Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "Apart from the arm64-specific bits (core arch and perf, new arm64
  selftests), it touches the generic cow_user_page() (reviewed by
  Kirill) together with a macro for x86 to preserve the existing
  behaviour on this architecture.

  Summary:

   - On ARMv8 CPUs without hardware updates of the access flag, avoid
     failing cow_user_page() on PFN mappings if the pte is old. The
     patches introduce an arch_faults_on_old_pte() macro, defined as
     false on x86. When true, cow_user_page() makes the pte young before
     attempting __copy_from_user_inatomic().

   - Covert the synchronous exception handling paths in
     arch/arm64/kernel/entry.S to C.

   - FTRACE_WITH_REGS support for arm64.

   - ZONE_DMA re-introduced on arm64 to support Raspberry Pi 4

   - Several kselftest cases specific to arm64, together with a
     MAINTAINERS update for these files (moved to the ARM64 PORT entry).

   - Workaround for a Neoverse-N1 erratum where the CPU may fetch stale
     instructions under certain conditions.

   - Workaround for Cortex-A57 and A72 errata where the CPU may
     speculatively execute an AT instruction and associate a VMID with
     the wrong guest page tables (corrupting the TLB).

   - Perf updates for arm64: additional PMU topologies on HiSilicon
     platforms, support for CCN-512 interconnect, AXI ID filtering in
     the IMX8 DDR PMU, support for the CCPI2 uncore PMU in ThunderX2.

   - GICv3 optimisation to avoid a heavy barrier when accessing the
     ICC_PMR_EL1 register.

   - ELF HWCAP documentation updates and clean-up.

   - SMC calling convention conduit code clean-up.

   - KASLR diagnostics printed during boot

   - NVIDIA Carmel CPU added to the KPTI whitelist

   - Some arm64 mm clean-ups: use generic free_initrd_mem(), remove
     stale macro, simplify calculation in __create_pgd_mapping(), typos.

   - Kconfig clean-ups: CMDLINE_FORCE to depend on CMDLINE, choice for
     endinanness to help with allmodconfig"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (93 commits)
  arm64: Kconfig: add a choice for endianness
  kselftest: arm64: fix spelling mistake "contiguos" -> "contiguous"
  arm64: Kconfig: make CMDLINE_FORCE depend on CMDLINE
  MAINTAINERS: Add arm64 selftests to the ARM64 PORT entry
  arm64: kaslr: Check command line before looking for a seed
  arm64: kaslr: Announce KASLR status on boot
  kselftest: arm64: fake_sigreturn_misaligned_sp
  kselftest: arm64: fake_sigreturn_bad_size
  kselftest: arm64: fake_sigreturn_duplicated_fpsimd
  kselftest: arm64: fake_sigreturn_missing_fpsimd
  kselftest: arm64: fake_sigreturn_bad_size_for_magic0
  kselftest: arm64: fake_sigreturn_bad_magic
  kselftest: arm64: add helper get_current_context
  kselftest: arm64: extend test_init functionalities
  kselftest: arm64: mangle_pstate_invalid_mode_el[123][ht]
  kselftest: arm64: mangle_pstate_invalid_daif_bits
  kselftest: arm64: mangle_pstate_invalid_compat_toggle and common utils
  kselftest: arm64: extend toplevel skeleton Makefile
  drivers/perf: hisi: update the sccl_id/ccl_id for certain HiSilicon platform
  arm64: mm: reserve CMA and crashkernel in ZONE_DMA32
  ...

8 files changed, 92 insertions, 42 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index dae64600ccbf..a9c4e4721434 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -110,17 +110,17 @@
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
-#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
-#define MCOUNT_REC()	. = ALIGN(8);				\
-			__start_mcount_loc = .;			\
-			KEEP(*(__patchable_function_entries))	\
-			__stop_mcount_loc = .;
-#else
+/*
+ * The ftrace call sites are logged to a section whose name depends on the
+ * compiler option used. A given kernel image will only use one, AKA
+ * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header
+ * dependencies for FTRACE_CALLSITE_SECTION's definition.
+ */
 #define MCOUNT_REC()	. = ALIGN(8);				\
 			__start_mcount_loc = .;			\
 			KEEP(*(__mcount_loc))			\
+			KEEP(*(__patchable_function_entries))	\
 			__stop_mcount_loc = .;
-#endif
 #else
 #define MCOUNT_REC()
 #endif
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 080012a6f025..df01a8579034 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -80,6 +80,22 @@
 
 #include <linux/linkage.h>
 #include <linux/types.h>
+
+enum arm_smccc_conduit {
+	SMCCC_CONDUIT_NONE,
+	SMCCC_CONDUIT_SMC,
+	SMCCC_CONDUIT_HVC,
+};
+
+/**
+ * arm_smccc_1_1_get_conduit()
+ *
+ * Returns the conduit to be used for SMCCCv1.1 or later.
+ *
+ * When SMCCCv1.1 is not present, returns SMCCC_CONDUIT_NONE.
+ */
+enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void);
+
 /**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h
index 3305ea7f9dc7..0a241c5c911d 100644
--- a/include/linux/arm_sdei.h
+++ b/include/linux/arm_sdei.h
@@ -5,12 +5,6 @@
 
 #include <uapi/linux/arm_sdei.h>
 
-enum sdei_conduit_types {
-	CONDUIT_INVALID = 0,
-	CONDUIT_SMC,
-	CONDUIT_HVC,
-};
-
 #include <acpi/ghes.h>
 
 #ifdef CONFIG_ARM_SDE_INTERFACE
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index adf993a3bd58..d03af3605460 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -5,6 +5,8 @@
 #include <linux/dma-mapping.h>
 #include <linux/mem_encrypt.h>
 
+extern unsigned int zone_dma_bits;
+
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
 #else
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8a8cb3c401b2..9141f2263286 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -499,7 +499,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
 /**
  * ftrace_make_nop - convert code into nop
  * @mod: module structure if called by module load initialization
- * @rec: the mcount call site record
+ * @rec: the call site record (e.g. mcount/fentry)
  * @addr: the address that the call site should be calling
  *
  * This is a very sensitive operation and great care needs
@@ -520,9 +520,38 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
 extern int ftrace_make_nop(struct module *mod,
 			   struct dyn_ftrace *rec, unsigned long addr);
 
+
+/**
+ * ftrace_init_nop - initialize a nop call site
+ * @mod: module structure if called by module load initialization
+ * @rec: the call site record (e.g. mcount/fentry)
+ *
+ * This is a very sensitive operation and great care needs
+ * to be taken by the arch.  The operation should carefully
+ * read the location, check to see if what is read is indeed
+ * what we expect it to be, and then on success of the compare,
+ * it should write to the location.
+ *
+ * The code segment at @rec->ip should contain the contents created by
+ * the compiler
+ *
+ * Return must be:
+ *  0 on success
+ *  -EFAULT on error reading the location
+ *  -EINVAL on a failed compare of the contents
+ *  -EPERM  on error writing to the location
+ * Any other value will be considered a failure.
+ */
+#ifndef ftrace_init_nop
+static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	return ftrace_make_nop(mod, rec, MCOUNT_ADDR);
+}
+#endif
+
 /**
  * ftrace_make_call - convert a nop call site into a call to addr
- * @rec: the mcount call site record
+ * @rec: the call site record (e.g. mcount/fentry)
  * @addr: the address that the call site should call
  *
  * This is a very sensitive operation and great care needs
@@ -545,7 +574,7 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 /**
  * ftrace_modify_call - convert from one addr to another (no nop)
- * @rec: the mcount call site record
+ * @rec: the call site record (e.g. mcount/fentry)
  * @old_addr: the address expected to be currently called to
  * @addr: the address to change to
  *
@@ -709,6 +738,11 @@ static inline unsigned long get_lock_parent_ip(void)
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
+#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
+#define FTRACE_CALLSITE_SECTION	"__patchable_function_entries"
+#else
+#define FTRACE_CALLSITE_SECTION	"__mcount_loc"
+#endif
 #else
 static inline void ftrace_init(void) { }
 #endif
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 5cc10cf7cb3e..a0bde9e12efa 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -487,6 +487,8 @@
 #define ICC_CTLR_EL1_EOImode_MASK	(1 << ICC_CTLR_EL1_EOImode_SHIFT)
 #define ICC_CTLR_EL1_CBPR_SHIFT		0
 #define ICC_CTLR_EL1_CBPR_MASK		(1 << ICC_CTLR_EL1_CBPR_SHIFT)
+#define ICC_CTLR_EL1_PMHE_SHIFT		6
+#define ICC_CTLR_EL1_PMHE_MASK		(1 << ICC_CTLR_EL1_PMHE_SHIFT)
 #define ICC_CTLR_EL1_PRI_BITS_SHIFT	8
 #define ICC_CTLR_EL1_PRI_BITS_MASK	(0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT)
 #define ICC_CTLR_EL1_ID_BITS_SHIFT	11
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bda20282746b..b0a36d1580b6 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -359,33 +359,40 @@ struct per_cpu_nodestat {
 #endif /* !__GENERATING_BOUNDS.H */
 
 enum zone_type {
-#ifdef CONFIG_ZONE_DMA
 	/*
-	 * ZONE_DMA is used when there are devices that are not able
-	 * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
-	 * carve out the portion of memory that is needed for these devices.
-	 * The range is arch specific.
+	 * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able
+	 * to DMA to all of the addressable memory (ZONE_NORMAL).
+	 * On architectures where this area covers the whole 32 bit address
+	 * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller
+	 * DMA addressing constraints. This distinction is important as a 32bit
+	 * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit
+	 * platforms may need both zones as they support peripherals with
+	 * different DMA addressing limitations.
+	 *
+	 * Some examples:
+	 *
+	 *  - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the
+	 *    rest of the lower 4G.
+	 *
+	 *  - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on
+	 *    the specific device.
+	 *
+	 *  - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the
+	 *    lower 4G.
 	 *
-	 * Some examples
+	 *  - powerpc only uses ZONE_DMA, the size, up to 2G, may vary
+	 *    depending on the specific device.
 	 *
-	 * Architecture		Limit
-	 * ---------------------------
-	 * parisc, ia64, sparc	<4G
-	 * s390, powerpc	<2G
-	 * arm			Various
-	 * alpha		Unlimited or 0-16MB.
+	 *  - s390 uses ZONE_DMA fixed to the lower 2G.
 	 *
-	 * i386, x86_64 and multiple other arches
-	 * 			<16M.
+	 *  - ia64 and riscv only use ZONE_DMA32.
+	 *
+	 *  - parisc uses neither.
 	 */
+#ifdef CONFIG_ZONE_DMA
 	ZONE_DMA,
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	/*
-	 * x86_64 needs two ZONE_DMAs because it supports devices that are
-	 * only able to do DMA to the lower 16M but also 32 bit devices that
-	 * can only do DMA areas below 4G.
-	 */
 	ZONE_DMA32,
 #endif
 	/*
diff --git a/include/linux/psci.h b/include/linux/psci.h
index e2bacc6fd2f2..ebe0a881d13d 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -7,6 +7,7 @@
 #ifndef __LINUX_PSCI_H
 #define __LINUX_PSCI_H
 
+#include <linux/arm-smccc.h>
 #include <linux/init.h>
 #include <linux/types.h>
 
@@ -18,12 +19,6 @@ bool psci_tos_resident_on(int cpu);
 int psci_cpu_suspend_enter(u32 state);
 bool psci_power_state_is_valid(u32 state);
 
-enum psci_conduit {
-	PSCI_CONDUIT_NONE,
-	PSCI_CONDUIT_SMC,
-	PSCI_CONDUIT_HVC,
-};
-
 enum smccc_version {
 	SMCCC_VERSION_1_0,
 	SMCCC_VERSION_1_1,
@@ -38,7 +33,7 @@ struct psci_operations {
 	int (*affinity_info)(unsigned long target_affinity,
 			unsigned long lowest_affinity_level);
 	int (*migrate_info_type)(void);
-	enum psci_conduit conduit;
+	enum arm_smccc_conduit conduit;
 	enum smccc_version smccc_version;
 };