summaryrefslogtreecommitdiff
path: root/arch/x86/crypto/sha1_ssse3_glue.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/crypto/sha1_ssse3_glue.c')
-rw-r--r--arch/x86/crypto/sha1_ssse3_glue.c49
1 files changed, 42 insertions, 7 deletions
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 4a11a9d72451..139a55c04d82 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -10,6 +10,7 @@
* Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
* Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
* Copyright (c) Mathias Krause <minipli@googlemail.com>
+ * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
@@ -39,6 +40,12 @@ asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
asmlinkage void sha1_transform_avx(u32 *digest, const char *data,
unsigned int rounds);
#endif
+#ifdef CONFIG_AS_AVX2
+#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */
+
+asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
+ unsigned int rounds);
+#endif
static asmlinkage void (*sha1_transform_asm)(u32 *, const char *, unsigned int);
@@ -165,6 +172,18 @@ static int sha1_ssse3_import(struct shash_desc *desc, const void *in)
return 0;
}
+#ifdef CONFIG_AS_AVX2
+static void sha1_apply_transform_avx2(u32 *digest, const char *data,
+ unsigned int rounds)
+{
+ /* Select the optimal transform based on data block size */
+ if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE)
+ sha1_transform_avx2(digest, data, rounds);
+ else
+ sha1_transform_avx(digest, data, rounds);
+}
+#endif
+
static struct shash_alg alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_ssse3_init,
@@ -189,7 +208,11 @@ static bool __init avx_usable(void)
{
u64 xcr0;
+#if defined(CONFIG_AS_AVX2)
+ if (!cpu_has_avx || !cpu_has_avx2 || !cpu_has_osxsave)
+#else
if (!cpu_has_avx || !cpu_has_osxsave)
+#endif
return false;
xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
@@ -205,23 +228,35 @@ static bool __init avx_usable(void)
static int __init sha1_ssse3_mod_init(void)
{
+ char *algo_name;
/* test for SSSE3 first */
- if (cpu_has_ssse3)
+ if (cpu_has_ssse3) {
sha1_transform_asm = sha1_transform_ssse3;
+ algo_name = "SSSE3";
+ }
#ifdef CONFIG_AS_AVX
/* allow AVX to override SSSE3, it's a little faster */
- if (avx_usable())
- sha1_transform_asm = sha1_transform_avx;
+ if (avx_usable()) {
+ if (cpu_has_avx) {
+ sha1_transform_asm = sha1_transform_avx;
+ algo_name = "AVX";
+ }
+#ifdef CONFIG_AS_AVX2
+ if (cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI2)) {
+ /* allow AVX2 to override AVX, it's a little faster */
+ sha1_transform_asm = sha1_apply_transform_avx2;
+ algo_name = "AVX2";
+ }
+#endif
+ }
#endif
if (sha1_transform_asm) {
- pr_info("Using %s optimized SHA-1 implementation\n",
- sha1_transform_asm == sha1_transform_ssse3 ? "SSSE3"
- : "AVX");
+ pr_info("Using %s optimized SHA-1 implementation\n", algo_name);
return crypto_register_shash(&alg);
}
- pr_info("Neither AVX nor SSSE3 is available/usable.\n");
+ pr_info("Neither AVX nor AVX2 nor SSSE3 is available/usable.\n");
return -ENODEV;
}