1 files changed, 72 insertions, 245 deletions

diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 6759dd1135be..aea5d4d06be7 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -1,48 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Accelerated GHASH implementation with Intel PCLMULQDQ-NI
  * instructions. This file contains glue code.
  *
  * Copyright (c) 2009 Intel Corp.
  *   Author: Huang Ying <ying.huang@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/crypto.h>
-#include <crypto/algapi.h>
-#include <crypto/cryptd.h>
-#include <crypto/gf128mul.h>
-#include <crypto/internal/hash.h>
-#include <asm/i387.h>
 #include <asm/cpu_device_id.h>
+#include <asm/simd.h>
+#include <crypto/b128ops.h>
+#include <crypto/ghash.h>
+#include <crypto/internal/hash.h>
+#include <crypto/utils.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
 
-#define GHASH_BLOCK_SIZE	16
-#define GHASH_DIGEST_SIZE	16
-
-void clmul_ghash_mul(char *dst, const be128 *shash);
-
-void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
-			const be128 *shash);
-
-void clmul_ghash_setkey(be128 *shash, const u8 *key);
-
-struct ghash_async_ctx {
-	struct cryptd_ahash *cryptd_tfm;
-};
+asmlinkage void clmul_ghash_mul(char *dst, const le128 *shash);
 
-struct ghash_ctx {
-	be128 shash;
-};
+asmlinkage int clmul_ghash_update(char *dst, const char *src,
+				  unsigned int srclen, const le128 *shash);
 
-struct ghash_desc_ctx {
-	u8 buffer[GHASH_BLOCK_SIZE];
-	u32 bytes;
+struct x86_ghash_ctx {
+	le128 shash;
 };
 
 static int ghash_init(struct shash_desc *desc)
@@ -57,79 +40,79 @@ static int ghash_init(struct shash_desc *desc)
 static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
-	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	struct x86_ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	u64 a, b;
 
-	if (keylen != GHASH_BLOCK_SIZE) {
-		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	if (keylen != GHASH_BLOCK_SIZE)
 		return -EINVAL;
-	}
-
-	clmul_ghash_setkey(&ctx->shash, key);
 
+	/*
+	 * GHASH maps bits to polynomial coefficients backwards, which makes it
+	 * hard to implement.  But it can be shown that the GHASH multiplication
+	 *
+	 *	D * K (mod x^128 + x^7 + x^2 + x + 1)
+	 *
+	 * (where D is a data block and K is the key) is equivalent to:
+	 *
+	 *	bitreflect(D) * bitreflect(K) * x^(-127)
+	 *		(mod x^128 + x^127 + x^126 + x^121 + 1)
+	 *
+	 * So, the code below precomputes:
+	 *
+	 *	bitreflect(K) * x^(-127) (mod x^128 + x^127 + x^126 + x^121 + 1)
+	 *
+	 * ... but in Montgomery form (so that Montgomery multiplication can be
+	 * used), i.e. with an extra x^128 factor, which means actually:
+	 *
+	 *	bitreflect(K) * x (mod x^128 + x^127 + x^126 + x^121 + 1)
+	 *
+	 * The within-a-byte part of bitreflect() cancels out GHASH's built-in
+	 * reflection, and thus bitreflect() is actually a byteswap.
+	 */
+	a = get_unaligned_be64(key);
+	b = get_unaligned_be64(key + 8);
+	ctx->shash.a = cpu_to_le64((a << 1) | (b >> 63));
+	ctx->shash.b = cpu_to_le64((b << 1) | (a >> 63));
+	if (a >> 63)
+		ctx->shash.a ^= cpu_to_le64((u64)0xc2 << 56);
 	return 0;
 }
 
 static int ghash_update(struct shash_desc *desc,
 			 const u8 *src, unsigned int srclen)
 {
+	struct x86_ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	u8 *dst = dctx->buffer;
+	int remain;
 
 	kernel_fpu_begin();
-	if (dctx->bytes) {
-		int n = min(srclen, dctx->bytes);
-		u8 *pos = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
-
-		dctx->bytes -= n;
-		srclen -= n;
-
-		while (n--)
-			*pos++ ^= *src++;
-
-		if (!dctx->bytes)
-			clmul_ghash_mul(dst, &ctx->shash);
-	}
-
-	clmul_ghash_update(dst, src, srclen, &ctx->shash);
+	remain = clmul_ghash_update(dst, src, srclen, &ctx->shash);
 	kernel_fpu_end();
-
-	if (srclen & 0xf) {
-		src += srclen - (srclen & 0xf);
-		srclen &= 0xf;
-		dctx->bytes = GHASH_BLOCK_SIZE - srclen;
-		while (srclen--)
-			*dst++ ^= *src++;
-	}
-
-	return 0;
+	return remain;
 }
 
-static void ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+static void ghash_flush(struct x86_ghash_ctx *ctx, struct ghash_desc_ctx *dctx,
+			const u8 *src, unsigned int len)
 {
 	u8 *dst = dctx->buffer;
 
-	if (dctx->bytes) {
-		u8 *tmp = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
-
-		while (dctx->bytes--)
-			*tmp++ ^= 0;
-
-		kernel_fpu_begin();
+	kernel_fpu_begin();
+	if (len) {
+		crypto_xor(dst, src, len);
 		clmul_ghash_mul(dst, &ctx->shash);
-		kernel_fpu_end();
 	}
-
-	dctx->bytes = 0;
+	kernel_fpu_end();
 }
 
-static int ghash_final(struct shash_desc *desc, u8 *dst)
+static int ghash_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *dst)
 {
+	struct x86_ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	u8 *buf = dctx->buffer;
 
-	ghash_flush(ctx, dctx);
+	ghash_flush(ctx, dctx, src, len);
 	memcpy(dst, buf, GHASH_BLOCK_SIZE);
 
 	return 0;
@@ -139,191 +122,36 @@ static struct shash_alg ghash_alg = {
 	.digestsize	= GHASH_DIGEST_SIZE,
 	.init		= ghash_init,
 	.update		= ghash_update,
-	.final		= ghash_final,
+	.finup		= ghash_finup,
 	.setkey		= ghash_setkey,
 	.descsize	= sizeof(struct ghash_desc_ctx),
 	.base		= {
-		.cra_name		= "__ghash",
-		.cra_driver_name	= "__ghash-pclmulqdqni",
-		.cra_priority		= 0,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_name		= "ghash",
+		.cra_driver_name	= "ghash-pclmulqdqni",
+		.cra_priority		= 400,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize		= GHASH_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct ghash_ctx),
+		.cra_ctxsize		= sizeof(struct x86_ghash_ctx),
 		.cra_module		= THIS_MODULE,
 	},
 };
 
-static int ghash_async_init(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-	if (!irq_fpu_usable()) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_init(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		desc->flags = req->base.flags;
-		return crypto_shash_init(desc);
-	}
-}
-
-static int ghash_async_update(struct ahash_request *req)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-
-	if (!irq_fpu_usable()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_update(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		return shash_ahash_update(req, desc);
-	}
-}
-
-static int ghash_async_final(struct ahash_request *req)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-
-	if (!irq_fpu_usable()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_final(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		return crypto_shash_final(desc, req->result);
-	}
-}
-
-static int ghash_async_digest(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-	if (!irq_fpu_usable()) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_digest(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		desc->flags = req->base.flags;
-		return shash_ahash_digest(req, desc);
-	}
-}
-
-static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
-			      unsigned int keylen)
-{
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct crypto_ahash *child = &ctx->cryptd_tfm->base;
-	int err;
-
-	crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm)
-			       & CRYPTO_TFM_REQ_MASK);
-	err = crypto_ahash_setkey(child, key, keylen);
-	crypto_ahash_set_flags(tfm, crypto_ahash_get_flags(child)
-			       & CRYPTO_TFM_RES_MASK);
-
-	return err;
-}
-
-static int ghash_async_init_tfm(struct crypto_tfm *tfm)
-{
-	struct cryptd_ahash *cryptd_tfm;
-	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_tfm = cryptd_alloc_ahash("__ghash-pclmulqdqni", 0, 0);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-	ctx->cryptd_tfm = cryptd_tfm;
-	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct ahash_request) +
-				 crypto_ahash_reqsize(&cryptd_tfm->base));
-
-	return 0;
-}
-
-static void ghash_async_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_free_ahash(ctx->cryptd_tfm);
-}
-
-static struct ahash_alg ghash_async_alg = {
-	.init		= ghash_async_init,
-	.update		= ghash_async_update,
-	.final		= ghash_async_final,
-	.setkey		= ghash_async_setkey,
-	.digest		= ghash_async_digest,
-	.halg = {
-		.digestsize	= GHASH_DIGEST_SIZE,
-		.base = {
-			.cra_name		= "ghash",
-			.cra_driver_name	= "ghash-clmulni",
-			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
-			.cra_blocksize		= GHASH_BLOCK_SIZE,
-			.cra_type		= &crypto_ahash_type,
-			.cra_module		= THIS_MODULE,
-			.cra_init		= ghash_async_init_tfm,
-			.cra_exit		= ghash_async_exit_tfm,
-		},
-	},
-};
-
 static const struct x86_cpu_id pcmul_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ), /* Pickle-Mickle-Duck */
+	X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), /* Pickle-Mickle-Duck */
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id);
 
 static int __init ghash_pclmulqdqni_mod_init(void)
 {
-	int err;
-
 	if (!x86_match_cpu(pcmul_cpu_id))
 		return -ENODEV;
 
-	err = crypto_register_shash(&ghash_alg);
-	if (err)
-		goto err_out;
-	err = crypto_register_ahash(&ghash_async_alg);
-	if (err)
-		goto err_shash;
-
-	return 0;
-
-err_shash:
-	crypto_unregister_shash(&ghash_alg);
-err_out:
-	return err;
+	return crypto_register_shash(&ghash_alg);
 }
 
 static void __exit ghash_pclmulqdqni_mod_exit(void)
 {
-	crypto_unregister_ahash(&ghash_async_alg);
 	crypto_unregister_shash(&ghash_alg);
 }
 
@@ -331,6 +159,5 @@ module_init(ghash_pclmulqdqni_mod_init);
 module_exit(ghash_pclmulqdqni_mod_exit);
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("GHASH Message Digest Algorithm, "
-		   "acclerated by PCLMULQDQ-NI");
-MODULE_ALIAS("ghash");
+MODULE_DESCRIPTION("GHASH hash function, accelerated by PCLMULQDQ-NI");
+MODULE_ALIAS_CRYPTO("ghash");