@@ -123,37 +123,38 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
}
}
-static int chacha_simd_stream_xor(struct skcipher_walk *walk,
+static int chacha_simd_stream_xor(struct skcipher_request *req,
const struct chacha_ctx *ctx, const u8 *iv)
{
u32 *state, state_buf[16 + 2] __aligned(8);
- int next_yield = 4096; /* bytes until next FPU yield */
- int err = 0;
+ struct skcipher_walk walk;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
- crypto_chacha_init(state, ctx, iv);
+ chacha_init_generic(state, ctx->key, iv);
- while (walk->nbytes > 0) {
- unsigned int nbytes = walk->nbytes;
+ while (walk.nbytes > 0) {
+ unsigned int nbytes = walk.nbytes;
- if (nbytes < walk->total) {
- nbytes = round_down(nbytes, walk->stride);
- next_yield -= nbytes;
- }
+ if (nbytes < walk.total)
+ nbytes = round_down(nbytes, walk.stride);
- chacha_dosimd(state, walk->dst.virt.addr, walk->src.virt.addr,
- nbytes, ctx->nrounds);
-
- if (next_yield <= 0) {
- /* temporarily allow preemption */
- kernel_fpu_end();
+ if (!crypto_simd_usable()) {
+ chacha_crypt_generic(state, walk.dst.virt.addr,
+ walk.src.virt.addr, nbytes,
+ ctx->nrounds);
+ } else {
kernel_fpu_begin();
- next_yield = 4096;
+ chacha_dosimd(state, walk.dst.virt.addr,
+ walk.src.virt.addr, nbytes,
+ ctx->nrounds);
+ kernel_fpu_end();
}
-
- err = skcipher_walk_done(walk, walk->nbytes - nbytes);
+ err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
}
return err;
@@ -163,55 +164,46 @@ static int chacha_simd(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
- struct skcipher_walk walk;
- int err;
-
- if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
- return crypto_chacha_crypt(req);
- err = skcipher_walk_virt(&walk, req, true);
- if (err)
- return err;
-
- kernel_fpu_begin();
- err = chacha_simd_stream_xor(&walk, ctx, req->iv);
- kernel_fpu_end();
- return err;
+ return chacha_simd_stream_xor(req, ctx, req->iv);
}
static int xchacha_simd(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
- struct skcipher_walk walk;
- struct chacha_ctx subctx;
u32 *state, state_buf[16 + 2] __aligned(8);
+ struct chacha_ctx subctx;
u8 real_iv[16];
- int err;
-
- if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
- return crypto_xchacha_crypt(req);
-
- err = skcipher_walk_virt(&walk, req, true);
- if (err)
- return err;
BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
- crypto_chacha_init(state, ctx, req->iv);
-
- kernel_fpu_begin();
-
- hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+ chacha_init_generic(state, ctx->key, req->iv);
+
+ if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
+ kernel_fpu_begin();
+ hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+ kernel_fpu_end();
+ } else {
+ hchacha_block_generic(state, subctx.key, ctx->nrounds);
+ }
subctx.nrounds = ctx->nrounds;
memcpy(&real_iv[0], req->iv + 24, 8);
memcpy(&real_iv[8], req->iv + 16, 8);
- err = chacha_simd_stream_xor(&walk, &subctx, real_iv);
+ return chacha_simd_stream_xor(req, &subctx, real_iv);
+}
- kernel_fpu_end();
+static int chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int keysize)
+{
+ return chacha_setkey(tfm, key, keysize, 20);
+}
- return err;
+static int chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int keysize)
+{
+ return chacha_setkey(tfm, key, keysize, 12);
}
static struct skcipher_alg algs[] = {
@@ -227,7 +219,7 @@ static struct skcipher_alg algs[] = {
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = CHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
- .setkey = crypto_chacha20_setkey,
+ .setkey = chacha20_setkey,
.encrypt = chacha_simd,
.decrypt = chacha_simd,
}, {
@@ -242,7 +234,7 @@ static struct skcipher_alg algs[] = {
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = XCHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
- .setkey = crypto_chacha20_setkey,
+ .setkey = chacha20_setkey,
.encrypt = xchacha_simd,
.decrypt = xchacha_simd,
}, {
@@ -257,7 +249,7 @@ static struct skcipher_alg algs[] = {
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = XCHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
- .setkey = crypto_chacha12_setkey,
+ .setkey = chacha12_setkey,
.encrypt = xchacha_simd,
.decrypt = xchacha_simd,
},
@@ -1417,7 +1417,7 @@ config CRYPTO_CHACHA20_X86_64
tristate "ChaCha stream cipher algorithms (x86_64/SSSE3/AVX2/AVX-512VL)"
depends on X86 && 64BIT
select CRYPTO_BLKCIPHER
- select CRYPTO_CHACHA20
+ select CRYPTO_LIB_CHACHA_GENERIC
help
SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20,
XChaCha20, and XChaCha12 stream ciphers.
In preparation of extending the x86 ChaCha driver to also expose the ChaCha library interface, drop the dependency on the chacha_generic crypto driver as a non-SIMD fallback, and depend on the generic ChaCha library directly. This way, we only pull in the code we actually need, without registering a set of ChaCha skciphers that we will never use. Since turning the FPU on and off is cheap these days, simplify the SIMD routine by dropping the per-page yield, which makes for a cleaner switch to the library API as well. This also allows use to invoke the skcipher walk routines in non-atomic mode. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/x86/crypto/chacha_glue.c | 98 +++++++++----------- crypto/Kconfig | 2 +- 2 files changed, 46 insertions(+), 54 deletions(-) -- 2.20.1