poly1305_block_sse2(a, m, b, 1);
}
+static unsigned int poly1305_scalar_blocks(struct poly1305_desc_ctx *dctx,
+ const u8 *src, unsigned int srclen)
+{
+ unsigned int datalen;
+
+ if (unlikely(!dctx->sset)) {
+ datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
+ src += srclen - datalen;
+ srclen = datalen;
+ }
+ if (srclen >= POLY1305_BLOCK_SIZE) {
+ poly1305_core_blocks(&dctx->h, dctx->r, src,
+ srclen / POLY1305_BLOCK_SIZE, 1);
+ srclen %= POLY1305_BLOCK_SIZE;
+ }
+ return srclen;
+}
+
static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
const u8 *src, unsigned int srclen)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
unsigned int bytes;
- /* kernel_fpu_begin/end is costly, use fallback for small updates */
- if (srclen <= 288 || !crypto_simd_usable())
- return crypto_poly1305_update(desc, src, srclen);
-
- kernel_fpu_begin();
-
if (unlikely(dctx->buflen)) {
bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
memcpy(dctx->buf + dctx->buflen, src, bytes);
dctx->buflen += bytes;
if (dctx->buflen == POLY1305_BLOCK_SIZE) {
- poly1305_simd_blocks(dctx, dctx->buf,
- POLY1305_BLOCK_SIZE);
+ if (likely(crypto_simd_usable())) {
+ kernel_fpu_begin();
+ poly1305_simd_blocks(dctx, dctx->buf,
+ POLY1305_BLOCK_SIZE);
+ kernel_fpu_end();
+ } else {
+ poly1305_scalar_blocks(dctx, dctx->buf,
+ POLY1305_BLOCK_SIZE);
+ }
dctx->buflen = 0;
}
}
if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
- bytes = poly1305_simd_blocks(dctx, src, srclen);
+ if (likely(crypto_simd_usable())) {
+ kernel_fpu_begin();
+ bytes = poly1305_simd_blocks(dctx, src, srclen);
+ kernel_fpu_end();
+ } else {
+ bytes = poly1305_scalar_blocks(dctx, src, srclen);
+ }
src += srclen - bytes;
srclen = bytes;
}
- kernel_fpu_end();
-
if (unlikely(srclen)) {
dctx->buflen = srclen;
memcpy(dctx->buf, src, srclen);
}
+}
+
+static int crypto_poly1305_init(struct shash_desc *desc)
+{
+ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+ poly1305_core_init(&dctx->h);
+ dctx->buflen = 0;
+ dctx->rset = 0;
+ dctx->sset = false;
+
+ return 0;
+}
+
+static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+ if (unlikely(!dctx->sset))
+ return -ENOKEY;
+ poly1305_final_generic(dctx, dst);
return 0;
}
#include <linux/module.h>
#include <asm/unaligned.h>
-int crypto_poly1305_init(struct shash_desc *desc)
+static int crypto_poly1305_init(struct shash_desc *desc)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
return 0;
}
-EXPORT_SYMBOL_GPL(crypto_poly1305_init);
static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
unsigned int srclen)
srclen / POLY1305_BLOCK_SIZE, 1);
}
-int crypto_poly1305_update(struct shash_desc *desc,
- const u8 *src, unsigned int srclen)
+static int crypto_poly1305_update(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
unsigned int bytes;
return 0;
}
-EXPORT_SYMBOL_GPL(crypto_poly1305_update);
-int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
+static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
poly1305_final_generic(dctx, dst);
return 0;
}
-EXPORT_SYMBOL_GPL(crypto_poly1305_final);
static struct shash_alg poly1305_alg = {
.digestsize = POLY1305_DIGEST_SIZE,
#include <linux/types.h>
#include <crypto/poly1305.h>
-struct shash_desc;
-
/*
* Poly1305 core functions. These implement the ε-almost-∆-universal hash
* function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce
unsigned int nblocks, u32 hibit);
void poly1305_core_emit(const struct poly1305_state *state, void *dst);
-/* Crypto API helper functions for the Poly1305 MAC */
-int crypto_poly1305_init(struct shash_desc *desc);
-
-int crypto_poly1305_update(struct shash_desc *desc,
- const u8 *src, unsigned int srclen);
-int crypto_poly1305_final(struct shash_desc *desc, u8 *dst);
-
/*
* Poly1305 requires a unique key for each tag, which implies that we can't set
* it on the tfm that gets accessed by multiple users simultaneously. Instead we