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

Pull arm64 updates from Catalin Marinas:

 - arm64 support for syscall emulation via PTRACE_SYSEMU{,_SINGLESTEP}

 - Wire up VM_FLUSH_RESET_PERMS for arm64, allowing the core code to
   manage the permissions of executable vmalloc regions more strictly

 - Slight performance improvement by keeping softirqs enabled while
   touching the FPSIMD/SVE state (kernel_neon_begin/end)

 - Expose a couple of ARMv8.5 features to user (HWCAP): CondM (new
   XAFLAG and AXFLAG instructions for floating point comparison flags
   manipulation) and FRINT (rounding floating point numbers to integers)

 - Re-instate ARM64_PSEUDO_NMI support which was previously marked as
   BROKEN due to some bugs (now fixed)

 - Improve parking of stopped CPUs and implement an arm64-specific
   panic_smp_self_stop() to avoid warning on not being able to stop
   secondary CPUs during panic

 - perf: enable the ARM Statistical Profiling Extensions (SPE) on ACPI
   platforms

 - perf: DDR performance monitor support for iMX8QXP

 - cache_line_size() can now be set from DT or ACPI/PPTT if provided to
   cope with a system cache info not exposed via the CPUID registers

 - Avoid warning on hardware cache line size greater than
   ARCH_DMA_MINALIGN if the system is fully coherent

 - arm64 do_page_fault() and hugetlb cleanups

 - Refactor set_pte_at() to avoid redundant READ_ONCE(*ptep)

 - Ignore ACPI 5.1 FADTs reported as 5.0 (infer from the
   'arm_boot_flags' introduced in 5.1)

 - CONFIG_RANDOMIZE_BASE now enabled in defconfig

 - Allow the selection of ARM64_MODULE_PLTS, currently only done via
   RANDOMIZE_BASE (and an erratum workaround), allowing modules to spill
   over into the vmalloc area

 - Make ZONE_DMA32 configurable

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (54 commits)
  perf: arm_spe: Enable ACPI/Platform automatic module loading
  arm_pmu: acpi: spe: Add initial MADT/SPE probing
  ACPI/PPTT: Add function to return ACPI 6.3 Identical tokens
  ACPI/PPTT: Modify node flag detection to find last IDENTICAL
  x86/entry: Simplify _TIF_SYSCALL_EMU handling
  arm64: rename dump_instr as dump_kernel_instr
  arm64/mm: Drop [PTE|PMD]_TYPE_FAULT
  arm64: Implement panic_smp_self_stop()
  arm64: Improve parking of stopped CPUs
  arm64: Expose FRINT capabilities to userspace
  arm64: Expose ARMv8.5 CondM capability to userspace
  arm64: defconfig: enable CONFIG_RANDOMIZE_BASE
  arm64: ARM64_MODULES_PLTS must depend on MODULES
  arm64: bpf: do not allocate executable memory
  arm64/kprobes: set VM_FLUSH_RESET_PERMS on kprobe instruction pages
  arm64/mm: wire up CONFIG_ARCH_HAS_SET_DIRECT_MAP
  arm64: module: create module allocations without exec permissions
  arm64: Allow user selection of ARM64_MODULE_PLTS
  acpi/arm64: ignore 5.1 FADTs that are reported as 5.0
  arm64: Allow selecting Pseudo-NMI again
  ...

14 files changed, 245 insertions, 101 deletions

diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 2804330c95dc..3a58e9db5cfe 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -152,10 +152,14 @@ static int __init acpi_fadt_sanity_check(void)
 	 */
 	if (table->revision < 5 ||
 	   (table->revision == 5 && fadt->minor_revision < 1)) {
-		pr_err("Unsupported FADT revision %d.%d, should be 5.1+\n",
+		pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 5.1+\n",
 		       table->revision, fadt->minor_revision);
-		ret = -EINVAL;
-		goto out;
+
+		if (!fadt->arm_boot_flags) {
+			ret = -EINVAL;
+			goto out;
+		}
+		pr_err("FADT has ARM boot flags set, assuming 5.1\n");
 	}
 
 	if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) {
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index 880d79904d36..7fa6828bb488 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -17,6 +17,15 @@
 #define CLIDR_CTYPE(clidr, level)	\
 	(((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
 
+int cache_line_size(void)
+{
+	if (coherency_max_size != 0)
+		return coherency_max_size;
+
+	return cache_line_size_of_cpu();
+}
+EXPORT_SYMBOL_GPL(cache_line_size);
+
 static inline enum cache_type get_cache_type(int level)
 {
 	u64 clidr;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index aabdabf52fdb..f29f36a65175 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1184,14 +1184,14 @@ static struct undef_hook ssbs_emulation_hook = {
 static void cpu_enable_ssbs(const struct arm64_cpu_capabilities *__unused)
 {
 	static bool undef_hook_registered = false;
-	static DEFINE_SPINLOCK(hook_lock);
+	static DEFINE_RAW_SPINLOCK(hook_lock);
 
-	spin_lock(&hook_lock);
+	raw_spin_lock(&hook_lock);
 	if (!undef_hook_registered) {
 		register_undef_hook(&ssbs_emulation_hook);
 		undef_hook_registered = true;
 	}
-	spin_unlock(&hook_lock);
+	raw_spin_unlock(&hook_lock);
 
 	if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
 		sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
@@ -1618,6 +1618,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
@@ -1629,6 +1630,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
 	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 0593665fc7b4..876055e37352 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -82,6 +82,8 @@ static const char *const hwcap_str[] = {
 	"svebitperm",
 	"svesha3",
 	"svesm4",
+	"flagm2",
+	"frint",
 	NULL
 };
 
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 2df8d0a1d980..9cdc4592da3e 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -247,6 +247,7 @@ alternative_else_nop_endif
 	/*
 	 * Registers that may be useful after this macro is invoked:
 	 *
+	 * x20 - ICC_PMR_EL1
 	 * x21 - aborted SP
 	 * x22 - aborted PC
 	 * x23 - aborted PSTATE
@@ -424,6 +425,38 @@ tsk	.req	x28		// current thread_info
 	irq_stack_exit
 	.endm
 
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	/*
+	 * Set res to 0 if irqs were unmasked in interrupted context.
+	 * Otherwise set res to non-0 value.
+	 */
+	.macro	test_irqs_unmasked res:req, pmr:req
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	sub	\res, \pmr, #GIC_PRIO_IRQON
+alternative_else
+	mov	\res, xzr
+alternative_endif
+	.endm
+#endif
+
+	.macro	gic_prio_kentry_setup, tmp:req
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	mov	\tmp, #(GIC_PRIO_PSR_I_SET | GIC_PRIO_IRQON)
+	msr_s	SYS_ICC_PMR_EL1, \tmp
+	alternative_else_nop_endif
+#endif
+	.endm
+
+	.macro	gic_prio_irq_setup, pmr:req, tmp:req
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	orr	\tmp, \pmr, #GIC_PRIO_PSR_I_SET
+	msr_s	SYS_ICC_PMR_EL1, \tmp
+	alternative_else_nop_endif
+#endif
+	.endm
+
 	.text
 
 /*
@@ -602,6 +635,7 @@ el1_dbg:
 	cmp	x24, #ESR_ELx_EC_BRK64		// if BRK64
 	cinc	x24, x24, eq			// set bit '0'
 	tbz	x24, #0, el1_inv		// EL1 only
+	gic_prio_kentry_setup tmp=x3
 	mrs	x0, far_el1
 	mov	x2, sp				// struct pt_regs
 	bl	do_debug_exception
@@ -619,20 +653,18 @@ ENDPROC(el1_sync)
 	.align	6
 el1_irq:
 	kernel_entry 1
+	gic_prio_irq_setup pmr=x20, tmp=x1
 	enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
+
 #ifdef CONFIG_ARM64_PSEUDO_NMI
-alternative_if ARM64_HAS_IRQ_PRIO_MASKING
-	ldr	x20, [sp, #S_PMR_SAVE]
-alternative_else
-	mov	x20, #GIC_PRIO_IRQON
-alternative_endif
-	cmp	x20, #GIC_PRIO_IRQOFF
-	/* Irqs were disabled, don't trace */
-	b.ls	1f
+	test_irqs_unmasked	res=x0, pmr=x20
+	cbz	x0, 1f
+	bl	asm_nmi_enter
+1:
 #endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
-1:
 #endif
 
 	irq_handler
@@ -651,14 +683,23 @@ alternative_else_nop_endif
 	bl	preempt_schedule_irq		// irq en/disable is done inside
 1:
 #endif
-#ifdef CONFIG_TRACE_IRQFLAGS
+
 #ifdef CONFIG_ARM64_PSEUDO_NMI
 	/*
-	 * if IRQs were disabled when we received the interrupt, we have an NMI
-	 * and we are not re-enabling interrupt upon eret. Skip tracing.
+	 * When using IRQ priority masking, we can get spurious interrupts while
+	 * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a
+	 * section with interrupts disabled. Skip tracing in those cases.
 	 */
-	cmp	x20, #GIC_PRIO_IRQOFF
-	b.ls	1f
+	test_irqs_unmasked	res=x0, pmr=x20
+	cbz	x0, 1f
+	bl	asm_nmi_exit
+1:
+#endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	test_irqs_unmasked	res=x0, pmr=x20
+	cbnz	x0, 1f
 #endif
 	bl	trace_hardirqs_on
 1:
@@ -776,6 +817,7 @@ el0_ia:
 	 * Instruction abort handling
 	 */
 	mrs	x26, far_el1
+	gic_prio_kentry_setup tmp=x0
 	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -821,6 +863,7 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x26, far_el1
+	gic_prio_kentry_setup tmp=x0
 	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -855,11 +898,12 @@ el0_dbg:
 	 * Debug exception handling
 	 */
 	tbnz	x24, #0, el0_inv		// EL0 only
+	gic_prio_kentry_setup tmp=x3
 	mrs	x0, far_el1
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_debug_exception
-	enable_daif
+	enable_da_f
 	ct_user_exit
 	b	ret_to_user
 el0_inv:
@@ -876,7 +920,9 @@ ENDPROC(el0_sync)
 el0_irq:
 	kernel_entry 0
 el0_irq_naked:
+	gic_prio_irq_setup pmr=x20, tmp=x0
 	enable_da_f
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
@@ -898,6 +944,7 @@ ENDPROC(el0_irq)
 el1_error:
 	kernel_entry 1
 	mrs	x1, esr_el1
+	gic_prio_kentry_setup tmp=x2
 	enable_dbg
 	mov	x0, sp
 	bl	do_serror
@@ -908,10 +955,11 @@ el0_error:
 	kernel_entry 0
 el0_error_naked:
 	mrs	x1, esr_el1
+	gic_prio_kentry_setup tmp=x2
 	enable_dbg
 	mov	x0, sp
 	bl	do_serror
-	enable_daif
+	enable_da_f
 	ct_user_exit
 	b	ret_to_user
 ENDPROC(el0_error)
@@ -932,6 +980,7 @@ work_pending:
  */
 ret_to_user:
 	disable_daif
+	gic_prio_kentry_setup tmp=x3
 	ldr	x1, [tsk, #TSK_TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
@@ -948,6 +997,7 @@ ENDPROC(ret_to_user)
  */
 	.align	6
 el0_svc:
+	gic_prio_kentry_setup tmp=x1
 	mov	x0, sp
 	bl	el0_svc_handler
 	b	ret_to_user
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 0cfcf5c237c5..eec4776ae5f0 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 +266,10 @@ 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(!have_cpu_fpsimd_context());
 
 	if (system_supports_sve() && test_thread_flag(TIF_SVE))
 		sve_load_state(sve_pffr(&current->thread),
@@ -233,16 +282,14 @@ 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(!have_cpu_fpsimd_context());
 
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
@@ -364,7 +411,8 @@ 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 +441,8 @@ 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 +606,7 @@ 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 +616,7 @@ 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 +929,7 @@ 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 +940,7 @@ 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 +984,8 @@ 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 +1000,8 @@ 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 +1011,7 @@ 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 +1052,7 @@ void fpsimd_flush_thread(void)
 			current->thread.sve_vl_onexec = 0;
 	}
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1011,9 +1064,9 @@ 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();
 }
 
 /*
@@ -1030,7 +1083,8 @@ 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)
 {
@@ -1076,14 +1130,14 @@ void fpsimd_restore_current_state(void)
 	if (!system_supports_fpsimd())
 		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();
 }
 
 /*
@@ -1096,7 +1150,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 	if (!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 +1161,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 
 	clear_thread_flag(TIF_FOREIGN_FPSTATE);
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1133,18 +1187,29 @@ 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)
 {
 	__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)
+{
+	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 +1235,13 @@ 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 +1256,10 @@ 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 +1351,7 @@ 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/irq.c b/arch/arm64/kernel/irq.c
index c70034fbd4ce..04a327ccf84d 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -16,8 +16,10 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/irqchip.h>
+#include <linux/kprobes.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <asm/daifflags.h>
 #include <asm/vmap_stack.h>
 
 unsigned long irq_err_count;
@@ -64,4 +66,28 @@ void __init init_IRQ(void)
 	irqchip_init();
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
+
+	if (system_uses_irq_prio_masking()) {
+		/*
+		 * Now that we have a stack for our IRQ handler, set
+		 * the PMR/PSR pair to a consistent state.
+		 */
+		WARN_ON(read_sysreg(daif) & PSR_A_BIT);
+		local_daif_restore(DAIF_PROCCTX_NOIRQ);
+	}
+}
+
+/*
+ * Stubs to make nmi_enter/exit() code callable from ASM
+ */
+asmlinkage void notrace asm_nmi_enter(void)
+{
+	nmi_enter();
+}
+NOKPROBE_SYMBOL(asm_nmi_enter);
+
+asmlinkage void notrace asm_nmi_exit(void)
+{
+	nmi_exit();
 }
+NOKPROBE_SYMBOL(asm_nmi_exit);
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 71530e080ecc..46e643e30708 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -34,7 +34,7 @@ void *module_alloc(unsigned long size)
 		module_alloc_end = MODULES_END;
 
 	p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
-				module_alloc_end, gfp_mask, PAGE_KERNEL_EXEC, 0,
+				module_alloc_end, gfp_mask, PAGE_KERNEL, 0,
 				NUMA_NO_NODE, __builtin_return_address(0));
 
 	if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
@@ -50,7 +50,7 @@ void *module_alloc(unsigned long size)
 		 */
 		p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
 				module_alloc_base + SZ_2G, GFP_KERNEL,
-				PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				PAGE_KERNEL, 0, NUMA_NO_NODE,
 				__builtin_return_address(0));
 
 	if (p && (kasan_module_alloc(p, size) < 0)) {
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 88ce502c8e6f..bd5dfffca272 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -122,8 +122,10 @@ void *alloc_insn_page(void)
 	void *page;
 
 	page = vmalloc_exec(PAGE_SIZE);
-	if (page)
+	if (page) {
 		set_memory_ro((unsigned long)page, 1);
+		set_vm_flush_reset_perms(page);
+	}
 
 	return page;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 9856395ccdb7..6a869d9f304f 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -83,7 +83,7 @@ static void __cpu_do_idle_irqprio(void)
 	 * be raised.
 	 */
 	pmr = gic_read_pmr();
-	gic_write_pmr(GIC_PRIO_IRQON);
+	gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 
 	__cpu_do_idle();
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index da2441d7b066..3cf3b135027e 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1808,8 +1808,12 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 
 int syscall_trace_enter(struct pt_regs *regs)
 {
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (test_thread_flag(TIF_SYSCALL_TRACE) ||
+		test_thread_flag(TIF_SYSCALL_EMU)) {
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+		if (!in_syscall(regs) || test_thread_flag(TIF_SYSCALL_EMU))
+			return -1;
+	}
 
 	/* Do the secure computing after ptrace; failures should be fast. */
 	if (secure_computing(NULL) == -1)
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 3e53ffa07994..f5b04dd8a710 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -27,7 +27,7 @@
  *	aff0 = mpidr_masked & 0xff;
  *	aff1 = mpidr_masked & 0xff00;
  *	aff2 = mpidr_masked & 0xff0000;
- *	aff2 = mpidr_masked & 0xff00000000;
+ *	aff3 = mpidr_masked & 0xff00000000;
  *	dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2 | aff3 >> rs3);
  *}
  * Input registers: rs0, rs1, rs2, rs3, mpidr, mask
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 6dcf9607d770..9286ee6749e8 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -181,11 +181,7 @@ static void init_gic_priority_masking(void)
 
 	WARN_ON(!(cpuflags & PSR_I_BIT));
 
-	gic_write_pmr(GIC_PRIO_IRQOFF);
-
-	/* We can only unmask PSR.I if we can take aborts */
-	if (!(cpuflags & PSR_A_BIT))
-		write_sysreg(cpuflags & ~PSR_I_BIT, daif);
+	gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 }
 
 /*
@@ -834,18 +830,23 @@ void arch_irq_work_raise(void)
 }
 #endif
 
-/*
- * ipi_cpu_stop - handle IPI from smp_send_stop()
- */
-static void ipi_cpu_stop(unsigned int cpu)
+static void local_cpu_stop(void)
 {
-	set_cpu_online(cpu, false);
+	set_cpu_online(smp_processor_id(), false);
 
 	local_daif_mask();
 	sdei_mask_local_cpu();
+	cpu_park_loop();
+}
 
-	while (1)
-		cpu_relax();
+/*
+ * We need to implement panic_smp_self_stop() for parallel panic() calls, so
+ * that cpu_online_mask gets correctly updated and smp_send_stop() can skip
+ * CPUs that have already stopped themselves.
+ */
+void panic_smp_self_stop(void)
+{
+	local_cpu_stop();
 }
 
 #ifdef CONFIG_KEXEC_CORE
@@ -898,7 +899,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 
 	case IPI_CPU_STOP:
 		irq_enter();
-		ipi_cpu_stop(cpu);
+		local_cpu_stop();
 		irq_exit();
 		break;
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 985721a1264c..a835a1a53826 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -55,16 +55,19 @@ static void dump_backtrace_entry(unsigned long where)
 	printk(" %pS\n", (void *)where);
 }
 
-static void __dump_instr(const char *lvl, struct pt_regs *regs)
+static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
 	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
 	int i;
 
+	if (user_mode(regs))
+		return;
+
 	for (i = -4; i < 1; i++) {
 		unsigned int val, bad;
 
-		bad = get_user(val, &((u32 *)addr)[i]);
+		bad = aarch64_insn_read(&((u32 *)addr)[i], &val);
 
 		if (!bad)
 			p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val);
@@ -73,19 +76,8 @@ static void __dump_instr(const char *lvl, struct pt_regs *regs)
 			break;
 		}
 	}
-	printk("%sCode: %s\n", lvl, str);
-}
 
-static void dump_instr(const char *lvl, struct pt_regs *regs)
-{
-	if (!user_mode(regs)) {
-		mm_segment_t fs = get_fs();
-		set_fs(KERNEL_DS);
-		__dump_instr(lvl, regs);
-		set_fs(fs);
-	} else {
-		__dump_instr(lvl, regs);
-	}
+	printk("%sCode: %s\n", lvl, str);
 }
 
 void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
@@ -171,8 +163,7 @@ static int __die(const char *str, int err, struct pt_regs *regs)
 	print_modules();
 	show_regs(regs);
 
-	if (!user_mode(regs))
-		dump_instr(KERN_EMERG, regs);
+	dump_kernel_instr(KERN_EMERG, regs);
 
 	return ret;
 }