From: Alexey Dobriyan Subject: Re: sha512: make it work, undo percpu message schedule Date: Fri, 13 Jan 2012 13:33:43 +0200 Message-ID: References: <20120111000040.GA3801@p183.telecom.by> <20120111003611.GA12257@gondor.apana.org.au> <20120112235514.GA5065@p183.telecom.by> <20120113070813.GA20068@gondor.apana.org.au> <1326450942.2272.20.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> <1326451301.2272.23.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> <1326452246.2272.31.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Cc: Herbert Xu , linux-crypto@vger.kernel.org, netdev@vger.kernel.org, ken@codelabs.ch, Steffen Klassert To: Eric Dumazet Return-path: Received: from mail-iy0-f174.google.com ([209.85.210.174]:36415 "EHLO mail-iy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752900Ab2AMLdo (ORCPT ); Fri, 13 Jan 2012 06:33:44 -0500 In-Reply-To: <1326452246.2272.31.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> Sender: linux-crypto-owner@vger.kernel.org List-ID: On 1/13/12, Eric Dumazet wrote: > + static u64 msg_schedule[80]; > + static DEFINE_SPINLOCK(msg_schedule_lock); No guys, no. SHA-512 only needs u64[16] running window for message scheduling. I'm sending whitespace mangled patch which is only tested with selfcryptotest passed, so you won't apply something complex. Stackspace usage drops down to like this: -139: 48 81 ec c8 02 00 00 sub $0x2c8,%rsp +136: 48 81 ec 18 01 00 00 sub $0x118,%rsp --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -21,8 +21,6 @@ #include #include -static DEFINE_PER_CPU(u64[80], msg_schedule); - static inline u64 Ch(u64 x, u64 y, u64 z) { return z ^ (x & (y ^ z)); @@ -80,7 +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] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16]; + W[I%16] = s1(W[(I-2)%16]) + W[(I-7)%16] + s0(W[(I-15)%16]) + W[I%16]; } static void @@ -89,38 +87,48 @@ sha512_transform(u64 *state, const u8 *input) u64 a, b, c, d, e, f, g, h, t1, t2; int i; - u64 *W = get_cpu_var(msg_schedule); + u64 W[16]; /* load the input */ for (i = 0; i < 16; i++) LOAD_OP(i, W, input); - for (i = 16; i < 80; i++) { - BLEND_OP(i, W); - } - /* 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]; - /* now iterate */ - for (i=0; i<80; i+=8) { - 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; - t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[i+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+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+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+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+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+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+7]; - t2 = e0(b) + Maj(b,c,d); e+=t1; a=t1+t2; +#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); } state[0] += a; state[1] += b; state[2] += c; state[3] += d; @@ -128,8 +136,6 @@ sha512_transform(u64 *state, const u8 *input) /* erase our data */ a = b = c = d = e = f = g = h = t1 = t2 = 0; - memset(W, 0, sizeof(__get_cpu_var(msg_schedule))); - put_cpu_var(msg_schedule); } static int