diff options
| author | Alexandre Ghiti <alexghiti@rivosinc.com> | 2024-11-03 15:51:45 +0100 |
|---|---|---|
| committer | Palmer Dabbelt <palmer@rivosinc.com> | 2024-11-11 07:33:12 -0800 |
| commit | 1658ef4314b37ff4858a6c207646ff9d280ca4f7 (patch) | |
| tree | 411b13687626ced159b40c4e8a0bb797dec15c29 /arch/riscv/include/asm/cmpxchg.h | |
| parent | 51624ddcf59dd78c810fd7da768d688e193b42d6 (diff) | |
| download | linux-next-1658ef4314b37ff4858a6c207646ff9d280ca4f7.tar.gz linux-next-1658ef4314b37ff4858a6c207646ff9d280ca4f7.zip | |
riscv: Implement cmpxchg8/16() using Zabha
This adds runtime support for Zabha in cmpxchg8/16() operations.
Note that in the absence of Zacas support in the toolchain, CAS
instructions from Zabha won't be used.
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-6-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Diffstat (limited to 'arch/riscv/include/asm/cmpxchg.h')
| -rw-r--r-- | arch/riscv/include/asm/cmpxchg.h | 78 |
1 files changed, 49 insertions, 29 deletions
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index 39c1daf39f6a..1f4cd12e4664 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -108,34 +108,49 @@ * 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, prepend, 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__ ( \ + prepend \ + " amocas" cas_sfx " %0, %z2, %1\n" \ + 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__ ( \ + 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_cas_sfx, prepend, append, r, p, co, o, n) \ @@ -177,8 +192,13 @@ \ switch (sizeof(*__ptr)) { \ case 1: \ + __arch_cmpxchg_masked(sc_cas_sfx, ".b" sc_cas_sfx, \ + prepend, append, \ + __ret, __ptr, __old, __new); \ + break; \ case 2: \ - __arch_cmpxchg_masked(sc_cas_sfx, prepend, append, \ + __arch_cmpxchg_masked(sc_cas_sfx, ".h" sc_cas_sfx, \ + prepend, append, \ __ret, __ptr, __old, __new); \ break; \ case 4: \ |