[llm_patch] Fix out-of-bounds access in pad2d function #15832
Merged
Conversation
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
#15623 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15832
Note: Links to docs will display an error until the docs builds have been completed. ❌ 6 New Failures, 2 Unrelated FailuresAs of commit e3ec533 with merge base b1e3e28 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
lucylq
added a commit
that referenced
this pull request
Nov 14, 2025
#15623 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/) ghstack-source-id: 323425010 Pull Request resolved: #15832
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
#15623 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Nov 14, 2025
Pull Request resolved: #15832 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/) ghstack-source-id: 323440692
manuelcandales
approved these changes
Nov 15, 2025
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds bounds checking to prevent out-of-bounds memory access in the pad1d, pad2d, and pad3d utility functions. The fix addresses a "wild-addr-read" crash by verifying that computed indices from the padding functions are within valid bounds before accessing the input tensor.
- Adds
ET_CHECKassertions to validate that computed indices are within the input tensor dimensions - Refactors index calculation to compute padding indices once before validation
- Applies the fix consistently across all three padding dimension functions (1D, 2D, and 3D)
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
#15623 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Nov 17, 2025
Pull Request resolved: #15832 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). ghstack-source-id: 323807151 Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/)
#15623 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Nov 17, 2025
Pull Request resolved: #15832 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). ghstack-source-id: 323816192 Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/)
Copilot finished reviewing on behalf of
mergennachin
November 17, 2025 19:28
Contributor
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 1 out of 1 changed files in this pull request and generated 5 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
#15623 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/) [ghstack-poisoned]
lucylq
added a commit
that referenced
this pull request
Nov 17, 2025
Pull Request resolved: #15832 Add checks for pad1d and pad3d, as well as pad2d. I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection). The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds. --- The crash is a "wild-addr-read" that occurs in the `pad2d` function, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address. The root cause of the crash is an out-of-bounds access in the `pad2d` function. The function uses a `padding_ix` function to calculate indices for the input tensor `in`, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of the `in` tensor, leading to the crash. The patch fixes the crash by adding bounds checking to the `pad2d` function. Specifically, it adds two `ET_CHECK` statements to verify that the indices calculated by `padding_ix` are within the valid range of the `in` tensor. The checks are performed using the following code: `ET_CHECK(in_h_idx < in_height)` and `ET_CHECK(in_w_idx < in_width)`. By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash. Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added `ET_CHECK` statements may introduce a small performance overhead, particularly if the `pad2d` function is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that the `ET_CHECK` statements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases. NOTE: This diff is entirely auto-generated by LLM-based patch generator. Reviewer should carefully examine this diff as Lionhead does not guarrantee the correctnesss of the patch beyond fixing the crash and passing existing tests. Please commandeer this diff and revise as needed. Our bot does not respond to comments or revision requests (yet). ghstack-source-id: 323827123 Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/)
Copilot finished reviewing on behalf of
mergennachin
November 17, 2025 22:54
Contributor
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
mergennachin
approved these changes
Nov 17, 2025
lucylq
had a problem deploying
to
cherry-pick-bot
GitHub Actions
Failure
lucylq
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
mergennachin
pushed a commit
that referenced
this pull request
Nov 18, 2025
This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #15832 by @lucylq ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/lucylq/128/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/lucylq/128/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/lucylq/128/orig Differential Revision: [D80831697](https://our.internmc.facebook.com/intern/diff/D80831697/) @diff-train-skip-merge Co-authored-by: lucylq <lfq@meta.com>
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.
Stack from ghstack (oldest at bottom):
#15623
Add checks for pad1d and pad3d, as well as pad2d.
I think what happens is, we 'broadcast' the input tensor into the padded regions, depending on the pad algorithm (replication, reflection).
The pad algorithm takes an output tensor index, and returns an input tensor index. We need to check that this input tensor index is valid/within bounds.
The crash is a "wild-addr-read" that occurs in the
pad2dfunction, which is part of the Executorch library. This type of crash typically indicates that the program is attempting to read from an invalid or uninitialized memory address.The root cause of the crash is an out-of-bounds access in the
pad2dfunction. The function uses apadding_ixfunction to calculate indices for the input tensorin, but it does not perform sufficient bounds checking to ensure that these indices are valid. As a result, the program may attempt to read from memory outside the bounds of theintensor, leading to the crash.The patch fixes the crash by adding bounds checking to the
pad2dfunction. Specifically, it adds twoET_CHECKstatements to verify that the indices calculated bypadding_ixare within the valid range of theintensor. The checks are performed using the following code:ET_CHECK(in_h_idx < in_height)andET_CHECK(in_w_idx < in_width). By adding these checks, the patch ensures that the program will not attempt to read from invalid memory addresses, preventing the "wild-addr-read" crash.Other considerations that reviewers should take into account when validating the patch include the potential impact on performance. The added
ET_CHECKstatements may introduce a small performance overhead, particularly if thepad2dfunction is called frequently. Reviewers should verify that the performance impact is acceptable and that the patch does not introduce any other unintended consequences. Additionally, reviewers should test the patch with a variety of input tensors and padding configurations to ensure that it correctly handles different edge cases. They should also verify that theET_CHECKstatements are triggered correctly when invalid indices are encountered, and that the program behaves as expected in these cases.NOTE: This diff is entirely auto-generated by LLM-based patch generator.
Reviewer should carefully examine this diff as Lionhead does not guarrantee the
correctnesss of the patch beyond fixing the crash and passing existing tests.
Please commandeer this diff and revise as needed. Our bot does not respond to
comments or revision requests (yet).
Differential Revision: D80831697