Merge tag 'riscv-for-linus-6.10-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Add byte/half-word compare-and-exchange, emulated via LR/SC loops

 - Support for Rust

 - Support for Zihintpause in hwprobe

 - Add PR_RISCV_SET_ICACHE_FLUSH_CTX prctl()

 - Support lockless lockrefs

* tag 'riscv-for-linus-6.10-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (42 commits)
  riscv: defconfig: Enable CONFIG_CLK_SOPHGO_CV1800
  riscv: select ARCH_HAS_FAST_MULTIPLIER
  riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required
  riscv: Annotate pgtable_l{4,5}_enabled with __ro_after_init
  riscv: Remove redundant CONFIG_64BIT from pgtable_l{4,5}_enabled
  riscv: mm: Always use an ASID to flush mm contexts
  riscv: mm: Preserve global TLB entries when switching contexts
  riscv: mm: Make asid_bits a local variable
  riscv: mm: Use a fixed layout for the MM context ID
  riscv: mm: Introduce cntx2asid/cntx2version helper macros
  riscv: Avoid TLB flush loops when affected by SiFive CIP-1200
  riscv: Apply SiFive CIP-1200 workaround to single-ASID sfence.vma
  riscv: mm: Combine the SMP and UP TLB flush code
  riscv: Only send remote fences when some other CPU is online
  riscv: mm: Broadcast kernel TLB flushes only when needed
  riscv: Use IPIs for remote cache/TLB flushes by default
  riscv: Factor out page table TLB synchronization
  riscv: Flush the instruction cache during SMP bringup
  riscv: hwprobe: export Zihintpause ISA extension
  riscv: misaligned: remove CONFIG_RISCV_M_MODE specific code
  ...

17 files changed, 317 insertions, 447 deletions

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 0e0522e588ca..5b96c2f61adb 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -195,22 +195,28 @@ ATOMIC_OPS(xor, xor, i)
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
+#define _arch_atomic_fetch_add_unless(_prev, _rc, counter, _a, _u, sfx)	\
+({									\
+	__asm__ __volatile__ (						\
+		"0:	lr." sfx "     %[p],  %[c]\n"			\
+		"	beq	       %[p],  %[u], 1f\n"		\
+		"	add            %[rc], %[p], %[a]\n"		\
+		"	sc." sfx ".rl  %[rc], %[rc], %[c]\n"		\
+		"	bnez           %[rc], 0b\n"			\
+		"	fence          rw, rw\n"			\
+		"1:\n"							\
+		: [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter)	\
+		: [a]"r" (_a), [u]"r" (_u)				\
+		: "memory");						\
+})
+
 /* This is required to provide a full barrier on success. */
 static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
        int prev, rc;
 
-	__asm__ __volatile__ (
-		"0:	lr.w     %[p],  %[c]\n"
-		"	beq      %[p],  %[u], 1f\n"
-		"	add      %[rc], %[p], %[a]\n"
-		"	sc.w.rl  %[rc], %[rc], %[c]\n"
-		"	bnez     %[rc], 0b\n"
-		RISCV_FULL_BARRIER
-		"1:\n"
-		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		: [a]"r" (a), [u]"r" (u)
-		: "memory");
+	_arch_atomic_fetch_add_unless(prev, rc, v->counter, a, u, "w");
+
 	return prev;
 }
 #define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
@@ -221,77 +227,86 @@ static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a,
        s64 prev;
        long rc;
 
-	__asm__ __volatile__ (
-		"0:	lr.d     %[p],  %[c]\n"
-		"	beq      %[p],  %[u], 1f\n"
-		"	add      %[rc], %[p], %[a]\n"
-		"	sc.d.rl  %[rc], %[rc], %[c]\n"
-		"	bnez     %[rc], 0b\n"
-		RISCV_FULL_BARRIER
-		"1:\n"
-		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		: [a]"r" (a), [u]"r" (u)
-		: "memory");
+	_arch_atomic_fetch_add_unless(prev, rc, v->counter, a, u, "d");
+
 	return prev;
 }
 #define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
 #endif
 
+#define _arch_atomic_inc_unless_negative(_prev, _rc, counter, sfx)	\
+({									\
+	__asm__ __volatile__ (						\
+		"0:	lr." sfx "      %[p],  %[c]\n"			\
+		"	bltz            %[p],  1f\n"			\
+		"	addi            %[rc], %[p], 1\n"		\
+		"	sc." sfx ".rl   %[rc], %[rc], %[c]\n"		\
+		"	bnez            %[rc], 0b\n"			\
+		"	fence           rw, rw\n"			\
+		"1:\n"							\
+		: [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter)	\
+		:							\
+		: "memory");						\
+})
+
 static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v)
 {
 	int prev, rc;
 
-	__asm__ __volatile__ (
-		"0:	lr.w      %[p],  %[c]\n"
-		"	bltz      %[p],  1f\n"
-		"	addi      %[rc], %[p], 1\n"
-		"	sc.w.rl   %[rc], %[rc], %[c]\n"
-		"	bnez      %[rc], 0b\n"
-		RISCV_FULL_BARRIER
-		"1:\n"
-		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		:
-		: "memory");
+	_arch_atomic_inc_unless_negative(prev, rc, v->counter, "w");
+
 	return !(prev < 0);
 }
 
 #define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative
 
+#define _arch_atomic_dec_unless_positive(_prev, _rc, counter, sfx)	\
+({									\
+	__asm__ __volatile__ (						\
+		"0:	lr." sfx "      %[p],  %[c]\n"			\
+		"	bgtz            %[p],  1f\n"			\
+		"	addi            %[rc], %[p], -1\n"		\
+		"	sc." sfx ".rl   %[rc], %[rc], %[c]\n"		\
+		"	bnez            %[rc], 0b\n"			\
+		"	fence           rw, rw\n"			\
+		"1:\n"							\
+		: [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter)	\
+		:							\
+		: "memory");						\
+})
+
 static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v)
 {
 	int prev, rc;
 
-	__asm__ __volatile__ (
-		"0:	lr.w      %[p],  %[c]\n"
-		"	bgtz      %[p],  1f\n"
-		"	addi      %[rc], %[p], -1\n"
-		"	sc.w.rl   %[rc], %[rc], %[c]\n"
-		"	bnez      %[rc], 0b\n"
-		RISCV_FULL_BARRIER
-		"1:\n"
-		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		:
-		: "memory");
+	_arch_atomic_dec_unless_positive(prev, rc, v->counter, "w");
+
 	return !(prev > 0);
 }
 
 #define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive
 
+#define _arch_atomic_dec_if_positive(_prev, _rc, counter, sfx)		\
+({									\
+	__asm__ __volatile__ (						\
+		"0:	lr." sfx "     %[p],  %[c]\n"			\
+		"	addi           %[rc], %[p], -1\n"		\
+		"	bltz           %[rc], 1f\n"			\
+		"	sc." sfx ".rl  %[rc], %[rc], %[c]\n"		\
+		"	bnez           %[rc], 0b\n"			\
+		"	fence          rw, rw\n"			\
+		"1:\n"							\
+		: [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter)	\
+		:							\
+		: "memory");						\
+})
+
 static __always_inline int arch_atomic_dec_if_positive(atomic_t *v)
 {
        int prev, rc;
 
-	__asm__ __volatile__ (
-		"0:	lr.w     %[p],  %[c]\n"
-		"	addi     %[rc], %[p], -1\n"
-		"	bltz     %[rc], 1f\n"
-		"	sc.w.rl  %[rc], %[rc], %[c]\n"
-		"	bnez     %[rc], 0b\n"
-		RISCV_FULL_BARRIER
-		"1:\n"
-		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		:
-		: "memory");
+	_arch_atomic_dec_if_positive(prev, rc, v->counter, "w");
+
 	return prev - 1;
 }
 
@@ -303,17 +318,8 @@ static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v)
 	s64 prev;
 	long rc;
 
-	__asm__ __volatile__ (
-		"0:	lr.d      %[p],  %[c]\n"
-		"	bltz      %[p],  1f\n"
-		"	addi      %[rc], %[p], 1\n"
-		"	sc.d.rl   %[rc], %[rc], %[c]\n"
-		"	bnez      %[rc], 0b\n"
-		RISCV_FULL_BARRIER
-		"1:\n"
-		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		:
-		: "memory");
+	_arch_atomic_inc_unless_negative(prev, rc, v->counter, "d");
+
 	return !(prev < 0);
 }
 
@@ -324,17 +330,8 @@ static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v)
 	s64 prev;
 	long rc;
 
-	__asm__ __volatile__ (
-		"0:	lr.d      %[p],  %[c]\n"
-		"	bgtz      %[p],  1f\n"
-		"	addi      %[rc], %[p], -1\n"
-		"	sc.d.rl   %[rc], %[rc], %[c]\n"
-		"	bnez      %[rc], 0b\n"
-		RISCV_FULL_BARRIER
-		"1:\n"
-		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		:
-		: "memory");
+	_arch_atomic_dec_unless_positive(prev, rc, v->counter, "d");
+
 	return !(prev > 0);
 }
 
@@ -345,17 +342,8 @@ static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
        s64 prev;
        long rc;
 
-	__asm__ __volatile__ (
-		"0:	lr.d     %[p],  %[c]\n"
-		"	addi      %[rc], %[p], -1\n"
-		"	bltz     %[rc], 1f\n"
-		"	sc.d.rl  %[rc], %[rc], %[c]\n"
-		"	bnez     %[rc], 0b\n"
-		RISCV_FULL_BARRIER
-		"1:\n"
-		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		:
-		: "memory");
+	_arch_atomic_dec_if_positive(prev, rc, v->counter, "d");
+
 	return prev - 1;
 }
 
diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
index 2174fe7bac9a..570e9d8acad1 100644
--- a/arch/riscv/include/asm/cache.h
+++ b/arch/riscv/include/asm/cache.h
@@ -26,8 +26,8 @@
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_RISCV_DMA_NONCOHERENT
 extern int dma_cache_alignment;
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
 #define dma_get_cache_alignment dma_get_cache_alignment
 static inline int dma_get_cache_alignment(void)
 {
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index a129dac4521d..dd8d07146116 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -33,8 +33,11 @@ static inline void flush_dcache_page(struct page *page)
  * so instead we just flush the whole thing.
  */
 #define flush_icache_range(start, end) flush_icache_all()
-#define flush_icache_user_page(vma, pg, addr, len) \
-	flush_icache_mm(vma->vm_mm, 0)
+#define flush_icache_user_page(vma, pg, addr, len)	\
+do {							\
+	if (vma->vm_flags & VM_EXEC)			\
+		flush_icache_mm(vma->vm_mm, 0);		\
+} while (0)
 
 #ifdef CONFIG_64BIT
 #define flush_cache_vmap(start, end)		flush_tlb_kernel_range(start, end)
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 2fee65cc8443..ddb002ed89de 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -10,140 +10,79 @@
 
 #include <asm/fence.h>
 
-#define __xchg_relaxed(ptr, new, size)					\
+#define __arch_xchg_masked(prepend, append, r, p, n)			\
+({									\
+	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+			<< __s;						\
+	ulong __newx = (ulong)(n) << __s;				\
+	ulong __retx;							\
+	ulong __rc;							\
+									\
+	__asm__ __volatile__ (						\
+	       prepend							\
+	       "0:	lr.w %0, %2\n"					\
+	       "	and  %1, %0, %z4\n"				\
+	       "	or   %1, %1, %z3\n"				\
+	       "	sc.w %1, %1, %2\n"				\
+	       "	bnez %1, 0b\n"					\
+	       append							\
+	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+	       : "rJ" (__newx), "rJ" (~__mask)				\
+	       : "memory");						\
+									\
+	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+})
+
+#define __arch_xchg(sfx, prepend, append, r, p, n)			\
+({									\
+	__asm__ __volatile__ (						\
+		prepend							\
+		"	amoswap" sfx " %0, %2, %1\n"			\
+		append							\
+		: "=r" (r), "+A" (*(p))					\
+		: "r" (n)						\
+		: "memory");						\
+})
+
+#define _arch_xchg(ptr, new, sfx, prepend, append)			\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(new) __new = (new);					\
-	__typeof__(*(ptr)) __ret;					\
-	switch (size) {							\
+	__typeof__(*(__ptr)) __new = (new);				\
+	__typeof__(*(__ptr)) __ret;					\
+									\
+	switch (sizeof(*__ptr)) {					\
+	case 1:								\
+	case 2:								\
+		__arch_xchg_masked(prepend, append,			\
+				   __ret, __ptr, __new);		\
+		break;							\
 	case 4:								\
-		__asm__ __volatile__ (					\
-			"	amoswap.w %0, %2, %1\n"			\
-			: "=r" (__ret), "+A" (*__ptr)			\
-			: "r" (__new)					\
-			: "memory");					\
+		__arch_xchg(".w" sfx, prepend, append,			\
+			      __ret, __ptr, __new);			\
 		break;							\
 	case 8:								\
-		__asm__ __volatile__ (					\
-			"	amoswap.d %0, %2, %1\n"			\
-			: "=r" (__ret), "+A" (*__ptr)			\
-			: "r" (__new)					\
-			: "memory");					\
+		__arch_xchg(".d" sfx, prepend, append,			\
+			      __ret, __ptr, __new);			\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
 	}								\
-	__ret;								\
+	(__typeof__(*(__ptr)))__ret;					\
 })
 
 #define arch_xchg_relaxed(ptr, x)					\
-({									\
-	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __xchg_relaxed((ptr),			\
-					    _x_, sizeof(*(ptr)));	\
-})
-
-#define __xchg_acquire(ptr, new, size)					\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(new) __new = (new);					\
-	__typeof__(*(ptr)) __ret;					\
-	switch (size) {							\
-	case 4:								\
-		__asm__ __volatile__ (					\
-			"	amoswap.w %0, %2, %1\n"			\
-			RISCV_ACQUIRE_BARRIER				\
-			: "=r" (__ret), "+A" (*__ptr)			\
-			: "r" (__new)					\
-			: "memory");					\
-		break;							\
-	case 8:								\
-		__asm__ __volatile__ (					\
-			"	amoswap.d %0, %2, %1\n"			\
-			RISCV_ACQUIRE_BARRIER				\
-			: "=r" (__ret), "+A" (*__ptr)			\
-			: "r" (__new)					\
-			: "memory");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
+	_arch_xchg(ptr, x, "", "", "")
 
 #define arch_xchg_acquire(ptr, x)					\
-({									\
-	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __xchg_acquire((ptr),			\
-					    _x_, sizeof(*(ptr)));	\
-})
-
-#define __xchg_release(ptr, new, size)					\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(new) __new = (new);					\
-	__typeof__(*(ptr)) __ret;					\
-	switch (size) {							\
-	case 4:								\
-		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
-			"	amoswap.w %0, %2, %1\n"			\
-			: "=r" (__ret), "+A" (*__ptr)			\
-			: "r" (__new)					\
-			: "memory");					\
-		break;							\
-	case 8:								\
-		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
-			"	amoswap.d %0, %2, %1\n"			\
-			: "=r" (__ret), "+A" (*__ptr)			\
-			: "r" (__new)					\
-			: "memory");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
+	_arch_xchg(ptr, x, "", "", RISCV_ACQUIRE_BARRIER)
 
 #define arch_xchg_release(ptr, x)					\
-({									\
-	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __xchg_release((ptr),			\
-					    _x_, sizeof(*(ptr)));	\
-})
-
-#define __arch_xchg(ptr, new, size)					\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(new) __new = (new);					\
-	__typeof__(*(ptr)) __ret;					\
-	switch (size) {							\
-	case 4:								\
-		__asm__ __volatile__ (					\
-			"	amoswap.w.aqrl %0, %2, %1\n"		\
-			: "=r" (__ret), "+A" (*__ptr)			\
-			: "r" (__new)					\
-			: "memory");					\
-		break;							\
-	case 8:								\
-		__asm__ __volatile__ (					\
-			"	amoswap.d.aqrl %0, %2, %1\n"		\
-			: "=r" (__ret), "+A" (*__ptr)			\
-			: "r" (__new)					\
-			: "memory");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
+	_arch_xchg(ptr, x, "", RISCV_RELEASE_BARRIER, "")
 
 #define arch_xchg(ptr, x)						\
-({									\
-	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __arch_xchg((ptr), _x_, sizeof(*(ptr)));	\
-})
+	_arch_xchg(ptr, x, ".aqrl", "", "")
 
 #define xchg32(ptr, x)							\
 ({									\
@@ -162,190 +101,95 @@
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
-#define __cmpxchg_relaxed(ptr, old, new, size)				\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(*(ptr)) __old = (old);				\
-	__typeof__(*(ptr)) __new = (new);				\
-	__typeof__(*(ptr)) __ret;					\
-	register unsigned int __rc;					\
-	switch (size) {							\
-	case 4:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.w %0, %2\n"				\
-			"	bne  %0, %z3, 1f\n"			\
-			"	sc.w %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" ((long)__old), "rJ" (__new)		\
-			: "memory");					\
-		break;							\
-	case 8:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.d %0, %2\n"				\
-			"	bne %0, %z3, 1f\n"			\
-			"	sc.d %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
-			: "memory");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
 
-#define arch_cmpxchg_relaxed(ptr, o, n)					\
+#define __arch_cmpxchg_masked(sc_sfx, prepend, append, r, p, o, n)	\
+({									\
+	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+			<< __s;						\
+	ulong __newx = (ulong)(n) << __s;				\
+	ulong __oldx = (ulong)(o) << __s;				\
+	ulong __retx;							\
+	ulong __rc;							\
+									\
+	__asm__ __volatile__ (						\
+		prepend							\
+		"0:	lr.w %0, %2\n"					\
+		"	and  %1, %0, %z5\n"				\
+		"	bne  %1, %z3, 1f\n"				\
+		"	and  %1, %0, %z6\n"				\
+		"	or   %1, %1, %z4\n"				\
+		"	sc.w" sc_sfx " %1, %1, %2\n"			\
+		"	bnez %1, 0b\n"					\
+		append							\
+		"1:\n"							\
+		: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+		: "rJ" ((long)__oldx), "rJ" (__newx),			\
+		  "rJ" (__mask), "rJ" (~__mask)				\
+		: "memory");						\
+									\
+	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+})
+
+#define __arch_cmpxchg(lr_sfx, sc_sfx, prepend, append, r, p, co, o, n)	\
 ({									\
-	__typeof__(*(ptr)) _o_ = (o);					\
-	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg_relaxed((ptr),			\
-					_o_, _n_, sizeof(*(ptr)));	\
-})
-
-#define __cmpxchg_acquire(ptr, old, new, size)				\
+	register unsigned int __rc;					\
+									\
+	__asm__ __volatile__ (						\
+		prepend							\
+		"0:	lr" lr_sfx " %0, %2\n"				\
+		"	bne  %0, %z3, 1f\n"				\
+		"	sc" sc_sfx " %1, %z4, %2\n"			\
+		"	bnez %1, 0b\n"					\
+		append							\
+		"1:\n"							\
+		: "=&r" (r), "=&r" (__rc), "+A" (*(p))			\
+		: "rJ" (co o), "rJ" (n)					\
+		: "memory");						\
+})
+
+#define _arch_cmpxchg(ptr, old, new, sc_sfx, prepend, append)		\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(*(ptr)) __old = (old);				\
-	__typeof__(*(ptr)) __new = (new);				\
-	__typeof__(*(ptr)) __ret;					\
-	register unsigned int __rc;					\
-	switch (size) {							\
+	__typeof__(*(__ptr)) __old = (old);				\
+	__typeof__(*(__ptr)) __new = (new);				\
+	__typeof__(*(__ptr)) __ret;					\
+									\
+	switch (sizeof(*__ptr)) {					\
+	case 1:								\
+	case 2:								\
+		__arch_cmpxchg_masked(sc_sfx, prepend, append,		\
+					__ret, __ptr, __old, __new);	\
+		break;							\
 	case 4:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.w %0, %2\n"				\
-			"	bne  %0, %z3, 1f\n"			\
-			"	sc.w %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			RISCV_ACQUIRE_BARRIER				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" ((long)__old), "rJ" (__new)		\
-			: "memory");					\
+		__arch_cmpxchg(".w", ".w" sc_sfx, prepend, append,	\
+				__ret, __ptr, (long), __old, __new);	\
 		break;							\
 	case 8:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.d %0, %2\n"				\
-			"	bne %0, %z3, 1f\n"			\
-			"	sc.d %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			RISCV_ACQUIRE_BARRIER				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
-			: "memory");					\
+		__arch_cmpxchg(".d", ".d" sc_sfx, prepend, append,	\
+				__ret, __ptr, /**/, __old, __new);	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
 	}								\
-	__ret;								\
+	(__typeof__(*(__ptr)))__ret;					\
 })
 
-#define arch_cmpxchg_acquire(ptr, o, n)					\
-({									\
-	__typeof__(*(ptr)) _o_ = (o);					\
-	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg_acquire((ptr),			\
-					_o_, _n_, sizeof(*(ptr)));	\
-})
+#define arch_cmpxchg_relaxed(ptr, o, n)					\
+	_arch_cmpxchg((ptr), (o), (n), "", "", "")
 
-#define __cmpxchg_release(ptr, old, new, size)				\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(*(ptr)) __old = (old);				\
-	__typeof__(*(ptr)) __new = (new);				\
-	__typeof__(*(ptr)) __ret;					\
-	register unsigned int __rc;					\
-	switch (size) {							\
-	case 4:								\
-		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
-			"0:	lr.w %0, %2\n"				\
-			"	bne  %0, %z3, 1f\n"			\
-			"	sc.w %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" ((long)__old), "rJ" (__new)		\
-			: "memory");					\
-		break;							\
-	case 8:								\
-		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
-			"0:	lr.d %0, %2\n"				\
-			"	bne %0, %z3, 1f\n"			\
-			"	sc.d %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
-			: "memory");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
+#define arch_cmpxchg_acquire(ptr, o, n)					\
+	_arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER)
 
 #define arch_cmpxchg_release(ptr, o, n)					\
-({									\
-	__typeof__(*(ptr)) _o_ = (o);					\
-	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg_release((ptr),			\
-					_o_, _n_, sizeof(*(ptr)));	\
-})
-
-#define __cmpxchg(ptr, old, new, size)					\
-({									\
-	__typeof__(ptr) __ptr = (ptr);					\
-	__typeof__(*(ptr)) __old = (old);				\
-	__typeof__(*(ptr)) __new = (new);				\
-	__typeof__(*(ptr)) __ret;					\
-	register unsigned int __rc;					\
-	switch (size) {							\
-	case 4:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.w %0, %2\n"				\
-			"	bne  %0, %z3, 1f\n"			\
-			"	sc.w.rl %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			RISCV_FULL_BARRIER				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" ((long)__old), "rJ" (__new)		\
-			: "memory");					\
-		break;							\
-	case 8:								\
-		__asm__ __volatile__ (					\
-			"0:	lr.d %0, %2\n"				\
-			"	bne %0, %z3, 1f\n"			\
-			"	sc.d.rl %1, %z4, %2\n"			\
-			"	bnez %1, 0b\n"				\
-			RISCV_FULL_BARRIER				\
-			"1:\n"						\
-			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
-			: "memory");					\
-		break;							\
-	default:							\
-		BUILD_BUG();						\
-	}								\
-	__ret;								\
-})
+	_arch_cmpxchg((ptr), (o), (n), "", RISCV_RELEASE_BARRIER, "")
 
 #define arch_cmpxchg(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) _o_ = (o);					\
-	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg((ptr),				\
-				       _o_, _n_, sizeof(*(ptr)));	\
-})
+	_arch_cmpxchg((ptr), (o), (n), ".rl", "", "	fence rw, rw\n")
 
 #define arch_cmpxchg_local(ptr, o, n)					\
-	(__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
+	arch_cmpxchg_relaxed((ptr), (o), (n))
 
 #define arch_cmpxchg64(ptr, o, n)					\
 ({									\
@@ -359,4 +203,22 @@
 	arch_cmpxchg_relaxed((ptr), (o), (n));				\
 })
 
+#define arch_cmpxchg64_relaxed(ptr, o, n)				\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg_relaxed((ptr), (o), (n));				\
+})
+
+#define arch_cmpxchg64_acquire(ptr, o, n)				\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg_acquire((ptr), (o), (n));				\
+})
+
+#define arch_cmpxchg64_release(ptr, o, n)				\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg_release((ptr), (o), (n));				\
+})
+
 #endif /* _ASM_RISCV_CMPXCHG_H */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index efd851e1b483..7c8a71a526a3 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -43,11 +43,21 @@ ALTERNATIVE(__stringify(RISCV_PTR do_page_fault),			\
 	    CONFIG_ERRATA_SIFIVE_CIP_453)
 #else /* !__ASSEMBLY__ */
 
-#define ALT_FLUSH_TLB_PAGE(x)						\
+#define ALT_SFENCE_VMA_ASID(asid)					\
+asm(ALTERNATIVE("sfence.vma x0, %0", "sfence.vma", SIFIVE_VENDOR_ID,	\
+		ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200)	\
+		: : "r" (asid) : "memory")
+
+#define ALT_SFENCE_VMA_ADDR(addr)					\
 asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID,	\
 		ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200)	\
 		: : "r" (addr) : "memory")
 
+#define ALT_SFENCE_VMA_ADDR_ASID(addr, asid)				\
+asm(ALTERNATIVE("sfence.vma %0, %1", "sfence.vma", SIFIVE_VENDOR_ID,	\
+		ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200)	\
+		: : "r" (addr), "r" (asid) : "memory")
+
 /*
  * _val is marked as "will be overwritten", so need to set it to 0
  * in the default case.
diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
index 08d4d6a5b7e9..6fd8cbfcfcc7 100644
--- a/arch/riscv/include/asm/irqflags.h
+++ b/arch/riscv/include/asm/irqflags.h
@@ -7,7 +7,6 @@
 #ifndef _ASM_RISCV_IRQFLAGS_H
 #define _ASM_RISCV_IRQFLAGS_H
 
-#include <asm/processor.h>
 #include <asm/csr.h>
 
 /* read interrupt enabled status */
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index 355504b37f8e..947fd60f9051 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -19,6 +19,8 @@ typedef struct {
 #ifdef CONFIG_SMP
 	/* A local icache flush is needed before user execution can resume. */
 	cpumask_t icache_stale_mask;
+	/* Force local icache flush on all migrations. */
+	bool force_icache_flush;
 #endif
 #ifdef CONFIG_BINFMT_ELF_FDPIC
 	unsigned long exec_fdpic_loadmap;
@@ -26,6 +28,9 @@ typedef struct {
 #endif
 } mm_context_t;
 
+#define cntx2asid(cntx)		((cntx) & SATP_ASID_MASK)
+#define cntx2version(cntx)	((cntx) & ~SATP_ASID_MASK)
+
 void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa,
 			       phys_addr_t sz, pgprot_t prot);
 #endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/patch.h
index e88b52d39eac..9f5d6e14c405 100644
--- a/arch/riscv/include/asm/patch.h
+++ b/arch/riscv/include/asm/patch.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_RISCV_PATCH_H
 #define _ASM_RISCV_PATCH_H
 
+int patch_insn_write(void *addr, const void *insn, size_t len);
 int patch_text_nosync(void *addr, const void *insns, size_t len);
 int patch_text_set_nosync(void *addr, u8 c, size_t len);
 int patch_text(void *addr, u32 *insns, int ninsns);
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index deaf971253a2..f52264304f77 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -8,6 +8,7 @@
 #define _ASM_RISCV_PGALLOC_H
 
 #include <linux/mm.h>
+#include <asm/sbi.h>
 #include <asm/tlb.h>
 
 #ifdef CONFIG_MMU
@@ -15,6 +16,14 @@
 #define __HAVE_ARCH_PUD_FREE
 #include <asm-generic/pgalloc.h>
 
+static inline void riscv_tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt)
+{
+	if (riscv_use_sbi_for_rfence())
+		tlb_remove_ptdesc(tlb, pt);
+	else
+		tlb_remove_page_ptdesc(tlb, pt);
+}
+
 static inline void pmd_populate_kernel(struct mm_struct *mm,
 	pmd_t *pmd, pte_t *pte)
 {
@@ -102,10 +111,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 		struct ptdesc *ptdesc = virt_to_ptdesc(pud);
 
 		pagetable_pud_dtor(ptdesc);
-		if (riscv_use_ipi_for_rfence())
-			tlb_remove_page_ptdesc(tlb, ptdesc);
-		else
-			tlb_remove_ptdesc(tlb, ptdesc);
+		riscv_tlb_remove_ptdesc(tlb, ptdesc);
 	}
 }
 
@@ -139,12 +145,8 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				  unsigned long addr)
 {
-	if (pgtable_l5_enabled) {
-		if (riscv_use_ipi_for_rfence())
-			tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
-		else
-			tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
-	}
+	if (pgtable_l5_enabled)
+		riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
@@ -176,10 +178,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
 
 	pagetable_pmd_dtor(ptdesc);
-	if (riscv_use_ipi_for_rfence())
-		tlb_remove_page_ptdesc(tlb, ptdesc);
-	else
-		tlb_remove_ptdesc(tlb, ptdesc);
+	riscv_tlb_remove_ptdesc(tlb, ptdesc);
 }
 
 #endif /* __PAGETABLE_PMD_FOLDED */
@@ -190,10 +189,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	struct ptdesc *ptdesc = page_ptdesc(pte);
 
 	pagetable_pte_dtor(ptdesc);
-	if (riscv_use_ipi_for_rfence())
-		tlb_remove_page_ptdesc(tlb, ptdesc);
-	else
-		tlb_remove_ptdesc(tlb, ptdesc);
+	riscv_tlb_remove_ptdesc(tlb, ptdesc);
 }
 #endif /* CONFIG_MMU */
 
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 0faf5f161f1e..68c3432dc6ea 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -68,6 +68,7 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
 
 struct task_struct;
 struct pt_regs;
@@ -122,6 +123,12 @@ struct thread_struct {
 	struct __riscv_v_ext_state vstate;
 	unsigned long align_ctl;
 	struct __riscv_v_ext_state kernel_vstate;
+#ifdef CONFIG_SMP
+	/* Flush the icache on migration */
+	bool force_icache_flush;
+	/* A forced icache flush is not needed if migrating to the previous cpu. */
+	unsigned int prev_cpu;
+#endif
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
@@ -183,6 +190,9 @@ extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
 #define GET_UNALIGN_CTL(tsk, addr)	get_unalign_ctl((tsk), (addr))
 #define SET_UNALIGN_CTL(tsk, val)	set_unalign_ctl((tsk), (val))
 
+#define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2)	riscv_set_icache_flush_ctx(arg1, arg2)
+extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per_thread);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 112a0a0d9f46..9186e7984672 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -387,8 +387,12 @@ unsigned long riscv_cached_marchid(unsigned int cpu_id);
 unsigned long riscv_cached_mimpid(unsigned int cpu_id);
 
 #if IS_ENABLED(CONFIG_SMP) && IS_ENABLED(CONFIG_RISCV_SBI)
+DECLARE_STATIC_KEY_FALSE(riscv_sbi_for_rfence);
+#define riscv_use_sbi_for_rfence() \
+	static_branch_unlikely(&riscv_sbi_for_rfence)
 void sbi_ipi_init(void);
 #else
+static inline bool riscv_use_sbi_for_rfence(void) { return false; }
 static inline void sbi_ipi_init(void) { }
 #endif
 
diff --git a/arch/riscv/include/asm/signal.h b/arch/riscv/include/asm/signal.h
deleted file mode 100644
index 956ae0a01bad..000000000000
--- a/arch/riscv/include/asm/signal.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-
-#ifndef __ASM_SIGNAL_H
-#define __ASM_SIGNAL_H
-
-#include <uapi/asm/signal.h>
-#include <uapi/asm/ptrace.h>
-
-asmlinkage __visible
-void do_work_pending(struct pt_regs *regs, unsigned long thread_info_flags);
-
-#endif
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
index 0d555847cde6..7ac80e9f2288 100644
--- a/arch/riscv/include/asm/smp.h
+++ b/arch/riscv/include/asm/smp.h
@@ -49,12 +49,7 @@ void riscv_ipi_disable(void);
 bool riscv_ipi_have_virq_range(void);
 
 /* Set the IPI interrupt numbers for arch (called by irqchip drivers) */
-void riscv_ipi_set_virq_range(int virq, int nr, bool use_for_rfence);
-
-/* Check if we can use IPIs for remote FENCEs */
-DECLARE_STATIC_KEY_FALSE(riscv_ipi_for_rfence);
-#define riscv_use_ipi_for_rfence() \
-	static_branch_unlikely(&riscv_ipi_for_rfence)
+void riscv_ipi_set_virq_range(int virq, int nr);
 
 /* Check other CPUs stop or not */
 bool smp_crash_stop_failed(void);
@@ -104,16 +99,10 @@ static inline bool riscv_ipi_have_virq_range(void)
 	return false;
 }
 
-static inline void riscv_ipi_set_virq_range(int virq, int nr,
-					    bool use_for_rfence)
+static inline void riscv_ipi_set_virq_range(int virq, int nr)
 {
 }
 
-static inline bool riscv_use_ipi_for_rfence(void)
-{
-	return false;
-}
-
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP)
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
index 4718096fa5e3..4ffb022b097f 100644
--- a/arch/riscv/include/asm/suspend.h
+++ b/arch/riscv/include/asm/suspend.h
@@ -13,7 +13,6 @@ struct suspend_context {
 	/* Saved and restored by low-level functions */
 	struct pt_regs regs;
 	/* Saved and restored by high-level functions */
-	unsigned long scratch;
 	unsigned long envcfg;
 	unsigned long tvec;
 	unsigned long ie;
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 7efdb0584d47..7594df37cc9f 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -8,6 +8,7 @@
 
 #include <linux/jump_label.h>
 #include <linux/sched/task_stack.h>
+#include <linux/mm_types.h>
 #include <asm/vector.h>
 #include <asm/cpufeature.h>
 #include <asm/processor.h>
@@ -72,14 +73,36 @@ static __always_inline bool has_fpu(void) { return false; }
 extern struct task_struct *__switch_to(struct task_struct *,
 				       struct task_struct *);
 
+static inline bool switch_to_should_flush_icache(struct task_struct *task)
+{
+#ifdef CONFIG_SMP
+	bool stale_mm = task->mm && task->mm->context.force_icache_flush;
+	bool stale_thread = task->thread.force_icache_flush;
+	bool thread_migrated = smp_processor_id() != task->thread.prev_cpu;
+
+	return thread_migrated && (stale_mm || stale_thread);
+#else
+	return false;
+#endif
+}
+
+#ifdef CONFIG_SMP
+#define __set_prev_cpu(thread) ((thread).prev_cpu = smp_processor_id())
+#else
+#define __set_prev_cpu(thread)
+#endif
+
 #define switch_to(prev, next, last)			\
 do {							\
 	struct task_struct *__prev = (prev);		\
 	struct task_struct *__next = (next);		\
+	__set_prev_cpu(__prev->thread);			\
 	if (has_fpu())					\
 		__switch_to_fpu(__prev, __next);	\
 	if (has_vector())					\
 		__switch_to_vector(__prev, __next);	\
+	if (switch_to_should_flush_icache(__next))	\
+		local_flush_icache_all();		\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
 
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 4112cc8d1d69..72e559934952 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -15,24 +15,34 @@
 #define FLUSH_TLB_NO_ASID       ((unsigned long)-1)
 
 #ifdef CONFIG_MMU
-extern unsigned long asid_mask;
-
 static inline void local_flush_tlb_all(void)
 {
 	__asm__ __volatile__ ("sfence.vma" : : : "memory");
 }
 
+static inline void local_flush_tlb_all_asid(unsigned long asid)
+{
+	if (asid != FLUSH_TLB_NO_ASID)
+		ALT_SFENCE_VMA_ASID(asid);
+	else
+		local_flush_tlb_all();
+}
+
 /* Flush one page from local TLB */
 static inline void local_flush_tlb_page(unsigned long addr)
 {
-	ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory"));
+	ALT_SFENCE_VMA_ADDR(addr);
+}
+
+static inline void local_flush_tlb_page_asid(unsigned long addr,
+					     unsigned long asid)
+{
+	if (asid != FLUSH_TLB_NO_ASID)
+		ALT_SFENCE_VMA_ADDR_ASID(addr, asid);
+	else
+		local_flush_tlb_page(addr);
 }
-#else /* CONFIG_MMU */
-#define local_flush_tlb_all()			do { } while (0)
-#define local_flush_tlb_page(addr)		do { } while (0)
-#endif /* CONFIG_MMU */
 
-#if defined(CONFIG_SMP) && defined(CONFIG_MMU)
 void flush_tlb_all(void);
 void flush_tlb_mm(struct mm_struct *mm);
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
@@ -55,27 +65,9 @@ void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
 void arch_flush_tlb_batched_pending(struct mm_struct *mm);
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 
-#else /* CONFIG_SMP && CONFIG_MMU */
-
-#define flush_tlb_all() local_flush_tlb_all()
-#define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-		unsigned long start, unsigned long end)
-{
-	local_flush_tlb_all();
-}
-
-/* Flush a range of kernel pages */
-static inline void flush_tlb_kernel_range(unsigned long start,
-	unsigned long end)
-{
-	local_flush_tlb_all();
-}
-
-#define flush_tlb_mm(mm) flush_tlb_all()
-#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
-#define local_flush_tlb_kernel_range(start, end) flush_tlb_all()
-#endif /* !CONFIG_SMP || !CONFIG_MMU */
+extern unsigned long tlb_flush_all_threshold;
+#else /* CONFIG_MMU */
+#define local_flush_tlb_all()			do { } while (0)
+#endif /* CONFIG_MMU */
 
 #endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 2902f68dc913..dda76a05420b 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -59,6 +59,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZTSO		(1ULL << 33)
 #define		RISCV_HWPROBE_EXT_ZACAS		(1ULL << 34)
 #define		RISCV_HWPROBE_EXT_ZICOND	(1ULL << 35)
+#define		RISCV_HWPROBE_EXT_ZIHINTPAUSE	(1ULL << 36)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)