crypto: crc32 - add crc32 pclmulqdq implementation and wrappers for table implementation

This patch adds crc32 algorithms to shash crypto api. One is wrapper to
gerneric crc32_le function. Second is crc32 pclmulqdq implementation. It
use hardware provided PCLMULQDQ instruction to accelerate the CRC32 disposal.
This instruction present from Intel Westmere and AMD Bulldozer CPUs.

For intel core i5 I got 450MB/s for table implementation and 2100MB/s
for pclmulqdq implementation.

Signed-off-by: Alexander Boyko <alexander_boyko@xyratex.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

3 files changed, 180 insertions, 0 deletions

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 4641d95651d3..e8b51e068179 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -355,6 +355,27 @@ config CRYPTO_CRC32C_SPARC64
           CRC32c CRC algorithm implemented using sparc64 crypto instructions,
           when available.
 
+config CRYPTO_CRC32
+        tristate "CRC32 CRC algorithm"
+        select CRYPTO_HASH
+        select CRC32
+        help
+          CRC-32-IEEE 802.3 cyclic redundancy-check algorithm.
+          Shash crypto api wrappers to crc32_le function.
+
+config CRYPTO_CRC32_PCLMUL
+        tristate "CRC32 PCLMULQDQ hardware acceleration"
+        depends on X86
+        select CRYPTO_HASH
+        select CRC32
+        help
+          From Intel Westmere and AMD Bulldozer processor with SSE4.2
+          and PCLMULQDQ supported, the processor will support
+          CRC32 PCLMULQDQ implementation using hardware accelerated PCLMULQDQ
+          instruction. This option will create 'crc32-plcmul' module,
+          which will enable any routine to use the CRC-32-IEEE 802.3 checksum
+          and gain better performance as compared with the table implementation.
+
 config CRYPTO_GHASH
         tristate "GHASH digest algorithm"
         select CRYPTO_GF128MUL
diff --git a/crypto/Makefile b/crypto/Makefile
index d59dec749804..be1a1bebbb86 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -81,6 +81,7 @@ obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
 obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
 obj-$(CONFIG_CRYPTO_CRC32C) += crc32c.o
+obj-$(CONFIG_CRYPTO_CRC32) += crc32.o
 obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
 obj-$(CONFIG_CRYPTO_LZO) += lzo.o
 obj-$(CONFIG_CRYPTO_842) += 842.o
diff --git a/crypto/crc32.c b/crypto/crc32.c
new file mode 100644
index 000000000000..9d1c41569898
--- /dev/null
+++ b/crypto/crc32.c
@@ -0,0 +1,158 @@
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please  visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ */
+
+/*
+ * This is crypto api shash wrappers to crc32_le.
+ */
+
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+
+#define CHKSUM_BLOCK_SIZE       1
+#define CHKSUM_DIGEST_SIZE      4
+
+static u32 __crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_le(crc, p, len);
+}
+
+/** No default init with ~0 */
+static int crc32_cra_init(struct crypto_tfm *tfm)
+{
+        u32 *key = crypto_tfm_ctx(tfm);
+
+        *key = 0;
+
+        return 0;
+}
+
+
+/*
+ * Setting the seed allows arbitrary accumulators and flexible XOR policy
+ * If your algorithm starts with ~0, then XOR with ~0 before you set
+ * the seed.
+ */
+static int crc32_setkey(struct crypto_shash *hash, const u8 *key,
+                        unsigned int keylen)
+{
+        u32 *mctx = crypto_shash_ctx(hash);
+
+        if (keylen != sizeof(u32)) {
+                crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+                return -EINVAL;
+        }
+        *mctx = le32_to_cpup((__le32 *)key);
+        return 0;
+}
+
+static int crc32_init(struct shash_desc *desc)
+{
+        u32 *mctx = crypto_shash_ctx(desc->tfm);
+        u32 *crcp = shash_desc_ctx(desc);
+
+        *crcp = *mctx;
+
+        return 0;
+}
+
+static int crc32_update(struct shash_desc *desc, const u8 *data,
+                        unsigned int len)
+{
+        u32 *crcp = shash_desc_ctx(desc);
+
+        *crcp = __crc32_le(*crcp, data, len);
+        return 0;
+}
+
+/* No final XOR 0xFFFFFFFF, like crc32_le */
+static int __crc32_finup(u32 *crcp, const u8 *data, unsigned int len,
+                         u8 *out)
+{
+        *(__le32 *)out = cpu_to_le32(__crc32_le(*crcp, data, len));
+        return 0;
+}
+
+static int crc32_finup(struct shash_desc *desc, const u8 *data,
+                       unsigned int len, u8 *out)
+{
+        return __crc32_finup(shash_desc_ctx(desc), data, len, out);
+}
+
+static int crc32_final(struct shash_desc *desc, u8 *out)
+{
+        u32 *crcp = shash_desc_ctx(desc);
+
+        *(__le32 *)out = cpu_to_le32p(crcp);
+        return 0;
+}
+
+static int crc32_digest(struct shash_desc *desc, const u8 *data,
+                        unsigned int len, u8 *out)
+{
+        return __crc32_finup(crypto_shash_ctx(desc->tfm), data, len,
+                             out);
+}
+static struct shash_alg alg = {
+        .setkey         = crc32_setkey,
+        .init           = crc32_init,
+        .update         = crc32_update,
+        .final          = crc32_final,
+        .finup          = crc32_finup,
+        .digest         = crc32_digest,
+        .descsize       = sizeof(u32),
+        .digestsize     = CHKSUM_DIGEST_SIZE,
+        .base           = {
+                .cra_name               = "crc32",
+                .cra_driver_name        = "crc32-table",
+                .cra_priority           = 100,
+                .cra_blocksize          = CHKSUM_BLOCK_SIZE,
+                .cra_ctxsize            = sizeof(u32),
+                .cra_module             = THIS_MODULE,
+                .cra_init               = crc32_cra_init,
+        }
+};
+
+static int __init crc32_mod_init(void)
+{
+        return crypto_register_shash(&alg);
+}
+
+static void __exit crc32_mod_fini(void)
+{
+        crypto_unregister_shash(&alg);
+}
+
+module_init(crc32_mod_init);
+module_exit(crc32_mod_fini);
+
+MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
+MODULE_DESCRIPTION("CRC32 calculations wrapper for lib/crc32");
+MODULE_LICENSE("GPL");