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
  ...

19 files changed, 174 insertions, 106 deletions

diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index ada0bc480a1b..b263e239cb59 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -38,6 +38,9 @@
 	(!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \
 	(unsigned long)(entry) + (entry)->header.length > (end))
 
+#define ACPI_MADT_GICC_SPE  (ACPI_OFFSET(struct acpi_madt_generic_interrupt, \
+	spe_interrupt) + sizeof(u16))
+
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
 pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 2247908e55d6..79155a8cfe7c 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -152,7 +152,9 @@ static inline bool gic_prio_masking_enabled(void)
 
 static inline void gic_pmr_mask_irqs(void)
 {
-	BUILD_BUG_ON(GICD_INT_DEF_PRI <= GIC_PRIO_IRQOFF);
+	BUILD_BUG_ON(GICD_INT_DEF_PRI < (GIC_PRIO_IRQOFF |
+					 GIC_PRIO_PSR_I_SET));
+	BUILD_BUG_ON(GICD_INT_DEF_PRI >= GIC_PRIO_IRQON);
 	gic_write_pmr(GIC_PRIO_IRQOFF);
 }
 
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index a05db636981a..64eeaa41e7ca 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -80,12 +80,15 @@ static inline u32 cache_type_cwg(void)
 
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
-static inline int cache_line_size(void)
+static inline int cache_line_size_of_cpu(void)
 {
 	u32 cwg = cache_type_cwg();
+
 	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
 }
 
+int cache_line_size(void);
+
 /*
  * Read the effective value of CTR_EL0.
  *
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 1fe4467442aa..665c78e0665a 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -176,4 +176,7 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 
 int set_memory_valid(unsigned long addr, int numpages, int enable);
 
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+
 #endif
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 373799b7982f..3d8db50d9ae2 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -614,6 +614,12 @@ static inline bool system_uses_irq_prio_masking(void)
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
 }
 
+static inline bool system_has_prio_mask_debugging(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) &&
+	       system_uses_irq_prio_masking();
+}
+
 #define ARM64_SSBD_UNKNOWN		-1
 #define ARM64_SSBD_FORCE_DISABLE	0
 #define ARM64_SSBD_KERNEL		1
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index 6dd8a8723525..987926ed535e 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -7,6 +7,7 @@
 
 #include <linux/irqflags.h>
 
+#include <asm/arch_gicv3.h>
 #include <asm/cpufeature.h>
 
 #define DAIF_PROCCTX		0
@@ -16,11 +17,20 @@
 /* mask/save/unmask/restore all exceptions, including interrupts. */
 static inline void local_daif_mask(void)
 {
+	WARN_ON(system_has_prio_mask_debugging() &&
+		(read_sysreg_s(SYS_ICC_PMR_EL1) == (GIC_PRIO_IRQOFF |
+						    GIC_PRIO_PSR_I_SET)));
+
 	asm volatile(
 		"msr	daifset, #0xf		// local_daif_mask\n"
 		:
 		:
 		: "memory");
+
+	/* Don't really care for a dsb here, we don't intend to enable IRQs */
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
 	trace_hardirqs_off();
 }
 
@@ -32,7 +42,7 @@ static inline unsigned long local_daif_save(void)
 
 	if (system_uses_irq_prio_masking()) {
 		/* If IRQs are masked with PMR, reflect it in the flags */
-		if (read_sysreg_s(SYS_ICC_PMR_EL1) <= GIC_PRIO_IRQOFF)
+		if (read_sysreg_s(SYS_ICC_PMR_EL1) != GIC_PRIO_IRQON)
 			flags |= PSR_I_BIT;
 	}
 
@@ -45,39 +55,50 @@ static inline void local_daif_restore(unsigned long flags)
 {
 	bool irq_disabled = flags & PSR_I_BIT;
 
+	WARN_ON(system_has_prio_mask_debugging() &&
+		!(read_sysreg(daif) & PSR_I_BIT));
+
 	if (!irq_disabled) {
 		trace_hardirqs_on();
 
-		if (system_uses_irq_prio_masking())
-			arch_local_irq_enable();
-	} else if (!(flags & PSR_A_BIT)) {
-		/*
-		 * If interrupts are disabled but we can take
-		 * asynchronous errors, we can take NMIs
-		 */
 		if (system_uses_irq_prio_masking()) {
-			flags &= ~PSR_I_BIT;
+			gic_write_pmr(GIC_PRIO_IRQON);
+			dsb(sy);
+		}
+	} else if (system_uses_irq_prio_masking()) {
+		u64 pmr;
+
+		if (!(flags & PSR_A_BIT)) {
 			/*
-			 * There has been concern that the write to daif
-			 * might be reordered before this write to PMR.
-			 * From the ARM ARM DDI 0487D.a, section D1.7.1
-			 * "Accessing PSTATE fields":
-			 *   Writes to the PSTATE fields have side-effects on
-			 *   various aspects of the PE operation. All of these
-			 *   side-effects are guaranteed:
-			 *     - Not to be visible to earlier instructions in
-			 *       the execution stream.
-			 *     - To be visible to later instructions in the
-			 *       execution stream
-			 *
-			 * Also, writes to PMR are self-synchronizing, so no
-			 * interrupts with a lower priority than PMR is signaled
-			 * to the PE after the write.
-			 *
-			 * So we don't need additional synchronization here.
+			 * If interrupts are disabled but we can take
+			 * asynchronous errors, we can take NMIs
 			 */
-			arch_local_irq_disable();
+			flags &= ~PSR_I_BIT;
+			pmr = GIC_PRIO_IRQOFF;
+		} else {
+			pmr = GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET;
 		}
+
+		/*
+		 * There has been concern that the write to daif
+		 * might be reordered before this write to PMR.
+		 * From the ARM ARM DDI 0487D.a, section D1.7.1
+		 * "Accessing PSTATE fields":
+		 *   Writes to the PSTATE fields have side-effects on
+		 *   various aspects of the PE operation. All of these
+		 *   side-effects are guaranteed:
+		 *     - Not to be visible to earlier instructions in
+		 *       the execution stream.
+		 *     - To be visible to later instructions in the
+		 *       execution stream
+		 *
+		 * Also, writes to PMR are self-synchronizing, so no
+		 * interrupts with a lower priority than PMR is signaled
+		 * to the PE after the write.
+		 *
+		 * So we don't need additional synchronization here.
+		 */
+		gic_write_pmr(pmr);
 	}
 
 	write_sysreg(flags, daif);
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 897029c8e9b5..b6a2c352f4c3 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -37,8 +37,6 @@ struct task_struct;
 extern void fpsimd_save_state(struct user_fpsimd_state *state);
 extern void fpsimd_load_state(struct user_fpsimd_state *state);
 
-extern void fpsimd_save(void);
-
 extern void fpsimd_thread_switch(struct task_struct *next);
 extern void fpsimd_flush_thread(void);
 
@@ -52,8 +50,7 @@ extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 				     void *sve_state, unsigned int sve_vl);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
-extern void fpsimd_flush_cpu_state(void);
-extern void sve_flush_cpu_state(void);
+extern void fpsimd_save_and_flush_cpu_state(void);
 
 /* Maximum VL that SVE VL-agnostic software can transparently support */
 #define SVE_VL_ARCH_MAX 0x100
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index e5d9420cd258..3d2f2472a36c 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -84,6 +84,8 @@
 #define KERNEL_HWCAP_SVEBITPERM		__khwcap2_feature(SVEBITPERM)
 #define KERNEL_HWCAP_SVESHA3		__khwcap2_feature(SVESHA3)
 #define KERNEL_HWCAP_SVESM4		__khwcap2_feature(SVESM4)
+#define KERNEL_HWCAP_FLAGM2		__khwcap2_feature(FLAGM2)
+#define KERNEL_HWCAP_FRINT		__khwcap2_feature(FRINT)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 66853fde60f9..7872f260c9ee 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -29,6 +29,12 @@
  */
 static inline void arch_local_irq_enable(void)
 {
+	if (system_has_prio_mask_debugging()) {
+		u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1);
+
+		WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF);
+	}
+
 	asm volatile(ALTERNATIVE(
 		"msr	daifclr, #2		// arch_local_irq_enable\n"
 		"nop",
@@ -42,6 +48,12 @@ static inline void arch_local_irq_enable(void)
 
 static inline void arch_local_irq_disable(void)
 {
+	if (system_has_prio_mask_debugging()) {
+		u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1);
+
+		WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF);
+	}
+
 	asm volatile(ALTERNATIVE(
 		"msr	daifset, #2		// arch_local_irq_disable",
 		__msr_s(SYS_ICC_PMR_EL1, "%0"),
@@ -56,43 +68,46 @@ static inline void arch_local_irq_disable(void)
  */
 static inline unsigned long arch_local_save_flags(void)
 {
-	unsigned long daif_bits;
 	unsigned long flags;
 
-	daif_bits = read_sysreg(daif);
-
-	/*
-	 * The asm is logically equivalent to:
-	 *
-	 * if (system_uses_irq_prio_masking())
-	 *	flags = (daif_bits & PSR_I_BIT) ?
-	 *			GIC_PRIO_IRQOFF :
-	 *			read_sysreg_s(SYS_ICC_PMR_EL1);
-	 * else
-	 *	flags = daif_bits;
-	 */
 	asm volatile(ALTERNATIVE(
-			"mov	%0, %1\n"
-			"nop\n"
-			"nop",
-			__mrs_s("%0", SYS_ICC_PMR_EL1)
-			"ands	%1, %1, " __stringify(PSR_I_BIT) "\n"
-			"csel	%0, %0, %2, eq",
-			ARM64_HAS_IRQ_PRIO_MASKING)
-		: "=&r" (flags), "+r" (daif_bits)
-		: "r" ((unsigned long) GIC_PRIO_IRQOFF)
+		"mrs	%0, daif",
+		__mrs_s("%0", SYS_ICC_PMR_EL1),
+		ARM64_HAS_IRQ_PRIO_MASKING)
+		: "=&r" (flags)
+		:
 		: "memory");
 
 	return flags;
 }
 
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	int res;
+
+	asm volatile(ALTERNATIVE(
+		"and	%w0, %w1, #" __stringify(PSR_I_BIT),
+		"eor	%w0, %w1, #" __stringify(GIC_PRIO_IRQON),
+		ARM64_HAS_IRQ_PRIO_MASKING)
+		: "=&r" (res)
+		: "r" ((int) flags)
+		: "memory");
+
+	return res;
+}
+
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
 
 	flags = arch_local_save_flags();
 
-	arch_local_irq_disable();
+	/*
+	 * There are too many states with IRQs disabled, just keep the current
+	 * state if interrupts are already disabled/masked.
+	 */
+	if (!arch_irqs_disabled_flags(flags))
+		arch_local_irq_disable();
 
 	return flags;
 }
@@ -108,26 +123,10 @@ static inline void arch_local_irq_restore(unsigned long flags)
 			__msr_s(SYS_ICC_PMR_EL1, "%0")
 			"dsb	sy",
 			ARM64_HAS_IRQ_PRIO_MASKING)
-		: "+r" (flags)
 		:
+		: "r" (flags)
 		: "memory");
 }
 
-static inline int arch_irqs_disabled_flags(unsigned long flags)
-{
-	int res;
-
-	asm volatile(ALTERNATIVE(
-			"and	%w0, %w1, #" __stringify(PSR_I_BIT) "\n"
-			"nop",
-			"cmp	%w1, #" __stringify(GIC_PRIO_IRQOFF) "\n"
-			"cset	%w0, ls",
-			ARM64_HAS_IRQ_PRIO_MASKING)
-		: "=&r" (res)
-		: "r" ((int) flags)
-		: "memory");
-
-	return res;
-}
 #endif
 #endif
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index c328191aa202..9f19c354b165 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -597,11 +597,12 @@ static inline void kvm_arm_vhe_guest_enter(void)
 	 * will not signal the CPU of interrupts of lower priority, and the
 	 * only way to get out will be via guest exceptions.
 	 * Naturally, we want to avoid this.
+	 *
+	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
+	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
 	 */
-	if (system_uses_irq_prio_masking()) {
-		gic_write_pmr(GIC_PRIO_IRQON);
+	if (system_uses_irq_prio_masking())
 		dsb(sy);
-	}
 }
 
 static inline void kvm_arm_vhe_guest_exit(void)
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 30e5e67749e5..db92950bb1a0 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -115,7 +115,6 @@
  * Level 2 descriptor (PMD).
  */
 #define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
-#define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
 #define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
 #define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
@@ -142,8 +141,8 @@
 /*
  * Level 3 descriptor (PTE).
  */
+#define PTE_VALID		(_AT(pteval_t, 1) << 0)
 #define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
-#define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
 #define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
 #define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index c81583be034b..f318258a14be 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -13,7 +13,6 @@
 /*
  * Software defined PTE bits definition.
  */
-#define PTE_VALID		(_AT(pteval_t, 1) << 0)
 #define PTE_WRITE		(PTE_DBM)		 /* same as DBM (51) */
 #define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index fca26759081a..3052381baaeb 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -235,29 +235,42 @@ extern void __sync_icache_dcache(pte_t pteval);
  *
  *   PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY)
  */
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pte)
+
+static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep,
+					   pte_t pte)
 {
 	pte_t old_pte;
 
-	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
-		__sync_icache_dcache(pte);
+	if (!IS_ENABLED(CONFIG_DEBUG_VM))
+		return;
+
+	old_pte = READ_ONCE(*ptep);
+
+	if (!pte_valid(old_pte) || !pte_valid(pte))
+		return;
+	if (mm != current->active_mm && atomic_read(&mm->mm_users) <= 1)
+		return;
 
 	/*
-	 * If the existing pte is valid, check for potential race with
-	 * hardware updates of the pte (ptep_set_access_flags safely changes
-	 * valid ptes without going through an invalid entry).
+	 * Check for potential race with hardware updates of the pte
+	 * (ptep_set_access_flags safely changes valid ptes without going
+	 * through an invalid entry).
 	 */
-	old_pte = READ_ONCE(*ptep);
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(old_pte) && pte_valid(pte) &&
-	   (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) {
-		VM_WARN_ONCE(!pte_young(pte),
-			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
-			     __func__, pte_val(old_pte), pte_val(pte));
-		VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte),
-			     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
-			     __func__, pte_val(old_pte), pte_val(pte));
-	}
+	VM_WARN_ONCE(!pte_young(pte),
+		     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
+		     __func__, pte_val(old_pte), pte_val(pte));
+	VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte),
+		     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
+		     __func__, pte_val(old_pte), pte_val(pte));
+}
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pte)
+{
+	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
+		__sync_icache_dcache(pte);
+
+	__check_racy_pte_update(mm, ptep, pte);
 
 	set_pte(ptep, pte);
 }
@@ -324,9 +337,14 @@ static inline pmd_t pte_pmd(pte_t pte)
 	return __pmd(pte_val(pte));
 }
 
-static inline pgprot_t mk_sect_prot(pgprot_t prot)
+static inline pgprot_t mk_pud_sect_prot(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT);
+}
+
+static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot)
 {
-	return __pgprot(pgprot_val(prot) & ~PTE_TABLE_BIT);
+	return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT);
 }
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index dad858b6adc6..81693244f58d 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -24,9 +24,15 @@
  * means masking more IRQs (or at least that the same IRQs remain masked).
  *
  * To mask interrupts, we clear the most significant bit of PMR.
+ *
+ * Some code sections either automatically switch back to PSR.I or explicitly
+ * require to not use priority masking. If bit GIC_PRIO_PSR_I_SET is included
+ * in the  the priority mask, it indicates that PSR.I should be set and
+ * interrupt disabling temporarily does not rely on IRQ priorities.
  */
-#define GIC_PRIO_IRQON		0xf0
-#define GIC_PRIO_IRQOFF		(GIC_PRIO_IRQON & ~0x80)
+#define GIC_PRIO_IRQON			0xc0
+#define GIC_PRIO_IRQOFF			(GIC_PRIO_IRQON & ~0x80)
+#define GIC_PRIO_PSR_I_SET		(1 << 4)
 
 /* Additional SPSR bits not exposed in the UABI */
 #define PSR_IL_BIT		(1 << 20)
diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
index 7e245b9e03a5..7434844036d3 100644
--- a/arch/arm64/include/asm/simd.h
+++ b/arch/arm64/include/asm/simd.h
@@ -12,9 +12,9 @@
 #include <linux/preempt.h>
 #include <linux/types.h>
 
-#ifdef CONFIG_KERNEL_MODE_NEON
+DECLARE_PER_CPU(bool, fpsimd_context_busy);
 
-DECLARE_PER_CPU(bool, kernel_neon_busy);
+#ifdef CONFIG_KERNEL_MODE_NEON
 
 /*
  * may_use_simd - whether it is allowable at this time to issue SIMD
@@ -26,15 +26,15 @@ DECLARE_PER_CPU(bool, kernel_neon_busy);
 static __must_check inline bool may_use_simd(void)
 {
 	/*
-	 * kernel_neon_busy is only set while preemption is disabled,
+	 * fpsimd_context_busy is only set while preemption is disabled,
 	 * and is clear whenever preemption is enabled. Since
-	 * this_cpu_read() is atomic w.r.t. preemption, kernel_neon_busy
+	 * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy
 	 * cannot change under our feet -- if it's set we cannot be
 	 * migrated, and if it's clear we cannot be migrated to a CPU
 	 * where it is set.
 	 */
 	return !in_irq() && !irqs_disabled() && !in_nmi() &&
-		!this_cpu_read(kernel_neon_busy);
+		!this_cpu_read(fpsimd_context_busy);
 }
 
 #else /* ! CONFIG_KERNEL_MODE_NEON */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cd7f7ce1a56a..d0bd4ffcf2c4 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -549,6 +549,7 @@
 
 /* id_aa64isar1 */
 #define ID_AA64ISAR1_SB_SHIFT		36
+#define ID_AA64ISAR1_FRINTTS_SHIFT	32
 #define ID_AA64ISAR1_GPI_SHIFT		28
 #define ID_AA64ISAR1_GPA_SHIFT		24
 #define ID_AA64ISAR1_LRCPC_SHIFT	20
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 2372e97db29c..180b34ec5965 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -65,6 +65,7 @@ void arch_release_task_struct(struct task_struct *tsk);
  *  TIF_SYSCALL_TRACEPOINT - syscall tracepoint for ftrace
  *  TIF_SYSCALL_AUDIT	- syscall auditing
  *  TIF_SECCOMP		- syscall secure computing
+ *  TIF_SYSCALL_EMU     - syscall emulation active
  *  TIF_SIGPENDING	- signal pending
  *  TIF_NEED_RESCHED	- rescheduling necessary
  *  TIF_NOTIFY_RESUME	- callback before returning to user
@@ -80,6 +81,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_SYSCALL_AUDIT	9
 #define TIF_SYSCALL_TRACEPOINT	10
 #define TIF_SECCOMP		11
+#define TIF_SYSCALL_EMU		12
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
@@ -98,6 +100,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_FSCHECK		(1 << TIF_FSCHECK)
 #define _TIF_32BIT		(1 << TIF_32BIT)
@@ -109,7 +112,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
-				 _TIF_NOHZ)
+				 _TIF_NOHZ | _TIF_SYSCALL_EMU)
 
 #define INIT_THREAD_INFO(tsk)						\
 {									\
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 1a772b162191..a1e72886b30c 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -63,5 +63,7 @@
 #define HWCAP2_SVEBITPERM	(1 << 4)
 #define HWCAP2_SVESHA3		(1 << 5)
 #define HWCAP2_SVESM4		(1 << 6)
+#define HWCAP2_FLAGM2		(1 << 7)
+#define HWCAP2_FRINT		(1 << 8)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index e932284993d4..7ed9294e2004 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -62,6 +62,9 @@
 #define PSR_x		0x0000ff00	/* Extension		*/
 #define PSR_c		0x000000ff	/* Control		*/
 
+/* syscall emulation path in ptrace */
+#define PTRACE_SYSEMU		  31
+#define PTRACE_SYSEMU_SINGLESTEP  32
 
 #ifndef __ASSEMBLY__