13 files changed, 158 insertions, 54 deletions

diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index e6f66491fbe9..862bb1cba4f0 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -197,6 +197,8 @@ out:
  */
 void __init acpi_boot_table_init(void)
 {
+	int ret;
+
 	/*
 	 * Enable ACPI instead of device tree unless
 	 * - ACPI has been disabled explicitly (acpi=off), or
@@ -250,10 +252,12 @@ done:
 		 * behaviour, use acpi=nospcr to disable console in ACPI SPCR
 		 * table as default serial console.
 		 */
-		acpi_parse_spcr(earlycon_acpi_spcr_enable,
+		ret = acpi_parse_spcr(earlycon_acpi_spcr_enable,
 			!param_acpi_nospcr);
-		pr_info("Use ACPI SPCR as default console: %s\n",
-				param_acpi_nospcr ? "No" : "Yes");
+		if (!ret || param_acpi_nospcr || !IS_ENABLED(CONFIG_ACPI_SPCR_TABLE))
+			pr_info("Use ACPI SPCR as default console: No\n");
+		else
+			pr_info("Use ACPI SPCR as default console: Yes\n");
 
 		if (IS_ENABLED(CONFIG_ACPI_BGRT))
 			acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 3f432d37d1e5..415608d1798f 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -111,7 +111,14 @@ static struct arm64_cpu_capabilities const __ro_after_init *cpucap_ptrs[ARM64_NC
 
 DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS);
 
-bool arm64_use_ng_mappings = false;
+/*
+ * arm64_use_ng_mappings must be placed in the .data section, otherwise it
+ * ends up in the .bss section where it is initialized in early_map_kernel()
+ * after the MMU (with the idmap) was enabled. create_init_idmap() - which
+ * runs before early_map_kernel() and reads the variable via PTE_MAYBE_NG -
+ * may end up generating an incorrect idmap page table attributes.
+ */
+bool arm64_use_ng_mappings __read_mostly = false;
 EXPORT_SYMBOL(arm64_use_ng_mappings);
 
 DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors;
@@ -2965,6 +2972,13 @@ static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope)
 }
 #endif
 
+#ifdef CONFIG_ARM64_SME
+static bool has_sme_feature(const struct arm64_cpu_capabilities *cap, int scope)
+{
+	return system_supports_sme() && has_user_cpuid_feature(cap, scope);
+}
+#endif
+
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL),
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES),
@@ -3043,25 +3057,25 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	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),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
 #endif /* CONFIG_ARM64_SME */
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA),
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 3fcd9d080bf2..d23315ef7b67 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -393,20 +393,16 @@ static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *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)
+static inline void fpsimd_syscall_enter(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.
-	 */
+	/* Ensure PSTATE.SM is clear, but leave PSTATE.ZA as-is. */
 	if (system_supports_sme())
 		sme_smstop_sm();
 
+	/*
+	 * The CPU is not in streaming mode. If non-streaming SVE is not
+	 * supported, there is no SVE state that needs to be discarded.
+	 */
 	if (!system_supports_sve())
 		return;
 
@@ -416,6 +412,33 @@ static inline void fp_user_discard(void)
 		sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1;
 		sve_flush_live(true, sve_vq_minus_one);
 	}
+
+	/*
+	 * Any live non-FPSIMD SVE state has been zeroed. Allow
+	 * fpsimd_save_user_state() to lazily discard SVE state until either
+	 * the live state is unbound or fpsimd_syscall_exit() is called.
+	 */
+	__this_cpu_write(fpsimd_last_state.to_save, FP_STATE_FPSIMD);
+}
+
+static __always_inline void fpsimd_syscall_exit(void)
+{
+	if (!system_supports_sve())
+		return;
+
+	/*
+	 * The current task's user FPSIMD/SVE/SME state is now bound to this
+	 * CPU. The fpsimd_last_state.to_save value is either:
+	 *
+	 * - FP_STATE_FPSIMD, if the state has not been reloaded on this CPU
+	 *   since fpsimd_syscall_enter().
+	 *
+	 * - FP_STATE_CURRENT, if the state has been reloaded on this CPU at
+	 *   any point.
+	 *
+	 * Reset this to FP_STATE_CURRENT to stop lazy discarding.
+	 */
+	__this_cpu_write(fpsimd_last_state.to_save, FP_STATE_CURRENT);
 }
 
 UNHANDLED(el1t, 64, sync)
@@ -707,10 +730,11 @@ static void noinstr el0_svc(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
 	cortex_a76_erratum_1463225_svc_handler();
-	fp_user_discard();
+	fpsimd_syscall_enter();
 	local_daif_restore(DAIF_PROCCTX);
 	do_el0_svc(regs);
 	exit_to_user_mode(regs);
+	fpsimd_syscall_exit();
 }
 
 static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 7ef0e127b149..189ce50055d1 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -823,6 +823,7 @@ SYM_CODE_END(__bp_harden_el1_vectors)
  *
  */
 SYM_FUNC_START(cpu_switch_to)
+	save_and_disable_daif x11
 	mov	x10, #THREAD_CPU_CONTEXT
 	add	x8, x0, x10
 	mov	x9, sp
@@ -846,6 +847,7 @@ SYM_FUNC_START(cpu_switch_to)
 	ptrauth_keys_install_kernel x1, x8, x9, x10
 	scs_save x0
 	scs_load_current
+	restore_irq x11
 	ret
 SYM_FUNC_END(cpu_switch_to)
 NOKPROBE(cpu_switch_to)
@@ -872,6 +874,7 @@ NOKPROBE(ret_from_fork)
  * Calls func(regs) using this CPU's irq stack and shadow irq stack.
  */
 SYM_FUNC_START(call_on_irq_stack)
+	save_and_disable_daif x9
 #ifdef CONFIG_SHADOW_CALL_STACK
 	get_current_task x16
 	scs_save x16
@@ -886,8 +889,10 @@ SYM_FUNC_START(call_on_irq_stack)
 
 	/* Move to the new stack and call the function there */
 	add	sp, x16, #IRQ_STACK_SIZE
+	restore_irq x9
 	blr	x1
 
+	save_and_disable_daif x9
 	/*
 	 * Restore the SP from the FP, and restore the FP and LR from the frame
 	 * record.
@@ -895,6 +900,7 @@ SYM_FUNC_START(call_on_irq_stack)
 	mov	sp, x29
 	ldp	x29, x30, [sp], #16
 	scs_load_current
+	restore_irq x9
 	ret
 SYM_FUNC_END(call_on_irq_stack)
 NOKPROBE(call_on_irq_stack)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index f38d22dac140..8854bce5cfe2 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -119,7 +119,7 @@
  *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
  */
 
-static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
+DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
 
 __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
 #ifdef CONFIG_ARM64_SVE
@@ -359,9 +359,6 @@ static void task_fpsimd_load(void)
 	WARN_ON(preemptible());
 	WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE));
 
-	if (system_supports_fpmr())
-		write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR);
-
 	if (system_supports_sve() || system_supports_sme()) {
 		switch (current->thread.fp_type) {
 		case FP_STATE_FPSIMD:
@@ -413,6 +410,9 @@ static void task_fpsimd_load(void)
 			restore_ffr = system_supports_fa64();
 	}
 
+	if (system_supports_fpmr())
+		write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR);
+
 	if (restore_sve_regs) {
 		WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE);
 		sve_load_state(sve_pffr(&current->thread),
@@ -453,12 +453,15 @@ static void fpsimd_save_user_state(void)
 		*(last->fpmr) = read_sysreg_s(SYS_FPMR);
 
 	/*
-	 * If a task is in a syscall the ABI allows us to only
-	 * preserve the state shared with FPSIMD so don't bother
-	 * saving the full SVE state in that case.
+	 * Save SVE state if it is live.
+	 *
+	 * The syscall ABI discards live SVE state at syscall entry. When
+	 * entering a syscall, fpsimd_syscall_enter() sets to_save to
+	 * FP_STATE_FPSIMD to allow the SVE state to be lazily discarded until
+	 * either new SVE state is loaded+bound or fpsimd_syscall_exit() is
+	 * called prior to a return to userspace.
 	 */
-	if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) &&
-	     !in_syscall(current_pt_regs())) ||
+	if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE)) ||
 	    last->to_save == FP_STATE_SVE) {
 		save_sve_regs = true;
 		save_ffr = true;
@@ -651,7 +654,7 @@ static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
  * task->thread.uw.fpsimd_state must be up to date before calling this
  * function.
  */
-static void fpsimd_to_sve(struct task_struct *task)
+static inline void fpsimd_to_sve(struct task_struct *task)
 {
 	unsigned int vq;
 	void *sst = task->thread.sve_state;
@@ -675,7 +678,7 @@ static void fpsimd_to_sve(struct task_struct *task)
  * bytes of allocated kernel memory.
  * task->thread.sve_state must be up to date before calling this function.
  */
-static void sve_to_fpsimd(struct task_struct *task)
+static inline void sve_to_fpsimd(struct task_struct *task)
 {
 	unsigned int vq, vl;
 	void const *sst = task->thread.sve_state;
@@ -1436,7 +1439,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 	 * If this not a trap due to SME being disabled then something
 	 * is being used in the wrong mode, report as SIGILL.
 	 */
-	if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) {
+	if (ESR_ELx_SME_ISS_SMTC(esr) != ESR_ELx_SME_ISS_SMTC_SME_DISABLED) {
 		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
 		return;
 	}
@@ -1460,6 +1463,8 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 		sme_set_vq(vq_minus_one);
 
 		fpsimd_bind_task_to_cpu();
+	} else {
+		fpsimd_flush_task_state(current);
 	}
 
 	put_cpu_fpsimd_context();
@@ -1573,8 +1578,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 		fpsimd_save_user_state();
 
 	if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) {
-		fpsimd_load_kernel_state(next);
 		fpsimd_flush_cpu_state();
+		fpsimd_load_kernel_state(next);
 	} else {
 		/*
 		 * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
@@ -1661,6 +1666,9 @@ void fpsimd_flush_thread(void)
 		current->thread.svcr = 0;
 	}
 
+	if (system_supports_fpmr())
+		current->thread.uw.fpmr = 0;
+
 	current->thread.fp_type = FP_STATE_FPSIMD;
 
 	put_cpu_fpsimd_context();
@@ -1801,7 +1809,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 	get_cpu_fpsimd_context();
 
 	current->thread.uw.fpsimd_state = *state;
-	if (test_thread_flag(TIF_SVE))
+	if (current->thread.fp_type == FP_STATE_SVE)
 		fpsimd_to_sve(current);
 
 	task_fpsimd_load();
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index a650f5e11fc5..b657f058bf4d 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -195,10 +195,17 @@ 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)
+static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
 {
 #ifdef CONFIG_MODULES
-	struct plt_entry *plt = mod->arch.ftrace_trampolines;
+	struct plt_entry *plt = NULL;
+
+	if (within_module_mem_type(addr, mod, MOD_INIT_TEXT))
+		plt = mod->arch.init_ftrace_trampolines;
+	else if (within_module_mem_type(addr, mod, MOD_TEXT))
+		plt = mod->arch.ftrace_trampolines;
+	else
+		return NULL;
 
 	return &plt[FTRACE_PLT_IDX];
 #else
@@ -270,7 +277,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 	if (WARN_ON(!mod))
 		return false;
 
-	plt = get_ftrace_plt(mod);
+	plt = get_ftrace_plt(mod, pc);
 	if (!plt) {
 		pr_err("ftrace: no module PLT for %ps\n", (void *)*addr);
 		return false;
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index bde32979c06a..7afd370da9f4 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -283,7 +283,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	unsigned long core_plts = 0;
 	unsigned long init_plts = 0;
 	Elf64_Sym *syms = NULL;
-	Elf_Shdr *pltsec, *tramp = NULL;
+	Elf_Shdr *pltsec, *tramp = NULL, *init_tramp = NULL;
 	int i;
 
 	/*
@@ -298,6 +298,9 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		else if (!strcmp(secstrings + sechdrs[i].sh_name,
 				 ".text.ftrace_trampoline"))
 			tramp = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name,
+				 ".init.text.ftrace_trampoline"))
+			init_tramp = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
 			syms = (Elf64_Sym *)sechdrs[i].sh_addr;
 	}
@@ -363,5 +366,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
 	}
 
+	if (init_tramp) {
+		init_tramp->sh_type = SHT_NOBITS;
+		init_tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+		init_tramp->sh_addralign = __alignof__(struct plt_entry);
+		init_tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
+	}
+
 	return 0;
 }
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 36b25af56324..65764ec1cc13 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -453,6 +453,17 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
 	__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
 
 	mod->arch.ftrace_trampolines = plts;
+
+	s = find_section(hdr, sechdrs, ".init.text.ftrace_trampoline");
+	if (!s)
+		return -ENOEXEC;
+
+	plts = (void *)s->sh_addr;
+
+	__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
+
+	mod->arch.init_ftrace_trampolines = plts;
+
 #endif
 	return 0;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 2bbcbb11d844..2edf88c1c695 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -544,6 +544,11 @@ static void permission_overlay_switch(struct task_struct *next)
 	current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
 	if (current->thread.por_el0 != next->thread.por_el0) {
 		write_sysreg_s(next->thread.por_el0, SYS_POR_EL0);
+		/*
+		 * No ISB required as we can tolerate spurious Overlay faults -
+		 * the fault handler will check again based on the new value
+		 * of POR_EL0.
+		 */
 	}
 }
 
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index d54c59ad4026..9bf98a370917 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -918,6 +918,7 @@ u8 k = 0;
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
 		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
@@ -929,6 +930,7 @@ u8 k = 0;
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
 		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
 		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_GOLD),
+		MIDR_ALL_VERSIONS(MIDR_HISI_HIP09),
 		{},
 	};
 	static const struct midr_range spectre_bhb_k11_list[] = {
@@ -1084,6 +1086,11 @@ static bool is_spectre_bse_affected(int scope)
 	return false;
 }
 
+u8 get_spectre_bhb_loop_value(void)
+{
+	return max_bhb_k;
+}
+
 static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
 {
 	const char *v = arm64_get_bp_hardening_vector(slot);
@@ -1101,7 +1108,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
 	isb();
 }
 
-static bool __read_mostly __nospectre_bhb;
+bool __read_mostly __nospectre_bhb;
 static int __init parse_spectre_bhb_param(char *str)
 {
 	__nospectre_bhb = true;
@@ -1240,6 +1247,11 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 	update_mitigation_state(&spectre_bse_state, bse_state);
 }
 
+bool is_spectre_bhb_fw_mitigated(void)
+{
+	return test_bit(BHB_FW_WA1, &system_bhb_mitigations) || test_bit(BHB_FW_WA3, &system_bhb_mitigations);
+}
+
 /* Patched to NOP when enabled */
 void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt,
 						     __le32 *origptr,
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 1559a239137f..1a8f4284cb69 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -140,7 +140,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
 
 	addr += n;
 	if (regs_within_kernel_stack(regs, (unsigned long)addr))
-		return *addr;
+		return READ_ONCE_NOCHECK(*addr);
 	else
 		return 0;
 }
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 2729faaee4b4..1d60a08a2184 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -123,6 +123,8 @@ kunwind_recover_return_address(struct kunwind_state *state)
 		orig_pc = kretprobe_find_ret_addr(state->task,
 						  (void *)state->common.fp,
 						  &state->kr_cur);
+		if (!orig_pc)
+			return -EINVAL;
 		state->common.pc = orig_pc;
 	}
 #endif /* CONFIG_KRETPROBES */
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 59645ab6b60b..c343113cee5d 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -942,6 +942,7 @@ void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigne
 
 void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr)
 {
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
 	console_verbose();
 
 	pr_crit("SError Interrupt on CPU%d, code 0x%016lx -- %s\n",