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

Pull arm64 updates from Will Deacon:
 "ACPI:

   - Improve error reporting when failing to manage SDEI on AGDI device
     removal

  Assembly routines:

   - Improve register constraints so that the compiler can make use of
     the zero register instead of moving an immediate #0 into a GPR

   - Allow the compiler to allocate the registers used for CAS
     instructions

  CPU features and system registers:

   - Cleanups to the way in which CPU features are identified from the
     ID register fields

   - Extend system register definition generation to handle Enum types
     when defining shared register fields

   - Generate definitions for new _EL2 registers and add new fields for
     ID_AA64PFR1_EL1

   - Allow SVE to be disabled separately from SME on the kernel
     command-line

  Tracing:

   - Support for "direct calls" in ftrace, which enables BPF tracing for
     arm64

  Kdump:

   - Don't bother unmapping the crashkernel from the linear mapping,
     which then allows us to use huge (block) mappings and reduce TLB
     pressure when a crashkernel is loaded.

  Memory management:

   - Try again to remove data cache invalidation from the coherent DMA
     allocation path

   - Simplify the fixmap code by mapping at page granularity

   - Allow the kfence pool to be allocated early, preventing the rest of
     the linear mapping from being forced to page granularity

  Perf and PMU:

   - Move CPU PMU code out to drivers/perf/ where it can be reused by
     the 32-bit ARM architecture when running on ARMv8 CPUs

   - Fix race between CPU PMU probing and pKVM host de-privilege

   - Add support for Apple M2 CPU PMU

   - Adjust the generic PERF_COUNT_HW_BRANCH_INSTRUCTIONS event
     dynamically, depending on what the CPU actually supports

   - Minor fixes and cleanups to system PMU drivers

  Stack tracing:

   - Use the XPACLRI instruction to strip PAC from pointers, rather than
     rolling our own function in C

   - Remove redundant PAC removal for toolchains that handle this in
     their builtins

   - Make backtracing more resilient in the face of instrumentation

  Miscellaneous:

   - Fix single-step with KGDB

   - Remove harmless warning when 'nokaslr' is passed on the kernel
     command-line

   - Minor fixes and cleanups across the board"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (72 commits)
  KVM: arm64: Ensure CPU PMU probes before pKVM host de-privilege
  arm64: kexec: include reboot.h
  arm64: delete dead code in this_cpu_set_vectors()
  arm64/cpufeature: Use helper macro to specify ID register for capabilites
  drivers/perf: hisi: add NULL check for name
  drivers/perf: hisi: Remove redundant initialized of pmu->name
  arm64/cpufeature: Consistently use symbolic constants for min_field_value
  arm64/cpufeature: Pull out helper for CPUID register definitions
  arm64/sysreg: Convert HFGITR_EL2 to automatic generation
  ACPI: AGDI: Improve error reporting for problems during .remove()
  arm64: kernel: Fix kernel warning when nokaslr is passed to commandline
  perf/arm-cmn: Fix port detection for CMN-700
  arm64: kgdb: Set PSTATE.SS to 1 to re-enable single-step
  arm64: move PAC masks to <asm/pointer_auth.h>
  arm64: use XPACLRI to strip PAC
  arm64: avoid redundant PAC stripping in __builtin_return_address()
  arm64/sme: Fix some comments of ARM SME
  arm64/signal: Alloc tpidr2 sigframe after checking system_supports_tpidr2()
  arm64/signal: Use system_supports_tpidr2() to check TPIDR2
  arm64/idreg: Don't disable SME when disabling SVE
  ...

88 files changed, 1936 insertions, 1725 deletions

diff --git a/Documentation/devicetree/bindings/arm/pmu.yaml b/Documentation/devicetree/bindings/arm/pmu.yaml
index dbb6f3dc5ae5..e14358bf0b9c 100644
--- a/Documentation/devicetree/bindings/arm/pmu.yaml
+++ b/Documentation/devicetree/bindings/arm/pmu.yaml
@@ -20,6 +20,8 @@ properties:
     items:
       - enum:
           - apm,potenza-pmu
+          - apple,avalanche-pmu
+          - apple,blizzard-pmu
           - apple,firestorm-pmu
           - apple,icestorm-pmu
           - arm,armv8-pmuv3 # Only for s/w models
diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h
new file mode 100644
index 000000000000..78d3d4b82c6c
--- /dev/null
+++ b/arch/arm/include/asm/arm_pmuv3.h
@@ -0,0 +1,247 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __ASM_PMUV3_H
+#define __ASM_PMUV3_H
+
+#include <asm/cp15.h>
+#include <asm/cputype.h>
+
+#define PMCCNTR			__ACCESS_CP15_64(0, c9)
+
+#define PMCR			__ACCESS_CP15(c9,  0, c12, 0)
+#define PMCNTENSET		__ACCESS_CP15(c9,  0, c12, 1)
+#define PMCNTENCLR		__ACCESS_CP15(c9,  0, c12, 2)
+#define PMOVSR			__ACCESS_CP15(c9,  0, c12, 3)
+#define PMSELR			__ACCESS_CP15(c9,  0, c12, 5)
+#define PMCEID0			__ACCESS_CP15(c9,  0, c12, 6)
+#define PMCEID1			__ACCESS_CP15(c9,  0, c12, 7)
+#define PMXEVTYPER		__ACCESS_CP15(c9,  0, c13, 1)
+#define PMXEVCNTR		__ACCESS_CP15(c9,  0, c13, 2)
+#define PMUSERENR		__ACCESS_CP15(c9,  0, c14, 0)
+#define PMINTENSET		__ACCESS_CP15(c9,  0, c14, 1)
+#define PMINTENCLR		__ACCESS_CP15(c9,  0, c14, 2)
+#define PMMIR			__ACCESS_CP15(c9,  0, c14, 6)
+#define PMCCFILTR		__ACCESS_CP15(c14, 0, c15, 7)
+
+#define PMEVCNTR0		__ACCESS_CP15(c14, 0, c8, 0)
+#define PMEVCNTR1		__ACCESS_CP15(c14, 0, c8, 1)
+#define PMEVCNTR2		__ACCESS_CP15(c14, 0, c8, 2)
+#define PMEVCNTR3		__ACCESS_CP15(c14, 0, c8, 3)
+#define PMEVCNTR4		__ACCESS_CP15(c14, 0, c8, 4)
+#define PMEVCNTR5		__ACCESS_CP15(c14, 0, c8, 5)
+#define PMEVCNTR6		__ACCESS_CP15(c14, 0, c8, 6)
+#define PMEVCNTR7		__ACCESS_CP15(c14, 0, c8, 7)
+#define PMEVCNTR8		__ACCESS_CP15(c14, 0, c9, 0)
+#define PMEVCNTR9		__ACCESS_CP15(c14, 0, c9, 1)
+#define PMEVCNTR10		__ACCESS_CP15(c14, 0, c9, 2)
+#define PMEVCNTR11		__ACCESS_CP15(c14, 0, c9, 3)
+#define PMEVCNTR12		__ACCESS_CP15(c14, 0, c9, 4)
+#define PMEVCNTR13		__ACCESS_CP15(c14, 0, c9, 5)
+#define PMEVCNTR14		__ACCESS_CP15(c14, 0, c9, 6)
+#define PMEVCNTR15		__ACCESS_CP15(c14, 0, c9, 7)
+#define PMEVCNTR16		__ACCESS_CP15(c14, 0, c10, 0)
+#define PMEVCNTR17		__ACCESS_CP15(c14, 0, c10, 1)
+#define PMEVCNTR18		__ACCESS_CP15(c14, 0, c10, 2)
+#define PMEVCNTR19		__ACCESS_CP15(c14, 0, c10, 3)
+#define PMEVCNTR20		__ACCESS_CP15(c14, 0, c10, 4)
+#define PMEVCNTR21		__ACCESS_CP15(c14, 0, c10, 5)
+#define PMEVCNTR22		__ACCESS_CP15(c14, 0, c10, 6)
+#define PMEVCNTR23		__ACCESS_CP15(c14, 0, c10, 7)
+#define PMEVCNTR24		__ACCESS_CP15(c14, 0, c11, 0)
+#define PMEVCNTR25		__ACCESS_CP15(c14, 0, c11, 1)
+#define PMEVCNTR26		__ACCESS_CP15(c14, 0, c11, 2)
+#define PMEVCNTR27		__ACCESS_CP15(c14, 0, c11, 3)
+#define PMEVCNTR28		__ACCESS_CP15(c14, 0, c11, 4)
+#define PMEVCNTR29		__ACCESS_CP15(c14, 0, c11, 5)
+#define PMEVCNTR30		__ACCESS_CP15(c14, 0, c11, 6)
+
+#define PMEVTYPER0		__ACCESS_CP15(c14, 0, c12, 0)
+#define PMEVTYPER1		__ACCESS_CP15(c14, 0, c12, 1)
+#define PMEVTYPER2		__ACCESS_CP15(c14, 0, c12, 2)
+#define PMEVTYPER3		__ACCESS_CP15(c14, 0, c12, 3)
+#define PMEVTYPER4		__ACCESS_CP15(c14, 0, c12, 4)
+#define PMEVTYPER5		__ACCESS_CP15(c14, 0, c12, 5)
+#define PMEVTYPER6		__ACCESS_CP15(c14, 0, c12, 6)
+#define PMEVTYPER7		__ACCESS_CP15(c14, 0, c12, 7)
+#define PMEVTYPER8		__ACCESS_CP15(c14, 0, c13, 0)
+#define PMEVTYPER9		__ACCESS_CP15(c14, 0, c13, 1)
+#define PMEVTYPER10		__ACCESS_CP15(c14, 0, c13, 2)
+#define PMEVTYPER11		__ACCESS_CP15(c14, 0, c13, 3)
+#define PMEVTYPER12		__ACCESS_CP15(c14, 0, c13, 4)
+#define PMEVTYPER13		__ACCESS_CP15(c14, 0, c13, 5)
+#define PMEVTYPER14		__ACCESS_CP15(c14, 0, c13, 6)
+#define PMEVTYPER15		__ACCESS_CP15(c14, 0, c13, 7)
+#define PMEVTYPER16		__ACCESS_CP15(c14, 0, c14, 0)
+#define PMEVTYPER17		__ACCESS_CP15(c14, 0, c14, 1)
+#define PMEVTYPER18		__ACCESS_CP15(c14, 0, c14, 2)
+#define PMEVTYPER19		__ACCESS_CP15(c14, 0, c14, 3)
+#define PMEVTYPER20		__ACCESS_CP15(c14, 0, c14, 4)
+#define PMEVTYPER21		__ACCESS_CP15(c14, 0, c14, 5)
+#define PMEVTYPER22		__ACCESS_CP15(c14, 0, c14, 6)
+#define PMEVTYPER23		__ACCESS_CP15(c14, 0, c14, 7)
+#define PMEVTYPER24		__ACCESS_CP15(c14, 0, c15, 0)
+#define PMEVTYPER25		__ACCESS_CP15(c14, 0, c15, 1)
+#define PMEVTYPER26		__ACCESS_CP15(c14, 0, c15, 2)
+#define PMEVTYPER27		__ACCESS_CP15(c14, 0, c15, 3)
+#define PMEVTYPER28		__ACCESS_CP15(c14, 0, c15, 4)
+#define PMEVTYPER29		__ACCESS_CP15(c14, 0, c15, 5)
+#define PMEVTYPER30		__ACCESS_CP15(c14, 0, c15, 6)
+
+#define RETURN_READ_PMEVCNTRN(n) \
+	return read_sysreg(PMEVCNTR##n)
+static unsigned long read_pmevcntrn(int n)
+{
+	PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN);
+	return 0;
+}
+
+#define WRITE_PMEVCNTRN(n) \
+	write_sysreg(val, PMEVCNTR##n)
+static void write_pmevcntrn(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVCNTRN);
+}
+
+#define WRITE_PMEVTYPERN(n) \
+	write_sysreg(val, PMEVTYPER##n)
+static void write_pmevtypern(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
+}
+
+static inline unsigned long read_pmmir(void)
+{
+	return read_sysreg(PMMIR);
+}
+
+static inline u32 read_pmuver(void)
+{
+	/* PMUVers is not a signed field */
+	u32 dfr0 = read_cpuid_ext(CPUID_EXT_DFR0);
+
+	return (dfr0 >> 24) & 0xf;
+}
+
+static inline void write_pmcr(u32 val)
+{
+	write_sysreg(val, PMCR);
+}
+
+static inline u32 read_pmcr(void)
+{
+	return read_sysreg(PMCR);
+}
+
+static inline void write_pmselr(u32 val)
+{
+	write_sysreg(val, PMSELR);
+}
+
+static inline void write_pmccntr(u64 val)
+{
+	write_sysreg(val, PMCCNTR);
+}
+
+static inline u64 read_pmccntr(void)
+{
+	return read_sysreg(PMCCNTR);
+}
+
+static inline void write_pmxevcntr(u32 val)
+{
+	write_sysreg(val, PMXEVCNTR);
+}
+
+static inline u32 read_pmxevcntr(void)
+{
+	return read_sysreg(PMXEVCNTR);
+}
+
+static inline void write_pmxevtyper(u32 val)
+{
+	write_sysreg(val, PMXEVTYPER);
+}
+
+static inline void write_pmcntenset(u32 val)
+{
+	write_sysreg(val, PMCNTENSET);
+}
+
+static inline void write_pmcntenclr(u32 val)
+{
+	write_sysreg(val, PMCNTENCLR);
+}
+
+static inline void write_pmintenset(u32 val)
+{
+	write_sysreg(val, PMINTENSET);
+}
+
+static inline void write_pmintenclr(u32 val)
+{
+	write_sysreg(val, PMINTENCLR);
+}
+
+static inline void write_pmccfiltr(u32 val)
+{
+	write_sysreg(val, PMCCFILTR);
+}
+
+static inline void write_pmovsclr(u32 val)
+{
+	write_sysreg(val, PMOVSR);
+}
+
+static inline u32 read_pmovsclr(void)
+{
+	return read_sysreg(PMOVSR);
+}
+
+static inline void write_pmuserenr(u32 val)
+{
+	write_sysreg(val, PMUSERENR);
+}
+
+static inline u32 read_pmceid0(void)
+{
+	return read_sysreg(PMCEID0);
+}
+
+static inline u32 read_pmceid1(void)
+{
+	return read_sysreg(PMCEID1);
+}
+
+static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
+static inline void kvm_clr_pmu_events(u32 clr) {}
+static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
+{
+	return false;
+}
+
+/* PMU Version in DFR Register */
+#define ARMV8_PMU_DFR_VER_NI        0
+#define ARMV8_PMU_DFR_VER_V3P4      0x5
+#define ARMV8_PMU_DFR_VER_V3P5      0x6
+#define ARMV8_PMU_DFR_VER_IMP_DEF   0xF
+
+static inline bool pmuv3_implemented(int pmuver)
+{
+	return !(pmuver == ARMV8_PMU_DFR_VER_IMP_DEF ||
+		 pmuver == ARMV8_PMU_DFR_VER_NI);
+}
+
+static inline bool is_pmuv3p4(int pmuver)
+{
+	return pmuver >= ARMV8_PMU_DFR_VER_V3P4;
+}
+
+static inline bool is_pmuv3p5(int pmuver)
+{
+	return pmuver >= ARMV8_PMU_DFR_VER_V3P5;
+}
+
+#endif
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index c5bbae86f725..be183ed1232d 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -403,7 +403,7 @@ config CPU_V6K
 	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V6 if MMU
 
-# ARMv7
+# ARMv7 and ARMv8 architectures
 config CPU_V7
 	bool
 	select CPU_32v6K
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5b71e0bc2ffa..3f5bf55050e8 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -186,6 +186,10 @@ config ARM64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
+		if $(cc-option,-fpatchable-function-entry=2)
+	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS \
+		if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS
 	select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \
 		if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG && \
 		    !CC_OPTIMIZE_FOR_SIZE)
@@ -363,6 +367,20 @@ config ARCH_PROC_KCORE_TEXT
 config BROKEN_GAS_INST
 	def_bool !$(as-instr,1:\n.inst 0\n.rept . - 1b\n\nnop\n.endr\n)
 
+config BUILTIN_RETURN_ADDRESS_STRIPS_PAC
+	bool
+	# Clang's __builtin_return_adddress() strips the PAC since 12.0.0
+	# https://reviews.llvm.org/D75044
+	default y if CC_IS_CLANG && (CLANG_VERSION >= 120000)
+	# GCC's __builtin_return_address() strips the PAC since 11.1.0,
+	# and this was backported to 10.2.0, 9.4.0, 8.5.0, but not earlier
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94891
+	default y if CC_IS_GCC && (GCC_VERSION >= 110100)
+	default y if CC_IS_GCC && (GCC_VERSION >= 100200) && (GCC_VERSION < 110000)
+	default y if CC_IS_GCC && (GCC_VERSION >=  90400) && (GCC_VERSION < 100000)
+	default y if CC_IS_GCC && (GCC_VERSION >=  80500) && (GCC_VERSION <  90000)
+	default n
+
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN_GENERIC || KASAN_SW_TAGS
diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h
new file mode 100644
index 000000000000..d6b51deb7bf0
--- /dev/null
+++ b/