diff options
Diffstat (limited to 'arch/riscv/include/asm/cmpxchg.h')
| -rw-r--r-- | arch/riscv/include/asm/cmpxchg.h | 286 |
1 files changed, 208 insertions, 78 deletions
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index ebbce134917c..4cadc56220fe 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -12,30 +12,43 @@ #include <asm/fence.h> #include <asm/hwcap.h> #include <asm/insn-def.h> - -#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); \ +#include <asm/cpufeature-macros.h> + +#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append, \ + swap_append, r, p, n) \ +({ \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) { \ + __asm__ __volatile__ ( \ + prepend \ + " amoswap" swap_sfx " %0, %z2, %1\n" \ + swap_append \ + : "=&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + 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" \ + sc_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) \ @@ -58,8 +71,13 @@ \ switch (sizeof(*__ptr)) { \ case 1: \ + __arch_xchg_masked(sc_sfx, ".b" swap_sfx, \ + prepend, sc_append, swap_append, \ + __ret, __ptr, __new); \ + break; \ case 2: \ - __arch_xchg_masked(sc_sfx, prepend, sc_append, \ + __arch_xchg_masked(sc_sfx, ".h" swap_sfx, \ + prepend, sc_append, swap_append, \ __ret, __ptr, __new); \ break; \ case 4: \ @@ -106,55 +124,90 @@ * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. */ - -#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_masked(sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + r, p, o, n) \ +({ \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && \ + IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) { \ + r = o; \ + \ + __asm__ __volatile__ ( \ + cas_prepend \ + " amocas" cas_sfx " %0, %z2, %1\n" \ + cas_append \ + : "+&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + 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__ ( \ + sc_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" \ + sc_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) \ +#define __arch_cmpxchg(lr_sfx, sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + r, p, co, o, n) \ ({ \ - register unsigned int __rc; \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) { \ + r = o; \ \ - __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"); \ + __asm__ __volatile__ ( \ + cas_prepend \ + " amocas" cas_sfx " %0, %z2, %1\n" \ + cas_append \ + : "+&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + register unsigned int __rc; \ + \ + __asm__ __volatile__ ( \ + sc_prepend \ + "0: lr" lr_sfx " %0, %2\n" \ + " bne %0, %z3, 1f\n" \ + " sc" sc_sfx " %1, %z4, %2\n" \ + " bnez %1, 0b\n" \ + sc_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) \ +#define _arch_cmpxchg(ptr, old, new, sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ __typeof__(*(__ptr)) __old = (old); \ @@ -163,17 +216,28 @@ \ switch (sizeof(*__ptr)) { \ case 1: \ + __arch_cmpxchg_masked(sc_sfx, ".b" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, __old, __new); \ + break; \ case 2: \ - __arch_cmpxchg_masked(sc_sfx, prepend, append, \ - __ret, __ptr, __old, __new); \ + __arch_cmpxchg_masked(sc_sfx, ".h" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, __old, __new); \ break; \ case 4: \ - __arch_cmpxchg(".w", ".w" sc_sfx, prepend, append, \ - __ret, __ptr, (long), __old, __new); \ + __arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, (long), __old, __new); \ break; \ case 8: \ - __arch_cmpxchg(".d", ".d" sc_sfx, prepend, append, \ - __ret, __ptr, /**/, __old, __new); \ + __arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, /**/, __old, __new); \ break; \ default: \ BUILD_BUG(); \ @@ -181,17 +245,40 @@ (__typeof__(*(__ptr)))__ret; \ }) +/* + * These macros are here to improve the readability of the arch_cmpxchg_XXX() + * macros. + */ +#define SC_SFX(x) x +#define CAS_SFX(x) x +#define SC_PREPEND(x) x +#define SC_APPEND(x) x +#define CAS_PREPEND(x) x +#define CAS_APPEND(x) x + #define arch_cmpxchg_relaxed(ptr, o, n) \ - _arch_cmpxchg((ptr), (o), (n), "", "", "") + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(""), SC_APPEND(""), \ + CAS_PREPEND(""), CAS_APPEND("")) #define arch_cmpxchg_acquire(ptr, o, n) \ - _arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER) + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(""), SC_APPEND(RISCV_ACQUIRE_BARRIER), \ + CAS_PREPEND(""), CAS_APPEND(RISCV_ACQUIRE_BARRIER)) #define arch_cmpxchg_release(ptr, o, n) \ - _arch_cmpxchg((ptr), (o), (n), "", RISCV_RELEASE_BARRIER, "") + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(RISCV_RELEASE_BARRIER), SC_APPEND(""), \ + CAS_PREPEND(RISCV_RELEASE_BARRIER), CAS_APPEND("")) #define arch_cmpxchg(ptr, o, n) \ - _arch_cmpxchg((ptr), (o), (n), ".rl", "", " fence rw, rw\n") + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(".rl"), CAS_SFX(".aqrl"), \ + SC_PREPEND(""), SC_APPEND(RISCV_FULL_BARRIER), \ + CAS_PREPEND(""), CAS_APPEND("")) #define arch_cmpxchg_local(ptr, o, n) \ arch_cmpxchg_relaxed((ptr), (o), (n)) @@ -226,6 +313,44 @@ arch_cmpxchg_release((ptr), (o), (n)); \ }) +#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS) + +#define system_has_cmpxchg128() riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS) + +union __u128_halves { + u128 full; + struct { + u64 low, high; + }; +}; + +#define __arch_cmpxchg128(p, o, n, cas_sfx) \ +({ \ + __typeof__(*(p)) __o = (o); \ + union __u128_halves __hn = { .full = (n) }; \ + union __u128_halves __ho = { .full = (__o) }; \ + register unsigned long t1 asm ("t1") = __hn.low; \ + register unsigned long t2 asm ("t2") = __hn.high; \ + register unsigned long t3 asm ("t3") = __ho.low; \ + register unsigned long t4 asm ("t4") = __ho.high; \ + \ + __asm__ __volatile__ ( \ + " amocas.q" cas_sfx " %0, %z3, %2" \ + : "+&r" (t3), "+&r" (t4), "+A" (*(p)) \ + : "rJ" (t1), "rJ" (t2) \ + : "memory"); \ + \ + ((u128)t4 << 64) | t3; \ +}) + +#define arch_cmpxchg128(ptr, o, n) \ + __arch_cmpxchg128((ptr), (o), (n), ".aqrl") + +#define arch_cmpxchg128_local(ptr, o, n) \ + __arch_cmpxchg128((ptr), (o), (n), "") + +#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS */ + #ifdef CONFIG_RISCV_ISA_ZAWRS /* * Despite wrs.nto being "WRS-with-no-timeout", in the absence of changes to @@ -245,6 +370,11 @@ static __always_inline void __cmpwait(volatile void *ptr, : : : : no_zawrs); switch (size) { + case 1: + fallthrough; + case 2: + /* RISC-V doesn't have lr instructions on byte and half-word. */ + goto no_zawrs; case 4: asm volatile( " lr.w %0, %1\n" |