summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorOndrej Mosnacek <omosnace@redhat.com>2018-09-13 10:51:33 +0200
committerHerbert Xu <herbert@gondor.apana.org.au>2018-09-21 13:24:52 +0800
commitc778f96bf3471b870caa2b9282f08f176a416f88 (patch)
tree85d8367951116ab1135f90bfeafcb9de05964b04
parentdc6d6d5a586fdd6876e18092d5363d48f26b7738 (diff)
downloadlinux-c778f96bf3471b870caa2b9282f08f176a416f88.tar.bz2
crypto: lrw - Optimize tweak computation
This patch rewrites the tweak computation to a slightly simpler method that performs less bswaps. Based on performance measurements the new code seems to provide slightly better performance than the old one. PERFORMANCE MEASUREMENTS (x86_64) Performed using: https://gitlab.com/omos/linux-crypto-bench Crypto driver used: lrw(ecb-aes-aesni) Before: ALGORITHM KEY (b) DATA (B) TIME ENC (ns) TIME DEC (ns) lrw(aes) 256 64 204 286 lrw(aes) 320 64 227 203 lrw(aes) 384 64 208 204 lrw(aes) 256 512 441 439 lrw(aes) 320 512 456 455 lrw(aes) 384 512 469 483 lrw(aes) 256 4096 2136 2190 lrw(aes) 320 4096 2161 2213 lrw(aes) 384 4096 2295 2369 lrw(aes) 256 16384 7692 7868 lrw(aes) 320 16384 8230 8691 lrw(aes) 384 16384 8971 8813 lrw(aes) 256 32768 15336 15560 lrw(aes) 320 32768 16410 16346 lrw(aes) 384 32768 18023 17465 After: ALGORITHM KEY (b) DATA (B) TIME ENC (ns) TIME DEC (ns) lrw(aes) 256 64 200 203 lrw(aes) 320 64 202 204 lrw(aes) 384 64 204 205 lrw(aes) 256 512 415 415 lrw(aes) 320 512 432 440 lrw(aes) 384 512 449 451 lrw(aes) 256 4096 1838 1995 lrw(aes) 320 4096 2123 1980 lrw(aes) 384 4096 2100 2119 lrw(aes) 256 16384 7183 6954 lrw(aes) 320 16384 7844 7631 lrw(aes) 384 16384 8256 8126 lrw(aes) 256 32768 14772 14484 lrw(aes) 320 32768 15281 15431 lrw(aes) 384 32768 16469 16293 Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
-rw-r--r--crypto/lrw.c61
1 files changed, 37 insertions, 24 deletions
diff --git a/crypto/lrw.c b/crypto/lrw.c
index 5504d1325a56..7377b5b486fd 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -120,27 +120,28 @@ static int setkey(struct crypto_skcipher *parent, const u8 *key,
return 0;
}
-static inline void inc(be128 *iv)
-{
- be64_add_cpu(&iv->b, 1);
- if (!iv->b)
- be64_add_cpu(&iv->a, 1);
-}
-
-/* this returns the number of consequative 1 bits starting
- * from the right, get_index128(00 00 00 00 00 00 ... 00 00 10 FB) = 2 */
-static inline int get_index128(be128 *block)
+/*
+ * Returns the number of trailing '1' bits in the words of the counter, which is
+ * represented by 4 32-bit words, arranged from least to most significant.
+ * At the same time, increments the counter by one.
+ *
+ * For example:
+ *
+ * u32 counter[4] = { 0xFFFFFFFF, 0x1, 0x0, 0x0 };
+ * int i = next_index(&counter);
+ * // i == 33, counter == { 0x0, 0x2, 0x0, 0x0 }
+ */
+static int next_index(u32 *counter)
{
- int x;
- __be32 *p = (__be32 *) block;
+ int i, res = 0;
- for (p += 3, x = 0; x < 128; p--, x += 32) {
- u32 val = be32_to_cpup(p);
-
- if (!~val)
- continue;
-
- return x + ffz(val);
+ for (i = 0; i < 4; i++) {
+ if (counter[i] + 1 != 0) {
+ res += ffz(counter[i]++);
+ break;
+ }
+ counter[i] = 0;
+ res += 32;
}
/*
@@ -214,8 +215,9 @@ static int pre_crypt(struct skcipher_request *req)
struct scatterlist *sg;
unsigned cryptlen;
unsigned offset;
- be128 *iv;
bool more;
+ __be32 *iv;
+ u32 counter[4];
int err;
subreq = &rctx->subreq;
@@ -230,7 +232,12 @@ static int pre_crypt(struct skcipher_request *req)
cryptlen, req->iv);
err = skcipher_walk_virt(&w, subreq, false);
- iv = w.iv;
+ iv = (__be32 *)w.iv;
+
+ counter[0] = be32_to_cpu(iv[3]);
+ counter[1] = be32_to_cpu(iv[2]);
+ counter[2] = be32_to_cpu(iv[1]);
+ counter[3] = be32_to_cpu(iv[0]);
while (w.nbytes) {
unsigned int avail = w.nbytes;
@@ -247,10 +254,16 @@ static int pre_crypt(struct skcipher_request *req)
/* T <- I*Key2, using the optimization
* discussed in the specification */
be128_xor(&rctx->t, &rctx->t,
- &ctx->mulinc[get_index128(iv)]);
- inc(iv);
+ &ctx->mulinc[next_index(counter)]);
} while ((avail -= bs) >= bs);
+ if (w.nbytes == w.total) {
+ iv[0] = cpu_to_be32(counter[3]);
+ iv[1] = cpu_to_be32(counter[2]);
+ iv[2] = cpu_to_be32(counter[1]);
+ iv[3] = cpu_to_be32(counter[0]);
+ }
+
err = skcipher_walk_done(&w, avail);
}
@@ -548,7 +561,7 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
inst->alg.base.cra_priority = alg->base.cra_priority;
inst->alg.base.cra_blocksize = LRW_BLOCK_SIZE;
inst->alg.base.cra_alignmask = alg->base.cra_alignmask |
- (__alignof__(u64) - 1);
+ (__alignof__(__be32) - 1);
inst->alg.ivsize = LRW_BLOCK_SIZE;
inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(alg) +