Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu: "API: - Add support for cipher output IVs in testmgr - Add missing crypto_ahash_blocksize helper - Mark authenc and des ciphers as not allowed under FIPS. Algorithms: - Add CRC support to 842 compression - Add keywrap algorithm - A number of changes to the akcipher interface: + Separate functions for setting public/private keys. + Use SG lists. Drivers: - Add Intel SHA Extension optimised SHA1 and SHA256 - Use dma_map_sg instead of custom functions in crypto drivers - Add support for STM32 RNG - Add support for ST RNG - Add Device Tree support to exynos RNG driver - Add support for mxs-dcp crypto device on MX6SL - Add xts(aes) support to caam - Add ctr(aes) and xts(aes) support to qat - A large set of fixes from Russell King for the marvell/cesa driver" * 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (115 commits) crypto: asymmetric_keys - Fix unaligned access in x509_get_sig_params() crypto: akcipher - Don't #include crypto/public_key.h as the contents aren't used hwrng: exynos - Add Device Tree support hwrng: exynos - Fix missing configuration after suspend to RAM hwrng: exynos - Add timeout for waiting on init done dt-bindings: rng: Describe Exynos4 PRNG bindings crypto: marvell/cesa - use __le32 for hardware descriptors crypto: marvell/cesa - fix missing cpu_to_le32() in mv_cesa_dma_add_op() crypto: marvell/cesa - use memcpy_fromio()/memcpy_toio() crypto: marvell/cesa - use gfp_t for gfp flags crypto: marvell/cesa - use dma_addr_t for cur_dma crypto: marvell/cesa - use readl_relaxed()/writel_relaxed() crypto: caam - fix indentation of close braces crypto: caam - only export the state we really need to export crypto: caam - fix non-block aligned hash calculation crypto: caam - avoid needlessly saving and restoring caam_hash_ctx crypto: caam - print errno code when hash registration fails crypto: marvell/cesa - fix memory leak crypto: marvell/cesa - fix first-fragment handling in mv_cesa_ahash_dma_last_req() crypto: marvell/cesa - rearrange handling for sw padded hashes ...
2015-11-04 09:11:12 -08:00
parent 66ef3493d4 271817a3e9
commit ccc9d4a6d6
98 changed files with 4082 additions and 1550 deletions
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -31,24 +31,11 @@
 #include <crypto/sha1_base.h>
 #include <asm/fpu/api.h>

+typedef void (sha1_transform_fn)(u32 *digest, const char *data,
+				unsigned int rounds);

-asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
-				     unsigned int rounds);
-#ifdef CONFIG_AS_AVX
-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 void (*sha1_transform_asm)(u32 *, const char *, unsigned int);
-
-static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len)
+static int sha1_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, sha1_transform_fn *sha1_xform)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);

@@ -61,14 +48,14 @@ static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data,

 	kernel_fpu_begin();
 	sha1_base_do_update(desc, data, len,
-			    (sha1_block_fn *)sha1_transform_asm);
+			    (sha1_block_fn *)sha1_xform);
 	kernel_fpu_end();

 	return 0;
 }

-static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data,
-			      unsigned int len, u8 *out)
+static int sha1_finup(struct shash_desc *desc, const u8 *data,
+		      unsigned int len, u8 *out, sha1_transform_fn *sha1_xform)
 {
 	if (!irq_fpu_usable())
 		return crypto_sha1_finup(desc, data, len, out);
@@ -76,32 +63,37 @@ static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data,
 	kernel_fpu_begin();
 	if (len)
 		sha1_base_do_update(desc, data, len,
-				    (sha1_block_fn *)sha1_transform_asm);
-	sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_transform_asm);
+				    (sha1_block_fn *)sha1_xform);
+	sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_xform);
 	kernel_fpu_end();

 	return sha1_base_finish(desc, out);
 }

+asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
+				     unsigned int rounds);
+
+static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	return sha1_update(desc, data, len,
+			(sha1_transform_fn *) sha1_transform_ssse3);
+}
+
+static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return sha1_finup(desc, data, len, out,
+			(sha1_transform_fn *) sha1_transform_ssse3);
+}
+
 /* Add padding and return the message digest. */
 static int sha1_ssse3_final(struct shash_desc *desc, u8 *out)
 {
 	return sha1_ssse3_finup(desc, NULL, 0, out);
 }

-#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 = {
+static struct shash_alg sha1_ssse3_alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	sha1_ssse3_update,
@@ -110,7 +102,7 @@ static struct shash_alg alg = {
 	.descsize	=	sizeof(struct sha1_state),
 	.base		=	{
 		.cra_name	=	"sha1",
-		.cra_driver_name=	"sha1-ssse3",
+		.cra_driver_name =	"sha1-ssse3",
 		.cra_priority	=	150,
 		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
@@ -118,8 +110,60 @@ static struct shash_alg alg = {
 	}
 };

+static int register_sha1_ssse3(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SSSE3))
+		return crypto_register_shash(&sha1_ssse3_alg);
+	return 0;
+}
+
+static void unregister_sha1_ssse3(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SSSE3))
+		crypto_unregister_shash(&sha1_ssse3_alg);
+}
+
 #ifdef CONFIG_AS_AVX
-static bool __init avx_usable(void)
+asmlinkage void sha1_transform_avx(u32 *digest, const char *data,
+				   unsigned int rounds);
+
+static int sha1_avx_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	return sha1_update(desc, data, len,
+			(sha1_transform_fn *) sha1_transform_avx);
+}
+
+static int sha1_avx_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return sha1_finup(desc, data, len, out,
+			(sha1_transform_fn *) sha1_transform_avx);
+}
+
+static int sha1_avx_final(struct shash_desc *desc, u8 *out)
+{
+	return sha1_avx_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg sha1_avx_alg = {
+	.digestsize	=	SHA1_DIGEST_SIZE,
+	.init		=	sha1_base_init,
+	.update		=	sha1_avx_update,
+	.final		=	sha1_avx_final,
+	.finup		=	sha1_avx_finup,
+	.descsize	=	sizeof(struct sha1_state),
+	.base		=	{
+		.cra_name	=	"sha1",
+		.cra_driver_name =	"sha1-avx",
+		.cra_priority	=	160,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA1_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static bool avx_usable(void)
 {
 	if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
 		if (cpu_has_avx)
@@ -130,55 +174,197 @@ static bool __init avx_usable(void)
 	return true;
 }

-#ifdef CONFIG_AS_AVX2
-static bool __init avx2_usable(void)
+static int register_sha1_avx(void)
 {
-	if (avx_usable() && cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI1) &&
-	    boot_cpu_has(X86_FEATURE_BMI2))
+	if (avx_usable())
+		return crypto_register_shash(&sha1_avx_alg);
+	return 0;
+}
+
+static void unregister_sha1_avx(void)
+{
+	if (avx_usable())
+		crypto_unregister_shash(&sha1_avx_alg);
+}
+
+#else  /* CONFIG_AS_AVX */
+static inline int register_sha1_avx(void) { return 0; }
+static inline void unregister_sha1_avx(void) { }
+#endif /* CONFIG_AS_AVX */
+
+
+#if defined(CONFIG_AS_AVX2) && (CONFIG_AS_AVX)
+#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);
+
+static bool avx2_usable(void)
+{
+	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+		&& boot_cpu_has(X86_FEATURE_BMI1)
+		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;

 	return false;
 }
+
+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);
+}
+
+static int sha1_avx2_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	return sha1_update(desc, data, len,
+		(sha1_transform_fn *) sha1_apply_transform_avx2);
+}
+
+static int sha1_avx2_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return sha1_finup(desc, data, len, out,
+		(sha1_transform_fn *) sha1_apply_transform_avx2);
+}
+
+static int sha1_avx2_final(struct shash_desc *desc, u8 *out)
+{
+	return sha1_avx2_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg sha1_avx2_alg = {
+	.digestsize	=	SHA1_DIGEST_SIZE,
+	.init		=	sha1_base_init,
+	.update		=	sha1_avx2_update,
+	.final		=	sha1_avx2_final,
+	.finup		=	sha1_avx2_finup,
+	.descsize	=	sizeof(struct sha1_state),
+	.base		=	{
+		.cra_name	=	"sha1",
+		.cra_driver_name =	"sha1-avx2",
+		.cra_priority	=	170,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA1_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static int register_sha1_avx2(void)
+{
+	if (avx2_usable())
+		return crypto_register_shash(&sha1_avx2_alg);
+	return 0;
+}
+
+static void unregister_sha1_avx2(void)
+{
+	if (avx2_usable())
+		crypto_unregister_shash(&sha1_avx2_alg);
+}
+
+#else
+static inline int register_sha1_avx2(void) { return 0; }
+static inline void unregister_sha1_avx2(void) { }
 #endif
+
+#ifdef CONFIG_AS_SHA1_NI
+asmlinkage void sha1_ni_transform(u32 *digest, const char *data,
+				   unsigned int rounds);
+
+static int sha1_ni_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	return sha1_update(desc, data, len,
+		(sha1_transform_fn *) sha1_ni_transform);
+}
+
+static int sha1_ni_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return sha1_finup(desc, data, len, out,
+		(sha1_transform_fn *) sha1_ni_transform);
+}
+
+static int sha1_ni_final(struct shash_desc *desc, u8 *out)
+{
+	return sha1_ni_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg sha1_ni_alg = {
+	.digestsize	=	SHA1_DIGEST_SIZE,
+	.init		=	sha1_base_init,
+	.update		=	sha1_ni_update,
+	.final		=	sha1_ni_final,
+	.finup		=	sha1_ni_finup,
+	.descsize	=	sizeof(struct sha1_state),
+	.base		=	{
+		.cra_name	=	"sha1",
+		.cra_driver_name =	"sha1-ni",
+		.cra_priority	=	250,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA1_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static int register_sha1_ni(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SHA_NI))
+		return crypto_register_shash(&sha1_ni_alg);
+	return 0;
+}
+
+static void unregister_sha1_ni(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SHA_NI))
+		crypto_unregister_shash(&sha1_ni_alg);
+}
+
+#else
+static inline int register_sha1_ni(void) { return 0; }
+static inline void unregister_sha1_ni(void) { }
 #endif

 static int __init sha1_ssse3_mod_init(void)
 {
-	char *algo_name;
+	if (register_sha1_ssse3())
+		goto fail;

-	/* test for SSSE3 first */
-	if (cpu_has_ssse3) {
-		sha1_transform_asm = sha1_transform_ssse3;
-		algo_name = "SSSE3";
+	if (register_sha1_avx()) {
+		unregister_sha1_ssse3();
+		goto fail;
 	}

-#ifdef CONFIG_AS_AVX
-	/* allow AVX to override SSSE3, it's a little faster */
-	if (avx_usable()) {
-		sha1_transform_asm = sha1_transform_avx;
-		algo_name = "AVX";
-#ifdef CONFIG_AS_AVX2
-		/* allow AVX2 to override AVX, it's a little faster */
-		if (avx2_usable()) {
-			sha1_transform_asm = sha1_apply_transform_avx2;
-			algo_name = "AVX2";
-		}
-#endif
+	if (register_sha1_avx2()) {
+		unregister_sha1_avx();
+		unregister_sha1_ssse3();
+		goto fail;
 	}
-#endif

-	if (sha1_transform_asm) {
-		pr_info("Using %s optimized SHA-1 implementation\n", algo_name);
-		return crypto_register_shash(&alg);
+	if (register_sha1_ni()) {
+		unregister_sha1_avx2();
+		unregister_sha1_avx();
+		unregister_sha1_ssse3();
+		goto fail;
 	}
-	pr_info("Neither AVX nor AVX2 nor SSSE3 is available/usable.\n");

+	return 0;
+fail:
 	return -ENODEV;
 }

 static void __exit sha1_ssse3_mod_fini(void)
 {
-	crypto_unregister_shash(&alg);
+	unregister_sha1_ni();
+	unregister_sha1_avx2();
+	unregister_sha1_avx();
+	unregister_sha1_ssse3();
 }

 module_init(sha1_ssse3_mod_init);