aboutsummaryrefslogtreecommitdiffstats
path: root/arch/arm64/crypto
diff options
context:
space:
mode:
authorArd Biesheuvel <ard.biesheuvel@linaro.org>2017-02-02 11:38:55 +0000
committerHerbert Xu <herbert@gondor.apana.org.au>2017-02-03 18:16:20 +0800
commit88a3f582bea9e1da0346ea412950bbbdc3125cc1 (patch)
tree37b29ebed0b653696165a69098dd344e837b293c /arch/arm64/crypto
parentcrypto: arm64/aes - replace scalar fallback with plain NEON fallback (diff)
downloadlinux-dev-88a3f582bea9e1da0346ea412950bbbdc3125cc1.tar.xz
linux-dev-88a3f582bea9e1da0346ea412950bbbdc3125cc1.zip
crypto: arm64/aes - don't use IV buffer to return final keystream block
The arm64 bit sliced AES core code uses the IV buffer to pass the final keystream block back to the glue code if the input is not a multiple of the block size, so that the asm code does not have to deal with anything except 16 byte blocks. This is done under the assumption that the outgoing IV is meaningless anyway in this case, given that chaining is no longer possible under these circumstances. However, as it turns out, the CCM driver does expect the IV to retain a value that is equal to the original IV except for the counter value, and even interprets byte zero as a length indicator, which may result in memory corruption if the IV is overwritten with something else. So use a separate buffer to return the final keystream block. 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/aes-neonbs-core.S37
-rw-r--r--arch/arm64/crypto/aes-neonbs-glue.c9
2 files changed, 28 insertions, 18 deletions
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index 8d0cdaa2768d..ca0472500433 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -853,13 +853,15 @@ ENDPROC(aesbs_xts_decrypt)
/*
* aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
- * int rounds, int blocks, u8 iv[], bool final)
+ * int rounds, int blocks, u8 iv[], u8 final[])
*/
ENTRY(aesbs_ctr_encrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
- add x4, x4, x6 // do one extra block if final
+ cmp x6, #0
+ cset x10, ne
+ add x4, x4, x10 // do one extra block if final
ldp x7, x8, [x5]
ld1 {v0.16b}, [x5]
@@ -874,19 +876,26 @@ CPU_LE( rev x8, x8 )
csel x4, x4, xzr, pl
csel x9, x9, xzr, le
+ tbnz x9, #1, 0f
next_ctr v1
+ tbnz x9, #2, 0f
next_ctr v2
+ tbnz x9, #3, 0f
next_ctr v3
+ tbnz x9, #4, 0f
next_ctr v4
+ tbnz x9, #5, 0f
next_ctr v5
+ tbnz x9, #6, 0f
next_ctr v6
+ tbnz x9, #7, 0f
next_ctr v7
0: mov bskey, x2
mov rounds, x3
bl aesbs_encrypt8
- lsr x9, x9, x6 // disregard the extra block
+ lsr x9, x9, x10 // disregard the extra block
tbnz x9, #0, 0f
ld1 {v8.16b}, [x1], #16
@@ -928,36 +937,36 @@ CPU_LE( rev x8, x8 )
eor v5.16b, v5.16b, v15.16b
st1 {v5.16b}, [x0], #16
- next_ctr v0
+8: next_ctr v0
cbnz x4, 99b
0: st1 {v0.16b}, [x5]
-8: ldp x29, x30, [sp], #16
+ ldp x29, x30, [sp], #16
ret
/*
- * If we are handling the tail of the input (x6 == 1), return the
- * final keystream block back to the caller via the IV buffer.
+ * If we are handling the tail of the input (x6 != NULL), return the
+ * final keystream block back to the caller.
*/
1: cbz x6, 8b
- st1 {v1.16b}, [x5]
+ st1 {v1.16b}, [x6]
b 8b
2: cbz x6, 8b
- st1 {v4.16b}, [x5]
+ st1 {v4.16b}, [x6]
b 8b
3: cbz x6, 8b
- st1 {v6.16b}, [x5]
+ st1 {v6.16b}, [x6]
b 8b
4: cbz x6, 8b
- st1 {v3.16b}, [x5]
+ st1 {v3.16b}, [x6]
b 8b
5: cbz x6, 8b
- st1 {v7.16b}, [x5]
+ st1 {v7.16b}, [x6]
b 8b
6: cbz x6, 8b
- st1 {v2.16b}, [x5]
+ st1 {v2.16b}, [x6]
b 8b
7: cbz x6, 8b
- st1 {v5.16b}, [x5]
+ st1 {v5.16b}, [x6]
b 8b
ENDPROC(aesbs_ctr_encrypt)
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index 863e436ecf89..db2501d93550 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[], bool final);
+ int rounds, int blocks, u8 iv[], u8 final[]);
asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
int rounds, int blocks, u8 iv[]);
@@ -201,6 +201,7 @@ 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 skcipher_walk walk;
+ u8 buf[AES_BLOCK_SIZE];
int err;
err = skcipher_walk_virt(&walk, req, true);
@@ -208,12 +209,12 @@ static int ctr_encrypt(struct skcipher_request *req)
kernel_neon_begin();
while (walk.nbytes > 0) {
unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
- bool final = (walk.total % AES_BLOCK_SIZE) != 0;
+ u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
if (walk.nbytes < walk.total) {
blocks = round_down(blocks,
walk.stride / AES_BLOCK_SIZE);
- final = false;
+ final = NULL;
}
aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
@@ -225,7 +226,7 @@ static int ctr_encrypt(struct skcipher_request *req)
if (dst != src)
memcpy(dst, src, walk.total % AES_BLOCK_SIZE);
- crypto_xor(dst, walk.iv, walk.total % AES_BLOCK_SIZE);
+ crypto_xor(dst, final, walk.total % AES_BLOCK_SIZE);
err = skcipher_walk_done(&walk, 0);
break;