crypto: serpent-sse2 - split generic glue code to new helper module

Now that serpent-sse2 glue code has been made generic, it can be split to
separate module.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

5 files changed, 431 insertions, 351 deletions

diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index ad746916f912..e908e5de82d3 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -3,6 +3,7 @@
 #
 
 obj-$(CONFIG_CRYPTO_ABLK_HELPER_X86) += ablk_helper.o
+obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
 
 obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
 obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
new file mode 100644
index 000000000000..4854f0f31e4f
--- /dev/null
+++ b/arch/x86/crypto/glue_helper.c
@@ -0,0 +1,307 @@
+/*
+ * Shared glue code for 128bit block ciphers
+ *
+ * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
+ *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ * CTR part based on code (crypto/ctr.c) by:
+ *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.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 Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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 for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/module.h>
+#include <crypto/b128ops.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
+#include <asm/crypto/glue_helper.h>
+#include <crypto/scatterwalk.h>
+
+static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
+                                   struct blkcipher_desc *desc,
+                                   struct blkcipher_walk *walk)
+{
+        void *ctx = crypto_blkcipher_ctx(desc->tfm);
+        const unsigned int bsize = 128 / 8;
+        unsigned int nbytes, i, func_bytes;
+        bool fpu_enabled = false;
+        int err;
+
+        err = blkcipher_walk_virt(desc, walk);
+
+        while ((nbytes = walk->nbytes)) {
+                u8 *wsrc = walk->src.virt.addr;
+                u8 *wdst = walk->dst.virt.addr;
+
+                fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+                                             desc, fpu_enabled, nbytes);
+
+                for (i = 0; i < gctx->num_funcs; i++) {
+                        func_bytes = bsize * gctx->funcs[i].num_blocks;
+
+                        /* Process multi-block batch */
+                        if (nbytes >= func_bytes) {
+                                do {
+                                        gctx->funcs[i].fn_u.ecb(ctx, wdst,
+                                                                wsrc);
+
+                                        wsrc += func_bytes;
+                                        wdst += func_bytes;
+                                        nbytes -= func_bytes;
+                                } while (nbytes >= func_bytes);
+
+                                if (nbytes < bsize)
+                                        goto done;
+                        }
+                }
+
+done:
+                err = blkcipher_walk_done(desc, walk, nbytes);
+        }
+
+        glue_fpu_end(fpu_enabled);
+        return err;
+}
+
+int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
+                          struct blkcipher_desc *desc, struct scatterlist *dst,
+                          struct scatterlist *src, unsigned int nbytes)
+{
+        struct blkcipher_walk walk;
+
+        blkcipher_walk_init(&walk, dst, src, nbytes);
+        return __glue_ecb_crypt_128bit(gctx, desc, &walk);
+}
+EXPORT_SYMBOL_GPL(glue_ecb_crypt_128bit);
+
+static unsigned int __glue_cbc_encrypt_128bit(const common_glue_func_t fn,
+                                              struct blkcipher_desc *desc,
+                                              struct blkcipher_walk *walk)
+{
+        void *ctx = crypto_blkcipher_ctx(desc->tfm);
+        const unsigned int bsize = 128 / 8;
+        unsigned int nbytes = walk->nbytes;
+        u128 *src = (u128 *)walk->src.virt.addr;
+        u128 *dst = (u128 *)walk->dst.virt.addr;
+        u128 *iv = (u128 *)walk->iv;
+
+        do {
+                u128_xor(dst, src, iv);
+                fn(ctx, (u8 *)dst, (u8 *)dst);
+                iv = dst;
+
+                src += 1;
+                dst += 1;
+                nbytes -= bsize;
+        } while (nbytes >= bsize);
+
+        u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv);
+        return nbytes;
+}
+
+int glue_cbc_encrypt_128bit(const common_glue_func_t fn,
+                            struct blkcipher_desc *desc,
+                            struct scatterlist *dst,
+                            struct scatterlist *src, unsigned int nbytes)
+{
+        struct blkcipher_walk walk;
+        int err;
+
+        blkcipher_walk_init(&walk, dst, src, nbytes);
+        err = blkcipher_walk_virt(desc, &walk);
+
+        while ((nbytes = walk.nbytes)) {
+                nbytes = __glue_cbc_encrypt_128bit(fn, desc, &walk);
+                err = blkcipher_walk_done(desc, &walk, nbytes);
+        }
+
+        return err;
+}
+EXPORT_SYMBOL_GPL(glue_cbc_encrypt_128bit);
+
+static unsigned int
+__glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
+                          struct blkcipher_desc *desc,
+                          struct blkcipher_walk *walk)
+{
+        void *ctx = crypto_blkcipher_ctx(desc->tfm);
+        const unsigned int bsize = 128 / 8;
+        unsigned int nbytes = walk->nbytes;
+        u128 *src = (u128 *)walk->src.virt.addr;
+        u128 *dst = (u128 *)walk->dst.virt.addr;
+        u128 last_iv;
+        unsigned int num_blocks, func_bytes;
+        unsigned int i;
+
+        /* Start of the last block. */
+        src += nbytes / bsize - 1;
+        dst += nbytes / bsize - 1;
+
+        last_iv = *src;
+
+        for (i = 0; i < gctx->num_funcs; i++) {
+                num_blocks = gctx->funcs[i].num_blocks;
+                func_bytes = bsize * num_blocks;
+
+                /* Process multi-block batch */
+                if (nbytes >= func_bytes) {
+                        do {
+                                nbytes -= func_bytes - bsize;
+                                src -= num_blocks - 1;
+                                dst -= num_blocks - 1;
+
+                                gctx->funcs[i].fn_u.cbc(ctx, dst, src);
+
+                                nbytes -= bsize;
+                                if (nbytes < bsize)
+                                        goto done;
+
+                                u128_xor(dst, dst, src - 1);
+                                src -= 1;
+