Copy input in json_parse to avoid ASAN error #7858
Closed
Conversation
This file contains 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
✅ Deploy Preview for meta-velox canceled.
|
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D51810542 |
Yuhta
force-pushed
the
export-D51810542
branch
from
7d877c8 to
28a033c
Compare
Yuhta
added a commit
to Yuhta/velox
that referenced
this pull request
Dec 5, 2023
Summary: `value` is put on offset 32 of the stack frame, and the total frame size is 88. In case `value` is inlined, and SIMD register is 64 bytes (e.g. AVX512), simdjson is reading the memory from offset 36 to 100, which exceeds the frame boundary. This caused some ASAN error, but no issue in production, because the padding data is not really used or changed. Fix it by asking `simdjson::dom::parser::parse` to copy the input to internal padded memory owned by parser. There is some minor performance loss but is probably not noticeable at query level. Reviewed By: mbasmanova Differential Revision: D51810542
|
This pull request was exported from Phabricator. Differential Revision: D51810542 |
Yuhta
added a commit
to Yuhta/velox
that referenced
this pull request
Dec 5, 2023
Summary: `value` is put on offset 32 of the stack frame, and the total frame size is 88. In case `value` is inlined, and SIMD register is 64 bytes (e.g. AVX512), simdjson is reading the memory from offset 36 to 100, which exceeds the frame boundary. This caused some ASAN error, but no issue in production, because the padding data is not really used or changed. Fix it by asking `simdjson::dom::parser::parse` to copy the input to internal padded memory owned by parser. There is some minor performance loss but is probably not noticeable at query level. Reviewed By: mbasmanova Differential Revision: D51810542
Yuhta
force-pushed
the
export-D51810542
branch
from
28a033c to
1e2258a
Compare
|
This pull request was exported from Phabricator. Differential Revision: D51810542 |
Yuhta
added a commit
to Yuhta/velox
that referenced
this pull request
Dec 5, 2023
Summary: `value` is put on offset 32 of the stack frame, and the total frame size is 88. In case `value` is inlined, and SIMD register is 64 bytes (e.g. AVX512), simdjson is reading the memory from offset 36 to 100, which exceeds the frame boundary. This caused some ASAN error, but no issue in production, because the padding data is not really used or changed. Fix it by asking `simdjson::dom::parser::parse` to copy the input to internal padded memory owned by parser. There is some minor performance loss but is probably not noticeable at query level. Reviewed By: mbasmanova Differential Revision: D51810542
Yuhta
force-pushed
the
export-D51810542
branch
from
1e2258a to
debc39e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D51810542 |
Yuhta
added a commit
to Yuhta/velox
that referenced
this pull request
Dec 5, 2023
Summary: `value` is put on offset 32 of the stack frame, and the total frame size is 88. In case `value` is inlined, and SIMD register is 64 bytes (e.g. AVX512), simdjson is reading the memory from offset 36 to 100, which exceeds the frame boundary. This caused some ASAN error, but no issue in production, because the padding data is not really used or changed. Fix it by asking `simdjson::dom::parser::parse` to copy the input to internal padded memory owned by parser. There is some minor performance loss but is probably not noticeable at query level. Reviewed By: mbasmanova Differential Revision: D51810542
Yuhta
force-pushed
the
export-D51810542
branch
from
debc39e to
620c940
Compare
|
This pull request was exported from Phabricator. Differential Revision: D51810542 |
Summary: `value` is put on offset 32 of the stack frame, and the total frame size is 88. In case `value` is inlined, and SIMD register is 64 bytes (e.g. AVX512), simdjson is reading the memory from offset 36 to 100, which exceeds the frame boundary. This caused some ASAN error, but no issue in production, because the padding data is not really used or changed. Fix it by asking `simdjson::dom::parser::parse` to copy the input to internal padded memory owned by parser. There is some minor performance loss but is probably not noticeable at query level. Reviewed By: mbasmanova Differential Revision: D51810542
Yuhta
force-pushed
the
export-D51810542
branch
from
620c940 to
8ff7f21
Compare
|
This pull request was exported from Phabricator. Differential Revision: D51810542 |
|
This pull request has been merged in 928f378. |
|
Conbench analyzed the 1 benchmark run on commit There were no benchmark performance regressions. 🎉 The full Conbench report has more details. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary:
valueis put on offset 32 of the stack frame, and the total frame size is 88. In casevalueis inlined, and SIMD register is 64 bytes (e.g. AVX512), simdjson is reading the memory from offset 36 to 100, which exceeds the frame boundary.This caused some ASAN error, but no issue in production, because the padding data is not really used or changed.
Differential Revision: D51810542