From 07918ddba3ab7549ea6f69156accbdb6c467832a Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 11 Jan 2022 18:58:43 +0100 Subject: [PATCH] lib/crypto: sha1: re-roll loops to reduce code size commit 9a1536b093bb5bf60689021275fd24d513bb8db0 upstream. With SHA-1 no longer being used for anything performance oriented, and also soon to be phased out entirely, we can make up for the space added by unrolled BLAKE2s by simply re-rolling SHA-1. Since SHA-1 is so much more complex, re-rolling it more or less takes care of the code size added by BLAKE2s. And eventually, hopefully we'll see SHA-1 removed entirely from most small kernel builds. Cc: Herbert Xu Cc: Ard Biesheuvel Tested-by: Geert Uytterhoeven Signed-off-by: Jason A. Donenfeld Signed-off-by: Greg Kroah-Hartman --- lib/sha1.c | 95 ++++++++---------------------------------------------- 1 file changed, 14 insertions(+), 81 deletions(-) diff --git a/lib/sha1.c b/lib/sha1.c index 49257a915bb6..5ad4e4948272 100644 --- a/lib/sha1.c +++ b/lib/sha1.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -55,7 +56,8 @@ #define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \ __u32 TEMP = input(t); setW(t, TEMP); \ E += TEMP + rol32(A,5) + (fn) + (constant); \ - B = ror32(B, 2); } while (0) + B = ror32(B, 2); \ + TEMP = E; E = D; D = C; C = B; B = A; A = TEMP; } while (0) #define T_0_15(t, A, B, C, D, E) SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) #define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) @@ -84,6 +86,7 @@ void sha1_transform(__u32 *digest, const char *data, __u32 *array) { __u32 A, B, C, D, E; + unsigned int i = 0; A = digest[0]; B = digest[1]; @@ -92,94 +95,24 @@ void sha1_transform(__u32 *digest, const char *data, __u32 *array) E = digest[4]; /* Round 1 - iterations 0-16 take their input from 'data' */ - T_0_15( 0, A, B, C, D, E); - T_0_15( 1, E, A, B, C, D); - T_0_15( 2, D, E, A, B, C); - T_0_15( 3, C, D, E, A, B); - T_0_15( 4, B, C, D, E, A); - T_0_15( 5, A, B, C, D, E); - T_0_15( 6, E, A, B, C, D); - T_0_15( 7, D, E, A, B, C); - T_0_15( 8, C, D, E, A, B); - T_0_15( 9, B, C, D, E, A); - T_0_15(10, A, B, C, D, E); - T_0_15(11, E, A, B, C, D); - T_0_15(12, D, E, A, B, C); - T_0_15(13, C, D, E, A, B); - T_0_15(14, B, C, D, E, A); - T_0_15(15, A, B, C, D, E); + for (; i < 16; ++i) + T_0_15(i, A, B, C, D, E); /* Round 1 - tail. Input from 512-bit mixing array */ - T_16_19(16, E, A, B, C, D); - T_16_19(17, D, E, A, B, C); - T_16_19(18, C, D, E, A, B); - T_16_19(19, B, C, D, E, A); + for (; i < 20; ++i) + T_16_19(i, A, B, C, D, E); /* Round 2 */ - T_20_39(20, A, B, C, D, E); - T_20_39(21, E, A, B, C, D); - T_20_39(22, D, E, A, B, C); - T_20_39(23, C, D, E, A, B); - T_20_39(24, B, C, D, E, A); - T_20_39(25, A, B, C, D, E); - T_20_39(26, E, A, B, C, D); - T_20_39(27, D, E, A, B, C); - T_20_39(28, C, D, E, A, B); - T_20_39(29, B, C, D, E, A); - T_20_39(30, A, B, C, D, E); - T_20_39(31, E, A, B, C, D); - T_20_39(32, D, E, A, B, C); - T_20_39(33, C, D, E, A, B); - T_20_39(34, B, C, D, E, A); - T_20_39(35, A, B, C, D, E); - T_20_39(36, E, A, B, C, D); - T_20_39(37, D, E, A, B, C); - T_20_39(38, C, D, E, A, B); - T_20_39(39, B, C, D, E, A); + for (; i < 40; ++i) + T_20_39(i, A, B, C, D, E); /* Round 3 */ - T_40_59(40, A, B, C, D, E); - T_40_59(41, E, A, B, C, D); - T_40_59(42, D, E, A, B, C); - T_40_59(43, C, D, E, A, B); - T_40_59(44, B, C, D, E, A); - T_40_59(45, A, B, C, D, E); - T_40_59(46, E, A, B, C, D); - T_40_59(47, D, E, A, B, C); - T_40_59(48, C, D, E, A, B); - T_40_59(49, B, C, D, E, A); - T_40_59(50, A, B, C, D, E); - T_40_59(51, E, A, B, C, D); - T_40_59(52, D, E, A, B, C); - T_40_59(53, C, D, E, A, B); - T_40_59(54, B, C, D, E, A); - T_40_59(55, A, B, C, D, E); - T_40_59(56, E, A, B, C, D); - T_40_59(57, D, E, A, B, C); - T_40_59(58, C, D, E, A, B); - T_40_59(59, B, C, D, E, A); + for (; i < 60; ++i) + T_40_59(i, A, B, C, D, E); /* Round 4 */ - T_60_79(60, A, B, C, D, E); - T_60_79(61, E, A, B, C, D); - T_60_79(62, D, E, A, B, C); - T_60_79(63, C, D, E, A, B); - T_60_79(64, B, C, D, E, A); - T_60_79(65, A, B, C, D, E); - T_60_79(66, E, A, B, C, D); - T_60_79(67, D, E, A, B, C); - T_60_79(68, C, D, E, A, B); - T_60_79(69, B, C, D, E, A); - T_60_79(70, A, B, C, D, E); - T_60_79(71, E, A, B, C, D); - T_60_79(72, D, E, A, B, C); - T_60_79(73, C, D, E, A, B); - T_60_79(74, B, C, D, E, A); - T_60_79(75, A, B, C, D, E); - T_60_79(76, E, A, B, C, D); - T_60_79(77, D, E, A, B, C); - T_60_79(78, C, D, E, A, B); - T_60_79(79, B, C, D, E, A); + for (; i < 80; ++i) + T_60_79(i, A, B, C, D, E); digest[0] += A; digest[1] += B;