From da619121a5d271e78ec709a1f9a3c5f99b9e10ad Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 6 Oct 2026 10:34:32 +0200 Subject: [PATCH 1/3] lib/crypto: poly1305: Use memzero_explicit() in poly1305_final() Use memzero_explicit() instead of a plain struct assignment to guarantee zeroization of the 'struct poly1305_desc_ctx'. Note that dead store elimination was only theoretically possible with link-time optimization here. But it's still worth fixing. Fixes: a1d93064094c ("crypto: poly1305 - expose init/update/final library interface") Cc: stable@vger.kernel.org Reported-by: Sashiko Closes: https://sashiko.dev/#/bug/linux-c3a6bd76-f6ab-4203-892a-cd06f7aa0c34 Reviewed-by: Ard Biesheuvel Link: https://patch.msgid.link/20261006083432.16328-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- lib/crypto/poly1305.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c index f313ccc4b4dd..048c7afe8613 100644 --- a/lib/crypto/poly1305.c +++ b/lib/crypto/poly1305.c @@ -78,7 +78,7 @@ void poly1305_final(struct poly1305_desc_ctx *desc, u8 *dst) } poly1305_emit(&desc->state.h, dst, desc->s); - *desc = (struct poly1305_desc_ctx){}; + memzero_explicit(desc, sizeof(*desc)); } EXPORT_SYMBOL(poly1305_final); From 24f07e8c07a0c0dd275331cbb41c79a78741eef9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Jean?= Date: Fri, 9 Oct 2026 14:53:53 +0200 Subject: [PATCH 2/3] lib/crypto: arm64: Fix lost Poly1305 carry when resuming NEON state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When poly1305_blocks_neon() resumes from a base 2^26 accumulator and the next update contains an odd number of full 16-byte blocks, it processes one leading block through poly1305_mult() so that the remaining NEON work has an even block count. That requires converting the accumulator to the base 2^64 form used by poly1305_mult(). The final ADC of that conversion stores the carry into d2, but the following accumulation and poly1305_mult() use h2. If the conversion carries across bit 128, the carry is dropped and the emitted tag is wrong. This was introduced by Cryptogams commit 03dc4adf91c8 ("arm/poly1305-armv*.pl: optimize branches."), which removed the reduction that consumed d2 shortly before Linux imported the code. OpenSSL's copy did not take that change. The carry is possible because the NEON code stores the accumulator [h0, h1, h2, h3, h4] in a lazily reduced, redundant base 2^26 form: its final carry chain leaves h0, h2, h3 < 2^26, but h1 and h4 may slightly exceed 2^26 - 1. For example, the reachable state h0 = 4 h1 = 2^26 h2 = 2^26 - 1 h3 = 2^26 - 1 h4 = 2^24 - 1 represents 4 + 2^26*2^26 + (2^26-1)*2^52 + (2^26-1)*2^78 + (2^24-1)*2^104 = 2^128 + 4, despite the bit representing the 2^128 term (bit 24 of h4) not being set; the extra comes from the h1 limb being above the normal base 2^26 range. When this value is converted into the non-redundant base 2^64 form, a carry into the new 2^128 bit (in bit 0 of h2) is necessary to preserve the value. Given the above bounds, a carry into bit 128 happens exactly when h1 >= 2^26, h2 = h3 = 2^26 - 1, and h4 mod 2^24 = 2^24 - 1. Store the carry into h2, matching the other base 2^26 to base 2^64 conversions in poly1305_blocks() and poly1305_emit(). This bug causes an incorrect tag to be emitted. However, this is unlikely to happen in practice where Poly1305 is used with a random key, since the random key tends to distribute the accumulator values throughout their valid range. There isn't an obvious way for an attacker without knowledge of the r_key to cause [h0, h1, h2, h3, h4] to land on the precise values where this bug occurs. [EB: Rewrote the commit message to more clearly describe the bug and its impact, and simplified explanation about why there's a carry bit.] Fixes: f569ca164751 ("crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation") Cc: stable@vger.kernel.org Assisted-by: LLM Reviewed-by: Jason A. Donenfeld Signed-off-by: Jérémy Jean Link: https://patch.msgid.link/20261009125354.315476-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- lib/crypto/arm64/poly1305-armv8.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/crypto/arm64/poly1305-armv8.pl b/lib/crypto/arm64/poly1305-armv8.pl index f1930c6b55ce..234398ff6b60 100644 --- a/lib/crypto/arm64/poly1305-armv8.pl +++ b/lib/crypto/arm64/poly1305-armv8.pl @@ -375,7 +375,7 @@ poly1305_blocks_neon: adc $h1,$h1,xzr lsr $h2,x14,#24 adds $h1,$h1,x14,lsl#40 - adc $d2,$h2,xzr // can be partially reduced... + adc $h2,$h2,xzr // preserve carry into top limb ldp $d0,$d1,[$inp],#16 // load input sub $len,$len,#16 From 7b817748bf083ad715a8d70de63f2184178cc372 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 9 Oct 2026 14:53:54 +0200 Subject: [PATCH 3/3] lib/crypto: tests: Add Poly1305 split-update carry regression test Add a test case which reproduces the bug fixed by commit 24f07e8c07a0 ("lib/crypto: arm64: Fix lost Poly1305 carry when resuming NEON state"). It is written in a fairly general way, such that it should also be able to reproduce similar bugs in other implementations. Update the comment on test_poly1305_allones_keys_and_message() to more accurately describe what it does and differentiate it from the new test. Reviewed-by: Jason A. Donenfeld Link: https://patch.msgid.link/20261009125354.315476-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- lib/crypto/tests/poly1305_kunit.c | 97 ++++++++++++++++++++++++++++--- 1 file changed, 88 insertions(+), 9 deletions(-) diff --git a/lib/crypto/tests/poly1305_kunit.c b/lib/crypto/tests/poly1305_kunit.c index f3cb6245bc29..d4490ee27c3d 100644 --- a/lib/crypto/tests/poly1305_kunit.c +++ b/lib/crypto/tests/poly1305_kunit.c @@ -55,16 +55,17 @@ static int poly1305_suite_init(struct kunit_suite *suite) * - Using an all-one-bits r_key tests the key clamping. * - Using an all-one-bits s_key tests carries in implementations of the * addition mod 2**128 during finalization. - * - Using all-one-bits message, and to a lesser extent r_key, tends to maximize - * any intermediate accumulator values. This increases the chance of - * detecting bugs that occur only in rare cases where the accumulator values - * get very large, for example the bug fixed by commit 678cce4019d746da - * ("crypto: x86/poly1305 - fix overflow during partial reduction"). + * - Using all-one-bits message and r_key results in large values for the + * internal products of r_key by (accumulator + message block). This + * increases the chance of detecting bugs that occur only in rare cases where + * the sum of these internal products is very large, for example the bug fixed + * by commit 678cce4019d7 ("crypto: x86/poly1305 - fix overflow during partial + * reduction"). * - * Accumulator overflow bugs may be specific to particular update lengths (in - * blocks) and/or particular values of the previous acculumator. Note that the - * accumulator starts at 0 which gives the lowest chance of an overflow. Thus, - * a single all-one-bits test vector may be insufficient. + * Bugs with the handling of large internal product sums may be specific to + * particular update lengths (in blocks) and/or require that the accumulator + * also have a large value. Note that the accumulator starts at 0. Thus, a + * single all-one-bits test vector may be insufficient. * * Considering that, do the following test: continuously update a single * Poly1305 context with all-one-bits data of varying lengths (0, 16, 32, ..., @@ -141,10 +142,88 @@ static void test_poly1305_reduction_edge_cases(struct kunit *test) } } +/* + * Test that Poly1305 MACs are computed correctly when r_key=1, s_key=0, and the + * message consists of all-ones blocks. + * + * With r_key=1 and s_key=0, Poly1305 degrades to the sum of the padded blocks + * mod 2**130 - 5, then reduced mod 2**128. A padded all-ones block maps to + * 2**128 + (2**128 - 1) = 2**129 - 1. Two such blocks sum to 2**130 - 2, which + * is congruent to 3 mod 2**130 - 5. Thus, the expected MAC is just 3 * + * floor(nblocks / 2), minus 1 if nblocks is odd, then reduced mod 2**128. If + * nblocks == 1 this is 2**128 - 1, otherwise it's just a small integer. + * + * Inside the Poly1305 implementation in this case, the multiplication does + * nothing and each block just adds 2**129 - 1 to the accumulator. Without the + * multiplication to mix things up, this results in some interesting values + * being reached where the limbs are at or near their maximum values, even after + * (lazy) reduction. This can reproduce bugs that happen only in such cases. + * + * For example, this test case reproduces the bug fixed by commit 24f07e8c07a0 + * ("lib/crypto: arm64: Fix lost Poly1305 carry when resuming NEON state"). + * + * However, reaching that bug required two consecutive updates: one with >= 8 + * blocks to cause NEON code to be used and leave the accumulator in base 2**26 + * with its limbs in a certain pattern, then one with an odd number of blocks >= + * 9 to cause NEON to be used again, but first processing one block using scalar + * code as a special case, triggering a conversion to base 2**64 where the carry + * into the 2**128 bit was lost. To cover this and other similar edge cases + * that may exist in other Poly1305 implementations, just test all possible + * block-aligned splits between three poly1305_update() calls. + */ +static void test_poly1305_split_update_carry(struct kunit *test) +{ + static const u8 key[POLY1305_KEY_SIZE] = { 1 }; /* r_key=1, s_key=0 */ + /* + * Use max_nblocks=66 so that it's a bit more than twice the AVX-512 + * threshold of 32 blocks. + */ + const int max_nblocks = 66; + u8 *data = alloc_buf(test, max_nblocks * POLY1305_BLOCK_SIZE); + u8 expected_mac[POLY1305_DIGEST_SIZE]; + u8 actual_mac[POLY1305_DIGEST_SIZE]; + struct poly1305_desc_ctx ctx; + + KUNIT_ASSERT_LE(test, 3 * (max_nblocks / 2), U8_MAX); + + memset(data, 0xff, max_nblocks * POLY1305_BLOCK_SIZE); + + for (int nblocks = 0; nblocks <= max_nblocks; nblocks++) { + size_t len = nblocks * POLY1305_BLOCK_SIZE; + + expected_mac[0] = 3 * (nblocks / 2) - (nblocks % 2); + memset(&expected_mac[1], nblocks == 1 ? 0xff : 0, + POLY1305_DIGEST_SIZE - 1); + for (size_t part1_len = 0; part1_len <= len; + part1_len += POLY1305_BLOCK_SIZE) { + for (size_t part2_len = 0; part2_len <= len - part1_len; + part2_len += POLY1305_BLOCK_SIZE) { + size_t part3_len = len - part1_len - part2_len; + + poly1305_init(&ctx, key); + poly1305_update(&ctx, data, part1_len); + poly1305_update(&ctx, &data[part1_len], + part2_len); + poly1305_update(&ctx, + &data[part1_len + part2_len], + part3_len); + poly1305_final(&ctx, actual_mac); + KUNIT_ASSERT_MEMEQ_MSG( + test, actual_mac, expected_mac, + POLY1305_DIGEST_SIZE, + "Failed with nblocks=%d, part1_len=%zu, part2_len=%zu, part3_len=%zu", + nblocks, part1_len, part2_len, + part3_len); + } + } + } +} + static struct kunit_case poly1305_test_cases[] = { HASH_KUNIT_CASES, KUNIT_CASE(test_poly1305_allones_keys_and_message), KUNIT_CASE(test_poly1305_reduction_edge_cases), + KUNIT_CASE(test_poly1305_split_update_carry), KUNIT_CASE(benchmark_hash), {}, };