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
  ...

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

arch/arm/include/asm/arm_pmuv3.h

+/* 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

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

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

arch/arm64/include/asm/arm_pmuv3.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __ASM_PMUV3_H
+#define __ASM_PMUV3_H
+
+#include <linux/kvm_host.h>
+
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
+
+#define RETURN_READ_PMEVCNTRN(n) \
+	return read_sysreg(pmevcntr##n##_el0)
+static unsigned long read_pmevcntrn(int n)
+{
+	PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN);
+	return 0;
+}
+
+#define WRITE_PMEVCNTRN(n) \
+	write_sysreg(val, pmevcntr##n##_el0)
+static void write_pmevcntrn(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVCNTRN);
+}
+
+#define WRITE_PMEVTYPERN(n) \
+	write_sysreg(val, pmevtyper##n##_el0)
+static void write_pmevtypern(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
+}
+
+static inline unsigned long read_pmmir(void)
+{
+	return read_cpuid(PMMIR_EL1);
+}
+
+static inline u32 read_pmuver(void)
+{
+	u64 dfr0 = read_sysreg(id_aa64dfr0_el1);
+
+	return cpuid_feature_extract_unsigned_field(dfr0,
+			ID_AA64DFR0_EL1_PMUVer_SHIFT);
+}
+
+static inline void write_pmcr(u32 val)
+{
+	write_sysreg(val, pmcr_el0);
+}
+
+static inline u32 read_pmcr(void)
+{
+	return read_sysreg(pmcr_el0);
+}
+
+static inline void write_pmselr(u32 val)
+{
+	write_sysreg(val, pmselr_el0);
+}
+
+static inline void write_pmccntr(u64 val)
+{
+	write_sysreg(val, pmccntr_el0);
+}
+
+static inline u64 read_pmccntr(void)
+{
+	return read_sysreg(pmccntr_el0);
+}
+
+static inline void write_pmxevcntr(u32 val)
+{
+	write_sysreg(val, pmxevcntr_el0);
+}
+
+static inline u32 read_pmxevcntr(void)
+{
+	return read_sysreg(pmxevcntr_el0);
+}
+
+static inline void write_pmxevtyper(u32 val)
+{
+	write_sysreg(val, pmxevtyper_el0);
+}
+
+static inline void write_pmcntenset(u32 val)
+{
+	write_sysreg(val, pmcntenset_el0);
+}
+
+static inline void write_pmcntenclr(u32 val)
+{
+	write_sysreg(val, pmcntenclr_el0);
+}
+
+static inline void write_pmintenset(u32 val)
+{
+	write_sysreg(val, pmintenset_el1);
+}
+
+static inline void write_pmintenclr(u32 val)
+{
+	write_sysreg(val, pmintenclr_el1);
+}
+
+static inline void write_pmccfiltr(u32 val)
+{
+	write_sysreg(val, pmccfiltr_el0);
+}
+
+static inline void write_pmovsclr(u32 val)
+{
+	write_sysreg(val, pmovsclr_el0);
+}
+
+static inline u32 read_pmovsclr(void)
+{
+	return read_sysreg(pmovsclr_el0);
+}
+
+static inline void write_pmuserenr(u32 val)
+{
+	write_sysreg(val, pmuserenr_el0);
+}
+
+static inline u32 read_pmceid0(void)
+{
+	return read_sysreg(pmceid0_el0);
+}
+
+static inline u32 read_pmceid1(void)
+{
+	return read_sysreg(pmceid1_el0);
+}
+
+static inline bool pmuv3_implemented(int pmuver)
+{
+	return !(pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF ||
+		 pmuver == ID_AA64DFR0_EL1_PMUVer_NI);
+}
+
+static inline bool is_pmuv3p4(int pmuver)
+{
+	return pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P4;
+}
+
+static inline bool is_pmuv3p5(int pmuver)
+{
+	return pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P5;
+}
+
+#endif

arch/arm64/include/asm/atomic_lse.h

@@ -251,22 +251,15 @@ __lse__cmpxchg_case_##name##sz(volatile void *ptr,			\
 					      u##sz old,		\
 					      u##sz new)		\
 {									\
-	register unsigned long x0 asm ("x0") = (unsigned long)ptr;	\
-	register u##sz x1 asm ("x1") = old;				\
-	register u##sz x2 asm ("x2") = new;				\
-	unsigned long tmp;						\
-									\
 	asm volatile(							\
 	__LSE_PREAMBLE							\
-	"	mov	%" #w "[tmp], %" #w "[old]\n"			\
-	"	cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n"	\
-	"	mov	%" #w "[ret], %" #w "[tmp]"			\
-	: [ret] "+r" (x0), [v] "+Q" (*(u##sz *)ptr),			\
-	  [tmp] "=&r" (tmp)						\
-	: [old] "r" (x1), [new] "r" (x2)				\
+	"	cas" #mb #sfx "	%" #w "[old], %" #w "[new], %[v]\n"	\
+	: [v] "+Q" (*(u##sz *)ptr),					\
+	  [old] "+r" (old)						\
+	: [new] "rZ" (new)						\
 	: cl);								\
 									\
-	return x0;							\
+	return old;							\
 }
 
 __CMPXCHG_CASE(w, b,     ,  8,   )

arch/arm64/include/asm/barrier.h

@@ -131,25 +131,25 @@ do {									\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
 				: "=Q" (*__p)				\
-				: "r" (*(__u8 *)__u.__c)		\
+				: "rZ" (*(__u8 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
 				: "=Q" (*__p)				\
-				: "r" (*(__u16 *)__u.__c)		\
+				: "rZ" (*(__u16 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
 				: "=Q" (*__p)				\
-				: "r" (*(__u32 *)__u.__c)		\
+				: "rZ" (*(__u32 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 8:								\
-		asm volatile ("stlr %1, %0"				\
+		asm volatile ("stlr %x1, %0"				\
 				: "=Q" (*__p)				\
-				: "r" (*(__u64 *)__u.__c)		\
+				: "rZ" (*(__u64 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	}								\

arch/arm64/include/asm/compat.h

@@ -83,10 +83,6 @@ struct compat_statfs {
 	int		f_spare[4];
 };
 
-#define COMPAT_RLIM_INFINITY		0xffffffff
-
-#define COMPAT_OFF_T_MAX	0x7fffffff
-
 #define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
 #define COMPAT_MINSIGSTKSZ	2048
 

arch/arm64/include/asm/compiler.h

@@ -8,19 +8,33 @@
 #define ARM64_ASM_PREAMBLE
 #endif
 
-/*
- * The EL0/EL1 pointer bits used by a pointer authentication code.
- * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply.
- */
-#define ptrauth_user_pac_mask()		GENMASK_ULL(54, vabits_actual)
-#define ptrauth_kernel_pac_mask()	GENMASK_ULL(63, vabits_actual)
+#define xpaclri(ptr)							\
+({									\
+	register unsigned long __xpaclri_ptr asm("x30") = (ptr);	\
+									\
+	asm(								\
+	ARM64_ASM_PREAMBLE						\
+	"	hint	#7\n"						\
+	: "+r" (__xpaclri_ptr));					\
+									\
+	__xpaclri_ptr;							\
+})
 
-/* Valid for EL0 TTBR0 and EL1 TTBR1 instruction pointers */
-#define ptrauth_clear_pac(ptr)						\
-	((ptr & BIT_ULL(55)) ? (ptr | ptrauth_kernel_pac_mask()) :	\
-			       (ptr & ~ptrauth_user_pac_mask()))
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
+#define ptrauth_strip_kernel_insn_pac(ptr)	xpaclri(ptr)
+#else
+#define ptrauth_strip_kernel_insn_pac(ptr)	(ptr)
+#endif
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+#define ptrauth_strip_user_insn_pac(ptr)	xpaclri(ptr)
+#else
+#define ptrauth_strip_user_insn_pac(ptr)	(ptr)
+#endif
 
+#if !defined(CONFIG_BUILTIN_RETURN_ADDRESS_STRIPS_PAC)
 #define __builtin_return_address(val)					\
-	(void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val)))
+	(void *)(ptrauth_strip_kernel_insn_pac((unsigned long)__builtin_return_address(val)))
+#endif
 
 #endif /* __ASM_COMPILER_H */

arch/arm64/include/asm/debug-monitors.h

@@ -104,6 +104,7 @@ void user_regs_reset_single_step(struct user_pt_regs *regs,
 void kernel_enable_single_step(struct pt_regs *regs);
 void kernel_disable_single_step(void);
 int kernel_active_single_step(void);
+void kernel_rewind_single_step(struct pt_regs *regs);
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 int reinstall_suspended_bps(struct pt_regs *regs);

arch/arm64/include/asm/fixmap.h

@@ -17,6 +17,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
+#include <linux/math.h>
 #include <linux/sizes.h>
 #include <asm/boot.h>
 #include <asm/page.h>
@@ -36,17 +37,13 @@ enum fixed_addresses {
 	FIX_HOLE,
 
 	/*
-	 * Reserve a virtual window for the FDT that is 2 MB larger than the
-	 * maximum supported size, and put it at the top of the fixmap region.
-	 * The additional space ensures that any FDT that does not exceed
-	 * MAX_FDT_SIZE can be mapped regardless of whether it crosses any
-	 * 2 MB alignment boundaries.
-	 *
-	 * Keep this at the top so it remains 2 MB aligned.
+	 * Reserve a virtual window for the FDT that is a page bigger than the
+	 * maximum supported size. The additional space ensures that any FDT
+	 * that does not exceed MAX_FDT_SIZE can be mapped regardless of
+	 * whether it crosses any page boundary.
 	 */
-#define FIX_FDT_SIZE		(MAX_FDT_SIZE + SZ_2M)
 	FIX_FDT_END,
-	FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
+	FIX_FDT = FIX_FDT_END + DIV_ROUND_UP(MAX_FDT_SIZE, PAGE_SIZE) + 1,
 
 	FIX_EARLYCON_MEM_BASE,
 	FIX_TEXT_POKE0,
@@ -95,12 +92,15 @@ enum fixed_addresses {
 	__end_of_fixed_addresses
 };
 
-#define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_SIZE		(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_TOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_TOT_START	(FIXADDR_TOP - FIXADDR_TOT_SIZE)
 
 #define FIXMAP_PAGE_IO     __pgprot(PROT_DEVICE_nGnRE)
 
 void __init early_fixmap_init(void);
+void __init fixmap_copy(pgd_t *pgdir);
 
 #define __early_set_fixmap __set_fixmap
 

arch/arm64/include/asm/ftrace.h

@@ -70,10 +70,19 @@ struct ftrace_ops;
 
 #define arch_ftrace_get_regs(regs) NULL
 
+/*
+ * Note: sizeof(struct ftrace_regs) must be a multiple of 16 to ensure correct
+ * stack alignment
+ */
 struct ftrace_regs {
 	/* x0 - x8 */
 	unsigned long regs[9];
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	unsigned long direct_tramp;
+#else
 	unsigned long __unused;
+#endif
 
 	unsigned long fp;
 	unsigned long lr;
@@ -136,6 +145,19 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #define ftrace_graph_func ftrace_graph_func
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
+						 unsigned long addr)
+{
+	/*
+	 * The ftrace trampoline will return to this address instead of the
+	 * instrumented function.
+	 */
+	fregs->direct_tramp = addr;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+
 #endif
 
 #define ftrace_return_address(n) return_address(n)

arch/arm64/include/asm/kernel-pgtable.h

@@ -59,8 +59,11 @@
 #define EARLY_KASLR	(0)
 #endif
 
+#define SPAN_NR_ENTRIES(vstart, vend, shift) \
+	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1)
+
 #define EARLY_ENTRIES(vstart, vend, shift, add) \
-	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1 + add)
+	(SPAN_NR_ENTRIES(vstart, vend, shift) + (add))
 
 #define EARLY_PGDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT, add))
 

arch/arm64/include/asm/kexec.h

@@ -102,12 +102,6 @@ void cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
 
 int machine_kexec_post_load(struct kimage *image);
 #define machine_kexec_post_load machine_kexec_post_load
-
-void arch_kexec_protect_crashkres(void);
-#define arch_kexec_protect_crashkres arch_kexec_protect_crashkres
-
-void arch_kexec_unprotect_crashkres(void);
-#define arch_kexec_unprotect_crashkres arch_kexec_unprotect_crashkres
 #endif
 
 #define ARCH_HAS_KIMAGE_ARCH

arch/arm64/include/asm/kfence.h

@@ -19,4 +19,14 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 	return true;
 }
 
+#ifdef CONFIG_KFENCE
+extern bool kfence_early_init;
+static inline bool arm64_kfence_can_set_direct_map(void)
+{
+	return !kfence_early_init;
+}
+#else /* CONFIG_KFENCE */
+static inline bool arm64_kfence_can_set_direct_map(void) { return false; }
+#endif /* CONFIG_KFENCE */
+
 #endif /* __ASM_KFENCE_H */

arch/arm64/include/asm/memory.h

@@ -374,11 +374,6 @@ static inline void *phys_to_virt(phys_addr_t x)
 })
 
 void dump_mem_limit(void);
-
-static inline bool defer_reserve_crashkernel(void)
-{
-	return IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32);
-}
 #endif /* !ASSEMBLY */
 
 /*

arch/arm64/include/asm/mmu.h

@@ -65,6 +65,8 @@ extern void paging_init(void);
 extern void bootmem_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 extern void init_mem_pgprot(void);
+extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
+				   phys_addr_t size, pgprot_t prot);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
 			       pgprot_t prot, bool page_mappings_only);

arch/arm64/include/asm/pointer_auth.h

@@ -10,6 +10,13 @@
 #include <asm/memory.h>
 #include <asm/sysreg.h>
 
+/*
+ * The EL0/EL1 pointer bits used by a pointer authentication code.
+ * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply.
+ */
+#define ptrauth_user_pac_mask()		GENMASK_ULL(54, vabits_actual)
+#define ptrauth_kernel_pac_mask()	GENMASK_ULL(63, vabits_actual)
+
 #define PR_PAC_ENABLED_KEYS_MASK                                               \
 	(PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY)
 
@@ -97,11 +104,6 @@ extern int ptrauth_set_enabled_keys(struct task_struct *tsk, unsigned long keys,
 				    unsigned long enabled);
 extern int ptrauth_get_enabled_keys(struct task_struct *tsk);
 
-static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
-{
-	return ptrauth_clear_pac(ptr);
-}
-
 static __always_inline void ptrauth_enable(void)
 {
 	if (!system_supports_address_auth())
@@ -133,7 +135,6 @@ static __always_inline void ptrauth_enable(void)
 #define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
 #define ptrauth_set_enabled_keys(tsk, keys, enabled)	(-EINVAL)
 #define ptrauth_get_enabled_keys(tsk)	(-EINVAL)
-#define ptrauth_strip_insn_pac(lr)	(lr)
 #define ptrauth_suspend_exit()
 #define ptrauth_thread_init_user()
 #define ptrauth_thread_switch_user(tsk)

arch/arm64/include/asm/sysreg.h

@@ -419,9 +419,6 @@
 #define SYS_MDCR_EL2			sys_reg(3, 4, 1, 1, 1)
 #define SYS_CPTR_EL2			sys_reg(3, 4, 1, 1, 2)
 #define SYS_HSTR_EL2			sys_reg(3, 4, 1, 1, 3)
-#define SYS_HFGRTR_EL2			sys_reg(3, 4, 1, 1, 4)
-#define SYS_HFGWTR_EL2			sys_reg(3, 4, 1, 1, 5)
-#define SYS_HFGITR_EL2			sys_reg(3, 4, 1, 1, 6)
 #define SYS_HACR_EL2			sys_reg(3, 4, 1, 1, 7)
 
 #define SYS_TTBR0_EL2			sys_reg(3, 4, 2, 0, 0)
@@ -758,12 +755,6 @@
 #define ICH_VTR_TDS_SHIFT	19
 #define ICH_VTR_TDS_MASK	(1 << ICH_VTR_TDS_SHIFT)
 
-/* HFG[WR]TR_EL2 bit definitions */
-#define HFGxTR_EL2_nTPIDR2_EL0_SHIFT	55
-#define HFGxTR_EL2_nTPIDR2_EL0_MASK	BIT_MASK(HFGxTR_EL2_nTPIDR2_EL0_SHIFT)
-#define HFGxTR_EL2_nSMPRI_EL1_SHIFT	54
-#define HFGxTR_EL2_nSMPRI_EL1_MASK	BIT_MASK(HFGxTR_EL2_nSMPRI_EL1_SHIFT)
-
 #define ARM64_FEATURE_FIELD_BITS	4
 
 /* Defined for compatibility only, do not add new users. */

arch/arm64/include/asm/uaccess.h

@@ -237,7 +237,7 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
 	"1:	" load "	" reg "1, [%2]\n"			\
 	"2:\n"								\
 	_ASM_EXTABLE_##type##ACCESS_ERR_ZERO(1b, 2b, %w0, %w1)		\
-	: "+r" (err), "=&r" (x)						\
+	: "+r" (err), "=r" (x)						\
 	: "r" (addr))
 
 #define __raw_get_mem(ldr, x, ptr, err, type)					\
@@ -327,7 +327,7 @@ do {									\
 	"2:\n"								\
 	_ASM_EXTABLE_##type##ACCESS_ERR(1b, 2b, %w0)			\
 	: "+r" (err)							\
-	: "r" (x), "r" (addr))
+	: "rZ" (x), "r" (addr))
 
 #define __raw_put_mem(str, x, ptr, err, type)					\
 do {										\
@@ -449,8 +449,6 @@ extern long strncpy_from_user(char *dest, const char __user *src, long count);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
-struct page;
-void memcpy_page_flushcache(char *to, struct page *page, size_t offset, size_t len);
 extern unsigned long __must_check __copy_user_flushcache(void *to, const void __user *from, unsigned long n);
 
 static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)

arch/arm64/kernel/Makefile

@@ -45,7 +45,6 @@ obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
 obj-$(CONFIG_MODULES)			+= module.o
 obj-$(CONFIG_ARM64_MODULE_PLTS)		+= module-plts.o
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
-obj-$(CONFIG_HW_PERF_EVENTS)		+= perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_CPU_PM)			+= sleep.o suspend.o
 obj-$(CONFIG_CPU_IDLE)			+= cpuidle.o

arch/arm64/kernel/armv8_deprecated.c

@@ -420,14 +420,14 @@ static DEFINE_MUTEX(insn_emulation_mutex);
 
 static void enable_insn_hw_mode(void *data)
 {
-	struct insn_emulation *insn = (struct insn_emulation *)data;
+	struct insn_emulation *insn = data;
 	if (insn->set_hw_mode)
 		insn->set_hw_mode(true);
 }
 
 static void disable_insn_hw_mode(void *data)
 {
-	struct insn_emulation *insn = (struct insn_emulation *)data;
+	struct insn_emulation *insn = data;
 	if (insn->set_hw_mode)
 		insn->set_hw_mode(false);
 }

arch/arm64/kernel/asm-offsets.c

@@ -93,6 +93,9 @@ int main(void)
   DEFINE(FREGS_LR,		offsetof(struct ftrace_regs, lr));
   DEFINE(FREGS_SP,		offsetof(struct ftrace_regs, sp));
   DEFINE(FREGS_PC,		offsetof(struct ftrace_regs, pc));
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+  DEFINE(FREGS_DIRECT_TRAMP,	offsetof(struct ftrace_regs, direct_tramp));
+#endif
   DEFINE(FREGS_SIZE,		sizeof(struct ftrace_regs));
   BLANK();
 #endif
@@ -197,6 +200,9 @@ int main(void)
 #endif
 #ifdef CONFIG_FUNCTION_TRACER
   DEFINE(FTRACE_OPS_FUNC,		offsetof(struct ftrace_ops, func));
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+  DEFINE(FTRACE_OPS_DIRECT_CALL,	offsetof(struct ftrace_ops, direct_call));
+#endif
 #endif
   return 0;
 }

arch/arm64/kernel/crash_core.c

@@ -8,6 +8,7 @@
 #include <asm/cpufeature.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
+#include <asm/pointer_auth.h>
 
 static inline u64 get_tcr_el1_t1sz(void);
 

arch/arm64/kernel/debug-monitors.c

@@ -438,6 +438,11 @@ int kernel_active_single_step(void)
 }
 NOKPROBE_SYMBOL(kernel_active_single_step);
 
+void kernel_rewind_single_step(struct pt_regs *regs)
+{
+	set_regs_spsr_ss(regs);
+}
+
 /* ptrace API */
 void user_enable_single_step(struct task_struct *task)
 {

arch/arm64/kernel/entry-ftrace.S

@@ -36,6 +36,31 @@
 SYM_CODE_START(ftrace_caller)
 	bti	c
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	/*
+	 * The literal pointer to the ops is at an 8-byte aligned boundary
+	 * which is either 12 or 16 bytes before the BL instruction in the call
+	 * site. See ftrace_call_adjust() for details.
+	 *
+	 * Therefore here the LR points at `literal + 16` or `literal + 20`,
+	 * and we can find the address of the literal in either case by
+	 * aligning to an 8-byte boundary and subtracting 16. We do the
+	 * alignment first as this allows us to fold the subtraction into the
+	 * LDR.
+	 */
+	bic	x11, x30, 0x7
+	ldr	x11, [x11, #-(4 * AARCH64_INSN_SIZE)]		// op
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	/*
+	 * If the op has a direct call, handle it immediately without
+	 * saving/restoring registers.
+	 */
+	ldr	x17, [x11, #FTRACE_OPS_DIRECT_CALL]		// op->direct_call
+	cbnz	x17, ftrace_caller_direct
+#endif
+#endif
+
 	/* Save original SP */
 	mov	x10, sp
 
@@ -49,6 +74,10 @@ SYM_CODE_START(ftrace_caller)
 	stp	x6, x7, [sp, #FREGS_X6]
 	str	x8,     [sp, #FREGS_X8]
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	str	xzr, [sp, #FREGS_DIRECT_TRAMP]
+#endif
+
 	/* Save the callsite's FP, LR, SP */
 	str	x29, [sp, #FREGS_FP]
 	str	x9,  [sp, #FREGS_LR]
@@ -71,20 +100,7 @@ SYM_CODE_START(ftrace_caller)
 	mov	x3, sp					// regs
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
-	/*
-	 * The literal pointer to the ops is at an 8-byte aligned boundary
-	 * which is either 12 or 16 bytes before the BL instruction in the call
-	 * site. See ftrace_call_adjust() for details.
-	 *
-	 * Therefore here the LR points at `literal + 16` or `literal + 20`,
-	 * and we can find the address of the literal in either case by
-	 * aligning to an 8-byte boundary and subtracting 16. We do the
-	 * alignment first as this allows us to fold the subtraction into the
-	 * LDR.
-	 */
-	bic	x2, x30, 0x7
-	ldr	x2, [x2, #-16]				// op
-
+	mov	x2, x11					// op
 	ldr	x4, [x2, #FTRACE_OPS_FUNC]		// op->func
 	blr	x4					// op->func(ip, parent_ip, op, regs)
 
@@ -107,8 +123,15 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	ldp	x6, x7, [sp, #FREGS_X6]
 	ldr	x8,     [sp, #FREGS_X8]
 
-	/* Restore the callsite's FP, LR, PC */
+	/* Restore the callsite's FP */
 	ldr	x29, [sp, #FREGS_FP]
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	ldr	x17, [sp, #FREGS_DIRECT_TRAMP]
+	cbnz	x17, ftrace_caller_direct_late
+#endif
+
+	/* Restore the callsite's LR and PC */
 	ldr	x30, [sp, #FREGS_LR]
 	ldr	x9,  [sp, #FREGS_PC]
 
@@ -116,8 +139,45 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	add	sp, sp, #FREGS_SIZE + 32
 
 	ret	x9
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+SYM_INNER_LABEL(ftrace_caller_direct_late, SYM_L_LOCAL)
+	/*
+	 * Head to a direct trampoline in x17 after having run other tracers.
+	 * The ftrace_regs are live, and x0-x8 and FP have been restored. The
+	 * LR, PC, and SP have not been restored.
+	 */
+
+	/*
+	 * Restore the callsite's LR and PC matching the trampoline calling
+	 * convention.
+	 */
+	ldr	x9,  [sp, #FREGS_LR]
+	ldr	x30, [sp, #FREGS_PC]
+
+	/* Restore the callsite's SP */
+	add	sp, sp, #FREGS_SIZE + 32
+
+SYM_INNER_LABEL(ftrace_caller_direct, SYM_L_LOCAL)
+	/*
+	 * Head to a direct trampoline in x17.
+	 *
+	 * We use `BR X17` as this can safely land on a `BTI C` or `PACIASP` in
+	 * the trampoline, and will not unbalance any return stack.
+	 */
+	br	x17
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 SYM_CODE_END(ftrace_caller)
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+SYM_CODE_START(ftrace_stub_direct_tramp)
+	bti	c
+	mov	x10, x30
+	mov	x30, x9
+	ret	x10
+SYM_CODE_END(ftrace_stub_direct_tramp)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+
 #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
 /*

arch/arm64/kernel/fpsimd.c

@@ -299,7 +299,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
 /*
  * TIF_SME controls whether a task can use SME without trapping while
  * in userspace, when TIF_SME is set then we must have storage
- * alocated in sve_state and sme_state to store the contents of both ZA
+ * allocated in sve_state and sme_state to store the contents of both ZA
  * and the SVE registers for both streaming and non-streaming modes.
  *
  * If both SVCR.ZA and SVCR.SM are disabled then at any point we
@@ -1477,7 +1477,7 @@ void do_sve_acc(unsigned long esr, struct pt_regs *regs)
  *
  * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state()
  * would have disabled the SME access trap for userspace during
- * ret_to_user, making an SVE access trap impossible in that case.
+ * ret_to_user, making an SME access trap impossible in that case.
  */
 void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 {

arch/arm64/kernel/ftrace.c

@@ -195,15 +195,22 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(pc, 0, new, false);
 }
 
-static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
+static struct plt_entry *get_ftrace_plt(struct module *mod)
 {
 #ifdef CONFIG_ARM64_MODULE_PLTS
 	struct plt_entry *plt = mod->arch.ftrace_trampolines;
 
-	if (addr == FTRACE_ADDR)
-		return &plt[FTRACE_PLT_IDX];
-#endif
+	return &plt[FTRACE_PLT_IDX];
+#else
 	return NULL;
+#endif
+}
+
+static bool reachable_by_bl(unsigned long addr, unsigned long pc)
+{
+	long offset = (long)addr - (long)pc;
+
+	return offset >= -SZ_128M && offset < SZ_128M;
 }
 
 /*
@@ -220,14 +227,21 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 				      unsigned long *addr)
 {
 	unsigned long pc = rec->ip;
-	long offset = (long)*addr - (long)pc;
 	struct plt_entry *plt;
 
+	/*
+	 * If a custom trampoline is unreachable, rely on the ftrace_caller
+	 * trampoline which knows how to indirectly reach that trampoline
+	 * through ops->direct_call.
+	 */
+	if (*addr != FTRACE_ADDR && !reachable_by_bl(*addr, pc))
+		*addr = FTRACE_ADDR;
+
 	/*
 	 * When the target is within range of the 'BL' instruction, use 'addr'
 	 * as-is and branch to that directly.
 	 */
-	if (offset >= -SZ_128M && offset < SZ_128M)
+	if (reachable_by_bl(*addr, pc))
 		return true;
 
 	/*
@@ -256,7 +270,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 	if (WARN_ON(!mod))
 		return false;
 
-	plt = get_ftrace_plt(mod, *addr);
+	plt = get_ftrace_plt(mod);
 	if (!plt) {
 		pr_err("ftrace: no module PLT for %ps\n", (void *)*addr);
 		return false;
@@ -330,12 +344,24 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
-	if (WARN_ON_ONCE(old_addr != (unsigned long)ftrace_caller))
+	unsigned long pc = rec->ip;
+	u32 old, new;
+	int ret;
+
+	ret = ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec));
+	if (ret)
+		return ret;
+
+	if (!ftrace_find_callable_addr(rec, NULL, &old_addr))
 		return -EINVAL;
-	if (WARN_ON_ONCE(addr != (unsigned long)ftrace_caller))
+	if (!ftrace_find_callable_addr(rec, NULL, &addr))
 		return -EINVAL;
 
-	return ftrace_rec_update_ops(rec);
+	old = aarch64_insn_gen_branch_imm(pc, old_addr,
+					  AARCH64_INSN_BRANCH_LINK);
+	new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
+
+	return ftrace_modify_code(pc, old, new, true);
 }
 #endif
 

arch/arm64/kernel/idreg-override.c

@@ -167,7 +167,7 @@ static const struct {
 } aliases[] __initconst = {
 	{ "kvm-arm.mode=nvhe",		"id_aa64mmfr1.vh=0" },
 	{ "kvm-arm.mode=protected",	"id_aa64mmfr1.vh=0" },
-	{ "arm64.nosve",		"id_aa64pfr0.sve=0 id_aa64pfr1.sme=0" },
+	{ "arm64.nosve",		"id_aa64pfr0.sve=0" },
 	{ "arm64.nosme",		"id_aa64pfr1.sme=0" },
 	{ "arm64.nobti",		"id_aa64pfr1.bt=0" },
 	{ "arm64.nopauth",
@@ -178,6 +178,13 @@ static const struct {
 	{ "nokaslr",			"kaslr.disabled=1" },
 };
 
+static int __init parse_nokaslr(char *unused)
+{
+	/* nokaslr param handling is done by early cpufeature code */
+	return 0;
+}
+early_param("nokaslr", parse_nokaslr);
+
 static int __init find_field(const char *cmdline,
 			     const struct ftr_set_desc *reg, int f, u64 *v)
 {

arch/arm64/kernel/kgdb.c

@@ -224,6 +224,8 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
 		 */
 		if (!kernel_active_single_step())
 			kernel_enable_single_step(linux_regs);
+		else
+			kernel_rewind_single_step(linux_regs);
 		err = 0;
 		break;
 	default:

arch/arm64/kernel/machine_kexec.c

@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/kexec.h>
 #include <linux/page-flags.h>
+#include <linux/reboot.h>
 #include <linux/set_memory.h>
 #include <linux/smp.h>
 
@@ -102,7 +103,7 @@ static void kexec_segment_flush(const struct kimage *kimage)
 /* Allocates pages for kexec page table */
 static void *kexec_page_alloc(void *arg)
 {
-	struct kimage *kimage = (struct kimage *)arg;
+	struct kimage *kimage = arg;
 	struct page *page = kimage_alloc_control_pages(kimage, 0);
 	void *vaddr = NULL;
 
@@ -268,26 +269,6 @@ void machine_crash_shutdown(struct pt_regs *regs)
 	pr_info("Starting crashdump kernel...\n");
 }
 
-void arch_kexec_protect_crashkres(void)
-{
-	int i;
-
-	for (i = 0; i < kexec_crash_image->nr_segments; i++)
-		set_memory_valid(
-			__phys_to_virt(kexec_crash_image->segment[i].mem),
-			kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 0);
-}
-
-void arch_kexec_unprotect_crashkres(void)
-{
-	int i;
-
-	for (i = 0; i < kexec_crash_image->nr_segments; i++)
-		set_memory_valid(
-			__phys_to_virt(kexec_crash_image->segment[i].mem),
-			kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 1);
-}
-
 #ifdef CONFIG_HIBERNATION
 /*
  * To preserve the crash dump kernel image, the relevant memory segments

arch/arm64/kernel/perf_callchain.c

@@ -38,7 +38,7 @@ user_backtrace(struct frame_tail __user *tail,
 	if (err)
 		return NULL;
 
-	lr = ptrauth_strip_insn_pac(buftail.lr);
+	lr = ptrauth_strip_user_insn_pac(buftail.lr);
 
 	perf_callchain_store(entry, lr);
 

arch/arm64/kernel/process.c

@@ -217,7 +217,7 @@ void __show_regs(struct pt_regs *regs)
 
 	if (!user_mode(regs)) {
 		printk("pc : %pS\n", (void *)regs->pc);
-		printk("lr : %pS\n", (void *)ptrauth_strip_insn_pac(lr));
+		printk("lr : %pS\n", (void *)ptrauth_strip_kernel_insn_pac(lr));
 	} else {
 		printk("pc : %016llx\n", regs->pc);
 		printk("lr : %016llx\n", lr);

arch/arm64/kernel/proton-pack.c

@@ -966,9 +966,6 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
 {
 	const char *v = arm64_get_bp_hardening_vector(slot);
 
-	if (slot < 0)
-		return;
-
 	__this_cpu_write(this_cpu_vector, v);
 
 	/*

arch/arm64/kernel/signal.c

@@ -651,7 +651,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			break;
 
 		case TPIDR2_MAGIC:
-			if (!system_supports_sme())
+			if (!system_supports_tpidr2())
 				goto invalid;
 
 			if (user->tpidr2)
@@ -802,7 +802,7 @@ static int restore_sigframe(struct pt_regs *regs,
 			err = restore_fpsimd_context(&user);
 	}
 
-	if (err == 0 && system_supports_sme() && user.tpidr2)
+	if (err == 0 && system_supports_tpidr2() && user.tpidr2)
 		err = restore_tpidr2_context(&user);
 
 	if (err == 0 && system_supports_sme() && user.za)
@@ -893,6 +893,13 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 			return err;
 	}
 
+	if (system_supports_tpidr2()) {
+		err = sigframe_alloc(user, &user->tpidr2_offset,
+				     sizeof(struct tpidr2_context));
+		if (err)
+			return err;
+	}
+
 	if (system_supports_sme()) {
 		unsigned int vl;
 		unsigned int vq = 0;
@@ -902,11 +909,6 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 		else
 			vl = task_get_sme_vl(current);
 
-		err = sigframe_alloc(user, &user->tpidr2_offset,
-				     sizeof(struct tpidr2_context));
-		if (err)
-			return err;
-
 		if (thread_za_enabled(&current->thread))
 			vq = sve_vq_from_vl(vl);
 
@@ -974,7 +976,7 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 	}
 
 	/* TPIDR2 if supported */
-	if (system_supports_sme() && err == 0) {
+	if (system_supports_tpidr2() && err == 0) {
 		struct tpidr2_context __user *tpidr2_ctx =
 			apply_user_offset(user, user->tpidr2_offset);
 		err |= preserve_tpidr2_context(tpidr2_ctx);

arch/arm64/kernel/stacktrace.c

@@ -25,8 +25,9 @@
  *
  * The regs must be on a stack currently owned by the calling task.
  */
-static __always_inline void unwind_init_from_regs(struct unwind_state *state,
-						  struct pt_regs *regs)
+static __always_inline void
+unwind_init_from_regs(struct unwind_state *state,
+		      struct pt_regs *regs)
 {
 	unwind_init_common(state, current);
 
@@ -42,7 +43,8 @@ static __always_inline void unwind_init_from_regs(struct unwind_state *state,
  *
  * The function which invokes this must be noinline.
  */
-static __always_inline void unwind_init_from_caller(struct unwind_state *state)
+static __always_inline void
+unwind_init_from_caller(struct unwind_state *state)
 {
 	unwind_init_common(state, current);
 
@@ -60,8 +62,9 @@ static __always_inline void unwind_init_from_caller(struct unwind_state *state)
  * duration of the unwind, or the unwind will be bogus. It is never valid to
  * call this for the current task.
  */
-static __always_inline void unwind_init_from_task(struct unwind_state *state,
-						  struct task_struct *task)
+static __always_inline void
+unwind_init_from_task(struct unwind_state *state,
+		      struct task_struct *task)
 {
 	unwind_init_common(state, task);
 
@@ -69,6 +72,32 @@ static __always_inline void unwind_init_from_task(struct unwind_state *state,
 	state->pc = thread_saved_pc(task);
 }
 
+static __always_inline int
+unwind_recover_return_address(struct unwind_state *state)
+{
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (state->task->ret_stack &&
+	    (state->pc == (unsigned long)return_to_handler)) {
+		unsigned long orig_pc;
+		orig_pc = ftrace_graph_ret_addr(state->task, NULL, state->pc,
+						(void *)state->fp);
+		if (WARN_ON_ONCE(state->pc == orig_pc))
+			return -EINVAL;
+		state->pc = orig_pc;
+	}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_KRETPROBES
+	if (is_kretprobe_trampoline(state->pc)) {
+		state->pc = kretprobe_find_ret_addr(state->task,
+						    (void *)state->fp,
+						    &state->kr_cur);
+	}
+#endif /* CONFIG_KRETPROBES */
+
+	return 0;
+}
+
 /*
  * Unwind from one frame record (A) to the next frame record (B).
  *
@@ -76,7 +105,8 @@ static __always_inline void unwind_init_from_task(struct unwind_state *state,
  * records (e.g. a cycle), determined based on the location and fp value of A
  * and the location (but not the fp value) of B.
  */
-static int notrace unwind_next(struct unwind_state *state)
+static __always_inline int
+unwind_next(struct unwind_state *state)
 {
 	struct task_struct *tsk = state->task;
 	unsigned long fp = state->fp;
@@ -90,37 +120,18 @@ static int notrace unwind_next(struct unwind_state *state)
 	if (err)
 		return err;
 
-	state->pc = ptrauth_strip_insn_pac(state->pc);
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	if (tsk->ret_stack &&
-		(state->pc == (unsigned long)return_to_handler)) {
-		unsigned long orig_pc;
-		/*
-		 * This is a case where function graph tracer has
-		 * modified a return address (LR) in a stack frame
-		 * to hook a function return.
-		 * So replace it to an original value.
-		 */
-		orig_pc = ftrace_graph_ret_addr(tsk, NULL, state->pc,
-						(void *)state->fp);
-		if (WARN_ON_ONCE(state->pc == orig_pc))
-			return -EINVAL;
-		state->pc = orig_pc;
-	}
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-#ifdef CONFIG_KRETPROBES
-	if (is_kretprobe_trampoline(state->pc))
-		state->pc = kretprobe_find_ret_addr(tsk, (void *)state->fp, &state->kr_cur);
-#endif
+	state->pc = ptrauth_strip_kernel_insn_pac(state->pc);
 
-	return 0;
+	return unwind_recover_return_address(state);
 }
-NOKPROBE_SYMBOL(unwind_next);
 
-static void notrace unwind(struct unwind_state *state,
-			   stack_trace_consume_fn consume_entry, void *cookie)
+static __always_inline void
+unwind(struct unwind_state *state, stack_trace_consume_fn consume_entry,
+       void *cookie)
 {
+	if (unwind_recover_return_address(state))
+		return;
+
 	while (1) {
 		int ret;
 
@@ -131,40 +142,6 @@ static void notrace unwind(struct unwind_state *state,
 			break;
 	}
 }
-NOKPROBE_SYMBOL(unwind);
-
-static bool dump_backtrace_entry(void *arg, unsigned long where)
-{
-	char *loglvl = arg;
-	printk("%s %pSb\n", loglvl, (void *)where);
-	return true;
-}
-
-void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
-		    const char *loglvl)
-{
-	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
-
-	if (regs && user_mode(regs))
-		return;
-
-	if (!tsk)
-		tsk = current;
-
-	if (!try_get_task_stack(tsk))
-		return;
-
-	printk("%sCall trace:\n", loglvl);
-	arch_stack_walk(dump_backtrace_entry, (void *)loglvl, tsk, regs);
-
-	put_task_stack(tsk);
-}
-
-void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
-{
-	dump_backtrace(NULL, tsk, loglvl);
-	barrier();
-}
 
 /*
  * Per-cpu stacks are only accessible when unwinding the current task in a
@@ -230,3 +207,36 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
 
 	unwind(&state, consume_entry, cookie);
 }
+
+static bool dump_backtrace_entry(void *arg, unsigned long where)
+{
+	char *loglvl = arg;
+	printk("%s %pSb\n", loglvl, (void *)where);
+	return true;
+}
+
+void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+		    const char *loglvl)
+{
+	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
+
+	if (regs && user_mode(regs))
+		return;
+
+	if (!tsk)
+		tsk = current;
+
+	if (!try_get_task_stack(tsk))
+		return;
+
+	printk("%sCall trace:\n", loglvl);
+	arch_stack_walk(dump_backtrace_entry, (void *)loglvl, tsk, regs);
+
+	put_task_stack(tsk);
+}
+
+void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
+{
+	dump_backtrace(NULL, tsk, loglvl);
+	barrier();
+}

arch/arm64/kvm/arm.c

@@ -16,7 +16,6 @@
 #include <linux/fs.h>
 #include <linux/mman.h>
 #include <linux/sched.h>
-#include <linux/kmemleak.h>
 #include <linux/kvm.h>
 #include <linux/kvm_irqfd.h>
 #include <linux/irqbypass.h>
@@ -46,7 +45,6 @@
 #include <kvm/arm_psci.h>
 
 static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT;
-DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
 
 DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector);
 
@@ -2130,41 +2128,6 @@ static int __init init_hyp_mode(void)
 	return err;
 }
 
-static void __init _kvm_host_prot_finalize(void *arg)
-{
-	int *err = arg;
-
-	if (WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize)))
-		WRITE_ONCE(*err, -EINVAL);
-}
-
-static int __init pkvm_drop_host_privileges(void)
-{
-	int ret = 0;
-
-	/*
-	 * Flip the static key upfront as that may no longer be possible
-	 * once the host stage 2 is installed.
-	 */
-	static_branch_enable(&kvm_protected_mode_initialized);
-	on_each_cpu(_kvm_host_prot_finalize, &ret, 1);
-	return ret;
-}
-
-static int __init finalize_hyp_mode(void)
-{
-	if (!is_protected_kvm_enabled())
-		return 0;
-
-	/*
-	 * Exclude HYP sections from kmemleak so that they don't get peeked
-	 * at, which would end badly once inaccessible.
-	 */
-	kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start);
-	kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size);
-	return pkvm_drop_host_privileges();
-}
-
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
 {
 	struct kvm_vcpu *vcpu;
@@ -2282,14 +2245,6 @@ static __init int kvm_arm_init(void)
 	if (err)
 		goto out_hyp;
 
-	if (!in_hyp_mode) {
-		err = finalize_hyp_mode();
-		if (err) {
-			kvm_err("Failed to finalize Hyp protection\n");
-			goto out_subs;
-		}
-	}
-
 	if (is_protected_kvm_enabled()) {
 		kvm_info("Protected nVHE mode initialized successfully\n");
 	} else if (in_hyp_mode) {

arch/arm64/kvm/pkvm.c

@@ -4,6 +4,8 @@
  * Author: Quentin Perret <qperret@google.com>
  */
 
+#include <linux/init.h>
+#include <linux/kmemleak.h>
 #include <linux/kvm_host.h>
 #include <linux/memblock.h>
 #include <linux/mutex.h>
@@ -13,6 +15,8 @@
 
 #include "hyp_constants.h"
 
+DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
+
 static struct memblock_region *hyp_memory = kvm_nvhe_sym(hyp_memory);
 static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr);
 
@@ -213,3 +217,46 @@ int pkvm_init_host_vm(struct kvm *host_kvm)
 	mutex_init(&host_kvm->lock);
 	return 0;
 }
+
+static void __init _kvm_host_prot_finalize(void *arg)
+{
+	int *err = arg;
+
+	if (WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize)))
+		WRITE_ONCE(*err, -EINVAL);
+}
+
+static int __init pkvm_drop_host_privileges(void)
+{
+	int ret = 0;
+
+	/*
+	 * Flip the static key upfront as that may no longer be possible
+	 * once the host stage 2 is installed.
+	 */
+	static_branch_enable(&kvm_protected_mode_initialized);
+	on_each_cpu(_kvm_host_prot_finalize, &ret, 1);
+	return ret;
+}
+
+static int __init finalize_pkvm(void)
+{
+	int ret;
+
+	if (!is_protected_kvm_enabled())
+		return 0;
+
+	/*
+	 * Exclude HYP sections from kmemleak so that they don't get peeked
+	 * at, which would end badly once inaccessible.
+	 */
+	kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start);
+	kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size);
+
+	ret = pkvm_drop_host_privileges();
+	if (ret)
+		pr_err("Failed to finalize Hyp protection: %d\n", ret);
+
+	return ret;
+}
+device_initcall_sync(finalize_pkvm);

arch/arm64/lib/uaccess_flushcache.c

@@ -19,12 +19,6 @@ void memcpy_flushcache(void *dst, const void *src, size_t cnt)
 }
 EXPORT_SYMBOL_GPL(memcpy_flushcache);
 
-void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
-			    size_t len)
-{
-	memcpy_flushcache(to, page_address(page) + offset, len);
-}
-
 unsigned long __copy_user_flushcache(void *to, const void __user *from,
 				     unsigned long n)
 {

arch/arm64/mm/Makefile

@@ -2,7 +2,7 @@
 obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   cache.o copypage.o flush.o \
 				   ioremap.o mmap.o pgd.o mmu.o \
-				   context.o proc.o pageattr.o
+				   context.o proc.o pageattr.o fixmap.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_PTDUMP_CORE)	+= ptdump.o
 obj-$(CONFIG_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o

arch/arm64/mm/dma-mapping.c

@@ -36,22 +36,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 {
 	unsigned long start = (unsigned long)page_address(page);
 
-	/*
-	 * The architecture only requires a clean to the PoC here in order to
-	 * meet the requirements of the DMA API. However, some vendors (i.e.
-	 * Qualcomm) abuse the DMA API for transferring buffers from the
-	 * non-secure to the secure world, resetting the system if a non-secure
-	 * access shows up after the buffer has been transferred:
-	 *
-	 * https://lore.kernel.org/r/20221114110329.68413-1-manivannan.sadhasivam@linaro.org
-	 *
-	 * Using clean+invalidate appears to make this issue less likely, but
-	 * the drivers themselves still need fixing as the CPU could issue a
-	 * speculative read from the buffer via the linear mapping irrespective
-	 * of the cache maintenance we use. Once the drivers are fixed, we can
-	 * relax this to a clean operation.
-	 */
-	dcache_clean_inval_poc(start, start + size);
+	dcache_clean_poc(start, start + size);
 }
 
 #ifdef CONFIG_IOMMU_DMA

arch/arm64/mm/fixmap.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Fixmap manipulation code
+ */
+
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/libfdt.h>
+#include <linux/memory.h>
+#include <linux/mm.h>
+#include <linux/sizes.h>
+
+#include <asm/fixmap.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+#define NR_BM_PTE_TABLES \
+	SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT)
+#define NR_BM_PMD_TABLES \
+	SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PUD_SHIFT)
+
+static_assert(NR_BM_PMD_TABLES == 1);
+
+#define __BM_TABLE_IDX(addr, shift) \
+	(((addr) >> (shift)) - (FIXADDR_TOT_START >> (shift)))
+
+#define BM_PTE_TABLE_IDX(addr)	__BM_TABLE_IDX(addr, PMD_SHIFT)
+
+static pte_t bm_pte[NR_BM_PTE_TABLES][PTRS_PER_PTE] __page_aligned_bss;
+static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
+static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
+
+static inline pte_t *fixmap_pte(unsigned long addr)
+{
+	return &bm_pte[BM_PTE_TABLE_IDX(addr)][pte_index(addr)];
+}
+
+static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr)
+{
+	pmd_t pmd = READ_ONCE(*pmdp);
+	pte_t *ptep;
+
+	if (pmd_none(pmd)) {
+		ptep = bm_pte[BM_PTE_TABLE_IDX(addr)];
+		__pmd_populate(pmdp, __pa_symbol(ptep), PMD_TYPE_TABLE);
+	}
+}
+
+static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr,
+					 unsigned long end)
+{
+	unsigned long next;
+	pud_t pud = READ_ONCE(*pudp);
+	pmd_t *pmdp;
+
+	if (pud_none(pud))
+		__pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE);
+
+	pmdp = pmd_offset_kimg(pudp, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		early_fixmap_init_pte(pmdp, addr);
+	} while (pmdp++, addr = next, addr != end);
+}
+
+
+static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr,
+					 unsigned long end)
+{
+	p4d_t p4d = READ_ONCE(*p4dp);
+	pud_t *pudp;
+
+	if (CONFIG_PGTABLE_LEVELS > 3 && !p4d_none(p4d) &&
+	    p4d_page_paddr(p4d) != __pa_symbol(bm_pud)) {
+		/*
+		 * We only end up here if the kernel mapping and the fixmap
+		 * share the top level pgd entry, which should only happen on
+		 * 16k/4 levels configurations.
+		 */
+		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
+	}
+
+	if (p4d_none(p4d))
+		__p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE);
+
+	pudp = pud_offset_kimg(p4dp, addr);
+	early_fixmap_init_pmd(pudp, addr, end);
+}
+
+/*
+ * The p*d_populate functions call virt_to_phys implicitly so they can't be used
+ * directly on kernel symbols (bm_p*d). This function is called too early to use
+ * lm_alias so __p*d_populate functions must be used to populate with the
+ * physical address from __pa_symbol.
+ */
+void __init early_fixmap_init(void)
+{
+	unsigned long addr = FIXADDR_TOT_START;
+	unsigned long end = FIXADDR_TOP;
+
+	pgd_t *pgdp = pgd_offset_k(addr);
+	p4d_t *p4dp = p4d_offset(pgdp, addr);
+
+	early_fixmap_init_pud(p4dp, addr, end);
+}
+
+/*
+ * Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we
+ * ever need to use IPIs for TLB broadcasting, then we're in trouble here.
+ */
+void __set_fixmap(enum fixed_addresses idx,
+			       phys_addr_t phys, pgprot_t flags)
+{
+	unsigned long addr = __fix_to_virt(idx);
+	pte_t *ptep;
+
+	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
+
+	ptep = fixmap_pte(addr);
+
+	if (pgprot_val(flags)) {
+		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
+	} else {
+		pte_clear(&init_mm, addr, ptep);
+		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
+	}
+}
+
+void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
+{
+	const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
+	phys_addr_t dt_phys_base;
+	int offset;
+	void *dt_virt;
+
+	/*
+	 * Check whether the physical FDT address is set and meets the minimum
+	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
+	 * at least 8 bytes so that we can always access the magic and size
+	 * fields of the FDT header after mapping the first chunk, double check
+	 * here if that is indeed the case.
+	 */
+	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
+	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
+		return NULL;
+
+	dt_phys_base = round_down(dt_phys, PAGE_SIZE);
+	offset = dt_phys % PAGE_SIZE;
+	dt_virt = (void *)dt_virt_base + offset;
+
+	/* map the first chunk so we can read the size from the header */
+	create_mapping_noalloc(dt_phys_base, dt_virt_base, PAGE_SIZE, prot);
+
+	if (fdt_magic(dt_virt) != FDT_MAGIC)
+		return NULL;
+
+	*size = fdt_totalsize(dt_virt);
+	if (*size > MAX_FDT_SIZE)
+		return NULL;
+
+	if (offset + *size > PAGE_SIZE) {
+		create_mapping_noalloc(dt_phys_base, dt_virt_base,
+				       offset + *size, prot);
+	}
+
+	return dt_virt;
+}
+
+/*
+ * Copy the fixmap region into a new pgdir.
+ */
+void __init fixmap_copy(pgd_t *pgdir)
+{
+	if (!READ_ONCE(pgd_val(*pgd_offset_pgd(pgdir, FIXADDR_TOT_START)))) {
+		/*
+		 * The fixmap falls in a separate pgd to the kernel, and doesn't
+		 * live in the carveout for the swapper_pg_dir. We can simply
+		 * re-use the existing dir for the fixmap.
+		 */
+		set_pgd(pgd_offset_pgd(pgdir, FIXADDR_TOT_START),
+			READ_ONCE(*pgd_offset_k(FIXADDR_TOT_START)));
+	} else if (CONFIG_PGTABLE_LEVELS > 3) {
+		pgd_t *bm_pgdp;
+		p4d_t *bm_p4dp;
+		pud_t *bm_pudp;
+		/*
+		 * The fixmap shares its top level pgd entry with the kernel
+		 * mapping. This can really only occur when we are running
+		 * with 16k/4 levels, so we can simply reuse the pud level
+		 * entry instead.
+		 */
+		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
+		bm_pgdp = pgd_offset_pgd(pgdir, FIXADDR_TOT_START);
+		bm_p4dp = p4d_offset(bm_pgdp, FIXADDR_TOT_START);
+		bm_pudp = pud_set_fixmap_offset(bm_p4dp, FIXADDR_TOT_START);
+		pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd));
+		pud_clear_fixmap();
+	} else {
+		BUG();
+	}
+}

arch/arm64/mm/init.c

@@ -61,34 +61,8 @@ EXPORT_SYMBOL(memstart_addr);
  * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
  * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
  * otherwise it is empty.
- *
- * Memory reservation for crash kernel either done early or deferred
- * depending on DMA memory zones configs (ZONE_DMA) --
- *
- * In absence of ZONE_DMA configs arm64_dma_phys_limit initialized
- * here instead of max_zone_phys().  This lets early reservation of
- * crash kernel memory which has a dependency on arm64_dma_phys_limit.
- * Reserving memory early for crash kernel allows linear creation of block
- * mappings (greater than page-granularity) for all the memory bank rangs.
- * In this scheme a comparatively quicker boot is observed.
- *
- * If ZONE_DMA configs are defined, crash kernel memory reservation
- * is delayed until DMA zone memory range size initialization performed in
- * zone_sizes_init().  The defer is necessary to steer clear of DMA zone
- * memory range to avoid overlap allocation.  So crash kernel memory boundaries
- * are not known when mapping all bank memory ranges, which otherwise means
- * not possible to exclude crash kernel range from creating block mappings
- * so page-granularity mappings are created for the entire memory range.
- * Hence a slightly slower boot is observed.
- *
- * Note: Page-granularity mappings are necessary for crash kernel memory
- * range for shrinking its size via /sys/kernel/kexec_crash_size interface.
  */
-#if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32)
 phys_addr_t __ro_after_init arm64_dma_phys_limit;
-#else
-phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
-#endif
 
 /* Current arm64 boot protocol requires 2MB alignment */
 #define CRASH_ALIGN			SZ_2M
@@ -248,6 +222,8 @@ static void __init zone_sizes_init(void)
 	if (!arm64_dma_phys_limit)
 		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max_pfn;
 
 	free_area_init(max_zone_pfns);
@@ -408,9 +384,6 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	if (!defer_reserve_crashkernel())
-		reserve_crashkernel();
-
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 }
 
@@ -457,8 +430,7 @@ void __init bootmem_init(void)
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
-	if (defer_reserve_crashkernel())
-		reserve_crashkernel();
+	reserve_crashkernel();
 
 	memblock_dump_all();
 }

arch/arm64/mm/pageattr.c

@@ -11,6 +11,7 @@
 #include <asm/cacheflush.h>
 #include <asm/set_memory.h>
 #include <asm/tlbflush.h>
+#include <asm/kfence.h>
 
 struct page_change_data {
 	pgprot_t set_mask;
@@ -22,12 +23,14 @@ bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED
 bool can_set_direct_map(void)
 {
 	/*
-	 * rodata_full, DEBUG_PAGEALLOC and KFENCE require linear map to be
+	 * rodata_full and DEBUG_PAGEALLOC require linear map to be
 	 * mapped at page granularity, so that it is possible to
 	 * protect/unprotect single pages.
+	 *
+	 * KFENCE pool requires page-granular mapping if initialized late.
 	 */
 	return (rodata_enabled && rodata_full) || debug_pagealloc_enabled() ||
-		IS_ENABLED(CONFIG_KFENCE);
+		arm64_kfence_can_set_direct_map();
 }
 
 static int change_page_range(pte_t *ptep, unsigned long addr, void *data)

arch/arm64/mm/ptdump.c

@@ -45,7 +45,7 @@ static struct addr_marker address_markers[] = {
 	{ MODULES_END,			"Modules end" },
 	{ VMALLOC_START,		"vmalloc() area" },
 	{ VMALLOC_END,			"vmalloc() end" },
-	{ FIXADDR_START,		"Fixmap start" },
+	{ FIXADDR_TOT_START,		"Fixmap start" },
 	{ FIXADDR_TOP,			"Fixmap end" },
 	{ PCI_IO_START,			"PCI I/O start" },
 	{ PCI_IO_END,			"PCI I/O end" },

arch/arm64/tools/gen-sysreg.awk

@@ -4,23 +4,35 @@
 #
 # Usage: awk -f gen-sysreg.awk sysregs.txt
 
+function block_current() {
+	return __current_block[__current_block_depth];
+}
+
 # Log an error and terminate
 function fatal(msg) {
 	print "Error at " NR ": " msg > "/dev/stderr"
+
+	printf "Current block nesting:"
+
+	for (i = 0; i <= __current_block_depth; i++) {
+		printf " " __current_block[i]
+	}
+	printf "\n"
+
 	exit 1
 }
 
-# Sanity check that the start or end of a block makes sense at this point in
-# the file. If not, produce an error and terminate.
-#
-# @this - the $Block or $EndBlock
-# @prev - the only valid block to already be in (value of @block)
-# @new - the new value of @block
-function change_block(this, prev, new) {
-	if (block != prev)
-		fatal("unexpected " this " (inside " block ")")
-
-	block = new
+# Enter a new block, setting the active block to @block
+function block_push(block) {
+	__current_block[++__current_block_depth] = block
+}
+
+# Exit a block, setting the active block to the parent block
+function block_pop() {
+	if (__current_block_depth == 0)
+		fatal("error: block_pop() in root block")
+
+	__current_block_depth--;
 }
 
 # Sanity check the number of records for a field makes sense. If not, produce
@@ -84,10 +96,14 @@ BEGIN {
 	print "/* Generated file - do not edit */"
 	print ""
 
-	block = "None"
+	__current_block_depth = 0
+	__current_block[__current_block_depth] = "Root"
 }
 
 END {
+	if (__current_block_depth != 0)
+		fatal("Missing terminator for " block_current() " block")
+
 	print "#endif /* __ASM_SYSREG_DEFS_H */"
 }
 
@@ -95,8 +111,9 @@ END {
 /^$/ { next }
 /^[\t ]*#/ { next }
 
-/^SysregFields/ {
-	change_block("SysregFields", "None", "SysregFields")
+/^SysregFields/ && block_current() == "Root" {
+	block_push("SysregFields")
+
 	expect_fields(2)
 
 	reg = $2
@@ -110,12 +127,10 @@ END {
 	next
 }
 
-/^EndSysregFields/ {
+/^EndSysregFields/ && block_current() == "SysregFields" {
 	if (next_bit > 0)
 		fatal("Unspecified bits in " reg)
 
-	change_block("EndSysregFields", "SysregFields", "None")
-
 	define(reg "_RES0", "(" res0 ")")
 	define(reg "_RES1", "(" res1 ")")
 	define(reg "_UNKN", "(" unkn ")")
@@ -126,11 +141,13 @@ END {
 	res1 = null
 	unkn = null
 
+	block_pop()
 	next
 }
 
-/^Sysreg/ {
-	change_block("Sysreg", "None", "Sysreg")
+/^Sysreg/ && block_current() == "Root" {
+	block_push("Sysreg")
+
 	expect_fields(7)
 
 	reg = $2
@@ -160,12 +177,10 @@ END {
 	next
 }
 
-/^EndSysreg/ {
+/^EndSysreg/ && block_current() == "Sysreg" {
 	if (next_bit > 0)
 		fatal("Unspecified bits in " reg)
 
-	change_block("EndSysreg", "Sysreg", "None")
-
 	if (res0 != null)
 		define(reg "_RES0", "(" res0 ")")
 	if (res1 != null)
@@ -185,12 +200,13 @@ END {
 	res1 = null
 	unkn = null
 
+	block_pop()
 	next
 }
 
 # Currently this is effectivey a comment, in future we may want to emit
 # defines for the fields.
-/^Fields/ && (block == "Sysreg") {
+/^Fields/ && block_current() == "Sysreg" {
 	expect_fields(2)
 
 	if (next_bit != 63)
@@ -208,7 +224,7 @@ END {
 }
 
 
-/^Res0/ && (block == "Sysreg" || block == "SysregFields") {
+/^Res0/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "RES0", $2)
 	field = "RES0_" msb "_" lsb
@@ -218,7 +234,7 @@ END {
 	next
 }
 
-/^Res1/ && (block == "Sysreg" || block == "SysregFields") {
+/^Res1/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "RES1", $2)
 	field = "RES1_" msb "_" lsb
@@ -228,7 +244,7 @@ END {
 	next
 }
 
-/^Unkn/ && (block == "Sysreg" || block == "SysregFields") {
+/^Unkn/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "UNKN", $2)
 	field = "UNKN_" msb "_" lsb
@@ -238,7 +254,7 @@ END {
 	next
 }
 
-/^Field/ && (block == "Sysreg" || block == "SysregFields") {
+/^Field/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(3)
 	field = $3
 	parse_bitdef(reg, field, $2)
@@ -249,15 +265,16 @@ END {
 	next
 }
 
-/^Raz/ && (block == "Sysreg" || block == "SysregFields") {
+/^Raz/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, field, $2)
 
 	next
 }
 
-/^SignedEnum/ {
-	change_block("Enum<", "Sysreg", "Enum")
+/^SignedEnum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+	block_push("Enum")
+
 	expect_fields(3)
 	field = $3
 	parse_bitdef(reg, field, $2)
@@ -268,8 +285,9 @@ END {
 	next
 }
 
-/^UnsignedEnum/ {
-	change_block("Enum<", "Sysreg", "Enum")
+/^UnsignedEnum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+	block_push("Enum")
+
 	expect_fields(3)
 	field = $3
 	parse_bitdef(reg, field, $2)
@@ -280,8 +298,9 @@ END {
 	next
 }
 
-/^Enum/ {
-	change_block("Enum", "Sysreg", "Enum")
+/^Enum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+	block_push("Enum")
+
 	expect_fields(3)
 	field = $3
 	parse_bitdef(reg, field, $2)
@@ -291,16 +310,18 @@ END {
 	next
 }
 
-/^EndEnum/ {
-	change_block("EndEnum", "Enum", "Sysreg")
+/^EndEnum/ && block_current() == "Enum" {
+
 	field = null
 	msb = null
 	lsb = null
 	print ""
+
+	block_pop()
 	next
 }
 
-/0b[01]+/ && block == "Enum" {
+/0b[01]+/ && block_current() == "Enum" {
 	expect_fields(2)
 	val = $1
 	name = $2

arch/arm64/tools/sysreg

@@ -879,7 +879,30 @@ EndEnum
 EndSysreg
 
 Sysreg	ID_AA64PFR1_EL1	3	0	0	4	1
-Res0	63:40
+UnsignedEnum	63:60	PFAR
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	59:56	DF2
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	55:52	MTEX
+	0b0000	MTE
+	0b0001	MTE4
+EndEnum
+UnsignedEnum	51:48	THE
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+UnsignedEnum	47:44	GCS
+	0b0000	NI
+	0b0001	IMP
+EndEnum
+Enum	43:40	MTE_frac
+	0b0000	ASYNC
+	0b1111	NI
+EndEnum
 UnsignedEnum	39:36	NMI
 	0b0000	NI
 	0b0001	IMP
@@ -1866,6 +1889,146 @@ Field	1	ZA
 Field	0	SM
 EndSysreg
 
+SysregFields	HFGxTR_EL2
+Field	63	nAMIAIR2_EL1
+Field	62	nMAIR2_EL1
+Field	61	nS2POR_EL1
+Field	60	nPOR_EL1
+Field	59	nPOR_EL0
+Field	58	nPIR_EL1
+Field	57	nPIRE0_EL1
+Field	56	nRCWMASK_EL1
+Field	55	nTPIDR2_EL0
+Field	54	nSMPRI_EL1
+Field	53	nGCS_EL1
+Field	52	nGCS_EL0
+Res0	51
+Field	50	nACCDATA_EL1
+Field	49	ERXADDR_EL1
+Field	48	EXRPFGCDN_EL1
+Field	47	EXPFGCTL_EL1
+Field	46	EXPFGF_EL1
+Field	45	ERXMISCn_EL1
+Field	44	ERXSTATUS_EL1
+Field	43	ERXCTLR_EL1
+Field	42	ERXFR_EL1
+Field	41	ERRSELR_EL1
+Field	40	ERRIDR_EL1
+Field	39	ICC_IGRPENn_EL1
+Field	38	VBAR_EL1
+Field	37	TTBR1_EL1
+Field	36	TTBR0_EL1
+Field	35	TPIDR_EL0
+Field	34	TPIDRRO_EL0
+Field	33	TPIDR_EL1
+Field	32	TCR_EL1
+Field	31	SCTXNUM_EL0
+Field	30	SCTXNUM_EL1
+Field	29	SCTLR_EL1
+Field	28	REVIDR_EL1
+Field	27	PAR_EL1
+Field	26	MPIDR_EL1
+Field	25	MIDR_EL1
+Field	24	MAIR_EL1
+Field	23	LORSA_EL1
+Field	22	LORN_EL1
+Field	21	LORID_EL1
+Field	20	LOREA_EL1
+Field	19	LORC_EL1
+Field	18	ISR_EL1
+Field	17	FAR_EL1
+Field	16	ESR_EL1
+Field	15	DCZID_EL0
+Field	14	CTR_EL0
+Field	13	CSSELR_EL1
+Field	12	CPACR_EL1
+Field	11	CONTEXTIDR_EL1
+Field	10	CLIDR_EL1
+Field	9	CCSIDR_EL1
+Field	8	APIBKey
+Field	7	APIAKey
+Field	6	APGAKey
+Field	5	APDBKey
+Field	4	APDAKey
+Field	3	AMAIR_EL1
+Field	2	AIDR_EL1
+Field	1	AFSR1_EL1
+Field	0	AFSR0_EL1
+EndSysregFields
+
+Sysreg HFGRTR_EL2	3	4	1	1	4
+Fields	HFGxTR_EL2
+EndSysreg
+
+Sysreg HFGWTR_EL2	3	4	1	1	5
+Fields	HFGxTR_EL2
+EndSysreg
+
+Sysreg HFGITR_EL2	3	4	1	1	6
+Res0	63:61
+Field	60	COSPRCTX
+Field	59	nGCSEPP
+Field	58	nGCSSTR_EL1
+Field	57	nGCSPUSHM_EL1
+Field	56	nBRBIALL
+Field	55	nBRBINJ
+Field	54	DCCVAC
+Field	53	SVC_EL1
+Field	52	SVC_EL0
+Field	51	ERET
+Field	50	CPPRCTX
+Field	49	DVPRCTX
+Field	48	CFPRCTX
+Field	47	TLBIVAALE1
+Field	46	TLBIVALE1
+Field	45	TLBIVAAE1
+Field	44	TLBIASIDE1
+Field	43	TLBIVAE1
+Field	42	TLBIVMALLE1
+Field	41	TLBIRVAALE1
+Field	40	TLBIRVALE1
+Field	39	TLBIRVAAE1
+Field	38	TLBIRVAE1
+Field	37	TLBIRVAALE1IS
+Field	36	TLBIRVALE1IS
+Field	35	TLBIRVAAE1IS
+Field	34	TLBIRVAE1IS
+Field	33	TLBIVAALE1IS
+Field	32	TLBIVALE1IS
+Field	31	TLBIVAAE1IS
+Field	30	TLBIASIDE1IS
+Field	29	TLBIVAE1IS
+Field	28	TLBIVMALLE1IS
+Field	27	TLBIRVAALE1OS
+Field	26	TLBIRVALE1OS
+Field	25	TLBIRVAAE1OS
+Field	24	TLBIRVAE1OS
+Field	23	TLBIVAALE1OS
+Field	22	TLBIVALE1OS
+Field	21	TLBIVAAE1OS
+Field	20	TLBIASIDE1OS
+Field	19	TLBIVAE1OS
+Field	18	TLBIVMALLE1OS
+Field	17	ATS1E1WP
+Field	16	ATS1E1RP
+Field	15	ATS1E0W
+Field	14	ATS1E0R
+Field	13	ATS1E1W
+Field	12	ATS1E1R
+Field	11	DCZVA
+Field	10	DCCIVAC
+Field	9	DCCVADP
+Field	8	DCCVAP
+Field	7	DCCVAU
+Field	6	DCCISW
+Field	5	DCCSW
+Field	4	DCISW
+Field	3	DCIVAC
+Field	2	ICIVAU
+Field	1	ICIALLU
+Field	0	ICIALLUIS
+EndSysreg
+
 Sysreg	ZCR_EL2	3	4	1	2	0
 Fields	ZCR_ELx
 EndSysreg

arch/s390/kernel/mcount.S

@@ -32,6 +32,11 @@ ENTRY(ftrace_stub)
 	BR_EX	%r14
 ENDPROC(ftrace_stub)
 
+SYM_CODE_START(ftrace_stub_direct_tramp)
+	lgr	%r1, %r0
+	BR_EX	%r1
+SYM_CODE_END(ftrace_stub_direct_tramp)
+
 	.macro	ftrace_regs_entry, allregs=0
 	stg	%r14,(__SF_GPRS+8*8)(%r15)	# save traced function caller
 

arch/x86/kernel/ftrace_32.S

@@ -163,6 +163,11 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	jmp	.Lftrace_ret
 SYM_CODE_END(ftrace_regs_caller)
 
+SYM_FUNC_START(ftrace_stub_direct_tramp)
+	CALL_DEPTH_ACCOUNT
+	RET
+SYM_FUNC_END(ftrace_stub_direct_tramp)
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 SYM_CODE_START(ftrace_graph_caller)
 	pushl	%eax

arch/x86/kernel/ftrace_64.S

@@ -309,6 +309,10 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 SYM_FUNC_END(ftrace_regs_caller)
 STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
 
+SYM_FUNC_START(ftrace_stub_direct_tramp)
+	CALL_DEPTH_ACCOUNT
+	RET
+SYM_FUNC_END(ftrace_stub_direct_tramp)
 
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 

drivers/acpi/arm64/agdi.c

@@ -64,8 +64,11 @@ static int agdi_remove(struct platform_device *pdev)
 	int err, i;
 
 	err = sdei_event_disable(adata->sdei_event);
-	if (err)
-		return err;
+	if (err) {
+		dev_err(&pdev->dev, "Failed to disable sdei-event #%d (%pe)\n",
+			adata->sdei_event, ERR_PTR(err));
+		return 0;
+	}
 
 	for (i = 0; i < 3; i++) {
 		err = sdei_event_unregister(adata->sdei_event);
@@ -75,7 +78,11 @@ static int agdi_remove(struct platform_device *pdev)
 		schedule();
 	}
 
-	return err;
+	if (err)
+		dev_err(&pdev->dev, "Failed to unregister sdei-event #%d (%pe)\n",
+			adata->sdei_event, ERR_PTR(err));
+
+	return 0;
 }
 
 static struct platform_driver agdi_driver = {

drivers/firmware/arm_sdei.c

@@ -43,6 +43,8 @@ static asmlinkage void (*sdei_firmware_call)(unsigned long function_id,
 /* entry point from firmware to arch asm code */
 static unsigned long sdei_entry_point;
 
+static int sdei_hp_state;
+
 struct sdei_event {
 	/* These three are protected by the sdei_list_lock */
 	struct list_head	list;
@@ -301,8 +303,6 @@ int sdei_mask_local_cpu(void)
 {
 	int err;
 
-	WARN_ON_ONCE(preemptible());
-
 	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_MASK, 0, 0, 0, 0, 0, NULL);
 	if (err && err != -EIO) {
 		pr_warn_once("failed to mask CPU[%u]: %d\n",
@@ -315,6 +315,7 @@ int sdei_mask_local_cpu(void)
 
 static void _ipi_mask_cpu(void *ignored)
 {
+	WARN_ON_ONCE(preemptible());
 	sdei_mask_local_cpu();
 }
 
@@ -322,8 +323,6 @@ int sdei_unmask_local_cpu(void)
 {
 	int err;
 
-	WARN_ON_ONCE(preemptible());
-
 	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_UNMASK, 0, 0, 0, 0, 0, NULL);
 	if (err && err != -EIO) {
 		pr_warn_once("failed to unmask CPU[%u]: %d\n",
@@ -336,6 +335,7 @@ int sdei_unmask_local_cpu(void)
 
 static void _ipi_unmask_cpu(void *ignored)
 {
+	WARN_ON_ONCE(preemptible());
 	sdei_unmask_local_cpu();
 }
 
@@ -343,6 +343,8 @@ static void _ipi_private_reset(void *ignored)
 {
 	int err;
 
+	WARN_ON_ONCE(preemptible());
+
 	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PRIVATE_RESET, 0, 0, 0, 0, 0,
 			     NULL);
 	if (err && err != -EIO)
@@ -389,8 +391,6 @@ static void _local_event_enable(void *data)
 	int err;
 	struct sdei_crosscall_args *arg = data;
 
-	WARN_ON_ONCE(preemptible());
-
 	err = sdei_api_event_enable(arg->event->event_num);
 
 	sdei_cross_call_return(arg, err);
@@ -479,8 +479,6 @@ static void _local_event_unregister(void *data)
 	int err;
 	struct sdei_crosscall_args *arg = data;
 
-	WARN_ON_ONCE(preemptible());
-
 	err = sdei_api_event_unregister(arg->event->event_num);
 
 	sdei_cross_call_return(arg, err);
@@ -561,8 +559,6 @@ static void _local_event_register(void *data)
 	struct sdei_registered_event *reg;
 	struct sdei_crosscall_args *arg = data;
 
-	WARN_ON(preemptible());
-
 	reg = per_cpu_ptr(arg->event->private_registered, smp_processor_id());
 	err = sdei_api_event_register(arg->event->event_num, sdei_entry_point,
 				      reg, 0, 0);
@@ -717,6 +713,8 @@ static int sdei_pm_notifier(struct notifier_block *nb, unsigned long action,
 {
 	int rv;
 
+	WARN_ON_ONCE(preemptible());
+
 	switch (action) {
 	case CPU_PM_ENTER:
 		rv = sdei_mask_local_cpu();
@@ -765,7 +763,7 @@ static int sdei_device_freeze(struct device *dev)
 	int err;
 
 	/* unregister private events */
-	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+	cpuhp_remove_state(sdei_entry_point);
 
 	err = sdei_unregister_shared();
 	if (err)
@@ -786,12 +784,15 @@ static int sdei_device_thaw(struct device *dev)
 		return err;
 	}
 
-	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SDEI",
 				&sdei_cpuhp_up, &sdei_cpuhp_down);
-	if (err)
+	if (err < 0) {
 		pr_warn("Failed to re-register CPU hotplug notifier...\n");
+		return err;
+	}
 
-	return err;
+	sdei_hp_state = err;
+	return 0;
 }
 
 static int sdei_device_restore(struct device *dev)
@@ -823,7 +824,7 @@ static int sdei_reboot_notifier(struct notifier_block *nb, unsigned long action,
 	 * We are going to reset the interface, after this there is no point
 	 * doing work when we take CPUs offline.
 	 */
-	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+	cpuhp_remove_state(sdei_hp_state);
 
 	sdei_platform_reset();
 
@@ -1003,13 +1004,15 @@ static int sdei_probe(struct platform_device *pdev)
 		goto remove_cpupm;
 	}
 
-	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SDEI",
 				&sdei_cpuhp_up, &sdei_cpuhp_down);
-	if (err) {
+	if (err < 0) {
 		pr_warn("Failed to register CPU hotplug notifier...\n");
 		goto remove_reboot;
 	}
 
+	sdei_hp_state = err;
+
 	return 0;
 
 remove_reboot:

drivers/perf/Kconfig

@@ -100,6 +100,16 @@ config ARM_SMMU_V3_PMU
 	   through the SMMU and allow the resulting information to be filtered
 	   based on the Stream ID of the corresponding master.
 
+config ARM_PMUV3
+	depends on HW_PERF_EVENTS && ((ARM && CPU_V7) || ARM64)
+	bool "ARM PMUv3 support" if !ARM64
+	default ARM64
+	  help
+	  Say y if you want to use the ARM performance monitor unit (PMU)
+	  version 3. The PMUv3 is the CPU performance monitors on ARMv8
+	  (aarch32 and aarch64) systems that implement the PMUv3
+	  architecture.
+
 config ARM_DSU_PMU
 	tristate "ARM DynamIQ Shared Unit (DSU) PMU"
 	depends on ARM64

drivers/perf/Makefile

@@ -5,6 +5,7 @@ obj-$(CONFIG_ARM_CMN) += arm-cmn.o
 obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
+obj-$(CONFIG_ARM_PMUV3) += arm_pmuv3.o
 obj-$(CONFIG_ARM_SMMU_V3_PMU) += arm_smmuv3_pmu.o
 obj-$(CONFIG_FSL_IMX8_DDR_PMU) += fsl_imx8_ddr_perf.o
 obj-$(CONFIG_HISI_PMU) += hisilicon/

drivers/perf/alibaba_uncore_drw_pmu.c

@@ -656,8 +656,7 @@ static int ali_drw_pmu_probe(struct platform_device *pdev)
 	drw_pmu->dev = &pdev->dev;
 	platform_set_drvdata(pdev, drw_pmu);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	drw_pmu->cfg_base = devm_ioremap_resource(&pdev->dev, res);
+	drw_pmu->cfg_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(drw_pmu->cfg_base))
 		return PTR_ERR(drw_pmu->cfg_base);
 

drivers/perf/amlogic/meson_ddr_pmu_core.c

@@ -156,10 +156,14 @@ static int meson_ddr_perf_event_add(struct perf_event *event, int flags)
 	u64 config2 = event->attr.config2;
 	int i;
 
-	for_each_set_bit(i, (const unsigned long *)&config1, sizeof(config1))
+	for_each_set_bit(i,
+			 (const unsigned long *)&config1,
+			 BITS_PER_TYPE(config1))
 		meson_ddr_set_axi_filter(event, i);
 
-	for_each_set_bit(i, (const unsigned long *)&config2, sizeof(config2))
+	for_each_set_bit(i,
+			 (const unsigned long *)&config2,
+			 BITS_PER_TYPE(config2))
 		meson_ddr_set_axi_filter(event, i + 64);
 
 	if (flags & PERF_EF_START)

drivers/perf/apple_m1_cpu_pmu.c

@@ -559,7 +559,21 @@ static int m1_pmu_fire_init(struct arm_pmu *cpu_pmu)
 	return m1_pmu_init(cpu_pmu);
 }
 
+static int m2_pmu_avalanche_init(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->name = "apple_avalanche_pmu";
+	return m1_pmu_init(cpu_pmu);
+}
+
+static int m2_pmu_blizzard_init(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->name = "apple_blizzard_pmu";
+	return m1_pmu_init(cpu_pmu);
+}
+
 static const struct of_device_id m1_pmu_of_device_ids[] = {
+	{ .compatible = "apple,avalanche-pmu",	.data = m2_pmu_avalanche_init, },
+	{ .compatible = "apple,blizzard-pmu",	.data = m2_pmu_blizzard_init, },
 	{ .compatible = "apple,icestorm-pmu",	.data = m1_pmu_ice_init, },
 	{ .compatible = "apple,firestorm-pmu",	.data = m1_pmu_fire_init, },
 	{ },
@@ -581,4 +595,3 @@ static struct platform_driver m1_pmu_driver = {
 };
 
 module_platform_driver(m1_pmu_driver);
-MODULE_LICENSE("GPL v2");

drivers/perf/arm-cmn.c

@@ -57,14 +57,12 @@
 #define CMN_INFO_REQ_VC_NUM		GENMASK_ULL(1, 0)
 
 /* XPs also have some local topology info which has uses too */
-#define CMN_MXP__CONNECT_INFO_P0	0x0008
-#define CMN_MXP__CONNECT_INFO_P1	0x0010
-#define CMN_MXP__CONNECT_INFO_P2	0x0028
-#define CMN_MXP__CONNECT_INFO_P3	0x0030
-#define CMN_MXP__CONNECT_INFO_P4	0x0038
-#define CMN_MXP__CONNECT_INFO_P5	0x0040
+#define CMN_MXP__CONNECT_INFO(p)	(0x0008 + 8 * (p))
 #define CMN__CONNECT_INFO_DEVICE_TYPE	GENMASK_ULL(4, 0)
 
+#define CMN_MAX_PORTS			6
+#define CI700_CONNECT_INFO_P2_5_OFFSET	0x10
+
 /* PMU registers occupy the 3rd 4KB page of each node's region */
 #define CMN_PMU_OFFSET			0x2000
 
@@ -166,7 +164,7 @@
 #define CMN_EVENT_BYNODEID(event)	FIELD_GET(CMN_CONFIG_BYNODEID, (event)->attr.config)
 #define CMN_EVENT_NODEID(event)		FIELD_GET(CMN_CONFIG_NODEID, (event)->attr.config)
 
-#define CMN_CONFIG_WP_COMBINE		GENMASK_ULL(27, 24)
+#define CMN_CONFIG_WP_COMBINE		GENMASK_ULL(30, 27)
 #define CMN_CONFIG_WP_DEV_SEL		GENMASK_ULL(50, 48)
 #define CMN_CONFIG_WP_CHN_SEL		GENMASK_ULL(55, 51)
 /* Note that we don't yet support the tertiary match group on newer IPs */
@@ -396,6 +394,25 @@ static struct arm_cmn_node *arm_cmn_node(const struct arm_cmn *cmn,
 	return NULL;
 }
 
+static u32 arm_cmn_device_connect_info(const struct arm_cmn *cmn,
+				       const struct arm_cmn_node *xp, int port)
+{
+	int offset = CMN_MXP__CONNECT_INFO(port);
+
+	if (port >= 2) {
+		if (cmn->model & (CMN600 | CMN650))
+			return 0;
+		/*
+		 * CI-700 may have extra ports, but still has the
+		 * mesh_port_connect_info registers in the way.
+		 */
+		if (cmn->model == CI700)
+			offset += CI700_CONNECT_INFO_P2_5_OFFSET;
+	}
+
+	return readl_relaxed(xp->pmu_base - CMN_PMU_OFFSET + offset);
+}
+
 static struct dentry *arm_cmn_debugfs;
 
 #ifdef CONFIG_DEBUG_FS
@@ -469,7 +486,7 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 	y = cmn->mesh_y;
 	while (y--) {
 		int xp_base = cmn->mesh_x * y;
-		u8 port[6][CMN_MAX_DIMENSION];
+		u8 port[CMN_MAX_PORTS][CMN_MAX_DIMENSION];
 
 		for (x = 0; x < cmn->mesh_x; x++)
 			seq_puts(s, "--------+");
@@ -477,14 +494,9 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 		seq_printf(s, "\n%d    |", y);
 		for (x = 0; x < cmn->mesh_x; x++) {
 			struct arm_cmn_node *xp = cmn->xps + xp_base + x;
-			void __iomem *base = xp->pmu_base - CMN_PMU_OFFSET;
-
-			port[0][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P0);
-			port[1][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P1);
-			port[2][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P2);
-			port[3][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P3);
-			port[4][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P4);
-			port[5][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P5);
+
+			for (p = 0; p < CMN_MAX_PORTS; p++)
+				port[p][x] = arm_cmn_device_connect_info(cmn, xp, p);
 			seq_printf(s, " XP #%-2d |", xp_base + x);
 		}
 
@@ -1546,7 +1558,7 @@ static int arm_cmn_event_init(struct perf_event *event)
 	type = CMN_EVENT_TYPE(event);
 	/* DTC events (i.e. cycles) already have everything they need */
 	if (type == CMN_TYPE_DTC)
-		return 0;
+		return arm_cmn_validate_group(cmn, event);
 
 	eventid = CMN_EVENT_EVENTID(event);
 	/* For watchpoints we need the actual XP node here */
@@ -2083,18 +2095,9 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
 		 * from this, since in that case we will see at least one XP
 		 * with port 2 connected, for the HN-D.
 		 */
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P0))
-			xp_ports |= BIT(0);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P1))
-			xp_ports |= BIT(1);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P2))
-			xp_ports |= BIT(2);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P3))
-			xp_ports |= BIT(3);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P4))
-			xp_ports |= BIT(4);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P5))
-			xp_ports |= BIT(5);
+		for (int p = 0; p < CMN_MAX_PORTS; p++)
+			if (arm_cmn_device_connect_info(cmn, xp, p))
+				xp_ports |= BIT(p);
 
 		if (cmn->multi_dtm && (xp_ports & 0xc))
 			arm_cmn_init_dtm(dtm++, xp, 1);

drivers/perf/arm_cspmu/arm_cspmu.c

@@ -1078,12 +1078,14 @@ static int arm_cspmu_request_irq(struct arm_cspmu *cspmu)
 static inline int arm_cspmu_find_cpu_container(int cpu, u32 container_uid)
 {
 	u32 acpi_uid;
-	struct device *cpu_dev = get_cpu_device(cpu);
-	struct acpi_device *acpi_dev = ACPI_COMPANION(cpu_dev);
+	struct device *cpu_dev;
+	struct acpi_device *acpi_dev;
 
+	cpu_dev = get_cpu_device(cpu);
 	if (!cpu_dev)
 		return -ENODEV;
 
+	acpi_dev = ACPI_COMPANION(cpu_dev);
 	while (acpi_dev) {
 		if (!strcmp(acpi_device_hid(acpi_dev),
 			    ACPI_PROCESSOR_CONTAINER_HID) &&

drivers/perf/arm_dmc620_pmu.c

@@ -655,8 +655,7 @@ static int dmc620_pmu_device_probe(struct platform_device *pdev)
 		.attr_groups	= dmc620_pmu_attr_groups,
 	};
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	dmc620_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	dmc620_pmu->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(dmc620_pmu->base))
 		return PTR_ERR(dmc620_pmu->base);
 

drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c

@@ -316,7 +316,7 @@ static int hisi_cpa_pmu_probe(struct platform_device *pdev)
 	if (!name)
 		return -ENOMEM;
 
-	hisi_pmu_init(cpa_pmu, name, THIS_MODULE);
+	hisi_pmu_init(cpa_pmu, THIS_MODULE);
 
 	/* Power Management should be disabled before using CPA PMU. */
 	hisi_cpa_pmu_disable_pm(cpa_pmu);

drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c

@@ -499,13 +499,6 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
-				       &ddrc_pmu->node);
-	if (ret) {
-		dev_err(&pdev->dev, "Error %d registering hotplug;\n", ret);
-		return ret;
-	}
-
 	if (ddrc_pmu->identifier >= HISI_PMU_V2)
 		name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 				      "hisi_sccl%u_ddrc%u_%u",
@@ -516,7 +509,17 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 				      "hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id,
 				      ddrc_pmu->index_id);
 
-	hisi_pmu_init(ddrc_pmu, name, THIS_MODULE);
+	if (!name)
+		return -ENOMEM;
+
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+				       &ddrc_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug;\n", ret);
+		return ret;
+	}
+
+	hisi_pmu_init(ddrc_pmu, THIS_MODULE);
 
 	ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1);
 	if (ret) {

drivers/perf/hisilicon/hisi_uncore_hha_pmu.c

@@ -510,6 +510,11 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u",
+			      hha_pmu->sccl_id, hha_pmu->index_id);
+	if (!name)
+		return -ENOMEM;
+
 	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
 				       &hha_pmu->node);
 	if (ret) {
@@ -517,9 +522,7 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u",
-			      hha_pmu->sccl_id, hha_pmu->index_id);
-	hisi_pmu_init(hha_pmu, name, THIS_MODULE);
+	hisi_pmu_init(hha_pmu, THIS_MODULE);
 
 	ret = perf_pmu_register(&hha_pmu->pmu, name, -1);
 	if (ret) {

drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c

@@ -544,6 +544,11 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u",
+			      l3c_pmu->sccl_id, l3c_pmu->ccl_id);
+	if (!name)
+		return -ENOMEM;
+
 	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
 				       &l3c_pmu->node);
 	if (ret) {
@@ -551,13 +556,7 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	/*
-	 * CCL_ID is used to identify the L3C in the same SCCL which was
-	 * used _UID by mistake.
-	 */
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u",
-			      l3c_pmu->sccl_id, l3c_pmu->ccl_id);
-	hisi_pmu_init(l3c_pmu, name, THIS_MODULE);
+	hisi_pmu_init(l3c_pmu, THIS_MODULE);
 
 	ret = perf_pmu_register(&l3c_pmu->pmu, name, -1);
 	if (ret) {

drivers/perf/hisilicon/hisi_uncore_pa_pmu.c

@@ -412,7 +412,7 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	hisi_pmu_init(pa_pmu, name, THIS_MODULE);
+	hisi_pmu_init(pa_pmu, THIS_MODULE);
 	ret = perf_pmu_register(&pa_pmu->pmu, name, -1);
 	if (ret) {
 		dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret);

drivers/perf/hisilicon/hisi_uncore_pmu.c

@@ -531,12 +531,10 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 }
 EXPORT_SYMBOL_GPL(hisi_uncore_pmu_offline_cpu);
 
-void hisi_pmu_init(struct hisi_pmu *hisi_pmu, const char *name,
-		   struct module *module)
+void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module)
 {
 	struct pmu *pmu = &hisi_pmu->pmu;
 
-	pmu->name               = name;
 	pmu->module             = module;
 	pmu->task_ctx_nr        = perf_invalid_context;
 	pmu->event_init         = hisi_uncore_pmu_event_init;

drivers/perf/hisilicon/hisi_uncore_pmu.h

@@ -121,6 +121,5 @@ ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev,
 int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu,
 			     struct platform_device *pdev);
 
-void hisi_pmu_init(struct hisi_pmu *hisi_pmu, const char *name,
-		   struct module *module);
+void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module);
 #endif /* __HISI_UNCORE_PMU_H__ */

drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c

@@ -445,7 +445,7 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	hisi_pmu_init(sllc_pmu, name, THIS_MODULE);
+	hisi_pmu_init(sllc_pmu, THIS_MODULE);
 
 	ret = perf_pmu_register(&sllc_pmu->pmu, name, -1);
 	if (ret) {

drivers/perf/qcom_l3_pmu.c

@@ -763,8 +763,7 @@ static int qcom_l3_cache_pmu_probe(struct platform_device *pdev)
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
-	memrc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	l3pmu->regs = devm_ioremap_resource(&pdev->dev, memrc);
+	l3pmu->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &memrc);
 	if (IS_ERR(l3pmu->regs))
 		return PTR_ERR(l3pmu->regs);
 

include/kvm/arm_pmu.h

@@ -8,7 +8,7 @@
 #define __ASM_ARM_KVM_PMU_H
 
 #include <linux/perf_event.h>
-#include <asm/perf_event.h>
+#include <linux/perf/arm_pmuv3.h>
 
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
 

include/linux/cpuhotplug.h

@@ -163,7 +163,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_CSTATE_STARTING,
 	CPUHP_AP_PERF_XTENSA_STARTING,
 	CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
-	CPUHP_AP_ARM_SDEI_STARTING,
 	CPUHP_AP_ARM_VFP_STARTING,
 	CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
 	CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,

include/linux/ftrace.h

@@ -241,6 +241,12 @@ enum {
 	FTRACE_OPS_FL_DIRECT			= BIT(17),
 };
 
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+#define FTRACE_OPS_FL_SAVE_ARGS                        FTRACE_OPS_FL_SAVE_REGS
+#else
+#define FTRACE_OPS_FL_SAVE_ARGS                        0
+#endif
+
 /*
  * FTRACE_OPS_CMD_* commands allow the ftrace core logic to request changes
  * to a ftrace_ops. Note, the requests may fail.
@@ -321,6 +327,9 @@ struct ftrace_ops {
 	unsigned long			trampoline_size;
 	struct list_head		list;
 	ftrace_ops_func_t		ops_func;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	unsigned long			direct_call;
+#endif
 #endif
 };
 
@@ -397,64 +406,36 @@ struct ftrace_func_entry {
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 extern int ftrace_direct_func_count;
-int register_ftrace_direct(unsigned long ip, unsigned long addr);
-int unregister_ftrace_direct(unsigned long ip, unsigned long addr);
-int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr);
-struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr);
-int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
-				struct dyn_ftrace *rec,
-				unsigned long old_addr,
-				unsigned long new_addr);
 unsigned long ftrace_find_rec_direct(unsigned long ip);
-int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
-int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
-int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
-int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr);
+int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr);
+int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr,
+			     bool free_filters);
+int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr);
+int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr);
+
+void ftrace_stub_direct_tramp(void);
 
 #else
 struct ftrace_ops;
 # define ftrace_direct_func_count 0
-static inline int register_ftrace_direct(unsigned long ip, unsigned long addr)
-{
-	return -ENOTSUPP;
-}
-static inline int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
-{
-	return -ENOTSUPP;
-}
-static inline int modify_ftrace_direct(unsigned long ip,
-				       unsigned long old_addr, unsigned long new_addr)
-{
-	return -ENOTSUPP;
-}
-static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr)
-{
-	return NULL;
-}
-static inline int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
-					      struct dyn_ftrace *rec,
-					      unsigned long old_addr,
-					      unsigned long new_addr)
-{
-	return -ENODEV;
-}
 static inline unsigned long ftrace_find_rec_direct(unsigned long ip)
 {
 	return 0;
 }
-static inline int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+static inline int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 {
 	return -ENODEV;
 }
-static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+static inline int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr,
+					   bool free_filters)
 {
 	return -ENODEV;
 }
-static inline int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+static inline int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 {
 	return -ENODEV;
 }
-static inline int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr)
+static inline int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr)
 {
 	return -ENODEV;
 }

kernel/bpf/trampoline.c

@@ -45,8 +45,8 @@ static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, enum ftrace_ops_cmd
 		lockdep_assert_held_once(&tr->mutex);
 
 		/* Instead of updating the trampoline here, we propagate
-		 * -EAGAIN to register_ftrace_direct_multi(). Then we can
-		 * retry register_ftrace_direct_multi() after updating the
+		 * -EAGAIN to register_ftrace_direct(). Then we can
+		 * retry register_ftrace_direct() after updating the
 		 * trampoline.
 		 */
 		if ((tr->flags & BPF_TRAMP_F_CALL_ORIG) &&
@@ -198,7 +198,7 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
 	int ret;
 
 	if (tr->func.ftrace_managed)
-		ret = unregister_ftrace_direct_multi(tr->fops, (long)old_addr);
+		ret = unregister_ftrace_direct(tr->fops, (long)old_addr, false);
 	else
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
 
@@ -215,9 +215,9 @@ static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_ad
 
 	if (tr->func.ftrace_managed) {
 		if (lock_direct_mutex)
-			ret = modify_ftrace_direct_multi(tr->fops, (long)new_addr);
+			ret = modify_ftrace_direct(tr->fops, (long)new_addr);
 		else
-			ret = modify_ftrace_direct_multi_nolock(tr->fops, (long)new_addr);
+			ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr);
 	} else {
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
 	}
@@ -243,7 +243,7 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 
 	if (tr->func.ftrace_managed) {
 		ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1);
-		ret = register_ftrace_direct_multi(tr->fops, (long)new_addr);
+		ret = register_ftrace_direct(tr->fops, (long)new_addr);
 	} else {
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
 	}

kernel/trace/Kconfig

@@ -257,7 +257,7 @@ config DYNAMIC_FTRACE_WITH_REGS
 
 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	def_bool y
-	depends on DYNAMIC_FTRACE_WITH_REGS
+	depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS
 	depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 
 config DYNAMIC_FTRACE_WITH_CALL_OPS

kernel/trace/trace_selftest.c

@@ -785,14 +785,7 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
-#ifndef CALL_DEPTH_ACCOUNT
-#define CALL_DEPTH_ACCOUNT ""
-#endif
-
-noinline __noclone static void trace_direct_tramp(void)
-{
-	asm(CALL_DEPTH_ACCOUNT);
-}
+static struct ftrace_ops direct;
 #endif
 
 /*
@@ -870,8 +863,9 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	 * Register direct function together with graph tracer
 	 * and make sure we get graph trace.
 	 */
-	ret = register_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
-				     (unsigned long) trace_direct_tramp);
+	ftrace_set_filter_ip(&direct, (unsigned long)DYN_FTRACE_TEST_NAME, 0, 0);
+	ret = register_ftrace_direct(&direct,
+				     (unsigned long)ftrace_stub_direct_tramp);
 	if (ret)
 		goto out;
 
@@ -891,8 +885,9 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 
 	unregister_ftrace_graph(&fgraph_ops);
 
-	ret = unregister_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
-				       (unsigned long) trace_direct_tramp);
+	ret = unregister_ftrace_direct(&direct,
+				       (unsigned long)ftrace_stub_direct_tramp,
+				       true);
 	if (ret)
 		goto out;
 

mm/kfence/core.c

@@ -818,6 +818,10 @@ void __init kfence_alloc_pool(void)
 	if (!kfence_sample_interval)
 		return;
 
+	/* if the pool has already been initialized by arch, skip the below. */
+	if (__kfence_pool)
+		return;
+
 	__kfence_pool = memblock_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
 
 	if (!__kfence_pool)

samples/Kconfig

@@ -38,7 +38,7 @@ config SAMPLE_FTRACE_DIRECT
 	  that hooks to wake_up_process and prints the parameters.
 
 config SAMPLE_FTRACE_DIRECT_MULTI
-	tristate "Build register_ftrace_direct_multi() example"
+	tristate "Build register_ftrace_direct() on multiple ips example"
 	depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS && m
 	depends on HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	help

samples/ftrace/ftrace-direct-modify.c

@@ -96,6 +96,8 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+static struct ftrace_ops direct;
+
 static unsigned long my_tramp = (unsigned long)my_tramp1;
 static unsigned long tramps[2] = {
 	(unsigned long)my_tramp1,
@@ -114,7 +116,7 @@ static int simple_thread(void *arg)
 		if (ret)
 			continue;
 		t ^= 1;
-		ret = modify_ftrace_direct(my_ip, my_tramp, tramps[t]);
+		ret = modify_ftrace_direct(&direct, tramps[t]);
 		if (!ret)
 			my_tramp = tramps[t];
 		WARN_ON_ONCE(ret);
@@ -129,7 +131,9 @@ static int __init ftrace_direct_init(void)
 {
 	int ret;
 
-	ret = register_ftrace_direct(my_ip, my_tramp);
+	ftrace_set_filter_ip(&direct, (unsigned long) my_ip, 0, 0);
+	ret = register_ftrace_direct(&direct, my_tramp);
+
 	if (!ret)
 		simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn");
 	return ret;
@@ -138,7 +142,7 @@ static int __init ftrace_direct_init(void)
 static void __exit ftrace_direct_exit(void)
 {
 	kthread_stop(simple_tsk);
-	unregister_ftrace_direct(my_ip, my_tramp);
+	unregister_ftrace_direct(&direct, my_tramp, true);
 }
 
 module_init(ftrace_direct_init);

samples/ftrace/ftrace-direct-multi-modify.c

@@ -123,7 +123,7 @@ static int simple_thread(void *arg)
 		if (ret)
 			continue;
 		t ^= 1;
-		ret = modify_ftrace_direct_multi(&direct, tramps[t]);
+		ret = modify_ftrace_direct(&direct, tramps[t]);
 		if (!ret)
 			my_tramp = tramps[t];
 		WARN_ON_ONCE(ret);
@@ -141,7 +141,7 @@ static int __init ftrace_direct_multi_init(void)
 	ftrace_set_filter_ip(&direct, (unsigned long) wake_up_process, 0, 0);
 	ftrace_set_filter_ip(&direct, (unsigned long) schedule, 0, 0);
 
-	ret = register_ftrace_direct_multi(&direct, my_tramp);
+	ret = register_ftrace_direct(&direct, my_tramp);
 
 	if (!ret)
 		simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn");
@@ -151,13 +151,12 @@ static int __init ftrace_direct_multi_init(void)
 static void __exit ftrace_direct_multi_exit(void)
 {
 	kthread_stop(simple_tsk);
-	unregister_ftrace_direct_multi(&direct, my_tramp);
-	ftrace_free_filter(&direct);
+	unregister_ftrace_direct(&direct, my_tramp, true);
 }
 
 module_init(ftrace_direct_multi_init);
 module_exit(ftrace_direct_multi_exit);
 
 MODULE_AUTHOR("Jiri Olsa");
-MODULE_DESCRIPTION("Example use case of using modify_ftrace_direct_multi()");
+MODULE_DESCRIPTION("Example use case of using modify_ftrace_direct()");
 MODULE_LICENSE("GPL");

samples/ftrace/ftrace-direct-multi.c

@@ -73,13 +73,12 @@ static int __init ftrace_direct_multi_init(void)
 	ftrace_set_filter_ip(&direct, (unsigned long) wake_up_process, 0, 0);
 	ftrace_set_filter_ip(&direct, (unsigned long) schedule, 0, 0);
 
-	return register_ftrace_direct_multi(&direct, (unsigned long) my_tramp);
+	return register_ftrace_direct(&direct, (unsigned long) my_tramp);
 }
 
 static void __exit ftrace_direct_multi_exit(void)
 {
-	unregister_ftrace_direct_multi(&direct, (unsigned long) my_tramp);
-	ftrace_free_filter(&direct);
+	unregister_ftrace_direct(&direct, (unsigned long) my_tramp, true);
 }
 
 module_init(ftrace_direct_multi_init);

samples/ftrace/ftrace-direct-too.c

@@ -70,16 +70,18 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+static struct ftrace_ops direct;
+
 static int __init ftrace_direct_init(void)
 {
-	return register_ftrace_direct((unsigned long)handle_mm_fault,
-				     (unsigned long)my_tramp);
+	ftrace_set_filter_ip(&direct, (unsigned long) handle_mm_fault, 0, 0);
+
+	return register_ftrace_direct(&direct, (unsigned long) my_tramp);
 }
 
 static void __exit ftrace_direct_exit(void)
 {
-	unregister_ftrace_direct((unsigned long)handle_mm_fault,
-				 (unsigned long)my_tramp);
+	unregister_ftrace_direct(&direct, (unsigned long)my_tramp, true);
 }
 
 module_init(ftrace_direct_init);

samples/ftrace/ftrace-direct.c

@@ -63,16 +63,18 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+static struct ftrace_ops direct;
+
 static int __init ftrace_direct_init(void)
 {
-	return register_ftrace_direct((unsigned long)wake_up_process,
-				     (unsigned long)my_tramp);
+	ftrace_set_filter_ip(&direct, (unsigned long) wake_up_process, 0, 0);
+
+	return register_ftrace_direct(&direct, (unsigned long) my_tramp);
 }
 
 static void __exit ftrace_direct_exit(void)
 {
-	unregister_ftrace_direct((unsigned long)wake_up_process,
-				 (unsigned long)my_tramp);
+	unregister_ftrace_direct(&direct, (unsigned long)my_tramp, true);
 }
 
 module_init(ftrace_direct_init);