23 files changed, 408 insertions, 150 deletions

diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 3a58e9db5cfe..a100483b47c4 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -274,7 +274,7 @@ int apei_claim_sea(struct pt_regs *regs)
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
 		return err;
 
-	current_flags = arch_local_save_flags();
+	current_flags = local_daif_save_flags();
 
 	/*
 	 * SEA can interrupt SError, mask it and describe this as an NMI so
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d1757ef1b1e7..73039949b5ce 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature)
  */
 static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	unsigned long replptr;
-
-	if (kernel_text_address(pc))
-		return true;
-
-	replptr = (unsigned long)ALT_REPL_PTR(alt);
-	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return false;
-
-	/*
-	 * Branching into *another* alternate sequence is doomed, and
-	 * we're not even trying to fix it up.
-	 */
-	BUG();
+	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
+	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
 }
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index ca158be21f83..bcb14d11232f 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -601,7 +601,7 @@ static struct undef_hook setend_hooks[] = {
 	},
 	{
 		/* Thumb mode */
-		.instr_mask	= 0x0000fff7,
+		.instr_mask	= 0xfffffff7,
 		.instr_val	= 0x0000b650,
 		.pstate_mask	= (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK),
 		.pstate_val	= (PSR_AA32_T_BIT | PSR_AA32_MODE_USR),
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index c87593ea489b..2ce5da59778d 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -87,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 }
 
 static void
-cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
+cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 {
 	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+	bool enable_uct_trap = false;
 
 	/* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
 	if ((read_cpuid_cachetype() & mask) !=
 	    (arm64_ftr_reg_ctrel0.sys_val & mask))
+		enable_uct_trap = true;
+
+	/* ... or if the system is affected by an erratum */
+	if (cap->capability == ARM64_WORKAROUND_1542419)
+		enable_uct_trap = true;
+
+	if (enable_uct_trap)
 		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
@@ -580,6 +588,7 @@ static const struct midr_range spectre_v2_safe_list[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
 	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+	MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 	{ /* sentinel */ }
 };
 
@@ -631,6 +640,18 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
 	return (need_wa > 0);
 }
 
+static bool __maybe_unused
+has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	u32 midr = read_cpuid_id();
+	bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT);
+	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && has_dic;
+}
+
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
 static const struct midr_range arm64_harden_el2_vectors[] = {
@@ -936,6 +957,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.matches = has_cortex_a76_erratum_1463225,
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_1542419
+	{
+		/* we depend on the firmware portion for correctness */
+		.desc = "ARM erratum 1542419 (kernel portion)",
+		.capability = ARM64_WORKAROUND_1542419,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_neoverse_n1_erratum_1542419,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d3fbb89a31e5..7bbea1b179f8 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -32,9 +32,7 @@ static unsigned long elf_hwcap __read_mostly;
 #define COMPAT_ELF_HWCAP_DEFAULT	\
 				(COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
 				 COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
-				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
-				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
-				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
+				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_IDIV|\
 				 COMPAT_HWCAP_LPAE)
 unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
 unsigned int compat_elf_hwcap2 __read_mostly;
@@ -175,11 +173,16 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -1361,7 +1364,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		/* FP/SIMD is not implemented */
 		.capability = ARM64_HAS_NO_FPSIMD,
-		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE,
 		.min_field_value = 0,
 		.matches = has_no_fpsimd,
 	},
@@ -1589,6 +1592,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.match_list = list,						\
 	}
 
+#define HWCAP_CAP_MATCH(match, cap_type, cap)					\
+	{									\
+		__HWCAP_CAP(#cap, cap_type, cap)				\
+		.matches = match,						\
+	}
+
 #ifdef CONFIG_ARM64_PTR_AUTH
 static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = {
 	{
@@ -1660,8 +1669,35 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	{},
 };
 
+#ifdef CONFIG_COMPAT
+static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope)
+{
+	/*
+	 * Check that all of MVFR1_EL1.{SIMDSP, SIMDInt, SIMDLS} are available,
+	 * in line with that of arm32 as in vfp_init(). We make sure that the
+	 * check is future proof, by making sure value is non-zero.
+	 */
+	u32 mvfr1;
+
+	WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible());
+	if (scope == SCOPE_SYSTEM)
+		mvfr1 = read_sanitised_ftr_reg(SYS_MVFR1_EL1);
+	else
+		mvfr1 = read_sysreg_s(SYS_MVFR1_EL1);
+
+	return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDSP_SHIFT) &&
+		cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDINT_SHIFT) &&
+		cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDLS_SHIFT);
+}
+#endif
+
 static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = {
 #ifdef CONFIG_COMPAT
+	HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON),
+	HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
+	/* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */
+	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
+	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
 	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
 	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
 	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 48222a4760c2..d64a3c1e1b6b 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init);
 /*
  * Single step API and exception handling.
  */
-static void set_regs_spsr_ss(struct pt_regs *regs)
+static void set_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(set_regs_spsr_ss);
+NOKPROBE_SYMBOL(set_user_regs_spsr_ss);
 
-static void clear_regs_spsr_ss(struct pt_regs *regs)
+static void clear_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(clear_regs_spsr_ss);
+NOKPROBE_SYMBOL(clear_user_regs_spsr_ss);
+
+#define set_regs_spsr_ss(r)	set_user_regs_spsr_ss(&(r)->user_regs)
+#define clear_regs_spsr_ss(r)	clear_user_regs_spsr_ss(&(r)->user_regs)
 
 static DEFINE_SPINLOCK(debug_hook_lock);
 static LIST_HEAD(user_step_hook);
@@ -393,17 +396,26 @@ void user_rewind_single_step(struct task_struct *task)
 	 * If single step is active for this thread, then set SPSR.SS
 	 * to 1 to avoid returning to the active-pending state.
 	 */
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		clear_regs_spsr_ss(task_pt_regs(task));
 }
 
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		set_user_regs_spsr_ss(regs);
+	else
+		clear_user_regs_spsr_ss(regs);
+}
+
 /* Kernel API */
 void kernel_enable_single_step(struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 0cfcf5c237c5..eef3dc2488e2 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -82,7 +82,8 @@
  * To prevent this from racing with the manipulation of the task's FPSIMD state
  * from task context and thereby corrupting the state, it is necessary to
  * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE
- * flag with local_bh_disable() unless softirqs are already masked.
+ * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to
+ * run but prevent them to use FPSIMD.
  *
  * For a certain task, the sequence may look something like this:
  * - the task gets scheduled in; if both the task's fpsimd_cpu field
@@ -145,6 +146,56 @@ extern void __percpu *efi_sve_state;
 
 #endif /* ! CONFIG_ARM64_SVE */
 
+DEFINE_PER_CPU(bool, fpsimd_context_busy);
+EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);
+
+static void __get_cpu_fpsimd_context(void)
+{
+	bool busy = __this_cpu_xchg(fpsimd_context_busy, true);
+
+	WARN_ON(busy);
+}
+
+/*
+ * Claim ownership of the CPU FPSIMD context for use by the calling context.
+ *
+ * The caller may freely manipulate the FPSIMD context metadata until
+ * put_cpu_fpsimd_context() is called.
+ *
+ * The double-underscore version must only be called if you know the task
+ * can't be preempted.
+ */
+static void get_cpu_fpsimd_context(void)
+{
+	preempt_disable();
+	__get_cpu_fpsimd_context();
+}
+
+static void __put_cpu_fpsimd_context(void)
+{
+	bool busy = __this_cpu_xchg(fpsimd_context_busy, false);
+
+	WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */
+}
+
+/*
+ * Release the CPU FPSIMD context.
+ *
+ * Must be called from a context in which get_cpu_fpsimd_context() was
+ * previously called, with no call to put_cpu_fpsimd_context() in the
+ * meantime.
+ */
+static void put_cpu_fpsimd_context(void)
+{
+	__put_cpu_fpsimd_context();
+	preempt_enable();
+}
+
+static bool have_cpu_fpsimd_context(void)
+{
+	return !preemptible() && __this_cpu_read(fpsimd_context_busy);
+}
+
 /*
  * Call __sve_free() directly only if you know task can't be scheduled
  * or preempted.
@@ -215,12 +266,11 @@ static void sve_free(struct task_struct *task)
  * This function should be called only when the FPSIMD/SVE state in
  * thread_struct is known to be up to date, when preparing to enter
  * userspace.
- *
- * Softirqs (and preemption) must be disabled.
  */
 static void task_fpsimd_load(void)
 {
-	WARN_ON(!in_softirq() && !irqs_disabled());
+	WARN_ON(!system_supports_fpsimd());
+	WARN_ON(!have_cpu_fpsimd_context());
 
 	if (system_supports_sve() && test_thread_flag(TIF_SVE))
 		sve_load_state(sve_pffr(&current->thread),
@@ -233,16 +283,15 @@ static void task_fpsimd_load(void)
 /*
  * Ensure FPSIMD/SVE storage in memory for the loaded context is up to
  * date with respect to the CPU registers.
- *
- * Softirqs (and preemption) must be disabled.
  */
-void fpsimd_save(void)
+static void fpsimd_save(void)
 {
 	struct fpsimd_last_state_struct const *last =
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
 
-	WARN_ON(!in_softirq() && !irqs_disabled());
+	WARN_ON(!system_supports_fpsimd());
+	WARN_ON(!have_cpu_fpsimd_context());
 
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
@@ -289,7 +338,7 @@ static unsigned int find_supported_vector_length(unsigned int vl)
 	return sve_vl_from_vq(__bit_to_vq(bit));
 }
 
-#ifdef CONFIG_SYSCTL
+#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL)
 
 static int sve_proc_do_default_vl(struct ctl_table *table, int write,
 				  void __user *buffer, size_t *lenp,
@@ -335,9 +384,9 @@ static int __init sve_sysctl_init(void)
 	return 0;
 }
 
-#else /* ! CONFIG_SYSCTL */
+#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 static int __init sve_sysctl_init(void) { return 0; }
-#endif /* ! CONFIG_SYSCTL */
+#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
@@ -364,7 +413,8 @@ static __uint128_t arm64_cpu_to_le128(__uint128_t x)
  * task->thread.sve_state.
  *
  * Task can be a non-runnable task, or current.  In the latter case,
- * softirqs (and preemption) must be disabled.
+ * the caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  * task->thread.sve_state must point to at least sve_state_size(task)
  * bytes of allocated kernel memory.
  * task->thread.uw.fpsimd_state must be up to date before calling this
@@ -393,7 +443,8 @@ static void fpsimd_to_sve(struct task_struct *task)
  * task->thread.uw.fpsimd_state.
  *
  * Task can be a non-runnable task, or current.  In the latter case,
- * softirqs (and preemption) must be disabled.
+ * the caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  * task->thread.sve_state must point to at least sve_state_size(task)
  * bytes of allocated kernel memory.
  * task->thread.sve_state must be up to date before calling this function.
@@ -557,7 +608,7 @@ int sve_set_vector_length(struct task_struct *task,
 	 * non-SVE thread.
 	 */
 	if (task == current) {
-		local_bh_disable();
+		get_cpu_fpsimd_context();
 
 		fpsimd_save();
 	}
@@ -567,7 +618,7 @@ int sve_set_vector_length(struct task_struct *task,
 		sve_to_fpsimd(task);
 
 	if (task == current)
-		local_bh_enable();
+		put_cpu_fpsimd_context();
 
 	/*
 	 * Force reallocation of task SVE state to the correct size
@@ -880,7 +931,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 
 	sve_alloc(current);
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	fpsimd_save();
 
@@ -891,7 +942,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 	if (test_and_set_thread_flag(TIF_SVE))
 		WARN_ON(1); /* SVE access shouldn't have trapped */
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -935,6 +986,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 	if (!system_supports_fpsimd())
 		return;
 
+	__get_cpu_fpsimd_context();
+
 	/* Save unsaved fpsimd state, if any: */
 	fpsimd_save();
 
@@ -949,6 +1002,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 	update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
 			       wrong_task || wrong_cpu);
+
+	__put_cpu_fpsimd_context();
 }
 
 void fpsimd_flush_thread(void)
@@ -958,7 +1013,7 @@ void fpsimd_flush_thread(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	fpsimd_flush_task_state(current);
 	memset(&current->thread.uw.fpsimd_state, 0,
@@ -999,7 +1054,7 @@ void fpsimd_flush_thread(void)
 			current->thread.sve_vl_onexec = 0;
 	}
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1011,9 +1066,9 @@ void fpsimd_preserve_current_state(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 	fpsimd_save();
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1030,13 +1085,15 @@ void fpsimd_signal_preserve_current_state(void)
 
 /*
  * Associate current's FPSIMD context with this cpu
- * Preemption must be disabled when calling this function.
+ * The caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  */
 void fpsimd_bind_task_to_cpu(void)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
 
+	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
 	last->sve_vl = current->thread.sve_vl;
@@ -1059,6 +1116,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
 
+	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
 	last->st = st;
@@ -1073,17 +1131,28 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
  */
 void fpsimd_restore_current_state(void)
 {
-	if (!system_supports_fpsimd())
+	/*
+	 * For the tasks that were created before we detected the absence of
+	 * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(),
+	 * e.g, init. This could be then inherited by the children processes.
+	 * If we later detect that the system doesn't support FP/SIMD,
+	 * we must clear the flag for  all the tasks to indicate that the
+	 * FPSTATE is clean (as we can't have one) to avoid looping for ever in
+	 * do_notify_resume().
+	 */
+	if (!system_supports_fpsimd()) {
+		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		return;
+	}
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		task_fpsimd_load();
 		fpsimd_bind_task_to_cpu();
 	}
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1093,10 +1162,10 @@ void fpsimd_restore_current_state(void)
  */
 void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 {
-	if (!system_supports_fpsimd())
+	if (WARN_ON(!system_supports_fpsimd()))
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	current->thread.uw.fpsimd_state = *state;
 	if (system_supports_sve() && test_thread_flag(TIF_SVE))
@@ -1107,7 +1176,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 
 	clear_thread_flag(TIF_FOREIGN_FPSTATE);
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1124,7 +1193,13 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 void fpsimd_flush_task_state(struct task_struct *t)
 {
 	t->thread.fpsimd_cpu = NR_CPUS;
-
+	/*
+	 * If we don't support fpsimd, bail out after we have
+	 * reset the fpsimd_cpu for this task and clear the
+	 * FPSTATE.
+	 */
+	if (!system_supports_fpsimd())
+		return;
 	barrier();
 	set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE);
 
@@ -1133,18 +1208,32 @@ void fpsimd_flush_task_state(struct task_struct *t)
 
 /*
  * Invalidate any task's FPSIMD state that is present on this cpu.
- * This function must be called with softirqs disabled.
+ * The FPSIMD context should be acquired with get_cpu_fpsimd_context()
+ * before calling this function.
  */
-void fpsimd_flush_cpu_state(void)
+static void fpsimd_flush_cpu_state(void)
 {
+	WARN_ON(!system_supports_fpsimd());
 	__this_cpu_write(fpsimd_last_state.st, NULL);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
 
-#ifdef CONFIG_KERNEL_MODE_NEON
+/*
+ * Save the FPSIMD state to memory and invalidate cpu view.
+ * This function must be called with preemption disabled.
+ */
+void fpsimd_save_and_flush_cpu_state(void)
+{
+	if (!system_supports_fpsimd())
+		return;
+	WARN_ON(preemptible());
+	__get_cpu_fpsimd_context();
+	fpsimd_save();
+	fpsimd_flush_cpu_state();
+	__put_cpu_fpsimd_context();
+}
 
-DEFINE_PER_CPU(bool, kernel_neon_busy);
-EXPORT_PER_CPU_SYMBOL(kernel_neon_busy);
+#ifdef CONFIG_KERNEL_MODE_NEON
 
 /*
  * Kernel-side NEON support functions
@@ -1170,19 +1259,13 @@ void kernel_neon_begin(void)
 
 	BUG_ON(!may_use_simd());
 
-	local_bh_disable();
-
-	__this_cpu_write(kernel_neon_busy, true);
+	get_cpu_fpsimd_context();
 
 	/* Save unsaved fpsimd state, if any: */
 	fpsimd_save();
 
 	/* Invalidate any task state remaining in the fpsimd regs: */
 	fpsimd_flush_cpu_state();
-
-	preempt_disable();
-
-	local_bh_enable();
 }
 EXPORT_SYMBOL(kernel_neon_begin);
 
@@ -1197,15 +1280,10 @@ EXPORT_SYMBOL(kernel_neon_begin);
  */
 void kernel_neon_end(void)
 {
-	bool busy;
-
 	if (!system_supports_fpsimd())
 		return;
 
-	busy = __this_cpu_xchg(kernel_neon_busy, false);
-	WARN_ON(!busy);	/* No matching kernel_neon_begin()? */
-
-	preempt_enable();
+	put_cpu_fpsimd_context();
 }
 EXPORT_SYMBOL(kernel_neon_end);
 
@@ -1297,8 +1375,7 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
 {
 	switch (cmd) {
 	case CPU_PM_ENTER:
-		fpsimd_save();
-		fpsimd_flush_cpu_state();
+		fpsimd_save_and_flush_cpu_state();
 		break;
 	case CPU_PM_EXIT:
 		break;
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2cdacd1c141b..191ad192a741 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -391,13 +391,19 @@ __create_page_tables:
 
 	/*
 	 * Since the page tables have been populated with non-cacheable
-	 * accesses (MMU disabled), invalidate the idmap and swapper page
-	 * tables again to remove any speculatively loaded cache lines.
+	 * accesses (MMU disabled), invalidate those tables again to
+	 * remove any speculatively loaded cache lines.
 	 */
+	dmb	sy
+
 	adrp	x0, idmap_pg_dir
+	adrp	x1, idmap_pg_end
+	sub	x1, x1, x0
+	bl	__inval_dcache_area
+
+	adrp	x0, init_pg_dir
 	adrp	x1, init_pg_end
 	sub	x1, x1, x0
-	dmb	sy
 	bl	__inval_dcache_area
 
 	ret	x28
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 67b3bae50b92..29eb4636d095 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -726,6 +726,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
 		return 0;
 }
 
+static int watchpoint_report(struct perf_event *wp, unsigned long addr,
+			     struct pt_regs *regs)
+{
+	int step = is_default_overflow_handler(wp);
+	struct arch_hw_breakpoint *info = counter_arch_bp(wp);
+
+	info->trigger = addr;
+
+	/*
+	 * If we triggered a user watchpoint from a uaccess routine, then
+	 * handle the stepping ourselves since userspace really can't help
+	 * us with this.
+	 */
+	if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0)
+		step = 1;
+	else
+		perf_bp_event(wp, regs);
+
+	return step;
+}
+
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -735,7 +756,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	u64 val;
 	struct perf_event *wp, **slots;
 	struct debug_info *debug_info;
-	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = this_cpu_ptr(wp_on_reg);
@@ -773,25 +793,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		if (dist != 0)
 			continue;
 
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
-
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
+		step = watchpoint_report(wp, addr, regs);
 	}
-	if (min_dist > 0 && min_dist != -1) {
-		/* No exact match found. */
-		wp = slots[closest_match];
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
 
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
-	}
+	/* No exact match found? */
+	if (min_dist > 0 && min_dist != -1)
+		step = watchpoint_report(slots[closest_match], addr, regs);
+
 	rcu_read_unlock();
 
 	if (!step)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 84b059ed04fc..63b511735e5c 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -1508,16 +1508,10 @@ static u32 aarch64_encode_immediate(u64 imm,
 				    u32 insn)
 {
 	unsigned int immr, imms, n, ones, ror, esz, tmp;
-	u64 mask = ~0UL;
-
-	/* Can't encode full zeroes or full ones */
-	if (!imm || !~imm)
-		return AARCH64_BREAK_FAULT;
+	u64 mask;
 
 	switch (variant) {
 	case AARCH64_INSN_VARIANT_32BIT:
-		if (upper_32_bits(imm))
-			return AARCH64_BREAK_FAULT;
 		esz = 32;
 		break;
 	case AARCH64_INSN_VARIANT_64BIT:
@@ -1529,6 +1523,12 @@ static u32 aarch64_encode_immediate(u64 imm,
 		return AARCH64_BREAK_FAULT;
 	}
 
+	mask = GENMASK(esz - 1, 0);
+
+	/* Can't encode full zeroes, full ones, or value wider than the mask */
+	if (!imm || imm == mask || imm & ~mask)
+		return AARCH64_BREAK_FAULT;
+
 	/*
 	 * Inverse of Replicate(). Try to spot a repeating pattern
 	 * with a pow2 stride.
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 43119922341f..1a157ca33262 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
-	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 0df8493624e0..cc049ff5c6a5 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -189,6 +189,7 @@ void machine_kexec(struct kimage *kimage)
 	 * the offline CPUs. Therefore, we must use the __* variant here.
 	 */
 	__flush_icache_range((uintptr_t)reboot_code_buffer,
+			     (uintptr_t)reboot_code_buffer +
 			     arm64_relocate_new_kernel_size);
 
 	/* Flush the kimage list and its buffers. */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 96e90e270042..1439cff99a28 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -154,7 +154,7 @@ armv8pmu_events_sysfs_show(struct device *dev,
 
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
 
-	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
 }
 
 #define ARMV8_EVENT_ATTR_RESOLVE(m) #m
@@ -303,10 +303,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,
 	    test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
 		return attr->mode;
 
-	pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
-	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
-	    test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap))
-		return attr->mode;
+	if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) {
+		u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+
+		if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+		    test_bit(id, cpu_pmu->pmceid_ext_bitmap))
+			return attr->mode;
+	}
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 0bbac612146e..7c6ae5cf0365 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 		return 0;
 
 	/*
-	 * Compat (i.e. 32 bit) mode:
-	 * - PC has been set in the pt_regs struct in kernel_entry,
-	 * - Handle SP and LR here.
+	 * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but
+	 * we're stuck with it for ABI compatability reasons.
+	 *
+	 * For a 32-bit consumer inspecting a 32-bit task, then it will look at
+	 * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h).
+	 * These correspond directly to a prefix of the registers saved in our
+	 * 'struct pt_regs', with the exception of the PC, so we copy that down
+	 * (x15 corresponds to SP_hyp in the architecture).
+	 *
+	 * So far, so good.
+	 *
+	 * The oddity arises when a 64-bit consumer looks at a 32-bit task and
+	 * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return
+	 * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and
+	 * PC registers would normally live. The initial idea was to allow a
+	 * 64-bit unwinder to unwind a 32-bit task and, although it's not clear
+	 * how well that works in practice, somebody might be relying on it.
+	 *
+	 * At the time we make a sample, we don't know whether the consumer is
+	 * 32-bit or 64-bit, so we have to cater for both possibilities.
 	 */
 	if (compat_user_mode(regs)) {
 		if ((u32)idx == PERF_REG_ARM64_SP)
 			return regs->compat_sp;
 		if ((u32)idx == PERF_REG_ARM64_LR)
 			return regs->compat_lr;
+		if (idx == 15)
+			return regs->pc;
 	}
 
 	if ((u32)idx == PERF_REG_ARM64_SP)
@@ -32,6 +51,10 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	if ((u32)idx == PERF_REG_ARM64_PC)
 		return regs->pc;
 
+	if (perf_reg_abi(current) == PERF_SAMPLE_REGS_ABI_32
+		&& idx == 15)
+		return regs->pc;
+
 	return regs->regs[idx];
 }
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 398601b29627..c6d7a2912e30 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -455,6 +455,13 @@ static void ssbs_thread_switch(struct task_struct *next)
 	if (unlikely(next->flags & PF_KTHREAD))
 		return;
 
+	/*
+	 * If all CPUs implement the SSBS extension, then we just need to
+	 * context-switch the PSTATE field.
+	 */
+	if (cpu_have_feature(cpu_feature(SSBS)))
+		return;
+
 	/* If the mitigation is enabled, then we leave SSBS clear. */
 	if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) ||
 	    test_tsk_thread_flag(next, TIF_SSBD))
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 85ee7d07889e..ea2d82bd93d8 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -76,7 +76,8 @@ static void cpu_psci_cpu_die(unsigned int cpu)
 
 static int cpu_psci_cpu_kill(unsigned int cpu)
 {
-	int err, i;
+	int err;
+	unsigned long start, end;
 
 	if (!psci_ops.affinity_info)
 		return 0;
@@ -86,16 +87,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	 * while it is dying. So, try again a few times.
 	 */
 
-	for (i = 0; i < 10; i++) {
+	start = jiffies;
+	end = start + msecs_to_jiffies(100);
+	do {
 		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
 		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
-			pr_info("CPU%d killed.\n", cpu);
+			pr_info("CPU%d killed (polled %d ms)\n", cpu,
+				jiffies_to_msecs(jiffies - start));
 			return 0;
 		}
 
-		msleep(10);
-		pr_info("Retrying again to check for CPU kill\n");
-	}
+		usleep_range(100, 1000);
+	} while (time_before(jiffies, end));
 
 	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
 			cpu, err);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index da2441d7b066..49bc065cf3f0 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -615,6 +615,13 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 	return 0;
 }
 
+static int fpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!system_supports_fpsimd())
+		return -ENODEV;
+	return regset->n;
+}
+
 /*
  * TODO: update fp accessors for lazy context switching (sync/flush hwstate)
  */
@@ -637,6 +644,9 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   void *kbuf, void __user *ubuf)
 {
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	if (target == current)
 		fpsimd_preserve_current_state();
 
@@ -676,6 +686,9 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 {
 	int ret;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0);
 	if (ret)
 		return ret;
@@ -1134,6 +1147,7 @@ static const struct user_regset aarch64_regsets[] = {
 		 */
 		.size = sizeof(u32),
 		.align = sizeof(u32),
+		.active = fpr_active,
 		.get = fpr_get,
 		.set = fpr_set
 	},
@@ -1348,6 +1362,9 @@ static int compat_vfp_get(struct task_struct *target,
 	compat_ulong_t fpscr;
 	int ret, vregs_end_pos;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	uregs = &target->thread.uw.fpsimd_state;
 
 	if (target == current)
@@ -1381,6 +1398,9 @@ static int compat_vfp_set(struct task_struct *target,
 	compat_ulong_t fpscr;
 	int ret, vregs_end_pos;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	uregs = &target->thread.uw.fpsimd_state;
 
 	vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t);
@@ -1438,6 +1458,7 @@ static const struct user_regset aarch32_regsets[] = {
 		.n = VFP_STATE_SIZE / sizeof(compat_ulong_t),
 		.size = sizeof(compat_ulong_t),
 		.align = sizeof(compat_ulong_t),
+		.active = fpr_active,
 		.get = compat_vfp_get,
 		.set = compat_vfp_set
 	},
@@ -1798,12 +1819,23 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	saved_reg = regs->regs[regno];
 	regs->regs[regno] = dir;
 
-	if (dir == PTRACE_SYSCALL_EXIT)
+	if (dir == PTRACE_SYSCALL_ENTER) {
+		if (tracehook_report_syscall_entry(regs))
+			forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else if (!test_thread_flag(TIF_SINGLESTEP)) {
 		tracehook_report_syscall_exit(regs, 0);
-	else if (tracehook_report_syscall_entry(regs))
-		forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else {
+		regs->regs[regno] = saved_reg;
 
-	regs->regs[regno] = saved_reg;
+		/*
+		 * Signal a pseudo-step exception since we are stepping but
+		 * tracer modifications to the registers may have rewound the
+		 * state machine.
+		 */
+		tracehook_report_syscall_exit(regs, 1);
+	}
 }
 
 int syscall_trace_enter(struct pt_regs *regs)
@@ -1826,12 +1858,14 @@ int syscall_trace_enter(struct pt_regs *regs)
 
 void syscall_trace_exit(struct pt_regs *regs)
 {
+	unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
 	audit_syscall_exit(regs);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (flags & _TIF_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, regs_return_value(regs));
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 
 	rseq_syscall(regs);
@@ -1909,8 +1943,8 @@ static int valid_native_regs(struct user_pt_regs *regs)
  */
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
-		regs->pstate &= ~DBG_SPSR_SS;
+	/* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */
+	user_regs_reset_single_step(regs, task);
 
 	if (is_compat_thread(task_thread_info(task)))
 		return valid_compat_regs(regs);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index dd2cdc0d5be2..ddb757b2c3e5 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -782,7 +782,6 @@ static void setup_restart_syscall(struct pt_regs *regs)
  */
 static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
 	sigset_t *oldset = sigmask_to_save();
 	int usig = ksig->sig;
 	int ret;
@@ -806,14 +805,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	 */
 	ret |= !valid_user_regs(&regs->user_regs, current);
 
-	/*
-	 * Fast forward the stepping logic so we step into the signal
-	 * handler.
-	 */
-	if (!ret)
-		user_fastforward_single_step(tsk);
-
-	signal_setup_done(ret, ksig, 0);
+	/* Step into the signal handler if we are stepping */
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
 
 /*
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a1aed6a1b8da..538b4ba66f5f 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -959,11 +959,22 @@ void tick_broadcast(const struct cpumask *mask)
 }
 #endif
 
+/*
+ * The number of CPUs online, not counting this CPU (which may not be
+ * fully online and so not counted in num_online_cpus()).
+ */
+static inline unsigned int num_other_online_cpus(void)
+{
+	unsigned int this_cpu_online = cpu_online(smp_processor_id());
+
+	return num_online_cpus() - this_cpu_online;
+}
+
 void smp_send_stop(void)
 {
 	unsigned long timeout;
 
-	if (num_online_cpus() > 1) {
+	if (num_other_online_cpus()) {
 		cpumask_t mask;
 
 		cpumask_copy(&mask, cpu_online_mask);
@@ -976,10 +987,10 @@ void smp_send_stop(void)
 
 	/* Wait up to one second for other CPUs to stop */
 	timeout = USEC_PER_SEC;
-	while (num_online_cpus() > 1 && timeout--)
+	while (num_other_online_cpus() && timeout--)
 		udelay(1);
 
-	if (num_online_cpus() > 1)
+	if (num_other_online_cpus())
 		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
 			   cpumask_pr_args(cpu_online_mask));
 
@@ -1002,7 +1013,11 @@ void crash_smp_send_stop(void)
 
 	cpus_stopped = 1;
 
-	if (num_online_cpus() == 1) {
+	/*
+	 * 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;
 	}
@@ -1010,7 +1025,7 @@ void crash_smp_send_stop(void)
 	cpumask_copy(&mask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &mask);
 
-	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+	atomic_set(&waiting_for_crash_ipi, num_other_online_cpus());
 
 	pr_crit("SMP: stopping secondary CPUs\n");
 	smp_cross_call(&mask, IPI_CPU_CRASH_STOP);
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index f1cb64959427..3c18c2454089 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/compat.h>
+#include <linux/cpufeature.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
@@ -17,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/system_misc.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 
 static long
@@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
+		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+			/*
+			 * The workaround requires an inner-shareable tlbi.
+			 * We pick the reserved-ASID to minimise the impact.
+			 */
+			__tlbi(aside1is, __TLBI_VADDR(0, 0));
+			dsb(ish);
+		}
+
 		ret = __flush_cache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 871c739f060a..1457a0ba83db 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = do_ni_syscall(regs, scno);
 	}
 
+	if (is_compat_task())
+		ret = lower_32_bits(ret);
+
 	regs->regs[0] = ret;
 }
 
@@ -121,7 +124,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags)) {
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
 			/*
 			 * We're off to userspace, where interrupts are
 			 * always enabled after we restore the flags from
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index b6706a886037..7788e4ea131b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -480,6 +480,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		/* Hide DIC so that we can trap the unnecessary maintenance...*/
+		val &= ~BIT(CTR_DIC_SHIFT);
+
+		/* ... and fake IminLine to reduce the number of traps. */
+		val &= ~CTR_IMINLINE_MASK;
+		val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK;
+	}
+
 	pt_regs_write_reg(regs, rt, val);
 
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 803b24d2464a..61d63657ab59 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -142,6 +142,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	idmap_pg_dir = .;
 	. += IDMAP_DIR_SIZE;
+	idmap_pg_end = .;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	tramp_pg_dir = .;
@@ -171,9 +172,6 @@ SECTIONS
 		*(.altinstructions)
 		__alt_instructions_end = .;
 	}
-	.altinstr_replacement : {
-		*(.altinstr_replacement)
-	}
 
 	. = ALIGN(PAGE_SIZE);
 	__inittext_end = .;