Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - KCSAN enabled for arm64.

 - Additional kselftests to exercise the syscall ABI w.r.t. SVE/FPSIMD.

 - Some more SVE clean-ups and refactoring in preparation for SME
   support (scalable matrix extensions).

 - BTI clean-ups (SYM_FUNC macros etc.)

 - arm64 atomics clean-up and codegen improvements.

 - HWCAPs for FEAT_AFP (alternate floating point behaviour) and
   FEAT_RPRESS (increased precision of reciprocal estimate and
   reciprocal square root estimate).

 - Use SHA3 instructions to speed-up XOR.

 - arm64 unwind code refactoring/unification.

 - Avoid DC (data cache maintenance) instructions when DCZID_EL0.DZP ==
   1 (potentially set by a hypervisor; user-space already does this).

 - Perf updates for arm64: support for CI-700, HiSilicon PCIe PMU,
   Marvell CN10K LLC-TAD PMU, miscellaneous clean-ups.

 - Other fixes and clean-ups; highlights: fix the handling of erratum
   1418040, correct the calculation of the nomap region boundaries,
   introduce io_stop_wc() mapped to the new DGH instruction (data
   gathering hint).

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (81 commits)
  arm64: Use correct method to calculate nomap region boundaries
  arm64: Drop outdated links in comments
  arm64: perf: Don't register user access sysctl handler multiple times
  drivers: perf: marvell_cn10k: fix an IS_ERR() vs NULL check
  perf/smmuv3: Fix unused variable warning when CONFIG_OF=n
  arm64: errata: Fix exec handling in erratum 1418040 workaround
  arm64: Unhash early pointer print plus improve comment
  asm-generic: introduce io_stop_wc() and add implementation for ARM64
  arm64: Ensure that the 'bti' macro is defined where linkage.h is included
  arm64: remove __dma_*_area() aliases
  docs/arm64: delete a space from tagged-address-abi
  arm64: Enable KCSAN
  kselftest/arm64: Add pidbench for floating point syscall cases
  arm64/fp: Add comments documenting the usage of state restore functions
  kselftest/arm64: Add a test program to exercise the syscall ABI
  kselftest/arm64: Allow signal tests to trigger from a function
  kselftest/arm64: Parameterise ptrace vector length information
  arm64/sve: Minor clarification of ABI documentation
  arm64/sve: Generalise vector length configuration prctl() for SME
  arm64/sve: Make sysctl interface for SVE reusable by SME
  ...

12 files changed, 193 insertions, 262 deletions

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 136d13f3d6e9..e8bd0af0141c 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -791,6 +791,16 @@ alternative_endif
 	.endm
 
 /*
+ * Branch Target Identifier (BTI)
+ */
+	.macro  bti, targets
+	.equ	.L__bti_targets_c, 34
+	.equ	.L__bti_targets_j, 36
+	.equ	.L__bti_targets_jc,38
+	hint	#.L__bti_targets_\targets
+	.endm
+
+/*
  * This macro emits a program property note section identifying
  * architecture features which require special handling, mainly for
  * use in assembly files included in the VDSO.
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index 13869b76b58c..fe0db8d416fb 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -44,11 +44,11 @@ __ll_sc_atomic_##op(int i, atomic_t *v)					\
 									\
 	asm volatile("// atomic_" #op "\n"				\
 	__LL_SC_FALLBACK(						\
-"	prfm	pstl1strm, %2\n"					\
-"1:	ldxr	%w0, %2\n"						\
-"	" #asm_op "	%w0, %w0, %w3\n"				\
-"	stxr	%w1, %w0, %2\n"						\
-"	cbnz	%w1, 1b\n")						\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ldxr	%w0, %2\n"					\
+	"	" #asm_op "	%w0, %w0, %w3\n"			\
+	"	stxr	%w1, %w0, %2\n"					\
+	"	cbnz	%w1, 1b\n")					\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
 	: __stringify(constraint) "r" (i));				\
 }
@@ -62,12 +62,12 @@ __ll_sc_atomic_##op##_return##name(int i, atomic_t *v)			\
 									\
 	asm volatile("// atomic_" #op "_return" #name "\n"		\
 	__LL_SC_FALLBACK(						\
-"	prfm	pstl1strm, %2\n"					\
-"1:	ld" #acq "xr	%w0, %2\n"					\
-"	" #asm_op "	%w0, %w0, %w3\n"				\
-"	st" #rel "xr	%w1, %w0, %2\n"					\
-"	cbnz	%w1, 1b\n"						\
-"	" #mb )								\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ld" #acq "xr	%w0, %2\n"				\
+	"	" #asm_op "	%w0, %w0, %w3\n"			\
+	"	st" #rel "xr	%w1, %w0, %2\n"				\
+	"	cbnz	%w1, 1b\n"					\
+	"	" #mb )							\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
 	: __stringify(constraint) "r" (i)				\
 	: cl);								\
@@ -84,12 +84,12 @@ __ll_sc_atomic_fetch_##op##name(int i, atomic_t *v)			\
 									\
 	asm volatile("// atomic_fetch_" #op #name "\n"			\
 	__LL_SC_FALLBACK(						\
-"	prfm	pstl1strm, %3\n"					\
-"1:	ld" #acq "xr	%w0, %3\n"					\
-"	" #asm_op "	%w1, %w0, %w4\n"				\
-"	st" #rel "xr	%w2, %w1, %3\n"					\
-"	cbnz	%w2, 1b\n"						\
-"	" #mb )								\
+	"	prfm	pstl1strm, %3\n"				\
+	"1:	ld" #acq "xr	%w0, %3\n"				\
+	"	" #asm_op "	%w1, %w0, %w4\n"			\
+	"	st" #rel "xr	%w2, %w1, %3\n"				\
+	"	cbnz	%w2, 1b\n"					\
+	"	" #mb )							\
 	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
 	: __stringify(constraint) "r" (i)				\
 	: cl);								\
@@ -143,11 +143,11 @@ __ll_sc_atomic64_##op(s64 i, atomic64_t *v)				\
 									\
 	asm volatile("// atomic64_" #op "\n"				\
 	__LL_SC_FALLBACK(						\
-"	prfm	pstl1strm, %2\n"					\
-"1:	ldxr	%0, %2\n"						\
-"	" #asm_op "	%0, %0, %3\n"					\
-"	stxr	%w1, %0, %2\n"						\
-"	cbnz	%w1, 1b")						\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ldxr	%0, %2\n"					\
+	"	" #asm_op "	%0, %0, %3\n"				\
+	"	stxr	%w1, %0, %2\n"					\
+	"	cbnz	%w1, 1b")					\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
 	: __stringify(constraint) "r" (i));				\
 }
@@ -161,12 +161,12 @@ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v)		\
 									\
 	asm volatile("// atomic64_" #op "_return" #name "\n"		\
 	__LL_SC_FALLBACK(						\
-"	prfm	pstl1strm, %2\n"					\
-"1:	ld" #acq "xr	%0, %2\n"					\
-"	" #asm_op "	%0, %0, %3\n"					\
-"	st" #rel "xr	%w1, %0, %2\n"					\
-"	cbnz	%w1, 1b\n"						\
-"	" #mb )								\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ld" #acq "xr	%0, %2\n"				\
+	"	" #asm_op "	%0, %0, %3\n"				\
+	"	st" #rel "xr	%w1, %0, %2\n"				\
+	"	cbnz	%w1, 1b\n"					\
+	"	" #mb )							\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
 	: __stringify(constraint) "r" (i)				\
 	: cl);								\
@@ -176,19 +176,19 @@ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v)		\
 
 #define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\
 static inline long							\
-__ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v)		\
+__ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v)			\
 {									\
 	s64 result, val;						\
 	unsigned long tmp;						\
 									\
 	asm volatile("// atomic64_fetch_" #op #name "\n"		\
 	__LL_SC_FALLBACK(						\
-"	prfm	pstl1strm, %3\n"					\
-"1:	ld" #acq "xr	%0, %3\n"					\
-"	" #asm_op "	%1, %0, %4\n"					\
-"	st" #rel "xr	%w2, %1, %3\n"					\
-"	cbnz	%w2, 1b\n"						\
-"	" #mb )								\
+	"	prfm	pstl1strm, %3\n"				\
+	"1:	ld" #acq "xr	%0, %3\n"				\
+	"	" #asm_op "	%1, %0, %4\n"				\
+	"	st" #rel "xr	%w2, %1, %3\n"				\
+	"	cbnz	%w2, 1b\n"					\
+	"	" #mb )							\
 	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
 	: __stringify(constraint) "r" (i)				\
 	: cl);								\
@@ -241,14 +241,14 @@ __ll_sc_atomic64_dec_if_positive(atomic64_t *v)
 
 	asm volatile("// atomic64_dec_if_positive\n"
 	__LL_SC_FALLBACK(
-"	prfm	pstl1strm, %2\n"
-"1:	ldxr	%0, %2\n"
-"	subs	%0, %0, #1\n"
-"	b.lt	2f\n"
-"	stlxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b\n"
-"	dmb	ish\n"
-"2:")
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	subs	%0, %0, #1\n"
+	"	b.lt	2f\n"
+	"	stlxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	"	dmb	ish\n"
+	"2:")
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	:
 	: "cc", "memory");
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index da3280f639cd..d955ade5df7c 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -11,13 +11,13 @@
 #define __ASM_ATOMIC_LSE_H
 
 #define ATOMIC_OP(op, asm_op)						\
-static inline void __lse_atomic_##op(int i, atomic_t *v)			\
+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));							\
+	"	" #asm_op "	%w[i], %[v]\n"				\
+	: [v] "+Q" (v->counter)						\
+	: [i] "r" (i));							\
 }
 
 ATOMIC_OP(andnot, stclr)
@@ -25,19 +25,27 @@ ATOMIC_OP(or, stset)
 ATOMIC_OP(xor, steor)
 ATOMIC_OP(add, stadd)
 
+static inline void __lse_atomic_sub(int i, atomic_t *v)
+{
+	__lse_atomic_add(-i, v);
+}
+
 #undef ATOMIC_OP
 
 #define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...)			\
 static inline int __lse_atomic_fetch_##op##name(int i, atomic_t *v)	\
 {									\
+	int old;							\
+									\
 	asm volatile(							\
 	__LSE_PREAMBLE							\
-"	" #asm_op #mb "	%w[i], %w[i], %[v]"				\
-	: [i] "+r" (i), [v] "+Q" (v->counter)				\
-	: "r" (v)							\
+	"	" #asm_op #mb "	%w[i], %w[old], %[v]"			\
+	: [v] "+Q" (v->counter),					\
+	  [old] "=r" (old)						\
+	: [i] "r" (i)							\
 	: cl);								\
 									\
-	return i;							\
+	return old;							\
 }
 
 #define ATOMIC_FETCH_OPS(op, asm_op)					\
@@ -54,51 +62,46 @@ ATOMIC_FETCH_OPS(add, ldadd)
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_FETCH_OPS
 
-#define ATOMIC_OP_ADD_RETURN(name, mb, cl...)				\
+#define ATOMIC_FETCH_OP_SUB(name)					\
+static inline int __lse_atomic_fetch_sub##name(int i, atomic_t *v)	\
+{									\
+	return __lse_atomic_fetch_add##name(-i, v);			\
+}
+
+ATOMIC_FETCH_OP_SUB(_relaxed)
+ATOMIC_FETCH_OP_SUB(_acquire)
+ATOMIC_FETCH_OP_SUB(_release)
+ATOMIC_FETCH_OP_SUB(        )
+
+#undef ATOMIC_FETCH_OP_SUB
+
+#define ATOMIC_OP_ADD_SUB_RETURN(name)					\
 static inline int __lse_atomic_add_return##name(int i, atomic_t *v)	\
 {									\
-	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)	\
-	: "r" (v)							\
-	: cl);								\
+	return __lse_atomic_fetch_add##name(i, v) + i;			\
+}									\
 									\
-	return i;							\
+static inline int __lse_atomic_sub_return##name(int i, atomic_t *v)	\
+{									\
+	return __lse_atomic_fetch_sub(i, v) - i;			\
 }
 
-ATOMIC_OP_ADD_RETURN(_relaxed,   )
-ATOMIC_OP_ADD_RETURN(_acquire,  a, "memory")
-ATOMIC_OP_ADD_RETURN(_release,  l, "memory")
-ATOMIC_OP_ADD_RETURN(        , al, "memory")
+ATOMIC_OP_ADD_SUB_RETURN(_relaxed)
+ATOMIC_OP_ADD_SUB_RETURN(_acquire)
+ATOMIC_OP_ADD_SUB_RETURN(_release)
+ATOMIC_OP_ADD_SUB_RETURN(        )
 
-#undef ATOMIC_OP_ADD_RETURN
+#undef ATOMIC_OP_ADD_SUB_RETURN
 
 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)
-	: "r" (v));
+	return __lse_atomic_andnot(~i, v);
 }
 
 #define ATOMIC_FETCH_OP_AND(name, mb, cl...)				\
 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)				\
-	: "r" (v)							\
-	: cl);								\
-									\
-	return i;							\
+	return __lse_atomic_fetch_andnot##name(~i, v);			\
 }
 
 ATOMIC_FETCH_OP_AND(_relaxed,   )
@@ -108,69 +111,14 @@ ATOMIC_FETCH_OP_AND(        , al, "memory")
 
 #undef ATOMIC_FETCH_OP_AND
 
-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)
-	: "r" (v));
-}
-
-#define ATOMIC_OP_SUB_RETURN(name, mb, cl...)				\
-static inline int __lse_atomic_sub_return##name(int i, atomic_t *v)	\
-{									\
-	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]"				\
-	: [i] "+&r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)	\
-	: "r" (v)							\
-	: cl);							\
-									\
-	return i;							\
-}
-
-ATOMIC_OP_SUB_RETURN(_relaxed,   )
-ATOMIC_OP_SUB_RETURN(_acquire,  a, "memory")
-ATOMIC_OP_SUB_RETURN(_release,  l, "memory")
-ATOMIC_OP_SUB_RETURN(        , al, "memory")
-
-#undef ATOMIC_OP_SUB_RETURN
-
-#define ATOMIC_FETCH_OP_SUB(name, mb, cl...)				\
-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)				\
-	: "r" (v)							\
-	: cl);								\
-									\
-	return i;							\
-}
-
-ATOMIC_FETCH_OP_SUB(_relaxed,   )
-ATOMIC_FETCH_OP_SUB(_acquire,  a, "memory")
-ATOMIC_FETCH_OP_SUB(_release,  l, "memory")
-ATOMIC_FETCH_OP_SUB(        , al, "memory")
-
-#undef ATOMIC_FETCH_OP_SUB
-
 #define ATOMIC64_OP(op, asm_op)						\
 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));							\
+	"	" #asm_op "	%[i], %[v]\n"				\
+	: [v] "+Q" (v->counter)						\
+	: [i] "r" (i));							\
 }
 
 ATOMIC64_OP(andnot, stclr)
@@ -178,19 +126,27 @@ ATOMIC64_OP(or, stset)
 ATOMIC64_OP(xor, steor)
 ATOMIC64_OP(add, stadd)
 
+static inline void __lse_atomic64_sub(s64 i, atomic64_t *v)
+{
+	__lse_atomic64_add(-i, v);
+}
+
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...)			\
 static inline long __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)\
 {									\
+	s64 old;							\
+									\
 	asm volatile(							\
 	__LSE_PREAMBLE							\
-"	" #asm_op #mb "	%[i], %[i], %[v]"				\
-	: [i] "+r" (i), [v] "+Q" (v->counter)				\
-	: "r" (v)							\
+	"	" #asm_op #mb "	%[i], %[old], %[v]"			\
+	: [v] "+Q" (v->counter),					\
+	  [old] "=r" (old)						\
+	: [i] "r" (i) 							\
 	: cl);								\
 									\
-	return i;							\
+	return old;							\
 }
 
 #define ATOMIC64_FETCH_OPS(op, asm_op)					\
@@ -207,51 +163,46 @@ ATOMIC64_FETCH_OPS(add, ldadd)
 #undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_FETCH_OPS
 
-#define ATOMIC64_OP_ADD_RETURN(name, mb, cl...)				\
+#define ATOMIC64_FETCH_OP_SUB(name)					\
+static inline long __lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v)	\
+{									\
+	return __lse_atomic64_fetch_add##name(-i, v);			\
+}
+
+ATOMIC64_FETCH_OP_SUB(_relaxed)
+ATOMIC64_FETCH_OP_SUB(_acquire)
+ATOMIC64_FETCH_OP_SUB(_release)
+ATOMIC64_FETCH_OP_SUB(        )
+
+#undef ATOMIC64_FETCH_OP_SUB
+
+#define ATOMIC64_OP_ADD_SUB_RETURN(name)				\
 static inline long __lse_atomic64_add_return##name(s64 i, atomic64_t *v)\
 {									\
-	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)	\
-	: "r" (v)							\
-	: cl);								\
+	return __lse_atomic64_fetch_add##name(i, v) + i;		\
+}									\
 									\
-	return i;							\
+static inline long __lse_atomic64_sub_return##name(s64 i, atomic64_t *v)\
+{									\
+	return __lse_atomic64_fetch_sub##name(i, v) - i;		\
 }
 
-ATOMIC64_OP_ADD_RETURN(_relaxed,   )
-ATOMIC64_OP_ADD_RETURN(_acquire,  a, "memory")
-ATOMIC64_OP_ADD_RETURN(_release,  l, "memory")
-ATOMIC64_OP_ADD_RETURN(        , al, "memory")
+ATOMIC64_OP_ADD_SUB_RETURN(_relaxed)
+ATOMIC64_OP_ADD_SUB_RETURN(_acquire)
+ATOMIC64_OP_ADD_SUB_RETURN(_release)
+ATOMIC64_OP_ADD_SUB_RETURN(        )
 
-#undef ATOMIC64_OP_ADD_RETURN
+#undef ATOMIC64_OP_ADD_SUB_RETURN
 
 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)
-	: "r" (v));
+	return __lse_atomic64_andnot(~i, v);
 }
 
 #define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
 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)				\
-	: "r" (v)							\
-	: cl);								\
-									\
-	return i;							\
+	return __lse_atomic64_fetch_andnot##name(~i, v);		\
 }
 
 ATOMIC64_FETCH_OP_AND(_relaxed,   )
@@ -261,61 +212,6 @@ ATOMIC64_FETCH_OP_AND(        , al, "memory")
 
 #undef ATOMIC64_FETCH_OP_AND
 
-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)
-	: "r" (v));
-}
-
-#define ATOMIC64_OP_SUB_RETURN(name, mb, cl...)				\
-static inline long __lse_atomic64_sub_return##name(s64 i, atomic64_t *v)	\
-{									\
-	unsigned long tmp;						\
-									\
-	asm volatile(							\
-	__LSE_PREAMBLE							\
-	"	neg	%[i], %[i]\n"					\
-	"	ldadd" #mb "	%[i], %x[tmp], %[v]\n"			\
-	"	add	%[i], %[i], %x[tmp]"				\
-	: [i] "+&r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)	\
-	: "r" (v)							\
-	: cl);								\
-									\
-	return i;							\
-}
-
-ATOMIC64_OP_SUB_RETURN(_relaxed,   )
-ATOMIC64_OP_SUB_RETURN(_acquire,  a, "memory")
-ATOMIC64_OP_SUB_RETURN(_release,  l, "memory")
-ATOMIC64_OP_SUB_RETURN(        , al, "memory")
-
-#undef ATOMIC64_OP_SUB_RETURN
-
-#define ATOMIC64_FETCH_OP_SUB(name, mb, cl...)				\
-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)				\
-	: "r" (v)							\
-	: cl);								\
-									\
-	return i;							\
-}
-
-ATOMIC64_FETCH_OP_SUB(_relaxed,   )
-ATOMIC64_FETCH_OP_SUB(_acquire,  a, "memory")
-ATOMIC64_FETCH_OP_SUB(_release,  l, "memory")
-ATOMIC64_FETCH_OP_SUB(        , al, "memory")
-
-#undef ATOMIC64_FETCH_OP_SUB
-
 static inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v)
 {
 	unsigned long tmp;
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 1c5a00598458..62217be36217 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -26,6 +26,14 @@
 #define __tsb_csync()	asm volatile("hint #18" : : : "memory")
 #define csdb()		asm volatile("hint #20" : : : "memory")
 
+/*
+ * Data Gathering Hint:
+ * This instruction prevents merging memory accesses with Normal-NC or
+ * Device-GRE attributes before the hint instruction with any memory accesses
+ * appearing after the hint instruction.
+ */
+#define dgh()		asm volatile("hint #6" : : : "memory")
+
 #ifdef CONFIG_ARM64_PSEUDO_NMI
 #define pmr_sync()						\
 	do {							\
@@ -46,6 +54,7 @@
 #define dma_rmb()	dmb(oshld)
 #define dma_wmb()	dmb(oshst)
 
+#define io_stop_wc()	dgh()
 
 #define tsb_csync()								\
 	do {									\
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 0f6d16faa540..a58e366f0b07 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -51,6 +51,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64dfr1;
 	u64		reg_id_aa64isar0;
 	u64		reg_id_aa64isar1;
+	u64		reg_id_aa64isar2;
 	u64		reg_id_aa64mmfr0;
 	u64		reg_id_aa64mmfr1;
 	u64		reg_id_aa64mmfr2;
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index dbb4b30a5648..cb24385e3632 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -51,8 +51,8 @@ extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
-/* Maximum VL that SVE VL-agnostic software can transparently support */
-#define SVE_VL_ARCH_MAX 0x100
+/* Maximum VL that SVE/SME VL-agnostic software can transparently support */
+#define VL_ARCH_MAX 0x100
 
 /* Offset of FFR in the SVE register dump */
 static inline size_t sve_ffr_offset(int vl)
@@ -122,7 +122,7 @@ extern void fpsimd_sync_to_sve(struct task_struct *task);
 extern void sve_sync_to_fpsimd(struct task_struct *task);
 extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
 
-extern int sve_set_vector_length(struct task_struct *task,
+extern int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 				 unsigned long vl, unsigned long flags);
 
 extern int sve_set_current_vl(unsigned long arg);
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index b100e0055eab..f68fbb207473 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -106,6 +106,8 @@
 #define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
 #define KERNEL_HWCAP_MTE		__khwcap2_feature(MTE)
 #define KERNEL_HWCAP_ECV		__khwcap2_feature(ECV)
+#define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
+#define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index 9906541a6861..b77e9b3f5371 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -1,48 +1,43 @@
 #ifndef __ASM_LINKAGE_H
 #define __ASM_LINKAGE_H
 
+#ifdef __ASSEMBLY__
+#include <asm/assembler.h>
+#endif
+
 #define __ALIGN		.align 2
 #define __ALIGN_STR	".align 2"
 
-#if defined(CONFIG_ARM64_BTI_KERNEL) && defined(__aarch64__)
-
-/*
- * Since current versions of gas reject the BTI instruction unless we
- * set the architecture version to v8.5 we use the hint instruction
- * instead.
- */
-#define BTI_C hint 34 ;
-
 /*
- * When using in-kernel BTI we need to ensure that PCS-conformant assembly
- * functions have suitable annotations.  Override SYM_FUNC_START to insert
- * a BTI landing pad at the start of everything.
+ * When using in-kernel BTI we need to ensure that PCS-conformant
+ * assembly functions have suitable annotations.  Override
+ * SYM_FUNC_START to insert a BTI landing pad at the start of
+ * everything, the override is done unconditionally so we're more
+ * likely to notice any drift from the overridden definitions.
  */
 #define SYM_FUNC_START(name)				\
 	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
-	BTI_C
+	bti c ;
 
 #define SYM_FUNC_START_NOALIGN(name)			\
 	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)	\
-	BTI_C
+	bti c ;
 
 #define SYM_FUNC_START_LOCAL(name)			\
 	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)	\
-	BTI_C
+	bti c ;
 
 #define SYM_FUNC_START_LOCAL_NOALIGN(name)		\
 	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)	\
-	BTI_C
+	bti c ;
 
 #define SYM_FUNC_START_WEAK(name)			\
 	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)	\
-	BTI_C
+	bti c ;
 
 #define SYM_FUNC_START_WEAK_NOALIGN(name)		\
 	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
-	BTI_C
-
-#endif
+	bti c ;
 
 /*
  * Annotate a function as position independent, i.e., safe to be called before
diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
index 478b9bcf69ad..e4704a403237 100644
--- a/arch/arm64/include/asm/mte-kasan.h
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -84,10 +84,12 @@ static inline void __dc_gzva(u64 p)
 static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag,
 					 bool init)
 {
-	u64 curr, mask, dczid_bs, end1, end2, end3;
+	u64 curr, mask, dczid, dczid_bs, dczid_dzp, end1, end2, end3;
 
 	/* Read DC G(Z)VA block size from the system register. */
-	dczid_bs = 4ul << (read_cpuid(DCZID_EL0) & 0xf);
+	dczid = read_cpuid(DCZID_EL0);
+	dczid_bs = 4ul << (dczid & 0xf);
+	dczid_dzp = (dczid >> 4) & 1;
 
 	curr = (u64)__tag_set(addr, tag);
 	mask = dczid_bs - 1;
@@ -106,7 +108,7 @@ static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag,
 	 */
 #define SET_MEMTAG_RANGE(stg_post, dc_gva)		\
 	do {						\
-		if (size >= 2 * dczid_bs) {		\
+		if (!dczid_dzp && size >= 2 * dczid_bs) {\
 			do {				\
 				curr = stg_post(curr);	\
 			} while (curr < end1);		\
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 6564a01cc085..e77cdef9ca29 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -47,6 +47,10 @@ struct stack_info {
  * @prev_type:   The type of stack this frame record was on, or a synthetic
  *               value of STACK_TYPE_UNKNOWN. This is used to detect a
  *               transition from one stack to another.
+ *
+ * @kr_cur:      When KRETPROBES is selected, holds the kretprobe instance
+ *               associated with the most recently encountered replacement lr
+ *               value.
  */
 struct stackframe {
 	unsigned long fp;
@@ -59,9 +63,6 @@ struct stackframe {
 #endif
 };
 
-extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
-extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
-			    bool (*fn)(void *, unsigned long), void *data);
 extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
 			   const char *loglvl);
 
@@ -146,7 +147,4 @@ static inline bool on_accessible_stack(const struct task_struct *tsk,
 	return false;
 }
 
-void start_backtrace(struct stackframe *frame, unsigned long fp,
-		     unsigned long pc);
-
 #endif	/* __ASM_STACKTRACE_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 16b3f1a1d468..4704f5893458 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -182,6 +182,7 @@
 
 #define SYS_ID_AA64ISAR0_EL1		sys_reg(3, 0, 0, 6, 0)
 #define SYS_ID_AA64ISAR1_EL1		sys_reg(3, 0, 0, 6, 1)
+#define SYS_ID_AA64ISAR2_EL1		sys_reg(3, 0, 0, 6, 2)
 
 #define SYS_ID_AA64MMFR0_EL1		sys_reg(3, 0, 0, 7, 0)
 #define SYS_ID_AA64MMFR1_EL1		sys_reg(3, 0, 0, 7, 1)
@@ -771,6 +772,20 @@
 #define ID_AA64ISAR1_GPI_NI			0x0
 #define ID_AA64ISAR1_GPI_IMP_DEF		0x1
 
+/* id_aa64isar2 */
+#define ID_AA64ISAR2_RPRES_SHIFT	4
+#define ID_AA64ISAR2_WFXT_SHIFT		0
+
+#define ID_AA64ISAR2_RPRES_8BIT		0x0
+#define ID_AA64ISAR2_RPRES_12BIT	0x1
+/*
+ * Value 0x1 has been removed from the architecture, and is
+ * reserved, but has not yet been removed from the ARM ARM
+ * as of ARM DDI 0487G.b.
+ */
+#define ID_AA64ISAR2_WFXT_NI		0x0
+#define ID_AA64ISAR2_WFXT_SUPPORTED	0x2
+
 /* id_aa64pfr0 */
 #define ID_AA64PFR0_CSV3_SHIFT		60
 #define ID_AA64PFR0_CSV2_SHIFT		56
@@ -889,6 +904,7 @@
 #endif
 
 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_AFP_SHIFT		44
 #define ID_AA64MMFR1_ETS_SHIFT		36
 #define ID_AA64MMFR1_TWED_SHIFT		32
 #define ID_AA64MMFR1_XNX_SHIFT		28
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 7b23b16f21ce..f03731847d9d 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -76,5 +76,7 @@
 #define HWCAP2_BTI		(1 << 17)
 #define HWCAP2_MTE		(1 << 18)
 #define HWCAP2_ECV		(1 << 19)
+#define HWCAP2_AFP		(1 << 20)
+#define HWCAP2_RPRES		(1 << 21)
 
 #endif /* _UAPI__ASM_HWCAP_H */