diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index e4e1b6550115..dfdc3e0af5e1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1406,10 +1406,13 @@ config ARM64_PAN
 config AS_HAS_LDAPR
 	def_bool $(as-instr,.arch_extension rcpc)
 
+config AS_HAS_LSE_ATOMICS
+	def_bool $(as-instr,.arch_extension lse)
+
 config ARM64_LSE_ATOMICS
 	bool
 	default ARM64_USE_LSE_ATOMICS
-	depends on $(as-instr,.arch_extension lse)
+	depends on AS_HAS_LSE_ATOMICS
 
 config ARM64_USE_LSE_ATOMICS
 	bool "Atomic instructions"
@@ -1666,6 +1669,7 @@ config ARM64_MTE
 	default y
 	depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI
 	depends on AS_HAS_ARMV8_5
+	depends on AS_HAS_LSE_ATOMICS
 	# Required for tag checking in the uaccess routines
 	depends on ARM64_PAN
 	select ARCH_USES_HIGH_VMA_FLAGS
diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h
index 3333950b5909..ea487218db79 100644
--- a/arch/arm64/include/asm/word-at-a-time.h
+++ b/arch/arm64/include/asm/word-at-a-time.h
@@ -53,7 +53,7 @@ static inline unsigned long find_zero(unsigned long mask)
  */
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long ret, offset;
+	unsigned long ret, tmp;
 
 	/* Load word from unaligned pointer addr */
 	asm(
@@ -61,9 +61,9 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
 	"2:\n"
 	"	.pushsection .fixup,\"ax\"\n"
 	"	.align 2\n"
-	"3:	and	%1, %2, #0x7\n"
-	"	bic	%2, %2, #0x7\n"
-	"	ldr	%0, [%2]\n"
+	"3:	bic	%1, %2, #0x7\n"
+	"	ldr	%0, [%1]\n"
+	"	and	%1, %2, #0x7\n"
 	"	lsl	%1, %1, #0x3\n"
 #ifndef __AARCH64EB__
 	"	lsr	%0, %0, %1\n"
@@ -73,7 +73,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
 	"	b	2b\n"
 	"	.popsection\n"
 	_ASM_EXTABLE(1b, 3b)
-	: "=&r" (ret), "=&r" (offset)
+	: "=&r" (ret), "=&r" (tmp)
 	: "r" (addr), "Q" (*(unsigned long *)addr));
 
 	return ret;
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a31a0a713c85..6acfc5e6b5e0 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -148,16 +148,18 @@ alternative_cb_end
 	.endm
 
 	/* Check for MTE asynchronous tag check faults */
-	.macro check_mte_async_tcf, flgs, tmp
+	.macro check_mte_async_tcf, tmp, ti_flags
 #ifdef CONFIG_ARM64_MTE
+	.arch_extension lse
 alternative_if_not ARM64_MTE
 	b	1f
 alternative_else_nop_endif
 	mrs_s	\tmp, SYS_TFSRE0_EL1
 	tbz	\tmp, #SYS_TFSR_EL1_TF0_SHIFT, 1f
 	/* Asynchronous TCF occurred for TTBR0 access, set the TI flag */
-	orr	\flgs, \flgs, #_TIF_MTE_ASYNC_FAULT
-	str	\flgs, [tsk, #TSK_TI_FLAGS]
+	mov	\tmp, #_TIF_MTE_ASYNC_FAULT
+	add	\ti_flags, tsk, #TSK_TI_FLAGS
+	stset	\tmp, [\ti_flags]
 	msr_s	SYS_TFSRE0_EL1, xzr
 1:
 #endif
@@ -244,7 +246,7 @@ alternative_else_nop_endif
 	disable_step_tsk x19, x20
 
 	/* Check for asynchronous tag check faults in user space */
-	check_mte_async_tcf x19, x22
+	check_mte_async_tcf x22, x23
 	apply_ssbd 1, x22, x23
 
 	ptrauth_keys_install_kernel tsk, x20, x22, x23
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 66aac2881ba8..85645b2b0c7a 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -267,10 +267,12 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 		if (!instruction_pointer(regs))
 			BUG();
 
-		if (kcb->kprobe_status == KPROBE_REENTER)
+		if (kcb->kprobe_status == KPROBE_REENTER) {
 			restore_previous_kprobe(kcb);
-		else
+		} else {
+			kprobes_restore_local_irqflag(kcb, regs);
 			reset_current_kprobe();
+		}
 
 		break;
 	case KPROBE_HIT_ACTIVE: