diff options
author | Xiao Wang <xiao.w.wang@intel.com> | 2023-10-31 14:45:53 +0800 |
---|---|---|
committer | Palmer Dabbelt <palmer@rivosinc.com> | 2023-11-09 10:15:52 -0800 |
commit | 457926b253200bd9bdfae9a016a3b1d1dc661d55 (patch) | |
tree | 28d569b7577836d8163a8ebc37f67bbf5524749e /arch | |
parent | e72c4333d2f2e7f2200f71a88c0480fd2a769a64 (diff) | |
download | lwn-457926b253200bd9bdfae9a016a3b1d1dc661d55.tar.gz lwn-457926b253200bd9bdfae9a016a3b1d1dc661d55.zip |
riscv: Optimize bitops with Zbb extension
This patch leverages the alternative mechanism to dynamically optimize
bitops (including __ffs, __fls, ffs, fls) with Zbb instructions. When
Zbb ext is not supported by the runtime CPU, legacy implementation is
used. If Zbb is supported, then the optimized variants will be selected
via alternative patching.
The legacy bitops support is taken from the generic C implementation as
fallback.
If the parameter is a build-time constant, we leverage compiler builtin to
calculate the result directly, this approach is inspired by x86 bitops
implementation.
EFI stub runs before the kernel, so alternative mechanism should not be
used there, this patch introduces a macro NO_ALTERNATIVE for this purpose.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231031064553.2319688-3-xiao.w.wang@intel.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Diffstat (limited to 'arch')
-rw-r--r-- | arch/riscv/include/asm/bitops.h | 254 |
1 files changed, 251 insertions, 3 deletions
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h index 3540b690944b..b212c2708cda 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -15,13 +15,261 @@ #include <asm/barrier.h> #include <asm/bitsperlong.h> +#if !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) #include <asm-generic/bitops/__ffs.h> -#include <asm-generic/bitops/ffz.h> -#include <asm-generic/bitops/fls.h> #include <asm-generic/bitops/__fls.h> +#include <asm-generic/bitops/ffs.h> +#include <asm-generic/bitops/fls.h> + +#else +#include <asm/alternative-macros.h> +#include <asm/hwcap.h> + +#if (BITS_PER_LONG == 64) +#define CTZW "ctzw " +#define CLZW "clzw " +#elif (BITS_PER_LONG == 32) +#define CTZW "ctz " +#define CLZW "clz " +#else +#error "Unexpected BITS_PER_LONG" +#endif + +static __always_inline unsigned long variable__ffs(unsigned long word) +{ + int num; + + asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : : : : legacy); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + "ctz %0, %1\n" + ".option pop\n" + : "=r" (word) : "r" (word) :); + + return word; + +legacy: + num = 0; +#if BITS_PER_LONG == 64 + if ((word & 0xffffffff) == 0) { + num += 32; + word >>= 32; + } +#endif + if ((word & 0xffff) == 0) { + num += 16; + word >>= 16; + } + if ((word & 0xff) == 0) { + num += 8; + word >>= 8; + } + if ((word & 0xf) == 0) { + num += 4; + word >>= 4; + } + if ((word & 0x3) == 0) { + num += 2; + word >>= 2; + } + if ((word & 0x1) == 0) + num += 1; + return num; +} + +/** + * __ffs - find first set bit in a long word + * @word: The word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +#define __ffs(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(word) : \ + variable__ffs(word)) + +static __always_inline unsigned long variable__fls(unsigned long word) +{ + int num; + + asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : : : : legacy); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + "clz %0, %1\n" + ".option pop\n" + : "=r" (word) : "r" (word) :); + + return BITS_PER_LONG - 1 - word; + +legacy: + num = BITS_PER_LONG - 1; +#if BITS_PER_LONG == 64 + if (!(word & (~0ul << 32))) { + num -= 32; + word <<= 32; + } +#endif + if (!(word & (~0ul << (BITS_PER_LONG - 16)))) { + num -= 16; + word <<= 16; + } + if (!(word & (~0ul << (BITS_PER_LONG - 8)))) { + num -= 8; + word <<= 8; + } + if (!(word & (~0ul << (BITS_PER_LONG - 4)))) { + num -= 4; + word <<= 4; + } + if (!(word & (~0ul << (BITS_PER_LONG - 2)))) { + num -= 2; + word <<= 2; + } + if (!(word & (~0ul << (BITS_PER_LONG - 1)))) + num -= 1; + return num; +} + +/** + * __fls - find last set bit in a long word + * @word: the word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +#define __fls(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)(BITS_PER_LONG - 1 - __builtin_clzl(word)) : \ + variable__fls(word)) + +static __always_inline int variable_ffs(int x) +{ + int r; + + if (!x) + return 0; + + asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : : : : legacy); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + CTZW "%0, %1\n" + ".option pop\n" + : "=r" (r) : "r" (x) :); + + return r + 1; + +legacy: + r = 1; + if (!(x & 0xffff)) { + x >>= 16; + r += 16; + } + if (!(x & 0xff)) { + x >>= 8; + r += 8; + } + if (!(x & 0xf)) { + x >>= 4; + r += 4; + } + if (!(x & 3)) { + x >>= 2; + r += 2; + } + if (!(x & 1)) { + x >>= 1; + r += 1; + } + return r; +} + +/** + * ffs - find first set bit in a word + * @x: the word to search + * + * This is defined the same way as the libc and compiler builtin ffs routines. + * + * ffs(value) returns 0 if value is 0 or the position of the first set bit if + * value is nonzero. The first (least significant) bit is at position 1. + */ +#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x)) + +static __always_inline int variable_fls(unsigned int x) +{ + int r; + + if (!x) + return 0; + + asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : : : : legacy); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + CLZW "%0, %1\n" + ".option pop\n" + : "=r" (r) : "r" (x) :); + + return 32 - r; + +legacy: + r = 32; + if (!(x & 0xffff0000u)) { + x <<= 16; + r -= 16; + } + if (!(x & 0xff000000u)) { + x <<= 8; + r -= 8; + } + if (!(x & 0xf0000000u)) { + x <<= 4; + r -= 4; + } + if (!(x & 0xc0000000u)) { + x <<= 2; + r -= 2; + } + if (!(x & 0x80000000u)) { + x <<= 1; + r -= 1; + } + return r; +} + +/** + * fls - find last set bit in a word + * @x: the word to search + * + * This is defined in a similar way as ffs, but returns the position of the most + * significant set bit. + * + * fls(value) returns 0 if value is 0 or the position of the last set bit if + * value is nonzero. The last (most significant) bit is at position 32. + */ +#define fls(x) \ +({ \ + typeof(x) x_ = (x); \ + __builtin_constant_p(x_) ? \ + (int)((x_ != 0) ? (32 - __builtin_clz(x_)) : 0) \ + : \ + variable_fls(x_); \ +}) + +#endif /* !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) */ + +#include <asm-generic/bitops/ffz.h> #include <asm-generic/bitops/fls64.h> #include <asm-generic/bitops/sched.h> -#include <asm-generic/bitops/ffs.h> #include <asm-generic/bitops/hweight.h> |