --git a/drivers/platform/x86/dell/dell-lis3lv02d.c b/drivers/platform/x86/dell/dell-lis3lv02d.c index 77905a9ddde9..fe52bcd896f7 100644 --- a/drivers/platform/x86/dell/dell-lis3lv02d.c +++ b/drivers/platform/x86/dell/dell-lis3lv02d.c @@ -44,6 +44,7 @@ static const struct dmi_system_id lis3lv02d_devices[] __initconst = { /* * Additional individual entries were added after verification. */ + DELL_LIS3LV02D_DMI_ENTRY("Latitude 5400", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Latitude 5480", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Latitude 5500", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Latitude E6330", 0x29), diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c index 5bfa7159f5bc..dbe096eefa75 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c @@ -10,6 +10,8 @@ #include <linux/fs.h> #include <linux/module.h> #include <linux/kernel.h> +#include <linux/printk.h> +#include <linux/string.h> #include <linux/wmi.h> #include "bioscfg.h" #include "../../firmware_attributes_class.h" @@ -781,6 +783,12 @@ static int hp_init_bios_buffer_attribute(enum hp_wmi_data_type attr_type, if (ret < 0) goto buff_attr_exit; + if (strlen(str) == 0) { + pr_debug("Ignoring attribute with empty name\n"); + ret = 0; + goto buff_attr_exit; + } + if (attr_type == HPWMI_PASSWORD_TYPE || attr_type == HPWMI_SECURE_PLATFORM_TYPE) temp_kset = bioscfg_drv.authentication_dir_kset; diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h index 3166ef328eba..f1eec0e4ba07 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h @@ -10,6 +10,7 @@ #include <linux/wmi.h> #include <linux/types.h> +#include <linux/string.h> #include <linux/device.h> #include <linux/module.h> #include <linux/kernel.h> @@ -56,14 +57,14 @@ enum mechanism_values { #define PASSWD_MECHANISM_TYPES "password" -#define HP_WMI_BIOS_GUID "5FB7F034-2C63-45e9-BE91-3D44E2C707E4" +#define HP_WMI_BIOS_GUID "5FB7F034-2C63-45E9-BE91-3D44E2C707E4" -#define HP_WMI_BIOS_STRING_GUID "988D08E3-68F4-4c35-AF3E-6A1B8106F83C" +#define HP_WMI_BIOS_STRING_GUID "988D08E3-68F4-4C35-AF3E-6A1B8106F83C" #define HP_WMI_BIOS_INTEGER_GUID "8232DE3D-663D-4327-A8F4-E293ADB9BF05" #define HP_WMI_BIOS_ENUMERATION_GUID "2D114B49-2DFB-4130-B8FE-4A3C09E75133" #define HP_WMI_BIOS_ORDERED_LIST_GUID "14EA9746-CE1F-4098-A0E0-7045CB4DA745" #define HP_WMI_BIOS_PASSWORD_GUID "322F2028-0F84-4901-988E-015176049E2D" -#define HP_WMI_SET_BIOS_SETTING_GUID "1F4C91EB-DC5C-460b-951D-C7CB9B4B8D5E" +#define HP_WMI_SET_BIOS_SETTING_GUID "1F4C91EB-DC5C-460B-951D-C7CB9B4B8D5E" enum hp_wmi_spm_commandtype { HPWMI_SECUREPLATFORM_GET_STATE = 0x10, @@ -285,8 +286,9 @@ enum hp_wmi_data_elements { { \ int i; \ \ - for (i = 0; i <= bioscfg_drv.type##_instances_count; i++) { \ - if (!strcmp(kobj->name, bioscfg_drv.type##_data[i].attr_name_kobj->name)) \ + for (i = 0; i < bioscfg_drv.type##_instances_count; i++) { \ + if (bioscfg_drv.type##_data[i].attr_name_kobj && \ + !strcmp(kobj->name, bioscfg_drv.type##_data[i].attr_name_kobj->name)) \ return i; \ } \ return -EIO; \ diff --git a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c index c50ad5880503..f346aad8e9d8 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c @@ -207,7 +207,7 @@ static int hp_populate_enumeration_elements_from_package(union acpi_object *enum case PREREQUISITES: size = min_t(u32, enum_data->common.prerequisites_size, MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { - if (elem >= enum_obj_count) { + if (elem + reqs >= enum_obj_count) { pr_err("Error enum-objects package is too small\n"); return -EINVAL; } @@ -255,7 +255,7 @@ static int hp_populate_enumeration_elements_from_package(union acpi_object *enum for (pos_values = 0; pos_values < size && pos_values < MAX_VALUES_SIZE; pos_values++) { - if (elem >= enum_obj_count) { + if (elem + pos_values >= enum_obj_count) { pr_err("Error enum-objects package is too small\n"); return -EINVAL; } diff --git a/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c index 6c7f4d5fa9cb..63b1fda2be4e 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c @@ -227,7 +227,7 @@ static int hp_populate_integer_elements_from_package(union acpi_object *integer_ size = min_t(u32, integer_data->common.prerequisites_size, MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { - if (elem >= integer_obj_count) { + if (elem + reqs >= integer_obj_count) { pr_err("Error elem-objects package is too small\n"); return -EINVAL; } diff --git a/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c index c6e57bb9d8b7..6a31f47ce3f5 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c @@ -216,6 +216,11 @@ static int hp_populate_ordered_list_elements_from_package(union acpi_object *ord size = min_t(u32, ordered_list_data->common.prerequisites_size, MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { + if (elem + reqs >= order_obj_count) { + pr_err("Error elem-objects package is too small\n"); + return -EINVAL; + } + ret = hp_convert_hexstr_to_str(order_obj[elem + reqs].string.pointer, order_obj[elem + reqs].string.length, &str_value, &value_len); diff --git a/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c index 187b372123ed..ec79d9d50377 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c @@ -303,6 +303,11 @@ static int hp_populate_password_elements_from_package(union acpi_object *passwor MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { + if (elem + reqs >= password_obj_count) { + pr_err("Error elem-objects package is too small\n"); + return -EINVAL; + } + ret = hp_convert_hexstr_to_str(password_obj[elem + reqs].string.pointer, password_obj[elem + reqs].string.length, &str_value, &value_len); diff --git a/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c index 27758b779b2d..7b885d25650c 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c @@ -217,7 +217,7 @@ static int hp_populate_string_elements_from_package(union acpi_object *string_ob MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { - if (elem >= string_obj_count) { + if (elem + reqs >= string_obj_count) { pr_err("Error elem-objects package is too small\n"); return -EINVAL; } diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c index 231b37909801..139956168cf9 100644 --- a/drivers/platform/x86/ibm_rtl.c +++ b/drivers/platform/x86/ibm_rtl.c @@ -273,7 +273,7 @@ static int __init ibm_rtl_init(void) { /* search for the _RTL_ signature at the start of the table */ for (i = 0 ; i < ebda_size/sizeof(unsigned int); i++) { struct ibm_rtl_table __iomem * tmp; - tmp = (struct ibm_rtl_table __iomem *) (ebda_map+i); + tmp = (struct ibm_rtl_table __iomem *) (ebda_map + i*sizeof(unsigned int)); if ((readq(&tmp->signature) & RTL_MASK) == RTL_SIGNATURE) { phys_addr_t addr; unsigned int plen; diff --git a/drivers/platform/x86/intel/pmt/discovery.c b/drivers/platform/x86/intel/pmt/discovery.c index 32713a194a55..e500aa327d23 100644 --- a/drivers/platform/x86/intel/pmt/discovery.c +++ b/drivers/platform/x86/intel/pmt/discovery.c @@ -503,8 +503,10 @@ static int pmt_features_discovery(struct pmt_features_priv *priv, ret = kobject_init_and_add(&feature->kobj, ktype, &priv->dev->kobj, "%s", pmt_feature_names[feature->id]); - if (ret) + if (ret) { + kobject_put(&feature->kobj); return ret; + } kobject_uevent(&feature->kobj, KOBJ_ADD); pmt_features_add_feat(feature); @@ -546,9 +548,9 @@ static int pmt_features_probe(struct auxiliary_device *auxdev, const struct auxi priv->dev = device_create(&intel_pmt_class, &auxdev->dev, MKDEV(0, 0), priv, "%s-%s", "features", dev_name(priv->parent)); if (IS_ERR(priv->dev)) - return dev_err_probe(priv->dev, PTR_ERR(priv->dev), + return dev_err_probe(&auxdev->dev, PTR_ERR(priv->dev), "Could not create %s-%s device node\n", - "features", dev_name(priv->dev)); + "features", dev_name(priv->parent)); /* Initialize each feature */ for (i = 0; i < ivdev->num_resources; i++) { diff --git a/drivers/platform/x86/lenovo/ideapad-laptop.c b/drivers/platform/x86/lenovo/ideapad-laptop.c index 5171a077f62c..7d5f7a2f6564 100644 --- a/drivers/platform/x86/lenovo/ideapad-laptop.c +++ b/drivers/platform/x86/lenovo/ideapad-laptop.c @@ -1367,7 +1367,7 @@ static const struct key_entry ideapad_keymap[] = { /* Performance toggle also Fn+Q, handled inside ideapad_wmi_notify() */ { KE_KEY, 0x3d | IDEAPAD_WMI_KEY, { KEY_PROG4 } }, /* shift + prtsc */ - { KE_KEY, 0x2d | IDEAPAD_WMI_KEY, { KEY_CUT } }, + { KE_KEY, 0x2d | IDEAPAD_WMI_KEY, { KEY_SELECTIVE_SCREENSHOT } }, { KE_KEY, 0x29 | IDEAPAD_WMI_KEY, { KEY_TOUCHPAD_TOGGLE } }, { KE_KEY, 0x2a | IDEAPAD_WMI_KEY, { KEY_ROOT_MENU } }, diff --git a/drivers/platform/x86/lenovo/think-lmi.c b/drivers/platform/x86/lenovo/think-lmi.c index 540b472b1bf3..c45f0206b4ab 100644 --- a/drivers/platform/x86/lenovo/think-lmi.c +++ b/drivers/platform/x86/lenovo/think-lmi.c @@ -195,7 +195,7 @@ static const struct tlmi_cert_guids thinkpad_cert_guid = { }; static const struct tlmi_cert_guids thinkcenter_cert_guid = { - .thumbprint = NULL, + .thumbprint = LENOVO_CERT_THUMBPRINT_GUID, /* Same GUID as TP */ .set_bios_setting = LENOVO_TC_SET_BIOS_SETTING_CERT_GUID, .save_bios_setting = LENOVO_TC_SAVE_BIOS_SETTING_CERT_GUID, .cert_to_password = LENOVO_TC_CERT_TO_PASSWORD_GUID, @@ -709,6 +709,10 @@ static ssize_t cert_thumbprint(char *buf, const char *arg, int count) if (!tlmi_priv.cert_guid->thumbprint) return -EOPNOTSUPP; + /* Older ThinkCenter BIOS may not have support */ + if (!wmi_has_guid(tlmi_priv.cert_guid->thumbprint)) + return -EOPNOTSUPP; + status = wmi_evaluate_method(tlmi_priv.cert_guid->thumbprint, 0, 0, &input, &output); if (ACPI_FAILURE(status)) { kfree(output.pointer); diff --git a/drivers/platform/x86/msi-laptop.c b/drivers/platform/x86/msi-laptop.c index c4b150fa093f..ddef6b78d2fa 100644 --- a/drivers/platform/x86/msi-laptop.c +++ b/drivers/platform/x86/msi-laptop.c @@ -1130,6 +1130,9 @@ static void __exit msi_cleanup(void) sysfs_remove_group(&msipf_device->dev.kobj, &msipf_attribute_group); if (!quirks->old_ec_model && threeg_exists) device_remove_file(&msipf_device->dev, &dev_attr_threeg); + if (quirks->old_ec_model) + sysfs_remove_group(&msipf_device->dev.kobj, + &msipf_old_attribute_group); platform_device_unregister(msipf_device); platform_driver_unregister(&msipf_driver); backlight_device_unregister(msibl_device); diff --git a/drivers/platform/x86/samsung-galaxybook.c b/drivers/platform/x86/samsung-galaxybook.c index 3c13e13d4885..755cb82bdb60 100644 --- a/drivers/platform/x86/samsung-galaxybook.c +++ b/drivers/platform/x86/samsung-galaxybook.c @@ -442,12 +442,13 @@ static int galaxybook_battery_ext_property_get(struct power_supply *psy, union power_supply_propval *val) { struct samsung_galaxybook *galaxybook = ext_data; + u8 value; int err; if (psp != POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD) return -EINVAL; - err = charge_control_end_threshold_acpi_get(galaxybook, (u8 *)&val->intval); + err = charge_control_end_threshold_acpi_get(galaxybook, &value); if (err) return err; @@ -455,8 +456,10 @@ static int galaxybook_battery_ext_property_get(struct power_supply *psy, * device stores "no end threshold" as 0 instead of 100; * if device has 0, report 100 */ - if (val->intval == 0) - val->intval = 100; + if (value == 0) + value = 100; + + val->intval = value; return 0; } diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c index bd7e63dd5181..0f935532f250 100644 --- a/drivers/platform/x86/uniwill/uniwill-acpi.c +++ b/drivers/platform/x86/uniwill/uniwill-acpi.c @@ -1845,6 +1845,13 @@ static const struct dmi_system_id uniwill_dmi_table[] __initconst = { }, }, { + .ident = "TUXEDO Book BA15 Gen10 AMD", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "PF5PU1G"), + }, + }, + { .ident = "TUXEDO Pulse 14 Gen1 AMD", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), diff --git a/drivers/pmdomain/imx/imx8m-blk-ctrl.c b/drivers/pmdomain/imx/imx8m-blk-ctrl.c index 5c83e5599f1e..74bf4936991d 100644 --- a/drivers/pmdomain/imx/imx8m-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8m-blk-ctrl.c @@ -846,22 +846,25 @@ static int imx8mq_vpu_power_notifier(struct notifier_block *nb, return NOTIFY_OK; } +/* + * For i.MX8MQ, the ADB in the VPUMIX domain has no separate reset and clock + * enable bits, but is ungated and reset together with the VPUs. + * Resetting G1 or G2 separately may led to system hang. + * Remove the rst_mask and clk_mask from the domain data of G1 and G2, + * Let imx8mq_vpu_power_notifier() do really vpu reset. + */ static const struct imx8m_blk_ctrl_domain_data imx8mq_vpu_blk_ctl_domain_data[] = { [IMX8MQ_VPUBLK_PD_G1] = { .name = "vpublk-g1", .clk_names = (const char *[]){ "g1", }, .num_clks = 1, .gpc_name = "g1", - .rst_mask = BIT(1), - .clk_mask = BIT(1), }, [IMX8MQ_VPUBLK_PD_G2] = { .name = "vpublk-g2", .clk_names = (const char *[]){ "g2", }, .num_clks = 1, .gpc_name = "g2", - .rst_mask = BIT(0), - .clk_mask = BIT(0), }, }; diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c index a8b37037c6fe..19849703be4a 100644 --- a/drivers/pmdomain/qcom/rpmhpd.c +++ b/drivers/pmdomain/qcom/rpmhpd.c @@ -246,6 +246,8 @@ static struct rpmhpd *sa8540p_rpmhpds[] = { [SC8280XP_MMCX_AO] = &mmcx_ao, [SC8280XP_MX] = &mx, [SC8280XP_MX_AO] = &mx_ao, + [SC8280XP_MXC] = &mxc, + [SC8280XP_MXC_AO] = &mxc_ao, [SC8280XP_NSP] = &nsp, }; @@ -700,6 +702,8 @@ static struct rpmhpd *sc8280xp_rpmhpds[] = { [SC8280XP_MMCX_AO] = &mmcx_ao, [SC8280XP_MX] = &mx, [SC8280XP_MX_AO] = &mx_ao, + [SC8280XP_MXC] = &mxc, + [SC8280XP_MXC_AO] = &mxc_ao, [SC8280XP_NSP] = &nsp, [SC8280XP_QPHY] = &qphy, }; diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c index 4f1336a0f49a..997e93c12951 100644 --- a/drivers/pmdomain/rockchip/pm-domains.c +++ b/drivers/pmdomain/rockchip/pm-domains.c @@ -879,6 +879,16 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, pd->genpd.name = pd->info->name; else pd->genpd.name = kbasename(node->full_name); + + /* + * power domain's needing a regulator should default to off, since + * the regulator state is unknown at probe time. Also the regulator + * state cannot be checked, since that usually requires IP needing + * (a different) power domain. + */ + if (pd->info->need_regulator) + rockchip_pd_power(pd, false); + pd->genpd.power_off = rockchip_pd_power_off; pd->genpd.power_on = rockchip_pd_power_on; pd->genpd.attach_dev = rockchip_pd_attach_dev; diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index cd06229db394..ec8731515333 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -2295,8 +2295,9 @@ static long pwm_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long ar .duty_offset_ns = wf.duty_offset_ns, }; - return copy_to_user((struct pwmchip_waveform __user *)arg, - &cwf, sizeof(cwf)); + ret = copy_to_user((struct pwmchip_waveform __user *)arg, + &cwf, sizeof(cwf)); + return ret ? -EFAULT : 0; } case PWM_IOCTL_GETWF: @@ -2329,8 +2330,9 @@ static long pwm_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long ar .duty_offset_ns = wf.duty_offset_ns, }; - return copy_to_user((struct pwmchip_waveform __user *)arg, - &cwf, sizeof(cwf)); + ret = copy_to_user((struct pwmchip_waveform __user *)arg, + &cwf, sizeof(cwf)); + return ret ? -EFAULT : 0; } case PWM_IOCTL_SETROUNDEDWF: diff --git a/drivers/pwm/pwm-max7360.c b/drivers/pwm/pwm-max7360.c index 16261958ce7f..732969303dd7 100644 --- a/drivers/pwm/pwm-max7360.c +++ b/drivers/pwm/pwm-max7360.c @@ -153,6 +153,7 @@ static int max7360_pwm_read_waveform(struct pwm_chip *chip, } static const struct pwm_ops max7360_pwm_ops = { + .sizeof_wfhw = sizeof(struct max7360_pwm_waveform), .request = max7360_pwm_request, .round_waveform_tohw = max7360_pwm_round_waveform_tohw, .round_waveform_fromhw = max7360_pwm_round_waveform_fromhw, diff --git a/drivers/regulator/fp9931.c b/drivers/regulator/fp9931.c index 69b3c712e5d5..7fbcc6327cc6 100644 --- a/drivers/regulator/fp9931.c +++ b/drivers/regulator/fp9931.c @@ -439,6 +439,9 @@ static int fp9931_probe(struct i2c_client *client) int i; data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + data->regmap = devm_regmap_init_i2c(client, ®map_config); if (IS_ERR(data->regmap)) return dev_err_probe(&client->dev, PTR_ERR(data->regmap), diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c index 0b5b158e1aaf..b495d5291868 100644 --- a/drivers/resctrl/mpam_devices.c +++ b/drivers/resctrl/mpam_devices.c @@ -1072,7 +1072,7 @@ static void __ris_msmon_read(void *arg) u64 now; bool nrdy = false; bool config_mismatch; - bool overflow; + bool overflow = false; struct mon_read *m = arg; struct mon_cfg *ctx = m->ctx; bool reset_on_next_read = false; @@ -1176,10 +1176,11 @@ static void __ris_msmon_read(void *arg) } mpam_mon_sel_unlock(msc); - if (nrdy) { + if (nrdy) m->err = -EBUSY; + + if (m->err) return; - } *m->val += now; } diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h index e79c3c47259c..e8971842b124 100644 --- a/drivers/resctrl/mpam_internal.h +++ b/drivers/resctrl/mpam_internal.h @@ -12,7 +12,6 @@ #include <linux/jump_label.h> #include <linux/llist.h> #include <linux/mutex.h> -#include <linux/srcu.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/types.h> @@ -201,8 +200,12 @@ struct mpam_props { } PACKED_FOR_KUNIT; #define mpam_has_feature(_feat, x) test_bit(_feat, (x)->features) -#define mpam_set_feature(_feat, x) set_bit(_feat, (x)->features) -#define mpam_clear_feature(_feat, x) clear_bit(_feat, (x)->features) +/* + * The non-atomic get/set operations are used because if struct mpam_props is + * packed, the alignment requirements for atomics aren't met. + */ +#define mpam_set_feature(_feat, x) __set_bit(_feat, (x)->features) +#define mpam_clear_feature(_feat, x) __clear_bit(_feat, (x)->features) /* The values for MSMON_CFG_MBWU_FLT.RWBW */ enum mon_filter_options { diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c index 8102c8134c49..8b0ad6f582ec 100644 --- a/drivers/s390/crypto/ap_card.c +++ b/drivers/s390/crypto/ap_card.c @@ -43,7 +43,7 @@ static ssize_t depth_show(struct device *dev, struct device_attribute *attr, { struct ap_card *ac = to_ap_card(dev); - return sysfs_emit(buf, "%d\n", ac->hwinfo.qd); + return sysfs_emit(buf, "%d\n", ac->hwinfo.qd + 1); } static DEVICE_ATTR_RO(depth); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 4a32c1e19a1e..a80ab87cad62 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -285,7 +285,7 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) list_move_tail(&ap_msg->list, &aq->pendingq); aq->requestq_count--; aq->pendingq_count++; - if (aq->queue_count < aq->card->hwinfo.qd) { + if (aq->queue_count < aq->card->hwinfo.qd + 1) { aq->sm_state = AP_SM_STATE_WORKING; return AP_SM_WAIT_AGAIN; } diff --git a/drivers/scsi/bfa/bfa_fcs.c b/drivers/scsi/bfa/bfa_fcs.c index e52ce9b01f49..9b57312f43f5 100644 --- a/drivers/scsi/bfa/bfa_fcs.c +++ b/drivers/scsi/bfa/bfa_fcs.c @@ -1169,7 +1169,7 @@ bfa_fcs_fabric_vport_lookup(struct bfa_fcs_fabric_s *fabric, wwn_t pwwn) * This function should be used only if there is any requirement * to check for FOS version below 6.3. * To check if the attached fabric is a brocade fabric, use - * bfa_lps_is_brcd_fabric() which works for FOS versions 6.3 + * fabric->lps->brcd_switch which works for FOS versions 6.3 * or above only. */ diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index a3971afc2dd1..a04a5aa0d005 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -878,6 +878,9 @@ qla27xx_copy_multiple_pkt(struct scsi_qla_host *vha, void **pkt, payload_size = sizeof(purex->els_frame_payload); } + if (total_bytes > sizeof(item->iocb.iocb)) + total_bytes = sizeof(item->iocb.iocb); + pending_bytes = total_bytes; no_bytes = (pending_bytes > payload_size) ? payload_size : pending_bytes; @@ -1163,6 +1166,10 @@ qla27xx_copy_fpin_pkt(struct scsi_qla_host *vha, void **pkt, total_bytes = (le16_to_cpu(purex->frame_size) & 0x0FFF) - PURX_ELS_HEADER_SIZE; + + if (total_bytes > sizeof(item->iocb.iocb)) + total_bytes = sizeof(item->iocb.iocb); + pending_bytes = total_bytes; entry_count = entry_count_remaining = purex->entry_count; no_bytes = (pending_bytes > sizeof(purex->els_frame_payload)) ? diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index f869108fd969..b6e8730e049e 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -282,11 +282,20 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; - unsigned int busy = scsi_host_busy(shost); + unsigned int busy; unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; + spin_unlock_irqrestore(shost->host_lock, flags); + /* + * The counting of busy requests needs to occur after adding to + * host_failed or after the lock acquire for adding to host_failed + * to prevent a race with host unbusy and missing an eh wakeup. + */ + busy = scsi_host_busy(shost); + + spin_lock_irqsave(shost->host_lock, flags); scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } @@ -1063,6 +1072,9 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, unsigned char *cmnd, int cmnd_size, unsigned sense_bytes) { struct scsi_device *sdev = scmd->device; +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct request *rq = scsi_cmd_to_rq(scmd); +#endif /* * We need saved copies of a number of fields - this is because @@ -1115,6 +1127,18 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, (sdev->lun << 5 & 0xe0); /* + * Encryption must be disabled for the commands submitted by the error handler. + * Hence, clear the encryption context information. + */ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + ses->rq_crypt_keyslot = rq->crypt_keyslot; + ses->rq_crypt_ctx = rq->crypt_ctx; + + rq->crypt_keyslot = NULL; + rq->crypt_ctx = NULL; +#endif + + /* * Zero the sense buffer. The scsi spec mandates that any * untransferred sense data should be interpreted as being zero. */ @@ -1131,6 +1155,10 @@ EXPORT_SYMBOL(scsi_eh_prep_cmnd); */ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) { +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct request *rq = scsi_cmd_to_rq(scmd); +#endif + /* * Restore original data */ @@ -1143,6 +1171,11 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; scmd->eh_eflags = ses->eh_eflags; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + rq->crypt_keyslot = ses->rq_crypt_keyslot; + rq->crypt_ctx = ses->rq_crypt_ctx; +#endif } EXPORT_SYMBOL(scsi_eh_restore_cmnd); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 93031326ac3e..4a902c9dfd8b 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -376,6 +376,14 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) rcu_read_lock(); __clear_bit(SCMD_STATE_INFLIGHT, &cmd->state); if (unlikely(scsi_host_in_recovery(shost))) { + /* + * Ensure the clear of SCMD_STATE_INFLIGHT is visible to + * other CPUs before counting busy requests. Otherwise, + * reordering can cause CPUs to race and miss an eh wakeup + * when no CPU sees all busy requests as done or timed out. + */ + smp_mb(); + unsigned int busy = scsi_host_busy(shost); spin_lock_irqsave(shost->host_lock, flags); @@ -2459,7 +2467,7 @@ EXPORT_SYMBOL(scsi_mode_sense); * @retries: number of retries before failing * @sshdr: outpout pointer for decoded sense information. * - * Returns zero if unsuccessful or an error if TUR failed. For + * Returns zero if successful or an error if TUR failed. For * removable media, UNIT_ATTENTION sets ->changed flag. **/ int diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 6e4112143c76..b43d876747b7 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1144,7 +1144,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, * The current SCSI handling on the host side does * not correctly handle: * INQUIRY command with page code parameter set to 0x80 - * MODE_SENSE command with cmd[2] == 0x1c + * MODE_SENSE and MODE_SENSE_10 command with cmd[2] == 0x1c * MAINTENANCE_IN is not supported by HyperV FC passthrough * * Setup srb and scsi status so this won't be fatal. @@ -1154,6 +1154,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, if ((stor_pkt->vm_srb.cdb[0] == INQUIRY) || (stor_pkt->vm_srb.cdb[0] == MODE_SENSE) || + (stor_pkt->vm_srb.cdb[0] == MODE_SENSE_10) || (stor_pkt->vm_srb.cdb[0] == MAINTENANCE_IN && hv_dev_is_fc(device))) { vstor_packet->vm_srb.scsi_status = 0; diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 005fa2ef100f..5079d3271ee8 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -146,6 +146,7 @@ static void slim_dev_release(struct device *dev) { struct slim_device *sbdev = to_slim_device(dev); + of_node_put(sbdev->dev.of_node); kfree(sbdev); } @@ -280,7 +281,6 @@ EXPORT_SYMBOL_GPL(slim_register_controller); /* slim_remove_device: Remove the effect of slim_add_device() */ static void slim_remove_device(struct slim_device *sbdev) { - of_node_put(sbdev->dev.of_node); device_unregister(&sbdev->dev); } @@ -366,6 +366,9 @@ static struct slim_device *find_slim_device(struct slim_controller *ctrl, * @ctrl: Controller on which this device will be added/queried * @e_addr: Enumeration address of the device to be queried * + * Takes a reference to the embedded struct device which needs to be dropped + * after use. + * * Return: pointer to a device if it has already reported. Creates a new * device and returns pointer to it if the device has not yet enumerated. */ @@ -379,14 +382,27 @@ struct slim_device *slim_get_device(struct slim_controller *ctrl, sbdev = slim_alloc_device(ctrl, e_addr, NULL); if (!sbdev) return ERR_PTR(-ENOMEM); + + get_device(&sbdev->dev); } return sbdev; } EXPORT_SYMBOL_GPL(slim_get_device); -static struct slim_device *of_find_slim_device(struct slim_controller *ctrl, - struct device_node *np) +/** + * of_slim_get_device() - get handle to a device using dt node. + * + * @ctrl: Controller on which this device will be queried + * @np: node pointer to device + * + * Takes a reference to the embedded struct device which needs to be dropped + * after use. + * + * Return: pointer to a device if it has been registered, otherwise NULL. + */ +struct slim_device *of_slim_get_device(struct slim_controller *ctrl, + struct device_node *np) { struct slim_device *sbdev; struct device *dev; @@ -399,21 +415,6 @@ static struct slim_device *of_find_slim_device(struct slim_controller *ctrl, return NULL; } - -/** - * of_slim_get_device() - get handle to a device using dt node. - * - * @ctrl: Controller on which this device will be added/queried - * @np: node pointer to device - * - * Return: pointer to a device if it has already reported. Creates a new - * device and returns pointer to it if the device has not yet enumerated. - */ -struct slim_device *of_slim_get_device(struct slim_controller *ctrl, - struct device_node *np) -{ - return of_find_slim_device(ctrl, np); -} EXPORT_SYMBOL_GPL(of_slim_get_device); static int slim_device_alloc_laddr(struct slim_device *sbdev, @@ -489,21 +490,24 @@ int slim_device_report_present(struct slim_controller *ctrl, if (ctrl->sched.clk_state != SLIM_CLK_ACTIVE) { dev_err(ctrl->dev, "slim ctrl not active,state:%d, ret:%d\n", ctrl->sched.clk_state, ret); - goto slimbus_not_active; + goto out_put_rpm; } sbdev = slim_get_device(ctrl, e_addr); - if (IS_ERR(sbdev)) - return -ENODEV; + if (IS_ERR(sbdev)) { + ret = -ENODEV; + goto out_put_rpm; + } if (sbdev->is_laddr_valid) { *laddr = sbdev->laddr; - return 0; + ret = 0; + } else { + ret = slim_device_alloc_laddr(sbdev, true); } - ret = slim_device_alloc_laddr(sbdev, true); - -slimbus_not_active: + put_device(&sbdev->dev); +out_put_rpm: pm_runtime_mark_last_busy(ctrl->dev); pm_runtime_put_autosuspend(ctrl->dev); return ret; diff --git a/drivers/soc/renesas/Kconfig b/drivers/soc/renesas/Kconfig index 340a1ff7e92b..2a8ae79a11af 100644 --- a/drivers/soc/renesas/Kconfig +++ b/drivers/soc/renesas/Kconfig @@ -445,6 +445,7 @@ config ARCH_R9A07G043 depends on RISCV_SBI select ARCH_RZG2L select AX45MP_L2_CACHE + select CACHEMAINT_FOR_DMA select DMA_GLOBAL_POOL select ERRATA_ANDES select ERRATA_ANDES_CMO diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 91e70cb46fb5..5c67c13e5735 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -105,7 +105,7 @@ static int sdw_drv_probe(struct device *dev) if (ret) return ret; - ret = ida_alloc_max(&slave->bus->slave_ida, SDW_FW_MAX_DEVICES, GFP_KERNEL); + ret = ida_alloc_max(&slave->bus->slave_ida, SDW_FW_MAX_DEVICES - 1, GFP_KERNEL); if (ret < 0) { dev_err(dev, "Failed to allocated ID: %d\n", ret); return ret; diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c index 3d4d00188c26..d933cebad52b 100644 --- a/drivers/soundwire/slave.c +++ b/drivers/soundwire/slave.c @@ -23,6 +23,7 @@ const struct device_type sdw_slave_type = { .release = sdw_slave_release, .uevent = sdw_slave_uevent, }; +EXPORT_SYMBOL_GPL(sdw_slave_type); int sdw_slave_add(struct sdw_bus *bus, struct sdw_slave_id *id, struct fwnode_handle *fwnode) diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 47054da630d0..41b5b58cbfac 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -729,6 +729,7 @@ static int cdns_spi_probe(struct platform_device *pdev) ctlr->unprepare_transfer_hardware = cdns_unprepare_transfer_hardware; ctlr->mode_bits = SPI_CPOL | SPI_CPHA; ctlr->bits_per_word_mask = SPI_BPW_MASK(8); + ctlr->flags = SPI_CONTROLLER_MUST_TX; if (of_device_is_compatible(pdev->dev.of_node, "cix,sky1-spi-r1p6")) ctlr->bits_per_word_mask |= SPI_BPW_MASK(16) | SPI_BPW_MASK(32); diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c index dadf558dd9c0..80a1a15de0bc 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -161,10 +161,8 @@ static const struct debugfs_reg32 hisi_spi_regs[] = { static int hisi_spi_debugfs_init(struct hisi_spi *hs) { char name[32]; + struct spi_controller *host = dev_get_drvdata(hs->dev); - struct spi_controller *host; - - host = container_of(hs->dev, struct spi_controller, dev); snprintf(name, 32, "hisi_spi%d", host->bus_num); hs->debugfs = debugfs_create_dir(name, NULL); if (IS_ERR(hs->debugfs)) diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index b8c572394aac..bce3d149bea1 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -81,6 +81,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x5794), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x5825), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x6e24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7723), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c index 262c11d977ea..f25b34a91756 100644 --- a/drivers/spi/spi-sprd-adi.c +++ b/drivers/spi/spi-sprd-adi.c @@ -528,7 +528,7 @@ static int sprd_adi_probe(struct platform_device *pdev) pdev->id = of_alias_get_id(np, "spi"); num_chipselect = of_get_child_count(np); - ctlr = spi_alloc_host(&pdev->dev, sizeof(struct sprd_adi)); + ctlr = devm_spi_alloc_host(&pdev->dev, sizeof(struct sprd_adi)); if (!ctlr) return -ENOMEM; @@ -536,10 +536,8 @@ static int sprd_adi_probe(struct platform_device *pdev) sadi = spi_controller_get_devdata(ctlr); sadi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); - if (IS_ERR(sadi->base)) { - ret = PTR_ERR(sadi->base); - goto put_ctlr; - } + if (IS_ERR(sadi->base)) + return PTR_ERR(sadi->base); sadi->slave_vbase = (unsigned long)sadi->base + data->slave_offset; @@ -551,18 +549,15 @@ static int sprd_adi_probe(struct platform_device *pdev) if (ret > 0 || (IS_ENABLED(CONFIG_HWSPINLOCK) && ret == 0)) { sadi->hwlock = devm_hwspin_lock_request_specific(&pdev->dev, ret); - if (!sadi->hwlock) { - ret = -ENXIO; - goto put_ctlr; - } + if (!sadi->hwlock) + return -ENXIO; } else { switch (ret) { case -ENOENT: dev_info(&pdev->dev, "no hardware spinlock supplied\n"); break; default: - dev_err_probe(&pdev->dev, ret, "failed to find hwlock id\n"); - goto put_ctlr; + return dev_err_probe(&pdev->dev, ret, "failed to find hwlock id\n"); } } @@ -579,26 +574,18 @@ static int sprd_adi_probe(struct platform_device *pdev) ctlr->transfer_one = sprd_adi_transfer_one; ret = devm_spi_register_controller(&pdev->dev, ctlr); - if (ret) { - dev_err(&pdev->dev, "failed to register SPI controller\n"); - goto put_ctlr; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "failed to register SPI controller\n"); if (sadi->data->restart) { ret = devm_register_restart_handler(&pdev->dev, sadi->data->restart, sadi); - if (ret) { - dev_err(&pdev->dev, "can not register restart handler\n"); - goto put_ctlr; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "can not register restart handler\n"); } return 0; - -put_ctlr: - spi_controller_put(ctlr); - return ret; } static struct sprd_adi_data sc9860_data = { diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 5e6cf34929b5..c1888c42afdd 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -741,8 +741,11 @@ void iscsit_dec_session_usage_count(struct iscsit_session *sess) spin_lock_bh(&sess->session_usage_lock); sess->session_usage_count--; - if (!sess->session_usage_count && sess->session_waiting_on_uc) + if (!sess->session_usage_count && sess->session_waiting_on_uc) { + spin_unlock_bh(&sess->session_usage_lock); complete(&sess->session_waiting_on_uc_comp); + return; + } spin_unlock_bh(&sess->session_usage_lock); } @@ -810,8 +813,11 @@ void iscsit_dec_conn_usage_count(struct iscsit_conn *conn) spin_lock_bh(&conn->conn_usage_lock); conn->conn_usage_count--; - if (!conn->conn_usage_count && conn->conn_waiting_on_uc) + if (!conn->conn_usage_count && conn->conn_waiting_on_uc) { + spin_unlock_bh(&conn->conn_usage_lock); complete(&conn->conn_waiting_on_uc_comp); + return; + } spin_unlock_bh(&conn->conn_usage_lock); } diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index c5a932f48f74..3efe075ef7b2 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1658,7 +1658,7 @@ static int pci_fintek_rs485_config(struct uart_port *port, struct ktermios *term } static const struct serial_rs485 pci_fintek_rs485_supported = { - .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND, + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND, /* F81504/508/512 does not support RTS delay before or after send */ }; diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 6ce6528f5c10..e6b0a55f0cfb 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1888,12 +1888,6 @@ static int qcom_geni_serial_probe(struct platform_device *pdev) if (ret) goto error; - devm_pm_runtime_enable(port->se.dev); - - ret = uart_add_one_port(drv, uport); - if (ret) - goto error; - if (port->wakeup_irq > 0) { device_init_wakeup(&pdev->dev, true); ret = dev_pm_set_dedicated_wake_irq(&pdev->dev, @@ -1901,11 +1895,16 @@ static int qcom_geni_serial_probe(struct platform_device *pdev) if (ret) { device_init_wakeup(&pdev->dev, false); ida_free(&port_ida, uport->line); - uart_remove_one_port(drv, uport); goto error; } } + devm_pm_runtime_enable(port->se.dev); + + ret = uart_add_one_port(drv, uport); + if (ret) + goto error; + return 0; error: diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 9930023e924c..2805cad10511 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -3074,6 +3074,12 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); + /* + * TTY port has to be linked with the driver before register_console() + * in uart_configure_port(), because user-space could open the console + * immediately after. + */ + tty_port_link_device(port, drv->tty_driver, uport->line); uart_configure_port(drv, state, uport); port->console = uart_console(uport); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 0babb7035200..604043a7533d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -10736,9 +10736,7 @@ static int ufshcd_add_scsi_host(struct ufs_hba *hba) if (is_mcq_supported(hba)) { ufshcd_mcq_enable(hba); err = ufshcd_alloc_mcq(hba); - if (!err) { - ufshcd_config_mcq(hba); - } else { + if (err) { /* Continue with SDB mode */ ufshcd_mcq_disable(hba); use_mcq_mode = false; @@ -11011,6 +11009,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) if (err) goto out_disable; + if (hba->mcq_enabled) + ufshcd_config_mcq(hba); + if (hba->quirks & UFSHCD_QUIRK_SKIP_PH_CONFIGURATION) goto initialized; diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c index ecbbf52bf734..66b11cc0703b 100644 --- a/drivers/ufs/host/ufs-mediatek.c +++ b/drivers/ufs/host/ufs-mediatek.c @@ -1112,7 +1112,7 @@ static void ufs_mtk_setup_clk_gating(struct ufs_hba *hba) unsigned long flags; u32 ah_ms = 10; u32 ah_scale, ah_timer; - u32 scale_us[] = {1, 10, 100, 1000, 10000, 100000}; + static const u32 scale_us[] = {1, 10, 100, 1000, 10000, 100000}; if (ufshcd_is_clkgating_allowed(hba)) { if (ufshcd_is_auto_hibern8_supported(hba) && hba->ahit) { diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index d93ed4e86a17..fa0d4e6aee16 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -3,7 +3,7 @@ * drivers/uio/uio.c * * Copyright(C) 2005, Benedikt Spranger <b.spranger@linutronix.de> - * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2006, Hans J. Koch <hjk@hansjkoch.de> * Copyright(C) 2006, Greg Kroah-Hartman <greg@kroah.com> * diff --git a/drivers/uio/uio_pci_generic_sva.c b/drivers/uio/uio_pci_generic_sva.c index 97e9ab9a081a..4a46acd994a8 100644 --- a/drivers/uio/uio_pci_generic_sva.c +++ b/drivers/uio/uio_pci_generic_sva.c @@ -29,7 +29,7 @@ static int uio_pci_sva_open(struct uio_info *info, struct inode *inode) struct uio_pci_sva_dev *udev = info->priv; struct iommu_domain *domain; - if (!udev && !udev->pdev) + if (!udev || !udev->pdev) return -ENODEV; domain = iommu_get_domain_for_dev(&udev->pdev->dev); @@ -51,7 +51,7 @@ static int uio_pci_sva_release(struct uio_info *info, struct inode *inode) { struct uio_pci_sva_dev *udev = info->priv; - if (!udev && !udev->pdev) + if (!udev || !udev->pdev) return -ENODEV; iommu_sva_unbind_device(udev->sva_handle); diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index baf5bc844b6f..2bb1ceb9d621 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -1040,6 +1040,11 @@ int usb_get_bos_descriptor(struct usb_device *dev) __u8 cap_type; int ret; + if (dev->quirks & USB_QUIRK_NO_BOS) { + dev_dbg(ddev, "skipping BOS descriptor\n"); + return -ENOMSG; + } + bos = kzalloc(sizeof(*bos), GFP_KERNEL); if (!bos) return -ENOMEM; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 47f589c4104a..c4d85089d19b 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -450,6 +450,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0c45, 0x7056), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Elgato 4K X - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x0fd9, 0x009b), .driver_info = USB_QUIRK_NO_BOS }, + /* Sony Xperia XZ1 Compact (lilac) smartphone in fastboot mode */ { USB_DEVICE(0x0fce, 0x0dde), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index ec8407972b9d..93fd5fdf95cb 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -993,6 +993,8 @@ static bool dwc3_core_is_valid(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_GSNPSID); dwc->ip = DWC3_GSNPS_ID(reg); + if (dwc->ip == DWC4_IP) + dwc->ip = DWC32_IP; /* This should read as U3 followed by revision number */ if (DWC3_IP_IS(DWC3)) { diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index a5fc92c4ffa3..45757169b672 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1265,6 +1265,7 @@ struct dwc3 { #define DWC3_IP 0x5533 #define DWC31_IP 0x3331 #define DWC32_IP 0x3332 +#define DWC4_IP 0x3430 u32 revision; diff --git a/drivers/usb/dwc3/dwc3-apple.c b/drivers/usb/dwc3/dwc3-apple.c index cc47cad232e3..40c3ccfddb67 100644 --- a/drivers/usb/dwc3/dwc3-apple.c +++ b/drivers/usb/dwc3/dwc3-apple.c @@ -218,25 +218,31 @@ static int dwc3_apple_core_init(struct dwc3_apple *appledwc) return ret; } -static void dwc3_apple_phy_set_mode(struct dwc3_apple *appledwc, enum phy_mode mode) -{ - lockdep_assert_held(&appledwc->lock); - - /* - * This platform requires SUSPHY to be enabled here already in order to properly configure - * the PHY and switch dwc3's PIPE interface to USB3 PHY. - */ - dwc3_enable_susphy(&appledwc->dwc, true); - phy_set_mode(appledwc->dwc.usb2_generic_phy[0], mode); - phy_set_mode(appledwc->dwc.usb3_generic_phy[0], mode); -} - static int dwc3_apple_init(struct dwc3_apple *appledwc, enum dwc3_apple_state state) { int ret, ret_reset; lockdep_assert_held(&appledwc->lock); + /* + * The USB2 PHY on this platform must be configured for host or device mode while it is + * still powered off and before dwc3 tries to access it. Otherwise, the new configuration + * will sometimes only take affect after the *next* time dwc3 is brought up which causes + * the connected device to just not work. + * The USB3 PHY must be configured later after dwc3 has already been initialized. + */ + switch (state) { + case DWC3_APPLE_HOST: + phy_set_mode(appledwc->dwc.usb2_generic_phy[0], PHY_MODE_USB_HOST); + break; + case DWC3_APPLE_DEVICE: + phy_set_mode(appledwc->dwc.usb2_generic_phy[0], PHY_MODE_USB_DEVICE); + break; + default: + /* Unreachable unless there's a bug in this driver */ + return -EINVAL; + } + ret = reset_control_deassert(appledwc->reset); if (ret) { dev_err(appledwc->dev, "Failed to deassert reset, err=%d\n", ret); @@ -257,7 +263,13 @@ static int dwc3_apple_init(struct dwc3_apple *appledwc, enum dwc3_apple_state st case DWC3_APPLE_HOST: appledwc->dwc.dr_mode = USB_DR_MODE_HOST; dwc3_apple_set_ptrcap(appledwc, DWC3_GCTL_PRTCAP_HOST); - dwc3_apple_phy_set_mode(appledwc, PHY_MODE_USB_HOST); + /* + * This platform requires SUSPHY to be enabled here already in order to properly + * configure the PHY and switch dwc3's PIPE interface to USB3 PHY. The USB2 PHY + * has already been configured to the correct mode earlier. + */ + dwc3_enable_susphy(&appledwc->dwc, true); + phy_set_mode(appledwc->dwc.usb3_generic_phy[0], PHY_MODE_USB_HOST); ret = dwc3_host_init(&appledwc->dwc); if (ret) { dev_err(appledwc->dev, "Failed to initialize host, ret=%d\n", ret); @@ -268,7 +280,13 @@ static int dwc3_apple_init(struct dwc3_apple *appledwc, enum dwc3_apple_state st case DWC3_APPLE_DEVICE: appledwc->dwc.dr_mode = USB_DR_MODE_PERIPHERAL; dwc3_apple_set_ptrcap(appledwc, DWC3_GCTL_PRTCAP_DEVICE); - dwc3_apple_phy_set_mode(appledwc, PHY_MODE_USB_DEVICE); + /* + * This platform requires SUSPHY to be enabled here already in order to properly + * configure the PHY and switch dwc3's PIPE interface to USB3 PHY. The USB2 PHY + * has already been configured to the correct mode earlier. + */ + dwc3_enable_susphy(&appledwc->dwc, true); + phy_set_mode(appledwc->dwc.usb3_generic_phy[0], PHY_MODE_USB_DEVICE); ret = dwc3_gadget_init(&appledwc->dwc); if (ret) { dev_err(appledwc->dev, "Failed to initialize gadget, ret=%d\n", ret); @@ -340,6 +358,22 @@ static int dwc3_usb_role_switch_set(struct usb_role_switch *sw, enum usb_role ro guard(mutex)(&appledwc->lock); /* + * Skip role switches if appledwc is already in the desired state. The + * USB-C port controller on M2 and M1/M2 Pro/Max/Ultra devices issues + * additional interrupts which results in usb_role_switch_set_role() + * calls with the current role. + * Ignore those calls here to ensure the USB-C port controller and + * appledwc are in a consistent state. + * This matches the behaviour in __dwc3_set_mode(). + * Do no handle USB_ROLE_NONE for DWC3_APPLE_NO_CABLE and + * DWC3_APPLE_PROBE_PENDING since that is no-op anyway. + */ + if (appledwc->state == DWC3_APPLE_HOST && role == USB_ROLE_HOST) + return 0; + if (appledwc->state == DWC3_APPLE_DEVICE && role == USB_ROLE_DEVICE) + return 0; + + /* * We need to tear all of dwc3 down and re-initialize it every time a cable is * connected or disconnected or when the mode changes. See the documentation for enum * dwc3_apple_state for details. diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index aa6ab666741a..a96476507d2f 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -362,6 +362,10 @@ uvc_function_set_alt(struct usb_function *f, unsigned interface, unsigned alt) return ret; usb_ep_enable(uvc->video.ep); + uvc->video.max_req_size = uvc->video.ep->maxpacket + * max_t(unsigned int, uvc->video.ep->maxburst, 1) + * (uvc->video.ep->mult); + memset(&v4l2_event, 0, sizeof(v4l2_event)); v4l2_event.type = UVC_EVENT_STREAMON; v4l2_event_queue(&uvc->vdev, &v4l2_event); diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h index 9e79cbe50715..676419a04976 100644 --- a/drivers/usb/gadget/function/uvc.h +++ b/drivers/usb/gadget/function/uvc.h @@ -107,7 +107,7 @@ struct uvc_video { unsigned int width; unsigned int height; unsigned int imagesize; - unsigned int interval; + unsigned int interval; /* in 100ns units */ struct mutex mutex; /* protects frame parameters */ unsigned int uvc_num_requests; @@ -117,6 +117,7 @@ struct uvc_video { /* Requests */ bool is_enabled; /* tracks whether video stream is enabled */ unsigned int req_size; + unsigned int max_req_size; struct list_head ureqs; /* all uvc_requests allocated by uvc_video */ /* USB requests that the video pump thread can encode into */ diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c index 9a1bbd79ff5a..586e5524c171 100644 --- a/drivers/usb/gadget/function/uvc_queue.c +++ b/drivers/usb/gadget/function/uvc_queue.c @@ -86,10 +86,17 @@ static int uvc_buffer_prepare(struct vb2_buffer *vb) buf->bytesused = 0; } else { buf->bytesused = vb2_get_plane_payload(vb, 0); - buf->req_payload_size = - DIV_ROUND_UP(buf->bytesused + - (video->reqs_per_frame * UVCG_REQUEST_HEADER_LEN), - video->reqs_per_frame); + + if (video->reqs_per_frame != 0) { + buf->req_payload_size = + DIV_ROUND_UP(buf->bytesused + + (video->reqs_per_frame * UVCG_REQUEST_HEADER_LEN), + video->reqs_per_frame); + if (buf->req_payload_size > video->req_size) + buf->req_payload_size = video->req_size; + } else { + buf->req_payload_size = video->max_req_size; + } } return 0; @@ -175,7 +182,15 @@ int uvcg_alloc_buffers(struct uvc_video_queue *queue, { int ret; +retry: ret = vb2_reqbufs(&queue->queue, rb); + if (ret < 0 && queue->use_sg) { + uvc_trace(UVC_TRACE_IOCTL, + "failed to alloc buffer with sg enabled, try non-sg mode\n"); + queue->use_sg = 0; + queue->queue.mem_ops = &vb2_vmalloc_memops; + goto retry; + } return ret ? ret : rb->count; } diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index fb77b0b21790..f568dee08b3b 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -499,13 +499,11 @@ uvc_video_prep_requests(struct uvc_video *video) { struct uvc_device *uvc = container_of(video, struct uvc_device, video); struct usb_composite_dev *cdev = uvc->func.config->cdev; - unsigned int interval_duration = video->ep->desc->bInterval * 1250; + unsigned int interval_duration; unsigned int max_req_size, req_size, header_size; unsigned int nreq; - max_req_size = video->ep->maxpacket - * max_t(unsigned int, video->ep->maxburst, 1) - * (video->ep->mult); + max_req_size = video->max_req_size; if (!usb_endpoint_xfer_isoc(video->ep->desc)) { video->req_size = max_req_size; @@ -515,8 +513,11 @@ uvc_video_prep_requests(struct uvc_video *video) return; } + interval_duration = 2 << (video->ep->desc->bInterval - 1); if (cdev->gadget->speed < USB_SPEED_HIGH) - interval_duration = video->ep->desc->bInterval * 10000; + interval_duration *= 10000; + else + interval_duration *= 1250; nreq = DIV_ROUND_UP(video->interval, interval_duration); @@ -837,7 +838,6 @@ int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc) video->interval = 666666; /* Initialize the video buffers queue. */ - uvcg_queue_init(&video->queue, uvc->v4l2_dev.dev->parent, + return uvcg_queue_init(&video->queue, uvc->v4l2_dev.dev->parent, V4L2_BUF_TYPE_VIDEO_OUTPUT, &video->mutex); - return 0; } diff --git a/drivers/usb/host/ohci-platform.c b/drivers/usb/host/ohci-platform.c index 2e4bb5cc2165..c801527d5bd2 100644 --- a/drivers/usb/host/ohci-platform.c +++ b/drivers/usb/host/ohci-platform.c @@ -392,3 +392,4 @@ MODULE_DESCRIPTION(DRIVER_DESC); MODULE_AUTHOR("Hauke Mehrtens"); MODULE_AUTHOR("Alan Stern"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: ehci_platform"); diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c index 5e02f2ceafb6..f4419d4526c4 100644 --- a/drivers/usb/host/uhci-platform.c +++ b/drivers/usb/host/uhci-platform.c @@ -211,3 +211,4 @@ static struct platform_driver uhci_platform_driver = { .of_match_table = platform_uhci_ids, }, }; +MODULE_SOFTDEP("pre: ehci_platform"); diff --git a/drivers/usb/host/xhci-sideband.c b/drivers/usb/host/xhci-sideband.c index a85f62a73313..2bd77255032b 100644 --- a/drivers/usb/host/xhci-sideband.c +++ b/drivers/usb/host/xhci-sideband.c @@ -210,7 +210,6 @@ xhci_sideband_remove_endpoint(struct xhci_sideband *sb, return -ENODEV; __xhci_sideband_remove_endpoint(sb, ep); - xhci_initialize_ring_info(ep->ring); return 0; } diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 31ccced5125e..8b492871d21d 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1563,7 +1563,7 @@ static int tegra_xusb_setup_wakeup(struct platform_device *pdev, struct tegra_xu for (i = 0; i < tegra->soc->max_num_wakes; i++) { struct irq_data *data; - tegra->wake_irqs[i] = platform_get_irq(pdev, i + WAKE_IRQ_START_INDEX); + tegra->wake_irqs[i] = platform_get_irq_optional(pdev, i + WAKE_IRQ_START_INDEX); if (tegra->wake_irqs[i] < 0) break; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 02c9bfe21ae2..b3ba16b9718c 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2898,16 +2898,25 @@ int xhci_stop_endpoint_sync(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, int gfp_t gfp_flags) { struct xhci_command *command; + struct xhci_ep_ctx *ep_ctx; unsigned long flags; - int ret; + int ret = -ENODEV; command = xhci_alloc_command(xhci, true, gfp_flags); if (!command) return -ENOMEM; spin_lock_irqsave(&xhci->lock, flags); - ret = xhci_queue_stop_endpoint(xhci, command, ep->vdev->slot_id, - ep->ep_index, suspend); + + /* make sure endpoint exists and is running before stopping it */ + if (ep->ring) { + ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); + if (GET_EP_CTX_STATE(ep_ctx) == EP_STATE_RUNNING) + ret = xhci_queue_stop_endpoint(xhci, command, + ep->vdev->slot_id, + ep->ep_index, suspend); + } + if (ret < 0) { spin_unlock_irqrestore(&xhci->lock, flags); goto out; diff --git a/drivers/usb/serial/f81232.c b/drivers/usb/serial/f81232.c index 530b77fc2f78..9262a2ac97f5 100644 --- a/drivers/usb/serial/f81232.c +++ b/drivers/usb/serial/f81232.c @@ -70,7 +70,6 @@ MODULE_DEVICE_TABLE(usb, combined_id_table); #define F81232_REGISTER_REQUEST 0xa0 #define F81232_GET_REGISTER 0xc0 #define F81232_SET_REGISTER 0x40 -#define F81534A_ACCESS_REG_RETRY 2 #define SERIAL_BASE_ADDRESS 0x0120 #define RECEIVE_BUFFER_REGISTER (0x00 + SERIAL_BASE_ADDRESS) @@ -824,36 +823,31 @@ static void f81232_lsr_worker(struct work_struct *work) static int f81534a_ctrl_set_register(struct usb_interface *intf, u16 reg, u16 size, void *val) { - struct usb_device *dev = interface_to_usbdev(intf); - int retry = F81534A_ACCESS_REG_RETRY; - int status; - - while (retry--) { - status = usb_control_msg_send(dev, - 0, - F81232_REGISTER_REQUEST, - F81232_SET_REGISTER, - reg, - 0, - val, - size, - USB_CTRL_SET_TIMEOUT, - GFP_KERNEL); - if (status) { - status = usb_translate_errors(status); - if (status == -EIO) - continue; - } - - break; - } - - if (status) { - dev_err(&intf->dev, "failed to set register 0x%x: %d\n", - reg, status); - } + return usb_control_msg_send(interface_to_usbdev(intf), + 0, + F81232_REGISTER_REQUEST, + F81232_SET_REGISTER, + reg, + 0, + val, + size, + USB_CTRL_SET_TIMEOUT, + GFP_KERNEL); +} - return status; +static int f81534a_ctrl_get_register(struct usb_interface *intf, u16 reg, + u16 size, void *val) +{ + return usb_control_msg_recv(interface_to_usbdev(intf), + 0, + F81232_REGISTER_REQUEST, + F81232_GET_REGISTER, + reg, + 0, + val, + size, + USB_CTRL_GET_TIMEOUT, + GFP_KERNEL); } static int f81534a_ctrl_enable_all_ports(struct usb_interface *intf, bool en) @@ -869,6 +863,29 @@ static int f81534a_ctrl_enable_all_ports(struct usb_interface *intf, bool en) * bit 0~11 : Serial port enable bit. */ if (en) { + /* + * The Fintek F81532A/534A/535/536 family relies on the + * F81534A_CTRL_CMD_ENABLE_PORT (116h) register during + * initialization to both determine serial port status and + * control port creation. + * + * If the driver experiences fast load/unload cycles, the + * device state may becomes unstable, resulting in the + * incomplete generation of serial ports. + * + * Performing a dummy read operation on the register prior + * to the initial write command resolves the issue. + * + * This clears the device's stale internal state. Subsequent + * write operations will correctly generate all serial ports. + */ + status = f81534a_ctrl_get_register(intf, + F81534A_CTRL_CMD_ENABLE_PORT, + sizeof(enable), + enable); + if (status) + return status; + enable[0] = 0xff; enable[1] = 0x8f; } diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index fe2f21d85737..acb48b1c83f7 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -848,6 +848,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_DEVEL_BOARD_PID, 1) }, { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_EVAL_BOARD_PID, 1) }, { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_ICDI_BOARD_PID, 1) }, + { USB_DEVICE(FTDI_VID, FTDI_AXE027_PID) }, { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_TURTELIZER_PID, 1) }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_USB60F) }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_SCU18) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 2539b9e2f712..6c76cfebfd0e 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -96,6 +96,8 @@ #define LMI_LM3S_EVAL_BOARD_PID 0xbcd9 #define LMI_LM3S_ICDI_BOARD_PID 0xbcda +#define FTDI_AXE027_PID 0xBD90 /* PICAXE AXE027 USB download cable */ + #define FTDI_TURTELIZER_PID 0xBDC8 /* JTAG/RS-232 adapter by egnite GmbH */ /* OpenDCC (www.opendcc.de) product id */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 4c0e5a3ab557..9f2cc5fb9f45 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1505,6 +1505,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff), /* Telit LE910Cx (RNDIS) */ .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x1250, 0xff, 0x00, 0x00) }, /* Telit LE910Cx (rmnet) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1252, 0xff) }, /* Telit LE910Cx (MBIM) */ { USB_DEVICE(TELIT_VENDOR_ID, 0x1260), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x1261), diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 4ca2746ce16b..be49a976428f 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -7890,7 +7890,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) port->partner_desc.identity = &port->partner_ident; port->role_sw = fwnode_usb_role_switch_get(tcpc->fwnode); - if (!port->role_sw) + if (IS_ERR_OR_NULL(port->role_sw)) port->role_sw = usb_role_switch_get(port->dev); if (IS_ERR(port->role_sw)) { err = PTR_ERR(port->role_sw); diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index 84d142a47ec6..b45a24d00387 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -561,7 +561,7 @@ nvgrace_gpu_map_and_read(struct nvgrace_gpu_pci_core_device *nvdev, ret = vfio_pci_core_do_io_rw(&nvdev->core_device, false, nvdev->resmem.ioaddr, buf, offset, mem_count, - 0, 0, false); + 0, 0, false, VFIO_PCI_IO_WIDTH_8); } return ret; @@ -693,7 +693,7 @@ nvgrace_gpu_map_and_write(struct nvgrace_gpu_pci_core_device *nvdev, ret = vfio_pci_core_do_io_rw(&nvdev->core_device, false, nvdev->resmem.ioaddr, (char __user *)buf, pos, mem_count, - 0, 0, true); + 0, 0, true, VFIO_PCI_IO_WIDTH_8); } return ret; diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c index 481992142f79..4915a7c1c491 100644 --- a/drivers/vfio/pci/pds/dirty.c +++ b/drivers/vfio/pci/pds/dirty.c @@ -292,8 +292,11 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio, len = num_ranges * sizeof(*region_info); node = interval_tree_iter_first(ranges, 0, ULONG_MAX); - if (!node) - return -EINVAL; + if (!node) { + err = -EINVAL; + goto out_free_region_info; + } + for (int i = 0; i < num_ranges; i++) { struct pds_lm_dirty_region_info *ri = ®ion_info[i]; u64 region_size = node->last - node->start + 1; diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c index d4d0f7d08c53..4be4a85005cb 100644 --- a/drivers/vfio/pci/vfio_pci_dmabuf.c +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c @@ -20,6 +20,16 @@ struct vfio_pci_dma_buf { u8 revoked : 1; }; +static int vfio_pci_dma_buf_pin(struct dma_buf_attachment *attachment) +{ + return -EOPNOTSUPP; +} + +static void vfio_pci_dma_buf_unpin(struct dma_buf_attachment *attachment) +{ + /* Do nothing */ +} + static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf, struct dma_buf_attachment *attachment) { @@ -76,6 +86,8 @@ static void vfio_pci_dma_buf_release(struct dma_buf *dmabuf) } static const struct dma_buf_ops vfio_pci_dmabuf_ops = { + .pin = vfio_pci_dma_buf_pin, + .unpin = vfio_pci_dma_buf_unpin, .attach = vfio_pci_dma_buf_attach, .map_dma_buf = vfio_pci_dma_buf_map, .unmap_dma_buf = vfio_pci_dma_buf_unmap, diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 6192788c8ba3..b38627b35c35 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -135,7 +135,8 @@ VFIO_IORDWR(64) ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, - size_t x_end, bool iswrite) + size_t x_end, bool iswrite, + enum vfio_pci_io_width max_width) { ssize_t done = 0; int ret; @@ -150,20 +151,19 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, else fillable = 0; - if (fillable >= 8 && !(off % 8)) { + if (fillable >= 8 && !(off % 8) && max_width >= 8) { ret = vfio_pci_iordwr64(vdev, iswrite, test_mem, io, buf, off, &filled); if (ret) return ret; - } else - if (fillable >= 4 && !(off % 4)) { + } else if (fillable >= 4 && !(off % 4) && max_width >= 4) { ret = vfio_pci_iordwr32(vdev, iswrite, test_mem, io, buf, off, &filled); if (ret) return ret; - } else if (fillable >= 2 && !(off % 2)) { + } else if (fillable >= 2 && !(off % 2) && max_width >= 2) { ret = vfio_pci_iordwr16(vdev, iswrite, test_mem, io, buf, off, &filled); if (ret) @@ -234,6 +234,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, void __iomem *io; struct resource *res = &vdev->pdev->resource[bar]; ssize_t done; + enum vfio_pci_io_width max_width = VFIO_PCI_IO_WIDTH_8; if (pci_resource_start(pdev, bar)) end = pci_resource_len(pdev, bar); @@ -262,6 +263,16 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, if (!io) return -ENOMEM; x_end = end; + + /* + * Certain devices (e.g. Intel X710) don't support qword + * access to the ROM bar. Otherwise PCI AER errors might be + * triggered. + * + * Disable qword access to the ROM bar universally, which + * worked reliably for years before qword access is enabled. + */ + max_width = VFIO_PCI_IO_WIDTH_4; } else { int ret = vfio_pci_core_setup_barmap(vdev, bar); if (ret) { @@ -278,7 +289,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, } done = vfio_pci_core_do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, - count, x_start, x_end, iswrite); + count, x_start, x_end, iswrite, max_width); if (done >= 0) *ppos += done; @@ -352,7 +363,7 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, * to the memory enable bit in the command register. */ done = vfio_pci_core_do_io_rw(vdev, false, iomem, buf, off, count, - 0, 0, iswrite); + 0, 0, iswrite, VFIO_PCI_IO_WIDTH_4); vga_put(vdev->pdev, rsrc); diff --git a/drivers/vfio/pci/xe/main.c b/drivers/vfio/pci/xe/main.c index 0156b53c678b..2a5eb9260ec7 100644 --- a/drivers/vfio/pci/xe/main.c +++ b/drivers/vfio/pci/xe/main.c @@ -250,6 +250,7 @@ xe_vfio_pci_alloc_file(struct xe_vfio_pci_core_device *xe_vdev, struct xe_vfio_pci_migration_file *migf; const struct file_operations *fops; int flags; + int ret; migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT); if (!migf) @@ -259,8 +260,9 @@ xe_vfio_pci_alloc_file(struct xe_vfio_pci_core_device *xe_vdev, flags = type == XE_VFIO_FILE_SAVE ? O_RDONLY : O_WRONLY; migf->filp = anon_inode_getfile("xe_vfio_mig", fops, migf, flags); if (IS_ERR(migf->filp)) { + ret = PTR_ERR(migf->filp); kfree(migf); - return ERR_CAST(migf->filp); + return ERR_PTR(ret); } mutex_init(&migf->lock); @@ -504,6 +506,7 @@ static const struct vfio_device_ops xe_vfio_pci_ops = { .open_device = xe_vfio_pci_open_device, .close_device = xe_vfio_pci_close_device, .ioctl = vfio_pci_core_ioctl, + .get_region_info_caps = vfio_pci_ioctl_get_region_info, .device_feature = vfio_pci_core_ioctl_feature, .read = vfio_pci_core_read, .write = vfio_pci_core_write, diff --git a/drivers/w1/slaves/w1_therm.c b/drivers/w1/slaves/w1_therm.c index 9ccedb3264fb..832e3da94b20 100644 --- a/drivers/w1/slaves/w1_therm.c +++ b/drivers/w1/slaves/w1_therm.c @@ -1836,53 +1836,35 @@ static ssize_t alarms_store(struct device *device, struct w1_slave *sl = dev_to_w1_slave(device); struct therm_info info; u8 new_config_register[3]; /* array of data to be written */ - int temp, ret; - char *token = NULL; + long long temp; + int ret = 0; s8 tl, th; /* 1 byte per value + temp ring order */ - char *p_args, *orig; - - p_args = orig = kmalloc(size, GFP_KERNEL); - /* Safe string copys as buf is const */ - if (!p_args) { - dev_warn(device, - "%s: error unable to allocate memory %d\n", - __func__, -ENOMEM); - return size; - } - strcpy(p_args, buf); - - /* Split string using space char */ - token = strsep(&p_args, " "); - - if (!token) { - dev_info(device, - "%s: error parsing args %d\n", __func__, -EINVAL); - goto free_m; - } - - /* Convert 1st entry to int */ - ret = kstrtoint (token, 10, &temp); + const char *p = buf; + char *endp; + + temp = simple_strtoll(p, &endp, 10); + if (p == endp || *endp != ' ') + ret = -EINVAL; + else if (temp < INT_MIN || temp > INT_MAX) + ret = -ERANGE; if (ret) { dev_info(device, "%s: error parsing args %d\n", __func__, ret); - goto free_m; + return size; } tl = int_to_short(temp); - /* Split string using space char */ - token = strsep(&p_args, " "); - if (!token) { - dev_info(device, - "%s: error parsing args %d\n", __func__, -EINVAL); - goto free_m; - } - /* Convert 2nd entry to int */ - ret = kstrtoint (token, 10, &temp); + p = endp + 1; + temp = simple_strtoll(p, &endp, 10); + if (p == endp) + ret = -EINVAL; + else if (temp < INT_MIN || temp > INT_MAX) + ret = -ERANGE; if (ret) { dev_info(device, "%s: error parsing args %d\n", __func__, ret); - goto free_m; + return size; } /* Prepare to cast to short by eliminating out of range values */ @@ -1905,7 +1887,7 @@ static ssize_t alarms_store(struct device *device, dev_info(device, "%s: error reading from the slave device %d\n", __func__, ret); - goto free_m; + return size; } /* Write data in the device RAM */ @@ -1913,7 +1895,7 @@ static ssize_t alarms_store(struct device *device, dev_info(device, "%s: Device not supported by the driver %d\n", __func__, -ENODEV); - goto free_m; + return size; } ret = SLAVE_SPECIFIC_FUNC(sl)->write_data(sl, new_config_register); @@ -1922,10 +1904,6 @@ static ssize_t alarms_store(struct device *device, "%s: error writing to the slave device %d\n", __func__, ret); -free_m: - /* free allocated memory */ - kfree(orig); - return size; } diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 002d2639aa12..5f78b0a0b766 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -758,8 +758,6 @@ int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn) if (err < 0) { dev_err(&dev->dev, "%s: Attaching %s failed.\n", __func__, sl->name); - dev->slave_count--; - w1_family_put(sl->family); atomic_dec(&sl->master->refcnt); kfree(sl); return err; diff --git a/drivers/xen/acpi.c b/drivers/xen/acpi.c index d2ee605c5ca1..eab28cfe9939 100644 --- a/drivers/xen/acpi.c +++ b/drivers/xen/acpi.c @@ -89,11 +89,11 @@ int xen_acpi_get_gsi_info(struct pci_dev *dev, int *trigger_out, int *polarity_out) { - int gsi; + u32 gsi; u8 pin; struct acpi_prt_entry *entry; int trigger = ACPI_LEVEL_SENSITIVE; - int polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC ? + int ret, polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC ? ACPI_ACTIVE_HIGH : ACPI_ACTIVE_LOW; if (!dev || !gsi_out || !trigger_out || !polarity_out) @@ -105,17 +105,18 @@ int xen_acpi_get_gsi_info(struct pci_dev *dev, entry = acpi_pci_irq_lookup(dev, pin); if (entry) { + ret = 0; if (entry->link) - gsi = acpi_pci_link_allocate_irq(entry->link, + ret = acpi_pci_link_allocate_irq(entry->link, entry->index, &trigger, &polarity, - NULL); + NULL, &gsi); else gsi = entry->index; } else - gsi = -1; + ret = -ENODEV; - if (gsi < 0) + if (ret < 0) return -EINVAL; *gsi_out = gsi; diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 0c51edfd13dc..7d5117e5efe0 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1262,6 +1262,7 @@ static void scsiback_remove(struct xenbus_device *dev) gnttab_page_cache_shrink(&info->free_pages, 0); dev_set_drvdata(&dev->dev, NULL); + kfree(info); } static int scsiback_probe(struct xenbus_device *dev, diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index e0d34e4e9076..af7f72abbb76 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -242,6 +242,7 @@ const struct file_operations v9fs_dir_operations = { .iterate_shared = v9fs_dir_readdir, .open = v9fs_file_open, .release = v9fs_dir_release, + .setlease = simple_nosetlease, }; const struct file_operations v9fs_dir_operations_dotl = { @@ -251,4 +252,5 @@ const struct file_operations v9fs_dir_operations_dotl = { .open = v9fs_file_open, .release = v9fs_dir_release, .fsync = v9fs_file_fsync_dotl, + .setlease = simple_nosetlease, }; diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 4438637c8900..6d6fc85835d4 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -115,6 +115,10 @@ config BTRFS_EXPERIMENTAL - extent tree v2 - complex rework of extent tracking - - large folio support + - large folio and block size (> page size) support + + - shutdown ioctl and auto-degradation support + + - asynchronous checksum generation for data writes If unsure, say N. diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index ce6e9f8812e0..4b7d9015e0da 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -152,37 +152,39 @@ again: return ERR_PTR(-ENOMEM); btrfs_init_delayed_node(node, root, ino); + /* Cached in the inode and can be accessed. */ + refcount_set(&node->refs, 2); + btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_NOFS); + btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_NOFS); + /* Allocate and reserve the slot, from now it can return a NULL from xa_load(). */ ret = xa_reserve(&root->delayed_nodes, ino, GFP_NOFS); - if (ret == -ENOMEM) { - btrfs_delayed_node_ref_tracker_dir_exit(node); - kmem_cache_free(delayed_node_cache, node); - return ERR_PTR(-ENOMEM); - } + if (ret == -ENOMEM) + goto cleanup; + xa_lock(&root->delayed_nodes); ptr = xa_load(&root->delayed_nodes, ino); if (ptr) { /* Somebody inserted it, go back and read it. */ xa_unlock(&root->delayed_nodes); - btrfs_delayed_node_ref_tracker_dir_exit(node); - kmem_cache_free(delayed_node_cache, node); - node = NULL; - goto again; + goto cleanup; } ptr = __xa_store(&root->delayed_nodes, ino, node, GFP_ATOMIC); ASSERT(xa_err(ptr) != -EINVAL); ASSERT(xa_err(ptr) != -ENOMEM); ASSERT(ptr == NULL); - - /* Cached in the inode and can be accessed. */ - refcount_set(&node->refs, 2); - btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_ATOMIC); - btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_ATOMIC); - btrfs_inode->delayed_node = node; xa_unlock(&root->delayed_nodes); return node; +cleanup: + btrfs_delayed_node_ref_tracker_free(node, tracker); + btrfs_delayed_node_ref_tracker_free(node, &node->inode_cache_tracker); + btrfs_delayed_node_ref_tracker_dir_exit(node); + kmem_cache_free(delayed_node_cache, node); + if (ret) + return ERR_PTR(ret); + goto again; } /* diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 89149fac804c..2833b44f4b4f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -498,28 +498,6 @@ static int btree_migrate_folio(struct address_space *mapping, #define btree_migrate_folio NULL #endif -static int btree_writepages(struct address_space *mapping, - struct writeback_control *wbc) -{ - int ret; - - if (wbc->sync_mode == WB_SYNC_NONE) { - struct btrfs_fs_info *fs_info; - - if (wbc->for_kupdate) - return 0; - - fs_info = inode_to_fs_info(mapping->host); - /* this is a bit racy, but that's ok */ - ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes, - BTRFS_DIRTY_METADATA_THRESH, - fs_info->dirty_metadata_batch); - if (ret < 0) - return 0; - } - return btree_write_cache_pages(mapping, wbc); -} - static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags) { if (folio_test_writeback(folio) || folio_test_dirty(folio)) @@ -1661,7 +1639,7 @@ static void backup_super_roots(struct btrfs_fs_info *info) btrfs_set_backup_chunk_root_level(root_backup, btrfs_header_level(info->chunk_root->node)); - if (!btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) { + if (!btrfs_fs_incompat(info, EXTENT_TREE_V2)) { struct btrfs_root *extent_root = btrfs_extent_root(info, 0); struct btrfs_root *csum_root = btrfs_csum_root(info, 0); @@ -2255,6 +2233,7 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) BTRFS_DATA_RELOC_TREE_OBJECTID, true); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + location.objectid = BTRFS_DATA_RELOC_TREE_OBJECTID; ret = PTR_ERR(root); goto out; } @@ -3254,6 +3233,15 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) return 0; } +static bool fs_is_full_ro(const struct btrfs_fs_info *fs_info) +{ + if (!sb_rdonly(fs_info->sb)) + return false; + if (unlikely(fs_info->mount_opt & BTRFS_MOUNT_FULL_RO_MASK)) + return true; + return false; +} + int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices) { u32 sectorsize; @@ -3362,6 +3350,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) WRITE_ONCE(fs_info->fs_error, -EUCLEAN); + /* If the fs has any rescue options, no transaction is allowed. */ + if (fs_is_full_ro(fs_info)) + WRITE_ONCE(fs_info->fs_error, -EROFS); + /* Set up fs_info before parsing mount options */ nodesize = btrfs_super_nodesize(disk_super); sectorsize = btrfs_super_sectorsize(disk_super); @@ -3488,6 +3480,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->generation == btrfs_super_uuid_tree_generation(disk_super)) set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags); + if (unlikely(btrfs_verify_dev_items(fs_info))) { + ret = -EUCLEAN; + goto fail_block_groups; + } ret = btrfs_verify_dev_extents(fs_info); if (ret) { btrfs_err(fs_info, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 629fd5af4286..f6cca3c97166 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1728,7 +1728,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, struct btrfs_ordered_extent *ordered; ordered = btrfs_lookup_first_ordered_range(inode, cur, - folio_end - cur); + fs_info->sectorsize); /* * We have just run delalloc before getting here, so * there must be an ordered extent. @@ -1742,7 +1742,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, btrfs_put_ordered_extent(ordered); btrfs_mark_ordered_io_finished(inode, folio, cur, - end - cur, true); + fs_info->sectorsize, true); /* * This range is beyond i_size, thus we don't need to * bother writing back. @@ -1751,8 +1751,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, * writeback the sectors with subpage dirty bits, * causing writeback without ordered extent. */ - btrfs_folio_clear_dirty(fs_info, folio, cur, end - cur); - break; + btrfs_folio_clear_dirty(fs_info, folio, cur, fs_info->sectorsize); + continue; } ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size); if (unlikely(ret < 0)) { @@ -2286,8 +2286,7 @@ void btrfs_btree_wait_writeback_range(struct btrfs_fs_info *fs_info, u64 start, } } -int btree_write_cache_pages(struct address_space *mapping, - struct writeback_control *wbc) +int btree_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct btrfs_eb_write_context ctx = { .wbc = wbc }; struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 02ebb2f238af..73571d5d3d5a 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -237,8 +237,7 @@ void extent_write_locked_range(struct inode *inode, const struct folio *locked_f u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty); int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc); -int btree_write_cache_pages(struct address_space *mapping, - struct writeback_control *wbc); +int btree_writepages(struct address_space *mapping, struct writeback_control *wbc); void btrfs_btree_wait_writeback_range(struct btrfs_fs_info *fs_info, u64 start, u64 end); void btrfs_readahead(struct readahead_control *rac); int set_folio_extent_mapped(struct folio *folio); diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 0f7e1ef27891..8ffbc40ebe45 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -264,6 +264,14 @@ enum { BTRFS_MOUNT_REF_TRACKER = (1ULL << 33), }; +/* These mount options require a full read-only fs, no new transaction is allowed. */ +#define BTRFS_MOUNT_FULL_RO_MASK \ + (BTRFS_MOUNT_NOLOGREPLAY | \ + BTRFS_MOUNT_IGNOREBADROOTS | \ + BTRFS_MOUNT_IGNOREDATACSUMS | \ + BTRFS_MOUNT_IGNOREMETACSUMS | \ + BTRFS_MOUNT_IGNORESUPERFLAGS) + /* * Compat flags that we support. If any incompat flags are set other than the * ones specified below then we will fail to mount diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 317db7d10a21..a2b5b440637e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -481,13 +481,15 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, ASSERT(size <= sectorsize); /* - * The compressed size also needs to be no larger than a sector. - * That's also why we only need one page as the parameter. + * The compressed size also needs to be no larger than a page. + * That's also why we only need one folio as the parameter. */ - if (compressed_folio) + if (compressed_folio) { ASSERT(compressed_size <= sectorsize); - else + ASSERT(compressed_size <= PAGE_SIZE); + } else { ASSERT(compressed_size == 0); + } if (compressed_size && compressed_folio) cur_size = compressed_size; @@ -574,6 +576,18 @@ static bool can_cow_file_range_inline(struct btrfs_inode *inode, if (offset != 0) return false; + /* + * Even for bs > ps cases, cow_file_range_inline() can only accept a + * single folio. + * + * This can be problematic and cause access beyond page boundary if a + * page sized folio is passed into that function. + * And encoded write is doing exactly that. + * So here limits the inlined extent size to PAGE_SIZE. + */ + if (size > PAGE_SIZE || compressed_size > PAGE_SIZE) + return false; + /* Inline extents are limited to sectorsize. */ if (size > fs_info->sectorsize) return false; @@ -618,19 +632,22 @@ static noinline int __cow_file_range_inline(struct btrfs_inode *inode, struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_trans_handle *trans; + struct btrfs_trans_handle *trans = NULL; u64 data_len = (compressed_size ?: size); int ret; struct btrfs_path *path; path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out; + } trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { - btrfs_free_path(path); - return PTR_ERR(trans); + ret = PTR_ERR(trans); + trans = NULL; + goto out; } trans->block_rsv = &inode->block_rsv; @@ -674,10 +691,15 @@ out: * it won't count as data extent, free them directly here. * And at reserve time, it's always aligned to page size, so * just free one page here. + * + * If we fallback to non-inline (ret == 1) due to -ENOSPC, then we need + * to keep the data reservation. */ - btrfs_qgroup_free_data(inode, NULL, 0, fs_info->sectorsize, NULL); + if (ret <= 0) + btrfs_qgroup_free_data(inode, NULL, 0, fs_info->sectorsize, NULL); btrfs_free_path(path); - btrfs_end_transaction(trans); + if (trans) + btrfs_end_transaction(trans); return ret; } @@ -4026,11 +4048,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path btrfs_set_inode_mapping_order(inode); cache_index: - ret = btrfs_init_file_extent_tree(inode); - if (ret) - goto out; - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); /* * If we were modified in the current generation and evicted from memory * and then re-read we need to do a full sync since we don't have any @@ -4117,6 +4134,20 @@ cache_acl: btrfs_ino(inode), btrfs_root_id(root), ret); } + /* + * We don't need the path anymore, so release it to avoid holding a read + * lock on a leaf while calling btrfs_init_file_extent_tree(), which can + * allocate memory that triggers reclaim (GFP_KERNEL) and cause a locking + * dependency. + */ + btrfs_release_path(path); + + ret = btrfs_init_file_extent_tree(inode); + if (ret) + goto out; + btrfs_inode_set_file_extent_range(inode, 0, + round_up(i_size_read(vfs_inode), fs_info->sectorsize)); + if (!maybe_acls) cache_no_acl(vfs_inode); @@ -4149,6 +4180,15 @@ cache_acl: return 0; out: + /* + * We may have a read locked leaf and iget_failed() triggers inode + * eviction which needs to release the delayed inode and that needs + * to lock the delayed inode's mutex. This can cause a ABBA deadlock + * with a task running delayed items, as that require first locking + * the delayed inode's mutex and then modifying its subvolume btree. + * So release the path before iget_failed(). + */ + btrfs_release_path(path); iget_failed(vfs_inode); return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d9d8d9968a58..206587820fec 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3208,9 +3208,15 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info, { struct btrfs_qgroup *src; struct btrfs_qgroup *parent; + struct btrfs_qgroup *qgroup; struct btrfs_qgroup_list *list; + LIST_HEAD(qgroup_list); + const u32 nodesize = fs_info->nodesize; int nr_parents = 0; + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_FULL) + return 0; + src = find_qgroup_rb(fs_info, srcid); if (!src) return -ENOENT; @@ -3245,8 +3251,19 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info, if (parent->excl != parent->rfer) return 1; - parent->excl += fs_info->nodesize; - parent->rfer += fs_info->nodesize; + qgroup_iterator_add(&qgroup_list, parent); + list_for_each_entry(qgroup, &qgroup_list, iterator) { + qgroup->rfer += nodesize; + qgroup->rfer_cmpr += nodesize; + qgroup->excl += nodesize; + qgroup->excl_cmpr += nodesize; + qgroup_dirty(fs_info, qgroup); + + /* Append parent qgroups to @qgroup_list. */ + list_for_each_entry(list, &qgroup->groups, next_group) + qgroup_iterator_add(&qgroup_list, list->group); + } + qgroup_iterator_clean(&qgroup_list); return 0; } diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index b5fe95baf92e..58dc3e5057ce 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -705,7 +705,6 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, struct inode *src = file_inode(file_src); struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); int ret; - int wb_ret; u64 len = olen; u64 bs = fs_info->sectorsize; u64 end; @@ -750,25 +749,29 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, btrfs_lock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state); ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); btrfs_unlock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state); + if (ret < 0) + return ret; /* * We may have copied an inline extent into a page of the destination - * range, so wait for writeback to complete before truncating pages + * range, so wait for writeback to complete before invalidating pages * from the page cache. This is a rare case. */ - wb_ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len); - ret = ret ? ret : wb_ret; + ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len); + if (ret < 0) + return ret; + /* - * Truncate page cache pages so that future reads will see the cloned - * data immediately and not the previous data. + * Invalidate page cache so that future reads will see the cloned data + * immediately and not the previous data. */ - truncate_inode_pages_range(&inode->i_data, - round_down(destoff, PAGE_SIZE), - round_up(destoff + len, PAGE_SIZE) - 1); + ret = filemap_invalidate_inode(inode, false, destoff, end); + if (ret < 0) + return ret; btrfs_btree_balance_dirty(fs_info); - return ret; + return 0; } static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 2522faa97478..d8127a7120c2 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6383,6 +6383,8 @@ static int range_is_hole_in_parent(struct send_ctx *sctx, extent_end = btrfs_file_extent_end(path); if (extent_end <= start) goto next; + if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) + return 0; if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) { search_start = extent_end; goto next; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 6babbe333741..3f08e450f796 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -306,18 +306,22 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) 0); if (ret) - return ret; + goto out_free; } ret = btrfs_sysfs_add_space_info_type(space_info); if (ret) - return ret; + goto out_free; list_add(&space_info->list, &info->space_info); if (flags & BTRFS_BLOCK_GROUP_DATA) info->data_sinfo = space_info; return ret; + +out_free: + kfree(space_info); + return ret; } int btrfs_init_space_info(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 1999533b52be..af56fdbba65d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -736,14 +736,12 @@ bool btrfs_check_options(const struct btrfs_fs_info *info, */ void btrfs_set_free_space_cache_settings(struct btrfs_fs_info *fs_info) { - if (fs_info->sectorsize < PAGE_SIZE) { + if (fs_info->sectorsize != PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) { + btrfs_info(fs_info, + "forcing free space tree for sector size %u with page size %lu", + fs_info->sectorsize, PAGE_SIZE); btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE); - if (!btrfs_test_opt(fs_info, FREE_SPACE_TREE)) { - btrfs_info(fs_info, - "forcing free space tree for sector size %u with page size %lu", - fs_info->sectorsize, PAGE_SIZE); - btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE); - } + btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE); } /* diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 1f64c132b387..4b3c2acac51a 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -26,7 +26,6 @@ #include "misc.h" #include "fs.h" #include "accessors.h" -#include "zoned.h" /* * Structure name Path @@ -1189,56 +1188,6 @@ static ssize_t btrfs_commit_stats_store(struct kobject *kobj, } BTRFS_ATTR_RW(, commit_stats, btrfs_commit_stats_show, btrfs_commit_stats_store); -static ssize_t btrfs_zoned_stats_show(struct kobject *kobj, - struct kobj_attribute *a, char *buf) -{ - struct btrfs_fs_info *fs_info = to_fs_info(kobj); - struct btrfs_block_group *bg; - size_t ret = 0; - - - if (!btrfs_is_zoned(fs_info)) - return ret; - - spin_lock(&fs_info->zone_active_bgs_lock); - ret += sysfs_emit_at(buf, ret, "active block-groups: %zu\n", - list_count_nodes(&fs_info->zone_active_bgs)); - spin_unlock(&fs_info->zone_active_bgs_lock); - - mutex_lock(&fs_info->reclaim_bgs_lock); - spin_lock(&fs_info->unused_bgs_lock); - ret += sysfs_emit_at(buf, ret, "\treclaimable: %zu\n", - list_count_nodes(&fs_info->reclaim_bgs)); - ret += sysfs_emit_at(buf, ret, "\tunused: %zu\n", - list_count_nodes(&fs_info->unused_bgs)); - spin_unlock(&fs_info->unused_bgs_lock); - mutex_unlock(&fs_info->reclaim_bgs_lock); - - ret += sysfs_emit_at(buf, ret, "\tneed reclaim: %s\n", - str_true_false(btrfs_zoned_should_reclaim(fs_info))); - - if (fs_info->data_reloc_bg) - ret += sysfs_emit_at(buf, ret, - "data relocation block-group: %llu\n", - fs_info->data_reloc_bg); - if (fs_info->treelog_bg) - ret += sysfs_emit_at(buf, ret, - "tree-log block-group: %llu\n", - fs_info->treelog_bg); - - spin_lock(&fs_info->zone_active_bgs_lock); - ret += sysfs_emit_at(buf, ret, "active zones:\n"); - list_for_each_entry(bg, &fs_info->zone_active_bgs, active_bg_list) { - ret += sysfs_emit_at(buf, ret, - "\tstart: %llu, wp: %llu used: %llu, reserved: %llu, unusable: %llu\n", - bg->start, bg->alloc_offset, bg->used, - bg->reserved, bg->zone_unusable); - } - spin_unlock(&fs_info->zone_active_bgs_lock); - return ret; -} -BTRFS_ATTR(, zoned_stats, btrfs_zoned_stats_show); - static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { @@ -1651,7 +1600,6 @@ static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(, bg_reclaim_threshold), BTRFS_ATTR_PTR(, commit_stats), BTRFS_ATTR_PTR(, temp_fsid), - BTRFS_ATTR_PTR(, zoned_stats), #ifdef CONFIG_BTRFS_EXPERIMENTAL BTRFS_ATTR_PTR(, offload_csum), #endif diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 0b9f25dd1a68..aabf825e8d7b 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -1059,6 +1059,7 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, if (out_stripe_len != BTRFS_STRIPE_LEN) { test_err("calculated stripe length doesn't match"); + ret = -EINVAL; goto out; } @@ -1066,12 +1067,14 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, for (i = 0; i < out_ndaddrs; i++) test_msg("mapped %llu", logical[i]); test_err("unexpected number of mapped addresses: %d", out_ndaddrs); + ret = -EINVAL; goto out; } for (i = 0; i < out_ndaddrs; i++) { if (logical[i] != test->mapped_logical[i]) { test_err("unexpected logical address mapped"); + ret = -EINVAL; goto out; } } diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index e9124605974b..0fcc31beeffe 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -517,11 +517,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) tmp_root->root_key.objectid = BTRFS_FS_TREE_OBJECTID; root->fs_info->fs_root = tmp_root; ret = btrfs_insert_fs_root(root->fs_info, tmp_root); + btrfs_put_root(tmp_root); if (ret) { test_err("couldn't insert fs root %d", ret); goto out; } - btrfs_put_root(tmp_root); tmp_root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(tmp_root)) { @@ -532,11 +532,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID; ret = btrfs_insert_fs_root(root->fs_info, tmp_root); + btrfs_put_root(tmp_root); if (ret) { - test_err("couldn't insert fs root %d", ret); + test_err("couldn't insert subvolume root %d", ret); goto out; } - btrfs_put_root(tmp_root); test_msg("running qgroup tests"); ret = test_no_shared_qgroup(root, sectorsize, nodesize); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 05ee4391c83a..bd03f465e2d3 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -520,13 +520,14 @@ static inline int is_transaction_blocked(struct btrfs_transaction *trans) * when this is done, it is safe to start a new transaction, but the current * transaction might not be fully on disk. */ -static void wait_current_trans(struct btrfs_fs_info *fs_info) +static void wait_current_trans(struct btrfs_fs_info *fs_info, unsigned int type) { struct btrfs_transaction *cur_trans; spin_lock(&fs_info->trans_lock); cur_trans = fs_info->running_transaction; - if (cur_trans && is_transaction_blocked(cur_trans)) { + if (cur_trans && is_transaction_blocked(cur_trans) && + (btrfs_blocked_trans_types[cur_trans->state] & type)) { refcount_inc(&cur_trans->use_count); spin_unlock(&fs_info->trans_lock); @@ -701,12 +702,12 @@ again: sb_start_intwrite(fs_info->sb); if (may_wait_transaction(fs_info, type)) - wait_current_trans(fs_info); + wait_current_trans(fs_info, type); do { ret = join_transaction(fs_info, type); if (ret == -EBUSY) { - wait_current_trans(fs_info); + wait_current_trans(fs_info, type); if (unlikely(type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART)) ret = -ENOENT; @@ -1003,7 +1004,7 @@ out: void btrfs_throttle(struct btrfs_fs_info *fs_info) { - wait_current_trans(fs_info); + wait_current_trans(fs_info, TRANS_START); } bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 31edc93a383e..6cffcf0c3e7a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -190,7 +190,7 @@ static void do_abort_log_replay(struct walk_control *wc, const char *function, btrfs_abort_transaction(wc->trans, error); - if (wc->subvol_path->nodes[0]) { + if (wc->subvol_path && wc->subvol_path->nodes[0]) { btrfs_crit(fs_info, "subvolume (root %llu) leaf currently being processed:", btrfs_root_id(wc->root)); @@ -2798,7 +2798,7 @@ static int replay_one_buffer(struct extent_buffer *eb, nritems = btrfs_header_nritems(eb); for (wc->log_slot = 0; wc->log_slot < nritems; wc->log_slot++) { - struct btrfs_inode_item *inode_item; + struct btrfs_inode_item *inode_item = NULL; btrfs_item_key_to_cpu(eb, &wc->log_key, wc->log_slot); @@ -6341,10 +6341,8 @@ again: * and no keys greater than that, so bail out. */ break; - } else if ((min_key->type == BTRFS_INODE_REF_KEY || - min_key->type == BTRFS_INODE_EXTREF_KEY) && - (inode->generation == trans->transid || - ctx->logging_conflict_inodes)) { + } else if (min_key->type == BTRFS_INODE_REF_KEY || + min_key->type == BTRFS_INODE_EXTREF_KEY) { u64 other_ino = 0; u64 other_parent = 0; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 13c514684cfb..8a08412f3529 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1364,7 +1364,9 @@ struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev, (bytenr + BTRFS_SUPER_INFO_SIZE) >> PAGE_SHIFT); } + filemap_invalidate_lock(mapping); page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); + filemap_invalidate_unlock(mapping); if (IS_ERR(page)) return ERR_CAST(page); @@ -7257,6 +7259,7 @@ static int read_one_dev(struct extent_buffer *leaf, return -EINVAL; } } + set_bit(BTRFS_DEV_STATE_ITEM_FOUND, &device->dev_state); set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && !test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { @@ -8083,6 +8086,45 @@ int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info) } /* + * Ensure that all devices registered in the fs have their device items in the + * chunk tree. + * + * Return true if unexpected device is found. + * Return false otherwise. + */ +bool btrfs_verify_dev_items(const struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *seed_devs; + struct btrfs_device *dev; + bool ret = false; + + mutex_lock(&uuid_mutex); + list_for_each_entry(dev, &fs_info->fs_devices->devices, dev_list) { + if (!test_bit(BTRFS_DEV_STATE_ITEM_FOUND, &dev->dev_state)) { + btrfs_err(fs_info, + "devid %llu path %s is registered but not found in chunk tree", + dev->devid, btrfs_dev_name(dev)); + ret = true; + } + } + list_for_each_entry(seed_devs, &fs_info->fs_devices->seed_list, seed_list) { + list_for_each_entry(dev, &seed_devs->devices, dev_list) { + if (!test_bit(BTRFS_DEV_STATE_ITEM_FOUND, &dev->dev_state)) { + btrfs_err(fs_info, + "devid %llu path %s is registered but not found in chunk tree", + dev->devid, btrfs_dev_name(dev)); + ret = true; + } + } + } + mutex_unlock(&uuid_mutex); + if (ret) + btrfs_err(fs_info, +"remove the above devices or use 'btrfs device scan --forget <dev>' to unregister them before mount"); + return ret; +} + +/* * Check whether the given block group or device is pinned by any inode being * used as a swapfile. */ diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 34b854c1a303..f20abeb16bce 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -100,6 +100,9 @@ enum btrfs_raid_types { #define BTRFS_DEV_STATE_FLUSH_SENT (4) #define BTRFS_DEV_STATE_NO_READA (5) +/* Set when the device item is found in chunk tree, used to catch unexpected registered device. */ +#define BTRFS_DEV_STATE_ITEM_FOUND (7) + /* Special value encoding failure to write primary super block. */ #define BTRFS_SUPER_PRIMARY_WRITE_ERROR (INT_MAX / 2) @@ -893,6 +896,7 @@ enum btrfs_raid_types __attribute_const__ btrfs_bg_flags_to_raid_index(u64 flags int btrfs_bg_type_to_factor(u64 flags); const char *btrfs_bg_type_to_raid_name(u64 flags); int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info); +bool btrfs_verify_dev_items(const struct btrfs_fs_info *fs_info); bool btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical); bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr); diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 6caba8be7c84..10ed48d4a846 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -139,6 +139,7 @@ static int copy_data_into_buffer(struct address_space *mapping, data_in = kmap_local_folio(folio, offset); memcpy(workspace->buf + cur - filepos, data_in, copy_length); kunmap_local(data_in); + folio_put(folio); cur += copy_length; } return 0; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 86d7aa594ea9..804588524cd5 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -2214,6 +2214,7 @@ const struct file_operations ceph_dir_fops = { .fsync = ceph_fsync, .lock = ceph_lock, .flock = ceph_flock, + .setlease = simple_nosetlease, }; const struct file_operations ceph_snapdir_fops = { @@ -2221,6 +2222,7 @@ const struct file_operations ceph_snapdir_fops = { .llseek = ceph_dir_llseek, .open = ceph_open, .release = ceph_release, + .setlease = simple_nosetlease, }; const struct inode_operations ceph_dir_iops = { diff --git a/fs/dcache.c b/fs/dcache.c index dc2fff4811d1..66dd1bb830d1 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1104,6 +1104,16 @@ struct dentry *d_find_alias_rcu(struct inode *inode) return de; } +/** + * d_dispose_if_unused - move unreferenced dentries to shrink list + * @dentry: dentry in question + * @dispose: head of shrink list + * + * If dentry has no external references, move it to shrink list. + * + * NOTE!!! The caller is responsible for preventing eviction of the dentry by + * holding dentry->d_inode->i_lock or equivalent. + */ void d_dispose_if_unused(struct dentry *dentry, struct list_head *dispose) { spin_lock(&dentry->d_lock); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 3978248247dc..8ab014db3e03 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -533,6 +533,7 @@ static struct dentry *ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, fsstack_copy_inode_size(dir, lower_dir); set_nlink(dir, lower_dir->i_nlink); out: + dput(lower_dir_dentry); end_creating(lower_dentry); if (d_really_is_negative(dentry)) d_drop(dentry); @@ -584,7 +585,7 @@ ecryptfs_mknod(struct mnt_idmap *idmap, struct inode *dir, fsstack_copy_attr_times(dir, lower_dir); fsstack_copy_inode_size(dir, lower_dir); out: - end_removing(lower_dentry); + end_creating(lower_dentry); if (d_really_is_negative(dentry)) d_drop(dentry); return rc; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 937a215f626c..5136cda5972a 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -644,14 +644,21 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) * fs contexts (including its own) due to self-controlled RO * accesses/contexts and no side-effect changes that need to * context save & restore so it can reuse the current thread - * context. However, it still needs to bump `s_stack_depth` to - * avoid kernel stack overflow from nested filesystems. + * context. + * However, we still need to prevent kernel stack overflow due + * to filesystem nesting: just ensure that s_stack_depth is 0 + * to disallow mounting EROFS on stacked filesystems. + * Note: s_stack_depth is not incremented here for now, since + * EROFS is the only fs supporting file-backed mounts for now. + * It MUST change if another fs plans to support them, which + * may also require adjusting FILESYSTEM_MAX_STACK_DEPTH. */ if (erofs_is_fileio_mode(sbi)) { - sb->s_stack_depth = - file_inode(sbi->dif0.file)->i_sb->s_stack_depth + 1; - if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { - erofs_err(sb, "maximum fs stacking depth exceeded"); + inode = file_inode(sbi->dif0.file); + if ((inode->i_sb->s_op == &erofs_sops && + !inode->i_sb->s_bdev) || + inode->i_sb->s_stack_depth) { + erofs_err(sb, "file-backed mounts cannot be applied to stacked fses"); return -ENOTBLK; } } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 0550fd30fd10..635fb8a52e0c 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -393,9 +393,11 @@ out: repair_branches: ret2 = 0; + ext4_double_down_write_data_sem(orig_inode, donor_inode); r_len = ext4_swap_extents(handle, donor_inode, orig_inode, mext->donor_lblk, orig_map->m_lblk, *m_len, 0, &ret2); + ext4_double_up_write_data_sem(orig_inode, donor_inode); if (ret2 || r_len != *m_len) { ext4_error_inode_block(orig_inode, (sector_t)(orig_map->m_lblk), EIO, "Unable to copy data block, data will be lost!"); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 2e02efbddaac..4ed8ddf2a60b 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1037,6 +1037,7 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, ext4_error_inode(ea_inode, __func__, __LINE__, 0, "EA inode %lu ref wraparound: ref_count=%lld ref_change=%d", ea_inode->i_ino, ref_count, ref_change); + brelse(iloc.bh); ret = -EFSCORRUPTED; goto out; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6800886c4d10..5444fc706ac7 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2492,7 +2492,9 @@ static void wakeup_dirtytime_writeback(struct work_struct *w) wb_wakeup(wb); } rcu_read_unlock(); - schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); + if (dirtytime_expire_interval) + schedule_delayed_work(&dirtytime_work, + round_jiffies_relative(dirtytime_expire_interval * HZ)); } static int dirtytime_interval_handler(const struct ctl_table *table, int write, @@ -2501,8 +2503,12 @@ static int dirtytime_interval_handler(const struct ctl_table *table, int write, int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (ret == 0 && write) - mod_delayed_work(system_percpu_wq, &dirtytime_work, 0); + if (ret == 0 && write) { + if (dirtytime_expire_interval) + mod_delayed_work(system_percpu_wq, &dirtytime_work, 0); + else + cancel_delayed_work_sync(&dirtytime_work); + } return ret; } @@ -2519,7 +2525,9 @@ static const struct ctl_table vm_fs_writeback_table[] = { static int __init start_dirtytime_writeback(void) { - schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); + if (dirtytime_expire_interval) + schedule_delayed_work(&dirtytime_work, + round_jiffies_relative(dirtytime_expire_interval * HZ)); register_sysctl_init("vm", vm_fs_writeback_table); return 0; } @@ -2750,8 +2758,13 @@ static void wait_sb_inodes(struct super_block *sb) * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. + * + * If the mapping does not have data integrity semantics, + * there's no need to wait for the writeout to complete, as the + * mapping cannot guarantee that data is persistently stored. */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) || + mapping_no_data_integrity(mapping)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 4b6b3d2758ff..3927cb069236 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -32,9 +32,9 @@ struct dentry_bucket { spinlock_t lock; }; -#define HASH_BITS 5 -#define HASH_SIZE (1 << HASH_BITS) -static struct dentry_bucket dentry_hash[HASH_SIZE]; +#define FUSE_HASH_BITS 5 +#define FUSE_HASH_SIZE (1 << FUSE_HASH_BITS) +static struct dentry_bucket dentry_hash[FUSE_HASH_SIZE]; struct delayed_work dentry_tree_work; /* Minimum invalidation work queue frequency */ @@ -83,7 +83,7 @@ MODULE_PARM_DESC(inval_wq, static inline struct dentry_bucket *get_dentry_bucket(struct dentry *dentry) { - int i = hash_ptr(dentry, HASH_BITS); + int i = hash_ptr(dentry, FUSE_HASH_BITS); return &dentry_hash[i]; } @@ -164,25 +164,31 @@ static void fuse_dentry_tree_work(struct work_struct *work) struct rb_node *node; int i; - for (i = 0; i < HASH_SIZE; i++) { + for (i = 0; i < FUSE_HASH_SIZE; i++) { spin_lock(&dentry_hash[i].lock); node = rb_first(&dentry_hash[i].tree); while (node) { fd = rb_entry(node, struct fuse_dentry, node); - if (time_after64(get_jiffies_64(), fd->time)) { - rb_erase(&fd->node, &dentry_hash[i].tree); - RB_CLEAR_NODE(&fd->node); + if (!time_before64(fd->time, get_jiffies_64())) + break; + + rb_erase(&fd->node, &dentry_hash[i].tree); + RB_CLEAR_NODE(&fd->node); + spin_lock(&fd->dentry->d_lock); + /* If dentry is still referenced, let next dput release it */ + fd->dentry->d_flags |= DCACHE_OP_DELETE; + spin_unlock(&fd->dentry->d_lock); + d_dispose_if_unused(fd->dentry, &dispose); + if (need_resched()) { spin_unlock(&dentry_hash[i].lock); - d_dispose_if_unused(fd->dentry, &dispose); cond_resched(); spin_lock(&dentry_hash[i].lock); - } else - break; + } node = rb_first(&dentry_hash[i].tree); } spin_unlock(&dentry_hash[i].lock); - shrink_dentry_list(&dispose); } + shrink_dentry_list(&dispose); if (inval_wq) schedule_delayed_work(&dentry_tree_work, @@ -213,7 +219,7 @@ void fuse_dentry_tree_init(void) { int i; - for (i = 0; i < HASH_SIZE; i++) { + for (i = 0; i < FUSE_HASH_SIZE; i++) { spin_lock_init(&dentry_hash[i].lock); dentry_hash[i].tree = RB_ROOT; } @@ -227,7 +233,7 @@ void fuse_dentry_tree_cleanup(void) inval_wq = 0; cancel_delayed_work_sync(&dentry_tree_work); - for (i = 0; i < HASH_SIZE; i++) + for (i = 0; i < FUSE_HASH_SIZE; i++) WARN_ON_ONCE(!RB_EMPTY_ROOT(&dentry_hash[i].tree)); } @@ -479,18 +485,12 @@ static int fuse_dentry_init(struct dentry *dentry) return 0; } -static void fuse_dentry_prune(struct dentry *dentry) +static void fuse_dentry_release(struct dentry *dentry) { struct fuse_dentry *fd = dentry->d_fsdata; if (!RB_EMPTY_NODE(&fd->node)) fuse_dentry_tree_del_node(dentry); -} - -static void fuse_dentry_release(struct dentry *dentry) -{ - struct fuse_dentry *fd = dentry->d_fsdata; - kfree_rcu(fd, rcu); } @@ -527,7 +527,6 @@ const struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, .d_delete = fuse_dentry_delete, .d_init = fuse_dentry_init, - .d_prune = fuse_dentry_prune, .d_release = fuse_dentry_release, .d_automount = fuse_dentry_automount, }; @@ -1584,8 +1583,8 @@ int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid, { int err = -ENOTDIR; struct inode *parent; - struct dentry *dir; - struct dentry *entry; + struct dentry *dir = NULL; + struct dentry *entry = NULL; parent = fuse_ilookup(fc, parent_nodeid, NULL); if (!parent) @@ -1598,11 +1597,19 @@ int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid, dir = d_find_alias(parent); if (!dir) goto put_parent; - - entry = start_removing_noperm(dir, name); - dput(dir); - if (IS_ERR(entry)) - goto put_parent; + while (!entry) { + struct dentry *child = try_lookup_noperm(name, dir); + if (!child || IS_ERR(child)) + goto put_parent; + entry = start_removing_dentry(dir, child); + dput(child); + if (IS_ERR(entry)) + goto put_parent; + if (!d_same_name(entry, dir, name)) { + end_removing(entry); + entry = NULL; + } + } fuse_dir_changed(parent); if (!(flags & FUSE_EXPIRE_ONLY)) @@ -1640,6 +1647,7 @@ int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid, end_removing(entry); put_parent: + dput(dir); iput(parent); return err; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 01bc894e9c2b..3b2a171e652f 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3200,8 +3200,10 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags) inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; - if (fc->writeback_cache) + if (fc->writeback_cache) { mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data); + mapping_set_no_data_integrity(&inode->i_data); + } INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index b2d23c98c996..86376f0dbf3a 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1608,6 +1608,7 @@ const struct file_operations gfs2_dir_fops = { .lock = gfs2_lock, .flock = gfs2_flock, .llseek = default_llseek, + .setlease = simple_nosetlease, .fop_flags = FOP_ASYNC_LOCK, }; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 97ebe457c00a..d27a0b1080a9 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -484,7 +484,7 @@ static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs) new = bio_alloc(prev->bi_bdev, nr_iovecs, prev->bi_opf, GFP_NOIO); bio_clone_blkg_association(new, prev); new->bi_iter.bi_sector = bio_end_sector(prev); - bio_chain(prev, new); + bio_chain(new, prev); submit_bio(prev); return new; } diff --git a/fs/inode.c b/fs/inode.c index 521383223d8a..379f4c19845c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1593,6 +1593,9 @@ EXPORT_SYMBOL(igrab); * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test + * @isnew: return argument telling whether I_NEW was set when + * the inode was found in hash (the caller needs to + * wait for I_NEW to clear) * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index e5c1ca440d93..6beb876658c0 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -832,7 +832,7 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, if (!mapping_large_folio_support(iter->inode->i_mapping)) len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); - if (iter->fbatch) { + if (iter->iomap.flags & IOMAP_F_FOLIO_BATCH) { struct folio *folio = folio_batch_next(iter->fbatch); if (!folio) @@ -851,6 +851,7 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, } folio_get(folio); + folio_wait_stable(folio); return folio; } @@ -929,7 +930,7 @@ static int iomap_write_begin(struct iomap_iter *iter, * process so return and let the caller iterate and refill the batch. */ if (!folio) { - WARN_ON_ONCE(!iter->fbatch); + WARN_ON_ONCE(!(iter->iomap.flags & IOMAP_F_FOLIO_BATCH)); return 0; } @@ -1544,23 +1545,39 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero, return status; } -loff_t +/** + * iomap_fill_dirty_folios - fill a folio batch with dirty folios + * @iter: Iteration structure + * @start: Start offset of range. Updated based on lookup progress. + * @end: End offset of range + * @iomap_flags: Flags to set on the associated iomap to track the batch. + * + * Returns the folio count directly. Also returns the associated control flag if + * the the batch lookup is performed and the expected offset of a subsequent + * lookup via out params. The caller is responsible to set the flag on the + * associated iomap. + */ +unsigned int iomap_fill_dirty_folios( struct iomap_iter *iter, - loff_t offset, - loff_t length) + loff_t *start, + loff_t end, + unsigned int *iomap_flags) { struct address_space *mapping = iter->inode->i_mapping; - pgoff_t start = offset >> PAGE_SHIFT; - pgoff_t end = (offset + length - 1) >> PAGE_SHIFT; + pgoff_t pstart = *start >> PAGE_SHIFT; + pgoff_t pend = (end - 1) >> PAGE_SHIFT; + unsigned int count; - iter->fbatch = kmalloc(sizeof(struct folio_batch), GFP_KERNEL); - if (!iter->fbatch) - return offset + length; - folio_batch_init(iter->fbatch); + if (!iter->fbatch) { + *start = end; + return 0; + } - filemap_get_folios_dirty(mapping, &start, end, iter->fbatch); - return (start << PAGE_SHIFT); + count = filemap_get_folios_dirty(mapping, &pstart, pend, iter->fbatch); + *start = (pstart << PAGE_SHIFT); + *iomap_flags |= IOMAP_F_FOLIO_BATCH; + return count; } EXPORT_SYMBOL_GPL(iomap_fill_dirty_folios); @@ -1569,17 +1586,21 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private) { + struct folio_batch fbatch; struct iomap_iter iter = { .inode = inode, .pos = pos, .len = len, .flags = IOMAP_ZERO, .private = private, + .fbatch = &fbatch, }; struct address_space *mapping = inode->i_mapping; int ret; bool range_dirty; + folio_batch_init(&fbatch); + /* * To avoid an unconditional flush, check pagecache state and only flush * if dirty and the fs returns a mapping that might convert on @@ -1590,11 +1611,11 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, while ((ret = iomap_iter(&iter, ops)) > 0) { const struct iomap *srcmap = iomap_iter_srcmap(&iter); - if (WARN_ON_ONCE(iter.fbatch && + if (WARN_ON_ONCE((iter.iomap.flags & IOMAP_F_FOLIO_BATCH) && srcmap->type != IOMAP_UNWRITTEN)) return -EIO; - if (!iter.fbatch && + if (!(iter.iomap.flags & IOMAP_F_FOLIO_BATCH) && (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)) { s64 status; diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index 8692e5e41c6d..c04796f6e57f 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -8,10 +8,10 @@ static inline void iomap_iter_reset_iomap(struct iomap_iter *iter) { - if (iter->fbatch) { + if (iter->iomap.flags & IOMAP_F_FOLIO_BATCH) { folio_batch_release(iter->fbatch); - kfree(iter->fbatch); - iter->fbatch = NULL; + folio_batch_reinit(iter->fbatch); + iter->iomap.flags &= ~IOMAP_F_FOLIO_BATCH; } iter->status = 0; diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index bb815a002984..3ab3f0ff7ebb 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -2,10 +2,10 @@ * JFFS2 -- Journalling Flash File System, Version 2. * * Copyright © 2001-2007 Red Hat, Inc. - * Copyright © 2004 Thomas Gleixner <tglx@linutronix.de> + * Copyright © 2004 Thomas Gleixner <tglx@kernel.org> * * Created by David Woodhouse <dwmw2@infradead.org> - * Modified debugged and enhanced by Thomas Gleixner <tglx@linutronix.de> + * Modified debugged and enhanced by Thomas Gleixner <tglx@kernel.org> * * For licensing information, see the file 'LICENCE' in this directory. * diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 109e5caae8c7..4b6f18d97734 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -97,7 +97,6 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; - struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST4 called\n"); @@ -107,7 +106,6 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; - test_owner = argp->lock.fl.c.flc_owner; /* Now check for conflicting locks */ resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock); @@ -116,7 +114,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) else dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); - nlmsvc_put_lockowner(test_owner); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 3a3d05cfe09a..6bce19fd024c 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -633,7 +633,13 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, } mode = lock_to_openmode(&lock->fl); - error = vfs_test_lock(file->f_file[mode], &lock->fl); + locks_init_lock(&conflock->fl); + /* vfs_test_lock only uses start, end, and owner, but tests flc_file */ + conflock->fl.c.flc_file = lock->fl.c.flc_file; + conflock->fl.fl_start = lock->fl.fl_start; + conflock->fl.fl_end = lock->fl.fl_end; + conflock->fl.c.flc_owner = lock->fl.c.flc_owner; + error = vfs_test_lock(file->f_file[mode], &conflock->fl); if (error) { /* We can't currently deal with deferred test requests */ if (error == FILE_LOCK_DEFERRED) @@ -643,22 +649,19 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } - if (lock->fl.c.flc_type == F_UNLCK) { + if (conflock->fl.c.flc_type == F_UNLCK) { ret = nlm_granted; goto out; } dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n", - lock->fl.c.flc_type, (long long)lock->fl.fl_start, - (long long)lock->fl.fl_end); + conflock->fl.c.flc_type, (long long)conflock->fl.fl_start, + (long long)conflock->fl.fl_end); conflock->caller = "somehost"; /* FIXME */ conflock->len = strlen(conflock->caller); conflock->oh.len = 0; /* don't return OH info */ - conflock->svid = lock->fl.c.flc_pid; - conflock->fl.c.flc_type = lock->fl.c.flc_type; - conflock->fl.fl_start = lock->fl.fl_start; - conflock->fl.fl_end = lock->fl.fl_end; - locks_release_private(&lock->fl); + conflock->svid = conflock->fl.c.flc_pid; + locks_release_private(&conflock->fl); ret = nlm_lck_denied; out: diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index f53d5177f267..5817ef272332 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -117,7 +117,6 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; - struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST called\n"); @@ -127,8 +126,6 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; - test_owner = argp->lock.fl.c.flc_owner; - /* Now check for conflicting locks */ resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock)); @@ -138,7 +135,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) dprintk("lockd: TEST status %d vers %d\n", ntohl(resp->status), rqstp->rq_vers); - nlmsvc_put_lockowner(test_owner); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; diff --git a/fs/locks.c b/fs/locks.c index 9f565802a88c..7ea949d7ff45 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -369,10 +369,19 @@ locks_dispose_list(struct list_head *dispose) while (!list_empty(dispose)) { flc = list_first_entry(dispose, struct file_lock_core, flc_list); list_del_init(&flc->flc_list); - if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) - locks_free_lease(file_lease(flc)); - else - locks_free_lock(file_lock(flc)); + locks_free_lock(file_lock(flc)); + } +} + +static void +lease_dispose_list(struct list_head *dispose) +{ + struct file_lock_core *flc; + + while (!list_empty(dispose)) { + flc = list_first_entry(dispose, struct file_lock_core, flc_list); + list_del_init(&flc->flc_list); + locks_free_lease(file_lease(flc)); } } @@ -576,10 +585,50 @@ lease_setup(struct file_lease *fl, void **priv) __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } +/** + * lease_open_conflict - see if the given file points to an inode that has + * an existing open that would conflict with the + * desired lease. + * @filp: file to check + * @arg: type of lease that we're trying to acquire + * + * Check to see if there's an existing open fd on this file that would + * conflict with the lease we're trying to set. + */ +static int +lease_open_conflict(struct file *filp, const int arg) +{ + struct inode *inode = file_inode(filp); + int self_wcount = 0, self_rcount = 0; + + if (arg == F_RDLCK) + return inode_is_open_for_write(inode) ? -EAGAIN : 0; + else if (arg != F_WRLCK) + return 0; + + /* + * Make sure that only read/write count is from lease requestor. + * Note that this will result in denying write leases when i_writecount + * is negative, which is what we want. (We shouldn't grant write leases + * on files open for execution.) + */ + if (filp->f_mode & FMODE_WRITE) + self_wcount = 1; + else if (filp->f_mode & FMODE_READ) + self_rcount = 1; + + if (atomic_read(&inode->i_writecount) != self_wcount || + atomic_read(&inode->i_readcount) != self_rcount) + return -EAGAIN; + + return 0; +} + static const struct lease_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, + .lm_open_conflict = lease_open_conflict, }; /* @@ -1620,7 +1669,7 @@ restart: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->c.flc_wait, list_empty(&new_fl->c.flc_blocked_member), break_time); @@ -1643,7 +1692,7 @@ restart: out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); free_lock: locks_free_lease(new_fl); return error; @@ -1727,7 +1776,7 @@ static int __fcntl_getlease(struct file *filp, unsigned int flavor) spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); } return type; } @@ -1745,52 +1794,6 @@ int fcntl_getdeleg(struct file *filp, struct delegation *deleg) return 0; } -/** - * check_conflicting_open - see if the given file points to an inode that has - * an existing open that would conflict with the - * desired lease. - * @filp: file to check - * @arg: type of lease that we're trying to acquire - * @flags: current lock flags - * - * Check to see if there's an existing open fd on this file that would - * conflict with the lease we're trying to set. - */ -static int -check_conflicting_open(struct file *filp, const int arg, int flags) -{ - struct inode *inode = file_inode(filp); - int self_wcount = 0, self_rcount = 0; - - if (flags & FL_LAYOUT) - return 0; - if (flags & FL_DELEG) - /* We leave these checks to the caller */ - return 0; - - if (arg == F_RDLCK) - return inode_is_open_for_write(inode) ? -EAGAIN : 0; - else if (arg != F_WRLCK) - return 0; - - /* - * Make sure that only read/write count is from lease requestor. - * Note that this will result in denying write leases when i_writecount - * is negative, which is what we want. (We shouldn't grant write leases - * on files open for execution.) - */ - if (filp->f_mode & FMODE_WRITE) - self_wcount = 1; - else if (filp->f_mode & FMODE_READ) - self_rcount = 1; - - if (atomic_read(&inode->i_writecount) != self_wcount || - atomic_read(&inode->i_readcount) != self_rcount) - return -EAGAIN; - - return 0; -} - static int generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv) { @@ -1827,7 +1830,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); - error = check_conflicting_open(filp, arg, lease->c.flc_flags); + error = lease->fl_lmops->lm_open_conflict(filp, arg); if (error) goto out; @@ -1884,7 +1887,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr * precedes these checks. */ smp_mb(); - error = check_conflicting_open(filp, arg, lease->c.flc_flags); + error = lease->fl_lmops->lm_open_conflict(filp, arg); if (error) { locks_unlink_lock_ctx(&lease->c); goto out; @@ -1896,7 +1899,7 @@ out_setup: out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); if (!error && !my_fl) @@ -1932,7 +1935,7 @@ static int generic_delete_lease(struct file *filp, void *owner) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); return error; } @@ -2236,13 +2239,21 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for - * @fl: The lock to test; also used to hold result + * @fl: The byte-range in the file to test; also used to hold result * + * On entry, @fl does not contain a lock, but identifies a range (fl_start, fl_end) + * in the file (c.flc_file), and an owner (c.flc_owner) for whom existing locks + * should be ignored. c.flc_type and c.flc_flags are ignored. + * Both fl_lmops and fl_ops in @fl must be NULL. * Returns -ERRNO on failure. Indicates presence of conflicting lock by - * setting conf->fl_type to something other than F_UNLCK. + * setting fl->fl_type to something other than F_UNLCK. + * + * If vfs_test_lock() does find a lock and return it, the caller must + * use locks_free_lock() or locks_release_private() on the returned lock. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { + WARN_ON_ONCE(fl->fl_ops || fl->fl_lmops); WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); @@ -2727,7 +2738,7 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); } /* diff --git a/fs/namei.c b/fs/namei.c index bf0f66f0e9b9..cf16b6822dd3 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -830,11 +830,9 @@ static inline bool legitimize_path(struct nameidata *nd, static bool legitimize_links(struct nameidata *nd) { int i; - if (unlikely(nd->flags & LOOKUP_CACHED)) { - drop_links(nd); - nd->depth = 0; - return false; - } + + VFS_BUG_ON(nd->flags & LOOKUP_CACHED); + for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { @@ -883,6 +881,11 @@ static bool try_to_unlazy(struct nameidata *nd) BUG_ON(!(nd->flags & LOOKUP_RCU)); + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + goto out1; + } if (unlikely(nd->depth && !legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) @@ -918,6 +921,11 @@ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry) int res; BUG_ON(!(nd->flags & LOOKUP_RCU)); + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + goto out2; + } if (unlikely(nd->depth && !legitimize_links(nd))) goto out2; res = __legitimize_mnt(nd->path.mnt, nd->m_seq); @@ -2836,10 +2844,11 @@ static int filename_parentat(int dfd, struct filename *name, } /** - * start_dirop - begin a create or remove dirop, performing locking and lookup + * __start_dirop - begin a create or remove dirop, performing locking and lookup * @parent: the dentry of the parent in which the operation will occur * @name: a qstr holding the name within that parent * @lookup_flags: intent and other lookup flags. + * @state: task state bitmask * * The lookup is performed and necessary locks are taken so that, on success, * the returned dentry can be operated on safely. diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index a95e7aadafd0..7a0ffa675fb1 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -137,7 +137,7 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, rreq->front_folio_order = order; fsize = PAGE_SIZE << order; fpos = folio_pos(folio); - fend = umin(fpos + fsize, rreq->i_size); + fend = fpos + fsize; trace_netfs_collect_folio(rreq, folio, fend, collected_to); diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index ab76120705e2..134d7f760a33 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -417,8 +417,10 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, d->map = bl_map_simple; d->pr_key = v->scsi.pr_key; - if (d->len == 0) - return -ENODEV; + if (d->len == 0) { + error = -ENODEV; + goto out_blkdev_put; + } ops = bdev->bd_disk->fops->pr_ops; if (!ops) { diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 2248e3ad089a..8a3857a49d84 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -149,7 +149,7 @@ static int nfs4_do_check_delegation(struct inode *inode, fmode_t type, int nfs4_have_delegation(struct inode *inode, fmode_t type, int flags) { if (S_ISDIR(inode->i_mode) && !directory_delegations) - nfs_inode_evict_delegation(inode); + nfs4_inode_set_return_delegation_on_close(inode); return nfs4_do_check_delegation(inode, type, flags, true); } @@ -581,6 +581,10 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation if (delegation == NULL) return 0; + /* Directory delegations don't require any state recovery */ + if (!S_ISREG(inode->i_mode)) + goto out_return; + if (!issync) mode |= O_NONBLOCK; /* Recall of any remaining application leases */ @@ -604,6 +608,7 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation goto out; } +out_return: err = nfs_do_return_delegation(inode, delegation, issync); out: /* Refcount matched in nfs_start_delegation_return_locked() */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 23a78a742b61..e3654f4a1b9a 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -66,6 +66,7 @@ const struct file_operations nfs_dir_operations = { .open = nfs_opendir, .release = nfs_closedir, .fsync = nfs_fsync_dir, + .setlease = simple_nosetlease, }; const struct address_space_operations nfs_dir_aops = { @@ -1440,7 +1441,8 @@ static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf) if (!dir || !nfs_verify_change_attribute(dir, verf)) return; - if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) + if (NFS_PROTO(dir)->have_delegation(dir, FMODE_READ, 0) || + (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0))) nfs_set_verifier_delegated(&verf); dentry->d_time = verf; } @@ -1465,6 +1467,49 @@ void nfs_set_verifier(struct dentry *dentry, unsigned long verf) EXPORT_SYMBOL_GPL(nfs_set_verifier); #if IS_ENABLED(CONFIG_NFS_V4) +static void nfs_clear_verifier_file(struct inode *inode) +{ + struct dentry *alias; + struct inode *dir; + + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { + spin_lock(&alias->d_lock); + dir = d_inode_rcu(alias->d_parent); + if (!dir || + !NFS_PROTO(dir)->have_delegation(dir, FMODE_READ, 0)) + nfs_unset_verifier_delegated(&alias->d_time); + spin_unlock(&alias->d_lock); + } +} + +static void nfs_clear_verifier_directory(struct inode *dir) +{ + struct dentry *this_parent; + struct dentry *dentry; + struct inode *inode; + + if (hlist_empty(&dir->i_dentry)) + return; + this_parent = + hlist_entry(dir->i_dentry.first, struct dentry, d_u.d_alias); + + spin_lock(&this_parent->d_lock); + nfs_unset_verifier_delegated(&this_parent->d_time); + dentry = d_first_child(this_parent); + hlist_for_each_entry_from(dentry, d_sib) { + if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) + continue; + inode = d_inode_rcu(dentry); + if (inode && + NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + nfs_unset_verifier_delegated(&dentry->d_time); + spin_unlock(&dentry->d_lock); + } + spin_unlock(&this_parent->d_lock); +} + /** * nfs_clear_verifier_delegated - clear the dir verifier delegation tag * @inode: pointer to inode @@ -1477,16 +1522,13 @@ EXPORT_SYMBOL_GPL(nfs_set_verifier); */ void nfs_clear_verifier_delegated(struct inode *inode) { - struct dentry *alias; - if (!inode) return; spin_lock(&inode->i_lock); - hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { - spin_lock(&alias->d_lock); - nfs_unset_verifier_delegated(&alias->d_time); - spin_unlock(&alias->d_lock); - } + if (S_ISREG(inode->i_mode)) + nfs_clear_verifier_file(inode); + else if (S_ISDIR(inode->i_mode)) + nfs_clear_verifier_directory(inode); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); @@ -1516,14 +1558,6 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, if (!nfs_dentry_verify_change(dir, dentry)) return 0; - /* - * If we have a directory delegation then we don't need to revalidate - * the directory. The delegation will either get recalled or we will - * receive a notification when it changes. - */ - if (nfs_have_directory_delegation(dir)) - return 0; - /* Revalidate nfsi->cache_change_attribute before we declare a match */ if (nfs_mapping_need_revalidate_inode(dir)) { if (rcu_walk) @@ -2217,13 +2251,6 @@ no_open: EXPORT_SYMBOL_GPL(nfs_atomic_open); static int -nfs_lookup_revalidate_delegated_parent(struct inode *dir, struct dentry *dentry, - struct inode *inode) -{ - return nfs_lookup_revalidate_done(dir, dentry, inode, 1); -} - -static int nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { @@ -2247,12 +2274,10 @@ nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, if (inode == NULL) goto full_reval; - if (nfs_verifier_is_delegated(dentry)) + if (nfs_verifier_is_delegated(dentry) || + nfs_have_directory_delegation(inode)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); - if (nfs_have_directory_delegation(dir)) - return nfs_lookup_revalidate_delegated_parent(dir, dentry, inode); - /* NFS only supports OPEN on regular files */ if (!S_ISREG(inode->i_mode)) goto full_reval; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d020aab40c64..d1c138a416cf 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -511,7 +511,8 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp) if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || current_is_kswapd() || current_is_kcompactd()) return false; - if (nfs_wb_folio(folio->mapping->host, folio) < 0) + if (nfs_wb_folio_reclaim(folio->mapping->host, folio) < 0 || + folio_test_private(folio)) return false; } return nfs_fscache_release_folio(folio, gfp); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index c55ea8fa3bfa..c2d8a13a9dbd 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -103,7 +103,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, sizeof(struct nfs4_ff_ds_version), gfp_flags); if (!ds_versions) - goto out_scratch; + goto out_err_drain_dsaddrs; for (i = 0; i < version_count; i++) { /* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) + diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 84049f3cd340..de2cce1d08f4 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -716,7 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int error = 0; kuid_t task_uid = current_fsuid(); kuid_t owner_uid = inode->i_uid; @@ -727,6 +727,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; + if (S_ISREG(inode->i_mode)) + nfs_file_block_o_direct(NFS_I(inode)); + + oldsize = i_size_read(inode); if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); @@ -774,10 +778,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) { - nfs_file_block_o_direct(NFS_I(inode)); + if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); - } fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { diff --git a/fs/nfs/io.c b/fs/nfs/io.c index d275b0a250bf..8337f0ae852d 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -84,6 +84,7 @@ nfs_start_io_write(struct inode *inode) nfs_file_block_o_direct(NFS_I(inode)); return err; } +EXPORT_SYMBOL_GPL(nfs_start_io_write); /** * nfs_end_io_write - declare that the buffered write operation is done @@ -97,6 +98,7 @@ nfs_end_io_write(struct inode *inode) { up_write(&inode->i_rwsem); } +EXPORT_SYMBOL_GPL(nfs_end_io_write); /* Call with exclusively locked inode->i_rwsem */ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode) diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index a113bfdacfd6..41fbcb3f9167 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -461,6 +461,8 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw) v = 0; total = hdr->args.count; base = hdr->args.pgbase; + pagevec += base >> PAGE_SHIFT; + base &= ~PAGE_MASK; while (total && v < hdr->page_array.npages) { len = min_t(size_t, total, PAGE_SIZE - base); bvec_set_page(&iocb->bvec[v], *pagevec, len, base); @@ -618,7 +620,6 @@ static void nfs_local_call_read(struct work_struct *work) struct nfs_local_kiocb *iocb = container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; - bool force_done = false; ssize_t status; int n_iters; @@ -637,13 +638,13 @@ static void nfs_local_call_read(struct work_struct *work) scoped_with_creds(filp->f_cred) status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]); - if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) - force_done = true; /* Partial read */ - if (nfs_local_pgio_done(iocb, status, force_done)) { - nfs_local_read_iocb_done(iocb); - break; - } + if (status == -EIOCBQUEUED) + continue; + /* Break on completion, errors, or short reads */ + if (nfs_local_pgio_done(iocb, status, false) || status < 0 || + (size_t)status < iov_iter_count(&iocb->iters[i])) { + nfs_local_read_iocb_done(iocb); + break; } } } @@ -821,7 +822,6 @@ static void nfs_local_call_write(struct work_struct *work) container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; unsigned long old_flags = current->flags; - bool force_done = false; ssize_t status; int n_iters; @@ -843,13 +843,13 @@ static void nfs_local_call_write(struct work_struct *work) scoped_with_creds(filp->f_cred) status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]); - if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) - force_done = true; /* Partial write */ - if (nfs_local_pgio_done(iocb, status, force_done)) { - nfs_local_write_iocb_done(iocb); - break; - } + if (status == -EIOCBQUEUED) + continue; + /* Break on completion, errors, or short writes */ + if (nfs_local_pgio_done(iocb, status, false) || status < 0 || + (size_t)status < iov_iter_count(&iocb->iters[i])) { + nfs_local_write_iocb_done(iocb); + break; } } file_end_write(filp); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index d537fb0c230e..c08520828708 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -114,7 +114,6 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, exception.inode = inode; exception.state = lock->open_context->state; - nfs_file_block_o_direct(NFS_I(inode)); err = nfs_sync_inode(inode); if (err) goto out; @@ -138,13 +137,17 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); @@ -155,7 +158,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -170,7 +173,9 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) @@ -179,7 +184,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_DEALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -189,14 +194,17 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) { nfs_truncate_last_folio(inode->i_mapping, oldsize, @@ -205,7 +213,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) } else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE; - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -416,7 +424,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; - loff_t oldsize_dst = i_size_read(dst_inode); + loff_t oldsize_dst; size_t count = args->count; ssize_t status; @@ -461,6 +469,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, &src_lock->open_context->state->flags); set_bit(NFS_CLNT_DST_SSC_COPY_STATE, &dst_lock->open_context->state->flags); + oldsize_dst = i_size_read(dst_inode); status = nfs4_call_sync(dst_server->client, dst_server, &msg, &args->seq_args, &res->seq_res, 0); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 7317f26892c5..7f43e890d356 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -431,8 +431,6 @@ void nfs42_ssc_unregister_ops(void) static int nfs4_setlease(struct file *file, int arg, struct file_lease **lease, void **priv) { - if (!S_ISREG(file_inode(file)->i_mode)) - return -EINVAL; return nfs4_proc_setlease(file, arg, lease, priv); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ec1ce593dea2..a0885ae55abc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3894,8 +3894,8 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->res.seqid = calldata->arg.seqid; calldata->res.server = server; calldata->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT; - calldata->lr.roc = pnfs_roc(state->inode, - &calldata->lr.arg, &calldata->lr.res, msg.rpc_cred); + calldata->lr.roc = pnfs_roc(state->inode, &calldata->lr.arg, + &calldata->lr.res, msg.rpc_cred, wait); if (calldata->lr.roc) { calldata->arg.lr_args = &calldata->lr.arg; calldata->res.lr_res = &calldata->lr.res; @@ -4494,6 +4494,25 @@ static bool should_request_dir_deleg(struct inode *inode) } #endif /* CONFIG_NFS_V4_1 */ +static void nfs4_call_getattr_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + nfs4_setup_sequence(data->seq_server->nfs_client, data->seq_args, + data->seq_res, task); +} + +static void nfs4_call_getattr_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + + nfs4_sequence_process(task, data->seq_res); +} + +static const struct rpc_call_ops nfs4_call_getattr_ops = { + .rpc_call_prepare = nfs4_call_getattr_prepare, + .rpc_call_done = nfs4_call_getattr_done, +}; + static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct inode *inode) { @@ -4511,16 +4530,26 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_argp = &args, .rpc_resp = &res, }; + struct nfs4_call_sync_data data = { + .seq_server = server, + .seq_args = &args.seq_args, + .seq_res = &res.seq_res, + }; + struct rpc_task_setup task_setup = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_call_getattr_ops, + .callback_data = &data, + }; struct nfs4_gdd_res gdd_res; - unsigned short task_flags = 0; int status; if (nfs4_has_session(server->nfs_client)) - task_flags = RPC_TASK_MOVEABLE; + task_setup.flags = RPC_TASK_MOVEABLE; /* Is this is an attribute revalidation, subject to softreval? */ if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) - task_flags |= RPC_TASK_TIMEOUT; + task_setup.flags |= RPC_TASK_TIMEOUT; args.get_dir_deleg = should_request_dir_deleg(inode); if (args.get_dir_deleg) @@ -4530,22 +4559,24 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, nfs_fattr_init(fattr); nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); - status = nfs4_do_call_sync(server->client, server, &msg, - &args.seq_args, &res.seq_res, task_flags); + status = nfs4_call_sync_custom(&task_setup); + if (args.get_dir_deleg) { switch (status) { case 0: if (gdd_res.status != GDD4_OK) break; - status = nfs_inode_set_delegation( - inode, current_cred(), FMODE_READ, - &gdd_res.deleg, 0, NFS4_OPEN_DELEGATE_READ); + nfs_inode_set_delegation(inode, current_cred(), + FMODE_READ, &gdd_res.deleg, 0, + NFS4_OPEN_DELEGATE_READ); break; case -ENOTSUPP: case -EOPNOTSUPP: server->caps &= ~NFS_CAP_DIR_DELEG; } } + + nfs4_sequence_free_slot(&res.seq_res); return status; } @@ -7005,7 +7036,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->inode = nfs_igrab_and_active(inode); if (data->inode || issync) { data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, - cred); + cred, issync); if (data->lr.roc) { data->args.lr_args = &data->lr.arg; data->res.lr_res = &data->lr.res; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 01179f7de322..dba51c622cf3 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1445,6 +1445,8 @@ void nfs_inode_find_state_and_recover(struct inode *inode, struct nfs4_state *state; bool found = false; + if (!S_ISREG(inode->i_mode)) + goto out; rcu_read_lock(); list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { state = ctx->state; @@ -1466,7 +1468,7 @@ void nfs_inode_find_state_and_recover(struct inode *inode, found = true; } rcu_read_unlock(); - +out: nfs_inode_find_delegation_state_and_recover(inode, stateid); if (found) nfs4_schedule_state_manager(clp); @@ -1478,6 +1480,8 @@ static void nfs4_state_mark_open_context_bad(struct nfs4_state *state, int err) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *ctx; + if (!S_ISREG(inode->i_mode)) + return; rcu_read_lock(); list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { if (ctx->state != state) diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 6ce55e8e6b67..9f9ce4a565ea 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1062,6 +1062,9 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done, DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done); +DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio_reclaim); +DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_reclaim_done); + DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b72d7cc36766..cff225721d1c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1533,10 +1533,9 @@ static int pnfs_layout_return_on_reboot(struct pnfs_layout_hdr *lo) PNFS_FL_LAYOUTRETURN_PRIVILEGED); } -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync) { struct nfs_inode *nfsi = NFS_I(ino); struct nfs_open_context *ctx; @@ -1547,7 +1546,7 @@ bool pnfs_roc(struct inode *ino, nfs4_stateid stateid; enum pnfs_iomode iomode = 0; bool layoutreturn = false, roc = false; - bool skip_read = false; + bool skip_read; if (!nfs_have_layout(ino)) return false; @@ -1560,20 +1559,14 @@ retry: lo = NULL; goto out_noroc; } - pnfs_get_layout_hdr(lo); - if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { - spin_unlock(&ino->i_lock); - rcu_read_unlock(); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, - TASK_UNINTERRUPTIBLE); - pnfs_put_layout_hdr(lo); - goto retry; - } /* no roc if we hold a delegation */ + skip_read = false; if (nfs4_check_delegation(ino, FMODE_READ)) { - if (nfs4_check_delegation(ino, FMODE_WRITE)) + if (nfs4_check_delegation(ino, FMODE_WRITE)) { + lo = NULL; goto out_noroc; + } skip_read = true; } @@ -1582,12 +1575,43 @@ retry: if (state == NULL) continue; /* Don't return layout if there is open file state */ - if (state->state & FMODE_WRITE) + if (state->state & FMODE_WRITE) { + lo = NULL; goto out_noroc; + } if (state->state & FMODE_READ) skip_read = true; } + if (skip_read) { + bool writes = false; + + list_for_each_entry(lseg, &lo->plh_segs, pls_list) { + if (lseg->pls_range.iomode != IOMODE_READ) { + writes = true; + break; + } + } + if (!writes) { + lo = NULL; + goto out_noroc; + } + } + + pnfs_get_layout_hdr(lo); + if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { + if (!sync) { + pnfs_set_plh_return_info( + lo, skip_read ? IOMODE_RW : IOMODE_ANY, 0); + goto out_noroc; + } + spin_unlock(&ino->i_lock); + rcu_read_unlock(); + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, + TASK_UNINTERRUPTIBLE); + pnfs_put_layout_hdr(lo); + goto retry; + } list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) { if (skip_read && lseg->pls_range.iomode == IOMODE_READ) @@ -1627,7 +1651,7 @@ retry: out_noroc: spin_unlock(&ino->i_lock); rcu_read_unlock(); - pnfs_layoutcommit_inode(ino, true); + pnfs_layoutcommit_inode(ino, sync); if (roc) { struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; if (ld->prepare_layoutreturn) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 91ff877185c8..3db8f13d8fe4 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -303,10 +303,9 @@ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, u32 seq); int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, struct list_head *lseg_list); -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred); +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync); int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, struct nfs4_layoutreturn_res **respp, int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, @@ -773,12 +772,10 @@ pnfs_layoutcommit_outstanding(struct inode *inode) return false; } - -static inline bool -pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +static inline bool pnfs_roc(struct inode *ino, + struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, + const struct cred *cred, bool sync) { return false; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 336c510f3750..bf412455e8ed 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2025,6 +2025,39 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) } /** + * nfs_wb_folio_reclaim - Write back all requests on one page + * @inode: pointer to page + * @folio: pointer to folio + * + * Assumes that the folio has been locked by the caller + */ +int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio) +{ + loff_t range_start = folio_pos(folio); + size_t len = folio_size(folio); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + .range_start = range_start, + .range_end = range_start + len - 1, + .for_sync = 1, + }; + int ret; + + if (folio_test_writeback(folio)) + return -EBUSY; + if (folio_clear_dirty_for_io(folio)) { + trace_nfs_writeback_folio_reclaim(inode, range_start, len); + ret = nfs_writepage_locked(folio, &wbc); + trace_nfs_writeback_folio_reclaim_done(inode, range_start, len, + ret); + return ret; + } + nfs_commit_inode(inode, 0); + return 0; +} + +/** * nfs_wb_folio - Write back all requests on one page * @inode: pointer to page * @folio: pointer to folio diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c index af09aed09fd2..0778743ae2c2 100644 --- a/fs/nfs_common/common.c +++ b/fs/nfs_common/common.c @@ -17,7 +17,6 @@ static const struct { { NFSERR_NOENT, -ENOENT }, { NFSERR_IO, -EIO }, { NFSERR_NXIO, -ENXIO }, -/* { NFSERR_EAGAIN, -EAGAIN }, */ { NFSERR_ACCES, -EACCES }, { NFSERR_EXIST, -EEXIST }, { NFSERR_XDEV, -EXDEV }, diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 3e2d0fde80a7..fe8338735e7c 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -66,6 +66,8 @@ struct nfsd_net { struct lock_manager nfsd4_manager; bool grace_ended; + bool grace_end_forced; + bool client_tracking_active; time64_t boot_time; struct dentry *nfsd_client_dir; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 683bd1130afe..ad7af8cfcf1f 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -764,9 +764,28 @@ nfsd4_layout_lm_change(struct file_lease *onlist, int arg, return lease_modify(onlist, arg, dispose); } +/** + * nfsd4_layout_lm_open_conflict - see if the given file points to an inode that has + * an existing open that would conflict with the + * desired lease. + * @filp: file to check + * @arg: type of lease that we're trying to acquire + * + * The kernel will call into this operation to determine whether there + * are conflicting opens that may prevent the layout from being granted. + * For nfsd, that check is done at a higher level, so this trivially + * returns 0. + */ +static int +nfsd4_layout_lm_open_conflict(struct file *filp, int arg) +{ + return 0; +} + static const struct lease_manager_operations nfsd4_layouts_lm_ops = { - .lm_break = nfsd4_layout_lm_break, - .lm_change = nfsd4_layout_lm_change, + .lm_break = nfsd4_layout_lm_break, + .lm_change = nfsd4_layout_lm_change, + .lm_open_conflict = nfsd4_layout_lm_open_conflict, }; int diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index b74800917583..9ec08dd4fe82 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1502,7 +1502,7 @@ try_again: (schedule_timeout(20*HZ) == 0)) { finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); - return nfserr_eagain; + return nfserr_jukebox; } finish_wait(&nn->nfsd_ssc_waitq, &wait); goto try_again; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 808c24fb5c9a..d5e0f3a52d4f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -84,7 +84,7 @@ static u64 current_sessionid = 1; /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); -void nfsd4_end_grace(struct nfsd_net *nn); +static void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); static void nfsd4_file_hash_remove(struct nfs4_file *fi); static void deleg_reaper(struct nfsd_net *nn); @@ -1218,13 +1218,15 @@ static void put_deleg_file(struct nfs4_file *fp) if (nf) nfsd_file_put(nf); - if (rnf) + if (rnf) { + nfsd_file_put(rnf); nfs4_file_put_access(fp, NFS4_SHARE_ACCESS_READ); + } } static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f) { - struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME }; + struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME | ATTR_DELEG }; struct inode *inode = file_inode(f); int ret; @@ -1757,7 +1759,7 @@ static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, /** * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem - * @net: used to identify instance of nfsd (there is one per net namespace) + * @nn: used to identify instance of nfsd (there is one per net namespace) * @sb: super_block used to identify target filesystem * * All nfs4 states (open, lock, delegation, layout) held by the server instance @@ -1769,16 +1771,15 @@ static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, * The clients which own the states will subsequently being notified that the * states have been "admin-revoked". */ -void nfsd4_revoke_states(struct net *net, struct super_block *sb) +void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) { - struct nfsd_net *nn = net_generic(net, nfsd_net_id); unsigned int idhashval; unsigned int sc_types; sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; spin_lock(&nn->client_lock); - for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) { + for (idhashval = 0; idhashval < CLIENT_HASH_SIZE; idhashval++) { struct list_head *head = &nn->conf_id_hashtbl[idhashval]; struct nfs4_client *clp; retry: @@ -3097,8 +3098,10 @@ static int client_states_open(struct inode *inode, struct file *file) return -ENXIO; ret = seq_open(file, &states_seq_ops); - if (ret) + if (ret) { + drop_client(clp); return ret; + } s = file->private_data; s->private = clp; return 0; @@ -5552,10 +5555,29 @@ nfsd_change_deleg_cb(struct file_lease *onlist, int arg, return -EAGAIN; } +/** + * nfsd4_deleg_lm_open_conflict - see if the given file points to an inode that has + * an existing open that would conflict with the + * desired lease. + * @filp: file to check + * @arg: type of lease that we're trying to acquire + * + * The kernel will call into this operation to determine whether there + * are conflicting opens that may prevent the deleg from being granted. + * For nfsd, that check is done at a higher level, so this trivially + * returns 0. + */ +static int +nfsd4_deleg_lm_open_conflict(struct file *filp, int arg) +{ + return 0; +} + static const struct lease_manager_operations nfsd_lease_mng_ops = { .lm_breaker_owns_lease = nfsd_breaker_owns_lease, .lm_break = nfsd_break_deleg_cb, .lm_change = nfsd_change_deleg_cb, + .lm_open_conflict = nfsd4_deleg_lm_open_conflict, }; static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4_stateowner *so, u32 seqid) @@ -6231,10 +6253,14 @@ nfsd4_add_rdaccess_to_wrdeleg(struct svc_rqst *rqstp, struct nfsd4_open *open, fp = stp->st_stid.sc_file; spin_lock(&fp->fi_lock); __nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ); - fp = stp->st_stid.sc_file; - fp->fi_fds[O_RDONLY] = nf; - fp->fi_rdeleg_file = nf; + if (!fp->fi_fds[O_RDONLY]) { + fp->fi_fds[O_RDONLY] = nf; + nf = NULL; + } + fp->fi_rdeleg_file = nfsd_file_get(fp->fi_fds[O_RDONLY]); spin_unlock(&fp->fi_lock); + if (nf) + nfsd_file_put(nf); } return true; } @@ -6562,7 +6588,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfs_ok; } -void +static void nfsd4_end_grace(struct nfsd_net *nn) { /* do nothing if grace period already ended */ @@ -6595,6 +6621,33 @@ nfsd4_end_grace(struct nfsd_net *nn) */ } +/** + * nfsd4_force_end_grace - forcibly end the NFSv4 grace period + * @nn: network namespace for the server instance to be updated + * + * Forces bypass of normal grace period completion, then schedules + * the laundromat to end the grace period immediately. Does not wait + * for the grace period to fully terminate before returning. + * + * Return values: + * %true: Grace termination schedule + * %false: No action was taken + */ +bool nfsd4_force_end_grace(struct nfsd_net *nn) +{ + if (!nn->client_tracking_ops) + return false; + spin_lock(&nn->client_lock); + if (nn->grace_ended || !nn->client_tracking_active) { + spin_unlock(&nn->client_lock); + return false; + } + WRITE_ONCE(nn->grace_end_forced, true); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + spin_unlock(&nn->client_lock); + return true; +} + /* * If we've waited a lease period but there are still clients trying to * reclaim, wait a little longer to give them a chance to finish. @@ -6604,6 +6657,8 @@ static bool clients_still_reclaiming(struct nfsd_net *nn) time64_t double_grace_period_end = nn->boot_time + 2 * nn->nfsd4_lease; + if (READ_ONCE(nn->grace_end_forced)) + return false; if (nn->track_reclaim_completes && atomic_read(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) @@ -8924,6 +8979,8 @@ static int nfs4_state_create_net(struct net *net) nn->unconf_name_tree = RB_ROOT; nn->boot_time = ktime_get_real_seconds(); nn->grace_ended = false; + nn->grace_end_forced = false; + nn->client_tracking_active = false; nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); INIT_LIST_HEAD(&nn->client_lru); @@ -9004,6 +9061,10 @@ nfs4_state_start_net(struct net *net) return ret; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); + /* safe for laundromat to run now */ + spin_lock(&nn->client_lock); + nn->client_tracking_active = true; + spin_unlock(&nn->client_lock); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", @@ -9052,6 +9113,9 @@ nfs4_state_shutdown_net(struct net *net) shrinker_free(nn->nfsd_client_shrinker); cancel_work_sync(&nn->nfsd_shrinker_work); + spin_lock(&nn->client_lock); + nn->client_tracking_active = false; + spin_unlock(&nn->client_lock); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 5ce9a49e76ba..084fc517e9e1 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -259,6 +259,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) struct path path; char *fo_path; int error; + struct nfsd_net *nn; /* sanity check */ if (size == 0) @@ -285,7 +286,13 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) * 3. Is that directory the root of an exported file system? */ error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb); - nfsd4_revoke_states(netns(file), path.dentry->d_sb); + mutex_lock(&nfsd_mutex); + nn = net_generic(netns(file), nfsd_net_id); + if (nn->nfsd_serv) + nfsd4_revoke_states(nn, path.dentry->d_sb); + else + error = -EINVAL; + mutex_unlock(&nfsd_mutex); path_put(&path); return error; @@ -1082,10 +1089,9 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case 'Y': case 'y': case '1': - if (!nn->nfsd_serv) + if (!nfsd4_force_end_grace(nn)) return -EBUSY; trace_nfsd_end_grace(netns(file)); - nfsd4_end_grace(nn); break; default: return -EINVAL; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 50be785f1d2c..b0283213a8f5 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -233,7 +233,6 @@ void nfsd_lockd_shutdown(void); #define nfserr_noent cpu_to_be32(NFSERR_NOENT) #define nfserr_io cpu_to_be32(NFSERR_IO) #define nfserr_nxio cpu_to_be32(NFSERR_NXIO) -#define nfserr_eagain cpu_to_be32(NFSERR_EAGAIN) #define nfserr_acces cpu_to_be32(NFSERR_ACCES) #define nfserr_exist cpu_to_be32(NFSERR_EXIST) #define nfserr_xdev cpu_to_be32(NFSERR_XDEV) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index f6cae4430ba4..f1cc223ecee2 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -406,26 +406,26 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - if (!nn->nfsd_net_up) - return; - - percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); - wait_for_completion(&nn->nfsd_net_confirm_done); - - nfsd_export_flush(net); - nfs4_state_shutdown_net(net); - nfsd_reply_cache_shutdown(nn); - nfsd_file_cache_shutdown_net(net); - if (nn->lockd_up) { - lockd_down(net); - nn->lockd_up = false; + if (nn->nfsd_net_up) { + percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); + wait_for_completion(&nn->nfsd_net_confirm_done); + + nfsd_export_flush(net); + nfs4_state_shutdown_net(net); + nfsd_reply_cache_shutdown(nn); + nfsd_file_cache_shutdown_net(net); + if (nn->lockd_up) { + lockd_down(net); + nn->lockd_up = false; + } + wait_for_completion(&nn->nfsd_net_free_done); } - wait_for_completion(&nn->nfsd_net_free_done); percpu_ref_exit(&nn->nfsd_net_ref); + if (nn->nfsd_net_up) + nfsd_shutdown_generic(); nn->nfsd_net_up = false; - nfsd_shutdown_generic(); } static DEFINE_SPINLOCK(nfsd_notifier_lock); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index b052c1effdc5..508b7e36d846 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -841,15 +841,15 @@ static inline void get_nfs4_file(struct nfs4_file *fi) struct nfsd_file *find_any_file(struct nfs4_file *f); #ifdef CONFIG_NFSD_V4 -void nfsd4_revoke_states(struct net *net, struct super_block *sb); +void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb); #else -static inline void nfsd4_revoke_states(struct net *net, struct super_block *sb) +static inline void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) { } #endif /* grace period management */ -void nfsd4_end_grace(struct nfsd_net *nn); +bool nfsd4_force_end_grace(struct nfsd_net *nn); /* nfs4recover operations */ extern int nfsd4_client_tracking_init(struct net *net); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 964cf922ad83..168d3ccc8155 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -2865,8 +2865,8 @@ nfsd_permission(struct svc_cred *cred, struct svc_export *exp, /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && - (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) || - acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC))) + (((acc & NFSD_MAY_MASK) == NFSD_MAY_READ) && + (acc & (NFSD_MAY_OWNER_OVERRIDE | NFSD_MAY_READ_IF_EXEC)))) err = inode_permission(&nop_mnt_idmap, inode, MAY_EXEC); return err? nfserrno(err) : 0; diff --git a/fs/pidfs.c b/fs/pidfs.c index dba703d4ce4a..1e20e36e0ed5 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -517,14 +517,18 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) switch (cmd) { /* Namespaces that hang of nsproxy. */ case PIDFD_GET_CGROUP_NAMESPACE: +#ifdef CONFIG_CGROUPS if (!ns_ref_get(nsp->cgroup_ns)) break; ns_common = to_ns_common(nsp->cgroup_ns); +#endif break; case PIDFD_GET_IPC_NAMESPACE: +#ifdef CONFIG_IPC_NS if (!ns_ref_get(nsp->ipc_ns)) break; ns_common = to_ns_common(nsp->ipc_ns); +#endif break; case PIDFD_GET_MNT_NAMESPACE: if (!ns_ref_get(nsp->mnt_ns)) @@ -532,32 +536,43 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) ns_common = to_ns_common(nsp->mnt_ns); break; case PIDFD_GET_NET_NAMESPACE: +#ifdef CONFIG_NET_NS if (!ns_ref_get(nsp->net_ns)) break; ns_common = to_ns_common(nsp->net_ns); +#endif break; case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE: +#ifdef CONFIG_PID_NS if (!ns_ref_get(nsp->pid_ns_for_children)) break; ns_common = to_ns_common(nsp->pid_ns_for_children); +#endif break; case PIDFD_GET_TIME_NAMESPACE: +#ifdef CONFIG_TIME_NS if (!ns_ref_get(nsp->time_ns)) break; ns_common = to_ns_common(nsp->time_ns); +#endif break; case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE: +#ifdef CONFIG_TIME_NS if (!ns_ref_get(nsp->time_ns_for_children)) break; ns_common = to_ns_common(nsp->time_ns_for_children); +#endif break; case PIDFD_GET_UTS_NAMESPACE: +#ifdef CONFIG_UTS_NS if (!ns_ref_get(nsp->uts_ns)) break; ns_common = to_ns_common(nsp->uts_ns); +#endif break; /* Namespaces that don't hang of nsproxy. */ case PIDFD_GET_USER_NAMESPACE: +#ifdef CONFIG_USER_NS scoped_guard(rcu) { struct user_namespace *user_ns; @@ -566,8 +581,10 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; ns_common = to_ns_common(user_ns); } +#endif break; case PIDFD_GET_PID_NAMESPACE: +#ifdef CONFIG_PID_NS scoped_guard(rcu) { struct pid_namespace *pid_ns; @@ -576,6 +593,7 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; ns_common = to_ns_common(pid_ns); } +#endif break; default: return -ENOIOCTLCMD; diff --git a/fs/readdir.c b/fs/readdir.c index 7764b8638978..73707b6816e9 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -316,6 +316,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct getdents_callback buf = { .ctx.actor = filldir, .ctx.count = count, + .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent }; int error; @@ -400,6 +401,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, struct getdents_callback64 buf = { .ctx.actor = filldir64, .ctx.count = count, + .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent }; int error; @@ -569,6 +571,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, struct compat_getdents_callback buf = { .ctx.actor = compat_filldir, .ctx.count = count, + .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent, }; int error; diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 360b00854115..ac55193bf398 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -458,7 +458,10 @@ static int romfs_fill_super(struct super_block *sb, struct fs_context *fc) #ifdef CONFIG_BLOCK if (!sb->s_mtd) { - sb_set_blocksize(sb, ROMBSIZE); + if (!sb_set_blocksize(sb, ROMBSIZE)) { + errorf(fc, "romfs: unable to set blocksize\n"); + return -EINVAL; + } } else { sb->s_blocksize = ROMBSIZE; sb->s_blocksize_bits = blksize_bits(ROMBSIZE); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index d9664634144d..a3dc7cb1ab54 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1149,9 +1149,6 @@ cifs_setlease(struct file *file, int arg, struct file_lease **lease, void **priv struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; - if (!S_ISREG(inode->i_mode)) - return -EINVAL; - /* Check if file is oplocked if this is request for new lease */ if (arg == F_UNLCK || ((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) || @@ -1712,6 +1709,7 @@ const struct file_operations cifs_dir_ops = { .remap_file_range = cifs_remap_file_range, .llseek = generic_file_llseek, .fsync = cifs_dir_fsync, + .setlease = simple_nosetlease, }; static void diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index 0a9935ce05a5..d1b153209424 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -588,6 +588,9 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) break; default: cifs_dbg(FYI, "unsupported ioctl\n"); + trace_smb3_unsupported_ioctl(xid, + pSMBFile ? pSMBFile->fid.persistent_fid : 0, + command); break; } cifs_ioc_exit: diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index a16ded46b5a2..c1aaf77e187b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1905,6 +1905,12 @@ retry: src_off_prev = src_off; dst_off_prev = dst_off; + /* + * __counted_by_le(ChunkCount): set to allocated chunks before + * populating Chunks[] + */ + cc_req->ChunkCount = cpu_to_le32(chunk_count); + chunks = 0; copy_bytes = 0; copy_bytes_left = umin(total_bytes_left, tcon->max_bytes_copy); diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index b0fbc2df642e..a584a7743113 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -1579,6 +1579,7 @@ DEFINE_EVENT(smb3_ioctl_class, smb3_##name, \ TP_ARGS(xid, fid, command)) DEFINE_SMB3_IOCTL_EVENT(ioctl); +DEFINE_SMB3_IOCTL_EVENT(unsupported_ioctl); DECLARE_EVENT_CLASS(smb3_shutdown_class, TP_PROTO(__u32 flags, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 469b70757dba..2fcd0d4d1fb0 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2281,7 +2281,7 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) { struct smb2_create_rsp *rsp; struct smb2_create_req *req; - int id; + int id = -1; int err; char *name; @@ -2338,6 +2338,9 @@ out: break; } + if (id >= 0) + ksmbd_session_rpc_close(work->sess, id); + if (!IS_ERR(name)) kfree(name); @@ -2809,6 +2812,7 @@ static int parse_durable_handle_context(struct ksmbd_work *work, SMB2_CLIENT_GUID_SIZE)) { if (!(req->hdr.Flags & SMB2_FLAGS_REPLAY_OPERATION)) { err = -ENOEXEC; + ksmbd_put_durable_fd(dh_info->fp); goto out; } @@ -3006,10 +3010,10 @@ int smb2_open(struct ksmbd_work *work) file_info = FILE_OPENED; rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat); + ksmbd_put_durable_fd(fp); if (rc) goto err_out2; - ksmbd_put_durable_fd(fp); goto reconnected_fp; } } else if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) @@ -4923,8 +4927,10 @@ static int get_file_all_info(struct ksmbd_work *work, ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); - if (ret) + if (ret) { + kfree(filename); return ret; + } ksmbd_debug(SMB, "filename = %s\n", filename); delete_pending = ksmbd_inode_pending_delete(fp); diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index f585359684d4..e4273932e7e4 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -1353,14 +1353,12 @@ static int get_sg_list(void *buf, int size, struct scatterlist *sg_list, int nen static int get_mapped_sg_list(struct ib_device *device, void *buf, int size, struct scatterlist *sg_list, int nentries, - enum dma_data_direction dir) + enum dma_data_direction dir, int *npages) { - int npages; - - npages = get_sg_list(buf, size, sg_list, nentries); - if (npages < 0) + *npages = get_sg_list(buf, size, sg_list, nentries); + if (*npages < 0) return -EINVAL; - return ib_dma_map_sg(device, sg_list, npages, dir); + return ib_dma_map_sg(device, sg_list, *npages, dir); } static int post_sendmsg(struct smbdirect_socket *sc, @@ -1431,12 +1429,13 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, for (i = 0; i < niov; i++) { struct ib_sge *sge; int sg_cnt; + int npages; sg_init_table(sg, SMBDIRECT_SEND_IO_MAX_SGE - 1); sg_cnt = get_mapped_sg_list(sc->ib.dev, iov[i].iov_base, iov[i].iov_len, sg, SMBDIRECT_SEND_IO_MAX_SGE - 1, - DMA_TO_DEVICE); + DMA_TO_DEVICE, &npages); if (sg_cnt <= 0) { pr_err("failed to map buffer\n"); ret = -ENOMEM; @@ -1444,7 +1443,7 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, } else if (sg_cnt + msg->num_sge > SMBDIRECT_SEND_IO_MAX_SGE) { pr_err("buffer not fitted into sges\n"); ret = -E2BIG; - ib_dma_unmap_sg(sc->ib.dev, sg, sg_cnt, + ib_dma_unmap_sg(sc->ib.dev, sg, npages, DMA_TO_DEVICE); goto err; } @@ -2708,6 +2707,7 @@ int ksmbd_rdma_init(void) { int ret; + smb_direct_port = SMB_DIRECT_PORT_INFINIBAND; smb_direct_listener.cm_id = NULL; ret = ib_register_client(&smb_direct_ib_client); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index f891344bd76b..b8e648b8300f 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1227,7 +1227,7 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *filepath, } /** - * ksmbd_vfs_kern_path_start_remove() - lookup a file and get path info prior to removal + * ksmbd_vfs_kern_path_start_removing() - lookup a file and get path info prior to removal * @work: work * @filepath: file path that is relative to share * @flags: lookup flags diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 42bedc4ec7af..230d7589d15c 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -186,6 +186,7 @@ const struct file_operations vboxsf_dir_fops = { .release = vboxsf_dir_release, .read = generic_read_dir, .llseek = generic_file_llseek, + .setlease = simple_nosetlease, }; /* diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d97295eaebe6..c19d6d713780 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -848,15 +848,16 @@ sparse_alloc: * invalid inode records, such as records that start at agbno 0 * or extend beyond the AG. * - * Set min agbno to the first aligned, non-zero agbno and max to - * the last aligned agbno that is at least one full chunk from - * the end of the AG. + * Set min agbno to the first chunk aligned, non-zero agbno and + * max to one less than the last chunk aligned agbno from the + * end of the AG. We subtract 1 from max so that the cluster + * allocation alignment takes over and allows allocation within + * the last full inode chunk in the AG. */ args.min_agbno = args.mp->m_sb.sb_inoalignmt; args.max_agbno = round_down(xfs_ag_block_count(args.mp, pag_agno(pag)), - args.mp->m_sb.sb_inoalignmt) - - igeo->ialloc_blks; + args.mp->m_sb.sb_inoalignmt) - 1; error = xfs_alloc_vextent_near_bno(&args, xfs_agbno_to_fsb(pag, diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index 9186c58e83d5..be16efaa6925 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -48,6 +48,31 @@ xfs_rtgroup_min_block( return 0; } +/* Compute the number of rt extents in this realtime group. */ +static xfs_rtxnum_t +__xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, + xfs_rtbxlen_t rextents) +{ + ASSERT(rgno < rgcount); + if (rgno == rgcount - 1) + return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); + + ASSERT(xfs_has_rtgroups(mp)); + return mp->m_sb.sb_rgextents; +} + +xfs_rtxnum_t +xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, + mp->m_sb.sb_rextents); +} + /* Precompute this group's geometry */ void xfs_rtgroup_calc_geometry( @@ -58,7 +83,8 @@ xfs_rtgroup_calc_geometry( xfs_rtbxlen_t rextents) { rtg->rtg_extents = __xfs_rtgroup_extents(mp, rgno, rgcount, rextents); - rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize; + rtg_group(rtg)->xg_block_count = + rtg->rtg_extents * mp->m_sb.sb_rextsize; rtg_group(rtg)->xg_min_gbno = xfs_rtgroup_min_block(mp, rgno); } @@ -136,31 +162,6 @@ out_unwind_new_rtgs: return error; } -/* Compute the number of rt extents in this realtime group. */ -xfs_rtxnum_t -__xfs_rtgroup_extents( - struct xfs_mount *mp, - xfs_rgnumber_t rgno, - xfs_rgnumber_t rgcount, - xfs_rtbxlen_t rextents) -{ - ASSERT(rgno < rgcount); - if (rgno == rgcount - 1) - return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); - - ASSERT(xfs_has_rtgroups(mp)); - return mp->m_sb.sb_rgextents; -} - -xfs_rtxnum_t -xfs_rtgroup_extents( - struct xfs_mount *mp, - xfs_rgnumber_t rgno) -{ - return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, - mp->m_sb.sb_rextents); -} - /* * Update the rt extent count of the previous tail rtgroup if it changed during * recovery (i.e. recovery of a growfs). diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 03f1e2493334..73cace4d25c7 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -285,8 +285,6 @@ void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents); -xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno, - xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents); xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno); void xfs_rtgroup_calc_geometry(struct xfs_mount *mp, struct xfs_rtgroup *rtg, xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount, diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 04f39ea15898..37a1b33e9045 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1831,7 +1831,6 @@ xfs_buffered_write_iomap_begin( */ if (flags & IOMAP_ZERO) { xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)); - u64 end; if (isnullstartblock(imap.br_startblock) && offset_fsb >= eof_fsb) @@ -1851,12 +1850,14 @@ xfs_buffered_write_iomap_begin( */ if (imap.br_state == XFS_EXT_UNWRITTEN && offset_fsb < eof_fsb) { - loff_t len = min(count, - XFS_FSB_TO_B(mp, imap.br_blockcount)); + loff_t foffset = offset, fend; - end = iomap_fill_dirty_folios(iter, offset, len); + fend = offset + + min(count, XFS_FSB_TO_B(mp, imap.br_blockcount)); + iomap_fill_dirty_folios(iter, &foffset, fend, + &iomap_flags); end_fsb = min_t(xfs_fileoff_t, end_fsb, - XFS_B_TO_FSB(mp, end)); + XFS_B_TO_FSB(mp, foffset)); } xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a311385b23d8..d4544ccafea5 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1180,9 +1180,11 @@ xfs_log_cover( int error = 0; bool need_covered; - ASSERT((xlog_cil_empty(mp->m_log) && xlog_iclogs_empty(mp->m_log) && - !xfs_ail_min_lsn(mp->m_log->l_ailp)) || - xlog_is_shutdown(mp->m_log)); + if (!xlog_is_shutdown(mp->m_log)) { + ASSERT(xlog_cil_empty(mp->m_log)); + ASSERT(xlog_iclogs_empty(mp->m_log)); + ASSERT(!xfs_ail_min_lsn(mp->m_log->l_ailp)); + } if (!xfs_log_writable(mp)) return 0; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index e063f4f2f2e6..a12ffed12391 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -126,7 +126,7 @@ xfs_rtcopy_summary( error = 0; out: xfs_rtbuf_cache_relse(oargs); - return 0; + return error; } /* * Mark an extent specified by start and len allocated. @@ -1265,7 +1265,7 @@ xfs_growfs_check_rtgeom( uint32_t rem; if (rextsize != 1) - return -EINVAL; + goto out_inval; div_u64_rem(nmp->m_sb.sb_rblocks, gblocks, &rem); if (rem) { xfs_warn(mp, @@ -1326,7 +1326,7 @@ xfs_grow_last_rtg( return true; if (mp->m_sb.sb_rgcount == 0) return false; - return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) <= + return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) < mp->m_sb.sb_rgextents; } diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h index b14d165632e7..402b97d12138 100644 --- a/include/acpi/acpi_drivers.h +++ b/include/acpi/acpi_drivers.h @@ -51,7 +51,7 @@ int acpi_irq_penalty_init(void); int acpi_pci_link_allocate_irq(acpi_handle handle, int index, int *triggering, - int *polarity, char **name); + int *polarity, char **name, u32 *gsi); int acpi_pci_link_free_irq(acpi_handle handle); /* ACPI PCI Device Binding */ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 1fff717cae51..4d679d2a206b 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -46,7 +46,8 @@ * * The mmu_gather API consists of: * - * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu() + * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / + * tlb_finish_mmu() * * start and finish a mmu_gather * @@ -364,6 +365,20 @@ struct mmu_gather { unsigned int vma_huge : 1; unsigned int vma_pfn : 1; + /* + * Did we unshare (unmap) any shared page tables? For now only + * used for hugetlb PMD table sharing. + */ + unsigned int unshared_tables : 1; + + /* + * Did we unshare any page tables such that they are now exclusive + * and could get reused+modified by the new owner? When setting this + * flag, "unshared_tables" will be set as well. For now only used + * for hugetlb PMD table sharing. + */ + unsigned int fully_unshared_tables : 1; + unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER @@ -400,6 +415,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; + tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an @@ -484,7 +500,7 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || - tlb->cleared_puds || tlb->cleared_p4ds)) + tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); @@ -773,6 +789,63 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) } #endif +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, + unsigned long addr) +{ + /* + * The caller must make sure that concurrent unsharing + exclusive + * reuse is impossible until tlb_flush_unshared_tables() was called. + */ + VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); + ptdesc_pmd_pts_dec(pt); + + /* Clearing a PUD pointing at a PMD table with PMD leaves. */ + tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); + + /* + * If the page table is now exclusively owned, we fully unshared + * a page table. + */ + if (!ptdesc_pmd_is_shared(pt)) + tlb->fully_unshared_tables = true; + tlb->unshared_tables = true; +} + +static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) +{ + /* + * As soon as the caller drops locks to allow for reuse of + * previously-shared tables, these tables could get modified and + * even reused outside of hugetlb context, so we have to make sure that + * any page table walkers (incl. TLB, GUP-fast) are aware of that + * change. + * + * Even if we are not fully unsharing a PMD table, we must + * flush the TLB for the unsharer now. + */ + if (tlb->unshared_tables) + tlb_flush_mmu_tlbonly(tlb); + + /* + * Similarly, we must make sure that concurrent GUP-fast will not + * walk previously-shared page tables that are getting modified+reused + * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. + * + * We only perform this when we are the last sharer of a page table, + * as the IPI will reach all CPUs: any GUP-fast. + * + * Note that on configs where tlb_remove_table_sync_one() is a NOP, + * the expectation is that the tlb_flush_mmu_tlbonly() would have issued + * required IPIs already for us. + */ + if (tlb->fully_unshared_tables) { + tlb_remove_table_sync_one(); + tlb->fully_unshared_tables = false; + } +} +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/drm/bridge/dw_hdmi_qp.h b/include/drm/bridge/dw_hdmi_qp.h index 3f461f6b9bbf..3af12f82da2c 100644 --- a/include/drm/bridge/dw_hdmi_qp.h +++ b/include/drm/bridge/dw_hdmi_qp.h @@ -34,5 +34,6 @@ struct dw_hdmi_qp_plat_data { struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, struct drm_encoder *encoder, const struct dw_hdmi_qp_plat_data *plat_data); +void dw_hdmi_qp_suspend(struct device *dev, struct dw_hdmi_qp *hdmi); void dw_hdmi_qp_resume(struct device *dev, struct dw_hdmi_qp *hdmi); #endif /* __DW_HDMI_QP__ */ diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index df2f24b950e4..14d2859f0bda 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -552,6 +552,22 @@ ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, void *buffer, size_t size); /** + * drm_dp_dpcd_readb() - read a single byte from the DPCD + * @aux: DisplayPort AUX channel + * @offset: address of the register to read + * @valuep: location where the value of the register will be stored + * + * Returns the number of bytes transferred (1) on success, or a negative + * error code on failure. In most of the cases you should be using + * drm_dp_dpcd_read_byte() instead. + */ +static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, + unsigned int offset, u8 *valuep) +{ + return drm_dp_dpcd_read(aux, offset, valuep, 1); +} + +/** * drm_dp_dpcd_read_data() - read a series of bytes from the DPCD * @aux: DisplayPort AUX channel (SST or MST) * @offset: address of the (first) register to read @@ -570,12 +586,29 @@ static inline int drm_dp_dpcd_read_data(struct drm_dp_aux *aux, void *buffer, size_t size) { int ret; + size_t i; + u8 *buf = buffer; ret = drm_dp_dpcd_read(aux, offset, buffer, size); - if (ret < 0) - return ret; - if (ret < size) - return -EPROTO; + if (ret >= 0) { + if (ret < size) + return -EPROTO; + return 0; + } + + /* + * Workaround for USB-C hubs/adapters with buggy firmware that fail + * multi-byte AUX reads but work with single-byte reads. + * Known affected devices: + * - Lenovo USB-C to VGA adapter (VIA VL817, idVendor=17ef, idProduct=7217) + * - Dell DA310 USB-C hub (idVendor=413c, idProduct=c010) + * Attempt byte-by-byte reading as a fallback. + */ + for (i = 0; i < size; i++) { + ret = drm_dp_dpcd_readb(aux, offset + i, &buf[i]); + if (ret < 0) + return ret; + } return 0; } @@ -610,22 +643,6 @@ static inline int drm_dp_dpcd_write_data(struct drm_dp_aux *aux, } /** - * drm_dp_dpcd_readb() - read a single byte from the DPCD - * @aux: DisplayPort AUX channel - * @offset: address of the register to read - * @valuep: location where the value of the register will be stored - * - * Returns the number of bytes transferred (1) on success, or a negative - * error code on failure. In most of the cases you should be using - * drm_dp_dpcd_read_byte() instead. - */ -static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, - unsigned int offset, u8 *valuep) -{ - return drm_dp_dpcd_read(aux, offset, valuep, 1); -} - -/** * drm_dp_dpcd_writeb() - write a single byte to the DPCD * @aux: DisplayPort AUX channel * @offset: address of the register to write diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index 53382fe93537..e154ee4f0696 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -60,6 +60,12 @@ int drm_atomic_helper_check_plane_state(struct drm_plane_state *plane_state, int drm_atomic_helper_check_planes(struct drm_device *dev, struct drm_atomic_state *state); int drm_atomic_helper_check_crtc_primary_plane(struct drm_crtc_state *crtc_state); +void drm_atomic_helper_commit_encoder_bridge_disable(struct drm_device *dev, + struct drm_atomic_state *state); +void drm_atomic_helper_commit_crtc_disable(struct drm_device *dev, + struct drm_atomic_state *state); +void drm_atomic_helper_commit_encoder_bridge_post_disable(struct drm_device *dev, + struct drm_atomic_state *state); int drm_atomic_helper_check(struct drm_device *dev, struct drm_atomic_state *state); void drm_atomic_helper_commit_tail(struct drm_atomic_state *state); @@ -89,8 +95,24 @@ drm_atomic_helper_update_legacy_modeset_state(struct drm_device *dev, void drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *state); +void drm_atomic_helper_commit_crtc_set_mode(struct drm_device *dev, + struct drm_atomic_state *state); + void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev, struct drm_atomic_state *state); + +void drm_atomic_helper_commit_writebacks(struct drm_device *dev, + struct drm_atomic_state *state); + +void drm_atomic_helper_commit_encoder_bridge_pre_enable(struct drm_device *dev, + struct drm_atomic_state *state); + +void drm_atomic_helper_commit_crtc_enable(struct drm_device *dev, + struct drm_atomic_state *state); + +void drm_atomic_helper_commit_encoder_bridge_enable(struct drm_device *dev, + struct drm_atomic_state *state); + void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, struct drm_atomic_state *old_state); diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 0ff7ab4aa868..dbafe136833f 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -176,33 +176,17 @@ struct drm_bridge_funcs { /** * @disable: * - * The @disable callback should disable the bridge. + * This callback should disable the bridge. It is called right before + * the preceding element in the display pipe is disabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @disable vfunc. If the preceding element is a &drm_encoder + * it's called right before the &drm_encoder_helper_funcs.disable, + * &drm_encoder_helper_funcs.prepare or &drm_encoder_helper_funcs.dpms + * hook. * * The bridge can assume that the display pipe (i.e. clocks and timing * signals) feeding it is still running when this callback is called. * - * - * If the preceding element is a &drm_bridge, then this is called before - * that bridge is disabled via one of: - * - * - &drm_bridge_funcs.disable - * - &drm_bridge_funcs.atomic_disable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called before the encoder is disabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_disable - * - &drm_encoder_helper_funcs.prepare - * - &drm_encoder_helper_funcs.disable - * - &drm_encoder_helper_funcs.dpms - * - * and the CRTC is disabled via one of: - * - * - &drm_crtc_helper_funcs.prepare - * - &drm_crtc_helper_funcs.atomic_disable - * - &drm_crtc_helper_funcs.disable - * - &drm_crtc_helper_funcs.dpms. - * * The @disable callback is optional. * * NOTE: @@ -215,34 +199,17 @@ struct drm_bridge_funcs { /** * @post_disable: * - * The bridge must assume that the display pipe (i.e. clocks and timing - * signals) feeding this bridge is no longer running when the - * @post_disable is called. + * This callback should disable the bridge. It is called right after the + * preceding element in the display pipe is disabled. If the preceding + * element is a bridge this means it's called after that bridge's + * @post_disable function. If the preceding element is a &drm_encoder + * it's called right after the encoder's + * &drm_encoder_helper_funcs.disable, &drm_encoder_helper_funcs.prepare + * or &drm_encoder_helper_funcs.dpms hook. * - * This callback should perform all the actions required by the hardware - * after it has stopped receiving signals from the preceding element. - * - * If the preceding element is a &drm_bridge, then this is called after - * that bridge is post-disabled (unless marked otherwise by the - * @pre_enable_prev_first flag) via one of: - * - * - &drm_bridge_funcs.post_disable - * - &drm_bridge_funcs.atomic_post_disable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called after the encoder is disabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_disable - * - &drm_encoder_helper_funcs.prepare - * - &drm_encoder_helper_funcs.disable - * - &drm_encoder_helper_funcs.dpms - * - * and the CRTC is disabled via one of: - * - * - &drm_crtc_helper_funcs.prepare - * - &drm_crtc_helper_funcs.atomic_disable - * - &drm_crtc_helper_funcs.disable - * - &drm_crtc_helper_funcs.dpms + * The bridge must assume that the display pipe (i.e. clocks and timing + * signals) feeding it is no longer running when this callback is + * called. * * The @post_disable callback is optional. * @@ -285,30 +252,18 @@ struct drm_bridge_funcs { /** * @pre_enable: * - * The display pipe (i.e. clocks and timing signals) feeding this bridge - * will not yet be running when the @pre_enable is called. - * - * This callback should perform all the necessary actions to prepare the - * bridge to accept signals from the preceding element. - * - * If the preceding element is a &drm_bridge, then this is called before - * that bridge is pre-enabled (unless marked otherwise by - * @pre_enable_prev_first flag) via one of: - * - * - &drm_bridge_funcs.pre_enable - * - &drm_bridge_funcs.atomic_pre_enable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called before the CRTC is enabled via one of: - * - * - &drm_crtc_helper_funcs.atomic_enable - * - &drm_crtc_helper_funcs.commit - * - * and the encoder is enabled via one of: + * This callback should enable the bridge. It is called right before + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @pre_enable function. If the preceding element is a + * &drm_encoder it's called right before the encoder's + * &drm_encoder_helper_funcs.enable, &drm_encoder_helper_funcs.commit or + * &drm_encoder_helper_funcs.dpms hook. * - * - &drm_encoder_helper_funcs.atomic_enable - * - &drm_encoder_helper_funcs.enable - * - &drm_encoder_helper_funcs.commit + * The display pipe (i.e. clocks and timing signals) feeding this bridge + * will not yet be running when this callback is called. The bridge must + * not enable the display link feeding the next bridge in the chain (if + * there is one) when this callback is called. * * The @pre_enable callback is optional. * @@ -322,31 +277,19 @@ struct drm_bridge_funcs { /** * @enable: * - * The @enable callback should enable the bridge. + * This callback should enable the bridge. It is called right after + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called after that + * bridge's @enable function. If the preceding element is a + * &drm_encoder it's called right after the encoder's + * &drm_encoder_helper_funcs.enable, &drm_encoder_helper_funcs.commit or + * &drm_encoder_helper_funcs.dpms hook. * * The bridge can assume that the display pipe (i.e. clocks and timing * signals) feeding it is running when this callback is called. This * callback must enable the display link feeding the next bridge in the * chain if there is one. * - * If the preceding element is a &drm_bridge, then this is called after - * that bridge is enabled via one of: - * - * - &drm_bridge_funcs.enable - * - &drm_bridge_funcs.atomic_enable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called after the CRTC is enabled via one of: - * - * - &drm_crtc_helper_funcs.atomic_enable - * - &drm_crtc_helper_funcs.commit - * - * and the encoder is enabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_enable - * - &drm_encoder_helper_funcs.enable - * - drm_encoder_helper_funcs.commit - * * The @enable callback is optional. * * NOTE: @@ -359,30 +302,17 @@ struct drm_bridge_funcs { /** * @atomic_pre_enable: * - * The display pipe (i.e. clocks and timing signals) feeding this bridge - * will not yet be running when the @atomic_pre_enable is called. - * - * This callback should perform all the necessary actions to prepare the - * bridge to accept signals from the preceding element. - * - * If the preceding element is a &drm_bridge, then this is called before - * that bridge is pre-enabled (unless marked otherwise by - * @pre_enable_prev_first flag) via one of: - * - * - &drm_bridge_funcs.pre_enable - * - &drm_bridge_funcs.atomic_pre_enable + * This callback should enable the bridge. It is called right before + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @atomic_pre_enable or @pre_enable function. If the preceding + * element is a &drm_encoder it's called right before the encoder's + * &drm_encoder_helper_funcs.atomic_enable hook. * - * If the preceding element of the bridge is a display controller, then - * this callback is called before the CRTC is enabled via one of: - * - * - &drm_crtc_helper_funcs.atomic_enable - * - &drm_crtc_helper_funcs.commit - * - * and the encoder is enabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_enable - * - &drm_encoder_helper_funcs.enable - * - &drm_encoder_helper_funcs.commit + * The display pipe (i.e. clocks and timing signals) feeding this bridge + * will not yet be running when this callback is called. The bridge must + * not enable the display link feeding the next bridge in the chain (if + * there is one) when this callback is called. * * The @atomic_pre_enable callback is optional. */ @@ -392,31 +322,18 @@ struct drm_bridge_funcs { /** * @atomic_enable: * - * The @atomic_enable callback should enable the bridge. + * This callback should enable the bridge. It is called right after + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called after that + * bridge's @atomic_enable or @enable function. If the preceding element + * is a &drm_encoder it's called right after the encoder's + * &drm_encoder_helper_funcs.atomic_enable hook. * * The bridge can assume that the display pipe (i.e. clocks and timing * signals) feeding it is running when this callback is called. This * callback must enable the display link feeding the next bridge in the * chain if there is one. * - * If the preceding element is a &drm_bridge, then this is called after - * that bridge is enabled via one of: - * - * - &drm_bridge_funcs.enable - * - &drm_bridge_funcs.atomic_enable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called after the CRTC is enabled via one of: - * - * - &drm_crtc_helper_funcs.atomic_enable - * - &drm_crtc_helper_funcs.commit - * - * and the encoder is enabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_enable - * - &drm_encoder_helper_funcs.enable - * - drm_encoder_helper_funcs.commit - * * The @atomic_enable callback is optional. */ void (*atomic_enable)(struct drm_bridge *bridge, @@ -424,32 +341,16 @@ struct drm_bridge_funcs { /** * @atomic_disable: * - * The @atomic_disable callback should disable the bridge. + * This callback should disable the bridge. It is called right before + * the preceding element in the display pipe is disabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @atomic_disable or @disable vfunc. If the preceding element + * is a &drm_encoder it's called right before the + * &drm_encoder_helper_funcs.atomic_disable hook. * * The bridge can assume that the display pipe (i.e. clocks and timing * signals) feeding it is still running when this callback is called. * - * If the preceding element is a &drm_bridge, then this is called before - * that bridge is disabled via one of: - * - * - &drm_bridge_funcs.disable - * - &drm_bridge_funcs.atomic_disable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called before the encoder is disabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_disable - * - &drm_encoder_helper_funcs.prepare - * - &drm_encoder_helper_funcs.disable - * - &drm_encoder_helper_funcs.dpms - * - * and the CRTC is disabled via one of: - * - * - &drm_crtc_helper_funcs.prepare - * - &drm_crtc_helper_funcs.atomic_disable - * - &drm_crtc_helper_funcs.disable - * - &drm_crtc_helper_funcs.dpms. - * * The @atomic_disable callback is optional. */ void (*atomic_disable)(struct drm_bridge *bridge, @@ -458,34 +359,16 @@ struct drm_bridge_funcs { /** * @atomic_post_disable: * - * The bridge must assume that the display pipe (i.e. clocks and timing - * signals) feeding this bridge is no longer running when the - * @atomic_post_disable is called. - * - * This callback should perform all the actions required by the hardware - * after it has stopped receiving signals from the preceding element. + * This callback should disable the bridge. It is called right after the + * preceding element in the display pipe is disabled. If the preceding + * element is a bridge this means it's called after that bridge's + * @atomic_post_disable or @post_disable function. If the preceding + * element is a &drm_encoder it's called right after the encoder's + * &drm_encoder_helper_funcs.atomic_disable hook. * - * If the preceding element is a &drm_bridge, then this is called after - * that bridge is post-disabled (unless marked otherwise by the - * @pre_enable_prev_first flag) via one of: - * - * - &drm_bridge_funcs.post_disable - * - &drm_bridge_funcs.atomic_post_disable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called after the encoder is disabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_disable - * - &drm_encoder_helper_funcs.prepare - * - &drm_encoder_helper_funcs.disable - * - &drm_encoder_helper_funcs.dpms - * - * and the CRTC is disabled via one of: - * - * - &drm_crtc_helper_funcs.prepare - * - &drm_crtc_helper_funcs.atomic_disable - * - &drm_crtc_helper_funcs.disable - * - &drm_crtc_helper_funcs.dpms + * The bridge must assume that the display pipe (i.e. clocks and timing + * signals) feeding it is no longer running when this callback is + * called. * * The @atomic_post_disable callback is optional. */ diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h index f6e7e234c089..eb29e5309f0a 100644 --- a/include/drm/drm_pagemap.h +++ b/include/drm/drm_pagemap.h @@ -8,6 +8,7 @@ #define NR_PAGES(order) (1U << (order)) +struct dma_fence; struct drm_pagemap; struct drm_pagemap_zdd; struct device; @@ -174,6 +175,8 @@ struct drm_pagemap_devmem_ops { * @pages: Pointer to array of device memory pages (destination) * @pagemap_addr: Pointer to array of DMA information (source) * @npages: Number of pages to copy + * @pre_migrate_fence: dma-fence to wait for before migration start. + * May be NULL. * * Copy pages to device memory. If the order of a @pagemap_addr entry * is greater than 0, the entry is populated but subsequent entries @@ -183,13 +186,16 @@ struct drm_pagemap_devmem_ops { */ int (*copy_to_devmem)(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages); + unsigned long npages, + struct dma_fence *pre_migrate_fence); /** * @copy_to_ram: Copy to system RAM (required for migration) * @pages: Pointer to array of device memory pages (source) * @pagemap_addr: Pointer to array of DMA information (destination) * @npages: Number of pages to copy + * @pre_migrate_fence: dma-fence to wait for before migration start. + * May be NULL. * * Copy pages to system RAM. If the order of a @pagemap_addr entry * is greater than 0, the entry is populated but subsequent entries @@ -199,9 +205,23 @@ struct drm_pagemap_devmem_ops { */ int (*copy_to_ram)(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages); + unsigned long npages, + struct dma_fence *pre_migrate_fence); }; +#if IS_ENABLED(CONFIG_ZONE_DEVICE) + +struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page); + +#else + +static inline struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page) +{ + return NULL; +} + +#endif /* IS_ENABLED(CONFIG_ZONE_DEVICE) */ + /** * struct drm_pagemap_devmem - Structure representing a GPU SVM device memory allocation * @@ -212,6 +232,8 @@ struct drm_pagemap_devmem_ops { * @dpagemap: The struct drm_pagemap of the pages this allocation belongs to. * @size: Size of device memory allocation * @timeslice_expiration: Timeslice expiration in jiffies + * @pre_migrate_fence: Fence to wait for or pipeline behind before migration starts. + * (May be NULL). */ struct drm_pagemap_devmem { struct device *dev; @@ -221,8 +243,11 @@ struct drm_pagemap_devmem { struct drm_pagemap *dpagemap; size_t size; u64 timeslice_expiration; + struct dma_fence *pre_migrate_fence; }; +#if IS_ENABLED(CONFIG_ZONE_DEVICE) + int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, struct mm_struct *mm, unsigned long start, unsigned long end, @@ -233,16 +258,17 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation); const struct dev_pagemap_ops *drm_pagemap_pagemap_ops_get(void); -struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page); - void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, struct device *dev, struct mm_struct *mm, const struct drm_pagemap_devmem_ops *ops, - struct drm_pagemap *dpagemap, size_t size); + struct drm_pagemap *dpagemap, size_t size, + struct dma_fence *pre_migrate_fence); int drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, unsigned long start, unsigned long end, struct mm_struct *mm, unsigned long timeslice_ms); +#endif /* IS_ENABLED(CONFIG_ZONE_DEVICE) */ + #endif diff --git a/include/dt-bindings/power/qcom,rpmhpd.h b/include/dt-bindings/power/qcom,rpmhpd.h index 50e7c886709d..06851363ae0e 100644 --- a/include/dt-bindings/power/qcom,rpmhpd.h +++ b/include/dt-bindings/power/qcom,rpmhpd.h @@ -264,5 +264,6 @@ #define SC8280XP_NSP 13 #define SC8280XP_QPHY 14 #define SC8280XP_XO 15 +#define SC8280XP_MXC_AO 16 #endif diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h index 04b18d0e37af..30fbbde81c5c 100644 --- a/include/hyperv/hvgdk_mini.h +++ b/include/hyperv/hvgdk_mini.h @@ -578,9 +578,12 @@ struct hv_tlb_flush { /* HV_INPUT_FLUSH_VIRTUAL_ADDRESS_LIST */ struct hv_tlb_flush_ex { u64 address_space; u64 flags; - struct hv_vpset hv_vp_set; - u64 gva_list[]; + __TRAILING_OVERLAP(struct hv_vpset, hv_vp_set, bank_contents, __packed, + u64 gva_list[]; + ); } __packed; +static_assert(offsetof(struct hv_tlb_flush_ex, hv_vp_set.bank_contents) == + offsetof(struct hv_tlb_flush_ex, gva_list)); struct ms_hyperv_tsc_page { /* HV_REFERENCE_TSC_PAGE */ volatile u32 tsc_sequence; diff --git a/include/hyperv/hvhdk.h b/include/hyperv/hvhdk.h index 469186df7826..08965970c17d 100644 --- a/include/hyperv/hvhdk.h +++ b/include/hyperv/hvhdk.h @@ -800,6 +800,53 @@ struct hv_x64_memory_intercept_message { u8 instruction_bytes[16]; } __packed; +#if IS_ENABLED(CONFIG_ARM64) +union hv_arm64_vp_execution_state { + u16 as_uint16; + struct { + u16 cpl:2; /* Exception Level (EL) */ + u16 debug_active:1; + u16 interruption_pending:1; + u16 vtl:4; + u16 virtualization_fault_active:1; + u16 reserved:7; + } __packed; +}; + +struct hv_arm64_intercept_message_header { + u32 vp_index; + u8 instruction_length; + u8 intercept_access_type; + union hv_arm64_vp_execution_state execution_state; + u64 pc; + u64 cpsr; +} __packed; + +union hv_arm64_memory_access_info { + u8 as_uint8; + struct { + u8 gva_valid:1; + u8 gva_gpa_valid:1; + u8 hypercall_output_pending:1; + u8 reserved:5; + } __packed; +}; + +struct hv_arm64_memory_intercept_message { + struct hv_arm64_intercept_message_header header; + u32 cache_type; /* enum hv_cache_type */ + u8 instruction_byte_count; + union hv_arm64_memory_access_info memory_access_info; + u16 reserved1; + u8 instruction_bytes[4]; + u32 reserved2; + u64 guest_virtual_address; + u64 guest_physical_address; + u64 syndrome; +} __packed; + +#endif /* CONFIG_ARM64 */ + /* * Dispatch state for the VP communicated by the hypervisor to the * VP-dispatching thread in the root on return from HVCALL_DISPATCH_VP. diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h index 108e96433ea4..c89b1b1b12dd 100644 --- a/include/kunit/run-in-irq-context.h +++ b/include/kunit/run-in-irq-context.h @@ -20,8 +20,8 @@ struct kunit_irq_test_state { bool task_func_reported_failure; bool hardirq_func_reported_failure; bool softirq_func_reported_failure; - unsigned long hardirq_func_calls; - unsigned long softirq_func_calls; + atomic_t hardirq_func_calls; + atomic_t softirq_func_calls; struct hrtimer timer; struct work_struct bh_work; }; @@ -32,7 +32,7 @@ static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer) container_of(timer, typeof(*state), timer); WARN_ON_ONCE(!in_hardirq()); - state->hardirq_func_calls++; + atomic_inc(&state->hardirq_func_calls); if (!state->func(state->test_specific_state)) state->hardirq_func_reported_failure = true; @@ -48,7 +48,7 @@ static void kunit_irq_test_bh_work_func(struct work_struct *work) container_of(work, typeof(*state), bh_work); WARN_ON_ONCE(!in_serving_softirq()); - state->softirq_func_calls++; + atomic_inc(&state->softirq_func_calls); if (!state->func(state->test_specific_state)) state->softirq_func_reported_failure = true; @@ -59,7 +59,10 @@ static void kunit_irq_test_bh_work_func(struct work_struct *work) * hardirq context concurrently, and reports a failure to KUnit if any * invocation of @func in any context returns false. @func is passed * @test_specific_state as its argument. At most 3 invocations of @func will - * run concurrently: one in each of task, softirq, and hardirq context. + * run concurrently: one in each of task, softirq, and hardirq context. @func + * will continue running until either @max_iterations calls have been made (so + * long as at least one each runs in task, softirq, and hardirq contexts), or + * one second has passed. * * The main purpose of this interrupt context testing is to validate fallback * code paths that run in contexts where the normal code path cannot be used, @@ -85,6 +88,8 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), .test_specific_state = test_specific_state, }; unsigned long end_jiffies; + int hardirq_calls, softirq_calls; + bool allctx = false; /* * Set up a hrtimer (the way we access hardirq context) and a work @@ -94,14 +99,25 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); INIT_WORK_ONSTACK(&state.bh_work, kunit_irq_test_bh_work_func); - /* Run for up to max_iterations or 1 second, whichever comes first. */ + /* + * Run for up to max_iterations (including at least one task, softirq, + * and hardirq), or 1 second, whichever comes first. + */ end_jiffies = jiffies + HZ; hrtimer_start(&state.timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL, HRTIMER_MODE_REL_HARD); - for (int i = 0; i < max_iterations && !time_after(jiffies, end_jiffies); - i++) { + for (int task_calls = 0, calls = 0; + ((calls < max_iterations) || !allctx) && + !time_after(jiffies, end_jiffies); + task_calls++) { if (!func(test_specific_state)) state.task_func_reported_failure = true; + + hardirq_calls = atomic_read(&state.hardirq_func_calls); + softirq_calls = atomic_read(&state.softirq_func_calls); + calls = task_calls + hardirq_calls + softirq_calls; + allctx = (task_calls > 0) && (hardirq_calls > 0) && + (softirq_calls > 0); } /* Cancel the timer and work. */ @@ -109,21 +125,18 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), flush_work(&state.bh_work); /* Sanity check: the timer and BH functions should have been run. */ - KUNIT_EXPECT_GT_MSG(test, state.hardirq_func_calls, 0, + KUNIT_EXPECT_GT_MSG(test, atomic_read(&state.hardirq_func_calls), 0, "Timer function was not called"); - KUNIT_EXPECT_GT_MSG(test, state.softirq_func_calls, 0, + KUNIT_EXPECT_GT_MSG(test, atomic_read(&state.softirq_func_calls), 0, "BH work function was not called"); - /* Check for incorrect hash values reported from any context. */ - KUNIT_EXPECT_FALSE_MSG( - test, state.task_func_reported_failure, - "Incorrect hash values reported from task context"); - KUNIT_EXPECT_FALSE_MSG( - test, state.hardirq_func_reported_failure, - "Incorrect hash values reported from hardirq context"); - KUNIT_EXPECT_FALSE_MSG( - test, state.softirq_func_reported_failure, - "Incorrect hash values reported from softirq context"); + /* Check for failure reported from any context. */ + KUNIT_EXPECT_FALSE_MSG(test, state.task_func_reported_failure, + "Failure reported from task context"); + KUNIT_EXPECT_FALSE_MSG(test, state.hardirq_func_reported_failure, + "Failure reported from hardirq context"); + KUNIT_EXPECT_FALSE_MSG(test, state.softirq_func_reported_failure, + "Failure reported from softirq context"); } #endif /* _KUNIT_RUN_IN_IRQ_CONTEXT_H */ diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h index 8afa92d15a66..1e99fda2b380 100644 --- a/include/linux/can/can-ml.h +++ b/include/linux/can/can-ml.h @@ -46,6 +46,12 @@ #include <linux/list.h> #include <linux/netdevice.h> +/* exposed CAN device capabilities for network layer */ +#define CAN_CAP_CC BIT(0) /* CAN CC aka Classical CAN */ +#define CAN_CAP_FD BIT(1) /* CAN FD */ +#define CAN_CAP_XL BIT(2) /* CAN XL */ +#define CAN_CAP_RO BIT(3) /* read-only mode (LISTEN/RESTRICTED) */ + #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 #define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) @@ -64,6 +70,7 @@ struct can_ml_priv { #ifdef CAN_J1939 struct j1939_priv *j1939_priv; #endif + u32 can_cap; }; static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) @@ -77,4 +84,21 @@ static inline void can_set_ml_priv(struct net_device *dev, netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); } +static inline bool can_cap_enabled(struct net_device *dev, u32 cap) +{ + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (!can_ml) + return false; + + return (can_ml->can_cap & cap); +} + +static inline void can_set_cap(struct net_device *dev, u32 cap) +{ + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + can_ml->can_cap = cap; +} + #endif /* CAN_ML_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index f6416a56e95d..6d0710d6f571 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -111,18 +111,12 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, void free_candev(struct net_device *dev); /* a candev safe wrapper around netdev_priv */ -#if IS_ENABLED(CONFIG_CAN_NETLINK) struct can_priv *safe_candev_priv(struct net_device *dev); -#else -static inline struct can_priv *safe_candev_priv(struct net_device *dev) -{ - return NULL; -} -#endif int open_candev(struct net_device *dev); void close_candev(struct net_device *dev); void can_set_default_mtu(struct net_device *dev); +void can_set_cap_info(struct net_device *dev); int __must_check can_set_static_ctrlmode(struct net_device *dev, u32 static_mode); int can_hwtstamp_get(struct net_device *netdev, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index b760a3c470a5..f7cc60de0058 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -626,7 +626,13 @@ struct cgroup { #endif /* All ancestors including self */ - struct cgroup *ancestors[]; + union { + DECLARE_FLEX_ARRAY(struct cgroup *, ancestors); + struct { + struct cgroup *_root_ancestor; + DECLARE_FLEX_ARRAY(struct cgroup *, _low_ancestors); + }; + }; }; /* @@ -647,16 +653,6 @@ struct cgroup_root { struct list_head root_list; struct rcu_head rcu; /* Must be near the top */ - /* - * The root cgroup. The containing cgroup_root will be destroyed on its - * release. cgrp->ancestors[0] will be used overflowing into the - * following field. cgrp_ancestor_storage must immediately follow. - */ - struct cgroup cgrp; - - /* must follow cgrp for cgrp->ancestors[0], see above */ - struct cgroup *cgrp_ancestor_storage; - /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; @@ -668,6 +664,13 @@ struct cgroup_root { /* The name for this hierarchy - may be empty */ char name[MAX_CGROUP_ROOT_NAMELEN]; + + /* + * The root cgroup. The containing cgroup_root will be destroyed on its + * release. This must be embedded last due to flexible array at the end + * of struct cgroup. + */ + struct cgroup cgrp; }; /* diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index cd8e0f0a634b..bbc67ec513ed 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -85,6 +85,8 @@ enum probe_type { * uevent. * @p: Driver core's private data, no one other than the driver * core can touch this. + * @p_cb: Callbacks private to the driver core; no one other than the + * driver core is allowed to touch this. * * The device driver-model tracks all of the drivers known to the system. * The main reason for this tracking is to enable the driver core to match @@ -119,6 +121,13 @@ struct device_driver { void (*coredump) (struct device *dev); struct driver_private *p; + struct { + /* + * Called after remove() and after all devres entries have been + * processed. This is a Rust only callback. + */ + void (*post_unbind_rust)(struct device *dev); + } p_cb; }; diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 43aa6153dc57..e7497f804644 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -18,7 +18,7 @@ * @power: The power consumed at this level (by 1 CPU or by a registered * device). It can be a total power: static and dynamic. * @cost: The cost coefficient associated with this level, used during - * energy calculation. Equal to: power * max_frequency / frequency + * energy calculation. Equal to: 10 * power * max_frequency / frequency * @flags: see "em_perf_state flags" description below. */ struct em_perf_state { diff --git a/include/linux/filelock.h b/include/linux/filelock.h index 54b824c05299..2f5e5588ee07 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -49,6 +49,7 @@ struct lease_manager_operations { int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); + int (*lm_open_conflict)(struct file *, int); }; struct lock_manager { diff --git a/include/linux/fs.h b/include/linux/fs.h index f5c9cf28c4dc..a01621fa636a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1855,6 +1855,8 @@ struct dir_context { * INT_MAX unlimited */ int count; + /* @actor supports these flags in d_type high bits */ + unsigned int dt_flags_mask; }; /* If OR-ed with d_type, pending signals are not checked */ @@ -3524,7 +3526,9 @@ static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { - return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); + unsigned int dt_mask = S_DT_MASK | ctx->dt_flags_mask; + + return ctx->actor(ctx, name, namelen, ctx->pos, ino, type & dt_mask); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 770f0dc993cc..a3a8989e3268 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1167,7 +1167,7 @@ static inline void ftrace_init(void) { } */ struct ftrace_graph_ent { unsigned long func; /* Current function */ - unsigned long depth; + long depth; /* signed to check for less than zero */ } __packed; /* diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 0bd581003cd5..60de63e46b33 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -44,6 +44,7 @@ struct gen_pool; * @nr: The number of zeroed bits we're looking for * @data: optional additional data used by the callback * @pool: the pool being allocated from + * @start_addr: start address of memory chunk */ typedef unsigned long (*genpool_algo_t)(unsigned long *map, unsigned long size, diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 2cf1bf65b225..0de12f14d6a4 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -2,7 +2,7 @@ /* * hrtimers - High-resolution kernel timers * - * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 019a1c5281e4..e51b8ef0cebd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -240,8 +240,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); @@ -300,13 +301,17 @@ static inline struct address_space *hugetlb_folio_mapping_lock_write( return NULL; } -static inline int huge_pmd_unshare(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline int huge_pmd_unshare(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } +static inline void huge_pmd_unshare_flush(struct mmu_gather *tlb, + struct vm_area_struct *vma) +{ +} + static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) @@ -1326,7 +1331,7 @@ static inline __init void hugetlb_cma_reserve(int order) #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { - return page_count(virt_to_page(pte)) > 1; + return ptdesc_pmd_is_shared(virt_to_ptdesc(pte)); } #else static inline bool hugetlb_pmd_shared(pte_t *pte) diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 4247497f3f8b..b87841a355f8 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -14,6 +14,7 @@ * @mlock: lock used to prevent simultaneous device state changes * @mlock_key: lockdep class for iio_dev lock * @info_exist_lock: lock to prevent use during removal + * @info_exist_key: lockdep class for info_exist lock * @trig_readonly: mark the current trigger immutable * @event_interface: event chrdevs associated with interrupt lines * @attached_buffers: array of buffers statically attached by the driver @@ -47,6 +48,7 @@ struct iio_dev_opaque { struct mutex mlock; struct lock_class_key mlock_key; struct mutex info_exist_lock; + struct lock_class_key info_exist_key; bool trig_readonly; struct iio_event_interface *event_interface; struct iio_buffer **attached_buffers; diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h index 53f6fe88e369..1a0f357c2427 100644 --- a/include/linux/intel_vsec.h +++ b/include/linux/intel_vsec.h @@ -80,13 +80,13 @@ enum intel_vsec_quirks { /** * struct pmt_callbacks - Callback infrastructure for PMT devices - * ->read_telem() when specified, called by client driver to access PMT data (instead - * of direct copy). - * @pdev: PCI device reference for the callback's use - * @guid: ID of data to acccss - * @data: buffer for the data to be copied - * @off: offset into the requested buffer - * @count: size of buffer + * @read_telem: when specified, called by client driver to access PMT + * data (instead of direct copy). + * * pdev: PCI device reference for the callback's use + * * guid: ID of data to acccss + * * data: buffer for the data to be copied + * * off: offset into the requested buffer + * * count: size of buffer */ struct pmt_callbacks { int (*read_telem)(struct pci_dev *pdev, u32 guid, u64 *data, loff_t off, u32 count); @@ -120,7 +120,7 @@ struct intel_vsec_platform_info { }; /** - * struct intel_sec_device - Auxbus specific device information + * struct intel_vsec_device - Auxbus specific device information * @auxdev: auxbus device struct for auxbus access * @pcidev: pci device associated with the device * @resource: any resources shared by the parent @@ -128,6 +128,7 @@ struct intel_vsec_platform_info { * @num_resources: number of resources * @id: xarray id * @priv_data: any private data needed + * @priv_data_size: size of private data area * @quirks: specified quirks * @base_addr: base address of entries (if specified) * @cap_id: the enumerated id of the vsec feature diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index e1adb0d20a0a..a3e8ddc9b380 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -424,11 +424,17 @@ struct io_ring_ctx { struct user_struct *user; struct mm_struct *mm_account; + /* + * List of tctx nodes for this ctx, protected by tctx_lock. For + * cancelation purposes, nests under uring_lock. + */ + struct list_head tctx_list; + struct mutex tctx_lock; + /* ctx exit and cancelation */ struct llist_head fallback_llist; struct delayed_work fallback_work; struct work_struct exit_work; - struct list_head tctx_list; struct completion ref_comp; /* io-wq management, e.g. thread count */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 520e967cb501..6bb941707d12 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -88,6 +88,9 @@ struct vm_fault; /* * Flags set by the core iomap code during operations: * + * IOMAP_F_FOLIO_BATCH indicates that the folio batch mechanism is active + * for this operation, set by iomap_fill_dirty_folios(). + * * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size * has changed as the result of this write operation. * @@ -95,6 +98,7 @@ struct vm_fault; * range it covers needs to be remapped by the high level before the operation * can proceed. */ +#define IOMAP_F_FOLIO_BATCH (1U << 13) #define IOMAP_F_SIZE_CHANGED (1U << 14) #define IOMAP_F_STALE (1U << 15) @@ -352,8 +356,8 @@ bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops); -loff_t iomap_fill_dirty_folios(struct iomap_iter *iter, loff_t offset, - loff_t length); +unsigned int iomap_fill_dirty_folios(struct iomap_iter *iter, loff_t *start, + loff_t end, unsigned int *iomap_flags); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private); diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h index 6ab913e57da0..d26d1b1bcbfb 100644 --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@ -110,7 +110,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs) static inline void local_irq_enable_exit_to_user(unsigned long ti_work); #ifndef local_irq_enable_exit_to_user -static inline void local_irq_enable_exit_to_user(unsigned long ti_work) +static __always_inline void local_irq_enable_exit_to_user(unsigned long ti_work) { local_irq_enable(); } @@ -125,7 +125,7 @@ static inline void local_irq_enable_exit_to_user(unsigned long ti_work) static inline void local_irq_disable_exit_to_user(void); #ifndef local_irq_disable_exit_to_user -static inline void local_irq_disable_exit_to_user(void) +static __always_inline void local_irq_disable_exit_to_user(void) { local_irq_disable(); } diff --git a/include/linux/kasan.h b/include/linux/kasan.h index f335c1d7b61d..338a1921a50a 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -28,6 +28,7 @@ typedef unsigned int __bitwise kasan_vmalloc_flags_t; #define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) #define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) #define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) +#define KASAN_VMALLOC_KEEP_TAG ((__force kasan_vmalloc_flags_t)0x08u) #define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */ #define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */ @@ -630,6 +631,27 @@ static __always_inline void kasan_poison_vmalloc(const void *start, __kasan_poison_vmalloc(start, size); } +void __kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags); +static __always_inline void +kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ + if (kasan_enabled()) + __kasan_unpoison_vmap_areas(vms, nr_vms, flags); +} + +void __kasan_vrealloc(const void *start, unsigned long old_size, + unsigned long new_size); + +static __always_inline void kasan_vrealloc(const void *start, + unsigned long old_size, + unsigned long new_size) +{ + if (kasan_enabled()) + __kasan_vrealloc(start, old_size, new_size); +} + #else /* CONFIG_KASAN_VMALLOC */ static inline void kasan_populate_early_vm_area_shadow(void *start, @@ -654,6 +676,14 @@ static inline void *kasan_unpoison_vmalloc(const void *start, static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } +static __always_inline void +kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ } + +static inline void kasan_vrealloc(const void *start, unsigned long old_size, + unsigned long new_size) { } + #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index ff7e231b0485..8a22bc9b8c6c 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -530,7 +530,7 @@ extern bool kexec_file_dbg_print; #define kexec_dprintk(fmt, arg...) \ do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0) -extern void *kimage_map_segment(struct kimage *image, unsigned long addr, unsigned long size); +extern void *kimage_map_segment(struct kimage *image, int idx); extern void kimage_unmap_segment(void *buffer); #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; @@ -540,7 +540,7 @@ static inline void __crash_kexec(struct pt_regs *regs) { } static inline void crash_kexec(struct pt_regs *regs) { } static inline int kexec_should_crash(struct task_struct *p) { return 0; } static inline int kexec_crash_loaded(void) { return 0; } -static inline void *kimage_map_segment(struct kimage *image, unsigned long addr, unsigned long size) +static inline void *kimage_map_segment(struct kimage *image, int idx) { return NULL; } static inline void kimage_unmap_segment(void *buffer) { } #define kexec_in_progress false diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 0ad1ddbb8b99..e5822f6e7f27 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -211,6 +211,7 @@ struct kmem_obj_info; * __kfence_obj_info() - fill kmem_obj_info struct * @kpp: kmem_obj_info to be filled * @object: the object + * @slab: the slab * * Return: * * false - not a KFENCE object diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 383ed9985802..f247e564602f 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -3,7 +3,7 @@ * * ktime_t - nanosecond-resolution time format. * - * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes and macros. diff --git a/include/linux/leafops.h b/include/linux/leafops.h index cfafe7a5e7b1..a9ff94b744f2 100644 --- a/include/linux/leafops.h +++ b/include/linux/leafops.h @@ -133,7 +133,7 @@ static inline bool softleaf_is_none(softleaf_t entry) /** * softleaf_type() - Identify the type of leaf entry. - * @enntry: Leaf entry. + * @entry: Leaf entry. * * Returns: the leaf entry type associated with @entry. */ @@ -534,7 +534,7 @@ static inline bool pte_is_uffd_wp_marker(pte_t pte) /** * pte_is_uffd_marker() - Does this PTE entry encode a userfault-specific marker * leaf entry? - * @entry: Leaf entry. + * @pte: PTE entry. * * It's useful to be able to determine which leaf entries encode UFFD-specific * markers so we can handle these correctly. diff --git a/include/linux/memfd.h b/include/linux/memfd.h index cc74de3dbcfe..c328a7b356d0 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -17,6 +17,7 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); * to by vm_flags_ptr. */ int memfd_check_seals_mmap(struct file *file, vm_flags_t *vm_flags_ptr); +struct file *memfd_alloc_file(const char *name, unsigned int flags); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -31,6 +32,11 @@ static inline int memfd_check_seals_mmap(struct file *file, { return 0; } + +static inline struct file *memfd_alloc_file(const char *name, unsigned int flags) +{ + return ERR_PTR(-EINVAL); +} #endif #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/memory-failure.h b/include/linux/memory-failure.h index bc326503d2d2..7b5e11cf905f 100644 --- a/include/linux/memory-failure.h +++ b/include/linux/memory-failure.h @@ -9,6 +9,8 @@ struct pfn_address_space; struct pfn_address_space { struct interval_tree_node node; struct address_space *mapping; + int (*pfn_to_vma_pgoff)(struct vm_area_struct *vma, + unsigned long pfn, pgoff_t *pgoff); }; int register_pfn_address_space(struct pfn_address_space *pfn_space); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 713ec0435b48..e3c2ccf872a8 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -224,7 +224,8 @@ static inline bool is_fsdax_page(const struct page *page) } #ifdef CONFIG_ZONE_DEVICE -void zone_device_page_init(struct page *page, unsigned int order); +void zone_device_page_init(struct page *page, struct dev_pagemap *pgmap, + unsigned int order); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); @@ -234,9 +235,11 @@ bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long memremap_compat_align(void); -static inline void zone_device_folio_init(struct folio *folio, unsigned int order) +static inline void zone_device_folio_init(struct folio *folio, + struct dev_pagemap *pgmap, + unsigned int order) { - zone_device_page_init(&folio->page, order); + zone_device_page_init(&folio->page, pgmap, order); if (order) folio_set_large_rmappable(folio); } diff --git a/include/linux/mm.h b/include/linux/mm.h index 15076261d0c2..f0d5be9dc736 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -608,7 +608,11 @@ enum { /* * Flags which should result in page tables being copied on fork. These are * flags which indicate that the VMA maps page tables which cannot be - * reconsistuted upon page fault, so necessitate page table copying upon + * reconsistuted upon page fault, so necessitate page table copying upon fork. + * + * Note that these flags should be compared with the DESTINATION VMA not the + * source, as VM_UFFD_WP may not be propagated to destination, while all other + * flags will be. * * VM_PFNMAP / VM_MIXEDMAP - These contain kernel-mapped data which cannot be * reasonably reconstructed on page fault. @@ -2459,10 +2463,10 @@ static inline int folio_expected_ref_count(const struct folio *folio) if (WARN_ON_ONCE(page_has_type(&folio->page) && !folio_test_hugetlb(folio))) return 0; - if (folio_test_anon(folio)) { - /* One reference per page from the swapcache. */ - ref_count += folio_test_swapcache(folio) << order; - } else { + /* One reference per page from the swapcache. */ + ref_count += folio_test_swapcache(folio) << order; + + if (!folio_test_anon(folio)) { /* One reference per page from the pagecache. */ ref_count += !!folio->mapping << order; /* One reference from PG_private. */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 42af2292951d..78950eb8926d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1329,7 +1329,7 @@ struct mm_struct { * The mm_cpumask needs to be at the end of mm_struct, because it * is dynamically sized based on nr_cpu_ids. */ - unsigned long cpu_bitmap[]; + char flexible_array[] __aligned(__alignof__(unsigned long)); }; /* Copy value to the first system word of mm flags, non-atomically. */ @@ -1366,19 +1366,24 @@ static inline void __mm_flags_set_mask_bits_word(struct mm_struct *mm, MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; +#define MM_STRUCT_FLEXIBLE_ARRAY_INIT \ +{ \ + [0 ... sizeof(cpumask_t) + MM_CID_STATIC_SIZE - 1] = 0 \ +} + /* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { unsigned long cpu_bitmap = (unsigned long)mm; - cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); + cpu_bitmap += offsetof(struct mm_struct, flexible_array); cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { - return (struct cpumask *)&mm->cpu_bitmap; + return (struct cpumask *)&mm->flexible_array; } #ifdef CONFIG_LRU_GEN @@ -1469,7 +1474,7 @@ static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm) { unsigned long bitmap = (unsigned long)mm; - bitmap += offsetof(struct mm_struct, cpu_bitmap); + bitmap += offsetof(struct mm_struct, flexible_array); /* Skip cpu_bitmap */ bitmap += cpumask_size(); return (struct cpumask *)bitmap; @@ -1495,7 +1500,7 @@ static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct * mm_init_cid(mm, p); return 0; } -#define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) +# define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) static inline void mm_destroy_cid(struct mm_struct *mm) { @@ -1509,6 +1514,8 @@ static inline unsigned int mm_cid_size(void) return cpumask_size() + bitmap_size(num_possible_cpus()); } +/* Use 2 * NR_CPUS as worse case for static allocation. */ +# define MM_CID_STATIC_SIZE (2 * sizeof(cpumask_t)) #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { } static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; } @@ -1517,11 +1524,13 @@ static inline unsigned int mm_cid_size(void) { return 0; } +# define MM_CID_STATIC_SIZE 0 #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma); extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 75ef7c9f9307..fc5d6c88d2f0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1648,14 +1648,15 @@ static inline int is_highmem(const struct zone *zone) return is_highmem_idx(zone_idx(zone)); } -#ifdef CONFIG_ZONE_DMA -bool has_managed_dma(void); -#else +bool has_managed_zone(enum zone_type zone); static inline bool has_managed_dma(void) { +#ifdef CONFIG_ZONE_DMA + return has_managed_zone(ZONE_DMA); +#else return false; -} #endif +} #ifndef CONFIG_NUMA diff --git a/include/linux/mtd/jedec.h b/include/linux/mtd/jedec.h index 56047a4e54c9..255972f3d88d 100644 --- a/include/linux/mtd/jedec.h +++ b/include/linux/mtd/jedec.h @@ -2,7 +2,7 @@ /* * Copyright © 2000-2010 David Woodhouse <dwmw2@infradead.org> * Steven J. Hill <sjhill@realitydiluted.com> - * Thomas Gleixner <tglx@linutronix.de> + * Thomas Gleixner <tglx@kernel.org> * * Contains all JEDEC related definitions */ diff --git a/include/linux/mtd/nand-ecc-sw-hamming.h b/include/linux/mtd/nand-ecc-sw-hamming.h index c6c71894c575..2aa2f8ef68d2 100644 --- a/include/linux/mtd/nand-ecc-sw-hamming.h +++ b/include/linux/mtd/nand-ecc-sw-hamming.h @@ -2,7 +2,7 @@ /* * Copyright (C) 2000-2010 Steven J. Hill <sjhill@realitydiluted.com> * David Woodhouse <dwmw2@infradead.org> - * Thomas Gleixner <tglx@linutronix.de> + * Thomas Gleixner <tglx@kernel.org> * * This file is the header for the NAND Hamming ECC implementation. */ diff --git a/include/linux/mtd/ndfc.h b/include/linux/mtd/ndfc.h index 98f075b86931..622891191e9c 100644 --- a/include/linux/mtd/ndfc.h +++ b/include/linux/mtd/ndfc.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2006 Thomas Gleixner <tglx@linutronix.de> + * Copyright (c) 2006 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * Info: * Contains defines, datastructures for ndfc nand controller diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index 55ab2e4d62f9..09a5cbd8f232 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -2,7 +2,7 @@ /* * Copyright © 2000-2010 David Woodhouse <dwmw2@infradead.org> * Steven J. Hill <sjhill@realitydiluted.com> - * Thomas Gleixner <tglx@linutronix.de> + * Thomas Gleixner <tglx@kernel.org> * * Contains all ONFI related definitions */ diff --git a/include/linux/mtd/platnand.h b/include/linux/mtd/platnand.h index bc11eb6b593b..2df6fba699f2 100644 --- a/include/linux/mtd/platnand.h +++ b/include/linux/mtd/platnand.h @@ -2,7 +2,7 @@ /* * Copyright © 2000-2010 David Woodhouse <dwmw2@infradead.org> * Steven J. Hill <sjhill@realitydiluted.com> - * Thomas Gleixner <tglx@linutronix.de> + * Thomas Gleixner <tglx@kernel.org> * * Contains all platform NAND related definitions. */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index d30bdc3fcfd7..5c70e7bd3ed5 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -2,7 +2,7 @@ /* * Copyright © 2000-2010 David Woodhouse <dwmw2@infradead.org> * Steven J. Hill <sjhill@realitydiluted.com> - * Thomas Gleixner <tglx@linutronix.de> + * Thomas Gleixner <tglx@kernel.org> * * Info: * Contains standard defines and IDs for NAND flash devices diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5870a9e514a5..d99b0fbc1942 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5323,7 +5323,8 @@ netdev_features_t netdev_increment_features(netdev_features_t all, static inline netdev_features_t netdev_add_tso_features(netdev_features_t features, netdev_features_t mask) { - return netdev_increment_features(features, NETIF_F_ALL_TSO, mask); + return netdev_increment_features(features, NETIF_F_ALL_TSO | + NETIF_F_ALL_FOR_ALL, mask); } int __netdev_update_features(struct net_device *dev); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a6624edb7226..8dd79a3f3d66 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -637,6 +637,7 @@ extern int nfs_update_folio(struct file *file, struct folio *folio, extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_folio(struct inode *inode, struct folio *folio); +extern int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index cf3c6ab408aa..207156f2143c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -83,6 +83,7 @@ static inline void reset_hung_task_detector(void) { } #if defined(CONFIG_HARDLOCKUP_DETECTOR) extern void hardlockup_detector_disable(void); extern unsigned int hardlockup_panic; +extern unsigned long hardlockup_si_mask; #else static inline void hardlockup_detector_disable(void) {} #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 31a848485ad9..ec442af3f886 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -210,6 +210,7 @@ enum mapping_flags { AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ + AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -345,6 +346,16 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } +static inline void mapping_set_no_data_integrity(struct address_space *mapping) +{ + set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); +} + +static inline bool mapping_no_data_integrity(const struct address_space *mapping) +{ + return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; diff --git a/include/linux/pci.h b/include/linux/pci.h index 864775651c6f..b5cc0c2b9906 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2210,6 +2210,10 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, { return -ENOSPC; } + +static inline void pci_free_irq_vectors(struct pci_dev *dev) +{ +} #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9870d768db4c..9ded2e582c60 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1,7 +1,7 @@ /* * Performance events: * - * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008-2009, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * diff --git a/include/linux/plist.h b/include/linux/plist.h index 8c1c8adf7fe9..16cf4355b5c1 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -8,7 +8,7 @@ * 2001-2005 (c) MontaVista Software, Inc. * Daniel Walker <dwalker@mvista.com> * - * (C) 2005 Thomas Gleixner <tglx@linutronix.de> + * (C) 2005 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * Simplifications of the original code by * Oleg Nesterov <oleg@tv-sign.ru> diff --git a/include/linux/rslib.h b/include/linux/rslib.h index a04dacbdc8ae..a2848f6907e3 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -2,7 +2,7 @@ /* * Generic Reed Solomon encoder / decoder library * - * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de) + * Copyright (C) 2004 Thomas Gleixner (tglx@kernel.org) * * RS code lifted from reed solomon library written by Phil Karn * Copyright 2002 Phil Karn, KA9Q diff --git a/include/linux/sched.h b/include/linux/sched.h index d395f2810fac..da0133524d08 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1874,7 +1874,6 @@ static inline int task_nice(const struct task_struct *p) extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); -extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0e1d73955fa5..95d0040df584 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -325,6 +325,7 @@ static inline void might_alloc(gfp_t gfp_mask) /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value + * @flags: Flags to add. * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). diff --git a/include/linux/soc/airoha/airoha_offload.h b/include/linux/soc/airoha/airoha_offload.h index 4d23cbb7d407..d01ef4a6b3d7 100644 --- a/include/linux/soc/airoha/airoha_offload.h +++ b/include/linux/soc/airoha/airoha_offload.h @@ -52,8 +52,8 @@ static inline void airoha_ppe_put_dev(struct airoha_ppe_dev *dev) { } -static inline int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, - void *type_data) +static inline int airoha_ppe_dev_setup_tc_block_cb(struct airoha_ppe_dev *dev, + void *type_data) { return -EOPNOTSUPP; } @@ -71,12 +71,12 @@ static inline void airoha_ppe_dev_check_skb(struct airoha_ppe_dev *dev, #define NPU_RX1_DESC_NUM 512 /* CTRL */ -#define NPU_RX_DMA_DESC_LAST_MASK BIT(29) -#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(28, 15) -#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(14, 1) +#define NPU_RX_DMA_DESC_LAST_MASK BIT(27) +#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(26, 14) +#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(13, 1) #define NPU_RX_DMA_DESC_DONE_MASK BIT(0) /* INFO */ -#define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 28) +#define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 29) #define NPU_RX_DMA_PKT_ID_MASK GENMASK(28, 26) #define NPU_RX_DMA_SRC_PORT_MASK GENMASK(25, 21) #define NPU_RX_DMA_CRSN_MASK GENMASK(20, 16) diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 6673e4d4ac2e..4933777404d6 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -35,6 +35,7 @@ struct ts_state * @get_pattern: return head of pattern * @get_pattern_len: return length of pattern * @owner: module reference to algorithm + * @list: list to search */ struct ts_ops { diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index ae04054a1be3..e6ca052b2a85 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -34,6 +34,13 @@ enum { TRACE_INTERNAL_SIRQ_BIT, TRACE_INTERNAL_TRANSITION_BIT, + /* Internal event use recursion bits */ + TRACE_INTERNAL_EVENT_BIT, + TRACE_INTERNAL_EVENT_NMI_BIT, + TRACE_INTERNAL_EVENT_IRQ_BIT, + TRACE_INTERNAL_EVENT_SIRQ_BIT, + TRACE_INTERNAL_EVENT_TRANSITION_BIT, + TRACE_BRANCH_BIT, /* * Abuse of the trace_recursion. @@ -58,6 +65,8 @@ enum { #define TRACE_LIST_START TRACE_INTERNAL_BIT +#define TRACE_EVENT_START TRACE_INTERNAL_EVENT_BIT + #define TRACE_CONTEXT_MASK ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) /* diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 18238dc8bfd3..334641e20fb1 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -3,7 +3,7 @@ * include/linux/uio_driver.h * * Copyright(C) 2005, Benedikt Spranger <b.spranger@linutronix.de> - * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2006, Hans J. Koch <hjk@hansjkoch.de> * Copyright(C) 2006, Greg Kroah-Hartman <greg@kroah.com> * diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 59409c1fc3de..2f7bd2fdc616 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -75,4 +75,7 @@ /* short SET_ADDRESS request timeout */ #define USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT BIT(16) +/* skip BOS descriptor request */ +#define USB_QUIRK_NO_BOS BIT(17) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 706877f998ff..1ac86896875c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -145,6 +145,13 @@ struct vfio_pci_core_device { struct list_head dmabufs; }; +enum vfio_pci_io_width { + VFIO_PCI_IO_WIDTH_1 = 1, + VFIO_PCI_IO_WIDTH_2 = 2, + VFIO_PCI_IO_WIDTH_4 = 4, + VFIO_PCI_IO_WIDTH_8 = 8, +}; + /* Will be exported for vfio pci drivers usage */ int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, unsigned int type, unsigned int subtype, @@ -188,7 +195,8 @@ pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, - size_t x_end, bool iswrite); + size_t x_end, bool iswrite, + enum vfio_pci_io_width max_width); bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev); bool vfio_pci_core_range_intersect_range(loff_t buf_start, size_t buf_cnt, loff_t reg_start, size_t reg_cnt, diff --git a/include/net/bonding.h b/include/net/bonding.h index 49edc7da0586..462078403557 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -521,13 +521,14 @@ static inline int bond_is_ip6_target_ok(struct in6_addr *addr) static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, struct slave *slave) { + unsigned long tmp, ret = READ_ONCE(slave->target_last_arp_rx[0]); int i = 1; - unsigned long ret = slave->target_last_arp_rx[0]; - - for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) - if (time_before(slave->target_last_arp_rx[i], ret)) - ret = slave->target_last_arp_rx[i]; + for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) { + tmp = READ_ONCE(slave->target_last_arp_rx[i]); + if (time_before(tmp, ret)) + ret = tmp; + } return ret; } @@ -537,7 +538,7 @@ static inline unsigned long slave_last_rx(struct bonding *bond, if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) return slave_oldest_target_arp_rx(bond, slave); - return slave->last_rx; + return READ_ONCE(slave->last_rx); } static inline void slave_update_last_tx(struct slave *slave) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 899f267b7cf9..2900202588a5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3221,8 +3221,6 @@ struct cfg80211_auth_request { * if this is %NULL for a link, that link is not requested * @elems: extra elements for the per-STA profile for this link * @elems_len: length of the elements - * @disabled: If set this link should be included during association etc. but it - * should not be used until enabled by the AP MLD. * @error: per-link error code, must be <= 0. If there is an error, then the * operation as a whole must fail. */ @@ -3230,7 +3228,6 @@ struct cfg80211_assoc_link { struct cfg80211_bss *bss; const u8 *elems; size_t elems_len; - bool disabled; int error; }; diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 58d91ccc56e0..a7b7abd66e21 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -67,6 +67,7 @@ FN(TC_EGRESS) \ FN(SECURITY_HOOK) \ FN(QDISC_DROP) \ + FN(QDISC_BURST_DROP) \ FN(QDISC_OVERLIMIT) \ FN(QDISC_CONGESTED) \ FN(CAKE_FLOOD) \ @@ -375,6 +376,11 @@ enum skb_drop_reason { */ SKB_DROP_REASON_QDISC_DROP, /** + * @SKB_DROP_REASON_QDISC_BURST_DROP: dropped when net.core.qdisc_max_burst + * limit is hit. + */ + SKB_DROP_REASON_QDISC_BURST_DROP, + /** * @SKB_DROP_REASON_QDISC_OVERLIMIT: dropped by qdisc when a qdisc * instance exceeds its total buffer size limit. */ diff --git a/include/net/dsa.h b/include/net/dsa.h index cced1a866757..6b2b5ed64ea4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -302,6 +302,7 @@ struct dsa_port { struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; + netdevice_tracker conduit_tracker; struct dsa_lag *lag; struct net_device *hsr_dev; diff --git a/include/net/hotdata.h b/include/net/hotdata.h index 4acec191c54a..6632b1aa7584 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -42,6 +42,7 @@ struct net_hotdata { int netdev_budget_usecs; int tstamp_prequeue; int max_backlog; + int qdisc_max_burst; int dev_tx_weight; int dev_rx_weight; int sysctl_max_skb_frags; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index ecae35512b9b..4021e6a73e32 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -19,6 +19,7 @@ #include <net/rtnetlink.h> #include <net/lwtunnel.h> #include <net/dst_cache.h> +#include <net/netdev_lock.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -372,7 +373,17 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, fl4->flowi4_flags = flow_flags; } -int ip_tunnel_init(struct net_device *dev); +int __ip_tunnel_init(struct net_device *dev); +#define ip_tunnel_init(DEV) \ +({ \ + struct net_device *__dev = (DEV); \ + int __res = __ip_tunnel_init(__dev); \ + \ + if (!__res) \ + netdev_lockdep_set_classes(__dev);\ + __res; \ +}) + void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 127e6c7d910d..c54df042db6b 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -219,6 +219,8 @@ static inline void nfc_free_device(struct nfc_dev *dev) int nfc_register_device(struct nfc_dev *dev); +void nfc_unregister_rfkill(struct nfc_dev *dev); +void nfc_remove_device(struct nfc_dev *dev); void nfc_unregister_device(struct nfc_dev *dev); /** diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 1ae08e81339f..15679be90c5c 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -41,6 +41,12 @@ struct scsi_eh_save { unsigned char cmnd[32]; struct scsi_data_buffer sdb; struct scatterlist sense_sgl; + + /* struct request fields */ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *rq_crypt_ctx; + struct blk_crypto_keyslot *rq_crypt_keyslot; +#endif }; extern void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 58fd6e84f961..a7860c047503 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1402,7 +1402,7 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s #define snd_pcm_lib_mmap_iomem NULL #endif -void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); +int snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 7e418f065b94..125bdc166bfe 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -224,7 +224,8 @@ DECLARE_EVENT_CLASS(btrfs__inode, __entry->generation = BTRFS_I(inode)->generation; __entry->last_trans = BTRFS_I(inode)->last_trans; __entry->logged_trans = BTRFS_I(inode)->logged_trans; - __entry->root_objectid = btrfs_root_id(BTRFS_I(inode)->root); + __entry->root_objectid = BTRFS_I(inode)->root ? + btrfs_root_id(BTRFS_I(inode)->root) : 0; ), TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%llu blocks=%llu " diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index de6f6d25767c..869f97c9bf73 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -322,6 +322,7 @@ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_recvmsg_peek_nowait, "PUT peek-nwt") \ EM(rxrpc_call_put_release_recvmsg_q, "PUT rls-rcmq") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ @@ -340,6 +341,9 @@ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_notify_released, "SEE nfy-rlsd") \ EM(rxrpc_call_see_recvmsg, "SEE recvmsg ") \ + EM(rxrpc_call_see_recvmsg_requeue, "SEE recv-rqu") \ + EM(rxrpc_call_see_recvmsg_requeue_first, "SEE recv-rqF") \ + EM(rxrpc_call_see_recvmsg_requeue_move, "SEE recv-rqM") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ diff --git a/include/trace/misc/nfs.h b/include/trace/misc/nfs.h index c82233e950ac..a394b4d38e18 100644 --- a/include/trace/misc/nfs.h +++ b/include/trace/misc/nfs.h @@ -16,7 +16,6 @@ TRACE_DEFINE_ENUM(NFSERR_PERM); TRACE_DEFINE_ENUM(NFSERR_NOENT); TRACE_DEFINE_ENUM(NFSERR_IO); TRACE_DEFINE_ENUM(NFSERR_NXIO); -TRACE_DEFINE_ENUM(NFSERR_EAGAIN); TRACE_DEFINE_ENUM(NFSERR_ACCES); TRACE_DEFINE_ENUM(NFSERR_EXIST); TRACE_DEFINE_ENUM(NFSERR_XDEV); @@ -52,7 +51,6 @@ TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); { NFSERR_NXIO, "NXIO" }, \ { ECHILD, "CHILD" }, \ { ETIMEDOUT, "TIMEDOUT" }, \ - { NFSERR_EAGAIN, "AGAIN" }, \ { NFSERR_ACCES, "ACCES" }, \ { NFSERR_EXIST, "EXIST" }, \ { NFSERR_XDEV, "XDEV" }, \ diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index e33f02703350..663836120966 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -81,7 +81,8 @@ enum blk_zone_cond { BLK_ZONE_COND_FULL = 0xE, BLK_ZONE_COND_OFFLINE = 0xF, - BLK_ZONE_COND_ACTIVE = 0xFF, + BLK_ZONE_COND_ACTIVE = 0xFF, /* added in Linux 6.19 */ +#define BLK_ZONE_COND_ACTIVE BLK_ZONE_COND_ACTIVE }; /** @@ -100,7 +101,8 @@ enum blk_zone_report_flags { BLK_ZONE_REP_CAPACITY = (1U << 0), /* Input flags */ - BLK_ZONE_REP_CACHED = (1U << 31), + BLK_ZONE_REP_CACHED = (1U << 31), /* added in Linux 6.19 */ +#define BLK_ZONE_REP_CACHED BLK_ZONE_REP_CACHED }; /** diff --git a/include/uapi/linux/comedi.h b/include/uapi/linux/comedi.h index 7314e5ee0a1e..798ec9a39e12 100644 --- a/include/uapi/linux/comedi.h +++ b/include/uapi/linux/comedi.h @@ -640,7 +640,7 @@ struct comedi_chaninfo { /** * struct comedi_rangeinfo - used to retrieve the range table for a channel - * @range_type: Encodes subdevice index (bits 27:24), channel index + * @range_type: Encodes subdevice index (bits 31:24), channel index * (bits 23:16) and range table length (bits 15:0). * @range_ptr: Pointer to array of @struct comedi_krange to be filled * in with the range table for the channel or subdevice. diff --git a/include/uapi/linux/dev_energymodel.h b/include/uapi/linux/dev_energymodel.h new file mode 100644 index 000000000000..355d8885c9a0 --- /dev/null +++ b/include/uapi/linux/dev_energymodel.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/dev-energymodel.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _UAPI_LINUX_DEV_ENERGYMODEL_H +#define _UAPI_LINUX_DEV_ENERGYMODEL_H + +#define DEV_ENERGYMODEL_FAMILY_NAME "dev-energymodel" +#define DEV_ENERGYMODEL_FAMILY_VERSION 1 + +/** + * enum dev_energymodel_perf_state_flags + * @DEV_ENERGYMODEL_PERF_STATE_FLAGS_PERF_STATE_INEFFICIENT: The performance + * state is inefficient. There is in this perf-domain, another performance + * state with a higher frequency but a lower or equal power cost. + */ +enum dev_energymodel_perf_state_flags { + DEV_ENERGYMODEL_PERF_STATE_FLAGS_PERF_STATE_INEFFICIENT = 1, +}; + +/** + * enum dev_energymodel_perf_domain_flags + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_MICROWATTS: The power values + * are in micro-Watts or some other scale. + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip + * inefficient states when estimating energy consumption. + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_ARTIFICIAL: The power values + * are artificial and might be created by platform missing real power + * information. + */ +enum dev_energymodel_perf_domain_flags { + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_MICROWATTS = 1, + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_SKIP_INEFFICIENCIES = 2, + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_ARTIFICIAL = 4, +}; + +enum { + DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD = 1, + DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID, + DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS, + DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS, + + __DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX, + DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX = (__DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID = 1, + DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE, + + __DEV_ENERGYMODEL_A_PERF_TABLE_MAX, + DEV_ENERGYMODEL_A_PERF_TABLE_MAX = (__DEV_ENERGYMODEL_A_PERF_TABLE_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_A_PERF_STATE_PAD = 1, + DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE, + DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY, + DEV_ENERGYMODEL_A_PERF_STATE_POWER, + DEV_ENERGYMODEL_A_PERF_STATE_COST, + DEV_ENERGYMODEL_A_PERF_STATE_FLAGS, + + __DEV_ENERGYMODEL_A_PERF_STATE_MAX, + DEV_ENERGYMODEL_A_PERF_STATE_MAX = (__DEV_ENERGYMODEL_A_PERF_STATE_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS = 1, + DEV_ENERGYMODEL_CMD_GET_PERF_TABLE, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_CREATED, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_UPDATED, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_DELETED, + + __DEV_ENERGYMODEL_CMD_MAX, + DEV_ENERGYMODEL_CMD_MAX = (__DEV_ENERGYMODEL_CMD_MAX - 1) +}; + +#define DEV_ENERGYMODEL_MCGRP_EVENT "event" + +#endif /* _UAPI_LINUX_DEV_ENERGYMODEL_H */ diff --git a/include/uapi/linux/energy_model.h b/include/uapi/linux/energy_model.h deleted file mode 100644 index 0bcad967854f..000000000000 --- a/include/uapi/linux/energy_model.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ -/* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/em.yaml */ -/* YNL-GEN uapi header */ -/* To regenerate run: tools/net/ynl/ynl-regen.sh */ - -#ifndef _UAPI_LINUX_ENERGY_MODEL_H -#define _UAPI_LINUX_ENERGY_MODEL_H - -#define EM_FAMILY_NAME "em" -#define EM_FAMILY_VERSION 1 - -enum { - EM_A_PDS_PD = 1, - - __EM_A_PDS_MAX, - EM_A_PDS_MAX = (__EM_A_PDS_MAX - 1) -}; - -enum { - EM_A_PD_PAD = 1, - EM_A_PD_PD_ID, - EM_A_PD_FLAGS, - EM_A_PD_CPUS, - - __EM_A_PD_MAX, - EM_A_PD_MAX = (__EM_A_PD_MAX - 1) -}; - -enum { - EM_A_PD_TABLE_PD_ID = 1, - EM_A_PD_TABLE_PS, - - __EM_A_PD_TABLE_MAX, - EM_A_PD_TABLE_MAX = (__EM_A_PD_TABLE_MAX - 1) -}; - -enum { - EM_A_PS_PAD = 1, - EM_A_PS_PERFORMANCE, - EM_A_PS_FREQUENCY, - EM_A_PS_POWER, - EM_A_PS_COST, - EM_A_PS_FLAGS, - - __EM_A_PS_MAX, - EM_A_PS_MAX = (__EM_A_PS_MAX - 1) -}; - -enum { - EM_CMD_GET_PDS = 1, - EM_CMD_GET_PD_TABLE, - EM_CMD_PD_CREATED, - EM_CMD_PD_UPDATED, - EM_CMD_PD_DELETED, - - __EM_CMD_MAX, - EM_CMD_MAX = (__EM_CMD_MAX - 1) -}; - -#define EM_MCGRP_EVENT "event" - -#endif /* _UAPI_LINUX_ENERGY_MODEL_H */ diff --git a/include/uapi/linux/ext4.h b/include/uapi/linux/ext4.h index 411dcc1e4a35..9c683991c32f 100644 --- a/include/uapi/linux/ext4.h +++ b/include/uapi/linux/ext4.h @@ -139,7 +139,7 @@ struct ext4_tune_sb_params { __u32 clear_feature_incompat_mask; __u32 clear_feature_ro_compat_mask; __u8 mount_opts[64]; - __u8 pad[64]; + __u8 pad[68]; }; #define EXT4_TUNE_FL_ERRORS_BEHAVIOR 0x00000001 diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index f030adc462ee..75fd7f5e6cc3 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -216,6 +216,23 @@ struct landlock_net_port_attr { * :manpage:`ftruncate(2)`, :manpage:`creat(2)`, or :manpage:`open(2)` with * ``O_TRUNC``. This access right is available since the third version of the * Landlock ABI. + * - %LANDLOCK_ACCESS_FS_IOCTL_DEV: Invoke :manpage:`ioctl(2)` commands on an opened + * character or block device. + * + * This access right applies to all `ioctl(2)` commands implemented by device + * drivers. However, the following common IOCTL commands continue to be + * invokable independent of the %LANDLOCK_ACCESS_FS_IOCTL_DEV right: + * + * * IOCTL commands targeting file descriptors (``FIOCLEX``, ``FIONCLEX``), + * * IOCTL commands targeting file descriptions (``FIONBIO``, ``FIOASYNC``), + * * IOCTL commands targeting file systems (``FIFREEZE``, ``FITHAW``, + * ``FIGETBSZ``, ``FS_IOC_GETFSUUID``, ``FS_IOC_GETFSSYSFSPATH``) + * * Some IOCTL commands which do not make sense when used with devices, but + * whose implementations are safe and return the right error codes + * (``FS_IOC_FIEMAP``, ``FICLONE``, ``FICLONERANGE``, ``FIDEDUPERANGE``) + * + * This access right is available since the fifth version of the Landlock + * ABI. * * Whether an opened file can be truncated with :manpage:`ftruncate(2)` or used * with `ioctl(2)` is determined during :manpage:`open(2)`, in the same way as @@ -275,26 +292,6 @@ struct landlock_net_port_attr { * If multiple requirements are not met, the ``EACCES`` error code takes * precedence over ``EXDEV``. * - * The following access right applies both to files and directories: - * - * - %LANDLOCK_ACCESS_FS_IOCTL_DEV: Invoke :manpage:`ioctl(2)` commands on an opened - * character or block device. - * - * This access right applies to all `ioctl(2)` commands implemented by device - * drivers. However, the following common IOCTL commands continue to be - * invokable independent of the %LANDLOCK_ACCESS_FS_IOCTL_DEV right: - * - * * IOCTL commands targeting file descriptors (``FIOCLEX``, ``FIONCLEX``), - * * IOCTL commands targeting file descriptions (``FIONBIO``, ``FIOASYNC``), - * * IOCTL commands targeting file systems (``FIFREEZE``, ``FITHAW``, - * ``FIGETBSZ``, ``FS_IOC_GETFSUUID``, ``FS_IOC_GETFSSYSFSPATH``) - * * Some IOCTL commands which do not make sense when used with devices, but - * whose implementations are safe and return the right error codes - * (``FS_IOC_FIEMAP``, ``FICLONE``, ``FICLONERANGE``, ``FIDEDUPERANGE``) - * - * This access right is available since the fifth version of the Landlock - * ABI. - * * .. warning:: * * It is currently not possible to restrict some file-related actions diff --git a/include/uapi/linux/media/arm/mali-c55-config.h b/include/uapi/linux/media/arm/mali-c55-config.h index 109082c5694f..3d335f950eeb 100644 --- a/include/uapi/linux/media/arm/mali-c55-config.h +++ b/include/uapi/linux/media/arm/mali-c55-config.h @@ -195,15 +195,6 @@ struct mali_c55_stats_buffer { } __attribute__((packed)); /** - * enum mali_c55_param_buffer_version - Mali-C55 parameters block versioning - * - * @MALI_C55_PARAM_BUFFER_V1: First version of Mali-C55 parameters block - */ -enum mali_c55_param_buffer_version { - MALI_C55_PARAM_BUFFER_V1, -}; - -/** * enum mali_c55_param_block_type - Enumeration of Mali-C55 parameter blocks * * This enumeration defines the types of Mali-C55 parameters block. Each block diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index f356f2ba3814..71c7196d3281 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -49,7 +49,6 @@ NFSERR_NOENT = 2, /* v2 v3 v4 */ NFSERR_IO = 5, /* v2 v3 v4 */ NFSERR_NXIO = 6, /* v2 v3 v4 */ - NFSERR_EAGAIN = 11, /* v2 v3 */ NFSERR_ACCES = 13, /* v2 v3 v4 */ NFSERR_EXIST = 17, /* v2 v3 v4 */ NFSERR_XDEV = 18, /* v3 v4 */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8134f10e4e6c..8433bac48112 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2880,8 +2880,9 @@ enum nl80211_commands { * index. If the userspace includes more RNR elements than number of * MBSSID elements then these will be added in every EMA beacon. * - * @NL80211_ATTR_MLO_LINK_DISABLED: Flag attribute indicating that the link is - * disabled. + * @NL80211_ATTR_MLO_LINK_DISABLED: Unused. It was used to indicate that a link + * is disabled during association. However, the AP will send the + * information by including a TTLM in the association response. * * @NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA: Include BSS usage data, i.e. * include BSSes that can only be used in restricted scenarios and/or diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index c44a8fb3e418..72f03153dd32 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -2,7 +2,7 @@ /* * Performance events: * - * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008-2009, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index c7c85bb504ba..2e5aef48fa7e 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -23,7 +23,7 @@ #define XATTR_REPLACE 0x2 /* set value, fail if attr does not exist */ struct xattr_args { - __aligned_u64 __user value; + __aligned_u64 value; __u32 size; __u32 flags; }; diff --git a/include/uapi/rdma/irdma-abi.h b/include/uapi/rdma/irdma-abi.h index f7788d33376b..36f20802bcc8 100644 --- a/include/uapi/rdma/irdma-abi.h +++ b/include/uapi/rdma/irdma-abi.h @@ -57,8 +57,8 @@ struct irdma_alloc_ucontext_resp { __u8 rsvd2; __aligned_u64 comp_mask; __u16 min_hw_wq_size; + __u8 revd3[2]; __u32 max_hw_srq_quanta; - __u8 rsvd3[2]; }; struct irdma_alloc_pd_resp { diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h index 5ded174687ee..838f8d460256 100644 --- a/include/uapi/rdma/rdma_user_cm.h +++ b/include/uapi/rdma/rdma_user_cm.h @@ -192,6 +192,7 @@ struct rdma_ucm_query_path_resp { struct rdma_ucm_query_ib_service_resp { __u32 num_service_recs; + __u32 reserved; struct ib_user_service_rec recs[]; }; @@ -354,7 +355,7 @@ enum { #define RDMA_USER_CM_IB_SERVICE_NAME_SIZE 64 struct rdma_ucm_ib_service { - __u64 service_id; + __aligned_u64 service_id; __u8 service_name[RDMA_USER_CM_IB_SERVICE_NAME_SIZE]; __u32 flags; __u32 reserved; @@ -362,6 +363,7 @@ struct rdma_ucm_ib_service { struct rdma_ucm_resolve_ib_service { __u32 id; + __u32 reserved; struct rdma_ucm_ib_service ibs; }; diff --git a/io_uring/cancel.c b/io_uring/cancel.c index ca12ac10c0ae..07b8d852218b 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -184,7 +184,9 @@ static int __io_async_cancel(struct io_cancel_data *cd, } while (1); /* slow path, try all io-wq's */ + __set_current_state(TASK_RUNNING); io_ring_submit_lock(ctx, issue_flags); + mutex_lock(&ctx->tctx_lock); ret = -ENOENT; list_for_each_entry(node, &ctx->tctx_list, ctx_node) { ret = io_async_cancel_one(node->task->io_uring, cd); @@ -194,6 +196,7 @@ static int __io_async_cancel(struct io_cancel_data *cd, nr++; } } + mutex_unlock(&ctx->tctx_lock); io_ring_submit_unlock(ctx, issue_flags); return all ? nr : ret; } @@ -484,6 +487,7 @@ static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) bool ret = false; mutex_lock(&ctx->uring_lock); + mutex_lock(&ctx->tctx_lock); list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; @@ -496,6 +500,7 @@ static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } + mutex_unlock(&ctx->tctx_lock); mutex_unlock(&ctx->uring_lock); return ret; diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index cd13d8aac3d2..2fa7d3601edb 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -598,9 +598,9 @@ static void io_worker_handle_work(struct io_wq_acct *acct, __releases(&acct->lock) { struct io_wq *wq = worker->wq; - bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); do { + bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); struct io_wq_work *work; /* @@ -947,16 +947,13 @@ static bool io_acct_for_each_worker(struct io_wq_acct *acct, return ret; } -static bool io_wq_for_each_worker(struct io_wq *wq, +static void io_wq_for_each_worker(struct io_wq *wq, bool (*func)(struct io_worker *, void *), void *data) { - for (int i = 0; i < IO_WQ_ACCT_NR; i++) { - if (!io_acct_for_each_worker(&wq->acct[i], func, data)) - return false; - } - - return true; + for (int i = 0; i < IO_WQ_ACCT_NR; i++) + if (io_acct_for_each_worker(&wq->acct[i], func, data)) + break; } static bool io_wq_worker_wake(struct io_worker *worker, void *data) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 6cb24cdf8e68..b7a077c11c21 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -340,6 +340,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->ltimeout_list); init_llist_head(&ctx->work_llist); INIT_LIST_HEAD(&ctx->tctx_list); + mutex_init(&ctx->tctx_lock); ctx->submit_state.free_list.next = NULL; INIT_HLIST_HEAD(&ctx->waitid_list); xa_init_flags(&ctx->zcrx_ctxs, XA_FLAGS_ALLOC); @@ -864,7 +865,7 @@ static __cold bool io_cqe_overflow_locked(struct io_ring_ctx *ctx, { struct io_overflow_cqe *ocqe; - ocqe = io_alloc_ocqe(ctx, cqe, big_cqe, GFP_ATOMIC); + ocqe = io_alloc_ocqe(ctx, cqe, big_cqe, GFP_NOWAIT); return io_cqring_add_overflow(ctx, ocqe); } @@ -3002,12 +3003,12 @@ static __cold void io_ring_exit_work(struct work_struct *work) mutex_unlock(&ctx->uring_lock); } - if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) - io_move_task_work_from_local(ctx); - /* The SQPOLL thread never reaches this path */ - while (io_uring_try_cancel_requests(ctx, NULL, true, false)) + do { + if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) + io_move_task_work_from_local(ctx); cond_resched(); + } while (io_uring_try_cancel_requests(ctx, NULL, true, false)); if (ctx->sq_data) { struct io_sq_data *sqd = ctx->sq_data; @@ -3045,6 +3046,7 @@ static __cold void io_ring_exit_work(struct work_struct *work) exit.ctx = ctx; mutex_lock(&ctx->uring_lock); + mutex_lock(&ctx->tctx_lock); while (!list_empty(&ctx->tctx_list)) { WARN_ON_ONCE(time_after(jiffies, timeout)); @@ -3056,6 +3058,7 @@ static __cold void io_ring_exit_work(struct work_struct *work) if (WARN_ON_ONCE(ret)) continue; + mutex_unlock(&ctx->tctx_lock); mutex_unlock(&ctx->uring_lock); /* * See comment above for @@ -3064,7 +3067,9 @@ static __cold void io_ring_exit_work(struct work_struct *work) */ wait_for_completion_interruptible(&exit.completion); mutex_lock(&ctx->uring_lock); + mutex_lock(&ctx->tctx_lock); } + mutex_unlock(&ctx->tctx_lock); mutex_unlock(&ctx->uring_lock); spin_lock(&ctx->completion_lock); spin_unlock(&ctx->completion_lock); diff --git a/io_uring/memmap.c b/io_uring/memmap.c index 18e574776ef6..7d3c5eb58480 100644 --- a/io_uring/memmap.c +++ b/io_uring/memmap.c @@ -268,8 +268,7 @@ static void *io_region_validate_mmap(struct io_ring_ctx *ctx, return io_region_get_ptr(mr); } -static void *io_uring_validate_mmap_request(struct file *file, loff_t pgoff, - size_t sz) +static void *io_uring_validate_mmap_request(struct file *file, loff_t pgoff) { struct io_ring_ctx *ctx = file->private_data; struct io_mapped_region *region; @@ -304,7 +303,7 @@ __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) guard(mutex)(&ctx->mmap_lock); - ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz); + ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff); if (IS_ERR(ptr)) return PTR_ERR(ptr); @@ -336,7 +335,7 @@ unsigned long io_uring_get_unmapped_area(struct file *filp, unsigned long addr, guard(mutex)(&ctx->mmap_lock); - ptr = io_uring_validate_mmap_request(filp, pgoff, len); + ptr = io_uring_validate_mmap_request(filp, pgoff); if (IS_ERR(ptr)) return -ENOMEM; @@ -386,7 +385,7 @@ unsigned long io_uring_get_unmapped_area(struct file *file, unsigned long addr, guard(mutex)(&ctx->mmap_lock); - ptr = io_uring_validate_mmap_request(file, pgoff, len); + ptr = io_uring_validate_mmap_request(file, pgoff); if (IS_ERR(ptr)) return PTR_ERR(ptr); diff --git a/io_uring/register.c b/io_uring/register.c index 62d39b3ff317..3d3822ff3fd9 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -320,6 +320,7 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, return 0; /* now propagate the restriction to all registered users */ + mutex_lock(&ctx->tctx_lock); list_for_each_entry(node, &ctx->tctx_list, ctx_node) { tctx = node->task->io_uring; if (WARN_ON_ONCE(!tctx->io_wq)) @@ -330,6 +331,7 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, /* ignore errors, it always returns zero anyway */ (void)io_wq_max_workers(tctx->io_wq, new_count); } + mutex_unlock(&ctx->tctx_lock); return 0; err: if (sqd) { diff --git a/io_uring/rw.c b/io_uring/rw.c index 70ca88cc1f54..28555bc85ba0 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -144,19 +144,22 @@ static inline int io_import_rw_buffer(int rw, struct io_kiocb *req, return 0; } -static void io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags) +static bool io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_rw *rw = req->async_data; if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) - return; + return false; io_alloc_cache_vec_kasan(&rw->vec); if (rw->vec.nr > IO_VEC_CACHE_SOFT_CAP) io_vec_free(&rw->vec); - if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) + if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) { io_req_async_data_clear(req, 0); + return true; + } + return false; } static void io_req_rw_cleanup(struct io_kiocb *req, unsigned int issue_flags) @@ -190,7 +193,11 @@ static void io_req_rw_cleanup(struct io_kiocb *req, unsigned int issue_flags) */ if (!(req->flags & (REQ_F_REISSUE | REQ_F_REFCOUNT))) { req->flags &= ~REQ_F_NEED_CLEANUP; - io_rw_recycle(req, issue_flags); + if (!io_rw_recycle(req, issue_flags)) { + struct io_async_rw *rw = req->async_data; + + io_vec_free(&rw->vec); + } } } diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 5b66755579c0..6d6f44215ec8 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -136,9 +136,9 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) return ret; } - mutex_lock(&ctx->uring_lock); + mutex_lock(&ctx->tctx_lock); list_add(&node->ctx_node, &ctx->tctx_list); - mutex_unlock(&ctx->uring_lock); + mutex_unlock(&ctx->tctx_lock); } return 0; } @@ -176,9 +176,9 @@ __cold void io_uring_del_tctx_node(unsigned long index) WARN_ON_ONCE(current != node->task); WARN_ON_ONCE(list_empty(&node->ctx_node)); - mutex_lock(&node->ctx->uring_lock); + mutex_lock(&node->ctx->tctx_lock); list_del(&node->ctx_node); - mutex_unlock(&node->ctx->uring_lock); + mutex_unlock(&node->ctx->tctx_lock); if (tctx->last == node->ctx) tctx->last = NULL; diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 2d4cbd47c67c..d25d60aed6af 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -114,11 +114,11 @@ static void io_waitid_remove_wq(struct io_kiocb *req) struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct wait_queue_head *head; - head = READ_ONCE(iw->head); + head = smp_load_acquire(&iw->head); if (head) { struct io_waitid_async *iwa = req->async_data; - iw->head = NULL; + smp_store_release(&iw->head, NULL); spin_lock_irq(&head->lock); list_del_init(&iwa->wo.child_wait.entry); spin_unlock_irq(&head->lock); @@ -246,7 +246,7 @@ static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, return 0; list_del_init(&wait->entry); - iw->head = NULL; + smp_store_release(&iw->head, NULL); /* cancel is in progress */ if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f0ca69f888fa..3135643d5695 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9609,6 +9609,11 @@ static int check_reg_const_str(struct bpf_verifier_env *env, if (reg->type != PTR_TO_MAP_VALUE) return -EINVAL; + if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) { + verbose(env, "R%d points to insn_array map which cannot be used as const string\n", regno); + return -EACCES; + } + if (!bpf_map_is_rdonly(map)) { verbose(env, "R%d does not point to a readonly map'\n", regno); return -EACCES; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e717208cfb18..5f0d33b04910 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic process-grouping system. * @@ -20,10 +21,6 @@ * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of the Linux - * distribution for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -5847,7 +5844,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ - cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL); + cgrp = kzalloc(struct_size(cgrp, _low_ancestors, level), GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 6e6eb09b8db6..c06e2e96f79d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kernel/cpuset.c * @@ -16,10 +17,6 @@ * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of the Linux - * distribution for more details. */ #include "cpuset-internal.h" @@ -1668,7 +1665,14 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs, static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) { WARN_ON_ONCE(!is_remote_partition(cs)); - WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus)); + /* + * When a CPU is offlined, top_cpuset may end up with no available CPUs, + * which should clear subpartitions_cpus. We should not emit a warning for this + * scenario: the hierarchy is updated from top to bottom, so subpartitions_cpus + * may already be cleared when disabling the partition. + */ + WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus) && + !cpumask_empty(subpartitions_cpus)); spin_lock_irq(&callback_lock); cs->remote_partition = false; @@ -3976,8 +3980,9 @@ retry: if (remote || (is_partition_valid(cs) && is_partition_valid(parent))) compute_partition_effective_cpumask(cs, &new_cpus); - if (remote && cpumask_empty(&new_cpus) && - partition_is_populated(cs, NULL)) { + if (remote && (cpumask_empty(subpartitions_cpus) || + (cpumask_empty(&new_cpus) && + partition_is_populated(cs, NULL)))) { cs->prs_err = PERR_HOTPLUG; remote_partition_disable(cs, tmp); compute_effective_cpumask(&new_cpus, cs, parent); @@ -3990,9 +3995,12 @@ retry: * 1) empty effective cpus but not valid empty partition. * 2) parent is invalid or doesn't grant any cpus to child * partitions. + * 3) subpartitions_cpus is empty. */ - if (is_local_partition(cs) && (!is_partition_valid(parent) || - tasks_nocpu_error(parent, cs, &new_cpus))) + if (is_local_partition(cs) && + (!is_partition_valid(parent) || + tasks_nocpu_error(parent, cs, &new_cpus) || + cpumask_empty(subpartitions_cpus))) partcmd = partcmd_invalidate; /* * On the other hand, an invalid partition root may be transitioned diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 915b02f65980..817c33450fee 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -1,17 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * cgroup_freezer.c - control group freezer subsystem * * Copyright IBM Corporation, 2007 * * Author : Cedric Le Goater <clg@fr.ibm.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of version 2.1 of the GNU Lesser General Public License - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. */ #include <linux/export.h> diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 26392badc36b..c5da29ad010c 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -184,6 +184,12 @@ static __init struct gen_pool *__dma_atomic_pool_init(size_t pool_size, return pool; } +#ifdef CONFIG_ZONE_DMA32 +#define has_managed_dma32 has_managed_zone(ZONE_DMA32) +#else +#define has_managed_dma32 false +#endif + static int __init dma_atomic_pool_init(void) { int ret = 0; @@ -199,17 +205,20 @@ static int __init dma_atomic_pool_init(void) } INIT_WORK(&atomic_pool_work, atomic_pool_work_fn); - atomic_pool_kernel = __dma_atomic_pool_init(atomic_pool_size, + /* All memory might be in the DMA zone(s) to begin with */ + if (has_managed_zone(ZONE_NORMAL)) { + atomic_pool_kernel = __dma_atomic_pool_init(atomic_pool_size, GFP_KERNEL); - if (!atomic_pool_kernel) - ret = -ENOMEM; + if (!atomic_pool_kernel) + ret = -ENOMEM; + } if (has_managed_dma()) { atomic_pool_dma = __dma_atomic_pool_init(atomic_pool_size, GFP_KERNEL | GFP_DMA); if (!atomic_pool_dma) ret = -ENOMEM; } - if (IS_ENABLED(CONFIG_ZONE_DMA32)) { + if (has_managed_dma32) { atomic_pool_dma32 = __dma_atomic_pool_init(atomic_pool_size, GFP_KERNEL | GFP_DMA32); if (!atomic_pool_dma32) @@ -224,11 +233,11 @@ postcore_initcall(dma_atomic_pool_init); static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) { if (prev == NULL) { - if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) - return atomic_pool_dma32; - if (atomic_pool_dma && (gfp & GFP_DMA)) - return atomic_pool_dma; - return atomic_pool_kernel; + if (gfp & GFP_DMA) + return atomic_pool_dma ?: atomic_pool_dma32 ?: atomic_pool_kernel; + if (gfp & GFP_DMA32) + return atomic_pool_dma32 ?: atomic_pool_dma ?: atomic_pool_kernel; + return atomic_pool_kernel ?: atomic_pool_dma32 ?: atomic_pool_dma; } if (prev == atomic_pool_kernel) return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma; diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index b9c7e00725d6..1f6589578703 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -2,7 +2,7 @@ /* * Performance events callchain code, extracted from core.c: * - * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> diff --git a/kernel/events/core.c b/kernel/events/core.c index dad0d3d2e85f..a0fa488bce84 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2,7 +2,7 @@ /* * Performance events core code: * - * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> @@ -6997,6 +6997,15 @@ static int perf_mmap_rb(struct vm_area_struct *vma, struct perf_event *event, if (data_page_nr(event->rb) != nr_pages) return -EINVAL; + /* + * If this event doesn't have mmap_count, we're attempting to + * create an alias of another event's mmap(); this would mean + * both events will end up scribbling the same user_page; + * which makes no sense. + */ + if (!refcount_read(&event->mmap_count)) + return -EBUSY; + if (refcount_inc_not_zero(&event->rb->mmap_count)) { /* * Success -- managed to mmap() the same buffer @@ -11906,6 +11915,11 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event) } } +static void perf_swevent_destroy_hrtimer(struct perf_event *event) +{ + hrtimer_cancel(&event->hw.hrtimer); +} + static void perf_swevent_init_hrtimer(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -11914,6 +11928,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event) return; hrtimer_setup(&hwc->hrtimer, perf_swevent_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + event->destroy = perf_swevent_destroy_hrtimer; /* * Since hrtimers have a fixed rate, we can do a static freq->period diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 20a905023736..3e7de2661417 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -2,7 +2,7 @@ /* * Performance events ring-buffer code: * - * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 3527defd2890..5c5ebaee35f2 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -// Copyright 2017 Thomas Gleixner <tglx@linutronix.de> +// Copyright 2017 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> #include <linux/irqdomain.h> #include <linux/irq.h> diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 8f222d1cccec..a50f2305a8dc 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2017 Thomas Gleixner <tglx@linutronix.de> +// Copyright (C) 2017 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> #include <linux/spinlock.h> #include <linux/seq_file.h> diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 0f92acdd354d..95c585c6ddc3 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -953,17 +953,24 @@ int kimage_load_segment(struct kimage *image, int idx) return result; } -void *kimage_map_segment(struct kimage *image, - unsigned long addr, unsigned long size) +void *kimage_map_segment(struct kimage *image, int idx) { + unsigned long addr, size, eaddr; unsigned long src_page_addr, dest_page_addr = 0; - unsigned long eaddr = addr + size; kimage_entry_t *ptr, entry; struct page **src_pages; unsigned int npages; + struct page *cma; void *vaddr = NULL; int i; + cma = image->segment_cma[idx]; + if (cma) + return page_address(cma); + + addr = image->segment[idx].mem; + size = image->segment[idx].memsz; + eaddr = addr + size; /* * Collect the source pages and map them in a contiguous VA range. */ @@ -1004,7 +1011,8 @@ void *kimage_map_segment(struct kimage *image, void kimage_unmap_segment(void *segment_buffer) { - vunmap(segment_buffer); + if (is_vmalloc_addr(segment_buffer)) + vunmap(segment_buffer); } struct kexec_load_limit { diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 9dc51fab604f..90d411a59f76 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -255,6 +255,14 @@ static struct page *kho_restore_page(phys_addr_t phys, bool is_folio) if (is_folio && info.order) prep_compound_page(page, info.order); + /* Always mark headpage's codetag as empty to avoid accounting mismatch */ + clear_page_tag_ref(page); + if (!is_folio) { + /* Also do that for the non-compound tail pages */ + for (unsigned int i = 1; i < nr_pages; i++) + clear_page_tag_ref(page + i); + } + adjust_managed_page_count(page, nr_pages); return page; } @@ -460,27 +468,23 @@ static void __init deserialize_bitmap(unsigned int order, } } -/* Return true if memory was deserizlied */ -static bool __init kho_mem_deserialize(const void *fdt) +/* Returns physical address of the preserved memory map from FDT */ +static phys_addr_t __init kho_get_mem_map_phys(const void *fdt) { - struct khoser_mem_chunk *chunk; const void *mem_ptr; - u64 mem; int len; mem_ptr = fdt_getprop(fdt, 0, PROP_PRESERVED_MEMORY_MAP, &len); if (!mem_ptr || len != sizeof(u64)) { pr_err("failed to get preserved memory bitmaps\n"); - return false; + return 0; } - mem = get_unaligned((const u64 *)mem_ptr); - chunk = mem ? phys_to_virt(mem) : NULL; - - /* No preserved physical pages were passed, no deserialization */ - if (!chunk) - return false; + return get_unaligned((const u64 *)mem_ptr); +} +static void __init kho_mem_deserialize(struct khoser_mem_chunk *chunk) +{ while (chunk) { unsigned int i; @@ -489,8 +493,6 @@ static bool __init kho_mem_deserialize(const void *fdt) &chunk->bitmaps[i]); chunk = KHOSER_LOAD_PTR(chunk->hdr.next); } - - return true; } /* @@ -1012,8 +1014,10 @@ int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation) chunk->phys[idx++] = phys; if (idx == ARRAY_SIZE(chunk->phys)) { chunk = new_vmalloc_chunk(chunk); - if (!chunk) + if (!chunk) { + err = -ENOMEM; goto err_free; + } idx = 0; } } @@ -1253,6 +1257,7 @@ bool kho_finalized(void) struct kho_in { phys_addr_t fdt_phys; phys_addr_t scratch_phys; + phys_addr_t mem_map_phys; struct kho_debugfs dbg; }; @@ -1434,12 +1439,10 @@ static void __init kho_release_scratch(void) void __init kho_memory_init(void) { - if (kho_in.scratch_phys) { + if (kho_in.mem_map_phys) { kho_scratch = phys_to_virt(kho_in.scratch_phys); kho_release_scratch(); - - if (!kho_mem_deserialize(kho_get_fdt())) - kho_in.fdt_phys = 0; + kho_mem_deserialize(phys_to_virt(kho_in.mem_map_phys)); } else { kho_reserve_scratch(); } @@ -1448,8 +1451,9 @@ void __init kho_memory_init(void) void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys, u64 scratch_len) { - void *fdt = NULL; struct kho_scratch *scratch = NULL; + phys_addr_t mem_map_phys; + void *fdt = NULL; int err = 0; unsigned int scratch_cnt = scratch_len / sizeof(*kho_scratch); @@ -1475,6 +1479,12 @@ void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, goto out; } + mem_map_phys = kho_get_mem_map_phys(fdt); + if (!mem_map_phys) { + err = -ENOENT; + goto out; + } + scratch = early_memremap(scratch_phys, scratch_len); if (!scratch) { pr_warn("setup: failed to memremap scratch (phys=0x%llx, len=%lld)\n", @@ -1515,6 +1525,7 @@ void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, kho_in.fdt_phys = fdt_phys; kho_in.scratch_phys = scratch_phys; + kho_in.mem_map_phys = mem_map_phys; kho_scratch_cnt = scratch_cnt; pr_info("found kexec handover data.\n"); diff --git a/kernel/module/kmod.c b/kernel/module/kmod.c index 25f253812512..a25dccdf7aa7 100644 --- a/kernel/module/kmod.c +++ b/kernel/module/kmod.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kmod - the kernel module loader * diff --git a/kernel/panic.c b/kernel/panic.c index 0d52210a9e2b..0c20fcaae98a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -131,7 +131,8 @@ static int proc_taint(const struct ctl_table *table, int write, static int sysctl_panic_print_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - panic_print_deprecated(); + if (write) + panic_print_deprecated(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } @@ -1014,7 +1015,6 @@ static int panic_print_set(const char *val, const struct kernel_param *kp) static int panic_print_get(char *val, const struct kernel_param *kp) { - panic_print_deprecated(); return param_get_ulong(val, kp); } diff --git a/kernel/power/em_netlink.c b/kernel/power/em_netlink.c index 4b85da138a06..5a611d3950fd 100644 --- a/kernel/power/em_netlink.c +++ b/kernel/power/em_netlink.c @@ -12,27 +12,35 @@ #include <linux/energy_model.h> #include <net/sock.h> #include <net/genetlink.h> -#include <uapi/linux/energy_model.h> +#include <uapi/linux/dev_energymodel.h> #include "em_netlink.h" #include "em_netlink_autogen.h" -#define EM_A_PD_CPUS_LEN 256 - /*************************** Command encoding ********************************/ +struct dump_ctx { + int idx; + int start; + struct sk_buff *skb; + struct netlink_callback *cb; +}; + static int __em_nl_get_pd_size(struct em_perf_domain *pd, void *data) { - char cpus_buf[EM_A_PD_CPUS_LEN]; + int nr_cpus, msg_sz, cpus_sz; int *tot_msg_sz = data; - int msg_sz, cpus_sz; - cpus_sz = snprintf(cpus_buf, sizeof(cpus_buf), "%*pb", - cpumask_pr_args(to_cpumask(pd->cpus))); + nr_cpus = cpumask_weight(to_cpumask(pd->cpus)); + cpus_sz = nla_total_size_64bit(sizeof(u64)) * nr_cpus; - msg_sz = nla_total_size(0) + /* EM_A_PDS_PD */ - nla_total_size(sizeof(u32)) + /* EM_A_PD_PD_ID */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PD_FLAGS */ - nla_total_size(cpus_sz); /* EM_A_PD_CPUS */ + msg_sz = nla_total_size(0) + + /* DEV_ENERGYMODEL_A_PERF_DOMAINS_PERF_DOMAIN */ + nla_total_size(sizeof(u32)) + + /* DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS */ + nla_total_size(cpus_sz); + /* DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS */ *tot_msg_sz += nlmsg_total_size(genlmsg_msg_size(msg_sz)); return 0; @@ -40,56 +48,80 @@ static int __em_nl_get_pd_size(struct em_perf_domain *pd, void *data) static int __em_nl_get_pd(struct em_perf_domain *pd, void *data) { - char cpus_buf[EM_A_PD_CPUS_LEN]; struct sk_buff *msg = data; - struct nlattr *entry; - - entry = nla_nest_start(msg, EM_A_PDS_PD); - if (!entry) - goto out_cancel_nest; + struct cpumask *cpumask; + int cpu; - if (nla_put_u32(msg, EM_A_PD_PD_ID, pd->id)) + if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID, + pd->id)) goto out_cancel_nest; - if (nla_put_u64_64bit(msg, EM_A_PD_FLAGS, pd->flags, EM_A_PD_PAD)) + if (nla_put_u64_64bit(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS, + pd->flags, DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD)) goto out_cancel_nest; - snprintf(cpus_buf, sizeof(cpus_buf), "%*pb", - cpumask_pr_args(to_cpumask(pd->cpus))); - if (nla_put_string(msg, EM_A_PD_CPUS, cpus_buf)) - goto out_cancel_nest; - - nla_nest_end(msg, entry); + cpumask = to_cpumask(pd->cpus); + for_each_cpu(cpu, cpumask) { + if (nla_put_u64_64bit(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS, + cpu, DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD)) + goto out_cancel_nest; + } return 0; out_cancel_nest: - nla_nest_cancel(msg, entry); - return -EMSGSIZE; } -int em_nl_get_pds_doit(struct sk_buff *skb, struct genl_info *info) +static int __em_nl_get_pd_for_dump(struct em_perf_domain *pd, void *data) { - struct sk_buff *msg; + const struct genl_info *info; + struct dump_ctx *ctx = data; void *hdr; + int ret; + + if (ctx->idx++ < ctx->start) + return 0; + + info = genl_info_dump(ctx->cb); + hdr = genlmsg_iput(ctx->skb, info); + if (!hdr) { + genlmsg_cancel(ctx->skb, hdr); + return -EMSGSIZE; + } + + ret = __em_nl_get_pd(pd, ctx->skb); + genlmsg_end(ctx->skb, hdr); + return ret; +} + +int dev_energymodel_nl_get_perf_domains_doit(struct sk_buff *skb, + struct genl_info *info) +{ + int id, ret = -EMSGSIZE, msg_sz = 0; int cmd = info->genlhdr->cmd; - int ret = -EMSGSIZE, msg_sz = 0; + struct em_perf_domain *pd; + struct sk_buff *msg; + void *hdr; + + if (!info->attrs[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID]) + return -EINVAL; - for_each_em_perf_domain(__em_nl_get_pd_size, &msg_sz); + id = nla_get_u32(info->attrs[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID]); + pd = em_perf_domain_get_by_id(id); + __em_nl_get_pd_size(pd, &msg_sz); msg = genlmsg_new(msg_sz, GFP_KERNEL); if (!msg) return -ENOMEM; - hdr = genlmsg_put_reply(msg, info, &em_nl_family, 0, cmd); + hdr = genlmsg_put_reply(msg, info, &dev_energymodel_nl_family, 0, cmd); if (!hdr) goto out_free_msg; - ret = for_each_em_perf_domain(__em_nl_get_pd, msg); + ret = __em_nl_get_pd(pd, msg); if (ret) goto out_cancel_msg; - genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); @@ -98,19 +130,31 @@ out_cancel_msg: genlmsg_cancel(msg, hdr); out_free_msg: nlmsg_free(msg); - return ret; } +int dev_energymodel_nl_get_perf_domains_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct dump_ctx ctx = { + .idx = 0, + .start = cb->args[0], + .skb = skb, + .cb = cb, + }; + + return for_each_em_perf_domain(__em_nl_get_pd_for_dump, &ctx); +} + static struct em_perf_domain *__em_nl_get_pd_table_id(struct nlattr **attrs) { struct em_perf_domain *pd; int id; - if (!attrs[EM_A_PD_TABLE_PD_ID]) + if (!attrs[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID]) return NULL; - id = nla_get_u32(attrs[EM_A_PD_TABLE_PD_ID]); + id = nla_get_u32(attrs[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID]); pd = em_perf_domain_get_by_id(id); return pd; } @@ -119,25 +163,34 @@ static int __em_nl_get_pd_table_size(const struct em_perf_domain *pd) { int id_sz, ps_sz; - id_sz = nla_total_size(sizeof(u32)); /* EM_A_PD_TABLE_PD_ID */ - ps_sz = nla_total_size(0) + /* EM_A_PD_TABLE_PS */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_PERFORMANCE */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_FREQUENCY */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_POWER */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_COST */ - nla_total_size_64bit(sizeof(u64)); /* EM_A_PS_FLAGS */ + id_sz = nla_total_size(sizeof(u32)); + /* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID */ + ps_sz = nla_total_size(0) + + /* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_STATE_POWER */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_STATE_COST */ + nla_total_size_64bit(sizeof(u64)); + /* DEV_ENERGYMODEL_A_PERF_STATE_FLAGS */ ps_sz *= pd->nr_perf_states; return nlmsg_total_size(genlmsg_msg_size(id_sz + ps_sz)); } -static int __em_nl_get_pd_table(struct sk_buff *msg, const struct em_perf_domain *pd) +static +int __em_nl_get_pd_table(struct sk_buff *msg, const struct em_perf_domain *pd) { struct em_perf_state *table, *ps; struct nlattr *entry; int i; - if (nla_put_u32(msg, EM_A_PD_TABLE_PD_ID, pd->id)) + if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID, + pd->id)) goto out_err; rcu_read_lock(); @@ -146,24 +199,35 @@ static int __em_nl_get_pd_table(struct sk_buff *msg, const struct em_perf_domain for (i = 0; i < pd->nr_perf_states; i++) { ps = &table[i]; - entry = nla_nest_start(msg, EM_A_PD_TABLE_PS); + entry = nla_nest_start(msg, + DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE); if (!entry) goto out_unlock_ps; - if (nla_put_u64_64bit(msg, EM_A_PS_PERFORMANCE, - ps->performance, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE, + ps->performance, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; - if (nla_put_u64_64bit(msg, EM_A_PS_FREQUENCY, - ps->frequency, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY, + ps->frequency, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; - if (nla_put_u64_64bit(msg, EM_A_PS_POWER, - ps->power, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_POWER, + ps->power, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; - if (nla_put_u64_64bit(msg, EM_A_PS_COST, - ps->cost, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_COST, + ps->cost, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; - if (nla_put_u64_64bit(msg, EM_A_PS_FLAGS, - ps->flags, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_FLAGS, + ps->flags, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; nla_nest_end(msg, entry); @@ -179,7 +243,8 @@ out_err: return -EMSGSIZE; } -int em_nl_get_pd_table_doit(struct sk_buff *skb, struct genl_info *info) +int dev_energymodel_nl_get_perf_table_doit(struct sk_buff *skb, + struct genl_info *info) { int cmd = info->genlhdr->cmd; int msg_sz, ret = -EMSGSIZE; @@ -197,7 +262,7 @@ int em_nl_get_pd_table_doit(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - hdr = genlmsg_put_reply(msg, info, &em_nl_family, 0, cmd); + hdr = genlmsg_put_reply(msg, info, &dev_energymodel_nl_family, 0, cmd); if (!hdr) goto out_free_msg; @@ -221,7 +286,7 @@ static void __em_notify_pd_table(const struct em_perf_domain *pd, int ntf_type) int msg_sz, ret = -EMSGSIZE; void *hdr; - if (!genl_has_listeners(&em_nl_family, &init_net, EM_NLGRP_EVENT)) + if (!genl_has_listeners(&dev_energymodel_nl_family, &init_net, DEV_ENERGYMODEL_NLGRP_EVENT)) return; msg_sz = __em_nl_get_pd_table_size(pd); @@ -230,7 +295,7 @@ static void __em_notify_pd_table(const struct em_perf_domain *pd, int ntf_type) if (!msg) return; - hdr = genlmsg_put(msg, 0, 0, &em_nl_family, 0, ntf_type); + hdr = genlmsg_put(msg, 0, 0, &dev_energymodel_nl_family, 0, ntf_type); if (!hdr) goto out_free_msg; @@ -240,28 +305,28 @@ static void __em_notify_pd_table(const struct em_perf_domain *pd, int ntf_type) genlmsg_end(msg, hdr); - genlmsg_multicast(&em_nl_family, msg, 0, EM_NLGRP_EVENT, GFP_KERNEL); + genlmsg_multicast(&dev_energymodel_nl_family, msg, 0, + DEV_ENERGYMODEL_NLGRP_EVENT, GFP_KERNEL); return; out_free_msg: nlmsg_free(msg); - return; } void em_notify_pd_created(const struct em_perf_domain *pd) { - __em_notify_pd_table(pd, EM_CMD_PD_CREATED); + __em_notify_pd_table(pd, DEV_ENERGYMODEL_CMD_PERF_DOMAIN_CREATED); } void em_notify_pd_updated(const struct em_perf_domain *pd) { - __em_notify_pd_table(pd, EM_CMD_PD_UPDATED); + __em_notify_pd_table(pd, DEV_ENERGYMODEL_CMD_PERF_DOMAIN_UPDATED); } static int __em_notify_pd_deleted_size(const struct em_perf_domain *pd) { - int id_sz = nla_total_size(sizeof(u32)); /* EM_A_PD_TABLE_PD_ID */ + int id_sz = nla_total_size(sizeof(u32)); /* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID */ return nlmsg_total_size(genlmsg_msg_size(id_sz)); } @@ -272,7 +337,8 @@ void em_notify_pd_deleted(const struct em_perf_domain *pd) void *hdr; int msg_sz; - if (!genl_has_listeners(&em_nl_family, &init_net, EM_NLGRP_EVENT)) + if (!genl_has_listeners(&dev_energymodel_nl_family, &init_net, + DEV_ENERGYMODEL_NLGRP_EVENT)) return; msg_sz = __em_notify_pd_deleted_size(pd); @@ -281,28 +347,29 @@ void em_notify_pd_deleted(const struct em_perf_domain *pd) if (!msg) return; - hdr = genlmsg_put(msg, 0, 0, &em_nl_family, 0, EM_CMD_PD_DELETED); + hdr = genlmsg_put(msg, 0, 0, &dev_energymodel_nl_family, 0, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_DELETED); if (!hdr) goto out_free_msg; - if (nla_put_u32(msg, EM_A_PD_TABLE_PD_ID, pd->id)) { + if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID, + pd->id)) goto out_free_msg; - } genlmsg_end(msg, hdr); - genlmsg_multicast(&em_nl_family, msg, 0, EM_NLGRP_EVENT, GFP_KERNEL); + genlmsg_multicast(&dev_energymodel_nl_family, msg, 0, + DEV_ENERGYMODEL_NLGRP_EVENT, GFP_KERNEL); return; out_free_msg: nlmsg_free(msg); - return; } /**************************** Initialization *********************************/ static int __init em_netlink_init(void) { - return genl_register_family(&em_nl_family); + return genl_register_family(&dev_energymodel_nl_family); } postcore_initcall(em_netlink_init); diff --git a/kernel/power/em_netlink_autogen.c b/kernel/power/em_netlink_autogen.c index ceb3b2bb6ebe..fedd473e4244 100644 --- a/kernel/power/em_netlink_autogen.c +++ b/kernel/power/em_netlink_autogen.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/em.yaml */ +/* Documentation/netlink/specs/dev-energymodel.yaml */ /* YNL-GEN kernel source */ /* To regenerate run: tools/net/ynl/ynl-regen.sh */ @@ -9,41 +9,53 @@ #include "em_netlink_autogen.h" -#include <uapi/linux/energy_model.h> +#include <uapi/linux/dev_energymodel.h> -/* EM_CMD_GET_PD_TABLE - do */ -static const struct nla_policy em_get_pd_table_nl_policy[EM_A_PD_TABLE_PD_ID + 1] = { - [EM_A_PD_TABLE_PD_ID] = { .type = NLA_U32, }, +/* DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS - do */ +static const struct nla_policy dev_energymodel_get_perf_domains_nl_policy[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID + 1] = { + [DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID] = { .type = NLA_U32, }, }; -/* Ops table for em */ -static const struct genl_split_ops em_nl_ops[] = { +/* DEV_ENERGYMODEL_CMD_GET_PERF_TABLE - do */ +static const struct nla_policy dev_energymodel_get_perf_table_nl_policy[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID + 1] = { + [DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID] = { .type = NLA_U32, }, +}; + +/* Ops table for dev_energymodel */ +static const struct genl_split_ops dev_energymodel_nl_ops[] = { + { + .cmd = DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS, + .doit = dev_energymodel_nl_get_perf_domains_doit, + .policy = dev_energymodel_get_perf_domains_nl_policy, + .maxattr = DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID, + .flags = GENL_CMD_CAP_DO, + }, { - .cmd = EM_CMD_GET_PDS, - .doit = em_nl_get_pds_doit, - .flags = GENL_CMD_CAP_DO, + .cmd = DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS, + .dumpit = dev_energymodel_nl_get_perf_domains_dumpit, + .flags = GENL_CMD_CAP_DUMP, }, { - .cmd = EM_CMD_GET_PD_TABLE, - .doit = em_nl_get_pd_table_doit, - .policy = em_get_pd_table_nl_policy, - .maxattr = EM_A_PD_TABLE_PD_ID, + .cmd = DEV_ENERGYMODEL_CMD_GET_PERF_TABLE, + .doit = dev_energymodel_nl_get_perf_table_doit, + .policy = dev_energymodel_get_perf_table_nl_policy, + .maxattr = DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID, .flags = GENL_CMD_CAP_DO, }, }; -static const struct genl_multicast_group em_nl_mcgrps[] = { - [EM_NLGRP_EVENT] = { "event", }, +static const struct genl_multicast_group dev_energymodel_nl_mcgrps[] = { + [DEV_ENERGYMODEL_NLGRP_EVENT] = { "event", }, }; -struct genl_family em_nl_family __ro_after_init = { - .name = EM_FAMILY_NAME, - .version = EM_FAMILY_VERSION, +struct genl_family dev_energymodel_nl_family __ro_after_init = { + .name = DEV_ENERGYMODEL_FAMILY_NAME, + .version = DEV_ENERGYMODEL_FAMILY_VERSION, .netnsok = true, .parallel_ops = true, .module = THIS_MODULE, - .split_ops = em_nl_ops, - .n_split_ops = ARRAY_SIZE(em_nl_ops), - .mcgrps = em_nl_mcgrps, - .n_mcgrps = ARRAY_SIZE(em_nl_mcgrps), + .split_ops = dev_energymodel_nl_ops, + .n_split_ops = ARRAY_SIZE(dev_energymodel_nl_ops), + .mcgrps = dev_energymodel_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(dev_energymodel_nl_mcgrps), }; diff --git a/kernel/power/em_netlink_autogen.h b/kernel/power/em_netlink_autogen.h index 140ab548103c..5caf2f7e18a5 100644 --- a/kernel/power/em_netlink_autogen.h +++ b/kernel/power/em_netlink_autogen.h @@ -1,24 +1,28 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/em.yaml */ +/* Documentation/netlink/specs/dev-energymodel.yaml */ /* YNL-GEN kernel header */ /* To regenerate run: tools/net/ynl/ynl-regen.sh */ -#ifndef _LINUX_EM_GEN_H -#define _LINUX_EM_GEN_H +#ifndef _LINUX_DEV_ENERGYMODEL_GEN_H +#define _LINUX_DEV_ENERGYMODEL_GEN_H #include <net/netlink.h> #include <net/genetlink.h> -#include <uapi/linux/energy_model.h> +#include <uapi/linux/dev_energymodel.h> -int em_nl_get_pds_doit(struct sk_buff *skb, struct genl_info *info); -int em_nl_get_pd_table_doit(struct sk_buff *skb, struct genl_info *info); +int dev_energymodel_nl_get_perf_domains_doit(struct sk_buff *skb, + struct genl_info *info); +int dev_energymodel_nl_get_perf_domains_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int dev_energymodel_nl_get_perf_table_doit(struct sk_buff *skb, + struct genl_info *info); enum { - EM_NLGRP_EVENT, + DEV_ENERGYMODEL_NLGRP_EVENT, }; -extern struct genl_family em_nl_family; +extern struct genl_family dev_energymodel_nl_family; -#endif /* _LINUX_EM_GEN_H */ +#endif /* _LINUX_DEV_ENERGYMODEL_GEN_H */ diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 11af9f64aa82..5b055cbe5341 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -449,8 +449,10 @@ static int em_create_pd(struct device *dev, int nr_states, INIT_LIST_HEAD(&pd->node); id = ida_alloc(&em_pd_ida, GFP_KERNEL); - if (id < 0) - return -ENOMEM; + if (id < 0) { + kfree(pd); + return id; + } pd->id = id; em_table = em_table_alloc(pd); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 2da4482bb6eb..57c44268698f 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -349,9 +349,12 @@ static int suspend_test(int level) if (pm_test_level == level) { pr_info("suspend debug: Waiting for %d second(s).\n", pm_test_delay); - for (i = 0; i < pm_test_delay && !pm_wakeup_pending(); i++) - msleep(1000); - + for (i = 0; i < pm_test_delay && !pm_wakeup_pending(); i++) { + if (level > TEST_CORE) + msleep(1000); + else + mdelay(1000); + } return 1; } #endif /* !CONFIG_PM_DEBUG */ diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 33a186373bef..8050e5182835 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -902,8 +902,11 @@ out_clean: for (thr = 0; thr < nr_threads; thr++) { if (data[thr].thr) kthread_stop(data[thr].thr); - acomp_request_free(data[thr].cr); - crypto_free_acomp(data[thr].cc); + if (data[thr].cr) + acomp_request_free(data[thr].cr); + + if (!IS_ERR_OR_NULL(data[thr].cc)) + crypto_free_acomp(data[thr].cc); } vfree(data); } @@ -1499,8 +1502,11 @@ out_clean: for (thr = 0; thr < nr_threads; thr++) { if (data[thr].thr) kthread_stop(data[thr].thr); - acomp_request_free(data[thr].cr); - crypto_free_acomp(data[thr].cc); + if (data[thr].cr) + acomp_request_free(data[thr].cr); + + if (!IS_ERR_OR_NULL(data[thr].cc)) + crypto_free_acomp(data[thr].cc); } vfree(data); } diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 3fa403f9831f..32fc12e53675 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1557,18 +1557,27 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) ctxt->allow_unsafe_takeover = nbcon_allow_unsafe_takeover(); while (nbcon_seq_read(con) < stop_seq) { - if (!nbcon_context_try_acquire(ctxt, false)) - return -EPERM; - /* - * nbcon_emit_next_record() returns false when the console was - * handed over or taken over. In both cases the context is no - * longer valid. + * Atomic flushing does not use console driver synchronization + * (i.e. it does not hold the port lock for uart consoles). + * Therefore IRQs must be disabled to avoid being interrupted + * and then calling into a driver that will deadlock trying + * to acquire console ownership. */ - if (!nbcon_emit_next_record(&wctxt, true)) - return -EAGAIN; + scoped_guard(irqsave) { + if (!nbcon_context_try_acquire(ctxt, false)) + return -EPERM; - nbcon_context_release(ctxt); + /* + * nbcon_emit_next_record() returns false when + * the console was handed over or taken over. + * In both cases the context is no longer valid. + */ + if (!nbcon_emit_next_record(&wctxt, true)) + return -EAGAIN; + + nbcon_context_release(ctxt); + } if (!ctxt->backlog) { /* Are there reserved but not yet finalized records? */ @@ -1595,22 +1604,11 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) { struct console_flush_type ft; - unsigned long flags; int err; again: - /* - * Atomic flushing does not use console driver synchronization (i.e. - * it does not hold the port lock for uart consoles). Therefore IRQs - * must be disabled to avoid being interrupted and then calling into - * a driver that will deadlock trying to acquire console ownership. - */ - local_irq_save(flags); - err = __nbcon_atomic_flush_pending_con(con, stop_seq); - local_irq_restore(flags); - /* * If there was a new owner (-EPERM, -EAGAIN), that context is * responsible for completing. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 41ba0be16911..045f83ad261e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4950,9 +4950,13 @@ struct balance_callback *splice_balance_callbacks(struct rq *rq) return __splice_balance_callbacks(rq, true); } -static void __balance_callbacks(struct rq *rq) +void __balance_callbacks(struct rq *rq, struct rq_flags *rf) { + if (rf) + rq_unpin_lock(rq, rf); do_balance_callbacks(rq, __splice_balance_callbacks(rq, false)); + if (rf) + rq_repin_lock(rq, rf); } void balance_callbacks(struct rq *rq, struct balance_callback *head) @@ -4991,7 +4995,7 @@ static inline void finish_lock_switch(struct rq *rq) * prev into current: */ spin_acquire(&__rq_lockp(rq)->dep_map, 0, 0, _THIS_IP_); - __balance_callbacks(rq); + __balance_callbacks(rq, NULL); raw_spin_rq_unlock_irq(rq); } @@ -6867,7 +6871,7 @@ keep_resched: proxy_tag_curr(rq, next); rq_unpin_lock(rq, &rf); - __balance_callbacks(rq); + __balance_callbacks(rq, NULL); raw_spin_rq_unlock_irq(rq); } trace_sched_exit_tp(is_switch); @@ -7316,7 +7320,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) trace_sched_pi_setprio(p, pi_task); oldprio = p->prio; - if (oldprio == prio) + if (oldprio == prio && !dl_prio(prio)) queue_flag &= ~DEQUEUE_MOVE; prev_class = p->sched_class; @@ -7362,9 +7366,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) out_unlock: /* Caller holds task_struct::pi_lock, IRQs are still disabled */ - rq_unpin_lock(rq, &rf); - __balance_callbacks(rq); - rq_repin_lock(rq, &rf); + __balance_callbacks(rq, &rf); __task_rq_unlock(rq, p, &rf); } #endif /* CONFIG_RT_MUTEXES */ @@ -9124,6 +9126,8 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup) if (resched) resched_curr(rq); + + __balance_callbacks(rq, &rq_guard.rf); } static struct cgroup_subsys_state * @@ -10694,10 +10698,11 @@ void sched_mm_cid_before_execve(struct task_struct *t) sched_mm_cid_exit(t); } -/* Reactivate MM CID after successful execve() */ +/* Reactivate MM CID after execve() */ void sched_mm_cid_after_execve(struct task_struct *t) { - sched_mm_cid_fork(t); + if (t->mm) + sched_mm_cid_fork(t); } static void mm_cid_work_fn(struct work_struct *work) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 319439fe1870..c509f2e7d69d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -752,8 +752,6 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - update_rq_clock(rq); - WARN_ON(is_dl_boosted(dl_se)); WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); @@ -1420,7 +1418,7 @@ update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se, int static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec) { - bool idle = rq->curr == rq->idle; + bool idle = idle_rq(rq); s64 scaled_delta_exec; if (unlikely(delta_exec <= 0)) { @@ -1603,8 +1601,8 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) * | 8 | B:zero_laxity-wait | | | * | | | <---+ | * | +--------------------------------+ | - * | | ^ ^ 2 | - * | | 7 | 2 +--------------------+ + * | | ^ ^ 2 | + * | | 7 | 2, 1 +----------------+ * | v | * | +-------------+ | * +-- | C:idle-wait | -+ @@ -1649,8 +1647,11 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) * dl_defer_idle = 0 * * - * [1] A->B, A->D + * [1] A->B, A->D, C->B * dl_server_start() + * dl_defer_idle = 0; + * if (dl_server_active) + * return; // [B] * dl_server_active = 1; * enqueue_dl_entity() * update_dl_entity(WAKEUP) @@ -1759,6 +1760,7 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) * "B:zero_laxity-wait" -> "C:idle-wait" [label="7:dl_server_update_idle"] * "B:zero_laxity-wait" -> "D:running" [label="3:dl_server_timer"] * "C:idle-wait" -> "A:init" [label="8:dl_server_timer"] + * "C:idle-wait" -> "B:zero_laxity-wait" [label="1:dl_server_start"] * "C:idle-wait" -> "B:zero_laxity-wait" [label="2:dl_server_update"] * "C:idle-wait" -> "C:idle-wait" [label="7:dl_server_update_idle"] * "D:running" -> "A:init" [label="4:pick_task_dl"] @@ -1784,6 +1786,7 @@ void dl_server_start(struct sched_dl_entity *dl_se) { struct rq *rq = dl_se->rq; + dl_se->dl_defer_idle = 0; if (!dl_server(dl_se) || dl_se->dl_server_active) return; @@ -1834,6 +1837,7 @@ void sched_init_dl_servers(void) rq = cpu_rq(cpu); guard(rq_lock_irq)(rq); + update_rq_clock(rq); dl_se = &rq->fair_server; @@ -2210,7 +2214,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) update_dl_entity(dl_se); } else if (flags & ENQUEUE_REPLENISH) { replenish_dl_entity(dl_se); - } else if ((flags & ENQUEUE_RESTORE) && + } else if ((flags & ENQUEUE_MOVE) && !is_dl_boosted(dl_se) && dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_se(dl_se)))) { setup_new_dl_entity(dl_se); @@ -3154,7 +3158,7 @@ void dl_add_task_root_domain(struct task_struct *p) struct rq *rq; struct dl_bw *dl_b; unsigned int cpu; - struct cpumask *msk = this_cpu_cpumask_var_ptr(local_cpu_mask_dl); + struct cpumask *msk; raw_spin_lock_irqsave(&p->pi_lock, rf.flags); if (!dl_task(p) || dl_entity_is_special(&p->dl)) { @@ -3162,20 +3166,12 @@ void dl_add_task_root_domain(struct task_struct *p) return; } - /* - * Get an active rq, whose rq->rd traces the correct root - * domain. - * Ideally this would be under cpuset reader lock until rq->rd is - * fetched. However, sleepable locks cannot nest inside pi_lock, so we - * rely on the caller of dl_add_task_root_domain() holds 'cpuset_mutex' - * to guarantee the CPU stays in the cpuset. - */ + msk = this_cpu_cpumask_var_ptr(local_cpu_mask_dl); dl_get_task_effective_cpus(p, msk); cpu = cpumask_first_and(cpu_active_mask, msk); BUG_ON(cpu >= nr_cpu_ids); rq = cpu_rq(cpu); dl_b = &rq->rd->dl_bw; - /* End of fetching rd */ raw_spin_lock(&dl_b->lock); __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span)); @@ -3299,6 +3295,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) static u64 get_prio_dl(struct rq *rq, struct task_struct *p) { + /* + * Make sure to update current so we don't return a stale value. + */ + if (task_current_donor(rq, p)) + update_curr_dl(rq); + return p->dl.deadline; } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 94164f2dec6d..afe28c04d5aa 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -545,6 +545,7 @@ static void scx_task_iter_start(struct scx_task_iter *iter) static void __scx_task_iter_rq_unlock(struct scx_task_iter *iter) { if (iter->locked_task) { + __balance_callbacks(iter->rq, &iter->rf); task_rq_unlock(iter->rq, iter->locked_task, &iter->rf); iter->locked_task = NULL; } @@ -1577,7 +1578,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags * * @p may go through multiple stopping <-> running transitions between * here and put_prev_task_scx() if task attribute changes occur while - * balance_scx() leaves @rq unlocked. However, they don't contain any + * balance_one() leaves @rq unlocked. However, they don't contain any * information meaningful to the BPF scheduler and can be suppressed by * skipping the callbacks if the task is !QUEUED. */ @@ -2372,7 +2373,7 @@ static void switch_class(struct rq *rq, struct task_struct *next) * preempted, and it regaining control of the CPU. * * ->cpu_release() complements ->cpu_acquire(), which is emitted the - * next time that balance_scx() is invoked. + * next time that balance_one() is invoked. */ if (!rq->scx.cpu_released) { if (SCX_HAS_OP(sch, cpu_release)) { @@ -2478,7 +2479,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) } /* - * If balance_scx() is telling us to keep running @prev, replenish slice + * If balance_one() is telling us to keep running @prev, replenish slice * if necessary and keep running @prev. Otherwise, pop the first one * from the local DSQ. */ @@ -3956,13 +3957,8 @@ static void bypass_lb_node(struct scx_sched *sch, int node) nr_donor_target, nr_target); } - for_each_cpu(cpu, resched_mask) { - struct rq *rq = cpu_rq(cpu); - - raw_spin_rq_lock_irq(rq); - resched_curr(rq); - raw_spin_rq_unlock_irq(rq); - } + for_each_cpu(cpu, resched_mask) + resched_cpu(cpu); for_each_cpu_and(cpu, cpu_online_mask, node_mask) { u32 nr = READ_ONCE(cpu_rq(cpu)->scx.bypass_dsq.nr); @@ -4025,7 +4021,7 @@ static DEFINE_TIMER(scx_bypass_lb_timer, scx_bypass_lb_timerfn); * * - ops.dispatch() is ignored. * - * - balance_scx() does not set %SCX_RQ_BAL_KEEP on non-zero slice as slice + * - balance_one() does not set %SCX_RQ_BAL_KEEP on non-zero slice as slice * can't be trusted. Whenever a tick triggers, the running task is rotated to * the tail of the queue with core_sched_at touched. * @@ -4783,8 +4779,10 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops) } sch->pcpu = alloc_percpu(struct scx_sched_pcpu); - if (!sch->pcpu) + if (!sch->pcpu) { + ret = -ENOMEM; goto err_free_gdsqs; + } sch->helper = kthread_run_worker(0, "sched_ext_helper"); if (IS_ERR(sch->helper)) { @@ -6067,7 +6065,7 @@ __bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id) /* * A successfully consumed task can be dequeued before it starts * running while the CPU is trying to migrate other dispatched - * tasks. Bump nr_tasks to tell balance_scx() to retry on empty + * tasks. Bump nr_tasks to tell balance_one() to retry on empty * local DSQ. */ dspc->nr_tasks++; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index da46c3164537..3eaeceda71b0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -15,7 +15,7 @@ * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> * * Scaled math optimizations by Thomas Gleixner - * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2007, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * Adaptive scheduling granularity, math enhancements by Peter Zijlstra * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra @@ -8828,16 +8828,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int if ((wake_flags & WF_FORK) || pse->sched_delayed) return; - /* - * If @p potentially is completing work required by current then - * consider preemption. - * - * Reschedule if waker is no longer eligible. */ - if (in_task() && !entity_eligible(cfs_rq, se)) { - preempt_action = PREEMPT_WAKEUP_RESCHED; - goto preempt; - } - /* Prefer picking wakee soon if appropriate. */ if (sched_feat(NEXT_BUDDY) && set_preempt_buddy(cfs_rq, wake_flags, pse, se)) { @@ -8995,12 +8985,6 @@ idle: goto again; } - /* - * rq is about to be idle, check if we need to update the - * lost_idle_time of clock_pelt - */ - update_idle_rq_clock_pelt(rq); - return NULL; } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 980d92bab8ab..136a6584be79 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -29,7 +29,7 @@ SCHED_FEAT(PREEMPT_SHORT, true) * wakeup-preemption), since its likely going to consume data we * touched, increases cache locality. */ -SCHED_FEAT(NEXT_BUDDY, true) +SCHED_FEAT(NEXT_BUDDY, false) /* * Allow completely ignoring cfs_rq->next; which can be set from various diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index c174afe1dd17..abf8f15d60c9 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -468,6 +468,12 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir scx_update_idle(rq, true, true); schedstat_inc(rq->sched_goidle); next->se.exec_start = rq_clock_task(rq); + + /* + * rq is about to be idle, check if we need to update the + * lost_idle_time of clock_pelt + */ + update_idle_rq_clock_pelt(rq); } struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf) diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index fa83bbaf4f3e..897790889ba3 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -15,7 +15,7 @@ * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> * * Scaled math optimizations by Thomas Gleixner - * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2007, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * Adaptive scheduling granularity, math enhancements by Peter Zijlstra * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d30cca6870f5..93fce4bbff5e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1364,6 +1364,28 @@ static inline u32 sched_rng(void) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues) +static inline bool idle_rq(struct rq *rq) +{ + return rq->curr == rq->idle && !rq->nr_running && !rq->ttwu_pending; +} + +/** + * available_idle_cpu - is a given CPU idle for enqueuing work. + * @cpu: the CPU in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +static inline bool available_idle_cpu(int cpu) +{ + if (!idle_rq(cpu_rq(cpu))) + return 0; + + if (vcpu_is_preempted(cpu)) + return 0; + + return 1; +} + #ifdef CONFIG_SCHED_PROXY_EXEC static inline void rq_set_donor(struct rq *rq, struct task_struct *t) { @@ -2366,7 +2388,8 @@ extern const u32 sched_prio_to_wmult[40]; * should preserve as much state as possible. * * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location - * in the runqueue. + * in the runqueue. IOW the priority is allowed to change. Callers + * must expect to deal with balance callbacks. * * NOCLOCK - skip the update_rq_clock() (avoids double updates) * @@ -3947,6 +3970,8 @@ extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags); extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags); extern struct balance_callback *splice_balance_callbacks(struct rq *rq); + +extern void __balance_callbacks(struct rq *rq, struct rq_flags *rf); extern void balance_callbacks(struct rq *rq, struct balance_callback *head); /* diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 0496dc29ed0f..6f10db3646e7 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -180,35 +180,7 @@ int task_prio(const struct task_struct *p) */ int idle_cpu(int cpu) { - struct rq *rq = cpu_rq(cpu); - - if (rq->curr != rq->idle) - return 0; - - if (rq->nr_running) - return 0; - - if (rq->ttwu_pending) - return 0; - - return 1; -} - -/** - * available_idle_cpu - is a given CPU idle for enqueuing work. - * @cpu: the CPU in question. - * - * Return: 1 if the CPU is currently idle. 0 otherwise. - */ -int available_idle_cpu(int cpu) -{ - if (!idle_cpu(cpu)) - return 0; - - if (vcpu_is_preempted(cpu)) - return 0; - - return 1; + return idle_rq(cpu_rq(cpu)); } /** @@ -667,7 +639,7 @@ change: * itself. */ newprio = rt_effective_prio(p, newprio); - if (newprio == oldprio) + if (newprio == oldprio && !dl_prio(newprio)) queue_flags &= ~DEQUEUE_MOVE; } diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index a59bc75ab7c5..eaae1ce9f060 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -2,7 +2,7 @@ /* * This file contains functions which manage clock event devices. * - * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index a1890a073196..df7194961658 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -252,7 +252,7 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { - int64_t md = 2 * watchdog->uncertainty_margin; + int64_t md = watchdog->uncertainty_margin; unsigned int nretries, max_retries; int64_t wd_delay, wd_seq_delay; u64 wd_end, wd_end2; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index f8ea8c8fc895..0e4bc1ca15ff 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * @@ -913,7 +913,7 @@ static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, return true; /* Extra check for softirq clock bases */ - if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) + if (base->index < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 0207868c8b4d..f63c65881364 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -3,7 +3,7 @@ * This file contains functions which emulate a local clock-event * device via a broadcast event source. * - * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 7e33d3f2e889..d305d8521896 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -3,7 +3,7 @@ * This file contains the base functions to manage periodic tick * related events. * - * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index ffee943d796d..7472597f3225 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -3,7 +3,7 @@ * This file contains functions which manage high resolution tick * related events. * - * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 8ddf74e705d3..2f8a7923fa27 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3ec3daa4acab..91fa2003351c 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2735,7 +2735,7 @@ static int __do_adjtimex(struct tk_data *tkd, struct __kernel_timex *txc, timekeeping_update_from_shadow(tkd, TK_CLOCK_WAS_SET); result->clock_set = true; } else { - tk_update_leap_state_all(&tk_core); + tk_update_leap_state_all(tkd); } /* Update the multiplier immediately if frequency was set directly */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ef2d5dca6f70..aa758efc3731 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1148,7 +1148,6 @@ struct ftrace_page { }; #define ENTRY_SIZE sizeof(struct dyn_ftrace) -#define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; @@ -3834,7 +3833,8 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) return 0; } -static int ftrace_allocate_records(struct ftrace_page *pg, int count) +static int ftrace_allocate_records(struct ftrace_page *pg, int count, + unsigned long *num_pages) { int order; int pages; @@ -3844,7 +3844,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) return -EINVAL; /* We want to fill as much as possible, with no empty pages */ - pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); + pages = DIV_ROUND_UP(count * ENTRY_SIZE, PAGE_SIZE); order = fls(pages) - 1; again: @@ -3859,6 +3859,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) } ftrace_number_of_pages += 1 << order; + *num_pages += 1 << order; ftrace_number_of_groups++; cnt = (PAGE_SIZE << order) / ENTRY_SIZE; @@ -3887,12 +3888,14 @@ static void ftrace_free_pages(struct ftrace_page *pages) } static struct ftrace_page * -ftrace_allocate_pages(unsigned long num_to_init) +ftrace_allocate_pages(unsigned long num_to_init, unsigned long *num_pages) { struct ftrace_page *start_pg; struct ftrace_page *pg; int cnt; + *num_pages = 0; + if (!num_to_init) return NULL; @@ -3906,7 +3909,7 @@ ftrace_allocate_pages(unsigned long num_to_init) * waste as little space as possible. */ for (;;) { - cnt = ftrace_allocate_records(pg, num_to_init); + cnt = ftrace_allocate_records(pg, num_to_init, num_pages); if (cnt < 0) goto free_pages; @@ -7192,8 +7195,6 @@ static int ftrace_process_locs(struct module *mod, if (!count) return 0; - pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); - /* * Sorting mcount in vmlinux at build time depend on * CONFIG_BUILDTIME_MCOUNT_SORT, while mcount loc in @@ -7206,7 +7207,7 @@ static int ftrace_process_locs(struct module *mod, test_is_sorted(start, count); } - start_pg = ftrace_allocate_pages(count); + start_pg = ftrace_allocate_pages(count, &pages); if (!start_pg) return -ENOMEM; @@ -7305,27 +7306,27 @@ static int ftrace_process_locs(struct module *mod, /* We should have used all pages unless we skipped some */ if (pg_unuse) { unsigned long pg_remaining, remaining = 0; - unsigned long skip; + long skip; /* Count the number of entries unused and compare it to skipped. */ - pg_remaining = (ENTRIES_PER_PAGE << pg->order) - pg->index; + pg_remaining = (PAGE_SIZE << pg->order) / ENTRY_SIZE - pg->index; if (!WARN(skipped < pg_remaining, "Extra allocated pages for ftrace")) { skip = skipped - pg_remaining; - for (pg = pg_unuse; pg; pg = pg->next) + for (pg = pg_unuse; pg && skip > 0; pg = pg->next) { remaining += 1 << pg->order; + skip -= (PAGE_SIZE << pg->order) / ENTRY_SIZE; + } pages -= remaining; - skip = DIV_ROUND_UP(skip, ENTRIES_PER_PAGE); - /* * Check to see if the number of pages remaining would * just fit the number of entries skipped. */ - WARN(skip != remaining, "Extra allocated pages for ftrace: %lu with %lu skipped", + WARN(pg || skip > 0, "Extra allocated pages for ftrace: %lu with %lu skipped", remaining, skipped); } /* Need to synchronize with ftrace_location_range() */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 41c9f5d079be..630221b00838 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3137,6 +3137,8 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, list) { list_del_init(&bpage->list); free_buffer_page(bpage); + + cond_resched(); } } out_err_unlock: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6f2148df14d9..8bd4ec08fb36 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -138,7 +138,7 @@ cpumask_var_t __read_mostly tracing_buffer_mask; * by commas. */ /* Set to string format zero to disable by default */ -char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0"; +static char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0"; /* When set, tracing will stop when a WARN*() is hit */ static int __disable_trace_on_warning; @@ -3012,6 +3012,11 @@ static void __ftrace_trace_stack(struct trace_array *tr, struct ftrace_stack *fstack; struct stack_entry *entry; int stackidx; + int bit; + + bit = trace_test_and_set_recursion(_THIS_IP_, _RET_IP_, TRACE_EVENT_START); + if (bit < 0) + return; /* * Add one, for this function and the call to save_stack_trace() @@ -3080,6 +3085,7 @@ static void __ftrace_trace_stack(struct trace_array *tr, /* Again, don't let gcc optimize things here */ barrier(); __this_cpu_dec(ftrace_stack_reserve); + trace_clear_recursion(bit); } static inline void ftrace_trace_stack(struct trace_array *tr, @@ -6109,10 +6115,10 @@ static int cmp_mod_entry(const void *key, const void *pivot) unsigned long addr = (unsigned long)key; const struct trace_mod_entry *ent = pivot; - if (addr >= ent[0].mod_addr && addr < ent[1].mod_addr) - return 0; - else - return addr - ent->mod_addr; + if (addr < ent[0].mod_addr) + return -1; + + return addr >= ent[1].mod_addr; } /** diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 76067529db61..137b4d9bb116 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -826,16 +826,15 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, * When soft_disable is set and enable is set, we want to * register the tracepoint for the event, but leave the event * as is. That means, if the event was already enabled, we do - * nothing (but set soft_mode). If the event is disabled, we - * set SOFT_DISABLED before enabling the event tracepoint, so - * it still seems to be disabled. + * nothing. If the event is disabled, we set SOFT_DISABLED + * before enabling the event tracepoint, so it still seems + * to be disabled. */ if (!soft_disable) clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); else { if (atomic_inc_return(&file->sm_ref) > 1) break; - soft_mode = true; /* Enable use of trace_buffered_event */ trace_buffered_event_enable(); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 5e6e70540eef..c97bb2fda5c0 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2057,6 +2057,15 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, hist_field->fn_num = HIST_FIELD_FN_RELDYNSTRING; else hist_field->fn_num = HIST_FIELD_FN_PSTRING; + } else if (field->filter_type == FILTER_STACKTRACE) { + flags |= HIST_FIELD_FL_STACKTRACE; + + hist_field->size = MAX_FILTER_STR_VAL; + hist_field->type = kstrdup_const(field->type, GFP_KERNEL); + if (!hist_field->type) + goto free; + + hist_field->fn_num = HIST_FIELD_FN_STACK; } else { hist_field->size = field->size; hist_field->is_signed = field->is_signed; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 4554c458b78c..45c187e77e21 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -130,7 +130,9 @@ static int synth_event_define_fields(struct trace_event_call *call) struct synth_event *event = call->data; unsigned int i, size, n_u64; char *name, *type; + int filter_type; bool is_signed; + bool is_stack; int ret = 0; for (i = 0, n_u64 = 0; i < event->n_fields; i++) { @@ -138,8 +140,12 @@ static int synth_event_define_fields(struct trace_event_call *call) is_signed = event->fields[i]->is_signed; type = event->fields[i]->type; name = event->fields[i]->name; + is_stack = event->fields[i]->is_stack; + + filter_type = is_stack ? FILTER_STACKTRACE : FILTER_OTHER; + ret = trace_define_field(call, type, name, offset, size, - is_signed, FILTER_OTHER); + is_signed, filter_type); if (ret) break; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index b1e9c9913309..1de6f1573621 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -901,7 +901,7 @@ static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entr trace_seq_printf(s, "%ps", func); if (args_size >= FTRACE_REGS_MAX_ARGS * sizeof(long)) { - print_function_args(s, entry->args, (unsigned long)func); + print_function_args(s, FGRAPH_ENTRY_ARGS(entry), (unsigned long)func); trace_seq_putc(s, ';'); } else trace_seq_puts(s, "();"); diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index fe9bf8db1922..e2784038bbed 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -36,7 +36,11 @@ struct hwerr_info { time64_t timestamp; }; -static struct hwerr_info hwerr_data[HWERR_RECOV_MAX]; +/* + * The hwerr_data[] array is declared with global scope so that it remains + * accessible to vmcoreinfo even when Link Time Optimization (LTO) is enabled. + */ +struct hwerr_info hwerr_data[HWERR_RECOV_MAX]; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 0685e3a8aa0a..366122f4a0f8 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -71,7 +71,7 @@ unsigned int __read_mostly hardlockup_panic = * hard lockup is detected, it could be task, memory, lock etc. * Refer include/linux/sys_info.h for detailed bit definition. */ -static unsigned long hardlockup_si_mask; +unsigned long hardlockup_si_mask; #ifdef CONFIG_SYSFS diff --git a/lib/buildid.c b/lib/buildid.c index aaf61dfc0919..818331051afe 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -5,6 +5,7 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/pagemap.h> +#include <linux/fs.h> #include <linux/secretmem.h> #define BUILD_ID 3 @@ -46,20 +47,9 @@ static int freader_get_folio(struct freader *r, loff_t file_off) freader_put_folio(r); - /* reject secretmem folios created with memfd_secret() */ - if (secretmem_mapping(r->file->f_mapping)) - return -EFAULT; - + /* only use page cache lookup - fail if not already cached */ r->folio = filemap_get_folio(r->file->f_mapping, file_off >> PAGE_SHIFT); - /* if sleeping is allowed, wait for the page, if necessary */ - if (r->may_fault && (IS_ERR(r->folio) || !folio_test_uptodate(r->folio))) { - filemap_invalidate_lock_shared(r->file->f_mapping); - r->folio = read_cache_folio(r->file->f_mapping, file_off >> PAGE_SHIFT, - NULL, r->file); - filemap_invalidate_unlock_shared(r->file->f_mapping); - } - if (IS_ERR(r->folio) || !folio_test_uptodate(r->folio)) { if (!IS_ERR(r->folio)) folio_put(r->folio); @@ -97,6 +87,24 @@ const void *freader_fetch(struct freader *r, loff_t file_off, size_t sz) return r->data + file_off; } + /* reject secretmem folios created with memfd_secret() */ + if (secretmem_mapping(r->file->f_mapping)) { + r->err = -EFAULT; + return NULL; + } + + /* use __kernel_read() for sleepable context */ + if (r->may_fault) { + ssize_t ret; + + ret = __kernel_read(r->file, r->buf, sz, &file_off); + if (ret != sz) { + r->err = (ret < 0) ? ret : -EIO; + return NULL; + } + return r->buf; + } + /* fetch or reuse folio for given file offset */ r->err = freader_get_folio(r, file_off); if (r->err) diff --git a/lib/crypto/aes.c b/lib/crypto/aes.c index b57fda3460f1..102aaa76bc8d 100644 --- a/lib/crypto/aes.c +++ b/lib/crypto/aes.c @@ -13,7 +13,7 @@ * Emit the sbox as volatile const to prevent the compiler from doing * constant folding on sbox references involving fixed indexes. */ -static volatile const u8 __cacheline_aligned aes_sbox[] = { +static volatile const u8 ____cacheline_aligned aes_sbox[] = { 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76, 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, @@ -48,7 +48,7 @@ static volatile const u8 __cacheline_aligned aes_sbox[] = { 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16, }; -static volatile const u8 __cacheline_aligned aes_inv_sbox[] = { +static volatile const u8 ____cacheline_aligned aes_inv_sbox[] = { 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb, 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, diff --git a/lib/crypto/tests/polyval_kunit.c b/lib/crypto/tests/polyval_kunit.c index e59f598c1572..f47f41a39a41 100644 --- a/lib/crypto/tests/polyval_kunit.c +++ b/lib/crypto/tests/polyval_kunit.c @@ -183,7 +183,7 @@ static void test_polyval_preparekey_in_irqs(struct kunit *test) rand_bytes(state.raw_key, sizeof(state.raw_key)); polyval_preparekey(&state.expected_key, state.raw_key); - kunit_run_irq_test(test, polyval_irq_test_func, 20000, &state); + kunit_run_irq_test(test, polyval_irq_test_func, 200000, &state); } static int polyval_suite_init(struct kunit_suite *suite) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index ecf8e7f978e3..89a1d6745dc2 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -2,7 +2,7 @@ /* * Generic infrastructure for lifetime debugging of objects. * - * Copyright (C) 2008, Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> */ #define pr_fmt(fmt) "ODEBUG: " fmt diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c index 84ecccddc771..012d5614efb9 100644 --- a/lib/flex_proportions.c +++ b/lib/flex_proportions.c @@ -64,13 +64,14 @@ void fprop_global_destroy(struct fprop_global *p) bool fprop_new_period(struct fprop_global *p, int periods) { s64 events = percpu_counter_sum(&p->events); + unsigned long flags; /* * Don't do anything if there are no events. */ if (events <= 1) return false; - preempt_disable_nested(); + local_irq_save(flags); write_seqcount_begin(&p->sequence); if (periods < 64) events -= events >> periods; @@ -78,7 +79,7 @@ bool fprop_new_period(struct fprop_global *p, int periods) percpu_counter_add(&p->events, -events); p->period += periods; write_seqcount_end(&p->sequence); - preempt_enable_nested(); + local_irq_restore(flags); return true; } diff --git a/lib/idr.c b/lib/idr.c index e2adc457abb4..457430cff8c5 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -40,6 +40,8 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) idr->idr_rt.xa_flags |= IDR_RT_MARKER; + if (max < base) + return -ENOSPC; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); diff --git a/lib/plist.c b/lib/plist.c index ba677c31e8f3..a5bef38add43 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -10,7 +10,7 @@ * 2001-2005 (c) MontaVista Software, Inc. * Daniel Walker <dwalker@mvista.com> * - * (C) 2005 Thomas Gleixner <tglx@linutronix.de> + * (C) 2005 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * Simplifications of the original code by * Oleg Nesterov <oleg@tv-sign.ru> diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c index 805de84ae83d..ef86ee2aec58 100644 --- a/lib/reed_solomon/decode_rs.c +++ b/lib/reed_solomon/decode_rs.c @@ -5,7 +5,7 @@ * Copyright 2002, Phil Karn, KA9Q * May be used under the terms of the GNU General Public License (GPL) * - * Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de) + * Adaption to the kernel by Thomas Gleixner (tglx@kernel.org) * * Generic data width independent code which is included by the wrappers. */ diff --git a/lib/reed_solomon/encode_rs.c b/lib/reed_solomon/encode_rs.c index 9112d46e869e..1d9e51dcc83d 100644 --- a/lib/reed_solomon/encode_rs.c +++ b/lib/reed_solomon/encode_rs.c @@ -5,7 +5,7 @@ * Copyright 2002, Phil Karn, KA9Q * May be used under the terms of the GNU General Public License (GPL) * - * Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de) + * Adaption to the kernel by Thomas Gleixner (tglx@kernel.org) * * Generic data width independent code which is included by the wrappers. */ diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c index bbc01bad3053..a9e2dcb6f2a7 100644 --- a/lib/reed_solomon/reed_solomon.c +++ b/lib/reed_solomon/reed_solomon.c @@ -2,7 +2,7 @@ /* * Generic Reed Solomon encoder / decoder library * - * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de) + * Copyright (C) 2004 Thomas Gleixner (tglx@kernel.org) * * Reed Solomon code lifted from reed solomon library written by Phil Karn * Copyright 2002 Phil Karn, KA9Q diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 8af169d3873a..455a6862ae50 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -662,7 +662,9 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror *dmirror, goto error; } - zone_device_folio_init(page_folio(dpage), order); + zone_device_folio_init(page_folio(dpage), + page_pgmap(folio_page(page_folio(dpage), 0)), + order); dpage->zone_device_data = rpage; return dpage; diff --git a/mm/Kconfig b/mm/Kconfig index bd0ea5454af8..a992f2203eb9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1220,10 +1220,14 @@ config ZONE_DEVICE Device memory hotplug support allows for establishing pmem, or other device driver discovered memory regions, in the memmap. This allows pfn_to_page() lookups of otherwise - "device-physical" addresses which is needed for using a DAX - mapping in an O_DIRECT operation, among other things. - - If FS_DAX is enabled, then say Y. + "device-physical" addresses which is needed for DAX, PCI_P2PDMA, and + DEVICE_PRIVATE features among others. + + Enabling this option will reduce the entropy of x86 KASLR memory + regions. For example - on a 46 bit system, the entropy goes down + from 16 bits to 15 bits. The actual reduction in entropy depends + on the physical address bits, on processor features, kernel config + (5 level page table) and physical memory present on the system. # # Helpers to mirror range of the CPU page tables of a process into device page diff --git a/mm/damon/core.c b/mm/damon/core.c index f9fc0375890a..84f80a20f233 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1431,6 +1431,35 @@ bool damon_is_running(struct damon_ctx *ctx) return running; } +/* + * damon_call_handle_inactive_ctx() - handle DAMON call request that added to + * an inactive context. + * @ctx: The inactive DAMON context. + * @control: Control variable of the call request. + * + * This function is called in a case that @control is added to @ctx but @ctx is + * not running (inactive). See if @ctx handled @control or not, and cleanup + * @control if it was not handled. + * + * Returns 0 if @control was handled by @ctx, negative error code otherwise. + */ +static int damon_call_handle_inactive_ctx( + struct damon_ctx *ctx, struct damon_call_control *control) +{ + struct damon_call_control *c; + + mutex_lock(&ctx->call_controls_lock); + list_for_each_entry(c, &ctx->call_controls, list) { + if (c == control) { + list_del(&control->list); + mutex_unlock(&ctx->call_controls_lock); + return -EINVAL; + } + } + mutex_unlock(&ctx->call_controls_lock); + return 0; +} + /** * damon_call() - Invoke a given function on DAMON worker thread (kdamond). * @ctx: DAMON context to call the function for. @@ -1461,7 +1490,7 @@ int damon_call(struct damon_ctx *ctx, struct damon_call_control *control) list_add_tail(&control->list, &ctx->call_controls); mutex_unlock(&ctx->call_controls_lock); if (!damon_is_running(ctx)) - return -EINVAL; + return damon_call_handle_inactive_ctx(ctx, control); if (control->repeat) return 0; wait_for_completion(&control->completion); @@ -2051,13 +2080,15 @@ static unsigned long damos_get_node_memcg_used_bp( rcu_read_lock(); memcg = mem_cgroup_from_id(goal->memcg_id); - rcu_read_unlock(); - if (!memcg) { + if (!memcg || !mem_cgroup_tryget(memcg)) { + rcu_read_unlock(); if (goal->metric == DAMOS_QUOTA_NODE_MEMCG_USED_BP) return 0; else /* DAMOS_QUOTA_NODE_MEMCG_FREE_BP */ return 10000; } + rcu_read_unlock(); + mem_cgroup_flush_stats(memcg); lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(goal->nid)); used_pages = lruvec_page_state(lruvec, NR_ACTIVE_ANON); @@ -2065,6 +2096,8 @@ static unsigned long damos_get_node_memcg_used_bp( used_pages += lruvec_page_state(lruvec, NR_ACTIVE_FILE); used_pages += lruvec_page_state(lruvec, NR_INACTIVE_FILE); + mem_cgroup_put(memcg); + si_meminfo_node(&i, goal->nid); if (goal->metric == DAMOS_QUOTA_NODE_MEMCG_USED_BP) numerator = used_pages; @@ -2751,13 +2784,13 @@ done: if (ctx->ops.cleanup) ctx->ops.cleanup(ctx); kfree(ctx->regions_score_histogram); + kdamond_call(ctx, true); pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); ctx->kdamond = NULL; mutex_unlock(&ctx->kdamond_lock); - kdamond_call(ctx, true); damos_walk_cancel(ctx); mutex_lock(&damon_lock); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 30d20f5b3192..3a699dcd5a7f 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -2152,13 +2152,13 @@ static int damon_sysfs_scheme_add_dirs(struct damon_sysfs_scheme *scheme) return err; err = damos_sysfs_set_dests(scheme); if (err) - goto put_access_pattern_out; + goto rmdir_put_access_pattern_out; err = damon_sysfs_scheme_set_quotas(scheme); if (err) goto put_dests_out; err = damon_sysfs_scheme_set_watermarks(scheme); if (err) - goto put_quotas_access_pattern_out; + goto rmdir_put_quotas_access_pattern_out; err = damos_sysfs_set_filter_dirs(scheme); if (err) goto put_watermarks_quotas_access_pattern_out; @@ -2183,13 +2183,15 @@ put_filters_watermarks_quotas_access_pattern_out: put_watermarks_quotas_access_pattern_out: kobject_put(&scheme->watermarks->kobj); scheme->watermarks = NULL; -put_quotas_access_pattern_out: +rmdir_put_quotas_access_pattern_out: + damon_sysfs_quotas_rm_dirs(scheme->quotas); kobject_put(&scheme->quotas->kobj); scheme->quotas = NULL; put_dests_out: kobject_put(&scheme->dests->kobj); scheme->dests = NULL; -put_access_pattern_out: +rmdir_put_access_pattern_out: + damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern); kobject_put(&scheme->access_pattern->kobj); scheme->access_pattern = NULL; return err; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index e2bd2d7becdd..95fd9375a7d8 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -792,7 +792,7 @@ static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) nr_regions_range = damon_sysfs_ul_range_alloc(10, 1000); if (!nr_regions_range) { err = -ENOMEM; - goto put_intervals_out; + goto rmdir_put_intervals_out; } err = kobject_init_and_add(&nr_regions_range->kobj, @@ -806,6 +806,8 @@ static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) put_nr_regions_intervals_out: kobject_put(&nr_regions_range->kobj); attrs->nr_regions_range = NULL; +rmdir_put_intervals_out: + damon_sysfs_intervals_rm_dirs(intervals); put_intervals_out: kobject_put(&intervals->kobj); attrs->intervals = NULL; @@ -948,7 +950,7 @@ static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) err = damon_sysfs_context_set_targets(context); if (err) - goto put_attrs_out; + goto rmdir_put_attrs_out; err = damon_sysfs_context_set_schemes(context); if (err) @@ -958,7 +960,8 @@ static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) put_targets_attrs_out: kobject_put(&context->targets->kobj); context->targets = NULL; -put_attrs_out: +rmdir_put_attrs_out: + damon_sysfs_attrs_rm_dirs(context->attrs); kobject_put(&context->attrs->kobj); context->attrs = NULL; return err; diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 2750c88e7225..23ed738a0bd6 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -743,7 +743,7 @@ huge_out: if (!folio) continue; if (damos_va_filter_out(s, folio, walk->vma, addr, pte, NULL)) - return 0; + continue; damos_va_migrate_dests_add(folio, walk->vma, addr, dests, migration_lists); nr = folio_nr_pages(folio); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 51273baec9e5..a1832da0f623 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4286,6 +4286,11 @@ static int __init hugepages_setup(char *s) unsigned long tmp; char *p = s; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring hugepages=%s cmdline\n", s); + return 0; + } + if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; @@ -4366,6 +4371,11 @@ static int __init hugepagesz_setup(char *s) unsigned long size; struct hstate *h; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring hugepagesz=%s cmdline\n", s); + return 0; + } + parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); @@ -4414,6 +4424,12 @@ static int __init default_hugepagesz_setup(char *s) unsigned long size; int i; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring default_hugepagesz=%s cmdline\n", + s); + return 0; + } + parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); @@ -5096,7 +5112,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; - bool shared_pmd = false; + struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); @@ -5106,6 +5122,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, * range. */ flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); @@ -5122,8 +5139,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; - if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { - shared_pmd = true; + if (huge_pmd_unshare(&tlb, vma, old_addr, src_pte)) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; @@ -5134,15 +5150,16 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); + tlb_remove_huge_tlb_entry(h, &tlb, src_pte, old_addr); } - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, old_end - len, old_end); + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); + mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); return len + old_addr - old_end; } @@ -5161,7 +5178,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); bool adjust_reservation; unsigned long last_addr_mask; - bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -5184,10 +5200,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(tlb, vma, address, ptep)) { spin_unlock(ptl); - tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); - force_flush = true; address |= last_addr_mask; continue; } @@ -5303,21 +5317,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } tlb_end_vma(tlb, vma); - /* - * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We - * could defer the flush until now, since by holding i_mmap_rwsem we - * guaranteed that the last reference would not be dropped. But we must - * do the flushing before we return, as otherwise i_mmap_rwsem will be - * dropped and the last reference to the shared PMDs page might be - * dropped as well. - * - * In theory we could defer the freeing of the PMD pages as well, but - * huge_pmd_unshare() relies on the exact page_count for the PMD page to - * detect sharing, so we cannot defer the release of the page either. - * Instead, do flush now. - */ - if (force_flush) - tlb_flush_mmu_tlbonly(tlb); + huge_pmd_unshare_flush(tlb, vma); } void __hugetlb_zap_begin(struct vm_area_struct *vma, @@ -6416,11 +6416,11 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); - bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + struct mmu_gather tlb; /* * In the case of shared PMDs, the area to flush could be beyond @@ -6433,6 +6433,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); @@ -6459,7 +6460,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, } } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(&tlb, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it @@ -6468,7 +6469,6 @@ long hugetlb_change_protection(struct vm_area_struct *vma, WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); - shared_pmd = true; address |= last_addr_mask; continue; } @@ -6529,23 +6529,16 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + tlb_remove_huge_tlb_entry(h, &tlb, ptep, address); } next: spin_unlock(ptl); cond_resched(); } - /* - * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare - * may have cleared our pud entry and done put_page on the page table: - * once we release i_mmap_rwsem, another task can do the final put_page - * and that page table be reused and filled with junk. If we actually - * did unshare a page of pmds, flush the range corresponding to the pud. - */ - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, start, end); + + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new @@ -6556,6 +6549,7 @@ next: i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); return pages > 0 ? (pages << h->order) : pages; } @@ -6912,18 +6906,27 @@ out: return pte; } -/* - * unmap huge page backed by shared pte. +/** + * huge_pmd_unshare - Unmap a pmd table if it is shared by multiple users + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * @addr: the address we are trying to unshare. + * @ptep: pointer into the (pmd) page table. * - * Called with page table lock held. + * Called with the page table lock held, the i_mmap_rwsem held in write mode + * and the hugetlb vma lock held in write mode. * - * returns: 1 successfully unmapped a shared pte page - * 0 the underlying pte page is not shared, or it is the last user + * Note: The caller must call huge_pmd_unshare_flush() before dropping the + * i_mmap_rwsem. + * + * Returns: 1 if it was a shared PMD table and it got unmapped, or 0 if it + * was not a shared PMD table. */ -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); + struct mm_struct *mm = vma->vm_mm; pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); @@ -6935,18 +6938,36 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); pud_clear(pud); - /* - * Once our caller drops the rmap lock, some other process might be - * using this page table as a normal, non-hugetlb page table. - * Wait for pending gup_fast() in other threads to finish before letting - * that happen. - */ - tlb_remove_table_sync_one(); - ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); + + tlb_unshare_pmd_ptdesc(tlb, virt_to_ptdesc(ptep), addr); + mm_dec_nr_pmds(mm); return 1; } +/* + * huge_pmd_unshare_flush - Complete a sequence of huge_pmd_unshare() calls + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * + * Perform necessary TLB flushes or IPI broadcasts to synchronize PMD table + * unsharing with concurrent page table walkers. + * + * This function must be called after a sequence of huge_pmd_unshare() + * calls while still holding the i_mmap_rwsem. + */ +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + /* + * We must synchronize page table unsharing such that nobody will + * try reusing a previously-shared page table while it might still + * be in use by previous sharers (TLB, GUP_fast). + */ + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + + tlb_flush_unshared_tables(tlb); +} + #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, @@ -6955,12 +6976,16 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; } -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { return 0; } +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ +} + void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { @@ -7227,6 +7252,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; + struct mmu_gather tlb; unsigned long address; spinlock_t *ptl; pte_t *ptep; @@ -7238,6 +7264,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, return; flush_cache_range(vma, start, end); + tlb_gather_mmu_vma(&tlb, vma); + /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. @@ -7256,10 +7284,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - huge_pmd_unshare(mm, vma, address, ptep); + huge_pmd_unshare(&tlb, vma, address, ptep); spin_unlock(ptl); } - flush_hugetlb_tlb_range(vma, start, end); + huge_pmd_unshare_flush(&tlb, vma); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); @@ -7269,6 +7297,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); } /* diff --git a/mm/init-mm.c b/mm/init-mm.c index 4600e7605cab..c5556bb9d5f0 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -44,7 +44,10 @@ struct mm_struct init_mm = { .mm_lock_seq = SEQCNT_ZERO(init_mm.mm_lock_seq), #endif .user_ns = &init_user_ns, - .cpu_bitmap = CPU_BITS_NONE, +#ifdef CONFIG_SCHED_MM_CID + .mm_cid.lock = __RAW_SPIN_LOCK_UNLOCKED(init_mm.mm_cid.lock), +#endif + .flexible_array = MM_STRUCT_FLEXIBLE_ARRAY_INIT, INIT_MM_CONTEXT(init_mm) }; diff --git a/mm/internal.h b/mm/internal.h index e430da900430..f35dbcf99a86 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -538,16 +538,8 @@ extern unsigned long highest_memmap_pfn; bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); -#ifdef CONFIG_NUMA int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat); -#else -static inline int user_proactive_reclaim(char *buf, - struct mem_cgroup *memcg, pg_data_t *pgdat) -{ - return 0; -} -#endif /* * in mm/rmap.c: diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 1d27f1bd260b..b7d05c2a6d93 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -28,6 +28,7 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/bug.h> +#include <linux/vmalloc.h> #include "kasan.h" #include "../slab.h" @@ -575,3 +576,55 @@ bool __kasan_check_byte(const void *address, unsigned long ip) } return true; } + +#ifdef CONFIG_KASAN_VMALLOC +void __kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ + unsigned long size; + void *addr; + int area; + u8 tag; + + /* + * If KASAN_VMALLOC_KEEP_TAG was set at this point, all vms[] pointers + * would be unpoisoned with the KASAN_TAG_KERNEL which would disable + * KASAN checks down the line. + */ + if (WARN_ON_ONCE(flags & KASAN_VMALLOC_KEEP_TAG)) + return; + + size = vms[0]->size; + addr = vms[0]->addr; + vms[0]->addr = __kasan_unpoison_vmalloc(addr, size, flags); + tag = get_tag(vms[0]->addr); + + for (area = 1 ; area < nr_vms ; area++) { + size = vms[area]->size; + addr = set_tag(vms[area]->addr, tag); + vms[area]->addr = + __kasan_unpoison_vmalloc(addr, size, flags | KASAN_VMALLOC_KEEP_TAG); + } +} + +void __kasan_vrealloc(const void *addr, unsigned long old_size, + unsigned long new_size) +{ + if (new_size < old_size) { + kasan_poison_last_granule(addr, new_size); + + new_size = round_up(new_size, KASAN_GRANULE_SIZE); + old_size = round_up(old_size, KASAN_GRANULE_SIZE); + if (new_size < old_size) + __kasan_poison_vmalloc(addr + new_size, + old_size - new_size); + } else if (new_size > old_size) { + old_size = round_down(old_size, KASAN_GRANULE_SIZE); + __kasan_unpoison_vmalloc(addr + old_size, + new_size - old_size, + KASAN_VMALLOC_PROT_NORMAL | + KASAN_VMALLOC_VM_ALLOC | + KASAN_VMALLOC_KEEP_TAG); + } +} +#endif diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 1c373cc4b3fa..cbef5e450954 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -361,7 +361,7 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, return (void *)start; } - tag = kasan_random_tag(); + tag = (flags & KASAN_VMALLOC_KEEP_TAG) ? get_tag(start) : kasan_random_tag(); start = set_tag(start, tag); /* Unpoison and initialize memory up to size. */ diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 29a751a8a08d..32fbdf759ea2 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -631,7 +631,9 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, !(flags & KASAN_VMALLOC_PROT_NORMAL)) return (void *)start; - start = set_tag(start, kasan_random_tag()); + if (unlikely(!(flags & KASAN_VMALLOC_KEEP_TAG))) + start = set_tag(start, kasan_random_tag()); + kasan_unpoison(start, size, false); return (void *)start; } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 577a1699c553..4f79ec720752 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -596,7 +596,7 @@ static void rcu_guarded_free(struct rcu_head *h) static unsigned long kfence_init_pool(void) { unsigned long addr, start_pfn; - int i; + int i, rand; if (!arch_kfence_init_pool()) return (unsigned long)__kfence_pool; @@ -647,13 +647,27 @@ static unsigned long kfence_init_pool(void) INIT_LIST_HEAD(&meta->list); raw_spin_lock_init(&meta->lock); meta->state = KFENCE_OBJECT_UNUSED; - meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */ - list_add_tail(&meta->list, &kfence_freelist); + /* Use addr to randomize the freelist. */ + meta->addr = i; /* Protect the right redzone. */ - if (unlikely(!kfence_protect(addr + PAGE_SIZE))) + if (unlikely(!kfence_protect(addr + 2 * i * PAGE_SIZE + PAGE_SIZE))) goto reset_slab; + } + + for (i = CONFIG_KFENCE_NUM_OBJECTS; i > 0; i--) { + rand = get_random_u32_below(i); + swap(kfence_metadata_init[i - 1].addr, kfence_metadata_init[rand].addr); + } + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + struct kfence_metadata *meta_1 = &kfence_metadata_init[i]; + struct kfence_metadata *meta_2 = &kfence_metadata_init[meta_1->addr]; + + list_add_tail(&meta_2->list, &kfence_freelist); + } + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + kfence_metadata_init[i].addr = addr; addr += 2 * PAGE_SIZE; } @@ -666,6 +680,7 @@ static unsigned long kfence_init_pool(void) return 0; reset_slab: + addr += 2 * i * PAGE_SIZE; for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { struct page *page; @@ -823,6 +838,9 @@ static struct notifier_block kfence_check_canary_notifier = { static struct delayed_work kfence_timer; #ifdef CONFIG_KFENCE_STATIC_KEYS +/* Wait queue to wake up allocation-gate timer task. */ +static DECLARE_WAIT_QUEUE_HEAD(allocation_wait); + static int kfence_reboot_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -832,7 +850,12 @@ static int kfence_reboot_callback(struct notifier_block *nb, */ WRITE_ONCE(kfence_enabled, false); /* Cancel any pending timer work */ - cancel_delayed_work_sync(&kfence_timer); + cancel_delayed_work(&kfence_timer); + /* + * Wake up any blocked toggle_allocation_gate() so it can complete + * early while the system is still able to handle IPIs. + */ + wake_up(&allocation_wait); return NOTIFY_OK; } @@ -842,9 +865,6 @@ static struct notifier_block kfence_reboot_notifier = { .priority = INT_MAX, /* Run early to stop timers ASAP */ }; -/* Wait queue to wake up allocation-gate timer task. */ -static DECLARE_WAIT_QUEUE_HEAD(allocation_wait); - static void wake_up_kfence_timer(struct irq_work *work) { wake_up(&allocation_wait); @@ -873,7 +893,9 @@ static void toggle_allocation_gate(struct work_struct *work) /* Enable static key, and await allocation to happen. */ static_branch_enable(&kfence_allocation_key); - wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate) > 0); + wait_event_idle(allocation_wait, + atomic_read(&kfence_allocation_gate) > 0 || + !READ_ONCE(kfence_enabled)); /* Disable static key and reset timer. */ static_branch_disable(&kfence_allocation_key); diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index e7f554a31bb4..9e1c5f2b7a41 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -207,7 +207,7 @@ void kmsan_free_page(struct page *page, unsigned int order) if (!kmsan_enabled || kmsan_in_runtime()) return; kmsan_enter_runtime(); - kmsan_internal_poison_memory(page_address(page), page_size(page), + kmsan_internal_poison_memory(page_address(page), PAGE_SIZE << order, GFP_KERNEL & ~(__GFP_RECLAIM), KMSAN_POISON_CHECK | KMSAN_POISON_FREE); kmsan_leave_runtime(); @@ -650,7 +650,7 @@ static int break_ksm_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned long en } } out_unlock: - pte_unmap_unlock(ptep, ptl); + pte_unmap_unlock(start_ptep, ptl); return found; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index be810c1fbfc3..86f43b7e5f71 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5638,6 +5638,6 @@ void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg) memcg = root_mem_cgroup; pr_warn("Memory cgroup min protection %lukB -- low protection %lukB", - K(atomic_long_read(&memcg->memory.children_min_usage)*PAGE_SIZE), - K(atomic_long_read(&memcg->memory.children_low_usage)*PAGE_SIZE)); + K(atomic_long_read(&memcg->memory.children_min_usage)), + K(atomic_long_read(&memcg->memory.children_low_usage))); } diff --git a/mm/memfd.c b/mm/memfd.c index ab5312aff14b..f032c6052926 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -456,7 +456,7 @@ err_name: return ERR_PTR(error); } -static struct file *alloc_file(const char *name, unsigned int flags) +struct file *memfd_alloc_file(const char *name, unsigned int flags) { unsigned int *file_seals; struct file *file; @@ -520,5 +520,5 @@ SYSCALL_DEFINE2(memfd_create, return PTR_ERR(name); fd_flags = (flags & MFD_CLOEXEC) ? O_CLOEXEC : 0; - return FD_ADD(fd_flags, alloc_file(name, flags)); + return FD_ADD(fd_flags, memfd_alloc_file(name, flags)); } diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c index 4f6ba63b4310..a34fccc23b6a 100644 --- a/mm/memfd_luo.c +++ b/mm/memfd_luo.c @@ -78,6 +78,7 @@ #include <linux/liveupdate.h> #include <linux/shmem_fs.h> #include <linux/vmalloc.h> +#include <linux/memfd.h> #include "internal.h" static int memfd_luo_preserve_folios(struct file *file, @@ -443,11 +444,11 @@ static int memfd_luo_retrieve(struct liveupdate_file_op_args *args) if (!ser) return -EINVAL; - file = shmem_file_setup("", 0, VM_NORESERVE); - + file = memfd_alloc_file("", 0); if (IS_ERR(file)) { pr_err("failed to setup file: %pe\n", file); - return PTR_ERR(file); + err = PTR_ERR(file); + goto free_ser; } vfs_setpos(file, ser->pos, MAX_LFS_FILESIZE); @@ -473,7 +474,8 @@ static int memfd_luo_retrieve(struct liveupdate_file_op_args *args) put_file: fput(file); - +free_ser: + kho_restore_free(ser); return err; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fbc5a01260c8..cf0d526e6d41 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -692,6 +692,8 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, unsigned long poisoned_pfn, struct to_kill *tk) { unsigned long pfn = 0; + unsigned long hwpoison_vaddr; + unsigned long mask; if (pte_present(pte)) { pfn = pte_pfn(pte); @@ -702,10 +704,12 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, pfn = softleaf_to_pfn(entry); } - if (!pfn || pfn != poisoned_pfn) + mask = ~((1UL << (shift - PAGE_SHIFT)) - 1); + if (!pfn || pfn != (poisoned_pfn & mask)) return 0; - set_to_kill(tk, addr, shift); + hwpoison_vaddr = addr + ((poisoned_pfn - pfn) << PAGE_SHIFT); + set_to_kill(tk, hwpoison_vaddr, shift); return 1; } @@ -1883,12 +1887,22 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag) return count; } -static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) +#define MF_HUGETLB_FREED 0 /* freed hugepage */ +#define MF_HUGETLB_IN_USED 1 /* in-use hugepage */ +#define MF_HUGETLB_NON_HUGEPAGE 2 /* not a hugepage */ +#define MF_HUGETLB_FOLIO_PRE_POISONED 3 /* folio already poisoned */ +#define MF_HUGETLB_PAGE_PRE_POISONED 4 /* exact page already poisoned */ +#define MF_HUGETLB_RETRY 5 /* hugepage is busy, retry */ +/* + * Set hugetlb folio as hwpoisoned, update folio private raw hwpoison list + * to keep track of the poisoned pages. + */ +static int hugetlb_update_hwpoison(struct folio *folio, struct page *page) { struct llist_head *head; struct raw_hwp_page *raw_hwp; struct raw_hwp_page *p; - int ret = folio_test_set_hwpoison(folio) ? -EHWPOISON : 0; + int ret = folio_test_set_hwpoison(folio) ? MF_HUGETLB_FOLIO_PRE_POISONED : 0; /* * Once the hwpoison hugepage has lost reliable raw error info, @@ -1896,20 +1910,17 @@ static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) * so skip to add additional raw error info. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) - return -EHWPOISON; + return MF_HUGETLB_FOLIO_PRE_POISONED; head = raw_hwp_list_head(folio); llist_for_each_entry(p, head->first, node) { if (p->page == page) - return -EHWPOISON; + return MF_HUGETLB_PAGE_PRE_POISONED; } raw_hwp = kmalloc(sizeof(struct raw_hwp_page), GFP_ATOMIC); if (raw_hwp) { raw_hwp->page = page; llist_add(&raw_hwp->node, head); - /* the first error event will be counted in action_result(). */ - if (ret) - num_poisoned_pages_inc(page_to_pfn(page)); } else { /* * Failed to save raw error info. We no longer trace all @@ -1957,42 +1968,39 @@ void folio_clear_hugetlb_hwpoison(struct folio *folio) /* * 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, bool *migratable_cleared) { struct page *page = pfn_to_page(pfn); struct folio *folio = page_folio(page); - int ret = 2; /* fallback to normal page handling */ bool count_increased = false; + int ret, rc; - if (!folio_test_hugetlb(folio)) + if (!folio_test_hugetlb(folio)) { + ret = MF_HUGETLB_NON_HUGEPAGE; goto out; - - if (flags & MF_COUNT_INCREASED) { - ret = 1; + } else if (flags & MF_COUNT_INCREASED) { + ret = MF_HUGETLB_IN_USED; count_increased = true; } else if (folio_test_hugetlb_freed(folio)) { - ret = 0; + ret = MF_HUGETLB_FREED; } else if (folio_test_hugetlb_migratable(folio)) { - ret = folio_try_get(folio); - if (ret) + if (folio_try_get(folio)) { + ret = MF_HUGETLB_IN_USED; count_increased = true; + } else { + ret = MF_HUGETLB_FREED; + } } else { - ret = -EBUSY; + ret = MF_HUGETLB_RETRY; if (!(flags & MF_NO_RETRY)) goto out; } - if (folio_set_hugetlb_hwpoison(folio, page)) { - ret = -EHWPOISON; + rc = hugetlb_update_hwpoison(folio, page); + if (rc >= MF_HUGETLB_FOLIO_PRE_POISONED) { + ret = rc; goto out; } @@ -2017,10 +2025,16 @@ out: * 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. + * Returns: + * 0 - not hugetlb, or recovered + * -EBUSY - not recovered + * -EOPNOTSUPP - hwpoison_filter'ed + * -EHWPOISON - folio or exact page already poisoned + * -EFAULT - kill_accessing_process finds current->mm null */ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) { - int res; + int res, rv; struct page *p = pfn_to_page(pfn); struct folio *folio; unsigned long page_flags; @@ -2029,22 +2043,29 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb *hugetlb = 1; retry: res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared); - if (res == 2) { /* fallback to normal page handling */ + switch (res) { + case MF_HUGETLB_NON_HUGEPAGE: /* fallback to normal page handling */ *hugetlb = 0; return 0; - } else if (res == -EHWPOISON) { - if (flags & MF_ACTION_REQUIRED) { - folio = page_folio(p); - res = kill_accessing_process(current, folio_pfn(folio), flags); - } - action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); - return res; - } else if (res == -EBUSY) { + case MF_HUGETLB_RETRY: if (!(flags & MF_NO_RETRY)) { flags |= MF_NO_RETRY; goto retry; } return action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED); + case MF_HUGETLB_FOLIO_PRE_POISONED: + case MF_HUGETLB_PAGE_PRE_POISONED: + rv = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + rv = kill_accessing_process(current, pfn, flags); + if (res == MF_HUGETLB_PAGE_PRE_POISONED) + action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); + else + action_result(pfn, MF_MSG_HUGE, MF_FAILED); + return rv; + default: + WARN_ON((res != MF_HUGETLB_FREED) && (res != MF_HUGETLB_IN_USED)); + break; } folio = page_folio(p); @@ -2055,7 +2076,7 @@ retry: if (migratable_cleared) folio_set_hugetlb_migratable(folio); folio_unlock(folio); - if (res == 1) + if (res == MF_HUGETLB_IN_USED) folio_put(folio); return -EOPNOTSUPP; } @@ -2064,7 +2085,7 @@ retry: * Handling free hugepage. The possible race with hugepage allocation * or demotion can be prevented by PageHWPoison flag. */ - if (res == 0) { + if (res == MF_HUGETLB_FREED) { folio_unlock(folio); if (__page_handle_poison(p) > 0) { page_ref_inc(p); @@ -2161,6 +2182,9 @@ int register_pfn_address_space(struct pfn_address_space *pfn_space) { guard(mutex)(&pfn_space_lock); + if (!pfn_space->pfn_to_vma_pgoff) + return -EINVAL; + if (interval_tree_iter_first(&pfn_space_itree, pfn_space->node.start, pfn_space->node.last)) @@ -2183,10 +2207,10 @@ void unregister_pfn_address_space(struct pfn_address_space *pfn_space) } EXPORT_SYMBOL_GPL(unregister_pfn_address_space); -static void add_to_kill_pfn(struct task_struct *tsk, - struct vm_area_struct *vma, - struct list_head *to_kill, - unsigned long pfn) +static void add_to_kill_pgoff(struct task_struct *tsk, + struct vm_area_struct *vma, + struct list_head *to_kill, + pgoff_t pgoff) { struct to_kill *tk; @@ -2197,12 +2221,12 @@ static void add_to_kill_pfn(struct task_struct *tsk, } /* Check for pgoff not backed by struct page */ - tk->addr = vma_address(vma, pfn, 1); + tk->addr = vma_address(vma, pgoff, 1); tk->size_shift = PAGE_SHIFT; if (tk->addr == -EFAULT) pr_info("Unable to find address %lx in %s\n", - pfn, tsk->comm); + pgoff, tsk->comm); get_task_struct(tsk); tk->tsk = tsk; @@ -2212,11 +2236,12 @@ static void add_to_kill_pfn(struct task_struct *tsk, /* * Collect processes when the error hit a PFN not backed by struct page. */ -static void collect_procs_pfn(struct address_space *mapping, +static void collect_procs_pfn(struct pfn_address_space *pfn_space, unsigned long pfn, struct list_head *to_kill) { struct vm_area_struct *vma; struct task_struct *tsk; + struct address_space *mapping = pfn_space->mapping; i_mmap_lock_read(mapping); rcu_read_lock(); @@ -2226,9 +2251,12 @@ static void collect_procs_pfn(struct address_space *mapping, t = task_early_kill(tsk, true); if (!t) continue; - vma_interval_tree_foreach(vma, &mapping->i_mmap, pfn, pfn) { - if (vma->vm_mm == t->mm) - add_to_kill_pfn(t, vma, to_kill, pfn); + vma_interval_tree_foreach(vma, &mapping->i_mmap, 0, ULONG_MAX) { + pgoff_t pgoff; + + if (vma->vm_mm == t->mm && + !pfn_space->pfn_to_vma_pgoff(vma, pfn, &pgoff)) + add_to_kill_pgoff(t, vma, to_kill, pgoff); } } rcu_read_unlock(); @@ -2264,7 +2292,7 @@ static int memory_failure_pfn(unsigned long pfn, int flags) struct pfn_address_space *pfn_space = container_of(node, struct pfn_address_space, node); - collect_procs_pfn(pfn_space->mapping, pfn, &tokill); + collect_procs_pfn(pfn_space, pfn, &tokill); mf_handled = true; } diff --git a/mm/memory.c b/mm/memory.c index 2a55edc48a65..da360a6eb8a4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1465,7 +1465,11 @@ copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, static bool vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { - if (src_vma->vm_flags & VM_COPY_ON_FORK) + /* + * We check against dst_vma as while sane VMA flags will have been + * copied, VM_UFFD_WP may be set only on dst_vma. + */ + if (dst_vma->vm_flags & VM_COPY_ON_FORK) return true; /* * The presence of an anon_vma indicates an anonymous VMA has page @@ -1963,10 +1967,9 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb, do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud)) { - if (next - addr != HPAGE_PUD_SIZE) { - mmap_assert_locked(tlb->mm); + if (next - addr != HPAGE_PUD_SIZE) split_huge_pud(vma, pud, addr); - } else if (zap_huge_pud(tlb, vma, pud, addr)) + else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } diff --git a/mm/memremap.c b/mm/memremap.c index 4c2e0d68eb27..ac7be07e3361 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -427,8 +427,6 @@ void free_zone_device_folio(struct folio *folio) if (folio_test_anon(folio)) { for (i = 0; i < nr; i++) __ClearPageAnonExclusive(folio_page(folio, i)); - } else { - VM_WARN_ON_ONCE(folio_test_large(folio)); } /* @@ -479,10 +477,43 @@ void free_zone_device_folio(struct folio *folio) } } -void zone_device_page_init(struct page *page, unsigned int order) +void zone_device_page_init(struct page *page, struct dev_pagemap *pgmap, + unsigned int order) { + struct page *new_page = page; + unsigned int i; + VM_WARN_ON_ONCE(order > MAX_ORDER_NR_PAGES); + for (i = 0; i < (1UL << order); ++i, ++new_page) { + struct folio *new_folio = (struct folio *)new_page; + + /* + * new_page could have been part of previous higher order folio + * which encodes the order, in page + 1, in the flags bits. We + * blindly clear bits which could have set my order field here, + * including page head. + */ + new_page->flags.f &= ~0xffUL; /* Clear possible order, page head */ + +#ifdef NR_PAGES_IN_LARGE_FOLIO + /* + * This pointer math looks odd, but new_page could have been + * part of a previous higher order folio, which sets _nr_pages + * in page + 1 (new_page). Therefore, we use pointer casting to + * correctly locate the _nr_pages bits within new_page which + * could have modified by previous higher order folio. + */ + ((struct folio *)(new_page - 1))->_nr_pages = 0; +#endif + + new_folio->mapping = NULL; + new_folio->pgmap = pgmap; /* Also clear compound head */ + new_folio->share = 0; /* fsdax only, unused for device private */ + VM_WARN_ON_FOLIO(folio_ref_count(new_folio), new_folio); + VM_WARN_ON_FOLIO(!folio_is_zone_device(new_folio), new_folio); + } + /* * Drivers shouldn't be allocating pages after calling * memunmap_pages(). diff --git a/mm/migrate.c b/mm/migrate.c index 5169f9717f60..4688b9e38cd2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1458,6 +1458,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; + enum ttu_flags ttu = 0; if (folio_ref_count(src) == 1) { /* page was freed from under us. So we are done. */ @@ -1498,8 +1499,6 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, goto put_anon; if (folio_mapped(src)) { - enum ttu_flags ttu = 0; - if (!folio_test_anon(src)) { /* * In shared mappings, try_to_unmap could potentially @@ -1516,16 +1515,17 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, try_to_migrate(src, ttu); page_was_mapped = 1; - - if (ttu & TTU_RMAP_LOCKED) - i_mmap_unlock_write(mapping); } if (!folio_mapped(src)) rc = move_to_new_folio(dst, src, mode); if (page_was_mapped) - remove_migration_ptes(src, !rc ? dst : src, 0); + remove_migration_ptes(src, !rc ? dst : src, + ttu ? RMP_LOCKED : 0); + + if (ttu & TTU_RMAP_LOCKED) + i_mmap_unlock_write(mapping); unlock_put_anon: folio_unlock(dst); diff --git a/mm/mm_init.c b/mm/mm_init.c index fc2a6f1e518f..2a809cd8e7fa 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2059,7 +2059,7 @@ static unsigned long __init deferred_init_pages(struct zone *zone, */ static unsigned long __init deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, - struct zone *zone) + struct zone *zone, bool can_resched) { int nid = zone_to_nid(zone); unsigned long nr_pages = 0; @@ -2085,10 +2085,10 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, spfn = chunk_end; - if (irqs_disabled()) - touch_nmi_watchdog(); - else + if (can_resched) cond_resched(); + else + touch_nmi_watchdog(); } } @@ -2101,7 +2101,7 @@ deferred_init_memmap_job(unsigned long start_pfn, unsigned long end_pfn, { struct zone *zone = arg; - deferred_init_memmap_chunk(start_pfn, end_pfn, zone); + deferred_init_memmap_chunk(start_pfn, end_pfn, zone, true); } static unsigned int __init @@ -2216,7 +2216,7 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order) for (spfn = first_deferred_pfn, epfn = SECTION_ALIGN_UP(spfn + 1); nr_pages < nr_pages_needed && spfn < zone_end_pfn(zone); spfn = epfn, epfn += PAGES_PER_SECTION) { - nr_pages += deferred_init_memmap_chunk(spfn, epfn, zone); + nr_pages += deferred_init_memmap_chunk(spfn, epfn, zone, false); } /* diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 247e3f9db6c7..7468ec388455 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -10,6 +10,7 @@ #include <linux/swap.h> #include <linux/rmap.h> #include <linux/pgalloc.h> +#include <linux/hugetlb.h> #include <asm/tlb.h> @@ -426,6 +427,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, #endif tlb->vma_pfn = 0; + tlb->fully_unshared_tables = 0; __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } @@ -460,6 +462,31 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) } /** + * tlb_gather_mmu_vma - initialize an mmu_gather structure for operating on a + * single VMA + * @tlb: the mmu_gather structure to initialize + * @vma: the vm_area_struct + * + * Called to initialize an (on-stack) mmu_gather structure for operating on + * a single VMA. In contrast to tlb_gather_mmu(), calling this function will + * not require another call to tlb_start_vma(). In contrast to tlb_start_vma(), + * this function will *not* call flush_cache_range(). + * + * For hugetlb VMAs, this function will also initialize the mmu_gather + * page_size accordingly, not requiring a separate call to + * tlb_change_page_size(). + * + */ +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + tlb_gather_mmu(tlb, vma->vm_mm); + tlb_update_vma_flags(tlb, vma); + if (is_vm_hugetlb_page(vma)) + /* All entries have the same size. */ + tlb_change_page_size(tlb, huge_page_size(hstate_vma(vma))); +} + +/** * tlb_finish_mmu - finish an mmu_gather structure * @tlb: the mmu_gather structure to finish * @@ -469,6 +496,12 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) void tlb_finish_mmu(struct mmu_gather *tlb) { /* + * We expect an earlier huge_pmd_unshare_flush() call to sort this out, + * due to complicated locking requirements with page table unsharing. + */ + VM_WARN_ON_ONCE(tlb->fully_unshared_tables); + + /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB * flush by batching, one thread may end up seeing inconsistent PTEs diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index 5b009a9cd8b4..8f5735fda0a2 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -7,6 +7,8 @@ #include <linux/numa.h> #include <linux/numa_memblks.h> +#include <asm/numa.h> + int numa_distance_cnt; static u8 *numa_distance; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 822e05f1a964..cbf758e27aa2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -167,6 +167,33 @@ static inline void __pcp_trylock_noop(unsigned long *flags) { } pcp_trylock_finish(UP_flags); \ }) +/* + * With the UP spinlock implementation, when we spin_lock(&pcp->lock) (for i.e. + * a potentially remote cpu drain) and get interrupted by an operation that + * attempts pcp_spin_trylock(), we can't rely on the trylock failure due to UP + * spinlock assumptions making the trylock a no-op. So we have to turn that + * spin_lock() to a spin_lock_irqsave(). This works because on UP there are no + * remote cpu's so we can only be locking the only existing local one. + */ +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +static inline void __flags_noop(unsigned long *flags) { } +#define pcp_spin_lock_maybe_irqsave(ptr, flags) \ +({ \ + __flags_noop(&(flags)); \ + spin_lock(&(ptr)->lock); \ +}) +#define pcp_spin_unlock_maybe_irqrestore(ptr, flags) \ +({ \ + spin_unlock(&(ptr)->lock); \ + __flags_noop(&(flags)); \ +}) +#else +#define pcp_spin_lock_maybe_irqsave(ptr, flags) \ + spin_lock_irqsave(&(ptr)->lock, flags) +#define pcp_spin_unlock_maybe_irqrestore(ptr, flags) \ + spin_unlock_irqrestore(&(ptr)->lock, flags) +#endif + #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -914,6 +941,17 @@ buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, NULL) != NULL; } +static void change_pageblock_range(struct page *pageblock_page, + int start_order, int migratetype) +{ + int nr_pageblocks = 1 << (start_order - pageblock_order); + + while (nr_pageblocks--) { + set_pageblock_migratetype(pageblock_page, migratetype); + pageblock_page += pageblock_nr_pages; + } +} + /* * Freeing function for a buddy system allocator. * @@ -1000,7 +1038,7 @@ static inline void __free_one_page(struct page *page, * expand() down the line puts the sub-blocks * on the right freelists. */ - set_pageblock_migratetype(buddy, migratetype); + change_pageblock_range(buddy, order, migratetype); } combined_pfn = buddy_pfn & pfn; @@ -2147,17 +2185,6 @@ bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *pag #endif /* CONFIG_MEMORY_ISOLATION */ -static void change_pageblock_range(struct page *pageblock_page, - int start_order, int migratetype) -{ - int nr_pageblocks = 1 << (start_order - pageblock_order); - - while (nr_pageblocks--) { - set_pageblock_migratetype(pageblock_page, migratetype); - pageblock_page += pageblock_nr_pages; - } -} - static inline bool boost_watermark(struct zone *zone) { unsigned long max_boost; @@ -2556,6 +2583,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) { int high_min, to_drain, to_drain_batched, batch; + unsigned long UP_flags; bool todo = false; high_min = READ_ONCE(pcp->high_min); @@ -2575,9 +2603,9 @@ bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) to_drain = pcp->count - pcp->high; while (to_drain > 0) { to_drain_batched = min(to_drain, batch); - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); free_pcppages_bulk(zone, to_drain_batched, pcp, 0); - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); todo = true; to_drain -= to_drain_batched; @@ -2594,14 +2622,15 @@ bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) */ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { + unsigned long UP_flags; int to_drain, batch; batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) { - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); free_pcppages_bulk(zone, to_drain, pcp, 0); - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } } #endif @@ -2612,10 +2641,11 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) static void drain_pages_zone(unsigned int cpu, struct zone *zone) { struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + unsigned long UP_flags; int count; do { - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); count = pcp->count; if (count) { int to_drain = min(count, @@ -2624,7 +2654,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) free_pcppages_bulk(zone, to_drain, pcp, 0); count -= to_drain; } - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } while (count); } @@ -5924,7 +5954,7 @@ static int zone_batchsize(struct zone *zone) * recycled, this leads to the once large chunks of space being * fragmented and becoming unavailable for high-order allocations. */ - return 0; + return 1; #endif } @@ -6109,6 +6139,7 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) { struct per_cpu_pages *pcp; struct cpu_cacheinfo *cci; + unsigned long UP_flags; pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); cci = get_cpu_cacheinfo(cpu); @@ -6119,12 +6150,12 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) * This can reduce zone lock contention without hurting * cache-hot pages sharing. */ - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch) pcp->flags |= PCPF_FREE_HIGH_BATCH; else pcp->flags &= ~PCPF_FREE_HIGH_BATCH; - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } void setup_pcp_cacheinfo(unsigned int cpu) @@ -6667,11 +6698,19 @@ static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table * int old_percpu_pagelist_high_fraction; int ret; + /* + * Avoid using pcp_batch_high_lock for reads as the value is read + * atomically and a race with offlining is harmless. + */ + + if (!write) + return proc_dointvec_minmax(table, write, buffer, length, ppos); + mutex_lock(&pcp_batch_high_lock); old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || ret < 0) + if (ret < 0) goto out; /* Sanity checking to avoid pcp imbalance */ @@ -7418,20 +7457,16 @@ bool put_page_back_buddy(struct page *page) } #endif -#ifdef CONFIG_ZONE_DMA -bool has_managed_dma(void) +bool has_managed_zone(enum zone_type zone) { struct pglist_data *pgdat; for_each_online_pgdat(pgdat) { - struct zone *zone = &pgdat->node_zones[ZONE_DMA]; - - if (managed_zone(zone)) + if (managed_zone(&pgdat->node_zones[zone])) return true; } return false; } -#endif /* CONFIG_ZONE_DMA */ #ifdef CONFIG_UNACCEPTED_MEMORY diff --git a/mm/page_owner.c b/mm/page_owner.c index a70245684206..b3260f0c17ba 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -952,7 +952,7 @@ static const struct file_operations page_owner_stack_fops = { .open = page_owner_stack_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; static int page_owner_threshold_get(void *data, u64 *val) diff --git a/mm/rmap.c b/mm/rmap.c index f955f02d570e..7b9879ef442d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -76,7 +76,7 @@ #include <linux/mm_inline.h> #include <linux/oom.h> -#include <asm/tlbflush.h> +#include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> @@ -2008,26 +2008,25 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { + + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* - * The ref count of the PMD page was - * dropped which is part of the way map - * counting is done for shared PMDs. - * Return 'true' here. When there is - * no other sharing, huge_pmd_unshare - * returns false and we will unmap the - * actual page and drop map count - * to zero. + * The PMD table was unmapped, + * consequently unmapping the folio. */ goto walk_done; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) @@ -2404,31 +2403,29 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, * fail if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { - hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { + hugetlb_vma_unlock_write(vma); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* - * The ref count of the PMD page was - * dropped which is part of the way map - * counting is done for shared PMDs. - * Return 'true' here. When there is - * no other sharing, huge_pmd_unshare - * returns false and we will unmap the - * actual page and drop map count - * to zero. + * The PMD table was unmapped, + * consequently unmapping the folio. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); diff --git a/mm/shmem.c b/mm/shmem.c index ec6c01378e9d..6c3485d24d66 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -962,17 +962,29 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) * being freed). */ static long shmem_free_swap(struct address_space *mapping, - pgoff_t index, void *radswap) + pgoff_t index, pgoff_t end, void *radswap) { - int order = xa_get_order(&mapping->i_pages, index); - void *old; + XA_STATE(xas, &mapping->i_pages, index); + unsigned int nr_pages = 0; + pgoff_t base; + void *entry; - old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); - if (old != radswap) - return 0; - free_swap_and_cache_nr(radix_to_swp_entry(radswap), 1 << order); + xas_lock_irq(&xas); + entry = xas_load(&xas); + if (entry == radswap) { + nr_pages = 1 << xas_get_order(&xas); + base = round_down(xas.xa_index, nr_pages); + if (base < index || base + nr_pages - 1 > end) + nr_pages = 0; + else + xas_store(&xas, NULL); + } + xas_unlock_irq(&xas); + + if (nr_pages) + free_swap_and_cache_nr(radix_to_swp_entry(radswap), nr_pages); - return 1 << order; + return nr_pages; } /* @@ -1124,8 +1136,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, uoff_t lend, if (xa_is_value(folio)) { if (unfalloc) continue; - nr_swaps_freed += shmem_free_swap(mapping, - indices[i], folio); + nr_swaps_freed += shmem_free_swap(mapping, indices[i], + end - 1, folio); continue; } @@ -1191,12 +1203,23 @@ whole_folios: folio = fbatch.folios[i]; if (xa_is_value(folio)) { + int order; long swaps_freed; if (unfalloc) continue; - swaps_freed = shmem_free_swap(mapping, indices[i], folio); + swaps_freed = shmem_free_swap(mapping, indices[i], + end - 1, folio); if (!swaps_freed) { + /* + * If found a large swap entry cross the end border, + * skip it as the truncate_inode_partial_folio above + * should have at least zerod its content once. + */ + order = shmem_confirm_swap(mapping, indices[i], + radix_to_swp_entry(folio)); + if (order > 0 && indices[i] + (1 << order) > end) + continue; /* Swap was replaced by page: retry */ index = indices[i]; break; diff --git a/mm/slub.c b/mm/slub.c index 861592ac5425..f77b7407c51b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5694,8 +5694,12 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node) if (unlikely(!size)) return ZERO_SIZE_PTR; - if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) - /* kmalloc_nolock() in PREEMPT_RT is not supported from irq */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible()) + /* + * kmalloc_nolock() in PREEMPT_RT is not supported from + * non-preemptible context because local_lock becomes a + * sleeping lock on RT. + */ return NULL; retry: if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) diff --git a/mm/swap.h b/mm/swap.h index d034c13d8dd2..1bd466da3039 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -198,7 +198,7 @@ int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug); void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug); /* linux/mm/swap_state.c */ -extern struct address_space swap_space __ro_after_init; +extern struct address_space swap_space __read_mostly; static inline struct address_space *swap_address_space(swp_entry_t entry) { return &swap_space; diff --git a/mm/swap_state.c b/mm/swap_state.c index 5f97c6ae70a2..44d228982521 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -37,8 +37,7 @@ static const struct address_space_operations swap_aops = { #endif }; -/* Set swap_space as read only as swap cache is handled by swap table */ -struct address_space swap_space __ro_after_init = { +struct address_space swap_space __read_mostly = { .a_ops = &swap_aops, }; @@ -37,6 +37,8 @@ struct mmap_state { bool check_ksm_early :1; /* If we map new, hold the file rmap lock on mapping. */ bool hold_file_rmap_lock :1; + /* If .mmap_prepare changed the file, we don't need to pin. */ + bool file_doesnt_need_get :1; }; #define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, vm_flags_, file_) \ @@ -67,18 +69,13 @@ struct mmap_state { .state = VMA_MERGE_START, \ } -/* - * If, at any point, the VMA had unCoW'd mappings from parents, it will maintain - * more than one anon_vma_chain connecting it to more than one anon_vma. A merge - * would mean a wider range of folios sharing the root anon_vma lock, and thus - * potential lock contention, we do not wish to encourage merging such that this - * scales to a problem. - */ -static bool vma_had_uncowed_parents(struct vm_area_struct *vma) +/* Was this VMA ever forked from a parent, i.e. maybe contains CoW mappings? */ +static bool vma_is_fork_child(struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from - * parents. This can improve scalability caused by anon_vma lock. + * parents. This can improve scalability caused by the anon_vma root + * lock. */ return vma && vma->anon_vma && !list_is_singular(&vma->anon_vma_chain); } @@ -115,11 +112,19 @@ static bool is_mergeable_anon_vma(struct vma_merge_struct *vmg, bool merge_next) VM_WARN_ON(src && src_anon != src->anon_vma); /* Case 1 - we will dup_anon_vma() from src into tgt. */ - if (!tgt_anon && src_anon) - return !vma_had_uncowed_parents(src); + if (!tgt_anon && src_anon) { + struct vm_area_struct *copied_from = vmg->copied_from; + + if (vma_is_fork_child(src)) + return false; + if (vma_is_fork_child(copied_from)) + return false; + + return true; + } /* Case 2 - we will simply use tgt's anon_vma. */ if (tgt_anon && !src_anon) - return !vma_had_uncowed_parents(tgt); + return !vma_is_fork_child(tgt); /* Case 3 - the anon_vma's are already shared. */ return src_anon == tgt_anon; } @@ -829,6 +834,8 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( VM_WARN_ON_VMG(middle && !(vma_iter_addr(vmg->vmi) >= middle->vm_start && vma_iter_addr(vmg->vmi) < middle->vm_end), vmg); + /* An existing merge can never be used by the mremap() logic. */ + VM_WARN_ON_VMG(vmg->copied_from, vmg); vmg->state = VMA_MERGE_NOMERGE; @@ -1099,6 +1106,33 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) } /* + * vma_merge_copied_range - Attempt to merge a VMA that is being copied by + * mremap() + * + * @vmg: Describes the VMA we are adding, in the copied-to range @vmg->start to + * @vmg->end (exclusive), which we try to merge with any adjacent VMAs if + * possible. + * + * vmg->prev, next, start, end, pgoff should all be relative to the COPIED TO + * range, i.e. the target range for the VMA. + * + * Returns: In instances where no merge was possible, NULL. Otherwise, a pointer + * to the VMA we expanded. + * + * ASSUMPTIONS: Same as vma_merge_new_range(), except vmg->middle must contain + * the copied-from VMA. + */ +static struct vm_area_struct *vma_merge_copied_range(struct vma_merge_struct *vmg) +{ + /* We must have a copied-from VMA. */ + VM_WARN_ON_VMG(!vmg->middle, vmg); + + vmg->copied_from = vmg->middle; + vmg->middle = NULL; + return vma_merge_new_range(vmg); +} + +/* * vma_expand - Expand an existing VMA * * @vmg: Describes a VMA expansion operation. @@ -1117,46 +1151,52 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) int vma_expand(struct vma_merge_struct *vmg) { struct vm_area_struct *anon_dup = NULL; - bool remove_next = false; struct vm_area_struct *target = vmg->target; struct vm_area_struct *next = vmg->next; + bool remove_next = false; vm_flags_t sticky_flags; - - sticky_flags = vmg->vm_flags & VM_STICKY; - sticky_flags |= target->vm_flags & VM_STICKY; - - VM_WARN_ON_VMG(!target, vmg); + int ret = 0; mmap_assert_write_locked(vmg->mm); - vma_start_write(target); - if (next && (target != next) && (vmg->end == next->vm_end)) { - int ret; - sticky_flags |= next->vm_flags & VM_STICKY; + if (next && target != next && vmg->end == next->vm_end) remove_next = true; - /* This should already have been checked by this point. */ - VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg); - vma_start_write(next); - /* - * In this case we don't report OOM, so vmg->give_up_on_mm is - * safe. - */ - ret = dup_anon_vma(target, next, &anon_dup); - if (ret) - return ret; - } + /* We must have a target. */ + VM_WARN_ON_VMG(!target, vmg); + /* This should have already been checked by this point. */ + VM_WARN_ON_VMG(remove_next && !can_merge_remove_vma(next), vmg); /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON_VMG(next && !remove_next && next != target && vmg->end > next->vm_start, vmg); - /* Only handles expanding */ + /* Only handles expanding. */ VM_WARN_ON_VMG(target->vm_start < vmg->start || target->vm_end > vmg->end, vmg); + sticky_flags = vmg->vm_flags & VM_STICKY; + sticky_flags |= target->vm_flags & VM_STICKY; if (remove_next) - vmg->__remove_next = true; + sticky_flags |= next->vm_flags & VM_STICKY; + + /* + * If we are removing the next VMA or copying from a VMA + * (e.g. mremap()'ing), we must propagate anon_vma state. + * + * Note that, by convention, callers ignore OOM for this case, so + * we don't need to account for vmg->give_up_on_mm here. + */ + if (remove_next) + ret = dup_anon_vma(target, next, &anon_dup); + if (!ret && vmg->copied_from) + ret = dup_anon_vma(target, vmg->copied_from, &anon_dup); + if (ret) + return ret; + if (remove_next) { + vma_start_write(next); + vmg->__remove_next = true; + } if (commit_merge(vmg)) goto nomem; @@ -1828,10 +1868,9 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ - vmg.middle = NULL; /* New VMA range. */ vmg.pgoff = pgoff; vmg.next = vma_iter_next_rewind(&vmi, NULL); - new_vma = vma_merge_new_range(&vmg); + new_vma = vma_merge_copied_range(&vmg); if (new_vma) { /* @@ -2413,7 +2452,9 @@ static int __mmap_new_file_vma(struct mmap_state *map, struct vma_iterator *vmi = map->vmi; int error; - vma->vm_file = get_file(map->file); + vma->vm_file = map->file; + if (!map->file_doesnt_need_get) + get_file(map->file); if (!map->file->f_op->mmap) return 0; @@ -2601,7 +2642,10 @@ static int call_mmap_prepare(struct mmap_state *map, /* Update fields permitted to be changed. */ map->pgoff = desc->pgoff; - map->file = desc->vm_file; + if (desc->vm_file != map->file) { + map->file_doesnt_need_get = true; + map->file = desc->vm_file; + } map->vm_flags = desc->vm_flags; map->page_prot = desc->page_prot; /* User-defined fields. */ @@ -106,6 +106,9 @@ struct vma_merge_struct { struct anon_vma_name *anon_name; enum vma_merge_state state; + /* If copied from (i.e. mremap()'d) the VMA from which we are copying. */ + struct vm_area_struct *copied_from; + /* Flags which callers can use to modify merge behaviour: */ /* diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ecbac900c35f..e286c2d2068c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4248,7 +4248,7 @@ void *vzalloc_node_noprof(unsigned long size, int node) EXPORT_SYMBOL(vzalloc_node_noprof); /** - * vrealloc_node_align_noprof - reallocate virtually contiguous memory; contents + * vrealloc_node_align - reallocate virtually contiguous memory; contents * remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate @@ -4322,7 +4322,7 @@ void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align if (want_init_on_free() || want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); vm->requested_size = size; - kasan_poison_vmalloc(p + size, old_size - size); + kasan_vrealloc(p, old_size, size); return (void *)p; } @@ -4330,14 +4330,13 @@ void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align * We already have the bytes available in the allocation; use them. */ if (size <= alloced_size) { - kasan_unpoison_vmalloc(p + old_size, size - old_size, - KASAN_VMALLOC_PROT_NORMAL); /* * No need to zero memory here, as unused memory will have * already been zeroed at initial allocation time or during * realloc shrink time. */ vm->requested_size = size; + kasan_vrealloc(p, old_size, size); return (void *)p; } @@ -5025,9 +5024,7 @@ retry: * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ - for (area = 0; area < nr_vms; area++) - vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr, - vms[area]->size, KASAN_VMALLOC_PROT_NORMAL); + kasan_unpoison_vmap_areas(vms, nr_vms, KASAN_VMALLOC_PROT_NORMAL); kfree(vas); return vms; diff --git a/mm/vmscan.c b/mm/vmscan.c index 670fe9fae5ba..614ccf39fe3f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -7707,6 +7707,17 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) return ret; } +#else + +static unsigned long __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, + unsigned long nr_pages, + struct scan_control *sc) +{ + return 0; +} + +#endif + enum { MEMORY_RECLAIM_SWAPPINESS = 0, MEMORY_RECLAIM_SWAPPINESS_MAX, @@ -7814,8 +7825,6 @@ int user_proactive_reclaim(char *buf, return 0; } -#endif - /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list diff --git a/mm/zswap.c b/mm/zswap.c index 5d0f8b13a958..ac9b7a60736b 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -787,7 +787,7 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) return 0; fail: - if (acomp) + if (!IS_ERR_OR_NULL(acomp)) crypto_free_acomp(acomp); kfree(buffer); return ret; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index a9f5b1a68356..cbc3a75d7326 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4420,6 +4420,7 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev) if (bis_capable(hdev)) { events[1] |= 0x20; /* LE PA Report */ events[1] |= 0x40; /* LE PA Sync Established */ + events[1] |= 0x80; /* LE PA Sync Lost */ events[3] |= 0x04; /* LE Create BIG Complete */ events[3] |= 0x08; /* LE Terminate BIG Complete */ events[3] |= 0x10; /* LE BIG Sync Established */ diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index c11cdef42b6f..0e46f9e08b10 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -849,6 +849,12 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (cis_peripheral_capable(hdev)) settings |= MGMT_SETTING_CIS_PERIPHERAL; + if (bis_capable(hdev)) + settings |= MGMT_SETTING_ISO_BROADCASTER; + + if (sync_recv_capable(hdev)) + settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; + if (ll_privacy_capable(hdev)) settings |= MGMT_SETTING_LL_PRIVACY; @@ -1960,6 +1966,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) } mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err); + mgmt_pending_free(cmd); return; } @@ -1978,6 +1985,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) sock_put(match.sk); hci_update_eir_sync(hdev); + mgmt_pending_free(cmd); } static int set_ssp_sync(struct hci_dev *hdev, void *data) @@ -6432,6 +6440,7 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err) hci_dev_clear_flag(hdev, HCI_ADVERTISING); settings_rsp(cmd, &match); + mgmt_pending_free(cmd); new_settings(hdev, match.sk); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 655efac6f133..26cfcfdc45eb 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1294,8 +1294,6 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, batch_size = NAPI_POLL_WEIGHT; else if (batch_size > TEST_XDP_MAX_BATCH) return -E2BIG; - - headroom += sizeof(struct xdp_page_head); } else if (batch_size) { return -EINVAL; } @@ -1308,16 +1306,26 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, /* There can't be user provided data before the meta data */ if (ctx->data_meta || ctx->data_end > kattr->test.data_size_in || ctx->data > ctx->data_end || - unlikely(xdp_metalen_invalid(ctx->data)) || (do_live && (kattr->test.data_out || kattr->test.ctx_out))) goto free_ctx; - /* Meta data is allocated from the headroom */ - headroom -= ctx->data; meta_sz = ctx->data; + if (xdp_metalen_invalid(meta_sz) || meta_sz > headroom - sizeof(struct xdp_frame)) + goto free_ctx; + + /* Meta data is allocated from the headroom */ + headroom -= meta_sz; linear_sz = ctx->data_end; } + /* The xdp_page_head structure takes up space in each page, limiting the + * size of the packet data; add the extra size to headroom here to make + * sure it's accounted in the length checks below, but not in the + * metadata size check above. + */ + if (do_live) + headroom += sizeof(struct xdp_page_head); + max_linear_sz = PAGE_SIZE - headroom - tailroom; linear_sz = min_t(u32, linear_sz, max_linear_sz); @@ -1355,13 +1363,13 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (sinfo->nr_frags == MAX_SKB_FRAGS) { ret = -ENOMEM; - goto out; + goto out_put_dev; } page = alloc_page(GFP_KERNEL); if (!page) { ret = -ENOMEM; - goto out; + goto out_put_dev; } frag = &sinfo->frags[sinfo->nr_frags++]; @@ -1373,7 +1381,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (copy_from_user(page_address(page), data_in + size, data_len)) { ret = -EFAULT; - goto out; + goto out_put_dev; } sinfo->xdp_frags_size += data_len; size += data_len; @@ -1388,6 +1396,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, ret = bpf_test_run_xdp_live(prog, &xdp, repeat, batch_size, &duration); else ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); +out_put_dev: /* We convert the xdp_buff back to an xdp_md before checking the return * code so the reference count of any held netdevice will be decremented * even if the test run failed. diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 58d22e2b85fc..0501ffcb8a3d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -70,7 +70,7 @@ static inline int has_expired(const struct net_bridge *br, { return !test_bit(BR_FDB_STATIC, &fdb->flags) && !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags) && - time_before_eq(fdb->updated + hold_time(br), jiffies); + time_before_eq(READ_ONCE(fdb->updated) + hold_time(br), jiffies); } static int fdb_to_nud(const struct net_bridge *br, @@ -126,9 +126,9 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags)) goto nla_put_failure; - ci.ndm_used = jiffies_to_clock_t(now - fdb->used); + ci.ndm_used = jiffies_to_clock_t(now - READ_ONCE(fdb->used)); ci.ndm_confirmed = 0; - ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); + ci.ndm_updated = jiffies_to_clock_t(now - READ_ONCE(fdb->updated)); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; @@ -551,7 +551,7 @@ void br_fdb_cleanup(struct work_struct *work) */ rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { - unsigned long this_timer = f->updated + delay; + unsigned long this_timer = READ_ONCE(f->updated) + delay; if (test_bit(BR_FDB_STATIC, &f->flags) || test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags)) { @@ -924,6 +924,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, { struct net_bridge_fdb_entry *f; struct __fdb_entry *fe = buf; + unsigned long delta; int num = 0; memset(buf, 0, maxnum*sizeof(struct __fdb_entry)); @@ -953,8 +954,11 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, fe->port_hi = f->dst->port_no >> 8; fe->is_local = test_bit(BR_FDB_LOCAL, &f->flags); - if (!test_bit(BR_FDB_STATIC, &f->flags)) - fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated); + if (!test_bit(BR_FDB_STATIC, &f->flags)) { + delta = jiffies - READ_ONCE(f->updated); + fe->ageing_timer_value = + jiffies_delta_to_clock_t(delta); + } ++fe; ++num; } @@ -1002,8 +1006,8 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, unsigned long now = jiffies; bool fdb_modified = false; - if (now != fdb->updated) { - fdb->updated = now; + if (now != READ_ONCE(fdb->updated)) { + WRITE_ONCE(fdb->updated, now); fdb_modified = __fdb_mark_active(fdb); } @@ -1242,10 +1246,10 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, if (fdb_handle_notify(fdb, notify)) modified = true; - fdb->used = jiffies; + WRITE_ONCE(fdb->used, jiffies); if (modified) { if (refresh) - fdb->updated = jiffies; + WRITE_ONCE(fdb->updated, jiffies); fdb_notify(br, fdb, RTM_NEWNEIGH, true); } @@ -1556,7 +1560,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, goto err_unlock; } - fdb->updated = jiffies; + WRITE_ONCE(fdb->updated, jiffies); if (READ_ONCE(fdb->dst) != p) { WRITE_ONCE(fdb->dst, p); @@ -1565,7 +1569,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (test_and_set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) { /* Refresh entry */ - fdb->used = jiffies; + WRITE_ONCE(fdb->used, jiffies); } else { modified = true; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 777fa869c1a1..1405f1061a54 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -221,8 +221,8 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (test_bit(BR_FDB_LOCAL, &dst->flags)) return br_pass_frame_up(skb, false); - if (now != dst->used) - dst->used = now; + if (now != READ_ONCE(dst->used)) + WRITE_ONCE(dst->used, now); br_forward(dst->dst, skb, local_rcv, false); } else { if (!mcast_hit) @@ -274,7 +274,7 @@ static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb) int ret; net = dev_net(skb->dev); -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING])) goto frame_finish; #endif diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 7280c4e9305f..b9b2981c4841 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -247,6 +247,7 @@ struct net_bridge_vlan { * struct net_bridge_vlan_group * * @vlan_hash: VLAN entry rhashtable + * @tunnel_hash: Hash table to map from tunnel key ID (e.g. VXLAN VNI) to VLAN * @vlan_list: sorted VLAN entry list * @num_vlans: number of total VLAN entries * @pvid: PVID VLAN id diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index a966a6ec8263..257cae9f1569 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -189,7 +189,6 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tunnel_dst; __be64 tunnel_id; - int err; if (!vlan) return 0; @@ -199,9 +198,13 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, return 0; skb_dst_drop(skb); - err = skb_vlan_pop(skb); - if (err) - return err; + /* For 802.1ad (QinQ), skb_vlan_pop() incorrectly moves the C-VLAN + * from payload to hwaccel after clearing S-VLAN. We only need to + * clear the hwaccel S-VLAN; the C-VLAN must stay in payload for + * correct VXLAN encapsulation. This is also correct for 802.1Q + * where no C-VLAN exists in payload. + */ + __vlan_hwaccel_clear_tag(skb); if (BR_INPUT_SKB_CB(skb)->backup_nhid) { __set_bit(IP_TUNNEL_KEY_BIT, flags); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 5697e3949a36..a04fc1757528 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1299,7 +1299,7 @@ int ebt_register_template(const struct ebt_table *t, int (*table_init)(struct ne list_for_each_entry(tmpl, &template_tables, list) { if (WARN_ON_ONCE(strcmp(t->name, tmpl->name) == 0)) { mutex_unlock(&ebt_mutex); - return -EEXIST; + return -EBUSY; } } diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 613a911dda10..8656ab388c83 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1695,8 +1695,16 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); - if (session->transmission) + if (session->transmission) { j1939_session_deactivate_activate_next(session); + } else if (session->state == J1939_SESSION_WAITING_ABORT) { + /* Force deactivation for the receiver. + * If we rely on the timer starting in j1939_session_cancel, + * a second RTS call here will cancel that timer and fail + * to restart it because the state is already WAITING_ABORT. + */ + j1939_session_deactivate_activate_next(session); + } return -EBUSY; } diff --git a/net/can/raw.c b/net/can/raw.c index be1ef7cf4204..12293363413c 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -49,8 +49,8 @@ #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> +#include <linux/can/can-ml.h> #include <linux/can/core.h> -#include <linux/can/dev.h> /* for can_is_canxl_dev_mtu() */ #include <linux/can/skb.h> #include <linux/can/raw.h> #include <net/sock.h> @@ -892,58 +892,21 @@ static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb) } } -static inline bool raw_dev_cc_enabled(struct net_device *dev, - struct can_priv *priv) -{ - /* The CANXL-only mode disables error-signalling on the CAN bus - * which is needed to send CAN CC/FD frames - */ - if (priv) - return !can_dev_in_xl_only_mode(priv); - - /* virtual CAN interfaces always support CAN CC */ - return true; -} - -static inline bool raw_dev_fd_enabled(struct net_device *dev, - struct can_priv *priv) -{ - /* check FD ctrlmode on real CAN interfaces */ - if (priv) - return (priv->ctrlmode & CAN_CTRLMODE_FD); - - /* check MTU for virtual CAN FD interfaces */ - return (READ_ONCE(dev->mtu) >= CANFD_MTU); -} - -static inline bool raw_dev_xl_enabled(struct net_device *dev, - struct can_priv *priv) -{ - /* check XL ctrlmode on real CAN interfaces */ - if (priv) - return (priv->ctrlmode & CAN_CTRLMODE_XL); - - /* check MTU for virtual CAN XL interfaces */ - return can_is_canxl_dev_mtu(READ_ONCE(dev->mtu)); -} - static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, struct net_device *dev) { - struct can_priv *priv = safe_candev_priv(dev); - /* Classical CAN */ - if (can_is_can_skb(skb) && raw_dev_cc_enabled(dev, priv)) + if (can_is_can_skb(skb) && can_cap_enabled(dev, CAN_CAP_CC)) return CAN_MTU; /* CAN FD */ if (ro->fd_frames && can_is_canfd_skb(skb) && - raw_dev_fd_enabled(dev, priv)) + can_cap_enabled(dev, CAN_CAP_FD)) return CANFD_MTU; /* CAN XL */ if (ro->xl_frames && can_is_canxl_skb(skb) && - raw_dev_xl_enabled(dev, priv)) + can_cap_enabled(dev, CAN_CAP_XL)) return CANXL_MTU; return 0; @@ -982,6 +945,12 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (!dev) return -ENXIO; + /* no sending on a CAN device in read-only mode */ + if (can_cap_enabled(dev, CAN_CAP_RO)) { + err = -EACCES; + goto put_dev; + } + skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 833e57849c1d..c9d50c0dcd33 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -2376,7 +2376,9 @@ static int process_auth_done(struct ceph_connection *con, void *p, void *end) ceph_decode_64_safe(&p, end, global_id, bad); ceph_decode_32_safe(&p, end, con->v2.con_mode, bad); + ceph_decode_32_safe(&p, end, payload_len, bad); + ceph_decode_need(&p, end, payload_len, bad); dout("%s con %p global_id %llu con_mode %d payload_len %d\n", __func__, con, global_id, con->v2.con_mode, payload_len); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index c227ececa925..fa8dd2a20f7d 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1417,7 +1417,7 @@ static int mon_handle_auth_done(struct ceph_connection *con, if (!ret) finish_hunting(monc); mutex_unlock(&monc->mutex); - return 0; + return ret; } static int mon_handle_auth_bad_method(struct ceph_connection *con, diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 3667319b949d..610e584524d1 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1586,6 +1586,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_pg_pool_info *pi; struct ceph_pg pgid, last_pgid; struct ceph_osds up, acting; + bool should_be_paused; bool is_read = t->flags & CEPH_OSD_FLAG_READ; bool is_write = t->flags & CEPH_OSD_FLAG_WRITE; bool force_resend = false; @@ -1654,10 +1655,16 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, &last_pgid)) force_resend = true; - if (t->paused && !target_should_be_paused(osdc, t, pi)) { - t->paused = false; + should_be_paused = target_should_be_paused(osdc, t, pi); + if (t->paused && !should_be_paused) { unpaused = true; } + if (t->paused != should_be_paused) { + dout("%s t %p paused %d -> %d\n", __func__, t, t->paused, + should_be_paused); + t->paused = should_be_paused; + } + legacy_change = ceph_pg_compare(&t->pgid, &pgid) || ceph_osds_changed(&t->acting, &acting, t->used_replica || any_change); @@ -4281,6 +4288,9 @@ static void osd_fault(struct ceph_connection *con) goto out_unlock; } + osd->o_sparse_op_idx = -1; + ceph_init_sparse_read(&osd->o_sparse_read); + if (!reopen_osd(osd)) kick_osd_requests(osd); maybe_request_map(osdc); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 34b3ab59602f..92a44026de29 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -241,22 +241,26 @@ static struct crush_choose_arg_map *alloc_choose_arg_map(void) static void free_choose_arg_map(struct crush_choose_arg_map *arg_map) { - if (arg_map) { - int i, j; + int i, j; + + if (!arg_map) + return; - WARN_ON(!RB_EMPTY_NODE(&arg_map->node)); + WARN_ON(!RB_EMPTY_NODE(&arg_map->node)); + if (arg_map->args) { for (i = 0; i < arg_map->size; i++) { struct crush_choose_arg *arg = &arg_map->args[i]; - - for (j = 0; j < arg->weight_set_size; j++) - kfree(arg->weight_set[j].weights); - kfree(arg->weight_set); + if (arg->weight_set) { + for (j = 0; j < arg->weight_set_size; j++) + kfree(arg->weight_set[j].weights); + kfree(arg->weight_set); + } kfree(arg->ids); } kfree(arg_map->args); - kfree(arg_map); } + kfree(arg_map); } DEFINE_RB_FUNCS(choose_arg_map, struct crush_choose_arg_map, choose_args_index, @@ -1979,11 +1983,13 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, bool msgr2, sizeof(u64) + sizeof(u32), e_inval); ceph_decode_copy(p, &fsid, sizeof(fsid)); epoch = ceph_decode_32(p); - BUG_ON(epoch != map->epoch+1); ceph_decode_copy(p, &modified, sizeof(modified)); new_pool_max = ceph_decode_64(p); new_flags = ceph_decode_32(p); + if (epoch != map->epoch + 1) + goto e_inval; + /* full map? */ ceph_decode_32_safe(p, end, len, e_inval); if (len > 0) { diff --git a/net/core/dev.c b/net/core/dev.c index 9094c0fb8c68..ccef685023c2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -478,15 +478,21 @@ static const unsigned short netdev_lock_type[] = { ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, + ARPHRD_CAN, ARPHRD_MCTP, ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, - ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, + ARPHRD_RAWHDLC, ARPHRD_RAWIP, + ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, - ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, - ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; + ARPHRD_IEEE80211_RADIOTAP, + ARPHRD_IEEE802154, ARPHRD_IEEE802154_MONITOR, + ARPHRD_PHONET, ARPHRD_PHONET_PIPE, + ARPHRD_CAIF, ARPHRD_IP6GRE, ARPHRD_NETLINK, ARPHRD_6LOWPAN, + ARPHRD_VSOCKMON, + ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = { "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", @@ -495,15 +501,21 @@ static const char *const netdev_lock_name[] = { "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", + "_xmit_CAN", "_xmit_MCTP", "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", + "_xmit_RAWHDLC", "_xmit_RAWIP", + "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; + "_xmit_IEEE80211_RADIOTAP", + "_xmit_IEEE802154", "_xmit_IEEE802154_MONITOR", + "_xmit_PHONET", "_xmit_PHONET_PIPE", + "_xmit_CAIF", "_xmit_IP6GRE", "_xmit_NETLINK", "_xmit_6LOWPAN", + "_xmit_VSOCKMON", + "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -516,6 +528,7 @@ static inline unsigned short netdev_lock_pos(unsigned short dev_type) if (netdev_lock_type[i] == dev_type) return i; /* the last key is used by default */ + WARN_ONCE(1, "netdev_lock_pos() could not find dev_type=%u\n", dev_type); return ARRAY_SIZE(netdev_lock_type) - 1; } @@ -4190,8 +4203,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, do { if (first_n && !defer_count) { defer_count = atomic_long_inc_return(&q->defer_count); - if (unlikely(defer_count > READ_ONCE(q->limit))) { - kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_DROP); + if (unlikely(defer_count > READ_ONCE(net_hotdata.qdisc_max_burst))) { + kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_BURST_DROP); return NET_XMIT_DROP; } } @@ -4209,7 +4222,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, ll_list = llist_del_all(&q->defer_list); /* There is a small race because we clear defer_count not atomically * with the prior llist_del_all(). This means defer_list could grow - * over q->limit. + * over qdisc_max_burst. */ atomic_long_set(&q->defer_count, 0); @@ -4241,9 +4254,11 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, int count = 0; llist_for_each_entry_safe(skb, next, ll_list, ll_node) { - prefetch(next); - prefetch(&next->priority); - skb_mark_not_on_list(skb); + if (next) { + prefetch(next); + prefetch(&next->priority); + skb_mark_not_on_list(skb); + } rc = dev_qdisc_enqueue(skb, q, &to_free, txq); count++; } diff --git a/net/core/dst.c b/net/core/dst.c index e9d35f49c9e7..1dae26c51ebe 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -68,6 +68,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->lwtstate = NULL; rcuref_init(&dst->__rcuref, 1); INIT_LIST_HEAD(&dst->rt_uncached); + dst->rt_uncached_list = NULL; dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; diff --git a/net/core/filter.c b/net/core/filter.c index 616e0520a0bb..bcd73d9bd764 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3353,6 +3353,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } + shinfo->gso_type |= SKB_GSO_DODGY; } bpf_skb_change_protocol(skb, ETH_P_IPV6); @@ -3383,6 +3384,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } + shinfo->gso_type |= SKB_GSO_DODGY; } bpf_skb_change_protocol(skb, ETH_P_IP); diff --git a/net/core/hotdata.c b/net/core/hotdata.c index dddd5c287cf0..a6db36580817 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -17,6 +17,7 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .tstamp_prequeue = 1, .max_backlog = 1000, + .qdisc_max_burst = 1000, .dev_tx_weight = 64, .dev_rx_weight = 64, .sysctl_max_skb_frags = MAX_SKB_FRAGS, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a00808f7be6a..61746c2b95f6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1312,14 +1312,15 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) has_mac = skb_mac_header_was_set(skb); has_trans = skb_transport_header_was_set(skb); - printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n" - "mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n" + printk("%sskb len=%u data_len=%u headroom=%u headlen=%u tailroom=%u\n" + "end-tail=%u mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n" "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n" "csum(0x%x start=%u offset=%u ip_summed=%u complete_sw=%u valid=%u level=%u)\n" "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n" "priority=0x%x mark=0x%x alloc_cpu=%u vlan_all=0x%x\n" "encapsulation=%d inner(proto=0x%04x, mac=%u, net=%u, trans=%u)\n", - level, skb->len, headroom, skb_headlen(skb), tailroom, + level, skb->len, skb->data_len, headroom, skb_headlen(skb), + tailroom, skb->end - skb->tail, has_mac ? skb->mac_header : -1, has_mac ? skb_mac_header_len(skb) : -1, skb->mac_len, @@ -4636,12 +4637,14 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, { struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; unsigned int tnl_hlen = skb_tnl_header_len(skb); - unsigned int delta_truesize = 0; unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int len_diff, err; + /* Only skb_gro_receive_list generated skbs arrive here */ + DEBUG_NET_WARN_ON_ONCE(!(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)); + skb_push(skb, -skb_network_offset(skb) + offset); /* Ensure the head is writeable before touching the shared info */ @@ -4655,8 +4658,9 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, nskb = list_skb; list_skb = list_skb->next; + DEBUG_NET_WARN_ON_ONCE(nskb->sk); + err = 0; - delta_truesize += nskb->truesize; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { @@ -4699,7 +4703,6 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, goto err_linearize; } - skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; skb->len = skb->len - delta_len; diff --git a/net/core/sock.c b/net/core/sock.c index 45c98bf524b2..a1c8b47b0d56 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3896,7 +3896,7 @@ void sock_enable_timestamp(struct sock *sk, enum sock_flags flag) int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type) { - struct sock_exterr_skb *serr; + struct sock_extended_err ee; struct sk_buff *skb; int copied, err; @@ -3916,8 +3916,9 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, sock_recv_timestamp(msg, sk, skb); - serr = SKB_EXT_ERR(skb); - put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); + /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ + ee = SKB_EXT_ERR(skb)->ee; + put_cmsg(msg, level, type, sizeof(ee), &ee); msg->msg_flags |= MSG_ERRQUEUE; err = copied; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8d4decb2606f..05dd55cf8b58 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -430,6 +430,13 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { + .procname = "qdisc_max_burst", + .data = &net_hotdata.qdisc_max_burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "netdev_rss_key", .data = &netdev_rss_key, .maxlen = sizeof(int), diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index a20efabe778f..35ce3941fae3 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -158,7 +158,7 @@ unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) bridge_num = find_next_zero_bit(&dsa_fwd_offloading_bridges, DSA_MAX_NUM_OFFLOADING_BRIDGES, 1); - if (bridge_num >= max) + if (bridge_num > max) return 0; set_bit(bridge_num, &dsa_fwd_offloading_bridges); @@ -367,16 +367,10 @@ static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst) { - struct device_node *ethernet; - struct net_device *conduit; struct dsa_port *cpu_dp; cpu_dp = dsa_tree_find_first_cpu(dst); - ethernet = of_parse_phandle(cpu_dp->dn, "ethernet", 0); - conduit = of_find_net_device_by_node(ethernet); - of_node_put(ethernet); - - return conduit; + return cpu_dp->conduit; } /* Assign the default CPU port (the first one in the tree) to all ports of the @@ -1253,14 +1247,25 @@ static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) if (ethernet) { struct net_device *conduit; const char *user_protocol; + int err; + rtnl_lock(); conduit = of_find_net_device_by_node(ethernet); of_node_put(ethernet); - if (!conduit) + if (!conduit) { + rtnl_unlock(); return -EPROBE_DEFER; + } + + netdev_hold(conduit, &dp->conduit_tracker, GFP_KERNEL); + put_device(&conduit->dev); + rtnl_unlock(); user_protocol = of_get_property(dn, "dsa-tag-protocol", NULL); - return dsa_port_parse_cpu(dp, conduit, user_protocol); + err = dsa_port_parse_cpu(dp, conduit, user_protocol); + if (err) + netdev_put(conduit, &dp->conduit_tracker); + return err; } if (link) @@ -1393,37 +1398,30 @@ static struct device *dev_find_class(struct device *parent, char *class) return device_find_child(parent, class, dev_is_class); } -static struct net_device *dsa_dev_to_net_device(struct device *dev) -{ - struct device *d; - - d = dev_find_class(dev, "net"); - if (d != NULL) { - struct net_device *nd; - - nd = to_net_dev(d); - dev_hold(nd); - put_device(d); - - return nd; - } - - return NULL; -} - static int dsa_port_parse(struct dsa_port *dp, const char *name, struct device *dev) { if (!strcmp(name, "cpu")) { struct net_device *conduit; + struct device *d; + int err; - conduit = dsa_dev_to_net_device(dev); - if (!conduit) + rtnl_lock(); + d = dev_find_class(dev, "net"); + if (!d) { + rtnl_unlock(); return -EPROBE_DEFER; + } - dev_put(conduit); + conduit = to_net_dev(d); + netdev_hold(conduit, &dp->conduit_tracker, GFP_KERNEL); + put_device(d); + rtnl_unlock(); - return dsa_port_parse_cpu(dp, conduit, NULL); + err = dsa_port_parse_cpu(dp, conduit, NULL); + if (err) + netdev_put(conduit, &dp->conduit_tracker); + return err; } if (!strcmp(name, "dsa")) @@ -1491,6 +1489,9 @@ static void dsa_switch_release_ports(struct dsa_switch *ds) struct dsa_vlan *v, *n; dsa_switch_for_each_port_safe(dp, next, ds) { + if (dsa_port_is_cpu(dp) && dp->conduit) + netdev_put(dp->conduit, &dp->conduit_tracker); + /* These are either entries that upper layers lost track of * (probably due to bugs), or installed through interfaces * where one does not necessarily have to remove them, like @@ -1635,8 +1636,10 @@ void dsa_switch_shutdown(struct dsa_switch *ds) /* Disconnect from further netdevice notifiers on the conduit, * since netdev_uses_dsa() will now return false. */ - dsa_switch_for_each_cpu_port(dp, ds) + dsa_switch_for_each_cpu_port(dp, ds) { dp->conduit->dsa_ptr = NULL; + netdev_put(dp->conduit, &dp->conduit_tracker); + } rtnl_unlock(); out: diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index 1d33a4675a48..b989456fc4c5 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -126,7 +126,8 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) } out_complete: - handshake_complete(req, -EIO, NULL); + if (req) + handshake_complete(req, -EIO, NULL); out_status: trace_handshake_cmd_accept_err(net, req, NULL, err); return err; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 7f3863daaa40..c8c3e1713c0e 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -564,7 +564,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, skb_reserve(skb, hlen); skb_reset_network_header(skb); - arp = skb_put(skb, arp_hdr_len(dev)); + skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (!src_hw) @@ -572,12 +572,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, if (!dest_hw) dest_hw = dev->broadcast; - /* - * Fill the device header for the ARP frame + /* Fill the device header for the ARP frame. + * Note: skb->head can be changed. */ if (dev_hard_header(skb, dev, ptype, dest_hw, src_hw, skb->len) < 0) goto out; + arp = arp_hdr(skb); /* * Fill out the arp protocol part. * diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 05828d4cb6cd..abd77162f5e7 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -122,8 +122,8 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, - XFRM_MODE_SKB_CB(skb)->protocol); + struct xfrm_offload *xo = xfrm_offload(skb); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto); __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6) : htons(ETH_P_IP); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a5f3c8459758..0caf38e44c73 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -2167,8 +2167,8 @@ void fib_select_multipath(struct fib_result *res, int hash, { struct fib_info *fi = res->fi; struct net *net = fi->fib_net; - bool found = false; bool use_neigh; + int score = -1; __be32 saddr; if (unlikely(res->fi->nh)) { @@ -2180,7 +2180,7 @@ void fib_select_multipath(struct fib_result *res, int hash, saddr = fl4 ? fl4->saddr : 0; change_nexthops(fi) { - int nh_upper_bound; + int nh_upper_bound, nh_score = 0; /* Nexthops without a carrier are assigned an upper bound of * minus one when "ignore_routes_with_linkdown" is set. @@ -2190,24 +2190,18 @@ void fib_select_multipath(struct fib_result *res, int hash, (use_neigh && !fib_good_nh(nexthop_nh))) continue; - if (!found) { + if (saddr && nexthop_nh->nh_saddr == saddr) + nh_score += 2; + if (hash <= nh_upper_bound) + nh_score++; + if (score < nh_score) { res->nh_sel = nhsel; res->nhc = &nexthop_nh->nh_common; - found = !saddr || nexthop_nh->nh_saddr == saddr; + if (nh_score == 3 || (!saddr && nh_score == 1)) + return; + score = nh_score; } - if (hash > nh_upper_bound) - continue; - - if (!saddr || nexthop_nh->nh_saddr == saddr) { - res->nh_sel = nhsel; - res->nhc = &nexthop_nh->nh_common; - return; - } - - if (found) - return; - } endfor_nexthops(fi); } #endif diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 59a6f0a9638f..7e2c17fec3fc 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2053,10 +2053,11 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) continue; } - /* Do not flush error routes if network namespace is - * not being dismantled + /* When not flushing the entire table, skip error + * routes that are not marked for deletion. */ - if (!flush_all && fib_props[fa->fa_type].error) { + if (!flush_all && fib_props[fa->fa_type].error && + !(fi->fib_flags & RTNH_F_DEAD)) { slen = fa->fa_slen; continue; } diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index 3970b6b7ace5..ab8f309f8925 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -215,6 +215,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) return gue_control_message(skb, guehdr); proto_ctype = guehdr->proto_ctype; + if (unlikely(!proto_ctype)) + goto drop; + __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 7a99639204b1..309d5ba983d0 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -15,7 +15,7 @@ const struct nla_policy fou_nl_policy[FOU_ATTR_IFINDEX + 1] = { [FOU_ATTR_PORT] = { .type = NLA_BE16, }, [FOU_ATTR_AF] = { .type = NLA_U8, }, - [FOU_ATTR_IPPROTO] = { .type = NLA_U8, }, + [FOU_ATTR_IPPROTO] = NLA_POLICY_MIN(NLA_U8, 1), [FOU_ATTR_TYPE] = { .type = NLA_U8, }, [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 001ee5c4d962..4e6d7467ed44 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -488,6 +488,8 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, } FRAG_CB(skb)->ip_defrag_offset = offset; + if (offset) + nf_reset_ct(skb); return IPFRAG_OK; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 761a53c6a89a..e13244729ad8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -330,6 +330,10 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!tun_dst) return PACKET_REJECT; + /* MUST set options_len before referencing options */ + info = &tun_dst->u.tun_info; + info->options_len = sizeof(*md); + /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it @@ -344,10 +348,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); - info = &tun_dst->u.tun_info; __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); - info->options_len = sizeof(*md); } skb_reset_mac_header(skb); @@ -889,10 +891,17 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); - struct iphdr *iph; struct gre_base_hdr *greh; + struct iphdr *iph; + int needed; + + needed = t->hlen + sizeof(*iph); + if (skb_headroom(skb) < needed && + pskb_expand_head(skb, HH_DATA_ALIGN(needed - skb_headroom(skb)), + 0, GFP_ATOMIC)) + return -needed; - iph = skb_push(skb, t->hlen + sizeof(*iph)); + iph = skb_push(skb, needed); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 158a30ae7c5f..50d0f5fe4e4c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1281,7 +1281,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], } EXPORT_SYMBOL_GPL(ip_tunnel_changelink); -int ip_tunnel_init(struct net_device *dev) +int __ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -1308,10 +1308,9 @@ int ip_tunnel_init(struct net_device *dev) if (tunnel->collect_md) netif_keep_dst(dev); - netdev_lockdep_set_classes(dev); return 0; } -EXPORT_SYMBOL_GPL(ip_tunnel_init); +EXPORT_SYMBOL_GPL(__ip_tunnel_init); void ip_tunnel_uninit(struct net_device *dev) { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index ad56588107cc..cfbd563498e8 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -828,10 +828,8 @@ out: out_free: if (free) kfree(ipc.opt); - if (!err) { - icmp_out_count(sock_net(sk), user_icmph.type); + if (!err) return len; - } return err; do_confirm: diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b549d6a57307..11d990703d31 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1537,9 +1537,9 @@ void rt_add_uncached_list(struct rtable *rt) void rt_del_uncached_list(struct rtable *rt) { - if (!list_empty(&rt->dst.rt_uncached)) { - struct uncached_list *ul = rt->dst.rt_uncached_list; + struct uncached_list *ul = rt->dst.rt_uncached_list; + if (ul) { spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f035440c475a..d5319ebe2452 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2652,10 +2652,8 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, if (sk->sk_state == TCP_LISTEN) goto out; - if (tp->recvmsg_inq) { + if (tp->recvmsg_inq) *cmsg_flags = TCP_CMSG_INQ; - msg->msg_get_inq = 1; - } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); /* Urgent data needs to be handled specially. */ @@ -2929,10 +2927,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags); release_sock(sk); - if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { + if ((cmsg_flags | msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); - if (msg->msg_get_inq) { + if ((cmsg_flags & TCP_CMSG_INQ) | msg->msg_get_inq) { msg->msg_inq = tcp_inq_hint(sk); if (cmsg_flags & TCP_CMSG_INQ) put_cmsg(msg, SOL_TCP, TCP_CM_INQ, diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index fdda18b1abda..942a948f1a31 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -107,7 +107,8 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) { struct tcphdr *th = tcp_hdr(skb); - if (skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) + if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) && + !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)) return __tcp4_gso_segment_list(skb, features); skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ffe074cb5865..ee63af0ef42c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1851,6 +1851,7 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) sk_peek_offset_bwd(sk, len); if (!skb_shared(skb)) { + skb_orphan(skb); skb_attempt_defer_free(skb); return; } diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 19d0b5b09ffa..589456bd8b5f 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -514,7 +514,8 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { /* Detect modified geometry and pass those to skb_segment. */ - if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) + if ((skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_DODGY)) return __udp_gso_segment_list(gso_skb, features, is_ipv6); ret = __skb_linearize(gso_skb); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b66217d1b2f8..27ab9d7adc64 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3112,12 +3112,12 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, in6_ifa_hold(ifp); read_unlock_bh(&idev->lock); - ipv6_del_addr(ifp); - if (!(ifp->flags & IFA_F_TEMPORARY) && (ifp->flags & IFA_F_MANAGETEMPADDR)) delete_tempaddrs(idev, ifp); + ipv6_del_addr(ifp); + addrconf_verify_rtnl(net); if (ipv6_addr_is_multicast(pfx)) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index df1986973430..21f6ed126253 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1342,7 +1342,8 @@ static int calipso_skbuff_setattr(struct sk_buff *skb, /* At this point new_end aligns to 4n, so (new_end & 4) pads to 8n */ pad = ((new_end & 4) + (end & 7)) & 7; len_delta = new_end - (int)end + pad; - ret_val = skb_cow(skb, skb_headroom(skb) + len_delta); + ret_val = skb_cow(skb, + skb_headroom(skb) + (len_delta > 0 ? len_delta : 0)); if (ret_val < 0) return ret_val; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 22410243ebe8..22895521a57d 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -158,8 +158,8 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, - XFRM_MODE_SKB_CB(skb)->protocol); + struct xfrm_offload *xo = xfrm_offload(skb); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto); __be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP) : htons(ETH_P_IPV6); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 5d2f90babaa5..9d37e7711bc2 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -965,7 +965,9 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) fl6.saddr = *saddr; - fl6.flowi6_oif = icmp6_iif(skb); + fl6.flowi6_oif = ipv6_addr_loopback(&fl6.daddr) ? + skb->dev->ifindex : + icmp6_iif(skb); fl6.fl6_icmp_type = type; fl6.flowi6_mark = mark; fl6.flowi6_uid = sock_net_uid(net, NULL); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c82a75510c0e..d19d86ed4376 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -535,6 +535,10 @@ static int ip6erspan_rcv(struct sk_buff *skb, if (!tun_dst) return PACKET_REJECT; + /* MUST set options_len before referencing options */ + info = &tun_dst->u.tun_info; + info->options_len = sizeof(*md); + /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it @@ -543,7 +547,6 @@ static int ip6erspan_rcv(struct sk_buff *skb, skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); - info = &tun_dst->u.tun_info; md = ip_tunnel_info_opts(info); md->version = ver; md2 = &md->u.md2; @@ -551,7 +554,6 @@ static int ip6erspan_rcv(struct sk_buff *skb, ERSPAN_V2_MDSIZE); __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); - info->options_len = sizeof(*md); ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); @@ -1366,9 +1368,16 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, { struct ip6_tnl *t = netdev_priv(dev); struct ipv6hdr *ipv6h; + int needed; __be16 *p; - ipv6h = skb_push(skb, t->hlen + sizeof(*ipv6h)); + needed = t->hlen + sizeof(*ipv6h); + if (skb_headroom(skb) < needed && + pskb_expand_head(skb, HH_DATA_ALIGN(needed - skb_headroom(skb)), + 0, GFP_ATOMIC)) + return -needed; + + ipv6h = skb_push(skb, needed); ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb, t->fl.u.ip6.flowlabel, true, &t->fl.u.ip6)); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 6405072050e0..c1f39735a236 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -844,7 +844,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_reset_network_header(skb); - if (!pskb_inet_may_pull(skb)) { + if (skb_vlan_inet_prepare(skb, true)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 59d17b6f06bf..f6a5d8c73af9 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1555,8 +1555,8 @@ skip_routeinfo: memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); - if (in6_dev->ra_mtu != mtu) { - in6_dev->ra_mtu = mtu; + if (READ_ONCE(in6_dev->ra_mtu) != mtu) { + WRITE_ONCE(in6_dev->ra_mtu, mtu); send_ifinfo_notify = true; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index aee6a10b112a..e3a260a5564b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -148,9 +148,9 @@ void rt6_uncached_list_add(struct rt6_info *rt) void rt6_uncached_list_del(struct rt6_info *rt) { - if (!list_empty(&rt->dst.rt_uncached)) { - struct uncached_list *ul = rt->dst.rt_uncached_list; + struct uncached_list *ul = rt->dst.rt_uncached_list; + if (ul) { spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); @@ -1470,7 +1470,18 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net, p = this_cpu_ptr(res->nh->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); - BUG_ON(prev); + if (unlikely(prev)) { + /* + * Another task on this CPU already installed a pcpu_rt. + * This can happen on PREEMPT_RT where preemption is possible. + * Free our allocation and return the existing one. + */ + WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RT)); + + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + return prev; + } if (res->f6i->fib6_destroying) { struct fib6_info *from; diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index effeba58630b..5670d32c27f8 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -170,7 +170,8 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) { struct tcphdr *th = tcp_hdr(skb); - if (skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) + if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) && + !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)) return __tcp6_gso_segment_list(skb, features); skb->ip_summed = CHECKSUM_NONE; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 687c1366a4d0..f9b0f666600f 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1086,8 +1086,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) tunnel = session->tunnel; /* Check protocol version */ - if (version != tunnel->version) + if (version != tunnel->version) { + l2tp_session_put(session); goto invalid; + } if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { @@ -1414,8 +1416,6 @@ static void l2tp_tunnel_del_work(struct work_struct *work) { struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, del_work); - struct sock *sk = tunnel->sock; - struct socket *sock = sk->sk_socket; l2tp_tunnel_closeall(tunnel); @@ -1423,6 +1423,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work) * the sk API to release it here. */ if (tunnel->fd < 0) { + struct socket *sock = tunnel->sock->sk_socket; + if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index b51c2c8584ae..c81091a5cc3a 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1345,7 +1345,6 @@ ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, size = sizeof(*new) + new_head_len + new_tail_len; - /* new or old multiple BSSID elements? */ if (params->mbssid_ies) { mbssid = params->mbssid_ies; size += struct_size(new->mbssid_ies, elem, mbssid->cnt); @@ -1355,15 +1354,6 @@ ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, } size += ieee80211_get_mbssid_beacon_len(mbssid, rnr, mbssid->cnt); - } else if (old && old->mbssid_ies) { - mbssid = old->mbssid_ies; - size += struct_size(new->mbssid_ies, elem, mbssid->cnt); - if (old && old->rnr_ies) { - rnr = old->rnr_ies; - size += struct_size(new->rnr_ies, elem, rnr->cnt); - } - size += ieee80211_get_mbssid_beacon_len(mbssid, rnr, - mbssid->cnt); } new = kzalloc(size, GFP_KERNEL); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index d0bfb1216401..d8c5f11afc15 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -90,6 +90,9 @@ next_interface: /* next (or first) interface */ iter->sdata = list_prepare_entry(iter->sdata, &local->interfaces, list); list_for_each_entry_continue(iter->sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(iter->sdata)) + continue; + /* AP_VLAN has a chanctx pointer but follows AP */ if (iter->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) continue; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 9d9313eee59f..bd573f8e61fb 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -451,8 +451,6 @@ struct ieee80211_mgd_assoc_data { struct ieee80211_conn_settings conn; u16 status; - - bool disabled; } link[IEEE80211_MLD_MAX_NUM_LINKS]; u8 ap_addr[ETH_ALEN] __aligned(2); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 4f04d95c19d4..515384ca2f8f 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -350,6 +350,8 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, /* we hold the RTNL here so can safely walk the list */ list_for_each_entry(nsdata, &local->interfaces, list) { if (nsdata != sdata && ieee80211_sdata_running(nsdata)) { + struct ieee80211_link_data *link; + /* * Only OCB and monitor mode may coexist */ @@ -376,8 +378,10 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, * will not add another interface while any channel * switch is active. */ - if (nsdata->vif.bss_conf.csa_active) - return -EBUSY; + for_each_link_data(nsdata, link) { + if (link->conf->csa_active) + return -EBUSY; + } /* * The remaining checks are only performed for interfaces @@ -1251,7 +1255,7 @@ configure_monitor: if (!creator_sdata) { struct ieee80211_sub_if_data *other; - list_for_each_entry(other, &local->mon_list, list) { + list_for_each_entry_rcu(other, &local->mon_list, u.mntr.list) { if (!other->vif.bss_conf.mu_mimo_owner) continue; diff --git a/net/mac80211/key.c b/net/mac80211/key.c index d5da7ccea66e..04c8809173d7 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -987,7 +987,8 @@ void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata) if (ieee80211_sdata_running(sdata)) { list_for_each_entry(key, &sdata->key_list, list) { - increment_tailroom_need_count(sdata); + if (!(key->flags & KEY_FLAG_TAINTED)) + increment_tailroom_need_count(sdata); ieee80211_key_enable_hw_accel(key); } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e56ad4b9330f..73f57b9e0ebf 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2025 Intel Corporation + * Copyright (C) 2018 - 2026 Intel Corporation */ #include <linux/delay.h> @@ -1126,7 +1126,10 @@ again: while (!ieee80211_chandef_usable(sdata, &chanreq->oper, IEEE80211_CHAN_DISABLED)) { - if (WARN_ON(chanreq->oper.width == NL80211_CHAN_WIDTH_20_NOHT)) { + if (chanreq->oper.width == NL80211_CHAN_WIDTH_20_NOHT) { + link_id_info(sdata, link_id, + "unusable channel (%d MHz) for connection\n", + chanreq->oper.chan->center_freq); ret = -EINVAL; goto free; } @@ -6158,6 +6161,100 @@ static bool ieee80211_get_dtim(const struct cfg80211_bss_ies *ies, return true; } +static u16 ieee80211_get_ttlm(u8 bm_size, u8 *data) +{ + if (bm_size == 1) + return *data; + + return get_unaligned_le16(data); +} + +static int +ieee80211_parse_adv_t2l(struct ieee80211_sub_if_data *sdata, + const struct ieee80211_ttlm_elem *ttlm, + struct ieee80211_adv_ttlm_info *ttlm_info) +{ + /* The element size was already validated in + * ieee80211_tid_to_link_map_size_ok() + */ + u8 control, link_map_presence, map_size, tid; + u8 *pos; + + memset(ttlm_info, 0, sizeof(*ttlm_info)); + pos = (void *)ttlm->optional; + control = ttlm->control; + + if ((control & IEEE80211_TTLM_CONTROL_DIRECTION) != + IEEE80211_TTLM_DIRECTION_BOTH) { + sdata_info(sdata, "Invalid advertised T2L map direction\n"); + return -EINVAL; + } + + if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { + link_map_presence = *pos; + pos++; + } + + if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) { + ttlm_info->switch_time = get_unaligned_le16(pos); + + /* Since ttlm_info->switch_time == 0 means no switch time, bump + * it by 1. + */ + if (!ttlm_info->switch_time) + ttlm_info->switch_time = 1; + + pos += 2; + } + + if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) { + ttlm_info->duration = pos[0] | pos[1] << 8 | pos[2] << 16; + pos += 3; + } + + if (control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP) { + ttlm_info->map = 0xffff; + return 0; + } + + if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) + map_size = 1; + else + map_size = 2; + + /* According to Draft P802.11be_D3.0 clause 35.3.7.1.7, an AP MLD shall + * not advertise a TID-to-link mapping that does not map all TIDs to the + * same link set, reject frame if not all links have mapping + */ + if (link_map_presence != 0xff) { + sdata_info(sdata, + "Invalid advertised T2L mapping presence indicator\n"); + return -EINVAL; + } + + ttlm_info->map = ieee80211_get_ttlm(map_size, pos); + if (!ttlm_info->map) { + sdata_info(sdata, + "Invalid advertised T2L map for TID 0\n"); + return -EINVAL; + } + + pos += map_size; + + for (tid = 1; tid < 8; tid++) { + u16 map = ieee80211_get_ttlm(map_size, pos); + + if (map != ttlm_info->map) { + sdata_info(sdata, "Invalid advertised T2L map for tid %d\n", + tid); + return -EINVAL; + } + + pos += map_size; + } + return 0; +} + static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, struct ieee802_11_elems *elems, @@ -6189,8 +6286,6 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, continue; valid_links |= BIT(link_id); - if (assoc_data->link[link_id].disabled) - dormant_links |= BIT(link_id); if (link_id != assoc_data->assoc_link_id) { err = ieee80211_sta_allocate_link(sta, link_id); @@ -6199,6 +6294,33 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } } + /* + * We do not support setting a negotiated TTLM during + * association. As such, we can assume that if there is a TTLM, + * then it is the currently active advertised TTLM. + * In that case, there must be exactly one TTLM that does not + * have a switch time set. This mapping should also leave us + * with at least one usable link. + */ + if (elems->ttlm_num > 1) { + sdata_info(sdata, + "More than one advertised TTLM in association response\n"); + goto out_err; + } else if (elems->ttlm_num == 1) { + if (ieee80211_parse_adv_t2l(sdata, elems->ttlm[0], + &sdata->u.mgd.ttlm_info) || + sdata->u.mgd.ttlm_info.switch_time != 0 || + !(valid_links & sdata->u.mgd.ttlm_info.map)) { + sdata_info(sdata, + "Invalid advertised TTLM in association response\n"); + goto out_err; + } + + sdata->u.mgd.ttlm_info.active = true; + dormant_links = + valid_links & ~sdata->u.mgd.ttlm_info.map; + } + ieee80211_vif_set_links(sdata, valid_links, dormant_links); } @@ -6989,95 +7111,6 @@ static void ieee80211_tid_to_link_map_work(struct wiphy *wiphy, sdata->u.mgd.ttlm_info.switch_time = 0; } -static u16 ieee80211_get_ttlm(u8 bm_size, u8 *data) -{ - if (bm_size == 1) - return *data; - else - return get_unaligned_le16(data); -} - -static int -ieee80211_parse_adv_t2l(struct ieee80211_sub_if_data *sdata, - const struct ieee80211_ttlm_elem *ttlm, - struct ieee80211_adv_ttlm_info *ttlm_info) -{ - /* The element size was already validated in - * ieee80211_tid_to_link_map_size_ok() - */ - u8 control, link_map_presence, map_size, tid; - u8 *pos; - - memset(ttlm_info, 0, sizeof(*ttlm_info)); - pos = (void *)ttlm->optional; - control = ttlm->control; - - if ((control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP) || - !(control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT)) - return 0; - - if ((control & IEEE80211_TTLM_CONTROL_DIRECTION) != - IEEE80211_TTLM_DIRECTION_BOTH) { - sdata_info(sdata, "Invalid advertised T2L map direction\n"); - return -EINVAL; - } - - link_map_presence = *pos; - pos++; - - ttlm_info->switch_time = get_unaligned_le16(pos); - - /* Since ttlm_info->switch_time == 0 means no switch time, bump it - * by 1. - */ - if (!ttlm_info->switch_time) - ttlm_info->switch_time = 1; - - pos += 2; - - if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) { - ttlm_info->duration = pos[0] | pos[1] << 8 | pos[2] << 16; - pos += 3; - } - - if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) - map_size = 1; - else - map_size = 2; - - /* According to Draft P802.11be_D3.0 clause 35.3.7.1.7, an AP MLD shall - * not advertise a TID-to-link mapping that does not map all TIDs to the - * same link set, reject frame if not all links have mapping - */ - if (link_map_presence != 0xff) { - sdata_info(sdata, - "Invalid advertised T2L mapping presence indicator\n"); - return -EINVAL; - } - - ttlm_info->map = ieee80211_get_ttlm(map_size, pos); - if (!ttlm_info->map) { - sdata_info(sdata, - "Invalid advertised T2L map for TID 0\n"); - return -EINVAL; - } - - pos += map_size; - - for (tid = 1; tid < 8; tid++) { - u16 map = ieee80211_get_ttlm(map_size, pos); - - if (map != ttlm_info->map) { - sdata_info(sdata, "Invalid advertised T2L map for tid %d\n", - tid); - return -EINVAL; - } - - pos += map_size; - } - return 0; -} - static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, u64 beacon_ts) @@ -9734,7 +9767,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, req, true, i, &assoc_data->link[i].conn); assoc_data->link[i].bss = link_cbss; - assoc_data->link[i].disabled = req->links[i].disabled; if (!bss->uapsd_supported) uapsd_supported = false; @@ -10716,8 +10748,6 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata, &data->link[link_id].conn); data->link[link_id].bss = link_cbss; - data->link[link_id].disabled = - req->add_links[link_id].disabled; data->link[link_id].elems = (u8 *)req->add_links[link_id].elems; data->link[link_id].elems_len = diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c index a5d4358f122a..ebb4f4d88c23 100644 --- a/net/mac80211/ocb.c +++ b/net/mac80211/ocb.c @@ -47,6 +47,9 @@ void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; int band; + if (!ifocb->joined) + return; + /* XXX: Consider removing the least recently used entry and * allow new one to be added. */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6a1899512d07..e0ccd9749853 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3511,6 +3511,11 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx) rx->skb->len < IEEE80211_MIN_ACTION_SIZE) return RX_DROP_U_RUNT_ACTION; + /* Drop non-broadcast Beacon frames */ + if (ieee80211_is_beacon(mgmt->frame_control) && + !is_broadcast_ether_addr(mgmt->da)) + return RX_DROP; + if (rx->sdata->vif.type == NL80211_IFTYPE_AP && ieee80211_is_beacon(mgmt->frame_control) && !(rx->flags & IEEE80211_RX_BEACON_REPORTED)) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 5ef315ed3b0f..4823c8d45639 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -347,8 +347,13 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) mgmt->da)) return; } else { - /* Beacons are expected only with broadcast address */ - if (!is_broadcast_ether_addr(mgmt->da)) + /* + * Non-S1G beacons are expected only with broadcast address. + * S1G beacons only carry the SA so no DA check is required + * nor possible. + */ + if (!ieee80211_is_s1g_beacon(mgmt->frame_control) && + !is_broadcast_ether_addr(mgmt->da)) return; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f4d3b67fda06..1a995bc301b1 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1533,6 +1533,10 @@ static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc) } } + sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL); + if (sinfo) + sta_set_sinfo(sta, sinfo, true); + if (sta->uploaded) { ret = drv_sta_state(local, sdata, sta, IEEE80211_STA_NONE, IEEE80211_STA_NOTEXIST); @@ -1541,9 +1545,6 @@ static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc) sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr); - sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL); - if (sinfo) - sta_set_sinfo(sta, sinfo, true); cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); kfree(sinfo); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 9d8b0a25f73c..1b55e8340413 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2397,6 +2397,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, if (chanctx_conf) chandef = &chanctx_conf->def; + else if (local->emulate_chanctx) + chandef = &local->hw.conf.chandef; else goto fail_rcu; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index f24ae7d40e88..43df4293f58b 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -408,6 +408,16 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, */ subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; if (subflow->request_mptcp) { + if (unlikely(subflow_simultaneous_connect(sk))) { + WARN_ON_ONCE(!mptcp_try_fallback(sk, MPTCP_MIB_SIMULTCONNFALLBACK)); + + /* Ensure mptcp_finish_connect() will not process the + * MPC handshake. + */ + subflow->request_mptcp = 0; + return false; + } + opts->suboptions = OPTION_MPTCP_MPC_SYN; opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk)); opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 57570a44e418..b26675054b0d 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -1294,16 +1294,26 @@ static void __reset_counters(struct pm_nl_pernet *pernet) int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); - LIST_HEAD(free_list); + struct list_head free_list; spin_lock_bh(&pernet->lock); - list_splice_init(&pernet->endp_list, &free_list); + free_list = pernet->endp_list; + INIT_LIST_HEAD_RCU(&pernet->endp_list); __reset_counters(pernet); pernet->next_id = 1; bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); - mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list); + + if (free_list.next == &pernet->endp_list) + return 0; + synchronize_rcu(); + + /* Adjust the pointers to free_list instead of pernet->endp_list */ + free_list.prev->next = &free_list; + free_list.next->prev = &free_list; + + mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list); __flush_addrs(&free_list); return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 9b1fafd87cb9..8d3233667418 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -821,11 +821,8 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) { - int err = sock_error(ssk); int ssk_state; - - if (!err) - return false; + int err; /* only propagate errors on fallen-back sockets or * on MPC connect @@ -833,6 +830,10 @@ static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) return false; + err = sock_error(ssk); + if (!err) + return false; + /* We need to propagate only transition to CLOSE state. * Orphaned socket will see such state change via * subflow_sched_work_if_closed() and that path will properly @@ -2467,10 +2468,10 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) */ static void __mptcp_subflow_disconnect(struct sock *ssk, struct mptcp_subflow_context *subflow, - unsigned int flags) + bool fastclosing) { if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - subflow->send_fastclose) { + fastclosing) { /* The MPTCP code never wait on the subflow sockets, TCP-level * disconnect should never fail */ @@ -2538,7 +2539,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { - __mptcp_subflow_disconnect(ssk, subflow, flags); + __mptcp_subflow_disconnect(ssk, subflow, msk->fastclosing); release_sock(ssk); goto out; @@ -2598,8 +2599,8 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb; - /* The first subflow can already be closed and still in the list */ - if (subflow->close_event_done) + /* The first subflow can already be closed or disconnected */ + if (subflow->close_event_done || READ_ONCE(subflow->local_id) < 0) return; subflow->close_event_done = true; @@ -2884,6 +2885,7 @@ static void mptcp_do_fastclose(struct sock *sk) mptcp_set_state(sk, TCP_CLOSE); mptcp_backlog_purge(sk); + msk->fastclosing = 1; /* Explicitly send the fastclose reset as need */ if (__mptcp_check_fallback(msk)) @@ -3418,6 +3420,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_sent = 0; msk->bytes_retrans = 0; msk->rcvspace_init = 0; + msk->fastclosing = 0; /* for fallback's sake */ WRITE_ONCE(msk->ack_seq, 0); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9c0d17876b22..66e973500791 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -320,7 +320,8 @@ struct mptcp_sock { fastopening:1, in_accept_queue:1, free_first:1, - rcvspace_init:1; + rcvspace_init:1, + fastclosing:1; u32 notsent_lowat; int keepalive_cnt; int keepalive_idle; @@ -1337,10 +1338,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - return (1 << sk->sk_state) & - (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) && - is_active_ssk(subflow) && - !subflow->conn_finished; + /* Note that the sk state implies !subflow->conn_finished. */ + return sk->sk_state == TCP_SYN_RECV && is_active_ssk(subflow); } #ifdef CONFIG_SYN_COOKIES diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 86ce58ae533d..96d54cb2cd93 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1878,12 +1878,6 @@ static void subflow_state_change(struct sock *sk) __subflow_state_change(sk); - if (subflow_simultaneous_connect(sk)) { - WARN_ON_ONCE(!mptcp_try_fallback(sk, MPTCP_MIB_SIMULTCONNFALLBACK)); - subflow->conn_finished = 1; - mptcp_propagate_state(parent, sk, subflow, NULL); - } - /* as recvmsg() does not acquire the subflow socket for ssk selection * a fin packet carrying a DSS can be unnoticed if we don't trigger * the data available machinery here. diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 3654f1e8976c..8487808c8761 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -229,6 +229,7 @@ static int __nf_conncount_add(struct net *net, nf_ct_put(found_ct); } + list->last_gc = (u32)jiffies; add_new_node: if (WARN_ON_ONCE(list->count > INT_MAX)) { @@ -248,7 +249,6 @@ add_new_node: conn->jiffies32 = (u32)jiffies; list_add_tail(&conn->node, &list->head); list->count++; - list->last_gc = (u32)jiffies; out_put: if (refcounted) diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 74cef8bf554c..62cf6a30875e 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -89,7 +89,7 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger) if (pf == NFPROTO_UNSPEC) { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { if (rcu_access_pointer(loggers[i][logger->type])) { - ret = -EEXIST; + ret = -EBUSY; goto unlock; } } @@ -97,7 +97,7 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger) rcu_assign_pointer(loggers[i][logger->type], logger); } else { if (rcu_access_pointer(loggers[pf][logger->type])) { - ret = -EEXIST; + ret = -EBUSY; goto unlock; } rcu_assign_pointer(loggers[pf][logger->type], logger); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 618af6e90773..729a92781a1a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4439,7 +4439,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, if (!nft_use_inc(&chain->use)) { err = -EMFILE; - goto err_release_rule; + goto err_destroy_flow; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { @@ -4489,6 +4489,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, err_destroy_flow_rule: nft_use_dec_restore(&chain->use); +err_destroy_flow: if (flow) nft_flow_rule_destroy(flow); err_release_rule: diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 112fe46788b6..6d77a5f0088a 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1317,8 +1317,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else dup_end = dup_key; - if (!memcmp(start, dup_key->data, sizeof(*dup_key->data)) && - !memcmp(end, dup_end->data, sizeof(*dup_end->data))) { + if (!memcmp(start, dup_key->data, set->klen) && + !memcmp(end, dup_end->data, set->klen)) { *elem_priv = &dup->priv; return -EEXIST; } diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 5d3e51825985..4d3e5a31b412 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -48,7 +48,7 @@ static void nft_synproxy_eval_v4(const struct nft_synproxy *priv, struct tcphdr *_tcph, struct synproxy_options *opts) { - struct nf_synproxy_info info = priv->info; + struct nf_synproxy_info info = READ_ONCE(priv->info); struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; @@ -79,7 +79,7 @@ static void nft_synproxy_eval_v6(const struct nft_synproxy *priv, struct tcphdr *_tcph, struct synproxy_options *opts) { - struct nf_synproxy_info info = priv->info; + struct nf_synproxy_info info = READ_ONCE(priv->info); struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; @@ -340,7 +340,7 @@ static void nft_synproxy_obj_update(struct nft_object *obj, struct nft_synproxy *newpriv = nft_obj_data(newobj); struct nft_synproxy *priv = nft_obj_data(obj); - priv->info = newpriv->info; + WRITE_ONCE(priv->info, newpriv->info); } static struct nft_object_type nft_synproxy_obj_type; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 90b7630421c4..48105ea3df15 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1764,7 +1764,7 @@ EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); int xt_register_template(const struct xt_table *table, int (*table_init)(struct net *net)) { - int ret = -EEXIST, af = table->af; + int ret = -EBUSY, af = table->af; struct xt_template *t; mutex_lock(&xt[af].mutex); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index b94cb2ffbaf8..9cc29ae85b06 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -752,7 +752,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) unsigned char *dptr; ax25_cb *ax25s; int ret; - struct sk_buff *skbn; + struct sk_buff *nskb, *oskb; /* * Reject malformed packets early. Check that it contains at least 2 @@ -811,14 +811,16 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) /* We are going to change the netrom headers so we should get our own skb, we also did not know until now how much header space we had to reserve... - RXQ */ - if ((skbn=skb_copy_expand(skb, dev->hard_header_len, 0, GFP_ATOMIC)) == NULL) { + nskb = skb_copy_expand(skb, dev->hard_header_len, 0, GFP_ATOMIC); + + if (!nskb) { nr_node_unlock(nr_node); nr_node_put(nr_node); dev_put(dev); return 0; } - kfree_skb(skb); - skb=skbn; + oskb = skb; + skb = nskb; skb->data[14]--; dptr = skb_push(skb, 1); @@ -837,6 +839,9 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) nr_node_unlock(nr_node); nr_node_put(nr_node); + if (ret) + kfree_skb(oskb); + return ret; } diff --git a/net/nfc/core.c b/net/nfc/core.c index ae1c842f9c64..f50e5bab35d8 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -1147,12 +1147,13 @@ int nfc_register_device(struct nfc_dev *dev) EXPORT_SYMBOL(nfc_register_device); /** - * nfc_unregister_device - unregister a nfc device in the nfc subsystem + * nfc_unregister_rfkill - unregister a nfc device in the rfkill subsystem * * @dev: The nfc device to unregister */ -void nfc_unregister_device(struct nfc_dev *dev) +void nfc_unregister_rfkill(struct nfc_dev *dev) { + struct rfkill *rfk = NULL; int rc; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); @@ -1164,13 +1165,26 @@ void nfc_unregister_device(struct nfc_dev *dev) device_lock(&dev->dev); if (dev->rfkill) { - rfkill_unregister(dev->rfkill); - rfkill_destroy(dev->rfkill); + rfk = dev->rfkill; dev->rfkill = NULL; } dev->shutting_down = true; device_unlock(&dev->dev); + if (rfk) { + rfkill_unregister(rfk); + rfkill_destroy(rfk); + } +} +EXPORT_SYMBOL(nfc_unregister_rfkill); + +/** + * nfc_remove_device - remove a nfc device in the nfc subsystem + * + * @dev: The nfc device to remove + */ +void nfc_remove_device(struct nfc_dev *dev) +{ if (dev->ops->check_presence) { timer_delete_sync(&dev->check_pres_timer); cancel_work_sync(&dev->check_pres_work); @@ -1183,6 +1197,18 @@ void nfc_unregister_device(struct nfc_dev *dev) device_del(&dev->dev); mutex_unlock(&nfc_devlist_mutex); } +EXPORT_SYMBOL(nfc_remove_device); + +/** + * nfc_unregister_device - unregister a nfc device in the nfc subsystem + * + * @dev: The nfc device to unregister + */ +void nfc_unregister_device(struct nfc_dev *dev) +{ + nfc_unregister_rfkill(dev); + nfc_remove_device(dev); +} EXPORT_SYMBOL(nfc_unregister_device); static int __init nfc_init(void) diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index e2680a3bef79..b652323bc2c1 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -778,8 +778,23 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, if (likely(frag_len > 0)) skb_put_data(pdu, msg_ptr, frag_len); + spin_lock(&local->tx_queue.lock); + + if (list_empty(&local->list)) { + spin_unlock(&local->tx_queue.lock); + + kfree_skb(pdu); + + len -= remaining_len; + if (len == 0) + len = -ENXIO; + break; + } + /* No need to check for the peer RW for UI frames */ - skb_queue_tail(&local->tx_queue, pdu); + __skb_queue_tail(&local->tx_queue, pdu); + + spin_unlock(&local->tx_queue.lock); remaining_len -= frag_len; msg_ptr += frag_len; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index beeb3b4d28ca..444a3774c8e8 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -316,7 +316,9 @@ static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev) spin_lock(&llcp_devices_lock); list_for_each_entry_safe(local, tmp, &llcp_devices, list) if (local->dev == dev) { - list_del(&local->list); + spin_lock(&local->tx_queue.lock); + list_del_init(&local->list); + spin_unlock(&local->tx_queue.lock); spin_unlock(&llcp_devices_lock); return local; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index fc921cd2cdff..e419e020a70a 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1303,6 +1303,8 @@ void nci_unregister_device(struct nci_dev *ndev) { struct nci_conn_info *conn_info, *n; + nfc_unregister_rfkill(ndev->nfc_dev); + /* This set_bit is not protected with specialized barrier, * However, it is fine because the mutex_lock(&ndev->req_lock); * in nci_close_device() will help to emit one. @@ -1320,7 +1322,7 @@ void nci_unregister_device(struct nci_dev *ndev) /* conn_info is allocated with devm_kzalloc */ } - nfc_unregister_device(ndev->nfc_dev); + nfc_remove_device(ndev->nfc_dev); } EXPORT_SYMBOL(nci_unregister_device); diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 91a11067e458..6574f9bcdc02 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -160,10 +160,19 @@ void ovs_netdev_detach_dev(struct vport *vport) static void netdev_destroy(struct vport *vport) { - rtnl_lock(); - if (netif_is_ovs_port(vport->dev)) - ovs_netdev_detach_dev(vport); - rtnl_unlock(); + /* When called from ovs_db_notify_wq() after a dp_device_event(), the + * port has already been detached, so we can avoid taking the RTNL by + * checking this first. + */ + if (netif_is_ovs_port(vport->dev)) { + rtnl_lock(); + /* Check again while holding the lock to ensure we don't race + * with the netdev notifier and detach twice. + */ + if (netif_is_ovs_port(vport->dev)) + ovs_netdev_detach_dev(vport); + rtnl_unlock(); + } call_rcu(&vport->rcu, vport_netdev_free); } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 6bbbc16ab778..f0ce8ce1dce0 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -310,22 +310,23 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) */ int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb) { + u64 tx_success = 0, tx_fail = 0; struct nlattr *nla; int i; - __u64 tx_success = 0; - __u64 tx_fail = 0; - for_each_possible_cpu(i) { const struct vport_upcall_stats_percpu *stats; + u64 n_success, n_fail; unsigned int start; stats = per_cpu_ptr(vport->upcall_stats, i); do { start = u64_stats_fetch_begin(&stats->syncp); - tx_success += u64_stats_read(&stats->n_success); - tx_fail += u64_stats_read(&stats->n_fail); + n_success = u64_stats_read(&stats->n_success); + n_fail = u64_stats_read(&stats->n_fail); } while (u64_stats_fetch_retry(&stats->syncp, start)); + tx_success += n_success; + tx_fail += n_fail; } nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_UPCALL_STATS); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index fd67494f2815..c0f5a515a8ce 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -205,7 +205,7 @@ start: spin_unlock_bh(&rose_list_lock); for (i = 0; i < cnt; i++) { - sk = array[cnt]; + sk = array[i]; rose = rose_sk(sk); lock_sock(sk); spin_lock_bh(&rose_list_lock); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5b7342d43486..36d6ca0d1089 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -387,7 +387,7 @@ struct rxrpc_peer { struct rb_root service_conns; /* Service connections */ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ unsigned long app_data; /* Application data (e.g. afs_server) */ - time64_t last_tx_at; /* Last time packet sent here */ + unsigned int last_tx_at; /* Last time packet sent here (time64_t LSW) */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ int debug_id; /* debug ID for printks */ @@ -1379,6 +1379,13 @@ void rxrpc_peer_keepalive_worker(struct work_struct *); void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t acked_serial, bool sendmsg_fail); +/* Update the last transmission time on a peer for keepalive purposes. */ +static inline void rxrpc_peer_mark_tx(struct rxrpc_peer *peer) +{ + /* To avoid tearing on 32-bit systems, we only keep the LSW. */ + WRITE_ONCE(peer->last_tx_at, ktime_get_seconds()); +} + /* * peer_object.c */ diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 232b6986da83..98ad9b51ca2c 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -194,7 +194,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, } ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret < 0) trace_rxrpc_tx_fail(chan->call_debug_id, serial, ret, rxrpc_tx_point_call_final_resend); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 8b5903b6e481..d70db367e358 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -275,7 +275,7 @@ static void rxrpc_send_ack_packet(struct rxrpc_call *call, int nr_kv, size_t len rxrpc_local_dont_fragment(conn->local, why == rxrpc_propose_ack_ping_for_mtu_probe); ret = do_udp_sendmsg(conn->local->socket, &msg, len); - call->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(call->peer); if (ret < 0) { trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); @@ -411,7 +411,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt)); ret = do_udp_sendmsg(conn->local->socket, &msg, sizeof(pkt)); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_abort); @@ -698,7 +698,7 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req ret = 0; trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags, rxrpc_txdata_inject_loss); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); goto done; } } @@ -711,7 +711,7 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req */ rxrpc_inc_stat(call->rxnet, stat_tx_data_send); ret = do_udp_sendmsg(conn->local->socket, &msg, len); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret == -EMSGSIZE) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_msgsize); @@ -797,7 +797,7 @@ void rxrpc_send_conn_abort(struct rxrpc_connection *conn) trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); } /* @@ -917,7 +917,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) trace_rxrpc_tx_packet(peer->debug_id, &whdr, rxrpc_tx_point_version_keepalive); - peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(peer); _leave(""); } @@ -973,7 +973,7 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response if (ret < 0) goto fail; - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); return; fail: diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 7f4729234957..9d02448ac062 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -238,6 +238,21 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, struct sk_buff *skb, } /* + * Reconstruct the last transmission time. The difference calculated should be + * valid provided no more than ~68 years elapsed since the last transmission. + */ +static time64_t rxrpc_peer_get_tx_mark(const struct rxrpc_peer *peer, time64_t base) +{ + s32 last_tx_at = READ_ONCE(peer->last_tx_at); + s32 base_lsw = base; + s32 diff = last_tx_at - base_lsw; + + diff = clamp(diff, -RXRPC_KEEPALIVE_TIME, RXRPC_KEEPALIVE_TIME); + + return diff + base; +} + +/* * Perform keep-alive pings. */ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, @@ -265,7 +280,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_unlock_bh(&rxnet->peer_hash_lock); if (use) { - keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; + keepalive_at = rxrpc_peer_get_tx_mark(peer, base) + RXRPC_KEEPALIVE_TIME; slot = keepalive_at - base; _debug("%02x peer %u t=%d {%pISp}", cursor, peer->debug_id, slot, &peer->srx.transport); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index d803562ca0ac..59292f7f9205 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -296,13 +296,13 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) now = ktime_get_seconds(); seq_printf(seq, - "UDP %-47.47s %-47.47s %3u %4u %5u %6llus %8d %8d\n", + "UDP %-47.47s %-47.47s %3u %4u %5u %6ds %8d %8d\n", lbuff, rbuff, refcount_read(&peer->ref), peer->cong_ssthresh, peer->max_data, - now - peer->last_tx_at, + (s32)now - (s32)READ_ONCE(peer->last_tx_at), READ_ONCE(peer->recent_srtt_us), READ_ONCE(peer->recent_rto_us)); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 7fa7e77f6bb9..e1f7513a46db 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -518,7 +518,8 @@ try_again: if (rxrpc_call_has_failed(call)) goto call_failed; - if (!skb_queue_empty(&call->recvmsg_queue)) + if (!(flags & MSG_PEEK) && + !skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); goto not_yet_complete; @@ -549,11 +550,21 @@ error_unlock_call: error_requeue_call: if (!(flags & MSG_PEEK)) { spin_lock_irq(&rx->recvmsg_lock); - list_add(&call->recvmsg_link, &rx->recvmsg_q); - spin_unlock_irq(&rx->recvmsg_lock); + if (list_empty(&call->recvmsg_link)) { + list_add(&call->recvmsg_link, &rx->recvmsg_q); + rxrpc_see_call(call, rxrpc_call_see_recvmsg_requeue); + spin_unlock_irq(&rx->recvmsg_lock); + } else if (list_is_first(&call->recvmsg_link, &rx->recvmsg_q)) { + spin_unlock_irq(&rx->recvmsg_lock); + rxrpc_put_call(call, rxrpc_call_see_recvmsg_requeue_first); + } else { + list_move(&call->recvmsg_link, &rx->recvmsg_q); + spin_unlock_irq(&rx->recvmsg_lock); + rxrpc_put_call(call, rxrpc_call_see_recvmsg_requeue_move); + } trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0); } else { - rxrpc_put_call(call, rxrpc_call_put_recvmsg); + rxrpc_put_call(call, rxrpc_call_put_recvmsg_peek_nowait); } error_no_call: release_sock(&rx->sk); diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index dce5a3d8a964..43cbf9efd89f 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -678,7 +678,7 @@ static int rxgk_issue_challenge(struct rxrpc_connection *conn) ret = do_udp_sendmsg(conn->local->socket, &msg, len); if (ret > 0) - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); __free_page(page); if (ret < 0) { diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 3657c0661cdc..a756855a0a62 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -694,7 +694,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) return -EAGAIN; } - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_rxkad_challenge); _leave(" = 0"); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index ff6be5cfe2b0..e1ab0faeb811 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -940,6 +940,8 @@ void tcf_idrinfo_destroy(const struct tc_action_ops *ops, int ret; idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p)) + continue; if (tc_act_in_hw(p) && !mutex_taken) { rtnl_lock(); mutex_taken = true; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 1dfdda6c2d4c..8e8f6af731d5 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -821,6 +821,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { +drop: qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -829,6 +830,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, skb_push(skb, skb->dev->hard_header_len); ife_meta = ife_encode(skb, metalen); + if (!ife_meta) + goto drop; spin_lock(&ife->tcf_lock); @@ -844,8 +847,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, if (err < 0) { /* too corrupt to keep around if overwritten */ spin_unlock(&ife->tcf_lock); - qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); - return TC_ACT_SHOT; + goto drop; } skboff += err; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 91c96cc625bd..05e0b14b5773 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -266,11 +266,22 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, goto err_cant_do; } + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); + + at_ingress = skb_at_tc_ingress(skb); + if (dev == skb->dev && want_ingress == at_ingress) { + pr_notice_once("tc mirred: Loop (%s:%s --> %s:%s)\n", + netdev_name(skb->dev), + at_ingress ? "ingress" : "egress", + netdev_name(dev), + want_ingress ? "ingress" : "egress"); + goto err_cant_do; + } + /* we could easily avoid the clone only if called by ingress and clsact; * since we can't easily detect the clsact caller, skip clone only for * ingress - that covers the TC S/W datapath. */ - at_ingress = skb_at_tc_ingress(skb); dont_clone = skb_at_tc_ingress(skb) && is_redirect && tcf_mirred_can_reinsert(retval); if (!dont_clone) { @@ -279,17 +290,6 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, goto err_cant_do; } - want_ingress = tcf_mirred_act_wants_ingress(m_eaction); - - if (dev == skb->dev && want_ingress == at_ingress) { - pr_notice_once("tc mirred: Loop (%s:%s --> %s:%s)\n", - netdev_name(skb->dev), - at_ingress ? "ingress" : "egress", - netdev_name(dev), - want_ingress ? "ingress" : "egress"); - goto err_cant_do; - } - /* All mirred/redirected skbs should clear previous ct info */ nf_reset_ct(skb_to_send); if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index d920f57dc6d7..e7778413e72f 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -373,7 +373,7 @@ static void qfq_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) /* Deschedule class and remove it from its parent aggregate. */ static void qfq_deact_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) { - if (cl->qdisc->q.qlen > 0) /* class is active */ + if (cl_is_active(cl)) /* class is active */ qfq_deactivate_class(q, cl); qfq_rm_from_agg(q, cl); @@ -529,8 +529,10 @@ set_change_agg: return 0; destroy_class: - qdisc_put(cl->qdisc); - kfree(cl); + if (!existing) { + qdisc_put(cl->qdisc); + kfree(cl); + } return err; } @@ -1481,7 +1483,7 @@ static void qfq_reset_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { - if (cl->qdisc->q.qlen > 0) + if (cl_is_active(cl)) qfq_deactivate_class(q, cl); qdisc_reset(cl->qdisc); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 8badec6d82a2..6e4bdaa876ed 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -178,6 +178,11 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt, if (m->dev == dev) return -ELOOP; + if (sch->parent != TC_H_ROOT) { + NL_SET_ERR_MSG_MOD(extack, "teql can only be used as root"); + return -EOPNOTSUPP; + } + q->m = m; skb_queue_head_init(&q->q); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 3755ba079d07..7b823d759141 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -603,6 +603,11 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_PEER_INIT, SCTP_PEER_INIT(initchunk)); + /* SCTP-AUTH: generate the association shared keys so that + * we can potentially sign the COOKIE-ECHO. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); + /* Reset init error count upon receipt of INIT-ACK. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); @@ -617,11 +622,6 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_COOKIE_ECHOED)); - /* SCTP-AUTH: generate the association shared keys so that - * we can potentially sign the COOKIE-ECHO. - */ - sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); - /* 5.1 C) "A" shall then send the State Cookie received in the * INIT ACK chunk in a COOKIE ECHO chunk, ... */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 55cdebfa0da0..d0511225799b 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3086,12 +3086,15 @@ unlock: mutex_unlock(&u->iolock); if (msg) { + bool do_cmsg = READ_ONCE(u->recvmsg_inq); + scm_recv_unix(sock, msg, &scm, flags); - if (READ_ONCE(u->recvmsg_inq) || msg->msg_get_inq) { + if ((do_cmsg | msg->msg_get_inq) && (copied ?: err) >= 0) { msg->msg_inq = READ_ONCE(u->inq_len); - put_cmsg(msg, SOL_SOCKET, SCM_INQ, - sizeof(msg->msg_inq), &msg->msg_inq); + if (do_cmsg) + put_cmsg(msg, SOL_SOCKET, SCM_INQ, + sizeof(msg->msg_inq), &msg->msg_inq); } } else { scm_destroy(&scm); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index adcba1b7bf74..a3505a4dcee0 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1787,6 +1787,10 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, } else { newsock->state = SS_CONNECTED; sock_graft(connected, newsock); + + set_bit(SOCK_CUSTOM_SOCKOPT, + &connected->sk_socket->flags); + if (vsock_msgzerocopy_allow(vconnected->transport)) set_bit(SOCK_SUPPORT_ZC, &connected->sk_socket->flags); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index dcc8a1d5851e..d3e26025ef58 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -28,6 +28,7 @@ static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, bool cancel_timeout); +static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs); static const struct virtio_transport * virtio_transport_get_ops(struct vsock_sock *vsk) @@ -499,9 +500,7 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) return 0; spin_lock_bh(&vvs->tx_lock); - ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); - if (ret > credit) - ret = credit; + ret = min_t(u32, credit, virtio_transport_has_space(vvs)); vvs->tx_cnt += ret; vvs->bytes_unsent += ret; spin_unlock_bh(&vvs->tx_lock); @@ -822,6 +821,15 @@ virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); +static u32 virtio_transport_tx_buf_size(struct virtio_vsock_sock *vvs) +{ + /* The peer advertises its receive buffer via peer_buf_alloc, but we + * cap it to our local buf_alloc so a remote peer cannot force us to + * queue more data than our own buffer configuration allows. + */ + return min(vvs->peer_buf_alloc, vvs->buf_alloc); +} + int virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, struct msghdr *msg, @@ -831,7 +839,7 @@ virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, spin_lock_bh(&vvs->tx_lock); - if (len > vvs->peer_buf_alloc) { + if (len > virtio_transport_tx_buf_size(vvs)) { spin_unlock_bh(&vvs->tx_lock); return -EMSGSIZE; } @@ -877,12 +885,16 @@ u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); -static s64 virtio_transport_has_space(struct vsock_sock *vsk) +static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs) { - struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; - bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + /* Use s64 arithmetic so if the peer shrinks peer_buf_alloc while + * we have bytes in flight (tx_cnt - peer_fwd_cnt), the subtraction + * does not underflow. + */ + bytes = (s64)virtio_transport_tx_buf_size(vvs) - + (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; @@ -895,7 +907,7 @@ s64 virtio_transport_stream_has_space(struct vsock_sock *vsk) s64 bytes; spin_lock_bh(&vvs->tx_lock); - bytes = virtio_transport_has_space(vsk); + bytes = virtio_transport_has_space(vvs); spin_unlock_bh(&vvs->tx_lock); return bytes; @@ -1359,9 +1371,11 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small - * payload. + * payload. Skip non-linear (e.g. zerocopy) skbs; these carry payload + * in skb_shinfo. */ - if (len <= GOOD_COPY_LEN && !skb_queue_empty(&vvs->rx_queue)) { + if (len <= GOOD_COPY_LEN && !skb_queue_empty(&vvs->rx_queue) && + !skb_is_nonlinear(skb)) { struct virtio_vsock_hdr *last_hdr; struct sk_buff *last_skb; @@ -1490,7 +1504,7 @@ static bool virtio_transport_space_update(struct sock *sk, spin_lock_bh(&vvs->tx_lock); vvs->peer_buf_alloc = le32_to_cpu(hdr->buf_alloc); vvs->peer_fwd_cnt = le32_to_cpu(hdr->fwd_cnt); - space_available = virtio_transport_has_space(vsk); + space_available = virtio_transport_has_space(vvs); spin_unlock_bh(&vvs->tx_lock); return space_available; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c961cd42a832..03efd45c007f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12241,9 +12241,6 @@ static int nl80211_process_links(struct cfg80211_registered_device *rdev, return -EINVAL; } } - - links[link_id].disabled = - nla_get_flag(attrs[NL80211_ATTR_MLO_LINK_DISABLED]); } return 0; @@ -12423,13 +12420,6 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } - if (req.links[req.link_id].disabled) { - GENL_SET_ERR_MSG(info, - "cannot have assoc link disabled"); - err = -EINVAL; - goto free; - } - if (info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]) req.ext_mld_capa_ops = nla_get_u16(info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 3a028ff287fb..4e629ca305bc 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -910,7 +910,7 @@ void __cfg80211_connect_result(struct net_device *dev, ssid_len = min(ssid->datalen, IEEE80211_MAX_SSID_LEN); memcpy(wdev->u.client.ssid, ssid->data, ssid_len); - wdev->u.client.ssid_len = ssid->datalen; + wdev->u.client.ssid_len = ssid_len; break; } rcu_read_unlock(); diff --git a/net/wireless/util.c b/net/wireless/util.c index 27e8a2f52f04..4f581aed45b7 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1561,12 +1561,14 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); - result = tmp; /* and take NSS, DCM into account */ - result = (result * rate->nss) / 8; + tmp *= rate->nss; + do_div(tmp, 8); if (rate->he_dcm) - result /= 2; + do_div(tmp, 2); + + result = tmp; return result / 10000; } diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index c32a7c6903d5..7b8e94214b07 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -1101,6 +1101,10 @@ static int compat_standard_call(struct net_device *dev, return ioctl_standard_call(dev, iwr, cmd, info, handler); iwp_compat = (struct compat_iw_point *) &iwr->u.data; + + /* struct iw_point has a 32bit hole on 64bit arches. */ + memset(&iwp, 0, sizeof(iwp)); + iwp.pointer = compat_ptr(iwp_compat->pointer); iwp.length = iwp_compat->length; iwp.flags = iwp_compat->flags; diff --git a/net/wireless/wext-priv.c b/net/wireless/wext-priv.c index 674d426a9d24..37d1147019c2 100644 --- a/net/wireless/wext-priv.c +++ b/net/wireless/wext-priv.c @@ -228,6 +228,10 @@ int compat_private_call(struct net_device *dev, struct iwreq *iwr, struct iw_point iwp; iwp_compat = (struct compat_iw_point *) &iwr->u.data; + + /* struct iw_point has a 32bit hole on 64bit arches. */ + memset(&iwp, 0, sizeof(iwp)); + iwp.pointer = compat_ptr(iwp_compat->pointer); iwp.length = iwp_compat->length; iwp.flags = iwp_compat->flags; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 9e14e453b55c..98b362d51836 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -3151,6 +3151,7 @@ int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) int err; if (family == AF_INET && + (!x->dir || x->dir == XFRM_SA_DIR_OUT) && READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; diff --git a/rust/helpers/bitops.c b/rust/helpers/bitops.c index 5d0861d29d3f..e79ef9e6d98f 100644 --- a/rust/helpers/bitops.c +++ b/rust/helpers/bitops.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> +#include <linux/find.h> void rust_helper___set_bit(unsigned long nr, unsigned long *addr) { @@ -21,3 +22,44 @@ void rust_helper_clear_bit(unsigned long nr, volatile unsigned long *addr) { clear_bit(nr, addr); } + +/* + * The rust_helper_ prefix is intentionally omitted below so that the + * declarations in include/linux/find.h are compatible with these helpers. + * + * Note that the below #ifdefs mean that the helper is only created if C does + * not provide a definition. + */ +#ifdef find_first_zero_bit +__rust_helper +unsigned long _find_first_zero_bit(const unsigned long *p, unsigned long size) +{ + return find_first_zero_bit(p, size); +} +#endif /* find_first_zero_bit */ + +#ifdef find_next_zero_bit +__rust_helper +unsigned long _find_next_zero_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + return find_next_zero_bit(addr, size, offset); +} +#endif /* find_next_zero_bit */ + +#ifdef find_first_bit +__rust_helper +unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) +{ + return find_first_bit(addr, size); +} +#endif /* find_first_bit */ + +#ifdef find_next_bit +__rust_helper +unsigned long _find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + return find_next_bit(addr, size, offset); +} +#endif /* find_next_bit */ diff --git a/rust/kernel/auxiliary.rs b/rust/kernel/auxiliary.rs index 56f3c180e8f6..be76f11aecb7 100644 --- a/rust/kernel/auxiliary.rs +++ b/rust/kernel/auxiliary.rs @@ -23,13 +23,22 @@ use core::{ /// An adapter for the registration of auxiliary drivers. pub struct Adapter<T: Driver>(T); -// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if +// SAFETY: +// - `bindings::auxiliary_driver` is a C type declared as `repr(C)`. +// - `T` is the type of the driver's device private data. +// - `struct auxiliary_driver` embeds a `struct device_driver`. +// - `DEVICE_DRIVER_OFFSET` is the correct byte offset to the embedded `struct device_driver`. +unsafe impl<T: Driver + 'static> driver::DriverLayout for Adapter<T> { + type DriverType = bindings::auxiliary_driver; + type DriverData = T; + const DEVICE_DRIVER_OFFSET: usize = core::mem::offset_of!(Self::DriverType, driver); +} + +// SAFETY: A call to `unregister` for a given instance of `DriverType` is guaranteed to be valid if // a preceding call to `register` has been successful. unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { - type RegType = bindings::auxiliary_driver; - unsafe fn register( - adrv: &Opaque<Self::RegType>, + adrv: &Opaque<Self::DriverType>, name: &'static CStr, module: &'static ThisModule, ) -> Result { @@ -41,14 +50,14 @@ unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { (*adrv.get()).id_table = T::ID_TABLE.as_ptr(); } - // SAFETY: `adrv` is guaranteed to be a valid `RegType`. + // SAFETY: `adrv` is guaranteed to be a valid `DriverType`. to_result(unsafe { bindings::__auxiliary_driver_register(adrv.get(), module.0, name.as_char_ptr()) }) } - unsafe fn unregister(adrv: &Opaque<Self::RegType>) { - // SAFETY: `adrv` is guaranteed to be a valid `RegType`. + unsafe fn unregister(adrv: &Opaque<Self::DriverType>) { + // SAFETY: `adrv` is guaranteed to be a valid `DriverType`. unsafe { bindings::auxiliary_driver_unregister(adrv.get()) } } } @@ -87,7 +96,9 @@ impl<T: Driver + 'static> Adapter<T> { // SAFETY: `remove_callback` is only ever called after a successful call to // `probe_callback`, hence it's guaranteed that `Device::set_drvdata()` has been called // and stored a `Pin<KBox<T>>`. - drop(unsafe { adev.as_ref().drvdata_obtain::<T>() }); + let data = unsafe { adev.as_ref().drvdata_borrow::<T>() }; + + T::unbind(adev, data); } } @@ -187,6 +198,20 @@ pub trait Driver { /// /// Called when an auxiliary device is matches a corresponding driver. fn probe(dev: &Device<device::Core>, id_info: &Self::IdInfo) -> impl PinInit<Self, Error>; + + /// Auxiliary driver unbind. + /// + /// Called when a [`Device`] is unbound from its bound [`Driver`]. Implementing this callback + /// is optional. + /// + /// This callback serves as a place for drivers to perform teardown operations that require a + /// `&Device<Core>` or `&Device<Bound>` reference. For instance, drivers may try to perform I/O + /// operations to gracefully tear down the device. + /// + /// Otherwise, release operations for driver resources should be performed in `Self::drop`. + fn unbind(dev: &Device<device::Core>, this: Pin<&Self>) { + let _ = (dev, this); + } } /// The auxiliary device representation. diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs index c79be2e2bfe3..031720bf5d8c 100644 --- a/rust/kernel/device.rs +++ b/rust/kernel/device.rs @@ -14,7 +14,6 @@ use core::{any::TypeId, marker::PhantomData, ptr}; #[cfg(CONFIG_PRINTK)] use crate::c_str; -use crate::str::CStrExt as _; pub mod property; @@ -67,8 +66,9 @@ static_assert!(core::mem::size_of::<bindings::driver_type>() >= core::mem::size_ /// /// # Implementing Bus Devices /// -/// This section provides a guideline to implement bus specific devices, such as [`pci::Device`] or -/// [`platform::Device`]. +/// This section provides a guideline to implement bus specific devices, such as: +#[cfg_attr(CONFIG_PCI, doc = "* [`pci::Device`](kernel::pci::Device)")] +/// * [`platform::Device`] /// /// A bus specific device should be defined as follows. /// @@ -160,7 +160,6 @@ static_assert!(core::mem::size_of::<bindings::driver_type>() >= core::mem::size_ /// /// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted /// [`impl_device_context_deref`]: kernel::impl_device_context_deref -/// [`pci::Device`]: kernel::pci::Device /// [`platform::Device`]: kernel::platform::Device #[repr(transparent)] pub struct Device<Ctx: DeviceContext = Normal>(Opaque<bindings::device>, PhantomData<Ctx>); @@ -233,30 +232,32 @@ impl Device<CoreInternal> { /// /// # Safety /// - /// - Must only be called once after a preceding call to [`Device::set_drvdata`]. /// - The type `T` must match the type of the `ForeignOwnable` previously stored by /// [`Device::set_drvdata`]. - pub unsafe fn drvdata_obtain<T: 'static>(&self) -> Pin<KBox<T>> { + pub(crate) unsafe fn drvdata_obtain<T: 'static>(&self) -> Option<Pin<KBox<T>>> { // SAFETY: By the type invariants, `self.as_raw()` is a valid pointer to a `struct device`. let ptr = unsafe { bindings::dev_get_drvdata(self.as_raw()) }; // SAFETY: By the type invariants, `self.as_raw()` is a valid pointer to a `struct device`. unsafe { bindings::dev_set_drvdata(self.as_raw(), core::ptr::null_mut()) }; + if ptr.is_null() { + return None; + } + // SAFETY: - // - By the safety requirements of this function, `ptr` comes from a previous call to - // `into_foreign()`. + // - If `ptr` is not NULL, it comes from a previous call to `into_foreign()`. // - `dev_get_drvdata()` guarantees to return the same pointer given to `dev_set_drvdata()` // in `into_foreign()`. - unsafe { Pin::<KBox<T>>::from_foreign(ptr.cast()) } + Some(unsafe { Pin::<KBox<T>>::from_foreign(ptr.cast()) }) } /// Borrow the driver's private data bound to this [`Device`]. /// /// # Safety /// - /// - Must only be called after a preceding call to [`Device::set_drvdata`] and before - /// [`Device::drvdata_obtain`]. + /// - Must only be called after a preceding call to [`Device::set_drvdata`] and before the + /// device is fully unbound. /// - The type `T` must match the type of the `ForeignOwnable` previously stored by /// [`Device::set_drvdata`]. pub unsafe fn drvdata_borrow<T: 'static>(&self) -> Pin<&T> { @@ -272,7 +273,7 @@ impl Device<Bound> { /// # Safety /// /// - Must only be called after a preceding call to [`Device::set_drvdata`] and before - /// [`Device::drvdata_obtain`]. + /// the device is fully unbound. /// - The type `T` must match the type of the `ForeignOwnable` previously stored by /// [`Device::set_drvdata`]. unsafe fn drvdata_unchecked<T: 'static>(&self) -> Pin<&T> { @@ -321,7 +322,7 @@ impl Device<Bound> { // SAFETY: // - The above check of `dev_get_drvdata()` guarantees that we are called after - // `set_drvdata()` and before `drvdata_obtain()`. + // `set_drvdata()`. // - We've just checked that the type of the driver's private data is in fact `T`. Ok(unsafe { self.drvdata_unchecked() }) } diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs index 62c42da12e9d..8e9721446014 100644 --- a/rust/kernel/device_id.rs +++ b/rust/kernel/device_id.rs @@ -15,7 +15,7 @@ use core::mem::MaybeUninit; /// # Safety /// /// Implementers must ensure that `Self` is layout-compatible with [`RawDeviceId::RawType`]; -/// i.e. it's safe to transmute to `RawDeviceId`. +/// i.e. it's safe to transmute to `RawType`. /// /// This requirement is needed so `IdArray::new` can convert `Self` to `RawType` when building /// the ID table. diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs index 84d3c67269e8..acc65b1e0f24 100644 --- a/rust/kernel/dma.rs +++ b/rust/kernel/dma.rs @@ -27,8 +27,9 @@ pub type DmaAddress = bindings::dma_addr_t; /// Trait to be implemented by DMA capable bus devices. /// /// The [`dma::Device`](Device) trait should be implemented by bus specific device representations, -/// where the underlying bus is DMA capable, such as [`pci::Device`](::kernel::pci::Device) or -/// [`platform::Device`](::kernel::platform::Device). +/// where the underlying bus is DMA capable, such as: +#[cfg_attr(CONFIG_PCI, doc = "* [`pci::Device`](kernel::pci::Device)")] +/// * [`platform::Device`](::kernel::platform::Device) pub trait Device: AsRef<device::Device<Core>> { /// Set up the device's DMA streaming addressing capabilities. /// @@ -532,8 +533,6 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { /// /// # Safety /// - /// * Callers must ensure that the device does not read/write to/from memory while the returned - /// slice is live. /// * Callers must ensure that this call does not race with a read or write to the same region /// that overlaps with this write. /// diff --git a/rust/kernel/driver.rs b/rust/kernel/driver.rs index 9beae2e3d57e..bee3ae21a27b 100644 --- a/rust/kernel/driver.rs +++ b/rust/kernel/driver.rs @@ -33,7 +33,14 @@ //! } //! ``` //! -//! For specific examples see [`auxiliary::Driver`], [`pci::Driver`] and [`platform::Driver`]. +//! For specific examples see: +//! +//! * [`platform::Driver`](kernel::platform::Driver) +#" +)] +#")] //! //! The `probe()` callback should return a `impl PinInit<Self, Error>`, i.e. the driver's private //! data. The bus abstraction should store the pointer in the corresponding bus device. The generic @@ -79,7 +86,6 @@ //! //! For this purpose the generic infrastructure in [`device_id`] should be used. //! -//! [`auxiliary::Driver`]: kernel::auxiliary::Driver //! [`Core`]: device::Core //! [`Device`]: device::Device //! [`Device<Core>`]: device::Device<device::Core> @@ -87,31 +93,49 @@ //! [`DeviceContext`]: device::DeviceContext //! [`device_id`]: kernel::device_id //! [`module_driver`]: kernel::module_driver -//! [`pci::Driver`]: kernel::pci::Driver -//! [`platform::Driver`]: kernel::platform::Driver use crate::error::{Error, Result}; use crate::{acpi, device, of, str::CStr, try_pin_init, types::Opaque, ThisModule}; use core::pin::Pin; use pin_init::{pin_data, pinned_drop, PinInit}; +/// Trait describing the layout of a specific device driver. +/// +/// This trait describes the layout of a specific driver structure, such as `struct pci_driver` or +/// `struct platform_driver`. +/// +/// # Safety +/// +/// Implementors must guarantee that: +/// - `DriverType` is `repr(C)`, +/// - `DriverData` is the type of the driver's device private data. +/// - `DriverType` embeds a valid `struct device_driver` at byte offset `DEVICE_DRIVER_OFFSET`. +pub unsafe trait DriverLayout { + /// The specific driver type embedding a `struct device_driver`. + type DriverType: Default; + + /// The type of the driver's device private data. + type DriverData; + + /// Byte offset of the embedded `struct device_driver` within `DriverType`. + /// + /// This must correspond exactly to the location of the embedded `struct device_driver` field. + const DEVICE_DRIVER_OFFSET: usize; +} + /// The [`RegistrationOps`] trait serves as generic interface for subsystems (e.g., PCI, Platform, /// Amba, etc.) to provide the corresponding subsystem specific implementation to register / -/// unregister a driver of the particular type (`RegType`). +/// unregister a driver of the particular type (`DriverType`). /// -/// For instance, the PCI subsystem would set `RegType` to `bindings::pci_driver` and call +/// For instance, the PCI subsystem would set `DriverType` to `bindings::pci_driver` and call /// `bindings::__pci_register_driver` from `RegistrationOps::register` and /// `bindings::pci_unregister_driver` from `RegistrationOps::unregister`. /// /// # Safety /// -/// A call to [`RegistrationOps::unregister`] for a given instance of `RegType` is only valid if a -/// preceding call to [`RegistrationOps::register`] has been successful. -pub unsafe trait RegistrationOps { - /// The type that holds information about the registration. This is typically a struct defined - /// by the C portion of the kernel. - type RegType: Default; - +/// A call to [`RegistrationOps::unregister`] for a given instance of `DriverType` is only valid if +/// a preceding call to [`RegistrationOps::register`] has been successful. +pub unsafe trait RegistrationOps: DriverLayout { /// Registers a driver. /// /// # Safety @@ -119,7 +143,7 @@ pub unsafe trait RegistrationOps { /// On success, `reg` must remain pinned and valid until the matching call to /// [`RegistrationOps::unregister`]. unsafe fn register( - reg: &Opaque<Self::RegType>, + reg: &Opaque<Self::DriverType>, name: &'static CStr, module: &'static ThisModule, ) -> Result; @@ -130,7 +154,7 @@ pub unsafe trait RegistrationOps { /// /// Must only be called after a preceding successful call to [`RegistrationOps::register`] for /// the same `reg`. - unsafe fn unregister(reg: &Opaque<Self::RegType>); + unsafe fn unregister(reg: &Opaque<Self::DriverType>); } /// A [`Registration`] is a generic type that represents the registration of some driver type (e.g. @@ -142,7 +166,7 @@ pub unsafe trait RegistrationOps { #[pin_data(PinnedDrop)] pub struct Registration<T: RegistrationOps> { #[pin] - reg: Opaque<T::RegType>, + reg: Opaque<T::DriverType>, } // SAFETY: `Registration` has no fields or methods accessible via `&Registration`, so it is safe to @@ -153,17 +177,51 @@ unsafe impl<T: RegistrationOps> Sync for Registration<T> {} // any thread, so `Registration` is `Send`. unsafe impl<T: RegistrationOps> Send for Registration<T> {} -impl<T: RegistrationOps> Registration<T> { +impl<T: RegistrationOps + 'static> Registration<T> { + extern "C" fn post_unbind_callback(dev: *mut bindings::device) { + // SAFETY: The driver core only ever calls the post unbind callback with a valid pointer to + // a `struct device`. + // + // INVARIANT: `dev` is valid for the duration of the `post_unbind_callback()`. + let dev = unsafe { &*dev.cast::<device::Device<device::CoreInternal>>() }; + + // `remove()` and all devres callbacks have been completed at this point, hence drop the + // driver's device private data. + // + // SAFETY: By the safety requirements of the `Driver` trait, `T::DriverData` is the + // driver's device private data type. + drop(unsafe { dev.drvdata_obtain::<T::DriverData>() }); + } + + /// Attach generic `struct device_driver` callbacks. + fn callbacks_attach(drv: &Opaque<T::DriverType>) { + let ptr = drv.get().cast::<u8>(); + + // SAFETY: + // - `drv.get()` yields a valid pointer to `Self::DriverType`. + // - Adding `DEVICE_DRIVER_OFFSET` yields the address of the embedded `struct device_driver` + // as guaranteed by the safety requirements of the `Driver` trait. + let base = unsafe { ptr.add(T::DEVICE_DRIVER_OFFSET) }; + + // CAST: `base` points to the offset of the embedded `struct device_driver`. + let base = base.cast::<bindings::device_driver>(); + + // SAFETY: It is safe to set the fields of `struct device_driver` on initialization. + unsafe { (*base).p_cb.post_unbind_rust = Some(Self::post_unbind_callback) }; + } + /// Creates a new instance of the registration object. pub fn new(name: &'static CStr, module: &'static ThisModule) -> impl PinInit<Self, Error> { try_pin_init!(Self { - reg <- Opaque::try_ffi_init(|ptr: *mut T::RegType| { + reg <- Opaque::try_ffi_init(|ptr: *mut T::DriverType| { // SAFETY: `try_ffi_init` guarantees that `ptr` is valid for write. - unsafe { ptr.write(T::RegType::default()) }; + unsafe { ptr.write(T::DriverType::default()) }; // SAFETY: `try_ffi_init` guarantees that `ptr` is valid for write, and it has // just been initialised above, so it's also valid for read. - let drv = unsafe { &*(ptr as *const Opaque<T::RegType>) }; + let drv = unsafe { &*(ptr as *const Opaque<T::DriverType>) }; + + Self::callbacks_attach(drv); // SAFETY: `drv` is guaranteed to be pinned until `T::unregister`. unsafe { T::register(drv, name, module) } diff --git a/rust/kernel/i2c.rs b/rust/kernel/i2c.rs index 491e6cc25cf4..39b0a9a207fd 100644 --- a/rust/kernel/i2c.rs +++ b/rust/kernel/i2c.rs @@ -92,13 +92,22 @@ macro_rules! i2c_device_table { /// An adapter for the registration of I2C drivers. pub struct Adapter<T: Driver>(T); -// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if +// SAFETY: +// - `bindings::i2c_driver` is a C type declared as `repr(C)`. +// - `T` is the type of the driver's device private data. +// - `struct i2c_driver` embeds a `struct device_driver`. +// - `DEVICE_DRIVER_OFFSET` is the correct byte offset to the embedded `struct device_driver`. +unsafe impl<T: Driver + 'static> driver::DriverLayout for Adapter<T> { + type DriverType = bindings::i2c_driver; + type DriverData = T; + const DEVICE_DRIVER_OFFSET: usize = core::mem::offset_of!(Self::DriverType, driver); +} + +// SAFETY: A call to `unregister` for a given instance of `DriverType` is guaranteed to be valid if // a preceding call to `register` has been successful. unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { - type RegType = bindings::i2c_driver; - unsafe fn register( - idrv: &Opaque<Self::RegType>, + idrv: &Opaque<Self::DriverType>, name: &'static CStr, module: &'static ThisModule, ) -> Result { @@ -133,12 +142,12 @@ unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { (*idrv.get()).driver.acpi_match_table = acpi_table; } - // SAFETY: `idrv` is guaranteed to be a valid `RegType`. + // SAFETY: `idrv` is guaranteed to be a valid `DriverType`. to_result(unsafe { bindings::i2c_register_driver(module.0, idrv.get()) }) } - unsafe fn unregister(idrv: &Opaque<Self::RegType>) { - // SAFETY: `idrv` is guaranteed to be a valid `RegType`. + unsafe fn unregister(idrv: &Opaque<Self::DriverType>) { + // SAFETY: `idrv` is guaranteed to be a valid `DriverType`. unsafe { bindings::i2c_del_driver(idrv.get()) } } } @@ -169,9 +178,9 @@ impl<T: Driver + 'static> Adapter<T> { // SAFETY: `remove_callback` is only ever called after a successful call to // `probe_callback`, hence it's guaranteed that `I2cClient::set_drvdata()` has been called // and stored a `Pin<KBox<T>>`. - let data = unsafe { idev.as_ref().drvdata_obtain::<T>() }; + let data = unsafe { idev.as_ref().drvdata_borrow::<T>() }; - T::unbind(idev, data.as_ref()); + T::unbind(idev, data); } extern "C" fn shutdown_callback(idev: *mut bindings::i2c_client) { @@ -181,9 +190,9 @@ impl<T: Driver + 'static> Adapter<T> { // SAFETY: `shutdown_callback` is only ever called after a successful call to // `probe_callback`, hence it's guaranteed that `Device::set_drvdata()` has been called // and stored a `Pin<KBox<T>>`. - let data = unsafe { idev.as_ref().drvdata_obtain::<T>() }; + let data = unsafe { idev.as_ref().drvdata_borrow::<T>() }; - T::shutdown(idev, data.as_ref()); + T::shutdown(idev, data); } /// The [`i2c::IdTable`] of the corresponding driver. diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index 98e8b84e68d1..b64b11f75a35 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -142,7 +142,8 @@ macro_rules! define_read { /// Bound checks are performed on compile time, hence if the offset is not known at compile /// time, the build will fail. $(#[$attr])* - #[inline] + // Always inline to optimize out error path of `io_addr_assert`. + #[inline(always)] pub fn $name(&self, offset: usize) -> $type_name { let addr = self.io_addr_assert::<$type_name>(offset); @@ -171,7 +172,8 @@ macro_rules! define_write { /// Bound checks are performed on compile time, hence if the offset is not known at compile /// time, the build will fail. $(#[$attr])* - #[inline] + // Always inline to optimize out error path of `io_addr_assert`. + #[inline(always)] pub fn $name(&self, value: $type_name, offset: usize) { let addr = self.io_addr_assert::<$type_name>(offset); @@ -239,7 +241,8 @@ impl<const SIZE: usize> Io<SIZE> { self.addr().checked_add(offset).ok_or(EINVAL) } - #[inline] + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] fn io_addr_assert<U>(&self, offset: usize) -> usize { build_assert!(Self::offset_valid::<U>(offset, SIZE)); diff --git a/rust/kernel/io/resource.rs b/rust/kernel/io/resource.rs index 56cfde97ce87..b7ac9faf141d 100644 --- a/rust/kernel/io/resource.rs +++ b/rust/kernel/io/resource.rs @@ -226,6 +226,8 @@ impl Flags { /// Resource represents a memory region that must be ioremaped using `ioremap_np`. pub const IORESOURCE_MEM_NONPOSTED: Flags = Flags::new(bindings::IORESOURCE_MEM_NONPOSTED); + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] const fn new(value: u32) -> Self { crate::build_assert!(value as u64 <= c_ulong::MAX as u64); Flags(value as c_ulong) diff --git a/rust/kernel/irq/flags.rs b/rust/kernel/irq/flags.rs index adfde96ec47c..d26e25af06ee 100644 --- a/rust/kernel/irq/flags.rs +++ b/rust/kernel/irq/flags.rs @@ -96,6 +96,8 @@ impl Flags { self.0 } + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] const fn new(value: u32) -> Self { build_assert!(value as u64 <= c_ulong::MAX as u64); Self(value as c_ulong) diff --git a/rust/kernel/maple_tree.rs b/rust/kernel/maple_tree.rs index e72eec56bf57..265d6396a78a 100644 --- a/rust/kernel/maple_tree.rs +++ b/rust/kernel/maple_tree.rs @@ -265,7 +265,16 @@ impl<T: ForeignOwnable> MapleTree<T> { loop { // This uses the raw accessor because we're destroying pointers without removing them // from the maple tree, which is only valid because this is the destructor. - let ptr = ma_state.mas_find_raw(usize::MAX); + // + // Take the rcu lock because mas_find_raw() requires that you hold either the spinlock + // or the rcu read lock. This is only really required if memory reclaim might + // reallocate entries in the tree, as we otherwise have exclusive access. That feature + // doesn't exist yet, so for now, taking the rcu lock only serves the purpose of + // silencing lockdep. + let ptr = { + let _rcu = kernel::sync::rcu::Guard::new(); + ma_state.mas_find_raw(usize::MAX) + }; if ptr.is_null() { break; } diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs index 82e128431f08..bea76ca9c3da 100644 --- a/rust/kernel/pci.rs +++ b/rust/kernel/pci.rs @@ -50,13 +50,22 @@ pub use self::irq::{ /// An adapter for the registration of PCI drivers. pub struct Adapter<T: Driver>(T); -// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if +// SAFETY: +// - `bindings::pci_driver` is a C type declared as `repr(C)`. +// - `T` is the type of the driver's device private data. +// - `struct pci_driver` embeds a `struct device_driver`. +// - `DEVICE_DRIVER_OFFSET` is the correct byte offset to the embedded `struct device_driver`. +unsafe impl<T: Driver + 'static> driver::DriverLayout for Adapter<T> { + type DriverType = bindings::pci_driver; + type DriverData = T; + const DEVICE_DRIVER_OFFSET: usize = core::mem::offset_of!(Self::DriverType, driver); +} + +// SAFETY: A call to `unregister` for a given instance of `DriverType` is guaranteed to be valid if // a preceding call to `register` has been successful. unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { - type RegType = bindings::pci_driver; - unsafe fn register( - pdrv: &Opaque<Self::RegType>, + pdrv: &Opaque<Self::DriverType>, name: &'static CStr, module: &'static ThisModule, ) -> Result { @@ -68,14 +77,14 @@ unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { (*pdrv.get()).id_table = T::ID_TABLE.as_ptr(); } - // SAFETY: `pdrv` is guaranteed to be a valid `RegType`. + // SAFETY: `pdrv` is guaranteed to be a valid `DriverType`. to_result(unsafe { bindings::__pci_register_driver(pdrv.get(), module.0, name.as_char_ptr()) }) } - unsafe fn unregister(pdrv: &Opaque<Self::RegType>) { - // SAFETY: `pdrv` is guaranteed to be a valid `RegType`. + unsafe fn unregister(pdrv: &Opaque<Self::DriverType>) { + // SAFETY: `pdrv` is guaranteed to be a valid `DriverType`. unsafe { bindings::pci_unregister_driver(pdrv.get()) } } } @@ -114,9 +123,9 @@ impl<T: Driver + 'static> Adapter<T> { // SAFETY: `remove_callback` is only ever called after a successful call to // `probe_callback`, hence it's guaranteed that `Device::set_drvdata()` has been called // and stored a `Pin<KBox<T>>`. - let data = unsafe { pdev.as_ref().drvdata_obtain::<T>() }; + let data = unsafe { pdev.as_ref().drvdata_borrow::<T>() }; - T::unbind(pdev, data.as_ref()); + T::unbind(pdev, data); } } diff --git a/rust/kernel/pci/io.rs b/rust/kernel/pci/io.rs index 0d55c3139b6f..82a4f1eba2f5 100644 --- a/rust/kernel/pci/io.rs +++ b/rust/kernel/pci/io.rs @@ -20,7 +20,7 @@ use core::ops::Deref; /// /// # Invariants /// -/// `Bar` always holds an `IoRaw` inststance that holds a valid pointer to the start of the I/O +/// `Bar` always holds an `IoRaw` instance that holds a valid pointer to the start of the I/O /// memory mapped PCI BAR and its size. pub struct Bar<const SIZE: usize = 0> { pdev: ARef<Device>, @@ -54,7 +54,7 @@ impl<const SIZE: usize> Bar<SIZE> { let ioptr: usize = unsafe { bindings::pci_iomap(pdev.as_raw(), num, 0) } as usize; if ioptr == 0 { // SAFETY: - // `pdev` valid by the invariants of `Device`. + // `pdev` is valid by the invariants of `Device`. // `num` is checked for validity by a previous call to `Device::resource_len`. unsafe { bindings::pci_release_region(pdev.as_raw(), num) }; return Err(ENOMEM); diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs index ed889f079cab..35a5813ffb33 100644 --- a/rust/kernel/platform.rs +++ b/rust/kernel/platform.rs @@ -26,13 +26,22 @@ use core::{ /// An adapter for the registration of platform drivers. pub struct Adapter<T: Driver>(T); -// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if +// SAFETY: +// - `bindings::platform_driver` is a C type declared as `repr(C)`. +// - `T` is the type of the driver's device private data. +// - `struct platform_driver` embeds a `struct device_driver`. +// - `DEVICE_DRIVER_OFFSET` is the correct byte offset to the embedded `struct device_driver`. +unsafe impl<T: Driver + 'static> driver::DriverLayout for Adapter<T> { + type DriverType = bindings::platform_driver; + type DriverData = T; + const DEVICE_DRIVER_OFFSET: usize = core::mem::offset_of!(Self::DriverType, driver); +} + +// SAFETY: A call to `unregister` for a given instance of `DriverType` is guaranteed to be valid if // a preceding call to `register` has been successful. unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { - type RegType = bindings::platform_driver; - unsafe fn register( - pdrv: &Opaque<Self::RegType>, + pdrv: &Opaque<Self::DriverType>, name: &'static CStr, module: &'static ThisModule, ) -> Result { @@ -55,12 +64,12 @@ unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { (*pdrv.get()).driver.acpi_match_table = acpi_table; } - // SAFETY: `pdrv` is guaranteed to be a valid `RegType`. + // SAFETY: `pdrv` is guaranteed to be a valid `DriverType`. to_result(unsafe { bindings::__platform_driver_register(pdrv.get(), module.0) }) } - unsafe fn unregister(pdrv: &Opaque<Self::RegType>) { - // SAFETY: `pdrv` is guaranteed to be a valid `RegType`. + unsafe fn unregister(pdrv: &Opaque<Self::DriverType>) { + // SAFETY: `pdrv` is guaranteed to be a valid `DriverType`. unsafe { bindings::platform_driver_unregister(pdrv.get()) }; } } @@ -92,9 +101,9 @@ impl<T: Driver + 'static> Adapter<T> { // SAFETY: `remove_callback` is only ever called after a successful call to // `probe_callback`, hence it's guaranteed that `Device::set_drvdata()` has been called // and stored a `Pin<KBox<T>>`. - let data = unsafe { pdev.as_ref().drvdata_obtain::<T>() }; + let data = unsafe { pdev.as_ref().drvdata_borrow::<T>() }; - T::unbind(pdev, data.as_ref()); + T::unbind(pdev, data); } } diff --git a/rust/kernel/usb.rs b/rust/kernel/usb.rs index d10b65e9fb6a..67ce5c85c619 100644 --- a/rust/kernel/usb.rs +++ b/rust/kernel/usb.rs @@ -27,13 +27,22 @@ use core::{ /// An adapter for the registration of USB drivers. pub struct Adapter<T: Driver>(T); -// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if +// SAFETY: +// - `bindings::usb_driver` is a C type declared as `repr(C)`. +// - `T` is the type of the driver's device private data. +// - `struct usb_driver` embeds a `struct device_driver`. +// - `DEVICE_DRIVER_OFFSET` is the correct byte offset to the embedded `struct device_driver`. +unsafe impl<T: Driver + 'static> driver::DriverLayout for Adapter<T> { + type DriverType = bindings::usb_driver; + type DriverData = T; + const DEVICE_DRIVER_OFFSET: usize = core::mem::offset_of!(Self::DriverType, driver); +} + +// SAFETY: A call to `unregister` for a given instance of `DriverType` is guaranteed to be valid if // a preceding call to `register` has been successful. unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { - type RegType = bindings::usb_driver; - unsafe fn register( - udrv: &Opaque<Self::RegType>, + udrv: &Opaque<Self::DriverType>, name: &'static CStr, module: &'static ThisModule, ) -> Result { @@ -45,14 +54,14 @@ unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> { (*udrv.get()).id_table = T::ID_TABLE.as_ptr(); } - // SAFETY: `udrv` is guaranteed to be a valid `RegType`. + // SAFETY: `udrv` is guaranteed to be a valid `DriverType`. to_result(unsafe { bindings::usb_register_driver(udrv.get(), module.0, name.as_char_ptr()) }) } - unsafe fn unregister(udrv: &Opaque<Self::RegType>) { - // SAFETY: `udrv` is guaranteed to be a valid `RegType`. + unsafe fn unregister(udrv: &Opaque<Self::DriverType>) { + // SAFETY: `udrv` is guaranteed to be a valid `DriverType`. unsafe { bindings::usb_deregister(udrv.get()) }; } } @@ -94,9 +103,9 @@ impl<T: Driver + 'static> Adapter<T> { // SAFETY: `disconnect_callback` is only ever called after a successful call to // `probe_callback`, hence it's guaranteed that `Device::set_drvdata()` has been called // and stored a `Pin<KBox<T>>`. - let data = unsafe { dev.drvdata_obtain::<T>() }; + let data = unsafe { dev.drvdata_borrow::<T>() }; - T::disconnect(intf, data.as_ref()); + T::disconnect(intf, data); } } diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index da3a9f2091f5..1ba1927b548e 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -176,8 +176,8 @@ asm ( " st.d $t0, $sp, 0\n" " st.d $ra, $sp, 8\n" " bl my_direct_func1\n" -" ld.d $t0, $sp, 0\n" -" ld.d $ra, $sp, 8\n" +" ld.d $ra, $sp, 0\n" +" ld.d $t0, $sp, 8\n" " addi.d $sp, $sp, 16\n" " jr $t0\n" " .size my_tramp1, .-my_tramp1\n" @@ -189,8 +189,8 @@ asm ( " st.d $t0, $sp, 0\n" " st.d $ra, $sp, 8\n" " bl my_direct_func2\n" -" ld.d $t0, $sp, 0\n" -" ld.d $ra, $sp, 8\n" +" ld.d $ra, $sp, 0\n" +" ld.d $t0, $sp, 8\n" " addi.d $sp, $sp, 16\n" " jr $t0\n" " .size my_tramp2, .-my_tramp2\n" diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c index 8f7986d698d8..7a7822dfeb50 100644 --- a/samples/ftrace/ftrace-direct-multi-modify.c +++ b/samples/ftrace/ftrace-direct-multi-modify.c @@ -199,8 +199,8 @@ asm ( " move $a0, $t0\n" " bl my_direct_func1\n" " ld.d $a0, $sp, 0\n" -" ld.d $t0, $sp, 8\n" -" ld.d $ra, $sp, 16\n" +" ld.d $ra, $sp, 8\n" +" ld.d $t0, $sp, 16\n" " addi.d $sp, $sp, 32\n" " jr $t0\n" " .size my_tramp1, .-my_tramp1\n" @@ -215,8 +215,8 @@ asm ( " move $a0, $t0\n" " bl my_direct_func2\n" " ld.d $a0, $sp, 0\n" -" ld.d $t0, $sp, 8\n" -" ld.d $ra, $sp, 16\n" +" ld.d $ra, $sp, 8\n" +" ld.d $t0, $sp, 16\n" " addi.d $sp, $sp, 32\n" " jr $t0\n" " .size my_tramp2, .-my_tramp2\n" diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c index db326c81a27d..3fe6ddaf0b69 100644 --- a/samples/ftrace/ftrace-direct-multi.c +++ b/samples/ftrace/ftrace-direct-multi.c @@ -131,8 +131,8 @@ asm ( " move $a0, $t0\n" " bl my_direct_func\n" " ld.d $a0, $sp, 0\n" -" ld.d $t0, $sp, 8\n" -" ld.d $ra, $sp, 16\n" +" ld.d $ra, $sp, 8\n" +" ld.d $t0, $sp, 16\n" " addi.d $sp, $sp, 32\n" " jr $t0\n" " .size my_tramp, .-my_tramp\n" diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c index 3d0fa260332d..bf2411aa6fd7 100644 --- a/samples/ftrace/ftrace-direct-too.c +++ b/samples/ftrace/ftrace-direct-too.c @@ -143,8 +143,8 @@ asm ( " ld.d $a0, $sp, 0\n" " ld.d $a1, $sp, 8\n" " ld.d $a2, $sp, 16\n" -" ld.d $t0, $sp, 24\n" -" ld.d $ra, $sp, 32\n" +" ld.d $ra, $sp, 24\n" +" ld.d $t0, $sp, 32\n" " addi.d $sp, $sp, 48\n" " jr $t0\n" " .size my_tramp, .-my_tramp\n" diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c index 956834b0d19a..5368c8c39cbb 100644 --- a/samples/ftrace/ftrace-direct.c +++ b/samples/ftrace/ftrace-direct.c @@ -124,8 +124,8 @@ asm ( " st.d $ra, $sp, 16\n" " bl my_direct_func\n" " ld.d $a0, $sp, 0\n" -" ld.d $t0, $sp, 8\n" -" ld.d $ra, $sp, 16\n" +" ld.d $ra, $sp, 8\n" +" ld.d $t0, $sp, 16\n" " addi.d $sp, $sp, 32\n" " jr $t0\n" " .size my_tramp, .-my_tramp\n" diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 52c08c4eb0b9..5037f4715d74 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -527,18 +527,6 @@ ifneq ($(userprogs),) include $(srctree)/scripts/Makefile.userprogs endif -ifneq ($(need-dtbslist)$(dtb-y)$(dtb-)$(filter %.dtb %.dtb.o %.dtbo.o,$(targets)),) -include $(srctree)/scripts/Makefile.dtbs -endif - -# Build -# --------------------------------------------------------------------------- - -$(obj)/: $(if $(KBUILD_BUILTIN), $(targets-for-builtin)) \ - $(if $(KBUILD_MODULES), $(targets-for-modules)) \ - $(subdir-ym) $(always-y) - @: - # Single targets # --------------------------------------------------------------------------- @@ -568,6 +556,20 @@ FORCE: targets += $(filter-out $(single-subdir-goals), $(MAKECMDGOALS)) targets := $(filter-out $(PHONY), $(targets)) +# Now that targets is fully known, include dtb rules if needed +ifneq ($(need-dtbslist)$(dtb-y)$(dtb-)$(filter %.dtb %.dtb.o %.dtbo.o,$(targets)),) +include $(srctree)/scripts/Makefile.dtbs +endif + +# Build +# Needs to be after the include of Makefile.dtbs, which updates always-y +# --------------------------------------------------------------------------- + +$(obj)/: $(if $(KBUILD_BUILTIN), $(targets-for-builtin)) \ + $(if $(KBUILD_MODULES), $(targets-for-modules)) \ + $(subdir-ym) $(always-y) + @: + # Read all saved command lines and dependencies for the $(targets) we # may be building above, using $(if_changed{,_dep}). As an # optimization, we don't need to read them if the target does not diff --git a/scripts/check-function-names.sh b/scripts/check-function-names.sh index 410042591cfc..08071133e5a5 100755 --- a/scripts/check-function-names.sh +++ b/scripts/check-function-names.sh @@ -13,7 +13,7 @@ if [ ! -f "$objfile" ]; then exit 1 fi -bad_symbols=$(nm "$objfile" | awk '$2 ~ /^[TtWw]$/ {print $3}' | grep -E '^(startup|exit|split|unlikely|hot|unknown)(\.|$)') +bad_symbols=$(${NM:-nm} "$objfile" | awk '$2 ~ /^[TtWw]$/ {print $3}' | grep -E '^(startup|exit|split|unlikely|hot|unknown)(\.|$)') if [ -n "$bad_symbols" ]; then echo "$bad_symbols" | while read -r sym; do diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index 6f4afa92a466..96e6e46ad1a7 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -21,12 +21,6 @@ _DEFAULT_LOG_LEVEL = 'WARNING' _FILENAME_PATTERN = r'^\..*\.cmd$' _LINE_PATTERN = r'^(saved)?cmd_[^ ]*\.o := (?P<command_prefix>.* )(?P<file_path>[^ ]*\.[cS]) *(;|$)' _VALID_LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'] - -# Pre-compiled regexes for better performance -_INCLUDE_PATTERN = re.compile(r'^\s*#\s*include\s*[<"]([^>"]*)[>"]') -_C_INCLUDE_PATTERN = re.compile(r'^\s*#\s*include\s*"([^"]*\.c)"\s*$') -_FILENAME_MATCHER = re.compile(_FILENAME_PATTERN) - # The tools/ directory adopts a different build system, and produces .cmd # files in a different format. Do not support it. _EXCLUDE_DIRS = ['.git', 'Documentation', 'include', 'tools'] @@ -88,6 +82,7 @@ def cmdfiles_in_dir(directory): The path to a .cmd file. """ + filename_matcher = re.compile(_FILENAME_PATTERN) exclude_dirs = [ os.path.join(directory, d) for d in _EXCLUDE_DIRS ] for dirpath, dirnames, filenames in os.walk(directory, topdown=True): @@ -97,7 +92,7 @@ def cmdfiles_in_dir(directory): continue for filename in filenames: - if _FILENAME_MATCHER.match(filename): + if filename_matcher.match(filename): yield os.path.join(dirpath, filename) @@ -154,87 +149,8 @@ def cmdfiles_for_modorder(modorder): yield to_cmdfile(mod_line.rstrip()) -def extract_includes_from_file(source_file, root_directory): - """Extract #include statements from a C file. - - Args: - source_file: Path to the source .c file to analyze - root_directory: Root directory for resolving relative paths - - Returns: - List of header files that should be included (without quotes/brackets) - """ - includes = [] - if not os.path.exists(source_file): - return includes - - try: - with open(source_file, 'r') as f: - for line in f: - line = line.strip() - # Look for #include statements. - # Match both #include "header.h" and #include <header.h>. - match = _INCLUDE_PATTERN.match(line) - if match: - header = match.group(1) - # Skip including other .c files to avoid circular includes. - if not header.endswith('.c'): - # For relative includes (quoted), resolve path relative to source file. - if '"' in line: - src_dir = os.path.dirname(source_file) - header_path = os.path.join(src_dir, header) - if os.path.exists(header_path): - rel_header = os.path.relpath(header_path, root_directory) - includes.append(rel_header) - else: - includes.append(header) - else: - # System include like <linux/sched.h>. - includes.append(header) - except IOError: - pass - - return includes - - -def find_included_c_files(source_file, root_directory): - """Find .c files that are included by the given source file. - - Args: - source_file: Path to the source .c file - root_directory: Root directory for resolving relative paths - - Yields: - Full paths to included .c files - """ - if not os.path.exists(source_file): - return - - try: - with open(source_file, 'r') as f: - for line in f: - line = line.strip() - # Look for #include "*.c" patterns. - match = _C_INCLUDE_PATTERN.match(line) - if match: - included_file = match.group(1) - # Handle relative paths. - if not os.path.isabs(included_file): - src_dir = os.path.dirname(source_file) - included_file = os.path.join(src_dir, included_file) - - # Normalize the path. - included_file = os.path.normpath(included_file) - - # Check if the file exists. - if os.path.exists(included_file): - yield included_file - except IOError: - pass - - def process_line(root_directory, command_prefix, file_path): - """Extracts information from a .cmd line and creates entries from it. + """Extracts information from a .cmd line and creates an entry from it. Args: root_directory: The directory that was searched for .cmd files. Usually @@ -244,8 +160,7 @@ def process_line(root_directory, command_prefix, file_path): Usually relative to root_directory, but sometimes absolute. Returns: - A list of entries to append to compile_commands (may include multiple - entries if the source file includes other .c files). + An entry to append to compile_commands. Raises: ValueError: Could not find the extracted file based on file_path and @@ -261,47 +176,11 @@ def process_line(root_directory, command_prefix, file_path): abs_path = os.path.realpath(os.path.join(root_directory, file_path)) if not os.path.exists(abs_path): raise ValueError('File %s not found' % abs_path) - - entries = [] - - # Create entry for the main source file. - main_entry = { + return { 'directory': root_directory, 'file': abs_path, 'command': prefix + file_path, } - entries.append(main_entry) - - # Find and create entries for included .c files. - for included_c_file in find_included_c_files(abs_path, root_directory): - # For included .c files, create a compilation command that: - # 1. Uses the same compilation flags as the parent file - # 2. But compiles the included file directly (not the parent) - # 3. Includes necessary headers from the parent file for proper macro resolution - - # Convert absolute path to relative for the command. - rel_path = os.path.relpath(included_c_file, root_directory) - - # Extract includes from the parent file to provide proper compilation context. - extra_includes = '' - try: - parent_includes = extract_includes_from_file(abs_path, root_directory) - if parent_includes: - extra_includes = ' ' + ' '.join('-include ' + inc for inc in parent_includes) - except IOError: - pass - - included_entry = { - 'directory': root_directory, - 'file': included_c_file, - # Use the same compilation prefix but target the included file directly. - # Add extra headers for proper macro resolution. - 'command': prefix + extra_includes + ' ' + rel_path, - } - entries.append(included_entry) - logging.debug('Added entry for included file: %s', included_c_file) - - return entries def main(): @@ -334,9 +213,9 @@ def main(): result = line_matcher.match(f.readline()) if result: try: - entries = process_line(directory, result.group('command_prefix'), + entry = process_line(directory, result.group('command_prefix'), result.group('file_path')) - compile_commands.extend(entries) + compile_commands.append(entry) except ValueError as err: logging.info('Could not add line from %s: %s', cmdfile, err) diff --git a/scripts/crypto/gen-hash-testvecs.py b/scripts/crypto/gen-hash-testvecs.py index c1d0517140bd..c773294fba64 100755 --- a/scripts/crypto/gen-hash-testvecs.py +++ b/scripts/crypto/gen-hash-testvecs.py @@ -118,7 +118,7 @@ def print_c_struct_u8_array_field(name, value): def alg_digest_size_const(alg): if alg.startswith('blake2'): return f'{alg.upper()}_HASH_SIZE' - return f'{alg.upper().replace('-', '_')}_DIGEST_SIZE' + return f"{alg.upper().replace('-', '_')}_DIGEST_SIZE" def gen_unkeyed_testvecs(alg): print('') diff --git a/scripts/kconfig/nconf-cfg.sh b/scripts/kconfig/nconf-cfg.sh index a20290b1a37d..4d08453f9bdb 100755 --- a/scripts/kconfig/nconf-cfg.sh +++ b/scripts/kconfig/nconf-cfg.sh @@ -6,8 +6,9 @@ set -eu cflags=$1 libs=$2 -PKG="ncursesw menuw panelw" -PKG2="ncurses menu panel" +# Keep library order for static linking (HOSTCC='cc -static') +PKG="menuw panelw ncursesw" +PKG2="menu panel ncurses" if [ -n "$(command -v ${HOSTPKG_CONFIG})" ]; then if ${HOSTPKG_CONFIG} --exists $PKG; then @@ -28,19 +29,19 @@ fi # find ncurses by pkg-config.) if [ -f /usr/include/ncursesw/ncurses.h ]; then echo -D_GNU_SOURCE -I/usr/include/ncursesw > ${cflags} - echo -lncursesw -lmenuw -lpanelw > ${libs} + echo -lmenuw -lpanelw -lncursesw > ${libs} exit 0 fi if [ -f /usr/include/ncurses/ncurses.h ]; then echo -D_GNU_SOURCE -I/usr/include/ncurses > ${cflags} - echo -lncurses -lmenu -lpanel > ${libs} + echo -lmenu -lpanel -lncurses > ${libs} exit 0 fi if [ -f /usr/include/ncurses.h ]; then echo -D_GNU_SOURCE > ${cflags} - echo -lncurses -lmenu -lpanel > ${libs} + echo -lmenu -lpanel -lncurses > ${libs} exit 0 fi diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index ef2ffb68f69d..b4178c42d08f 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -199,6 +199,9 @@ int main(void) DEVID(cpu_feature); DEVID_FIELD(cpu_feature, feature); + DEVID(mcb_device_id); + DEVID_FIELD(mcb_device_id, device); + DEVID(mei_cl_device_id); DEVID_FIELD(mei_cl_device_id, name); DEVID_FIELD(mei_cl_device_id, uuid); diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index b3333560b95e..4e99393a35f1 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1110,6 +1110,14 @@ static void do_cpu_entry(struct module *mod, void *symval) module_alias_printf(mod, false, "cpu:type:*:feature:*%04X*", feature); } +/* Looks like: mcb:16zN */ +static void do_mcb_entry(struct module *mod, void *symval) +{ + DEF_FIELD(symval, mcb_device_id, device); + + module_alias_printf(mod, false, "mcb:16z%03d", device); +} + /* Looks like: mei:S:uuid:N:* */ static void do_mei_entry(struct module *mod, void *symval) { @@ -1444,6 +1452,7 @@ static const struct devtable devtable[] = { {"mipscdmm", SIZE_mips_cdmm_device_id, do_mips_cdmm_entry}, {"x86cpu", SIZE_x86_cpu_id, do_x86cpu_entry}, {"cpu", SIZE_cpu_feature, do_cpu_entry}, + {"mcb", SIZE_mcb_device_id, do_mcb_entry}, {"mei", SIZE_mei_cl_device_id, do_mei_entry}, {"rapidio", SIZE_rio_device_id, do_rio_entry}, {"ulpi", SIZE_ulpi_device_id, do_ulpi_entry}, diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 8d608f61bf37..908029e45ca2 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -1,6 +1,6 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -# Copyright Thomas Gleixner <tglx@linutronix.de> +# Copyright Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> from argparse import ArgumentParser from ply import lex, yacc diff --git a/scripts/tracepoint-update.c b/scripts/tracepoint-update.c index 90046aedc97b..5cf43c0aac89 100644 --- a/scripts/tracepoint-update.c +++ b/scripts/tracepoint-update.c @@ -49,6 +49,8 @@ static int add_string(const char *str, const char ***vals, int *count) array = realloc(array, sizeof(char *) * size); if (!array) { fprintf(stderr, "Failed memory allocation\n"); + free(*vals); + *vals = NULL; return -1; } *vals = array; diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c index 7362f68f2d8b..5beb69edd12f 100644 --- a/security/integrity/ima/ima_kexec.c +++ b/security/integrity/ima/ima_kexec.c @@ -250,9 +250,7 @@ void ima_kexec_post_load(struct kimage *image) if (!image->ima_buffer_addr) return; - ima_kexec_buffer = kimage_map_segment(image, - image->ima_buffer_addr, - image->ima_buffer_size); + ima_kexec_buffer = kimage_map_segment(image, image->ima_segment_index); if (!ima_kexec_buffer) { pr_err("Could not map measurements buffer.\n"); return; diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index a7ea4a1c3bed..6340823f8b53 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -465,7 +465,7 @@ out: } /** - * tpm2_unseal_cmd() - execute a TPM2_Unload command + * tpm2_unseal_cmd() - execute a TPM2_Unseal command * * @chip: TPM chip to use * @payload: the key data in clear and encrypted form @@ -498,7 +498,7 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, return rc; } - rc = tpm_buf_append_name(chip, &buf, options->keyhandle, NULL); + rc = tpm_buf_append_name(chip, &buf, blob_handle, NULL); if (rc) goto out; diff --git a/security/landlock/audit.c b/security/landlock/audit.c index c52d079cdb77..e899995f1fd5 100644 --- a/security/landlock/audit.c +++ b/security/landlock/audit.c @@ -191,7 +191,7 @@ static size_t get_denied_layer(const struct landlock_ruleset *const domain, long youngest_layer = -1; for_each_set_bit(access_bit, &access_req, layer_masks_size) { - const access_mask_t mask = (*layer_masks)[access_bit]; + const layer_mask_t mask = (*layer_masks)[access_bit]; long layer; if (!mask) diff --git a/security/landlock/domain.h b/security/landlock/domain.h index 7fb70b25f85a..621f054c9a2b 100644 --- a/security/landlock/domain.h +++ b/security/landlock/domain.h @@ -97,7 +97,7 @@ struct landlock_hierarchy { */ atomic64_t num_denials; /** - * @id: Landlock domain ID, sets once at domain creation time. + * @id: Landlock domain ID, set once at domain creation time. */ u64 id; /** diff --git a/security/landlock/errata/abi-6.h b/security/landlock/errata/abi-6.h index df7bc0e1fdf4..5113a829f87e 100644 --- a/security/landlock/errata/abi-6.h +++ b/security/landlock/errata/abi-6.h @@ -9,7 +9,7 @@ * This fix addresses an issue where signal scoping was overly restrictive, * preventing sandboxed threads from signaling other threads within the same * process if they belonged to different domains. Because threads are not - * security boundaries, user space might assume that any thread within the same + * security boundaries, user space might assume that all threads within the same * process can send signals between themselves (see :manpage:`nptl(7)` and * :manpage:`libpsx(3)`). Consistent with :manpage:`ptrace(2)` behavior, direct * interaction between threads of the same process should always be allowed. diff --git a/security/landlock/fs.c b/security/landlock/fs.c index fe794875ad46..8205673c8b1c 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -939,7 +939,12 @@ jump_up: } path_put(&walker_path); - if (!allowed_parent1) { + /* + * Check CONFIG_AUDIT to enable elision of log_request_parent* and + * associated caller's stack variables thanks to dead code elimination. + */ +#ifdef CONFIG_AUDIT + if (!allowed_parent1 && log_request_parent1) { log_request_parent1->type = LANDLOCK_REQUEST_FS_ACCESS; log_request_parent1->audit.type = LSM_AUDIT_DATA_PATH; log_request_parent1->audit.u.path = *path; @@ -949,7 +954,7 @@ jump_up: ARRAY_SIZE(*layer_masks_parent1); } - if (!allowed_parent2) { + if (!allowed_parent2 && log_request_parent2) { log_request_parent2->type = LANDLOCK_REQUEST_FS_ACCESS; log_request_parent2->audit.type = LSM_AUDIT_DATA_PATH; log_request_parent2->audit.u.path = *path; @@ -958,6 +963,8 @@ jump_up: log_request_parent2->layer_masks_size = ARRAY_SIZE(*layer_masks_parent2); } +#endif /* CONFIG_AUDIT */ + return allowed_parent1 && allowed_parent2; } @@ -1314,7 +1321,8 @@ static void hook_sb_delete(struct super_block *const sb) * second call to iput() for the same Landlock object. Also * checks I_NEW because such inode cannot be tied to an object. */ - if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) { + if (inode_state_read(inode) & + (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); continue; } diff --git a/security/landlock/net.c b/security/landlock/net.c index 1f3915a90a80..e6367e30e5b0 100644 --- a/security/landlock/net.c +++ b/security/landlock/net.c @@ -71,6 +71,61 @@ static int current_check_access_socket(struct socket *const sock, switch (address->sa_family) { case AF_UNSPEC: + if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) { + /* + * Connecting to an address with AF_UNSPEC dissolves + * the TCP association, which have the same effect as + * closing the connection while retaining the socket + * object (i.e., the file descriptor). As for dropping + * privileges, closing connections is always allowed. + * + * For a TCP access control system, this request is + * legitimate. Let the network stack handle potential + * inconsistencies and return -EINVAL if needed. + */ + return 0; + } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { + /* + * Binding to an AF_UNSPEC address is treated + * differently by IPv4 and IPv6 sockets. The socket's + * family may change under our feet due to + * setsockopt(IPV6_ADDRFORM), but that's ok: we either + * reject entirely or require + * %LANDLOCK_ACCESS_NET_BIND_TCP for the given port, so + * it cannot be used to bypass the policy. + * + * IPv4 sockets map AF_UNSPEC to AF_INET for + * retrocompatibility for bind accesses, only if the + * address is INADDR_ANY (cf. __inet_bind). IPv6 + * sockets always reject it. + * + * Checking the address is required to not wrongfully + * return -EACCES instead of -EAFNOSUPPORT or -EINVAL. + * We could return 0 and let the network stack handle + * these checks, but it is safer to return a proper + * error and test consistency thanks to kselftest. + */ + if (sock->sk->__sk_common.skc_family == AF_INET) { + const struct sockaddr_in *const sockaddr = + (struct sockaddr_in *)address; + + if (addrlen < sizeof(struct sockaddr_in)) + return -EINVAL; + + if (sockaddr->sin_addr.s_addr != + htonl(INADDR_ANY)) + return -EAFNOSUPPORT; + } else { + if (addrlen < SIN6_LEN_RFC2133) + return -EINVAL; + else + return -EAFNOSUPPORT; + } + } else { + WARN_ON_ONCE(1); + } + /* Only for bind(AF_UNSPEC+INADDR_ANY) on IPv4 socket. */ + fallthrough; case AF_INET: { const struct sockaddr_in *addr4; @@ -119,57 +174,18 @@ static int current_check_access_socket(struct socket *const sock, return 0; } - /* Specific AF_UNSPEC handling. */ - if (address->sa_family == AF_UNSPEC) { - /* - * Connecting to an address with AF_UNSPEC dissolves the TCP - * association, which have the same effect as closing the - * connection while retaining the socket object (i.e., the file - * descriptor). As for dropping privileges, closing - * connections is always allowed. - * - * For a TCP access control system, this request is legitimate. - * Let the network stack handle potential inconsistencies and - * return -EINVAL if needed. - */ - if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) - return 0; - - /* - * For compatibility reason, accept AF_UNSPEC for bind - * accesses (mapped to AF_INET) only if the address is - * INADDR_ANY (cf. __inet_bind). Checking the address is - * required to not wrongfully return -EACCES instead of - * -EAFNOSUPPORT. - * - * We could return 0 and let the network stack handle these - * checks, but it is safer to return a proper error and test - * consistency thanks to kselftest. - */ - if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { - /* addrlen has already been checked for AF_UNSPEC. */ - const struct sockaddr_in *const sockaddr = - (struct sockaddr_in *)address; - - if (sock->sk->__sk_common.skc_family != AF_INET) - return -EINVAL; - - if (sockaddr->sin_addr.s_addr != htonl(INADDR_ANY)) - return -EAFNOSUPPORT; - } - } else { - /* - * Checks sa_family consistency to not wrongfully return - * -EACCES instead of -EINVAL. Valid sa_family changes are - * only (from AF_INET or AF_INET6) to AF_UNSPEC. - * - * We could return 0 and let the network stack handle this - * check, but it is safer to return a proper error and test - * consistency thanks to kselftest. - */ - if (address->sa_family != sock->sk->__sk_common.skc_family) - return -EINVAL; - } + /* + * Checks sa_family consistency to not wrongfully return + * -EACCES instead of -EINVAL. Valid sa_family changes are + * only (from AF_INET or AF_INET6) to AF_UNSPEC. + * + * We could return 0 and let the network stack handle this + * check, but it is safer to return a proper error and test + * consistency thanks to kselftest. + */ + if (address->sa_family != sock->sk->__sk_common.skc_family && + address->sa_family != AF_UNSPEC) + return -EINVAL; id.key.data = (__force uintptr_t)port; BUILD_BUG_ON(sizeof(port) > sizeof(id.key.data)); diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c index dfcdc19ea268..0a5b0c76b3f7 100644 --- a/security/landlock/ruleset.c +++ b/security/landlock/ruleset.c @@ -23,7 +23,6 @@ #include <linux/workqueue.h> #include "access.h" -#include "audit.h" #include "domain.h" #include "limits.h" #include "object.h" diff --git a/security/landlock/task.c b/security/landlock/task.c index 2385017418ca..833bc0cfe5c9 100644 --- a/security/landlock/task.c +++ b/security/landlock/task.c @@ -86,7 +86,6 @@ static int hook_ptrace_access_check(struct task_struct *const child, const unsigned int mode) { const struct landlock_cred_security *parent_subject; - const struct landlock_ruleset *child_dom; int err; /* Quick return for non-landlocked tasks. */ @@ -96,7 +95,8 @@ static int hook_ptrace_access_check(struct task_struct *const child, scoped_guard(rcu) { - child_dom = landlock_get_task_domain(child); + const struct landlock_ruleset *const child_dom = + landlock_get_task_domain(child); err = domain_ptrace(parent_subject->domain, child_dom); } @@ -166,15 +166,15 @@ static int hook_ptrace_traceme(struct task_struct *const parent) } /** - * domain_is_scoped - Checks if the client domain is scoped in the same - * domain as the server. + * domain_is_scoped - Check if an interaction from a client/sender to a + * server/receiver should be restricted based on scope controls. * * @client: IPC sender domain. * @server: IPC receiver domain. * @scope: The scope restriction criteria. * - * Returns: True if the @client domain is scoped to access the @server, - * unless the @server is also scoped in the same domain as @client. + * Returns: True if @server is in a different domain from @client, and @client + * is scoped to access @server (i.e. access should be denied). */ static bool domain_is_scoped(const struct landlock_ruleset *const client, const struct landlock_ruleset *const server, diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c index f4254703d29f..bb9b795e0226 100644 --- a/sound/ac97/bus.c +++ b/sound/ac97/bus.c @@ -298,6 +298,7 @@ static void ac97_adapter_release(struct device *dev) idr_remove(&ac97_adapter_idr, ac97_ctrl->nr); dev_dbg(&ac97_ctrl->adap, "adapter unregistered by %s\n", dev_name(ac97_ctrl->parent)); + kfree(ac97_ctrl); } static const struct device_type ac97_adapter_type = { @@ -319,7 +320,9 @@ static int ac97_add_adapter(struct ac97_controller *ac97_ctrl) ret = device_register(&ac97_ctrl->adap); if (ret) put_device(&ac97_ctrl->adap); - } + } else + kfree(ac97_ctrl); + if (!ret) { list_add(&ac97_ctrl->controllers, &ac97_controllers); dev_dbg(&ac97_ctrl->adap, "adapter registered by %s\n", @@ -361,14 +364,11 @@ struct ac97_controller *snd_ac97_controller_register( ret = ac97_add_adapter(ac97_ctrl); if (ret) - goto err; + return ERR_PTR(ret); ac97_bus_reset(ac97_ctrl); ac97_bus_scan(ac97_ctrl); return ac97_ctrl; -err: - kfree(ac97_ctrl); - return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(snd_ac97_controller_register); diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index a82dd155e1d3..b12df5b5ddfc 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1074,7 +1074,9 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) runtime->oss.params = 0; runtime->oss.prepare = 1; runtime->oss.buffer_used = 0; - snd_pcm_runtime_buffer_set_silence(runtime); + err = snd_pcm_runtime_buffer_set_silence(runtime); + if (err < 0) + goto failure; runtime->oss.period_frames = snd_pcm_alsa_frames(substream, oss_period_size); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 68bee40c9ada..932a9bf98cbc 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -730,13 +730,18 @@ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime) } /* fill the PCM buffer with the current silence format; called from pcm_oss.c */ -void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) +int snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) { - snd_pcm_buffer_access_lock(runtime); + int err; + + err = snd_pcm_buffer_access_lock(runtime); + if (err < 0) + return err; if (runtime->dma_area) snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes)); snd_pcm_buffer_access_unlock(runtime); + return 0; } EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence); diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 1de46c06f8c2..cafa48b5aceb 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -3736,6 +3736,7 @@ enum { ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, ALC298_FIXUP_LENOVO_C940_DUET7, + ALC287_FIXUP_LENOVO_YOGA_BOOK_9I, ALC287_FIXUP_13S_GEN2_SPEAKERS, ALC256_FIXUP_SET_COEF_DEFAULTS, ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, @@ -3823,6 +3824,23 @@ static void alc298_fixup_lenovo_c940_duet7(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +/* A special fixup for Lenovo Yoga 9i and Yoga Book 9i 13IRU8 + * both have the very same PCI SSID and vendor ID, so we need + * to apply different fixups depending on the subsystem ID + */ +static void alc287_fixup_lenovo_yoga_book_9i(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + int id; + + if (codec->core.subsystem_id == 0x17aa3881) + id = ALC287_FIXUP_TAS2781_I2C; /* Yoga Book 9i 13IRU8 */ + else + id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP; /* Yoga 9i */ + __snd_hda_apply_fixup(codec, id, action, 0); +} + static const struct hda_fixup alc269_fixups[] = { [ALC269_FIXUP_GPIO2] = { .type = HDA_FIXUP_FUNC, @@ -5834,6 +5852,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc298_fixup_lenovo_c940_duet7, }, + [ALC287_FIXUP_LENOVO_YOGA_BOOK_9I] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_lenovo_yoga_book_9i, + }, [ALC287_FIXUP_13S_GEN2_SPEAKERS] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -6321,6 +6343,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), @@ -6508,6 +6531,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x863e, "HP Spectre x360 15-df1xxx", ALC285_FIXUP_HP_SPECTRE_X360_DF1), SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x8706, "HP Laptop 15s-eq1xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), 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), @@ -6611,6 +6635,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8a2e, "HP Envy 16", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a30, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a31, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8a34, "HP Pavilion x360 2-in-1 Laptop 14-ek0xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -6815,6 +6840,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8f42, "HP ZBook 8 G2a 14W", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8f57, "HP Trekker G7JC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8f62, "HP ZBook 8 G2a 16W", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), + SND_PCI_QUIRK(0x1043, 0x1024, "ASUS Zephyrus G14 2025", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1032, "ASUS VivoBook X513EA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1034, "ASUS GU605C", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), @@ -7009,6 +7035,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { 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(0x144d, 0xc876, "Samsung 730QED (NP730QED-KA2US)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xca03, "Samsung Galaxy Book2 Pro 360 (NP930QED)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xca06, "Samsung Galaxy Book3 360 (NP730QFG)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc868, "Samsung Galaxy Book2 Pro (NP930XED)", ALC298_FIXUP_SAMSUNG_AMP), @@ -7187,7 +7214,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x383d, "Legion Y9000X 2019", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), - SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP), + SND_PCI_QUIRK(0x17aa, 0x3843, "Lenovo Yoga 9i / Yoga Book 9i", ALC287_FIXUP_LENOVO_YOGA_BOOK_9I), SND_PCI_QUIRK(0x17aa, 0x3847, "Legion 7 16ACHG6", ALC287_FIXUP_LEGION_16ACHG6), SND_PCI_QUIRK(0x17aa, 0x384a, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), @@ -7778,6 +7805,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60140}, {0x19, 0x04a11030}, {0x21, 0x04211020}), + SND_HDA_PIN_QUIRK(0x10ec0274, 0x1d05, "TongFang", ALC274_FIXUP_HP_HEADSET_MIC, + {0x17, 0x90170110}, + {0x19, 0x03a11030}, + {0x21, 0x03211020}), SND_HDA_PIN_QUIRK(0x10ec0282, 0x1025, "Acer", ALC282_FIXUP_ACER_DISABLE_LINEOUT, ALC282_STANDARD_PINS, {0x12, 0x90a609c0}, diff --git a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c index 3cca750857b6..dc35932b6b22 100644 --- a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c +++ b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c @@ -103,6 +103,7 @@ static int cirrus_scodec_test_gpio_probe(struct platform_device *pdev) /* GPIO core modifies our struct gpio_chip so use a copy */ gpio_priv->chip = cirrus_scodec_test_gpio_chip; + gpio_priv->chip.parent = &pdev->dev; ret = devm_gpiochip_add_data(&pdev->dev, &gpio_priv->chip, gpio_priv); if (ret) return dev_err_probe(&pdev->dev, ret, "Failed to add gpiochip\n"); @@ -319,7 +320,7 @@ static struct kunit_case cirrus_scodec_test_cases[] = { }; static struct kunit_suite cirrus_scodec_test_suite = { - .name = "snd-hda-scodec-cs35l56-test", + .name = "snd-hda-cirrus-scodec-test", .init = cirrus_scodec_test_case_init, .test_cases = cirrus_scodec_test_cases, }; diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index c8619995b1d7..624a822341bb 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -2,7 +2,7 @@ // // TAS2781 HDA I2C driver // -// Copyright 2023 - 2025 Texas Instruments, Inc. +// Copyright 2023 - 2026 Texas Instruments, Inc. // // Author: Shenghao Ding <shenghao-ding@ti.com> // Current maintainer: Baojun Xu <baojun.xu@ti.com> @@ -60,6 +60,7 @@ struct tas2781_hda_i2c_priv { int (*save_calibration)(struct tas2781_hda *h); int hda_chip_id; + bool skip_calibration; }; static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data) @@ -111,8 +112,10 @@ static int tas2781_read_acpi(struct tasdevice_priv *p, const char *hid) sub = acpi_get_subsystem_id(ACPI_HANDLE(physdev)); if (IS_ERR(sub)) { /* No subsys id in older tas2563 projects. */ - if (!strncmp(hid, "INT8866", sizeof("INT8866"))) + if (!strncmp(hid, "INT8866", sizeof("INT8866"))) { + p->speaker_id = -1; goto end_2563; + } dev_err(p->dev, "Failed to get SUBSYS ID.\n"); ret = PTR_ERR(sub); goto err; @@ -489,7 +492,8 @@ static void tasdevice_dspfw_init(void *context) /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - hda_priv->save_calibration(tas_hda); + if (!hda_priv->skip_calibration) + hda_priv->save_calibration(tas_hda); } static void tasdev_fw_ready(const struct firmware *fmw, void *context) @@ -546,6 +550,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, void *master_data) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + struct tas2781_hda_i2c_priv *hda_priv = tas_hda->hda_priv; struct hda_component_parent *parent = master_data; struct hda_component *comp; struct hda_codec *codec; @@ -566,11 +571,22 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, case 0x1028: tas_hda->catlog_id = DELL; break; + case 0x103C: + tas_hda->catlog_id = HP; + break; default: tas_hda->catlog_id = LENOVO; break; } + /* + * Using ASUS ROG Xbox Ally X (RC73XA) UEFI calibration data + * causes audio dropouts during playback, use fallback data + * from DSP firmware as a workaround. + */ + if (codec->core.subsystem_id == 0x10431384) + hda_priv->skip_calibration = true; + pm_runtime_get_sync(dev); comp->dev = dev; diff --git a/sound/pci/ctxfi/ctamixer.c b/sound/pci/ctxfi/ctamixer.c index bb4658592636..c30162be27ee 100644 --- a/sound/pci/ctxfi/ctamixer.c +++ b/sound/pci/ctxfi/ctamixer.c @@ -205,6 +205,7 @@ static int amixer_rsc_init(struct amixer *amixer, /* Set amixer specific operations */ amixer->rsc.ops = &amixer_basic_rsc_ops; + amixer->rsc.conj = 0; amixer->ops = &amixer_ops; amixer->input = NULL; amixer->sum = NULL; @@ -367,6 +368,7 @@ static int sum_rsc_init(struct sum *sum, return err; sum->rsc.ops = &sum_basic_rsc_ops; + sum->rsc.conj = 0; return 0; } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index bf4d9d336561..0294177acc66 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -420,6 +420,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6500RE"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "M6501RM"), } }, diff --git a/sound/soc/codecs/pm4125.c b/sound/soc/codecs/pm4125.c index 8bc3b9994019..1f0a3f5389f1 100644 --- a/sound/soc/codecs/pm4125.c +++ b/sound/soc/codecs/pm4125.c @@ -1505,10 +1505,6 @@ static int pm4125_bind(struct device *dev) struct device_link *devlink; int ret; - /* Initialize device pointers to NULL for safe cleanup */ - pm4125->rxdev = NULL; - pm4125->txdev = NULL; - /* Give the soundwire subdevices some more time to settle */ usleep_range(15000, 15010); @@ -1537,13 +1533,7 @@ static int pm4125_bind(struct device *dev) pm4125->sdw_priv[AIF1_CAP] = dev_get_drvdata(pm4125->txdev); pm4125->sdw_priv[AIF1_CAP]->pm4125 = pm4125; - pm4125->tx_sdw_dev = dev_to_sdw_dev(pm4125->txdev); - if (!pm4125->tx_sdw_dev) { - dev_err(dev, "could not get txslave with matching of dev\n"); - ret = -EINVAL; - goto error_put_tx; - } /* * As TX is the main CSR reg interface, which should not be suspended first. @@ -1624,11 +1614,8 @@ static void pm4125_unbind(struct device *dev) device_link_remove(dev, pm4125->rxdev); device_link_remove(pm4125->rxdev, pm4125->txdev); - /* Release device references acquired in bind */ - if (pm4125->txdev) - put_device(pm4125->txdev); - if (pm4125->rxdev) - put_device(pm4125->rxdev); + put_device(pm4125->txdev); + put_device(pm4125->rxdev); component_unbind_all(dev, pm4125); } diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c index 443cf59cb71a..fdf4a9add852 100644 --- a/sound/soc/codecs/tlv320adcx140.c +++ b/sound/soc/codecs/tlv320adcx140.c @@ -23,7 +23,6 @@ #include "tlv320adcx140.h" struct adcx140_priv { - struct snd_soc_component *component; struct regulator *supply_areg; struct gpio_desc *gpio_reset; struct regmap *regmap; @@ -338,7 +337,7 @@ static const struct snd_kcontrol_new adcx140_dapm_ch4_dre_en_switch = SOC_DAPM_SINGLE("Switch", ADCX140_CH4_CFG0, 0, 1, 0); static const struct snd_kcontrol_new adcx140_dapm_dre_en_switch = - SOC_DAPM_SINGLE("Switch", ADCX140_DSP_CFG1, 3, 1, 0); + SOC_DAPM_SINGLE("Switch", ADCX140_DSP_CFG1, 3, 1, 1); /* Output Mixer */ static const struct snd_kcontrol_new adcx140_output_mixer_controls[] = { @@ -699,7 +698,6 @@ static void adcx140_pwr_ctrl(struct adcx140_priv *adcx140, bool power_state) { int pwr_ctrl = 0; int ret = 0; - struct snd_soc_component *component = adcx140->component; if (power_state) pwr_ctrl = ADCX140_PWR_CFG_ADC_PDZ | ADCX140_PWR_CFG_PLL_PDZ; @@ -711,7 +709,7 @@ static void adcx140_pwr_ctrl(struct adcx140_priv *adcx140, bool power_state) ret = regmap_write(adcx140->regmap, ADCX140_PHASE_CALIB, adcx140->phase_calib_on ? 0x00 : 0x40); if (ret) - dev_err(component->dev, "%s: register write error %d\n", + dev_err(adcx140->dev, "%s: register write error %d\n", __func__, ret); } @@ -727,7 +725,7 @@ static int adcx140_hw_params(struct snd_pcm_substream *substream, struct adcx140_priv *adcx140 = snd_soc_component_get_drvdata(component); u8 data = 0; - switch (params_width(params)) { + switch (params_physical_width(params)) { case 16: data = ADCX140_16_BIT_WORD; break; @@ -742,7 +740,7 @@ static int adcx140_hw_params(struct snd_pcm_substream *substream, break; default: dev_err(component->dev, "%s: Unsupported width %d\n", - __func__, params_width(params)); + __func__, params_physical_width(params)); return -EINVAL; } @@ -1156,6 +1154,9 @@ static int adcx140_i2c_probe(struct i2c_client *i2c) adcx140->gpio_reset = devm_gpiod_get_optional(adcx140->dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(adcx140->gpio_reset)) + return dev_err_probe(&i2c->dev, PTR_ERR(adcx140->gpio_reset), + "Failed to get Reset GPIO\n"); + if (!adcx140->gpio_reset) dev_info(&i2c->dev, "Reset GPIO not defined\n"); adcx140->supply_areg = devm_regulator_get_optional(adcx140->dev, diff --git a/sound/soc/codecs/wcd937x.c b/sound/soc/codecs/wcd937x.c index f4dbcf04be49..10a2d598caa7 100644 --- a/sound/soc/codecs/wcd937x.c +++ b/sound/soc/codecs/wcd937x.c @@ -2763,11 +2763,6 @@ static int wcd937x_bind(struct device *dev) wcd937x->sdw_priv[AIF1_CAP] = dev_get_drvdata(wcd937x->txdev); wcd937x->sdw_priv[AIF1_CAP]->wcd937x = wcd937x; wcd937x->tx_sdw_dev = dev_to_sdw_dev(wcd937x->txdev); - if (!wcd937x->tx_sdw_dev) { - dev_err(dev, "could not get txslave with matching of dev\n"); - ret = -EINVAL; - goto err_put_txdev; - } /* * As TX is the main CSR reg interface, which should not be suspended first. diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index d7aca6567c2d..2fc234adca5f 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -678,6 +678,7 @@ struct wsa881x_priv { */ unsigned int sd_n_val; int active_ports; + bool hw_init; bool port_prepared[WSA881X_MAX_SWR_PORTS]; bool port_enable[WSA881X_MAX_SWR_PORTS]; }; @@ -687,6 +688,9 @@ static void wsa881x_init(struct wsa881x_priv *wsa881x) struct regmap *rm = wsa881x->regmap; unsigned int val = 0; + if (wsa881x->hw_init) + return; + regmap_register_patch(wsa881x->regmap, wsa881x_rev_2_0, ARRAY_SIZE(wsa881x_rev_2_0)); @@ -724,6 +728,8 @@ static void wsa881x_init(struct wsa881x_priv *wsa881x) regmap_update_bits(rm, WSA881X_OTP_REG_28, 0x3F, 0x3A); regmap_update_bits(rm, WSA881X_BONGO_RESRV_REG1, 0xFF, 0xB2); regmap_update_bits(rm, WSA881X_BONGO_RESRV_REG2, 0xFF, 0x05); + + wsa881x->hw_init = true; } static int wsa881x_component_probe(struct snd_soc_component *comp) @@ -1067,6 +1073,9 @@ static int wsa881x_update_status(struct sdw_slave *slave, { struct wsa881x_priv *wsa881x = dev_get_drvdata(&slave->dev); + if (status == SDW_SLAVE_UNATTACHED) + wsa881x->hw_init = false; + if (status == SDW_SLAVE_ATTACHED && slave->dev_num > 0) wsa881x_init(wsa881x); diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c index c3046e260cb9..468d2b38a22a 100644 --- a/sound/soc/codecs/wsa883x.c +++ b/sound/soc/codecs/wsa883x.c @@ -475,6 +475,7 @@ struct wsa883x_priv { int active_ports; int dev_mode; int comp_offset; + bool hw_init; /* * Protects temperature reading code (related to speaker protection) and * fields: temperature and pa_on. @@ -1043,6 +1044,9 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) struct regmap *regmap = wsa883x->regmap; int variant, version, ret; + if (wsa883x->hw_init) + return 0; + ret = regmap_read(regmap, WSA883X_OTP_REG_0, &variant); if (ret) return ret; @@ -1054,22 +1058,23 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) switch (variant) { case WSA8830: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8830\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8830\n", + version); break; case WSA8835: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835\n", + version); break; case WSA8832: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8832\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8832\n", + version); break; case WSA8835_V2: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835_V2\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835_V2\n", + version); break; default: + dev_warn(wsa883x->dev, "unknown variant: %d\n", variant); break; } @@ -1085,6 +1090,8 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) wsa883x->comp_offset); } + wsa883x->hw_init = true; + return 0; } @@ -1093,6 +1100,9 @@ static int wsa883x_update_status(struct sdw_slave *slave, { struct wsa883x_priv *wsa883x = dev_get_drvdata(&slave->dev); + if (status == SDW_SLAVE_UNATTACHED) + wsa883x->hw_init = false; + if (status == SDW_SLAVE_ATTACHED && slave->dev_num > 0) return wsa883x_init(wsa883x); diff --git a/sound/soc/codecs/wsa884x.c b/sound/soc/codecs/wsa884x.c index 887edd2be705..6c6b497657d0 100644 --- a/sound/soc/codecs/wsa884x.c +++ b/sound/soc/codecs/wsa884x.c @@ -1534,7 +1534,7 @@ static void wsa884x_init(struct wsa884x_priv *wsa884x) wsa884x_set_gain_parameters(wsa884x); - wsa884x->hw_init = false; + wsa884x->hw_init = true; } static int wsa884x_update_status(struct sdw_slave *slave, @@ -2109,7 +2109,6 @@ static int wsa884x_probe(struct sdw_slave *pdev, /* Start in cache-only until device is enumerated */ regcache_cache_only(wsa884x->regmap, true); - wsa884x->hw_init = true; if (IS_REACHABLE(CONFIG_HWMON)) { struct device *hwmon; diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 355f7ec8943c..bdc02e85b089 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1179,9 +1179,9 @@ void graph_util_parse_link_direction(struct device_node *np, bool is_playback_only = of_property_read_bool(np, "playback-only"); bool is_capture_only = of_property_read_bool(np, "capture-only"); - if (playback_only) + if (np && playback_only) *playback_only = is_playback_only; - if (capture_only) + if (np && capture_only) *capture_only = is_capture_only; } EXPORT_SYMBOL_GPL(graph_util_parse_link_direction); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 2c1001148d54..8721a098d53f 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -767,6 +767,14 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { { .callback = sof_sdw_quirk_cb, .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0DD6") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_ptlrvp"), }, .driver_data = (void *)(SOC_SDW_PCH_DMIC), diff --git a/sound/soc/intel/boards/sof_sdw_common.h b/sound/soc/intel/boards/sof_sdw_common.h index 3aa1dcec5172..5390f0a749d6 100644 --- a/sound/soc/intel/boards/sof_sdw_common.h +++ b/sound/soc/intel/boards/sof_sdw_common.h @@ -46,11 +46,11 @@ enum { #define SOC_SDW_NO_AGGREGATION BIT(14) /* BT audio offload: reserve 3 bits for future */ -#define SOF_BT_OFFLOAD_SSP_SHIFT 15 -#define SOF_BT_OFFLOAD_SSP_MASK (GENMASK(17, 15)) +#define SOF_BT_OFFLOAD_SSP_SHIFT 18 +#define SOF_BT_OFFLOAD_SSP_MASK (GENMASK(20, 18)) #define SOF_BT_OFFLOAD_SSP(quirk) \ (((quirk) << SOF_BT_OFFLOAD_SSP_SHIFT) & SOF_BT_OFFLOAD_SSP_MASK) -#define SOF_SSP_BT_OFFLOAD_PRESENT BIT(18) +#define SOF_SSP_BT_OFFLOAD_PRESENT BIT(21) struct intel_mc_ctx { struct sof_hdmi_private hdmi; diff --git a/sound/soc/sdw_utils/soc_sdw_cs42l43.c b/sound/soc/sdw_utils/soc_sdw_cs42l43.c index 4c954501e500..2685ff4f0932 100644 --- a/sound/soc/sdw_utils/soc_sdw_cs42l43.c +++ b/sound/soc/sdw_utils/soc_sdw_cs42l43.c @@ -44,7 +44,7 @@ static const struct snd_soc_dapm_route cs42l43_dmic_map[] = { static struct snd_soc_jack_pin soc_jack_pins[] = { { .pin = "Headphone", - .mask = SND_JACK_HEADPHONE, + .mask = SND_JACK_HEADPHONE | SND_JACK_LINEOUT, }, { .pin = "Headset Mic", diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index f169d95895ea..ccf149f949e8 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -841,6 +841,19 @@ struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_part(const u64 adr) } EXPORT_SYMBOL_NS(asoc_sdw_find_codec_info_part, "SND_SOC_SDW_UTILS"); +static struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_sdw_id(const struct sdw_slave_id *id) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(codec_info_list); i++) + if (id->part_id == codec_info_list[i].part_id && + (!codec_info_list[i].version_id || + id->sdw_version == codec_info_list[i].version_id)) + return &codec_info_list[i]; + + return NULL; +} + struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_acpi(const u8 *acpi_id) { int i; @@ -873,22 +886,46 @@ struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_dai(const char *dai_name, i } EXPORT_SYMBOL_NS(asoc_sdw_find_codec_info_dai, "SND_SOC_SDW_UTILS"); +static int asoc_sdw_find_codec_info_dai_index(const struct asoc_sdw_codec_info *codec_info, + const char *dai_name) +{ + int i; + + for (i = 0; i < codec_info->dai_num; i++) { + if (!strcmp(codec_info->dais[i].dai_name, dai_name)) + return i; + } + + return -ENOENT; +} + int asoc_sdw_rtd_init(struct snd_soc_pcm_runtime *rtd) { struct snd_soc_card *card = rtd->card; struct snd_soc_dapm_context *dapm = snd_soc_card_to_dapm(card); struct asoc_sdw_codec_info *codec_info; struct snd_soc_dai *dai; + struct sdw_slave *sdw_peripheral; const char *spk_components=""; int dai_index; int ret; int i; for_each_rtd_codec_dais(rtd, i, dai) { - codec_info = asoc_sdw_find_codec_info_dai(dai->name, &dai_index); + if (is_sdw_slave(dai->component->dev)) + sdw_peripheral = dev_to_sdw_dev(dai->component->dev); + else if (dai->component->dev->parent && is_sdw_slave(dai->component->dev->parent)) + sdw_peripheral = dev_to_sdw_dev(dai->component->dev->parent); + else + continue; + + codec_info = asoc_sdw_find_codec_info_sdw_id(&sdw_peripheral->id); if (!codec_info) return -EINVAL; + dai_index = asoc_sdw_find_codec_info_dai_index(codec_info, dai->name); + WARN_ON(dai_index < 0); + /* * A codec dai can be connected to different dai links for capture and playback, * but we only need to call the rtd_init function once. @@ -898,6 +935,10 @@ int asoc_sdw_rtd_init(struct snd_soc_pcm_runtime *rtd) if (codec_info->dais[dai_index].rtd_init_done) continue; + dev_dbg(card->dev, "%#x/%s initializing for %s/%s\n", + codec_info->part_id, codec_info->dais[dai_index].dai_name, + dai->component->name, dai->name); + /* * Add card controls and dapm widgets for the first codec dai. * The controls and widgets will be used for all codec dais. @@ -1414,10 +1455,6 @@ static int is_sdca_endpoint_present(struct device *dev, } slave = dev_to_sdw_dev(sdw_dev); - if (!slave) { - ret = -EINVAL; - goto put_device; - } /* Make sure BIOS provides SDCA properties */ if (!slave->sdca_data.interface_revision) { diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 624e9269fc25..ba42939d5f01 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -543,11 +543,11 @@ int snd_soc_bytes_get(struct snd_kcontrol *kcontrol, ucontrol->value.bytes.data[0] &= ~params->mask; break; case 2: - ((u16 *)(&ucontrol->value.bytes.data))[0] + ((__be16 *)(&ucontrol->value.bytes.data))[0] &= cpu_to_be16(~params->mask); break; case 4: - ((u32 *)(&ucontrol->value.bytes.data))[0] + ((__be32 *)(&ucontrol->value.bytes.data))[0] &= cpu_to_be32(~params->mask); break; default: diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index c1518dbee1b7..0bb85f92e106 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1549,6 +1549,7 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev) * name string if quirk flag is set. */ if (mach) { + const struct sof_intel_dsp_desc *chip = get_chip_info(sdev->pdata); bool tplg_fixup = false; bool dmic_fixup = false; @@ -1598,6 +1599,18 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev) sof_pdata->tplg_filename = tplg_filename; } + if (tplg_fixup && mach->mach_params.bt_link_mask && + chip->hw_ip_version >= SOF_INTEL_ACE_4_0) { + int bt_port = fls(mach->mach_params.bt_link_mask) - 1; + + tplg_filename = devm_kasprintf(sdev->dev, GFP_KERNEL, "%s-ssp%d-bt", + sof_pdata->tplg_filename, bt_port); + if (!tplg_filename) + return NULL; + + sof_pdata->tplg_filename = tplg_filename; + } + if (mach->link_mask) { mach->mach_params.links = mach->links; mach->mach_params.link_mask = mach->link_mask; @@ -1609,7 +1622,6 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev) if (tplg_fixup && mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_SSP_NUMBER && mach->mach_params.i2s_link_mask) { - const struct sof_intel_dsp_desc *chip = get_chip_info(sdev->pdata); int ssp_num; int mclk_mask; diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c index 2e7ac8ab71bb..1e755a716c63 100644 --- a/sound/soc/sunxi/sun4i-spdif.c +++ b/sound/soc/sunxi/sun4i-spdif.c @@ -171,6 +171,8 @@ * @reg_dac_txdata: TX FIFO offset for DMA config. * @has_reset: SoC needs reset deasserted. * @val_fctl_ftx: TX FIFO flush bitmask. + * @mclk_multiplier: ratio of internal MCLK divider + * @tx_clk_name: name of TX module clock if split clock design */ struct sun4i_spdif_quirks { unsigned int reg_dac_txdata; diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c index 261d9067d27b..e795907a3963 100644 --- a/sound/soc/tegra/tegra210_ahub.c +++ b/sound/soc/tegra/tegra210_ahub.c @@ -2077,7 +2077,7 @@ static const struct regmap_config tegra210_ahub_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = TEGRA210_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct regmap_config tegra186_ahub_regmap_config = { @@ -2085,7 +2085,7 @@ static const struct regmap_config tegra186_ahub_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = TEGRA186_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct regmap_config tegra264_ahub_regmap_config = { @@ -2094,7 +2094,7 @@ static const struct regmap_config tegra264_ahub_regmap_config = { .reg_stride = 4, .writeable_reg = tegra264_ahub_wr_reg, .max_register = TEGRA264_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct tegra_ahub_soc_data soc_data_tegra210 = { diff --git a/sound/soc/ti/davinci-evm.c b/sound/soc/ti/davinci-evm.c index 3848766d96c3..ad514c2e5a25 100644 --- a/sound/soc/ti/davinci-evm.c +++ b/sound/soc/ti/davinci-evm.c @@ -194,27 +194,32 @@ static int davinci_evm_probe(struct platform_device *pdev) return -EINVAL; dai->cpus->of_node = of_parse_phandle(np, "ti,mcasp-controller", 0); - if (!dai->cpus->of_node) - return -EINVAL; + if (!dai->cpus->of_node) { + ret = -EINVAL; + goto err_put; + } dai->platforms->of_node = dai->cpus->of_node; evm_soc_card.dev = &pdev->dev; ret = snd_soc_of_parse_card_name(&evm_soc_card, "ti,model"); if (ret) - return ret; + goto err_put; mclk = devm_clk_get(&pdev->dev, "mclk"); if (PTR_ERR(mclk) == -EPROBE_DEFER) { - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto err_put; } else if (IS_ERR(mclk)) { dev_dbg(&pdev->dev, "mclk not found.\n"); mclk = NULL; } drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; + if (!drvdata) { + ret = -ENOMEM; + goto err_put; + } drvdata->mclk = mclk; @@ -224,7 +229,8 @@ static int davinci_evm_probe(struct platform_device *pdev) if (!drvdata->mclk) { dev_err(&pdev->dev, "No clock or clock rate defined.\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put; } drvdata->sysclk = clk_get_rate(drvdata->mclk); } else if (drvdata->mclk) { @@ -240,8 +246,25 @@ static int davinci_evm_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(&evm_soc_card, drvdata); ret = devm_snd_soc_register_card(&pdev->dev, &evm_soc_card); - if (ret) + if (ret) { dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret); + goto err_put; + } + + return ret; + +err_put: + dai->platforms->of_node = NULL; + + if (dai->cpus->of_node) { + of_node_put(dai->cpus->of_node); + dai->cpus->of_node = NULL; + } + + if (dai->codecs->of_node) { + of_node_put(dai->codecs->of_node); + dai->codecs->of_node = NULL; + } return ret; } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 3af71d42b9b9..bfe15b1cb66c 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1813,11 +1813,10 @@ static void __build_feature_ctl(struct usb_mixer_interface *mixer, range = (cval->max - cval->min) / cval->res; /* - * Are there devices with volume range more than 255? I use a bit more - * to be sure. 384 is a resolution magic number found on Logitech - * devices. It will definitively catch all buggy Logitech devices. + * There are definitely devices with a range of ~20,000, so let's be + * conservative and allow for a bit more. */ - if (range > 384) { + if (range > 65535) { usb_audio_warn(mixer->chip, "Warning! Unlikely big volume range (=%u), cval->res is probably wrong.", range); @@ -2946,10 +2945,23 @@ static int parse_audio_unit(struct mixer_build *state, int unitid) static void snd_usb_mixer_free(struct usb_mixer_interface *mixer) { + struct usb_mixer_elem_list *list, *next; + int id; + /* kill pending URBs */ snd_usb_mixer_disconnect(mixer); - kfree(mixer->id_elems); + /* Unregister controls first, snd_ctl_remove() frees the element */ + if (mixer->id_elems) { + for (id = 0; id < MAX_ID_ELEMS; id++) { + for (list = mixer->id_elems[id]; list; list = next) { + next = list->next_id_elem; + if (list->kctl) + snd_ctl_remove(mixer->chip->card, list->kctl); + } + } + kfree(mixer->id_elems); + } if (mixer->urb) { kfree(mixer->urb->transfer_buffer); usb_free_urb(mixer->urb); diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index f2446bf3982c..bef8c9e544dd 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -2533,13 +2533,13 @@ static int scarlett2_usb_get_config( err = scarlett2_usb_get(mixer, config_item->offset, buf, size); if (err < 0) return err; - if (size == 2) { + if (config_item->size == 16) { u16 *buf_16 = buf; for (i = 0; i < count; i++, buf_16++) *buf_16 = le16_to_cpu(*(__le16 *)buf_16); - } else if (size == 4) { - u32 *buf_32 = buf; + } else if (config_item->size == 32) { + u32 *buf_32 = (u32 *)buf; for (i = 0; i < count; i++, buf_32++) *buf_32 = le32_to_cpu(*(__le32 *)buf_32); diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 54d01dfd820f..682b6c1fe76b 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1553,7 +1553,8 @@ static int prepare_playback_urb(struct snd_usb_substream *subs, for (i = 0; i < ctx->packets; i++) { counts = snd_usb_endpoint_next_packet_size(ep, ctx, i, avail); - if (counts < 0) + if (counts < 0 || + (frames + counts) * stride > ctx->buffer_size) break; /* set up descriptor */ urb->iso_frame_desc[i].offset = frames * stride; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index f38330b095e9..2d9f28558874 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2390,6 +2390,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x2d99, 0x0026, /* HECATE G2 GAMING HEADSET */ QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), + DEVICE_FLG(0x2fc6, 0xf06b, /* MOONDROP Moonriver2 Ti */ + QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x2fc6, 0xf0b7, /* iBasso DC07 Pro */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index f898c47e551f..9b73c1aa3ad7 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -81,7 +81,6 @@ #define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 -#define ARM_CPU_PART_CORTEX_X1C 0xD4C #define ARM_CPU_PART_CORTEX_A520 0xD80 #define ARM_CPU_PART_CORTEX_A710 0xD47 #define ARM_CPU_PART_CORTEX_A715 0xD4D @@ -93,6 +92,7 @@ #define ARM_CPU_PART_NEOVERSE_V2 0xD4F #define ARM_CPU_PART_CORTEX_A720 0xD81 #define ARM_CPU_PART_CORTEX_X4 0xD82 +#define ARM_CPU_PART_NEOVERSE_V3AE 0xD83 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define ARM_CPU_PART_CORTEX_X925 0xD85 #define ARM_CPU_PART_CORTEX_A725 0xD87 @@ -130,6 +130,7 @@ #define NVIDIA_CPU_PART_DENVER 0x003 #define NVIDIA_CPU_PART_CARMEL 0x004 +#define NVIDIA_CPU_PART_OLYMPUS 0x010 #define FUJITSU_CPU_PART_A64FX 0x001 @@ -171,7 +172,6 @@ #define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) -#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715) @@ -183,6 +183,7 @@ #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) +#define MIDR_NEOVERSE_V3AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3AE) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) #define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) @@ -222,6 +223,7 @@ #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER) #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) +#define MIDR_NVIDIA_OLYMPUS MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_OLYMPUS) #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX) #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) #define MIDR_HISI_HIP09 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP09) @@ -245,7 +247,7 @@ /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX #define MIDR_FUJITSU_ERRATUM_010001_MASK (~MIDR_CPU_VAR_REV(1, 0)) -#define TCR_CLEAR_FUJITSU_ERRATUM_010001 (TCR_NFD1 | TCR_NFD0) +#define TCR_CLEAR_FUJITSU_ERRATUM_010001 (TCR_EL1_NFD1 | TCR_EL1_NFD0) #ifndef __ASSEMBLER__ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index ccc01ad6ff7c..c3b53beb1300 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -314,6 +314,7 @@ #define X86_FEATURE_SM4 (12*32+ 2) /* SM4 instructions */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_LASS (12*32+ 6) /* "lass" Linear Address Space Separation */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */ #define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* Intel Architectural PerfMon Extension */ #define X86_FEATURE_FZRM (12*32+10) /* Fast zero-length REP MOVSB */ @@ -338,6 +339,7 @@ #define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ #define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */ #define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/ +#define X86_FEATURE_EFER_LMSLE_MBZ (13*32+20) /* EFER.LMSLE must be zero */ #define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */ @@ -502,6 +504,15 @@ #define X86_FEATURE_IBPB_EXIT_TO_USER (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */ #define X86_FEATURE_ABMC (21*32+15) /* Assignable Bandwidth Monitoring Counters */ #define X86_FEATURE_MSR_IMM (21*32+16) /* MSR immediate form instructions */ +#define X86_FEATURE_SGX_EUPDATESVN (21*32+17) /* Support for ENCLS[EUPDATESVN] instruction */ + +#define X86_FEATURE_SDCIAE (21*32+18) /* L3 Smart Data Cache Injection Allocation Enforcement */ +#define X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO (21*32+19) /* + * Clear CPU buffers before VM-Enter if the vCPU + * can access host MMIO (ignored for all intents + * and purposes if CLEAR_CPU_BUF_VM is set). + */ +#define X86_FEATURE_X2AVIC_EXT (21*32+20) /* AMD SVM x2AVIC support for 4k vCPUs */ /* * BUG word(s) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 9e1720d73244..3d0a0950d20a 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -166,6 +166,10 @@ * Processor MMIO stale data * vulnerabilities. */ +#define ARCH_CAP_MCU_ENUM BIT(16) /* + * Indicates the presence of microcode update + * feature enumeration and status information. + */ #define ARCH_CAP_FB_CLEAR BIT(17) /* * VERW clears CPU fill buffer * even on MDS_NO CPUs. @@ -327,6 +331,26 @@ PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \ PERF_CAP_PEBS_TIMING_INFO) +/* Arch PEBS */ +#define MSR_IA32_PEBS_BASE 0x000003f4 +#define MSR_IA32_PEBS_INDEX 0x000003f5 +#define ARCH_PEBS_OFFSET_MASK 0x7fffff +#define ARCH_PEBS_INDEX_WR_SHIFT 4 + +#define ARCH_PEBS_RELOAD 0xffffffff +#define ARCH_PEBS_CNTR_ALLOW BIT_ULL(35) +#define ARCH_PEBS_CNTR_GP BIT_ULL(36) +#define ARCH_PEBS_CNTR_FIXED BIT_ULL(37) +#define ARCH_PEBS_CNTR_METRICS BIT_ULL(38) +#define ARCH_PEBS_LBR_SHIFT 40 +#define ARCH_PEBS_LBR (0x3ull << ARCH_PEBS_LBR_SHIFT) +#define ARCH_PEBS_VECR_XMM BIT_ULL(49) +#define ARCH_PEBS_GPR BIT_ULL(61) +#define ARCH_PEBS_AUX BIT_ULL(62) +#define ARCH_PEBS_EN BIT_ULL(63) +#define ARCH_PEBS_CNTR_MASK (ARCH_PEBS_CNTR_GP | ARCH_PEBS_CNTR_FIXED | \ + ARCH_PEBS_CNTR_METRICS) + #define MSR_IA32_RTIT_CTL 0x00000570 #define RTIT_CTL_TRACEEN BIT(0) #define RTIT_CTL_CYCLEACC BIT(1) @@ -929,6 +953,10 @@ #define MSR_IA32_APICBASE_BASE (0xfffff<<12) #define MSR_IA32_UCODE_WRITE 0x00000079 + +#define MSR_IA32_MCU_ENUMERATION 0x0000007b +#define MCU_STAGING BIT(4) + #define MSR_IA32_UCODE_REV 0x0000008b /* Intel SGX Launch Enclave Public Key Hash MSRs */ @@ -1226,6 +1254,8 @@ #define MSR_IA32_VMX_VMFUNC 0x00000491 #define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492 +#define MSR_IA32_MCU_STAGING_MBOX_ADDR 0x000007a5 + /* Resctrl MSRs: */ /* - Intel: */ #define MSR_IA32_L3_QOS_CFG 0xc81 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index d420c9c066d4..7ceff6583652 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -502,6 +502,7 @@ struct kvm_sync_regs { /* vendor-specific groups and attributes for system fd */ #define KVM_X86_GRP_SEV 1 # define KVM_X86_SEV_VMSA_FEATURES 0 +# define KVM_X86_SNP_POLICY_BITS 1 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index a7f030fc5e83..362cf8f4a0a0 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -99,7 +99,8 @@ FEATURE_TESTS_BASIC := \ libzstd \ disassembler-four-args \ disassembler-init-styled \ - file-handle + file-handle \ + libopenssl # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list # of all feature tests @@ -147,7 +148,8 @@ FEATURE_DISPLAY ?= \ lzma \ bpf \ libaio \ - libzstd + libzstd \ + libopenssl # # Declare group members of a feature to display the logical OR of the detection diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 87a5a908d6fa..0d5a15654b17 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -67,12 +67,13 @@ FILES= \ test-libopencsd.bin \ test-clang.bin \ test-llvm.bin \ - test-llvm-perf.bin \ + test-llvm-perf.bin \ test-libaio.bin \ test-libzstd.bin \ test-clang-bpf-co-re.bin \ test-file-handle.bin \ - test-libpfm4.bin + test-libpfm4.bin \ + test-libopenssl.bin FILES := $(addprefix $(OUTPUT),$(FILES)) @@ -106,7 +107,7 @@ all: $(FILES) __BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS) BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1 BUILD_BFD = $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl - BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -ldl -lz -llzma -lzstd + BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -ldl -lz -llzma -lzstd -lssl __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS) BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1 @@ -381,6 +382,9 @@ $(OUTPUT)test-file-handle.bin: $(OUTPUT)test-libpfm4.bin: $(BUILD) -lpfm +$(OUTPUT)test-libopenssl.bin: + $(BUILD) -lssl + $(OUTPUT)test-bpftool-skeletons.bin: $(SYSTEM_BPFTOOL) version | grep '^features:.*skeletons' \ > $(@:.bin=.make.output) 2>&1 diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index eb346160d0ba..1488bf6e6078 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -142,6 +142,10 @@ # include "test-libtraceevent.c" #undef main +#define main main_test_libopenssl +# include "test-libopenssl.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -173,6 +177,7 @@ int main(int argc, char *argv[]) main_test_reallocarray(); main_test_libzstd(); main_test_libtraceevent(); + main_test_libopenssl(); return 0; } diff --git a/tools/build/feature/test-libopenssl.c b/tools/build/feature/test-libopenssl.c new file mode 100644 index 000000000000..168c45894e8b --- /dev/null +++ b/tools/build/feature/test-libopenssl.c @@ -0,0 +1,7 @@ +#include <openssl/ssl.h> +#include <openssl/opensslv.h> + +int main(void) +{ + return SSL_library_init(); +} diff --git a/tools/include/io_uring/mini_liburing.h b/tools/include/io_uring/mini_liburing.h index 9ccb16074eb5..44be4446feda 100644 --- a/tools/include/io_uring/mini_liburing.h +++ b/tools/include/io_uring/mini_liburing.h @@ -6,6 +6,7 @@ #include <stdio.h> #include <string.h> #include <unistd.h> +#include <sys/uio.h> struct io_sq_ring { unsigned int *head; @@ -55,6 +56,7 @@ struct io_uring { struct io_uring_sq sq; struct io_uring_cq cq; int ring_fd; + unsigned flags; }; #if defined(__x86_64) || defined(__i386__) @@ -72,7 +74,14 @@ static inline int io_uring_mmap(int fd, struct io_uring_params *p, void *ptr; int ret; - sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned int); + if (p->flags & IORING_SETUP_NO_SQARRAY) { + sq->ring_sz = p->cq_off.cqes; + sq->ring_sz += p->cq_entries * sizeof(struct io_uring_cqe); + } else { + sq->ring_sz = p->sq_off.array; + sq->ring_sz += p->sq_entries * sizeof(unsigned int); + } + ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING); if (ptr == MAP_FAILED) @@ -83,7 +92,8 @@ static inline int io_uring_mmap(int fd, struct io_uring_params *p, sq->kring_entries = ptr + p->sq_off.ring_entries; sq->kflags = ptr + p->sq_off.flags; sq->kdropped = ptr + p->sq_off.dropped; - sq->array = ptr + p->sq_off.array; + if (!(p->flags & IORING_SETUP_NO_SQARRAY)) + sq->array = ptr + p->sq_off.array; size = p->sq_entries * sizeof(struct io_uring_sqe); sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE, @@ -126,28 +136,39 @@ static inline int io_uring_enter(int fd, unsigned int to_submit, flags, sig, _NSIG / 8); } -static inline int io_uring_queue_init(unsigned int entries, - struct io_uring *ring, - unsigned int flags) +static inline int io_uring_queue_init_params(unsigned int entries, + struct io_uring *ring, + struct io_uring_params *p) { - struct io_uring_params p; int fd, ret; memset(ring, 0, sizeof(*ring)); - memset(&p, 0, sizeof(p)); - p.flags = flags; - fd = io_uring_setup(entries, &p); + fd = io_uring_setup(entries, p); if (fd < 0) return fd; - ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq); - if (!ret) + ret = io_uring_mmap(fd, p, &ring->sq, &ring->cq); + if (!ret) { ring->ring_fd = fd; - else + ring->flags = p->flags; + } else { close(fd); + } return ret; } +static inline int io_uring_queue_init(unsigned int entries, + struct io_uring *ring, + unsigned int flags) +{ + struct io_uring_params p; + + memset(&p, 0, sizeof(p)); + p.flags = flags; + + return io_uring_queue_init_params(entries, ring, &p); +} + /* Get a sqe */ static inline struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring) { @@ -199,10 +220,18 @@ static inline int io_uring_submit(struct io_uring *ring) ktail = *sq->ktail; to_submit = sq->sqe_tail - sq->sqe_head; - for (submitted = 0; submitted < to_submit; submitted++) { - read_barrier(); - sq->array[ktail++ & mask] = sq->sqe_head++ & mask; + + if (!(ring->flags & IORING_SETUP_NO_SQARRAY)) { + for (submitted = 0; submitted < to_submit; submitted++) { + read_barrier(); + sq->array[ktail++ & mask] = sq->sqe_head++ & mask; + } + } else { + ktail += to_submit; + sq->sqe_head += to_submit; + submitted = to_submit; } + if (!submitted) return 0; diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h index 65db9349f905..3de43b12209e 100644 --- a/tools/include/linux/gfp_types.h +++ b/tools/include/linux/gfp_types.h @@ -55,9 +55,7 @@ enum { #ifdef CONFIG_LOCKDEP ___GFP_NOLOCKDEP_BIT, #endif -#ifdef CONFIG_SLAB_OBJ_EXT ___GFP_NO_OBJ_EXT_BIT, -#endif ___GFP_LAST_BIT }; @@ -98,11 +96,7 @@ enum { #else #define ___GFP_NOLOCKDEP 0 #endif -#ifdef CONFIG_SLAB_OBJ_EXT #define ___GFP_NO_OBJ_EXT BIT(___GFP_NO_OBJ_EXT_BIT) -#else -#define ___GFP_NO_OBJ_EXT 0 -#endif /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h index 4928e33d44ac..d41f8a261bce 100644 --- a/tools/include/linux/types.h +++ b/tools/include/linux/types.h @@ -88,6 +88,14 @@ typedef struct { # define __aligned_u64 __u64 __attribute__((aligned(8))) #endif +#ifndef __aligned_be64 +# define __aligned_be64 __be64 __attribute__((aligned(8))) +#endif + +#ifndef __aligned_le64 +# define __aligned_le64 __le64 __attribute__((aligned(8))) +#endif + struct list_head { struct list_head *next, *prev; }; diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 04e0077fb4c9..942370b3f5d2 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -857,9 +857,11 @@ __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) __SYSCALL(__NR_file_getattr, sys_file_getattr) #define __NR_file_setattr 469 __SYSCALL(__NR_file_setattr, sys_file_setattr) +#define __NR_listns 470 +__SYSCALL(__NR_listns, sys_listns) #undef __NR_syscalls -#define __NR_syscalls 470 +#define __NR_syscalls 471 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 3cd5cf15e3c9..27cc159c1d27 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -906,6 +906,21 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT 6 +/** + * DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE + * + * If set to 1 the DRM core will allow setting the COLOR_PIPELINE + * property on a &drm_plane, as well as drm_colorop properties. + * + * Setting of these plane properties will be rejected when this client + * cap is set: + * - COLOR_ENCODING + * - COLOR_RANGE + * + * The client must enable &DRM_CLIENT_CAP_ATOMIC first. + */ +#define DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE 7 + /* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 52f6000ab020..dddb781b0507 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -179,6 +179,7 @@ struct kvm_xen_exit { #define KVM_EXIT_LOONGARCH_IOCSR 38 #define KVM_EXIT_MEMORY_FAULT 39 #define KVM_EXIT_TDX 40 +#define KVM_EXIT_ARM_SEA 41 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -473,6 +474,14 @@ struct kvm_run { } setup_event_notify; }; } tdx; + /* KVM_EXIT_ARM_SEA */ + struct { +#define KVM_EXIT_ARM_SEA_FLAG_GPA_VALID (1ULL << 0) + __u64 flags; + __u64 esr; + __u64 gva; + __u64 gpa; + } arm_sea; /* Fix the size of the union. */ char padding[256]; }; @@ -963,6 +972,8 @@ struct kvm_enable_cap { #define KVM_CAP_RISCV_MP_STATE_RESET 242 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 #define KVM_CAP_GUEST_MEMFD_FLAGS 244 +#define KVM_CAP_ARM_SEA_TO_USER 245 +#define KVM_CAP_S390_USER_OPEREXEC 246 struct kvm_irq_routing_irqchip { __u32 irqchip; diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index c44a8fb3e418..72f03153dd32 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -2,7 +2,7 @@ /* * Performance events: * - * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008-2009, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * diff --git a/tools/mm/page_owner_sort.c b/tools/mm/page_owner_sort.c index 14c67e9e84c4..e6954909401c 100644 --- a/tools/mm/page_owner_sort.c +++ b/tools/mm/page_owner_sort.c @@ -181,7 +181,11 @@ static int compare_ts(const void *p1, const void *p2) { const struct block_list *l1 = p1, *l2 = p2; - return l1->ts_nsec < l2->ts_nsec ? -1 : 1; + if (l1->ts_nsec < l2->ts_nsec) + return -1; + if (l1->ts_nsec > l2->ts_nsec) + return 1; + return 0; } static int compare_cull_condition(const void *p1, const void *p2) diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index 7736b492f559..9b692f368be7 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -41,7 +41,7 @@ clean distclean: rm -rf pyynl.egg-info rm -rf build -install: libynl.a lib/*.h +install: libynl.a lib/*.h ynltool @echo -e "\tINSTALL libynl.a" @$(INSTALL) -d $(DESTDIR)$(libdir) @$(INSTALL) -m 0644 libynl.a $(DESTDIR)$(libdir)/libynl.a @@ -51,7 +51,7 @@ install: libynl.a lib/*.h @echo -e "\tINSTALL pyynl" @pip install --prefix=$(DESTDIR)$(prefix) . @make -C generated install - @make -C tests install + @make -C ynltool install run_tests: @$(MAKE) -C tests run_tests diff --git a/tools/net/ynl/pyynl/lib/doc_generator.py b/tools/net/ynl/pyynl/lib/doc_generator.py index 3a16b8eb01ca..8b922d8f89e8 100644 --- a/tools/net/ynl/pyynl/lib/doc_generator.py +++ b/tools/net/ynl/pyynl/lib/doc_generator.py @@ -166,13 +166,13 @@ class YnlDocGenerator: continue lines.append(self.fmt.rst_paragraph(self.fmt.bold(key), level + 1)) if key in ['request', 'reply']: - lines.append(self.parse_do_attributes(do_dict[key], level + 1) + "\n") + lines.append(self.parse_op_attributes(do_dict[key], level + 1) + "\n") else: lines.append(self.fmt.headroom(level + 2) + do_dict[key] + "\n") return "\n".join(lines) - def parse_do_attributes(self, attrs: Dict[str, Any], level: int = 0) -> str: + def parse_op_attributes(self, attrs: Dict[str, Any], level: int = 0) -> str: """Parse 'attributes' section""" if "attributes" not in attrs: return "" @@ -184,7 +184,7 @@ class YnlDocGenerator: def parse_operations(self, operations: List[Dict[str, Any]], namespace: str) -> str: """Parse operations block""" - preprocessed = ["name", "doc", "title", "do", "dump", "flags"] + preprocessed = ["name", "doc", "title", "do", "dump", "flags", "event"] linkable = ["fixed-header", "attribute-set"] lines = [] @@ -217,6 +217,9 @@ class YnlDocGenerator: if "dump" in operation: lines.append(self.fmt.rst_paragraph(":dump:", 0)) lines.append(self.parse_do(operation["dump"], 0)) + if "event" in operation: + lines.append(self.fmt.rst_paragraph(":event:", 0)) + lines.append(self.parse_op_attributes(operation["event"], 0)) # New line after fields lines.append("\n") diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 81b4ecd89100..d9809276db98 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -21,7 +21,7 @@ files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do # params: 0 1 2 3 # $YAML YNL-GEN kernel $mode - params=( $(git grep -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) + params=( $(git grep --no-line-number -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) args=$(sed -n 's@/\* YNL-ARG \(.*\) \*/@\1@p' $f) if [ $f -nt ${params[0]} -a -z "$force" ]; then diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index ad6e1ec706ce..a40f30232929 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -72,23 +72,40 @@ HOST_OVERRIDES := CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" # # To support disassembly, objtool needs libopcodes which is provided -# with libbdf (binutils-dev or binutils-devel package). +# with libbfd (binutils-dev or binutils-devel package). # -FEATURE_USER = .objtool -FEATURE_TESTS = libbfd disassembler-init-styled -FEATURE_DISPLAY = -include $(srctree)/tools/build/Makefile.feature - -ifeq ($(feature-disassembler-init-styled), 1) - OBJTOOL_CFLAGS += -DDISASM_INIT_STYLED -endif +# We check using HOSTCC directly rather than the shared feature framework +# because objtool is a host tool that links against host libraries. +# +# When using shared libraries, -lopcodes is sufficient as dependencies are +# resolved automatically. With static libraries, we must explicitly link +# against libopcodes' dependencies: libbfd, libiberty, and sometimes libz. +# Try each combination and use the first one that succeeds. +# +LIBOPCODES_LIBS := $(shell \ + for libs in "-lopcodes" \ + "-lopcodes -lbfd" \ + "-lopcodes -lbfd -liberty" \ + "-lopcodes -lbfd -liberty -lz"; do \ + echo 'extern void disassemble_init_for_target(void *);' \ + 'int main(void) { disassemble_init_for_target(0); return 0; }' | \ + $(HOSTCC) -xc - -o /dev/null $$libs 2>/dev/null && \ + echo "$$libs" && break; \ + done) + +# Styled disassembler support requires binutils >= 2.39 +HAVE_DISASM_STYLED := $(shell echo '$(pound)include <dis-asm.h>' | \ + $(HOSTCC) -E -xc - 2>/dev/null | grep -q disassembler_style && echo y) BUILD_DISAS := n -ifeq ($(feature-libbfd),1) +ifneq ($(LIBOPCODES_LIBS),) BUILD_DISAS := y - OBJTOOL_CFLAGS += -DDISAS -DPACKAGE="objtool" - OBJTOOL_LDFLAGS += -lopcodes + OBJTOOL_CFLAGS += -DDISAS -DPACKAGE='"objtool"' + OBJTOOL_LDFLAGS += $(LIBOPCODES_LIBS) +ifeq ($(HAVE_DISASM_STYLED),y) + OBJTOOL_CFLAGS += -DDISASM_INIT_STYLED +endif endif export BUILD_DISAS diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index 25ff7942b4d5..2b27b54096b8 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -152,8 +152,8 @@ static inline void unindent(int *unused) { indent--; } if (unlikely(insn->sym && insn->sym->pfunc && \ insn->sym->pfunc->debug_checksum)) { \ char *insn_off = offstr(insn->sec, insn->offset); \ - __dbg("checksum: %s %s %016lx", \ - func->name, insn_off, checksum); \ + __dbg("checksum: %s %s %016llx", \ + func->name, insn_off, (unsigned long long)checksum);\ free(insn_off); \ } \ }) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index bd9f4804d56b..d8d25f62aaad 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -701,6 +701,11 @@ ifndef NO_LIBBPF endif endif +ifeq ($(feature-libopenssl), 1) + $(call detected,CONFIG_LIBOPENSSL) + CFLAGS += -DHAVE_LIBOPENSSL_SUPPORT +endif + ifndef BUILD_BPF_SKEL # BPF skeletons control a large number of perf features, by default # they are enabled. @@ -717,6 +722,9 @@ ifeq ($(BUILD_BPF_SKEL),1) else ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) $(warning Warning: Disabled BPF skeletons as libbpf is required) BUILD_BPF_SKEL := 0 + else ifeq ($(filter -DHAVE_LIBOPENSSL_SUPPORT, $(CFLAGS)),) + $(warning Warning: Disabled BPF skeletons as libopenssl is required) + BUILD_BPF_SKEL := 0 else ifeq ($(call get-executable,$(CLANG)),) $(warning Warning: Disabled BPF skeletons as clang ($(CLANG)) is missing) BUILD_BPF_SKEL := 0 diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl index b07e699aaa3c..fd09afae72a2 100644 --- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl @@ -484,3 +484,4 @@ 467 common open_tree_attr sys_open_tree_attr 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr +470 common listns sys_listns diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 7a7049c2c307..9b92bddf06b5 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -384,3 +384,4 @@ 467 n64 open_tree_attr sys_open_tree_attr 468 n64 file_getattr sys_file_getattr 469 n64 file_setattr sys_file_setattr +470 n64 listns sys_listns diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index b453e80dfc00..ec4458cdb97b 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -560,3 +560,4 @@ 467 common open_tree_attr sys_open_tree_attr 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr +470 common listns sys_listns diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 8a6744d658db..5863787ab036 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -472,3 +472,4 @@ 467 common open_tree_attr sys_open_tree_attr sys_open_tree_attr 468 common file_getattr sys_file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr sys_file_setattr +470 common listns sys_listns sys_listns diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl index 5e9c9eff5539..969c11325ade 100644 --- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl @@ -473,3 +473,4 @@ 467 common open_tree_attr sys_open_tree_attr 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr +470 common listns sys_listns diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl index ebb7d06d1044..39aa26b6a50b 100644 --- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl @@ -515,3 +515,4 @@ 467 common open_tree_attr sys_open_tree_attr 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr +470 common listns sys_listns diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl index 4877e16da69a..e979a3eac7a3 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl @@ -475,3 +475,4 @@ 467 i386 open_tree_attr sys_open_tree_attr 468 i386 file_getattr sys_file_getattr 469 i386 file_setattr sys_file_setattr +470 i386 listns sys_listns diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index ced2a1deecd7..8a4ac4841be6 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -394,6 +394,7 @@ 467 common open_tree_attr sys_open_tree_attr 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr +470 common listns sys_listns # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl index 374e4cb788d8..438a3b170402 100644 --- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl @@ -440,3 +440,4 @@ 467 common open_tree_attr sys_open_tree_attr 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr +470 common listns sys_listns diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index c98104481c8a..539e779e3268 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -276,12 +276,14 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) { char filename[PATH_MAX]; struct build_id bid = { .size = 0, }; + int err; if (!dso__build_id_filename(dso, filename, sizeof(filename), false)) return true; - if (filename__read_build_id(filename, &bid) == -1) { - if (errno == ENOENT) + err = filename__read_build_id(filename, &bid); + if (err < 0) { + if (err == -ENOENT) return false; pr_warning("Problems with %s file, consider removing it from the cache\n", diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 5cbca0bacd35..87a5491048ac 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -4,7 +4,7 @@ * * Builtin list command: list all event types * - * Copyright (C) 2009, Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2009, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar <mingo@redhat.com> * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> */ diff --git a/tools/perf/tests/shell/kvm.sh b/tools/perf/tests/shell/kvm.sh index 2fafde1a29cc..2a399b83fe80 100755 --- a/tools/perf/tests/shell/kvm.sh +++ b/tools/perf/tests/shell/kvm.sh @@ -118,7 +118,7 @@ setup_qemu() { skip "/dev/kvm not accessible" fi - if ! perf kvm stat record -a sleep 0.01 >/dev/null 2>&1; then + if ! perf kvm stat record -o /dev/null -a sleep 0.01 >/dev/null 2>&1; then skip "No permission to record kvm events" fi diff --git a/tools/perf/tests/shell/top.sh b/tools/perf/tests/shell/top.sh index 768ebcf7a89c..ad7fccd09025 100755 --- a/tools/perf/tests/shell/top.sh +++ b/tools/perf/tests/shell/top.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf top tests +# perf top tests (exclusive) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 77d7c59f5d8b..ec715ad4bf25 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -32,11 +32,29 @@ typedef __kernel_sa_family_t sa_family_t; * 1003.1g requires sa_family_t and that sa_data is char. */ +/* Deprecated for in-kernel use. Use struct sockaddr_unsized instead. */ struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ char sa_data[14]; /* 14 bytes of protocol address */ }; +/** + * struct sockaddr_unsized - Unspecified size sockaddr for callbacks + * @sa_family: Address family (AF_UNIX, AF_INET, AF_INET6, etc.) + * @sa_data: Flexible array for address data + * + * This structure is designed for callback interfaces where the + * total size is known via the sockaddr_len parameter. Unlike struct + * sockaddr which has a fixed 14-byte sa_data limit or struct + * sockaddr_storage which has a fixed 128-byte sa_data limit, this + * structure can accommodate addresses of any size, but must be used + * carefully. + */ +struct sockaddr_unsized { + __kernel_sa_family_t sa_family; /* address family, AF_xxx */ + char sa_data[]; /* flexible address data */ +}; + struct linger { int l_onoff; /* Linger active */ int l_linger; /* How long to linger for */ @@ -450,10 +468,10 @@ extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); extern int __sys_listen_socket(struct socket *sock, int backlog); +extern int do_getsockname(struct socket *sock, int peer, + struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, - int __user *usockaddr_len); -extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, - int __user *usockaddr_len); + int __user *usockaddr_len, int peer); extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown_sock(struct socket *sock, int how); diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h index 3741ea1b73d8..aadfbf6e0cb3 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h @@ -4,6 +4,7 @@ #include <asm/fcntl.h> #include <linux/openat2.h> +#include <linux/types.h> #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) @@ -79,6 +80,17 @@ */ #define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET +/* Set/Get delegations */ +#define F_GETDELEG (F_LINUX_SPECIFIC_BASE + 15) +#define F_SETDELEG (F_LINUX_SPECIFIC_BASE + 16) + +/* Argument structure for F_GETDELEG and F_SETDELEG */ +struct delegation { + __u32 d_flags; /* Must be 0 */ + __u16 d_type; /* F_RDLCK, F_WRLCK, F_UNLCK */ + __u16 __pad; /* Must be 0 */ +}; + /* * Types of directory notifications that may be requested. */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index beb4c2d1e41c..66ca526cf786 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -298,8 +298,9 @@ struct file_attr { #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) #define BLKGETDISKSEQ _IOR(0x12,128,__u64) -/* 130-136 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */ +/* 130-136 and 142 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */ /* 137-141 are used by blk-crypto ioctls (uapi/linux/blk-crypto.h) */ +#define BLKTRACESETUP2 _IOWR(0x12, 142, struct blk_user_trace_setup2) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index 7fa67c2031a5..5d3f8c9e3a62 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -197,7 +197,7 @@ struct statmount { */ struct mnt_id_req { __u32 size; - __u32 spare; + __u32 mnt_ns_fd; __u64 mnt_id; __u64 param; __u64 mnt_ns_id; diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h index 5a049eeaecce..d3ce75ba938a 100644 --- a/tools/perf/trace/beauty/include/uapi/sound/asound.h +++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h @@ -60,7 +60,7 @@ struct snd_cea_861_aud_if { unsigned char db2_sf_ss; /* sample frequency and size */ unsigned char db3; /* not used, all zeros */ unsigned char db4_ca; /* channel allocation code */ - unsigned char db5_dminh_lsv; /* downmix inhibit & level-shit values */ + unsigned char db5_dminh_lsv; /* downmix inhibit & level-shift values */ }; /**************************************************************************** diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index dc19e72258f3..70dd9bee47c7 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -587,6 +587,7 @@ static const struct midr_range common_ds_encoding_cpus[] = { MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), + MIDR_ALL_VERSIONS(MIDR_NVIDIA_OLYMPUS), {}, }; diff --git a/tools/perf/util/libbfd.c b/tools/perf/util/libbfd.c index cc0c474cbfaa..79f4528234a9 100644 --- a/tools/perf/util/libbfd.c +++ b/tools/perf/util/libbfd.c @@ -426,8 +426,10 @@ int libbfd__read_build_id(const char *filename, struct build_id *bid) if (!filename) return -EFAULT; + + errno = 0; if (!is_regular_file(filename)) - return -EWOULDBLOCK; + return errno == 0 ? -EWOULDBLOCK : -errno; fd = open(filename, O_RDONLY); if (fd < 0) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 17c1c36a7bf9..000c89a1e50d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -251,8 +251,11 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); evsel = evsel__new_idx(attr, *idx); - if (!evsel) - goto out_err; + if (!evsel) { + perf_cpu_map__put(cpus); + perf_cpu_map__put(pmu_cpus); + return NULL; + } if (name) { evsel->name = strdup(name); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 957143fbf8a0..d1dcafa4b3b8 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -902,8 +902,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid) if (!filename) return -EFAULT; + + errno = 0; if (!is_regular_file(filename)) - return -EWOULDBLOCK; + return errno == 0 ? -EWOULDBLOCK : -errno; err = kmod_path__parse(&m, filename); if (err) diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index c6b17c14a2e9..8221dc9868f7 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -104,8 +104,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid) if (!filename) return -EFAULT; + + errno = 0; if (!is_regular_file(filename)) - return -EWOULDBLOCK; + return errno == 0 ? -EWOULDBLOCK : -errno; fd = open(filename, O_RDONLY); if (fd < 0) diff --git a/tools/sched_ext/scx_show_state.py b/tools/sched_ext/scx_show_state.py index 7cdcc6729ea4..02e43c184d43 100644 --- a/tools/sched_ext/scx_show_state.py +++ b/tools/sched_ext/scx_show_state.py @@ -27,16 +27,18 @@ def read_static_key(name): def state_str(state): return prog['scx_enable_state_str'][state].string_().decode() -ops = prog['scx_ops'] +root = prog['scx_root'] enable_state = read_atomic("scx_enable_state_var") -print(f'ops : {ops.name.string_().decode()}') +if root: + print(f'ops : {root.ops.name.string_().decode()}') +else: + print('ops : ') print(f'enabled : {read_static_key("__scx_enabled")}') print(f'switching_all : {read_int("scx_switching_all")}') print(f'switched_all : {read_static_key("__scx_switched_all")}') print(f'enable_state : {state_str(enable_state)} ({enable_state})') -print(f'in_softlockup : {prog["scx_in_softlockup"].value_()}') -print(f'breather_depth: {read_atomic("scx_breather_depth")}') +print(f'aborting : {prog["scx_aborting"].value_()}') print(f'bypass_depth : {prog["scx_bypass_depth"].value_()}') print(f'nr_rejected : {read_atomic("scx_nr_rejected")}') print(f'enable_seq : {read_atomic("scx_enable_seq")}') diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl index d1ae5e92c615..e74868be513c 100644 --- a/tools/scripts/syscall.tbl +++ b/tools/scripts/syscall.tbl @@ -410,3 +410,4 @@ 467 common open_tree_attr sys_open_tree_attr 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr +470 common listns sys_listns diff --git a/tools/testing/cxl/test/cxl_translate.c b/tools/testing/cxl/test/cxl_translate.c index 2200ae21795c..16328b2112b2 100644 --- a/tools/testing/cxl/test/cxl_translate.c +++ b/tools/testing/cxl/test/cxl_translate.c @@ -68,6 +68,8 @@ static u64 to_hpa(u64 dpa_offset, int pos, u8 r_eiw, u16 r_eig, u8 hb_ways, /* Calculate base HPA offset from DPA and position */ hpa_offset = cxl_calculate_hpa_offset(dpa_offset, pos, r_eiw, r_eig); + if (hpa_offset == ULLONG_MAX) + return ULLONG_MAX; if (math == XOR_MATH) { cximsd->nr_maps = hbiw_to_nr_maps[hb_ways]; @@ -258,19 +260,23 @@ static int test_random_params(void) pos = get_random_u32() % ways; dpa = get_random_u64() >> 12; + reverse_dpa = ULLONG_MAX; + reverse_pos = -1; + hpa = cxl_calculate_hpa_offset(dpa, pos, eiw, eig); - reverse_dpa = cxl_calculate_dpa_offset(hpa, eiw, eig); - reverse_pos = cxl_calculate_position(hpa, eiw, eig); - - if (reverse_dpa != dpa || reverse_pos != pos) { - pr_err("test random iter %d FAIL hpa=%llu, dpa=%llu reverse_dpa=%llu, pos=%d reverse_pos=%d eiw=%u eig=%u\n", - i, hpa, dpa, reverse_dpa, pos, reverse_pos, eiw, - eig); - - if (failures++ > 10) { - pr_err("test random too many failures, stop\n"); - break; - } + if (hpa != ULLONG_MAX) { + reverse_dpa = cxl_calculate_dpa_offset(hpa, eiw, eig); + reverse_pos = cxl_calculate_position(hpa, eiw, eig); + if (reverse_dpa == dpa && reverse_pos == pos) + continue; + } + + pr_err("test random iter %d FAIL hpa=%llu, dpa=%llu reverse_dpa=%llu, pos=%d reverse_pos=%d eiw=%u eig=%u\n", + i, hpa, dpa, reverse_dpa, pos, reverse_pos, eiw, eig); + + if (failures++ > 10) { + pr_err("test random too many failures, stop\n"); + break; } } pr_info("..... test random: PASS %d FAIL %d\n", i - failures, failures); diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 2f830ff8396c..945144e98507 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -57,6 +57,26 @@ void idr_alloc_test(void) idr_destroy(&idr); } +void idr_alloc2_test(void) +{ + int id; + struct idr idr = IDR_INIT_BASE(idr, 1); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 1, GFP_KERNEL); + assert(id == -ENOSPC); + + id = idr_alloc(&idr, idr_alloc2_test, 1, 2, GFP_KERNEL); + assert(id == 1); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 1, GFP_KERNEL); + assert(id == -ENOSPC); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 2, GFP_KERNEL); + assert(id == -ENOSPC); + + idr_destroy(&idr); +} + void idr_replace_test(void) { DEFINE_IDR(idr); @@ -409,6 +429,7 @@ void idr_checks(void) idr_replace_test(); idr_alloc_test(); + idr_alloc2_test(); idr_null_test(); idr_nowait_test(); idr_get_next_test(0); diff --git a/tools/testing/selftests/alsa/utimer-test.c b/tools/testing/selftests/alsa/utimer-test.c index c45cb226bd8f..d221972cd8fb 100644 --- a/tools/testing/selftests/alsa/utimer-test.c +++ b/tools/testing/selftests/alsa/utimer-test.c @@ -141,7 +141,6 @@ TEST_F(timer_f, utimer) { TEST(wrong_timers_test) { int timer_dev_fd; int utimer_fd; - size_t i; struct snd_timer_uinfo wrong_timer = { .resolution = 0, .id = UTIMER_DEFAULT_ID, diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index ee94c281888a..26159e0499c7 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -47,6 +47,7 @@ void test_xdp_context_test_run(void) struct test_xdp_context_test_run *skel = NULL; char data[sizeof(pkt_v4) + sizeof(__u32)]; char bad_ctx[sizeof(struct xdp_md) + 1]; + char large_data[256]; struct xdp_md ctx_in, ctx_out; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, @@ -94,9 +95,6 @@ void test_xdp_context_test_run(void) test_xdp_context_error(prog_fd, opts, 4, sizeof(__u32), sizeof(data), 0, 0, 0); - /* Meta data must be 255 bytes or smaller */ - test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0); - /* Total size of data must be data_end - data_meta or larger */ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data) + 1, 0, 0, 0); @@ -116,6 +114,16 @@ void test_xdp_context_test_run(void) test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data), 0, 0, 1); + /* Meta data must be 216 bytes or smaller (256 - sizeof(struct + * xdp_frame)). Test both nearest invalid size and nearest invalid + * 4-byte-aligned size, and make sure data_in is large enough that we + * actually hit the check on metadata length + */ + opts.data_in = large_data; + opts.data_size_in = sizeof(large_data); + test_xdp_context_error(prog_fd, opts, 0, 217, sizeof(large_data), 0, 0, 0); + test_xdp_context_error(prog_fd, opts, 0, 220, sizeof(large_data), 0, 0, 0); + test_xdp_context_test_run__destroy(skel); } diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index 766bfc4ad842..d5d247eca6b7 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -22,7 +22,7 @@ try: NlError, RtnlFamily, DevlinkFamily, PSPFamily from net.lib.py import CmdExitFailure from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \ - fd_read_timeout, ip, rand_port, wait_port_listen, wait_file + fd_read_timeout, ip, rand_port, wait_port_listen, wait_file, tool from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ ksft_setup, ksft_variants, KsftNamedVariant @@ -37,7 +37,7 @@ try: "CmdExitFailure", "bkg", "cmd", "bpftool", "bpftrace", "defer", "ethtool", "fd_read_timeout", "ip", "rand_port", - "wait_port_listen", "wait_file", + "wait_port_listen", "wait_file", "tool", "KsftSkipEx", "KsftFailEx", "KsftXfailEx", "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run", "ksft_setup", "ksft_variants", "KsftNamedVariant", diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.c b/tools/testing/selftests/drivers/net/hw/toeplitz.c index d23b3b0c20a3..285bb17df9c2 100644 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.c +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.c @@ -485,8 +485,8 @@ static void parse_rps_bitmap(const char *arg) bitmap = strtoul(arg, NULL, 0); - if (bitmap & ~(RPS_MAX_CPUS - 1)) - error(1, 0, "rps bitmap 0x%lx out of bounds 0..%lu", + if (bitmap & ~((1UL << RPS_MAX_CPUS) - 1)) + error(1, 0, "rps bitmap 0x%lx out of bounds, max cpu %lu", bitmap, RPS_MAX_CPUS - 1); for (i = 0; i < RPS_MAX_CPUS; i++) diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py index d2db5ee9e358..d288c57894f6 100755 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.py +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py @@ -94,12 +94,14 @@ def _configure_rps(cfg, rps_cpus): mask = 0 for cpu in rps_cpus: mask |= (1 << cpu) - mask = hex(mask)[2:] + + mask = hex(mask) # Set RPS bitmap for all rx queues for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"): with open(rps_file, "w", encoding="utf-8") as fp: - fp.write(mask) + # sysfs expects hex without '0x' prefix, toeplitz.c needs the prefix + fp.write(mask[2:]) return mask diff --git a/tools/testing/selftests/drivers/net/netdevsim/peer.sh b/tools/testing/selftests/drivers/net/netdevsim/peer.sh index 7f32b5600925..f4721f7636dd 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/peer.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/peer.sh @@ -52,6 +52,39 @@ cleanup_ns() ip netns del nssv } +is_carrier_up() +{ + local netns="$1" + local nsim_dev="$2" + + test "$(ip netns exec "$netns" \ + cat /sys/class/net/"$nsim_dev"/carrier 2>/dev/null)" -eq 1 +} + +assert_carrier_up() +{ + local netns="$1" + local nsim_dev="$2" + + if ! is_carrier_up "$netns" "$nsim_dev"; then + echo "$nsim_dev's carrier should be UP, but it isn't" + cleanup_ns + exit 1 + fi +} + +assert_carrier_down() +{ + local netns="$1" + local nsim_dev="$2" + + if is_carrier_up "$netns" "$nsim_dev"; then + echo "$nsim_dev's carrier should be DOWN, but it isn't" + cleanup_ns + exit 1 + fi +} + ### ### Code start ### @@ -113,6 +146,32 @@ if [ $? -eq 0 ]; then exit 1 fi +# netdevsim carrier state consistency checking +assert_carrier_up nssv "$NSIM_DEV_1_NAME" +assert_carrier_up nscl "$NSIM_DEV_2_NAME" + +echo "$NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX" > "$NSIM_DEV_SYS_UNLINK" + +assert_carrier_down nssv "$NSIM_DEV_1_NAME" +assert_carrier_down nscl "$NSIM_DEV_2_NAME" + +ip netns exec nssv ip link set dev "$NSIM_DEV_1_NAME" down +ip netns exec nssv ip link set dev "$NSIM_DEV_1_NAME" up + +assert_carrier_down nssv "$NSIM_DEV_1_NAME" +assert_carrier_down nscl "$NSIM_DEV_2_NAME" + +echo "$NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX $NSIM_DEV_2_FD:$NSIM_DEV_2_IFIDX" > $NSIM_DEV_SYS_LINK + +assert_carrier_up nssv "$NSIM_DEV_1_NAME" +assert_carrier_up nscl "$NSIM_DEV_2_NAME" + +ip netns exec nssv ip link set dev "$NSIM_DEV_1_NAME" down +ip netns exec nssv ip link set dev "$NSIM_DEV_1_NAME" up + +assert_carrier_up nssv "$NSIM_DEV_1_NAME" +assert_carrier_up nscl "$NSIM_DEV_2_NAME" + # send/recv packets tmp_file=$(mktemp) diff --git a/tools/testing/selftests/drivers/net/psp.py b/tools/testing/selftests/drivers/net/psp.py index 06559ef49b9a..52523bdad240 100755 --- a/tools/testing/selftests/drivers/net/psp.py +++ b/tools/testing/selftests/drivers/net/psp.py @@ -573,8 +573,9 @@ def psp_ip_ver_test_builder(name, test_func, psp_ver, ipver): """Build test cases for each combo of PSP version and IP version""" def test_case(cfg): cfg.require_ipver(ipver) - test_case.__name__ = f"{name}_v{psp_ver}_ip{ipver}" test_func(cfg, psp_ver, ipver) + + test_case.__name__ = f"{name}_v{psp_ver}_ip{ipver}" return test_case @@ -582,8 +583,9 @@ def ipver_test_builder(name, test_func, ipver): """Build test cases for each IP version""" def test_case(cfg): cfg.require_ipver(ipver) - test_case.__name__ = f"{name}_ip{ipver}" test_func(cfg, ipver) + + test_case.__name__ = f"{name}_ip{ipver}" return test_case diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_marker_raw.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker_raw.tc index 7daf7292209e..a2c42e13f614 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/trace_marker_raw.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker_raw.tc @@ -89,6 +89,7 @@ test_buffer() { # The id must be four bytes, test that 3 bytes fails a write if echo -n abc > ./trace_marker_raw ; then echo "Too small of write expected to fail but did not" + echo ${ORIG} > buffer_size_kb exit_fail fi @@ -99,9 +100,24 @@ test_buffer() { if write_buffer 0xdeadbeef $size ; then echo "Too big of write expected to fail but did not" + echo ${ORIG} > buffer_size_kb exit_fail fi } +ORIG=`cat buffer_size_kb` + +# test_multiple_writes test needs at least 12KB buffer +NEW_SIZE=12 + +if [ ${ORIG} -lt ${NEW_SIZE} ]; then + echo ${NEW_SIZE} > buffer_size_kb +fi + test_buffer -test_multiple_writes +if ! test_multiple_writes; then + echo ${ORIG} > buffer_size_kb + exit_fail +fi + +echo ${ORIG} > buffer_size_kb diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc index 93c10ea42a68..8b8e1aea985b 100644 --- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc @@ -1,7 +1,8 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event tracing - enable/disable with top level files -# requires: available_events set_event events/enable +# requires: set_event events/enable +# flags: instance do_reset() { echo > set_event diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc index aee22289536b..1b57771dbfdf 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc @@ -90,9 +90,10 @@ if [ $on != "0" ]; then fail "Tracing is not off" fi -csum1=`md5sum trace` +# Cannot rely on names being around as they are only cached, strip them +csum1=`cat trace | sed -e 's/^ *[^ ]*\(-[0-9][0-9]*\)/\1/' | md5sum` sleep $SLEEP_TIME -csum2=`md5sum trace` +csum2=`cat trace | sed -e 's/^ *[^ ]*\(-[0-9][0-9]*\)/\1/' | md5sum` if [ "$csum1" != "$csum2" ]; then fail "Tracing file is still changing" diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 2839d2612ce3..50ec9e0406ab 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -184,6 +184,8 @@ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ -I$(INCLUDE_DIR) CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ diff --git a/tools/testing/selftests/hid/tests/conftest.py b/tools/testing/selftests/hid/tests/conftest.py index 1361ec981db6..985a535324b2 100644 --- a/tools/testing/selftests/hid/tests/conftest.py +++ b/tools/testing/selftests/hid/tests/conftest.py @@ -5,6 +5,7 @@ # Copyright (c) 2017 Benjamin Tissoires <benjamin.tissoires@gmail.com> # Copyright (c) 2017 Red Hat, Inc. +from packaging.version import Version import platform import pytest import re @@ -14,6 +15,19 @@ from .base import HIDTestUdevRule from pathlib import Path +@pytest.fixture(autouse=True) +def hidtools_version_check(): + HIDTOOLS_VERSION = "0.12" + try: + import hidtools + + version = hidtools.__version__ # type: ignore + if Version(version) < Version(HIDTOOLS_VERSION): + pytest.skip(reason=f"have hidtools {version}, require >={HIDTOOLS_VERSION}") + except Exception: + pytest.skip(reason=f"hidtools >={HIDTOOLS_VERSION} required") + + # See the comment in HIDTestUdevRule, this doesn't set up but it will clean # up once the last test exited. @pytest.fixture(autouse=True, scope="session") diff --git a/tools/testing/selftests/hid/tests/test_multitouch.py b/tools/testing/selftests/hid/tests/test_multitouch.py index ece0ba8e7d34..fa4fb2054bd4 100644 --- a/tools/testing/selftests/hid/tests/test_multitouch.py +++ b/tools/testing/selftests/hid/tests/test_multitouch.py @@ -9,6 +9,7 @@ from . import base from hidtools.hut import HUT from hidtools.util import BusType +import enum import libevdev import logging import pytest @@ -232,11 +233,17 @@ class Digitizer(base.UHIDTestDevice): return 0 +class HIDButtonType(enum.IntEnum): + CLICKPAD = 0 + PRESSUREPAD = 1 + DISCRETE_BUTTONS = 2 + + class PTP(Digitizer): def __init__( self, name, - type="Click Pad", + buttontype=HIDButtonType.CLICKPAD, rdesc_str=None, rdesc=None, application="Touch Pad", @@ -244,11 +251,8 @@ class PTP(Digitizer): max_contacts=None, input_info=None, ): - self.type = type.lower().replace(" ", "") - if self.type == "clickpad": - self.buttontype = 0 - else: # pressurepad - self.buttontype = 1 + self.buttontype = buttontype + self.clickpad_state = False self.left_state = False self.right_state = False @@ -975,15 +979,36 @@ class BaseTest: assert libevdev.InputEvent(libevdev.EV_ABS.ABS_MT_ORIENTATION, 90) in events class TestPTP(TestWin8Multitouch): + def test_buttontype(self): + """Check for the right ButtonType.""" + uhdev = self.uhdev + assert uhdev is not None + evdev = uhdev.get_evdev() + + # If libevdev.so is not yet compiled with INPUT_PROP_PRESSUREPAD + # python-libevdev won't have it either, let's fake it + if not getattr(libevdev, "INPUT_PROP_PRESSUREPAD", None): + prop = libevdev.InputProperty(name="INPUT_PROP_PRESSUREPAD", value=0x7) + libevdev.INPUT_PROP_PRESSUREPAD = prop + libevdev.props.append(prop) + + if uhdev.buttontype == HIDButtonType.CLICKPAD: + assert libevdev.INPUT_PROP_BUTTONPAD in evdev.properties + elif uhdev.buttontype == HIDButtonType.PRESSUREPAD: + assert libevdev.INPUT_PROP_PRESSUREPAD in evdev.properties + else: + assert libevdev.INPUT_PROP_PRESSUREPAD not in evdev.properties + assert libevdev.INPUT_PROP_BUTTONPAD not in evdev.properties + def test_ptp_buttons(self): """check for button reliability. - There are 2 types of touchpads: the click pads and the pressure pads. - Each should reliably report the BTN_LEFT events. + There are 3 types of touchpads: click pads + pressure pads and + those with discrete buttons. Each should reliably report the BTN_LEFT events. """ uhdev = self.uhdev evdev = uhdev.get_evdev() - if uhdev.type == "clickpad": + if uhdev.buttontype in [HIDButtonType.CLICKPAD, HIDButtonType.PRESSUREPAD]: r = uhdev.event(click=True) events = uhdev.next_sync_events() self.debug_reports(r, uhdev, events) @@ -995,7 +1020,7 @@ class BaseTest: self.debug_reports(r, uhdev, events) assert libevdev.InputEvent(libevdev.EV_KEY.BTN_LEFT, 0) in events assert evdev.value[libevdev.EV_KEY.BTN_LEFT] == 0 - else: + elif uhdev.buttontype == HIDButtonType.DISCRETE_BUTTONS: r = uhdev.event(left=True) events = uhdev.next_sync_events() self.debug_reports(r, uhdev, events) @@ -1918,7 +1943,7 @@ class Testdell_044e_1220(BaseTest.TestPTP): def create_device(self): return PTP( "uhid test dell_044e_1220", - type="pressurepad", + buttontype=HIDButtonType.DISCRETE_BUTTONS, rdesc="05 01 09 02 a1 01 85 01 09 01 a1 00 05 09 19 01 29 03 15 00 25 01 75 01 95 03 81 02 95 05 81 01 05 01 09 30 09 31 15 81 25 7f 75 08 95 02 81 06 09 38 95 01 81 06 05 0c 0a 38 02 81 06 c0 c0 05 0d 09 05 a1 01 85 08 09 22 a1 02 15 00 25 01 09 47 09 42 95 02 75 01 81 02 95 01 75 03 25 05 09 51 81 02 75 01 95 03 81 03 05 01 15 00 26 af 04 75 10 55 0e 65 11 09 30 35 00 46 e8 03 95 01 81 02 26 7b 02 46 12 02 09 31 81 02 c0 55 0c 66 01 10 47 ff ff 00 00 27 ff ff 00 00 75 10 95 01 05 0d 09 56 81 02 09 54 25 05 95 01 75 08 81 02 05 09 19 01 29 03 25 01 75 01 95 03 81 02 95 05 81 03 05 0d 85 09 09 55 75 08 95 01 25 05 b1 02 06 00 ff 85 0a 09 c5 15 00 26 ff 00 75 08 96 00 01 b1 02 c0 06 01 ff 09 01 a1 01 85 03 09 01 15 00 26 ff 00 95 1b 81 02 85 04 09 02 95 50 81 02 85 05 09 03 95 07 b1 02 85 06 09 04 81 02 c0 06 02 ff 09 01 a1 01 85 07 09 02 95 86 75 08 b1 02 c0 05 0d 09 0e a1 01 85 0b 09 22 a1 02 09 52 15 00 25 0a 75 08 95 01 b1 02 c0 09 22 a1 00 85 0c 09 57 09 58 75 01 95 02 25 01 b1 02 95 06 b1 03 c0 c0", ) @@ -2018,7 +2043,7 @@ class Testelan_04f3_313a(BaseTest.TestPTP): def create_device(self): return PTP( "uhid test elan_04f3_313a", - type="touchpad", + buttontype=HIDButtonType.DISCRETE_BUTTONS, input_info=(BusType.I2C, 0x04F3, 0x313A), rdesc="05 01 09 02 a1 01 85 01 09 01 a1 00 05 09 19 01 29 03 15 00 25 01 75 01 95 03 81 02 95 05 81 03 05 01 09 30 09 31 15 81 25 7f 75 08 95 02 81 06 75 08 95 05 81 03 c0 06 00 ff 09 01 85 0e 09 c5 15 00 26 ff 00 75 08 95 04 b1 02 85 0a 09 c6 15 00 26 ff 00 75 08 95 04 b1 02 c0 06 00 ff 09 01 a1 01 85 5c 09 01 95 0b 75 08 81 06 85 0d 09 c5 15 00 26 ff 00 75 08 95 04 b1 02 85 0c 09 c6 96 80 03 75 08 b1 02 85 0b 09 c7 95 82 75 08 b1 02 c0 05 0d 09 05 a1 01 85 04 09 22 a1 02 15 00 25 01 09 47 09 42 95 02 75 01 81 02 05 09 09 02 09 03 15 00 25 01 75 01 95 02 81 02 05 0d 95 01 75 04 25 0f 09 51 81 02 05 01 15 00 26 d7 0e 75 10 55 0d 65 11 09 30 35 00 46 44 2f 95 01 81 02 46 12 16 26 eb 06 26 eb 06 09 31 81 02 05 0d 15 00 25 64 95 03 c0 55 0c 66 01 10 47 ff ff 00 00 27 ff ff 00 00 75 10 95 01 09 56 81 02 09 54 25 7f 95 01 75 08 81 02 25 01 75 01 95 08 81 03 09 c5 75 08 95 02 81 03 05 0d 85 02 09 55 09 59 75 04 95 02 25 0f b1 02 85 07 09 60 75 01 95 01 15 00 25 01 b1 02 95 0f b1 03 06 00 ff 06 00 ff 85 06 09 c5 15 00 26 ff 00 75 08 96 00 01 b1 02 c0 05 0d 09 0e a1 01 85 03 09 22 a1 00 09 52 15 00 25 0a 75 10 95 01 b1 02 c0 09 22 a1 00 85 05 09 57 09 58 75 01 95 02 25 01 b1 02 95 0e b1 03 c0 c0 05 01 09 02 a1 01 85 2a 09 01 a1 00 05 09 19 01 29 03 15 00 25 01 75 01 95 03 81 02 95 05 81 03 05 01 09 30 09 31 15 81 25 7f 35 81 45 7f 55 00 65 13 75 08 95 02 81 06 75 08 95 05 81 03 c0 c0", ) @@ -2058,6 +2083,16 @@ class Testite_06cb_2968(BaseTest.TestPTP): ) +class Testven_0488_108c(BaseTest.TestPTP): + def create_device(self): + return PTP( + "uhid test ven_0488_108c", + rdesc="05 01 09 02 a1 01 85 06 09 01 a1 00 05 09 19 01 29 03 15 00 25 01 95 03 75 01 81 02 95 01 75 05 81 03 05 01 09 30 09 31 09 38 15 81 25 7f 75 08 95 03 81 06 c0 c0 05 0d 09 05 a1 01 85 01 05 0d 09 22 a1 02 15 00 25 01 09 47 09 42 95 02 75 01 81 02 95 01 75 03 25 05 09 51 81 02 81 03 05 01 15 00 26 ba 0d 75 10 55 0e 65 11 09 30 35 00 46 d0 05 95 01 81 02 26 d0 06 46 bb 02 09 31 81 02 05 0d 95 01 75 10 26 ff 7f 46 ff 7f 09 30 81 02 c0 05 0d 09 22 a1 02 15 00 25 01 09 47 09 42 95 02 75 01 81 02 95 01 75 03 25 05 09 51 81 02 81 03 05 01 15 00 26 ba 0d 75 10 55 0e 65 11 09 30 35 00 46 d0 05 95 01 81 02 26 d0 06 46 bb 02 09 31 81 02 05 0d 95 01 75 10 26 ff 7f 46 ff 7f 09 30 81 02 c0 05 0d 09 22 a1 02 15 00 25 01 09 47 09 42 95 02 75 01 81 02 95 01 75 03 25 05 09 51 81 02 81 03 05 01 15 00 26 ba 0d 75 10 55 0e 65 11 09 30 35 00 46 d0 05 95 01 81 02 26 d0 06 46 bb 02 09 31 81 02 05 0d 95 01 75 10 26 ff 7f 46 ff 7f 09 30 81 02 c0 55 0c 66 01 10 47 ff ff 00 00 27 ff ff 00 00 75 10 95 01 05 0d 09 56 81 02 09 54 25 05 95 01 75 08 81 02 05 09 09 01 25 01 75 01 95 01 81 02 95 07 81 03 05 0d 85 02 09 55 75 08 95 01 25 05 b1 02 09 59 b1 02 06 00 ff 85 03 09 c5 15 00 26 ff 00 75 08 96 00 01 b1 02 05 0e 09 01 a1 02 85 13 09 23 15 00 25 64 75 08 95 01 b1 02 c0 c0 05 0d 09 0e a1 01 85 04 09 22 a1 02 09 52 15 00 25 0a 75 08 95 01 b1 02 c0 09 22 a1 00 85 05 09 57 09 58 75 01 95 02 25 01 b1 02 95 06 b1 03 c0 c0 06 01 ff 09 02 a1 01 09 00 85 07 15 00 26 ff 00 75 08 96 12 02 b1 02 c0 06 00 ff 09 01 a1 01 85 0d 15 00 26 ff 00 75 08 95 11 09 01 81 02 09 01 91 02 c0 05 0e 09 01 a1 01 85 11 09 35 15 00 26 ff 00 75 08 95 17 b1 02 c0 06 81 ff 09 01 a1 01 09 20 85 17 15 00 26 ff 00 75 08 95 3f 09 01 81 02 09 01 91 02 c0", + input_info=(0x18, 0x0488, 0x108C), + buttontype=HIDButtonType.PRESSUREPAD, + ) + + class Testn_trig_1b96_0c01(BaseTest.TestWin8Multitouch): def create_device(self): return Digitizer( @@ -2110,7 +2145,7 @@ class Testsipodev_0603_0002(BaseTest.TestPTP): def create_device(self): return PTP( "uhid test sipodev_0603_0002", - type="clickpad", + buttontype=HIDButtonType.CLICKPAD, rdesc="05 01 09 02 a1 01 85 03 09 01 a1 00 05 09 19 01 29 02 25 01 75 01 95 02 81 02 95 06 81 03 05 01 09 30 09 31 15 80 25 7f 75 08 95 02 81 06 c0 c0 05 0d 09 05 a1 01 85 04 09 22 a1 02 15 00 25 01 09 47 09 42 95 02 75 01 81 02 75 01 95 02 81 03 95 01 75 04 25 05 09 51 81 02 05 01 15 00 26 44 0a 75 0c 55 0e 65 11 09 30 35 00 46 ac 03 95 01 81 02 46 fe 01 26 34 05 75 0c 09 31 81 02 05 0d c0 55 0c 66 01 10 47 ff ff 00 00 27 ff ff 00 00 75 10 95 01 09 56 81 02 09 54 25 0a 95 01 75 04 81 02 75 01 95 03 81 03 05 09 09 01 25 01 75 01 95 01 81 02 05 0d 85 0a 09 55 09 59 75 04 95 02 25 0f b1 02 85 0b 09 60 75 01 95 01 15 00 25 01 b1 02 95 07 b1 03 85 09 06 00 ff 09 c5 15 00 26 ff 00 75 08 96 00 01 b1 02 c0 05 0d 09 0e a1 01 85 06 09 22 a1 02 09 52 15 00 25 0a 75 08 95 01 b1 02 c0 09 22 a1 00 85 07 09 57 09 58 75 01 95 02 25 01 b1 02 95 06 b1 03 c0 c0 05 01 09 0c a1 01 85 08 15 00 25 01 09 c6 75 01 95 01 81 06 75 07 81 03 c0 05 01 09 80 a1 01 85 01 15 00 25 01 75 01 0a 81 00 0a 82 00 0a 83 00 95 03 81 06 95 05 81 01 c0 06 0c 00 09 01 a1 01 85 02 25 01 15 00 75 01 0a b5 00 0a b6 00 0a b7 00 0a cd 00 0a e2 00 0a a2 00 0a e9 00 0a ea 00 95 08 81 02 0a 83 01 0a 6f 00 0a 70 00 0a 88 01 0a 8a 01 0a 92 01 0a a8 02 0a 24 02 95 08 81 02 0a 21 02 0a 23 02 0a 96 01 0a 25 02 0a 26 02 0a 27 02 0a 23 02 0a b1 02 95 08 81 02 c0 06 00 ff 09 01 a1 01 85 05 15 00 26 ff 00 19 01 29 02 75 08 95 05 b1 02 c0", ) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index baae6b7ded41..16a119a4656c 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -70,6 +70,12 @@ #include "kselftest.h" +static inline void __kselftest_memset_safe(void *s, int c, size_t n) +{ + if (n > 0) + memset(s, c, n); +} + #define TEST_TIMEOUT_DEFAULT 30 /* Utilities exposed to the test definitions */ @@ -416,7 +422,7 @@ self = mmap(NULL, sizeof(*self), PROT_READ | PROT_WRITE, \ MAP_SHARED | MAP_ANONYMOUS, -1, 0); \ } else { \ - memset(&self_private, 0, sizeof(self_private)); \ + __kselftest_memset_safe(&self_private, 0, sizeof(self_private)); \ self = &self_private; \ } \ } \ diff --git a/tools/testing/selftests/kvm/x86/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c index f4ce5a185a7d..37b166260ee3 100644 --- a/tools/testing/selftests/kvm/x86/amx_test.c +++ b/tools/testing/selftests/kvm/x86/amx_test.c @@ -69,6 +69,12 @@ static inline void __tileloadd(void *tile) : : "a"(tile), "d"(0)); } +static inline int tileloadd_safe(void *tile) +{ + return kvm_asm_safe(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10", + "a"(tile), "d"(0)); +} + static inline void __tilerelease(void) { asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); @@ -124,27 +130,52 @@ static void set_tilecfg(struct tile_config *cfg) } } +enum { + /* Retrieve TMM0 from guest, stash it for TEST_RESTORE_TILEDATA */ + TEST_SAVE_TILEDATA = 1, + + /* Check TMM0 against tiledata */ + TEST_COMPARE_TILEDATA = 2, + + /* Restore TMM0 from earlier save */ + TEST_RESTORE_TILEDATA = 4, + + /* Full VM save/restore */ + TEST_SAVE_RESTORE = 8, +}; + static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, struct tile_data *tiledata, struct xstate *xstate) { + int vector; + GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE) && this_cpu_has(X86_FEATURE_OSXSAVE)); check_xtile_info(); - GUEST_SYNC(1); + GUEST_SYNC(TEST_SAVE_RESTORE); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(2); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - GUEST_SYNC(3); + GUEST_SYNC(TEST_SAVE_RESTORE); /* Check save/restore when trap to userspace */ __tileloadd(tiledata); - GUEST_SYNC(4); + GUEST_SYNC(TEST_SAVE_TILEDATA | TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + /* xfd=0x40000, disable amx tiledata */ + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); + + /* host tries setting tiledata while guest XFD is set */ + GUEST_SYNC(TEST_RESTORE_TILEDATA); + GUEST_SYNC(TEST_SAVE_RESTORE); + + wrmsr(MSR_IA32_XFD, 0); __tilerelease(); - GUEST_SYNC(5); + GUEST_SYNC(TEST_SAVE_RESTORE); /* * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in * the xcomp_bv. @@ -154,6 +185,8 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA); + /* #NM test */ + /* xfd=0x40000, disable amx tiledata */ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); @@ -166,32 +199,33 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA)); - GUEST_SYNC(6); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - /* Trigger #NM exception */ - __tileloadd(tiledata); - GUEST_SYNC(10); - GUEST_DONE(); -} + /* Trigger #NM exception */ + vector = tileloadd_safe(tiledata); + __GUEST_ASSERT(vector == NM_VECTOR, + "Wanted #NM on tileloadd with XFD[18]=1, got %s", + ex_str(vector)); -void guest_nm_handler(struct ex_regs *regs) -{ - /* Check if #NM is triggered by XFEATURE_MASK_XTILE_DATA */ - GUEST_SYNC(7); GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); - GUEST_SYNC(8); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); /* Clear xfd_err */ wrmsr(MSR_IA32_XFD_ERR, 0); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(9); + GUEST_SYNC(TEST_SAVE_RESTORE); + + __tileloadd(tiledata); + GUEST_SYNC(TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + GUEST_DONE(); } int main(int argc, char *argv[]) @@ -200,10 +234,10 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_x86_state *state; + struct kvm_x86_state *tile_state = NULL; int xsave_restore_size; vm_vaddr_t amx_cfg, tiledata, xstate; struct ucall uc; - u32 amx_offset; int ret; /* @@ -228,9 +262,6 @@ int main(int argc, char *argv[]) vcpu_regs_get(vcpu, ®s1); - /* Register #NM handler */ - vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); - /* amx cfg for guest_code */ amx_cfg = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize()); @@ -244,6 +275,7 @@ int main(int argc, char *argv[]) memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); + int iter = 0; for (;;) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); @@ -253,37 +285,47 @@ int main(int argc, char *argv[]) REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: - switch (uc.args[1]) { - case 1: - case 2: - case 3: - case 5: - case 6: - case 7: - case 8: - fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]); - break; - case 4: - case 10: - fprintf(stderr, - "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]); + ++iter; + if (uc.args[1] & TEST_SAVE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, save tiledata\n", iter); + tile_state = vcpu_save_state(vcpu); + } + if (uc.args[1] & TEST_COMPARE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, check TMM0 contents\n", iter); /* Compacted mode, get amx offset by xsave area * size subtract 8K amx size. */ - amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; - state = vcpu_save_state(vcpu); - void *amx_start = (void *)state->xsave + amx_offset; + u32 amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; + void *amx_start = (void *)tile_state->xsave + amx_offset; void *tiles_data = (void *)addr_gva2hva(vm, tiledata); /* Only check TMM0 register, 1 tile */ ret = memcmp(amx_start, tiles_data, TILE_SIZE); TEST_ASSERT(ret == 0, "memcmp failed, ret=%d", ret); + } + if (uc.args[1] & TEST_RESTORE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, before KVM_SET_XSAVE\n", iter); + vcpu_xsave_set(vcpu, tile_state->xsave); + fprintf(stderr, "GUEST_SYNC #%d, after KVM_SET_XSAVE\n", iter); + } + if (uc.args[1] & TEST_SAVE_RESTORE) { + fprintf(stderr, "GUEST_SYNC #%d, save/restore VM state\n", iter); + state = vcpu_save_state(vcpu); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vcpu, ®s1); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); kvm_x86_state_cleanup(state); - break; - case 9: - fprintf(stderr, - "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]); - break; + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vcpu, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); } break; case UCALL_DONE: @@ -293,22 +335,6 @@ int main(int argc, char *argv[]) TEST_FAIL("Unknown ucall %lu", uc.cmd); } - state = vcpu_save_state(vcpu); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vcpu, ®s1); - - kvm_vm_release(vm); - - /* Restore state in a new VM. */ - vcpu = vm_recreate_with_one_vcpu(vm); - vcpu_load_state(vcpu, state); - kvm_x86_state_cleanup(state); - - memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vcpu, ®s2); - TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), - "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", - (ulong) regs2.rdi, (ulong) regs2.rsi); } done: kvm_vm_free(vm); diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 230b75f6015b..90551650299c 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -237,6 +237,7 @@ struct service_fixture { struct sockaddr_un unix_addr; socklen_t unix_addr_len; }; + struct sockaddr_storage _largest; }; }; diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index eee814e09dd7..968a91c927a4 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -4362,22 +4362,24 @@ TEST_F_FORK(layout1, named_unix_domain_socket_ioctl) { const char *const path = file1_s1d1; int srv_fd, cli_fd, ruleset_fd; - socklen_t size; - struct sockaddr_un srv_un, cli_un; + struct sockaddr_un srv_un = { + .sun_family = AF_UNIX, + }; + struct sockaddr_un cli_un = { + .sun_family = AF_UNIX, + }; const struct landlock_ruleset_attr attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_IOCTL_DEV, }; /* Sets up a server */ - srv_un.sun_family = AF_UNIX; - strncpy(srv_un.sun_path, path, sizeof(srv_un.sun_path)); - ASSERT_EQ(0, unlink(path)); srv_fd = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, srv_fd); - size = offsetof(struct sockaddr_un, sun_path) + strlen(srv_un.sun_path); - ASSERT_EQ(0, bind(srv_fd, (struct sockaddr *)&srv_un, size)); + strncpy(srv_un.sun_path, path, sizeof(srv_un.sun_path)); + ASSERT_EQ(0, bind(srv_fd, (struct sockaddr *)&srv_un, sizeof(srv_un))); + ASSERT_EQ(0, listen(srv_fd, 10 /* qlen */)); /* Enables Landlock. */ @@ -4387,24 +4389,18 @@ TEST_F_FORK(layout1, named_unix_domain_socket_ioctl) ASSERT_EQ(0, close(ruleset_fd)); /* Sets up a client connection to it */ - cli_un.sun_family = AF_UNIX; cli_fd = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, cli_fd); - size = offsetof(struct sockaddr_un, sun_path) + strlen(cli_un.sun_path); - ASSERT_EQ(0, bind(cli_fd, (struct sockaddr *)&cli_un, size)); - - bzero(&cli_un, sizeof(cli_un)); - cli_un.sun_family = AF_UNIX; strncpy(cli_un.sun_path, path, sizeof(cli_un.sun_path)); - size = offsetof(struct sockaddr_un, sun_path) + strlen(cli_un.sun_path); - - ASSERT_EQ(0, connect(cli_fd, (struct sockaddr *)&cli_un, size)); + ASSERT_EQ(0, + connect(cli_fd, (struct sockaddr *)&cli_un, sizeof(cli_un))); /* FIONREAD and other IOCTLs should not be forbidden. */ EXPECT_EQ(0, test_fionread_ioctl(cli_fd)); - ASSERT_EQ(0, close(cli_fd)); + EXPECT_EQ(0, close(cli_fd)); + EXPECT_EQ(0, close(srv_fd)); } /* clang-format off */ @@ -7074,8 +7070,8 @@ static int matches_log_fs_extra(struct __test_metadata *const _metadata, return -E2BIG; /* - * It is assume that absolute_path does not contain control characters nor - * spaces, see audit_string_contains_control(). + * It is assumed that absolute_path does not contain control + * characters nor spaces, see audit_string_contains_control(). */ absolute_path = realpath(path, NULL); if (!absolute_path) diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 2a45208551e6..b34b139b3f89 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -121,6 +121,10 @@ static socklen_t get_addrlen(const struct service_fixture *const srv, { switch (srv->protocol.domain) { case AF_UNSPEC: + if (minimal) + return sizeof(sa_family_t); + return sizeof(struct sockaddr_storage); + case AF_INET: return sizeof(srv->ipv4_addr); @@ -758,6 +762,11 @@ TEST_F(protocol, bind_unspec) bind_fd = socket_variant(&self->srv0); ASSERT_LE(0, bind_fd); + /* Tries to bind with too small addrlen. */ + EXPECT_EQ(-EINVAL, bind_variant_addrlen( + bind_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, true) - 1)); + /* Allowed bind on AF_UNSPEC/INADDR_ANY. */ ret = bind_variant(bind_fd, &self->unspec_any0); if (variant->prot.domain == AF_INET) { @@ -766,6 +775,8 @@ TEST_F(protocol, bind_unspec) TH_LOG("Failed to bind to unspec/any socket: %s", strerror(errno)); } + } else if (variant->prot.domain == AF_INET6) { + EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret); } @@ -792,6 +803,8 @@ TEST_F(protocol, bind_unspec) } else { EXPECT_EQ(0, ret); } + } else if (variant->prot.domain == AF_INET6) { + EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret); } @@ -801,7 +814,8 @@ TEST_F(protocol, bind_unspec) bind_fd = socket_variant(&self->srv0); ASSERT_LE(0, bind_fd); ret = bind_variant(bind_fd, &self->unspec_srv0); - if (variant->prot.domain == AF_INET) { + if (variant->prot.domain == AF_INET || + variant->prot.domain == AF_INET6) { EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret) @@ -892,7 +906,19 @@ TEST_F(protocol, connect_unspec) EXPECT_EQ(0, close(ruleset_fd)); } - ret = connect_variant(connect_fd, &self->unspec_any0); + /* Try to re-disconnect with a truncated address struct. */ + EXPECT_EQ(-EINVAL, + connect_variant_addrlen( + connect_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, true) - 1)); + + /* + * Re-disconnect, with a minimal sockaddr struct (just a + * bare af_family=AF_UNSPEC field). + */ + ret = connect_variant_addrlen(connect_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, + true)); if (self->srv0.protocol.domain == AF_UNIX && self->srv0.protocol.type == SOCK_STREAM) { EXPECT_EQ(-EINVAL, ret); diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c index 4e356334ecb7..4f64c90583cd 100644 --- a/tools/testing/selftests/landlock/ptrace_test.c +++ b/tools/testing/selftests/landlock/ptrace_test.c @@ -86,16 +86,9 @@ static int get_yama_ptrace_scope(void) } /* clang-format off */ -FIXTURE(hierarchy) {}; +FIXTURE(scoped_domains) {}; /* clang-format on */ -FIXTURE_VARIANT(hierarchy) -{ - const bool domain_both; - const bool domain_parent; - const bool domain_child; -}; - /* * Test multiple tracing combinations between a parent process P1 and a child * process P2. @@ -104,155 +97,18 @@ FIXTURE_VARIANT(hierarchy) * restriction is enforced in addition to any Landlock check, which means that * all P2 requests to trace P1 would be denied. */ +#include "scoped_base_variants.h" -/* - * No domain - * - * P1-. P1 -> P2 : allow - * \ P2 -> P1 : allow - * 'P2 - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_without_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = false, - .domain_child = false, -}; - -/* - * Child domain - * - * P1--. P1 -> P2 : allow - * \ P2 -> P1 : deny - * .'-----. - * | P2 | - * '------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_with_one_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = false, - .domain_child = true, -}; - -/* - * Parent domain - * .------. - * | P1 --. P1 -> P2 : deny - * '------' \ P2 -> P1 : allow - * ' - * P2 - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_parent_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = true, - .domain_child = false, -}; - -/* - * Parent + child domain (siblings) - * .------. - * | P1 ---. P1 -> P2 : deny - * '------' \ P2 -> P1 : deny - * .---'--. - * | P2 | - * '------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_sibling_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = true, - .domain_child = true, -}; - -/* - * Same domain (inherited) - * .-------------. - * | P1----. | P1 -> P2 : allow - * | \ | P2 -> P1 : allow - * | ' | - * | P2 | - * '-------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_sibling_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = false, - .domain_child = false, -}; - -/* - * Inherited + child domain - * .-----------------. - * | P1----. | P1 -> P2 : allow - * | \ | P2 -> P1 : deny - * | .-'----. | - * | | P2 | | - * | '------' | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_with_nested_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = false, - .domain_child = true, -}; - -/* - * Inherited + parent domain - * .-----------------. - * |.------. | P1 -> P2 : deny - * || P1 ----. | P2 -> P1 : allow - * |'------' \ | - * | ' | - * | P2 | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_nested_and_parent_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = true, - .domain_child = false, -}; - -/* - * Inherited + parent and child domain (siblings) - * .-----------------. - * | .------. | P1 -> P2 : deny - * | | P1 . | P2 -> P1 : deny - * | '------'\ | - * | \ | - * | .--'---. | - * | | P2 | | - * | '------' | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_forked_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = true, - .domain_child = true, -}; - -FIXTURE_SETUP(hierarchy) +FIXTURE_SETUP(scoped_domains) { } -FIXTURE_TEARDOWN(hierarchy) +FIXTURE_TEARDOWN(scoped_domains) { } /* Test PTRACE_TRACEME and PTRACE_ATTACH for parent and child. */ -TEST_F(hierarchy, trace) +TEST_F(scoped_domains, trace) { pid_t child, parent; int status, err_proc_read; diff --git a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c index 6825082c079c..72f97648d4a7 100644 --- a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c +++ b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c @@ -543,7 +543,7 @@ TEST_F(scoped_vs_unscoped, unix_scoping) ASSERT_EQ(1, write(pipe_child[1], ".", 1)); ASSERT_EQ(grand_child, waitpid(grand_child, &status, 0)); - EXPECT_EQ(0, close(stream_server_child)) + EXPECT_EQ(0, close(stream_server_child)); EXPECT_EQ(0, close(dgram_server_child)); return; } @@ -779,7 +779,6 @@ FIXTURE_TEARDOWN(various_address_sockets) TEST_F(various_address_sockets, scoped_pathname_sockets) { - socklen_t size_stream, size_dgram; pid_t child; int status; char buf_child, buf_parent; @@ -798,12 +797,8 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) /* Pathname address. */ snprintf(stream_pathname_addr.sun_path, sizeof(stream_pathname_addr.sun_path), "%s", stream_path); - size_stream = offsetof(struct sockaddr_un, sun_path) + - strlen(stream_pathname_addr.sun_path); snprintf(dgram_pathname_addr.sun_path, sizeof(dgram_pathname_addr.sun_path), "%s", dgram_path); - size_dgram = offsetof(struct sockaddr_un, sun_path) + - strlen(dgram_pathname_addr.sun_path); /* Abstract address. */ memset(&stream_abstract_addr, 0, sizeof(stream_abstract_addr)); @@ -841,8 +836,9 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) /* Connects with pathname sockets. */ stream_pathname_socket = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, stream_pathname_socket); - ASSERT_EQ(0, connect(stream_pathname_socket, - &stream_pathname_addr, size_stream)); + ASSERT_EQ(0, + connect(stream_pathname_socket, &stream_pathname_addr, + sizeof(stream_pathname_addr))); ASSERT_EQ(1, write(stream_pathname_socket, "b", 1)); EXPECT_EQ(0, close(stream_pathname_socket)); @@ -850,12 +846,13 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) dgram_pathname_socket = socket(AF_UNIX, SOCK_DGRAM, 0); ASSERT_LE(0, dgram_pathname_socket); err = sendto(dgram_pathname_socket, "c", 1, 0, - &dgram_pathname_addr, size_dgram); + &dgram_pathname_addr, sizeof(dgram_pathname_addr)); EXPECT_EQ(1, err); /* Sends with connection. */ - ASSERT_EQ(0, connect(dgram_pathname_socket, - &dgram_pathname_addr, size_dgram)); + ASSERT_EQ(0, + connect(dgram_pathname_socket, &dgram_pathname_addr, + sizeof(dgram_pathname_addr))); ASSERT_EQ(1, write(dgram_pathname_socket, "d", 1)); EXPECT_EQ(0, close(dgram_pathname_socket)); @@ -910,13 +907,13 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) stream_pathname_socket = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, stream_pathname_socket); ASSERT_EQ(0, bind(stream_pathname_socket, &stream_pathname_addr, - size_stream)); + sizeof(stream_pathname_addr))); ASSERT_EQ(0, listen(stream_pathname_socket, backlog)); dgram_pathname_socket = socket(AF_UNIX, SOCK_DGRAM, 0); ASSERT_LE(0, dgram_pathname_socket); ASSERT_EQ(0, bind(dgram_pathname_socket, &dgram_pathname_addr, - size_dgram)); + sizeof(dgram_pathname_addr))); /* Sets up abstract servers. */ stream_abstract_socket = socket(AF_UNIX, SOCK_STREAM, 0); diff --git a/tools/testing/selftests/landlock/scoped_base_variants.h b/tools/testing/selftests/landlock/scoped_base_variants.h index d3b1fa8a584e..7116728ebc68 100644 --- a/tools/testing/selftests/landlock/scoped_base_variants.h +++ b/tools/testing/selftests/landlock/scoped_base_variants.h @@ -1,8 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Landlock scoped_domains variants + * Landlock scoped_domains test variant definition. * - * See the hierarchy variants from ptrace_test.c + * This file defines a fixture variant "scoped_domains" that has all + * permutations of parent/child process being in separate or shared + * Landlock domain, or not being in a Landlock domain at all. + * + * Scoped access tests can include this file to avoid repeating these + * combinations. * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2019-2020 ANSSI diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index 6279893a0adc..f61150d28eb2 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -179,7 +179,7 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) if (rw && shared && fs_is_unknown(fs_type)) { ksft_print_msg("Unknown filesystem\n"); result = KSFT_SKIP; - return; + break; } /* * R/O pinning or pinning in a private mapping is always diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index 363c1033cc7d..10b686102b79 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -22,12 +22,37 @@ FIXTURE(merge) struct procmap_fd procmap; }; +static char *map_carveout(unsigned int page_size) +{ + return mmap(NULL, 30 * page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); +} + +static pid_t do_fork(struct procmap_fd *procmap) +{ + pid_t pid = fork(); + + if (pid == -1) + return -1; + if (pid != 0) { + wait(NULL); + return pid; + } + + /* Reopen for child. */ + if (close_procmap(procmap)) + return -1; + if (open_self_procmap(procmap)) + return -1; + + return 0; +} + FIXTURE_SETUP(merge) { self->page_size = psize(); /* Carve out PROT_NONE region to map over. */ - self->carveout = mmap(NULL, 30 * self->page_size, PROT_NONE, - MAP_ANON | MAP_PRIVATE, -1, 0); + self->carveout = map_carveout(self->page_size); ASSERT_NE(self->carveout, MAP_FAILED); /* Setup PROCMAP_QUERY interface. */ ASSERT_EQ(open_self_procmap(&self->procmap), 0); @@ -36,7 +61,8 @@ FIXTURE_SETUP(merge) FIXTURE_TEARDOWN(merge) { ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); - ASSERT_EQ(close_procmap(&self->procmap), 0); + /* May fail for parent of forked process. */ + close_procmap(&self->procmap); /* * Clear unconditionally, as some tests set this. It is no issue if this * fails (KSM may be disabled for instance). @@ -44,6 +70,44 @@ FIXTURE_TEARDOWN(merge) prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); } +FIXTURE(merge_with_fork) +{ + unsigned int page_size; + char *carveout; + struct procmap_fd procmap; +}; + +FIXTURE_VARIANT(merge_with_fork) +{ + bool forked; +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, forked) +{ + .forked = true, +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, unforked) +{ + .forked = false, +}; + +FIXTURE_SETUP(merge_with_fork) +{ + self->page_size = psize(); + self->carveout = map_carveout(self->page_size); + ASSERT_NE(self->carveout, MAP_FAILED); + ASSERT_EQ(open_self_procmap(&self->procmap), 0); +} + +FIXTURE_TEARDOWN(merge_with_fork) +{ + ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); + ASSERT_EQ(close_procmap(&self->procmap), 0); + /* See above. */ + prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); +} + TEST_F(merge, mprotect_unfaulted_left) { unsigned int page_size = self->page_size; @@ -322,8 +386,8 @@ TEST_F(merge, forked_target_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -344,19 +408,10 @@ TEST_F(merge, forked_target_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -386,8 +441,8 @@ TEST_F(merge, forked_source_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -408,19 +463,10 @@ TEST_F(merge, forked_source_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -1171,4 +1217,288 @@ TEST_F(merge, mremap_correct_placed_faulted) ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); } +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |------------| + * | \ | + * |-----------| | / |---------| + * | unfaulted | v \ | faulted | + * |-----------| / |---------| + * B \ A + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |---------------------------| + * | \ | + * | |-----------| / |---------| + * v | unfaulted | \ | faulted | + * |-----------| / |---------| + * B \ A + * + * Then unmap VMA A to trigger the bug. + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b, *ptr_c; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | unfaulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + /* Fault it in. */ + ptr_b[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMAs A, C in position, + * unfaulted. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA C into place. */ + ptr_c = mmap(&self->carveout[page_size + 3 * page_size + 3 * page_size], + 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_c, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 9 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); + + /* If forked, B and C should also not have merged. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 3 * page_size); + } +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_faulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + char *ptr_a, *ptr_b, *ptr_bc; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | faulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* + * Map VMA B and C into place. We have to map them together so their + * anon_vma is the same and the vma->vm_pgoff's are correctly aligned. + */ + ptr_bc = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_bc, MAP_FAILED); + + /* Fault it in. */ + ptr_bc[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move VMA B out the way (splitting VMA BC) so we can place VMA A + * in position, unfaulted, and leave the remainder of the VMA we just + * moved in place, faulted, as VMA C. + */ + ptr_b = mremap(ptr_bc, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged. A,B,C if unforked, B, C if forked. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 6 * page_size); + } else { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + 9 * page_size); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index f4807242c5b2..6f5e404a446c 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -1317,7 +1317,7 @@ static thread_state thread_state_get(pid_t tid) p = strstr(tmp, header); if (p) { /* For example, "State:\tD (disk sleep)" */ - c = *(p + sizeof(header) - 1); + c = *(p + strlen(header)); return c == 'D' ? THR_STATE_UNINTERRUPTIBLE : THR_STATE_UNKNOWN; } diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b66ba04f19d9..45c4ea381bc3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -48,6 +48,7 @@ TEST_PROGS := \ ipv6_flowlabel.sh \ ipv6_force_forwarding.sh \ ipv6_route_update_soft_lockup.sh \ + ipvtap_test.sh \ l2_tos_ttl_inherit.sh \ l2tp.sh \ link_netns.py \ diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 3ef209cacb8e..663744305e52 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -73,6 +73,8 @@ # +------------------------+ #============================================================================== +source lib.sh + readonly LISTENER=$(mktemp -u listener-XXXXXXXX) readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX) readonly RELAY=$(mktemp -u relay-XXXXXXXX) @@ -246,14 +248,15 @@ test_ipv6_forward() send_mcast4() { - sleep 2 + sleep 5 + wait_local_port_listen ${LISTENER} 4000 udp ip netns exec "${SOURCE}" bash -c \ 'printf "%s %128s" 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' & } send_mcast6() { - sleep 2 + wait_local_port_listen ${LISTENER} 6000 udp ip netns exec "${SOURCE}" bash -c \ 'printf "%s %128s" 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' & } diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 1e1f253118f5..b84362b9b508 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -48,6 +48,7 @@ CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPV6_SIT=y CONFIG_IPV6_VTI=y CONFIG_IPVLAN=m +CONFIG_IPVTAP=m CONFIG_KALLSYMS=y CONFIG_L2TP=m CONFIG_L2TP_ETH=m @@ -116,6 +117,7 @@ CONFIG_PROC_SYSCTL=y CONFIG_PSAMPLE=m CONFIG_RPS=y CONFIG_SYSFS=y +CONFIG_TAP=m CONFIG_TCP_MD5SIG=y CONFIG_TEST_BLACKHOLE_DEV=m CONFIG_TEST_BPF=m diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 844a580ae74e..890c3f8e51bb 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -2327,6 +2327,13 @@ ipv6_ping_novrf() log_test_addr ${a} $? 2 "ping local, device bind" done + for a in ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSA_DEV} ${NSA_IP6} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ::1 ${a} + log_test_addr ${a} $? 0 "ping local, from localhost" + done + # # ip rule blocks address # diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh index ec2d6ceb1f08..c01be076b210 100755 --- a/tools/testing/selftests/net/fib-onlink-tests.sh +++ b/tools/testing/selftests/net/fib-onlink-tests.sh @@ -120,7 +120,7 @@ log_subsection() run_cmd() { - local cmd="$*" + local cmd="$1" local out local rc @@ -145,7 +145,7 @@ get_linklocal() local pfx local addr - addr=$(${pfx} ip -6 -br addr show dev ${dev} | \ + addr=$(${pfx} ${IP} -6 -br addr show dev ${dev} | \ awk '{ for (i = 3; i <= NF; ++i) { if ($i ~ /^fe80/) @@ -173,58 +173,48 @@ setup() set -e - # create namespace - setup_ns PEER_NS + # create namespaces + setup_ns ns1 + IP="ip -netns $ns1" + setup_ns ns2 # add vrf table - ip li add ${VRF} type vrf table ${VRF_TABLE} - ip li set ${VRF} up - ip ro add table ${VRF_TABLE} unreachable default metric 8192 - ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192 + ${IP} li add ${VRF} type vrf table ${VRF_TABLE} + ${IP} li set ${VRF} up + ${IP} ro add table ${VRF_TABLE} unreachable default metric 8192 + ${IP} -6 ro add table ${VRF_TABLE} unreachable default metric 8192 # create test interfaces - ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} - ip li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} - ip li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} - ip li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} + ${IP} li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} + ${IP} li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} + ${IP} li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} + ${IP} li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} # enslave vrf interfaces for n in 5 7; do - ip li set ${NETIFS[p${n}]} vrf ${VRF} + ${IP} li set ${NETIFS[p${n}]} vrf ${VRF} done # add addresses for n in 1 3 5 7; do - ip li set ${NETIFS[p${n}]} up - ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad + ${IP} li set ${NETIFS[p${n}]} up + ${IP} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ${IP} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done # move peer interfaces to namespace and add addresses for n in 2 4 6 8; do - ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up - ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad + ${IP} li set ${NETIFS[p${n}]} netns ${ns2} up + ip -netns $ns2 addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ip -netns $ns2 addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done - ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} - ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} + ${IP} -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} + ${IP} -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} set +e } -cleanup() -{ - # make sure we start from a clean slate - cleanup_ns ${PEER_NS} 2>/dev/null - for n in 1 3 5 7; do - ip link del ${NETIFS[p${n}]} 2>/dev/null - done - ip link del ${VRF} 2>/dev/null - ip ro flush table ${VRF_TABLE} - ip -6 ro flush table ${VRF_TABLE} -} - ################################################################################ # IPv4 tests # @@ -241,7 +231,7 @@ run_ip() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip ro add table "${table}" "${prefix}"/32 via "${gw}" "${dev}" onlink + run_cmd "${IP} ro add table ${table} ${prefix}/32 via ${gw} ${dev} onlink" log_test $? ${exp_rc} "${desc}" } @@ -257,8 +247,8 @@ run_ip_mpath() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip ro add table "${table}" "${prefix}"/32 \ - nexthop via ${nh1} nexthop via ${nh2} + run_cmd "${IP} ro add table ${table} ${prefix}/32 \ + nexthop via ${nh1} nexthop via ${nh2}" log_test $? ${exp_rc} "${desc}" } @@ -339,7 +329,7 @@ run_ip6() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip -6 ro add table "${table}" "${prefix}"/128 via "${gw}" "${dev}" onlink + run_cmd "${IP} -6 ro add table ${table} ${prefix}/128 via ${gw} ${dev} onlink" log_test $? ${exp_rc} "${desc}" } @@ -353,8 +343,8 @@ run_ip6_mpath() local exp_rc="$6" local desc="$7" - run_cmd ip -6 ro add table "${table}" "${prefix}"/128 "${opts}" \ - nexthop via ${nh1} nexthop via ${nh2} + run_cmd "${IP} -6 ro add table ${table} ${prefix}/128 ${opts} \ + nexthop via ${nh1} nexthop via ${nh2}" log_test $? ${exp_rc} "${desc}" } @@ -491,10 +481,9 @@ do esac done -cleanup setup run_onlink_tests -cleanup +cleanup_ns ${ns1} ${ns2} if [ "$TESTS" != "none" ]; then printf "\nTests passed: %3d\n" ${nsuccess} diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 2b0a90581e2f..21026b667667 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -800,6 +800,14 @@ ipv6_fcnal() set +e check_nexthop "dev veth1" "" log_test $? 0 "Nexthops removed on admin down" + + # error routes should be deleted when their nexthop is deleted + run_cmd "$IP li set dev veth1 up" + run_cmd "$IP -6 nexthop add id 58 dev veth1" + run_cmd "$IP ro add blackhole 2001:db8:101::1/128 nhid 58" + run_cmd "$IP nexthop del id 58" + check_route6 "2001:db8:101::1" "" + log_test $? 0 "Error route removed on nexthop deletion" } ipv6_grp_refs() @@ -1459,6 +1467,13 @@ ipv4_fcnal() run_cmd "$IP ro del 172.16.102.0/24" log_test $? 0 "Delete route when not specifying nexthop attributes" + + # error routes should be deleted when their nexthop is deleted + run_cmd "$IP nexthop add id 23 dev veth1" + run_cmd "$IP ro add blackhole 172.16.102.100/32 nhid 23" + run_cmd "$IP nexthop del id 23" + check_route "172.16.102.100" "" + log_test $? 0 "Error route removed on nexthop deletion" } ipv4_grp_fcnal() diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index a88f797c549a..c5694cc4ddd2 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -12,7 +12,7 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \ ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \ ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \ ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance \ - fib6_ra_to_static" + ipv4_mpath_balance_preferred fib6_ra_to_static" VERBOSE=0 PAUSE_ON_FAIL=no @@ -2751,6 +2751,73 @@ ipv4_mpath_balance_test() forwarding_cleanup } +get_route_dev_src() +{ + local pfx="$1" + local src="$2" + local out + + if out=$($IP -j route get "$pfx" from "$src" | jq -re ".[0].dev"); then + echo "$out" + fi +} + +ipv4_mpath_preferred() +{ + local src_ip=$1 + local pref_dev=$2 + local dev routes + local route0=0 + local route1=0 + local pref_route=0 + num_routes=254 + + for i in $(seq 1 $num_routes) ; do + dev=$(get_route_dev_src 172.16.105.$i $src_ip) + if [ "$dev" = "$pref_dev" ]; then + pref_route=$((pref_route+1)) + elif [ "$dev" = "veth1" ]; then + route0=$((route0+1)) + elif [ "$dev" = "veth3" ]; then + route1=$((route1+1)) + fi + done + + routes=$((route0+route1)) + + [ "$VERBOSE" = "1" ] && echo "multipath: routes seen: ($route0,$route1,$pref_route)" + + if [ x"$pref_dev" = x"" ]; then + [[ $routes -ge $num_routes ]] && [[ $route0 -gt 0 ]] && [[ $route1 -gt 0 ]] + else + [[ $pref_route -ge $num_routes ]] + fi + +} + +ipv4_mpath_balance_preferred_test() +{ + echo + echo "IPv4 multipath load balance preferred route" + + forwarding_setup + + $IP route add 172.16.105.0/24 \ + nexthop via 172.16.101.2 \ + nexthop via 172.16.103.2 + + ipv4_mpath_preferred 172.16.101.1 veth1 + log_test $? 0 "IPv4 multipath loadbalance from veth1" + + ipv4_mpath_preferred 172.16.103.1 veth3 + log_test $? 0 "IPv4 multipath loadbalance from veth3" + + ipv4_mpath_preferred 198.51.100.1 + log_test $? 0 "IPv4 multipath loadbalance from dummy" + + forwarding_cleanup +} + ipv6_mpath_balance_test() { echo @@ -2861,6 +2928,7 @@ do ipv6_mpath_list) ipv6_mpath_list_test;; ipv4_mpath_balance) ipv4_mpath_balance_test;; ipv6_mpath_balance) ipv6_mpath_balance_test;; + ipv4_mpath_balance_preferred) ipv4_mpath_balance_preferred_test;; fib6_ra_to_static) fib6_ra_to_static;; help) echo "Test names: $TESTS"; exit 0;; diff --git a/tools/testing/selftests/net/ipvtap_test.sh b/tools/testing/selftests/net/ipvtap_test.sh new file mode 100755 index 000000000000..354ca7ce8584 --- /dev/null +++ b/tools/testing/selftests/net/ipvtap_test.sh @@ -0,0 +1,168 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Simple tests for ipvtap + + +# +# The testing environment looks this way: +# +# |------HNS-------| |------PHY-------| +# | veth<----------------->veth | +# |------|--|------| |----------------| +# | | +# | | |-----TST0-------| +# | |------------|----ipvlan | +# | |----------------| +# | +# | |-----TST1-------| +# |---------------|----ipvlan | +# |----------------| +# + +ALL_TESTS=" + test_ip_set +" + +source lib.sh + +DEBUG=0 + +VETH_HOST=vethtst.h +VETH_PHY=vethtst.p + +NS_COUNT=32 +IP_ITERATIONS=1024 +IPSET_TIMEOUT="60s" + +ns_run() { + ns=$1 + shift + if [[ "$ns" == "global" ]]; then + "$@" >/dev/null + else + ip netns exec "$ns" "$@" >/dev/null + fi +} + +test_ip_setup_env() { + setup_ns NS_PHY + setup_ns HST_NS + + # setup simulated other-host (phy) and host itself + ns_run "$HST_NS" ip link add $VETH_HOST type veth peer name $VETH_PHY \ + netns "$NS_PHY" >/dev/null + ns_run "$HST_NS" ip link set $VETH_HOST up + ns_run "$NS_PHY" ip link set $VETH_PHY up + + for ((i=0; i<NS_COUNT; i++)); do + setup_ns ipvlan_ns_$i + ns="ipvlan_ns_$i" + if [ "$DEBUG" = "1" ]; then + echo "created NS ${!ns}" + fi + if ! ns_run "$HST_NS" ip link add netns ${!ns} ipvlan0 \ + link $VETH_HOST \ + type ipvtap mode l2 bridge; then + exit_error "FAIL: Failed to configure ipvlan link." + fi + done +} + +test_ip_cleanup_env() { + ns_run "$HST_NS" ip link del $VETH_HOST + cleanup_all_ns +} + +exit_error() { + echo "$1" + exit $ksft_fail +} + +rnd() { + echo $(( RANDOM % 32 + 16 )) +} + +test_ip_set_thread() { + # Here we are trying to create some IP conflicts between namespaces. + # If just add/remove IP, nothing interesting will happen. + # But if add random IP and then remove random IP, + # eventually conflicts start to apear. + ip link set ipvlan0 up + for ((i=0; i<IP_ITERATIONS; i++)); do + v=$(rnd) + ip a a "172.25.0.$v/24" dev ipvlan0 2>/dev/null + ip a a "fc00::$v/64" dev ipvlan0 2>/dev/null + v=$(rnd) + ip a d "172.25.0.$v/24" dev ipvlan0 2>/dev/null + ip a d "fc00::$v/64" dev ipvlan0 2>/dev/null + done +} + +test_ip_set() { + RET=0 + + trap test_ip_cleanup_env EXIT + + test_ip_setup_env + + declare -A ns_pids + for ((i=0; i<NS_COUNT; i++)); do + ns="ipvlan_ns_$i" + ns_run ${!ns} timeout "$IPSET_TIMEOUT" \ + bash -c "$0 test_ip_set_thread"& + ns_pids[$i]=$! + done + + for ((i=0; i<NS_COUNT; i++)); do + wait "${ns_pids[$i]}" + done + + declare -A all_ips + for ((i=0; i<NS_COUNT; i++)); do + ns="ipvlan_ns_$i" + ip_output=$(ip netns exec ${!ns} ip a l dev ipvlan0 | grep inet) + while IFS= read -r nsip_out; do + if [[ -z $nsip_out ]]; then + continue; + fi + nsip=$(awk '{print $2}' <<< "$nsip_out") + if [[ -v all_ips[$nsip] ]]; then + RET=$ksft_fail + log_test "conflict for $nsip" + return "$RET" + else + all_ips[$nsip]=$i + fi + done <<< "$ip_output" + done + + if [ "$DEBUG" = "1" ]; then + for key in "${!all_ips[@]}"; do + echo "$key: ${all_ips[$key]}" + done + fi + + trap - EXIT + test_ip_cleanup_env + + log_test "test multithreaded ip set" +} + +if [[ "$1" == "-d" ]]; then + DEBUG=1 + shift +fi + +if [[ "$1" == "-t" ]]; then + shift + TESTS="$*" +fi + +if [[ "$1" == "test_ip_set_thread" ]]; then + test_ip_set_thread +else + require_command ip + + tests_run +fi diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 40f9ce307dd1..f528b67639de 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -13,7 +13,7 @@ from .ksft import KsftFailEx, KsftSkipEx, KsftXfailEx, ksft_pr, ksft_eq, \ from .netns import NetNS, NetNSEnter from .nsim import NetdevSim, NetdevSimDev from .utils import CmdExitFailure, fd_read_timeout, cmd, bkg, defer, \ - bpftool, ip, ethtool, bpftrace, rand_port, wait_port_listen, wait_file + bpftool, ip, ethtool, bpftrace, rand_port, wait_port_listen, wait_file, tool from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily from .ynl import NetshaperFamily, DevlinkFamily, PSPFamily @@ -26,7 +26,7 @@ __all__ = ["KSRC", "NetNS", "NetNSEnter", "CmdExitFailure", "fd_read_timeout", "cmd", "bkg", "defer", "bpftool", "ip", "ethtool", "bpftrace", "rand_port", - "wait_port_listen", "wait_file", + "wait_port_listen", "wait_file", "tool", "NetdevSim", "NetdevSimDev", "NetshaperFamily", "DevlinkFamily", "PSPFamily", "NlError", "YnlFamily", "EthtoolFamily", "NetdevFamily", "RtnlFamily", diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 15d144a25d82..4dd6278cd3dd 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -3,6 +3,7 @@ top_srcdir = ../../../../.. CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -I$(top_srcdir)/tools/include TEST_PROGS := \ diag.sh \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 404a77bf366a..10f6f99cfd4e 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -33,6 +33,7 @@ #include <linux/tcp.h> #include <linux/time_types.h> #include <linux/sockios.h> +#include <linux/compiler.h> extern int optind; @@ -140,7 +141,7 @@ static void die_usage(void) exit(1); } -static void xerror(const char *fmt, ...) +static void __noreturn xerror(const char *fmt, ...) { va_list ap; diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c index e084796e804d..8e0b1b8d84b6 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_diag.c +++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c @@ -5,6 +5,7 @@ #include <linux/rtnetlink.h> #include <linux/inet_diag.h> #include <linux/netlink.h> +#include <linux/compiler.h> #include <sys/socket.h> #include <netinet/in.h> #include <linux/tcp.h> @@ -87,7 +88,7 @@ enum { #define rta_getattr(type, value) (*(type *)RTA_DATA(value)) -static void die_perror(const char *msg) +static void __noreturn die_perror(const char *msg) { perror(msg); exit(1); diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index 8e8f6441ad8b..5716998da192 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -28,6 +28,7 @@ #include <linux/tcp.h> #include <linux/sockios.h> +#include <linux/compiler.h> #ifndef IPPROTO_MPTCP #define IPPROTO_MPTCP 262 @@ -40,7 +41,7 @@ static int pf = AF_INET; static int proto_tx = IPPROTO_MPTCP; static int proto_rx = IPPROTO_MPTCP; -static void die_perror(const char *msg) +static void __noreturn die_perror(const char *msg) { perror(msg); exit(1); @@ -52,7 +53,7 @@ static void die_usage(int r) exit(r); } -static void xerror(const char *fmt, ...) +static void __noreturn xerror(const char *fmt, ...) { va_list ap; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index b2e6e548f796..e70d3420954f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2329,17 +2329,16 @@ signal_address_tests() ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 # It is not directly linked to the commit introducing this # symbol but for the parent one which is linked anyway. - if ! mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then - chk_join_nr 3 3 2 - chk_add_nr 4 4 - else - chk_join_nr 3 3 3 + if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then # the server will not signal the address terminating # the MPC subflow chk_add_nr 3 3 + else + chk_add_nr 4 4 fi fi } @@ -3847,21 +3846,28 @@ userspace_pm_chk_get_addr() fi } -# $1: ns ; $2: event type ; $3: count +# $1: ns ; $2: event type ; $3: count ; [ $4: attr ; $5: attr count ] chk_evt_nr() { local ns=${1} local evt_name="${2}" local exp="${3}" + local attr="${4}" + local attr_exp="${5}" local evts="${evts_ns1}" local evt="${!evt_name}" + local attr_name local count + if [ -n "${attr}" ]; then + attr_name=", ${attr}: ${attr_exp}" + fi + evt_name="${evt_name:16}" # without MPTCP_LIB_EVENT_ [ "${ns}" == "ns2" ] && evts="${evts_ns2}" - print_check "event ${ns} ${evt_name} (${exp})" + print_check "event ${ns} ${evt_name} (${exp}${attr_name})" if [[ "${evt_name}" = "LISTENER_"* ]] && ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then @@ -3872,11 +3878,42 @@ chk_evt_nr() count=$(grep -cw "type:${evt}" "${evts}") if [ "${count}" != "${exp}" ]; then fail_test "got ${count} events, expected ${exp}" + cat "${evts}" + return + elif [ -z "${attr}" ]; then + print_ok + return + fi + + count=$(grep -w "type:${evt}" "${evts}" | grep -c ",${attr}:") + if [ "${count}" != "${attr_exp}" ]; then + fail_test "got ${count} event attributes, expected ${attr_exp}" + grep -w "type:${evt}" "${evts}" else print_ok fi } +# $1: ns ; $2: event type ; $3: expected count +wait_event() +{ + local ns="${1}" + local evt_name="${2}" + local exp="${3}" + + local evt="${!evt_name}" + local evts="${evts_ns1}" + local count + + [ "${ns}" == "ns2" ] && evts="${evts_ns2}" + + for _ in $(seq 100); do + count=$(grep -cw "type:${evt}" "${evts}") + [ "${count}" -ge "${exp}" ] && break + sleep 0.1 + done +} + userspace_tests() { # userspace pm type prevents add_addr @@ -4085,6 +4122,36 @@ userspace_tests() kill_events_pids mptcp_lib_kill_group_wait $tests_pid fi + + # userspace pm no duplicated spurious close events after an error + if reset_with_events "userspace pm no dup close events after error" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 2 + { timeout_test=120 test_linkfail=128 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null + local tests_pid=$! + wait_event ns2 MPTCP_LIB_EVENT_ESTABLISHED 1 + userspace_pm_add_sf $ns2 10.0.3.2 20 + chk_mptcp_info subflows 1 subflows 1 + chk_subflows_total 2 2 + + # force quick loss + ip netns exec $ns2 sysctl -q net.ipv4.tcp_syn_retries=1 + if ip netns exec "${ns1}" ${iptables} -A INPUT -s "10.0.1.2" \ + -p tcp --tcp-option 30 -j REJECT --reject-with tcp-reset && + ip netns exec "${ns2}" ${iptables} -A INPUT -d "10.0.1.2" \ + -p tcp --tcp-option 30 -j REJECT --reject-with tcp-reset; then + wait_event ns2 MPTCP_LIB_EVENT_SUB_CLOSED 1 + wait_event ns1 MPTCP_LIB_EVENT_SUB_CLOSED 1 + chk_subflows_total 1 1 + userspace_pm_add_sf $ns2 10.0.1.2 0 + wait_event ns2 MPTCP_LIB_EVENT_SUB_CLOSED 2 + chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_CLOSED 2 error 2 + fi + kill_events_pids + mptcp_lib_kill_group_wait $tests_pid + fi } endpoint_tests() diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index 286164f7246e..b6e58d936ebe 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -25,6 +25,7 @@ #include <netinet/in.h> #include <linux/tcp.h> +#include <linux/compiler.h> static int pf = AF_INET; @@ -127,7 +128,7 @@ struct so_state { #define MIN(a, b) ((a) < (b) ? (a) : (b)) #endif -static void die_perror(const char *msg) +static void __noreturn die_perror(const char *msg) { perror(msg); exit(1); @@ -139,7 +140,7 @@ static void die_usage(int r) exit(r); } -static void xerror(const char *fmt, ...) +static void __noreturn xerror(const char *fmt, ...) { va_list ap; diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh index ad97c6227f35..394166f224a4 100755 --- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh @@ -29,7 +29,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below -BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate" +BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate insert_overlap" # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" @@ -420,6 +420,18 @@ race_repeat 0 perf_duration 0 " +TYPE_insert_overlap=" +display reject overlapping range on add +type_spec ipv4_addr . ipv4_addr +chain_spec ip saddr . ip daddr +dst addr4 +proto icmp + +race_repeat 0 + +perf_duration 0 +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -1954,6 +1966,37 @@ EOF return 0 } +add_fail() +{ + if nft add element inet filter test "$1" 2>/dev/null ; then + err "Returned success for add ${1} given set:" + err "$(nft -a list set inet filter test )" + return 1 + fi + + return 0 +} + +test_bug_insert_overlap() +{ + local elements="1.2.3.4 . 1.2.4.1" + + setup veth send_"${proto}" set || return ${ksft_skip} + + add "{ $elements }" || return 1 + + elements="1.2.3.0-1.2.3.4 . 1.2.4.1" + add_fail "{ $elements }" || return 1 + + elements="1.2.3.0-1.2.3.4 . 1.2.4.2" + add "{ $elements }" || return 1 + + elements="1.2.3.4 . 1.2.4.1-1.2.4.2" + add_fail "{ $elements }" || return 1 + + return 0 +} + test_reported_issues() { eval test_bug_"${subtest}" } diff --git a/tools/testing/selftests/net/tap.c b/tools/testing/selftests/net/tap.c index 9ec1c9b50e77..a0c9418132c8 100644 --- a/tools/testing/selftests/net/tap.c +++ b/tools/testing/selftests/net/tap.c @@ -56,18 +56,12 @@ static void rtattr_end(struct nlmsghdr *nh, struct rtattr *attr) static struct rtattr *rtattr_add_str(struct nlmsghdr *nh, unsigned short type, const char *s) { - struct rtattr *rta = rtattr_add(nh, type, strlen(s)); + unsigned int strsz = strlen(s) + 1; + struct rtattr *rta; - memcpy(RTA_DATA(rta), s, strlen(s)); - return rta; -} - -static struct rtattr *rtattr_add_strsz(struct nlmsghdr *nh, unsigned short type, - const char *s) -{ - struct rtattr *rta = rtattr_add(nh, type, strlen(s) + 1); + rta = rtattr_add(nh, type, strsz); - strcpy(RTA_DATA(rta), s); + memcpy(RTA_DATA(rta), s, strsz); return rta; } @@ -119,7 +113,7 @@ static int dev_create(const char *dev, const char *link_type, link_info = rtattr_begin(&req.nh, IFLA_LINKINFO); - rtattr_add_strsz(&req.nh, IFLA_INFO_KIND, link_type); + rtattr_add_str(&req.nh, IFLA_INFO_KIND, link_type); if (fill_info_data) { info_data = rtattr_begin(&req.nh, IFLA_INFO_DATA); diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index da156feabcbf..b056eb966871 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -1098,5 +1098,52 @@ "teardown": [ "$TC qdisc del dev $DUMMY root" ] + }, + { + "id": "4ed9", + "name": "Try to redirect to self on egress with clsact", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY clsact", + "$TC filter add dev $DUMMY egress protocol ip prio 10 matchall action mirred egress redirect dev $DUMMY index 1" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "egress", + "index": 1, + "stats": { + "packets": 1, + "overlimits": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY clsact" + ] } + ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json index e5cc31f265f8..0179c57104ad 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json @@ -81,5 +81,30 @@ "$TC qdisc del dev $DUMMY handle 1: root", "$IP link del dev $DUMMY" ] + }, + { + "id": "124e", + "name": "Try to add teql as a child qdisc", + "category": [ + "qdisc", + "ets", + "tbf" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: qfq", + "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 15 maxpkt 16384" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1:1 handle 2:1 teql0", + "expExitCode": "2", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:1", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1:" + ] } ] diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile index 837977b62417..06ba6fde098d 100644 --- a/tools/testing/selftests/ublk/Makefile +++ b/tools/testing/selftests/ublk/Makefile @@ -22,6 +22,7 @@ TEST_PROGS += test_generic_11.sh TEST_PROGS += test_generic_12.sh TEST_PROGS += test_generic_13.sh TEST_PROGS += test_generic_14.sh +TEST_PROGS += test_generic_15.sh TEST_PROGS += test_null_01.sh TEST_PROGS += test_null_02.sh @@ -50,10 +51,10 @@ TEST_PROGS += test_stress_07.sh TEST_GEN_PROGS_EXTENDED = kublk +LOCAL_HDRS += $(wildcard *.h) include ../lib.mk -$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c \ - fault_inject.c +$(TEST_GEN_PROGS_EXTENDED): $(wildcard *.c) check: shellcheck -x -f gcc *.sh diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index 185ba553686a..f197ad9cc262 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -753,7 +753,7 @@ static int ublk_thread_is_idle(struct ublk_thread *t) static int ublk_thread_is_done(struct ublk_thread *t) { - return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t); + return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t) && !t->cmd_inflight; } static inline void ublksrv_handle_tgt_cqe(struct ublk_thread *t, @@ -1054,7 +1054,9 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) } if (ret < 0) { ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret); - goto fail; + /* stop device so that inflight uring_cmd can be cancelled */ + ublk_ctrl_stop_dev(dev); + goto fail_start; } ublk_ctrl_get_info(dev); @@ -1062,7 +1064,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) ublk_ctrl_dump(dev); else ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id); - +fail_start: /* wait until we are terminated */ for (i = 0; i < dev->nthreads; i++) pthread_join(tinfo[i].thread, &thread_ret); @@ -1272,7 +1274,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) } ret = ublk_start_daemon(ctx, dev); - ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\b", ret); + ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\n", __func__, ret); if (ret < 0) ublk_ctrl_del_dev(dev); @@ -1618,6 +1620,7 @@ int main(int argc, char *argv[]) int option_idx, opt; const char *cmd = argv[1]; struct dev_ctx ctx = { + ._evtfd = -1, .queue_depth = 128, .nr_hw_queues = 2, .dev_id = -1, diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh index 6f1c042de40e..ea9a5f3eb70a 100755 --- a/tools/testing/selftests/ublk/test_common.sh +++ b/tools/testing/selftests/ublk/test_common.sh @@ -178,8 +178,9 @@ _have_feature() _create_ublk_dev() { local dev_id; local cmd=$1 + local settle=$2 - shift 1 + shift 2 if [ ! -c /dev/ublk-control ]; then return ${UBLK_SKIP_CODE} @@ -194,7 +195,10 @@ _create_ublk_dev() { echo "fail to add ublk dev $*" return 255 fi - udevadm settle + + if [ "$settle" = "yes" ]; then + udevadm settle + fi if [[ "$dev_id" =~ ^[0-9]+$ ]]; then echo "${dev_id}" @@ -204,14 +208,18 @@ _create_ublk_dev() { } _add_ublk_dev() { - _create_ublk_dev "add" "$@" + _create_ublk_dev "add" "yes" "$@" +} + +_add_ublk_dev_no_settle() { + _create_ublk_dev "add" "no" "$@" } _recover_ublk_dev() { local dev_id local state - dev_id=$(_create_ublk_dev "recover" "$@") + dev_id=$(_create_ublk_dev "recover" "yes" "$@") for ((j=0;j<20;j++)); do state=$(_get_ublk_dev_state "${dev_id}") [ "$state" == "LIVE" ] && break diff --git a/tools/testing/selftests/ublk/test_generic_15.sh b/tools/testing/selftests/ublk/test_generic_15.sh new file mode 100755 index 000000000000..76379362e0a2 --- /dev/null +++ b/tools/testing/selftests/ublk/test_generic_15.sh @@ -0,0 +1,68 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="generic_15" +ERR_CODE=0 + +_test_partition_scan_no_hang() +{ + local recovery_flag=$1 + local expected_state=$2 + local dev_id + local state + local daemon_pid + local start_time + local elapsed + + # Create ublk device with fault_inject target and very large delay + # to simulate hang during partition table read + # --delay_us 60000000 = 60 seconds delay + # Use _add_ublk_dev_no_settle to avoid udevadm settle hang waiting + # for partition scan events to complete + if [ "$recovery_flag" = "yes" ]; then + echo "Testing partition scan with recovery support..." + dev_id=$(_add_ublk_dev_no_settle -t fault_inject -q 1 -d 1 --delay_us 60000000 -r 1) + else + echo "Testing partition scan without recovery..." + dev_id=$(_add_ublk_dev_no_settle -t fault_inject -q 1 -d 1 --delay_us 60000000) + fi + + _check_add_dev "$TID" $? + + # The add command should return quickly because partition scan is async. + # Now sleep briefly to let the async partition scan work start and hit + # the delay in the fault_inject handler. + sleep 1 + + # Kill the ublk daemon while partition scan is potentially blocked + # And check state transitions properly + start_time=${SECONDS} + daemon_pid=$(_get_ublk_daemon_pid "${dev_id}") + state=$(__ublk_kill_daemon "${dev_id}" "${expected_state}") + elapsed=$((SECONDS - start_time)) + + # Verify the device transitioned to expected state + if [ "$state" != "${expected_state}" ]; then + echo "FAIL: Device state is $state, expected ${expected_state}" + ERR_CODE=255 + ${UBLK_PROG} del -n "${dev_id}" > /dev/null 2>&1 + return + fi + echo "PASS: Device transitioned to ${expected_state} in ${elapsed}s without hanging" + + # Clean up the device + ${UBLK_PROG} del -n "${dev_id}" > /dev/null 2>&1 +} + +_prep_test "partition_scan" "verify async partition scan prevents IO hang" + +# Test 1: Without recovery support - should transition to DEAD +_test_partition_scan_no_hang "no" "DEAD" + +# Test 2: With recovery support - should transition to QUIESCED +_test_partition_scan_no_hang "yes" "QUIESCED" + +_cleanup_test "partition_scan" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/vDSO/vgetrandom-chacha.S b/tools/testing/selftests/vDSO/vgetrandom-chacha.S index a4a82e1c28a9..8c3cbf4dfd6a 100644 --- a/tools/testing/selftests/vDSO/vgetrandom-chacha.S +++ b/tools/testing/selftests/vDSO/vgetrandom-chacha.S @@ -14,7 +14,7 @@ #elif defined(__riscv) && __riscv_xlen == 64 #include "../../../../arch/riscv/kernel/vdso/vgetrandom-chacha.S" #elif defined(__s390x__) -#include "../../../../arch/s390/kernel/vdso64/vgetrandom-chacha.S" +#include "../../../../arch/s390/kernel/vdso/vgetrandom-chacha.S" #elif defined(__x86_64__) #include "../../../../arch/x86/entry/vdso/vgetrandom-chacha.S" #endif diff --git a/tools/testing/selftests/vfio/lib/include/libvfio/iova_allocator.h b/tools/testing/selftests/vfio/lib/include/libvfio/iova_allocator.h index 8f1d994e9ea2..c7c0796a757f 100644 --- a/tools/testing/selftests/vfio/lib/include/libvfio/iova_allocator.h +++ b/tools/testing/selftests/vfio/lib/include/libvfio/iova_allocator.h @@ -2,7 +2,6 @@ #ifndef SELFTESTS_VFIO_LIB_INCLUDE_LIBVFIO_IOVA_ALLOCATOR_H #define SELFTESTS_VFIO_LIB_INCLUDE_LIBVFIO_IOVA_ALLOCATOR_H -#include <uapi/linux/types.h> #include <linux/list.h> #include <linux/types.h> #include <linux/iommufd.h> diff --git a/tools/testing/selftests/vfio/lib/iommu.c b/tools/testing/selftests/vfio/lib/iommu.c index 8079d43523f3..58b7fb7430d4 100644 --- a/tools/testing/selftests/vfio/lib/iommu.c +++ b/tools/testing/selftests/vfio/lib/iommu.c @@ -11,7 +11,6 @@ #include <sys/ioctl.h> #include <sys/mman.h> -#include <uapi/linux/types.h> #include <linux/limits.h> #include <linux/mman.h> #include <linux/types.h> diff --git a/tools/testing/selftests/vfio/lib/iova_allocator.c b/tools/testing/selftests/vfio/lib/iova_allocator.c index a12b0a51e9e6..8c1cc86b70cd 100644 --- a/tools/testing/selftests/vfio/lib/iova_allocator.c +++ b/tools/testing/selftests/vfio/lib/iova_allocator.c @@ -11,7 +11,6 @@ #include <sys/ioctl.h> #include <sys/mman.h> -#include <uapi/linux/types.h> #include <linux/iommufd.h> #include <linux/limits.h> #include <linux/mman.h> diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index 8e34b9bfc96b..fac4c0ecadef 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -11,7 +11,6 @@ #include <sys/ioctl.h> #include <sys/mman.h> -#include <uapi/linux/types.h> #include <linux/iommufd.h> #include <linux/limits.h> #include <linux/mman.h> diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c index 16eba2ecca47..3bf984b337ac 100644 --- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c @@ -3,7 +3,6 @@ #include <sys/mman.h> #include <unistd.h> -#include <uapi/linux/types.h> #include <linux/iommufd.h> #include <linux/limits.h> #include <linux/mman.h> diff --git a/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c b/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c index 17017ed3beac..ec1e5633e080 100644 --- a/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c +++ b/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include <uapi/linux/types.h> #include <linux/limits.h> #include <linux/sizes.h> #include <linux/vfio.h> diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 83148875a12c..434065215d12 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -36,6 +36,7 @@ BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) CFLAGS := -O2 -g -std=gnu99 -pthread -Wall $(KHDR_INCLUDES) +CFLAGS += -I $(top_srcdir)/tools/testing/selftests/ # call32_from_64 in thunks.S uses absolute addresses. ifeq ($(CAN_BUILD_WITH_NOPIE),1) diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index d843643ced6b..9430ef5b8bc3 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -511,6 +511,18 @@ void run_tests(const struct test_case *test_cases, printf("ok\n"); } + + printf("All tests have been executed. Waiting other peer..."); + fflush(stdout); + + /* + * Final full barrier, to ensure that all tests have been run and + * that even the last one has been successful on both sides. + */ + control_writeln("COMPLETED"); + control_expectln("COMPLETED"); + + printf("ok\n"); } void list_tests(const struct test_case *test_cases) diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 142c02a6834a..bf633cde82b0 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -25,7 +25,7 @@ enum transport { }; static const char * const transport_ksyms[] = { - #define x(name, symbol) "d " symbol "_transport", + #define x(name, symbol) " " symbol "_transport", KNOWN_TRANSPORTS(x) #undef x }; diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 9e1250790f33..5bd20ccd9335 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -347,10 +347,12 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) } #define SOCK_BUF_SIZE (2 * 1024 * 1024) +#define SOCK_BUF_SIZE_SMALL (64 * 1024) #define MAX_MSG_PAGES 4 static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) { + unsigned long long sock_buf_size; unsigned long curr_hash; size_t max_msg_size; int page_size; @@ -363,6 +365,16 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) exit(EXIT_FAILURE); } + sock_buf_size = SOCK_BUF_SIZE; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + /* Wait, until receiver sets buffer size. */ control_expectln("SRVREADY"); @@ -2192,6 +2204,128 @@ static void test_stream_nolinger_server(const struct test_opts *opts) close(fd); } +static void test_stream_accepted_setsockopt_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_accepted_setsockopt_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + enable_so_zerocopy_check(fd); + close(fd); +} + +static void test_stream_tx_credit_bounds_client(const struct test_opts *opts) +{ + unsigned long long sock_buf_size; + size_t total = 0; + char buf[4096]; + int fd; + + memset(buf, 'A', sizeof(buf)); + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + sock_buf_size = SOCK_BUF_SIZE_SMALL; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + + if (fcntl(fd, F_SETFL, fcntl(fd, F_GETFL, 0) | O_NONBLOCK) < 0) { + perror("fcntl(F_SETFL)"); + exit(EXIT_FAILURE); + } + + control_expectln("SRVREADY"); + + for (;;) { + ssize_t sent = send(fd, buf, sizeof(buf), 0); + + if (sent == 0) { + fprintf(stderr, "unexpected EOF while sending bytes\n"); + exit(EXIT_FAILURE); + } + + if (sent < 0) { + if (errno == EINTR) + continue; + + if (errno == EAGAIN || errno == EWOULDBLOCK) + break; + + perror("send"); + exit(EXIT_FAILURE); + } + + total += sent; + } + + control_writeln("CLIDONE"); + close(fd); + + /* We should not be able to send more bytes than the value set as + * local buffer size. + */ + if (total > sock_buf_size) { + fprintf(stderr, + "TX credit too large: queued %zu bytes (expected <= %llu)\n", + total, sock_buf_size); + exit(EXIT_FAILURE); + } +} + +static void test_stream_tx_credit_bounds_server(const struct test_opts *opts) +{ + unsigned long long sock_buf_size; + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + sock_buf_size = SOCK_BUF_SIZE; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + + control_writeln("SRVREADY"); + control_expectln("CLIDONE"); + + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -2371,6 +2505,21 @@ static struct test_case test_cases[] = { .run_client = test_seqpacket_unread_bytes_client, .run_server = test_seqpacket_unread_bytes_server, }, + { + .name = "SOCK_STREAM accept()ed socket custom setsockopt()", + .run_client = test_stream_accepted_setsockopt_client, + .run_server = test_stream_accepted_setsockopt_server, + }, + { + .name = "SOCK_STREAM virtio MSG_ZEROCOPY coalescence corruption", + .run_client = test_stream_msgzcopy_mangle_client, + .run_server = test_stream_msgzcopy_mangle_server, + }, + { + .name = "SOCK_STREAM TX credit bounds", + .run_client = test_stream_tx_credit_bounds_client, + .run_server = test_stream_tx_credit_bounds_server, + }, {}, }; diff --git a/tools/testing/vsock/vsock_test_zerocopy.c b/tools/testing/vsock/vsock_test_zerocopy.c index 9d9a6cb9614a..a31ddfc1cd0c 100644 --- a/tools/testing/vsock/vsock_test_zerocopy.c +++ b/tools/testing/vsock/vsock_test_zerocopy.c @@ -9,14 +9,18 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/ioctl.h> #include <sys/mman.h> #include <unistd.h> #include <poll.h> #include <linux/errqueue.h> #include <linux/kernel.h> +#include <linux/sockios.h> +#include <linux/time64.h> #include <errno.h> #include "control.h" +#include "timeout.h" #include "vsock_test_zerocopy.h" #include "msg_zerocopy_common.h" @@ -356,3 +360,73 @@ void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts) control_expectln("DONE"); close(fd); } + +#define GOOD_COPY_LEN 128 /* net/vmw_vsock/virtio_transport_common.c */ + +void test_stream_msgzcopy_mangle_client(const struct test_opts *opts) +{ + char sbuf1[PAGE_SIZE + 1], sbuf2[GOOD_COPY_LEN]; + unsigned long hash; + struct pollfd fds; + int fd, i; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + enable_so_zerocopy_check(fd); + + memset(sbuf1, 'x', sizeof(sbuf1)); + send_buf(fd, sbuf1, sizeof(sbuf1), 0, sizeof(sbuf1)); + + for (i = 0; i < sizeof(sbuf2); i++) + sbuf2[i] = rand() & 0xff; + + send_buf(fd, sbuf2, sizeof(sbuf2), MSG_ZEROCOPY, sizeof(sbuf2)); + + hash = hash_djb2(sbuf2, sizeof(sbuf2)); + control_writeulong(hash); + + fds.fd = fd; + fds.events = 0; + + if (poll(&fds, 1, TIMEOUT * MSEC_PER_SEC) != 1 || + !(fds.revents & POLLERR)) { + perror("poll"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +void test_stream_msgzcopy_mangle_server(const struct test_opts *opts) +{ + unsigned long local_hash, remote_hash; + char rbuf[PAGE_SIZE + 1]; + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Wait, don't race the (buggy) skbs coalescence. */ + vsock_ioctl_int(fd, SIOCINQ, PAGE_SIZE + 1 + GOOD_COPY_LEN); + + /* Discard the first packet. */ + recv_buf(fd, rbuf, PAGE_SIZE + 1, 0, PAGE_SIZE + 1); + + recv_buf(fd, rbuf, GOOD_COPY_LEN, 0, GOOD_COPY_LEN); + remote_hash = control_readulong(); + local_hash = hash_djb2(rbuf, GOOD_COPY_LEN); + + if (local_hash != remote_hash) { + fprintf(stderr, "Data received corrupted\n"); + exit(EXIT_FAILURE); + } + + close(fd); +} diff --git a/tools/testing/vsock/vsock_test_zerocopy.h b/tools/testing/vsock/vsock_test_zerocopy.h index 3ef2579e024d..d46c91a69f16 100644 --- a/tools/testing/vsock/vsock_test_zerocopy.h +++ b/tools/testing/vsock/vsock_test_zerocopy.h @@ -12,4 +12,7 @@ void test_seqpacket_msgzcopy_server(const struct test_opts *opts); void test_stream_msgzcopy_empty_errq_client(const struct test_opts *opts); void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts); +void test_stream_msgzcopy_mangle_client(const struct test_opts *opts); +void test_stream_msgzcopy_mangle_server(const struct test_opts *opts); + #endif /* VSOCK_TEST_ZEROCOPY_H */ |