Message ID | 20241103223154.136127-4-ebiggers@kernel.org (mailing list archive) |
---|---|
State | New |
Headers | show |
Series | Wire up CRC32 library functions to arch-optimized code | expand |
On Sun, 3 Nov 2024 at 23:34, Eric Biggers <ebiggers@kernel.org> wrote: > > From: Eric Biggers <ebiggers@google.com> > > Make the CRC32 library export a function crc32_optimizations() which > returns flags that indicate which CRC32 functions are actually executing > optimized code at runtime. > > This will be used to determine whether the crc32[c]-$arch shash > algorithms should be registered in the crypto API. btrfs could also > start using these flags instead of the hack that it currently uses where > it parses the crypto_shash_driver_name. > > Signed-off-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> > --- > arch/arm64/lib/crc32-glue.c | 10 ++++++++++ > arch/riscv/lib/crc32-riscv.c | 10 ++++++++++ > include/linux/crc32.h | 15 +++++++++++++++ > 3 files changed, 35 insertions(+) > > diff --git a/arch/arm64/lib/crc32-glue.c b/arch/arm64/lib/crc32-glue.c > index d7f6e1cbf0d2..15c4c9db573e 100644 > --- a/arch/arm64/lib/crc32-glue.c > +++ b/arch/arm64/lib/crc32-glue.c > @@ -83,7 +83,17 @@ u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len) > > return crc32_be_arm64(crc, p, len); > } > EXPORT_SYMBOL(crc32_be_arch); > > +u32 crc32_optimizations(void) > +{ > + if (alternative_has_cap_likely(ARM64_HAS_CRC32)) > + return CRC32_LE_OPTIMIZATION | > + CRC32_BE_OPTIMIZATION | > + CRC32C_OPTIMIZATION; > + return 0; > +} > +EXPORT_SYMBOL(crc32_optimizations); > + > MODULE_LICENSE("GPL"); > MODULE_DESCRIPTION("arm64-optimized CRC32 functions"); > diff --git a/arch/riscv/lib/crc32-riscv.c b/arch/riscv/lib/crc32-riscv.c > index a3ff7db2a1ce..53d56ab422c7 100644 > --- a/arch/riscv/lib/crc32-riscv.c > +++ b/arch/riscv/lib/crc32-riscv.c > @@ -295,7 +295,17 @@ u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len) > legacy: > return crc32_be_base(crc, p, len); > } > EXPORT_SYMBOL(crc32_be_arch); > > +u32 crc32_optimizations(void) > +{ > + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) > + return CRC32_LE_OPTIMIZATION | > + CRC32_BE_OPTIMIZATION | > + CRC32C_OPTIMIZATION; > + return 0; > +} > +EXPORT_SYMBOL(crc32_optimizations); > + > MODULE_LICENSE("GPL"); > MODULE_DESCRIPTION("Accelerated CRC32 implementation with Zbc extension"); > diff --git a/include/linux/crc32.h b/include/linux/crc32.h > index 58c632533b08..e9bd40056687 100644 > --- a/include/linux/crc32.h > +++ b/include/linux/crc32.h > @@ -35,10 +35,25 @@ static inline u32 __pure __crc32c_le(u32 crc, const u8 *p, size_t len) > if (IS_ENABLED(CONFIG_CRC32_ARCH)) > return crc32c_le_arch(crc, p, len); > return crc32c_le_base(crc, p, len); > } > > +/* > + * crc32_optimizations() returns flags that indicate which CRC32 library > + * functions are using architecture-specific optimizations. Unlike > + * IS_ENABLED(CONFIG_CRC32_ARCH) it takes into account the different CRC32 > + * variants and also whether any needed CPU features are available at runtime. > + */ > +#define CRC32_LE_OPTIMIZATION BIT(0) /* crc32_le() is optimized */ > +#define CRC32_BE_OPTIMIZATION BIT(1) /* crc32_be() is optimized */ > +#define CRC32C_OPTIMIZATION BIT(2) /* __crc32c_le() is optimized */ > +#if IS_ENABLED(CONFIG_CRC32_ARCH) > +u32 crc32_optimizations(void); > +#else > +static inline u32 crc32_optimizations(void) { return 0; } > +#endif > + > /** > * crc32_le_combine - Combine two crc32 check values into one. For two > * sequences of bytes, seq1 and seq2 with lengths len1 > * and len2, crc32_le() check values were calculated > * for each, crc1 and crc2. > -- > 2.47.0 > >
diff --git a/arch/arm64/lib/crc32-glue.c b/arch/arm64/lib/crc32-glue.c index d7f6e1cbf0d2..15c4c9db573e 100644 --- a/arch/arm64/lib/crc32-glue.c +++ b/arch/arm64/lib/crc32-glue.c @@ -83,7 +83,17 @@ u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len) return crc32_be_arm64(crc, p, len); } EXPORT_SYMBOL(crc32_be_arch); +u32 crc32_optimizations(void) +{ + if (alternative_has_cap_likely(ARM64_HAS_CRC32)) + return CRC32_LE_OPTIMIZATION | + CRC32_BE_OPTIMIZATION | + CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("arm64-optimized CRC32 functions"); diff --git a/arch/riscv/lib/crc32-riscv.c b/arch/riscv/lib/crc32-riscv.c index a3ff7db2a1ce..53d56ab422c7 100644 --- a/arch/riscv/lib/crc32-riscv.c +++ b/arch/riscv/lib/crc32-riscv.c @@ -295,7 +295,17 @@ u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len) legacy: return crc32_be_base(crc, p, len); } EXPORT_SYMBOL(crc32_be_arch); +u32 crc32_optimizations(void) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return CRC32_LE_OPTIMIZATION | + CRC32_BE_OPTIMIZATION | + CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Accelerated CRC32 implementation with Zbc extension"); diff --git a/include/linux/crc32.h b/include/linux/crc32.h index 58c632533b08..e9bd40056687 100644 --- a/include/linux/crc32.h +++ b/include/linux/crc32.h @@ -35,10 +35,25 @@ static inline u32 __pure __crc32c_le(u32 crc, const u8 *p, size_t len) if (IS_ENABLED(CONFIG_CRC32_ARCH)) return crc32c_le_arch(crc, p, len); return crc32c_le_base(crc, p, len); } +/* + * crc32_optimizations() returns flags that indicate which CRC32 library + * functions are using architecture-specific optimizations. Unlike + * IS_ENABLED(CONFIG_CRC32_ARCH) it takes into account the different CRC32 + * variants and also whether any needed CPU features are available at runtime. + */ +#define CRC32_LE_OPTIMIZATION BIT(0) /* crc32_le() is optimized */ +#define CRC32_BE_OPTIMIZATION BIT(1) /* crc32_be() is optimized */ +#define CRC32C_OPTIMIZATION BIT(2) /* __crc32c_le() is optimized */ +#if IS_ENABLED(CONFIG_CRC32_ARCH) +u32 crc32_optimizations(void); +#else +static inline u32 crc32_optimizations(void) { return 0; } +#endif + /** * crc32_le_combine - Combine two crc32 check values into one. For two * sequences of bytes, seq1 and seq2 with lengths len1 * and len2, crc32_le() check values were calculated * for each, crc1 and crc2.