@@ -131,15 +131,18 @@ CPU_LE( rev32 v11.16b, v11.16b )
/*
* Final block: add padding and total bit count.
- * Skip if we have no total byte count in x4. In that case, the input
- * size was not a round multiple of the block size, and the padding is
- * handled by the C code.
+ * Skip if the input size was not a round multiple of the block size,
+ * the padding is handled by the C code in that case.
*/
cbz x4, 3f
+ ldr x5, [x2, #-8] // sha1_state::count
+ tst x5, #0x3f // round multiple of block size?
+ b.ne 3f
+ str wzr, [x4]
movi v9.2d, #0
mov x8, #0x80000000
movi v10.2d, #0
- ror x7, x4, #29 // ror(lsl(x4, 3), 32)
+ ror x7, x5, #29 // ror(lsl(x4, 3), 32)
fmov d8, x8
mov x4, #0
mov v11.d[0], xzr
@@ -12,6 +12,7 @@
#include <asm/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/sha.h>
+#include <crypto/sha1_base.h>
#include <linux/cpufeature.h>
#include <linux/crypto.h>
#include <linux/module.h>
@@ -21,132 +22,46 @@ MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
- u8 *head, long bytes);
+ const u8 *head, void *p);
-static int sha1_init(struct shash_desc *desc)
+static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
{
- struct sha1_state *sctx = shash_desc_ctx(desc);
-
- *sctx = (struct sha1_state){
- .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
- };
- return 0;
-}
-
-static int sha1_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- struct sha1_state *sctx = shash_desc_ctx(desc);
- unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
-
- sctx->count += len;
-
- if ((partial + len) >= SHA1_BLOCK_SIZE) {
- int blocks;
-
- if (partial) {
- int p = SHA1_BLOCK_SIZE - partial;
-
- memcpy(sctx->buffer + partial, data, p);
- data += p;
- len -= p;
- }
-
- blocks = len / SHA1_BLOCK_SIZE;
- len %= SHA1_BLOCK_SIZE;
-
- kernel_neon_begin_partial(16);
- sha1_ce_transform(blocks, data, sctx->state,
- partial ? sctx->buffer : NULL, 0);
- kernel_neon_end();
-
- data += blocks * SHA1_BLOCK_SIZE;
- partial = 0;
- }
- if (len)
- memcpy(sctx->buffer + partial, data, len);
- return 0;
-}
-
-static int sha1_final(struct shash_desc *desc, u8 *out)
-{
- static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
-
- struct sha1_state *sctx = shash_desc_ctx(desc);
- __be64 bits = cpu_to_be64(sctx->count << 3);
- __be32 *dst = (__be32 *)out;
- int i;
-
- u32 padlen = SHA1_BLOCK_SIZE
- - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
-
- sha1_update(desc, padding, padlen);
- sha1_update(desc, (const u8 *)&bits, sizeof(bits));
-
- for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
- put_unaligned_be32(sctx->state[i], dst++);
+ kernel_neon_begin_partial(16);
+ sha1_base_do_update(desc, data, len, sha1_ce_transform, NULL);
+ kernel_neon_end();
- *sctx = (struct sha1_state){};
return 0;
}
-static int sha1_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
+static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
{
- struct sha1_state *sctx = shash_desc_ctx(desc);
- __be32 *dst = (__be32 *)out;
- int blocks;
- int i;
-
- if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) {
- sha1_update(desc, data, len);
- return sha1_final(desc, out);
- }
-
- /*
- * Use a fast path if the input is a multiple of 64 bytes. In
- * this case, there is no need to copy data around, and we can
- * perform the entire digest calculation in a single invocation
- * of sha1_ce_transform()
- */
- blocks = len / SHA1_BLOCK_SIZE;
+ u32 finalize = 1;
kernel_neon_begin_partial(16);
- sha1_ce_transform(blocks, data, sctx->state, NULL, len);
+ if (len)
+ sha1_base_do_update(desc, data, len, sha1_ce_transform,
+ &finalize);
+ if (finalize)
+ sha1_base_do_finalize(desc, sha1_ce_transform, NULL);
kernel_neon_end();
- for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
- put_unaligned_be32(sctx->state[i], dst++);
-
- *sctx = (struct sha1_state){};
- return 0;
+ return sha1_base_finish(desc, out);
}
-static int sha1_export(struct shash_desc *desc, void *out)
+static int sha1_ce_final(struct shash_desc *desc, u8 *out)
{
- struct sha1_state *sctx = shash_desc_ctx(desc);
- struct sha1_state *dst = out;
-
- *dst = *sctx;
- return 0;
-}
-
-static int sha1_import(struct shash_desc *desc, const void *in)
-{
- struct sha1_state *sctx = shash_desc_ctx(desc);
- struct sha1_state const *src = in;
-
- *sctx = *src;
- return 0;
+ return sha1_ce_finup(desc, NULL, 0, out);
}
static struct shash_alg alg = {
- .init = sha1_init,
- .update = sha1_update,
- .final = sha1_final,
- .finup = sha1_finup,
- .export = sha1_export,
- .import = sha1_import,
+ .init = sha1_base_init,
+ .update = sha1_ce_update,
+ .final = sha1_ce_final,
+ .finup = sha1_ce_finup,
+ .export = sha1_base_export,
+ .import = sha1_base_import,
.descsize = sizeof(struct sha1_state),
.digestsize = SHA1_DIGEST_SIZE,
.statesize = sizeof(struct sha1_state),
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm64/crypto/sha1-ce-core.S | 11 ++-- arch/arm64/crypto/sha1-ce-glue.c | 133 +++++++-------------------------------- 2 files changed, 31 insertions(+), 113 deletions(-)