fix(simd): NEON vfloat4::load(values,n) read past the end of the buffer - #5404
Merged
lgritz merged 1 commit intoAug 16, 2026
Merged
Conversation
The NEON branch loaded all 4 lanes with vld1q_f32 and then zeroed the ones it didn't want, so a partial load of n<4 elements read up to 12 bytes past the caller's buffer. ASan flags it as a heap-buffer-overflow of size 16. The SSE branch gets this right by switching on n before loading. Within OIIO the over-read has been harmless, because imagebuf.cpp and imagecache.cpp deliberately pad their allocations by OIIO_SIMD_MAX_SIZE_BYTES to permit exactly this. But simd.h is a public header, and a downstream caller has no reason to expect a 4-element load to touch 16 bytes. Also, n==0 fell through to `default:` after the load without zeroing anything, returning the over-read garbage instead of zeros. Assisted-by: Claude Code / claude-opus-5 Signed-off-by: Larry Gritz <lg@larrygritz.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The NEON branch loaded all 4 lanes with vld1q_f32 and then zeroed the ones it didn't want, so a partial load of n<4 elements read up to 12 bytes past the caller's buffer. ASan flags it as a heap-buffer-overflow of size 16. The SSE branch gets this right by switching on n before loading.
Within OIIO the over-read has been harmless, because imagebuf.cpp and imagecache.cpp deliberately pad their allocations by OIIO_SIMD_MAX_SIZE_BYTES to permit exactly this. But simd.h is a public header, and a downstream caller has no reason to expect a 4-element load to touch 16 bytes.
Also, n==0 fell through to
default:after the load without zeroing anything, returning the over-read garbage instead of zeros.Assisted-by: Claude Code / claude-opus-5