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

Optimise SVE switching for CPUs with 128-bit implementations.

* for-next/sve:
  arm64/sve: Skip flushing Z registers with 128 bit vectors
  arm64/sve: Use the sve_flush macros in sve_load_from_fpsimd_state()
  arm64/sve: Split _sve_flush macro into separate Z and predicate flushes
diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst
index 18b8cc1..a9192e7 100644
--- a/Documentation/arm64/booting.rst
+++ b/Documentation/arm64/booting.rst
@@ -277,6 +277,12 @@
 
     - SCR_EL3.FGTEn (bit 27) must be initialised to 0b1.
 
+  For CPUs with support for HCRX_EL2 (FEAT_HCX) present:
+
+  - If EL3 is present and the kernel is entered at EL2:
+
+    - SCR_EL3.HXEn (bit 38) must be initialised to 0b1.
+
   For CPUs with Advanced SIMD and floating point support:
 
   - If EL3 is present:
diff --git a/Makefile b/Makefile
index e446835..e38c74d 100644
--- a/Makefile
+++ b/Makefile
@@ -1031,7 +1031,7 @@
 endif
 
 ifeq ($(CONFIG_RELR),y)
-LDFLAGS_vmlinux	+= --pack-dyn-relocs=relr
+LDFLAGS_vmlinux	+= --pack-dyn-relocs=relr --use-android-relr-tags
 endif
 
 # We never want expected sections to be placed heuristically by the
diff --git a/arch/alpha/include/asm/page.h b/arch/alpha/include/asm/page.h
index 268f99b4..18f48a6 100644
--- a/arch/alpha/include/asm/page.h
+++ b/arch/alpha/include/asm/page.h
@@ -17,9 +17,9 @@
 extern void clear_page(void *page);
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vmaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vmaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 extern void copy_page(void * _to, void * _from);
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
index 0d67ed6..dc8f53f 100644
--- a/arch/arm/include/asm/cpuidle.h
+++ b/arch/arm/include/asm/cpuidle.h
@@ -49,4 +49,9 @@
 
 extern int arm_cpuidle_init(int cpu);
 
+struct arm_cpuidle_irq_context { };
+
+#define arm_cpuidle_save_irq_context(c)		(void)c
+#define arm_cpuidle_restore_irq_context(c)	(void)c
+
 #endif
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 2924d79..eb21904 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -773,10 +773,10 @@
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
 	} else if (idx == ARMV7_IDX_CYCLE_COUNTER) {
-		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" ((u32)value));
 	} else {
 		armv7_pmnc_select_counter(idx);
-		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value));
+		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" ((u32)value));
 	}
 }
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9f1d856..dabe9b8 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1481,12 +1481,6 @@
 config ARM64_PTR_AUTH
 	bool "Enable support for pointer authentication"
 	default y
-	depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
-	# Modern compilers insert a .note.gnu.property section note for PAC
-	# which is only understood by binutils starting with version 2.33.1.
-	depends on LD_IS_LLD || LD_VERSION >= 23301 || (CC_IS_GCC && GCC_VERSION < 90100)
-	depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE
-	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
 	help
 	  Pointer authentication (part of the ARMv8.3 Extensions) provides
 	  instructions for signing and authenticating pointers against secret
@@ -1498,13 +1492,6 @@
 	  for each process at exec() time, with these keys being
 	  context-switched along with the process.
 
-	  If the compiler supports the -mbranch-protection or
-	  -msign-return-address flag (e.g. GCC 7 or later), then this option
-	  will also cause the kernel itself to be compiled with return address
-	  protection. In this case, and if the target hardware is known to
-	  support pointer authentication, then CONFIG_STACKPROTECTOR can be
-	  disabled with minimal loss of protection.
-
 	  The feature is detected at runtime. If the feature is not present in
 	  hardware it will not be advertised to userspace/KVM guest nor will it
 	  be enabled.
@@ -1515,6 +1502,24 @@
 	  but with the feature disabled. On such a system, this option should
 	  not be selected.
 
+config ARM64_PTR_AUTH_KERNEL
+	bool "Use pointer authentication for kernel"
+	default y
+	depends on ARM64_PTR_AUTH
+	depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
+	# Modern compilers insert a .note.gnu.property section note for PAC
+	# which is only understood by binutils starting with version 2.33.1.
+	depends on LD_IS_LLD || LD_VERSION >= 23301 || (CC_IS_GCC && GCC_VERSION < 90100)
+	depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE
+	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
+	help
+	  If the compiler supports the -mbranch-protection or
+	  -msign-return-address flag (e.g. GCC 7 or later), then this option
+	  will cause the kernel itself to be compiled with return address
+	  protection. In this case, and if the target hardware is known to
+	  support pointer authentication, then CONFIG_STACKPROTECTOR can be
+	  disabled with minimal loss of protection.
+
 	  This feature works with FUNCTION_GRAPH_TRACER option only if
 	  DYNAMIC_FTRACE_WITH_REGS is enabled.
 
@@ -1606,7 +1611,7 @@
 	bool "Use Branch Target Identification for kernel"
 	default y
 	depends on ARM64_BTI
-	depends on ARM64_PTR_AUTH
+	depends on ARM64_PTR_AUTH_KERNEL
 	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
 	depends on !CC_IS_GCC || GCC_VERSION >= 100100
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index b52481f..3b5b1c4 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -70,7 +70,7 @@
 # off, this will be overridden if we are using branch protection.
 branch-prot-flags-y += $(call cc-option,-mbranch-protection=none)
 
-ifeq ($(CONFIG_ARM64_PTR_AUTH),y)
+ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
 branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all
 # We enable additional protection for leaf functions as there is some
 # narrow potential for ROP protection benefits and no substantial
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 8a078fc..7e157ab 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -3,12 +3,10 @@
 #define __ASM_ALTERNATIVE_MACROS_H
 
 #include <asm/cpucaps.h>
+#include <asm/insn-def.h>
 
 #define ARM64_CB_PATCH ARM64_NCAPS
 
-/* A64 instructions are always 32 bits. */
-#define	AARCH64_INSN_SIZE		4
-
 #ifndef __ASSEMBLY__
 
 #include <linux/stringify.h>
@@ -197,11 +195,6 @@
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
 
-.macro user_alt, label, oldinstr, newinstr, cond
-9999:	alternative_insn "\oldinstr", "\newinstr", \cond
-	_asm_extable 9999b, \label
-.endm
-
 #endif  /*  __ASSEMBLY__  */
 
 /*
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 934b9be..4ad22c3 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -124,7 +124,8 @@
 #define gic_read_lpir(c)		readq_relaxed(c)
 #define gic_write_lpir(v, c)		writeq_relaxed(v, c)
 
-#define gic_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
+#define gic_flush_dcache_to_poc(a,l)	\
+	dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
 
 #define gits_read_baser(c)		readq_relaxed(c)
 #define gits_write_baser(v, c)		writeq_relaxed(v, c)
diff --git a/arch/arm64/include/asm/asm-prototypes.h b/arch/arm64/include/asm/asm-prototypes.h
index 1c9a3a0..ec1d965 100644
--- a/arch/arm64/include/asm/asm-prototypes.h
+++ b/arch/arm64/include/asm/asm-prototypes.h
@@ -23,4 +23,10 @@
 long long __ashrti3(long long a, int b);
 long long __lshrti3(long long a, int b);
 
+/*
+ * This function uses a custom calling convention and cannot be called from C so
+ * this prototype is not entirely accurate.
+ */
+void __hwasan_tag_mismatch(unsigned long addr, unsigned long access_info);
+
 #endif /* __ASM_PROTOTYPES_H */
diff --git a/arch/arm64/include/asm/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h
index 8ca2dc0..f1bba5f 100644
--- a/arch/arm64/include/asm/asm_pointer_auth.h
+++ b/arch/arm64/include/asm/asm_pointer_auth.h
@@ -7,19 +7,7 @@
 #include <asm/cpufeature.h>
 #include <asm/sysreg.h>
 
-#ifdef CONFIG_ARM64_PTR_AUTH
-/*
- * thread.keys_user.ap* as offset exceeds the #imm offset range
- * so use the base value of ldp as thread.keys_user and offset as
- * thread.keys_user.ap*.
- */
-	.macro __ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
-	mov	\tmp1, #THREAD_KEYS_USER
-	add	\tmp1, \tsk, \tmp1
-	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIA]
-	msr_s	SYS_APIAKEYLO_EL1, \tmp2
-	msr_s	SYS_APIAKEYHI_EL1, \tmp3
-	.endm
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
 
 	.macro __ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
 	mov	\tmp1, #THREAD_KEYS_KERNEL
@@ -42,6 +30,33 @@
 alternative_else_nop_endif
 	.endm
 
+#else /* CONFIG_ARM64_PTR_AUTH_KERNEL */
+
+	.macro __ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
+	.endm
+
+	.macro ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
+	.endm
+
+	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
+	.endm
+
+#endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+/*
+ * thread.keys_user.ap* as offset exceeds the #imm offset range
+ * so use the base value of ldp as thread.keys_user and offset as
+ * thread.keys_user.ap*.
+ */
+	.macro __ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+	mov	\tmp1, #THREAD_KEYS_USER
+	add	\tmp1, \tsk, \tmp1
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIA]
+	msr_s	SYS_APIAKEYLO_EL1, \tmp2
+	msr_s	SYS_APIAKEYHI_EL1, \tmp3
+	.endm
+
 	.macro __ptrauth_keys_init_cpu tsk, tmp1, tmp2, tmp3
 	mrs	\tmp1, id_aa64isar1_el1
 	ubfx	\tmp1, \tmp1, #ID_AA64ISAR1_APA_SHIFT, #8
@@ -64,17 +79,11 @@
 .Lno_addr_auth\@:
 	.endm
 
-#else /* CONFIG_ARM64_PTR_AUTH */
+#else /* !CONFIG_ARM64_PTR_AUTH */
 
 	.macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
 	.endm
 
-	.macro ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
-	.endm
-
-	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
-	.endm
-
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
 #endif /* __ASM_ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 8418c1b..89faca0 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -130,15 +130,27 @@
 	.endm
 
 /*
- * Emit an entry into the exception table
+ * Create an exception table entry for `insn`, which will branch to `fixup`
+ * when an unhandled fault is taken.
  */
-	.macro		_asm_extable, from, to
+	.macro		_asm_extable, insn, fixup
 	.pushsection	__ex_table, "a"
 	.align		3
-	.long		(\from - .), (\to - .)
+	.long		(\insn - .), (\fixup - .)
 	.popsection
 	.endm
 
+/*
+ * Create an exception table entry for `insn` if `fixup` is provided. Otherwise
+ * do nothing.
+ */
+	.macro		_cond_extable, insn, fixup
+	.ifnc		\fixup,
+	_asm_extable	\insn, \fixup
+	.endif
+	.endm
+
+
 #define USER(l, x...)				\
 9999:	x;					\
 	_asm_extable	9999b, l
@@ -232,17 +244,25 @@
 	 * @dst: destination register
 	 */
 #if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__)
-	.macro	this_cpu_offset, dst
+	.macro	get_this_cpu_offset, dst
 	mrs	\dst, tpidr_el2
 	.endm
 #else
-	.macro	this_cpu_offset, dst
+	.macro	get_this_cpu_offset, dst
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	\dst, tpidr_el1
 alternative_else
 	mrs	\dst, tpidr_el2
 alternative_endif
 	.endm
+
+	.macro	set_this_cpu_offset, src
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+	msr	tpidr_el1, \src
+alternative_else
+	msr	tpidr_el2, \src
+alternative_endif
+	.endm
 #endif
 
 	/*
@@ -253,7 +273,7 @@
 	.macro adr_this_cpu, dst, sym, tmp
 	adrp	\tmp, \sym
 	add	\dst, \tmp, #:lo12:\sym
-	this_cpu_offset \tmp
+	get_this_cpu_offset \tmp
 	add	\dst, \dst, \tmp
 	.endm
 
@@ -264,7 +284,7 @@
 	 */
 	.macro ldr_this_cpu dst, sym, tmp
 	adr_l	\dst, \sym
-	this_cpu_offset \tmp
+	get_this_cpu_offset \tmp
 	ldr	\dst, [\dst, \tmp]
 	.endm
 
@@ -375,51 +395,53 @@
 	bfi	\tcr, \tmp0, \pos, #3
 	.endm
 
-/*
- * Macro to perform a data cache maintenance for the interval
- * [kaddr, kaddr + size)
- *
- * 	op:		operation passed to dc instruction
- * 	domain:		domain used in dsb instruciton
- * 	kaddr:		starting virtual address of the region
- * 	size:		size of the region
- * 	Corrupts:	kaddr, size, tmp1, tmp2
- */
-	.macro __dcache_op_workaround_clean_cache, op, kaddr
+	.macro __dcache_op_workaround_clean_cache, op, addr
 alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
-	dc	\op, \kaddr
+	dc	\op, \addr
 alternative_else
-	dc	civac, \kaddr
+	dc	civac, \addr
 alternative_endif
 	.endm
 
-	.macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2
+/*
+ * Macro to perform a data cache maintenance for the interval
+ * [start, end)
+ *
+ * 	op:		operation passed to dc instruction
+ * 	domain:		domain used in dsb instruciton
+ * 	start:          starting virtual address of the region
+ * 	end:            end virtual address of the region
+ * 	fixup:		optional label to branch to on user fault
+ * 	Corrupts:       start, end, tmp1, tmp2
+ */
+	.macro dcache_by_line_op op, domain, start, end, tmp1, tmp2, fixup
 	dcache_line_size \tmp1, \tmp2
-	add	\size, \kaddr, \size
 	sub	\tmp2, \tmp1, #1
-	bic	\kaddr, \kaddr, \tmp2
-9998:
+	bic	\start, \start, \tmp2
+.Ldcache_op\@:
 	.ifc	\op, cvau
-	__dcache_op_workaround_clean_cache \op, \kaddr
+	__dcache_op_workaround_clean_cache \op, \start
 	.else
 	.ifc	\op, cvac
-	__dcache_op_workaround_clean_cache \op, \kaddr
+	__dcache_op_workaround_clean_cache \op, \start
 	.else
 	.ifc	\op, cvap
-	sys	3, c7, c12, 1, \kaddr	// dc cvap
+	sys	3, c7, c12, 1, \start	// dc cvap
 	.else
 	.ifc	\op, cvadp
-	sys	3, c7, c13, 1, \kaddr	// dc cvadp
+	sys	3, c7, c13, 1, \start	// dc cvadp
 	.else
-	dc	\op, \kaddr
+	dc	\op, \start
 	.endif
 	.endif
 	.endif
 	.endif
-	add	\kaddr, \kaddr, \tmp1
-	cmp	\kaddr, \size
-	b.lo	9998b
+	add	\start, \start, \tmp1
+	cmp	\start, \end
+	b.lo	.Ldcache_op\@
 	dsb	\domain
+
+	_cond_extable .Ldcache_op\@, \fixup
 	.endm
 
 /*
@@ -427,20 +449,22 @@
  * [start, end)
  *
  * 	start, end:	virtual addresses describing the region
- *	label:		A label to branch to on user fault.
+ *	fixup:		optional label to branch to on user fault
  * 	Corrupts:	tmp1, tmp2
  */
-	.macro invalidate_icache_by_line start, end, tmp1, tmp2, label
+	.macro invalidate_icache_by_line start, end, tmp1, tmp2, fixup
 	icache_line_size \tmp1, \tmp2
 	sub	\tmp2, \tmp1, #1
 	bic	\tmp2, \start, \tmp2
-9997:
-USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
+.Licache_op\@:
+	ic	ivau, \tmp2			// invalidate I line PoU
 	add	\tmp2, \tmp2, \tmp1
 	cmp	\tmp2, \end
-	b.lo	9997b
+	b.lo	.Licache_op\@
 	dsb	ish
 	isb
+
+	_cond_extable .Licache_op\@, \fixup
 	.endm
 
 /*
@@ -745,7 +769,7 @@
 	cbz		\tmp, \lbl
 #endif
 	adr_l		\tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING
-	this_cpu_offset	\tmp2
+	get_this_cpu_offset	\tmp2
 	ldr		w\tmp, [\tmp, \tmp2]
 	cbnz		w\tmp, \lbl	// yield on pending softirq in task context
 .Lnoyield_\@:
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index a074459..a9c0716 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -47,7 +47,7 @@
  * cache before the transfer is done, causing old data to be seen by
  * the CPU.
  */
-#define ARCH_DMA_MINALIGN	(128)
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
 
 #ifdef CONFIG_KASAN_SW_TAGS
 #define ARCH_SLAB_MINALIGN	(1ULL << KASAN_SHADOW_SCALE_SHIFT)
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 52e5c16..543c997 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -30,45 +30,58 @@
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
  *	VIPT I-cache.
  *
- *	flush_icache_range(start, end)
+ *	All functions below apply to the interval [start, end)
+ *		- start  - virtual start address (inclusive)
+ *		- end    - virtual end address (exclusive)
  *
- *		Ensure coherency between the I-cache and the D-cache in the
- *		region described by start, end.
- *		- start  - virtual start address
- *		- end    - virtual end address
+ *	caches_clean_inval_pou(start, end)
  *
- *	invalidate_icache_range(start, end)
+ *		Ensure coherency between the I-cache and the D-cache region to
+ *		the Point of Unification.
  *
- *		Invalidate the I-cache in the region described by start, end.
- *		- start  - virtual start address
- *		- end    - virtual end address
+ *	caches_clean_inval_user_pou(start, end)
  *
- *	__flush_cache_user_range(start, end)
+ *		Ensure coherency between the I-cache and the D-cache region to
+ *		the Point of Unification.
+ *		Use only if the region might access user memory.
  *
- *		Ensure coherency between the I-cache and the D-cache in the
- *		region described by start, end.
- *		- start  - virtual start address
- *		- end    - virtual end address
+ *	icache_inval_pou(start, end)
  *
- *	__flush_dcache_area(kaddr, size)
+ *		Invalidate I-cache region to the Point of Unification.
  *
- *		Ensure that the data held in page is written back.
- *		- kaddr  - page address
- *		- size   - region size
+ *	dcache_clean_inval_poc(start, end)
+ *
+ *		Clean and invalidate D-cache region to the Point of Coherency.
+ *
+ *	dcache_inval_poc(start, end)
+ *
+ *		Invalidate D-cache region to the Point of Coherency.
+ *
+ *	dcache_clean_poc(start, end)
+ *
+ *		Clean D-cache region to the Point of Coherency.
+ *
+ *	dcache_clean_pop(start, end)
+ *
+ *		Clean D-cache region to the Point of Persistence.
+ *
+ *	dcache_clean_pou(start, end)
+ *
+ *		Clean D-cache region to the Point of Unification.
  */
-extern void __flush_icache_range(unsigned long start, unsigned long end);
-extern int  invalidate_icache_range(unsigned long start, unsigned long end);
-extern void __flush_dcache_area(void *addr, size_t len);
-extern void __inval_dcache_area(void *addr, size_t len);
-extern void __clean_dcache_area_poc(void *addr, size_t len);
-extern void __clean_dcache_area_pop(void *addr, size_t len);
-extern void __clean_dcache_area_pou(void *addr, size_t len);
-extern long __flush_cache_user_range(unsigned long start, unsigned long end);
-extern void sync_icache_aliases(void *kaddr, unsigned long len);
+extern void caches_clean_inval_pou(unsigned long start, unsigned long end);
+extern void icache_inval_pou(unsigned long start, unsigned long end);
+extern void dcache_clean_inval_poc(unsigned long start, unsigned long end);
+extern void dcache_inval_poc(unsigned long start, unsigned long end);
+extern void dcache_clean_poc(unsigned long start, unsigned long end);
+extern void dcache_clean_pop(unsigned long start, unsigned long end);
+extern void dcache_clean_pou(unsigned long start, unsigned long end);
+extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end);
+extern void sync_icache_aliases(unsigned long start, unsigned long end);
 
 static inline void flush_icache_range(unsigned long start, unsigned long end)
 {
-	__flush_icache_range(start, end);
+	caches_clean_inval_pou(start, end);
 
 	/*
 	 * IPI all online CPUs so that they undergo a context synchronization
@@ -122,7 +135,7 @@
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
-static __always_inline void __flush_icache_all(void)
+static __always_inline void icache_inval_all_pou(void)
 {
 	if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
 		return;
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 7faae6f..0f6d16f 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -12,26 +12,7 @@
 /*
  * Records attributes of an individual CPU.
  */
-struct cpuinfo_arm64 {
-	struct cpu	cpu;
-	struct kobject	kobj;
-	u32		reg_ctr;
-	u32		reg_cntfrq;
-	u32		reg_dczid;
-	u32		reg_midr;
-	u32		reg_revidr;
-
-	u64		reg_id_aa64dfr0;
-	u64		reg_id_aa64dfr1;
-	u64		reg_id_aa64isar0;
-	u64		reg_id_aa64isar1;
-	u64		reg_id_aa64mmfr0;
-	u64		reg_id_aa64mmfr1;
-	u64		reg_id_aa64mmfr2;
-	u64		reg_id_aa64pfr0;
-	u64		reg_id_aa64pfr1;
-	u64		reg_id_aa64zfr0;
-
+struct cpuinfo_32bit {
 	u32		reg_id_dfr0;
 	u32		reg_id_dfr1;
 	u32		reg_id_isar0;
@@ -54,6 +35,30 @@
 	u32		reg_mvfr0;
 	u32		reg_mvfr1;
 	u32		reg_mvfr2;
+};
+
+struct cpuinfo_arm64 {
+	struct cpu	cpu;
+	struct kobject	kobj;
+	u64		reg_ctr;
+	u64		reg_cntfrq;
+	u64		reg_dczid;
+	u64		reg_midr;
+	u64		reg_revidr;
+	u64		reg_gmid;
+
+	u64		reg_id_aa64dfr0;
+	u64		reg_id_aa64dfr1;
+	u64		reg_id_aa64isar0;
+	u64		reg_id_aa64isar1;
+	u64		reg_id_aa64mmfr0;
+	u64		reg_id_aa64mmfr1;
+	u64		reg_id_aa64mmfr2;
+	u64		reg_id_aa64pfr0;
+	u64		reg_id_aa64pfr1;
+	u64		reg_id_aa64zfr0;
+
+	struct cpuinfo_32bit	aarch32;
 
 	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
 	u64		reg_zcr;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 338840c..9bb9d11 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -619,6 +619,13 @@
 	return val > 0;
 }
 
+static inline bool id_aa64pfr1_mte(u64 pfr1)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT);
+
+	return val >= ID_AA64PFR1_MTE;
+}
+
 void __init setup_cpu_features(void);
 void check_local_cpu_capabilities(void);
 
@@ -630,9 +637,15 @@
 	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
 }
 
+const struct cpumask *system_32bit_el0_cpumask(void);
+DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
+
 static inline bool system_supports_32bit_el0(void)
 {
-	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
+	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	return static_branch_unlikely(&arm64_mismatched_32bit_el0) ||
+	       id_aa64pfr0_32bit_el0(pfr0);
 }
 
 static inline bool system_supports_4kb_granule(void)
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
index 3c5ddb4..14a19d1 100644
--- a/arch/arm64/include/asm/cpuidle.h
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -18,4 +18,39 @@
 	return -EOPNOTSUPP;
 }
 #endif
+
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+#include <asm/arch_gicv3.h>
+
+struct arm_cpuidle_irq_context {
+	unsigned long pmr;
+	unsigned long daif_bits;
+};
+
+#define arm_cpuidle_save_irq_context(__c)				\
+	do {								\
+		struct arm_cpuidle_irq_context *c = __c;		\
+		if (system_uses_irq_prio_masking()) {			\
+			c->daif_bits = read_sysreg(daif);		\
+			write_sysreg(c->daif_bits | PSR_I_BIT | PSR_F_BIT, \
+				     daif);				\
+			c->pmr = gic_read_pmr();			\
+			gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); \
+		}							\
+	} while (0)
+
+#define arm_cpuidle_restore_irq_context(__c)				\
+	do {								\
+		struct arm_cpuidle_irq_context *c = __c;		\
+		if (system_uses_irq_prio_masking()) {			\
+			gic_write_pmr(c->pmr);				\
+			write_sysreg(c->daif_bits, daif);		\
+		}							\
+	} while (0)
+#else
+struct arm_cpuidle_irq_context { };
+
+#define arm_cpuidle_save_irq_context(c)		(void)c
+#define arm_cpuidle_restore_irq_context(c)	(void)c
+#endif
 #endif
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 3578aba..1bed37e 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -137,7 +137,7 @@
 
 static inline void efi_capsule_flush_cache_range(void *addr, int size)
 {
-	__flush_dcache_area(addr, size);
+	dcache_clean_inval_poc((unsigned long)addr, (unsigned long)addr + size);
 }
 
 #endif /* _ASM_EFI_H */
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 6546158..4afbc45 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -31,20 +31,35 @@
 	return esr;
 }
 
-asmlinkage void el1_sync_handler(struct pt_regs *regs);
-asmlinkage void el0_sync_handler(struct pt_regs *regs);
-asmlinkage void el0_sync_compat_handler(struct pt_regs *regs);
+asmlinkage void handle_bad_stack(struct pt_regs *regs);
 
-asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs);
-asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs);
+asmlinkage void el1t_64_sync_handler(struct pt_regs *regs);
+asmlinkage void el1t_64_irq_handler(struct pt_regs *regs);
+asmlinkage void el1t_64_fiq_handler(struct pt_regs *regs);
+asmlinkage void el1t_64_error_handler(struct pt_regs *regs);
+
+asmlinkage void el1h_64_sync_handler(struct pt_regs *regs);
+asmlinkage void el1h_64_irq_handler(struct pt_regs *regs);
+asmlinkage void el1h_64_fiq_handler(struct pt_regs *regs);
+asmlinkage void el1h_64_error_handler(struct pt_regs *regs);
+
+asmlinkage void el0t_64_sync_handler(struct pt_regs *regs);
+asmlinkage void el0t_64_irq_handler(struct pt_regs *regs);
+asmlinkage void el0t_64_fiq_handler(struct pt_regs *regs);
+asmlinkage void el0t_64_error_handler(struct pt_regs *regs);
+
+asmlinkage void el0t_32_sync_handler(struct pt_regs *regs);
+asmlinkage void el0t_32_irq_handler(struct pt_regs *regs);
+asmlinkage void el0t_32_fiq_handler(struct pt_regs *regs);
+asmlinkage void el0t_32_error_handler(struct pt_regs *regs);
+
+asmlinkage void call_on_irq_stack(struct pt_regs *regs,
+				  void (*func)(struct pt_regs *));
 asmlinkage void enter_from_user_mode(void);
 asmlinkage void exit_to_user_mode(void);
-void arm64_enter_nmi(struct pt_regs *regs);
-void arm64_exit_nmi(struct pt_regs *regs);
 void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs);
 void do_undefinstr(struct pt_regs *regs);
 void do_bti(struct pt_regs *regs);
-asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr);
 void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 			struct pt_regs *regs);
 void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs);
@@ -57,4 +72,7 @@
 void do_el0_svc(struct pt_regs *regs);
 void do_el0_svc_compat(struct pt_regs *regs);
 void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr);
+void do_serror(struct pt_regs *regs, unsigned int esr);
+
+void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far);
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/insn-def.h b/arch/arm64/include/asm/insn-def.h
new file mode 100644
index 0000000..2c075f6
--- /dev/null
+++ b/arch/arm64/include/asm/insn-def.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_INSN_DEF_H
+#define __ASM_INSN_DEF_H
+
+/* A64 instructions are always 32 bits. */
+#define	AARCH64_INSN_SIZE		4
+
+#endif /* __ASM_INSN_DEF_H */
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 4ebb9c0..6b776c8 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -10,7 +10,7 @@
 #include <linux/build_bug.h>
 #include <linux/types.h>
 
-#include <asm/alternative.h>
+#include <asm/insn-def.h>
 
 #ifndef __ASSEMBLY__
 /*
@@ -30,6 +30,7 @@
  */
 enum aarch64_insn_encoding_class {
 	AARCH64_INSN_CLS_UNKNOWN,	/* UNALLOCATED */
+	AARCH64_INSN_CLS_SVE,		/* SVE instructions */
 	AARCH64_INSN_CLS_DP_IMM,	/* Data processing - immediate */
 	AARCH64_INSN_CLS_DP_REG,	/* Data processing - register */
 	AARCH64_INSN_CLS_DP_FPSIMD,	/* Data processing - SIMD and FP */
@@ -294,6 +295,12 @@
 __AARCH64_INSN_FUNCS(adrp,	0x9F000000, 0x90000000)
 __AARCH64_INSN_FUNCS(prfm,	0x3FC00000, 0x39800000)
 __AARCH64_INSN_FUNCS(prfm_lit,	0xFF000000, 0xD8000000)
+__AARCH64_INSN_FUNCS(store_imm,	0x3FC00000, 0x39000000)
+__AARCH64_INSN_FUNCS(load_imm,	0x3FC00000, 0x39400000)
+__AARCH64_INSN_FUNCS(store_pre,	0x3FE00C00, 0x38000C00)
+__AARCH64_INSN_FUNCS(load_pre,	0x3FE00C00, 0x38400C00)
+__AARCH64_INSN_FUNCS(store_post,	0x3FE00C00, 0x38000400)
+__AARCH64_INSN_FUNCS(load_post,	0x3FE00C00, 0x38400400)
 __AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
 __AARCH64_INSN_FUNCS(ldadd,	0x3F20FC00, 0x38200000)
 __AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
@@ -302,6 +309,8 @@
 __AARCH64_INSN_FUNCS(exclusive,	0x3F800000, 0x08000000)
 __AARCH64_INSN_FUNCS(load_ex,	0x3F400000, 0x08400000)
 __AARCH64_INSN_FUNCS(store_ex,	0x3F400000, 0x08000000)
+__AARCH64_INSN_FUNCS(stp,	0x7FC00000, 0x29000000)
+__AARCH64_INSN_FUNCS(ldp,	0x7FC00000, 0x29400000)
 __AARCH64_INSN_FUNCS(stp_post,	0x7FC00000, 0x28800000)
 __AARCH64_INSN_FUNCS(ldp_post,	0x7FC00000, 0x28C00000)
 __AARCH64_INSN_FUNCS(stp_pre,	0x7FC00000, 0x29800000)
@@ -334,6 +343,7 @@
 __AARCH64_INSN_FUNCS(and,	0x7F200000, 0x0A000000)
 __AARCH64_INSN_FUNCS(bic,	0x7F200000, 0x0A200000)
 __AARCH64_INSN_FUNCS(orr,	0x7F200000, 0x2A000000)
+__AARCH64_INSN_FUNCS(mov_reg,	0x7FE0FFE0, 0x2A0003E0)
 __AARCH64_INSN_FUNCS(orn,	0x7F200000, 0x2A200000)
 __AARCH64_INSN_FUNCS(eor,	0x7F200000, 0x4A000000)
 __AARCH64_INSN_FUNCS(eon,	0x7F200000, 0x4A200000)
@@ -368,6 +378,14 @@
 __AARCH64_INSN_FUNCS(mrs,	0xFFF00000, 0xD5300000)
 __AARCH64_INSN_FUNCS(msr_imm,	0xFFF8F01F, 0xD500401F)
 __AARCH64_INSN_FUNCS(msr_reg,	0xFFF00000, 0xD5100000)
+__AARCH64_INSN_FUNCS(dmb,	0xFFFFF0FF, 0xD50330BF)
+__AARCH64_INSN_FUNCS(dsb_base,	0xFFFFF0FF, 0xD503309F)
+__AARCH64_INSN_FUNCS(dsb_nxs,	0xFFFFF3FF, 0xD503323F)
+__AARCH64_INSN_FUNCS(isb,	0xFFFFF0FF, 0xD50330DF)
+__AARCH64_INSN_FUNCS(sb,	0xFFFFFFFF, 0xD50330FF)
+__AARCH64_INSN_FUNCS(clrex,	0xFFFFF0FF, 0xD503305F)
+__AARCH64_INSN_FUNCS(ssbb,	0xFFFFFFFF, 0xD503309F)
+__AARCH64_INSN_FUNCS(pssbb,	0xFFFFFFFF, 0xD503349F)
 
 #undef	__AARCH64_INSN_FUNCS
 
@@ -379,8 +397,47 @@
 	return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn);
 }
 
-int aarch64_insn_read(void *addr, u32 *insnp);
-int aarch64_insn_write(void *addr, u32 insn);
+static inline bool aarch64_insn_is_dsb(u32 insn)
+{
+	return aarch64_insn_is_dsb_base(insn) || aarch64_insn_is_dsb_nxs(insn);
+}
+
+static inline bool aarch64_insn_is_barrier(u32 insn)
+{
+	return aarch64_insn_is_dmb(insn) || aarch64_insn_is_dsb(insn) ||
+	       aarch64_insn_is_isb(insn) || aarch64_insn_is_sb(insn) ||
+	       aarch64_insn_is_clrex(insn) || aarch64_insn_is_ssbb(insn) ||
+	       aarch64_insn_is_pssbb(insn);
+}
+
+static inline bool aarch64_insn_is_store_single(u32 insn)
+{
+	return aarch64_insn_is_store_imm(insn) ||
+	       aarch64_insn_is_store_pre(insn) ||
+	       aarch64_insn_is_store_post(insn);
+}
+
+static inline bool aarch64_insn_is_store_pair(u32 insn)
+{
+	return aarch64_insn_is_stp(insn) ||
+	       aarch64_insn_is_stp_pre(insn) ||
+	       aarch64_insn_is_stp_post(insn);
+}
+
+static inline bool aarch64_insn_is_load_single(u32 insn)
+{
+	return aarch64_insn_is_load_imm(insn) ||
+	       aarch64_insn_is_load_pre(insn) ||
+	       aarch64_insn_is_load_post(insn);
+}
+
+static inline bool aarch64_insn_is_load_pair(u32 insn)
+{
+	return aarch64_insn_is_ldp(insn) ||
+	       aarch64_insn_is_ldp_pre(insn) ||
+	       aarch64_insn_is_ldp_post(insn);
+}
+
 enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
 bool aarch64_insn_uses_literal(u32 insn);
 bool aarch64_insn_is_branch(u32 insn);
@@ -487,9 +544,6 @@
 s32 aarch64_get_branch_offset(u32 insn);
 u32 aarch64_set_branch_offset(u32 insn, s32 offset);
 
-int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
-int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
-
 s32 aarch64_insn_adrp_get_offset(u32 insn);
 u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset);
 
@@ -506,6 +560,7 @@
 
 typedef bool (pstate_check_t)(unsigned long);
 extern pstate_check_t * const aarch32_opcode_cond_checks[16];
+
 #endif /* __ASSEMBLY__ */
 
 #endif	/* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index d44df9d..3512184 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -18,9 +18,9 @@
  * 64K (section size = 512M).
  */
 #ifdef CONFIG_ARM64_4K_PAGES
-#define ARM64_SWAPPER_USES_SECTION_MAPS 1
+#define ARM64_KERNEL_USES_PMD_MAPS 1
 #else
-#define ARM64_SWAPPER_USES_SECTION_MAPS 0
+#define ARM64_KERNEL_USES_PMD_MAPS 0
 #endif
 
 /*
@@ -33,7 +33,7 @@
  * VA range, so pages required to map highest possible PA are reserved in all
  * cases.
  */
-#if ARM64_SWAPPER_USES_SECTION_MAPS
+#if ARM64_KERNEL_USES_PMD_MAPS
 #define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS - 1)
 #define IDMAP_PGTABLE_LEVELS	(ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT) - 1)
 #else
@@ -90,9 +90,9 @@
 #define IDMAP_DIR_SIZE		(IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
 
 /* Initial memory map size */
-#if ARM64_SWAPPER_USES_SECTION_MAPS
-#define SWAPPER_BLOCK_SHIFT	SECTION_SHIFT
-#define SWAPPER_BLOCK_SIZE	SECTION_SIZE
+#if ARM64_KERNEL_USES_PMD_MAPS
+#define SWAPPER_BLOCK_SHIFT	PMD_SHIFT
+#define SWAPPER_BLOCK_SIZE	PMD_SIZE
 #define SWAPPER_TABLE_SHIFT	PUD_SHIFT
 #else
 #define SWAPPER_BLOCK_SHIFT	PAGE_SHIFT
@@ -100,16 +100,13 @@
 #define SWAPPER_TABLE_SHIFT	PMD_SHIFT
 #endif
 
-/* The size of the initial kernel direct mapping */
-#define SWAPPER_INIT_MAP_SIZE	(_AC(1, UL) << SWAPPER_TABLE_SHIFT)
-
 /*
  * Initial memory map attributes.
  */
 #define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
-#if ARM64_SWAPPER_USES_SECTION_MAPS
+#if ARM64_KERNEL_USES_PMD_MAPS
 #define SWAPPER_MM_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
 #else
 #define SWAPPER_MM_MMUFLAGS	(PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS)
@@ -125,7 +122,7 @@
 #if defined(CONFIG_ARM64_4K_PAGES)
 #define ARM64_MEMSTART_SHIFT		PUD_SHIFT
 #elif defined(CONFIG_ARM64_16K_PAGES)
-#define ARM64_MEMSTART_SHIFT		(PMD_SHIFT + 5)
+#define ARM64_MEMSTART_SHIFT		CONT_PMD_SHIFT
 #else
 #define ARM64_MEMSTART_SHIFT		PMD_SHIFT
 #endif
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index cf8df03..894edda 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -8,6 +8,7 @@
 #define __ARM_KVM_ASM_H__
 
 #include <asm/hyp_image.h>
+#include <asm/insn.h>
 #include <asm/virt.h>
 
 #define ARM_EXIT_WITH_SERROR_BIT  31
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 25ed956..f4cbfa9 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -180,7 +180,8 @@
 
 struct kvm;
 
-#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
+#define kvm_flush_dcache_to_poc(a,l)	\
+	dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
 
 static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
@@ -208,12 +209,12 @@
 {
 	if (icache_is_aliasing()) {
 		/* any kind of VIPT cache */
-		__flush_icache_all();
+		icache_inval_all_pou();
 	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
 		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
 		void *va = page_address(pfn_to_page(pfn));
 
-		invalidate_icache_range((unsigned long)va,
+		icache_inval_pou((unsigned long)va,
 					(unsigned long)va + size);
 	}
 }
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index ba89a9a..9906541 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -56,8 +56,16 @@
 		SYM_FUNC_START_ALIAS(__pi_##x);	\
 		SYM_FUNC_START_WEAK(x)
 
+#define SYM_FUNC_START_WEAK_ALIAS_PI(x)		\
+		SYM_FUNC_START_ALIAS(__pi_##x);	\
+		SYM_START(x, SYM_L_WEAK, SYM_A_ALIGN)
+
 #define SYM_FUNC_END_PI(x)			\
 		SYM_FUNC_END(x);		\
 		SYM_FUNC_END_ALIAS(__pi_##x)
 
+#define SYM_FUNC_END_ALIAS_PI(x)		\
+		SYM_FUNC_END_ALIAS(x);		\
+		SYM_FUNC_END_ALIAS(__pi_##x)
+
 #endif
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 87b90dc..7b36096 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -135,10 +135,8 @@
 #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
+#define MT_DEVICE_nGnRnE	3
+#define MT_DEVICE_nGnRE		4
 
 /*
  * Memory types for Stage-2 translation
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index d3cef91..eeb2109 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -177,9 +177,9 @@
 		return;
 
 	if (mm == &init_mm)
-		ttbr = __pa_symbol(reserved_pg_dir);
+		ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
 	else
-		ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48;
+		ttbr = phys_to_ttbr(virt_to_phys(mm->pgd)) | ASID(mm) << 48;
 
 	WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr);
 }
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
index 8100456..a11ccad 100644
--- a/arch/arm64/include/asm/module.lds.h
+++ b/arch/arm64/include/asm/module.lds.h
@@ -1,7 +1,20 @@
-#ifdef CONFIG_ARM64_MODULE_PLTS
 SECTIONS {
+#ifdef CONFIG_ARM64_MODULE_PLTS
 	.plt 0 (NOLOAD) : { BYTE(0) }
 	.init.plt 0 (NOLOAD) : { BYTE(0) }
 	.text.ftrace_trampoline 0 (NOLOAD) : { BYTE(0) }
-}
 #endif
+
+#ifdef CONFIG_KASAN_SW_TAGS
+	/*
+	 * Outlined checks go into comdat-deduplicated sections named .text.hot.
+	 * Because they are in comdats they are not combined by the linker and
+	 * we otherwise end up with multiple sections with the same .text.hot
+	 * name in the .ko file. The kernel module loader warns if it sees
+	 * multiple sections with the same name so we use this sections
+	 * directive to force them into a single section and silence the
+	 * warning.
+	 */
+	.text.hot : { *(.text.hot) }
+#endif
+}
diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
index ddd4d17..d952352 100644
--- a/arch/arm64/include/asm/mte-kasan.h
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -48,43 +48,84 @@
 	return mte_get_ptr_tag(addr);
 }
 
+static inline u64 __stg_post(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "stg %0, [%0], #16"
+		     : "+r"(p)
+		     :
+		     : "memory");
+	return p;
+}
+
+static inline u64 __stzg_post(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "stzg %0, [%0], #16"
+		     : "+r"(p)
+		     :
+		     : "memory");
+	return p;
+}
+
+static inline void __dc_gva(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "dc gva, %0" : : "r"(p) : "memory");
+}
+
+static inline void __dc_gzva(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "dc gzva, %0" : : "r"(p) : "memory");
+}
+
 /*
  * Assign allocation tags for a region of memory based on the pointer tag.
  * Note: The address must be non-NULL and MTE_GRANULE_SIZE aligned and
- * size must be non-zero and MTE_GRANULE_SIZE aligned.
+ * size must be MTE_GRANULE_SIZE aligned.
  */
-static inline void mte_set_mem_tag_range(void *addr, size_t size,
-						u8 tag, bool init)
+static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag,
+					 bool init)
 {
-	u64 curr, end;
+	u64 curr, mask, dczid_bs, end1, end2, end3;
 
-	if (!size)
-		return;
+	/* Read DC G(Z)VA block size from the system register. */
+	dczid_bs = 4ul << (read_cpuid(DCZID_EL0) & 0xf);
 
 	curr = (u64)__tag_set(addr, tag);
-	end = curr + size;
+	mask = dczid_bs - 1;
+	/* STG/STZG up to the end of the first block. */
+	end1 = curr | mask;
+	end3 = curr + size;
+	/* DC GVA / GZVA in [end1, end2) */
+	end2 = end3 & ~mask;
 
 	/*
-	 * 'asm volatile' is required to prevent the compiler to move
-	 * the statement outside of the loop.
+	 * The following code uses STG on the first DC GVA block even if the
+	 * start address is aligned - it appears to be faster than an alignment
+	 * check + conditional branch. Also, if the range size is at least 2 DC
+	 * GVA blocks, the first two loops can use post-condition to save one
+	 * branch each.
 	 */
-	if (init) {
-		do {
-			asm volatile(__MTE_PREAMBLE "stzg %0, [%0]"
-				     :
-				     : "r" (curr)
-				     : "memory");
-			curr += MTE_GRANULE_SIZE;
-		} while (curr != end);
-	} else {
-		do {
-			asm volatile(__MTE_PREAMBLE "stg %0, [%0]"
-				     :
-				     : "r" (curr)
-				     : "memory");
-			curr += MTE_GRANULE_SIZE;
-		} while (curr != end);
-	}
+#define SET_MEMTAG_RANGE(stg_post, dc_gva)		\
+	do {						\
+		if (size >= 2 * dczid_bs) {		\
+			do {				\
+				curr = stg_post(curr);	\
+			} while (curr < end1);		\
+							\
+			do {				\
+				dc_gva(curr);		\
+				curr += dczid_bs;	\
+			} while (curr < end2);		\
+		}					\
+							\
+		while (curr < end3)			\
+			curr = stg_post(curr);		\
+	} while (0)
+
+	if (init)
+		SET_MEMTAG_RANGE(__stzg_post, __dc_gzva);
+	else
+		SET_MEMTAG_RANGE(__stg_post, __dc_gva);
+#undef SET_MEMTAG_RANGE
 }
 
 void mte_enable_kernel_sync(void);
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index bc88a1c..67bf259 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -37,6 +37,7 @@
 /* track which pages have valid allocation tags */
 #define PG_mte_tagged	PG_arch_2
 
+void mte_zero_clear_page_tags(void *addr);
 void mte_sync_tags(pte_t *ptep, pte_t pte);
 void mte_copy_page_tags(void *kto, const void *kfrom);
 void mte_thread_init_user(void);
@@ -53,6 +54,9 @@
 /* unused if !CONFIG_ARM64_MTE, silence the compiler */
 #define PG_mte_tagged	0
 
+static inline void mte_zero_clear_page_tags(void *addr)
+{
+}
 static inline void mte_sync_tags(pte_t *ptep, pte_t pte)
 {
 }
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 012cffc..ed1b9dc 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -13,6 +13,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/personality.h> /* for READ_IMPLIES_EXEC */
+#include <linux/types.h> /* for gfp_t */
 #include <asm/pgtable-types.h>
 
 struct page;
@@ -28,9 +29,12 @@
 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
+struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+						unsigned long vaddr);
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
+
+void tag_clear_highpage(struct page *to);
+#define __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
 
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
diff --git a/arch/arm64/include/asm/patching.h b/arch/arm64/include/asm/patching.h
new file mode 100644
index 0000000..6bf5adc
--- /dev/null
+++ b/arch/arm64/include/asm/patching.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef	__ASM_PATCHING_H
+#define	__ASM_PATCHING_H
+
+#include <linux/types.h>
+
+int aarch64_insn_read(void *addr, u32 *insnp);
+int aarch64_insn_write(void *addr, u32 insn);
+
+int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
+int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
+
+#endif	/* __ASM_PATCHING_H */
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 60731f6..4ef6f19 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -239,6 +239,11 @@
 /* PMMIR_EL1.SLOTS mask */
 #define ARMV8_PMU_SLOTS_MASK	0xff
 
+#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
+#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
+#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
+#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+
 #ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index b82575a..40085e5 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -72,13 +72,6 @@
 #define PTRS_PER_PGD		(1 << (VA_BITS - PGDIR_SHIFT))
 
 /*
- * Section address mask and size definitions.
- */
-#define SECTION_SHIFT		PMD_SHIFT
-#define SECTION_SIZE		(_AC(1, UL) << SECTION_SHIFT)
-#define SECTION_MASK		(~(SECTION_SIZE-1))
-
-/*
  * Contiguous page definitions.
  */
 #define CONT_PTE_SHIFT		(CONFIG_ARM64_CONT_PTE_SHIFT + PAGE_SHIFT)
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 938092d..7032f04 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -55,7 +55,6 @@
 #define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
 #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))
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0b10204..11e60d0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -511,13 +511,12 @@
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
 
-#define pmd_bad(pmd)		(!(pmd_val(pmd) & PMD_TABLE_BIT))
-
 #define pmd_table(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
 				 PMD_TYPE_TABLE)
 #define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
 				 PMD_TYPE_SECT)
 #define pmd_leaf(pmd)		pmd_sect(pmd)
+#define pmd_bad(pmd)		(!pmd_table(pmd))
 
 #define pmd_leaf_size(pmd)	(pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE)
 #define pte_leaf_size(pte)	(pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE)
@@ -604,7 +603,7 @@
 	pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
 
 #define pud_none(pud)		(!pud_val(pud))
-#define pud_bad(pud)		(!(pud_val(pud) & PUD_TABLE_BIT))
+#define pud_bad(pud)		(!pud_table(pud))
 #define pud_present(pud)	pte_present(pud_pte(pud))
 #define pud_leaf(pud)		pud_sect(pud)
 #define pud_valid(pud)		pte_valid(pud_pte(pud))
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index d50416b..28a78b6 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -31,10 +31,6 @@
 	struct ptrauth_key apga;
 };
 
-struct ptrauth_keys_kernel {
-	struct ptrauth_key apia;
-};
-
 #define __ptrauth_key_install_nosync(k, v)			\
 do {								\
 	struct ptrauth_key __pki_v = (v);			\
@@ -42,6 +38,29 @@
 	write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1);	\
 } while (0)
 
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
+
+struct ptrauth_keys_kernel {
+	struct ptrauth_key apia;
+};
+
+static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
+{
+	if (system_supports_address_auth())
+		get_random_bytes(&keys->apia, sizeof(keys->apia));
+}
+
+static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys)
+{
+	if (!system_supports_address_auth())
+		return;
+
+	__ptrauth_key_install_nosync(APIA, keys->apia);
+	isb();
+}
+
+#endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */
+
 static inline void ptrauth_keys_install_user(struct ptrauth_keys_user *keys)
 {
 	if (system_supports_address_auth()) {
@@ -69,21 +88,6 @@
 	ptrauth_keys_install_user(keys);
 }
 
-static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
-{
-	if (system_supports_address_auth())
-		get_random_bytes(&keys->apia, sizeof(keys->apia));
-}
-
-static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys)
-{
-	if (!system_supports_address_auth())
-		return;
-
-	__ptrauth_key_install_nosync(APIA, keys->apia);
-	isb();
-}
-
 extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
 
 extern int ptrauth_set_enabled_keys(struct task_struct *tsk, unsigned long keys,
@@ -121,11 +125,6 @@
 #define ptrauth_thread_switch_user(tsk)                                        \
 	ptrauth_keys_install_user(&(tsk)->thread.keys_user)
 
-#define ptrauth_thread_init_kernel(tsk)					\
-	ptrauth_keys_init_kernel(&(tsk)->thread.keys_kernel)
-#define ptrauth_thread_switch_kernel(tsk)				\
-	ptrauth_keys_switch_kernel(&(tsk)->thread.keys_kernel)
-
 #else /* CONFIG_ARM64_PTR_AUTH */
 #define ptrauth_enable()
 #define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
@@ -134,11 +133,19 @@
 #define ptrauth_strip_insn_pac(lr)	(lr)
 #define ptrauth_suspend_exit()
 #define ptrauth_thread_init_user()
-#define ptrauth_thread_init_kernel(tsk)
 #define ptrauth_thread_switch_user(tsk)
-#define ptrauth_thread_switch_kernel(tsk)
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
+#define ptrauth_thread_init_kernel(tsk)					\
+	ptrauth_keys_init_kernel(&(tsk)->thread.keys_kernel)
+#define ptrauth_thread_switch_kernel(tsk)				\
+	ptrauth_keys_switch_kernel(&(tsk)->thread.keys_kernel)
+#else
+#define ptrauth_thread_init_kernel(tsk)
+#define ptrauth_thread_switch_kernel(tsk)
+#endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */
+
 #define PR_PAC_ENABLED_KEYS_MASK                                               \
 	(PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY)
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 9df3fee..b6517fd 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -148,8 +148,10 @@
 	struct debug_info	debug;		/* debugging */
 #ifdef CONFIG_ARM64_PTR_AUTH
 	struct ptrauth_keys_user	keys_user;
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
 	struct ptrauth_keys_kernel	keys_kernel;
 #endif
+#endif
 #ifdef CONFIG_ARM64_MTE
 	u64			gcr_user_excl;
 #endif
@@ -257,8 +259,6 @@
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 					 struct task_struct *next);
 
-asmlinkage void arm64_preempt_schedule_irq(void);
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
 
@@ -329,13 +329,13 @@
  * of header definitions for the use of task_stack_page.
  */
 
-#define current_top_of_stack()							\
-({										\
-	struct stack_info _info;						\
-	BUG_ON(!on_accessible_stack(current, current_stack_pointer, &_info));	\
-	_info.high;								\
+#define current_top_of_stack()								\
+({											\
+	struct stack_info _info;							\
+	BUG_ON(!on_accessible_stack(current, current_stack_pointer, 1, &_info));	\
+	_info.high;									\
 })
-#define on_thread_stack()	(on_task_stack(current, current_stack_pointer, NULL))
+#define on_thread_stack()	(on_task_stack(current, current_stack_pointer, 1, NULL))
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
index eaa2cd9..8297bcc 100644
--- a/arch/arm64/include/asm/scs.h
+++ b/arch/arm64/include/asm/scs.h
@@ -9,18 +9,18 @@
 #ifdef CONFIG_SHADOW_CALL_STACK
 	scs_sp	.req	x18
 
-	.macro scs_load tsk, tmp
+	.macro scs_load tsk
 	ldr	scs_sp, [\tsk, #TSK_TI_SCS_SP]
 	.endm
 
-	.macro scs_save tsk, tmp
+	.macro scs_save tsk
 	str	scs_sp, [\tsk, #TSK_TI_SCS_SP]
 	.endm
 #else
-	.macro scs_load tsk, tmp
+	.macro scs_load tsk
 	.endm
 
-	.macro scs_save tsk, tmp
+	.macro scs_save tsk
 	.endm
 #endif /* CONFIG_SHADOW_CALL_STACK */
 
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
index 63e0b92..7bea1d7 100644
--- a/arch/arm64/include/asm/sdei.h
+++ b/arch/arm64/include/asm/sdei.h
@@ -37,13 +37,17 @@
 asmlinkage unsigned long __sdei_handler(struct pt_regs *regs,
 					struct sdei_registered_event *arg);
 
+unsigned long do_sdei_event(struct pt_regs *regs,
+			    struct sdei_registered_event *arg);
+
 unsigned long sdei_arch_get_entry_point(int conduit);
 #define sdei_arch_get_entry_point(x)	sdei_arch_get_entry_point(x)
 
 struct stack_info;
 
-bool _on_sdei_stack(unsigned long sp, struct stack_info *info);
-static inline bool on_sdei_stack(unsigned long sp,
+bool _on_sdei_stack(unsigned long sp, unsigned long size,
+		    struct stack_info *info);
+static inline bool on_sdei_stack(unsigned long sp, unsigned long size,
 				struct stack_info *info)
 {
 	if (!IS_ENABLED(CONFIG_VMAP_STACK))
@@ -51,7 +55,7 @@
 	if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
 		return false;
 	if (in_nmi())
-		return _on_sdei_stack(sp, info);
+		return _on_sdei_stack(sp, size, info);
 
 	return false;
 }
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 0e35775..fc55f5a 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -73,12 +73,10 @@
 
 /*
  * Initial data for bringing up a secondary CPU.
- * @stack  - sp for the secondary CPU
  * @status - Result passed back from the secondary CPU to
  *           indicate failure.
  */
 struct secondary_data {
-	void *stack;
 	struct task_struct *task;
 	long status;
 };
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 4b33ca6..1801399 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -69,14 +69,14 @@
 
 DECLARE_PER_CPU(unsigned long *, irq_stack_ptr);
 
-static inline bool on_stack(unsigned long sp, unsigned long low,
-				unsigned long high, enum stack_type type,
-				struct stack_info *info)
+static inline bool on_stack(unsigned long sp, unsigned long size,
+			    unsigned long low, unsigned long high,
+			    enum stack_type type, struct stack_info *info)
 {
 	if (!low)
 		return false;
 
-	if (sp < low || sp >= high)
+	if (sp < low || sp + size < sp || sp + size > high)
 		return false;
 
 	if (info) {
@@ -87,38 +87,38 @@
 	return true;
 }
 
-static inline bool on_irq_stack(unsigned long sp,
+static inline bool on_irq_stack(unsigned long sp, unsigned long size,
 				struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
 	unsigned long high = low + IRQ_STACK_SIZE;
 
-	return on_stack(sp, low, high, STACK_TYPE_IRQ, info);
+	return on_stack(sp, size, low, high, STACK_TYPE_IRQ, info);
 }
 
 static inline bool on_task_stack(const struct task_struct *tsk,
-				 unsigned long sp,
+				 unsigned long sp, unsigned long size,
 				 struct stack_info *info)
 {
 	unsigned long low = (unsigned long)task_stack_page(tsk);
 	unsigned long high = low + THREAD_SIZE;
 
-	return on_stack(sp, low, high, STACK_TYPE_TASK, info);
+	return on_stack(sp, size, low, high, STACK_TYPE_TASK, info);
 }
 
 #ifdef CONFIG_VMAP_STACK
 DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
 
-static inline bool on_overflow_stack(unsigned long sp,
+static inline bool on_overflow_stack(unsigned long sp, unsigned long size,
 				struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
 	unsigned long high = low + OVERFLOW_STACK_SIZE;
 
-	return on_stack(sp, low, high, STACK_TYPE_OVERFLOW, info);
+	return on_stack(sp, size, low, high, STACK_TYPE_OVERFLOW, info);
 }
 #else
-static inline bool on_overflow_stack(unsigned long sp,
+static inline bool on_overflow_stack(unsigned long sp, unsigned long size,
 			struct stack_info *info) { return false; }
 #endif
 
@@ -128,21 +128,21 @@
  * context.
  */
 static inline bool on_accessible_stack(const struct task_struct *tsk,
-				       unsigned long sp,
+				       unsigned long sp, unsigned long size,
 				       struct stack_info *info)
 {
 	if (info)
 		info->type = STACK_TYPE_UNKNOWN;
 
-	if (on_task_stack(tsk, sp, info))
+	if (on_task_stack(tsk, sp, size, info))
 		return true;
 	if (tsk != current || preemptible())
 		return false;
-	if (on_irq_stack(sp, info))
+	if (on_irq_stack(sp, size, info))
 		return true;
-	if (on_overflow_stack(sp, info))
+	if (on_overflow_stack(sp, size, info))
 		return true;
-	if (on_sdei_stack(sp, info))
+	if (on_sdei_stack(sp, size, info))
 		return true;
 
 	return false;
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 65d15700..9ea84bc 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -703,9 +703,7 @@
 /* MAIR_ELx memory attributes (used by Linux) */
 #define MAIR_ATTR_DEVICE_nGnRnE		UL(0x00)
 #define MAIR_ATTR_DEVICE_nGnRE		UL(0x04)
-#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)
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 61c97d3..c995d1f 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -28,6 +28,10 @@
  */
 static inline int tlb_get_level(struct mmu_gather *tlb)
 {
+	/* The TTL field is only valid for the leaf entry. */
+	if (tlb->freed_tables)
+		return 0;
+
 	if (tlb->cleared_ptes && !(tlb->cleared_pmds ||
 				   tlb->cleared_puds ||
 				   tlb->cleared_p4ds))
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 6cc9773..cce3085 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -14,15 +14,22 @@
 CFLAGS_REMOVE_syscall.o	 = -fstack-protector -fstack-protector-strong
 CFLAGS_syscall.o	+= -fno-stack-protector
 
+# It's not safe to invoke KCOV when portions of the kernel environment aren't
+# available or are out-of-sync with HW state. Since `noinstr` doesn't always
+# inhibit KCOV instrumentation, disable it for the entire compilation unit.
+KCOV_INSTRUMENT_entry.o := n
+KCOV_INSTRUMENT_idle.o := n
+
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-common.o entry-fpsimd.o process.o ptrace.o	\
 			   setup.o signal.o sys.o stacktrace.o time.o traps.o	\
-			   io.o vdso.o hyp-stub.o psci.o cpu_ops.o insn.o	\
+			   io.o vdso.o hyp-stub.o psci.o cpu_ops.o		\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
-			   syscall.o proton-pack.o idreg-override.o
+			   syscall.o proton-pack.o idreg-override.o idle.o	\
+			   patching.o
 
 targets			+= efi-entry.o
 
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index cada0b8..f385172 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -239,6 +239,18 @@
 	}
 }
 
+static pgprot_t __acpi_get_writethrough_mem_attribute(void)
+{
+	/*
+	 * Although UEFI specifies the use of Normal Write-through for
+	 * EFI_MEMORY_WT, it is seldom used in practice and not implemented
+	 * by most (all?) CPUs. Rather than allocate a MAIR just for this
+	 * purpose, emit a warning and use Normal Non-cacheable instead.
+	 */
+	pr_warn_once("No MAIR allocation for EFI_MEMORY_WT; treating as Normal Non-cacheable\n");
+	return __pgprot(PROT_NORMAL_NC);
+}
+
 pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 {
 	/*
@@ -246,7 +258,7 @@
 	 * types" of UEFI 2.5 section 2.3.6.1, each EFI memory type is
 	 * mapped to a corresponding MAIR attribute encoding.
 	 * The EFI memory attribute advises all possible capabilities
-	 * of a memory region. We use the most efficient capability.
+	 * of a memory region.
 	 */
 
 	u64 attr;
@@ -254,10 +266,10 @@
 	attr = efi_mem_attributes(addr);
 	if (attr & EFI_MEMORY_WB)
 		return PAGE_KERNEL;
-	if (attr & EFI_MEMORY_WT)
-		return __pgprot(PROT_NORMAL_WT);
 	if (attr & EFI_MEMORY_WC)
 		return __pgprot(PROT_NORMAL_NC);
+	if (attr & EFI_MEMORY_WT)
+		return __acpi_get_writethrough_mem_attribute();
 	return __pgprot(PROT_DEVICE_nGnRnE);
 }
 
@@ -340,10 +352,10 @@
 		default:
 			if (region->attribute & EFI_MEMORY_WB)
 				prot = PAGE_KERNEL;
-			else if (region->attribute & EFI_MEMORY_WT)
-				prot = __pgprot(PROT_NORMAL_WT);
 			else if (region->attribute & EFI_MEMORY_WC)
 				prot = __pgprot(PROT_NORMAL_NC);
+			else if (region->attribute & EFI_MEMORY_WT)
+				prot = __acpi_get_writethrough_mem_attribute();
 		}
 	}
 	return __ioremap(phys, size, prot);
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index c906d20..3fb79b7 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -181,7 +181,7 @@
 	 */
 	if (!is_module) {
 		dsb(ish);
-		__flush_icache_all();
+		icache_inval_all_pou();
 		isb();
 
 		/* Ignore ARM64_CB bit from feature mask */
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 0cb34cc..0a73b76 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -27,6 +27,7 @@
 int main(void)
 {
   DEFINE(TSK_ACTIVE_MM,		offsetof(struct task_struct, active_mm));
+  DEFINE(TSK_CPU,		offsetof(struct task_struct, cpu));
   BLANK();
   DEFINE(TSK_TI_FLAGS,		offsetof(struct task_struct, thread_info.flags));
   DEFINE(TSK_TI_PREEMPT,	offsetof(struct task_struct, thread_info.preempt_count));
@@ -46,6 +47,8 @@
   DEFINE(THREAD_SCTLR_USER,	offsetof(struct task_struct, thread.sctlr_user));
 #ifdef CONFIG_ARM64_PTR_AUTH
   DEFINE(THREAD_KEYS_USER,	offsetof(struct task_struct, thread.keys_user));
+#endif
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
   DEFINE(THREAD_KEYS_KERNEL,	offsetof(struct task_struct, thread.keys_kernel));
 #endif
 #ifdef CONFIG_ARM64_MTE
@@ -99,7 +102,6 @@
   DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT);
   DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
   BLANK();
-  DEFINE(CPU_BOOT_STACK,	offsetof(struct secondary_data, stack));
   DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
   BLANK();
   DEFINE(FTR_OVR_VAL_OFFSET,	offsetof(struct arm64_ftr_override, val));
@@ -138,6 +140,15 @@
   DEFINE(ARM_SMCCC_RES_X2_OFFS,		offsetof(struct arm_smccc_res, a2));
   DEFINE(ARM_SMCCC_QUIRK_ID_OFFS,	offsetof(struct arm_smccc_quirk, id));
   DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS,	offsetof(struct arm_smccc_quirk, state));
+  DEFINE(ARM_SMCCC_1_2_REGS_X0_OFFS,	offsetof(struct arm_smccc_1_2_regs, a0));
+  DEFINE(ARM_SMCCC_1_2_REGS_X2_OFFS,	offsetof(struct arm_smccc_1_2_regs, a2));
+  DEFINE(ARM_SMCCC_1_2_REGS_X4_OFFS,	offsetof(struct arm_smccc_1_2_regs, a4));
+  DEFINE(ARM_SMCCC_1_2_REGS_X6_OFFS,	offsetof(struct arm_smccc_1_2_regs, a6));
+  DEFINE(ARM_SMCCC_1_2_REGS_X8_OFFS,	offsetof(struct arm_smccc_1_2_regs, a8));
+  DEFINE(ARM_SMCCC_1_2_REGS_X10_OFFS,	offsetof(struct arm_smccc_1_2_regs, a10));
+  DEFINE(ARM_SMCCC_1_2_REGS_X12_OFFS,	offsetof(struct arm_smccc_1_2_regs, a12));
+  DEFINE(ARM_SMCCC_1_2_REGS_X14_OFFS,	offsetof(struct arm_smccc_1_2_regs, a14));
+  DEFINE(ARM_SMCCC_1_2_REGS_X16_OFFS,	offsetof(struct arm_smccc_1_2_regs, a16));
   BLANK();
   DEFINE(HIBERN_PBE_ORIG,	offsetof(struct pbe, orig_address));
   DEFINE(HIBERN_PBE_ADDR,	offsetof(struct pbe, address));
@@ -153,7 +164,9 @@
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
   DEFINE(PTRAUTH_USER_KEY_APIA,		offsetof(struct ptrauth_keys_user, apia));
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
   DEFINE(PTRAUTH_KERNEL_KEY_APIA,	offsetof(struct ptrauth_keys_kernel, apia));
+#endif
   BLANK();
 #endif
   return 0;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index efed283..125d5c9 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -76,6 +76,7 @@
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/fpsimd.h>
+#include <asm/insn.h>
 #include <asm/kvm_host.h>
 #include <asm/mmu_context.h>
 #include <asm/mte.h>
@@ -108,6 +109,24 @@
 EXPORT_SYMBOL(arm64_use_ng_mappings);
 
 /*
+ * Permit PER_LINUX32 and execve() of 32-bit binaries even if not all CPUs
+ * support it?
+ */
+static bool __read_mostly allow_mismatched_32bit_el0;
+
+/*
+ * Static branch enabled only if allow_mismatched_32bit_el0 is set and we have
+ * seen at least one CPU capable of 32-bit EL0.
+ */
+DEFINE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
+
+/*
+ * Mask of CPUs supporting 32-bit EL0.
+ * Only valid if arm64_mismatched_32bit_el0 is enabled.
+ */
+static cpumask_var_t cpu_32bit_el0_mask __cpumask_var_read_mostly;
+
+/*
  * Flag to indicate if we have computed the system wide
  * capabilities based on the boot time active CPUs. This
  * will be used to determine if a new booting CPU should
@@ -400,6 +419,11 @@
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_gmid[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, SYS_GMID_EL1_BS_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_isar0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_DIVIDE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_DEBUG_SHIFT, 4, 0),
@@ -617,6 +641,9 @@
 	/* Op1 = 0, CRn = 1, CRm = 2 */
 	ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
 
+	/* Op1 = 1, CRn = 0, CRm = 0 */
+	ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid),
+
 	/* Op1 = 3, CRn = 0, CRm = 0 */
 	{ SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
 	ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
@@ -767,7 +794,7 @@
  * Any bits that are not covered by an arm64_ftr_bits entry are considered
  * RES0 for the system-wide value, and must strictly match.
  */
-static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
+static void init_cpu_ftr_reg(u32 sys_reg, u64 new)
 {
 	u64 val = 0;
 	u64 strict_mask = ~0x0ULL;
@@ -863,6 +890,31 @@
 
 static void __init setup_boot_cpu_capabilities(void);
 
+static void init_32bit_cpu_features(struct cpuinfo_32bit *info)
+{
+	init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
+	init_cpu_ftr_reg(SYS_ID_DFR1_EL1, info->reg_id_dfr1);
+	init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0);
+	init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1);
+	init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2);
+	init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3);
+	init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4);
+	init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5);
+	init_cpu_ftr_reg(SYS_ID_ISAR6_EL1, info->reg_id_isar6);
+	init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0);
+	init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1);
+	init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2);
+	init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3);
+	init_cpu_ftr_reg(SYS_ID_MMFR4_EL1, info->reg_id_mmfr4);
+	init_cpu_ftr_reg(SYS_ID_MMFR5_EL1, info->reg_id_mmfr5);
+	init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0);
+	init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1);
+	init_cpu_ftr_reg(SYS_ID_PFR2_EL1, info->reg_id_pfr2);
+	init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0);
+	init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1);
+	init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
+}
+
 void __init init_cpu_features(struct cpuinfo_arm64 *info)
 {
 	/* Before we start using the tables, make sure it is sorted */
@@ -882,35 +934,17 @@
 	init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
 	init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
 
-	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
-		init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
-		init_cpu_ftr_reg(SYS_ID_DFR1_EL1, info->reg_id_dfr1);
-		init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0);
-		init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1);
-		init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2);
-		init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3);
-		init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4);
-		init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5);
-		init_cpu_ftr_reg(SYS_ID_ISAR6_EL1, info->reg_id_isar6);
-		init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0);
-		init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1);
-		init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2);
-		init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3);
-		init_cpu_ftr_reg(SYS_ID_MMFR4_EL1, info->reg_id_mmfr4);
-		init_cpu_ftr_reg(SYS_ID_MMFR5_EL1, info->reg_id_mmfr5);
-		init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0);
-		init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1);
-		init_cpu_ftr_reg(SYS_ID_PFR2_EL1, info->reg_id_pfr2);
-		init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0);
-		init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1);
-		init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
-	}
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
+		init_32bit_cpu_features(&info->aarch32);
 
 	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
 		init_cpu_ftr_reg(SYS_ZCR_EL1, info->reg_zcr);
 		sve_init_vq_map();
 	}
 
+	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
+		init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid);
+
 	/*
 	 * Initialize the indirect array of CPU hwcaps capabilities pointers
 	 * before we handle the boot CPU below.
@@ -975,21 +1009,29 @@
 	WARN_ON(!ftrp->width);
 }
 
-static int update_32bit_cpu_features(int cpu, struct cpuinfo_arm64 *info,
-				     struct cpuinfo_arm64 *boot)
+static void lazy_init_32bit_cpu_features(struct cpuinfo_arm64 *info,
+					 struct cpuinfo_arm64 *boot)
+{
+	static bool boot_cpu_32bit_regs_overridden = false;
+
+	if (!allow_mismatched_32bit_el0 || boot_cpu_32bit_regs_overridden)
+		return;
+
+	if (id_aa64pfr0_32bit_el0(boot->reg_id_aa64pfr0))
+		return;
+
+	boot->aarch32 = info->aarch32;
+	init_32bit_cpu_features(&boot->aarch32);
+	boot_cpu_32bit_regs_overridden = true;
+}
+
+static int update_32bit_cpu_features(int cpu, struct cpuinfo_32bit *info,
+				     struct cpuinfo_32bit *boot)
 {
 	int taint = 0;
 	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
 
 	/*
-	 * If we don't have AArch32 at all then skip the checks entirely
-	 * as the register values may be UNKNOWN and we're not going to be
-	 * using them for anything.
-	 */
-	if (!id_aa64pfr0_32bit_el0(pfr0))
-		return taint;
-
-	/*
 	 * If we don't have AArch32 at EL1, then relax the strictness of
 	 * EL1-dependent register fields to avoid spurious sanity check fails.
 	 */
@@ -1135,10 +1177,29 @@
 	}
 
 	/*
+	 * The kernel uses the LDGM/STGM instructions and the number of tags
+	 * they read/write depends on the GMID_EL1.BS field. Check that the
+	 * value is the same on all CPUs.
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_MTE) &&
+	    id_aa64pfr1_mte(info->reg_id_aa64pfr1)) {
+		taint |= check_update_ftr_reg(SYS_GMID_EL1, cpu,
+					      info->reg_gmid, boot->reg_gmid);
+	}
+
+	/*
+	 * If we don't have AArch32 at all then skip the checks entirely
+	 * as the register values may be UNKNOWN and we're not going to be
+	 * using them for anything.
+	 *
 	 * This relies on a sanitised view of the AArch64 ID registers
 	 * (e.g. SYS_ID_AA64PFR0_EL1), so we call it last.
 	 */
-	taint |= update_32bit_cpu_features(cpu, info, boot);
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
+		lazy_init_32bit_cpu_features(info, boot);
+		taint |= update_32bit_cpu_features(cpu, &info->aarch32,
+						   &boot->aarch32);
+	}
 
 	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
@@ -1248,6 +1309,28 @@
 	return feature_matches(val, entry);
 }
 
+const struct cpumask *system_32bit_el0_cpumask(void)
+{
+	if (!system_supports_32bit_el0())
+		return cpu_none_mask;
+
+	if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+		return cpu_32bit_el0_mask;
+
+	return cpu_possible_mask;
+}
+
+static bool has_32bit_el0(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	if (!has_cpuid_feature(entry, scope))
+		return allow_mismatched_32bit_el0;
+
+	if (scope == SCOPE_SYSTEM)
+		pr_info("detected: 32-bit EL0 Support\n");
+
+	return true;
+}
+
 static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry, int scope)
 {
 	bool has_sre;
@@ -1866,10 +1949,9 @@
 		.cpu_enable = cpu_copy_el2regs,
 	},
 	{
-		.desc = "32-bit EL0 Support",
-		.capability = ARM64_HAS_32BIT_EL0,
+		.capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
-		.matches = has_cpuid_feature,
+		.matches = has_32bit_el0,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.sign = FTR_UNSIGNED,
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
@@ -2378,7 +2460,7 @@
 	{},
 };
 
-static void __init cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap)
+static void cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
@@ -2423,7 +2505,7 @@
 	return rc;
 }
 
-static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
+static void setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
 {
 	/* We support emulation of accesses to CPU ID feature registers */
 	cpu_set_named_feature(CPUID);
@@ -2598,7 +2680,7 @@
 }
 
 static void
-verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps)
+__verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps)
 {
 
 	for (; caps->matches; caps++)
@@ -2609,6 +2691,14 @@
 		}
 }
 
+static void verify_local_elf_hwcaps(void)
+{
+	__verify_local_elf_hwcaps(arm64_elf_hwcaps);
+
+	if (id_aa64pfr0_32bit_el0(read_cpuid(ID_AA64PFR0_EL1)))
+		__verify_local_elf_hwcaps(compat_elf_hwcaps);
+}
+
 static void verify_sve_features(void)
 {
 	u64 safe_zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
@@ -2673,11 +2763,7 @@
 	 * on all secondary CPUs.
 	 */
 	verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU);
-
-	verify_local_elf_hwcaps(arm64_elf_hwcaps);
-
-	if (system_supports_32bit_el0())
-		verify_local_elf_hwcaps(compat_elf_hwcaps);
+	verify_local_elf_hwcaps();
 
 	if (system_supports_sve())
 		verify_sve_features();
@@ -2812,6 +2898,34 @@
 			ARCH_DMA_MINALIGN);
 }
 
+static int enable_mismatched_32bit_el0(unsigned int cpu)
+{
+	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
+	bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0);
+
+	if (cpu_32bit) {
+		cpumask_set_cpu(cpu, cpu_32bit_el0_mask);
+		static_branch_enable_cpuslocked(&arm64_mismatched_32bit_el0);
+		setup_elf_hwcaps(compat_elf_hwcaps);
+	}
+
+	return 0;
+}
+
+static int __init init_32bit_el0_mask(void)
+{
+	if (!allow_mismatched_32bit_el0)
+		return 0;
+
+	if (!zalloc_cpumask_var(&cpu_32bit_el0_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				 "arm64/mismatched_32bit_el0:online",
+				 enable_mismatched_32bit_el0, NULL);
+}
+subsys_initcall_sync(init_32bit_el0_mask);
+
 static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap)
 {
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
@@ -2905,8 +3019,8 @@
 }
 
 static struct undef_hook mrs_hook = {
-	.instr_mask = 0xfff00000,
-	.instr_val  = 0xd5300000,
+	.instr_mask = 0xffff0000,
+	.instr_val  = 0xd5380000,
 	.pstate_mask = PSR_AA32_MODE_MASK,
 	.pstate_val = PSR_MODE_EL0t,
 	.fn = emulate_mrs,
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 51fcf99..87731fe 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -246,7 +246,7 @@
 		struct cpuinfo_arm64 *info = kobj_to_cpuinfo(kobj);		\
 										\
 		if (info->reg_midr)						\
-			return sprintf(buf, "0x%016x\n", info->reg_##_field);	\
+			return sprintf(buf, "0x%016llx\n", info->reg_##_field);	\
 		else								\
 			return 0;						\
 	}									\
@@ -344,6 +344,32 @@
 	pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu);
 }
 
+static void __cpuinfo_store_cpu_32bit(struct cpuinfo_32bit *info)
+{
+	info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
+	info->reg_id_dfr1 = read_cpuid(ID_DFR1_EL1);
+	info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
+	info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
+	info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
+	info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1);
+	info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1);
+	info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1);
+	info->reg_id_isar6 = read_cpuid(ID_ISAR6_EL1);
+	info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1);
+	info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
+	info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);
+	info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1);
+	info->reg_id_mmfr4 = read_cpuid(ID_MMFR4_EL1);
+	info->reg_id_mmfr5 = read_cpuid(ID_MMFR5_EL1);
+	info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
+	info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
+	info->reg_id_pfr2 = read_cpuid(ID_PFR2_EL1);
+
+	info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
+	info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
+	info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
+}
+
 static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 {
 	info->reg_cntfrq = arch_timer_get_cntfrq();
@@ -371,31 +397,11 @@
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
 	info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1);
 
-	/* Update the 32bit ID registers only if AArch32 is implemented */
-	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
-		info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
-		info->reg_id_dfr1 = read_cpuid(ID_DFR1_EL1);
-		info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
-		info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
-		info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
-		info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1);
-		info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1);
-		info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1);
-		info->reg_id_isar6 = read_cpuid(ID_ISAR6_EL1);
-		info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1);
-		info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
-		info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);
-		info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1);
-		info->reg_id_mmfr4 = read_cpuid(ID_MMFR4_EL1);
-		info->reg_id_mmfr5 = read_cpuid(ID_MMFR5_EL1);
-		info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
-		info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
-		info->reg_id_pfr2 = read_cpuid(ID_PFR2_EL1);
+	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
+		info->reg_gmid = read_cpuid(GMID_EL1);
 
-		info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
-		info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
-		info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
-	}
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
+		__cpuinfo_store_cpu_32bit(&info->aarch32);
 
 	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
 	    id_aa64pfr0_sve(info->reg_id_aa64pfr0))
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 0073b24..61a87fa 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -28,7 +28,8 @@
 	 * stale icache entries from before relocation.
 	 */
 	ldr	w1, =kernel_size
-	bl	__clean_dcache_area_poc
+	add	x1, x0, x1
+	bl	dcache_clean_poc
 	ic	ialluis
 
 	/*
@@ -36,8 +37,8 @@
 	 * so that we can safely disable the MMU and caches.
 	 */
 	adr	x0, 0f
-	ldr	w1, 3f
-	bl	__clean_dcache_area_poc
+	adr	x1, 3f
+	bl	dcache_clean_poc
 0:
 	/* Turn off Dcache and MMU */
 	mrs	x0, CurrentEL
@@ -64,5 +65,5 @@
 	mov	x2, xzr
 	mov	x3, xzr
 	br	x19
+3:
 SYM_CODE_END(efi_enter_kernel)
-3:	.long	. - 0b
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 340d04e..12ce14a 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -6,7 +6,11 @@
  */
 
 #include <linux/context_tracking.h>
+#include <linux/linkage.h>
+#include <linux/lockdep.h>
 #include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/thread_info.h>
 
 #include <asm/cpufeature.h>
@@ -15,7 +19,11 @@
 #include <asm/exception.h>
 #include <asm/kprobes.h>
 #include <asm/mmu.h>
+#include <asm/processor.h>
+#include <asm/sdei.h>
+#include <asm/stacktrace.h>
 #include <asm/sysreg.h>
+#include <asm/system_misc.h>
 
 /*
  * This is intended to match the logic in irqentry_enter(), handling the kernel
@@ -67,7 +75,7 @@
 	}
 }
 
-void noinstr arm64_enter_nmi(struct pt_regs *regs)
+static void noinstr arm64_enter_nmi(struct pt_regs *regs)
 {
 	regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
 
@@ -80,7 +88,7 @@
 	ftrace_nmi_enter();
 }
 
-void noinstr arm64_exit_nmi(struct pt_regs *regs)
+static void noinstr arm64_exit_nmi(struct pt_regs *regs)
 {
 	bool restore = regs->lockdep_hardirqs;
 
@@ -97,7 +105,7 @@
 	__nmi_exit();
 }
 
-asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs)
+static void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
 		arm64_enter_nmi(regs);
@@ -105,7 +113,7 @@
 		enter_from_kernel_mode(regs);
 }
 
-asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
+static void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
 		arm64_exit_nmi(regs);
@@ -113,6 +121,65 @@
 		exit_to_kernel_mode(regs);
 }
 
+static void __sched arm64_preempt_schedule_irq(void)
+{
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * DAIF.DA are cleared at the start of IRQ/FIQ handling, and when GIC
+	 * priority masking is used the GIC irqchip driver will clear DAIF.IF
+	 * using gic_arch_enable_irqs() for normal IRQs. If anything is set in
+	 * DAIF we must have handled an NMI, so skip preemption.
+	 */
+	if (system_uses_irq_prio_masking() && read_sysreg(daif))
+		return;
+
+	/*
+	 * Preempting a task from an IRQ means we leave copies of PSTATE
+	 * on the stack. cpufeature's enable calls may modify PSTATE, but
+	 * resuming one of these preempted tasks would undo those changes.
+	 *
+	 * Only allow a task to be preempted once cpufeatures have been
+	 * enabled.
+	 */
+	if (system_capabilities_finalized())
+		preempt_schedule_irq();
+}
+
+static void do_interrupt_handler(struct pt_regs *regs,
+				 void (*handler)(struct pt_regs *))
+{
+	if (on_thread_stack())
+		call_on_irq_stack(regs, handler);
+	else
+		handler(regs);
+}
+
+extern void (*handle_arch_irq)(struct pt_regs *);
+extern void (*handle_arch_fiq)(struct pt_regs *);
+
+static void noinstr __panic_unhandled(struct pt_regs *regs, const char *vector,
+				      unsigned int esr)
+{
+	arm64_enter_nmi(regs);
+
+	console_verbose();
+
+	pr_crit("Unhandled %s exception on CPU%d, ESR 0x%08x -- %s\n",
+		vector, smp_processor_id(), esr,
+		esr_get_class_string(esr));
+
+	__show_regs(regs);
+	panic("Unhandled exception");
+}
+
+#define UNHANDLED(el, regsize, vector)							\
+asmlinkage void noinstr el##_##regsize##_##vector##_handler(struct pt_regs *regs)	\
+{											\
+	const char *desc = #regsize "-bit " #el " " #vector;				\
+	__panic_unhandled(regs, desc, read_sysreg(esr_el1));				\
+}
+
 #ifdef CONFIG_ARM64_ERRATUM_1463225
 static DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
 
@@ -162,6 +229,11 @@
 }
 #endif /* CONFIG_ARM64_ERRATUM_1463225 */
 
+UNHANDLED(el1t, 64, sync)
+UNHANDLED(el1t, 64, irq)
+UNHANDLED(el1t, 64, fiq)
+UNHANDLED(el1t, 64, error)
+
 static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr)
 {
 	unsigned long far = read_sysreg(far_el1);
@@ -193,15 +265,6 @@
 	exit_to_kernel_mode(regs);
 }
 
-static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr)
-{
-	enter_from_kernel_mode(regs);
-	local_daif_inherit(regs);
-	bad_mode(regs, 0, esr);
-	local_daif_mask();
-	exit_to_kernel_mode(regs);
-}
-
 static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
 {
 	regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
@@ -245,7 +308,7 @@
 	exit_to_kernel_mode(regs);
 }
 
-asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs)
+asmlinkage void noinstr el1h_64_sync_handler(struct pt_regs *regs)
 {
 	unsigned long esr = read_sysreg(esr_el1);
 
@@ -275,10 +338,50 @@
 		el1_fpac(regs, esr);
 		break;
 	default:
-		el1_inv(regs, esr);
+		__panic_unhandled(regs, "64-bit el1h sync", esr);
 	}
 }
 
+static void noinstr el1_interrupt(struct pt_regs *regs,
+				  void (*handler)(struct pt_regs *))
+{
+	write_sysreg(DAIF_PROCCTX_NOIRQ, daif);
+
+	enter_el1_irq_or_nmi(regs);
+	do_interrupt_handler(regs, handler);
+
+	/*
+	 * Note: thread_info::preempt_count includes both thread_info::count
+	 * and thread_info::need_resched, and is not equivalent to
+	 * preempt_count().
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPTION) &&
+	    READ_ONCE(current_thread_info()->preempt_count) == 0)
+		arm64_preempt_schedule_irq();
+
+	exit_el1_irq_or_nmi(regs);
+}
+
+asmlinkage void noinstr el1h_64_irq_handler(struct pt_regs *regs)
+{
+	el1_interrupt(regs, handle_arch_irq);
+}
+
+asmlinkage void noinstr el1h_64_fiq_handler(struct pt_regs *regs)
+{
+	el1_interrupt(regs, handle_arch_fiq);
+}
+
+asmlinkage void noinstr el1h_64_error_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	local_daif_restore(DAIF_ERRCTX);
+	arm64_enter_nmi(regs);
+	do_serror(regs, esr);
+	arm64_exit_nmi(regs);
+}
+
 asmlinkage void noinstr enter_from_user_mode(void)
 {
 	lockdep_hardirqs_off(CALLER_ADDR0);
@@ -398,7 +501,7 @@
 
 	enter_from_user_mode();
 	do_debug_exception(far, esr, regs);
-	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+	local_daif_restore(DAIF_PROCCTX);
 }
 
 static void noinstr el0_svc(struct pt_regs *regs)
@@ -415,7 +518,7 @@
 	do_ptrauth_fault(regs, esr);
 }
 
-asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs)
+asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs)
 {
 	unsigned long esr = read_sysreg(esr_el1);
 
@@ -468,6 +571,56 @@
 	}
 }
 
+static void noinstr el0_interrupt(struct pt_regs *regs,
+				  void (*handler)(struct pt_regs *))
+{
+	enter_from_user_mode();
+
+	write_sysreg(DAIF_PROCCTX_NOIRQ, daif);
+
+	if (regs->pc & BIT(55))
+		arm64_apply_bp_hardening();
+
+	do_interrupt_handler(regs, handler);
+}
+
+static void noinstr __el0_irq_handler_common(struct pt_regs *regs)
+{
+	el0_interrupt(regs, handle_arch_irq);
+}
+
+asmlinkage void noinstr el0t_64_irq_handler(struct pt_regs *regs)
+{
+	__el0_irq_handler_common(regs);
+}
+
+static void noinstr __el0_fiq_handler_common(struct pt_regs *regs)
+{
+	el0_interrupt(regs, handle_arch_fiq);
+}
+
+asmlinkage void noinstr el0t_64_fiq_handler(struct pt_regs *regs)
+{
+	__el0_fiq_handler_common(regs);
+}
+
+static void __el0_error_handler_common(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	enter_from_user_mode();
+	local_daif_restore(DAIF_ERRCTX);
+	arm64_enter_nmi(regs);
+	do_serror(regs, esr);
+	arm64_exit_nmi(regs);
+	local_daif_restore(DAIF_PROCCTX);
+}
+
+asmlinkage void noinstr el0t_64_error_handler(struct pt_regs *regs)
+{
+	__el0_error_handler_common(regs);
+}
+
 #ifdef CONFIG_COMPAT
 static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr)
 {
@@ -483,7 +636,7 @@
 	do_el0_svc_compat(regs);
 }
 
-asmlinkage void noinstr el0_sync_compat_handler(struct pt_regs *regs)
+asmlinkage void noinstr el0t_32_sync_handler(struct pt_regs *regs)
 {
 	unsigned long esr = read_sysreg(esr_el1);
 
@@ -526,4 +679,71 @@
 		el0_inv(regs, esr);
 	}
 }
+
+asmlinkage void noinstr el0t_32_irq_handler(struct pt_regs *regs)
+{
+	__el0_irq_handler_common(regs);
+}
+
+asmlinkage void noinstr el0t_32_fiq_handler(struct pt_regs *regs)
+{
+	__el0_fiq_handler_common(regs);
+}
+
+asmlinkage void noinstr el0t_32_error_handler(struct pt_regs *regs)
+{
+	__el0_error_handler_common(regs);
+}
+#else /* CONFIG_COMPAT */
+UNHANDLED(el0t, 32, sync)
+UNHANDLED(el0t, 32, irq)
+UNHANDLED(el0t, 32, fiq)
+UNHANDLED(el0t, 32, error)
 #endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_VMAP_STACK
+asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs)
+{
+	unsigned int esr = read_sysreg(esr_el1);
+	unsigned long far = read_sysreg(far_el1);
+
+	arm64_enter_nmi(regs);
+	panic_bad_stack(regs, esr, far);
+}
+#endif /* CONFIG_VMAP_STACK */
+
+#ifdef CONFIG_ARM_SDE_INTERFACE
+asmlinkage noinstr unsigned long
+__sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
+{
+	unsigned long ret;
+
+	/*
+	 * We didn't take an exception to get here, so the HW hasn't
+	 * set/cleared bits in PSTATE that we may rely on.
+	 *
+	 * The original SDEI spec (ARM DEN 0054A) can be read ambiguously as to
+	 * whether PSTATE bits are inherited unchanged or generated from
+	 * scratch, and the TF-A implementation always clears PAN and always
+	 * clears UAO. There are no other known implementations.
+	 *
+	 * Subsequent revisions (ARM DEN 0054B) follow the usual rules for how
+	 * PSTATE is modified upon architectural exceptions, and so PAN is
+	 * either inherited or set per SCTLR_ELx.SPAN, and UAO is always
+	 * cleared.
+	 *
+	 * We must explicitly reset PAN to the expected state, including
+	 * clearing it when the host isn't using it, in case a VM had it set.
+	 */
+	if (system_uses_hw_pan())
+		set_pstate_pan(1);
+	else if (cpu_has_pan())
+		set_pstate_pan(0);
+
+	arm64_enter_nmi(regs);
+	ret = do_sdei_event(regs, arg);
+	arm64_exit_nmi(regs);
+
+	return ret;
+}
+#endif /* CONFIG_ARM_SDE_INTERFACE */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 3513984..863d44f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -33,12 +33,6 @@
  * Context tracking and irqflag tracing need to instrument transitions between
  * user and kernel mode.
  */
-	.macro user_exit_irqoff
-#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS)
-	bl	enter_from_user_mode
-#endif
-	.endm
-
 	.macro user_enter_irqoff
 #if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS)
 	bl	exit_to_user_mode
@@ -51,16 +45,7 @@
 	.endr
 	.endm
 
-/*
- * Bad Abort numbers
- *-----------------
- */
-#define BAD_SYNC	0
-#define BAD_IRQ		1
-#define BAD_FIQ		2
-#define BAD_ERROR	3
-
-	.macro kernel_ventry, el, label, regsize = 64
+	.macro kernel_ventry, el:req, ht:req, regsize:req, label:req
 	.align 7
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	.if	\el == 0
@@ -87,7 +72,7 @@
 	tbnz	x0, #THREAD_SHIFT, 0f
 	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
 	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
-	b	el\()\el\()_\label
+	b	el\el\ht\()_\regsize\()_\label
 
 0:
 	/*
@@ -119,7 +104,7 @@
 	sub	sp, sp, x0
 	mrs	x0, tpidrro_el0
 #endif
-	b	el\()\el\()_\label
+	b	el\el\ht\()_\regsize\()_\label
 	.endm
 
 	.macro tramp_alias, dst, sym
@@ -275,7 +260,7 @@
 
 	mte_set_kernel_gcr x22, x23
 
-	scs_load tsk, x20
+	scs_load tsk
 	.else
 	add	x21, sp, #PT_REGS_SIZE
 	get_current_task tsk
@@ -285,7 +270,7 @@
 	stp	lr, x21, [sp, #S_LR]
 
 	/*
-	 * For exceptions from EL0, create a terminal frame record.
+	 * For exceptions from EL0, create a final frame record.
 	 * For exceptions from EL1, create a synthetic frame record so the
 	 * interrupted code shows up in the backtrace.
 	 */
@@ -375,7 +360,7 @@
 alternative_else_nop_endif
 #endif
 3:
-	scs_save tsk, x0
+	scs_save tsk
 
 #ifdef CONFIG_ARM64_PTR_AUTH
 alternative_if ARM64_HAS_ADDRESS_AUTH
@@ -486,63 +471,12 @@
 SYM_CODE_END(__swpan_exit_el0)
 #endif
 
-	.macro	irq_stack_entry
-	mov	x19, sp			// preserve the original sp
-#ifdef CONFIG_SHADOW_CALL_STACK
-	mov	x24, scs_sp		// preserve the original shadow stack
-#endif
-
-	/*
-	 * Compare sp with the base of the task stack.
-	 * If the top ~(THREAD_SIZE - 1) bits match, we are on a task stack,
-	 * and should switch to the irq stack.
-	 */
-	ldr	x25, [tsk, TSK_STACK]
-	eor	x25, x25, x19
-	and	x25, x25, #~(THREAD_SIZE - 1)
-	cbnz	x25, 9998f
-
-	ldr_this_cpu x25, irq_stack_ptr, x26
-	mov	x26, #IRQ_STACK_SIZE
-	add	x26, x25, x26
-
-	/* switch to the irq stack */
-	mov	sp, x26
-
-#ifdef CONFIG_SHADOW_CALL_STACK
-	/* also switch to the irq shadow stack */
-	ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x26
-#endif
-
-9998:
-	.endm
-
-	/*
-	 * The callee-saved regs (x19-x29) should be preserved between
-	 * irq_stack_entry and irq_stack_exit, but note that kernel_entry
-	 * uses x20-x23 to store data for later use.
-	 */
-	.macro	irq_stack_exit
-	mov	sp, x19
-#ifdef CONFIG_SHADOW_CALL_STACK
-	mov	scs_sp, x24
-#endif
-	.endm
-
 /* GPRs used by entry code */
 tsk	.req	x28		// current thread_info
 
 /*
  * Interrupt handling.
  */
-	.macro	irq_handler, handler:req
-	ldr_l	x1, \handler
-	mov	x0, sp
-	irq_stack_entry
-	blr	x1
-	irq_stack_exit
-	.endm
-
 	.macro	gic_prio_kentry_setup, tmp:req
 #ifdef CONFIG_ARM64_PSEUDO_NMI
 	alternative_if ARM64_HAS_IRQ_PRIO_MASKING
@@ -552,45 +486,6 @@
 #endif
 	.endm
 
-	.macro el1_interrupt_handler, handler:req
-	enable_da
-
-	mov	x0, sp
-	bl	enter_el1_irq_or_nmi
-
-	irq_handler	\handler
-
-#ifdef CONFIG_PREEMPTION
-	ldr	x24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
-alternative_if ARM64_HAS_IRQ_PRIO_MASKING
-	/*
-	 * DA were cleared at start of handling, and IF are cleared by
-	 * the GIC irqchip driver using gic_arch_enable_irqs() for
-	 * normal IRQs. If anything is set, it means we come back from
-	 * an NMI instead of a normal IRQ, so skip preemption
-	 */
-	mrs	x0, daif
-	orr	x24, x24, x0
-alternative_else_nop_endif
-	cbnz	x24, 1f				// preempt count != 0 || NMI return path
-	bl	arm64_preempt_schedule_irq	// irq en/disable is done inside
-1:
-#endif
-
-	mov	x0, sp
-	bl	exit_el1_irq_or_nmi
-	.endm
-
-	.macro el0_interrupt_handler, handler:req
-	user_exit_irqoff
-	enable_da
-
-	tbz	x22, #55, 1f
-	bl	do_el0_irq_bp_hardening
-1:
-	irq_handler	\handler
-	.endm
-
 	.text
 
 /*
@@ -600,32 +495,25 @@
 
 	.align	11
 SYM_CODE_START(vectors)
-	kernel_ventry	1, sync_invalid			// Synchronous EL1t
-	kernel_ventry	1, irq_invalid			// IRQ EL1t
-	kernel_ventry	1, fiq_invalid			// FIQ EL1t
-	kernel_ventry	1, error_invalid		// Error EL1t
+	kernel_ventry	1, t, 64, sync		// Synchronous EL1t
+	kernel_ventry	1, t, 64, irq		// IRQ EL1t
+	kernel_ventry	1, t, 64, fiq		// FIQ EL1h
+	kernel_ventry	1, t, 64, error		// Error EL1t
 
-	kernel_ventry	1, sync				// Synchronous EL1h
-	kernel_ventry	1, irq				// IRQ EL1h
-	kernel_ventry	1, fiq				// FIQ EL1h
-	kernel_ventry	1, error			// Error EL1h
+	kernel_ventry	1, h, 64, sync		// Synchronous EL1h
+	kernel_ventry	1, h, 64, irq		// IRQ EL1h
+	kernel_ventry	1, h, 64, fiq		// FIQ EL1h
+	kernel_ventry	1, h, 64, error		// Error EL1h
 
-	kernel_ventry	0, sync				// Synchronous 64-bit EL0
-	kernel_ventry	0, irq				// IRQ 64-bit EL0
-	kernel_ventry	0, fiq				// FIQ 64-bit EL0
-	kernel_ventry	0, error			// Error 64-bit EL0
+	kernel_ventry	0, t, 64, sync		// Synchronous 64-bit EL0
+	kernel_ventry	0, t, 64, irq		// IRQ 64-bit EL0
+	kernel_ventry	0, t, 64, fiq		// FIQ 64-bit EL0
+	kernel_ventry	0, t, 64, error		// Error 64-bit EL0
 
-#ifdef CONFIG_COMPAT
-	kernel_ventry	0, sync_compat, 32		// Synchronous 32-bit EL0
-	kernel_ventry	0, irq_compat, 32		// IRQ 32-bit EL0
-	kernel_ventry	0, fiq_compat, 32		// FIQ 32-bit EL0
-	kernel_ventry	0, error_compat, 32		// Error 32-bit EL0
-#else
-	kernel_ventry	0, sync_invalid, 32		// Synchronous 32-bit EL0
-	kernel_ventry	0, irq_invalid, 32		// IRQ 32-bit EL0
-	kernel_ventry	0, fiq_invalid, 32		// FIQ 32-bit EL0
-	kernel_ventry	0, error_invalid, 32		// Error 32-bit EL0
-#endif
+	kernel_ventry	0, t, 32, sync		// Synchronous 32-bit EL0
+	kernel_ventry	0, t, 32, irq		// IRQ 32-bit EL0
+	kernel_ventry	0, t, 32, fiq		// FIQ 32-bit EL0
+	kernel_ventry	0, t, 32, error		// Error 32-bit EL0
 SYM_CODE_END(vectors)
 
 #ifdef CONFIG_VMAP_STACK
@@ -656,147 +544,46 @@
 	ASM_BUG()
 #endif /* CONFIG_VMAP_STACK */
 
-/*
- * Invalid mode handlers
- */
-	.macro	inv_entry, el, reason, regsize = 64
+
+	.macro entry_handler el:req, ht:req, regsize:req, label:req
+SYM_CODE_START_LOCAL(el\el\ht\()_\regsize\()_\label)
 	kernel_entry \el, \regsize
 	mov	x0, sp
-	mov	x1, #\reason
-	mrs	x2, esr_el1
-	bl	bad_mode
-	ASM_BUG()
+	bl	el\el\ht\()_\regsize\()_\label\()_handler
+	.if \el == 0
+	b	ret_to_user
+	.else
+	b	ret_to_kernel
+	.endif
+SYM_CODE_END(el\el\ht\()_\regsize\()_\label)
 	.endm
 
-SYM_CODE_START_LOCAL(el0_sync_invalid)
-	inv_entry 0, BAD_SYNC
-SYM_CODE_END(el0_sync_invalid)
-
-SYM_CODE_START_LOCAL(el0_irq_invalid)
-	inv_entry 0, BAD_IRQ
-SYM_CODE_END(el0_irq_invalid)
-
-SYM_CODE_START_LOCAL(el0_fiq_invalid)
-	inv_entry 0, BAD_FIQ
-SYM_CODE_END(el0_fiq_invalid)
-
-SYM_CODE_START_LOCAL(el0_error_invalid)
-	inv_entry 0, BAD_ERROR
-SYM_CODE_END(el0_error_invalid)
-
-SYM_CODE_START_LOCAL(el1_sync_invalid)
-	inv_entry 1, BAD_SYNC
-SYM_CODE_END(el1_sync_invalid)
-
-SYM_CODE_START_LOCAL(el1_irq_invalid)
-	inv_entry 1, BAD_IRQ
-SYM_CODE_END(el1_irq_invalid)
-
-SYM_CODE_START_LOCAL(el1_fiq_invalid)
-	inv_entry 1, BAD_FIQ
-SYM_CODE_END(el1_fiq_invalid)
-
-SYM_CODE_START_LOCAL(el1_error_invalid)
-	inv_entry 1, BAD_ERROR
-SYM_CODE_END(el1_error_invalid)
-
 /*
- * EL1 mode handlers.
+ * Early exception handlers
  */
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el1_sync)
-	kernel_entry 1
-	mov	x0, sp
-	bl	el1_sync_handler
+	entry_handler	1, t, 64, sync
+	entry_handler	1, t, 64, irq
+	entry_handler	1, t, 64, fiq
+	entry_handler	1, t, 64, error
+
+	entry_handler	1, h, 64, sync
+	entry_handler	1, h, 64, irq
+	entry_handler	1, h, 64, fiq
+	entry_handler	1, h, 64, error
+
+	entry_handler	0, t, 64, sync
+	entry_handler	0, t, 64, irq
+	entry_handler	0, t, 64, fiq
+	entry_handler	0, t, 64, error
+
+	entry_handler	0, t, 32, sync
+	entry_handler	0, t, 32, irq
+	entry_handler	0, t, 32, fiq
+	entry_handler	0, t, 32, error
+
+SYM_CODE_START_LOCAL(ret_to_kernel)
 	kernel_exit 1
-SYM_CODE_END(el1_sync)
-
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el1_irq)
-	kernel_entry 1
-	el1_interrupt_handler handle_arch_irq
-	kernel_exit 1
-SYM_CODE_END(el1_irq)
-
-SYM_CODE_START_LOCAL_NOALIGN(el1_fiq)
-	kernel_entry 1
-	el1_interrupt_handler handle_arch_fiq
-	kernel_exit 1
-SYM_CODE_END(el1_fiq)
-
-/*
- * EL0 mode handlers.
- */
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el0_sync)
-	kernel_entry 0
-	mov	x0, sp
-	bl	el0_sync_handler
-	b	ret_to_user
-SYM_CODE_END(el0_sync)
-
-#ifdef CONFIG_COMPAT
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el0_sync_compat)
-	kernel_entry 0, 32
-	mov	x0, sp
-	bl	el0_sync_compat_handler
-	b	ret_to_user
-SYM_CODE_END(el0_sync_compat)
-
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el0_irq_compat)
-	kernel_entry 0, 32
-	b	el0_irq_naked
-SYM_CODE_END(el0_irq_compat)
-
-SYM_CODE_START_LOCAL_NOALIGN(el0_fiq_compat)
-	kernel_entry 0, 32
-	b	el0_fiq_naked
-SYM_CODE_END(el0_fiq_compat)
-
-SYM_CODE_START_LOCAL_NOALIGN(el0_error_compat)
-	kernel_entry 0, 32
-	b	el0_error_naked
-SYM_CODE_END(el0_error_compat)
-#endif
-
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el0_irq)
-	kernel_entry 0
-el0_irq_naked:
-	el0_interrupt_handler handle_arch_irq
-	b	ret_to_user
-SYM_CODE_END(el0_irq)
-
-SYM_CODE_START_LOCAL_NOALIGN(el0_fiq)
-	kernel_entry 0
-el0_fiq_naked:
-	el0_interrupt_handler handle_arch_fiq
-	b	ret_to_user
-SYM_CODE_END(el0_fiq)
-
-SYM_CODE_START_LOCAL(el1_error)
-	kernel_entry 1
-	mrs	x1, esr_el1
-	enable_dbg
-	mov	x0, sp
-	bl	do_serror
-	kernel_exit 1
-SYM_CODE_END(el1_error)
-
-SYM_CODE_START_LOCAL(el0_error)
-	kernel_entry 0
-el0_error_naked:
-	mrs	x25, esr_el1
-	user_exit_irqoff
-	enable_dbg
-	mov	x0, sp
-	mov	x1, x25
-	bl	do_serror
-	enable_da
-	b	ret_to_user
-SYM_CODE_END(el0_error)
+SYM_CODE_END(ret_to_kernel)
 
 /*
  * "slow" syscall return path.
@@ -979,8 +766,8 @@
 	mov	sp, x9
 	msr	sp_el0, x1
 	ptrauth_keys_install_kernel x1, x8, x9, x10
-	scs_save x0, x8
-	scs_load x1, x8
+	scs_save x0
+	scs_load x1
 	ret
 SYM_FUNC_END(cpu_switch_to)
 NOKPROBE(cpu_switch_to)
@@ -998,6 +785,42 @@
 SYM_CODE_END(ret_from_fork)
 NOKPROBE(ret_from_fork)
 
+/*
+ * void call_on_irq_stack(struct pt_regs *regs,
+ * 		          void (*func)(struct pt_regs *));
+ *
+ * Calls func(regs) using this CPU's irq stack and shadow irq stack.
+ */
+SYM_FUNC_START(call_on_irq_stack)
+#ifdef CONFIG_SHADOW_CALL_STACK
+	stp	scs_sp, xzr, [sp, #-16]!
+	ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x17
+#endif
+	/* Create a frame record to save our LR and SP (implicit in FP) */
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+
+	ldr_this_cpu x16, irq_stack_ptr, x17
+	mov	x15, #IRQ_STACK_SIZE
+	add	x16, x16, x15
+
+	/* Move to the new stack and call the function there */
+	mov	sp, x16
+	blr	x1
+
+	/*
+	 * Restore the SP from the FP, and restore the FP and LR from the frame
+	 * record.
+	 */
+	mov	sp, x29
+	ldp	x29, x30, [sp], #16
+#ifdef CONFIG_SHADOW_CALL_STACK
+	ldp	scs_sp, xzr, [sp], #16
+#endif
+	ret
+SYM_FUNC_END(call_on_irq_stack)
+NOKPROBE(call_on_irq_stack)
+
 #ifdef CONFIG_ARM_SDE_INTERFACE
 
 #include <asm/sdei.h>
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index b5d3dda..7f467bd 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -15,6 +15,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/ftrace.h>
 #include <asm/insn.h>
+#include <asm/patching.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 /*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 96873df..c5c994a 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -16,6 +16,7 @@
 #include <asm/asm_pointer_auth.h>
 #include <asm/assembler.h>
 #include <asm/boot.h>
+#include <asm/bug.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
@@ -117,8 +118,8 @@
 	dmb	sy				// needed before dc ivac with
 						// MMU off
 
-	mov	x1, #0x20			// 4 x 8 bytes
-	b	__inval_dcache_area		// tail call
+	add	x1, x0, #0x20			// 4 x 8 bytes
+	b	dcache_inval_poc		// tail call
 SYM_CODE_END(preserve_boot_args)
 
 /*
@@ -195,7 +196,7 @@
 	and	\iend, \iend, \istart	// iend = (vend >> shift) & (ptrs - 1)
 	mov	\istart, \ptrs
 	mul	\istart, \istart, \count
-	add	\iend, \iend, \istart	// iend += (count - 1) * ptrs
+	add	\iend, \iend, \istart	// iend += count * ptrs
 					// our entries span multiple tables
 
 	lsr	\istart, \vstart, \shift
@@ -268,8 +269,7 @@
 	 */
 	adrp	x0, init_pg_dir
 	adrp	x1, init_pg_end
-	sub	x1, x1, x0
-	bl	__inval_dcache_area
+	bl	dcache_inval_poc
 
 	/*
 	 * Clear the init page tables.
@@ -354,7 +354,6 @@
 #endif
 1:
 	ldr_l	x4, idmap_ptrs_per_pgd
-	mov	x5, x3				// __pa(__idmap_text_start)
 	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
 
 	map_memory x0, x1, x3, x6, x7, x3, x4, x10, x11, x12, x13, x14
@@ -382,39 +381,57 @@
 
 	adrp	x0, idmap_pg_dir
 	adrp	x1, idmap_pg_end
-	sub	x1, x1, x0
-	bl	__inval_dcache_area
+	bl	dcache_inval_poc
 
 	adrp	x0, init_pg_dir
 	adrp	x1, init_pg_end
-	sub	x1, x1, x0
-	bl	__inval_dcache_area
+	bl	dcache_inval_poc
 
 	ret	x28
 SYM_FUNC_END(__create_page_tables)
 
+	/*
+	 * Initialize CPU registers with task-specific and cpu-specific context.
+	 *
+	 * Create a final frame record at task_pt_regs(current)->stackframe, so
+	 * that the unwinder can identify the final frame record of any task by
+	 * its location in the task stack. We reserve the entire pt_regs space
+	 * for consistency with user tasks and kthreads.
+	 */
+	.macro	init_cpu_task tsk, tmp1, tmp2
+	msr	sp_el0, \tsk
+
+	ldr	\tmp1, [\tsk, #TSK_STACK]
+	add	sp, \tmp1, #THREAD_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
+
+	stp	xzr, xzr, [sp, #S_STACKFRAME]
+	add	x29, sp, #S_STACKFRAME
+
+	scs_load \tsk
+
+	adr_l	\tmp1, __per_cpu_offset
+	ldr	w\tmp2, [\tsk, #TSK_CPU]
+	ldr	\tmp1, [\tmp1, \tmp2, lsl #3]
+	set_this_cpu_offset \tmp1
+	.endm
+
 /*
  * The following fragment of code is executed with the MMU enabled.
  *
  *   x0 = __PHYS_OFFSET
  */
 SYM_FUNC_START_LOCAL(__primary_switched)
-	adrp	x4, init_thread_union
-	add	sp, x4, #THREAD_SIZE
-	adr_l	x5, init_task
-	msr	sp_el0, x5			// Save thread_info
+	adr_l	x4, init_task
+	init_cpu_task x4, x5, x6
 
 	adr_l	x8, vectors			// load VBAR_EL1 with virtual
 	msr	vbar_el1, x8			// vector table address
 	isb
 
-	stp	xzr, x30, [sp, #-16]!
+	stp	x29, x30, [sp, #-16]!
 	mov	x29, sp
 
-#ifdef CONFIG_SHADOW_CALL_STACK
-	adr_l	scs_sp, init_shadow_call_stack	// Set shadow call stack
-#endif
-
 	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
 
 	ldr_l	x4, kimage_vaddr		// Save the offset between
@@ -446,10 +463,9 @@
 0:
 #endif
 	bl	switch_to_vhe			// Prefer VHE if possible
-	add	sp, sp, #16
-	mov	x29, #0
-	mov	x30, #0
-	b	start_kernel
+	ldp	x29, x30, [sp], #16
+	bl	start_kernel
+	ASM_BUG()
 SYM_FUNC_END(__primary_switched)
 
 	.pushsection ".rodata", "a"
@@ -551,7 +567,7 @@
 	cmp	w0, #BOOT_CPU_MODE_EL2
 	b.ne	1f
 	add	x1, x1, #4
-1:	str	w0, [x1]			// This CPU has booted in EL1
+1:	str	w0, [x1]			// Save CPU boot mode
 	dmb	sy
 	dc	ivac, x1			// Invalidate potentially stale cache line
 	ret
@@ -632,21 +648,17 @@
 	isb
 
 	adr_l	x0, secondary_data
-	ldr	x1, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
-	cbz	x1, __secondary_too_slow
-	mov	sp, x1
 	ldr	x2, [x0, #CPU_BOOT_TASK]
 	cbz	x2, __secondary_too_slow
-	msr	sp_el0, x2
-	scs_load x2, x3
-	mov	x29, #0
-	mov	x30, #0
+
+	init_cpu_task x2, x1, x3
 
 #ifdef CONFIG_ARM64_PTR_AUTH
 	ptrauth_keys_init_cpu x2, x3, x4, x5
 #endif
 
-	b	secondary_start_kernel
+	bl	secondary_start_kernel
+	ASM_BUG()
 SYM_FUNC_END(__secondary_switched)
 
 SYM_FUNC_START_LOCAL(__secondary_too_slow)
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 8ccca66..81c0186 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -45,7 +45,7 @@
  * Because this code has to be copied to a 'safe' page, it can't call out to
  * other functions by PC-relative address. Also remember that it may be
  * mid-way through over-writing other functions. For this reason it contains
- * code from flush_icache_range() and uses the copy_page() macro.
+ * code from caches_clean_inval_pou() and uses the copy_page() macro.
  *
  * This 'safe' page is mapped via ttbr0, and executed from there. This function
  * switches to a copy of the linear map in ttbr1, performs the restore, then
@@ -87,11 +87,12 @@
 	copy_page	x0, x1, x2, x3, x4, x5, x6, x7, x8, x9
 
 	add	x1, x10, #PAGE_SIZE
-	/* Clean the copied page to PoU - based on flush_icache_range() */
+	/* Clean the copied page to PoU - based on caches_clean_inval_pou() */
 	raw_dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x10, x3
-2:	dc	cvau, x4	/* clean D line / unified line */
+2:	/* clean D line / unified line */
+alternative_insn "dc cvau, x4",  "dc civac, x4",  ARM64_WORKAROUND_CLEAN_CACHE
 	add	x4, x4, x2
 	cmp	x4, x1
 	b.lo	2b
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index b1cef37..46a0b4d 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -210,7 +210,7 @@
 		return -ENOMEM;
 
 	memcpy(page, src_start, length);
-	__flush_icache_range((unsigned long)page, (unsigned long)page + length);
+	caches_clean_inval_pou((unsigned long)page, (unsigned long)page + length);
 	rc = trans_pgd_idmap_page(&trans_info, &trans_ttbr0, &t0sz, page);
 	if (rc)
 		return rc;
@@ -240,8 +240,6 @@
 	return 0;
 }
 
-#define dcache_clean_range(start, end)	__flush_dcache_area(start, (end - start))
-
 #ifdef CONFIG_ARM64_MTE
 
 static DEFINE_XARRAY(mte_pages);
@@ -383,13 +381,18 @@
 		ret = swsusp_save();
 	} else {
 		/* Clean kernel core startup/idle code to PoC*/
-		dcache_clean_range(__mmuoff_data_start, __mmuoff_data_end);
-		dcache_clean_range(__idmap_text_start, __idmap_text_end);
+		dcache_clean_inval_poc((unsigned long)__mmuoff_data_start,
+				    (unsigned long)__mmuoff_data_end);
+		dcache_clean_inval_poc((unsigned long)__idmap_text_start,
+				    (unsigned long)__idmap_text_end);
 
 		/* Clean kvm setup code to PoC? */
 		if (el2_reset_needed()) {
-			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
-			dcache_clean_range(__hyp_text_start, __hyp_text_end);
+			dcache_clean_inval_poc(
+				(unsigned long)__hyp_idmap_text_start,
+				(unsigned long)__hyp_idmap_text_end);
+			dcache_clean_inval_poc((unsigned long)__hyp_text_start,
+					    (unsigned long)__hyp_text_end);
 		}
 
 		swsusp_mte_restore_tags();
@@ -474,7 +477,8 @@
 	 * The hibernate exit text contains a set of el2 vectors, that will
 	 * be executed at el2 with the mmu off in order to reload hyp-stub.
 	 */
-	__flush_dcache_area(hibernate_exit, exit_size);
+	dcache_clean_inval_poc((unsigned long)hibernate_exit,
+			    (unsigned long)hibernate_exit + exit_size);
 
 	/*
 	 * KASLR will cause the el2 vectors to be in a different location in
diff --git a/arch/arm64/kernel/idle.c b/arch/arm64/kernel/idle.c
new file mode 100644
index 0000000..a2cfbace
--- /dev/null
+++ b/arch/arm64/kernel/idle.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Low-level idle sequences
+ */
+
+#include <linux/cpu.h>
+#include <linux/irqflags.h>
+
+#include <asm/barrier.h>
+#include <asm/cpuidle.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
+
+/*
+ *	cpu_do_idle()
+ *
+ *	Idle the processor (wait for interrupt).
+ *
+ *	If the CPU supports priority masking we must do additional work to
+ *	ensure that interrupts are not masked at the PMR (because the core will
+ *	not wake up if we block the wake up signal in the interrupt controller).
+ */
+void noinstr cpu_do_idle(void)
+{
+	struct arm_cpuidle_irq_context context;
+
+	arm_cpuidle_save_irq_context(&context);
+
+	dsb(sy);
+	wfi();
+
+	arm_cpuidle_restore_irq_context(&context);
+}
+
+/*
+ * This is our default idle handler.
+ */
+void noinstr arch_cpu_idle(void)
+{
+	/*
+	 * This should do all the clock switching and wait for interrupt
+	 * tricks
+	 */
+	cpu_do_idle();
+	raw_local_irq_enable();
+}
diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index e628c8c..53a381a 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -237,7 +237,8 @@
 
 	for (i = 0; i < ARRAY_SIZE(regs); i++) {
 		if (regs[i]->override)
-			__flush_dcache_area(regs[i]->override,
+			dcache_clean_inval_poc((unsigned long)regs[i]->override,
+					    (unsigned long)regs[i]->override +
 					    sizeof(*regs[i]->override));
 	}
 }
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index bcf3c27..c96a9a0 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -35,7 +35,7 @@
 __efistub_strcmp		= __pi_strcmp;
 __efistub_strncmp		= __pi_strncmp;
 __efistub_strrchr		= __pi_strrchr;
-__efistub___clean_dcache_area_poc = __pi___clean_dcache_area_poc;
+__efistub_dcache_clean_poc = __pi_dcache_clean_poc;
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 __efistub___memcpy		= __pi_memcpy;
diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
index 9a8a0ae..fc98037 100644
--- a/arch/arm64/kernel/jump_label.c
+++ b/arch/arm64/kernel/jump_label.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/jump_label.h>
 #include <asm/insn.h>
+#include <asm/patching.h>
 
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 341342b..cfa2cfd 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -72,7 +72,9 @@
 	 * we end up running with module randomization disabled.
 	 */
 	module_alloc_base = (u64)_etext - MODULES_VSIZE;
-	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
+	dcache_clean_inval_poc((unsigned long)&module_alloc_base,
+			    (unsigned long)&module_alloc_base +
+				    sizeof(module_alloc_base));
 
 	/*
 	 * Try to map the FDT early. If this fails, we simply bail,
@@ -170,8 +172,12 @@
 	module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
 	module_alloc_base &= PAGE_MASK;
 
-	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
-	__flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
+	dcache_clean_inval_poc((unsigned long)&module_alloc_base,
+			    (unsigned long)&module_alloc_base +
+				    sizeof(module_alloc_base));
+	dcache_clean_inval_poc((unsigned long)&memstart_offset_seed,
+			    (unsigned long)&memstart_offset_seed +
+				    sizeof(memstart_offset_seed));
 
 	return offset;
 }
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 1a157ca3..2aede78 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -17,6 +17,7 @@
 
 #include <asm/debug-monitors.h>
 #include <asm/insn.h>
+#include <asm/patching.h>
 #include <asm/traps.h>
 
 struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 90a335c..03ceabe 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -68,10 +68,16 @@
 	kimage->arch.kern_reloc = __pa(reloc_code);
 	kexec_image_info(kimage);
 
-	/* Flush the reloc_code in preparation for its execution. */
-	__flush_dcache_area(reloc_code, arm64_relocate_new_kernel_size);
-	flush_icache_range((uintptr_t)reloc_code, (uintptr_t)reloc_code +
-			   arm64_relocate_new_kernel_size);
+	/*
+	 * For execution with the MMU off, reloc_code needs to be cleaned to the
+	 * PoC and invalidated from the I-cache.
+	 */
+	dcache_clean_inval_poc((unsigned long)reloc_code,
+			    (unsigned long)reloc_code +
+				    arm64_relocate_new_kernel_size);
+	icache_inval_pou((uintptr_t)reloc_code,
+				(uintptr_t)reloc_code +
+					arm64_relocate_new_kernel_size);
 
 	return 0;
 }
@@ -102,16 +108,18 @@
 
 	for (entry = &kimage->head; ; entry++) {
 		unsigned int flag;
-		void *addr;
+		unsigned long addr;
 
 		/* flush the list entries. */
-		__flush_dcache_area(entry, sizeof(kimage_entry_t));
+		dcache_clean_inval_poc((unsigned long)entry,
+				    (unsigned long)entry +
+					    sizeof(kimage_entry_t));
 
 		flag = *entry & IND_FLAGS;
 		if (flag == IND_DONE)
 			break;
 
-		addr = phys_to_virt(*entry & PAGE_MASK);
+		addr = (unsigned long)phys_to_virt(*entry & PAGE_MASK);
 
 		switch (flag) {
 		case IND_INDIRECTION:
@@ -120,7 +128,7 @@
 			break;
 		case IND_SOURCE:
 			/* flush the source pages. */
-			__flush_dcache_area(addr, PAGE_SIZE);
+			dcache_clean_inval_poc(addr, addr + PAGE_SIZE);
 			break;
 		case IND_DESTINATION:
 			break;
@@ -147,8 +155,10 @@
 			kimage->segment[i].memsz,
 			kimage->segment[i].memsz /  PAGE_SIZE);
 
-		__flush_dcache_area(phys_to_virt(kimage->segment[i].mem),
-			kimage->segment[i].memsz);
+		dcache_clean_inval_poc(
+			(unsigned long)phys_to_virt(kimage->segment[i].mem),
+			(unsigned long)phys_to_virt(kimage->segment[i].mem) +
+				kimage->segment[i].memsz);
 	}
 }
 
diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c
new file mode 100644
index 0000000..771f543
--- /dev/null
+++ b/arch/arm64/kernel/patching.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/stop_machine.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
+#include <asm/insn.h>
+#include <asm/kprobes.h>
+#include <asm/patching.h>
+#include <asm/sections.h>
+
+static DEFINE_RAW_SPINLOCK(patch_lock);
+
+static bool is_exit_text(unsigned long addr)
+{
+	/* discarded with init text/data */
+	return system_state < SYSTEM_RUNNING &&
+		addr >= (unsigned long)__exittext_begin &&
+		addr < (unsigned long)__exittext_end;
+}
+
+static bool is_image_text(unsigned long addr)
+{
+	return core_kernel_text(addr) || is_exit_text(addr);
+}
+
+static void __kprobes *patch_map(void *addr, int fixmap)
+{
+	unsigned long uintaddr = (uintptr_t) addr;
+	bool image = is_image_text(uintaddr);
+	struct page *page;
+
+	if (image)
+		page = phys_to_page(__pa_symbol(addr));
+	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		page = vmalloc_to_page(addr);
+	else
+		return addr;
+
+	BUG_ON(!page);
+	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
+			(uintaddr & ~PAGE_MASK));
+}
+
+static void __kprobes patch_unmap(int fixmap)
+{
+	clear_fixmap(fixmap);
+}
+/*
+ * In ARMv8-A, A64 instructions have a fixed length of 32 bits and are always
+ * little-endian.
+ */
+int __kprobes aarch64_insn_read(void *addr, u32 *insnp)
+{
+	int ret;
+	__le32 val;
+
+	ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE);
+	if (!ret)
+		*insnp = le32_to_cpu(val);
+
+	return ret;
+}
+
+static int __kprobes __aarch64_insn_write(void *addr, __le32 insn)
+{
+	void *waddr = addr;
+	unsigned long flags = 0;
+	int ret;
+
+	raw_spin_lock_irqsave(&patch_lock, flags);
+	waddr = patch_map(addr, FIX_TEXT_POKE0);
+
+	ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE);
+
+	patch_unmap(FIX_TEXT_POKE0);
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
+
+	return ret;
+}
+
+int __kprobes aarch64_insn_write(void *addr, u32 insn)
+{
+	return __aarch64_insn_write(addr, cpu_to_le32(insn));
+}
+
+int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
+{
+	u32 *tp = addr;
+	int ret;
+
+	/* A64 instructions must be word aligned */
+	if ((uintptr_t)tp & 0x3)
+		return -EINVAL;
+
+	ret = aarch64_insn_write(tp, insn);
+	if (ret == 0)
+		caches_clean_inval_pou((uintptr_t)tp,
+				     (uintptr_t)tp + AARCH64_INSN_SIZE);
+
+	return ret;
+}
+
+struct aarch64_insn_patch {
+	void		**text_addrs;
+	u32		*new_insns;
+	int		insn_cnt;
+	atomic_t	cpu_count;
+};
+
+static int __kprobes aarch64_insn_patch_text_cb(void *arg)
+{
+	int i, ret = 0;
+	struct aarch64_insn_patch *pp = arg;
+
+	/* The first CPU becomes master */
+	if (atomic_inc_return(&pp->cpu_count) == 1) {
+		for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
+			ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
+							     pp->new_insns[i]);
+		/* Notify other processors with an additional increment. */
+		atomic_inc(&pp->cpu_count);
+	} else {
+		while (atomic_read(&pp->cpu_count) <= num_online_cpus())
+			cpu_relax();
+		isb();
+	}
+
+	return ret;
+}
+
+int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
+{
+	struct aarch64_insn_patch patch = {
+		.text_addrs = addrs,
+		.new_insns = insns,
+		.insn_cnt = cnt,
+		.cpu_count = ATOMIC_INIT(0),
+	};
+
+	if (cnt <= 0)
+		return -EINVAL;
+
+	return stop_machine_cpuslocked(aarch64_insn_patch_text_cb, &patch,
+				       cpu_online_mask);
+}
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 88ff471..4a72c27 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -116,7 +116,7 @@
 		tail = (struct frame_tail __user *)regs->regs[29];
 
 		while (entry->nr < entry->max_stack &&
-		       tail && !((unsigned long)tail & 0xf))
+		       tail && !((unsigned long)tail & 0x7))
 			tail = user_backtrace(tail, entry);
 	} else {
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index f594957..d07788d 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -165,10 +165,7 @@
 }
 
 #define ARMV8_EVENT_ATTR(name, config)						\
-	(&((struct perf_pmu_events_attr) {					\
-		.attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL),	\
-		.id = config,							\
-	}).attr.attr)
+	PMU_EVENT_ATTR_ID(name, armv8pmu_events_sysfs_show, config)
 
 static struct attribute *armv8_pmuv3_event_attrs[] = {
 	ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR),
@@ -312,13 +309,46 @@
 	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
 	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
 
-	return snprintf(page, PAGE_SIZE, "0x%08x\n", slots);
+	return sysfs_emit(page, "0x%08x\n", slots);
 }
 
 static DEVICE_ATTR_RO(slots);
 
+static ssize_t bus_slots_show(struct device *dev, struct device_attribute *attr,
+			      char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 bus_slots = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_SLOTS_SHIFT)
+			& ARMV8_PMU_BUS_SLOTS_MASK;
+
+	return sysfs_emit(page, "0x%08x\n", bus_slots);
+}
+
+static DEVICE_ATTR_RO(bus_slots);
+
+static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr,
+			      char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 bus_width = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_WIDTH_SHIFT)
+			& ARMV8_PMU_BUS_WIDTH_MASK;
+	u32 val = 0;
+
+	/* Encoded as Log2(number of bytes), plus one */
+	if (bus_width > 2 && bus_width < 13)
+		val = 1 << (bus_width - 1);
+
+	return sysfs_emit(page, "0x%08x\n", val);
+}
+
+static DEVICE_ATTR_RO(bus_width);
+
 static struct attribute *armv8_pmuv3_caps_attrs[] = {
 	&dev_attr_slots.attr,
+	&dev_attr_bus_slots.attr,
+	&dev_attr_bus_width.attr,
 	NULL,
 };
 
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d607c99..609edde 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -7,26 +7,28 @@
  * Copyright (C) 2013 Linaro Limited.
  * Author: Sandeepa Prabhu <sandeepa.prabhu@linaro.org>
  */
+#include <linux/extable.h>
 #include <linux/kasan.h>
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
-#include <linux/extable.h>
-#include <linux/slab.h>
-#include <linux/stop_machine.h>
 #include <linux/sched/debug.h>
 #include <linux/set_memory.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
 #include <linux/stringify.h>
-#include <linux/vmalloc.h>
-#include <asm/traps.h>
-#include <asm/ptrace.h>
-#include <asm/cacheflush.h>
-#include <asm/debug-monitors.h>
-#include <asm/daifflags.h>
-#include <asm/system_misc.h>
-#include <asm/insn.h>
 #include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+
+#include <asm/cacheflush.h>
+#include <asm/daifflags.h>
+#include <asm/debug-monitors.h>
+#include <asm/insn.h>
 #include <asm/irq.h>
+#include <asm/patching.h>
+#include <asm/ptrace.h>
 #include <asm/sections.h>
+#include <asm/system_misc.h>
+#include <asm/traps.h>
 
 #include "decode-insn.h"
 
diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c
index 25f67ec..22d0b32 100644
--- a/arch/arm64/kernel/probes/simulate-insn.c
+++ b/arch/arm64/kernel/probes/simulate-insn.c
@@ -10,6 +10,7 @@
 #include <linux/kprobes.h>
 
 #include <asm/ptrace.h>
+#include <asm/traps.h>
 
 #include "simulate-insn.h"
 
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 2c24763..9be668f 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -21,7 +21,7 @@
 	memcpy(dst, src, len);
 
 	/* flush caches (dcache/icache) */
-	sync_icache_aliases(dst, len);
+	sync_icache_aliases((unsigned long)dst, (unsigned long)dst + len);
 
 	kunmap_atomic(xol_page_kaddr);
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index b4bb67f..6b8b4b3 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -18,7 +18,6 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
-#include <linux/lockdep.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/nospec.h>
@@ -46,7 +45,6 @@
 #include <linux/prctl.h>
 
 #include <asm/alternative.h>
-#include <asm/arch_gicv3.h>
 #include <asm/compat.h>
 #include <asm/cpufeature.h>
 #include <asm/cacheflush.h>
@@ -74,63 +72,6 @@
 
 void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 
-static void noinstr __cpu_do_idle(void)
-{
-	dsb(sy);
-	wfi();
-}
-
-static void noinstr __cpu_do_idle_irqprio(void)
-{
-	unsigned long pmr;
-	unsigned long daif_bits;
-
-	daif_bits = read_sysreg(daif);
-	write_sysreg(daif_bits | PSR_I_BIT | PSR_F_BIT, daif);
-
-	/*
-	 * Unmask PMR before going idle to make sure interrupts can
-	 * be raised.
-	 */
-	pmr = gic_read_pmr();
-	gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-
-	__cpu_do_idle();
-
-	gic_write_pmr(pmr);
-	write_sysreg(daif_bits, daif);
-}
-
-/*
- *	cpu_do_idle()
- *
- *	Idle the processor (wait for interrupt).
- *
- *	If the CPU supports priority masking we must do additional work to
- *	ensure that interrupts are not masked at the PMR (because the core will
- *	not wake up if we block the wake up signal in the interrupt controller).
- */
-void noinstr cpu_do_idle(void)
-{
-	if (system_uses_irq_prio_masking())
-		__cpu_do_idle_irqprio();
-	else
-		__cpu_do_idle();
-}
-
-/*
- * This is our default idle handler.
- */
-void noinstr arch_cpu_idle(void)
-{
-	/*
-	 * This should do all the clock switching and wait for interrupt
-	 * tricks
-	 */
-	cpu_do_idle();
-	raw_local_irq_enable();
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 void arch_cpu_idle_dead(void)
 {
@@ -435,6 +376,11 @@
 	}
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
 	p->thread.cpu_context.sp = (unsigned long)childregs;
+	/*
+	 * For the benefit of the unwinder, set up childregs->stackframe
+	 * as the final frame for the new task.
+	 */
+	p->thread.cpu_context.fp = (unsigned long)childregs->stackframe;
 
 	ptrace_hw_copy_thread(p);
 
@@ -527,6 +473,15 @@
 	write_sysreg(val, cntkctl_el1);
 }
 
+static void compat_thread_switch(struct task_struct *next)
+{
+	if (!is_compat_thread(task_thread_info(next)))
+		return;
+
+	if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+		set_tsk_thread_flag(next, TIF_NOTIFY_RESUME);
+}
+
 static void update_sctlr_el1(u64 sctlr)
 {
 	/*
@@ -568,6 +523,7 @@
 	ssbs_thread_switch(next);
 	erratum_1418040_thread_switch(prev, next);
 	ptrauth_thread_switch_user(next);
+	compat_thread_switch(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
@@ -633,8 +589,15 @@
  */
 void arch_setup_new_exec(void)
 {
-	current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
+	unsigned long mmflags = 0;
 
+	if (is_compat_task()) {
+		mmflags = MMCF_AARCH32;
+		if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+			set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+	}
+
+	current->mm->context.flags = mmflags;
 	ptrauth_thread_init_user();
 	mte_thread_init_user();
 
@@ -724,22 +687,6 @@
 core_initcall(tagged_addr_init);
 #endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
 
-asmlinkage void __sched arm64_preempt_schedule_irq(void)
-{
-	lockdep_assert_irqs_disabled();
-
-	/*
-	 * Preempting a task from an IRQ means we leave copies of PSTATE
-	 * on the stack. cpufeature's enable calls may modify PSTATE, but
-	 * resuming one of these preempted tasks would undo those changes.
-	 *
-	 * Only allow a task to be preempted once cpufeatures have been
-	 * enabled.
-	 */
-	if (system_capabilities_finalized())
-		preempt_schedule_irq();
-}
-
 #ifdef CONFIG_BINFMT_ELF
 int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state,
 			 bool has_interp, bool is_interp)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index eb2f739..499b6b2 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -122,7 +122,7 @@
 {
 	return ((addr & ~(THREAD_SIZE - 1))  ==
 		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) ||
-		on_irq_stack(addr, NULL);
+		on_irq_stack(addr, sizeof(unsigned long), NULL);
 }
 
 /**
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 2c7ca44..47f77d12 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -162,31 +162,33 @@
 	return err;
 }
 
-static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info)
+static bool on_sdei_normal_stack(unsigned long sp, unsigned long size,
+				 struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
 
-	return on_stack(sp, low, high, STACK_TYPE_SDEI_NORMAL, info);
+	return on_stack(sp, size, low, high, STACK_TYPE_SDEI_NORMAL, info);
 }
 
-static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info)
+static bool on_sdei_critical_stack(unsigned long sp, unsigned long size,
+				   struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
 
-	return on_stack(sp, low, high, STACK_TYPE_SDEI_CRITICAL, info);
+	return on_stack(sp, size, low, high, STACK_TYPE_SDEI_CRITICAL, info);
 }
 
-bool _on_sdei_stack(unsigned long sp, struct stack_info *info)
+bool _on_sdei_stack(unsigned long sp, unsigned long size, struct stack_info *info)
 {
 	if (!IS_ENABLED(CONFIG_VMAP_STACK))
 		return false;
 
-	if (on_sdei_critical_stack(sp, info))
+	if (on_sdei_critical_stack(sp, size, info))
 		return true;
 
-	if (on_sdei_normal_stack(sp, info))
+	if (on_sdei_normal_stack(sp, size, info))
 		return true;
 
 	return false;
@@ -231,13 +233,13 @@
 }
 
 /*
- * __sdei_handler() returns one of:
+ * do_sdei_event() returns one of:
  *  SDEI_EV_HANDLED -  success, return to the interrupted context.
  *  SDEI_EV_FAILED  -  failure, return this error code to firmare.
  *  virtual-address -  success, return to this address.
  */
-static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
-					     struct sdei_registered_event *arg)
+unsigned long __kprobes do_sdei_event(struct pt_regs *regs,
+				      struct sdei_registered_event *arg)
 {
 	u32 mode;
 	int i, err = 0;
@@ -292,45 +294,3 @@
 
 	return vbar + 0x480;
 }
-
-static void __kprobes notrace __sdei_pstate_entry(void)
-{
-	/*
-	 * The original SDEI spec (ARM DEN 0054A) can be read ambiguously as to
-	 * whether PSTATE bits are inherited unchanged or generated from
-	 * scratch, and the TF-A implementation always clears PAN and always
-	 * clears UAO. There are no other known implementations.
-	 *
-	 * Subsequent revisions (ARM DEN 0054B) follow the usual rules for how
-	 * PSTATE is modified upon architectural exceptions, and so PAN is
-	 * either inherited or set per SCTLR_ELx.SPAN, and UAO is always
-	 * cleared.
-	 *
-	 * We must explicitly reset PAN to the expected state, including
-	 * clearing it when the host isn't using it, in case a VM had it set.
-	 */
-	if (system_uses_hw_pan())
-		set_pstate_pan(1);
-	else if (cpu_has_pan())
-		set_pstate_pan(0);
-}
-
-asmlinkage noinstr unsigned long
-__sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
-{
-	unsigned long ret;
-
-	/*
-	 * We didn't take an exception to get here, so the HW hasn't
-	 * set/cleared bits in PSTATE that we may rely on. Initialize PAN.
-	 */
-	__sdei_pstate_entry();
-
-	arm64_enter_nmi(regs);
-
-	ret = _sdei_handler(regs, arg);
-
-	arm64_exit_nmi(regs);
-
-	return ret;
-}
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 61845c0..8ed6614 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -87,12 +87,6 @@
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	set_cpu_logical_map(0, mpidr);
 
-	/*
-	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
-	 * using percpu variable early, for example, lockdep will
-	 * access percpu variable inside lock_release
-	 */
-	set_my_cpu_offset(0);
 	pr_info("Booting Linux on physical CPU 0x%010lx [0x%08x]\n",
 		(unsigned long)mpidr, read_cpuid_id());
 }
@@ -381,7 +375,7 @@
 	 * faults in case uaccess_enable() is inadvertently called by the init
 	 * thread.
 	 */
-	init_task.thread_info.ttbr0 = __pa_symbol(reserved_pg_dir);
+	init_task.thread_info.ttbr0 = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
 #endif
 
 	if (boot_args[1] || boot_args[2] || boot_args[3]) {
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 6237486..f8192f4 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -911,6 +911,19 @@
 	restore_saved_sigmask();
 }
 
+static bool cpu_affinity_invalid(struct pt_regs *regs)
+{
+	if (!compat_user_mode(regs))
+		return false;
+
+	/*
+	 * We're preemptible, but a reschedule will cause us to check the
+	 * affinity again.
+	 */
+	return !cpumask_test_cpu(raw_smp_processor_id(),
+				 system_32bit_el0_cpumask());
+}
+
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 				 unsigned long thread_flags)
 {
@@ -938,6 +951,19 @@
 			if (thread_flags & _TIF_NOTIFY_RESUME) {
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
+
+				/*
+				 * If we reschedule after checking the affinity
+				 * then we must ensure that TIF_NOTIFY_RESUME
+				 * is set so that we check the affinity again.
+				 * Since tracehook_notify_resume() clears the
+				 * flag, ensure that the compiler doesn't move
+				 * it after the affinity check.
+				 */
+				barrier();
+
+				if (cpu_affinity_invalid(regs))
+					force_sig(SIGKILL);
 			}
 
 			if (thread_flags & _TIF_FOREIGN_FPSTATE)
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
index d624479..d3d37f9 100644
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -7,8 +7,34 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
+#include <asm/thread_info.h>
+
+/*
+ * If we have SMCCC v1.3 and (as is likely) no SVE state in
+ * the registers then set the SMCCC hint bit to say there's no
+ * need to preserve it.  Do this by directly adjusting the SMCCC
+ * function value which is already stored in x0 ready to be called.
+ */
+SYM_FUNC_START(__arm_smccc_sve_check)
+
+	ldr_l	x16, smccc_has_sve_hint
+	cbz	x16, 2f
+
+	get_current_task x16
+	ldr	x16, [x16, #TSK_TI_FLAGS]
+	tbnz	x16, #TIF_FOREIGN_FPSTATE, 1f	// Any live FP state?
+	tbnz	x16, #TIF_SVE, 2f		// Does that state include SVE?
+
+1:	orr	x0, x0, ARM_SMCCC_1_3_SVE_HINT
+
+2:	ret
+SYM_FUNC_END(__arm_smccc_sve_check)
+EXPORT_SYMBOL(__arm_smccc_sve_check)
 
 	.macro SMCCC instr
+alternative_if ARM64_SVE
+	bl	__arm_smccc_sve_check
+alternative_else_nop_endif
 	\instr	#0
 	ldr	x4, [sp]
 	stp	x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
@@ -43,3 +69,60 @@
 	SMCCC	hvc
 SYM_FUNC_END(__arm_smccc_hvc)
 EXPORT_SYMBOL(__arm_smccc_hvc)
+
+	.macro SMCCC_1_2 instr
+	/* Save `res` and free a GPR that won't be clobbered */
+	stp     x1, x19, [sp, #-16]!
+
+	/* Ensure `args` won't be clobbered while loading regs in next step */
+	mov	x19, x0
+
+	/* Load the registers x0 - x17 from the struct arm_smccc_1_2_regs */
+	ldp	x0, x1, [x19, #ARM_SMCCC_1_2_REGS_X0_OFFS]
+	ldp	x2, x3, [x19, #ARM_SMCCC_1_2_REGS_X2_OFFS]
+	ldp	x4, x5, [x19, #ARM_SMCCC_1_2_REGS_X4_OFFS]
+	ldp	x6, x7, [x19, #ARM_SMCCC_1_2_REGS_X6_OFFS]
+	ldp	x8, x9, [x19, #ARM_SMCCC_1_2_REGS_X8_OFFS]
+	ldp	x10, x11, [x19, #ARM_SMCCC_1_2_REGS_X10_OFFS]
+	ldp	x12, x13, [x19, #ARM_SMCCC_1_2_REGS_X12_OFFS]
+	ldp	x14, x15, [x19, #ARM_SMCCC_1_2_REGS_X14_OFFS]
+	ldp	x16, x17, [x19, #ARM_SMCCC_1_2_REGS_X16_OFFS]
+
+	\instr #0
+
+	/* Load the `res` from the stack */
+	ldr	x19, [sp]
+
+	/* Store the registers x0 - x17 into the result structure */
+	stp	x0, x1, [x19, #ARM_SMCCC_1_2_REGS_X0_OFFS]
+	stp	x2, x3, [x19, #ARM_SMCCC_1_2_REGS_X2_OFFS]
+	stp	x4, x5, [x19, #ARM_SMCCC_1_2_REGS_X4_OFFS]
+	stp	x6, x7, [x19, #ARM_SMCCC_1_2_REGS_X6_OFFS]
+	stp	x8, x9, [x19, #ARM_SMCCC_1_2_REGS_X8_OFFS]
+	stp	x10, x11, [x19, #ARM_SMCCC_1_2_REGS_X10_OFFS]
+	stp	x12, x13, [x19, #ARM_SMCCC_1_2_REGS_X12_OFFS]
+	stp	x14, x15, [x19, #ARM_SMCCC_1_2_REGS_X14_OFFS]
+	stp	x16, x17, [x19, #ARM_SMCCC_1_2_REGS_X16_OFFS]
+
+	/* Restore original x19 */
+	ldp     xzr, x19, [sp], #16
+	ret
+.endm
+
+/*
+ * void arm_smccc_1_2_hvc(const struct arm_smccc_1_2_regs *args,
+ *			  struct arm_smccc_1_2_regs *res);
+ */
+SYM_FUNC_START(arm_smccc_1_2_hvc)
+	SMCCC_1_2 hvc
+SYM_FUNC_END(arm_smccc_1_2_hvc)
+EXPORT_SYMBOL(arm_smccc_1_2_hvc)
+
+/*
+ * void arm_smccc_1_2_smc(const struct arm_smccc_1_2_regs *args,
+ *			  struct arm_smccc_1_2_regs *res);
+ */
+SYM_FUNC_START(arm_smccc_1_2_smc)
+	SMCCC_1_2 smc
+SYM_FUNC_END(arm_smccc_1_2_smc)
+EXPORT_SYMBOL(arm_smccc_1_2_smc)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index dcd7041..161dab4 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -120,9 +120,7 @@
 	 * page tables.
 	 */
 	secondary_data.task = idle;
-	secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
 	update_cpu_boot_status(CPU_MMU_OFF);
-	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 
 	/* Now bring the CPU into our world */
 	ret = boot_secondary(cpu, idle);
@@ -142,8 +140,6 @@
 
 	pr_crit("CPU%u: failed to come online\n", cpu);
 	secondary_data.task = NULL;
-	secondary_data.stack = NULL;
-	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	status = READ_ONCE(secondary_data.status);
 	if (status == CPU_MMU_OFF)
 		status = READ_ONCE(__early_cpu_boot_status);
@@ -202,10 +198,7 @@
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	struct mm_struct *mm = &init_mm;
 	const struct cpu_operations *ops;
-	unsigned int cpu;
-
-	cpu = task_cpu(current);
-	set_my_cpu_offset(per_cpu_offset(cpu));
+	unsigned int cpu = smp_processor_id();
 
 	/*
 	 * All kernel threads share the same mm context; grab a
@@ -352,7 +345,7 @@
 		pr_crit("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
-	pr_notice("CPU%u: shutdown\n", cpu);
+	pr_debug("CPU%u: shutdown\n", cpu);
 
 	/*
 	 * Now that the dying CPU is beyond the point of no return w.r.t.
@@ -452,6 +445,11 @@
 
 void __init smp_prepare_boot_cpu(void)
 {
+	/*
+	 * The runtime per-cpu areas have been allocated by
+	 * setup_per_cpu_areas(), and CPU0's boot time per-cpu area will be
+	 * freed shortly, so we must move over to the runtime per-cpu area.
+	 */
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 	cpuinfo_store_boot_cpu();
 
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index c45a835..7e1624e 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -36,7 +36,7 @@
 	unsigned long size = sizeof(secondary_holding_pen_release);
 
 	secondary_holding_pen_release = val;
-	__flush_dcache_area(start, size);
+	dcache_clean_inval_poc((unsigned long)start, (unsigned long)start + size);
 }
 
 
@@ -90,8 +90,9 @@
 	 * the boot protocol.
 	 */
 	writeq_relaxed(pa_holding_pen, release_addr);
-	__flush_dcache_area((__force void *)release_addr,
-			    sizeof(*release_addr));
+	dcache_clean_inval_poc((__force unsigned long)release_addr,
+			    (__force unsigned long)release_addr +
+				    sizeof(*release_addr));
 
 	/*
 	 * Send an event to wake up the secondary CPU.
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index de07147..b189de5 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -68,13 +68,17 @@
 	unsigned long fp = frame->fp;
 	struct stack_info info;
 
-	if (fp & 0xf)
-		return -EINVAL;
-
 	if (!tsk)
 		tsk = current;
 
-	if (!on_accessible_stack(tsk, fp, &info))
+	/* Final frame; nothing to unwind */
+	if (fp == (unsigned long)task_pt_regs(tsk)->stackframe)
+		return -ENOENT;
+
+	if (fp & 0x7)
+		return -EINVAL;
+
+	if (!on_accessible_stack(tsk, fp, 16, &info))
 		return -EINVAL;
 
 	if (test_bit(info.type, frame->stacks_done))
@@ -128,12 +132,6 @@
 
 	frame->pc = ptrauth_strip_insn_pac(frame->pc);
 
-	/*
-	 * This is a terminal record, so we have finished unwinding.
-	 */
-	if (!frame->fp && !frame->pc)
-		return -ENOENT;
-
 	return 0;
 }
 NOKPROBE_SYMBOL(unwind_frame);
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index e3f72df..938ce6f 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -7,6 +7,7 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
+#include <asm/cpuidle.h>
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/exec.h>
@@ -91,6 +92,7 @@
 	int ret = 0;
 	unsigned long flags;
 	struct sleep_stack_data state;
+	struct arm_cpuidle_irq_context context;
 
 	/* Report any MTE async fault before going to suspend */
 	mte_suspend_enter();
@@ -103,12 +105,18 @@
 	flags = local_daif_save();
 
 	/*
-	 * Function graph tracer state gets incosistent when the kernel
+	 * Function graph tracer state gets inconsistent when the kernel
 	 * calls functions that never return (aka suspend finishers) hence
 	 * disable graph tracing during their execution.
 	 */
 	pause_graph_tracing();
 
+	/*
+	 * Switch to using DAIF.IF instead of PMR in order to reliably
+	 * resume if we're using pseudo-NMIs.
+	 */
+	arm_cpuidle_save_irq_context(&context);
+
 	if (__cpu_suspend_enter(&state)) {
 		/* Call the suspend finisher */
 		ret = fn(arg);
@@ -126,6 +134,8 @@
 		RCU_NONIDLE(__cpu_suspend_exit());
 	}
 
+	arm_cpuidle_restore_irq_context(&context);
+
 	unpause_graph_tracing();
 
 	/*
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 265fe3e..db5159a 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -41,7 +41,7 @@
 			dsb(ish);
 		}
 
-		ret = __flush_cache_user_range(start, start + chunk);
+		ret = caches_clean_inval_user_pou(start, start + chunk);
 		if (ret)
 			return ret;
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index a05d34f..b03e383 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -38,6 +38,7 @@
 #include <asm/extable.h>
 #include <asm/insn.h>
 #include <asm/kprobes.h>
+#include <asm/patching.h>
 #include <asm/traps.h>
 #include <asm/smp.h>
 #include <asm/stack_pointer.h>
@@ -45,11 +46,102 @@
 #include <asm/system_misc.h>
 #include <asm/sysreg.h>
 
-static const char *handler[] = {
-	"Synchronous Abort",
-	"IRQ",
-	"FIQ",
-	"Error"
+static bool __kprobes __check_eq(unsigned long pstate)
+{
+	return (pstate & PSR_Z_BIT) != 0;
+}
+
+static bool __kprobes __check_ne(unsigned long pstate)
+{
+	return (pstate & PSR_Z_BIT) == 0;
+}
+
+static bool __kprobes __check_cs(unsigned long pstate)
+{
+	return (pstate & PSR_C_BIT) != 0;
+}
+
+static bool __kprobes __check_cc(unsigned long pstate)
+{
+	return (pstate & PSR_C_BIT) == 0;
+}
+
+static bool __kprobes __check_mi(unsigned long pstate)
+{
+	return (pstate & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_pl(unsigned long pstate)
+{
+	return (pstate & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_vs(unsigned long pstate)
+{
+	return (pstate & PSR_V_BIT) != 0;
+}
+
+static bool __kprobes __check_vc(unsigned long pstate)
+{
+	return (pstate & PSR_V_BIT) == 0;
+}
+
+static bool __kprobes __check_hi(unsigned long pstate)
+{
+	pstate &= ~(pstate >> 1);	/* PSR_C_BIT &= ~PSR_Z_BIT */
+	return (pstate & PSR_C_BIT) != 0;
+}
+
+static bool __kprobes __check_ls(unsigned long pstate)
+{
+	pstate &= ~(pstate >> 1);	/* PSR_C_BIT &= ~PSR_Z_BIT */
+	return (pstate & PSR_C_BIT) == 0;
+}
+
+static bool __kprobes __check_ge(unsigned long pstate)
+{
+	pstate ^= (pstate << 3);	/* PSR_N_BIT ^= PSR_V_BIT */
+	return (pstate & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_lt(unsigned long pstate)
+{
+	pstate ^= (pstate << 3);	/* PSR_N_BIT ^= PSR_V_BIT */
+	return (pstate & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_gt(unsigned long pstate)
+{
+	/*PSR_N_BIT ^= PSR_V_BIT */
+	unsigned long temp = pstate ^ (pstate << 3);
+
+	temp |= (pstate << 1);	/*PSR_N_BIT |= PSR_Z_BIT */
+	return (temp & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_le(unsigned long pstate)
+{
+	/*PSR_N_BIT ^= PSR_V_BIT */
+	unsigned long temp = pstate ^ (pstate << 3);
+
+	temp |= (pstate << 1);	/*PSR_N_BIT |= PSR_Z_BIT */
+	return (temp & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_al(unsigned long pstate)
+{
+	return true;
+}
+
+/*
+ * Note that the ARMv8 ARM calls condition code 0b1111 "nv", but states that
+ * it behaves identically to 0b1110 ("al").
+ */
+pstate_check_t * const aarch32_opcode_cond_checks[16] = {
+	__check_eq, __check_ne, __check_cs, __check_cc,
+	__check_mi, __check_pl, __check_vs, __check_vc,
+	__check_hi, __check_ls, __check_ge, __check_lt,
+	__check_gt, __check_le, __check_al, __check_al
 };
 
 int show_unhandled_signals = 0;
@@ -751,27 +843,8 @@
 }
 
 /*
- * bad_mode handles the impossible case in the exception vector. This is always
- * fatal.
- */
-asmlinkage void notrace bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
-{
-	arm64_enter_nmi(regs);
-
-	console_verbose();
-
-	pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
-		handler[reason], smp_processor_id(), esr,
-		esr_get_class_string(esr));
-
-	__show_regs(regs);
-	local_daif_mask();
-	panic("bad mode");
-}
-
-/*
  * bad_el0_sync handles unexpected, but potentially recoverable synchronous
- * exceptions taken from EL0. Unlike bad_mode, this returns.
+ * exceptions taken from EL0.
  */
 void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 {
@@ -789,15 +862,11 @@
 DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)
 	__aligned(16);
 
-asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs)
+void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far)
 {
 	unsigned long tsk_stk = (unsigned long)current->stack;
 	unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr);
 	unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
-	unsigned int esr = read_sysreg(esr_el1);
-	unsigned long far = read_sysreg(far_el1);
-
-	arm64_enter_nmi(regs);
 
 	console_verbose();
 	pr_emerg("Insufficient stack space to handle exception!");
@@ -870,15 +939,11 @@
 	}
 }
 
-asmlinkage void noinstr do_serror(struct pt_regs *regs, unsigned int esr)
+void do_serror(struct pt_regs *regs, unsigned int esr)
 {
-	arm64_enter_nmi(regs);
-
 	/* non-RAS errors are not containable */
 	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
 		arm64_serror_panic(regs, esr);
-
-	arm64_exit_nmi(regs);
 }
 
 /* GENERIC_BUG traps */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 1cb39c0..dc2bc55 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -692,6 +692,15 @@
 	}
 }
 
+static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
+{
+	if (likely(!vcpu_mode_is_32bit(vcpu)))
+		return false;
+
+	return !system_supports_32bit_el0() ||
+		static_branch_unlikely(&arm64_mismatched_32bit_el0);
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -875,7 +884,7 @@
 		 * with the asymmetric AArch32 case), return to userspace with
 		 * a fatal error.
 		 */
-		if (!system_supports_32bit_el0() && vcpu_mode_is_32bit(vcpu)) {
+		if (vcpu_mode_is_bad_32bit(vcpu)) {
 			/*
 			 * As we have caught the guest red-handed, decide that
 			 * it isn't fit for purpose anymore by making the vcpu
@@ -1064,7 +1073,7 @@
 		if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
 			stage2_unmap_vm(vcpu->kvm);
 		else
-			__flush_icache_all();
+			icache_inval_all_pou();
 	}
 
 	vcpu_reset_hcr(vcpu);
diff --git a/arch/arm64/kvm/hyp/nvhe/cache.S b/arch/arm64/kvm/hyp/nvhe/cache.S
index 36cef69..958734f 100644
--- a/arch/arm64/kvm/hyp/nvhe/cache.S
+++ b/arch/arm64/kvm/hyp/nvhe/cache.S
@@ -7,7 +7,7 @@
 #include <asm/assembler.h>
 #include <asm/alternative.h>
 
-SYM_FUNC_START_PI(__flush_dcache_area)
+SYM_FUNC_START_PI(dcache_clean_inval_poc)
 	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-SYM_FUNC_END_PI(__flush_dcache_area)
+SYM_FUNC_END_PI(dcache_clean_inval_poc)
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 7488f53..8143ebd 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -134,7 +134,8 @@
 	for (i = 0; i < hyp_nr_cpus; i++) {
 		params = per_cpu_ptr(&kvm_init_params, i);
 		params->pgd_pa = __hyp_pa(pkvm_pgtable.pgd);
-		__flush_dcache_area(params, sizeof(*params));
+		dcache_clean_inval_poc((unsigned long)params,
+				    (unsigned long)params + sizeof(*params));
 	}
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 83dc3b2..38ed0f6 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -104,7 +104,7 @@
 	 * you should be running with VHE enabled.
 	 */
 	if (icache_is_vpipt())
-		__flush_icache_all();
+		icache_inval_all_pou();
 
 	__tlb_switch_to_host(&cxt);
 }
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index c37c1dc..e9ad7fb 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -839,8 +839,11 @@
 	stage2_put_pte(ptep, mmu, addr, level, mm_ops);
 
 	if (need_flush) {
-		__flush_dcache_area(kvm_pte_follow(pte, mm_ops),
-				    kvm_granule_size(level));
+		kvm_pte_t *pte_follow = kvm_pte_follow(pte, mm_ops);
+
+		dcache_clean_inval_poc((unsigned long)pte_follow,
+				    (unsigned long)pte_follow +
+					    kvm_granule_size(level));
 	}
 
 	if (childp)
@@ -988,11 +991,15 @@
 	struct kvm_pgtable *pgt = arg;
 	struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;
 	kvm_pte_t pte = *ptep;
+	kvm_pte_t *pte_follow;
 
 	if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pgt, pte))
 		return 0;
 
-	__flush_dcache_area(kvm_pte_follow(pte, mm_ops), kvm_granule_size(level));
+	pte_follow = kvm_pte_follow(pte, mm_ops);
+	dcache_clean_inval_poc((unsigned long)pte_follow,
+			    (unsigned long)pte_follow +
+				    kvm_granule_size(level));
 	return 0;
 }
 
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index d31e116..6dd56a4 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   copy_to_user.o copy_in_user.o copy_page.o		\
-		   clear_page.o csum.o memchr.o memcpy.o memmove.o	\
+		   clear_page.o csum.o insn.o memchr.o memcpy.o		\
 		   memset.o memcmp.o strcmp.o strncmp.o strlen.o	\
 		   strnlen.o strchr.o strrchr.o tishift.o
 
@@ -18,3 +18,5 @@
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 
 obj-$(CONFIG_ARM64_MTE) += mte.o
+
+obj-$(CONFIG_KASAN_SW_TAGS) += kasan_sw_tags.o
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index af9afcb..a7efb2a 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -1,12 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Based on arch/arm/lib/clear_user.S
- *
- * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2021 Arm Ltd.
  */
-#include <linux/linkage.h>
 
-#include <asm/asm-uaccess.h>
+#include <linux/linkage.h>
 #include <asm/assembler.h>
 
 	.text
@@ -19,25 +16,33 @@
  *
  * Alignment fixed up by hardware.
  */
+
+	.p2align 4
+	// Alignment is for the loop, but since the prologue (including BTI)
+	// is also 16 bytes we can keep any padding outside the function
 SYM_FUNC_START(__arch_clear_user)
-	mov	x2, x1			// save the size for fixup return
+	add	x2, x0, x1
 	subs	x1, x1, #8
 	b.mi	2f
 1:
-user_ldst 9f, sttr, xzr, x0, 8
+USER(9f, sttr	xzr, [x0])
+	add	x0, x0, #8
 	subs	x1, x1, #8
-	b.pl	1b
-2:	adds	x1, x1, #4
-	b.mi	3f
-user_ldst 9f, sttr, wzr, x0, 4
-	sub	x1, x1, #4
-3:	adds	x1, x1, #2
-	b.mi	4f
-user_ldst 9f, sttrh, wzr, x0, 2
-	sub	x1, x1, #2
-4:	adds	x1, x1, #1
-	b.mi	5f
-user_ldst 9f, sttrb, wzr, x0, 0
+	b.hi	1b
+USER(9f, sttr	xzr, [x2, #-8])
+	mov	x0, #0
+	ret
+
+2:	tbz	x1, #2, 3f
+USER(9f, sttr	wzr, [x0])
+USER(8f, sttr	wzr, [x2, #-4])
+	mov	x0, #0
+	ret
+
+3:	tbz	x1, #1, 4f
+USER(9f, sttrh	wzr, [x0])
+4:	tbz	x1, #0, 5f
+USER(7f, sttrb	wzr, [x2, #-1])
 5:	mov	x0, #0
 	ret
 SYM_FUNC_END(__arch_clear_user)
@@ -45,6 +50,8 @@
 
 	.section .fixup,"ax"
 	.align	2
-9:	mov	x0, x2			// return the original size
+7:	sub	x0, x2, #5	// Adjust for faulting on the final byte...
+8:	add	x0, x0, #4	// ...or the second word of the 4-7 byte case
+9:	sub	x0, x2, x0
 	ret
 	.previous
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/lib/insn.c
similarity index 86%
rename from arch/arm64/kernel/insn.c
rename to arch/arm64/lib/insn.c
index 6c0de2f..b506a4b 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/lib/insn.c
@@ -7,21 +7,14 @@
  */
 #include <linux/bitops.h>
 #include <linux/bug.h>
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/spinlock.h>
-#include <linux/stop_machine.h>
+#include <linux/printk.h>
+#include <linux/sizes.h>
 #include <linux/types.h>
-#include <linux/uaccess.h>
 
-#include <asm/cacheflush.h>
 #include <asm/debug-monitors.h>
-#include <asm/fixmap.h>
+#include <asm/errno.h>
 #include <asm/insn.h>
 #include <asm/kprobes.h>
-#include <asm/sections.h>
 
 #define AARCH64_INSN_SF_BIT	BIT(31)
 #define AARCH64_INSN_N_BIT	BIT(22)
@@ -30,7 +23,7 @@
 static const int aarch64_insn_encoding_class[] = {
 	AARCH64_INSN_CLS_UNKNOWN,
 	AARCH64_INSN_CLS_UNKNOWN,
-	AARCH64_INSN_CLS_UNKNOWN,
+	AARCH64_INSN_CLS_SVE,
 	AARCH64_INSN_CLS_UNKNOWN,
 	AARCH64_INSN_CLS_LDST,
 	AARCH64_INSN_CLS_DP_REG,
@@ -83,81 +76,6 @@
 		aarch64_insn_is_bcond(insn));
 }
 
-static DEFINE_RAW_SPINLOCK(patch_lock);
-
-static bool is_exit_text(unsigned long addr)
-{
-	/* discarded with init text/data */
-	return system_state < SYSTEM_RUNNING &&
-		addr >= (unsigned long)__exittext_begin &&
-		addr < (unsigned long)__exittext_end;
-}
-
-static bool is_image_text(unsigned long addr)
-{
-	return core_kernel_text(addr) || is_exit_text(addr);
-}
-
-static void __kprobes *patch_map(void *addr, int fixmap)
-{
-	unsigned long uintaddr = (uintptr_t) addr;
-	bool image = is_image_text(uintaddr);
-	struct page *page;
-
-	if (image)
-		page = phys_to_page(__pa_symbol(addr));
-	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
-		page = vmalloc_to_page(addr);
-	else
-		return addr;
-
-	BUG_ON(!page);
-	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
-			(uintaddr & ~PAGE_MASK));
-}
-
-static void __kprobes patch_unmap(int fixmap)
-{
-	clear_fixmap(fixmap);
-}
-/*
- * In ARMv8-A, A64 instructions have a fixed length of 32 bits and are always
- * little-endian.
- */
-int __kprobes aarch64_insn_read(void *addr, u32 *insnp)
-{
-	int ret;
-	__le32 val;
-
-	ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE);
-	if (!ret)
-		*insnp = le32_to_cpu(val);
-
-	return ret;
-}
-
-static int __kprobes __aarch64_insn_write(void *addr, __le32 insn)
-{
-	void *waddr = addr;
-	unsigned long flags = 0;
-	int ret;
-
-	raw_spin_lock_irqsave(&patch_lock, flags);
-	waddr = patch_map(addr, FIX_TEXT_POKE0);
-
-	ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE);
-
-	patch_unmap(FIX_TEXT_POKE0);
-	raw_spin_unlock_irqrestore(&patch_lock, flags);
-
-	return ret;
-}
-
-int __kprobes aarch64_insn_write(void *addr, u32 insn)
-{
-	return __aarch64_insn_write(addr, cpu_to_le32(insn));
-}
-
 bool __kprobes aarch64_insn_uses_literal(u32 insn)
 {
 	/* ldr/ldrsw (literal), prfm */
@@ -187,67 +105,6 @@
 		aarch64_insn_is_bcond(insn);
 }
 
-int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
-{
-	u32 *tp = addr;
-	int ret;
-
-	/* A64 instructions must be word aligned */
-	if ((uintptr_t)tp & 0x3)
-		return -EINVAL;
-
-	ret = aarch64_insn_write(tp, insn);
-	if (ret == 0)
-		__flush_icache_range((uintptr_t)tp,
-				     (uintptr_t)tp + AARCH64_INSN_SIZE);
-
-	return ret;
-}
-
-struct aarch64_insn_patch {
-	void		**text_addrs;
-	u32		*new_insns;
-	int		insn_cnt;
-	atomic_t	cpu_count;
-};
-
-static int __kprobes aarch64_insn_patch_text_cb(void *arg)
-{
-	int i, ret = 0;
-	struct aarch64_insn_patch *pp = arg;
-
-	/* The first CPU becomes master */
-	if (atomic_inc_return(&pp->cpu_count) == 1) {
-		for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
-			ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
-							     pp->new_insns[i]);
-		/* Notify other processors with an additional increment. */
-		atomic_inc(&pp->cpu_count);
-	} else {
-		while (atomic_read(&pp->cpu_count) <= num_online_cpus())
-			cpu_relax();
-		isb();
-	}
-
-	return ret;
-}
-
-int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
-{
-	struct aarch64_insn_patch patch = {
-		.text_addrs = addrs,
-		.new_insns = insns,
-		.insn_cnt = cnt,
-		.cpu_count = ATOMIC_INIT(0),
-	};
-
-	if (cnt <= 0)
-		return -EINVAL;
-
-	return stop_machine_cpuslocked(aarch64_insn_patch_text_cb, &patch,
-				       cpu_online_mask);
-}
-
 static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type,
 						u32 *maskp, int *shiftp)
 {
@@ -1432,104 +1289,6 @@
 	return insn & CRM_MASK;
 }
 
-static bool __kprobes __check_eq(unsigned long pstate)
-{
-	return (pstate & PSR_Z_BIT) != 0;
-}
-
-static bool __kprobes __check_ne(unsigned long pstate)
-{
-	return (pstate & PSR_Z_BIT) == 0;
-}
-
-static bool __kprobes __check_cs(unsigned long pstate)
-{
-	return (pstate & PSR_C_BIT) != 0;
-}
-
-static bool __kprobes __check_cc(unsigned long pstate)
-{
-	return (pstate & PSR_C_BIT) == 0;
-}
-
-static bool __kprobes __check_mi(unsigned long pstate)
-{
-	return (pstate & PSR_N_BIT) != 0;
-}
-
-static bool __kprobes __check_pl(unsigned long pstate)
-{
-	return (pstate & PSR_N_BIT) == 0;
-}
-
-static bool __kprobes __check_vs(unsigned long pstate)
-{
-	return (pstate & PSR_V_BIT) != 0;
-}
-
-static bool __kprobes __check_vc(unsigned long pstate)
-{
-	return (pstate & PSR_V_BIT) == 0;
-}
-
-static bool __kprobes __check_hi(unsigned long pstate)
-{
-	pstate &= ~(pstate >> 1);	/* PSR_C_BIT &= ~PSR_Z_BIT */
-	return (pstate & PSR_C_BIT) != 0;
-}
-
-static bool __kprobes __check_ls(unsigned long pstate)
-{
-	pstate &= ~(pstate >> 1);	/* PSR_C_BIT &= ~PSR_Z_BIT */
-	return (pstate & PSR_C_BIT) == 0;
-}
-
-static bool __kprobes __check_ge(unsigned long pstate)
-{
-	pstate ^= (pstate << 3);	/* PSR_N_BIT ^= PSR_V_BIT */
-	return (pstate & PSR_N_BIT) == 0;
-}
-
-static bool __kprobes __check_lt(unsigned long pstate)
-{
-	pstate ^= (pstate << 3);	/* PSR_N_BIT ^= PSR_V_BIT */
-	return (pstate & PSR_N_BIT) != 0;
-}
-
-static bool __kprobes __check_gt(unsigned long pstate)
-{
-	/*PSR_N_BIT ^= PSR_V_BIT */
-	unsigned long temp = pstate ^ (pstate << 3);
-
-	temp |= (pstate << 1);	/*PSR_N_BIT |= PSR_Z_BIT */
-	return (temp & PSR_N_BIT) == 0;
-}
-
-static bool __kprobes __check_le(unsigned long pstate)
-{
-	/*PSR_N_BIT ^= PSR_V_BIT */
-	unsigned long temp = pstate ^ (pstate << 3);
-
-	temp |= (pstate << 1);	/*PSR_N_BIT |= PSR_Z_BIT */
-	return (temp & PSR_N_BIT) != 0;
-}
-
-static bool __kprobes __check_al(unsigned long pstate)
-{
-	return true;
-}
-
-/*
- * Note that the ARMv8 ARM calls condition code 0b1111 "nv", but states that
- * it behaves identically to 0b1110 ("al").
- */
-pstate_check_t * const aarch32_opcode_cond_checks[16] = {
-	__check_eq, __check_ne, __check_cs, __check_cc,
-	__check_mi, __check_pl, __check_vs, __check_vc,
-	__check_hi, __check_ls, __check_ge, __check_lt,
-	__check_gt, __check_le, __check_al, __check_al
-};
-
 static bool range_of_ones(u64 val)
 {
 	/* Doesn't handle full ones or full zeroes */
diff --git a/arch/arm64/lib/kasan_sw_tags.S b/arch/arm64/lib/kasan_sw_tags.S
new file mode 100644
index 0000000..5b04464
--- /dev/null
+++ b/arch/arm64/lib/kasan_sw_tags.S
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Google LLC
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Report a tag mismatch detected by tag-based KASAN.
+ *
+ * A compiler-generated thunk calls this with a non-AAPCS calling
+ * convention. Upon entry to this function, registers are as follows:
+ *
+ * x0:         fault address (see below for restore)
+ * x1:         fault description (see below for restore)
+ * x2 to x15:  callee-saved
+ * x16 to x17: safe to clobber
+ * x18 to x30: callee-saved
+ * sp:         pre-decremented by 256 bytes (see below for restore)
+ *
+ * The caller has decremented the SP by 256 bytes, and created a
+ * structure on the stack as follows:
+ *
+ * sp + 0..15:    x0 and x1 to be restored
+ * sp + 16..231:  free for use
+ * sp + 232..247: x29 and x30 (same as in GPRs)
+ * sp + 248..255: free for use
+ *
+ * Note that this is not a struct pt_regs.
+ *
+ * To call a regular AAPCS function we must save x2 to x15 (which we can
+ * store in the gaps), and create a frame record (for which we can use
+ * x29 and x30 spilled by the caller as those match the GPRs).
+ *
+ * The caller expects x0 and x1 to be restored from the structure, and
+ * for the structure to be removed from the stack (i.e. the SP must be
+ * incremented by 256 prior to return).
+ */
+SYM_CODE_START(__hwasan_tag_mismatch)
+#ifdef BTI_C
+	BTI_C
+#endif
+	add	x29, sp, #232
+	stp	x2, x3, [sp, #8 * 2]
+	stp	x4, x5, [sp, #8 * 4]
+	stp	x6, x7, [sp, #8 * 6]
+	stp	x8, x9, [sp, #8 * 8]
+	stp	x10, x11, [sp, #8 * 10]
+	stp	x12, x13, [sp, #8 * 12]
+	stp	x14, x15, [sp, #8 * 14]
+#ifndef CONFIG_SHADOW_CALL_STACK
+	str	x18, [sp, #8 * 18]
+#endif
+
+	mov	x2, x30
+	bl	kasan_tag_mismatch
+
+	ldp	x0, x1, [sp]
+	ldp	x2, x3, [sp, #8 * 2]
+	ldp	x4, x5, [sp, #8 * 4]
+	ldp	x6, x7, [sp, #8 * 6]
+	ldp	x8, x9, [sp, #8 * 8]
+	ldp	x10, x11, [sp, #8 * 10]
+	ldp	x12, x13, [sp, #8 * 12]
+	ldp	x14, x15, [sp, #8 * 14]
+#ifndef CONFIG_SHADOW_CALL_STACK
+	ldr	x18, [sp, #8 * 18]
+#endif
+	ldp	x29, x30, [sp, #8 * 29]
+
+	/* remove the structure from the stack */
+	add	sp, sp, #256
+	ret
+SYM_CODE_END(__hwasan_tag_mismatch)
+EXPORT_SYMBOL(__hwasan_tag_mismatch)
diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S
index edf6b97..7c2276f 100644
--- a/arch/arm64/lib/memchr.S
+++ b/arch/arm64/lib/memchr.S
@@ -1,9 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Based on arch/arm/lib/memchr.S
- *
- * Copyright (C) 1995-2000 Russell King
- * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2021 Arm Ltd.
  */
 
 #include <linux/linkage.h>
@@ -19,16 +16,60 @@
  * Returns:
  *	x0 - address of first occurrence of 'c' or 0
  */
+
+#define L(label) .L ## label
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+
+#define srcin		x0
+#define chrin		w1
+#define cntin		x2
+
+#define result		x0
+
+#define wordcnt		x3
+#define rep01		x4
+#define repchr		x5
+#define cur_word	x6
+#define cur_byte	w6
+#define tmp		x7
+#define tmp2		x8
+
+	.p2align 4
+	nop
 SYM_FUNC_START_WEAK_PI(memchr)
-	and	w1, w1, #0xff
-1:	subs	x2, x2, #1
-	b.mi	2f
-	ldrb	w3, [x0], #1
-	cmp	w3, w1
-	b.ne	1b
-	sub	x0, x0, #1
+	and	chrin, chrin, #0xff
+	lsr	wordcnt, cntin, #3
+	cbz	wordcnt, L(byte_loop)
+	mov	rep01, #REP8_01
+	mul	repchr, x1, rep01
+	and	cntin, cntin, #7
+L(word_loop):
+	ldr	cur_word, [srcin], #8
+	sub	wordcnt, wordcnt, #1
+	eor	cur_word, cur_word, repchr
+	sub	tmp, cur_word, rep01
+	orr	tmp2, cur_word, #REP8_7f
+	bics	tmp, tmp, tmp2
+	b.ne	L(found_word)
+	cbnz	wordcnt, L(word_loop)
+L(byte_loop):
+	cbz	cntin, L(not_found)
+	ldrb	cur_byte, [srcin], #1
+	sub	cntin, cntin, #1
+	cmp	cur_byte, chrin
+	b.ne	L(byte_loop)
+	sub	srcin, srcin, #1
 	ret
-2:	mov	x0, #0
+L(found_word):
+CPU_LE(	rev	tmp, tmp)
+	clz	tmp, tmp
+	sub	tmp, tmp, #64
+	add	result, srcin, tmp, asr #3
+	ret
+L(not_found):
+	mov	result, #0
 	ret
 SYM_FUNC_END_PI(memchr)
 EXPORT_SYMBOL_NOKASAN(memchr)
diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S
index c0671e7..7d95638 100644
--- a/arch/arm64/lib/memcmp.S
+++ b/arch/arm64/lib/memcmp.S
@@ -1,247 +1,139 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
+ * Copyright (c) 2013-2021, Arm Limited.
  *
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/e823e3abf5f89ecb/string/aarch64/memcmp.S
  */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-/*
-* compare memory areas(when two memory areas' offset are different,
-* alignment handled by the hardware)
-*
-* Parameters:
-*  x0 - const memory area 1 pointer
-*  x1 - const memory area 2 pointer
-*  x2 - the maximal compare byte length
-* Returns:
-*  x0 - a compare result, maybe less than, equal to, or greater than ZERO
-*/
+/* Assumptions:
+ *
+ * ARMv8-a, AArch64, unaligned accesses.
+ */
+
+#define L(label) .L ## label
 
 /* Parameters and result.  */
-src1		.req	x0
-src2		.req	x1
-limit		.req	x2
-result		.req	x0
+#define src1		x0
+#define src2		x1
+#define limit		x2
+#define result		w0
 
 /* Internal variables.  */
-data1		.req	x3
-data1w		.req	w3
-data2		.req	x4
-data2w		.req	w4
-has_nul		.req	x5
-diff		.req	x6
-endloop		.req	x7
-tmp1		.req	x8
-tmp2		.req	x9
-tmp3		.req	x10
-pos		.req	x11
-limit_wd	.req	x12
-mask		.req	x13
+#define data1		x3
+#define data1w		w3
+#define data1h		x4
+#define data2		x5
+#define data2w		w5
+#define data2h		x6
+#define tmp1		x7
+#define tmp2		x8
 
 SYM_FUNC_START_WEAK_PI(memcmp)
-	cbz	limit, .Lret0
-	eor	tmp1, src1, src2
-	tst	tmp1, #7
-	b.ne	.Lmisaligned8
-	ands	tmp1, src1, #7
-	b.ne	.Lmutual_align
-	sub	limit_wd, limit, #1 /* limit != 0, so no underflow.  */
-	lsr	limit_wd, limit_wd, #3 /* Convert to Dwords.  */
-	/*
-	* The input source addresses are at alignment boundary.
-	* Directly compare eight bytes each time.
-	*/
-.Lloop_aligned:
-	ldr	data1, [src1], #8
-	ldr	data2, [src2], #8
-.Lstart_realigned:
-	subs	limit_wd, limit_wd, #1
-	eor	diff, data1, data2	/* Non-zero if differences found.  */
-	csinv	endloop, diff, xzr, cs	/* Last Dword or differences.  */
-	cbz	endloop, .Lloop_aligned
+	subs	limit, limit, 8
+	b.lo	L(less8)
 
-	/* Not reached the limit, must have found a diff.  */
-	tbz	limit_wd, #63, .Lnot_limit
+	ldr	data1, [src1], 8
+	ldr	data2, [src2], 8
+	cmp	data1, data2
+	b.ne	L(return)
 
-	/* Limit % 8 == 0 => the diff is in the last 8 bytes. */
-	ands	limit, limit, #7
-	b.eq	.Lnot_limit
-	/*
-	* The remained bytes less than 8. It is needed to extract valid data
-	* from last eight bytes of the intended memory range.
-	*/
-	lsl	limit, limit, #3	/* bytes-> bits.  */
-	mov	mask, #~0
-CPU_BE( lsr	mask, mask, limit )
-CPU_LE( lsl	mask, mask, limit )
-	bic	data1, data1, mask
-	bic	data2, data2, mask
+	subs	limit, limit, 8
+	b.gt	L(more16)
 
-	orr	diff, diff, mask
-	b	.Lnot_limit
+	ldr	data1, [src1, limit]
+	ldr	data2, [src2, limit]
+	b	L(return)
 
-.Lmutual_align:
-	/*
-	* Sources are mutually aligned, but are not currently at an
-	* alignment boundary. Round down the addresses and then mask off
-	* the bytes that precede the start point.
-	*/
-	bic	src1, src1, #7
-	bic	src2, src2, #7
-	ldr	data1, [src1], #8
-	ldr	data2, [src2], #8
-	/*
-	* We can not add limit with alignment offset(tmp1) here. Since the
-	* addition probably make the limit overflown.
-	*/
-	sub	limit_wd, limit, #1/*limit != 0, so no underflow.*/
-	and	tmp3, limit_wd, #7
-	lsr	limit_wd, limit_wd, #3
-	add	tmp3, tmp3, tmp1
-	add	limit_wd, limit_wd, tmp3, lsr #3
-	add	limit, limit, tmp1/* Adjust the limit for the extra.  */
+L(more16):
+	ldr	data1, [src1], 8
+	ldr	data2, [src2], 8
+	cmp	data1, data2
+	bne	L(return)
 
-	lsl	tmp1, tmp1, #3/* Bytes beyond alignment -> bits.*/
-	neg	tmp1, tmp1/* Bits to alignment -64.  */
-	mov	tmp2, #~0
-	/*mask off the non-intended bytes before the start address.*/
-CPU_BE( lsl	tmp2, tmp2, tmp1 )/*Big-endian.Early bytes are at MSB*/
-	/* Little-endian.  Early bytes are at LSB.  */
-CPU_LE( lsr	tmp2, tmp2, tmp1 )
+	/* Jump directly to comparing the last 16 bytes for 32 byte (or less)
+	   strings.  */
+	subs	limit, limit, 16
+	b.ls	L(last_bytes)
 
-	orr	data1, data1, tmp2
-	orr	data2, data2, tmp2
-	b	.Lstart_realigned
+	/* We overlap loads between 0-32 bytes at either side of SRC1 when we
+	   try to align, so limit it only to strings larger than 128 bytes.  */
+	cmp	limit, 96
+	b.ls	L(loop16)
 
-	/*src1 and src2 have different alignment offset.*/
-.Lmisaligned8:
-	cmp	limit, #8
-	b.lo	.Ltiny8proc /*limit < 8: compare byte by byte*/
+	/* Align src1 and adjust src2 with bytes not yet done.  */
+	and	tmp1, src1, 15
+	add	limit, limit, tmp1
+	sub	src1, src1, tmp1
+	sub	src2, src2, tmp1
 
-	and	tmp1, src1, #7
-	neg	tmp1, tmp1
-	add	tmp1, tmp1, #8/*valid length in the first 8 bytes of src1*/
-	and	tmp2, src2, #7
-	neg	tmp2, tmp2
-	add	tmp2, tmp2, #8/*valid length in the first 8 bytes of src2*/
-	subs	tmp3, tmp1, tmp2
-	csel	pos, tmp1, tmp2, hi /*Choose the maximum.*/
+	/* Loop performing 16 bytes per iteration using aligned src1.
+	   Limit is pre-decremented by 16 and must be larger than zero.
+	   Exit if <= 16 bytes left to do or if the data is not equal.  */
+	.p2align 4
+L(loop16):
+	ldp	data1, data1h, [src1], 16
+	ldp	data2, data2h, [src2], 16
+	subs	limit, limit, 16
+	ccmp	data1, data2, 0, hi
+	ccmp	data1h, data2h, 0, eq
+	b.eq	L(loop16)
 
-	sub	limit, limit, pos
-	/*compare the proceeding bytes in the first 8 byte segment.*/
-.Ltinycmp:
-	ldrb	data1w, [src1], #1
-	ldrb	data2w, [src2], #1
-	subs	pos, pos, #1
-	ccmp	data1w, data2w, #0, ne  /* NZCV = 0b0000.  */
-	b.eq	.Ltinycmp
-	cbnz	pos, 1f /*diff occurred before the last byte.*/
+	cmp	data1, data2
+	bne	L(return)
+	mov	data1, data1h
+	mov	data2, data2h
+	cmp	data1, data2
+	bne	L(return)
+
+	/* Compare last 1-16 bytes using unaligned access.  */
+L(last_bytes):
+	add	src1, src1, limit
+	add	src2, src2, limit
+	ldp	data1, data1h, [src1]
+	ldp	data2, data2h, [src2]
+	cmp	data1, data2
+	bne	L(return)
+	mov	data1, data1h
+	mov	data2, data2h
+	cmp	data1, data2
+
+	/* Compare data bytes and set return value to 0, -1 or 1.  */
+L(return):
+#ifndef __AARCH64EB__
+	rev	data1, data1
+	rev	data2, data2
+#endif
+	cmp	data1, data2
+L(ret_eq):
+	cset	result, ne
+	cneg	result, result, lo
+	ret
+
+	.p2align 4
+	/* Compare up to 8 bytes.  Limit is [-8..-1].  */
+L(less8):
+	adds	limit, limit, 4
+	b.lo	L(less4)
+	ldr	data1w, [src1], 4
+	ldr	data2w, [src2], 4
 	cmp	data1w, data2w
-	b.eq	.Lstart_align
-1:
-	sub	result, data1, data2
+	b.ne	L(return)
+	sub	limit, limit, 4
+L(less4):
+	adds	limit, limit, 4
+	beq	L(ret_eq)
+L(byte_loop):
+	ldrb	data1w, [src1], 1
+	ldrb	data2w, [src2], 1
+	subs	limit, limit, 1
+	ccmp	data1w, data2w, 0, ne	/* NZCV = 0b0000.  */
+	b.eq	L(byte_loop)
+	sub	result, data1w, data2w
 	ret
 
-.Lstart_align:
-	lsr	limit_wd, limit, #3
-	cbz	limit_wd, .Lremain8
-
-	ands	xzr, src1, #7
-	b.eq	.Lrecal_offset
-	/*process more leading bytes to make src1 aligned...*/
-	add	src1, src1, tmp3 /*backwards src1 to alignment boundary*/
-	add	src2, src2, tmp3
-	sub	limit, limit, tmp3
-	lsr	limit_wd, limit, #3
-	cbz	limit_wd, .Lremain8
-	/*load 8 bytes from aligned SRC1..*/
-	ldr	data1, [src1], #8
-	ldr	data2, [src2], #8
-
-	subs	limit_wd, limit_wd, #1
-	eor	diff, data1, data2  /*Non-zero if differences found.*/
-	csinv	endloop, diff, xzr, ne
-	cbnz	endloop, .Lunequal_proc
-	/*How far is the current SRC2 from the alignment boundary...*/
-	and	tmp3, tmp3, #7
-
-.Lrecal_offset:/*src1 is aligned now..*/
-	neg	pos, tmp3
-.Lloopcmp_proc:
-	/*
-	* Divide the eight bytes into two parts. First,backwards the src2
-	* to an alignment boundary,load eight bytes and compare from
-	* the SRC2 alignment boundary. If all 8 bytes are equal,then start
-	* the second part's comparison. Otherwise finish the comparison.
-	* This special handle can garantee all the accesses are in the
-	* thread/task space in avoid to overrange access.
-	*/
-	ldr	data1, [src1,pos]
-	ldr	data2, [src2,pos]
-	eor	diff, data1, data2  /* Non-zero if differences found.  */
-	cbnz	diff, .Lnot_limit
-
-	/*The second part process*/
-	ldr	data1, [src1], #8
-	ldr	data2, [src2], #8
-	eor	diff, data1, data2  /* Non-zero if differences found.  */
-	subs	limit_wd, limit_wd, #1
-	csinv	endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
-	cbz	endloop, .Lloopcmp_proc
-.Lunequal_proc:
-	cbz	diff, .Lremain8
-
-/* There is difference occurred in the latest comparison. */
-.Lnot_limit:
-/*
-* For little endian,reverse the low significant equal bits into MSB,then
-* following CLZ can find how many equal bits exist.
-*/
-CPU_LE( rev	diff, diff )
-CPU_LE( rev	data1, data1 )
-CPU_LE( rev	data2, data2 )
-
-	/*
-	* The MS-non-zero bit of DIFF marks either the first bit
-	* that is different, or the end of the significant data.
-	* Shifting left now will bring the critical information into the
-	* top bits.
-	*/
-	clz	pos, diff
-	lsl	data1, data1, pos
-	lsl	data2, data2, pos
-	/*
-	* We need to zero-extend (char is unsigned) the value and then
-	* perform a signed subtraction.
-	*/
-	lsr	data1, data1, #56
-	sub	result, data1, data2, lsr #56
-	ret
-
-.Lremain8:
-	/* Limit % 8 == 0 =>. all data are equal.*/
-	ands	limit, limit, #7
-	b.eq	.Lret0
-
-.Ltiny8proc:
-	ldrb	data1w, [src1], #1
-	ldrb	data2w, [src2], #1
-	subs	limit, limit, #1
-
-	ccmp	data1w, data2w, #0, ne  /* NZCV = 0b0000. */
-	b.eq	.Ltiny8proc
-	sub	result, data1, data2
-	ret
-.Lret0:
-	mov	result, #0
-	ret
 SYM_FUNC_END_PI(memcmp)
 EXPORT_SYMBOL_NOKASAN(memcmp)
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index dc8d2a2..b82fd64 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -1,66 +1,252 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
+ * Copyright (c) 2012-2021, Arm Limited.
  *
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/afd6244a1f8d9229/string/aarch64/memcpy.S
  */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <asm/cache.h>
 
-/*
- * Copy a buffer from src to dest (alignment handled by the hardware)
+/* Assumptions:
  *
- * Parameters:
- *	x0 - dest
- *	x1 - src
- *	x2 - n
- * Returns:
- *	x0 - dest
+ * ARMv8-a, AArch64, unaligned accesses.
+ *
  */
-	.macro ldrb1 reg, ptr, val
-	ldrb  \reg, [\ptr], \val
-	.endm
 
-	.macro strb1 reg, ptr, val
-	strb \reg, [\ptr], \val
-	.endm
+#define L(label) .L ## label
 
-	.macro ldrh1 reg, ptr, val
-	ldrh  \reg, [\ptr], \val
-	.endm
+#define dstin	x0
+#define src	x1
+#define count	x2
+#define dst	x3
+#define srcend	x4
+#define dstend	x5
+#define A_l	x6
+#define A_lw	w6
+#define A_h	x7
+#define B_l	x8
+#define B_lw	w8
+#define B_h	x9
+#define C_l	x10
+#define C_lw	w10
+#define C_h	x11
+#define D_l	x12
+#define D_h	x13
+#define E_l	x14
+#define E_h	x15
+#define F_l	x16
+#define F_h	x17
+#define G_l	count
+#define G_h	dst
+#define H_l	src
+#define H_h	srcend
+#define tmp1	x14
 
-	.macro strh1 reg, ptr, val
-	strh \reg, [\ptr], \val
-	.endm
+/* This implementation handles overlaps and supports both memcpy and memmove
+   from a single entry point.  It uses unaligned accesses and branchless
+   sequences to keep the code small, simple and improve performance.
 
-	.macro ldr1 reg, ptr, val
-	ldr \reg, [\ptr], \val
-	.endm
+   Copies are split into 3 main cases: small copies of up to 32 bytes, medium
+   copies of up to 128 bytes, and large copies.  The overhead of the overlap
+   check is negligible since it is only required for large copies.
 
-	.macro str1 reg, ptr, val
-	str \reg, [\ptr], \val
-	.endm
+   Large copies use a software pipelined loop processing 64 bytes per iteration.
+   The destination pointer is 16-byte aligned to minimize unaligned accesses.
+   The loop tail is handled by always copying 64 bytes from the end.
+*/
 
-	.macro ldp1 reg1, reg2, ptr, val
-	ldp \reg1, \reg2, [\ptr], \val
-	.endm
-
-	.macro stp1 reg1, reg2, ptr, val
-	stp \reg1, \reg2, [\ptr], \val
-	.endm
-
+SYM_FUNC_START_ALIAS(__memmove)
+SYM_FUNC_START_WEAK_ALIAS_PI(memmove)
 SYM_FUNC_START_ALIAS(__memcpy)
 SYM_FUNC_START_WEAK_PI(memcpy)
-#include "copy_template.S"
+	add	srcend, src, count
+	add	dstend, dstin, count
+	cmp	count, 128
+	b.hi	L(copy_long)
+	cmp	count, 32
+	b.hi	L(copy32_128)
+
+	/* Small copies: 0..32 bytes.  */
+	cmp	count, 16
+	b.lo	L(copy16)
+	ldp	A_l, A_h, [src]
+	ldp	D_l, D_h, [srcend, -16]
+	stp	A_l, A_h, [dstin]
+	stp	D_l, D_h, [dstend, -16]
 	ret
+
+	/* Copy 8-15 bytes.  */
+L(copy16):
+	tbz	count, 3, L(copy8)
+	ldr	A_l, [src]
+	ldr	A_h, [srcend, -8]
+	str	A_l, [dstin]
+	str	A_h, [dstend, -8]
+	ret
+
+	.p2align 3
+	/* Copy 4-7 bytes.  */
+L(copy8):
+	tbz	count, 2, L(copy4)
+	ldr	A_lw, [src]
+	ldr	B_lw, [srcend, -4]
+	str	A_lw, [dstin]
+	str	B_lw, [dstend, -4]
+	ret
+
+	/* Copy 0..3 bytes using a branchless sequence.  */
+L(copy4):
+	cbz	count, L(copy0)
+	lsr	tmp1, count, 1
+	ldrb	A_lw, [src]
+	ldrb	C_lw, [srcend, -1]
+	ldrb	B_lw, [src, tmp1]
+	strb	A_lw, [dstin]
+	strb	B_lw, [dstin, tmp1]
+	strb	C_lw, [dstend, -1]
+L(copy0):
+	ret
+
+	.p2align 4
+	/* Medium copies: 33..128 bytes.  */
+L(copy32_128):
+	ldp	A_l, A_h, [src]
+	ldp	B_l, B_h, [src, 16]
+	ldp	C_l, C_h, [srcend, -32]
+	ldp	D_l, D_h, [srcend, -16]
+	cmp	count, 64
+	b.hi	L(copy128)
+	stp	A_l, A_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
+	ret
+
+	.p2align 4
+	/* Copy 65..128 bytes.  */
+L(copy128):
+	ldp	E_l, E_h, [src, 32]
+	ldp	F_l, F_h, [src, 48]
+	cmp	count, 96
+	b.ls	L(copy96)
+	ldp	G_l, G_h, [srcend, -64]
+	ldp	H_l, H_h, [srcend, -48]
+	stp	G_l, G_h, [dstend, -64]
+	stp	H_l, H_h, [dstend, -48]
+L(copy96):
+	stp	A_l, A_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	E_l, E_h, [dstin, 32]
+	stp	F_l, F_h, [dstin, 48]
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
+	ret
+
+	.p2align 4
+	/* Copy more than 128 bytes.  */
+L(copy_long):
+	/* Use backwards copy if there is an overlap.  */
+	sub	tmp1, dstin, src
+	cbz	tmp1, L(copy0)
+	cmp	tmp1, count
+	b.lo	L(copy_long_backwards)
+
+	/* Copy 16 bytes and then align dst to 16-byte alignment.  */
+
+	ldp	D_l, D_h, [src]
+	and	tmp1, dstin, 15
+	bic	dst, dstin, 15
+	sub	src, src, tmp1
+	add	count, count, tmp1	/* Count is now 16 too large.  */
+	ldp	A_l, A_h, [src, 16]
+	stp	D_l, D_h, [dstin]
+	ldp	B_l, B_h, [src, 32]
+	ldp	C_l, C_h, [src, 48]
+	ldp	D_l, D_h, [src, 64]!
+	subs	count, count, 128 + 16	/* Test and readjust count.  */
+	b.ls	L(copy64_from_end)
+
+L(loop64):
+	stp	A_l, A_h, [dst, 16]
+	ldp	A_l, A_h, [src, 16]
+	stp	B_l, B_h, [dst, 32]
+	ldp	B_l, B_h, [src, 32]
+	stp	C_l, C_h, [dst, 48]
+	ldp	C_l, C_h, [src, 48]
+	stp	D_l, D_h, [dst, 64]!
+	ldp	D_l, D_h, [src, 64]!
+	subs	count, count, 64
+	b.hi	L(loop64)
+
+	/* Write the last iteration and copy 64 bytes from the end.  */
+L(copy64_from_end):
+	ldp	E_l, E_h, [srcend, -64]
+	stp	A_l, A_h, [dst, 16]
+	ldp	A_l, A_h, [srcend, -48]
+	stp	B_l, B_h, [dst, 32]
+	ldp	B_l, B_h, [srcend, -32]
+	stp	C_l, C_h, [dst, 48]
+	ldp	C_l, C_h, [srcend, -16]
+	stp	D_l, D_h, [dst, 64]
+	stp	E_l, E_h, [dstend, -64]
+	stp	A_l, A_h, [dstend, -48]
+	stp	B_l, B_h, [dstend, -32]
+	stp	C_l, C_h, [dstend, -16]
+	ret
+
+	.p2align 4
+
+	/* Large backwards copy for overlapping copies.
+	   Copy 16 bytes and then align dst to 16-byte alignment.  */
+L(copy_long_backwards):
+	ldp	D_l, D_h, [srcend, -16]
+	and	tmp1, dstend, 15
+	sub	srcend, srcend, tmp1
+	sub	count, count, tmp1
+	ldp	A_l, A_h, [srcend, -16]
+	stp	D_l, D_h, [dstend, -16]
+	ldp	B_l, B_h, [srcend, -32]
+	ldp	C_l, C_h, [srcend, -48]
+	ldp	D_l, D_h, [srcend, -64]!
+	sub	dstend, dstend, tmp1
+	subs	count, count, 128
+	b.ls	L(copy64_from_start)
+
+L(loop64_backwards):
+	stp	A_l, A_h, [dstend, -16]
+	ldp	A_l, A_h, [srcend, -16]
+	stp	B_l, B_h, [dstend, -32]
+	ldp	B_l, B_h, [srcend, -32]
+	stp	C_l, C_h, [dstend, -48]
+	ldp	C_l, C_h, [srcend, -48]
+	stp	D_l, D_h, [dstend, -64]!
+	ldp	D_l, D_h, [srcend, -64]!
+	subs	count, count, 64
+	b.hi	L(loop64_backwards)
+
+	/* Write the last iteration and copy 64 bytes from the start.  */
+L(copy64_from_start):
+	ldp	G_l, G_h, [src, 48]
+	stp	A_l, A_h, [dstend, -16]
+	ldp	A_l, A_h, [src, 32]
+	stp	B_l, B_h, [dstend, -32]
+	ldp	B_l, B_h, [src, 16]
+	stp	C_l, C_h, [dstend, -48]
+	ldp	C_l, C_h, [src]
+	stp	D_l, D_h, [dstend, -64]
+	stp	G_l, G_h, [dstin, 48]
+	stp	A_l, A_h, [dstin, 32]
+	stp	B_l, B_h, [dstin, 16]
+	stp	C_l, C_h, [dstin]
+	ret
+
 SYM_FUNC_END_PI(memcpy)
 EXPORT_SYMBOL(memcpy)
 SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(__memcpy)
+SYM_FUNC_END_ALIAS_PI(memmove)
+EXPORT_SYMBOL(memmove)
+SYM_FUNC_END_ALIAS(__memmove)
+EXPORT_SYMBOL(__memmove)
diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S
deleted file mode 100644
index 1035dce..0000000
--- a/arch/arm64/lib/memmove.S
+++ /dev/null
@@ -1,189 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
- *
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/cache.h>
-
-/*
- * Move a buffer from src to test (alignment handled by the hardware).
- * If dest <= src, call memcpy, otherwise copy in reverse order.
- *
- * Parameters:
- *	x0 - dest
- *	x1 - src
- *	x2 - n
- * Returns:
- *	x0 - dest
- */
-dstin	.req	x0
-src	.req	x1
-count	.req	x2
-tmp1	.req	x3
-tmp1w	.req	w3
-tmp2	.req	x4
-tmp2w	.req	w4
-tmp3	.req	x5
-tmp3w	.req	w5
-dst	.req	x6
-
-A_l	.req	x7
-A_h	.req	x8
-B_l	.req	x9
-B_h	.req	x10
-C_l	.req	x11
-C_h	.req	x12
-D_l	.req	x13
-D_h	.req	x14
-
-SYM_FUNC_START_ALIAS(__memmove)
-SYM_FUNC_START_WEAK_PI(memmove)
-	cmp	dstin, src
-	b.lo	__memcpy
-	add	tmp1, src, count
-	cmp	dstin, tmp1
-	b.hs	__memcpy		/* No overlap.  */
-
-	add	dst, dstin, count
-	add	src, src, count
-	cmp	count, #16
-	b.lo	.Ltail15  /*probably non-alignment accesses.*/
-
-	ands	tmp2, src, #15     /* Bytes to reach alignment.  */
-	b.eq	.LSrcAligned
-	sub	count, count, tmp2
-	/*
-	* process the aligned offset length to make the src aligned firstly.
-	* those extra instructions' cost is acceptable. It also make the
-	* coming accesses are based on aligned address.
-	*/
-	tbz	tmp2, #0, 1f
-	ldrb	tmp1w, [src, #-1]!
-	strb	tmp1w, [dst, #-1]!
-1:
-	tbz	tmp2, #1, 2f
-	ldrh	tmp1w, [src, #-2]!
-	strh	tmp1w, [dst, #-2]!
-2:
-	tbz	tmp2, #2, 3f
-	ldr	tmp1w, [src, #-4]!
-	str	tmp1w, [dst, #-4]!
-3:
-	tbz	tmp2, #3, .LSrcAligned
-	ldr	tmp1, [src, #-8]!
-	str	tmp1, [dst, #-8]!
-
-.LSrcAligned:
-	cmp	count, #64
-	b.ge	.Lcpy_over64
-
-	/*
-	* Deal with small copies quickly by dropping straight into the
-	* exit block.
-	*/
-.Ltail63:
-	/*
-	* Copy up to 48 bytes of data. At this point we only need the
-	* bottom 6 bits of count to be accurate.
-	*/
-	ands	tmp1, count, #0x30
-	b.eq	.Ltail15
-	cmp	tmp1w, #0x20
-	b.eq	1f
-	b.lt	2f
-	ldp	A_l, A_h, [src, #-16]!
-	stp	A_l, A_h, [dst, #-16]!
-1:
-	ldp	A_l, A_h, [src, #-16]!
-	stp	A_l, A_h, [dst, #-16]!
-2:
-	ldp	A_l, A_h, [src, #-16]!
-	stp	A_l, A_h, [dst, #-16]!
-
-.Ltail15:
-	tbz	count, #3, 1f
-	ldr	tmp1, [src, #-8]!
-	str	tmp1, [dst, #-8]!
-1:
-	tbz	count, #2, 2f
-	ldr	tmp1w, [src, #-4]!
-	str	tmp1w, [dst, #-4]!
-2:
-	tbz	count, #1, 3f
-	ldrh	tmp1w, [src, #-2]!
-	strh	tmp1w, [dst, #-2]!
-3:
-	tbz	count, #0, .Lexitfunc
-	ldrb	tmp1w, [src, #-1]
-	strb	tmp1w, [dst, #-1]
-
-.Lexitfunc:
-	ret
-
-.Lcpy_over64:
-	subs	count, count, #128
-	b.ge	.Lcpy_body_large
-	/*
-	* Less than 128 bytes to copy, so handle 64 bytes here and then jump
-	* to the tail.
-	*/
-	ldp	A_l, A_h, [src, #-16]
-	stp	A_l, A_h, [dst, #-16]
-	ldp	B_l, B_h, [src, #-32]
-	ldp	C_l, C_h, [src, #-48]
-	stp	B_l, B_h, [dst, #-32]
-	stp	C_l, C_h, [dst, #-48]
-	ldp	D_l, D_h, [src, #-64]!
-	stp	D_l, D_h, [dst, #-64]!
-
-	tst	count, #0x3f
-	b.ne	.Ltail63
-	ret
-
-	/*
-	* Critical loop. Start at a new cache line boundary. Assuming
-	* 64 bytes per line this ensures the entire loop is in one line.
-	*/
-	.p2align	L1_CACHE_SHIFT
-.Lcpy_body_large:
-	/* pre-load 64 bytes data. */
-	ldp	A_l, A_h, [src, #-16]
-	ldp	B_l, B_h, [src, #-32]
-	ldp	C_l, C_h, [src, #-48]
-	ldp	D_l, D_h, [src, #-64]!
-1:
-	/*
-	* interlace the load of next 64 bytes data block with store of the last
-	* loaded 64 bytes data.
-	*/
-	stp	A_l, A_h, [dst, #-16]
-	ldp	A_l, A_h, [src, #-16]
-	stp	B_l, B_h, [dst, #-32]
-	ldp	B_l, B_h, [src, #-32]
-	stp	C_l, C_h, [dst, #-48]
-	ldp	C_l, C_h, [src, #-48]
-	stp	D_l, D_h, [dst, #-64]!
-	ldp	D_l, D_h, [src, #-64]!
-	subs	count, count, #64
-	b.ge	1b
-	stp	A_l, A_h, [dst, #-16]
-	stp	B_l, B_h, [dst, #-32]
-	stp	C_l, C_h, [dst, #-48]
-	stp	D_l, D_h, [dst, #-64]!
-
-	tst	count, #0x3f
-	b.ne	.Ltail63
-	ret
-SYM_FUNC_END_PI(memmove)
-EXPORT_SYMBOL(memmove)
-SYM_FUNC_END_ALIAS(__memmove)
-EXPORT_SYMBOL(__memmove)
diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S
index 351537c..e83643b 100644
--- a/arch/arm64/lib/mte.S
+++ b/arch/arm64/lib/mte.S
@@ -37,6 +37,26 @@
 SYM_FUNC_END(mte_clear_page_tags)
 
 /*
+ * Zero the page and tags at the same time
+ *
+ * Parameters:
+ *	x0 - address to the beginning of the page
+ */
+SYM_FUNC_START(mte_zero_clear_page_tags)
+	mrs	x1, dczid_el0
+	and	w1, w1, #0xf
+	mov	x2, #4
+	lsl	x1, x2, x1
+	and	x0, x0, #(1 << MTE_TAG_SHIFT) - 1	// clear the tag
+
+1:	dc	gzva, x0
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_zero_clear_page_tags)
+
+/*
  * Copy the tags from the source page to the destination one
  *   x0 - address of the destination page
  *   x1 - address of the source page
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
index 4e79566..d7bee21 100644
--- a/arch/arm64/lib/strcmp.S
+++ b/arch/arm64/lib/strcmp.S
@@ -1,84 +1,123 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
+ * Copyright (c) 2012-2021, Arm Limited.
  *
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/afd6244a1f8d9229/string/aarch64/strcmp.S
  */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-/*
- * compare two strings
+/* Assumptions:
  *
- * Parameters:
- *	x0 - const string 1 pointer
- *    x1 - const string 2 pointer
- * Returns:
- * x0 - an integer less than, equal to, or greater than zero
- * if  s1  is  found, respectively, to be less than, to match,
- * or be greater than s2.
+ * ARMv8-a, AArch64
  */
 
+#define L(label) .L ## label
+
 #define REP8_01 0x0101010101010101
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
 /* Parameters and result.  */
-src1		.req	x0
-src2		.req	x1
-result		.req	x0
+#define src1		x0
+#define src2		x1
+#define result		x0
 
 /* Internal variables.  */
-data1		.req	x2
-data1w		.req	w2
-data2		.req	x3
-data2w		.req	w3
-has_nul		.req	x4
-diff		.req	x5
-syndrome	.req	x6
-tmp1		.req	x7
-tmp2		.req	x8
-tmp3		.req	x9
-zeroones	.req	x10
-pos		.req	x11
+#define data1		x2
+#define data1w		w2
+#define data2		x3
+#define data2w		w3
+#define has_nul		x4
+#define diff		x5
+#define syndrome	x6
+#define tmp1		x7
+#define tmp2		x8
+#define tmp3		x9
+#define zeroones	x10
+#define pos		x11
 
+	/* Start of performance-critical section  -- one 64B cache line.  */
+	.align 6
 SYM_FUNC_START_WEAK_PI(strcmp)
 	eor	tmp1, src1, src2
 	mov	zeroones, #REP8_01
 	tst	tmp1, #7
-	b.ne	.Lmisaligned8
+	b.ne	L(misaligned8)
 	ands	tmp1, src1, #7
-	b.ne	.Lmutual_align
-
-	/*
-	* NUL detection works on the principle that (X - 1) & (~X) & 0x80
-	* (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
-	* can be done in parallel across the entire word.
-	*/
-.Lloop_aligned:
+	b.ne	L(mutual_align)
+	/* NUL detection works on the principle that (X - 1) & (~X) & 0x80
+	   (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+	   can be done in parallel across the entire word.  */
+L(loop_aligned):
 	ldr	data1, [src1], #8
 	ldr	data2, [src2], #8
-.Lstart_realigned:
+L(start_realigned):
 	sub	tmp1, data1, zeroones
 	orr	tmp2, data1, #REP8_7f
 	eor	diff, data1, data2	/* Non-zero if differences found.  */
 	bic	has_nul, tmp1, tmp2	/* Non-zero if NUL terminator.  */
 	orr	syndrome, diff, has_nul
-	cbz	syndrome, .Lloop_aligned
-	b	.Lcal_cmpresult
+	cbz	syndrome, L(loop_aligned)
+	/* End of performance-critical section  -- one 64B cache line.  */
 
-.Lmutual_align:
-	/*
-	* Sources are mutually aligned, but are not currently at an
-	* alignment boundary.  Round down the addresses and then mask off
-	* the bytes that preceed the start point.
-	*/
+L(end):
+#ifndef	__AARCH64EB__
+	rev	syndrome, syndrome
+	rev	data1, data1
+	/* The MS-non-zero bit of the syndrome marks either the first bit
+	   that is different, or the top bit of the first zero byte.
+	   Shifting left now will bring the critical information into the
+	   top bits.  */
+	clz	pos, syndrome
+	rev	data2, data2
+	lsl	data1, data1, pos
+	lsl	data2, data2, pos
+	/* But we need to zero-extend (char is unsigned) the value and then
+	   perform a signed 32-bit subtraction.  */
+	lsr	data1, data1, #56
+	sub	result, data1, data2, lsr #56
+	ret
+#else
+	/* For big-endian we cannot use the trick with the syndrome value
+	   as carry-propagation can corrupt the upper bits if the trailing
+	   bytes in the string contain 0x01.  */
+	/* However, if there is no NUL byte in the dword, we can generate
+	   the result directly.  We can't just subtract the bytes as the
+	   MSB might be significant.  */
+	cbnz	has_nul, 1f
+	cmp	data1, data2
+	cset	result, ne
+	cneg	result, result, lo
+	ret
+1:
+	/* Re-compute the NUL-byte detection, using a byte-reversed value.  */
+	rev	tmp3, data1
+	sub	tmp1, tmp3, zeroones
+	orr	tmp2, tmp3, #REP8_7f
+	bic	has_nul, tmp1, tmp2
+	rev	has_nul, has_nul
+	orr	syndrome, diff, has_nul
+	clz	pos, syndrome
+	/* The MS-non-zero bit of the syndrome marks either the first bit
+	   that is different, or the top bit of the first zero byte.
+	   Shifting left now will bring the critical information into the
+	   top bits.  */
+	lsl	data1, data1, pos
+	lsl	data2, data2, pos
+	/* But we need to zero-extend (char is unsigned) the value and then
+	   perform a signed 32-bit subtraction.  */
+	lsr	data1, data1, #56
+	sub	result, data1, data2, lsr #56
+	ret
+#endif
+
+L(mutual_align):
+	/* Sources are mutually aligned, but are not currently at an
+	   alignment boundary.  Round down the addresses and then mask off
+	   the bytes that preceed the start point.  */
 	bic	src1, src1, #7
 	bic	src2, src2, #7
 	lsl	tmp1, tmp1, #3		/* Bytes beyond alignment -> bits.  */
@@ -86,138 +125,52 @@
 	neg	tmp1, tmp1		/* Bits to alignment -64.  */
 	ldr	data2, [src2], #8
 	mov	tmp2, #~0
+#ifdef __AARCH64EB__
 	/* Big-endian.  Early bytes are at MSB.  */
-CPU_BE( lsl	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */
+	lsl	tmp2, tmp2, tmp1	/* Shift (tmp1 & 63).  */
+#else
 	/* Little-endian.  Early bytes are at LSB.  */
-CPU_LE( lsr	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */
-
+	lsr	tmp2, tmp2, tmp1	/* Shift (tmp1 & 63).  */
+#endif
 	orr	data1, data1, tmp2
 	orr	data2, data2, tmp2
-	b	.Lstart_realigned
+	b	L(start_realigned)
 
-.Lmisaligned8:
-	/*
-	* Get the align offset length to compare per byte first.
-	* After this process, one string's address will be aligned.
-	*/
-	and	tmp1, src1, #7
-	neg	tmp1, tmp1
-	add	tmp1, tmp1, #8
-	and	tmp2, src2, #7
-	neg	tmp2, tmp2
-	add	tmp2, tmp2, #8
-	subs	tmp3, tmp1, tmp2
-	csel	pos, tmp1, tmp2, hi /*Choose the maximum. */
-.Ltinycmp:
+L(misaligned8):
+	/* Align SRC1 to 8 bytes and then compare 8 bytes at a time, always
+	   checking to make sure that we don't access beyond page boundary in
+	   SRC2.  */
+	tst	src1, #7
+	b.eq	L(loop_misaligned)
+L(do_misaligned):
 	ldrb	data1w, [src1], #1
 	ldrb	data2w, [src2], #1
-	subs	pos, pos, #1
-	ccmp	data1w, #1, #0, ne  /* NZCV = 0b0000.  */
-	ccmp	data1w, data2w, #0, cs  /* NZCV = 0b0000.  */
-	b.eq	.Ltinycmp
-	cbnz	pos, 1f /*find the null or unequal...*/
 	cmp	data1w, #1
-	ccmp	data1w, data2w, #0, cs
-	b.eq	.Lstart_align /*the last bytes are equal....*/
-1:
+	ccmp	data1w, data2w, #0, cs	/* NZCV = 0b0000.  */
+	b.ne	L(done)
+	tst	src1, #7
+	b.ne	L(do_misaligned)
+
+L(loop_misaligned):
+	/* Test if we are within the last dword of the end of a 4K page.  If
+	   yes then jump back to the misaligned loop to copy a byte at a time.  */
+	and	tmp1, src2, #0xff8
+	eor	tmp1, tmp1, #0xff8
+	cbz	tmp1, L(do_misaligned)
+	ldr	data1, [src1], #8
+	ldr	data2, [src2], #8
+
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, #REP8_7f
+	eor	diff, data1, data2	/* Non-zero if differences found.  */
+	bic	has_nul, tmp1, tmp2	/* Non-zero if NUL terminator.  */
+	orr	syndrome, diff, has_nul
+	cbz	syndrome, L(loop_misaligned)
+	b	L(end)
+
+L(done):
 	sub	result, data1, data2
 	ret
 
-.Lstart_align:
-	ands	xzr, src1, #7
-	b.eq	.Lrecal_offset
-	/*process more leading bytes to make str1 aligned...*/
-	add	src1, src1, tmp3
-	add	src2, src2, tmp3
-	/*load 8 bytes from aligned str1 and non-aligned str2..*/
-	ldr	data1, [src1], #8
-	ldr	data2, [src2], #8
-
-	sub	tmp1, data1, zeroones
-	orr	tmp2, data1, #REP8_7f
-	bic	has_nul, tmp1, tmp2
-	eor	diff, data1, data2 /* Non-zero if differences found.  */
-	orr	syndrome, diff, has_nul
-	cbnz	syndrome, .Lcal_cmpresult
-	/*How far is the current str2 from the alignment boundary...*/
-	and	tmp3, tmp3, #7
-.Lrecal_offset:
-	neg	pos, tmp3
-.Lloopcmp_proc:
-	/*
-	* Divide the eight bytes into two parts. First,backwards the src2
-	* to an alignment boundary,load eight bytes from the SRC2 alignment
-	* boundary,then compare with the relative bytes from SRC1.
-	* If all 8 bytes are equal,then start the second part's comparison.
-	* Otherwise finish the comparison.
-	* This special handle can garantee all the accesses are in the
-	* thread/task space in avoid to overrange access.
-	*/
-	ldr	data1, [src1,pos]
-	ldr	data2, [src2,pos]
-	sub	tmp1, data1, zeroones
-	orr	tmp2, data1, #REP8_7f
-	bic	has_nul, tmp1, tmp2
-	eor	diff, data1, data2  /* Non-zero if differences found.  */
-	orr	syndrome, diff, has_nul
-	cbnz	syndrome, .Lcal_cmpresult
-
-	/*The second part process*/
-	ldr	data1, [src1], #8
-	ldr	data2, [src2], #8
-	sub	tmp1, data1, zeroones
-	orr	tmp2, data1, #REP8_7f
-	bic	has_nul, tmp1, tmp2
-	eor	diff, data1, data2  /* Non-zero if differences found.  */
-	orr	syndrome, diff, has_nul
-	cbz	syndrome, .Lloopcmp_proc
-
-.Lcal_cmpresult:
-	/*
-	* reversed the byte-order as big-endian,then CLZ can find the most
-	* significant zero bits.
-	*/
-CPU_LE( rev	syndrome, syndrome )
-CPU_LE( rev	data1, data1 )
-CPU_LE( rev	data2, data2 )
-
-	/*
-	* For big-endian we cannot use the trick with the syndrome value
-	* as carry-propagation can corrupt the upper bits if the trailing
-	* bytes in the string contain 0x01.
-	* However, if there is no NUL byte in the dword, we can generate
-	* the result directly.  We cannot just subtract the bytes as the
-	* MSB might be significant.
-	*/
-CPU_BE( cbnz	has_nul, 1f )
-CPU_BE( cmp	data1, data2 )
-CPU_BE( cset	result, ne )
-CPU_BE( cneg	result, result, lo )
-CPU_BE( ret )
-CPU_BE( 1: )
-	/*Re-compute the NUL-byte detection, using a byte-reversed value. */
-CPU_BE(	rev	tmp3, data1 )
-CPU_BE(	sub	tmp1, tmp3, zeroones )
-CPU_BE(	orr	tmp2, tmp3, #REP8_7f )
-CPU_BE(	bic	has_nul, tmp1, tmp2 )
-CPU_BE(	rev	has_nul, has_nul )
-CPU_BE(	orr	syndrome, diff, has_nul )
-
-	clz	pos, syndrome
-	/*
-	* The MS-non-zero bit of the syndrome marks either the first bit
-	* that is different, or the top bit of the first zero byte.
-	* Shifting left now will bring the critical information into the
-	* top bits.
-	*/
-	lsl	data1, data1, pos
-	lsl	data2, data2, pos
-	/*
-	* But we need to zero-extend (char is unsigned) the value and then
-	* perform a signed 32-bit subtraction.
-	*/
-	lsr	data1, data1, #56
-	sub	result, data1, data2, lsr #56
-	ret
 SYM_FUNC_END_PI(strcmp)
 EXPORT_SYMBOL_NOKASAN(strcmp)
diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S
index ee3ed88..35fbdb7 100644
--- a/arch/arm64/lib/strlen.S
+++ b/arch/arm64/lib/strlen.S
@@ -1,115 +1,203 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
+ * Copyright (c) 2013-2021, Arm Limited.
  *
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/98e4d6a5c13c8e54/string/aarch64/strlen.S
  */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-/*
- * calculate the length of a string
+/* Assumptions:
  *
- * Parameters:
- *	x0 - const string pointer
- * Returns:
- *	x0 - the return length of specific string
+ * ARMv8-a, AArch64, unaligned accesses, min page size 4k.
  */
 
+#define L(label) .L ## label
+
 /* Arguments and results.  */
-srcin		.req	x0
-len		.req	x0
+#define srcin		x0
+#define len		x0
 
 /* Locals and temporaries.  */
-src		.req	x1
-data1		.req	x2
-data2		.req	x3
-data2a		.req	x4
-has_nul1	.req	x5
-has_nul2	.req	x6
-tmp1		.req	x7
-tmp2		.req	x8
-tmp3		.req	x9
-tmp4		.req	x10
-zeroones	.req	x11
-pos		.req	x12
+#define src		x1
+#define data1		x2
+#define data2		x3
+#define has_nul1	x4
+#define has_nul2	x5
+#define tmp1		x4
+#define tmp2		x5
+#define tmp3		x6
+#define tmp4		x7
+#define zeroones	x8
+
+	/* NUL detection works on the principle that (X - 1) & (~X) & 0x80
+	   (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+	   can be done in parallel across the entire word. A faster check
+	   (X - 1) & 0x80 is zero for non-NUL ASCII characters, but gives
+	   false hits for characters 129..255.	*/
 
 #define REP8_01 0x0101010101010101
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
+#define MIN_PAGE_SIZE 4096
+
+	/* Since strings are short on average, we check the first 16 bytes
+	   of the string for a NUL character.  In order to do an unaligned ldp
+	   safely we have to do a page cross check first.  If there is a NUL
+	   byte we calculate the length from the 2 8-byte words using
+	   conditional select to reduce branch mispredictions (it is unlikely
+	   strlen will be repeatedly called on strings with the same length).
+
+	   If the string is longer than 16 bytes, we align src so don't need
+	   further page cross checks, and process 32 bytes per iteration
+	   using the fast NUL check.  If we encounter non-ASCII characters,
+	   fallback to a second loop using the full NUL check.
+
+	   If the page cross check fails, we read 16 bytes from an aligned
+	   address, remove any characters before the string, and continue
+	   in the main loop using aligned loads.  Since strings crossing a
+	   page in the first 16 bytes are rare (probability of
+	   16/MIN_PAGE_SIZE ~= 0.4%), this case does not need to be optimized.
+
+	   AArch64 systems have a minimum page size of 4k.  We don't bother
+	   checking for larger page sizes - the cost of setting up the correct
+	   page size is just not worth the extra gain from a small reduction in
+	   the cases taking the slow path.  Note that we only care about
+	   whether the first fetch, which may be misaligned, crosses a page
+	   boundary.  */
+
 SYM_FUNC_START_WEAK_PI(strlen)
-	mov	zeroones, #REP8_01
-	bic	src, srcin, #15
-	ands	tmp1, srcin, #15
-	b.ne	.Lmisaligned
-	/*
-	* NUL detection works on the principle that (X - 1) & (~X) & 0x80
-	* (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
-	* can be done in parallel across the entire word.
-	*/
-	/*
-	* The inner loop deals with two Dwords at a time. This has a
-	* slightly higher start-up cost, but we should win quite quickly,
-	* especially on cores with a high number of issue slots per
-	* cycle, as we get much better parallelism out of the operations.
-	*/
-.Lloop:
-	ldp	data1, data2, [src], #16
-.Lrealigned:
+	and	tmp1, srcin, MIN_PAGE_SIZE - 1
+	mov	zeroones, REP8_01
+	cmp	tmp1, MIN_PAGE_SIZE - 16
+	b.gt	L(page_cross)
+	ldp	data1, data2, [srcin]
+#ifdef __AARCH64EB__
+	/* For big-endian, carry propagation (if the final byte in the
+	   string is 0x01) means we cannot use has_nul1/2 directly.
+	   Since we expect strings to be small and early-exit,
+	   byte-swap the data now so has_null1/2 will be correct.  */
+	rev	data1, data1
+	rev	data2, data2
+#endif
 	sub	tmp1, data1, zeroones
-	orr	tmp2, data1, #REP8_7f
+	orr	tmp2, data1, REP8_7f
 	sub	tmp3, data2, zeroones
-	orr	tmp4, data2, #REP8_7f
-	bic	has_nul1, tmp1, tmp2
-	bics	has_nul2, tmp3, tmp4
-	ccmp	has_nul1, #0, #0, eq	/* NZCV = 0000  */
-	b.eq	.Lloop
+	orr	tmp4, data2, REP8_7f
+	bics	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	ccmp	has_nul2, 0, 0, eq
+	beq	L(main_loop_entry)
 
-	sub	len, src, srcin
-	cbz	has_nul1, .Lnul_in_data2
-CPU_BE(	mov	data2, data1 )	/*prepare data to re-calculate the syndrome*/
-	sub	len, len, #8
-	mov	has_nul2, has_nul1
-.Lnul_in_data2:
-	/*
-	* For big-endian, carry propagation (if the final byte in the
-	* string is 0x01) means we cannot use has_nul directly.  The
-	* easiest way to get the correct byte is to byte-swap the data
-	* and calculate the syndrome a second time.
-	*/
-CPU_BE( rev	data2, data2 )
-CPU_BE( sub	tmp1, data2, zeroones )
-CPU_BE( orr	tmp2, data2, #REP8_7f )
-CPU_BE( bic	has_nul2, tmp1, tmp2 )
-
-	sub	len, len, #8
-	rev	has_nul2, has_nul2
-	clz	pos, has_nul2
-	add	len, len, pos, lsr #3		/* Bits to bytes.  */
+	/* Enter with C = has_nul1 == 0.  */
+	csel	has_nul1, has_nul1, has_nul2, cc
+	mov	len, 8
+	rev	has_nul1, has_nul1
+	clz	tmp1, has_nul1
+	csel	len, xzr, len, cc
+	add	len, len, tmp1, lsr 3
 	ret
 
-.Lmisaligned:
-	cmp	tmp1, #8
-	neg	tmp1, tmp1
-	ldp	data1, data2, [src], #16
-	lsl	tmp1, tmp1, #3		/* Bytes beyond alignment -> bits.  */
-	mov	tmp2, #~0
-	/* Big-endian.  Early bytes are at MSB.  */
-CPU_BE( lsl	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */
-	/* Little-endian.  Early bytes are at LSB.  */
-CPU_LE( lsr	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */
+	/* The inner loop processes 32 bytes per iteration and uses the fast
+	   NUL check.  If we encounter non-ASCII characters, use a second
+	   loop with the accurate NUL check.  */
+	.p2align 4
+L(main_loop_entry):
+	bic	src, srcin, 15
+	sub	src, src, 16
+L(main_loop):
+	ldp	data1, data2, [src, 32]!
+L(page_cross_entry):
+	sub	tmp1, data1, zeroones
+	sub	tmp3, data2, zeroones
+	orr	tmp2, tmp1, tmp3
+	tst	tmp2, zeroones, lsl 7
+	bne	1f
+	ldp	data1, data2, [src, 16]
+	sub	tmp1, data1, zeroones
+	sub	tmp3, data2, zeroones
+	orr	tmp2, tmp1, tmp3
+	tst	tmp2, zeroones, lsl 7
+	beq	L(main_loop)
+	add	src, src, 16
+1:
+	/* The fast check failed, so do the slower, accurate NUL check.	 */
+	orr	tmp2, data1, REP8_7f
+	orr	tmp4, data2, REP8_7f
+	bics	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	ccmp	has_nul2, 0, 0, eq
+	beq	L(nonascii_loop)
 
-	orr	data1, data1, tmp2
-	orr	data2a, data2, tmp2
-	csinv	data1, data1, xzr, le
-	csel	data2, data2, data2a, le
-	b	.Lrealigned
+	/* Enter with C = has_nul1 == 0.  */
+L(tail):
+#ifdef __AARCH64EB__
+	/* For big-endian, carry propagation (if the final byte in the
+	   string is 0x01) means we cannot use has_nul1/2 directly.  The
+	   easiest way to get the correct byte is to byte-swap the data
+	   and calculate the syndrome a second time.  */
+	csel	data1, data1, data2, cc
+	rev	data1, data1
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, REP8_7f
+	bic	has_nul1, tmp1, tmp2
+#else
+	csel	has_nul1, has_nul1, has_nul2, cc
+#endif
+	sub	len, src, srcin
+	rev	has_nul1, has_nul1
+	add	tmp2, len, 8
+	clz	tmp1, has_nul1
+	csel	len, len, tmp2, cc
+	add	len, len, tmp1, lsr 3
+	ret
+
+L(nonascii_loop):
+	ldp	data1, data2, [src, 16]!
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, REP8_7f
+	sub	tmp3, data2, zeroones
+	orr	tmp4, data2, REP8_7f
+	bics	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	ccmp	has_nul2, 0, 0, eq
+	bne	L(tail)
+	ldp	data1, data2, [src, 16]!
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, REP8_7f
+	sub	tmp3, data2, zeroones
+	orr	tmp4, data2, REP8_7f
+	bics	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	ccmp	has_nul2, 0, 0, eq
+	beq	L(nonascii_loop)
+	b	L(tail)
+
+	/* Load 16 bytes from [srcin & ~15] and force the bytes that precede
+	   srcin to 0x7f, so we ignore any NUL bytes before the string.
+	   Then continue in the aligned loop.  */
+L(page_cross):
+	bic	src, srcin, 15
+	ldp	data1, data2, [src]
+	lsl	tmp1, srcin, 3
+	mov	tmp4, -1
+#ifdef __AARCH64EB__
+	/* Big-endian.	Early bytes are at MSB.	 */
+	lsr	tmp1, tmp4, tmp1	/* Shift (tmp1 & 63).  */
+#else
+	/* Little-endian.  Early bytes are at LSB.  */
+	lsl	tmp1, tmp4, tmp1	/* Shift (tmp1 & 63).  */
+#endif
+	orr	tmp1, tmp1, REP8_80
+	orn	data1, data1, tmp1
+	orn	tmp2, data2, tmp1
+	tst	srcin, 8
+	csel	data1, data1, tmp4, eq
+	csel	data2, data2, tmp2, eq
+	b	L(page_cross_entry)
+
 SYM_FUNC_END_PI(strlen)
 EXPORT_SYMBOL_NOKASAN(strlen)
diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S
index 2a7ee94..48d44f7 100644
--- a/arch/arm64/lib/strncmp.S
+++ b/arch/arm64/lib/strncmp.S
@@ -1,299 +1,261 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
+ * Copyright (c) 2013-2021, Arm Limited.
  *
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/e823e3abf5f89ecb/string/aarch64/strncmp.S
  */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-/*
- * compare two strings
+/* Assumptions:
  *
- * Parameters:
- *  x0 - const string 1 pointer
- *  x1 - const string 2 pointer
- *  x2 - the maximal length to be compared
- * Returns:
- *  x0 - an integer less than, equal to, or greater than zero if s1 is found,
- *     respectively, to be less than, to match, or be greater than s2.
+ * ARMv8-a, AArch64
  */
 
+#define L(label) .L ## label
+
 #define REP8_01 0x0101010101010101
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
 /* Parameters and result.  */
-src1		.req	x0
-src2		.req	x1
-limit		.req	x2
-result		.req	x0
+#define src1		x0
+#define src2		x1
+#define limit		x2
+#define result		x0
 
 /* Internal variables.  */
-data1		.req	x3
-data1w		.req	w3
-data2		.req	x4
-data2w		.req	w4
-has_nul		.req	x5
-diff		.req	x6
-syndrome	.req	x7
-tmp1		.req	x8
-tmp2		.req	x9
-tmp3		.req	x10
-zeroones	.req	x11
-pos		.req	x12
-limit_wd	.req	x13
-mask		.req	x14
-endloop		.req	x15
+#define data1		x3
+#define data1w		w3
+#define data2		x4
+#define data2w		w4
+#define has_nul		x5
+#define diff		x6
+#define syndrome	x7
+#define tmp1		x8
+#define tmp2		x9
+#define tmp3		x10
+#define zeroones	x11
+#define pos		x12
+#define limit_wd	x13
+#define mask		x14
+#define endloop		x15
+#define count		mask
 
 SYM_FUNC_START_WEAK_PI(strncmp)
-	cbz	limit, .Lret0
+	cbz	limit, L(ret0)
 	eor	tmp1, src1, src2
 	mov	zeroones, #REP8_01
 	tst	tmp1, #7
-	b.ne	.Lmisaligned8
-	ands	tmp1, src1, #7
-	b.ne	.Lmutual_align
+	and	count, src1, #7
+	b.ne	L(misaligned8)
+	cbnz	count, L(mutual_align)
 	/* Calculate the number of full and partial words -1.  */
-	/*
-	* when limit is mulitply of 8, if not sub 1,
-	* the judgement of last dword will wrong.
-	*/
-	sub	limit_wd, limit, #1 /* limit != 0, so no underflow.  */
-	lsr	limit_wd, limit_wd, #3  /* Convert to Dwords.  */
+	sub	limit_wd, limit, #1	/* limit != 0, so no underflow.  */
+	lsr	limit_wd, limit_wd, #3	/* Convert to Dwords.  */
 
-	/*
-	* NUL detection works on the principle that (X - 1) & (~X) & 0x80
-	* (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
-	* can be done in parallel across the entire word.
-	*/
-.Lloop_aligned:
+	/* NUL detection works on the principle that (X - 1) & (~X) & 0x80
+	   (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+	   can be done in parallel across the entire word.  */
+	.p2align 4
+L(loop_aligned):
 	ldr	data1, [src1], #8
 	ldr	data2, [src2], #8
-.Lstart_realigned:
+L(start_realigned):
 	subs	limit_wd, limit_wd, #1
 	sub	tmp1, data1, zeroones
 	orr	tmp2, data1, #REP8_7f
-	eor	diff, data1, data2  /* Non-zero if differences found.  */
-	csinv	endloop, diff, xzr, pl  /* Last Dword or differences.*/
-	bics	has_nul, tmp1, tmp2 /* Non-zero if NUL terminator.  */
+	eor	diff, data1, data2	/* Non-zero if differences found.  */
+	csinv	endloop, diff, xzr, pl	/* Last Dword or differences.  */
+	bics	has_nul, tmp1, tmp2	/* Non-zero if NUL terminator.  */
 	ccmp	endloop, #0, #0, eq
-	b.eq	.Lloop_aligned
+	b.eq	L(loop_aligned)
+	/* End of main loop */
 
-	/*Not reached the limit, must have found the end or a diff.  */
-	tbz	limit_wd, #63, .Lnot_limit
+	/* Not reached the limit, must have found the end or a diff.  */
+	tbz	limit_wd, #63, L(not_limit)
 
 	/* Limit % 8 == 0 => all bytes significant.  */
 	ands	limit, limit, #7
-	b.eq	.Lnot_limit
+	b.eq	L(not_limit)
 
-	lsl	limit, limit, #3    /* Bits -> bytes.  */
+	lsl	limit, limit, #3	/* Bits -> bytes.  */
 	mov	mask, #~0
-CPU_BE( lsr	mask, mask, limit )
-CPU_LE( lsl	mask, mask, limit )
+#ifdef __AARCH64EB__
+	lsr	mask, mask, limit
+#else
+	lsl	mask, mask, limit
+#endif
 	bic	data1, data1, mask
 	bic	data2, data2, mask
 
 	/* Make sure that the NUL byte is marked in the syndrome.  */
 	orr	has_nul, has_nul, mask
 
-.Lnot_limit:
+L(not_limit):
 	orr	syndrome, diff, has_nul
-	b	.Lcal_cmpresult
 
-.Lmutual_align:
-	/*
-	* Sources are mutually aligned, but are not currently at an
-	* alignment boundary.  Round down the addresses and then mask off
-	* the bytes that precede the start point.
-	* We also need to adjust the limit calculations, but without
-	* overflowing if the limit is near ULONG_MAX.
-	*/
-	bic	src1, src1, #7
-	bic	src2, src2, #7
-	ldr	data1, [src1], #8
-	neg	tmp3, tmp1, lsl #3  /* 64 - bits(bytes beyond align). */
-	ldr	data2, [src2], #8
-	mov	tmp2, #~0
-	sub	limit_wd, limit, #1 /* limit != 0, so no underflow.  */
-	/* Big-endian.  Early bytes are at MSB.  */
-CPU_BE( lsl	tmp2, tmp2, tmp3 )	/* Shift (tmp1 & 63).  */
-	/* Little-endian.  Early bytes are at LSB.  */
-CPU_LE( lsr	tmp2, tmp2, tmp3 )	/* Shift (tmp1 & 63).  */
-
-	and	tmp3, limit_wd, #7
-	lsr	limit_wd, limit_wd, #3
-	/* Adjust the limit. Only low 3 bits used, so overflow irrelevant.*/
-	add	limit, limit, tmp1
-	add	tmp3, tmp3, tmp1
-	orr	data1, data1, tmp2
-	orr	data2, data2, tmp2
-	add	limit_wd, limit_wd, tmp3, lsr #3
-	b	.Lstart_realigned
-
-/*when src1 offset is not equal to src2 offset...*/
-.Lmisaligned8:
-	cmp	limit, #8
-	b.lo	.Ltiny8proc /*limit < 8... */
-	/*
-	* Get the align offset length to compare per byte first.
-	* After this process, one string's address will be aligned.*/
-	and	tmp1, src1, #7
-	neg	tmp1, tmp1
-	add	tmp1, tmp1, #8
-	and	tmp2, src2, #7
-	neg	tmp2, tmp2
-	add	tmp2, tmp2, #8
-	subs	tmp3, tmp1, tmp2
-	csel	pos, tmp1, tmp2, hi /*Choose the maximum. */
-	/*
-	* Here, limit is not less than 8, so directly run .Ltinycmp
-	* without checking the limit.*/
-	sub	limit, limit, pos
-.Ltinycmp:
-	ldrb	data1w, [src1], #1
-	ldrb	data2w, [src2], #1
-	subs	pos, pos, #1
-	ccmp	data1w, #1, #0, ne  /* NZCV = 0b0000.  */
-	ccmp	data1w, data2w, #0, cs  /* NZCV = 0b0000.  */
-	b.eq	.Ltinycmp
-	cbnz	pos, 1f /*find the null or unequal...*/
-	cmp	data1w, #1
-	ccmp	data1w, data2w, #0, cs
-	b.eq	.Lstart_align /*the last bytes are equal....*/
-1:
-	sub	result, data1, data2
-	ret
-
-.Lstart_align:
-	lsr	limit_wd, limit, #3
-	cbz	limit_wd, .Lremain8
-	/*process more leading bytes to make str1 aligned...*/
-	ands	xzr, src1, #7
-	b.eq	.Lrecal_offset
-	add	src1, src1, tmp3	/*tmp3 is positive in this branch.*/
-	add	src2, src2, tmp3
-	ldr	data1, [src1], #8
-	ldr	data2, [src2], #8
-
-	sub	limit, limit, tmp3
-	lsr	limit_wd, limit, #3
-	subs	limit_wd, limit_wd, #1
-
-	sub	tmp1, data1, zeroones
-	orr	tmp2, data1, #REP8_7f
-	eor	diff, data1, data2  /* Non-zero if differences found.  */
-	csinv	endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
-	bics	has_nul, tmp1, tmp2
-	ccmp	endloop, #0, #0, eq /*has_null is ZERO: no null byte*/
-	b.ne	.Lunequal_proc
-	/*How far is the current str2 from the alignment boundary...*/
-	and	tmp3, tmp3, #7
-.Lrecal_offset:
-	neg	pos, tmp3
-.Lloopcmp_proc:
-	/*
-	* Divide the eight bytes into two parts. First,backwards the src2
-	* to an alignment boundary,load eight bytes from the SRC2 alignment
-	* boundary,then compare with the relative bytes from SRC1.
-	* If all 8 bytes are equal,then start the second part's comparison.
-	* Otherwise finish the comparison.
-	* This special handle can garantee all the accesses are in the
-	* thread/task space in avoid to overrange access.
-	*/
-	ldr	data1, [src1,pos]
-	ldr	data2, [src2,pos]
-	sub	tmp1, data1, zeroones
-	orr	tmp2, data1, #REP8_7f
-	bics	has_nul, tmp1, tmp2 /* Non-zero if NUL terminator.  */
-	eor	diff, data1, data2  /* Non-zero if differences found.  */
-	csinv	endloop, diff, xzr, eq
-	cbnz	endloop, .Lunequal_proc
-
-	/*The second part process*/
-	ldr	data1, [src1], #8
-	ldr	data2, [src2], #8
-	subs	limit_wd, limit_wd, #1
-	sub	tmp1, data1, zeroones
-	orr	tmp2, data1, #REP8_7f
-	eor	diff, data1, data2  /* Non-zero if differences found.  */
-	csinv	endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
-	bics	has_nul, tmp1, tmp2
-	ccmp	endloop, #0, #0, eq /*has_null is ZERO: no null byte*/
-	b.eq	.Lloopcmp_proc
-
-.Lunequal_proc:
-	orr	syndrome, diff, has_nul
-	cbz	syndrome, .Lremain8
-.Lcal_cmpresult:
-	/*
-	* reversed the byte-order as big-endian,then CLZ can find the most
-	* significant zero bits.
-	*/
-CPU_LE( rev	syndrome, syndrome )
-CPU_LE( rev	data1, data1 )
-CPU_LE( rev	data2, data2 )
-	/*
-	* For big-endian we cannot use the trick with the syndrome value
-	* as carry-propagation can corrupt the upper bits if the trailing
-	* bytes in the string contain 0x01.
-	* However, if there is no NUL byte in the dword, we can generate
-	* the result directly.  We can't just subtract the bytes as the
-	* MSB might be significant.
-	*/
-CPU_BE( cbnz	has_nul, 1f )
-CPU_BE( cmp	data1, data2 )
-CPU_BE( cset	result, ne )
-CPU_BE( cneg	result, result, lo )
-CPU_BE( ret )
-CPU_BE( 1: )
-	/* Re-compute the NUL-byte detection, using a byte-reversed value.*/
-CPU_BE( rev	tmp3, data1 )
-CPU_BE( sub	tmp1, tmp3, zeroones )
-CPU_BE( orr	tmp2, tmp3, #REP8_7f )
-CPU_BE( bic	has_nul, tmp1, tmp2 )
-CPU_BE( rev	has_nul, has_nul )
-CPU_BE( orr	syndrome, diff, has_nul )
-	/*
-	* The MS-non-zero bit of the syndrome marks either the first bit
-	* that is different, or the top bit of the first zero byte.
-	* Shifting left now will bring the critical information into the
-	* top bits.
-	*/
+#ifndef	__AARCH64EB__
+	rev	syndrome, syndrome
+	rev	data1, data1
+	/* The MS-non-zero bit of the syndrome marks either the first bit
+	   that is different, or the top bit of the first zero byte.
+	   Shifting left now will bring the critical information into the
+	   top bits.  */
 	clz	pos, syndrome
+	rev	data2, data2
 	lsl	data1, data1, pos
 	lsl	data2, data2, pos
-	/*
-	* But we need to zero-extend (char is unsigned) the value and then
-	* perform a signed 32-bit subtraction.
-	*/
+	/* But we need to zero-extend (char is unsigned) the value and then
+	   perform a signed 32-bit subtraction.  */
 	lsr	data1, data1, #56
 	sub	result, data1, data2, lsr #56
 	ret
+#else
+	/* For big-endian we cannot use the trick with the syndrome value
+	   as carry-propagation can corrupt the upper bits if the trailing
+	   bytes in the string contain 0x01.  */
+	/* However, if there is no NUL byte in the dword, we can generate
+	   the result directly.  We can't just subtract the bytes as the
+	   MSB might be significant.  */
+	cbnz	has_nul, 1f
+	cmp	data1, data2
+	cset	result, ne
+	cneg	result, result, lo
+	ret
+1:
+	/* Re-compute the NUL-byte detection, using a byte-reversed value.  */
+	rev	tmp3, data1
+	sub	tmp1, tmp3, zeroones
+	orr	tmp2, tmp3, #REP8_7f
+	bic	has_nul, tmp1, tmp2
+	rev	has_nul, has_nul
+	orr	syndrome, diff, has_nul
+	clz	pos, syndrome
+	/* The MS-non-zero bit of the syndrome marks either the first bit
+	   that is different, or the top bit of the first zero byte.
+	   Shifting left now will bring the critical information into the
+	   top bits.  */
+	lsl	data1, data1, pos
+	lsl	data2, data2, pos
+	/* But we need to zero-extend (char is unsigned) the value and then
+	   perform a signed 32-bit subtraction.  */
+	lsr	data1, data1, #56
+	sub	result, data1, data2, lsr #56
+	ret
+#endif
 
-.Lremain8:
-	/* Limit % 8 == 0 => all bytes significant.  */
-	ands	limit, limit, #7
-	b.eq	.Lret0
-.Ltiny8proc:
+L(mutual_align):
+	/* Sources are mutually aligned, but are not currently at an
+	   alignment boundary.  Round down the addresses and then mask off
+	   the bytes that precede the start point.
+	   We also need to adjust the limit calculations, but without
+	   overflowing if the limit is near ULONG_MAX.  */
+	bic	src1, src1, #7
+	bic	src2, src2, #7
+	ldr	data1, [src1], #8
+	neg	tmp3, count, lsl #3	/* 64 - bits(bytes beyond align). */
+	ldr	data2, [src2], #8
+	mov	tmp2, #~0
+	sub	limit_wd, limit, #1	/* limit != 0, so no underflow.  */
+#ifdef __AARCH64EB__
+	/* Big-endian.  Early bytes are at MSB.  */
+	lsl	tmp2, tmp2, tmp3	/* Shift (count & 63).  */
+#else
+	/* Little-endian.  Early bytes are at LSB.  */
+	lsr	tmp2, tmp2, tmp3	/* Shift (count & 63).  */
+#endif
+	and	tmp3, limit_wd, #7
+	lsr	limit_wd, limit_wd, #3
+	/* Adjust the limit. Only low 3 bits used, so overflow irrelevant.  */
+	add	limit, limit, count
+	add	tmp3, tmp3, count
+	orr	data1, data1, tmp2
+	orr	data2, data2, tmp2
+	add	limit_wd, limit_wd, tmp3, lsr #3
+	b	L(start_realigned)
+
+	.p2align 4
+	/* Don't bother with dwords for up to 16 bytes.  */
+L(misaligned8):
+	cmp	limit, #16
+	b.hs	L(try_misaligned_words)
+
+L(byte_loop):
+	/* Perhaps we can do better than this.  */
 	ldrb	data1w, [src1], #1
 	ldrb	data2w, [src2], #1
 	subs	limit, limit, #1
-
-	ccmp	data1w, #1, #0, ne  /* NZCV = 0b0000.  */
-	ccmp	data1w, data2w, #0, cs  /* NZCV = 0b0000.  */
-	b.eq	.Ltiny8proc
+	ccmp	data1w, #1, #0, hi	/* NZCV = 0b0000.  */
+	ccmp	data1w, data2w, #0, cs	/* NZCV = 0b0000.  */
+	b.eq	L(byte_loop)
+L(done):
 	sub	result, data1, data2
 	ret
+	/* Align the SRC1 to a dword by doing a bytewise compare and then do
+	   the dword loop.  */
+L(try_misaligned_words):
+	lsr	limit_wd, limit, #3
+	cbz	count, L(do_misaligned)
 
-.Lret0:
+	neg	count, count
+	and	count, count, #7
+	sub	limit, limit, count
+	lsr	limit_wd, limit, #3
+
+L(page_end_loop):
+	ldrb	data1w, [src1], #1
+	ldrb	data2w, [src2], #1
+	cmp	data1w, #1
+	ccmp	data1w, data2w, #0, cs	/* NZCV = 0b0000.  */
+	b.ne	L(done)
+	subs	count, count, #1
+	b.hi	L(page_end_loop)
+
+L(do_misaligned):
+	/* Prepare ourselves for the next page crossing.  Unlike the aligned
+	   loop, we fetch 1 less dword because we risk crossing bounds on
+	   SRC2.  */
+	mov	count, #8
+	subs	limit_wd, limit_wd, #1
+	b.lo	L(done_loop)
+L(loop_misaligned):
+	and	tmp2, src2, #0xff8
+	eor	tmp2, tmp2, #0xff8
+	cbz	tmp2, L(page_end_loop)
+
+	ldr	data1, [src1], #8
+	ldr	data2, [src2], #8
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, #REP8_7f
+	eor	diff, data1, data2	/* Non-zero if differences found.  */
+	bics	has_nul, tmp1, tmp2	/* Non-zero if NUL terminator.  */
+	ccmp	diff, #0, #0, eq
+	b.ne	L(not_limit)
+	subs	limit_wd, limit_wd, #1
+	b.pl	L(loop_misaligned)
+
+L(done_loop):
+	/* We found a difference or a NULL before the limit was reached.  */
+	and	limit, limit, #7
+	cbz	limit, L(not_limit)
+	/* Read the last word.  */
+	sub	src1, src1, 8
+	sub	src2, src2, 8
+	ldr	data1, [src1, limit]
+	ldr	data2, [src2, limit]
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, #REP8_7f
+	eor	diff, data1, data2	/* Non-zero if differences found.  */
+	bics	has_nul, tmp1, tmp2	/* Non-zero if NUL terminator.  */
+	ccmp	diff, #0, #0, eq
+	b.ne	L(not_limit)
+
+L(ret0):
 	mov	result, #0
 	ret
+
 SYM_FUNC_END_PI(strncmp)
 EXPORT_SYMBOL_NOKASAN(strncmp)
diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c
index c83bb5a..baee2296 100644
--- a/arch/arm64/lib/uaccess_flushcache.c
+++ b/arch/arm64/lib/uaccess_flushcache.c
@@ -15,7 +15,7 @@
 	 * barrier to order the cache maintenance against the memcpy.
 	 */
 	memcpy(dst, src, cnt);
-	__clean_dcache_area_pop(dst, cnt);
+	dcache_clean_pop((unsigned long)dst, (unsigned long)dst + cnt);
 }
 EXPORT_SYMBOL_GPL(memcpy_flushcache);
 
@@ -33,6 +33,6 @@
 	rc = raw_copy_from_user(to, from, n);
 
 	/* See above */
-	__clean_dcache_area_pop(to, n - rc);
+	dcache_clean_pop((unsigned long)to, (unsigned long)to + n - rc);
 	return rc;
 }
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 2d881f3..5051b3c 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -15,7 +15,7 @@
 #include <asm/asm-uaccess.h>
 
 /*
- *	flush_icache_range(start,end)
+ *	caches_clean_inval_pou_macro(start,end) [fixup]
  *
  *	Ensure that the I and D caches are coherent within specified region.
  *	This is typically used when code has been written to a memory region,
@@ -23,70 +23,54 @@
  *
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
+ *	- fixup   - optional label to branch to on user fault
  */
-SYM_FUNC_START(__flush_icache_range)
-	/* FALLTHROUGH */
-
-/*
- *	__flush_cache_user_range(start,end)
- *
- *	Ensure that the I and D caches are coherent within specified region.
- *	This is typically used when code has been written to a memory region,
- *	and will be executed.
- *
- *	- start   - virtual start address of region
- *	- end     - virtual end address of region
- */
-SYM_FUNC_START(__flush_cache_user_range)
-	uaccess_ttbr0_enable x2, x3, x4
+.macro	caches_clean_inval_pou_macro, fixup
 alternative_if ARM64_HAS_CACHE_IDC
-	dsb	ishst
-	b	7f
+	dsb     ishst
+	b       .Ldc_skip_\@
 alternative_else_nop_endif
-	dcache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x4, x0, x3
-1:
-user_alt 9f, "dc cvau, x4",  "dc civac, x4",  ARM64_WORKAROUND_CLEAN_CACHE
-	add	x4, x4, x2
-	cmp	x4, x1
-	b.lo	1b
-	dsb	ish
-
-7:
+	mov     x2, x0
+	mov     x3, x1
+	dcache_by_line_op cvau, ish, x2, x3, x4, x5, \fixup
+.Ldc_skip_\@:
 alternative_if ARM64_HAS_CACHE_DIC
 	isb
-	b	8f
+	b	.Lic_skip_\@
 alternative_else_nop_endif
-	invalidate_icache_by_line x0, x1, x2, x3, 9f
-8:	mov	x0, #0
-1:
-	uaccess_ttbr0_disable x1, x2
-	ret
-9:
-	mov	x0, #-EFAULT
-	b	1b
-SYM_FUNC_END(__flush_icache_range)
-SYM_FUNC_END(__flush_cache_user_range)
+	invalidate_icache_by_line x0, x1, x2, x3, \fixup
+.Lic_skip_\@:
+.endm
 
 /*
- *	invalidate_icache_range(start,end)
+ *	caches_clean_inval_pou(start,end)
  *
- *	Ensure that the I cache is invalid within specified region.
+ *	Ensure that the I and D caches are coherent within specified region.
+ *	This is typically used when code has been written to a memory region,
+ *	and will be executed.
  *
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-SYM_FUNC_START(invalidate_icache_range)
-alternative_if ARM64_HAS_CACHE_DIC
-	mov	x0, xzr
-	isb
+SYM_FUNC_START(caches_clean_inval_pou)
+	caches_clean_inval_pou_macro
 	ret
-alternative_else_nop_endif
+SYM_FUNC_END(caches_clean_inval_pou)
 
+/*
+ *	caches_clean_inval_user_pou(start,end)
+ *
+ *	Ensure that the I and D caches are coherent within specified region.
+ *	This is typically used when code has been written to a memory region,
+ *	and will be executed.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+SYM_FUNC_START(caches_clean_inval_user_pou)
 	uaccess_ttbr0_enable x2, x3, x4
 
-	invalidate_icache_by_line x0, x1, x2, x3, 2f
+	caches_clean_inval_pou_macro 2f
 	mov	x0, xzr
 1:
 	uaccess_ttbr0_disable x1, x2
@@ -94,60 +78,77 @@
 2:
 	mov	x0, #-EFAULT
 	b	1b
-SYM_FUNC_END(invalidate_icache_range)
+SYM_FUNC_END(caches_clean_inval_user_pou)
 
 /*
- *	__flush_dcache_area(kaddr, size)
+ *	icache_inval_pou(start,end)
  *
- *	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ *	Ensure that the I cache is invalid within specified region.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+SYM_FUNC_START(icache_inval_pou)
+alternative_if ARM64_HAS_CACHE_DIC
+	isb
+	ret
+alternative_else_nop_endif
+
+	invalidate_icache_by_line x0, x1, x2, x3
+	ret
+SYM_FUNC_END(icache_inval_pou)
+
+/*
+ *	dcache_clean_inval_poc(start, end)
+ *
+ *	Ensure that any D-cache lines for the interval [start, end)
  *	are cleaned and invalidated to the PoC.
  *
- *	- kaddr   - kernel address
- *	- size    - size in question
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
  */
-SYM_FUNC_START_PI(__flush_dcache_area)
+SYM_FUNC_START_PI(dcache_clean_inval_poc)
 	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-SYM_FUNC_END_PI(__flush_dcache_area)
+SYM_FUNC_END_PI(dcache_clean_inval_poc)
 
 /*
- *	__clean_dcache_area_pou(kaddr, size)
+ *	dcache_clean_pou(start, end)
  *
- * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	Ensure that any D-cache lines for the interval [start, end)
  * 	are cleaned to the PoU.
  *
- *	- kaddr   - kernel address
- *	- size    - size in question
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
  */
-SYM_FUNC_START(__clean_dcache_area_pou)
+SYM_FUNC_START(dcache_clean_pou)
 alternative_if ARM64_HAS_CACHE_IDC
 	dsb	ishst
 	ret
 alternative_else_nop_endif
 	dcache_by_line_op cvau, ish, x0, x1, x2, x3
 	ret
-SYM_FUNC_END(__clean_dcache_area_pou)
+SYM_FUNC_END(dcache_clean_pou)
 
 /*
- *	__inval_dcache_area(kaddr, size)
+ *	dcache_inval_poc(start, end)
  *
- * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	Ensure that any D-cache lines for the interval [start, end)
  * 	are invalidated. Any partial lines at the ends of the interval are
  *	also cleaned to PoC to prevent data loss.
  *
- *	- kaddr   - kernel address
- *	- size    - size in question
+ *	- start   - kernel start address of region
+ *	- end     - kernel end address of region
  */
 SYM_FUNC_START_LOCAL(__dma_inv_area)
-SYM_FUNC_START_PI(__inval_dcache_area)
+SYM_FUNC_START_PI(dcache_inval_poc)
 	/* FALLTHROUGH */
 
 /*
- *	__dma_inv_area(start, size)
+ *	__dma_inv_area(start, end)
  *	- start   - virtual start address of region
- *	- size    - size in question
+ *	- end     - virtual end address of region
  */
-	add	x1, x1, x0
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	tst	x1, x3				// end cache line aligned?
@@ -165,48 +166,48 @@
 	b.lo	2b
 	dsb	sy
 	ret
-SYM_FUNC_END_PI(__inval_dcache_area)
+SYM_FUNC_END_PI(dcache_inval_poc)
 SYM_FUNC_END(__dma_inv_area)
 
 /*
- *	__clean_dcache_area_poc(kaddr, size)
+ *	dcache_clean_poc(start, end)
  *
- * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	Ensure that any D-cache lines for the interval [start, end)
  * 	are cleaned to the PoC.
  *
- *	- kaddr   - kernel address
- *	- size    - size in question
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
  */
 SYM_FUNC_START_LOCAL(__dma_clean_area)
-SYM_FUNC_START_PI(__clean_dcache_area_poc)
+SYM_FUNC_START_PI(dcache_clean_poc)
 	/* FALLTHROUGH */
 
 /*
- *	__dma_clean_area(start, size)
+ *	__dma_clean_area(start, end)
  *	- start   - virtual start address of region
- *	- size    - size in question
+ *	- end     - virtual end address of region
  */
 	dcache_by_line_op cvac, sy, x0, x1, x2, x3
 	ret
-SYM_FUNC_END_PI(__clean_dcache_area_poc)
+SYM_FUNC_END_PI(dcache_clean_poc)
 SYM_FUNC_END(__dma_clean_area)
 
 /*
- *	__clean_dcache_area_pop(kaddr, size)
+ *	dcache_clean_pop(start, end)
  *
- * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	Ensure that any D-cache lines for the interval [start, end)
  * 	are cleaned to the PoP.
  *
- *	- kaddr   - kernel address
- *	- size    - size in question
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
  */
-SYM_FUNC_START_PI(__clean_dcache_area_pop)
+SYM_FUNC_START_PI(dcache_clean_pop)
 	alternative_if_not ARM64_HAS_DCPOP
-	b	__clean_dcache_area_poc
+	b	dcache_clean_poc
 	alternative_else_nop_endif
 	dcache_by_line_op cvap, sy, x0, x1, x2, x3
 	ret
-SYM_FUNC_END_PI(__clean_dcache_area_pop)
+SYM_FUNC_END_PI(dcache_clean_pop)
 
 /*
  *	__dma_flush_area(start, size)
@@ -217,6 +218,7 @@
  *	- size    - size in question
  */
 SYM_FUNC_START_PI(__dma_flush_area)
+	add	x1, x0, x1
 	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
 SYM_FUNC_END_PI(__dma_flush_area)
@@ -228,6 +230,7 @@
  *	- dir	- DMA direction
  */
 SYM_FUNC_START_PI(__dma_map_area)
+	add	x1, x0, x1
 	cmp	w2, #DMA_FROM_DEVICE
 	b.eq	__dma_inv_area
 	b	__dma_clean_area
@@ -240,6 +243,7 @@
  *	- dir	- DMA direction
  */
 SYM_FUNC_START_PI(__dma_unmap_area)
+	add	x1, x0, x1
 	cmp	w2, #DMA_TO_DEVICE
 	b.ne	__dma_inv_area
 	ret
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 001737a..cd72576 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -402,14 +402,12 @@
 {
 	asid_bits = get_cpu_asid_bits();
 	atomic64_set(&asid_generation, ASID_FIRST_VERSION);
-	asid_map = kcalloc(BITS_TO_LONGS(NUM_USER_ASIDS), sizeof(*asid_map),
-			   GFP_KERNEL);
+	asid_map = bitmap_zalloc(NUM_USER_ASIDS, GFP_KERNEL);
 	if (!asid_map)
 		panic("Failed to allocate bitmap for %lu ASIDs\n",
 		      NUM_USER_ASIDS);
 
-	pinned_asid_map = kcalloc(BITS_TO_LONGS(NUM_USER_ASIDS),
-				  sizeof(*pinned_asid_map), GFP_KERNEL);
+	pinned_asid_map = bitmap_zalloc(NUM_USER_ASIDS, GFP_KERNEL);
 	nr_pinned_asids = 0;
 
 	/*
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 871c82a..349c488 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -99,6 +99,8 @@
 	pr_alert("  EA = %lu, S1PTW = %lu\n",
 		 (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT,
 		 (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT);
+	pr_alert("  FSC = 0x%02x: %s\n", (esr & ESR_ELx_FSC),
+		 esr_to_fault_info(esr)->name);
 
 	if (esr_is_data_abort(esr))
 		data_abort_decode(esr);
@@ -232,13 +234,17 @@
 	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
 }
 
+static bool is_el1_data_abort(unsigned int esr)
+{
+	return ESR_ELx_EC(esr) == ESR_ELx_EC_DABT_CUR;
+}
+
 static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr,
 					   struct pt_regs *regs)
 {
-	unsigned int ec       = ESR_ELx_EC(esr);
 	unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
 
-	if (ec != ESR_ELx_EC_DABT_CUR && ec != ESR_ELx_EC_IABT_CUR)
+	if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr))
 		return false;
 
 	if (fsc_type == ESR_ELx_FSC_PERM)
@@ -258,7 +264,7 @@
 	unsigned long flags;
 	u64 par, dfsc;
 
-	if (ESR_ELx_EC(esr) != ESR_ELx_EC_DABT_CUR ||
+	if (!is_el1_data_abort(esr) ||
 	    (esr & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT)
 		return false;
 
@@ -346,10 +352,9 @@
 
 static bool is_el1_mte_sync_tag_check_fault(unsigned int esr)
 {
-	unsigned int ec = ESR_ELx_EC(esr);
 	unsigned int fsc = esr & ESR_ELx_FSC;
 
-	if (ec != ESR_ELx_EC_DABT_CUR)
+	if (!is_el1_data_abort(esr))
 		return false;
 
 	if (fsc == ESR_ELx_FSC_MTE)
@@ -504,7 +509,7 @@
 	 */
 	if (!(vma->vm_flags & vm_flags))
 		return VM_FAULT_BADACCESS;
-	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, regs);
+	return handle_mm_fault(vma, addr, mm_flags, regs);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -836,13 +841,6 @@
 }
 NOKPROBE_SYMBOL(do_mem_abort);
 
-void do_el0_irq_bp_hardening(void)
-{
-	/* PC has already been checked in entry.S */
-	arm64_apply_bp_hardening();
-}
-NOKPROBE_SYMBOL(do_el0_irq_bp_hardening);
-
 void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN,
@@ -921,3 +919,29 @@
 	debug_exception_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug_exception);
+
+/*
+ * Used during anonymous page fault handling.
+ */
+struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+						unsigned long vaddr)
+{
+	gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO;
+
+	/*
+	 * If the page is mapped with PROT_MTE, initialise the tags at the
+	 * point of allocation and page zeroing as this is usually faster than
+	 * separate DC ZVA and STGM.
+	 */
+	if (vma->vm_flags & VM_MTE)
+		flags |= __GFP_ZEROTAGS;
+
+	return alloc_page_vma(flags, vma, vaddr);
+}
+
+void tag_clear_highpage(struct page *page)
+{
+	mte_zero_clear_page_tags(page_address(page));
+	page_kasan_tag_reset(page);
+	set_bit(PG_mte_tagged, &page->flags);
+}
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 6d44c02..2aaf950 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -14,28 +14,25 @@
 #include <asm/cache.h>
 #include <asm/tlbflush.h>
 
-void sync_icache_aliases(void *kaddr, unsigned long len)
+void sync_icache_aliases(unsigned long start, unsigned long end)
 {
-	unsigned long addr = (unsigned long)kaddr;
-
 	if (icache_is_aliasing()) {
-		__clean_dcache_area_pou(kaddr, len);
-		__flush_icache_all();
+		dcache_clean_pou(start, end);
+		icache_inval_all_pou();
 	} else {
 		/*
 		 * Don't issue kick_all_cpus_sync() after I-cache invalidation
 		 * for user mappings.
 		 */
-		__flush_icache_range(addr, addr + len);
+		caches_clean_inval_pou(start, end);
 	}
 }
 
-static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
-				unsigned long uaddr, void *kaddr,
-				unsigned long len)
+static void flush_ptrace_access(struct vm_area_struct *vma, unsigned long start,
+				unsigned long end)
 {
 	if (vma->vm_flags & VM_EXEC)
-		sync_icache_aliases(kaddr, len);
+		sync_icache_aliases(start, end);
 }
 
 /*
@@ -48,7 +45,7 @@
 		       unsigned long len)
 {
 	memcpy(dst, src, len);
-	flush_ptrace_access(vma, page, uaddr, dst, len);
+	flush_ptrace_access(vma, (unsigned long)dst, (unsigned long)dst + len);
 }
 
 void __sync_icache_dcache(pte_t pte)
@@ -56,7 +53,9 @@
 	struct page *page = pte_page(pte);
 
 	if (!test_bit(PG_dcache_clean, &page->flags)) {
-		sync_icache_aliases(page_address(page), page_size(page));
+		sync_icache_aliases((unsigned long)page_address(page),
+				    (unsigned long)page_address(page) +
+					    page_size(page));
 		set_bit(PG_dcache_clean, &page->flags);
 	}
 }
@@ -77,20 +76,20 @@
 /*
  * Additional functions defined in assembly.
  */
-EXPORT_SYMBOL(__flush_icache_range);
+EXPORT_SYMBOL(caches_clean_inval_pou);
 
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size)
 {
 	/* Ensure order against any prior non-cacheable writes */
 	dmb(osh);
-	__clean_dcache_area_pop(addr, size);
+	dcache_clean_pop((unsigned long)addr, (unsigned long)addr + size);
 }
 EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
 
 void arch_invalidate_pmem(void *addr, size_t size)
 {
-	__inval_dcache_area(addr, size);
+	dcache_inval_poc((unsigned long)addr, (unsigned long)addr + size);
 }
 EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
 #endif
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index e55409c..6e1ca04 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -499,6 +499,13 @@
 	BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64);
 #endif
 
+	/*
+	 * Selected page table levels should match when derived from
+	 * scratch using the virtual address range and page size.
+	 */
+	BUILD_BUG_ON(ARM64_HW_PGTABLE_LEVELS(CONFIG_ARM64_VA_BITS) !=
+		     CONFIG_PGTABLE_LEVELS);
+
 	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
 		extern int sysctl_overcommit_memory;
 		/*
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 6dd9369..e04e4b6 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -228,7 +228,7 @@
 		next = pmd_addr_end(addr, end);
 
 		/* try section mapping first */
-		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
+		if (((addr | next | phys) & ~PMD_MASK) == 0 &&
 		    (flags & NO_BLOCK_MAPPINGS) == 0) {
 			pmd_set_huge(pmdp, phys, prot);
 
@@ -1113,14 +1113,14 @@
 }
 #endif
 
-#if !ARM64_SWAPPER_USES_SECTION_MAPS
+#if !ARM64_KERNEL_USES_PMD_MAPS
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
 	return vmemmap_populate_basepages(start, end, node, altmap);
 }
-#else	/* !ARM64_SWAPPER_USES_SECTION_MAPS */
+#else	/* !ARM64_KERNEL_USES_PMD_MAPS */
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
@@ -1165,17 +1165,18 @@
 
 	return 0;
 }
-#endif	/* !ARM64_SWAPPER_USES_SECTION_MAPS */
+#endif	/* !ARM64_KERNEL_USES_PMD_MAPS */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
 void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap)
 {
-#ifdef CONFIG_MEMORY_HOTPLUG
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
 
 	unmap_hotplug_range(start, end, true, altmap);
 	free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
-#endif
 }
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
 static inline pud_t *fixmap_pud(unsigned long addr)
 {
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 97d7bcd..35936c5 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -46,9 +46,13 @@
 #endif
 
 #ifdef CONFIG_KASAN_HW_TAGS
-#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
+#define TCR_MTE_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
 #else
-#define TCR_KASAN_HW_FLAGS 0
+/*
+ * The mte_zero_clear_page_tags() implementation uses DC GZVA, which relies on
+ * TBI being enabled at EL1.
+ */
+#define TCR_MTE_FLAGS TCR_TBI1 | TCR_TBID1
 #endif
 
 /*
@@ -58,10 +62,8 @@
 #define MAIR_EL1_SET							\
 	(MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) |	\
 	 MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRE, MT_DEVICE_nGnRE) |	\
-	 MAIR_ATTRIDX(MAIR_ATTR_DEVICE_GRE, MT_DEVICE_GRE) |		\
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_NC, MT_NORMAL_NC) |		\
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) |			\
-	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT) |		\
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL_TAGGED))
 
 #ifdef CONFIG_CPU_PM
@@ -83,11 +85,7 @@
 	mrs	x9, mdscr_el1
 	mrs	x10, oslsr_el1
 	mrs	x11, sctlr_el1
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	x12, tpidr_el1
-alternative_else
-	mrs	x12, tpidr_el2
-alternative_endif
+	get_this_cpu_offset x12
 	mrs	x13, sp_el0
 	stp	x2, x3, [x0]
 	stp	x4, x5, [x0, #16]
@@ -145,11 +143,7 @@
 	msr	mdscr_el1, x10
 
 	msr	sctlr_el1, x12
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	msr	tpidr_el1, x13
-alternative_else
-	msr	tpidr_el2, x13
-alternative_endif
+	set_this_cpu_offset x13
 	msr	sp_el0, x14
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
@@ -464,7 +458,7 @@
 	msr_s	SYS_TFSRE0_EL1, xzr
 
 	/* set the TCR_EL1 bits */
-	mov_q	x10, TCR_KASAN_HW_FLAGS
+	mov_q	x10, TCR_MTE_FLAGS
 	orr	tcr, tcr, x10
 1:
 #endif
diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c
index a1937df..1c40353 100644
--- a/arch/arm64/mm/ptdump.c
+++ b/arch/arm64/mm/ptdump.c
@@ -159,10 +159,6 @@
 		.set	= "DEVICE/nGnRE",
 	}, {
 		.mask	= PTE_ATTRINDX_MASK,
-		.val	= PTE_ATTRINDX(MT_DEVICE_GRE),
-		.set	= "DEVICE/GRE",
-	}, {
-		.mask	= PTE_ATTRINDX_MASK,
 		.val	= PTE_ATTRINDX(MT_NORMAL_NC),
 		.set	= "MEM/NORMAL-NC",
 	}, {
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index f7b1948..dd5000d 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -16,6 +16,7 @@
 #include <asm/byteorder.h>
 #include <asm/cacheflush.h>
 #include <asm/debug-monitors.h>
+#include <asm/insn.h>
 #include <asm/set_memory.h>
 
 #include "bpf_jit.h"
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 21fbdda..49305c2 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -3,7 +3,8 @@
 # Internal CPU capabilities constants, keep this list sorted
 
 BTI
-HAS_32BIT_EL0
+# Unreliable: use system_supports_32bit_el0() instead.
+HAS_32BIT_EL0_DO_NOT_USE
 HAS_32BIT_EL1
 HAS_ADDRESS_AUTH
 HAS_ADDRESS_AUTH_ARCH
diff --git a/arch/ia64/include/asm/page.h b/arch/ia64/include/asm/page.h
index f4dc81f..1b99046 100644
--- a/arch/ia64/include/asm/page.h
+++ b/arch/ia64/include/asm/page.h
@@ -82,16 +82,16 @@
 } while (0)
 
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr)		\
+#define alloc_zeroed_user_highpage_movable(vma, vaddr)			\
 ({									\
 	struct page *page = alloc_page_vma(				\
-		GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr);	\
+		GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr);		\
 	if (page)							\
  		flush_dcache_page(page);				\
 	page;								\
 })
 
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 
diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index 8d0f862..c9d0d84 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -13,9 +13,9 @@
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
-#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 alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #define __pa(vaddr)		((unsigned long)(vaddr))
 #define __va(paddr)		((void *)((unsigned long)(paddr)))
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index cc98f9b..479dc76 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -68,9 +68,9 @@
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
-#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 alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 /*
  * These are used to make use of C type-checking..
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 7555b48..4d5810c 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -34,9 +34,9 @@
 	copy_page(to, from);
 }
 
-#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 alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #ifndef __pa
 #define __pa(x)		__phys_addr((unsigned long)(x))
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 3c1c5da..e3da38e1 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -335,10 +335,15 @@
 {
 	int ret;
 
-	if (!psci_power_state_loses_context(state))
+	if (!psci_power_state_loses_context(state)) {
+		struct arm_cpuidle_irq_context context;
+
+		arm_cpuidle_save_irq_context(&context);
 		ret = psci_ops.cpu_suspend(state, 0);
-	else
+		arm_cpuidle_restore_irq_context(&context);
+	} else {
 		ret = cpu_suspend(state, psci_suspend_finisher);
+	}
 
 	return ret;
 }
diff --git a/drivers/firmware/smccc/smccc.c b/drivers/firmware/smccc/smccc.c
index 028f81d..9f937b1 100644
--- a/drivers/firmware/smccc/smccc.c
+++ b/drivers/firmware/smccc/smccc.c
@@ -15,6 +15,7 @@
 static enum arm_smccc_conduit smccc_conduit = SMCCC_CONDUIT_NONE;
 
 bool __ro_after_init smccc_trng_available = false;
+u64 __ro_after_init smccc_has_sve_hint = false;
 
 void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit)
 {
@@ -22,6 +23,9 @@
 	smccc_conduit = conduit;
 
 	smccc_trng_available = smccc_probe_trng();
+	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
+	    smccc_version >= ARM_SMCCC_VERSION_1_3)
+		smccc_has_sve_hint = true;
 }
 
 enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)
diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c
index 0e8254d..a164896 100644
--- a/drivers/misc/lkdtm/bugs.c
+++ b/drivers/misc/lkdtm/bugs.c
@@ -463,7 +463,7 @@
 #ifdef CONFIG_ARM64
 static noinline void change_pac_parameters(void)
 {
-	if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) {
+	if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL)) {
 		/* Reset the keys of current task */
 		ptrauth_thread_init_kernel(current);
 		ptrauth_thread_switch_kernel(current);
@@ -477,8 +477,8 @@
 #define CORRUPT_PAC_ITERATE	10
 	int i;
 
-	if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH))
-		pr_err("FAIL: kernel not built with CONFIG_ARM64_PTR_AUTH\n");
+	if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL))
+		pr_err("FAIL: kernel not built with CONFIG_ARM64_PTR_AUTH_KERNEL\n");
 
 	if (!system_supports_address_auth()) {
 		pr_err("FAIL: CPU lacks pointer authentication feature\n");
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 666d8a9..54aca3a6 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -37,7 +37,7 @@
 
 #define CCI_PMU_CNTR_SIZE(model)	((model)->cntr_size)
 #define CCI_PMU_CNTR_BASE(model, idx)	((idx) * CCI_PMU_CNTR_SIZE(model))
-#define CCI_PMU_CNTR_MASK		((1ULL << 32) -1)
+#define CCI_PMU_CNTR_MASK		((1ULL << 32) - 1)
 #define CCI_PMU_CNTR_LAST(cci_pmu)	(cci_pmu->num_cntrs - 1)
 
 #define CCI_PMU_MAX_HW_CNTRS(model) \
@@ -806,7 +806,7 @@
 		return cci_pmu->model->get_event_idx(cci_pmu, hw, cci_event);
 
 	/* Generic code to find an unused idx from the mask */
-	for(idx = 0; idx <= CCI_PMU_CNTR_LAST(cci_pmu); idx++)
+	for (idx = 0; idx <= CCI_PMU_CNTR_LAST(cci_pmu); idx++)
 		if (!test_and_set_bit(idx, hw->used_mask))
 			return idx;
 
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 96d47cb..a96c316 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1211,7 +1211,7 @@
 	perf_pmu_migrate_context(&dt->pmu, cpu, target);
 	dt->cpu = target;
 	if (ccn->irq)
-		WARN_ON(irq_set_affinity_hint(ccn->irq, cpumask_of(dt->cpu)));
+		WARN_ON(irq_set_affinity(ccn->irq, cpumask_of(dt->cpu)));
 	return 0;
 }
 
@@ -1291,7 +1291,7 @@
 
 	/* Also make sure that the overflow interrupt is handled by this CPU */
 	if (ccn->irq) {
-		err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
+		err = irq_set_affinity(ccn->irq, cpumask_of(ccn->dt.cpu));
 		if (err) {
 			dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
 			goto error_set_affinity;
@@ -1325,8 +1325,6 @@
 
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
 					    &ccn->dt.node);
-	if (ccn->irq)
-		irq_set_affinity_hint(ccn->irq, NULL);
 	for (i = 0; i < ccn->num_xps; i++)
 		writel(0, ccn->xp[i].base + CCN_XP_DT_CONTROL);
 	writel(0, ccn->dt.base + CCN_DT_PMCR);
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 56a5c35..bc3cba5 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -31,7 +31,7 @@
 #define CMN_CI_CHILD_COUNT		GENMASK_ULL(15, 0)
 #define CMN_CI_CHILD_PTR_OFFSET		GENMASK_ULL(31, 16)
 
-#define CMN_CHILD_NODE_ADDR		GENMASK(27,0)
+#define CMN_CHILD_NODE_ADDR		GENMASK(27, 0)
 #define CMN_CHILD_NODE_EXTERNAL		BIT(31)
 
 #define CMN_ADDR_NODE_PTR		GENMASK(27, 14)
@@ -1162,7 +1162,7 @@
 
 	perf_pmu_migrate_context(&cmn->pmu, cpu, target);
 	for (i = 0; i < cmn->num_dtcs; i++)
-		irq_set_affinity_hint(cmn->dtc[i].irq, cpumask_of(target));
+		irq_set_affinity(cmn->dtc[i].irq, cpumask_of(target));
 	cmn->cpu = target;
 	return 0;
 }
@@ -1212,7 +1212,7 @@
 		irq = cmn->dtc[i].irq;
 		for (j = i; j--; ) {
 			if (cmn->dtc[j].irq == irq) {
-				cmn->dtc[j].irq_friend = j - i;
+				cmn->dtc[j].irq_friend = i - j;
 				goto next;
 			}
 		}
@@ -1222,7 +1222,7 @@
 		if (err)
 			return err;
 
-		err = irq_set_affinity_hint(irq, cpumask_of(cmn->cpu));
+		err = irq_set_affinity(irq, cpumask_of(cmn->cpu));
 		if (err)
 			return err;
 	next:
@@ -1568,16 +1568,11 @@
 static int arm_cmn_remove(struct platform_device *pdev)
 {
 	struct arm_cmn *cmn = platform_get_drvdata(pdev);
-	int i;
 
 	writel_relaxed(0, cmn->dtc[0].base + CMN_DT_DTC_CTL);
 
 	perf_pmu_unregister(&cmn->pmu);
 	cpuhp_state_remove_instance(arm_cmn_hp_state, &cmn->cpuhp_node);
-
-	for (i = 0; i < cmn->num_dtcs; i++)
-		irq_set_affinity_hint(cmn->dtc[i].irq, NULL);
-
 	return 0;
 }
 
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index b6c2511..280a6ae 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -421,7 +421,7 @@
 	if (ret)
 		goto out_free_aff;
 
-	ret = irq_set_affinity_hint(irq_num, cpumask_of(irq->cpu));
+	ret = irq_set_affinity(irq_num, cpumask_of(irq->cpu));
 	if (ret)
 		goto out_free_irq;
 
@@ -475,7 +475,6 @@
 	list_del(&irq->irqs_node);
 	mutex_unlock(&dmc620_pmu_irqs_lock);
 
-	WARN_ON(irq_set_affinity_hint(irq->irq_num, NULL));
 	free_irq(irq->irq_num, irq);
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &irq->node);
 	kfree(irq);
@@ -622,7 +621,7 @@
 		perf_pmu_migrate_context(&dmc620_pmu->pmu, irq->cpu, target);
 	mutex_unlock(&dmc620_pmu_irqs_lock);
 
-	WARN_ON(irq_set_affinity_hint(irq->irq_num, cpumask_of(target)));
+	WARN_ON(irq_set_affinity(irq->irq_num, cpumask_of(target)));
 	irq->cpu = target;
 
 	return 0;
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index 196faea..a36698a 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -687,7 +687,7 @@
 static void dsu_pmu_set_active_cpu(int cpu, struct dsu_pmu *dsu_pmu)
 {
 	cpumask_set_cpu(cpu, &dsu_pmu->active_cpu);
-	if (irq_set_affinity_hint(dsu_pmu->irq, &dsu_pmu->active_cpu))
+	if (irq_set_affinity(dsu_pmu->irq, &dsu_pmu->active_cpu))
 		pr_warn("Failed to set irq affinity to %d\n", cpu);
 }
 
@@ -769,7 +769,6 @@
 	if (rc) {
 		cpuhp_state_remove_instance(dsu_pmu_cpuhp_state,
 						 &dsu_pmu->cpuhp_node);
-		irq_set_affinity_hint(dsu_pmu->irq, NULL);
 	}
 
 	return rc;
@@ -781,7 +780,6 @@
 
 	perf_pmu_unregister(&dsu_pmu->pmu);
 	cpuhp_state_remove_instance(dsu_pmu_cpuhp_state, &dsu_pmu->cpuhp_node);
-	irq_set_affinity_hint(dsu_pmu->irq, NULL);
 
 	return 0;
 }
@@ -840,10 +838,8 @@
 
 	dst = dsu_pmu_get_online_cpu_any_but(dsu_pmu, cpu);
 	/* If there are no active CPUs in the DSU, leave IRQ disabled */
-	if (dst >= nr_cpu_ids) {
-		irq_set_affinity_hint(dsu_pmu->irq, NULL);
+	if (dst >= nr_cpu_ids)
 		return 0;
-	}
 
 	perf_pmu_migrate_context(&dsu_pmu->pmu, cpu, dst);
 	dsu_pmu_set_active_cpu(dst, dsu_pmu);
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index d4f7f1f..3cbc3ba 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -563,14 +563,14 @@
 	return ret;
 }
 
-static ssize_t armpmu_cpumask_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
+static ssize_t cpus_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(dev_get_drvdata(dev));
 	return cpumap_print_to_pagebuf(true, buf, &armpmu->supported_cpus);
 }
 
-static DEVICE_ATTR(cpus, S_IRUGO, armpmu_cpumask_show, NULL);
+static DEVICE_ATTR_RO(cpus);
 
 static struct attribute *armpmu_common_attrs[] = {
 	&dev_attr_cpus.attr,
@@ -644,11 +644,9 @@
 		}
 
 		irq_flags = IRQF_PERCPU |
-			    IRQF_NOBALANCING |
+			    IRQF_NOBALANCING | IRQF_NO_AUTOEN |
 			    IRQF_NO_THREAD;
 
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
-
 		err = request_nmi(irq, handler, irq_flags, "arm-pmu",
 				  per_cpu_ptr(&cpu_armpmu, cpu));
 
@@ -670,7 +668,7 @@
 						 &cpu_armpmu);
 			irq_ops = &percpu_pmuirq_ops;
 		} else {
-			has_nmi= true;
+			has_nmi = true;
 			irq_ops = &percpu_pmunmi_ops;
 		}
 	} else {
@@ -869,10 +867,8 @@
 	int cpu;
 
 	pmu = kzalloc(sizeof(*pmu), flags);
-	if (!pmu) {
-		pr_info("failed to allocate PMU device!\n");
+	if (!pmu)
 		goto out;
-	}
 
 	pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, flags);
 	if (!pmu->hw_events) {
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index ff6fab4..2263488 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -277,7 +277,7 @@
 				       struct perf_event *event, int idx)
 {
 	u32 span, sid;
-	unsigned int num_ctrs = smmu_pmu->num_counters;
+	unsigned int cur_idx, num_ctrs = smmu_pmu->num_counters;
 	bool filter_en = !!get_filter_enable(event);
 
 	span = filter_en ? get_filter_span(event) :
@@ -285,17 +285,19 @@
 	sid = filter_en ? get_filter_stream_id(event) :
 			   SMMU_PMCG_DEFAULT_FILTER_SID;
 
-	/* Support individual filter settings */
-	if (!smmu_pmu->global_filter) {
+	cur_idx = find_first_bit(smmu_pmu->used_counters, num_ctrs);
+	/*
+	 * Per-counter filtering, or scheduling the first globally-filtered
+	 * event into an empty PMU so idx == 0 and it works out equivalent.
+	 */
+	if (!smmu_pmu->global_filter || cur_idx == num_ctrs) {
 		smmu_pmu_set_event_filter(event, idx, span, sid);
 		return 0;
 	}
 
-	/* Requested settings same as current global settings*/
-	idx = find_first_bit(smmu_pmu->used_counters, num_ctrs);
-	if (idx == num_ctrs ||
-	    smmu_pmu_check_global_filter(smmu_pmu->events[idx], event)) {
-		smmu_pmu_set_event_filter(event, 0, span, sid);
+	/* Otherwise, must match whatever's currently scheduled */
+	if (smmu_pmu_check_global_filter(smmu_pmu->events[cur_idx], event)) {
+		smmu_pmu_set_evtyper(smmu_pmu, idx, get_event(event));
 		return 0;
 	}
 
@@ -509,11 +511,8 @@
 	return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
 }
 
-#define SMMU_EVENT_ATTR(name, config)					\
-	(&((struct perf_pmu_events_attr) {				\
-		.attr = __ATTR(name, 0444, smmu_pmu_event_show, NULL),	\
-		.id = config,						\
-	}).attr.attr)
+#define SMMU_EVENT_ATTR(name, config)			\
+	PMU_EVENT_ATTR_ID(name, smmu_pmu_event_show, config)
 
 static struct attribute *smmu_pmu_events[] = {
 	SMMU_EVENT_ATTR(cycles, 0),
@@ -628,7 +627,7 @@
 
 	perf_pmu_migrate_context(&smmu_pmu->pmu, cpu, target);
 	smmu_pmu->on_cpu = target;
-	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, cpumask_of(target)));
+	WARN_ON(irq_set_affinity(smmu_pmu->irq, cpumask_of(target)));
 
 	return 0;
 }
@@ -839,15 +838,14 @@
 
 	/* Pick one CPU to be the preferred one to use */
 	smmu_pmu->on_cpu = raw_smp_processor_id();
-	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq,
-				      cpumask_of(smmu_pmu->on_cpu)));
+	WARN_ON(irq_set_affinity(smmu_pmu->irq, cpumask_of(smmu_pmu->on_cpu)));
 
 	err = cpuhp_state_add_instance_nocalls(cpuhp_state_num,
 					       &smmu_pmu->node);
 	if (err) {
 		dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
 			err, &res_0->start);
-		goto out_clear_affinity;
+		return err;
 	}
 
 	err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
@@ -866,8 +864,6 @@
 
 out_unregister:
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
-out_clear_affinity:
-	irq_set_affinity_hint(smmu_pmu->irq, NULL);
 	return err;
 }
 
@@ -877,7 +873,6 @@
 
 	perf_pmu_unregister(&smmu_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
-	irq_set_affinity_hint(smmu_pmu->irq, NULL);
 
 	return 0;
 }
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 8a1e86a..d44bcc2 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -231,15 +231,14 @@
 	.attrs	= arm_spe_pmu_formats_attr,
 };
 
-static ssize_t arm_spe_pmu_get_attr_cpumask(struct device *dev,
-					    struct device_attribute *attr,
-					    char *buf)
+static ssize_t cpumask_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
 {
 	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
 
 	return cpumap_print_to_pagebuf(true, buf, &spe_pmu->supported_cpus);
 }
-static DEVICE_ATTR(cpumask, S_IRUGO, arm_spe_pmu_get_attr_cpumask, NULL);
+static DEVICE_ATTR_RO(cpumask);
 
 static struct attribute *arm_spe_pmu_attrs[] = {
 	&dev_attr_cpumask.attr,
@@ -1044,7 +1043,6 @@
 		 spe_pmu->max_record_sz, spe_pmu->align, spe_pmu->features);
 
 	spe_pmu->features |= SPE_PMU_FEAT_DEV_PROBED;
-	return;
 }
 
 static void __arm_spe_pmu_reset_local(void)
@@ -1190,10 +1188,8 @@
 	}
 
 	spe_pmu = devm_kzalloc(dev, sizeof(*spe_pmu), GFP_KERNEL);
-	if (!spe_pmu) {
-		dev_err(dev, "failed to allocate spe_pmu\n");
+	if (!spe_pmu)
 		return -ENOMEM;
-	}
 
 	spe_pmu->handle = alloc_percpu(typeof(*spe_pmu->handle));
 	if (!spe_pmu->handle)
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 2bbb931..94ebc1e 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -222,11 +222,8 @@
 	return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
 }
 
-#define IMX8_DDR_PMU_EVENT_ATTR(_name, _id)				\
-	(&((struct perf_pmu_events_attr[]) {				\
-		{ .attr = __ATTR(_name, 0444, ddr_pmu_event_show, NULL),\
-		  .id = _id, }						\
-	})[0].attr.attr)
+#define IMX8_DDR_PMU_EVENT_ATTR(_name, _id)		\
+	PMU_EVENT_ATTR_ID(_name, ddr_pmu_event_show, _id)
 
 static struct attribute *ddr_perf_events_attrs[] = {
 	IMX8_DDR_PMU_EVENT_ATTR(cycles, EVENT_CYCLES_ID),
@@ -674,7 +671,7 @@
 	perf_pmu_migrate_context(&pmu->pmu, cpu, target);
 	pmu->cpu = target;
 
-	WARN_ON(irq_set_affinity_hint(pmu->irq, cpumask_of(pmu->cpu)));
+	WARN_ON(irq_set_affinity(pmu->irq, cpumask_of(pmu->cpu)));
 
 	return 0;
 }
@@ -705,8 +702,10 @@
 
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DDR_PERF_DEV_NAME "%d",
 			      num);
-	if (!name)
-		return -ENOMEM;
+	if (!name) {
+		ret = -ENOMEM;
+		goto cpuhp_state_err;
+	}
 
 	pmu->devtype_data = of_device_get_match_data(&pdev->dev);
 
@@ -749,7 +748,7 @@
 	}
 
 	pmu->irq = irq;
-	ret = irq_set_affinity_hint(pmu->irq, cpumask_of(pmu->cpu));
+	ret = irq_set_affinity(pmu->irq, cpumask_of(pmu->cpu));
 	if (ret) {
 		dev_err(pmu->dev, "Failed to set interrupt affinity!\n");
 		goto ddr_perf_err;
@@ -777,7 +776,6 @@
 
 	cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node);
 	cpuhp_remove_multi_state(pmu->cpuhp_state);
-	irq_set_affinity_hint(pmu->irq, NULL);
 
 	perf_pmu_unregister(&pmu->pmu);
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index 7c8a4bc..62299ab 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -2,7 +2,7 @@
 /*
  * HiSilicon SoC DDRC uncore Hardware event counters support
  *
- * Copyright (C) 2017 Hisilicon Limited
+ * Copyright (C) 2017 HiSilicon Limited
  * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
  *         Anurup M <anurup.m@huawei.com>
  *
@@ -537,7 +537,6 @@
 		dev_err(ddrc_pmu->dev, "DDRC PMU register failed!\n");
 		cpuhp_state_remove_instance_nocalls(
 			CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, &ddrc_pmu->node);
-		irq_set_affinity_hint(ddrc_pmu->irq, NULL);
 	}
 
 	return ret;
@@ -550,8 +549,6 @@
 	perf_pmu_unregister(&ddrc_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
 					    &ddrc_pmu->node);
-	irq_set_affinity_hint(ddrc_pmu->irq, NULL);
-
 	return 0;
 }
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 0316fab..3935131 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -2,7 +2,7 @@
 /*
  * HiSilicon SoC HHA uncore Hardware event counters support
  *
- * Copyright (C) 2017 Hisilicon Limited
+ * Copyright (C) 2017 HiSilicon Limited
  * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
  *         Anurup M <anurup.m@huawei.com>
  *
@@ -90,7 +90,7 @@
 
 		val = readl(hha_pmu->base + HHA_DATSRC_CTRL);
 		val |= HHA_DATSRC_SKT_EN;
-		writel(ds_skt, hha_pmu->base + HHA_DATSRC_CTRL);
+		writel(val, hha_pmu->base + HHA_DATSRC_CTRL);
 	}
 }
 
@@ -104,7 +104,7 @@
 
 		val = readl(hha_pmu->base + HHA_DATSRC_CTRL);
 		val &= ~HHA_DATSRC_SKT_EN;
-		writel(ds_skt, hha_pmu->base + HHA_DATSRC_CTRL);
+		writel(val, hha_pmu->base + HHA_DATSRC_CTRL);
 	}
 }
 
@@ -540,7 +540,6 @@
 		dev_err(hha_pmu->dev, "HHA PMU register failed!\n");
 		cpuhp_state_remove_instance_nocalls(
 			CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, &hha_pmu->node);
-		irq_set_affinity_hint(hha_pmu->irq, NULL);
 	}
 
 	return ret;
@@ -553,8 +552,6 @@
 	perf_pmu_unregister(&hha_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
 					    &hha_pmu->node);
-	irq_set_affinity_hint(hha_pmu->irq, NULL);
-
 	return 0;
 }
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index bf9f777..560ab96 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -2,7 +2,7 @@
 /*
  * HiSilicon SoC L3C uncore Hardware event counters support
  *
- * Copyright (C) 2017 Hisilicon Limited
+ * Copyright (C) 2017 HiSilicon Limited
  * Author: Anurup M <anurup.m@huawei.com>
  *         Shaokun Zhang <zhangshaokun@hisilicon.com>
  *
@@ -578,7 +578,6 @@
 		dev_err(l3c_pmu->dev, "L3C PMU register failed!\n");
 		cpuhp_state_remove_instance_nocalls(
 			CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, &l3c_pmu->node);
-		irq_set_affinity_hint(l3c_pmu->irq, NULL);
 	}
 
 	return ret;
@@ -591,8 +590,6 @@
 	perf_pmu_unregister(&l3c_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
 					    &l3c_pmu->node);
-	irq_set_affinity_hint(l3c_pmu->irq, NULL);
-
 	return 0;
 }
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
index 14f23eb..83264ec 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
@@ -333,7 +333,7 @@
 	NULL
 };
 
-static struct attribute_group hisi_pa_pmu_identifier_group = {
+static const struct attribute_group hisi_pa_pmu_identifier_group = {
 	.attrs = hisi_pa_pmu_identifier_attrs,
 };
 
@@ -436,7 +436,6 @@
 		dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret);
 		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
 					    &pa_pmu->node);
-		irq_set_affinity_hint(pa_pmu->irq, NULL);
 		return ret;
 	}
 
@@ -451,8 +450,6 @@
 	perf_pmu_unregister(&pa_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
 					    &pa_pmu->node);
-	irq_set_affinity_hint(pa_pmu->irq, NULL);
-
 	return 0;
 }
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 13c68b5..a738aea 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -2,7 +2,7 @@
 /*
  * HiSilicon SoC Hardware event counters support
  *
- * Copyright (C) 2017 Hisilicon Limited
+ * Copyright (C) 2017 HiSilicon Limited
  * Author: Anurup M <anurup.m@huawei.com>
  *         Shaokun Zhang <zhangshaokun@hisilicon.com>
  *
@@ -488,7 +488,7 @@
 	hisi_pmu->on_cpu = cpu;
 
 	/* Overflow interrupt also should use the same CPU */
-	WARN_ON(irq_set_affinity_hint(hisi_pmu->irq, cpumask_of(cpu)));
+	WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(cpu)));
 
 	return 0;
 }
@@ -521,7 +521,7 @@
 	perf_pmu_migrate_context(&hisi_pmu->pmu, cpu, target);
 	/* Use this CPU for event counting */
 	hisi_pmu->on_cpu = target;
-	WARN_ON(irq_set_affinity_hint(hisi_pmu->irq, cpumask_of(target)));
+	WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(target)));
 
 	return 0;
 }
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h
index ea9d89b..7f5841d 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.h
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h
@@ -2,7 +2,7 @@
 /*
  * HiSilicon SoC Hardware event counters support
  *
- * Copyright (C) 2017 Hisilicon Limited
+ * Copyright (C) 2017 HiSilicon Limited
  * Author: Anurup M <anurup.m@huawei.com>
  *         Shaokun Zhang <zhangshaokun@hisilicon.com>
  *
diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
index 46be312..6aedc303 100644
--- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
@@ -2,7 +2,7 @@
 /*
  * HiSilicon SLLC uncore Hardware event counters support
  *
- * Copyright (C) 2020 Hisilicon Limited
+ * Copyright (C) 2020 HiSilicon Limited
  * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
  *
  * This code is based on the uncore PMUs like arm-cci and arm-ccn.
@@ -366,7 +366,7 @@
 	NULL
 };
 
-static struct attribute_group hisi_sllc_pmu_identifier_group = {
+static const struct attribute_group hisi_sllc_pmu_identifier_group = {
 	.attrs = hisi_sllc_pmu_identifier_attrs,
 };
 
@@ -465,7 +465,6 @@
 		dev_err(sllc_pmu->dev, "PMU register failed, ret = %d\n", ret);
 		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
 					    &sllc_pmu->node);
-		irq_set_affinity_hint(sllc_pmu->irq, NULL);
 		return ret;
 	}
 
@@ -481,8 +480,6 @@
 	perf_pmu_unregister(&sllc_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
 					    &sllc_pmu->node);
-	irq_set_affinity_hint(sllc_pmu->irq, NULL);
-
 	return 0;
 }
 
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index fc54a80..5b093ba 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -679,11 +679,8 @@
 	return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
 }
 
-#define L2CACHE_EVENT_ATTR(_name, _id)					     \
-	(&((struct perf_pmu_events_attr[]) {				     \
-		{ .attr = __ATTR(_name, 0444, l2cache_pmu_event_show, NULL), \
-		  .id = _id, }						     \
-	})[0].attr.attr)
+#define L2CACHE_EVENT_ATTR(_name, _id)			    \
+	PMU_EVENT_ATTR_ID(_name, l2cache_pmu_event_show, _id)
 
 static struct attribute *l2_cache_pmu_events[] = {
 	L2CACHE_EVENT_ATTR(cycles, L2_EVENT_CYCLES),
@@ -869,14 +866,14 @@
 	irq = platform_get_irq(sdev, 0);
 	if (irq < 0)
 		return irq;
-	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	cluster->irq = irq;
 
 	cluster->l2cache_pmu = l2cache_pmu;
 	cluster->on_cpu = -1;
 
 	err = devm_request_irq(&pdev->dev, irq, l2_cache_handle_irq,
-			       IRQF_NOBALANCING | IRQF_NO_THREAD,
+			       IRQF_NOBALANCING | IRQF_NO_THREAD |
+			       IRQF_NO_AUTOEN,
 			       "l2-cache-pmu", cluster);
 	if (err) {
 		dev_err(&pdev->dev,
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index bba0780..1ff2ff6 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -647,10 +647,7 @@
 }
 
 #define L3CACHE_EVENT_ATTR(_name, _id)					     \
-	(&((struct perf_pmu_events_attr[]) {				     \
-		{ .attr = __ATTR(_name, 0444, l3cache_pmu_event_show, NULL), \
-		  .id = _id, }						     \
-	})[0].attr.attr)
+	PMU_EVENT_ATTR_ID(_name, l3cache_pmu_event_show, _id)
 
 static struct attribute *qcom_l3_cache_pmu_events[] = {
 	L3CACHE_EVENT_ATTR(cycles, L3_EVENT_CYCLES),
@@ -670,15 +667,15 @@
 
 /* cpumask */
 
-static ssize_t qcom_l3_cache_pmu_cpumask_show(struct device *dev,
-				     struct device_attribute *attr, char *buf)
+static ssize_t cpumask_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
 {
 	struct l3cache_pmu *l3pmu = to_l3cache_pmu(dev_get_drvdata(dev));
 
 	return cpumap_print_to_pagebuf(true, buf, &l3pmu->cpumask);
 }
 
-static DEVICE_ATTR(cpumask, 0444, qcom_l3_cache_pmu_cpumask_show, NULL);
+static DEVICE_ATTR_RO(cpumask);
 
 static struct attribute *qcom_l3_cache_pmu_cpumask_attrs[] = {
 	&dev_attr_cpumask.attr,
@@ -767,10 +764,8 @@
 
 	memrc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	l3pmu->regs = devm_ioremap_resource(&pdev->dev, memrc);
-	if (IS_ERR(l3pmu->regs)) {
-		dev_err(&pdev->dev, "Can't map PMU @%pa\n", &memrc->start);
+	if (IS_ERR(l3pmu->regs))
 		return PTR_ERR(l3pmu->regs);
-	}
 
 	qcom_l3_cache__init(l3pmu);
 
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index 06a6d56..fc1a376 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -817,10 +817,8 @@
 	}
 
 	base = devm_ioremap_resource(dev, &res);
-	if (IS_ERR(base)) {
-		dev_err(dev, "PMU type %d: Fail to map resource\n", type);
+	if (IS_ERR(base))
 		return NULL;
-	}
 
 	tx2_pmu = devm_kzalloc(dev, sizeof(*tx2_pmu), GFP_KERNEL);
 	if (!tx2_pmu)
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index ffe3bde..2b6d476 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -278,17 +278,14 @@
 static ssize_t xgene_pmu_event_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
-	struct dev_ext_attribute *eattr;
+	struct perf_pmu_events_attr *pmu_attr =
+		container_of(attr, struct perf_pmu_events_attr, attr);
 
-	eattr = container_of(attr, struct dev_ext_attribute, attr);
-	return sysfs_emit(buf, "config=0x%lx\n", (unsigned long) eattr->var);
+	return sysfs_emit(buf, "config=0x%llx\n", pmu_attr->id);
 }
 
 #define XGENE_PMU_EVENT_ATTR(_name, _config)		\
-	(&((struct dev_ext_attribute[]) {		\
-		{ .attr = __ATTR(_name, S_IRUGO, xgene_pmu_event_show, NULL), \
-		  .var = (void *) _config, }		\
-	 })[0].attr.attr)
+	PMU_EVENT_ATTR_ID(_name, xgene_pmu_event_show, _config)
 
 static struct attribute *l3c_pmu_events_attrs[] = {
 	XGENE_PMU_EVENT_ATTR(cycle-count,			0x00),
@@ -604,15 +601,15 @@
 /*
  * sysfs cpumask attributes
  */
-static ssize_t xgene_pmu_cpumask_show(struct device *dev,
-				      struct device_attribute *attr, char *buf)
+static ssize_t cpumask_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
 {
 	struct xgene_pmu_dev *pmu_dev = to_pmu_dev(dev_get_drvdata(dev));
 
 	return cpumap_print_to_pagebuf(true, buf, &pmu_dev->parent->cpu);
 }
 
-static DEVICE_ATTR(cpumask, S_IRUGO, xgene_pmu_cpumask_show, NULL);
+static DEVICE_ATTR_RO(cpumask);
 
 static struct attribute *xgene_pmu_cpumask_attrs[] = {
 	&dev_attr_cpumask.attr,
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 6861489..7d1cabe 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -63,6 +63,9 @@
 #define ARM_SMCCC_VERSION_1_0		0x10000
 #define ARM_SMCCC_VERSION_1_1		0x10001
 #define ARM_SMCCC_VERSION_1_2		0x10002
+#define ARM_SMCCC_VERSION_1_3		0x10003
+
+#define ARM_SMCCC_1_3_SVE_HINT		0x10000
 
 #define ARM_SMCCC_VERSION_FUNC_ID					\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
@@ -216,6 +219,8 @@
 
 void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit);
 
+extern u64 smccc_has_sve_hint;
+
 /**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
@@ -227,6 +232,61 @@
 	unsigned long a3;
 };
 
+#ifdef CONFIG_ARM64
+/**
+ * struct arm_smccc_1_2_regs - Arguments for or Results from SMC/HVC call
+ * @a0-a17 argument values from registers 0 to 17
+ */
+struct arm_smccc_1_2_regs {
+	unsigned long a0;
+	unsigned long a1;
+	unsigned long a2;
+	unsigned long a3;
+	unsigned long a4;
+	unsigned long a5;
+	unsigned long a6;
+	unsigned long a7;
+	unsigned long a8;
+	unsigned long a9;
+	unsigned long a10;
+	unsigned long a11;
+	unsigned long a12;
+	unsigned long a13;
+	unsigned long a14;
+	unsigned long a15;
+	unsigned long a16;
+	unsigned long a17;
+};
+
+/**
+ * arm_smccc_1_2_hvc() - make HVC calls
+ * @args: arguments passed via struct arm_smccc_1_2_regs
+ * @res: result values via struct arm_smccc_1_2_regs
+ *
+ * This function is used to make HVC calls following SMC Calling Convention
+ * v1.2 or above. The content of the supplied param are copied from the
+ * structure to registers prior to the HVC instruction. The return values
+ * are updated with the content from registers on return from the HVC
+ * instruction.
+ */
+asmlinkage void arm_smccc_1_2_hvc(const struct arm_smccc_1_2_regs *args,
+				  struct arm_smccc_1_2_regs *res);
+
+/**
+ * arm_smccc_1_2_smc() - make SMC calls
+ * @args: arguments passed via struct arm_smccc_1_2_regs
+ * @res: result values via struct arm_smccc_1_2_regs
+ *
+ * This function is used to make SMC calls following SMC Calling Convention
+ * v1.2 or above. The content of the supplied param are copied from the
+ * structure to registers prior to the SMC instruction. The return values
+ * are updated with the content from registers on return from the SMC
+ * instruction.
+ */
+asmlinkage void arm_smccc_1_2_smc(const struct arm_smccc_1_2_regs *args,
+				  struct arm_smccc_1_2_regs *res);
+#endif
+
 /**
  * struct arm_smccc_quirk - Contains quirk information
  * @id: quirk identification
@@ -241,6 +301,15 @@
 };
 
 /**
+ * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls
+ *
+ * Sets the SMCCC hint bit to indicate if there is live state in the SVE
+ * registers, this modifies x0 in place and should never be called from C
+ * code.
+ */
+asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0);
+
+/**
  * __arm_smccc_smc() - make SMC calls
  * @a0-a7: arguments passed in registers 0 to 7
  * @res: result values from registers 0 to 3
@@ -297,6 +366,20 @@
 
 #endif
 
+/* nVHE hypervisor doesn't have a current thread so needs separate checks */
+#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__)
+
+#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n",  "bl __arm_smccc_sve_check \n", \
+				    ARM64_SVE)
+#define smccc_sve_clobbers "x16", "x30", "cc",
+
+#else
+
+#define SMCCC_SVE_CHECK
+#define smccc_sve_clobbers
+
+#endif
+
 #define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x
 
 #define __count_args(...)						\
@@ -364,7 +447,7 @@
 
 #define ___constraints(count)						\
 	: __constraint_read_ ## count					\
-	: "memory"
+	: smccc_sve_clobbers "memory"
 #define __constraints(count)	___constraints(count)
 
 /*
@@ -379,7 +462,8 @@
 		register unsigned long r2 asm("r2");			\
 		register unsigned long r3 asm("r3"); 			\
 		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm volatile(inst "\n" :				\
+		asm volatile(SMCCC_SVE_CHECK				\
+			     inst "\n" :				\
 			     "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3)	\
 			     __constraints(__count_args(__VA_ARGS__)));	\
 		if (___res)						\
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 11da8af..e6102df 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -53,8 +53,10 @@
 #define ___GFP_HARDWALL		0x100000u
 #define ___GFP_THISNODE		0x200000u
 #define ___GFP_ACCOUNT		0x400000u
+#define ___GFP_ZEROTAGS		0x800000u
+#define ___GFP_SKIP_KASAN_POISON	0x1000000u
 #ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP	0x800000u
+#define ___GFP_NOLOCKDEP	0x2000000u
 #else
 #define ___GFP_NOLOCKDEP	0
 #endif
@@ -229,16 +231,25 @@
  * %__GFP_COMP address compound page metadata.
  *
  * %__GFP_ZERO returns a zeroed page on success.
+ *
+ * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if
+ * __GFP_ZERO is set.
+ *
+ * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned
+ * on deallocation. Typically used for userspace pages. Currently only has an
+ * effect in HW tags mode.
  */
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
+#define __GFP_ZEROTAGS	((__force gfp_t)___GFP_ZEROTAGS)
+#define __GFP_SKIP_KASAN_POISON	((__force gfp_t)___GFP_SKIP_KASAN_POISON)
 
 /* Disable lockdep for GFP context tracking */
 #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
 
 /* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP))
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /**
@@ -319,7 +330,8 @@
 #define GFP_DMA		__GFP_DMA
 #define GFP_DMA32	__GFP_DMA32
 #define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
-#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
+#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE | \
+			 __GFP_SKIP_KASAN_POISON)
 #define GFP_TRANSHUGE_LIGHT	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
 			 __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
 #define GFP_TRANSHUGE	(GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 832b49b..8c6e8e9 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -152,28 +152,24 @@
 }
 #endif
 
-#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 /**
- * __alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA with caller-specified movable GFP flags
- * @movableflags: The GFP flags related to the pages future ability to move like __GFP_MOVABLE
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move
  * @vma: The VMA the page is to be allocated for
  * @vaddr: The virtual address the page will be inserted into
  *
- * This function will allocate a page for a VMA but the caller is expected
- * to specify via movableflags whether the page will be movable in the
- * future or not
+ * This function will allocate a page for a VMA that the caller knows will
+ * be able to migrate in the future using move_pages() or reclaimed
  *
  * An architecture may override this function by defining
- * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE and providing their own
+ * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE and providing their own
  * implementation.
  */
 static inline struct page *
-__alloc_zeroed_user_highpage(gfp_t movableflags,
-			struct vm_area_struct *vma,
-			unsigned long vaddr)
+alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+				   unsigned long vaddr)
 {
-	struct page *page = alloc_page_vma(GFP_HIGHUSER | movableflags,
-			vma, vaddr);
+	struct page *page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
 
 	if (page)
 		clear_user_highpage(page, vaddr);
@@ -182,21 +178,6 @@
 }
 #endif
 
-/**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move
- * @vma: The VMA the page is to be allocated for
- * @vaddr: The virtual address the page will be inserted into
- *
- * This function will allocate a page for a VMA that the caller knows will
- * be able to migrate in the future using move_pages() or reclaimed
- */
-static inline struct page *
-alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-					unsigned long vaddr)
-{
-	return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
-}
-
 static inline void clear_highpage(struct page *page)
 {
 	void *kaddr = kmap_atomic(page);
@@ -204,6 +185,14 @@
 	kunmap_atomic(kaddr);
 }
 
+#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
+
+static inline void tag_clear_highpage(struct page *page)
+{
+}
+
+#endif
+
 /*
  * If we pass in a base or tail page, we can zero up to PAGE_SIZE.
  * If we pass in a head page, we can zero up to the size of the compound page.
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 4777850..35a3742 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -319,39 +319,8 @@
 
 extern cpumask_var_t irq_default_affinity;
 
-/* Internal implementation. Use the helpers below */
-extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask,
-			      bool force);
-
-/**
- * irq_set_affinity - Set the irq affinity of a given irq
- * @irq:	Interrupt to set affinity
- * @cpumask:	cpumask
- *
- * Fails if cpumask does not contain an online CPU
- */
-static inline int
-irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
-{
-	return __irq_set_affinity(irq, cpumask, false);
-}
-
-/**
- * irq_force_affinity - Force the irq affinity of a given irq
- * @irq:	Interrupt to set affinity
- * @cpumask:	cpumask
- *
- * Same as irq_set_affinity, but without checking the mask against
- * online cpus.
- *
- * Solely for low level cpu hotplug code, where we need to make per
- * cpu interrupts affine before the cpu becomes online.
- */
-static inline int
-irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
-{
-	return __irq_set_affinity(irq, cpumask, true);
-}
+extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask);
 
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index b1678a6..a1c7ce5 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_KASAN_H
 #define _LINUX_KASAN_H
 
+#include <linux/bug.h>
 #include <linux/static_key.h>
 #include <linux/types.h>
 
@@ -79,14 +80,6 @@
 
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
-#ifdef CONFIG_KASAN
-
-struct kasan_cache {
-	int alloc_meta_offset;
-	int free_meta_offset;
-	bool is_kmalloc;
-};
-
 #ifdef CONFIG_KASAN_HW_TAGS
 
 DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled);
@@ -101,11 +94,14 @@
 	return kasan_enabled();
 }
 
+void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags);
+void kasan_free_pages(struct page *page, unsigned int order);
+
 #else /* CONFIG_KASAN_HW_TAGS */
 
 static inline bool kasan_enabled(void)
 {
-	return true;
+	return IS_ENABLED(CONFIG_KASAN);
 }
 
 static inline bool kasan_has_integrated_init(void)
@@ -113,8 +109,30 @@
 	return false;
 }
 
+static __always_inline void kasan_alloc_pages(struct page *page,
+					      unsigned int order, gfp_t flags)
+{
+	/* Only available for integrated init. */
+	BUILD_BUG();
+}
+
+static __always_inline void kasan_free_pages(struct page *page,
+					     unsigned int order)
+{
+	/* Only available for integrated init. */
+	BUILD_BUG();
+}
+
 #endif /* CONFIG_KASAN_HW_TAGS */
 
+#ifdef CONFIG_KASAN
+
+struct kasan_cache {
+	int alloc_meta_offset;
+	int free_meta_offset;
+	bool is_kmalloc;
+};
+
 slab_flags_t __kasan_never_merge(void);
 static __always_inline slab_flags_t kasan_never_merge(void)
 {
@@ -130,20 +148,20 @@
 		__kasan_unpoison_range(addr, size);
 }
 
-void __kasan_alloc_pages(struct page *page, unsigned int order, bool init);
-static __always_inline void kasan_alloc_pages(struct page *page,
+void __kasan_poison_pages(struct page *page, unsigned int order, bool init);
+static __always_inline void kasan_poison_pages(struct page *page,
 						unsigned int order, bool init)
 {
 	if (kasan_enabled())
-		__kasan_alloc_pages(page, order, init);
+		__kasan_poison_pages(page, order, init);
 }
 
-void __kasan_free_pages(struct page *page, unsigned int order, bool init);
-static __always_inline void kasan_free_pages(struct page *page,
-						unsigned int order, bool init)
+void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init);
+static __always_inline void kasan_unpoison_pages(struct page *page,
+						 unsigned int order, bool init)
 {
 	if (kasan_enabled())
-		__kasan_free_pages(page, order, init);
+		__kasan_unpoison_pages(page, order, init);
 }
 
 void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
@@ -285,21 +303,15 @@
 
 #else /* CONFIG_KASAN */
 
-static inline bool kasan_enabled(void)
-{
-	return false;
-}
-static inline bool kasan_has_integrated_init(void)
-{
-	return false;
-}
 static inline slab_flags_t kasan_never_merge(void)
 {
 	return 0;
 }
 static inline void kasan_unpoison_range(const void *address, size_t size) {}
-static inline void kasan_alloc_pages(struct page *page, unsigned int order, bool init) {}
-static inline void kasan_free_pages(struct page *page, unsigned int order, bool init) {}
+static inline void kasan_poison_pages(struct page *page, unsigned int order,
+				      bool init) {}
+static inline void kasan_unpoison_pages(struct page *page, unsigned int order,
+					bool init) {}
 static inline void kasan_cache_create(struct kmem_cache *cache,
 				      unsigned int *size,
 				      slab_flags_t *flags) {}
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 04a34c0..40e2c50 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -138,6 +138,9 @@
 #ifdef CONFIG_64BIT
 	PG_arch_2,
 #endif
+#ifdef CONFIG_KASAN_HW_TAGS
+	PG_skip_kasan_poison,
+#endif
 	__NR_PAGEFLAGS,
 
 	/* Filesystems */
@@ -443,6 +446,12 @@
 PAGEFLAG(Idle, idle, PF_ANY)
 #endif
 
+#ifdef CONFIG_KASAN_HW_TAGS
+PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD)
+#else
+PAGEFLAG_FALSE(SkipKASanPoison)
+#endif
+
 /*
  * PageReported() is used to track reported free pages within the Buddy
  * allocator. We can use the non-atomic version of the test and set
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f5a6a2f..2d510ad 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1576,6 +1576,12 @@
 	.event_str	= _str,						    \
 };
 
+#define PMU_EVENT_ATTR_ID(_name, _show, _id)				\
+	(&((struct perf_pmu_events_attr[]) {				\
+		{ .attr = __ATTR(_name, 0444, _show, NULL),		\
+		  .id = _id, }						\
+	})[0].attr.attr)
+
 #define PMU_FORMAT_ATTR(_name, _format)					\
 static ssize_t								\
 _name##_show(struct device *dev,					\
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 629c7a0e..390270e 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -85,6 +85,12 @@
 #define IF_HAVE_PG_ARCH_2(flag,string)
 #endif
 
+#ifdef CONFIG_KASAN_HW_TAGS
+#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string)
+#endif
+
 #define __def_pageflag_names						\
 	{1UL << PG_locked,		"locked"	},		\
 	{1UL << PG_waiters,		"waiters"	},		\
@@ -112,7 +118,8 @@
 IF_HAVE_PG_HWPOISON(PG_hwpoison,	"hwpoison"	)		\
 IF_HAVE_PG_IDLE(PG_young,		"young"		)		\
 IF_HAVE_PG_IDLE(PG_idle,		"idle"		)		\
-IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)
+IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)		\
+IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison")
 
 #define show_page_flags(flags)						\
 	(flags) ? __print_flags(flags, "|",				\
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 4c14356..a847dd2 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -441,7 +441,8 @@
 	return ret;
 }
 
-int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
+static int __irq_set_affinity(unsigned int irq, const struct cpumask *mask,
+			      bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -456,6 +457,36 @@
 	return ret;
 }
 
+/**
+ * irq_set_affinity - Set the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @cpumask:	cpumask
+ *
+ * Fails if cpumask does not contain an online CPU
+ */
+int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, false);
+}
+EXPORT_SYMBOL_GPL(irq_set_affinity);
+
+/**
+ * irq_force_affinity - Force the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @cpumask:	cpumask
+ *
+ * Same as irq_set_affinity, but without checking the mask against
+ * online cpus.
+ *
+ * Solely for low level cpu hotplug code, where we need to make per
+ * cpu interrupts affine before the cpu becomes online.
+ */
+int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, true);
+}
+EXPORT_SYMBOL_GPL(irq_force_affinity);
+
 int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 {
 	unsigned long flags;
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 6bb87f2..0ecd293 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -97,7 +97,7 @@
 	return 0;
 }
 
-void __kasan_alloc_pages(struct page *page, unsigned int order, bool init)
+void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init)
 {
 	u8 tag;
 	unsigned long i;
@@ -111,7 +111,7 @@
 	kasan_unpoison(page_address(page), PAGE_SIZE << order, init);
 }
 
-void __kasan_free_pages(struct page *page, unsigned int order, bool init)
+void __kasan_poison_pages(struct page *page, unsigned int order, bool init)
 {
 	if (likely(!PageHighMem(page)))
 		kasan_poison(page_address(page), PAGE_SIZE << order,
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index 4004388..ed5e5b8 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -238,6 +238,38 @@
 	return &alloc_meta->free_track[0];
 }
 
+void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags)
+{
+	/*
+	 * This condition should match the one in post_alloc_hook() in
+	 * page_alloc.c.
+	 */
+	bool init = !want_init_on_free() && want_init_on_alloc(flags);
+
+	if (flags & __GFP_SKIP_KASAN_POISON)
+		SetPageSkipKASanPoison(page);
+
+	if (flags & __GFP_ZEROTAGS) {
+		int i;
+
+		for (i = 0; i != 1 << order; ++i)
+			tag_clear_highpage(page + i);
+	} else {
+		kasan_unpoison_pages(page, order, init);
+	}
+}
+
+void kasan_free_pages(struct page *page, unsigned int order)
+{
+	/*
+	 * This condition should match the one in free_pages_prepare() in
+	 * page_alloc.c.
+	 */
+	bool init = want_init_on_free();
+
+	kasan_poison_pages(page, order, init);
+}
+
 #if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
 
 void kasan_set_tagging_report_once(bool state)
diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c
index 9df8e7f..9362938 100644
--- a/mm/kasan/sw_tags.c
+++ b/mm/kasan/sw_tags.c
@@ -207,3 +207,10 @@
 
 	return &alloc_meta->free_track[i];
 }
+
+void kasan_tag_mismatch(unsigned long addr, unsigned long access_info,
+			unsigned long ret_ip)
+{
+	kasan_report(addr, 1 << (access_info & 0xf), access_info & 0x10,
+		     ret_ip);
+}
diff --git a/mm/mempool.c b/mm/mempool.c
index a258cf4..0b8afbe 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -106,7 +106,8 @@
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
 		kasan_slab_free_mempool(element);
 	else if (pool->alloc == mempool_alloc_pages)
-		kasan_free_pages(element, (unsigned long)pool->pool_data, false);
+		kasan_poison_pages(element, (unsigned long)pool->pool_data,
+				   false);
 }
 
 static void kasan_unpoison_element(mempool_t *pool, void *element)
@@ -114,7 +115,8 @@
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
 		kasan_unpoison_range(element, __ksize(element));
 	else if (pool->alloc == mempool_alloc_pages)
-		kasan_alloc_pages(element, (unsigned long)pool->pool_data, false);
+		kasan_unpoison_pages(element, (unsigned long)pool->pool_data,
+				     false);
 }
 
 static __always_inline void add_element(mempool_t *pool, void *element)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index aaa1655..5ad76e5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -382,7 +382,7 @@
 static DEFINE_STATIC_KEY_TRUE(deferred_pages);
 
 /*
- * Calling kasan_free_pages() only after deferred memory initialization
+ * Calling kasan_poison_pages() only after deferred memory initialization
  * has completed. Poisoning pages during deferred memory init will greatly
  * lengthen the process and cause problem in large memory systems as the
  * deferred pages initialization is done with interrupt disabled.
@@ -394,15 +394,12 @@
  * on-demand allocation and then freed again before the deferred pages
  * initialization is done, but this is not likely to happen.
  */
-static inline void kasan_free_nondeferred_pages(struct page *page, int order,
-						bool init, fpi_t fpi_flags)
+static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
 {
-	if (static_branch_unlikely(&deferred_pages))
-		return;
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
-			(fpi_flags & FPI_SKIP_KASAN_POISON))
-		return;
-	kasan_free_pages(page, order, init);
+	return static_branch_unlikely(&deferred_pages) ||
+	       (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+		(fpi_flags & FPI_SKIP_KASAN_POISON)) ||
+	       PageSkipKASanPoison(page);
 }
 
 /* Returns true if the struct page for the pfn is uninitialised */
@@ -453,13 +450,11 @@
 	return false;
 }
 #else
-static inline void kasan_free_nondeferred_pages(struct page *page, int order,
-						bool init, fpi_t fpi_flags)
+static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
 {
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
-			(fpi_flags & FPI_SKIP_KASAN_POISON))
-		return;
-	kasan_free_pages(page, order, init);
+	return (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+		(fpi_flags & FPI_SKIP_KASAN_POISON)) ||
+	       PageSkipKASanPoison(page);
 }
 
 static inline bool early_page_uninitialised(unsigned long pfn)
@@ -1226,10 +1221,16 @@
 	return ret;
 }
 
-static void kernel_init_free_pages(struct page *page, int numpages)
+static void kernel_init_free_pages(struct page *page, int numpages, bool zero_tags)
 {
 	int i;
 
+	if (zero_tags) {
+		for (i = 0; i < numpages; i++)
+			tag_clear_highpage(page + i);
+		return;
+	}
+
 	/* s390's use of memset() could override KASAN redzones. */
 	kasan_disable_current();
 	for (i = 0; i < numpages; i++) {
@@ -1245,7 +1246,7 @@
 			unsigned int order, bool check_free, fpi_t fpi_flags)
 {
 	int bad = 0;
-	bool init;
+	bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 
@@ -1314,10 +1315,17 @@
 	 * With hardware tag-based KASAN, memory tags must be set before the
 	 * page becomes unavailable via debug_pagealloc or arch_free_page.
 	 */
-	init = want_init_on_free();
-	if (init && !kasan_has_integrated_init())
-		kernel_init_free_pages(page, 1 << order);
-	kasan_free_nondeferred_pages(page, order, init, fpi_flags);
+	if (kasan_has_integrated_init()) {
+		if (!skip_kasan_poison)
+			kasan_free_pages(page, order);
+	} else {
+		bool init = want_init_on_free();
+
+		if (init)
+			kernel_init_free_pages(page, 1 << order, false);
+		if (!skip_kasan_poison)
+			kasan_poison_pages(page, order, init);
+	}
 
 	/*
 	 * arch_free_page() can make the page's contents inaccessible.  s390
@@ -2324,8 +2332,6 @@
 inline void post_alloc_hook(struct page *page, unsigned int order,
 				gfp_t gfp_flags)
 {
-	bool init;
-
 	set_page_private(page, 0);
 	set_page_refcounted(page);
 
@@ -2344,10 +2350,16 @@
 	 * kasan_alloc_pages and kernel_init_free_pages must be
 	 * kept together to avoid discrepancies in behavior.
 	 */
-	init = !want_init_on_free() && want_init_on_alloc(gfp_flags);
-	kasan_alloc_pages(page, order, init);
-	if (init && !kasan_has_integrated_init())
-		kernel_init_free_pages(page, 1 << order);
+	if (kasan_has_integrated_init()) {
+		kasan_alloc_pages(page, order, gfp_flags);
+	} else {
+		bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags);
+
+		kasan_unpoison_pages(page, order, init);
+		if (init)
+			kernel_init_free_pages(page, 1 << order,
+					       gfp_flags & __GFP_ZEROTAGS);
+	}
 
 	set_page_owner(page, order, gfp_flags);
 }
diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan
index 3d79190..801c415 100644
--- a/scripts/Makefile.kasan
+++ b/scripts/Makefile.kasan
@@ -50,6 +50,7 @@
 CFLAGS_KASAN := -fsanitize=kernel-hwaddress \
 		$(call cc-param,hwasan-instrument-stack=$(stack_enable)) \
 		$(call cc-param,hwasan-use-short-granules=0) \
+		$(call cc-param,hwasan-inline-all-checks=0) \
 		$(instrumentation_flags)
 
 endif # CONFIG_KASAN_SW_TAGS
diff --git a/scripts/tools-support-relr.sh b/scripts/tools-support-relr.sh
index 45e8aa3..cb55878 100755
--- a/scripts/tools-support-relr.sh
+++ b/scripts/tools-support-relr.sh
@@ -7,7 +7,8 @@
 cat << "END" | $CC -c -x c - -o $tmp_file.o >/dev/null 2>&1
 void *p = &p;
 END
-$LD $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr -o $tmp_file
+$LD $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr \
+  --use-android-relr-tags -o $tmp_file
 
 # Despite printing an error message, GNU nm still exits with exit code 0 if it
 # sees a relr section. So we need to check that nothing is printed to stderr.
diff --git a/tools/testing/selftests/arm64/fp/sve-probe-vls.c b/tools/testing/selftests/arm64/fp/sve-probe-vls.c
index b29cbc6..76e1385 100644
--- a/tools/testing/selftests/arm64/fp/sve-probe-vls.c
+++ b/tools/testing/selftests/arm64/fp/sve-probe-vls.c
@@ -25,7 +25,7 @@
 	ksft_set_plan(2);
 
 	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
-		ksft_exit_skip("SVE not available");
+		ksft_exit_skip("SVE not available\n");
 
 	/*
 	 * Enumerate up to SVE_VQ_MAX vector lengths