August 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] lib/crypto: arm64/poly1305: Fix register corruption in" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x eec76ea5a7213c48529a46eed1b343e5cee3aaab # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081557-sinless-cleat-22ee@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From eec76ea5a7213c48529a46eed1b343e5cee3aaab Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:58 -0700 Subject: [PATCH] lib/crypto: arm64/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check that was removed by commit a59e5468a921 ("crypto: arm64/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use may_use_simd() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: a59e5468a921 ("crypto: arm64/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-4-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/arm64/poly1305-glue.c b/lib/crypto/arm64/poly1305-glue.c index c9a74766785b..31aea21ce42f 100644 --- a/lib/crypto/arm64/poly1305-glue.c +++ b/lib/crypto/arm64/poly1305-glue.c @@ -7,6 +7,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> +#include <asm/simd.h> #include <crypto/internal/poly1305.h> #include <linux/cpufeature.h> #include <linux/jump_label.h> @@ -33,7 +34,7 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src, unsigned int len, u32 padbit) { len = round_down(len, POLY1305_BLOCK_SIZE); - if (static_branch_likely(&have_neon)) { + if (static_branch_likely(&have_neon) && likely(may_use_simd())) { do { unsigned int todo = min_t(unsigned int, len, SZ_4K);

3 weeks, 5 days

1
0
0 0

FAILED: patch "[PATCH] lib/crypto: arm64/poly1305: Fix register corruption in" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x eec76ea5a7213c48529a46eed1b343e5cee3aaab # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081556-relish-alongside-9c22@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From eec76ea5a7213c48529a46eed1b343e5cee3aaab Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:58 -0700 Subject: [PATCH] lib/crypto: arm64/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check that was removed by commit a59e5468a921 ("crypto: arm64/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use may_use_simd() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: a59e5468a921 ("crypto: arm64/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-4-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/arm64/poly1305-glue.c b/lib/crypto/arm64/poly1305-glue.c index c9a74766785b..31aea21ce42f 100644 --- a/lib/crypto/arm64/poly1305-glue.c +++ b/lib/crypto/arm64/poly1305-glue.c @@ -7,6 +7,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> +#include <asm/simd.h> #include <crypto/internal/poly1305.h> #include <linux/cpufeature.h> #include <linux/jump_label.h> @@ -33,7 +34,7 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src, unsigned int len, u32 padbit) { len = round_down(len, POLY1305_BLOCK_SIZE); - if (static_branch_likely(&have_neon)) { + if (static_branch_likely(&have_neon) && likely(may_use_simd())) { do { unsigned int todo = min_t(unsigned int, len, SZ_4K);

3 weeks, 5 days

1
0
0 0

FAILED: patch "[PATCH] lib/crypto: arm64/poly1305: Fix register corruption in" failed to apply to 6.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.15.y git checkout FETCH_HEAD git cherry-pick -x eec76ea5a7213c48529a46eed1b343e5cee3aaab # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081556-septic-skeleton-d360@gregkh' --subject-prefix 'PATCH 6.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From eec76ea5a7213c48529a46eed1b343e5cee3aaab Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:58 -0700 Subject: [PATCH] lib/crypto: arm64/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check that was removed by commit a59e5468a921 ("crypto: arm64/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use may_use_simd() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: a59e5468a921 ("crypto: arm64/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-4-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/arm64/poly1305-glue.c b/lib/crypto/arm64/poly1305-glue.c index c9a74766785b..31aea21ce42f 100644 --- a/lib/crypto/arm64/poly1305-glue.c +++ b/lib/crypto/arm64/poly1305-glue.c @@ -7,6 +7,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> +#include <asm/simd.h> #include <crypto/internal/poly1305.h> #include <linux/cpufeature.h> #include <linux/jump_label.h> @@ -33,7 +34,7 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src, unsigned int len, u32 padbit) { len = round_down(len, POLY1305_BLOCK_SIZE); - if (static_branch_likely(&have_neon)) { + if (static_branch_likely(&have_neon) && likely(may_use_simd())) { do { unsigned int todo = min_t(unsigned int, len, SZ_4K);

3 weeks, 5 days

1
0
0 0

[PATCH] netfs: Fix unbuffered write error handling

by David Howells

If all the subrequests in an unbuffered write stream fail, the subrequest collector doesn't update the stream->transferred value and it retains its initial LONG_MAX value. Unfortunately, if all active streams fail, then we take the smallest value of { LONG_MAX, LONG_MAX, ... } as the value to set in wreq->transferred - which is then returned from ->write_iter(). LONG_MAX was chosen as the initial value so that all the streams can be quickly assessed by taking the smallest value of all stream->transferred - but this only works if we've set any of them. Fix this by adding a flag to indicate whether the value in stream->transferred is valid and checking that when we integrate the values. stream->transferred can then be initialised to zero. This was found by running the generic/750 xfstest against cifs with cache=none. It splices data to the target file. Once (if) it has used up all the available scratch space, the writes start failing with ENOSPC. This causes ->write_iter() to fail. However, it was returning wreq->transferred, i.e. LONG_MAX, rather than an error (because it thought the amount transferred was non-zero) and iter_file_splice_write() would then try to clean up that amount of pipe bufferage - leading to an oops when it overran. The kernel log showed: CIFS: VFS: Send error in write = -28 followed by: BUG: kernel NULL pointer dereference, address: 0000000000000008 with: RIP: 0010:iter_file_splice_write+0x3a4/0x520 do_splice+0x197/0x4e0 or: RIP: 0010:pipe_buf_release (include/linux/pipe_fs_i.h:282) iter_file_splice_write (fs/splice.c:755) Also put a warning check into splice to announce if ->write_iter() returned that it had written more than it was asked to. Fixes: 288ace2f57c9 ("netfs: New writeback implementation") Reported-by: Xiaoli Feng <fengxiaoli0714(a)gmail.com> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220445 Signed-off-by: David Howells <dhowells(a)redhat.com> cc: Paulo Alcantara <pc(a)manguebit.org> cc: Steve French <sfrench(a)samba.org> cc: Shyam Prasad N <sprasad(a)microsoft.com> cc: netfs(a)lists.linux.dev cc: linux-cifs(a)vger.kernel.org cc: linux-fsdevel(a)vger.kernel.org cc: stable(a)vger.kernel.org --- fs/netfs/read_collect.c | 4 +++- fs/netfs/write_collect.c | 10 ++++++++-- fs/netfs/write_issue.c | 4 ++-- fs/splice.c | 3 +++ include/linux/netfs.h | 1 + 5 files changed, 17 insertions(+), 5 deletions(-) diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3e804da1e1eb..a95e7aadafd0 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -281,8 +281,10 @@ static void netfs_collect_read_results(struct netfs_io_request *rreq) } else if (test_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags)) { notes |= MADE_PROGRESS; } else { - if (!stream->failed) + if (!stream->failed) { stream->transferred += transferred; + stream->transferred_valid = true; + } if (front->transferred < front->len) set_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags); notes |= MADE_PROGRESS; diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 0f3a36852a4d..cbf3d9194c7b 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -254,6 +254,7 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq) if (front->start + front->transferred > stream->collected_to) { stream->collected_to = front->start + front->transferred; stream->transferred = stream->collected_to - wreq->start; + stream->transferred_valid = true; notes |= MADE_PROGRESS; } if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { @@ -356,6 +357,7 @@ bool netfs_write_collection(struct netfs_io_request *wreq) { struct netfs_inode *ictx = netfs_inode(wreq->inode); size_t transferred; + bool transferred_valid = false; int s; _enter("R=%x", wreq->debug_id); @@ -376,12 +378,16 @@ bool netfs_write_collection(struct netfs_io_request *wreq) continue; if (!list_empty(&stream->subrequests)) return false; - if (stream->transferred < transferred) + if (stream->transferred_valid && + stream->transferred < transferred) { transferred = stream->transferred; + transferred_valid = true; + } } /* Okay, declare that all I/O is complete. */ - wreq->transferred = transferred; + if (transferred_valid) + wreq->transferred = transferred; trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); if (wreq->io_streams[1].active && diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 50bee2c4130d..0584cba1a043 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -118,12 +118,12 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, wreq->io_streams[0].prepare_write = ictx->ops->prepare_write; wreq->io_streams[0].issue_write = ictx->ops->issue_write; wreq->io_streams[0].collected_to = start; - wreq->io_streams[0].transferred = LONG_MAX; + wreq->io_streams[0].transferred = 0; wreq->io_streams[1].stream_nr = 1; wreq->io_streams[1].source = NETFS_WRITE_TO_CACHE; wreq->io_streams[1].collected_to = start; - wreq->io_streams[1].transferred = LONG_MAX; + wreq->io_streams[1].transferred = 0; if (fscache_resources_valid(&wreq->cache_resources)) { wreq->io_streams[1].avail = true; wreq->io_streams[1].active = true; diff --git a/fs/splice.c b/fs/splice.c index 4d6df083e0c0..f5094b6d00a0 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -739,6 +739,9 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, sd.pos = kiocb.ki_pos; if (ret <= 0) break; + WARN_ONCE(ret > sd.total_len - left, + "Splice Exceeded! ret=%zd tot=%zu left=%zu\n", + ret, sd.total_len, left); sd.num_spliced += ret; sd.total_len -= ret; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 185bd8196503..98c96d649bf9 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -150,6 +150,7 @@ struct netfs_io_stream { bool active; /* T if stream is active */ bool need_retry; /* T if this stream needs retrying */ bool failed; /* T if this stream failed */ + bool transferred_valid; /* T is ->transferred is valid */ }; /*

3 weeks, 5 days

3
2
0 0

FAILED: patch "[PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081509-octopus-proponent-0409@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:59 -0700 Subject: [PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check and base conversion that were removed by commit 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use irq_fpu_usable() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-5-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/x86/poly1305_glue.c b/lib/crypto/x86/poly1305_glue.c index b7e78a583e07..968d84677631 100644 --- a/lib/crypto/x86/poly1305_glue.c +++ b/lib/crypto/x86/poly1305_glue.c @@ -25,6 +25,42 @@ struct poly1305_arch_internal { struct { u32 r2, r1, r4, r3; } rn[9]; }; +/* + * The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit + * the unfortunate situation of using AVX and then having to go back to scalar + * -- because the user is silly and has called the update function from two + * separate contexts -- then we need to convert back to the original base before + * proceeding. It is possible to reason that the initial reduction below is + * sufficient given the implementation invariants. However, for an avoidance of + * doubt and because this is not performance critical, we do the full reduction + * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py + */ +static void convert_to_base2_64(void *ctx) +{ + struct poly1305_arch_internal *state = ctx; + u32 cy; + + if (!state->is_base2_26) + return; + + cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy; + cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy; + cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy; + cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy; + state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0]; + state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12); + state->hs[2] = state->h[4] >> 24; + /* Unsigned Less Than: branchlessly produces 1 if a < b, else 0. */ +#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1)) + cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL); + state->hs[2] &= 3; + state->hs[0] += cy; + state->hs[1] += (cy = ULT(state->hs[0], cy)); + state->hs[2] += ULT(state->hs[1], cy); +#undef ULT + state->is_base2_26 = 0; +} + asmlinkage void poly1305_block_init_arch( struct poly1305_block_state *state, const u8 raw_key[POLY1305_BLOCK_SIZE]); @@ -62,7 +98,9 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *inp, BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || SZ_4K % POLY1305_BLOCK_SIZE); - if (!static_branch_likely(&poly1305_use_avx)) { + if (!static_branch_likely(&poly1305_use_avx) || + unlikely(!irq_fpu_usable())) { + convert_to_base2_64(ctx); poly1305_blocks_x86_64(ctx, inp, len, padbit); return; }

3 weeks, 5 days

1
0
0 0

FAILED: patch "[PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081508-handcart-oversweet-f21e@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:59 -0700 Subject: [PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check and base conversion that were removed by commit 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use irq_fpu_usable() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-5-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/x86/poly1305_glue.c b/lib/crypto/x86/poly1305_glue.c index b7e78a583e07..968d84677631 100644 --- a/lib/crypto/x86/poly1305_glue.c +++ b/lib/crypto/x86/poly1305_glue.c @@ -25,6 +25,42 @@ struct poly1305_arch_internal { struct { u32 r2, r1, r4, r3; } rn[9]; }; +/* + * The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit + * the unfortunate situation of using AVX and then having to go back to scalar + * -- because the user is silly and has called the update function from two + * separate contexts -- then we need to convert back to the original base before + * proceeding. It is possible to reason that the initial reduction below is + * sufficient given the implementation invariants. However, for an avoidance of + * doubt and because this is not performance critical, we do the full reduction + * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py + */ +static void convert_to_base2_64(void *ctx) +{ + struct poly1305_arch_internal *state = ctx; + u32 cy; + + if (!state->is_base2_26) + return; + + cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy; + cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy; + cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy; + cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy; + state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0]; + state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12); + state->hs[2] = state->h[4] >> 24; + /* Unsigned Less Than: branchlessly produces 1 if a < b, else 0. */ +#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1)) + cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL); + state->hs[2] &= 3; + state->hs[0] += cy; + state->hs[1] += (cy = ULT(state->hs[0], cy)); + state->hs[2] += ULT(state->hs[1], cy); +#undef ULT + state->is_base2_26 = 0; +} + asmlinkage void poly1305_block_init_arch( struct poly1305_block_state *state, const u8 raw_key[POLY1305_BLOCK_SIZE]); @@ -62,7 +98,9 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *inp, BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || SZ_4K % POLY1305_BLOCK_SIZE); - if (!static_branch_likely(&poly1305_use_avx)) { + if (!static_branch_likely(&poly1305_use_avx) || + unlikely(!irq_fpu_usable())) { + convert_to_base2_64(ctx); poly1305_blocks_x86_64(ctx, inp, len, padbit); return; }

3 weeks, 5 days

1
0
0 0

FAILED: patch "[PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081508-pelt-scouting-b79c@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:59 -0700 Subject: [PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check and base conversion that were removed by commit 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use irq_fpu_usable() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-5-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/x86/poly1305_glue.c b/lib/crypto/x86/poly1305_glue.c index b7e78a583e07..968d84677631 100644 --- a/lib/crypto/x86/poly1305_glue.c +++ b/lib/crypto/x86/poly1305_glue.c @@ -25,6 +25,42 @@ struct poly1305_arch_internal { struct { u32 r2, r1, r4, r3; } rn[9]; }; +/* + * The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit + * the unfortunate situation of using AVX and then having to go back to scalar + * -- because the user is silly and has called the update function from two + * separate contexts -- then we need to convert back to the original base before + * proceeding. It is possible to reason that the initial reduction below is + * sufficient given the implementation invariants. However, for an avoidance of + * doubt and because this is not performance critical, we do the full reduction + * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py + */ +static void convert_to_base2_64(void *ctx) +{ + struct poly1305_arch_internal *state = ctx; + u32 cy; + + if (!state->is_base2_26) + return; + + cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy; + cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy; + cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy; + cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy; + state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0]; + state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12); + state->hs[2] = state->h[4] >> 24; + /* Unsigned Less Than: branchlessly produces 1 if a < b, else 0. */ +#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1)) + cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL); + state->hs[2] &= 3; + state->hs[0] += cy; + state->hs[1] += (cy = ULT(state->hs[0], cy)); + state->hs[2] += ULT(state->hs[1], cy); +#undef ULT + state->is_base2_26 = 0; +} + asmlinkage void poly1305_block_init_arch( struct poly1305_block_state *state, const u8 raw_key[POLY1305_BLOCK_SIZE]); @@ -62,7 +98,9 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *inp, BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || SZ_4K % POLY1305_BLOCK_SIZE); - if (!static_branch_likely(&poly1305_use_avx)) { + if (!static_branch_likely(&poly1305_use_avx) || + unlikely(!irq_fpu_usable())) { + convert_to_base2_64(ctx); poly1305_blocks_x86_64(ctx, inp, len, padbit); return; }

3 weeks, 5 days

1
0
0 0

FAILED: patch "[PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081507-raking-viewless-4b7d@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:59 -0700 Subject: [PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check and base conversion that were removed by commit 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use irq_fpu_usable() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-5-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/x86/poly1305_glue.c b/lib/crypto/x86/poly1305_glue.c index b7e78a583e07..968d84677631 100644 --- a/lib/crypto/x86/poly1305_glue.c +++ b/lib/crypto/x86/poly1305_glue.c @@ -25,6 +25,42 @@ struct poly1305_arch_internal { struct { u32 r2, r1, r4, r3; } rn[9]; }; +/* + * The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit + * the unfortunate situation of using AVX and then having to go back to scalar + * -- because the user is silly and has called the update function from two + * separate contexts -- then we need to convert back to the original base before + * proceeding. It is possible to reason that the initial reduction below is + * sufficient given the implementation invariants. However, for an avoidance of + * doubt and because this is not performance critical, we do the full reduction + * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py + */ +static void convert_to_base2_64(void *ctx) +{ + struct poly1305_arch_internal *state = ctx; + u32 cy; + + if (!state->is_base2_26) + return; + + cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy; + cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy; + cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy; + cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy; + state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0]; + state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12); + state->hs[2] = state->h[4] >> 24; + /* Unsigned Less Than: branchlessly produces 1 if a < b, else 0. */ +#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1)) + cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL); + state->hs[2] &= 3; + state->hs[0] += cy; + state->hs[1] += (cy = ULT(state->hs[0], cy)); + state->hs[2] += ULT(state->hs[1], cy); +#undef ULT + state->is_base2_26 = 0; +} + asmlinkage void poly1305_block_init_arch( struct poly1305_block_state *state, const u8 raw_key[POLY1305_BLOCK_SIZE]); @@ -62,7 +98,9 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *inp, BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || SZ_4K % POLY1305_BLOCK_SIZE); - if (!static_branch_likely(&poly1305_use_avx)) { + if (!static_branch_likely(&poly1305_use_avx) || + unlikely(!irq_fpu_usable())) { + convert_to_base2_64(ctx); poly1305_blocks_x86_64(ctx, inp, len, padbit); return; }

3 weeks, 5 days

1
0
0 0

FAILED: patch "[PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081507-verse-prozac-3c44@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:59 -0700 Subject: [PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check and base conversion that were removed by commit 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use irq_fpu_usable() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-5-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/x86/poly1305_glue.c b/lib/crypto/x86/poly1305_glue.c index b7e78a583e07..968d84677631 100644 --- a/lib/crypto/x86/poly1305_glue.c +++ b/lib/crypto/x86/poly1305_glue.c @@ -25,6 +25,42 @@ struct poly1305_arch_internal { struct { u32 r2, r1, r4, r3; } rn[9]; }; +/* + * The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit + * the unfortunate situation of using AVX and then having to go back to scalar + * -- because the user is silly and has called the update function from two + * separate contexts -- then we need to convert back to the original base before + * proceeding. It is possible to reason that the initial reduction below is + * sufficient given the implementation invariants. However, for an avoidance of + * doubt and because this is not performance critical, we do the full reduction + * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py + */ +static void convert_to_base2_64(void *ctx) +{ + struct poly1305_arch_internal *state = ctx; + u32 cy; + + if (!state->is_base2_26) + return; + + cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy; + cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy; + cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy; + cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy; + state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0]; + state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12); + state->hs[2] = state->h[4] >> 24; + /* Unsigned Less Than: branchlessly produces 1 if a < b, else 0. */ +#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1)) + cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL); + state->hs[2] &= 3; + state->hs[0] += cy; + state->hs[1] += (cy = ULT(state->hs[0], cy)); + state->hs[2] += ULT(state->hs[1], cy); +#undef ULT + state->is_base2_26 = 0; +} + asmlinkage void poly1305_block_init_arch( struct poly1305_block_state *state, const u8 raw_key[POLY1305_BLOCK_SIZE]); @@ -62,7 +98,9 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *inp, BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || SZ_4K % POLY1305_BLOCK_SIZE); - if (!static_branch_likely(&poly1305_use_avx)) { + if (!static_branch_likely(&poly1305_use_avx) || + unlikely(!irq_fpu_usable())) { + convert_to_base2_64(ctx); poly1305_blocks_x86_64(ctx, inp, len, padbit); return; }

3 weeks, 5 days

1
0
0 0

FAILED: patch "[PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD" failed to apply to 6.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.15.y git checkout FETCH_HEAD git cherry-pick -x 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081506-washable-climatic-2c7b@gregkh' --subject-prefix 'PATCH 6.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 16f2c30e290e04135b70ad374fb7e1d1ed9ff5e7 Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)kernel.org> Date: Sun, 6 Jul 2025 16:10:59 -0700 Subject: [PATCH] lib/crypto: x86/poly1305: Fix register corruption in no-SIMD contexts Restore the SIMD usability check and base conversion that were removed by commit 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface"). This safety check is cheap and is well worth eliminating a footgun. While the Poly1305 functions should not be called when SIMD registers are unusable, if they are anyway, they should just do the right thing instead of corrupting random tasks' registers and/or computing incorrect MACs. Fixing this is also needed for poly1305_kunit to pass. Just use irq_fpu_usable() instead of the original crypto_simd_usable(), since poly1305_kunit won't rely on crypto_simd_disabled_for_test. Fixes: 318c53ae02f2 ("crypto: x86/poly1305 - Add block-only interface") Cc: stable(a)vger.kernel.org Reviewed-by: Ard Biesheuvel <ardb(a)kernel.org> Link: https://lore.kernel.org/r/20250706231100.176113-5-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers(a)kernel.org> diff --git a/lib/crypto/x86/poly1305_glue.c b/lib/crypto/x86/poly1305_glue.c index b7e78a583e07..968d84677631 100644 --- a/lib/crypto/x86/poly1305_glue.c +++ b/lib/crypto/x86/poly1305_glue.c @@ -25,6 +25,42 @@ struct poly1305_arch_internal { struct { u32 r2, r1, r4, r3; } rn[9]; }; +/* + * The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit + * the unfortunate situation of using AVX and then having to go back to scalar + * -- because the user is silly and has called the update function from two + * separate contexts -- then we need to convert back to the original base before + * proceeding. It is possible to reason that the initial reduction below is + * sufficient given the implementation invariants. However, for an avoidance of + * doubt and because this is not performance critical, we do the full reduction + * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py + */ +static void convert_to_base2_64(void *ctx) +{ + struct poly1305_arch_internal *state = ctx; + u32 cy; + + if (!state->is_base2_26) + return; + + cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy; + cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy; + cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy; + cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy; + state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0]; + state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12); + state->hs[2] = state->h[4] >> 24; + /* Unsigned Less Than: branchlessly produces 1 if a < b, else 0. */ +#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1)) + cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL); + state->hs[2] &= 3; + state->hs[0] += cy; + state->hs[1] += (cy = ULT(state->hs[0], cy)); + state->hs[2] += ULT(state->hs[1], cy); +#undef ULT + state->is_base2_26 = 0; +} + asmlinkage void poly1305_block_init_arch( struct poly1305_block_state *state, const u8 raw_key[POLY1305_BLOCK_SIZE]); @@ -62,7 +98,9 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *inp, BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || SZ_4K % POLY1305_BLOCK_SIZE); - if (!static_branch_likely(&poly1305_use_avx)) { + if (!static_branch_likely(&poly1305_use_avx) || + unlikely(!irq_fpu_usable())) { + convert_to_base2_64(ctx); poly1305_blocks_x86_64(ctx, inp, len, padbit); return; }

3 weeks, 5 days

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2025