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
  ...

35 files changed, 615 insertions, 666 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 410d1d6e1b6c..0bdcc383644d 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -23,6 +23,7 @@ config RISCV
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DEBUG_WX
+	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
@@ -57,10 +58,11 @@ config RISCV
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
 	select ARCH_SUPPORTS_PER_VMA_LOCK if MMU
 	select ARCH_SUPPORTS_SHADOW_CALL_STACK if HAVE_SHADOW_CALL_STACK
+	select ARCH_USE_CMPXCHG_LOCKREF if 64BIT
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USES_CFI_TRAPS if CFI_CLANG
-	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP && MMU
+	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if MMU
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT
@@ -71,7 +73,7 @@ config RISCV
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
-	select CLINT_TIMER if !MMU
+	select CLINT_TIMER if RISCV_M_MODE
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
@@ -155,6 +157,7 @@ config RISCV
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK if !XIP_KERNEL
 	select HAVE_RSEQ
+	select HAVE_RUST if 64BIT
 	select HAVE_SAMPLE_FTRACE_DIRECT
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_STACKPROTECTOR
@@ -231,8 +234,12 @@ config ARCH_MMAP_RND_COMPAT_BITS_MAX
 
 # set if we run in machine mode, cleared if we run in supervisor mode
 config RISCV_M_MODE
-	bool
-	default !MMU
+	bool "Build a kernel that runs in machine mode"
+	depends on !MMU
+	default y
+	help
+	  Select this option if you want to run the kernel in M-mode,
+	  without the assistance of any other firmware.
 
 # set if we are running in S-mode and can use SBI calls
 config RISCV_SBI
@@ -249,8 +256,9 @@ config MMU
 
 config PAGE_OFFSET
 	hex
-	default 0xC0000000 if 32BIT && MMU
-	default 0x80000000 if !MMU
+	default 0x80000000 if !MMU && RISCV_M_MODE
+	default 0x80200000 if !MMU
+	default 0xc0000000 if 32BIT
 	default 0xff60000000000000 if 64BIT
 
 config KASAN_SHADOW_OFFSET
@@ -598,7 +606,6 @@ config TOOLCHAIN_HAS_VECTOR_CRYPTO
 config RISCV_ISA_ZBB
 	bool "Zbb extension support for bit manipulation instructions"
 	depends on TOOLCHAIN_HAS_ZBB
-	depends on MMU
 	depends on RISCV_ALTERNATIVE
 	default y
 	help
@@ -630,7 +637,6 @@ config RISCV_ISA_ZICBOM
 
 config RISCV_ISA_ZICBOZ
 	bool "Zicboz extension support for faster zeroing of memory"
-	depends on MMU
 	depends on RISCV_ALTERNATIVE
 	default y
 	help
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 1e002d8003c5..c537764ee3c9 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -34,6 +34,9 @@ ifeq ($(CONFIG_ARCH_RV64I),y)
 	KBUILD_AFLAGS += -mabi=lp64
 
 	KBUILD_LDFLAGS += -melf64lriscv
+
+	KBUILD_RUSTFLAGS += -Ctarget-cpu=generic-rv64 --target=riscv64imac-unknown-none-elf \
+			    -Cno-redzone
 else
 	BITS := 32
 	UTS_MACHINE := riscv32
@@ -68,6 +71,10 @@ riscv-march-$(CONFIG_FPU)		:= $(riscv-march-y)fd
 riscv-march-$(CONFIG_RISCV_ISA_C)	:= $(riscv-march-y)c
 riscv-march-$(CONFIG_RISCV_ISA_V)	:= $(riscv-march-y)v
 
+ifneq ($(CONFIG_RISCV_ISA_C),y)
+	KBUILD_RUSTFLAGS += -Ctarget-feature=-c
+endif
+
 ifdef CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC
 KBUILD_CFLAGS += -Wa,-misa-spec=2.2
 KBUILD_AFLAGS += -Wa,-misa-spec=2.2
@@ -133,7 +140,15 @@ boot		:= arch/riscv/boot
 ifeq ($(CONFIG_XIP_KERNEL),y)
 KBUILD_IMAGE := $(boot)/xipImage
 else
+ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN_K210),yy)
+KBUILD_IMAGE := $(boot)/loader.bin
+else
+ifeq ($(CONFIG_EFI_ZBOOT),)
 KBUILD_IMAGE	:= $(boot)/Image.gz
+else
+KBUILD_IMAGE := $(boot)/vmlinuz.efi
+endif
+endif
 endif
 
 libs-y += arch/riscv/lib/
@@ -153,17 +168,6 @@ endif
 vdso-install-y			+= arch/riscv/kernel/vdso/vdso.so.dbg
 vdso-install-$(CONFIG_COMPAT)	+= arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg
 
-ifneq ($(CONFIG_XIP_KERNEL),y)
-ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN_K210),yy)
-KBUILD_IMAGE := $(boot)/loader.bin
-else
-ifeq ($(CONFIG_EFI_ZBOOT),)
-KBUILD_IMAGE := $(boot)/Image.gz
-else
-KBUILD_IMAGE := $(boot)/vmlinuz.efi
-endif
-endif
-endif
 BOOT_TARGETS := Image Image.gz loader loader.bin xipImage vmlinuz.efi
 
 all:	$(notdir $(KBUILD_IMAGE))
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 3cae018f9315..12dc8c73a8ac 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -234,6 +234,7 @@ CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VIRTIO_MMIO=y
 CONFIG_RENESAS_OSTM=y
+CONFIG_CLK_SOPHGO_CV1800=y
 CONFIG_SUN8I_DE2_CCU=m
 CONFIG_SUN50I_IOMMU=y
 CONFIG_RPMSG_CHAR=y
diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c
index 3d9a32d791f7..716cfedad3a2 100644
--- a/arch/riscv/errata/sifive/errata.c
+++ b/arch/riscv/errata/sifive/errata.c
@@ -42,6 +42,11 @@ static bool errata_cip_1200_check_func(unsigned long  arch_id, unsigned long imp
 		return false;
 	if ((impid & 0xffffff) > 0x200630 || impid == 0x1200626)
 		return false;
+
+#ifdef CONFIG_MMU
+	tlb_flush_all_threshold = 0;
+#endif
+
 	return true;
 }
 
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"			\
-			"	b