diff options
| author | Andrew Morton <akpm@osdl.org> | 2004-10-25 06:47:38 -0700 |
|---|---|---|
| committer | David S. Miller <davem@nuts.davemloft.net> | 2004-10-25 06:47:38 -0700 |
| commit | e0abaebae36abff9e3dd6e9f8aac098c66542f18 (patch) | |
| tree | d6401411bc0746d903463d0ef4039faabd13931e | |
| parent | bc30e521501808ab0241aba022377863e0274ee5 (diff) | |
[CRYPTO]: reduce sha512_transform() stack usage, speedup
Patch moves large temporary u64 W[80] from stack to ctx struct:
* reduces stack usage by 640 bytes
* saves one 640-byte memset() per sha512_transform()
(we still do it after *all* iterations are done)
* quite unexpectedly saves 1.6k of code on i386
because stack offsets now fit into 8bits
and many stack addressing insns got 3 bytes smaller:
# size sha512.o.org sha512.o
text data bss dec hex filename
8281 372 0 8653 21cd sha512.o.org
6649 372 0 7021 1b6d sha512.o
# objdump -d sha512.o.org | cut -b9- >sha512.d.org
# objdump -d sha512.o | cut -b9- >sha512.d
# diff -u sha512.d.org sha512.d
[snip]
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
| -rw-r--r-- | crypto/sha512.c | 12 |
1 files changed, 7 insertions, 5 deletions
diff --git a/crypto/sha512.c b/crypto/sha512.c index 763093b17c1e..6acaea9b7e2b 100644 --- a/crypto/sha512.c +++ b/crypto/sha512.c @@ -30,6 +30,7 @@ struct sha512_ctx { u64 state[8]; u32 count[4]; u8 buf[128]; + u64 W[80]; }; static inline u64 Ch(u64 x, u64 y, u64 z) @@ -113,10 +114,9 @@ static inline void BLEND_OP(int I, u64 *W) } static void -sha512_transform(u64 *state, const u8 *input) +sha512_transform(u64 *state, u64 *W, const u8 *input) { u64 a, b, c, d, e, f, g, h, t1, t2; - u64 W[80]; int i; @@ -157,7 +157,6 @@ sha512_transform(u64 *state, const u8 *input) /* erase our data */ a = b = c = d = e = f = g = h = t1 = t2 = 0; - memset(W, 0, 80 * sizeof(u64)); } static void @@ -215,10 +214,10 @@ sha512_update(void *ctx, const u8 *data, unsigned int len) /* Transform as many times as possible. */ if (len >= part_len) { memcpy(&sctx->buf[index], data, part_len); - sha512_transform(sctx->state, sctx->buf); + sha512_transform(sctx->state, sctx->W, sctx->buf); for (i = part_len; i + 127 < len; i+=128) - sha512_transform(sctx->state, &data[i]); + sha512_transform(sctx->state, sctx->W, &data[i]); index = 0; } else { @@ -227,6 +226,9 @@ sha512_update(void *ctx, const u8 *data, unsigned int len) /* Buffer remaining input */ memcpy(&sctx->buf[index], &data[i], len - i); + + /* erase our data */ + memset(sctx->W, 0, sizeof(sctx->W)); } static void |