summaryrefslogtreecommitdiffstats
path: root/arch/arm64/crypto/aes-neonbs-glue.c
diff options
context:
space:
mode:
authorArd Biesheuvel <ardb@kernel.org>2022-01-27 12:35:44 +0100
committerHerbert Xu <herbert@gondor.apana.org.au>2022-02-05 15:10:51 +1100
commitfc074e130051015e39245a4241956ff122e2f465 (patch)
treebd626b745bb39ebd97f5b932ff4f4a2948111b1c /arch/arm64/crypto/aes-neonbs-glue.c
parentc8bf850e991a1838964ed8d8426f96cf8d3fbab5 (diff)
downloadlinux-fc074e130051015e39245a4241956ff122e2f465.tar.bz2
crypto: arm64/aes-neonbs-ctr - fallback to plain NEON for final chunk
Instead of processing the entire input with the 8-way bit sliced algorithm, which is sub-optimal for inputs that are not a multiple of 128 bytes in size, invoke the plain NEON version of CTR for the remainder of the input after processing the bulk using 128 byte strides. This allows us to greatly simplify the asm code that implements CTR, and get rid of all the branches and special code paths. It also gains us a couple of percent of performance. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/arm64/crypto/aes-neonbs-glue.c')
-rw-r--r--arch/arm64/crypto/aes-neonbs-glue.c64
1 files changed, 29 insertions, 35 deletions
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index 8df6ad8cb09d..3189003e1cbe 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -34,7 +34,7 @@ asmlinkage void aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
int rounds, int blocks, u8 iv[]);
asmlinkage void aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
- int rounds, int blocks, u8 iv[], u8 final[]);
+ int rounds, int blocks, u8 iv[]);
asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
int rounds, int blocks, u8 iv[]);
@@ -46,6 +46,8 @@ asmlinkage void neon_aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[],
int rounds, int blocks);
asmlinkage void neon_aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[],
int rounds, int blocks, u8 iv[]);
+asmlinkage void neon_aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int bytes, u8 ctr[]);
asmlinkage void neon_aes_xts_encrypt(u8 out[], u8 const in[],
u32 const rk1[], int rounds, int bytes,
u32 const rk2[], u8 iv[], int first);
@@ -58,7 +60,7 @@ struct aesbs_ctx {
int rounds;
} __aligned(AES_BLOCK_SIZE);
-struct aesbs_cbc_ctx {
+struct aesbs_cbc_ctr_ctx {
struct aesbs_ctx key;
u32 enc[AES_MAX_KEYLENGTH_U32];
};
@@ -128,10 +130,10 @@ static int ecb_decrypt(struct skcipher_request *req)
return __ecb_crypt(req, aesbs_ecb_decrypt);
}
-static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+static int aesbs_cbc_ctr_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
unsigned int key_len)
{
- struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
struct crypto_aes_ctx rk;
int err;
@@ -154,7 +156,7 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
static int cbc_encrypt(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
struct skcipher_walk walk;
int err;
@@ -177,7 +179,7 @@ static int cbc_encrypt(struct skcipher_request *req)
static int cbc_decrypt(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
struct skcipher_walk walk;
int err;
@@ -205,40 +207,32 @@ static int cbc_decrypt(struct skcipher_request *req)
static int ctr_encrypt(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
struct skcipher_walk walk;
- u8 buf[AES_BLOCK_SIZE];
int err;
err = skcipher_walk_virt(&walk, req, false);
while (walk.nbytes > 0) {
- unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
- u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
-
- if (walk.nbytes < walk.total) {
- blocks = round_down(blocks,
- walk.stride / AES_BLOCK_SIZE);
- final = NULL;
- }
+ int blocks = (walk.nbytes / AES_BLOCK_SIZE) & ~7;
+ int nbytes = walk.nbytes % (8 * AES_BLOCK_SIZE);
+ const u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
kernel_neon_begin();
- aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
- ctx->rk, ctx->rounds, blocks, walk.iv, final);
- kernel_neon_end();
-
- if (final) {
- u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
- u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
-
- crypto_xor_cpy(dst, src, final,
- walk.total % AES_BLOCK_SIZE);
-
- err = skcipher_walk_done(&walk, 0);
- break;
+ if (blocks >= 8) {
+ aesbs_ctr_encrypt(dst, src, ctx->key.rk, ctx->key.rounds,
+ blocks, walk.iv);
+ dst += blocks * AES_BLOCK_SIZE;
+ src += blocks * AES_BLOCK_SIZE;
}
- err = skcipher_walk_done(&walk,
- walk.nbytes - blocks * AES_BLOCK_SIZE);
+ if (nbytes && walk.nbytes == walk.total) {
+ neon_aes_ctr_encrypt(dst, src, ctx->enc, ctx->key.rounds,
+ nbytes, walk.iv);
+ nbytes = 0;
+ }
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk, nbytes);
}
return err;
}
@@ -402,14 +396,14 @@ static struct skcipher_alg aes_algs[] = { {
.base.cra_driver_name = "cbc-aes-neonbs",
.base.cra_priority = 250,
.base.cra_blocksize = AES_BLOCK_SIZE,
- .base.cra_ctxsize = sizeof(struct aesbs_cbc_ctx),
+ .base.cra_ctxsize = sizeof(struct aesbs_cbc_ctr_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = AES_MIN_KEY_SIZE,
.max_keysize = AES_MAX_KEY_SIZE,
.walksize = 8 * AES_BLOCK_SIZE,
.ivsize = AES_BLOCK_SIZE,
- .setkey = aesbs_cbc_setkey,
+ .setkey = aesbs_cbc_ctr_setkey,
.encrypt = cbc_encrypt,
.decrypt = cbc_decrypt,
}, {
@@ -417,7 +411,7 @@ static struct skcipher_alg aes_algs[] = { {
.base.cra_driver_name = "ctr-aes-neonbs",
.base.cra_priority = 250,
.base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct aesbs_ctx),
+ .base.cra_ctxsize = sizeof(struct aesbs_cbc_ctr_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = AES_MIN_KEY_SIZE,
@@ -425,7 +419,7 @@ static struct skcipher_alg aes_algs[] = { {
.chunksize = AES_BLOCK_SIZE,
.walksize = 8 * AES_BLOCK_SIZE,
.ivsize = AES_BLOCK_SIZE,
- .setkey = aesbs_setkey,
+ .setkey = aesbs_cbc_ctr_setkey,
.encrypt = ctr_encrypt,
.decrypt = ctr_encrypt,
}, {