diff options
Diffstat (limited to 'arch/x86/crypto/crc32c-intel_glue.c')
| -rw-r--r-- | arch/x86/crypto/crc32c-intel_glue.c | 81 |
1 files changed, 81 insertions, 0 deletions
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 493f959..6812ad9 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -32,6 +32,8 @@ #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> +#include <asm/i387.h> +#include <asm/fpu-internal.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 @@ -44,6 +46,31 @@ #define REX_PRE #endif +#ifdef CONFIG_X86_64 +/* + * use carryless multiply version of crc32c when buffer + * size is >= 512 (when eager fpu is enabled) or + * >= 1024 (when eager fpu is disabled) to account + * for fpu state save/restore overhead. + */ +#define CRC32C_PCL_BREAKEVEN_EAGERFPU 512 +#define CRC32C_PCL_BREAKEVEN_NOEAGERFPU 1024 + +asmlinkage unsigned int crc_pcl(const u8 *buffer, int len, + unsigned int crc_init); +static int crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_EAGERFPU; +#if defined(X86_FEATURE_EAGER_FPU) +#define set_pcl_breakeven_point() \ +do { \ + if (!use_eager_fpu()) \ + crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU; \ +} while (0) +#else +#define set_pcl_breakeven_point() \ + (crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU) +#endif +#endif /* CONFIG_X86_64 */ + static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length) { while (length--) { @@ -154,6 +181,52 @@ static int crc32c_intel_cra_init(struct crypto_tfm *tfm) return 0; } +#ifdef CONFIG_X86_64 +static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + u32 *crcp = shash_desc_ctx(desc); + + /* + * use faster PCL version if datasize is large enough to + * overcome kernel fpu state save/restore overhead + */ + if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) { + kernel_fpu_begin(); + *crcp = crc_pcl(data, len, *crcp); + kernel_fpu_end(); + } else + *crcp = crc32c_intel_le_hw(*crcp, data, len); + return 0; +} + +static int __crc32c_pcl_intel_finup(u32 *crcp, const u8 *data, unsigned int len, + u8 *out) +{ + if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) { + kernel_fpu_begin(); + *(__le32 *)out = ~cpu_to_le32(crc_pcl(data, len, *crcp)); + kernel_fpu_end(); + } else + *(__le32 *)out = + ~cpu_to_le32(crc32c_intel_le_hw(*crcp, data, len)); + return 0; +} + +static int crc32c_pcl_intel_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return __crc32c_pcl_intel_finup(shash_desc_ctx(desc), data, len, out); +} + +static int crc32c_pcl_intel_digest(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return __crc32c_pcl_intel_finup(crypto_shash_ctx(desc->tfm), data, len, + out); +} +#endif /* CONFIG_X86_64 */ + static struct shash_alg alg = { .setkey = crc32c_intel_setkey, .init = crc32c_intel_init, @@ -184,6 +257,14 @@ static int __init crc32c_intel_mod_init(void) { if (!x86_match_cpu(crc32c_cpu_id)) return -ENODEV; +#ifdef CONFIG_X86_64 + if (cpu_has_pclmulqdq) { + alg.update = crc32c_pcl_intel_update; + alg.finup = crc32c_pcl_intel_finup; + alg.digest = crc32c_pcl_intel_digest; + set_pcl_breakeven_point(); + } +#endif return crypto_register_shash(&alg); } |
