Adding upstream version 6.10.3.upstream/6.10.3

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

23 files changed, 448 insertions, 477 deletions

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 0e0522e588..5b96c2f61a 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 2174fe7bac..570e9d8aca 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 a129dac452..ce79c558a4 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -13,6 +13,12 @@ static inline void local_flush_icache_all(void)
 	asm volatile ("fence.i" ::: "memory");
 }
 
+static inline void local_flush_icache_range(unsigned long start,
+					    unsigned long end)
+{
+	local_flush_icache_all();
+}
+
 #define PG_dcache_clean PG_arch_1
 
 static inline void flush_dcache_folio(struct folio *folio)
@@ -33,8 +39,11 @@ 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 2fee65cc84..808b4c7846 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -10,140 +10,81 @@
 
 #include <asm/fence.h>
 
-#define __xchg_relaxed(ptr, new, size)					\
+#define __arch_xchg_masked(sc_sfx, 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" sc_sfx " %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, sc_sfx, swap_sfx, prepend,			\
+		   sc_append, swap_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(sc_sfx, prepend, sc_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" swap_sfx, prepend, swap_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" swap_sfx, prepend, swap_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, 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, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
 
 #define xchg32(ptr, x)							\
 ({									\
@@ -162,190 +103,95 @@
  * 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 +205,22 @@
 	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/csr.h b/arch/riscv/include/asm/csr.h
index 9d1b079327..25966995da 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -168,7 +168,8 @@
 #define VSIP_TO_HVIP_SHIFT	(IRQ_VS_SOFT - IRQ_S_SOFT)
 #define VSIP_VALID_MASK		((_AC(1, UL) << IRQ_S_SOFT) | \
 				 (_AC(1, UL) << IRQ_S_TIMER) | \
-				 (_AC(1, UL) << IRQ_S_EXT))
+				 (_AC(1, UL) << IRQ_S_EXT) | \
+				 (_AC(1, UL) << IRQ_PMU_OVF))
 
 /* AIA CSR bits */
 #define TOPI_IID_SHIFT		16
diff --git a/arch/riscv/include/asm/fpu.h b/arch/riscv/include/asm/fpu.h
new file mode 100644
index 0000000000..91c04c244e
--- /dev/null
+++ b/arch/riscv/include/asm/fpu.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_RISCV_FPU_H
+#define _ASM_RISCV_FPU_H
+
+#include <asm/switch_to.h>
+
+#define kernel_fpu_available()	has_fpu()
+
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
+
+#endif /* ! _ASM_RISCV_FPU_H */
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 1276d7d9ca..9eb31a7ea0 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -124,20 +124,82 @@ struct dyn_ftrace;
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+#define arch_ftrace_get_regs(regs) NULL
 struct ftrace_ops;
-struct ftrace_regs;
+struct ftrace_regs {
+	unsigned long epc;
+	unsigned long ra;
+	unsigned long sp;
+	unsigned long s0;
+	unsigned long t1;
+	union {
+		unsigned long args[8];
+		struct {
+			unsigned long a0;
+			unsigned long a1;
+			unsigned long a2;
+			unsigned long a3;
+			unsigned long a4;
+			unsigned long a5;
+			unsigned long a6;
+			unsigned long a7;
+		};
+	};
+};
+
+static __always_inline unsigned long ftrace_regs_get_instruction_pointer(const struct ftrace_regs
+									 *fregs)
+{
+	return fregs->epc;
+}
+
+static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
+								unsigned long pc)
+{
+	fregs->epc = pc;
+}
+
+static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs)
+{
+	return fregs->sp;
+}
+
+static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs,
+							      unsigned int n)
+{
+	if (n < 8)
+		return fregs->args[n];
+	return 0;
+}
+
+static __always_inline unsigned long ftrace_regs_get_return_value(const struct ftrace_regs *fregs)
+{
+	return fregs->a0;
+}
+
+static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs,
+							 unsigned long ret)
+{
+	fregs->a0 = ret;
+}
+
+static __always_inline void ftrace_override_function_with_return(struct ftrace_regs *fregs)
+{
+	fregs->epc = fregs->ra;
+}
+
+int ftrace_regs_query_register_offset(const char *name);
+
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #define ftrace_graph_func ftrace_graph_func
 
-static inline void __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
+static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr)
 {
-		regs->t1 = addr;
+	fregs->t1 = addr;
 }
-#define arch_ftrace_set_direct_caller(fregs, addr) \
-	__arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index 22deb7a2a6..b1ce97a9db 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -5,11 +5,11 @@
 #include <asm/cacheflush.h>
 #include <asm/page.h>
 
-static inline void arch_clear_hugepage_flags(struct page *page)
+static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
-	clear_bit(PG_dcache_clean, &page->flags);
+	clear_bit(PG_dcache_clean, &folio->flags);
 }
-#define arch_clear_hugepage_flags arch_clear_hugepage_flags
+#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
 
 #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
 bool arch_hugetlb_migration_supported(struct hstate *h);
diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
index 08d4d6a5b7..6fd8cbfcfc 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/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 484d04a92f..d962812785 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -43,6 +43,17 @@
 	KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_STEAL_UPDATE		KVM_ARCH_REQ(6)
 
+#define KVM_HEDELEG_DEFAULT		(BIT(EXC_INST_MISALIGNED) | \
+					 BIT(EXC_BREAKPOINT)      | \
+					 BIT(EXC_SYSCALL)         | \
+					 BIT(EXC_INST_PAGE_FAULT) | \
+					 BIT(EXC_LOAD_PAGE_FAULT) | \
+					 BIT(EXC_STORE_PAGE_FAULT))
+
+#define KVM_HIDELEG_DEFAULT		(BIT(IRQ_VS_SOFT)  | \
+					 BIT(IRQ_VS_TIMER) | \
+					 BIT(IRQ_VS_EXT))
+
 enum kvm_riscv_hfence_type {
 	KVM_RISCV_HFENCE_UNKNOWN = 0,
 	KVM_RISCV_HFENCE_GVMA_VMID_GPA,
@@ -169,6 +180,7 @@ struct kvm_vcpu_csr {
 struct kvm_vcpu_config {
 	u64 henvcfg;
 	u64 hstateen0;
+	unsigned long hedeleg;
 };
 
 struct kvm_vcpu_smstateen_csr {
@@ -211,6 +223,7 @@ struct kvm_vcpu_arch {
 
 	/* CPU context upon Guest VCPU reset */
 	struct kvm_cpu_context guest_reset_context;
+	spinlock_t reset_cntx_lock;
 
 	/* CPU CSR context upon Guest VCPU reset */
 	struct kvm_vcpu_csr guest_reset_csr;
@@ -252,8 +265,9 @@ struct kvm_vcpu_arch {
 	/* Cache pages needed to program page tables with spinlock held */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
-	/* VCPU power-off state */
-	bool power_off;
+	/* VCPU power state */
+	struct kvm_mp_state mp_state;
+	spinlock_t mp_state_lock;
 
 	/* Don't run the VCPU (blocked) */
 	bool pause;
@@ -374,8 +388,11 @@ int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
 void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu);
 bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask);
+void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
+void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
+bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu);
 
 void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu);
diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h
index 395518a166..fa0f535bbb 100644
--- a/arch/riscv/include/asm/kvm_vcpu_pmu.h
+++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h
@@ -20,7 +20,7 @@ static_assert(RISCV_KVM_MAX_COUNTERS <= 64);
 
 struct kvm_fw_event {
 	/* Current value of the event */
-	unsigned long value;
+	u64 value;
 
 	/* Event monitoring status */
 	bool started;
@@ -36,6 +36,7 @@ struct kvm_pmc {
 	bool started;
 	/* Monitoring event ID */
 	unsigned long event_idx;
+	struct kvm_vcpu *vcpu;
 };
 
 /* PMU data structure per vcpu */
@@ -50,6 +51,12 @@ struct kvm_pmu {
 	bool init_done;
 	/* Bit map of all the virtual counter used */
 	DECLARE_BITMAP(pmc_in_use, RISCV_KVM_MAX_COUNTERS);
+	/* Bit map of all the virtual counter overflown */
+	DECLARE_BITMAP(pmc_overflown, RISCV_KVM_MAX_COUNTERS);
+	/* The address of the counter snapshot area (guest physical address) */
+	gpa_t snapshot_addr;
+	/* The actual data of the snapshot */
+	struct riscv_pmu_snapshot_data *sdata;
 };
 
 #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu_context)
@@ -82,9 +89,14 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba
 				     unsigned long ctr_mask, unsigned long flags,
 				     unsigned long eidx, u64 evtdata,
 				     struct kvm_vcpu_sbi_return *retdata);
-int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx,
+int kvm_riscv_vcpu_pmu_fw_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx,
 				struct kvm_vcpu_sbi_return *retdata);
+int kvm_riscv_vcpu_pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx,
+				      struct kvm_vcpu_sbi_return *retdata);
 void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long saddr_low,
+				      unsigned long saddr_high, unsigned long flags,
+				      struct kvm_vcpu_sbi_return *retdata);
 void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu);
 
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index 355504b37f..947fd60f90 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 e88b52d39e..9f5d6e14c4 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 deaf971253..f52264304f 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/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 221a5c1ee2..8c36a88184 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -16,8 +16,6 @@ extern bool pgtable_l5_enabled;
 #define PGDIR_SHIFT_L3  30
 #define PGDIR_SHIFT_L4  39
 #define PGDIR_SHIFT_L5  48
-#define PGDIR_SIZE_L3   (_AC(1, UL) << PGDIR_SHIFT_L3)
-
 #define PGDIR_SHIFT     (pgtable_l5_enabled ? PGDIR_SHIFT_L5 : \
 		(pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3))
 /* Size of region mapped by a page global directory */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 6afd6bb488..aad8b8ca51 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -55,6 +55,9 @@
 #define MODULES_LOWEST_VADDR	(KERNEL_LINK_ADDR - SZ_2G)
 #define MODULES_VADDR		(PFN_ALIGN((unsigned long)&_end) - SZ_2G)
 #define MODULES_END		(PFN_ALIGN((unsigned long)&_start))
+#else
+#define MODULES_VADDR		VMALLOC_START
+#define MODULES_END		VMALLOC_END
 #endif
 
 /*
@@ -648,6 +651,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 
 #define __pud_to_phys(pud)  (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT)
 
+#define pud_pfn pud_pfn
 static inline unsigned long pud_pfn(pud_t pud)
 {
 	return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT);
@@ -876,7 +880,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
  */
 #ifdef CONFIG_64BIT
 #define TASK_SIZE_64	(PGDIR_SIZE * PTRS_PER_PGD / 2)
-#define TASK_SIZE_MIN	(PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
+#define TASK_SIZE_MAX	LONG_MAX
 
 #ifdef CONFIG_COMPAT
 #define TASK_SIZE_32	(_AC(0x80000000, UL) - PAGE_SIZE)
@@ -888,7 +892,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 
 #else
 #define TASK_SIZE	FIXADDR_START
-#define TASK_SIZE_MIN	TASK_SIZE
 #endif
 
 #else /* CONFIG_MMU */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 0faf5f161f..68c3432dc6 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 0fab508a65..1079e214fe 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -131,6 +131,8 @@ enum sbi_ext_pmu_fid {
 	SBI_EXT_PMU_COUNTER_START,
 	SBI_EXT_PMU_COUNTER_STOP,
 	SBI_EXT_PMU_COUNTER_FW_READ,
+	SBI_EXT_PMU_COUNTER_FW_READ_HI,
+	SBI_EXT_PMU_SNAPSHOT_SET_SHMEM,
 };
 
 union sbi_pmu_ctr_info {
@@ -147,6 +149,13 @@ union sbi_pmu_ctr_info {
 	};
 };
 
+/* Data structure to contain the pmu snapshot data */
+struct riscv_pmu_snapshot_data {
+	u64 ctr_overflow_mask;
+	u64 ctr_values[64];
+	u64 reserved[447];
+};
+
 #define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0)
 #define RISCV_PMU_RAW_EVENT_IDX 0x20000
 
@@ -232,20 +241,22 @@ enum sbi_pmu_ctr_type {
 #define SBI_PMU_EVENT_IDX_INVALID 0xFFFFFFFF
 
 /* Flags defined for config matching function */
-#define SBI_PMU_CFG_FLAG_SKIP_MATCH	(1 << 0)
-#define SBI_PMU_CFG_FLAG_CLEAR_VALUE	(1 << 1)
-#define SBI_PMU_CFG_FLAG_AUTO_START	(1 << 2)
-#define SBI_PMU_CFG_FLAG_SET_VUINH	(1 << 3)
-#define SBI_PMU_CFG_FLAG_SET_VSINH	(1 << 4)
-#define SBI_PMU_CFG_FLAG_SET_UINH	(1 << 5)
-#define SBI_PMU_CFG_FLAG_SET_SINH	(1 << 6)
-#define SBI_PMU_CFG_FLAG_SET_MINH	(1 << 7)
+#define SBI_PMU_CFG_FLAG_SKIP_MATCH	BIT(0)
+#define SBI_PMU_CFG_FLAG_CLEAR_VALUE	BIT(1)
+#define SBI_PMU_CFG_FLAG_AUTO_START	BIT(2)
+#define SBI_PMU_CFG_FLAG_SET_VUINH	BIT(3)
+#define SBI_PMU_CFG_FLAG_SET_VSINH	BIT(4)
+#define SBI_PMU_CFG_FLAG_SET_UINH	BIT(5)
+#define SBI_PMU_CFG_FLAG_SET_SINH	BIT(6)
+#define SBI_PMU_CFG_FLAG_SET_MINH	BIT(7)
 
 /* Flags defined for counter start function */
-#define SBI_PMU_START_FLAG_SET_INIT_VALUE (1 << 0)
+#define SBI_PMU_START_FLAG_SET_INIT_VALUE BIT(0)
+#define SBI_PMU_START_FLAG_INIT_SNAPSHOT BIT(1)
 
 /* Flags defined for counter stop function */
-#define SBI_PMU_STOP_FLAG_RESET (1 << 0)
+#define SBI_PMU_STOP_FLAG_RESET BIT(0)
+#define SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT BIT(1)
 
 enum sbi_ext_dbcn_fid {
 	SBI_EXT_DBCN_CONSOLE_WRITE = 0,
@@ -266,7 +277,7 @@ struct sbi_sta_struct {
 	u8 pad[47];
 } __packed;
 
-#define SBI_STA_SHMEM_DISABLE		-1
+#define SBI_SHMEM_DISABLE		-1
 
 /* SBI spec version fields */
 #define SBI_SPEC_VERSION_DEFAULT	0x1
@@ -284,6 +295,7 @@ struct sbi_sta_struct {
 #define SBI_ERR_ALREADY_AVAILABLE -6
 #define SBI_ERR_ALREADY_STARTED -7
 #define SBI_ERR_ALREADY_STOPPED -8
+#define SBI_ERR_NO_SHMEM	-9
 
 extern unsigned long sbi_spec_version;
 struct sbiret {
@@ -355,8 +367,8 @@ static inline unsigned long sbi_minor_version(void)
 static inline unsigned long sbi_mk_version(unsigned long major,
 					    unsigned long minor)
 {
-	return ((major & SBI_SPEC_VERSION_MAJOR_MASK) <<
-		SBI_SPEC_VERSION_MAJOR_SHIFT) | minor;
+	return ((major & SBI_SPEC_VERSION_MAJOR_MASK) << SBI_SPEC_VERSION_MAJOR_SHIFT)
+		| (minor & SBI_SPEC_VERSION_MINOR_MASK);
 }
 
 int sbi_err_map_linux_errno(int err);
@@ -377,8 +389,12 @@ 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 956ae0a01b..0000000000
--- 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 0d555847cd..7ac80e9f22 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 4718096fa5..4ffb022b09 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 7efdb0584d..7594df37cc 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 79dada53d7..72e5599349 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -15,8 +15,6 @@
 #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");
@@ -44,12 +42,7 @@ static inline void local_flush_tlb_page_asid(unsigned long addr,
 	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,
@@ -72,27 +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 */