diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-02-14 05:33:45 +0100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-02-14 05:33:45 +0100 |
commit | ca81a62198e39ad9155f12725c269fcc2a9f1f8b (patch) | |
tree | 922decd817e170899c30eaa47335bec080f020da /crypto | |
parent | Merge tag 'for-linus' of git://github.com/rustyrussell/linux (diff) | |
parent | crypto: sha512 - Avoid stack bloat on i386 (diff) | |
download | linux-ca81a62198e39ad9155f12725c269fcc2a9f1f8b.tar.xz linux-ca81a62198e39ad9155f12725c269fcc2a9f1f8b.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6
This updates the sha512 fix so that it doesn't cause excessive stack
usage on i386. This is done by reverting to the original code, and
avoiding the W duplication by moving its initialisation into the loop.
As the underlying code is in fact the one that we have used for years,
I'm pushing this now instead of postponing to the next cycle.
* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
crypto: sha512 - Avoid stack bloat on i386
crypto: sha512 - Use binary and instead of modulus
Diffstat (limited to 'crypto')
-rw-r--r-- | crypto/sha512_generic.c | 70 |
1 files changed, 33 insertions, 37 deletions
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c index 88f160b77b1f..f04af931a682 100644 --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -78,7 +78,7 @@ static inline void LOAD_OP(int I, u64 *W, const u8 *input) static inline void BLEND_OP(int I, u64 *W) { - W[I % 16] += s1(W[(I-2) % 16]) + W[(I-7) % 16] + s0(W[(I-15) % 16]); + W[I & 15] += s1(W[(I-2) & 15]) + W[(I-7) & 15] + s0(W[(I-15) & 15]); } static void @@ -89,46 +89,42 @@ sha512_transform(u64 *state, const u8 *input) int i; u64 W[16]; - /* load the input */ - for (i = 0; i < 16; i++) - LOAD_OP(i, W, input); - /* load the state into our registers */ a=state[0]; b=state[1]; c=state[2]; d=state[3]; e=state[4]; f=state[5]; g=state[6]; h=state[7]; -#define SHA512_0_15(i, a, b, c, d, e, f, g, h) \ - t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[i]; \ - t2 = e0(a) + Maj(a, b, c); \ - d += t1; \ - h = t1 + t2 - -#define SHA512_16_79(i, a, b, c, d, e, f, g, h) \ - BLEND_OP(i, W); \ - t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[(i)%16]; \ - t2 = e0(a) + Maj(a, b, c); \ - d += t1; \ - h = t1 + t2 - - for (i = 0; i < 16; i += 8) { - SHA512_0_15(i, a, b, c, d, e, f, g, h); - SHA512_0_15(i + 1, h, a, b, c, d, e, f, g); - SHA512_0_15(i + 2, g, h, a, b, c, d, e, f); - SHA512_0_15(i + 3, f, g, h, a, b, c, d, e); - SHA512_0_15(i + 4, e, f, g, h, a, b, c, d); - SHA512_0_15(i + 5, d, e, f, g, h, a, b, c); - SHA512_0_15(i + 6, c, d, e, f, g, h, a, b); - SHA512_0_15(i + 7, b, c, d, e, f, g, h, a); - } - for (i = 16; i < 80; i += 8) { - SHA512_16_79(i, a, b, c, d, e, f, g, h); - SHA512_16_79(i + 1, h, a, b, c, d, e, f, g); - SHA512_16_79(i + 2, g, h, a, b, c, d, e, f); - SHA512_16_79(i + 3, f, g, h, a, b, c, d, e); - SHA512_16_79(i + 4, e, f, g, h, a, b, c, d); - SHA512_16_79(i + 5, d, e, f, g, h, a, b, c); - SHA512_16_79(i + 6, c, d, e, f, g, h, a, b); - SHA512_16_79(i + 7, b, c, d, e, f, g, h, a); + /* now iterate */ + for (i=0; i<80; i+=8) { + if (!(i & 8)) { + int j; + + if (i < 16) { + /* load the input */ + for (j = 0; j < 16; j++) + LOAD_OP(i + j, W, input); + } else { + for (j = 0; j < 16; j++) { + BLEND_OP(i + j, W); + } + } + } + + t1 = h + e1(e) + Ch(e,f,g) + sha512_K[i ] + W[(i & 15)]; + t2 = e0(a) + Maj(a,b,c); d+=t1; h=t1+t2; + t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[(i & 15) + 1]; + t2 = e0(h) + Maj(h,a,b); c+=t1; g=t1+t2; + t1 = f + e1(c) + Ch(c,d,e) + sha512_K[i+2] + W[(i & 15) + 2]; + t2 = e0(g) + Maj(g,h,a); b+=t1; f=t1+t2; + t1 = e + e1(b) + Ch(b,c,d) + sha512_K[i+3] + W[(i & 15) + 3]; + t2 = e0(f) + Maj(f,g,h); a+=t1; e=t1+t2; + t1 = d + e1(a) + Ch(a,b,c) + sha512_K[i+4] + W[(i & 15) + 4]; + t2 = e0(e) + Maj(e,f,g); h+=t1; d=t1+t2; + t1 = c + e1(h) + Ch(h,a,b) + sha512_K[i+5] + W[(i & 15) + 5]; + t2 = e0(d) + Maj(d,e,f); g+=t1; c=t1+t2; + t1 = b + e1(g) + Ch(g,h,a) + sha512_K[i+6] + W[(i & 15) + 6]; + t2 = e0(c) + Maj(c,d,e); f+=t1; b=t1+t2; + t1 = a + e1(f) + Ch(f,g,h) + sha512_K[i+7] + W[(i & 15) + 7]; + t2 = e0(b) + Maj(b,c,d); e+=t1; a=t1+t2; } state[0] += a; state[1] += b; state[2] += c; state[3] += d; |