From c29e3ddfbd904f0b7cf600c04c4263c71c1f4830 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 5 Feb 2012 15:09:28 +1100 Subject: [PATCH] crypto: sha512 - Avoid stack bloat on i386 commit 3a92d687c8015860a19213e3c102cad6b722f83c upstream. Unfortunately in reducing W from 80 to 16 we ended up unrolling the loop twice. As gcc has issues dealing with 64-bit ops on i386 this means that we end up using even more stack space (>1K). This patch solves the W reduction by moving LOAD_OP/BLEND_OP into the loop itself, thus avoiding the need to duplicate it. While the stack space still isn't great (>0.5K) it is at least in the same ball park as the amount of stack used for our C sha1 implementation. Note that this patch basically reverts to the original code so the diff looks bigger than it really is. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/sha512_generic.c | 68 +++++++++++++++++++---------------------- 1 file changed, 32 insertions(+), 36 deletions(-) diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c index 3edebfd4dbec..f04af931a682 100644 --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -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)&15]; \ - 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; -- 2.34.1