19 files changed, 166 insertions, 135 deletions

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f9d456fe132d..a5f533f63b60 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -222,7 +222,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
 		       FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0),
@@ -2708,12 +2708,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.desc = "Enhanced Virtualization Traps",
 		.capability = ARM64_HAS_EVT,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
-		.sys_reg = SYS_ID_AA64MMFR2_EL1,
-		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64MMFR2_EL1_EVT_SHIFT,
-		.field_width = 4,
-		.min_field_value = ID_AA64MMFR2_EL1_EVT_IMP,
 		.matches = has_cpuid_feature,
+		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP)
 	},
 	{},
 };
@@ -2844,6 +2840,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES),
 	HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
 	HWCAP_CAP(ID_AA64ISAR2_EL1, MOPS, IMP, CAP_HWCAP, KERNEL_HWCAP_MOPS),
+	HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC),
 #ifdef CONFIG_ARM64_SME
 	HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index d1f68599c29f..f372295207fb 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -9,8 +9,6 @@
 #include <linux/acpi.h>
 #include <linux/cpuidle.h>
 #include <linux/cpu_pm.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/psci.h>
 
 #ifdef CONFIG_ACPI_PROCESSOR_IDLE
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 58622dc85917..98fda8500535 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -126,6 +126,7 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_SME_B16B16]	= "smeb16b16",
 	[KERNEL_HWCAP_SME_F16F16]	= "smef16f16",
 	[KERNEL_HWCAP_MOPS]		= "mops",
+	[KERNEL_HWCAP_HBC]		= "hbc",
 };
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index baab8dd3ead3..49efbdbd6f7a 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -158,7 +158,21 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f)
 	return s;
 }
 
-DEFINE_RAW_SPINLOCK(efi_rt_lock);
+static DEFINE_RAW_SPINLOCK(efi_rt_lock);
+
+void arch_efi_call_virt_setup(void)
+{
+	efi_virtmap_load();
+	__efi_fpsimd_begin();
+	raw_spin_lock(&efi_rt_lock);
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	raw_spin_unlock(&efi_rt_lock);
+	__efi_fpsimd_end();
+	efi_virtmap_unload();
+}
 
 asmlinkage u64 *efi_rt_stack_top __ro_after_init;
 
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 6b2e0c367702..0fc94207e69a 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -355,6 +355,35 @@ static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 }
 #endif /* CONFIG_ARM64_ERRATUM_1463225 */
 
+/*
+ * As per the ABI exit SME streaming mode and clear the SVE state not
+ * shared with FPSIMD on syscall entry.
+ */
+static inline void fp_user_discard(void)
+{
+	/*
+	 * If SME is active then exit streaming mode.  If ZA is active
+	 * then flush the SVE registers but leave userspace access to
+	 * both SVE and SME enabled, otherwise disable SME for the
+	 * task and fall through to disabling SVE too.  This means
+	 * that after a syscall we never have any streaming mode
+	 * register state to track, if this changes the KVM code will
+	 * need updating.
+	 */
+	if (system_supports_sme())
+		sme_smstop_sm();
+
+	if (!system_supports_sve())
+		return;
+
+	if (test_thread_flag(TIF_SVE)) {
+		unsigned int sve_vq_minus_one;
+
+		sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1;
+		sve_flush_live(true, sve_vq_minus_one);
+	}
+}
+
 UNHANDLED(el1t, 64, sync)
 UNHANDLED(el1t, 64, irq)
 UNHANDLED(el1t, 64, fiq)
@@ -644,6 +673,8 @@ static void noinstr el0_svc(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
 	cortex_a76_erratum_1463225_svc_handler();
+	fp_user_discard();
+	local_daif_restore(DAIF_PROCCTX);
 	do_el0_svc(regs);
 	exit_to_user_mode(regs);
 }
@@ -783,6 +814,7 @@ static void noinstr el0_svc_compat(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
 	cortex_a76_erratum_1463225_svc_handler();
+	local_daif_restore(DAIF_PROCCTX);
 	do_el0_svc_compat(regs);
 	exit_to_user_mode(regs);
 }
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a40e5e50fa55..6ad61de03d0a 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -986,9 +986,13 @@ SYM_CODE_START(__sdei_asm_handler)
 
 	mov	x19, x1
 
-#if defined(CONFIG_VMAP_STACK) || defined(CONFIG_SHADOW_CALL_STACK)
+	/* Store the registered-event for crash_smp_send_stop() */
 	ldrb	w4, [x19, #SDEI_EVENT_PRIORITY]
-#endif
+	cbnz	w4, 1f
+	adr_this_cpu dst=x5, sym=sdei_active_normal_event, tmp=x6
+	b	2f
+1:	adr_this_cpu dst=x5, sym=sdei_active_critical_event, tmp=x6
+2:	str	x19, [x5]
 
 #ifdef CONFIG_VMAP_STACK
 	/*
@@ -1055,6 +1059,14 @@ SYM_CODE_START(__sdei_asm_handler)
 
 	ldr_l	x2, sdei_exit_mode
 
+	/* Clear the registered-event seen by crash_smp_send_stop() */
+	ldrb	w3, [x4, #SDEI_EVENT_PRIORITY]
+	cbnz	w3, 1f
+	adr_this_cpu dst=x5, sym=sdei_active_normal_event, tmp=x6
+	b	2f
+1:	adr_this_cpu dst=x5, sym=sdei_active_critical_event, tmp=x6
+2:	str	xzr, [x5]
+
 alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
 	sdei_handler_exit exit_mode=x2
 alternative_else_nop_endif
@@ -1065,4 +1077,15 @@ alternative_else_nop_endif
 #endif
 SYM_CODE_END(__sdei_asm_handler)
 NOKPROBE(__sdei_asm_handler)
+
+SYM_CODE_START(__sdei_handler_abort)
+	mov_q	x0, SDEI_1_0_FN_SDEI_EVENT_COMPLETE_AND_RESUME
+	adr	x1, 1f
+	ldr_l	x2, sdei_exit_mode
+	sdei_handler_exit exit_mode=x2
+	// exit the handler and jump to the next instruction.
+	// Exit will stomp x0-x17, PSTATE, ELR_ELx, and SPSR_ELx.
+1:	ret
+SYM_CODE_END(__sdei_handler_abort)
+NOKPROBE(__sdei_handler_abort)
 #endif /* CONFIG_ARM_SDE_INTERFACE */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 7a1aeb95d7c3..91e44ac7150f 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -679,7 +679,7 @@ static void fpsimd_to_sve(struct task_struct *task)
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
 
-	if (!system_supports_sve())
+	if (!system_supports_sve() && !system_supports_sme())
 		return;
 
 	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
@@ -705,7 +705,7 @@ static void sve_to_fpsimd(struct task_struct *task)
 	unsigned int i;
 	__uint128_t const *p;
 
-	if (!system_supports_sve())
+	if (!system_supports_sve() && !system_supports_sme())
 		return;
 
 	vl = thread_get_cur_vl(&task->thread);
@@ -835,7 +835,8 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
 
-	if (!test_tsk_thread_flag(task, TIF_SVE))
+	if (!test_tsk_thread_flag(task, TIF_SVE) &&
+	    !thread_sm_enabled(&task->thread))
 		return;
 
 	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
@@ -847,6 +848,8 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 			  unsigned long vl, unsigned long flags)
 {
+	bool free_sme = false;
+
 	if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
 				     PR_SVE_SET_VL_ONEXEC))
 		return -EINVAL;
@@ -897,24 +900,39 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 		task->thread.fp_type = FP_STATE_FPSIMD;
 	}
 
-	if (system_supports_sme() && type == ARM64_VEC_SME) {
-		task->thread.svcr &= ~(SVCR_SM_MASK |
-				       SVCR_ZA_MASK);
-		clear_thread_flag(TIF_SME);
+	if (system_supports_sme()) {
+		if (type == ARM64_VEC_SME ||
+		    !(task->thread.svcr & (SVCR_SM_MASK | SVCR_ZA_MASK))) {
+			/*
+			 * We are changing the SME VL or weren't using
+			 * SME anyway, discard the state and force a
+			 * reallocation.
+			 */
+			task->thread.svcr &= ~(SVCR_SM_MASK |
+					       SVCR_ZA_MASK);
+			clear_tsk_thread_flag(task, TIF_SME);
+			free_sme = true;
+		}
 	}
 
 	if (task == current)
 		put_cpu_fpsimd_context();
 
+	task_set_vl(task, type, vl);
+
 	/*
-	 * Force reallocation of task SVE and SME state to the correct
-	 * size on next use:
+	 * Free the changed states if they are not in use, SME will be
+	 * reallocated to the correct size on next use and we just
+	 * allocate SVE now in case it is needed for use in streaming
+	 * mode.
 	 */
-	sve_free(task);
-	if (system_supports_sme() && type == ARM64_VEC_SME)
-		sme_free(task);
+	if (system_supports_sve()) {
+		sve_free(task);
+		sve_alloc(task, true);
+	}
 
-	task_set_vl(task, type, vl);
+	if (free_sme)
+		sme_free(task);
 
 out:
 	update_tsk_thread_flag(task, vec_vl_inherit_flag(type),
@@ -1161,9 +1179,6 @@ void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
  */
 u64 read_zcr_features(void)
 {
-	u64 zcr;
-	unsigned int vq_max;
-
 	/*
 	 * Set the maximum possible VL, and write zeroes to all other
 	 * bits to see if they stick.
@@ -1171,12 +1186,8 @@ u64 read_zcr_features(void)
 	sve_kernel_enable(NULL);
 	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
 
-	zcr = read_sysreg_s(SYS_ZCR_EL1);
-	zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
-	vq_max = sve_vq_from_vl(sve_get_vl());
-	zcr |= vq_max - 1; /* set LEN field to maximum effective value */
-
-	return zcr;
+	/* Return LEN value that would be written to get the maximum VL */
+	return sve_vq_from_vl(sve_get_vl()) - 1;
 }
 
 void __init sve_setup(void)
@@ -1267,9 +1278,9 @@ void fpsimd_release_task(struct task_struct *dead_task)
  * the interest of testability and predictability, the architecture
  * guarantees that when ZA is enabled it will be zeroed.
  */
-void sme_alloc(struct task_struct *task)
+void sme_alloc(struct task_struct *task, bool flush)
 {
-	if (task->thread.sme_state) {
+	if (task->thread.sme_state && flush) {
 		memset(task->thread.sme_state, 0, sme_state_size(task));
 		return;
 	}
@@ -1331,9 +1342,6 @@ void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
  */
 u64 read_smcr_features(void)
 {
-	u64 smcr;
-	unsigned int vq_max;
-
 	sme_kernel_enable(NULL);
 
 	/*
@@ -1342,12 +1350,8 @@ u64 read_smcr_features(void)
 	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK,
 		       SYS_SMCR_EL1);
 
-	smcr = read_sysreg_s(SYS_SMCR_EL1);
-	smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */
-	vq_max = sve_vq_from_vl(sme_get_vl());
-	smcr |= vq_max - 1; /* set LEN field to maximum effective value */
-
-	return smcr;
+	/* Return LEN value that would be written to get the maximum VL */
+	return sve_vq_from_vl(sme_get_vl()) - 1;
 }
 
 void __init sme_setup(void)
@@ -1497,7 +1501,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 	}
 
 	sve_alloc(current, false);
-	sme_alloc(current);
+	sme_alloc(current, true);
 	if (!current->thread.sve_state || !current->thread.sme_state) {
 		force_sig(SIGKILL);
 		return;
@@ -1649,7 +1653,6 @@ void fpsimd_flush_thread(void)
 
 		fpsimd_flush_thread_vl(ARM64_VEC_SME);
 		current->thread.svcr = 0;
-		sme_smstop();
 	}
 
 	current->thread.fp_type = FP_STATE_FPSIMD;
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 757a0de07f91..7b236994f0e1 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -113,7 +113,7 @@ SYM_CODE_START(primary_entry)
 	 */
 #if VA_BITS > 48
 	mrs_s	x0, SYS_ID_AA64MMFR2_EL1
-	tst	x0, #0xf << ID_AA64MMFR2_EL1_VARange_SHIFT
+	tst	x0, ID_AA64MMFR2_EL1_VARange_MASK
 	mov	x0, #VA_BITS
 	mov	x25, #VA_BITS_MIN
 	csel	x25, x25, x0, eq
@@ -756,7 +756,7 @@ SYM_FUNC_START(__cpu_secondary_check52bitva)
 	b.ne	2f
 
 	mrs_s	x0, SYS_ID_AA64MMFR2_EL1
-	and	x0, x0, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT)
+	and	x0, x0, ID_AA64MMFR2_EL1_VARange_MASK
 	cbnz	x0, 2f
 
 	update_early_cpu_boot_status \
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index db2a1861bb97..35225632d70a 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -654,7 +654,7 @@ static int breakpoint_handler(unsigned long unused, unsigned long esr,
 		perf_bp_event(bp, regs);
 
 		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(bp))
+		if (uses_default_overflow_handler(bp))
 			step = 1;
 unlock:
 		rcu_read_unlock();
@@ -733,7 +733,7 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
 static int watchpoint_report(struct perf_event *wp, unsigned long addr,
 			     struct pt_regs *regs)
 {
-	int step = is_default_overflow_handler(wp);
+	int step = uses_default_overflow_handler(wp);
 	struct arch_hw_breakpoint *info = counter_arch_bp(wp);
 
 	info->trigger = addr;
diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index 2fe2491b692c..aee12c75b738 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -262,9 +262,9 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases)
 		if (!len)
 			return;
 
-		len = min(len, ARRAY_SIZE(buf) - 1);
-		strncpy(buf, cmdline, len);
-		buf[len] = 0;
+		len = strscpy(buf, cmdline, ARRAY_SIZE(buf));
+		if (len == -E2BIG)
+			len = ARRAY_SIZE(buf) - 1;
 
 		if (strcmp(buf, "--") == 0)
 			return;
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 4c5ef9b20065..4edecaac8f91 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -35,41 +35,18 @@ DEFINE_STATIC_KEY_FALSE(mte_async_or_asymm_mode);
 EXPORT_SYMBOL_GPL(mte_async_or_asymm_mode);
 #endif
 
-static void mte_sync_page_tags(struct page *page, pte_t old_pte,
-			       bool check_swap, bool pte_is_tagged)
-{
-	if (check_swap && is_swap_pte(old_pte)) {
-		swp_entry_t entry = pte_to_swp_entry(old_pte);
-
-		if (!non_swap_entry(entry))
-			mte_restore_tags(entry, page);
-	}
-
-	if (!pte_is_tagged)
-		return;
-
-	if (try_page_mte_tagging(page)) {
-		mte_clear_page_tags(page_address(page));
-		set_page_mte_tagged(page);
-	}
-}
-
-void mte_sync_tags(pte_t old_pte, pte_t pte)
+void mte_sync_tags(pte_t pte)
 {
 	struct page *page = pte_page(pte);
 	long i, nr_pages = compound_nr(page);
-	bool check_swap = nr_pages == 1;
-	bool pte_is_tagged = pte_tagged(pte);
-
-	/* Early out if there's nothing to do */
-	if (!check_swap && !pte_is_tagged)
-		return;
 
 	/* if PG_mte_tagged is set, tags have already been initialised */
-	for (i = 0; i < nr_pages; i++, page++)
-		if (!page_mte_tagged(page))
-			mte_sync_page_tags(page, old_pte, check_swap,
-					   pte_is_tagged);
+	for (i = 0; i < nr_pages; i++, page++) {
+		if (try_page_mte_tagging(page)) {
+			mte_clear_page_tags(page_address(page));
+			set_page_mte_tagged(page);
+		}
+	}
 
 	/* ensure the tags are visible before the PTE is set */
 	smp_wmb();
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index 2276689b5411..f872c57e9909 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -11,8 +11,6 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/of_pci.h>
-#include <linux/of_platform.h>
 #include <linux/pci.h>
 #include <linux/pci-acpi.h>
 #include <linux/pci-ecam.h>
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index d7f4f0d1ae12..20d7ef82de90 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -881,10 +881,18 @@ static int sve_set_common(struct task_struct *target,
 			break;
 		case ARM64_VEC_SME:
 			target->thread.svcr |= SVCR_SM_MASK;
+
+			/*
+			 * Disable traps and ensure there is SME storage but
+			 * preserve any currently set values in ZA/ZT.
+			 */
+			sme_alloc(target, false);
+			set_tsk_thread_flag(target, TIF_SME);
 			break;
 		default:
 			WARN_ON_ONCE(1);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
 
 		/*
@@ -932,11 +940,13 @@ static int sve_set_common(struct task_struct *target,
 	/*
 	 * Ensure target->thread.sve_state is up to date with target's
 	 * FPSIMD regs, so that a short copyin leaves trailing
-	 * registers unmodified.  Always enable SVE even if going into
-	 * streaming mode.
+	 * registers unmodified.  Only enable SVE if we are
+	 * configuring normal SVE, a system with streaming SVE may not
+	 * have normal SVE.
 	 */
 	fpsimd_sync_to_sve(target);
-	set_tsk_thread_flag(target, TIF_SVE);
+	if (type == ARM64_VEC_SVE)
+		set_tsk_thread_flag(target, TIF_SVE);
 	target->thread.fp_type = FP_STATE_SVE;
 
 	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
@@ -1098,7 +1108,7 @@ static int za_set(struct task_struct *target,
 	}
 
 	/* Allocate/reinit ZA storage */
-	sme_alloc(target);
+	sme_alloc(target, true);
 	if (!target->thread.sme_state) {
 		ret = -ENOMEM;
 		goto out;
@@ -1168,8 +1178,13 @@ static int zt_set(struct task_struct *target,
 	if (!system_supports_sme2())
 		return -EINVAL;
 
+	/* Ensure SVE storage in case this is first use of SME */
+	sve_alloc(target, false);
+	if (!target->thread.sve_state)
+		return -ENOMEM;
+
 	if (!thread_za_enabled(&target->thread)) {
-		sme_alloc(target);
+		sme_alloc(target, true);
 		if (!target->thread.sme_state)
 			return -ENOMEM;
 	}
@@ -1177,8 +1192,12 @@ static int zt_set(struct task_struct *target,
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 thread_zt_state(&target->thread),
 				 0, ZT_SIG_REG_BYTES);
-	if (ret == 0)
+	if (ret == 0) {
 		target->thread.svcr |= SVCR_ZA_MASK;
+		set_tsk_thread_flag(target, TIF_SME);
+	}
+
+	fpsimd_flush_task_state(target);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 830be01af32d..255d12f881c2 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -47,6 +47,9 @@ DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_normal_ptr);
 DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_critical_ptr);
 #endif
 
+DEFINE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event);
+DEFINE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event);
+
 static void _free_sdei_stack(unsigned long * __percpu *ptr, int cpu)
 {
 	unsigned long *p;
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index e304f7ebec2a..c7ebe744c64e 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -475,7 +475,7 @@ static int restore_za_context(struct user_ctxs *user)
 	fpsimd_flush_task_state(current);
 	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
 
-	sme_alloc(current);
+	sme_alloc(current, true);
 	if (!current->thread.sme_state) {
 		current->thread.svcr &= ~SVCR_ZA_MASK;
 		clear_thread_flag(TIF_SME);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index edd63894d61e..960b98b43506 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -1044,10 +1044,8 @@ void crash_smp_send_stop(void)
 	 * If this cpu is the only one alive at this point in time, online or
 	 * not, there are no stop messages to be sent around, so just back out.
 	 */
-	if (num_other_online_cpus() == 0) {
-		sdei_mask_local_cpu();
-		return;
-	}
+	if (num_other_online_cpus() == 0)
+		goto skip_ipi;
 
 	cpumask_copy(&mask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &mask);
@@ -1066,7 +1064,9 @@ void crash_smp_send_stop(void)
 		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
 			cpumask_pr_args(&mask));
 
+skip_ipi:
 	sdei_mask_local_cpu();
+	sdei_handler_abort();
 }
 
 bool smp_crash_stop_failed(void)
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 5a668d7f3c1f..9a70d9746b66 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -8,7 +8,6 @@
 #include <linux/randomize_kstack.h>
 #include <linux/syscalls.h>
 
-#include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/exception.h>
 #include <asm/fpsimd.h>
@@ -75,9 +74,6 @@ static inline bool has_syscall_work(unsigned long flags)
 	return unlikely(flags & _TIF_SYSCALL_WORK);
 }
 
-int syscall_trace_enter(struct pt_regs *regs);
-void syscall_trace_exit(struct pt_regs *regs);
-
 static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 			   const syscall_fn_t syscall_table[])
 {
@@ -104,8 +100,6 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	 * (Similarly for HVC and SMC elsewhere.)
 	 */
 
-	local_daif_restore(DAIF_PROCCTX);
-
 	if (flags & _TIF_MTE_ASYNC_FAULT) {
 		/*
 		 * Process the asynchronous tag check fault before the actual
@@ -156,38 +150,8 @@ trace_exit:
 	syscall_trace_exit(regs);
 }
 
-/*
- * As per the ABI exit SME streaming mode and clear the SVE state not
- * shared with FPSIMD on syscall entry.
- */
-static inline void fp_user_discard(void)
-{
-	/*
-	 * If SME is active then exit streaming mode.  If ZA is active
-	 * then flush the SVE registers but leave userspace access to
-	 * both SVE and SME enabled, otherwise disable SME for the
-	 * task and fall through to disabling SVE too.  This means
-	 * that after a syscall we never have any streaming mode
-	 * register state to track, if this changes the KVM code will
-	 * need updating.
-	 */
-	if (system_supports_sme())
-		sme_smstop_sm();
-
-	if (!system_supports_sve())
-		return;
-
-	if (test_thread_flag(TIF_SVE)) {
-		unsigned int sve_vq_minus_one;
-
-		sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1;
-		sve_flush_live(true, sve_vq_minus_one);
-	}
-}
-
 void do_el0_svc(struct pt_regs *regs)
 {
-	fp_user_discard();
 	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
 }
 
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index 6028f1fe2d1c..45354f2ddf70 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -50,9 +50,7 @@ SECTIONS
 
 	. = ALIGN(4);
 	.altinstructions : {
-		__alt_instructions = .;
 		*(.altinstructions)
-		__alt_instructions_end = .;
 	}
 
 	.dynamic	: { *(.dynamic) }		:text	:dynamic
diff --git a/arch/arm64/kernel/vdso/vgettimeofday.c b/arch/arm64/kernel/vdso/vgettimeofday.c
index 4236cf34d7d9..9941c5b04f15 100644
--- a/arch/arm64/kernel/vdso/vgettimeofday.c
+++ b/arch/arm64/kernel/vdso/vgettimeofday.c
@@ -6,6 +6,10 @@
  *
  */
 
+int __kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+int __kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
+
 int __kernel_clock_gettime(clockid_t clock,
 			   struct __kernel_timespec *ts)
 {