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

Pull arm64 updates from Catalin Marinas:

 - Initial support for the ARMv9 Scalable Matrix Extension (SME).

   SME takes the approach used for vectors in SVE and extends this to
   provide architectural support for matrix operations. No KVM support
   yet, SME is disabled in guests.

 - Support for crashkernel reservations above ZONE_DMA via the
   'crashkernel=X,high' command line option.

 - btrfs search_ioctl() fix for live-lock with sub-page faults.

 - arm64 perf updates: support for the Hisilicon "CPA" PMU for
   monitoring coherent I/O traffic, support for Arm's CMN-650 and
   CMN-700 interconnect PMUs, minor driver fixes, kerneldoc cleanup.

 - Kselftest updates for SME, BTI, MTE.

 - Automatic generation of the system register macros from a 'sysreg'
   file describing the register bitfields.

 - Update the type of the function argument holding the ESR_ELx register
   value to unsigned long to match the architecture register size
   (originally 32-bit but extended since ARMv8.0).

 - stacktrace cleanups.

 - ftrace cleanups.

 - Miscellaneous updates, most notably: arm64-specific huge_ptep_get(),
   avoid executable mappings in kexec/hibernate code, drop TLB flushing
   from get_clear_flush() (and rename it to get_clear_contig()),
   ARCH_NR_GPIO bumped to 2048 for ARCH_APPLE.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (145 commits)
  arm64/sysreg: Generate definitions for FAR_ELx
  arm64/sysreg: Generate definitions for DACR32_EL2
  arm64/sysreg: Generate definitions for CSSELR_EL1
  arm64/sysreg: Generate definitions for CPACR_ELx
  arm64/sysreg: Generate definitions for CONTEXTIDR_ELx
  arm64/sysreg: Generate definitions for CLIDR_EL1
  arm64/sve: Move sve_free() into SVE code section
  arm64: Kconfig.platforms: Add comments
  arm64: Kconfig: Fix indentation and add comments
  arm64: mm: avoid writable executable mappings in kexec/hibernate code
  arm64: lds: move special code sections out of kernel exec segment
  arm64/hugetlb: Implement arm64 specific huge_ptep_get()
  arm64/hugetlb: Use ptep_get() to get the pte value of a huge page
  arm64: kdump: Do not allocate crash low memory if not needed
  arm64/sve: Generate ZCR definitions
  arm64/sme: Generate defintions for SVCR
  arm64/sme: Generate SMPRI_EL1 definitions
  arm64/sme: Automatically generate SMPRIMAP_EL2 definitions
  arm64/sme: Automatically generate SMIDR_EL1 defines
  arm64/sme: Automatically generate defines for SMCR
  ...

32 files changed, 636 insertions, 183 deletions

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 345fe98605ba..5c8ee5a541d2 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -7,3 +7,4 @@ generic-y += parport.h
 generic-y += user.h
 
 generated-y += cpucaps.h
+generated-y += sysreg-defs.h
diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h
index d1bb5e71df25..3a6b6d38c5b8 100644
--- a/arch/arm64/include/asm/archrandom.h
+++ b/arch/arm64/include/asm/archrandom.h
@@ -142,7 +142,7 @@ static inline bool __init __early_cpu_has_rndr(void)
 {
 	/* Open code as we run prior to the first call to cpufeature. */
 	unsigned long ftr = read_sysreg_s(SYS_ID_AA64ISAR0_EL1);
-	return (ftr >> ID_AA64ISAR0_RNDR_SHIFT) & 0xf;
+	return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf;
 }
 
 static inline bool __init __must_check
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index a58e366f0b07..115cdec1ae87 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -58,11 +58,15 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
 	u64		reg_id_aa64zfr0;
+	u64		reg_id_aa64smfr0;
 
 	struct cpuinfo_32bit	aarch32;
 
 	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
 	u64		reg_zcr;
+
+	/* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */
+	u64		reg_smcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index c62e7e5e2f0c..14a8f3d93add 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -622,6 +622,13 @@ static inline bool id_aa64pfr0_sve(u64 pfr0)
 	return val > 0;
 }
 
+static inline bool id_aa64pfr1_sme(u64 pfr1)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_SME_SHIFT);
+
+	return val > 0;
+}
+
 static inline bool id_aa64pfr1_mte(u64 pfr1)
 {
 	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT);
@@ -759,6 +766,23 @@ static __always_inline bool system_supports_sve(void)
 		cpus_have_const_cap(ARM64_SVE);
 }
 
+static __always_inline bool system_supports_sme(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME);
+}
+
+static __always_inline bool system_supports_fa64(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME_FA64);
+}
+
+static __always_inline bool system_supports_tpidr2(void)
+{
+	return system_supports_sme();
+}
+
 static __always_inline bool system_supports_cnp(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_CNP) &&
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index ff8f4511df71..92331c07c2d1 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -36,7 +36,7 @@
 #define MIDR_VARIANT(midr)	\
 	(((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT)
 #define MIDR_IMPLEMENTOR_SHIFT	24
-#define MIDR_IMPLEMENTOR_MASK	(0xff << MIDR_IMPLEMENTOR_SHIFT)
+#define MIDR_IMPLEMENTOR_MASK	(0xffU << MIDR_IMPLEMENTOR_SHIFT)
 #define MIDR_IMPLEMENTOR(midr)	\
 	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
 
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 00c291067e57..7b7e05c02691 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -64,7 +64,7 @@ struct task_struct;
 
 struct step_hook {
 	struct list_head node;
-	int (*fn)(struct pt_regs *regs, unsigned int esr);
+	int (*fn)(struct pt_regs *regs, unsigned long esr);
 };
 
 void register_user_step_hook(struct step_hook *hook);
@@ -75,7 +75,7 @@ void unregister_kernel_step_hook(struct step_hook *hook);
 
 struct break_hook {
 	struct list_head node;
-	int (*fn)(struct pt_regs *regs, unsigned int esr);
+	int (*fn)(struct pt_regs *regs, unsigned long esr);
 	u16 imm;
 	u16 mask; /* These bits are ignored when comparing with imm */
 };
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index c31be7eda9df..34ceff08cac4 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -143,6 +143,50 @@
 .Lskip_sve_\@:
 .endm
 
+/* SME register access and priority mapping */
+.macro __init_el2_nvhe_sme
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_SME_SHIFT, #4
+	cbz	x1, .Lskip_sme_\@
+
+	bic	x0, x0, #CPTR_EL2_TSM		// Also disable SME traps
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+	isb
+
+	mrs	x1, sctlr_el2
+	orr	x1, x1, #SCTLR_ELx_ENTP2	// Disable TPIDR2 traps
+	msr	sctlr_el2, x1
+	isb
+
+	mov	x1, #0				// SMCR controls
+
+	mrs_s	x2, SYS_ID_AA64SMFR0_EL1
+	ubfx	x2, x2, #ID_AA64SMFR0_FA64_SHIFT, #1 // Full FP in SM?
+	cbz	x2, .Lskip_sme_fa64_\@
+
+	orr	x1, x1, SMCR_ELx_FA64_MASK
+.Lskip_sme_fa64_\@:
+
+	orr	x1, x1, #SMCR_ELx_LEN_MASK	// Enable full SME vector
+	msr_s	SYS_SMCR_EL2, x1		// length for EL1.
+
+	mrs_s	x1, SYS_SMIDR_EL1		// Priority mapping supported?
+	ubfx    x1, x1, #SMIDR_EL1_SMPS_SHIFT, #1
+	cbz     x1, .Lskip_sme_\@
+
+	msr_s	SYS_SMPRIMAP_EL2, xzr		// Make all priorities equal
+
+	mrs	x1, id_aa64mmfr1_el1		// HCRX_EL2 present?
+	ubfx	x1, x1, #ID_AA64MMFR1_HCX_SHIFT, #4
+	cbz	x1, .Lskip_sme_\@
+
+	mrs_s	x1, SYS_HCRX_EL2
+	orr	x1, x1, #HCRX_EL2_SMPME_MASK	// Enable priority mapping
+	msr_s	SYS_HCRX_EL2, x1
+
+.Lskip_sme_\@:
+.endm
+
 /* Disable any fine grained traps */
 .macro __init_el2_fgt
 	mrs	x1, id_aa64mmfr0_el1
@@ -153,15 +197,26 @@
 	mrs	x1, id_aa64dfr0_el1
 	ubfx	x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
 	cmp	x1, #3
-	b.lt	.Lset_fgt_\@
+	b.lt	.Lset_debug_fgt_\@
 	/* Disable PMSNEVFR_EL1 read and write traps */
 	orr	x0, x0, #(1 << 62)
 
-.Lset_fgt_\@:
+.Lset_debug_fgt_\@:
 	msr_s	SYS_HDFGRTR_EL2, x0
 	msr_s	SYS_HDFGWTR_EL2, x0
-	msr_s	SYS_HFGRTR_EL2, xzr
-	msr_s	SYS_HFGWTR_EL2, xzr
+
+	mov	x0, xzr
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_SME_SHIFT, #4
+	cbz	x1, .Lset_fgt_\@
+
+	/* Disable nVHE traps of TPIDR2 and SMPRI */
+	orr	x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK
+	orr	x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK
+
+.Lset_fgt_\@:
+	msr_s	SYS_HFGRTR_EL2, x0
+	msr_s	SYS_HFGWTR_EL2, x0
 	msr_s	SYS_HFGITR_EL2, xzr
 
 	mrs	x1, id_aa64pfr0_el1		// AMU traps UNDEF without AMU
@@ -196,6 +251,7 @@
 	__init_el2_nvhe_idregs
 	__init_el2_nvhe_cptr
 	__init_el2_nvhe_sve
+	__init_el2_nvhe_sme
 	__init_el2_fgt
 	__init_el2_nvhe_prepare_eret
 .endm
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index d52a0b269ee8..8f236de7359c 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -37,7 +37,8 @@
 #define ESR_ELx_EC_ERET		(0x1a)	/* EL2 only */
 /* Unallocated EC: 0x1B */
 #define ESR_ELx_EC_FPAC		(0x1C)	/* EL1 and above */
-/* Unallocated EC: 0x1D - 0x1E */
+#define ESR_ELx_EC_SME		(0x1D)
+/* Unallocated EC: 0x1E */
 #define ESR_ELx_EC_IMP_DEF	(0x1f)	/* EL3 only */
 #define ESR_ELx_EC_IABT_LOW	(0x20)
 #define ESR_ELx_EC_IABT_CUR	(0x21)
@@ -75,6 +76,7 @@
 #define ESR_ELx_IL_SHIFT	(25)
 #define ESR_ELx_IL		(UL(1) << ESR_ELx_IL_SHIFT)
 #define ESR_ELx_ISS_MASK	(ESR_ELx_IL - 1)
+#define ESR_ELx_ISS(esr)	((esr) & ESR_ELx_ISS_MASK)
 
 /* ISS field definitions shared by different classes */
 #define ESR_ELx_WNR_SHIFT	(6)
@@ -136,7 +138,7 @@
 #define ESR_ELx_WFx_ISS_TI	(UL(1) << 0)
 #define ESR_ELx_WFx_ISS_WFI	(UL(0) << 0)
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
-#define ESR_ELx_xVC_IMM_MASK	((1UL << 16) - 1)
+#define ESR_ELx_xVC_IMM_MASK	((UL(1) << 16) - 1)
 
 #define DISR_EL1_IDS		(UL(1) << 24)
 /*
@@ -327,17 +329,26 @@
 #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ	(ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\
 					 ESR_ELx_CP15_32_ISS_DIR_READ)
 
+/*
+ * ISS values for SME traps
+ */
+
+#define ESR_ELx_SME_ISS_SME_DISABLED	0
+#define ESR_ELx_SME_ISS_ILL		1
+#define ESR_ELx_SME_ISS_SM_DISABLED	2
+#define ESR_ELx_SME_ISS_ZA_DISABLED	3
+
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 
-static inline bool esr_is_data_abort(u32 esr)
+static inline bool esr_is_data_abort(unsigned long esr)
 {
-	const u32 ec = ESR_ELx_EC(esr);
+	const unsigned long ec = ESR_ELx_EC(esr);
 
 	return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
 }
 
-const char *esr_get_class_string(u32 esr);
+const char *esr_get_class_string(unsigned long esr);
 #endif /* __ASSEMBLY */
 
 #endif /* __ASM_ESR_H */
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 339477dca551..d94aecff9690 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -19,9 +19,9 @@
 #define __exception_irq_entry	__kprobes
 #endif
 
-static inline u32 disr_to_esr(u64 disr)
+static inline unsigned long disr_to_esr(u64 disr)
 {
-	unsigned int esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT;
+	unsigned long esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT;
 
 	if ((disr & DISR_EL1_IDS) == 0)
 		esr |= (disr & DISR_EL1_ESR_MASK);
@@ -57,23 +57,24 @@ asmlinkage void call_on_irq_stack(struct pt_regs *regs,
 				  void (*func)(struct pt_regs *));
 asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs);
 
-void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs);
+void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs);
 void do_undefinstr(struct pt_regs *regs);
 void do_bti(struct pt_regs *regs);
-void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
+void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr,
 			struct pt_regs *regs);
-void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs);
-void do_sve_acc(unsigned int esr, struct pt_regs *regs);
-void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs);
-void do_sysinstr(unsigned int esr, struct pt_regs *regs);
-void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
-void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr);
-void do_cp15instr(unsigned int esr, struct pt_regs *regs);
+void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs);
+void do_sve_acc(unsigned long esr, struct pt_regs *regs);
+void do_sme_acc(unsigned long esr, struct pt_regs *regs);
+void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs);
+void do_sysinstr(unsigned long esr, struct pt_regs *regs);
+void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs);
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr);
+void do_cp15instr(unsigned long esr, struct pt_regs *regs);
 void do_el0_svc(struct pt_regs *regs);
 void do_el0_svc_compat(struct pt_regs *regs);
-void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr);
-void do_serror(struct pt_regs *regs, unsigned int esr);
+void do_ptrauth_fault(struct pt_regs *regs, unsigned long esr);
+void do_serror(struct pt_regs *regs, unsigned long esr);
 void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags);
 
-void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far);
+void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far);
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index cb24385e3632..9bb1873f5295 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -32,6 +32,18 @@
 #define VFP_STATE_SIZE		((32 * 8) + 4)
 #endif
 
+/*
+ * When we defined the maximum SVE vector length we defined the ABI so
+ * that the maximum vector length included all the reserved for future
+ * expansion bits in ZCR rather than those just currently defined by
+ * the architecture. While SME follows a similar pattern the fact that
+ * it includes a square matrix means that any allocations that attempt
+ * to cover the maximum potential vector length (such as happen with
+ * the regset used for ptrace) end up being extremely large. Define
+ * the much lower actual limit for use in such situations.
+ */
+#define SME_VQ_MAX	16
+
 struct task_struct;
 
 extern void fpsimd_save_state(struct user_fpsimd_state *state);
@@ -46,11 +58,23 @@ extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
-				     void *sve_state, unsigned int sve_vl);
+				     void *sve_state, unsigned int sve_vl,
+				     void *za_state, unsigned int sme_vl,
+				     u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SVCR_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK);
+}
+
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
 #define VL_ARCH_MAX 0x100
 
@@ -62,7 +86,14 @@ static inline size_t sve_ffr_offset(int vl)
 
 static inline void *sve_pffr(struct thread_struct *thread)
 {
-	return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread));
+	unsigned int vl;
+
+	if (system_supports_sme() && thread_sm_enabled(thread))
+		vl = thread_get_sme_vl(thread);
+	else
+		vl = thread_get_sve_vl(thread);
+
+	return (char *)thread->sve_state + sve_ffr_offset(vl);
 }
 
 extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
@@ -71,11 +102,17 @@ extern void sve_load_state(void const *state, u32 const *pfpsr,
 extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
 extern unsigned int sve_get_vl(void);
 extern void sve_set_vq(unsigned long vq_minus_1);
+extern void sme_set_vq(unsigned long vq_minus_1);
+extern void za_save_state(void *state);
+extern void za_load_state(void const *state);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 
 extern u64 read_zcr_features(void);
+extern u64 read_smcr_features(void);
 
 /*
  * Helpers to translate bit indices in sve_vq_map to VQ values (and
@@ -119,6 +156,7 @@ struct vl_info {
 extern void sve_alloc(struct task_struct *task);
 extern void fpsimd_release_task(struct task_struct *task);
 extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void fpsimd_force_sync_to_sve(struct task_struct *task);
 extern void sve_sync_to_fpsimd(struct task_struct *task);
 extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
 
@@ -171,6 +209,12 @@ static inline void write_vl(enum vec_type type, u64 val)
 		write_sysreg_s(tmp | val, SYS_ZCR_EL1);
 		break;
 #endif
+#ifdef CONFIG_ARM64_SME
+	case ARM64_VEC_SME:
+		tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK;
+		write_sysreg_s(tmp | val, SYS_SMCR_EL1);
+		break;
+#endif
 	default:
 		WARN_ON_ONCE(1);
 		break;
@@ -208,6 +252,8 @@ static inline bool sve_vq_available(unsigned int vq)
 	return vq_available(ARM64_VEC_SVE, vq);
 }
 
+size_t sve_state_size(struct task_struct const *task);
+
 #else /* ! CONFIG_ARM64_SVE */
 
 static inline void sve_alloc(struct task_struct *task) { }
@@ -247,8 +293,93 @@ static inline void vec_update_vq_map(enum vec_type t) { }
 static inline int vec_verify_vq_map(enum vec_type t) { return 0; }
 static inline void sve_setup(void) { }
 
+static inline size_t sve_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
 #endif /* ! CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static inline void sme_user_disable(void)
+{
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0);
+}
+
+static inline void sme_user_enable(void)
+{
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN);
+}
+
+static inline void sme_smstart_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr"));
+}
+
+extern void __init sme_setup(void);
+
+static inline int sme_max_vl(void)
+{
+	return vec_max_vl(ARM64_VEC_SME);
+}
+
+static inline int sme_max_virtualisable_vl(void)
+{
+	return vec_max_virtualisable_vl(ARM64_VEC_SME);
+}
+
+extern void sme_alloc(struct task_struct *task);
+extern unsigned int sme_get_vl(void);
+extern int sme_set_current_vl(unsigned long arg);
+extern int sme_get_current_vl(void);
+
+/*
+ * Return how many bytes of memory are required to store the full SME
+ * specific state (currently just ZA) for task, given task's currently
+ * configured vector length.
+ */
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	unsigned int vl = task_get_sme_vl(task);
+
+	return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+}
+
+#else
+
+static inline void sme_user_disable(void) { BUILD_BUG(); }
+static inline void sme_user_enable(void) { BUILD_BUG(); }
+
+static inline void sme_smstart_sm(void) { }
+static inline void sme_smstop_sm(void) { }
+static inline void sme_smstop(void) { }
+
+static inline void sme_alloc(struct task_struct *task) { }
+static inline void sme_setup(void) { }
+static inline unsigned int sme_get_vl(void) { return 0; }
+static inline int sme_max_vl(void) { return 0; }
+static inline int sme_max_virtualisable_vl(void) { return 0; }
+static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
+static inline int sme_get_current_vl(void) { return -EINVAL; }
+
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
+#endif /* ! CONFIG_ARM64_SME */
+
 /* For use by EFI runtime services calls only */
 extern void __efi_fpsimd_begin(void);
 extern void __efi_fpsimd_end(void);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 2509d7dde55a..5e0910cf4832 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -93,6 +93,12 @@
 	.endif
 .endm
 
+.macro _sme_check_wv v
+	.if (\v) < 12 || (\v) > 15
+		.error "Bad vector select register \v."
+	.endif
+.endm
+
 /* SVE instruction encodings for non-SVE-capable assemblers */
 /* (pre binutils 2.28, all kernel capable clang versions support SVE) */
 
@@ -174,6 +180,54 @@
 		| (\np)
 .endm
 
+/* SME instruction encodings for non-SME-capable assemblers */
+/* (pre binutils 2.38/LLVM 13) */
+
+/* RDSVL X\nx, #\imm */
+.macro _sme_rdsvl nx, imm
+	_check_general_reg \nx
+	_check_num (\imm), -0x20, 0x1f
+	.inst	0x04bf5800			\
+		| (\nx)				\
+		| (((\imm) & 0x3f) << 5)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ *	STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _sme_str_zav nw, nxbase, offset=0
+	_sme_check_wv \nw
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe1200000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * LDR (vector to ZA array):
+ *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _sme_ldr_zav nw, nxbase, offset=0
+	_sme_check_wv \nw
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe1000000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * Zero the entire ZA array
+ *	ZERO ZA
+ */
+.macro zero_za
+	.inst 0xc00800ff
+.endm
+
 .macro __for from:req, to:req
 	.if (\from) == (\to)
 		_for__body %\from
@@ -208,6 +262,17 @@
 921:
 .endm
 
+/* Update SMCR_EL1.LEN with the new VQ */
+.macro sme_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_SMCR_EL1
+		bic		\xtmp2, \xtmp, SMCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_SMCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
 /* Preserve the first 128-bits of Znz and zero the rest. */
 .macro _sve_flush_z nz
 	_sve_check_zreg \nz
@@ -254,3 +319,25 @@
 		ldr		w\nxtmp, [\xpfpsr, #4]
 		msr		fpcr, x\nxtmp
 .endm
+
+.macro sme_save_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_str_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
+
+.macro sme_load_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_ldr_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index 1494cfa8639b..dbc45a4157fa 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -80,8 +80,15 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 struct dyn_ftrace;
+struct ftrace_ops;
+struct ftrace_regs;
+
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
+
+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
 #endif
 
 #define ftrace_return_address(n) return_address(n)
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 1242f71937f8..d656822b13f1 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -44,6 +44,8 @@ extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, unsigned long sz);
+#define __HAVE_ARCH_HUGE_PTEP_GET
+extern pte_t huge_ptep_get(pte_t *ptep);
 extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, unsigned long sz);
 #define set_huge_swap_pte_at set_huge_swap_pte_at
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 8db5ec0089db..9f0ce004fdbc 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -109,6 +109,14 @@
 #define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
 #define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)
 #define KERNEL_HWCAP_MTE3		__khwcap2_feature(MTE3)
+#define KERNEL_HWCAP_SME		__khwcap2_feature(SME)
+#define KERNEL_HWCAP_SME_I16I64		__khwcap2_feature(SME_I16I64)
+#define KERNEL_HWCAP_SME_F64F64		__khwcap2_feature(SME_F64F64)
+#define KERNEL_HWCAP_SME_I8I32		__khwcap2_feature(SME_I8I32)
+#define KERNEL_HWCAP_SME_F16F32		__khwcap2_feature(SME_F16F32)
+#define KERNEL_HWCAP_SME_B16F32		__khwcap2_feature(SME_B16F32)
+#define KERNEL_HWCAP_SME_F32F32		__khwcap2_feature(SME_F32F32)
+#define KERNEL_HWCAP_SME_FA64		__khwcap2_feature(SME_FA64)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 1767ded83888..13ae232ec4a1 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -279,6 +279,7 @@
 #define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
+#define CPTR_EL2_TSM	(1 << 12)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
 #define CPTR_NVHE_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index f71358271b71..08233172e7a9 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -236,14 +236,14 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 	return mode != PSR_MODE_EL0t;
 }
 
-static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
+static __always_inline u64 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault.esr_el2;
 }
 
 static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_esr(vcpu);
+	u64 esr = kvm_vcpu_get_esr(vcpu);
 
 	if (esr & ESR_ELx_CV)
 		return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
@@ -374,7 +374,7 @@ static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 
 static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_esr(vcpu);
+	u64 esr = kvm_vcpu_get_esr(vcpu);
 	return ESR_ELx_SYS64_ISS_RT(esr);
 }
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 94a27a7520f4..d5888dedf02a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -153,7 +153,7 @@ struct kvm_arch {
 };
 
 struct kvm_vcpu_fault_info {
-	u32 esr_el2;		/* Hyp Syndrom Register */
+	u64 esr_el2;		/* Hyp Syndrom Register */
 	u64 far_el2;		/* Hyp Fault Address Register */
 	u64 hpfar_el2;		/* Hyp IPA Fault Address Register */
 	u64 disr_el1;		/* Deferred [SError] Status Register */
@@ -295,8 +295,11 @@ struct vcpu_reset_state {
 
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
+
+	/* Guest floating point state */
 	void *sve_state;
 	unsigned int sve_max_vl;
+	u64 svcr;
 
 	/* Stage 2 paging state used by the hardware on next switch */
 	struct kvm_s2_mmu *hw_mmu;
@@ -451,6 +454,7 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE	(1 << 13) /* Save TRBE context if active  */
 #define KVM_ARM64_FP_FOREIGN_FPSTATE	(1 << 14)
 #define KVM_ARM64_ON_UNSUPPORTED_CPU	(1 << 15) /* Physical CPU not in supported_cpus */
+#define KVM_ARM64_HOST_SME_ENABLED	(1 << 16) /* SME enabled for EL0 */
 
 #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
 				 KVM_GUESTDBG_USE_SW_BP | \
diff --git a/arch/arm64/include/asm/kvm_ras.h b/arch/arm64/include/asm/kvm_ras.h
index 8ac6ee77437c..87e10d9a635b 100644
--- a/arch/arm64/include/asm/kvm_ras.h
+++ b/arch/arm64/include/asm/kvm_ras.h
@@ -14,7 +14,7 @@
  * Was this synchronous external abort a RAS notification?
  * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
  */
-static inline int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr)
+static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr)
 {
 	/* apei_claim_sea(NULL) expects to mask interrupts itself */
 	lockdep_assert_irqs_enabled();
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index adcb937342f1..aa523591a44e 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -47,6 +47,7 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg);
 long get_mte_ctrl(struct task_struct *task);
 int mte_ptrace_copy_tags(struct task_struct *child, long request,
 			 unsigned long addr, unsigned long data);
+size_t mte_probe_user_range(const char __user *uaddr, size_t size);
 
 #else /* CONFIG_ARM64_MTE */
 
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 66671ff05183..dd3d12bce07b 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -49,7 +49,7 @@
 #define PMD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
 #define PMD_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_MASK		(~(PMD_SIZE-1))
-#define PTRS_PER_PMD		PTRS_PER_PTE
+#define PTRS_PER_PMD		(1 << (PAGE_SHIFT - 3))
 #endif
 
 /*
@@ -59,7 +59,7 @@
 #define PUD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
 #define PUD_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_MASK		(~(PUD_SIZE-1))
-#define PTRS_PER_PUD		PTRS_PER_PTE
+#define PTRS_PER_PUD		(1 << (PAGE_SHIFT - 3))
 #endif
 
 /*
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index dff2b483ea50..45c358538f13 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1001,7 +1001,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
  */
 static inline bool arch_faults_on_old_pte(void)
 {
-	WARN_ON(preemptible());
+	/* The register read below requires a stable CPU to make any sense */
+	cant_migrate();
 
 	return !cpu_has_hw_af();
 }
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 73e38d9a540c..8de5a4fc06e3 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -118,6 +118,7 @@ struct debug_info {
 
 enum vec_type {
 	ARM64_VEC_SVE = 0,
+	ARM64_VEC_SME,
 	ARM64_VEC_MAX,
 };
 
@@ -153,6 +154,7 @@ struct thread_struct {
 
 	unsigned int		fpsimd_cpu;
 	void			*sve_state;	/* SVE registers, if any */
+	void			*za_state;	/* ZA register, if any */
 	unsigned int		vl[ARM64_VEC_MAX];	/* vector length */
 	unsigned int		vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */
 	unsigned long		fault_address;	/* fault info */
@@ -168,6 +170,8 @@ struct thread_struct {
 	u64			mte_ctrl;
 #endif
 	u64			sctlr_user;
+	u64			svcr;
+	u64			tpidr2_el0;
 };
 
 static inline unsigned int thread_get_vl(struct thread_struct *thread,
@@ -181,6 +185,19 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread)
 	return thread_get_vl(thread, ARM64_VEC_SVE);
 }
 
+static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
+{
+	return thread_get_vl(thread, ARM64_VEC_SME);
+}
+
+static inline unsigned int thread_get_cur_vl(struct thread_struct *thread)
+{
+	if (system_supports_sme() && (thread->svcr & SVCR_SM_MASK))
+		return thread_get_sme_vl(thread);
+	else
+		return thread_get_sve_vl(thread);
+}
+
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type);
 void task_set_vl(struct task_struct *task, enum vec_type type,
 		 unsigned long vl);
@@ -194,6 +211,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task)
 	return task_get_vl(task, ARM64_VEC_SVE);
 }
 
+static inline unsigned int task_get_sme_vl(const struct task_struct *task)
+{
+	return task_get_vl(task, ARM64_VEC_SME);
+}
+
 static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl)
 {
 	task_set_vl(task, ARM64_VEC_SVE, vl);
@@ -354,9 +376,11 @@ extern void __init minsigstksz_setup(void);
  */
 #include <asm/fpsimd.h>
 
-/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
+/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */
 #define SVE_SET_VL(arg)	sve_set_current_vl(arg)
 #define SVE_GET_VL()	sve_get_current_vl()
+#define SME_SET_VL(arg)	sme_set_current_vl(arg)
+#define SME_GET_VL()	sme_get_current_vl()
 
 /* PR_PAC_RESET_KEYS prctl */
 #define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index e77cdef9ca29..aec9315bf156 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -31,38 +31,6 @@ struct stack_info {
 	enum stack_type type;
 };
 
-/*
- * A snapshot of a frame record or fp/lr register values, along with some
- * accounting information necessary for robust unwinding.
- *
- * @fp:          The fp value in the frame record (or the real fp)
- * @pc:          The lr value in the frame record (or the real lr)
- *
- * @stacks_done: Stacks which have been entirely unwound, for which it is no
- *               longer valid to unwind to.
- *
- * @prev_fp:     The fp that pointed to this frame record, or a synthetic value
- *               of 0. This is used to ensure that within a stack, each
- *               subsequent frame record is at an increasing address.
- * @prev_type:   The type of stack this frame record was on, or a synthetic
- *               value of STACK_TYPE_UNKNOWN. This is used to detect a
- *               transition from one stack to another.
- *
- * @kr_cur:      When KRETPROBES is selected, holds the kretprobe instance
- *               associated with the most recently encountered replacement lr
- *               value.
- */
-struct stackframe {
-	unsigned long fp;
-	unsigned long pc;
-	DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES);
-	unsigned long prev_fp;
-	enum stack_type prev_type;
-#ifdef CONFIG_KRETPROBES
-	struct llist_node *kr_cur;
-#endif
-};
-
 extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
 			   const char *loglvl);
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index fbf5f8bb9055..55f998c3dc28 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -115,9 +115,21 @@
 #define SYS_DC_CISW			sys_insn(1, 0, 7, 14, 2)
 
 /*
+ * Automatically generated definitions for system registers, the
+ * manual encodings below are in the process of being converted to
+ * come from here. The header relies on the definition of sys_reg()
+ * earlier in this file.
+ */
+#include "asm/sysreg-defs.h"
+
+/*
  * System registers, organised loosely by encoding but grouped together
  * where the architected name contains an index. e.g. ID_MMFR<n>_EL1.
  */
+#define SYS_SVCR_SMSTOP_SM_EL0		sys_reg(0, 3, 4, 2, 3)
+#define SYS_SVCR_SMSTART_SM_EL0		sys_reg(0, 3, 4, 3, 3)
+#define SYS_SVCR_SMSTOP_SMZA_EL0	sys_reg(0, 3, 4, 6, 3)
+
 #define SYS_OSDTRRX_EL1			sys_reg(2, 0, 0, 0, 2)
 #define SYS_MDCCINT_EL1			sys_reg(2, 0, 0, 2, 0)
 #define SYS_MDSCR_EL1			sys_reg(2, 0, 0, 2, 2)
@@ -181,6 +193,7 @@
 #define SYS_ID_AA64PFR0_EL1		sys_reg(3, 0, 0, 4, 0)
 #define SYS_ID_AA64PFR1_EL1		sys_reg(3, 0, 0, 4, 1)
 #define SYS_ID_AA64ZFR0_EL1		sys_reg(3, 0, 0, 4, 4)
+#define SYS_ID_AA64SMFR0_EL1		sys_reg(3, 0, 0, 4, 5)
 
 #define SYS_ID_AA64DFR0_EL1		sys_reg(3, 0, 0, 5, 0)
 #define SYS_ID_AA64DFR1_EL1		sys_reg(3, 0, 0, 5, 1)
@@ -188,7 +201,6 @@
 #define SYS_ID_AA64AFR0_EL1		sys_reg(3, 0, 0, 5, 4)
 #define SYS_ID_AA64AFR1_EL1		sys_reg(3, 0, 0, 5, 5)
 
-#define SYS_ID_AA64ISAR0_EL1		sys_reg(3, 0, 0, 6, 0)
 #define SYS_ID_AA64ISAR1_EL1		sys_reg(3, 0, 0, 6, 1)
 #define SYS_ID_AA64ISAR2_EL1		sys_reg(3, 0, 0, 6, 2)
 
@@ -196,17 +208,12 @@
 #define SYS_ID_AA64MMFR1_EL1		sys_reg(3, 0, 0, 7, 1)
 #define SYS_ID_AA64MMFR2_EL1		sys_reg(3, 0, 0, 7, 2)
 
-#define SYS_SCTLR_EL1			sys_reg(3, 0, 1, 0, 0)
 #define SYS_ACTLR_EL1			sys_reg(3, 0, 1, 0, 1)
-#define SYS_CPACR_EL1			sys_reg(3, 0, 1, 0, 2)
 #define SYS_RGSR_EL1			sys_reg(3, 0, 1, 0, 5)
 #define SYS_GCR_EL1			sys_reg(3, 0, 1, 0, 6)
 
-#define SYS_ZCR_EL1			sys_reg(3, 0, 1, 2, 0)
 #define SYS_TRFCR_EL1			sys_reg(3, 0, 1, 2, 1)
 
-#define SYS_TTBR0_EL1			sys_reg(3, 0, 2, 0, 0)
-#define SYS_TTBR1_EL1			sys_reg(3, 0, 2, 0, 1)
 #define SYS_TCR_EL1			sys_reg(3, 0, 2, 0, 2)
 
 #define SYS_APIAKEYLO_EL1		sys_reg(3, 0, 2, 1, 0)
@@ -242,7 +249,6 @@
 #define SYS_TFSR_EL1			sys_reg(3, 0, 5, 6, 0)
 #define SYS_TFSRE0_EL1			sys_reg(3, 0, 5, 6, 1)
 
-#define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
 #define SYS_PAR_EL1_F			BIT(0)
@@ -441,7 +447,6 @@
 #define SYS_ICC_IGRPEN0_EL1		sys_reg(3, 0, 12, 12, 6)
 #define SYS_ICC_IGRPEN1_EL1		sys_reg(3, 0, 12, 12, 7)
 
-#define SYS_CONTEXTIDR_EL1		sys_reg(3, 0, 13, 0, 1)
 #define SYS_TPIDR_EL1			sys_reg(3, 0, 13, 0, 4)
 
 #define SYS_SCXTNUM_EL1			sys_reg(3, 0, 13, 0, 7)
@@ -449,11 +454,12 @@
 #define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
 
 #define SYS_CCSIDR_EL1			sys_reg(3, 1, 0, 0, 0)
-#define SYS_CLIDR_EL1			sys_reg(3, 1, 0, 0, 1)
 #define SYS_GMID_EL1			sys_reg(3, 1, 0, 0, 4)
 #define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
 
-#define SYS_CSSELR_EL1			sys_reg(3, 2, 0, 0, 0)
+#define SMIDR_EL1_IMPLEMENTER_SHIFT	24
+#define SMIDR_EL1_SMPS_SHIFT	15
+#define SMIDR_EL1_AFFINITY_SHIFT	0
 
 #define SYS_CTR_EL0			sys_reg(3, 3, 0, 0, 1)
 #define SYS_DCZID_EL0			sys_reg(3, 3, 0, 0, 7)
@@ -477,6 +483,7 @@
 
 #define SYS_TPIDR_EL0			sys_reg(3, 3, 13, 0, 2)
 #define SYS_TPIDRRO_EL0			sys_reg(3, 3, 13, 0, 3)
+#define SYS_TPIDR2_EL0			sys_reg(3, 3, 13, 0, 5)
 
 #define SYS_SCXTNUM_EL0			sys_reg(3, 3, 13, 0, 7)
 
@@ -544,9 +551,8 @@
 #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_ZCR_EL2			sys_reg(3, 4, 1, 2, 0)
 #define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
-#define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
+#define SYS_HCRX_EL2			sys_reg(3, 4, 1, 2, 2)
 #define SYS_HDFGRTR_EL2			sys_reg(3, 4, 3, 1, 4)
 #define SYS_HDFGWTR_EL2			sys_reg(3, 4, 3, 1, 5)
 #define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
@@ -557,7 +563,6 @@
 #define SYS_VSESR_EL2			sys_reg(3, 4, 5, 2, 3)
 #define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
 #define SYS_TFSR_EL2			sys_reg(3, 4, 5, 6, 0)
-#define SYS_FAR_EL2			sys_reg(3, 4, 6, 0, 0)
 
 #define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1,  1)
 #define __SYS__AP0Rx_EL2(x)		sys_reg(3, 4, 12, 8, x)
@@ -603,8 +608,6 @@
 
 /* VHE encodings for architectural EL0/1 system registers */
 #define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
-#define SYS_CPACR_EL12			sys_reg(3, 5, 1, 0, 2)
-#define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
 #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
 #define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
 #define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
@@ -614,11 +617,9 @@
 #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
 #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
 #define SYS_TFSR_EL12			sys_reg(3, 5, 5, 6, 0)
-#define SYS_FAR_EL12			sys_reg(3, 5, 6, 0, 0)
 #define SYS_MAIR_EL12			sys_reg(3, 5, 10, 2, 0)
 #define SYS_AMAIR_EL12			sys_reg(3, 5, 10, 3, 0)
 #define SYS_VBAR_EL12			sys_reg(3, 5, 12, 0, 0)
-#define SYS_CONTEXTIDR_EL12		sys_reg(3, 5, 13, 0, 1)
 #define SYS_CNTKCTL_EL12		sys_reg(3, 5, 14, 1, 0)
 #define SYS_CNTP_TVAL_EL02		sys_reg(3, 5, 14, 2, 0)
 #define SYS_CNTP_CTL_EL02		sys_reg(3, 5, 14, 2, 1)
@@ -628,31 +629,30 @@
 #define SYS_CNTV_CVAL_EL02		sys_reg(3, 5, 14, 3, 2)
 
 /* Common SCTLR_ELx flags. */
+#define SCTLR_ELx_ENTP2	(BIT(60))
 #define SCTLR_ELx_DSSBS	(BIT(44))
 #define SCTLR_ELx_ATA	(BIT(43))
 
-#define SCTLR_ELx_TCF_SHIFT	40
-#define SCTLR_ELx_TCF_NONE	(UL(0x0) << SCTLR_ELx_TCF_SHIFT)
-#define SCTLR_ELx_TCF_SYNC	(UL(0x1) << SCTLR_ELx_TCF_SHIFT)
-#define SCTLR_ELx_TCF_ASYNC	(UL(0x2) << SCTLR_ELx_TCF_SHIFT)
-#define SCTLR_ELx_TCF_ASYMM	(UL(0x3) << SCTLR_ELx_TCF_SHIFT)
-#define SCTLR_ELx_TCF_MASK	(UL(0x3) << SCTLR_ELx_TCF_SHIFT)
-
 #define SCTLR_ELx_ENIA_SHIFT	31
 
-#define SCTLR_ELx_ITFSB	(BIT(37))
-#define SCTLR_ELx_ENIA	(BIT(SCTLR_ELx_ENIA_SHIFT))
-#define SCTLR_ELx_ENIB	(BIT(30))
-#define SCTLR_ELx_ENDA	(BIT(27))
-#define SCTLR_ELx_EE    (BIT(25))
-#define SCTLR_ELx_IESB	(BIT(21))
-#define SCTLR_ELx_WXN	(BIT(19))
-#define SCTLR_ELx_ENDB	(BIT(13))
-#define SCTLR_ELx_I	(BIT(12))
-#define SCTLR_ELx_SA	(BIT(3))
-#define SCTLR_ELx_C	(BIT(2))
-#define SCTLR_ELx_A	(BIT(1))
-#define SCTLR_ELx_M	(BIT(0))
+#define SCTLR_ELx_ITFSB	 (BIT(37))
+#define SCTLR_ELx_ENIA	 (BIT(SCTLR_ELx_ENIA_SHIFT))
+#define SCTLR_ELx_ENIB	 (BIT(30))
+#define SCTLR_ELx_LSMAOE (BIT(29))
+#define SCTLR_ELx_nTLSMD (BIT(28))
+#define SCTLR_ELx_ENDA	 (BIT(27))
+#define SCTLR_ELx_EE     (BIT(25))
+#define SCTLR_ELx_EIS	 (BIT(22))
+#define SCTLR_ELx_IESB	 (BIT(21))
+#define SCTLR_ELx_TSCXT	 (BIT(20))
+#define SCTLR_ELx_WXN	 (BIT(19))
+#define SCTLR_ELx_ENDB	 (BIT(13))
+#define SCTLR_ELx_I	 (BIT(12))
+#define SCTLR_ELx_EOS	 (BIT(11))
+#define SCTLR_ELx_SA	 (BIT(3))
+#define SCTLR_ELx_C	 (BIT(2))
+#define SCTLR_ELx_A	 (BIT(1))
+#define SCTLR_ELx_M	 (BIT(0))
 
 /* SCTLR_EL2 specific flags. */
 #define SCTLR_EL2_RES1	((BIT(4))  | (BIT(5))  | (BIT(11)) | (BIT(16)) | \
@@ -674,34 +674,6 @@
 	(SCTLR_EL2_RES1 | ENDIAN_SET_EL2)
 
 /* SCTLR_EL1 specific flags. */
-#define SCTLR_EL1_EPAN		(BIT(57))
-#define SCTLR_EL1_ATA0		(BIT(42))
-
-#define SCTLR_EL1_TCF0_SHIFT	38
-#define SCTLR_EL1_TCF0_NONE	(UL(0x0) << SCTLR_EL1_TCF0_SHIFT)
-#define SCTLR_EL1_TCF0_SYNC	(UL(0x1) << SCTLR_EL1_TCF0_SHIFT)
-#define SCTLR_EL1_TCF0_ASYNC	(UL(0x2) << SCTLR_EL1_TCF0_SHIFT)
-#define SCTLR_EL1_TCF0_ASYMM	(UL(0x3) << SCTLR_EL1_TCF0_SHIFT)
-#define SCTLR_EL1_TCF0_MASK	(UL(0x3) << SCTLR_EL1_TCF0_SHIFT)
-
-#define SCTLR_EL1_BT1		(BIT(36))
-#define SCTLR_EL1_BT0		(BIT(35))
-#define SCTLR_EL1_UCI		(BIT(26))
-#define SCTLR_EL1_E0E		(BIT(24))
-#define SCTLR_EL1_SPAN		(BIT(23))
-#define SCTLR_EL1_NTWE		(BIT(18))
-#define SCTLR_EL1_NTWI		(BIT(16))
-#define SCTLR_EL1_UCT		(BIT(15))
-#define SCTLR_EL1_DZE		(BIT(14))
-#define SCTLR_EL1_UMA		(BIT(9))
-#define SCTLR_EL1_SED		(BIT(8))
-#define SCTLR_EL1_ITD		(BIT(7))
-#define SCTLR_EL1_CP15BEN	(BIT(5))
-#define SCTLR_EL1_SA0		(BIT(4))
-
-#define SCTLR_EL1_RES1	((BIT(11)) | (BIT(20)) | (BIT(22)) | (BIT(28)) | \
-			 (BIT(29)))
-
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define ENDIAN_SET_EL1		(SCTLR_EL1_E0E | SCTLR_ELx_EE)
 #else
@@ -709,13 +681,17 @@
 #endif
 
 #define INIT_SCTLR_EL1_MMU_OFF \
-	(ENDIAN_SET_EL1 | SCTLR_EL1_RES1)
+	(ENDIAN_SET_EL1 | SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD | \
+	 SCTLR_EL1_EIS  | SCTLR_EL1_TSCXT  | SCTLR_EL1_EOS)
 
 #define INIT_SCTLR_EL1_MMU_ON \
-	(SCTLR_ELx_M    | SCTLR_ELx_C    | SCTLR_ELx_SA   | SCTLR_EL1_SA0   | \
-	 SCTLR_EL1_SED  | SCTLR_ELx_I    | SCTLR_EL1_DZE  | SCTLR_EL1_UCT   | \
-	 SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \
-	 ENDIAN_SET_EL1 | SCTLR_EL1_UCI  | SCTLR_EL1_EPAN | SCTLR_EL1_RES1)
+	(SCTLR_ELx_M      | SCTLR_ELx_C      | SCTLR_ELx_SA    | \
+	 SCTLR_EL1_SA0    | SCTLR_EL1_SED    | SCTLR_ELx_I     | \
+	 SCTLR_EL1_DZE    | SCTLR_EL1_UCT    | SCTLR_EL1_nTWE  | \
+	 SCTLR_ELx_IESB   | SCTLR_EL1_SPAN   | SCTLR_ELx_ITFSB | \
+	 ENDIAN_SET_EL1   | SCTLR_EL1_UCI    | SCTLR_EL1_EPAN  | \
+	 SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD | SCTLR_EL1_EIS   | \
+	 SCTLR_EL1_TSCXT  | SCTLR_EL1_EOS)
 
 /* MAIR_ELx memory attributes (used by Linux) */
 #define MAIR_ATTR_DEVICE_nGnRnE		UL(0x00)
@@ -728,25 +704,6 @@
 /* Position the attr at the correct index */
 #define MAIR_ATTRIDX(attr, idx)		((attr) << ((idx) * 8))
 
-/* id_aa64isar0 */
-#define ID_AA64ISAR0_RNDR_SHIFT		60
-#define ID_AA64ISAR0_TLB_SHIFT		56
-#define ID_AA64ISAR0_TS_SHIFT		52
-#define ID_AA64ISAR0_FHM_SHIFT		48
-#define ID_AA64ISAR0_DP_SHIFT		44
-#define ID_AA64ISAR0_SM4_SHIFT		40
-#define ID_AA64ISAR0_SM3_SHIFT		36
-#define ID_AA64ISAR0_SHA3_SHIFT		32
-#define ID_AA64ISAR0_RDM_SHIFT		28
-#define ID_AA64ISAR0_ATOMICS_SHIFT	20
-#define ID_AA64ISAR0_CRC32_SHIFT	16
-#define ID_AA64ISAR0_SHA2_SHIFT		12
-#define ID_AA64ISAR0_SHA1_SHIFT		8
-#define ID_AA64ISAR0_AES_SHIFT		4
-
-#define ID_AA64ISAR0_TLB_RANGE_NI	0x0
-#define ID_AA64ISAR0_TLB_RANGE		0x2
-
 /* id_aa64isar1 */
 #define ID_AA64ISAR1_I8MM_SHIFT		52
 #define ID_AA64ISAR1_DGH_SHIFT		48
@@ -836,6 +793,7 @@
 #define ID_AA64PFR0_ELx_32BIT_64BIT	0x2
 
 /* id_aa64pfr1 */
+#define ID_AA64PFR1_SME_SHIFT		24
 #define ID_AA64PFR1_MPAMFRAC_SHIFT	16
 #define ID_AA64PFR1_RASFRAC_SHIFT	12
 #define ID_AA64PFR1_MTE_SHIFT		8
@@ -846,6 +804,7 @@
 #define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 #define ID_AA64PFR1_BT_BTI		0x1
+#define ID_AA64PFR1_SME			1
 
 #define ID_AA64PFR1_MTE_NI		0x0
 #define ID_AA64PFR1_MTE_EL0		0x1
@@ -874,6 +833,23 @@
 #define ID_AA64ZFR0_AES_PMULL		0x2
 #define ID_AA64ZFR0_SVEVER_SVE2		0x1
 
+/* id_aa64smfr0 */
+#define ID_AA64SMFR0_FA64_SHIFT		63
+#define ID_AA64SMFR0_I16I64_SHIFT	52
+#define ID_AA64SMFR0_F64F64_SHIFT	48
+#define ID_AA64SMFR0_I8I32_SHIFT	36
+#define ID_AA64SMFR0_F16F32_SHIFT	35
+#define ID_AA64SMFR0_B16F32_SHIFT	34
+#define ID_AA64SMFR0_F32F32_SHIFT	32
+
+#define ID_AA64SMFR0_FA64		0x1
+#define ID_AA64SMFR0_I16I64		0x4
+#define ID_AA64SMFR0_F64F64		0x1
+#define ID_AA64SMFR0_I8I32		0x4
+#define ID_AA64SMFR0_F16F32		0x1
+#define ID_AA64SMFR0_B16F32		0x1
+#define ID_AA64SMFR0_F32F32		0x1
+
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_ECV_SHIFT		60
 #define ID_AA64MMFR0_FGT_SHIFT		56
@@ -926,6 +902,7 @@
 
 /* id_aa64mmfr1 */
 #define ID_AA64MMFR1_ECBHB_SHIFT	60
+#define ID_AA64MMFR1_HCX_SHIFT		40
 #define ID_AA64MMFR1_AFP_SHIFT		44
 #define ID_AA64MMFR1_ETS_SHIFT		36
 #define ID_AA64MMFR1_TWED_SHIFT		32
@@ -1110,18 +1087,12 @@
 #define DCZID_DZP_SHIFT			4
 #define DCZID_BS_SHIFT			0
 
-/*
- * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which
- * are reserved by the SVE architecture for future expansion of the LEN
- * field, with compatible semantics.
- */
-#define ZCR_ELx_LEN_SHIFT	0
-#define ZCR_ELx_LEN_SIZE	9
-#define ZCR_ELx_LEN_MASK	0x1ff
-
 #define CPACR_EL1_FPEN_EL1EN	(BIT(20)) /* enable EL1 access */
 #define CPACR_EL1_FPEN_EL0EN	(BIT(21)) /* enable EL0 access, if EL1EN set */
 
+#define CPACR_EL1_SMEN_EL1EN	(BIT(24)) /* enable EL1 access */
+#define CPACR_EL1_SMEN_EL0EN	(BIT(25)) /* enable EL0 access, if EL1EN set */
+
 #define CPACR_EL1_ZEN_EL1EN	(BIT(16)) /* enable EL1 access */
 #define CPACR_EL1_ZEN_EL0EN	(BIT(17)) /* enable EL0 access, if EL1EN set */
 
@@ -1170,6 +1141,8 @@
 #define TRFCR_ELx_ExTRE			BIT(1)
 #define TRFCR_ELx_E0TRE			BIT(0)
 
+/* HCRX_EL2 definitions */
+#define HCRX_EL2_SMPME_MASK		(1 << 5)
 
 /* GIC Hypervisor interface registers */
 /* ICH_MISR_EL2 bit definitions */
@@ -1233,6 +1206,12 @@
 #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
 
 /* Create a mask for the feature bits of the specified feature. */
@@ -1345,4 +1324,10 @@
 
 #endif
 
+#define SYS_FIELD_PREP(reg, field, val)		\
+		 FIELD_PREP(reg##_##field##_MASK, val)
+
+#define SYS_FIELD_PREP_ENUM(reg, field, val)		\
+		 FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val)
+
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 305a7157c6a6..0eb7709422e2 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -23,9 +23,9 @@ void die(const char *msg, struct pt_regs *regs, int err);
 struct siginfo;
 void arm64_notify_die(const char *str, struct pt_regs *regs,
 		      int signo, int sicode, unsigned long far,
-		      int err);
+		      unsigned long err);
 
-void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
+void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned long,
 					     struct pt_regs *),
 			   int sig, int code, const char *name);
 
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index e1317b7c4525..848739c15de8 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -82,6 +82,8 @@ int arch_dup_task_struct(struct task_struct *dst,
 #define TIF_SVE_VL_INHERIT	24	/* Inherit SVE vl_onexec across exec */
 #define TIF_SSBD		25	/* Wants SSB mitigation */
 #define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
+#define TIF_SME			27	/* SME in use */
+#define TIF_SME_VL_INHERIT	28	/* Inherit SME vl_onexec across exec */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 54f32a0675df..6e5826470bea 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -24,7 +24,7 @@ struct undef_hook {
 
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
-void force_signal_inject(int signal, int code, unsigned long address, unsigned int err);
+void force_signal_inject(int signal, int code, unsigned long address, unsigned long err);
 void arm64_notify_segfault(unsigned long addr);
 void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str);
 void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str);
@@ -57,7 +57,7 @@ static inline int in_entry_text(unsigned long ptr)
  * errors share the same encoding as an all-zeros encoding from a CPU that
  * doesn't support RAS.
  */
-static inline bool arm64_is_ras_serror(u32 esr)
+static inline bool arm64_is_ras_serror(unsigned long esr)
 {
 	WARN_ON(preemptible());
 
@@ -77,9 +77,9 @@ static inline bool arm64_is_ras_serror(u32 esr)
  * We treat them as Uncontainable.
  * Non-RAS SError's are reported as Uncontained/Uncategorized.
  */
-static inline u32 arm64_ras_serror_get_severity(u32 esr)
+static inline unsigned long arm64_ras_serror_get_severity(unsigned long esr)
 {
-	u32 aet = esr & ESR_ELx_AET;
+	unsigned long aet = esr & ESR_ELx_AET;
 
 	if (!arm64_is_ras_serror(esr)) {
 		/* Not a RAS error, we can't interpret the ESR. */
@@ -98,6 +98,6 @@ static inline u32 arm64_ras_serror_get_severity(u32 esr)
 	return aet;
 }
 
-bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr);
-void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr);
+bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr);
+void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr);
 #endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index e8dce0cc5eaa..63f9c828f1a7 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -460,4 +460,19 @@ static inline int __copy_from_user_flushcache(void *dst, const void __user *src,
 }
 #endif
 
+#ifdef CONFIG_ARCH_HAS_SUBPAGE_FAULTS
+
+/*
+ * Return 0 on success, the number of bytes not probed otherwise.
+ */
+static inline size_t probe_subpage_writeable(const char __user *uaddr,
+					     size_t size)
+{
+	if (!system_supports_mte())
+		return 0;
+	return mte_probe_user_range(uaddr, size);
+}
+
+#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
+
 #endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 99cb5d383048..b0256cec63b5 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -79,5 +79,13 @@
 #define HWCAP2_AFP		(1 << 20)
 #define HWCAP2_RPRES		(1 << 21)
 #define HWCAP2_MTE3		(1 << 22)
+#define HWCAP2_SME		(1 << 23)
+#define HWCAP2_SME_I16I64	(1 << 24)
+#define HWCAP2_SME_F64F64	(1 << 25)
+#define HWCAP2_SME_I8I32	(1 << 26)
+#define HWCAP2_SME_F16F32	(1 << 27)
+#define HWCAP2_SME_B16F32	(1 << 28)
+#define HWCAP2_SME_F32F32	(1 << 29)
+#define HWCAP2_SME_FA64		(1 << 30)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index c1b6ddc02d2f..ab585359242d 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -139,8 +139,10 @@ struct kvm_guest_debug_arch {
 	__u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS];
 };
 
+#define KVM_DEBUG_ARCH_HSR_HIGH_VALID	(1 << 0)
 struct kvm_debug_exit_arch {
 	__u32 hsr;
+	__u32 hsr_high;	/* ESR_EL2[61:32] */
 	__u64 far;	/* used for watchpoints */
 };
 
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 758ae984ff97..7fa2f7036aa7 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -109,7 +109,7 @@ struct user_hwdebug_state {
 	}		dbg_regs[16];
 };
 
-/* SVE/FP/SIMD state (NT_ARM_SVE) */
+/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */
 
 struct user_sve_header {
 	__u32 size; /* total meaningful regset content in bytes */
@@ -220,6 +220,7 @@ struct user_sve_header {
 	(SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \
 		SVE_PT_SVE_PREGS_OFFSET(vq))
 
+/* For streaming mode SVE (SSVE) FFR must be read and written as zero */
 #define SVE_PT_SVE_FFR_OFFSET(vq) \
 	(SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq))
 
@@ -240,10 +241,12 @@ struct user_sve_header {
 			- SVE_PT_SVE_OFFSET + (__SVE_VQ_BYTES - 1))	\
 		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
 
-#define SVE_PT_SIZE(vq, flags)						\
-	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		\
-		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	\
-		: SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags))
+#define SVE_PT_SIZE(vq, flags)						  \
+	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		  \
+		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	  \
+		: ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ?  \
+		    SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \
+		  : SVE_PT_REGS_OFFSET)))
 
 /* pointer authentication masks (NT_ARM_PAC_MASK) */
 
@@ -265,6 +268,62 @@ struct user_pac_generic_keys {
 	__uint128_t	apgakey;
 };
 
+/* ZA state (NT_ARM_ZA) */
+
+struct user_za_header {
+	__u32 size; /* total meaningful regset content in bytes */
+	__u32 max_size; /* maxmium possible size for this thread */
+	__u16 vl; /* current vector length */
+	__u16 max_vl; /* maximum possible vector length */
+	__u16 flags;
+	__u16 __reserved;
+};
+
+/*
+ * Common ZA_PT_* flags:
+ * These must be kept in sync with prctl interface in <linux/prctl.h>
+ */
+#define ZA_PT_VL_INHERIT		((1 << 17) /* PR_SME_VL_INHERIT */ >> 16)
+#define ZA_PT_VL_ONEXEC			((1 << 18) /* PR_SME_SET_VL_ONEXEC */ >> 16)
+
+
+/*
+ * The remainder of the ZA state follows struct user_za_header.  The
+ * total size of the ZA state (including header) depends on the
+ * metadata in the header:  ZA_PT_SIZE(vq, flags) gives the total size
+ * of the state in bytes, including the header.
+ *
+ * Refer to <asm/sigcontext.h> for details of how to pass the correct
+ * "vq" argument to these macros.
+ */
+
+/* Offset from the start of struct user_za_header to the register data */
+#define ZA_PT_ZA_OFFSET						\
+	((sizeof(struct user_za_header) + (__SVE_VQ_BYTES - 1))	\
+		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
+
+/*
+ * The payload starts at offset ZA_PT_ZA_OFFSET, and is of size
+ * ZA_PT_ZA_SIZE(vq, flags).
+ *
+ * The ZA array is stored as a sequence of horizontal vectors ZAV of SVL/8
+ * bytes each, starting from vector 0.
+ *
+ * Additional data might be appended in the future.
+ *
+ * The ZA matrix is represented in memory in an endianness-invariant layout
+ * which differs from the layout used for the FPSIMD V-registers on big-endian
+ * systems: see sigcontext.h for more explanation.
+ */
+
+#define ZA_PT_ZAV_OFFSET(vq, n) \
+	(ZA_PT_ZA_OFFSET + ((vq * __SVE_VQ_BYTES) * n))
+
+#define ZA_PT_ZA_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES))
+
+#define ZA_PT_SIZE(vq)						\
+	(ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq))
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI__ASM_PTRACE_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index 0c796c795dbe..4aaf31e3bf16 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -134,6 +134,17 @@ struct extra_context {
 struct sve_context {
 	struct _aarch64_ctx head;
 	__u16 vl;
+	__u16 flags;
+	__u16 __reserved[2];
+};
+
+#define SVE_SIG_FLAG_SM	0x1	/* Context describes streaming mode */
+
+#define ZA_MAGIC	0x54366345
+
+struct za_context {
+	struct _aarch64_ctx head;
+	__u16 vl;
 	__u16 __reserved[3];
 };
 
@@ -186,9 +197,16 @@ struct sve_context {
  * sve_context.vl must equal the thread's current vector length when
  * doing a sigreturn.
  *
+ * On systems with support for SME the SVE register state may reflect either
+ * streaming or non-streaming mode.  In streaming mode the streaming mode
+ * vector length will be used and the flag SVE_SIG_FLAG_SM will be set in
+ * the flags field. It is permitted to enter or leave streaming mode in
+ * a signal return, applications should take care to ensure that any difference
+ * in vector length between the two modes is handled, including any resizing
+ * and movement of context blocks.
  *
- * Note: for all these macros, the "vq" argument denotes the SVE
- * vector length in quadwords (i.e., units of 128 bits).
+ * Note: for all these macros, the "vq" argument denotes the vector length
+ * in quadwords (i.e., units of 128 bits).
  *
  * The correct way to obtain vq is to use sve_vq_from_vl(vl).  The
  * result is valid if and only if sve_vl_valid(vl) is true.  This is
@@ -249,4 +267,37 @@ struct sve_context {
 #define SVE_SIG_CONTEXT_SIZE(vq) \
 		(SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq))
 
+/*
+ * If the ZA register is enabled for the thread at signal delivery then,
+ * za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl))
+ * and the register data may be accessed using the ZA_SIG_*() macros.
+ *
+ * If za_context.head.size < ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl))
+ * then ZA was not enabled and no register data was included in which case
+ * ZA register was not enabled for the thread and no register data
+ * the ZA_SIG_*() macros should not be used except for this check.
+ *
+ * The same convention applies when returning from a signal: a caller
+ * will need to remove or resize the za_context block if it wants to
+ * enable the ZA register when it was previously non-live or vice-versa.
+ * This may require the caller to allocate fresh memory and/or move other
+ * context blocks in the signal frame.
+ *
+ * Changing the vector length during signal return is not permitted:
+ * za_context.vl must equal the thread's current SME vector length when
+ * doing a sigreturn.
+ */
+
+#define ZA_SIG_REGS_OFFSET					\
+	((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1))	\
+		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
+
+#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES))
+
+#define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \
+				  (SVE_SIG_ZREG_SIZE(vq) * n))
+
+#define ZA_SIG_CONTEXT_SIZE(vq) \
+		(ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq))
+
 #endif /* _UAPI__ASM_SIGCONTEXT_H */