diff options
Diffstat (limited to 'arch/riscv/include/asm/cmpxchg.h')
-rw-r--r-- | arch/riscv/include/asm/cmpxchg.h | 466 |
1 files changed, 194 insertions, 272 deletions
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index 2fee65cc8443..ebbce134917c 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -8,142 +8,86 @@ #include <linux/bug.h> +#include <asm/alternative-macros.h> #include <asm/fence.h> +#include <asm/hwcap.h> +#include <asm/insn-def.h> -#define __xchg_relaxed(ptr, new, size) \ +#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n) \ ({ \ - __typeof__(ptr) __ptr = (ptr); \ - __typeof__(new) __new = (new); \ - __typeof__(*(ptr)) __ret; \ - switch (size) { \ - case 4: \ - __asm__ __volatile__ ( \ - " amoswap.w %0, %2, %1\n" \ - : "=r" (__ret), "+A" (*__ptr) \ - : "r" (__new) \ - : "memory"); \ - break; \ - case 8: \ - __asm__ __volatile__ ( \ - " amoswap.d %0, %2, %1\n" \ - : "=r" (__ret), "+A" (*__ptr) \ - : "r" (__new) \ - : "memory"); \ - break; \ - default: \ - BUILD_BUG(); \ - } \ - __ret; \ + 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_relaxed(ptr, x) \ +#define __arch_xchg(sfx, prepend, append, r, p, n) \ ({ \ - __typeof__(*(ptr)) _x_ = (x); \ - (__typeof__(*(ptr))) __xchg_relaxed((ptr), \ - _x_, sizeof(*(ptr))); \ + __asm__ __volatile__ ( \ + prepend \ + " amoswap" sfx " %0, %2, %1\n" \ + append \ + : "=r" (r), "+A" (*(p)) \ + : "r" (n) \ + : "memory"); \ }) -#define __xchg_acquire(ptr, new, size) \ +#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" \ - RISCV_ACQUIRE_BARRIER \ - : "=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" \ - RISCV_ACQUIRE_BARRIER \ - : "=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_acquire(ptr, x) \ -({ \ - __typeof__(*(ptr)) _x_ = (x); \ - (__typeof__(*(ptr))) __xchg_acquire((ptr), \ - _x_, sizeof(*(ptr))); \ -}) +#define arch_xchg_relaxed(ptr, x) \ + _arch_xchg(ptr, x, "", "", "", "", "") -#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; \ -}) +#define arch_xchg_acquire(ptr, x) \ + _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 +106,95 @@ * 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) \ ({ \ - __typeof__(*(ptr)) _o_ = (o); \ - __typeof__(*(ptr)) _n_ = (n); \ - (__typeof__(*(ptr))) __cmpxchg_relaxed((ptr), \ - _o_, _n_, sizeof(*(ptr))); \ + 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 __cmpxchg_acquire(ptr, old, new, size) \ +#define __arch_cmpxchg(lr_sfx, sc_sfx, prepend, append, r, p, co, o, n) \ ({ \ - __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" \ - RISCV_ACQUIRE_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 %1, %z4, %2\n" \ - " bnez %1, 0b\n" \ - RISCV_ACQUIRE_BARRIER \ - "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) \ -({ \ - __typeof__(*(ptr)) _o_ = (o); \ - __typeof__(*(ptr)) _n_ = (n); \ - (__typeof__(*(ptr))) __cmpxchg_acquire((ptr), \ - _o_, _n_, sizeof(*(ptr))); \ + \ + __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 __cmpxchg_release(ptr, old, new, size) \ +#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__ ( \ - 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"); \ + __arch_cmpxchg(".w", ".w" sc_sfx, prepend, append, \ + __ret, __ptr, (long), __old, __new); \ 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"); \ + __arch_cmpxchg(".d", ".d" sc_sfx, prepend, append, \ + __ret, __ptr, /**/, __old, __new); \ break; \ default: \ BUILD_BUG(); \ } \ - __ret; \ + (__typeof__(*(__ptr)))__ret; \ }) -#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 arch_cmpxchg_relaxed(ptr, o, n) \ + _arch_cmpxchg((ptr), (o), (n), "", "", "") -#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; \ -}) +#define arch_cmpxchg_acquire(ptr, o, n) \ + _arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER) + +#define arch_cmpxchg_release(ptr, o, n) \ + _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 +208,77 @@ 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)); \ +}) + +#ifdef CONFIG_RISCV_ISA_ZAWRS +/* + * Despite wrs.nto being "WRS-with-no-timeout", in the absence of changes to + * @val we expect it to still terminate within a "reasonable" amount of time + * for an implementation-specific other reason, a pending, locally-enabled + * interrupt, or because it has been configured to raise an illegal + * instruction exception. + */ +static __always_inline void __cmpwait(volatile void *ptr, + unsigned long val, + int size) +{ + unsigned long tmp; + + asm goto(ALTERNATIVE("j %l[no_zawrs]", "nop", + 0, RISCV_ISA_EXT_ZAWRS, 1) + : : : : no_zawrs); + + switch (size) { + case 4: + asm volatile( + " lr.w %0, %1\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(u32 *)ptr) + : "r" (val)); + break; +#if __riscv_xlen == 64 + case 8: + asm volatile( + " lr.d %0, %1\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(u64 *)ptr) + : "r" (val)); + break; +#endif + default: + BUILD_BUG(); + } + + return; + +no_zawrs: + asm volatile(RISCV_PAUSE : : : "memory"); +} + +#define __cmpwait_relaxed(ptr, val) \ + __cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr))) +#endif + #endif /* _ASM_RISCV_CMPXCHG_H */ |