leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Browse Source 
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
This commit is contained in:
Linus Torvalds 2012-02-13 20:33:45 -08:00
commit ca81a62198
1 changed files with 31 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
crypto/sha512_generic.c
View File

@ -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) 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 static void
@ -89,46 +89,42 @@ sha512_transform(u64 *state, const u8 *input)
int i; int i;
u64 W[16]; u64 W[16];
/* load the input */
for (i = 0; i < 16; i++)
LOAD_OP(i, W, input);
/* load the state into our registers */ /* load the state into our registers */
a=state[0]; b=state[1]; c=state[2]; d=state[3]; a=state[0]; b=state[1]; c=state[2]; d=state[3];
e=state[4]; f=state[5]; g=state[6]; h=state[7]; 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) \ /* now iterate */
t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[i]; \ for (i=0; i<80; i+=8) {
t2 = e0(a) + Maj(a, b, c); \ if (!(i & 8)) {
d += t1; \ int j;
h = t1 + t2
#define SHA512_16_79(i, a, b, c, d, e, f, g, h) \ if (i < 16) {
BLEND_OP(i, W); \ /* load the input */
t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[(i)%16]; \ for (j = 0; j < 16; j++)
t2 = e0(a) + Maj(a, b, c); \ LOAD_OP(i + j, W, input);
d += t1; \ } else {
h = t1 + t2 for (j = 0; j < 16; j++) {
BLEND_OP(i + j, W);
}
}
}
for (i = 0; i < 16; i += 8) { t1 = h + e1(e) + Ch(e,f,g) + sha512_K[i ] + W[(i & 15)];
SHA512_0_15(i, a, b, c, d, e, f, g, h); t2 = e0(a) + Maj(a,b,c); d+=t1; h=t1+t2;
SHA512_0_15(i + 1, h, a, b, c, d, e, f, g); t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[(i & 15) + 1];
SHA512_0_15(i + 2, g, h, a, b, c, d, e, f); t2 = e0(h) + Maj(h,a,b); c+=t1; g=t1+t2;
SHA512_0_15(i + 3, f, g, h, a, b, c, d, e); t1 = f + e1(c) + Ch(c,d,e) + sha512_K[i+2] + W[(i & 15) + 2];
SHA512_0_15(i + 4, e, f, g, h, a, b, c, d); t2 = e0(g) + Maj(g,h,a); b+=t1; f=t1+t2;
SHA512_0_15(i + 5, d, e, f, g, h, a, b, c); t1 = e + e1(b) + Ch(b,c,d) + sha512_K[i+3] + W[(i & 15) + 3];
SHA512_0_15(i + 6, c, d, e, f, g, h, a, b); t2 = e0(f) + Maj(f,g,h); a+=t1; e=t1+t2;
SHA512_0_15(i + 7, b, c, d, e, f, g, h, a); 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;
for (i = 16; i < 80; i += 8) { t1 = c + e1(h) + Ch(h,a,b) + sha512_K[i+5] + W[(i & 15) + 5];
SHA512_16_79(i, a, b, c, d, e, f, g, h); t2 = e0(d) + Maj(d,e,f); g+=t1; c=t1+t2;
SHA512_16_79(i + 1, h, a, b, c, d, e, f, g); t1 = b + e1(g) + Ch(g,h,a) + sha512_K[i+6] + W[(i & 15) + 6];
SHA512_16_79(i + 2, g, h, a, b, c, d, e, f); t2 = e0(c) + Maj(c,d,e); f+=t1; b=t1+t2;
SHA512_16_79(i + 3, f, g, h, a, b, c, d, e); t1 = a + e1(f) + Ch(f,g,h) + sha512_K[i+7] + W[(i & 15) + 7];
SHA512_16_79(i + 4, e, f, g, h, a, b, c, d); t2 = e0(b) + Maj(b,c,d); e+=t1; a=t1+t2;
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);
} }
state[0] += a; state[1] += b; state[2] += c; state[3] += d; state[0] += a; state[1] += b; state[2] += c; state[3] += d;