Merge branch 'for-next/mte' into for-next/core

Add userspace support for the Memory Tagging Extension introduced by
Armv8.5.

(Catalin Marinas and others)
* for-next/mte: (30 commits)
  arm64: mte: Fix typo in memory tagging ABI documentation
  arm64: mte: Add Memory Tagging Extension documentation
  arm64: mte: Kconfig entry
  arm64: mte: Save tags when hibernating
  arm64: mte: Enable swap of tagged pages
  mm: Add arch hooks for saving/restoring tags
  fs: Handle intra-page faults in copy_mount_options()
  arm64: mte: ptrace: Add NT_ARM_TAGGED_ADDR_CTRL regset
  arm64: mte: ptrace: Add PTRACE_{PEEK,POKE}MTETAGS support
  arm64: mte: Allow {set,get}_tagged_addr_ctrl() on non-current tasks
  arm64: mte: Restore the GCR_EL1 register after a suspend
  arm64: mte: Allow user control of the generated random tags via prctl()
  arm64: mte: Allow user control of the tag check mode via prctl()
  mm: Allow arm64 mmap(PROT_MTE) on RAM-based files
  arm64: mte: Validate the PROT_MTE request via arch_validate_flags()
  mm: Introduce arch_validate_flags()
  arm64: mte: Add PROT_MTE support to mmap() and mprotect()
  mm: Introduce arch_calc_vm_flag_bits()
  arm64: mte: Tags-aware aware memcmp_pages() implementation
  arm64: Avoid unnecessary clear_user_page() indirection
  ...

16 files changed, 299 insertions, 25 deletions

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index c4ac9a13ad5f..42868dbd29fd 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -64,7 +64,8 @@
 #define ARM64_BTI				54
 #define ARM64_HAS_ARMv8_4_TTL			55
 #define ARM64_HAS_TLB_RANGE			56
+#define ARM64_MTE				57
 
-#define ARM64_NCAPS				57
+#define ARM64_NCAPS				58
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 4099b05372c9..f7e7144af174 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -681,6 +681,12 @@ static __always_inline bool system_uses_irq_prio_masking(void)
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
 }
 
+static inline bool system_supports_mte(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_MTE) &&
+		cpus_have_const_cap(ARM64_MTE);
+}
+
 static inline bool system_has_prio_mask_debugging(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) &&
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 6493a4c63a2f..9a5498c2c8ee 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -104,7 +104,7 @@
 #define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
 #define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
 #define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
-/* reserved for KERNEL_HWCAP_MTE	__khwcap2_feature(MTE) */
+#define KERNEL_HWCAP_MTE		__khwcap2_feature(MTE)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 32acf95d49c7..64ce29378467 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -12,6 +12,7 @@
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
+#define HCR_ATA		(UL(1) << 56)
 #define HCR_FWB		(UL(1) << 46)
 #define HCR_API		(UL(1) << 41)
 #define HCR_APK		(UL(1) << 40)
@@ -78,7 +79,7 @@
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
 			 HCR_FMO | HCR_IMO | HCR_PTW )
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
-#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
+#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 20a9b322d342..43640d797455 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -126,13 +126,18 @@
 
 /*
  * Memory types available.
+ *
+ * IMPORTANT: MT_NORMAL must be index 0 since vm_get_page_prot() may 'or' in
+ *	      the MT_NORMAL_TAGGED memory type for PROT_MTE mappings. Note
+ *	      that protection_map[] only contains MT_NORMAL attributes.
  */
-#define MT_DEVICE_nGnRnE	0
-#define MT_DEVICE_nGnRE		1
-#define MT_DEVICE_GRE		2
-#define MT_NORMAL_NC		3
-#define MT_NORMAL		4
-#define MT_NORMAL_WT		5
+#define MT_NORMAL		0
+#define MT_NORMAL_TAGGED	1
+#define MT_NORMAL_NC		2
+#define MT_NORMAL_WT		3
+#define MT_DEVICE_nGnRnE	4
+#define MT_DEVICE_nGnRE		5
+#define MT_DEVICE_GRE		6
 
 /*
  * Memory types for Stage-2 translation
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 081ec8de9ea6..e3e28f7daf62 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/arch/arm64/include/asm/mman.h
@@ -9,16 +9,53 @@
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 	unsigned long pkey __always_unused)
 {
+	unsigned long ret = 0;
+
 	if (system_supports_bti() && (prot & PROT_BTI))
-		return VM_ARM64_BTI;
+		ret |= VM_ARM64_BTI;
 
-	return 0;
+	if (system_supports_mte() && (prot & PROT_MTE))
+		ret |= VM_MTE;
+
+	return ret;
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
+static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+{
+	/*
+	 * Only allow MTE on anonymous mappings as these are guaranteed to be
+	 * backed by tags-capable memory. The vm_flags may be overridden by a
+	 * filesystem supporting MTE (RAM-based).
+	 */
+	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+		return VM_MTE_ALLOWED;
+
+	return 0;
+}
+#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
-	return (vm_flags & VM_ARM64_BTI) ? __pgprot(PTE_GP) : __pgprot(0);
+	pteval_t prot = 0;
+
+	if (vm_flags & VM_ARM64_BTI)
+		prot |= PTE_GP;
+
+	/*
+	 * There are two conditions required for returning a Normal Tagged
+	 * memory type: (1) the user requested it via PROT_MTE passed to
+	 * mmap() or mprotect() and (2) the corresponding vma supports MTE. We
+	 * register (1) as VM_MTE in the vma->vm_flags and (2) as
+	 * VM_MTE_ALLOWED. Note that the latter can only be set during the
+	 * mmap() call since mprotect() does not accept MAP_* flags.
+	 * Checking for VM_MTE only is sufficient since arch_validate_flags()
+	 * does not permit (VM_MTE & !VM_MTE_ALLOWED).
+	 */
+	if (vm_flags & VM_MTE)
+		prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED);
+
+	return __pgprot(prot);
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
 
@@ -30,8 +67,21 @@ static inline bool arch_validate_prot(unsigned long prot,
 	if (system_supports_bti())
 		supported |= PROT_BTI;
 
+	if (system_supports_mte())
+		supported |= PROT_MTE;
+
 	return (prot & ~supported) == 0;
 }
 #define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
 
+static inline bool arch_validate_flags(unsigned long vm_flags)
+{
+	if (!system_supports_mte())
+		return true;
+
+	/* only allow VM_MTE if VM_MTE_ALLOWED has been set previously */
+	return !(vm_flags & VM_MTE) || (vm_flags & VM_MTE_ALLOWED);
+}
+#define arch_validate_flags(vm_flags) arch_validate_flags(vm_flags)
+
 #endif /* ! __ASM_MMAN_H__ */
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
new file mode 100644
index 000000000000..1c99fcadb58c
--- /dev/null
+++ b/arch/arm64/include/asm/mte.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_MTE_H
+#define __ASM_MTE_H
+
+#define MTE_GRANULE_SIZE	UL(16)
+#define MTE_GRANULE_MASK	(~(MTE_GRANULE_SIZE - 1))
+#define MTE_TAG_SHIFT		56
+#define MTE_TAG_SIZE		4
+
+#ifndef __ASSEMBLY__
+
+#include <linux/page-flags.h>
+
+#include <asm/pgtable-types.h>
+
+void mte_clear_page_tags(void *addr);
+unsigned long mte_copy_tags_from_user(void *to, const void __user *from,
+				      unsigned long n);
+unsigned long mte_copy_tags_to_user(void __user *to, void *from,
+				    unsigned long n);
+int mte_save_tags(struct page *page);
+void mte_save_page_tags(const void *page_addr, void *tag_storage);
+bool mte_restore_tags(swp_entry_t entry, struct page *page);
+void mte_restore_page_tags(void *page_addr, const void *tag_storage);
+void mte_invalidate_tags(int type, pgoff_t offset);
+void mte_invalidate_tags_area(int type);
+void *mte_allocate_tag_storage(void);
+void mte_free_tag_storage(char *storage);
+
+#ifdef CONFIG_ARM64_MTE
+
+/* track which pages have valid allocation tags */
+#define PG_mte_tagged	PG_arch_2
+
+void mte_sync_tags(pte_t *ptep, pte_t pte);
+void mte_copy_page_tags(void *kto, const void *kfrom);
+void flush_mte_state(void);
+void mte_thread_switch(struct task_struct *next);
+void mte_suspend_exit(void);
+long set_mte_ctrl(struct task_struct *task, unsigned long arg);
+long get_mte_ctrl(struct task_struct *task);
+int mte_ptrace_copy_tags(struct task_struct *child, long request,
+			 unsigned long addr, unsigned long data);
+
+#else
+
+/* unused if !CONFIG_ARM64_MTE, silence the compiler */
+#define PG_mte_tagged	0
+
+static inline void mte_sync_tags(pte_t *ptep, pte_t pte)
+{
+}
+static inline void mte_copy_page_tags(void *kto, const void *kfrom)
+{
+}
+static inline void flush_mte_state(void)
+{
+}
+static inline void mte_thread_switch(struct task_struct *next)
+{
+}
+static inline void mte_suspend_exit(void)
+{
+}
+static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg)
+{
+	return 0;
+}
+static inline long get_mte_ctrl(struct task_struct *task)
+{
+	return 0;
+}
+static inline int mte_ptrace_copy_tags(struct task_struct *child,
+				       long request, unsigned long addr,
+				       unsigned long data)
+{
+	return -EIO;
+}
+
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_MTE_H  */
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index c01b52add377..012cffc574e8 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -15,18 +15,25 @@
 #include <linux/personality.h> /* for READ_IMPLIES_EXEC */
 #include <asm/pgtable-types.h>
 
-extern void __cpu_clear_user_page(void *p, unsigned long user);
-extern void __cpu_copy_user_page(void *to, const void *from,
-				 unsigned long user);
+struct page;
+struct vm_area_struct;
+
 extern void copy_page(void *to, const void *from);
 extern void clear_page(void *to);
 
+void copy_user_highpage(struct page *to, struct page *from,
+			unsigned long vaddr, struct vm_area_struct *vma);
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+
+void copy_highpage(struct page *to, struct page *from);
+#define __HAVE_ARCH_COPY_HIGHPAGE
+
 #define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
 	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
-#define clear_user_page(addr,vaddr,pg)  __cpu_clear_user_page(addr, vaddr)
-#define copy_user_page(to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr)
+#define clear_user_page(page, vaddr, pg)	clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
 typedef struct page *pgtable_t;
 
@@ -36,7 +43,7 @@ extern int pfn_valid(unsigned long);
 
 #endif /* !__ASSEMBLY__ */
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
+#define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
 
 #include <asm-generic/getorder.h>
 
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2df4b75fce3c..4cd0d6ca8aa1 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -57,6 +57,7 @@ extern bool arm64_use_ng_mappings;
 #define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
 #define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
 #define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_NORMAL_TAGGED	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_TAGGED))
 
 #define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -66,6 +67,7 @@ extern bool arm64_use_ng_mappings;
 #define _HYP_PAGE_DEFAULT	_PAGE_DEFAULT
 
 #define PAGE_KERNEL		__pgprot(PROT_NORMAL)
+#define PAGE_KERNEL_TAGGED	__pgprot(PROT_NORMAL_TAGGED)
 #define PAGE_KERNEL_RO		__pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
 #define PAGE_KERNEL_ROX		__pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(PROT_NORMAL & ~PTE_PXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 80f4278f7183..a11bf52e0c38 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -9,6 +9,7 @@
 #include <asm/proc-fns.h>
 
 #include <asm/memory.h>
+#include <asm/mte.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable-prot.h>
 #include <asm/tlbflush.h>
@@ -94,6 +95,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
 #define pte_devmap(pte)		(!!(pte_val(pte) & PTE_DEVMAP))
+#define pte_tagged(pte)		((pte_val(pte) & PTE_ATTRINDX_MASK) == \
+				 PTE_ATTRINDX(MT_NORMAL_TAGGED))
 
 #define pte_cont_addr_end(addr, end)						\
 ({	unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK;	\
@@ -300,6 +303,10 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte);
 
+	if (system_supports_mte() &&
+	    pte_present(pte) && pte_tagged(pte) && !pte_special(pte))
+		mte_sync_tags(ptep, pte);
+
 	__check_racy_pte_update(mm, ptep, pte);
 
 	set_pte(ptep, pte);
@@ -709,8 +716,13 @@ static inline unsigned long p4d_page_vaddr(p4d_t p4d)
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
+	/*
+	 * Normal and Normal-Tagged are two different memory types and indices
+	 * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK.
+	 */
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
-			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
+			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP |
+			      PTE_ATTRINDX_MASK;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
 		pte = pte_mkdirty(pte);
@@ -895,6 +907,38 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 
 extern int kern_addr_valid(unsigned long addr);
 
+#ifdef CONFIG_ARM64_MTE
+
+#define __HAVE_ARCH_PREPARE_TO_SWAP
+static inline int arch_prepare_to_swap(struct page *page)
+{
+	if (system_supports_mte())
+		return mte_save_tags(page);
+	return 0;
+}
+
+#define __HAVE_ARCH_SWAP_INVALIDATE
+static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
+{
+	if (system_supports_mte())
+		mte_invalidate_tags(type, offset);
+}
+
+static inline void arch_swap_invalidate_area(int type)
+{
+	if (system_supports_mte())
+		mte_invalidate_tags_area(type);
+}
+
+#define __HAVE_ARCH_SWAP_RESTORE
+static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
+{
+	if (system_supports_mte() && mte_restore_tags(entry, page))
+		set_bit(PG_mte_tagged, &page->flags);
+}
+
+#endif /* CONFIG_ARM64_MTE */
+
 /*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
  */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 7d90ea2e2063..fce8cbecd6bc 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -152,6 +152,10 @@ struct thread_struct {
 	struct ptrauth_keys_user	keys_user;
 	struct ptrauth_keys_kernel	keys_kernel;
 #endif
+#ifdef CONFIG_ARM64_MTE
+	u64			sctlr_tcf0;
+	u64			gcr_user_incl;
+#endif
 };
 
 static inline void arch_thread_struct_whitelist(unsigned long *offset,
@@ -301,10 +305,10 @@ extern void __init minsigstksz_setup(void);
 
 #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
 /* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */
-long set_tagged_addr_ctrl(unsigned long arg);
-long get_tagged_addr_ctrl(void);
-#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(arg)
-#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl()
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg);
+long get_tagged_addr_ctrl(struct task_struct *task);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(current, arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl(current)
 #endif
 
 /*
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 6beef073871d..d52c1b3ce589 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -91,10 +91,12 @@
 #define PSTATE_PAN			pstate_field(0, 4)
 #define PSTATE_UAO			pstate_field(0, 3)
 #define PSTATE_SSBS			pstate_field(3, 1)
+#define PSTATE_TCO			pstate_field(3, 4)
 
 #define SET_PSTATE_PAN(x)		__emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
 #define SET_PSTATE_UAO(x)		__emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
 #define SET_PSTATE_SSBS(x)		__emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_TCO(x)		__emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift))
 
 #define __SYS_BARRIER_INSN(CRm, op2, Rt) \
 	__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
@@ -181,6 +183,8 @@
 #define SYS_SCTLR_EL1			sys_reg(3, 0, 1, 0, 0)
 #define SYS_ACTLR_EL1			sys_reg(3, 0, 1, 0, 1)
 #define SYS_CPACR_EL1			sys_reg(3, 0, 1, 0, 2)
+#define SYS_RGSR_EL1			sys_reg(3, 0, 1, 0, 5)
+#define SYS_GCR_EL1			sys_reg(3, 0, 1, 0, 6)
 
 #define SYS_ZCR_EL1			sys_reg(3, 0, 1, 2, 0)
 
@@ -218,6 +222,8 @@
 #define SYS_ERXADDR_EL1			sys_reg(3, 0, 5, 4, 3)
 #define SYS_ERXMISC0_EL1		sys_reg(3, 0, 5, 5, 0)
 #define SYS_ERXMISC1_EL1		sys_reg(3, 0, 5, 5, 1)
+#define SYS_TFSR_EL1			sys_reg(3, 0, 5, 6, 0)
+#define SYS_TFSRE0_EL1			sys_reg(3, 0, 5, 6, 1)
 
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
@@ -370,6 +376,7 @@
 
 #define SYS_CCSIDR_EL1			sys_reg(3, 1, 0, 0, 0)
 #define SYS_CLIDR_EL1			sys_reg(3, 1, 0, 0, 1)
+#define SYS_GMID_EL1			sys_reg(3, 1, 0, 0, 4)
 #define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
 
 #define SYS_CSSELR_EL1			sys_reg(3, 2, 0, 0, 0)
@@ -462,6 +469,7 @@
 #define SYS_ESR_EL2			sys_reg(3, 4, 5, 2, 0)
 #define SYS_VSESR_EL2			sys_reg(3, 4, 5, 2, 3)
 #define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
+#define SYS_TFSR_EL2			sys_reg(3, 4, 5, 6, 0)
 #define SYS_FAR_EL2			sys_reg(3, 4, 6, 0, 0)
 
 #define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1,  1)
@@ -518,6 +526,7 @@
 #define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
 #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
 #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
+#define SYS_TFSR_EL12			sys_reg(3, 5, 5, 6, 0)
 #define SYS_FAR_EL12			sys_reg(3, 5, 6, 0, 0)
 #define SYS_MAIR_EL12			sys_reg(3, 5, 10, 2, 0)
 #define SYS_AMAIR_EL12			sys_reg(3, 5, 10, 3, 0)
@@ -533,6 +542,15 @@
 
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_DSSBS	(BIT(44))
+#define SCTLR_ELx_ATA	(BIT(43))
+
+#define SCTLR_ELx_TCF_SHIFT	40
+#define SCTLR_ELx_TCF_NONE	(UL(0x0) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_SYNC	(UL(0x1) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_ASYNC	(UL(0x2) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_MASK	(UL(0x3) << SCTLR_ELx_TCF_SHIFT)
+
+#define SCTLR_ELx_ITFSB	(BIT(37))
 #define SCTLR_ELx_ENIA	(BIT(31))
 #define SCTLR_ELx_ENIB	(BIT(30))
 #define SCTLR_ELx_ENDA	(BIT(27))
@@ -561,6 +579,14 @@
 #endif
 
 /* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_ATA0		(BIT(42))
+
+#define SCTLR_EL1_TCF0_SHIFT	38
+#define SCTLR_EL1_TCF0_NONE	(UL(0x0) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_SYNC	(UL(0x1) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_ASYNC	(UL(0x2) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_MASK	(UL(0x3) << SCTLR_EL1_TCF0_SHIFT)
+
 #define SCTLR_EL1_BT1		(BIT(36))
 #define SCTLR_EL1_BT0		(BIT(35))
 #define SCTLR_EL1_UCI		(BIT(26))
@@ -589,6 +615,7 @@
 			 SCTLR_EL1_SA0  | SCTLR_EL1_SED  | SCTLR_ELx_I    |\
 			 SCTLR_EL1_DZE  | SCTLR_EL1_UCT                   |\
 			 SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\
+			 SCTLR_ELx_ITFSB| SCTLR_ELx_ATA  | SCTLR_EL1_ATA0 |\
 			 ENDIAN_SET_EL1 | SCTLR_EL1_UCI  | SCTLR_EL1_RES1)
 
 /* MAIR_ELx memory attributes (used by Linux) */
@@ -597,6 +624,7 @@
 #define MAIR_ATTR_DEVICE_GRE		UL(0x0c)
 #define MAIR_ATTR_NORMAL_NC		UL(0x44)
 #define MAIR_ATTR_NORMAL_WT		UL(0xbb)
+#define MAIR_ATTR_NORMAL_TAGGED		UL(0xf0)
 #define MAIR_ATTR_NORMAL		UL(0xff)
 #define MAIR_ATTR_MASK			UL(0xff)
 
@@ -696,6 +724,10 @@
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 #define ID_AA64PFR1_BT_BTI		0x1
 
+#define ID_AA64PFR1_MTE_NI		0x0
+#define ID_AA64PFR1_MTE_EL0		0x1
+#define ID_AA64PFR1_MTE			0x2
+
 /* id_aa64zfr0 */
 #define ID_AA64ZFR0_F64MM_SHIFT		56
 #define ID_AA64ZFR0_F32MM_SHIFT		52
@@ -930,6 +962,28 @@
 #define CPACR_EL1_ZEN_EL0EN	(BIT(17)) /* enable EL0 access, if EL1EN set */
 #define CPACR_EL1_ZEN		(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
 
+/* TCR EL1 Bit Definitions */
+#define SYS_TCR_EL1_TCMA1	(BIT(58))
+#define SYS_TCR_EL1_TCMA0	(BIT(57))
+
+/* GCR_EL1 Definitions */
+#define SYS_GCR_EL1_RRND	(BIT(16))
+#define SYS_GCR_EL1_EXCL_MASK	0xffffUL
+
+/* RGSR_EL1 Definitions */
+#define SYS_RGSR_EL1_TAG_MASK	0xfUL
+#define SYS_RGSR_EL1_SEED_SHIFT	8
+#define SYS_RGSR_EL1_SEED_MASK	0xffffUL
+
+/* GMID_EL1 field definitions */
+#define SYS_GMID_EL1_BS_SHIFT	0
+#define SYS_GMID_EL1_BS_SIZE	4
+
+/* TFSR{,E0}_EL1 bit definitions */
+#define SYS_TFSR_EL1_TF0_SHIFT	0
+#define SYS_TFSR_EL1_TF1_SHIFT	1
+#define SYS_TFSR_EL1_TF0	(UL(1) << SYS_TFSR_EL1_TF0_SHIFT)
+#define SYS_TFSR_EL1_TF1	(UK(2) << SYS_TFSR_EL1_TF1_SHIFT)
 
 /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
 #define SYS_MPIDR_SAFE_VAL	(BIT(31))
@@ -1034,6 +1088,13 @@
 		write_sysreg(__scs_new, sysreg);			\
 } while (0)
 
+#define sysreg_clear_set_s(sysreg, clear, set) do {			\
+	u64 __scs_val = read_sysreg_s(sysreg);				\
+	u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set);		\
+	if (__scs_new != __scs_val)					\
+		write_sysreg_s(__scs_new, sysreg);			\
+} while (0)
+
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 5e784e16ee89..1fbab854a51b 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -67,6 +67,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
 #define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_FSCHECK		5	/* Check FS is USER_DS on return */
+#define TIF_MTE_ASYNC_FAULT	6	/* MTE Asynchronous Tag Check Fault */
 #define TIF_SYSCALL_TRACE	8	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing */
 #define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
@@ -96,10 +97,11 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
+#define _TIF_MTE_ASYNC_FAULT	(1 << TIF_MTE_ASYNC_FAULT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
-				 _TIF_UPROBE | _TIF_FSCHECK)
+				 _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 912162f73529..b8f41aa234ee 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -74,6 +74,6 @@
 #define HWCAP2_DGH		(1 << 15)
 #define HWCAP2_RNG		(1 << 16)
 #define HWCAP2_BTI		(1 << 17)
-/* reserved for HWCAP2_MTE	(1 << 18) */
+#define HWCAP2_MTE		(1 << 18)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/mman.h b/arch/arm64/include/uapi/asm/mman.h
index 6fdd71eb644f..1e6482a838e1 100644
--- a/arch/arm64/include/uapi/asm/mman.h
+++ b/arch/arm64/include/uapi/asm/mman.h
@@ -5,5 +5,6 @@
 #include <asm-generic/mman.h>
 
 #define PROT_BTI	0x10		/* BTI guarded page */
+#define PROT_MTE	0x20		/* Normal Tagged mapping */
 
 #endif /* ! _UAPI__ASM_MMAN_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 42cbe34d95ce..758ae984ff97 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -51,6 +51,7 @@
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
 #define PSR_DIT_BIT	0x01000000
+#define PSR_TCO_BIT	0x02000000
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000
@@ -75,6 +76,9 @@
 /* syscall emulation path in ptrace */
 #define PTRACE_SYSEMU		  31
 #define PTRACE_SYSEMU_SINGLESTEP  32
+/* MTE allocation tag access */
+#define PTRACE_PEEKMTETAGS	  33
+#define PTRACE_POKEMTETAGS	  34
 
 #ifndef __ASSEMBLY__