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

Pull arm64 updates from Will Deacon:
 - Errata workarounds for Qualcomm's Falkor CPU
 - Qualcomm L2 Cache PMU driver
 - Qualcomm SMCCC firmware quirk
 - Support for DEBUG_VIRTUAL
 - CPU feature detection for userspace via MRS emulation
 - Preliminary work for the Statistical Profiling Extension
 - Misc cleanups and non-critical fixes

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (74 commits)
  arm64/kprobes: consistently handle MRS/MSR with XZR
  arm64: cpufeature: correctly handle MRS to XZR
  arm64: traps: correctly handle MRS/MSR with XZR
  arm64: ptrace: add XZR-safe regs accessors
  arm64: include asm/assembler.h in entry-ftrace.S
  arm64: fix warning about swapper_pg_dir overflow
  arm64: Work around Falkor erratum 1003
  arm64: head.S: Enable EL1 (host) access to SPE when entered at EL2
  arm64: arch_timer: document Hisilicon erratum 161010101
  arm64: use is_vmalloc_addr
  arm64: use linux/sizes.h for constants
  arm64: uaccess: consistently check object sizes
  perf: add qcom l2 cache perf events driver
  arm64: remove wrong CONFIG_PROC_SYSCTL ifdef
  ARM: smccc: Update HVC comment to describe new quirk parameter
  arm64: do not trace atomic operations
  ACPI/IORT: Fix the error return code in iort_add_smmu_platform_device()
  ACPI/IORT: Fix iort_node_get_id() mapping entries indexing
  arm64: mm: enable CONFIG_HOLES_IN_ZONE for NUMA
  perf: xgene: Include module.h
  ...

59 files changed, 945 insertions, 354 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 916024d6a2b1..a39029b5414e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -6,6 +6,7 @@ config ARM64
 	select ACPI_MCFG if ACPI
 	select ACPI_SPCR_TABLE if ACPI
 	select ARCH_CLOCKSOURCE_DATA
+	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ELF_RANDOMIZE
@@ -479,6 +480,34 @@ config CAVIUM_ERRATUM_27456
 
 	  If unsure, say Y.
 
+config QCOM_FALKOR_ERRATUM_1003
+	bool "Falkor E1003: Incorrect translation due to ASID change"
+	default y
+	select ARM64_PAN if ARM64_SW_TTBR0_PAN
+	help
+	  On Falkor v1, an incorrect ASID may be cached in the TLB when ASID
+	  and BADDR are changed together in TTBRx_EL1. The workaround for this
+	  issue is to use a reserved ASID in cpu_do_switch_mm() before
+	  switching to the new ASID. Saying Y here selects ARM64_PAN if
+	  ARM64_SW_TTBR0_PAN is selected. This is done because implementing and
+	  maintaining the E1003 workaround in the software PAN emulation code
+	  would be an unnecessary complication. The affected Falkor v1 CPU
+	  implements ARMv8.1 hardware PAN support and using hardware PAN
+	  support versus software PAN emulation is mutually exclusive at
+	  runtime.
+
+	  If unsure, say Y.
+
+config QCOM_FALKOR_ERRATUM_1009
+	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
+	default y
+	help
+	  On Falkor v1, the CPU may prematurely complete a DSB following a
+	  TLBI xxIS invalidate maintenance operation. Repeat the TLBI operation
+	  one more time to fix the issue.
+
+	  If unsure, say Y.
+
 endmenu
 
 
@@ -614,6 +643,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
 	def_bool y
 	depends on NUMA
 
+config HOLES_IN_ZONE
+	def_bool y
+	depends on NUMA
+
 source kernel/Kconfig.preempt
 source kernel/Kconfig.hz
 
@@ -1010,7 +1043,7 @@ source "fs/Kconfig.binfmt"
 config COMPAT
 	bool "Kernel support for 32-bit EL0"
 	depends on ARM64_4K_PAGES || EXPERT
-	select COMPAT_BINFMT_ELF
+	select COMPAT_BINFMT_ELF if BINFMT_ELF
 	select HAVE_UID16
 	select OLD_SIGSUSPEND3
 	select COMPAT_OLD_SIGACTION
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 560a8d85a4f8..fca2f02cde68 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -84,6 +84,14 @@ config DEBUG_ALIGN_RODATA
 
 	  If in doubt, say N.
 
+config DEBUG_EFI
+	depends on EFI && DEBUG_INFO
+	bool "UEFI debugging"
+	help
+	  Enable this option to include EFI specific debugging features into
+	  the kernel that are only useful when using a debug build of the
+	  UEFI firmware
+
 source "drivers/hwtracing/coresight/Kconfig"
 
 endmenu
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 3a4301163e04..1b67c3782d00 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -25,6 +25,7 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
+#include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
@@ -441,6 +442,28 @@ alternative_endif
 	.endm
 
 /*
+ * Errata workaround prior to TTBR0_EL1 update
+ *
+ * 	val:	TTBR value with new BADDR, preserved
+ * 	tmp0:	temporary register, clobbered
+ * 	tmp1:	other temporary register, clobbered
+ */
+	.macro	pre_ttbr0_update_workaround, val, tmp0, tmp1
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
+alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
+	mrs	\tmp0, ttbr0_el1
+	mov	\tmp1, #FALKOR_RESERVED_ASID
+	bfi	\tmp0, \tmp1, #48, #16		// reserved ASID + old BADDR
+	msr	ttbr0_el1, \tmp0
+	isb
+	bfi	\tmp0, \val, #0, #48		// reserved ASID + new BADDR
+	msr	ttbr0_el1, \tmp0
+	isb
+alternative_else_nop_endif
+#endif
+	.endm
+
+/*
  * Errata workaround post TTBR0_EL1 update.
  */
 	.macro	post_ttbr0_update_workaround
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 4174f09678c4..fb78a5d3b60b 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -35,7 +35,9 @@
 #define ARM64_HYP_OFFSET_LOW			14
 #define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
 #define ARM64_HAS_NO_FPSIMD			16
+#define ARM64_WORKAROUND_REPEAT_TLBI		17
+#define ARM64_WORKAROUND_QCOM_FALKOR_E1003	18
 
-#define ARM64_NCAPS				17
+#define ARM64_NCAPS				19
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index b4989df48670..4ce82ed3e7c3 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -29,7 +29,20 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 
-/* CPU feature register tracking */
+/*
+ * CPU feature register tracking
+ *
+ * The safe value of a CPUID feature field is dependent on the implications
+ * of the values assigned to it by the architecture. Based on the relationship
+ * between the values, the features are classified into 3 types - LOWER_SAFE,
+ * HIGHER_SAFE and EXACT.
+ *
+ * The lowest value of all the CPUs is chosen for LOWER_SAFE and highest
+ * for HIGHER_SAFE. It is expected that all CPUs have the same value for
+ * a field when EXACT is specified, failing which, the safe value specified
+ * in the table is chosen.
+ */
+
 enum ftr_type {
 	FTR_EXACT,	/* Use a predefined safe value */
 	FTR_LOWER_SAFE,	/* Smaller value is safe */
@@ -42,8 +55,12 @@ enum ftr_type {
 #define FTR_SIGNED	true	/* Value should be treated as signed */
 #define FTR_UNSIGNED	false	/* Value should be treated as unsigned */
 
+#define FTR_VISIBLE	true	/* Feature visible to the user space */
+#define FTR_HIDDEN	false	/* Feature is hidden from the user */
+
 struct arm64_ftr_bits {
 	bool		sign;	/* Value is signed ? */
+	bool		visible;
 	bool		strict;	/* CPU Sanity check: strict matching required ? */
 	enum ftr_type	type;
 	u8		shift;
@@ -59,7 +76,9 @@ struct arm64_ftr_bits {
 struct arm64_ftr_reg {
 	const char			*name;
 	u64				strict_mask;
+	u64				user_mask;
 	u64				sys_val;
+	u64				user_val;
 	const struct arm64_ftr_bits	*ftr_bits;
 };
 
@@ -159,6 +178,11 @@ static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
 	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
 }
 
+static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg)
+{
+	return (reg->user_val | (reg->sys_val & reg->user_mask));
+}
+
 static inline int __attribute_const__
 cpuid_feature_extract_field(u64 features, int field, bool sign)
 {
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 26a68ddb11c1..fc502713ab37 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -56,6 +56,9 @@
 	(0xf			<< MIDR_ARCHITECTURE_SHIFT) | \
 	((partnum)		<< MIDR_PARTNUM_SHIFT))
 
+#define MIDR_CPU_VAR_REV(var, rev) \
+	(((var)	<< MIDR_VARIANT_SHIFT) | (rev))
+
 #define MIDR_CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \
 			     MIDR_ARCHITECTURE_MASK)
 
@@ -71,6 +74,7 @@
 #define ARM_CPU_IMP_APM			0x50
 #define ARM_CPU_IMP_CAVIUM		0x43
 #define ARM_CPU_IMP_BRCM		0x42
+#define ARM_CPU_IMP_QCOM		0x51
 
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
@@ -84,10 +88,13 @@
 
 #define BRCM_CPU_PART_VULCAN		0x516
 
+#define QCOM_CPU_PART_FALKOR_V1		0x800
+
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
+#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index bc853663dd51..aecc07e09a18 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -332,6 +332,8 @@ bool aarch64_insn_is_branch(u32 insn);
 u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn);
 u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 				  u32 insn, u64 imm);
+u32 aarch64_insn_decode_register(enum aarch64_insn_register_type type,
+					 u32 insn);
 u32 aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
 				enum aarch64_insn_branch_type type);
 u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 2a2752b5b6aa..6e99978e83bd 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -188,6 +188,9 @@
 #define CPTR_EL2_DEFAULT	0x000033ff
 
 /* Hyp Debug Configuration Register bits */
+#define MDCR_EL2_TPMS		(1 << 14)
+#define MDCR_EL2_E2PB_MASK	(UL(0x3))
+#define MDCR_EL2_E2PB_SHIFT	(UL(12))
 #define MDCR_EL2_TDRA		(1 << 11)
 #define MDCR_EL2_TDOSA		(1 << 10)
 #define MDCR_EL2_TDA		(1 << 9)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e5050388e062..443b387021f2 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -229,7 +229,12 @@ struct kvm_vcpu_arch {
 
 	/* Pointer to host CPU context */
 	kvm_cpu_context_t *host_cpu_context;
-	struct kvm_guest_debug_arch host_debug_state;
+	struct {
+		/* {Break,watch}point registers */
+		struct kvm_guest_debug_arch regs;
+		/* Statistical profiling extension */
+		u64 pmscr_el1;
+	} host_debug_state;
 
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6f72fe8b0e3e..55772c13a375 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -47,7 +47,7 @@
  * If the page is in the bottom half, we have to use the top half. If
  * the page is in the top half, we have to use the bottom half:
  *
- * T = __virt_to_phys(__hyp_idmap_text_start)
+ * T = __pa_symbol(__hyp_idmap_text_start)
  * if (T & BIT(VA_BITS - 1))
  *	HYP_VA_MIN = 0  //idmap in upper half
  * else
@@ -271,7 +271,7 @@ static inline void __kvm_flush_dcache_pud(pud_t pud)
 	kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
 }
 
-#define kvm_virt_to_phys(x)		__virt_to_phys((unsigned long)(x))
+#define kvm_virt_to_phys(x)		__pa_symbol(x)
 
 void kvm_set_way_flush(struct kvm_vcpu *vcpu);
 void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
index fc756e22c84c..606b20910a5c 100644
--- a/arch/arm64/include/asm/lse.h
+++ b/arch/arm64/include/asm/lse.h
@@ -19,7 +19,7 @@
 __asm__(".arch_extension	lse");
 
 /* Move the ll/sc atomics out-of-line */
-#define __LL_SC_INLINE
+#define __LL_SC_INLINE		notrace
 #define __LL_SC_PREFIX(x)	__ll_sc_##x
 #define __LL_SC_EXPORT(x)	EXPORT_SYMBOL(__LL_SC_PREFIX(x))
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 90c39a662379..32f82723338a 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -102,25 +102,6 @@
 #endif
 
 /*
- * Physical vs virtual RAM address space conversion.  These are
- * private definitions which should NOT be used outside memory.h
- * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
- */
-#define __virt_to_phys(x) ({						\
-	phys_addr_t __x = (phys_addr_t)(x);				\
-	__x & BIT(VA_BITS - 1) ? (__x & ~PAGE_OFFSET) + PHYS_OFFSET :	\
-				 (__x - kimage_voffset); })
-
-#define __phys_to_virt(x)	((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET)
-#define __phys_to_kimg(x)	((unsigned long)((x) + kimage_voffset))
-
-/*
- * Convert a page to/from a physical address
- */
-#define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
-#define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
-
-/*
  * Memory types available.
  */
 #define MT_DEVICE_nGnRnE	0
@@ -187,6 +168,48 @@ static inline unsigned long kaslr_offset(void)
 #define PHYS_PFN_OFFSET	(PHYS_OFFSET >> PAGE_SHIFT)
 
 /*
+ * Physical vs virtual RAM address space conversion.  These are
+ * private definitions which should NOT be used outside memory.h
+ * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
+ */
+
+
+/*
+ * The linear kernel range starts in the middle of the virtual adddress
+ * space. Testing the top bit for the start of the region is a
+ * sufficient check.
+ */
+#define __is_lm_address(addr)	(!!((addr) & BIT(VA_BITS - 1)))
+
+#define __lm_to_phys(addr)	(((addr) & ~PAGE_OFFSET) + PHYS_OFFSET)
+#define __kimg_to_phys(addr)	((addr) - kimage_voffset)
+
+#define __virt_to_phys_nodebug(x) ({					\
+	phys_addr_t __x = (phys_addr_t)(x);				\
+	__is_lm_address(__x) ? __lm_to_phys(__x) :			\
+			       __kimg_to_phys(__x);			\
+})
+
+#define __pa_symbol_nodebug(x)	__kimg_to_phys((phys_addr_t)(x))
+
+#ifdef CONFIG_DEBUG_VIRTUAL
+extern phys_addr_t __virt_to_phys(unsigned long x);
+extern phys_addr_t __phys_addr_symbol(unsigned long x);
+#else
+#define __virt_to_phys(x)	__virt_to_phys_nodebug(x)
+#define __phys_addr_symbol(x)	__pa_symbol_nodebug(x)
+#endif
+
+#define __phys_to_virt(x)	((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET)
+#define __phys_to_kimg(x)	((unsigned long)((x) + kimage_voffset))
+
+/*
+ * Convert a page to/from a physical address
+ */
+#define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
+#define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
+
+/*
  * Note: Drivers should NOT use these.  They are the wrong
  * translation for translating DMA addresses.  Use the driver
  * DMA support - see dma-mapping.h.
@@ -207,9 +230,12 @@ static inline void *phys_to_virt(phys_addr_t x)
  * Drivers should NOT use these either.
  */
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
+#define __pa_symbol(x)		__phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0))
+#define __pa_nodebug(x)		__virt_to_phys_nodebug((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
-#define virt_to_pfn(x)      __phys_to_pfn(__virt_to_phys(x))
+#define virt_to_pfn(x)      __phys_to_pfn(__virt_to_phys((unsigned long)(x)))
+#define sym_to_pfn(x)	    __phys_to_pfn(__pa_symbol(x))
 
 /*
  *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 0363fe80455c..1ef40d82cfd3 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -19,6 +19,10 @@
 #ifndef __ASM_MMU_CONTEXT_H
 #define __ASM_MMU_CONTEXT_H
 
+#define FALKOR_RESERVED_ASID	1
+
+#ifndef __ASSEMBLY__
+
 #include <linux/compiler.h>
 #include <linux/sched.h>
 
@@ -45,7 +49,7 @@ static inline void contextidr_thread_switch(struct task_struct *next)
  */
 static inline void cpu_set_reserved_ttbr0(void)
 {
-	unsigned long ttbr = virt_to_phys(empty_zero_page);
+	unsigned long ttbr = __pa_symbol(empty_zero_page);
 
 	write_sysreg(ttbr, ttbr0_el1);
 	isb();
@@ -114,7 +118,7 @@ static inline void cpu_install_idmap(void)
 	local_flush_tlb_all();
 	cpu_set_idmap_tcr_t0sz();
 
-	cpu_switch_mm(idmap_pg_dir, &init_mm);
+	cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm);
 }
 
 /*
@@ -129,7 +133,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgd)
 
 	phys_addr_t pgd_phys = virt_to_phys(pgd);
 
-	replace_phys = (void *)virt_to_phys(idmap_cpu_replace_ttbr1);
+	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 
 	cpu_install_idmap();
 	replace_phys(pgd_phys);
@@ -220,4 +224,6 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 void verify_cpu_asid_bits(void);
 
-#endif
+#endif /* !__ASSEMBLY__ */
+
+#endif /* !__ASM_MMU_CONTEXT_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index ffbb9a520563..0eef6064bf3b 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -52,7 +52,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
  * for zero-mapped memory areas etc..
  */
 extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr)	pfn_to_page(PHYS_PFN(__pa(empty_zero_page)))
+#define ZERO_PAGE(vaddr)	phys_to_page(__pa_symbol(empty_zero_page))
 
 #define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
 
@@ -71,9 +71,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
 #define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
-#define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
+#define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
-#define pte_ng(pte)		(!!(pte_val(pte) & PTE_NG))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -84,8 +83,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_global(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_NG)) == PTE_VALID)
+/*
+ * Execute-only user mappings do not have the PTE_USER bit set. All valid
+ * kernel mappings have the PTE_UXN bit set.
+ */
+#define pte_valid_not_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
 
@@ -178,7 +181,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
 	 * or update_mmu_cache() have the necessary barriers.
 	 */
-	if (pte_valid_global(pte)) {
+	if (pte_valid_not_user(pte)) {
 		dsb(ishst);
 		isb();
 	}
@@ -212,7 +215,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
-		if (pte_ng(pte) && pte_exec(pte) && !pte_special(pte))
+		if (pte_user_exec(pte) && !pte_special(pte))
 			__sync_icache_dcache(pte, addr);
 	}
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 747c65a616ed..c97b8bd2acba 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -187,7 +187,6 @@ static inline void spin_lock_prefetch(const void *ptr)
 #endif
 
 int cpu_enable_pan(void *__unused);
-int cpu_enable_uao(void *__unused);
 int cpu_enable_cache_maint_trap(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 513daf050e84..11403fdd0a50 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -194,6 +194,26 @@ static inline u64 regs_get_register(struct pt_reg