crypto: x86/poly1305 - fix overflow during partial reduction

commit 678cce4019 upstream.

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: b1ccc8f4b6 ("crypto: poly1305 - Add a four block AVX2 variant for x86_64")
Fixes: c70f4abef0 ("crypto: poly1305 - Add a SSE2 SIMD variant for x86_64")
Cc: <stable@vger.kernel.org> # v4.3+
Cc: Martin Willi <martin@strongswan.org>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Eric Biggers 2019-03-31 13:04:11 -07:00 committed by Greg Kroah-Hartman
parent dacdbc115d
commit fbe5cff932
3 changed files with 67 additions and 13 deletions

View File

@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2)
vpaddq t2,t1,t1
vmovq t1x,d4
# Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
# h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
# amount. Careful: we must not assume the carry bits 'd0 >> 26',
# 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
# integers. It's true in a single-block implementation, but not here.
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
lea (%eax,%eax,4),%eax
add %eax,%ebx
lea (%rax,%rax,4),%rax
add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
mov %ebx,%eax
shr $26,%eax
mov %rbx,%rax
shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx

View File

@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
lea (%eax,%eax,4),%eax
add %eax,%ebx
lea (%rax,%rax,4),%rax
add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
mov %ebx,%eax
shr $26,%eax
mov %rbx,%rax
shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
@ -520,6 +520,12 @@ ENTRY(poly1305_2block_sse2)
paddq t2,t1
movq t1,d4
# Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
# h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
# amount. Careful: we must not assume the carry bits 'd0 >> 26',
# 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
# integers. It's true in a single-block implementation, but not here.
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
@ -558,16 +564,16 @@ ENTRY(poly1305_2block_sse2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
lea (%eax,%eax,4),%eax
add %eax,%ebx
lea (%rax,%rax,4),%rax
add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
mov %ebx,%eax
shr $26,%eax
mov %rbx,%rax
shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx

View File

@ -5592,7 +5592,49 @@ 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",
}
};
/*