@@ -99,9 +99,8 @@ static int __ecb_crypt(struct skcipher_request *req,
struct skcipher_walk walk;
int err;
- err = skcipher_walk_virt(&walk, req, true);
+ err = skcipher_walk_virt(&walk, req, false);
- kernel_neon_begin();
while (walk.nbytes >= AES_BLOCK_SIZE) {
unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -109,12 +108,13 @@ static int __ecb_crypt(struct skcipher_request *req,
blocks = round_down(blocks,
walk.stride / AES_BLOCK_SIZE);
+ kernel_neon_begin();
fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
ctx->rounds, blocks);
+ kernel_neon_end();
err = skcipher_walk_done(&walk,
walk.nbytes - blocks * AES_BLOCK_SIZE);
}
- kernel_neon_end();
return err;
}
@@ -158,19 +158,19 @@ static int cbc_encrypt(struct skcipher_request *req)
struct skcipher_walk walk;
int err;
- err = skcipher_walk_virt(&walk, req, true);
+ err = skcipher_walk_virt(&walk, req, false);
- kernel_neon_begin();
while (walk.nbytes >= AES_BLOCK_SIZE) {
unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
/* fall back to the non-bitsliced NEON implementation */
+ kernel_neon_begin();
neon_aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
ctx->enc, ctx->key.rounds, blocks,
walk.iv);
+ kernel_neon_end();
err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
- kernel_neon_end();
return err;
}
@@ -181,9 +181,8 @@ static int cbc_decrypt(struct skcipher_request *req)
struct skcipher_walk walk;
int err;
- err = skcipher_walk_virt(&walk, req, true);
+ err = skcipher_walk_virt(&walk, req, false);
- kernel_neon_begin();
while (walk.nbytes >= AES_BLOCK_SIZE) {
unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -191,13 +190,14 @@ static int cbc_decrypt(struct skcipher_request *req)
blocks = round_down(blocks,
walk.stride / AES_BLOCK_SIZE);
+ kernel_neon_begin();
aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
ctx->key.rk, ctx->key.rounds, blocks,
walk.iv);
+ kernel_neon_end();
err = skcipher_walk_done(&walk,
walk.nbytes - blocks * AES_BLOCK_SIZE);
}
- kernel_neon_end();
return err;
}
@@ -229,9 +229,8 @@ static int ctr_encrypt(struct skcipher_request *req)
u8 buf[AES_BLOCK_SIZE];
int err;
- err = skcipher_walk_virt(&walk, req, true);
+ err = skcipher_walk_virt(&walk, req, false);
- kernel_neon_begin();
while (walk.nbytes > 0) {
unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
@@ -242,8 +241,10 @@ static int ctr_encrypt(struct skcipher_request *req)
final = NULL;
}
+ 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;
@@ -258,8 +259,6 @@ static int ctr_encrypt(struct skcipher_request *req)
err = skcipher_walk_done(&walk,
walk.nbytes - blocks * AES_BLOCK_SIZE);
}
- kernel_neon_end();
-
return err;
}
@@ -304,12 +303,11 @@ static int __xts_crypt(struct skcipher_request *req,
struct skcipher_walk walk;
int err;
- err = skcipher_walk_virt(&walk, req, true);
+ err = skcipher_walk_virt(&walk, req, false);
kernel_neon_begin();
-
- neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey,
- ctx->key.rounds, 1);
+ neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, ctx->key.rounds, 1);
+ kernel_neon_end();
while (walk.nbytes >= AES_BLOCK_SIZE) {
unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -318,13 +316,13 @@ static int __xts_crypt(struct skcipher_request *req,
blocks = round_down(blocks,
walk.stride / AES_BLOCK_SIZE);
+ kernel_neon_begin();
fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk,
ctx->key.rounds, blocks, walk.iv);
+ kernel_neon_end();
err = skcipher_walk_done(&walk,
walk.nbytes - blocks * AES_BLOCK_SIZE);
}
- kernel_neon_end();
-
return err;
}
When kernel mode NEON was first introduced on arm64, the preserve and restore of the userland NEON state was completely unoptimized, and involved saving all registers on each call to kernel_neon_begin(), and restoring them on each call to kernel_neon_end(). For this reason, the NEON crypto code that was introduced at the time keeps the NEON enabled throughout the execution of the crypto API methods, which may include calls back into the crypto API that could result in memory allocation or other actions that we should avoid when running with preemption disabled. Since then, we have optimized the kernel mode NEON handling, which now restores lazily (upon return to userland), and so the preserve action is only costly the first time it is called after entering the kernel. So let's put the kernel_neon_begin() and kernel_neon_end() calls around the actual invocations of the NEON crypto code, and run the remainder of the code with kernel mode NEON disabled (and preemption enabled) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm64/crypto/aes-neonbs-glue.c | 36 +++++++++----------- 1 file changed, 17 insertions(+), 19 deletions(-)