[PATCH v2 06/10] riscv: Implement xchg8/16() using Zabha

[Guo Ren]

On Wed, Jun 26, 2024 at 9:10 PM Alexandre Ghiti <alexghiti at rivosinc.com> wrote:
>
> This adds runtime support for Zabha in xchg8/16() operations.
>
> Signed-off-by: Alexandre Ghiti <alexghiti at rivosinc.com>
> ---
>  arch/riscv/include/asm/cmpxchg.h | 33 +++++++++++++++++++++++++++++---
>  arch/riscv/include/asm/hwcap.h   |  1 +
>  arch/riscv/kernel/cpufeature.c   |  1 +
>  3 files changed, 32 insertions(+), 3 deletions(-)
>
> diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
> index da42f32ea53d..eb35e2d30a97 100644
> --- a/arch/riscv/include/asm/cmpxchg.h
> +++ b/arch/riscv/include/asm/cmpxchg.h
> @@ -11,8 +11,17 @@
>  #include <asm/fence.h>
>  #include <asm/alternative.h>
>
> -#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n)           \
> +#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append,       \
> +                          swap_append, r, p, n)                        \
>  ({                                                                     \
> +       __label__ zabha, end;                                           \
> +                                                                       \
> +       if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA)) {                       \
> +               asm goto(ALTERNATIVE("nop", "j %[zabha]", 0,            \
> +                                    RISCV_ISA_EXT_ZABHA, 1)            \
> +                        : : : : zabha);                                \
> +       }                                                               \
> +                                                                       \
Could we exchange the sequence between Zabha & lr/sc?
I mean:
nop -> zabha
j -> lr/sc


>         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)   \
> @@ -28,12 +37,25 @@
>                "        or   %1, %1, %z3\n"                             \
>                "        sc.w" sc_sfx " %1, %1, %2\n"                    \
>                "        bnez %1, 0b\n"                                  \
> -              append                                                   \
> +              sc_append                                                        \
>                : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))       \
>                : "rJ" (__newx), "rJ" (~__mask)                          \
>                : "memory");                                             \
>                                                                         \
>         r = (__typeof__(*(p)))((__retx & __mask) >> __s);               \
> +       goto end;                                                       \
> +                                                                       \
> +zabha:
jump lr/sc implementation because it's already slow.
                                                               \
> +       if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA)) {                       \
> +               __asm__ __volatile__ (                                  \
> +                       prepend                                         \
> +                       "       amoswap" swap_sfx " %0, %z2, %1\n"      \
> +                       swap_append                                             \
> +                       : "=&r" (r), "+A" (*(p))                        \
> +                       : "rJ" (n)                                      \
> +                       : "memory");                                    \
> +       }                                                               \
> +end:;                                                                  \
>  })
>
>  #define __arch_xchg(sfx, prepend, append, r, p, n)                     \
> @@ -56,8 +78,13 @@
>                                                                         \
>         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:                                                         \
> diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
> index e17d0078a651..f71ddd2ca163 100644
> --- a/arch/riscv/include/asm/hwcap.h
> +++ b/arch/riscv/include/asm/hwcap.h
> @@ -81,6 +81,7 @@
>  #define RISCV_ISA_EXT_ZTSO             72
>  #define RISCV_ISA_EXT_ZACAS            73
>  #define RISCV_ISA_EXT_XANDESPMU                74
> +#define RISCV_ISA_EXT_ZABHA            75
>
>  #define RISCV_ISA_EXT_XLINUXENVCFG     127
>
> diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
> index 5ef48cb20ee1..c125d82c894b 100644
> --- a/arch/riscv/kernel/cpufeature.c
> +++ b/arch/riscv/kernel/cpufeature.c
> @@ -257,6 +257,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
>         __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
>         __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
>         __RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
> +       __RISCV_ISA_EXT_DATA(zabha, RISCV_ISA_EXT_ZABHA),
>         __RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
>         __RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
>         __RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
> --
> 2.39.2
>


-- 
Best Regards
 Guo Ren