summaryrefslogtreecommitdiffstats
path: root/arch/arm64/crypto
diff options
context:
space:
mode:
authorArd Biesheuvel <ard.biesheuvel@linaro.org>2018-03-10 15:21:50 +0000
committerHerbert Xu <herbert@gondor.apana.org.au>2018-03-16 23:35:55 +0800
commit4bf7e7a19df127391ddc5c47888bc62ef1bfd0ad (patch)
treea8d0702d69f509f967b4fdfd57f91cef9a0cfdde /arch/arm64/crypto
parent78ad7b08d8e096e5f00bc2cbeba9ef6d24be1bc4 (diff)
downloadlinux-4bf7e7a19df127391ddc5c47888bc62ef1bfd0ad.tar.bz2
crypto: arm64/chacha20 - move kernel mode neon en/disable into loop
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> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/arm64/crypto')
-rw-r--r--arch/arm64/crypto/chacha20-neon-glue.c12
1 files changed, 9 insertions, 3 deletions
diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c
index cbdb75d15cd0..727579c93ded 100644
--- a/arch/arm64/crypto/chacha20-neon-glue.c
+++ b/arch/arm64/crypto/chacha20-neon-glue.c
@@ -37,12 +37,19 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src,
u8 buf[CHACHA20_BLOCK_SIZE];
while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
+ kernel_neon_begin();
chacha20_4block_xor_neon(state, dst, src);
+ kernel_neon_end();
bytes -= CHACHA20_BLOCK_SIZE * 4;
src += CHACHA20_BLOCK_SIZE * 4;
dst += CHACHA20_BLOCK_SIZE * 4;
state[12] += 4;
}
+
+ if (!bytes)
+ return;
+
+ kernel_neon_begin();
while (bytes >= CHACHA20_BLOCK_SIZE) {
chacha20_block_xor_neon(state, dst, src);
bytes -= CHACHA20_BLOCK_SIZE;
@@ -55,6 +62,7 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src,
chacha20_block_xor_neon(state, buf, buf);
memcpy(dst, buf, bytes);
}
+ kernel_neon_end();
}
static int chacha20_neon(struct skcipher_request *req)
@@ -68,11 +76,10 @@ static int chacha20_neon(struct skcipher_request *req)
if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE)
return crypto_chacha20_crypt(req);
- err = skcipher_walk_virt(&walk, req, true);
+ err = skcipher_walk_virt(&walk, req, false);
crypto_chacha20_init(state, ctx, walk.iv);
- kernel_neon_begin();
while (walk.nbytes > 0) {
unsigned int nbytes = walk.nbytes;
@@ -83,7 +90,6 @@ static int chacha20_neon(struct skcipher_request *req)
nbytes);
err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
}
- kernel_neon_end();
return err;
}