Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index b263e23..a45366c 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -12,6 +12,7 @@
 #include <linux/efi.h>
 #include <linux/memblock.h>
 #include <linux/psci.h>
+#include <linux/stddef.h>
 
 #include <asm/cputype.h>
 #include <asm/io.h>
@@ -31,14 +32,14 @@
  * is therefore used to delimit the MADT GICC structure minimum length
  * appropriately.
  */
-#define ACPI_MADT_GICC_MIN_LENGTH   ACPI_OFFSET(  \
+#define ACPI_MADT_GICC_MIN_LENGTH   offsetof(  \
 	struct acpi_madt_generic_interrupt, efficiency_class)
 
 #define BAD_MADT_GICC_ENTRY(entry, end)					\
 	(!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \
 	(unsigned long)(entry) + (entry)->header.length > (end))
 
-#define ACPI_MADT_GICC_SPE  (ACPI_OFFSET(struct acpi_madt_generic_interrupt, \
+#define ACPI_MADT_GICC_SPE  (offsetof(struct acpi_madt_generic_interrupt, \
 	spe_interrupt) + sizeof(u16))
 
 /* Basic configuration for ACPI */
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index b9f8d78..3cb3c4a 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -35,13 +35,16 @@
 static inline void apply_alternatives_module(void *start, size_t length) { }
 #endif
 
-#define ALTINSTR_ENTRY(feature,cb)					      \
+#define ALTINSTR_ENTRY(feature)					              \
 	" .word 661b - .\n"				/* label           */ \
-	" .if " __stringify(cb) " == 0\n"				      \
 	" .word 663f - .\n"				/* new instruction */ \
-	" .else\n"							      \
+	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte 662b-661b\n"				/* source len      */ \
+	" .byte 664f-663f\n"				/* replacement len */
+
+#define ALTINSTR_ENTRY_CB(feature, cb)					      \
+	" .word 661b - .\n"				/* label           */ \
 	" .word " __stringify(cb) "- .\n"		/* callback */	      \
-	" .endif\n"							      \
 	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
 	" .byte 662b-661b\n"				/* source len      */ \
 	" .byte 664f-663f\n"				/* replacement len */
@@ -62,33 +65,40 @@
  *
  * Alternatives with callbacks do not generate replacement instructions.
  */
-#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled, cb)	\
+#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled)	\
 	".if "__stringify(cfg_enabled)" == 1\n"				\
 	"661:\n\t"							\
 	oldinstr "\n"							\
 	"662:\n"							\
 	".pushsection .altinstructions,\"a\"\n"				\
-	ALTINSTR_ENTRY(feature,cb)					\
+	ALTINSTR_ENTRY(feature)						\
 	".popsection\n"							\
-	" .if " __stringify(cb) " == 0\n"				\
-	".pushsection .altinstr_replacement, \"a\"\n"			\
+	".subsection 1\n"						\
 	"663:\n\t"							\
 	newinstr "\n"							\
 	"664:\n\t"							\
-	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
-	".org	. - (662b-661b) + (664b-663b)\n"			\
-	".else\n\t"							\
+	".org	. - (662b-661b) + (664b-663b)\n\t"			\
+	".previous\n"							\
+	".endif\n"
+
+#define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb)	\
+	".if "__stringify(cfg_enabled)" == 1\n"				\
+	"661:\n\t"							\
+	oldinstr "\n"							\
+	"662:\n"							\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY_CB(feature, cb)					\
+	".popsection\n"							\
 	"663:\n\t"							\
 	"664:\n\t"							\
-	".endif\n"							\
 	".endif\n"
 
 #define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...)	\
-	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg), 0)
+	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg))
 
 #define ALTERNATIVE_CB(oldinstr, cb) \
-	__ALTERNATIVE_CFG(oldinstr, "NOT_AN_INSTRUCTION", ARM64_CB_PATCH, 1, cb)
+	__ALTERNATIVE_CFG_CB(oldinstr, ARM64_CB_PATCH, 1, cb)
 #else
 
 #include <asm/assembler.h>
@@ -107,11 +117,11 @@
 662:	.pushsection .altinstructions, "a"
 	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 663:	\insn2
-664:	.popsection
-	.org	. - (664b-663b) + (662b-661b)
+664:	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
+	.previous
 	.endif
 .endm
 
@@ -150,7 +160,7 @@
 	.pushsection .altinstructions, "a"
 	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.align 2	/* So GAS knows label 661 is suitably aligned */
 661:
 .endm
@@ -169,9 +179,9 @@
 .macro alternative_else
 662:
 	.if .Lasm_alt_mode==0
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.else
-	.popsection
+	.previous
 	.endif
 663:
 .endm
@@ -181,11 +191,11 @@
  */
 .macro alternative_endif
 664:
-	.if .Lasm_alt_mode==0
-	.popsection
-	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
+	.if .Lasm_alt_mode==0
+	.previous
+	.endif
 .endm
 
 /*
@@ -211,7 +221,7 @@
 
 .macro user_alt, label, oldinstr, newinstr, cond
 9999:	alternative_insn "\oldinstr", "\newinstr", \cond
-	_ASM_EXTABLE 9999b, \label
+	_asm_extable 9999b, \label
 .endm
 
 /*
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 89e4c8b..ee9bdaa 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -109,7 +109,7 @@
 	return read_sysreg_s(SYS_ICC_PMR_EL1);
 }
 
-static inline void gic_write_pmr(u32 val)
+static __always_inline void gic_write_pmr(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_PMR_EL1);
 }
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 7ae54d7..88d20f0 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -58,6 +58,7 @@
 	u64 (*read_cntvct_el0)(void);
 	int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
 	int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
+	bool disable_compat_vdso;
 };
 
 DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
@@ -164,25 +165,6 @@
 	isb();
 }
 
-/*
- * Ensure that reads of the counter are treated the same as memory reads
- * for the purposes of ordering by subsequent memory barriers.
- *
- * This insanity brought to you by speculative system register reads,
- * out-of-order memory accesses, sequence locks and Thomas Gleixner.
- *
- * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
- */
-#define arch_counter_enforce_ordering(val) do {				\
-	u64 tmp, _val = (val);						\
-									\
-	asm volatile(							\
-	"	eor	%0, %1, %1\n"					\
-	"	add	%0, sp, %0\n"					\
-	"	ldr	xzr, [%0]"					\
-	: "=r" (tmp) : "r" (_val));					\
-} while (0)
-
 static __always_inline u64 __arch_counter_get_cntpct_stable(void)
 {
 	u64 cnt;
@@ -223,8 +205,6 @@
 	return cnt;
 }
 
-#undef arch_counter_enforce_ordering
-
 static inline int arch_timer_arch_init(void)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index c764cc8..9bf56e3 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -15,10 +15,10 @@
 	.macro	__uaccess_ttbr0_disable, tmp1
 	mrs	\tmp1, ttbr1_el1			// swapper_pg_dir
 	bic	\tmp1, \tmp1, #TTBR_ASID_MASK
-	sub	\tmp1, \tmp1, #RESERVED_TTBR0_SIZE	// reserved_ttbr0 just before swapper_pg_dir
+	sub	\tmp1, \tmp1, #PAGE_SIZE		// reserved_pg_dir just before swapper_pg_dir
 	msr	ttbr0_el1, \tmp1			// set reserved TTBR0_EL1
 	isb
-	add	\tmp1, \tmp1, #RESERVED_TTBR0_SIZE
+	add	\tmp1, \tmp1, #PAGE_SIZE
 	msr	ttbr1_el1, \tmp1		// set reserved ASID
 	isb
 	.endm
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index b8cf7c8..4a4258f 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -462,6 +462,7 @@
 	.endm
 
 /*
+ * Deprecated! Use SYM_FUNC_{START,START_WEAK,END}_PI instead.
  * Annotate a function as position independent, i.e., safe to be called before
  * the kernel virtual mapping is activated.
  */
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 9543b5e..6e0f48d 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -17,7 +17,7 @@
 #include <asm/lse.h>
 
 #define ATOMIC_OP(op)							\
-static inline void arch_##op(int i, atomic_t *v)			\
+static __always_inline void arch_##op(int i, atomic_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -32,7 +32,7 @@
 #undef ATOMIC_OP
 
 #define ATOMIC_FETCH_OP(name, op)					\
-static inline int arch_##op##name(int i, atomic_t *v)			\
+static __always_inline int arch_##op##name(int i, atomic_t *v)		\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -56,7 +56,7 @@
 #undef ATOMIC_FETCH_OPS
 
 #define ATOMIC64_OP(op)							\
-static inline void arch_##op(long i, atomic64_t *v)			\
+static __always_inline void arch_##op(long i, atomic64_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -71,7 +71,7 @@
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, op)					\
-static inline long arch_##op##name(long i, atomic64_t *v)		\
+static __always_inline long arch_##op##name(long i, atomic64_t *v)	\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -94,7 +94,7 @@
 #undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_FETCH_OPS
 
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 574808b..da3280f 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -14,6 +14,7 @@
 static inline void __lse_atomic_##op(int i, atomic_t *v)			\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op "	%w[i], %[v]\n"					\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v));							\
@@ -30,6 +31,7 @@
 static inline int __lse_atomic_fetch_##op##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op #mb "	%w[i], %w[i], %[v]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v)							\
@@ -58,6 +60,7 @@
 	u32 tmp;							\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	ldadd" #mb "	%w[i], %w[tmp], %[v]\n"			\
 	"	add	%w[i], %w[i], %w[tmp]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)	\
@@ -77,6 +80,7 @@
 static inline void __lse_atomic_and(int i, atomic_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	mvn	%w[i], %w[i]\n"
 	"	stclr	%w[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
@@ -87,6 +91,7 @@
 static inline int __lse_atomic_fetch_and##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mvn	%w[i], %w[i]\n"					\
 	"	ldclr" #mb "	%w[i], %w[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
@@ -106,6 +111,7 @@
 static inline void __lse_atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	neg	%w[i], %w[i]\n"
 	"	stadd	%w[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
@@ -118,6 +124,7 @@
 	u32 tmp;							\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[tmp], %[v]\n"			\
 	"	add	%w[i], %w[i], %w[tmp]"				\
@@ -139,6 +146,7 @@
 static inline int __lse_atomic_fetch_sub##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
@@ -159,6 +167,7 @@
 static inline void __lse_atomic64_##op(s64 i, atomic64_t *v)		\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op "	%[i], %[v]\n"					\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v));							\
@@ -175,6 +184,7 @@
 static inline long __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op #mb "	%[i], %[i], %[v]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v)							\
@@ -203,6 +213,7 @@
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	ldadd" #mb "	%[i], %x[tmp], %[v]\n"			\
 	"	add	%[i], %[i], %x[tmp]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)	\
@@ -222,6 +233,7 @@
 static inline void __lse_atomic64_and(s64 i, atomic64_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	mvn	%[i], %[i]\n"
 	"	stclr	%[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
@@ -232,6 +244,7 @@
 static inline long __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mvn	%[i], %[i]\n"					\
 	"	ldclr" #mb "	%[i], %[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
@@ -251,6 +264,7 @@
 static inline void __lse_atomic64_sub(s64 i, atomic64_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	neg	%[i], %[i]\n"
 	"	stadd	%[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
@@ -263,6 +277,7 @@
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %x[tmp], %[v]\n"			\
 	"	add	%[i], %[i], %x[tmp]"				\
@@ -284,6 +299,7 @@
 static inline long __lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
@@ -305,6 +321,7 @@
 	unsigned long tmp;
 
 	asm volatile(
+	__LSE_PREAMBLE
 	"1:	ldr	%x[tmp], %[v]\n"
 	"	subs	%[ret], %x[tmp], #1\n"
 	"	b.lt	2f\n"
@@ -332,6 +349,7 @@
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mov	%" #w "[tmp], %" #w "[old]\n"			\
 	"	cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n"	\
 	"	mov	%" #w "[ret], %" #w "[tmp]"			\
@@ -379,6 +397,7 @@
 	register unsigned long x4 asm ("x4") = (unsigned long)ptr;	\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
 	"	eor	%[old1], %[old1], %[oldval1]\n"			\
 	"	eor	%[old2], %[old2], %[oldval2]\n"			\
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index e0e2b19..0fcd854 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -57,6 +57,25 @@
 	return mask;
 }
 
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
+ */
+#define arch_counter_enforce_ordering(val) do {				\
+	u64 tmp, _val = (val);						\
+									\
+	asm volatile(							\
+	"	eor	%0, %1, %1\n"					\
+	"	add	%0, sp, %0\n"					\
+	"	ldr	xzr, [%0]"					\
+	: "=r" (tmp) : "r" (_val));					\
+} while (0)
+
 #define __smp_mb()	dmb(ish)
 #define __smp_rmb()	dmb(ishld)
 #define __smp_wmb()	dmb(ishst)
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 43da6dd..806e9dc 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -11,6 +11,7 @@
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
 #define CTR_IMINLINE_SHIFT	0
+#define CTR_IMINLINE_MASK	0xf
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
@@ -18,7 +19,7 @@
 #define CTR_DIC_SHIFT		29
 
 #define CTR_CACHE_MINLINE_MASK	\
-	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+	(0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT)
 
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 665c78e..3e7dda6 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -79,7 +79,7 @@
 	 * IPI all online CPUs so that they undergo a context synchronization
 	 * event and are forced to refetch the new instructions.
 	 */
-#ifdef CONFIG_KGDB
+
 	/*
 	 * KGDB performs cache maintenance with interrupts disabled, so we
 	 * will deadlock trying to IPI the secondary CPUs. In theory, we can
@@ -89,9 +89,9 @@
 	 * the patching operation, so we don't need extra IPIs here anyway.
 	 * In which case, add a KGDB-specific bodge and return early.
 	 */
-	if (kgdb_connected && irqs_disabled())
+	if (in_dbg_master())
 		return;
-#endif
+
 	kick_all_cpus_sync();
 }
 
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index d064a50..5665a3f 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -19,16 +19,17 @@
 {
 	__uint128_t tmp;
 	u64 sum;
+	int n = ihl; /* we want it signed */
 
 	tmp = *(const __uint128_t *)iph;
 	iph += 16;
-	ihl -= 4;
+	n -= 4;
 	tmp += ((tmp >> 64) | (tmp << 64));
 	sum = tmp >> 64;
 	do {
 		sum += *(const u32 *)iph;
 		iph += 4;
-	} while (--ihl);
+	} while (--n > 0);
 
 	sum += ((sum >> 32) | (sum << 32));
 	return csum_fold((__force u32)(sum >> 32));
diff --git a/arch/arm64/include/asm/clocksource.h b/arch/arm64/include/asm/clocksource.h
index 0ece64a..0c79104 100644
--- a/arch/arm64/include/asm/clocksource.h
+++ b/arch/arm64/include/asm/clocksource.h
@@ -2,8 +2,11 @@
 #ifndef _ASM_CLOCKSOURCE_H
 #define _ASM_CLOCKSOURCE_H
 
+#include <asm/vdso/clocksource.h>
+
 struct arch_clocksource_data {
-	bool vdso_direct;	/* Usable for direct VDSO access? */
+	/* Usable for direct VDSO access? */
+	enum vdso_arch_clockmode clock_mode;
 };
 
 #endif
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index b0d53a2..7b4172c 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -4,6 +4,9 @@
  */
 #ifndef __ASM_COMPAT_H
 #define __ASM_COMPAT_H
+
+#include <asm-generic/compat.h>
+
 #ifdef CONFIG_COMPAT
 
 /*
@@ -13,8 +16,6 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 
-#include <asm-generic/compat.h>
-
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
 #define COMPAT_UTS_MACHINE	"armv8b\0\0"
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index ac1dbca..1dc3c76 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -54,7 +54,8 @@
 #define ARM64_WORKAROUND_1463225		44
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
+#define ARM64_WORKAROUND_1542419		47
 
-#define ARM64_NCAPS				47
+#define ARM64_NCAPS				48
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 9cde5d2..ccae05d 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -262,6 +262,8 @@
 /*
  * CPU feature detected at boot time based on feature of one or more CPUs.
  * All possible conflicts for a late CPU are ignored.
+ * NOTE: this means that a late CPU with the feature will *not* cause the
+ * capability to be advertised by cpus_have_*cap()!
  */
 #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE		\
 	(ARM64_CPUCAP_SCOPE_LOCAL_CPU		|	\
@@ -601,7 +603,7 @@
 		 cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF));
 }
 
-static inline bool system_uses_irq_prio_masking(void)
+static __always_inline bool system_uses_irq_prio_masking(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index 063c964..48bfbf7 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -36,7 +36,7 @@
 	trace_hardirqs_off();
 }
 
-static inline unsigned long local_daif_save(void)
+static inline unsigned long local_daif_save_flags(void)
 {
 	unsigned long flags;
 
@@ -48,6 +48,15 @@
 			flags |= PSR_I_BIT;
 	}
 
+	return flags;
+}
+
+static inline unsigned long local_daif_save(void)
+{
+	unsigned long flags;
+
+	flags = local_daif_save_flags();
+
 	local_daif_mask();
 
 	return flags;
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 7619f47..d825e35 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -109,6 +109,8 @@
 
 void user_rewind_single_step(struct task_struct *task);
 void user_fastforward_single_step(struct task_struct *task);
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task);
 
 void kernel_enable_single_step(struct pt_regs *regs);
 void kernel_disable_single_step(void);
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index a6e5da7..9679b74 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -65,8 +65,8 @@
 #define EARLY_KASLR	(0)
 #endif
 
-#define EARLY_ENTRIES(vstart, vend, shift) (((vend) >> (shift)) \
-					- ((vstart) >> (shift)) + 1 + EARLY_KASLR)
+#define EARLY_ENTRIES(vstart, vend, shift) \
+	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1 + EARLY_KASLR)
 
 #define EARLY_PGDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT))
 
@@ -89,12 +89,6 @@
 #define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
 #define IDMAP_DIR_SIZE		(IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
 
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
-#define RESERVED_TTBR0_SIZE	(PAGE_SIZE)
-#else
-#define RESERVED_TTBR0_SIZE	(0)
-#endif
-
 /* Initial memory map size */
 #if ARM64_SWAPPER_USES_SECTION_MAPS
 #define SWAPPER_BLOCK_SHIFT	SECTION_SHIFT
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index ddf9d76..9be64c0 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -72,11 +72,12 @@
  * IMO:		Override CPSR.I and enable signaling with VI
  * FMO:		Override CPSR.F and enable signaling with VF
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
+ * PTW:		Take a stage2 fault if a stage1 walk steps in device memory
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
 			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
-			 HCR_FMO | HCR_IMO)
+			 HCR_FMO | HCR_IMO | HCR_PTW )
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
@@ -275,6 +276,7 @@
 #define CPTR_EL2_DEFAULT	CPTR_EL2_RES1
 
 /* Hyp Debug Configuration Register bits */
+#define MDCR_EL2_TTRF		(1 << 19)
 #define MDCR_EL2_TPMS		(1 << 14)
 #define MDCR_EL2_E2PB_MASK	(UL(0x3))
 #define MDCR_EL2_E2PB_SHIFT	(UL(12))
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 44a2437..c54e759 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -60,7 +60,7 @@
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
+extern void __kvm_flush_cpu_context(struct kvm_vcpu *vcpu);
 
 extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high);
 
@@ -88,6 +88,34 @@
 		*__hyp_this_cpu_ptr(sym);				\
 	 })
 
+#define __KVM_EXTABLE(from, to)						\
+	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
+	"	.align		3\n"					\
+	"	.long		(" #from " - .), (" #to " - .)\n"	\
+	"	.popsection\n"
+
+
+#define __kvm_at(at_op, addr)						\
+( { 									\
+	int __kvm_at_err = 0;						\
+	u64 spsr, elr;							\
+	asm volatile(							\
+	"	mrs	%1, spsr_el2\n"					\
+	"	mrs	%2, elr_el2\n"					\
+	"1:	at	"at_op", %3\n"					\
+	"	isb\n"							\
+	"	b	9f\n"						\
+	"2:	msr	spsr_el2, %1\n"					\
+	"	msr	elr_el2, %2\n"					\
+	"	mov	%w0, %4\n"					\
+	"9:\n"								\
+	__KVM_EXTABLE(1b, 2b)						\
+	: "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr)		\
+	: "r" (addr), "i" (-EFAULT));					\
+	__kvm_at_err;							\
+} )
+
+
 #else /* __ASSEMBLY__ */
 
 .macro hyp_adr_this_cpu reg, sym, tmp
@@ -113,6 +141,21 @@
 	kern_hyp_va	\vcpu
 .endm
 
+/*
+ * KVM extable for unexpected exceptions.
+ * In the same format _asm_extable, but output to a different section so that
+ * it can be mapped to EL2. The KVM version is not sorted. The caller must
+ * ensure:
+ * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented
+ * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup.
+ */
+.macro	_kvm_extable, from, to
+	.pushsection	__kvm_ex_table, "a"
+	.align		3
+	.long		(\from - .), (\to - .)
+	.popsection
+.endm
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index d69c1ef..f65ff6b 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -97,12 +97,6 @@
 	vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK);
 }
 
-static inline void vcpu_ptrauth_setup_lazy(struct kvm_vcpu *vcpu)
-{
-	if (vcpu_has_ptrauth(vcpu))
-		vcpu_ptrauth_disable(vcpu);
-}
-
 static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.vsesr_el2;
@@ -204,6 +198,38 @@
 		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
 }
 
+/*
+ * The layout of SPSR for an AArch32 state is different when observed from an
+ * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
+ * view given an AArch64 view.
+ *
+ * In ARM DDI 0487E.a see:
+ *
+ * - The AArch64 view (SPSR_EL2) in section C5.2.18, page C5-426
+ * - The AArch32 view (SPSR_abt) in section G8.2.126, page G8-6256
+ * - The AArch32 view (SPSR_und) in section G8.2.132, page G8-6280
+ *
+ * Which show the following differences:
+ *
+ * | Bit | AA64 | AA32 | Notes                       |
+ * +-----+------+------+-----------------------------|
+ * | 24  | DIT  | J    | J is RES0 in ARMv8          |
+ * | 21  | SS   | DIT  | SS doesn't exist in AArch32 |
+ *
+ * ... and all other bits are (currently) common.
+ */
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	const unsigned long overlap = BIT(24) | BIT(21);
+	unsigned long dit = !!(spsr & PSR_AA32_DIT_BIT);
+
+	spsr &= ~overlap;
+
+	spsr |= dit << 21;
+
+	return spsr;
+}
+
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 {
 	u32 mode;
@@ -263,12 +289,17 @@
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
 }
 
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
+}
+
 static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 {
 	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
-static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
 }
@@ -276,7 +307,7 @@
 static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
-		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+		kvm_vcpu_abt_iss1tw(vcpu); /* AF/DBM update */
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
@@ -305,6 +336,11 @@
 	return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
 }
 
+static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+}
+
 static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC;
@@ -342,6 +378,9 @@
 
 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
+	if (kvm_vcpu_abt_iss1tw(vcpu))
+		return true;
+
 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f656169..697702a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -182,6 +182,7 @@
 #define c2_TTBR1	(TTBR1_EL1 * 2)	/* Translation Table Base Register 1 */
 #define c2_TTBR1_high	(c2_TTBR1 + 1)	/* TTBR1 top 32 bits */
 #define c2_TTBCR	(TCR_EL1 * 2)	/* Translation Table Base Control R. */
+#define c2_TTBCR2	(c2_TTBCR + 1)	/* Translation Table Base Control R. 2 */
 #define c3_DACR		(DACR32_EL2 * 2)/* Domain Access Control Register */
 #define c5_DFSR		(ESR_EL1 * 2)	/* Data Fault Status Register */
 #define c5_IFSR		(IFSR32_EL2 * 2)/* Instruction Fault Status Register */
@@ -209,6 +210,7 @@
 #define cp14_DBGWCR0	(DBGWCR0_EL1 * 2)
 #define cp14_DBGWVR0	(DBGWVR0_EL1 * 2)
 #define cp14_DBGDCCINT	(MDCCINT_EL1 * 2)
+#define cp14_DBGVCR	(DBGVCR32_EL2 * 2)
 
 #define NR_COPRO_REGS	(NR_SYS_REGS * 2)
 
@@ -392,8 +394,10 @@
  * CP14 and CP15 live in the same array, as they are backed by the
  * same system registers.
  */
-#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r)])
-#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r)])
+#define CPx_BIAS		IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
+
+#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
+#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
 
 struct kvm_vm_stat {
 	ulong remote_tlb_flush;
@@ -425,7 +429,7 @@
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva_range(struct kvm *kvm,
-			unsigned long start, unsigned long end);
+			unsigned long start, unsigned long end, unsigned flags);
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
@@ -548,6 +552,7 @@
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
 void kvm_arm_init_debug(void);
+void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
@@ -677,4 +682,6 @@
 #define kvm_arm_vcpu_sve_finalized(vcpu) \
 	((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED)
 
+#define kvm_arm_vcpu_loaded(vcpu)	((vcpu)->arch.sysregs_loaded_on_cpu)
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 97f21cc..7f7fdb1 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -71,6 +71,9 @@
 
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
 void __debug_switch_to_host(struct kvm_vcpu *vcpu);
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+
 
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
index 02b5c48..b204501 100644
--- a/arch/arm64/include/asm/kvm_mmio.h
+++ b/arch/arm64/include/asm/kvm_mmio.h
@@ -10,13 +10,11 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_arm.h>
 
-/*
- * This is annoying. The mmio code requires this, even if we don't
- * need any decoding. To be fixed.
- */
 struct kvm_decode {
 	unsigned long rt;
 	bool sign_extend;
+	/* Witdth of the register accessed by the faulting instruction is 64-bits */
+	bool sixty_four;
 };
 
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index 1b26629..ebee311 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -4,4 +4,20 @@
 #define __ALIGN		.align 2
 #define __ALIGN_STR	".align 2"
 
+/*
+ * Annotate a function as position independent, i.e., safe to be called before
+ * the kernel virtual mapping is activated.
+ */
+#define SYM_FUNC_START_PI(x)			\
+		SYM_FUNC_START_ALIAS(__pi_##x);	\
+		SYM_FUNC_START(x)
+
+#define SYM_FUNC_START_WEAK_PI(x)		\
+		SYM_FUNC_START_ALIAS(__pi_##x);	\
+		SYM_FUNC_START_WEAK(x)
+
+#define SYM_FUNC_END_PI(x)			\
+		SYM_FUNC_END(x);		\
+		SYM_FUNC_END_ALIAS(__pi_##x)
+
 #endif
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
index 80b3882..5de1321 100644
--- a/arch/arm64/include/asm/lse.h
+++ b/arch/arm64/include/asm/lse.h
@@ -6,6 +6,8 @@
 
 #if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
 
+#define __LSE_PREAMBLE	".arch_extension lse\n"
+
 #include <linux/compiler_types.h>
 #include <linux/export.h>
 #include <linux/jump_label.h>
@@ -14,8 +16,6 @@
 #include <asm/atomic_lse.h>
 #include <asm/cpucaps.h>
 
-__asm__(".arch_extension	lse");
-
 extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
 extern struct static_key_false arm64_const_caps_ready;
 
@@ -34,7 +34,7 @@
 
 /* In-line patching at runtime */
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)				\
-	ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS)
+	ALTERNATIVE(llsc, __LSE_PREAMBLE lse, ARM64_HAS_LSE_ATOMICS)
 
 #else	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index c23c473..67b6b90 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -178,7 +178,6 @@
 #include <linux/bitops.h>
 #include <linux/mmdebug.h>
 
-extern s64			physvirt_offset;
 extern s64			memstart_addr;
 /* PHYS_OFFSET - the physical address of the start of memory. */
 #define PHYS_OFFSET		({ VM_BUG_ON(memstart_addr & 1); memstart_addr; })
@@ -219,7 +218,7 @@
 	((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
 
 #define untagged_addr(addr)	({					\
-	u64 __addr = (__force u64)addr;					\
+	u64 __addr = (__force u64)(addr);					\
 	__addr &= __untagged_addr(__addr);				\
 	(__force __typeof__(addr))__addr;				\
 })
@@ -248,13 +247,13 @@
 
 
 /*
- * The linear kernel range starts at the bottom of the virtual address
- * space. Testing the top bit for the start of the region is a
- * sufficient check and avoids having to worry about the tag.
+ * Check whether an arbitrary address is within the linear map, which
+ * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the
+ * kernel's TTBR1 address range.
  */
-#define __is_lm_address(addr)	(!(((u64)addr) & BIT(vabits_actual - 1)))
+#define __is_lm_address(addr)	(((u64)(addr) ^ PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET))
 
-#define __lm_to_phys(addr)	(((addr) + physvirt_offset))
+#define __lm_to_phys(addr)	(((addr) & ~PAGE_OFFSET) + PHYS_OFFSET)
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
 
 #define __virt_to_phys_nodebug(x) ({					\
@@ -272,7 +271,7 @@
 #define __phys_addr_symbol(x)	__pa_symbol_nodebug(x)
 #endif /* CONFIG_DEBUG_VIRTUAL */
 
-#define __phys_to_virt(x)	((unsigned long)((x) - physvirt_offset))
+#define __phys_to_virt(x)	((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET)
 #define __phys_to_kimg(x)	((unsigned long)((x) + kimage_voffset))
 
 /*
@@ -316,6 +315,11 @@
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
 #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
+#define page_to_virt(x)	({						\
+	__typeof__(x) __page = x;					\
+	void *__addr = __va(page_to_phys(__page));			\
+	(void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
+})
 #define virt_to_page(x)		pfn_to_page(virt_to_pfn(x))
 #else
 #define page_to_virt(x)	({						\
@@ -333,7 +337,7 @@
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */
 
 #define virt_addr_valid(addr)	({					\
-	__typeof__(addr) __addr = addr;					\
+	__typeof__(addr) __addr = __tag_reset(addr);			\
 	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
 })
 
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 3827ff4..fb564de 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -36,11 +36,11 @@
 }
 
 /*
- * Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0.
+ * Set TTBR0 to reserved_pg_dir. No translations will be possible via TTBR0.
  */
 static inline void cpu_set_reserved_ttbr0(void)
 {
-	unsigned long ttbr = phys_to_ttbr(__pa_symbol(empty_zero_page));
+	unsigned long ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
 
 	write_sysreg(ttbr, ttbr0_el1);
 	isb();
@@ -63,10 +63,7 @@
 
 static inline bool __cpu_uses_extended_idmap(void)
 {
-	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52))
-		return false;
-
-	return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS));
+	return unlikely(idmap_t0sz != TCR_T0SZ(vabits_actual));
 }
 
 /*
@@ -187,9 +184,9 @@
 		return;
 
 	if (mm == &init_mm)
-		ttbr = __pa_symbol(empty_zero_page);
+		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/numa.h b/arch/arm64/include/asm/numa.h
index 626ad01..dd87039 100644
--- a/arch/arm64/include/asm/numa.h
+++ b/arch/arm64/include/asm/numa.h
@@ -25,6 +25,9 @@
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
 static inline const struct cpumask *cpumask_of_node(int node)
 {
+	if (node == NUMA_NO_NODE)
+		return cpu_all_mask;
+
 	return node_to_cpumask_map[node];
 }
 #endif
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 8dc6c5c..99b0a32 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -54,7 +54,7 @@
 #define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
 #define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
 #define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
-#define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
+#define PAGE_HYP_DEVICE		__pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN)
 
 #define PAGE_S2_MEMATTR(attr)						\
 	({								\
@@ -85,13 +85,12 @@
 #define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
-#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
 
 #define __P000  PAGE_NONE
 #define __P001  PAGE_READONLY
 #define __P010  PAGE_READONLY
 #define __P011  PAGE_READONLY
-#define __P100  PAGE_EXECONLY
+#define __P100  PAGE_READONLY_EXEC
 #define __P101  PAGE_READONLY_EXEC
 #define __P110  PAGE_READONLY_EXEC
 #define __P111  PAGE_READONLY_EXEC
@@ -100,7 +99,7 @@
 #define __S001  PAGE_READONLY
 #define __S010  PAGE_SHARED
 #define __S011  PAGE_SHARED
-#define __S100  PAGE_EXECONLY
+#define __S100  PAGE_READONLY_EXEC
 #define __S101  PAGE_READONLY_EXEC
 #define __S110  PAGE_SHARED_EXEC
 #define __S111  PAGE_SHARED_EXEC
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 565aa45..a92a187 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -23,6 +23,8 @@
 #define VMALLOC_START		(MODULES_END)
 #define VMALLOC_END		(- PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
+#define vmemmap			((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
+
 #define FIRST_USER_ADDRESS	0UL
 
 #ifndef __ASSEMBLY__
@@ -33,8 +35,6 @@
 #include <linux/mm_types.h>
 #include <linux/sched.h>
 
-extern struct page *vmemmap;
-
 extern void __pte_error(const char *file, int line, unsigned long val);
 extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pud_error(const char *file, int line, unsigned long val);
@@ -96,14 +96,8 @@
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-/*
- * Execute-only user mappings do not have the PTE_USER bit set. All valid
- * kernel mappings have the PTE_UXN bit set.
- */
 #define pte_valid_not_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
-#define pte_valid_young(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 
@@ -111,14 +105,17 @@
  * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
  * so that we don't erroneously return false for pages that have been
  * remapped as PROT_NONE but are yet to be flushed from the TLB.
+ * Note that we can't make any assumptions based on the state of the access
+ * flag, since ptep_clear_flush_young() elides a DSB when invalidating the
+ * TLB.
  */
 #define pte_accessible(mm, pte)	\
-	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte))
+	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
 
 /*
  * p??_access_permitted() is true for valid user mappings (subject to the
- * write permission check) other than user execute-only which do not have the
- * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set.
+ * write permission check). PROT_NONE mappings do not have the PTE_VALID bit
+ * set.
  */
 #define pte_access_permitted(pte, write) \
 	(pte_valid_user(pte) && (!(write) || pte_write(pte)))
@@ -139,13 +136,6 @@
 	return pte;
 }
 
-static inline pte_t pte_wrprotect(pte_t pte)
-{
-	pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
-	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
-	return pte;
-}
-
 static inline pte_t pte_mkwrite(pte_t pte)
 {
 	pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
@@ -171,6 +161,20 @@
 	return pte;
 }
 
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	/*
+	 * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
+	 * clear), set the PTE_DIRTY bit.
+	 */
+	if (pte_hw_dirty(pte))
+		pte = pte_mkdirty(pte);
+
+	pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
+	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+	return pte;
+}
+
 static inline pte_t pte_mkold(pte_t pte)
 {
 	return clear_pte_bit(pte, __pgprot(PTE_AF));
@@ -460,7 +464,9 @@
 extern pgd_t init_pg_end[];
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t idmap_pg_end[];
 extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
+extern pgd_t reserved_pg_dir[PTRS_PER_PGD];
 
 extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd);
 
@@ -785,12 +791,6 @@
 	pte = READ_ONCE(*ptep);
 	do {
 		old_pte = pte;
-		/*
-		 * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
-		 * clear), set the PTE_DIRTY bit.
-		 */
-		if (pte_hw_dirty(pte))
-			pte = pte_mkdirty(pte);
 		pte = pte_wrprotect(pte);
 		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
 					       pte_val(old_pte), pte_val(pte));
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 7a24bad..076a415 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -3,7 +3,6 @@
 #define __ASM_POINTER_AUTH_H
 
 #include <linux/bitops.h>
-#include <linux/random.h>
 
 #include <asm/cpufeature.h>
 #include <asm/memory.h>
@@ -30,6 +29,13 @@
 	struct ptrauth_key apga;
 };
 
+/*
+ * Only include random.h once ptrauth_keys_* structures are defined
+ * to avoid yet another circular include hell (random.h * ends up
+ * including asm/smp.h, which requires ptrauth_keys_kernel).
+ */
+#include <linux/random.h>
+
 static inline void ptrauth_keys_init(struct ptrauth_keys *keys)
 {
 	if (system_supports_address_auth()) {
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index fbebb41..92b2575 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -62,6 +62,7 @@
 #define PSR_AA32_I_BIT		0x00000080
 #define PSR_AA32_A_BIT		0x00000100
 #define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_PAN_BIT	0x00400000
 #define PSR_AA32_SSBS_BIT	0x00800000
 #define PSR_AA32_DIT_BIT	0x01000000
 #define PSR_AA32_Q_BIT		0x08000000
@@ -298,7 +299,17 @@
 
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
-	return regs->regs[0];
+	unsigned long val = regs->regs[0];
+
+	/*
+	 * Audit currently uses regs_return_value() instead of
+	 * syscall_get_return_value(). Apply the same sign-extension here until
+	 * audit is updated to use syscall_get_return_value().
+	 */
+	if (compat_user_mode(regs))
+		val = sign_extend64(val, 31);
+
+	return val;
 }
 
 static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 788ae97..25a73aa 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -15,6 +15,7 @@
 extern char __idmap_text_start[], __idmap_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __inittext_begin[], __inittext_end[];
+extern char __exittext_begin[], __exittext_end[];
 extern char __irqentry_text_start[], __irqentry_text_end[];
 extern char __mmuoff_data_start[], __mmuoff_data_end[];
 extern char __entry_tramp_text_start[], __entry_tramp_text_end[];
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index a0c8a0b..0eadbf9 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -46,7 +46,12 @@
  * Logical CPU mapping.
  */
 extern u64 __cpu_logical_map[NR_CPUS];
-#define cpu_logical_map(cpu)    __cpu_logical_map[cpu]
+extern u64 cpu_logical_map(int cpu);
+
+static inline void set_cpu_logical_map(int cpu, u64 hwid)
+{
+	__cpu_logical_map[cpu] = hwid;
+}
 
 struct seq_file;
 
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 65299a2..03e2089 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -29,25 +29,36 @@
 	regs->regs[0] = regs->orig_x0;
 }
 
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	unsigned long val = regs->regs[0];
+
+	if (is_compat_thread(task_thread_info(task)))
+		val = sign_extend64(val, 31);
+
+	return val;
+}
 
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	unsigned long error = regs->regs[0];
-	return IS_ERR_VALUE(error) ? error : 0;
-}
+	unsigned long error = syscall_get_return_value(task, regs);
 
-static inline long syscall_get_return_value(struct task_struct *task,
-					    struct pt_regs *regs)
-{
-	return regs->regs[0];
+	return IS_ERR_VALUE(error) ? error : 0;
 }
 
 static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	regs->regs[0] = (long) error ? error : val;
+	if (error)
+		val = error;
+
+	if (is_compat_thread(task_thread_info(task)))
+		val = lower_32_bits(val);
+
+	regs->regs[0] = val;
 }
 
 #define SYSCALL_MAX_ARGS 6
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 6e919fa..9b68f1b 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -49,7 +49,9 @@
 #ifndef CONFIG_BROKEN_GAS_INST
 
 #ifdef __ASSEMBLY__
-#define __emit_inst(x)			.inst (x)
+// The space separator is omitted so that __emit_inst(x) can be parsed as
+// either an assembler directive or an assembler macro argument.
+#define __emit_inst(x)			.inst(x)
 #else
 #define __emit_inst(x)			".inst " __stringify((x)) "\n\t"
 #endif
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index f0cec41..4e3ed70 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -91,6 +91,7 @@
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_FSCHECK		(1 << TIF_FSCHECK)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 127712b..b9a37a4 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -62,8 +62,13 @@
 {
 	unsigned long ret, limit = current_thread_info()->addr_limit;
 
+	/*
+	 * Asynchronous I/O running in a kernel thread does not have the
+	 * TIF_TAGGED_ADDR flag of the process owning the mm, so always untag
+	 * the user address before checking.
+	 */
 	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) &&
-	    test_thread_flag(TIF_TAGGED_ADDR))
+	    (current->flags & PF_KTHREAD || test_thread_flag(TIF_TAGGED_ADDR)))
 		addr = untagged_addr(addr);
 
 	__chk_user_ptr(addr);
@@ -107,8 +112,8 @@
 	local_irq_save(flags);
 	ttbr = read_sysreg(ttbr1_el1);
 	ttbr &= ~TTBR_ASID_MASK;
-	/* reserved_ttbr0 placed before swapper_pg_dir */
-	write_sysreg(ttbr - RESERVED_TTBR0_SIZE, ttbr0_el1);
+	/* reserved_pg_dir placed before swapper_pg_dir */
+	write_sysreg(ttbr - PAGE_SIZE, ttbr0_el1);
 	isb();
 	/* Set reserved ASID */
 	write_sysreg(ttbr, ttbr1_el1);
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 2629a68..8c1b73d 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -25,8 +25,8 @@
 #define __NR_compat_gettimeofday	78
 #define __NR_compat_sigreturn		119
 #define __NR_compat_rt_sigreturn	173
-#define __NR_compat_clock_getres	247
 #define __NR_compat_clock_gettime	263
+#define __NR_compat_clock_getres	264
 #define __NR_compat_clock_gettime64	403
 #define __NR_compat_clock_getres_time64	406
 
@@ -42,7 +42,6 @@
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
-#define __ARCH_WANT_SYS_CLONE3
 
 #ifndef __COMPAT_SYSCALL_NR
 #include <uapi/asm/unistd.h>
diff --git a/arch/arm64/include/asm/vdso/clocksource.h b/arch/arm64/include/asm/vdso/clocksource.h
new file mode 100644
index 0000000..8019f61
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/clocksource.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSOCLOCKSOURCE_H
+#define __ASM_VDSOCLOCKSOURCE_H
+
+enum vdso_arch_clockmode {
+	/* vdso clocksource not usable */
+	VDSO_CLOCKMODE_NONE,
+	/* vdso clocksource for both 32 and 64bit tasks */
+	VDSO_CLOCKMODE_ARCHTIMER,
+	/* vdso clocksource for 64bit tasks only */
+	VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT,
+};
+
+#endif
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index c50ee1b..413d42e 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -10,6 +10,7 @@
 #include <asm/unistd.h>
 #include <uapi/linux/time.h>
 
+#include <asm/vdso/clocksource.h>
 #include <asm/vdso/compat_barrier.h>
 
 #define __VDSO_USE_SYSCALL		ULLONG_MAX
@@ -117,10 +118,10 @@
 	u64 res;
 
 	/*
-	 * clock_mode == 0 implies that vDSO are enabled otherwise
+	 * clock_mode == ARCHTIMER implies that vDSO are enabled otherwise
 	 * fallback on syscall.
 	 */
-	if (clock_mode)
+	if (clock_mode != VDSO_CLOCKMODE_ARCHTIMER)
 		return __VDSO_USE_SYSCALL;
 
 	/*
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index b08f476..d7361fa 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -10,6 +10,8 @@
 #include <asm/unistd.h>
 #include <uapi/linux/time.h>
 
+#include <asm/vdso/clocksource.h>
+
 #define __VDSO_USE_SYSCALL		ULLONG_MAX
 
 #define VDSO_HAS_CLOCK_GETRES		1
@@ -71,10 +73,10 @@
 	u64 res;
 
 	/*
-	 * clock_mode == 0 implies that vDSO are enabled otherwise
+	 * clock_mode != NONE implies that vDSO are enabled otherwise
 	 * fallback on syscall.
 	 */
-	if (clock_mode)
+	if (clock_mode == VDSO_CLOCKMODE_NONE)
 		return __VDSO_USE_SYSCALL;
 
 	/*
@@ -83,11 +85,7 @@
 	 */
 	isb();
 	asm volatile("mrs %0, cntvct_el0" : "=r" (res) :: "memory");
-	/*
-	 * This isb() is required to prevent that the seq lock is
-	 * speculated.#
-	 */
-	isb();
+	arch_counter_enforce_ordering(res);
 
 	return res;
 }
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
index 0c20a7c..e50f267 100644
--- a/arch/arm64/include/asm/vdso/vsyscall.h
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -24,9 +24,7 @@
 static __always_inline
 int __arm64_get_clock_mode(struct timekeeper *tk)
 {
-	u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
-
-	return use_syscall;
+	return tk->tkr_mono.clock->archdata.clock_mode;
 }
 #define __arch_get_clock_mode __arm64_get_clock_mode
 
diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h
index 3333950..ea48721 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 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 @@
 	"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 @@
 	"	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;