6 files changed, 21 insertions, 10 deletions
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 00d97b8a757f..51746005239b 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -26,9 +26,12 @@ void __init apply_alternatives_all(void);
 bool alternative_is_applied(u16 cpucap);
 
 #ifdef CONFIG_MODULES
-void apply_alternatives_module(void *start, size_t length);
+int apply_alternatives_module(void *start, size_t length);
 #else
-static inline void apply_alternatives_module(void *start, size_t length) { }
+static inline int apply_alternatives_module(void *start, size_t length)
+{
+	return 0;
+}
 #endif
 
 void alt_cb_patch_nops(struct alt_instr *alt, __le32 *origptr,
diff --git a/arch/arm64/include/asm/kfence.h b/arch/arm64/include/asm/kfence.h
index a81937fae9f6..21dbc9dda747 100644
--- a/arch/arm64/include/asm/kfence.h
+++ b/arch/arm64/include/asm/kfence.h
@@ -10,8 +10,6 @@
 
 #include <asm/set_memory.h>
 
-static inline bool arch_kfence_init_pool(void) { return true; }
-
 static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
 	set_memory_valid(addr, 1, !protect);
@@ -25,6 +23,7 @@ static inline bool arm64_kfence_can_set_direct_map(void)
 {
 	return !kfence_early_init;
 }
+bool arch_kfence_init_pool(void);
 #else /* CONFIG_KFENCE */
 static inline bool arm64_kfence_can_set_direct_map(void) { return false; }
 #endif /* CONFIG_KFENCE */
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 9abcc8ef3087..b57b2bb00967 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -77,7 +77,7 @@ __percpu_##name##_case_##sz(void *ptr, unsigned long val)		\
 	"	stxr" #sfx "\t%w[loop], %" #w "[tmp], %[ptr]\n"		\
 	"	cbnz	%w[loop], 1b",					\
 	/* LSE atomics */						\
-		#op_lse "\t%" #w "[val], %[ptr]\n"			\
+		#op_lse "\t%" #w "[val], %" #w "[tmp], %[ptr]\n"	\
 		__nops(3))						\
 	: [loop] "=&r" (loop), [tmp] "=&r" (tmp),			\
 	  [ptr] "+Q"(*(u##sz *)ptr)					\
@@ -124,9 +124,16 @@ PERCPU_RW_OPS(8)
 PERCPU_RW_OPS(16)
 PERCPU_RW_OPS(32)
 PERCPU_RW_OPS(64)
-PERCPU_OP(add, add, stadd)
-PERCPU_OP(andnot, bic, stclr)
-PERCPU_OP(or, orr, stset)
+
+/*
+ * Use value-returning atomics for CPU-local ops as they are more likely
+ * to execute "near" to the CPU (e.g. in L1$).
+ *
+ * https://lore.kernel.org/r/e7d539ed-ced0-4b96-8ecd-048a5b803b85@paulmck-laptop
+ */
+PERCPU_OP(add, add, ldadd)
+PERCPU_OP(andnot, bic, ldclr)
+PERCPU_OP(or, orr, ldset)
 PERCPU_RET_OP(add, add, ldadd)
 
 #undef PERCPU_RW_OPS
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index aa89c2e67ebc..0944e296dd4a 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -293,7 +293,8 @@ static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot)
 static inline pte_t pte_mkwrite_novma(pte_t pte)
 {
 	pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
-	pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+	if (pte_sw_dirty(pte))
+		pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
 	return pte;
 }
 
diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
index a76f9b387a26..c59f6324f2bb 100644
--- a/arch/arm64/include/asm/scs.h
+++ b/arch/arm64/include/asm/scs.h
@@ -53,7 +53,7 @@ enum {
 	EDYNSCS_INVALID_CFA_OPCODE		= 4,
 };
 
-int __pi_scs_patch(const u8 eh_frame[], int size);
+int __pi_scs_patch(const u8 eh_frame[], int size, bool skip_dry_run);
 
 #endif /* __ASSEMBLY __ */
 
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index 8fef12626090..900454aaa292 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -117,6 +117,7 @@ void spectre_bhb_patch_wa3(struct alt_instr *alt,
 			   __le32 *origptr, __le32 *updptr, int nr_inst);
 void spectre_bhb_patch_clearbhb(struct alt_instr *alt,
 				__le32 *origptr, __le32 *updptr, int nr_inst);
+void spectre_print_disabled_mitigations(void);
 
 #endif	/* __ASSEMBLY__ */
 #endif	/* __ASM_SPECTRE_H */