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
  ...

11 files changed, 639 insertions, 11 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 88f160afc468..bbaf0bc4ad60 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_CRASH_CORE)		+= crash_core.o
 obj-$(CONFIG_ARM_SDE_INTERFACE)		+= sdei.o
 obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
 obj-$(CONFIG_SHADOW_CALL_STACK)		+= scs.o
+obj-$(CONFIG_ARM64_MTE)			+= mte.o
 
 obj-y					+= vdso/ probes/
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32/
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 79207c323553..dcc165b3fc04 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -75,6 +75,7 @@
 #include <asm/cpu_ops.h>
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
+#include <asm/mte.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
 #include <asm/traps.h>
@@ -227,6 +228,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MTE_SHIFT, 4, ID_AA64PFR1_MTE_NI),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_BTI),
 				    FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_BT_SHIFT, 4, 0),
@@ -1688,6 +1691,22 @@ static void bti_enable(const struct arm64_cpu_capabilities *__unused)
 }
 #endif /* CONFIG_ARM64_BTI */
 
+#ifdef CONFIG_ARM64_MTE
+static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
+{
+	static bool cleared_zero_page = false;
+
+	/*
+	 * Clear the tags in the zero page. This needs to be done via the
+	 * linear map which has the Tagged attribute.
+	 */
+	if (!cleared_zero_page) {
+		cleared_zero_page = true;
+		mte_clear_page_tags(lm_alias(empty_zero_page));
+	}
+}
+#endif /* CONFIG_ARM64_MTE */
+
 /* Internal helper functions to match cpu capability type */
 static bool
 cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -2104,6 +2123,19 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.sign = FTR_UNSIGNED,
 	},
 #endif
+#ifdef CONFIG_ARM64_MTE
+	{
+		.desc = "Memory Tagging Extension",
+		.capability = ARM64_MTE,
+		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.field_pos = ID_AA64PFR1_MTE_SHIFT,
+		.min_field_value = ID_AA64PFR1_MTE,
+		.sign = FTR_UNSIGNED,
+		.cpu_enable = cpu_enable_mte,
+	},
+#endif /* CONFIG_ARM64_MTE */
 	{},
 };
 
@@ -2220,6 +2252,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
 #endif
+#ifdef CONFIG_ARM64_MTE
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_MTE, CAP_HWCAP, KERNEL_HWCAP_MTE),
+#endif /* CONFIG_ARM64_MTE */
 	{},
 };
 
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 25113245825c..6a7bb3729d60 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -93,6 +93,7 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_DGH]		= "dgh",
 	[KERNEL_HWCAP_RNG]		= "rng",
 	[KERNEL_HWCAP_BTI]		= "bti",
+	[KERNEL_HWCAP_MTE]		= "mte",
 };
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index aeb337029d56..f30007dff35f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -147,6 +147,32 @@ alternative_cb_end
 .L__asm_ssbd_skip\@:
 	.endm
 
+	/* Check for MTE asynchronous tag check faults */
+	.macro check_mte_async_tcf, flgs, tmp
+#ifdef CONFIG_ARM64_MTE
+alternative_if_not ARM64_MTE
+	b	1f
+alternative_else_nop_endif
+	mrs_s	\tmp, SYS_TFSRE0_EL1
+	tbz	\tmp, #SYS_TFSR_EL1_TF0_SHIFT, 1f
+	/* Asynchronous TCF occurred for TTBR0 access, set the TI flag */
+	orr	\flgs, \flgs, #_TIF_MTE_ASYNC_FAULT
+	str	\flgs, [tsk, #TSK_TI_FLAGS]
+	msr_s	SYS_TFSRE0_EL1, xzr
+1:
+#endif
+	.endm
+
+	/* Clear the MTE asynchronous tag check faults */
+	.macro clear_mte_async_tcf
+#ifdef CONFIG_ARM64_MTE
+alternative_if ARM64_MTE
+	dsb	ish
+	msr_s	SYS_TFSRE0_EL1, xzr
+alternative_else_nop_endif
+#endif
+	.endm
+
 	.macro	kernel_entry, el, regsize = 64
 	.if	\regsize == 32
 	mov	w0, w0				// zero upper 32 bits of x0
@@ -180,6 +206,8 @@ alternative_cb_end
 	ldr	x19, [tsk, #TSK_TI_FLAGS]
 	disable_step_tsk x19, x20
 
+	/* Check for asynchronous tag check faults in user space */
+	check_mte_async_tcf x19, x22
 	apply_ssbd 1, x22, x23
 
 	ptrauth_keys_install_kernel tsk, x20, x22, x23
@@ -231,6 +259,13 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	str	x20, [sp, #S_PMR_SAVE]
 alternative_else_nop_endif
 
+	/* Re-enable tag checking (TCO set on exception entry) */
+#ifdef CONFIG_ARM64_MTE
+alternative_if ARM64_MTE
+	SET_PSTATE_TCO(0)
+alternative_else_nop_endif
+#endif
+
 	/*
 	 * Registers that may be useful after this macro is invoked:
 	 *
@@ -740,6 +775,8 @@ SYM_CODE_START_LOCAL(ret_to_user)
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
 finish_ret_to_user:
+	/* Ignore asynchronous tag check faults in the uaccess routines */
+	clear_mte_async_tcf
 	enable_step_tsk x1, x2
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 	bl	stackleak_erase
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 3a1662392c95..42003774d261 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -30,6 +30,7 @@
 #include <asm/kexec.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
+#include <asm/mte.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
@@ -284,6 +285,117 @@ static int create_safe_exec_page(void *src_start, size_t length,
 
 #define dcache_clean_range(start, end)	__flush_dcache_area(start, (end - start))
 
+#ifdef CONFIG_ARM64_MTE
+
+static DEFINE_XARRAY(mte_pages);
+
+static int save_tags(struct page *page, unsigned long pfn)
+{
+	void *tag_storage, *ret;
+
+	tag_storage = mte_allocate_tag_storage();
+	if (!tag_storage)
+		return -ENOMEM;
+
+	mte_save_page_tags(page_address(page), tag_storage);
+
+	ret = xa_store(&mte_pages, pfn, tag_storage, GFP_KERNEL);
+	if (WARN(xa_is_err(ret), "Failed to store MTE tags")) {
+		mte_free_tag_storage(tag_storage);
+		return xa_err(ret);
+	} else if (WARN(ret, "swsusp: %s: Duplicate entry", __func__)) {
+		mte_free_tag_storage(ret);
+	}
+
+	return 0;
+}
+
+static void swsusp_mte_free_storage(void)
+{
+	XA_STATE(xa_state, &mte_pages, 0);
+	void *tags;
+
+	xa_lock(&mte_pages);
+	xas_for_each(&xa_state, tags, ULONG_MAX) {
+		mte_free_tag_storage(tags);
+	}
+	xa_unlock(&mte_pages);
+
+	xa_destroy(&mte_pages);
+}
+
+static int swsusp_mte_save_tags(void)
+{
+	struct zone *zone;
+	unsigned long pfn, max_zone_pfn;
+	int ret = 0;
+	int n = 0;
+
+	if (!system_supports_mte())
+		return 0;
+
+	for_each_populated_zone(zone) {
+		max_zone_pfn = zone_end_pfn(zone);
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
+			struct page *page = pfn_to_online_page(pfn);
+
+			if (!page)
+				continue;
+
+			if (!test_bit(PG_mte_tagged, &page->flags))
+				continue;
+
+			ret = save_tags(page, pfn);
+			if (ret) {
+				swsusp_mte_free_storage();
+				goto out;
+			}
+
+			n++;
+		}
+	}
+	pr_info("Saved %d MTE pages\n", n);
+
+out:
+	return ret;
+}
+
+static void swsusp_mte_restore_tags(void)
+{
+	XA_STATE(xa_state, &mte_pages, 0);
+	int n = 0;
+	void *tags;
+
+	xa_lock(&mte_pages);
+	xas_for_each(&xa_state, tags, ULONG_MAX) {
+		unsigned long pfn = xa_state.xa_index;
+		struct page *page = pfn_to_online_page(pfn);
+
+		mte_restore_page_tags(page_address(page), tags);
+
+		mte_free_tag_storage(tags);
+		n++;
+	}
+	xa_unlock(&mte_pages);
+
+	pr_info("Restored %d MTE pages\n", n);
+
+	xa_destroy(&mte_pages);
+}
+
+#else	/* CONFIG_ARM64_MTE */
+
+static int swsusp_mte_save_tags(void)
+{
+	return 0;
+}
+
+static void swsusp_mte_restore_tags(void)
+{
+}
+
+#endif	/* CONFIG_ARM64_MTE */
+
 int swsusp_arch_suspend(void)
 {
 	int ret = 0;
@@ -301,6 +413,10 @@ int swsusp_arch_suspend(void)
 		/* make the crash dump kernel image visible/saveable */
 		crash_prepare_suspend();
 
+		ret = swsusp_mte_save_tags();
+		if (ret)
+			return ret;
+
 		sleep_cpu = smp_processor_id();
 		ret = swsusp_save();
 	} else {
@@ -314,6 +430,8 @@ int swsusp_arch_suspend(void)
 			dcache_clean_range(__hyp_text_start, __hyp_text_end);
 		}
 
+		swsusp_mte_restore_tags();
+
 		/* make the crash dump kernel image protected again */
 		crash_post_resume();
 
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
new file mode 100644
index 000000000000..52a0638ed967
--- /dev/null
+++ b/arch/arm64/kernel/mte.c
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/prctl.h>
+#include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/string.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/thread_info.h>
+#include <linux/uio.h>
+
+#include <asm/cpufeature.h>
+#include <asm/mte.h>
+#include <asm/ptrace.h>
+#include <asm/sysreg.h>
+
+static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
+{
+	pte_t old_pte = READ_ONCE(*ptep);
+
+	if (check_swap && is_swap_pte(old_pte)) {
+		swp_entry_t entry = pte_to_swp_entry(old_pte);
+
+		if (!non_swap_entry(entry) && mte_restore_tags(entry, page))
+			return;
+	}
+
+	mte_clear_page_tags(page_address(page));
+}
+
+void mte_sync_tags(pte_t *ptep, pte_t pte)
+{
+	struct page *page = pte_page(pte);
+	long i, nr_pages = compound_nr(page);
+	bool check_swap = nr_pages == 1;
+
+	/* if PG_mte_tagged is set, tags have already been initialised */
+	for (i = 0; i < nr_pages; i++, page++) {
+		if (!test_and_set_bit(PG_mte_tagged, &page->flags))
+			mte_sync_page_tags(page, ptep, check_swap);
+	}
+}
+
+int memcmp_pages(struct page *page1, struct page *page2)
+{
+	char *addr1, *addr2;
+	int ret;
+
+	addr1 = page_address(page1);
+	addr2 = page_address(page2);
+	ret = memcmp(addr1, addr2, PAGE_SIZE);
+
+	if (!system_supports_mte() || ret)
+		return ret;
+
+	/*
+	 * If the page content is identical but at least one of the pages is
+	 * tagged, return non-zero to avoid KSM merging. If only one of the
+	 * pages is tagged, set_pte_at() may zero or change the tags of the
+	 * other page via mte_sync_tags().
+	 */
+	if (test_bit(PG_mte_tagged, &page1->flags) ||
+	    test_bit(PG_mte_tagged, &page2->flags))
+		return addr1 != addr2;
+
+	return ret;
+}
+
+static void update_sctlr_el1_tcf0(u64 tcf0)
+{
+	/* ISB required for the kernel uaccess routines */
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF0_MASK, tcf0);
+	isb();
+}
+
+static void set_sctlr_el1_tcf0(u64 tcf0)
+{
+	/*
+	 * mte_thread_switch() checks current->thread.sctlr_tcf0 as an
+	 * optimisation. Disable preemption so that it does not see
+	 * the variable update before the SCTLR_EL1.TCF0 one.
+	 */
+	preempt_disable();
+	current->thread.sctlr_tcf0 = tcf0;
+	update_sctlr_el1_tcf0(tcf0);
+	preempt_enable();
+}
+
+static void update_gcr_el1_excl(u64 incl)
+{
+	u64 excl = ~incl & SYS_GCR_EL1_EXCL_MASK;
+
+	/*
+	 * Note that 'incl' is an include mask (controlled by the user via
+	 * prctl()) while GCR_EL1 accepts an exclude mask.
+	 * No need for ISB since this only affects EL0 currently, implicit
+	 * with ERET.
+	 */
+	sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl);
+}
+
+static void set_gcr_el1_excl(u64 incl)
+{
+	current->thread.gcr_user_incl = incl;
+	update_gcr_el1_excl(incl);
+}
+
+void flush_mte_state(void)
+{
+	if (!system_supports_mte())
+		return;
+
+	/* clear any pending asynchronous tag fault */
+	dsb(ish);
+	write_sysreg_s(0, SYS_TFSRE0_EL1);
+	clear_thread_flag(TIF_MTE_ASYNC_FAULT);
+	/* disable tag checking */
+	set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE);
+	/* reset tag generation mask */
+	set_gcr_el1_excl(0);
+}
+
+void mte_thread_switch(struct task_struct *next)
+{
+	if (!system_supports_mte())
+		return;
+
+	/* avoid expensive SCTLR_EL1 accesses if no change */
+	if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0)
+		update_sctlr_el1_tcf0(next->thread.sctlr_tcf0);
+	update_gcr_el1_excl(next->thread.gcr_user_incl);
+}
+
+void mte_suspend_exit(void)
+{
+	if (!system_supports_mte())
+		return;
+
+	update_gcr_el1_excl(current->thread.gcr_user_incl);
+}
+
+long set_mte_ctrl(struct task_struct *task, unsigned long arg)
+{
+	u64 tcf0;
+	u64 gcr_incl = (arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT;
+
+	if (!system_supports_mte())
+		return 0;
+
+	switch (arg & PR_MTE_TCF_MASK) {
+	case PR_MTE_TCF_NONE:
+		tcf0 = SCTLR_EL1_TCF0_NONE;
+		break;
+	case PR_MTE_TCF_SYNC:
+		tcf0 = SCTLR_EL1_TCF0_SYNC;
+		break;
+	case PR_MTE_TCF_ASYNC:
+		tcf0 = SCTLR_EL1_TCF0_ASYNC;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (task != current) {
+		task->thread.sctlr_tcf0 = tcf0;
+		task->thread.gcr_user_incl = gcr_incl;
+	} else {
+		set_sctlr_el1_tcf0(tcf0);
+		set_gcr_el1_excl(gcr_incl);
+	}
+
+	return 0;
+}
+
+long get_mte_ctrl(struct task_struct *task)
+{
+	unsigned long ret;
+
+	if (!system_supports_mte())
+		return 0;
+
+	ret = task->thread.gcr_user_incl << PR_MTE_TAG_SHIFT;
+
+	switch (task->thread.sctlr_tcf0) {
+	case SCTLR_EL1_TCF0_NONE:
+		return PR_MTE_TCF_NONE;
+	case SCTLR_EL1_TCF0_SYNC:
+		ret |= PR_MTE_TCF_SYNC;
+		break;
+	case SCTLR_EL1_TCF0_ASYNC:
+		ret |= PR_MTE_TCF_ASYNC;
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Access MTE tags in another process' address space as given in mm. Update
+ * the number of tags copied. Return 0 if any tags copied, error otherwise.
+ * Inspired by __access_remote_vm().
+ */
+static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
+				struct iovec *kiov, unsigned int gup_flags)
+{
+	struct vm_area_struct *vma;
+	void __user *buf = kiov->iov_base;
+	size_t len = kiov->iov_len;
+	int ret;
+	int write = gup_flags & FOLL_WRITE;
+
+	if (!access_ok(buf, len))
+		return -EFAULT;
+
+	if (mmap_read_lock_killable(mm))
+		return -EIO;
+
+	while (len) {
+		unsigned long tags, offset;
+		void *maddr;
+		struct page *page = NULL;
+
+		ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page,
+					    &vma, NULL);
+		if (ret <= 0)
+			break;
+
+		/*
+		 * Only copy tags if the page has been mapped as PROT_MTE
+		 * (PG_mte_tagged set). Otherwise the tags are not valid and
+		 * not accessible to user. Moreover, an mprotect(PROT_MTE)
+		 * would cause the existing tags to be cleared if the page
+		 * was never mapped with PROT_MTE.
+		 */
+		if (!test_bit(PG_mte_tagged, &page->flags)) {
+			ret = -EOPNOTSUPP;
+			put_page(page);
+			break;
+		}
+
+		/* limit access to the end of the page */
+		offset = offset_in_page(addr);
+		tags = min(len, (PAGE_SIZE - offset) / MTE_GRANULE_SIZE);
+
+		maddr = page_address(page);
+		if (write) {
+			tags = mte_copy_tags_from_user(maddr + offset, buf, tags);
+			set_page_dirty_lock(page);
+		} else {
+			tags = mte_copy_tags_to_user(buf, maddr + offset, tags);
+		}
+		put_page(page);
+
+		/* error accessing the tracer's buffer */
+		if (!tags)
+			break;
+
+		len -= tags;
+		buf += tags;
+		addr += tags * MTE_GRANULE_SIZE;
+	}
+	mmap_read_unlock(mm);
+
+	/* return an error if no tags copied */
+	kiov->iov_len = buf - kiov->iov_base;
+	if (!kiov->iov_len) {
+		/* check for error accessing the tracee's address space */
+		if (ret <= 0)
+			return -EIO;
+		else
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+/*
+ * Copy MTE tags in another process' address space at 'addr' to/from tracer's
+ * iovec buffer. Return 0 on success. Inspired by ptrace_access_vm().
+ */
+static int access_remote_tags(struct task_struct *tsk, unsigned long addr,
+			      struct iovec *kiov, unsigned int gup_flags)
+{
+	struct mm_struct *mm;
+	int ret;
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		return -EPERM;
+
+	if (!tsk->ptrace || (current != tsk->parent) ||
+	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
+	     !ptracer_capable(tsk, mm->user_ns))) {
+		mmput(mm);
+		return -EPERM;
+	}
+
+	ret = __access_remote_tags(mm, addr, kiov, gup_flags);
+	mmput(mm);
+
+	return ret;
+}
+
+int mte_ptrace_copy_tags(struct task_struct *child, long request,
+			 unsigned long addr, unsigned long data)
+{
+	int ret;
+	struct iovec kiov;
+	struct iovec __user *uiov = (void __user *)data;
+	unsigned int gup_flags = FOLL_FORCE;
+
+	if (!system_supports_mte())
+		return -EIO;
+
+	if (get_user(kiov.iov_base, &uiov->iov_base) ||
+	    get_user(kiov.iov_len, &uiov->iov_len))
+		return -EFAULT;
+
+	if (request == PTRACE_POKEMTETAGS)
+		gup_flags |= FOLL_WRITE;
+
+	/* align addr to the MTE tag granule */
+	addr &= MTE_GRANULE_MASK;
+
+	ret = access_remote_tags(child, addr, &kiov, gup_flags);
+	if (!ret)
+		ret = put_user(kiov.iov_len, &uiov->iov_len);
+
+	return ret;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 085d8ca39e47..4784011cecac 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -53,6 +53,7 @@
 #include <asm/exec.h>
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
+#include <asm/mte.h>
 #include <asm/processor.h>
 #include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>
@@ -240,7 +241,7 @@ static void print_pstate(struct pt_regs *regs)
 		const char *btype_str = btypes[(pstate & PSR_BTYPE_MASK) >>
 					       PSR_BTYPE_SHIFT];
 
-		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO BTYPE=%s)\n",
+		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO %cTCO BTYPE=%s)\n",
 			pstate,
 			pstate & PSR_N_BIT ? 'N' : 'n',
 			pstate & PSR_Z_BIT ? 'Z' : 'z',
@@ -252,6 +253,7 @@ static void print_pstate(struct pt_regs *regs)
 			pstate & PSR_F_BIT ? 'F' : 'f',
 			pstate & PSR_PAN_BIT ? '+' : '-',
 			pstate & PSR_UAO_BIT ? '+' : '-',
+			pstate & PSR_TCO_BIT ? '+' : '-',
 			btype_str);
 	}
 }
@@ -337,6 +339,7 @@ void flush_thread(void)
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
 	flush_tagged_addr_state();
+	flush_mte_state();
 }
 
 void release_thread(struct task_struct *dead_task)
@@ -369,6 +372,9 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	dst->thread.sve_state = NULL;
 	clear_tsk_thread_flag(dst, TIF_SVE);
 
+	/* clear any pending asynchronous tag fault raised by the parent */
+	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
+
 	return 0;
 }
 
@@ -561,6 +567,13 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	 */
 	dsb(ish);
 
+	/*
+	 * MTE thread switching must happen after the DSB above to ensure that
+	 * any asynchronous tag check faults have been logged in the TFSR*_EL1
+	 * registers.
+	 */
+	mte_thread_switch(next);
+
 	/* the actual thread switch */
 	last = cpu_switch_to(prev, next);
 
@@ -623,11 +636,18 @@ void arch_setup_new_exec(void)
  */
 static unsigned int tagged_addr_disabled;
 
-long set_tagged_addr_ctrl(unsigned long arg)
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 {
-	if (is_compat_task())
+	unsigned long valid_mask = PR_TAGGED_ADDR_ENABLE;
+	struct thread_info *ti = task_thread_info(task);
+
+	if (is_compat_thread(ti))
 		return -EINVAL;
-	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+
+	if (system_supports_mte())
+		valid_mask |= PR_MTE_TCF_MASK | PR_MTE_TAG_MASK;
+
+	if (arg & ~valid_mask)
 		return -EINVAL;
 
 	/*
@@ -637,20 +657,28 @@ long set_tagged_addr_ctrl(unsigned long arg)
 	if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled)
 		return -EINVAL;
 
-	update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
+	if (set_mte_ctrl(task, arg) != 0)
+		return -EINVAL;
+
+	update_ti_thread_flag(ti, TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
 
 	return 0;
 }
 
-long get_tagged_addr_ctrl(void)
+long get_tagged_addr_ctrl(struct task_struct *task)
 {
-	if (is_compat_task())
+	long ret = 0;
+	struct thread_info *ti = task_thread_info(task);
+
+	if (is_compat_thread(ti))
 		return -EINVAL;
 
-	if (test_thread_flag(TIF_TAGGED_ADDR))
-		return PR_TAGGED_ADDR_ENABLE;
+	if (test_ti_thread_flag(ti, TIF_TAGGED_ADDR))
+		ret = PR_TAGGED_ADDR_ENABLE;
 
-	return 0;
+	ret |= get_mte_ctrl(task);
+
+	return ret;
 }
 
 /*
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index d8ebfd813e28..f49b349e16a3 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -34,6 +34,7 @@
 #include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/fpsimd.h>
+#include <asm/mte.h>
 #include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>
 #include <asm/syscall.h>
@@ -1032,6 +1033,35 @@ static int pac_generic_keys_set(struct task_struct *target,
 #endif /* CONFIG_CHECKPOINT_RESTORE */
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+static int tagged_addr_ctrl_get(struct task_struct *target,
+				const struct user_regset *regset,
+				struct membuf to)
+{
+	long ctrl = get_tagged_addr_ctrl(target);
+
+	if (IS_ERR_VALUE(ctrl))
+		return ctrl;
+
+	return membuf_write(&to, &ctrl, sizeof(ctrl));
+}
+
+static int tagged_addr_ctrl_set(struct task_struct *target, const struct
+				user_regset *regset, unsigned int pos,
+				unsigned int count, const void *kbuf, const
+				void __user *ubuf)
+{
+	int ret;
+	long ctrl;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
+	if (ret)
+		return ret;
+
+	return set_tagged_addr_ctrl(target, ctrl);
+}
+#endif
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -1051,6 +1081,9 @@ enum aarch64_regset {
 	REGSET_PACG_KEYS,
 #endif
 #endif
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+	REGSET_TAGGED_ADDR_CTRL,
+#endif
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -1148,6 +1181,16 @@ static const struct user_regset aarch64_regsets[] = {
 	},
 #endif
 #endif
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+	[REGSET_TAGGED_ADDR_CTRL] = {
+		.core_note_type = NT_ARM_TAGGED_ADDR_CTRL,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.regset_get = tagged_addr_ctrl_get,
+		.set = tagged_addr_ctrl_set,
+	},
+#endif
 };
 
 static const struct user_regset_view user_aarch64_view = {
@@ -1691,6 +1734,12 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 long arch_ptrace(struct task_struct *child, long request,
 		 unsigned long addr, unsigned long data)
 {
+	switch (request) {
+	case PTRACE_PEEKMTETAGS:
+	case PTRACE_POKEMTETAGS:
+		return mte_ptrace_copy_tags(child, request, addr, data);
+	}
+
 	return ptrace_request(child, request, addr, data);
 }
 
@@ -1793,7 +1842,7 @@ void syscall_trace_exit(struct pt_regs *regs)
  * We also reserve IL for the kernel; SS is handled dynamically.
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
-	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
+	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 26) | GENMASK_ULL(23, 22) | \
 	 GENMASK_ULL(20, 13) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
 	(GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20))
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index f3af68dc1cf8..bdcaaf091e1e 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -749,6 +749,9 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		regs->pstate |= PSR_BTYPE_C;
 	}
 
+	/* TCO (Tag Check Override) always cleared for signal handlers */
+	regs->pstate &= ~PSR_TCO_BIT;
+
 	if (ka->sa.sa_flags & SA_RESTORER)
 		sigtramp = ka->sa.sa_restorer;
 	else
@@ -933,6 +936,12 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 			if (thread_flags & _TIF_UPROBE)
 				uprobe_notify_resume(regs);
 
+			if (thread_flags & _TIF_MTE_ASYNC_FAULT) {
+				clear_thread_flag(TIF_MTE_ASYNC_FAULT);
+				send_sig_fault(SIGSEGV, SEGV_MTEAERR,
+					       (void __user *)NULL, current);
+			}
+
 			if (thread_flags & _TIF_SIGPENDING)
 				do_signal(regs);
 
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 584c14ce3c86..96cd347c7a46 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -10,6 +10,7 @@
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/exec.h>
+#include <asm/mte.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
 #include <asm/smp_plat.h>
@@ -73,6 +74,9 @@ void notrace __cpu_suspend_exit(void)
 	 * disabled it, make sure their wishes are obeyed.
 	 */
 	spectre_v4_enable_mitigation(NULL);
+
+	/* Restore additional MTE-specific configuration */
+	mte_suspend_exit();
 }
 
 /*
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 5f0c04863d2c..e4c0dadf0d92 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -123,6 +123,16 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	local_daif_restore(DAIF_PROCCTX);
 	user_exit();
 
+	if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) {
+		/*
+		 * Process the asynchronous tag check fault before the actual
+		 * syscall. do_notify_resume() will send a signal to userspace
+		 * before the syscall is restarted.
+		 */
+		regs->regs[0] = -ERESTARTNOINTR;
+		return;
+	}
+
 	if (has_syscall_work(flags)) {
 		/*
 		 * The de-facto standard way to skip a system call using ptrace