diff options
| author | Guo Ren <guoren@linux.alibaba.com> | 2024-12-16 20:39:10 -0500 |
|---|---|---|
| committer | Alexandre Ghiti <alexghiti@rivosinc.com> | 2025-03-18 09:12:45 +0000 |
| commit | d9708b1931fc0ebb21cd94a56283d09222847749 (patch) | |
| tree | c71d6dabdefb4051d9093b0908967705f4664367 | |
| parent | d9be2b9b60497a82aeceec3a98d8b37fdd2960f2 (diff) | |
riscv: Implement smp_cond_load8/16() with Zawrs
RISC-V code uses the queued spinlock implementation, which calls
the macros smp_cond_load_acquire for one byte. So, complement the
implementation of byte and halfword versions.
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Cc: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241217013910.1039923-1-guoren@kernel.org
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
| -rw-r--r-- | arch/riscv/include/asm/cmpxchg.h | 38 |
1 files changed, 35 insertions, 3 deletions
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index 427c41dde643..2ec119eb147b 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -365,16 +365,48 @@ static __always_inline void __cmpwait(volatile void *ptr, { unsigned long tmp; + u32 *__ptr32b; + ulong __s, __val, __mask; + asm goto(ALTERNATIVE("j %l[no_zawrs]", "nop", 0, RISCV_ISA_EXT_ZAWRS, 1) : : : : no_zawrs); switch (size) { case 1: - fallthrough; + __ptr32b = (u32 *)((ulong)(ptr) & ~0x3); + __s = ((ulong)(ptr) & 0x3) * BITS_PER_BYTE; + __val = val << __s; + __mask = 0xff << __s; + + asm volatile( + " lr.w %0, %1\n" + " and %0, %0, %3\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(__ptr32b)) + : "r" (__val), "r" (__mask) + : "memory"); + break; case 2: - /* RISC-V doesn't have lr instructions on byte and half-word. */ - goto no_zawrs; + __ptr32b = (u32 *)((ulong)(ptr) & ~0x3); + __s = ((ulong)(ptr) & 0x2) * BITS_PER_BYTE; + __val = val << __s; + __mask = 0xffff << __s; + + asm volatile( + " lr.w %0, %1\n" + " and %0, %0, %3\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(__ptr32b)) + : "r" (__val), "r" (__mask) + : "memory"); + break; case 4: asm volatile( " lr.w %0, %1\n" |