From 678cce4019d746da6c680c48ba9e6d417803e127 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 31 Mar 2019 13:04:11 -0700 Subject: crypto: x86/poly1305 - fix overflow during partial reduction The x86_64 implementation of Poly1305 produces the wrong result on some inputs because poly1305_4block_avx2() incorrectly assumes that when partially reducing the accumulator, the bits carried from limb 'd4' to limb 'h0' fit in a 32-bit integer. This is true for poly1305-generic which processes only one block at a time. However, it's not true for the AVX2 implementation, which processes 4 blocks at a time and therefore can produce intermediate limbs about 4x larger. Fix it by making the relevant calculations use 64-bit arithmetic rather than 32-bit. Note that most of the carries already used 64-bit arithmetic, but the d4 -> h0 carry was different for some reason. To be safe I also made the same change to the corresponding SSE2 code, though that only operates on 1 or 2 blocks at a time. I don't think it's really needed for poly1305_block_sse2(), but it doesn't hurt because it's already x86_64 code. It *might* be needed for poly1305_2block_sse2(), but overflows aren't easy to reproduce there. This bug was originally detected by my patches that improve testmgr to fuzz algorithms against their generic implementation. But also add a test vector which reproduces it directly (in the AVX2 case). Fixes: b1ccc8f4b631 ("crypto: poly1305 - Add a four block AVX2 variant for x86_64") Fixes: c70f4abef07a ("crypto: poly1305 - Add a SSE2 SIMD variant for x86_64") Cc: # v4.3+ Cc: Martin Willi Cc: Jason A. Donenfeld Signed-off-by: Eric Biggers Reviewed-by: Martin Willi Signed-off-by: Herbert Xu --- crypto/testmgr.h | 44 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 43 insertions(+), 1 deletion(-) (limited to 'crypto') diff --git a/crypto/testmgr.h b/crypto/testmgr.h index f267633cf13a..d18a37629f05 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -5634,7 +5634,49 @@ static const struct hash_testvec poly1305_tv_template[] = { .psize = 80, .digest = "\x13\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00", - }, + }, { /* Regression test for overflow in AVX2 implementation */ + .plaintext = "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff", + .psize = 300, + .digest = "\xfb\x5e\x96\xd8\x61\xd5\xc7\xc8" + "\x78\xe5\x87\xcc\x2d\x5a\x22\xe1", + } }; /* NHPoly1305 test vectors from https://github.com/google/adiantum */ -- cgit v1.2.3-59-g8ed1b