cuda.core: validate IPC buffer import size against mapped extent (Glasswing V2.2)#2224
Merged
Andy-Jost merged 1 commit intoJun 15, 2026
Conversation
Reject peer-supplied IPCBufferDescriptor sizes larger than the driver-reported allocation extent before storing buf._size, preventing oversized cuMemcpyAsync lengths on imported buffers (Glasswing V2.2).
mdboom
approved these changes
Jun 15, 2026
|
Andy-Jost
added a commit
to Andy-Jost/cuda-python
that referenced
this pull request
Jul 8, 2026
Add a Highlights section, backfill PR/issue links on New features entries, and add Bug fixes entries for the v1.1.0 IPC import hardening (NVIDIA#2219, NVIDIA#2223, NVIDIA#2224), the ManagedBuffer.accessed_by torn-state fix (NVIDIA#2222), and graph node attachment lifetimes (NVIDIA#2280). Highlights (per review): the .pyi type-stub support and the new cuda.core.texture module; NVLink enumeration is covered in New features / Bug fixes rather than as a highlight. Also adds a New features entry for the cuda.core.texture module (NVIDIA#467, NVIDIA#2095, NVIDIA#2307).
Andy-Jost
added a commit
to Andy-Jost/cuda-python
that referenced
this pull request
Jul 8, 2026
Add a Highlights section, backfill PR/issue links on New features entries, and add Bug fixes entries for the v1.1.0 IPC import hardening (NVIDIA#2219, NVIDIA#2223, NVIDIA#2224), the ManagedBuffer.accessed_by torn-state fix (NVIDIA#2222), and graph node attachment lifetimes (NVIDIA#2280). Highlights (per review): the .pyi type-stub support and the new cuda.core.texture module; NVLink enumeration is covered in New features / Bug fixes rather than as a highlight. Also adds a New features entry for the cuda.core.texture module (NVIDIA#467, NVIDIA#2095, NVIDIA#2307).
Andy-Jost
added a commit
that referenced
this pull request
Jul 8, 2026
* docs(core): finalize 1.1.0 release notes Add a Highlights section, backfill PR/issue links on New features entries, and add Bug fixes entries for the v1.1.0 IPC import hardening (#2219, #2223, #2224), the ManagedBuffer.accessed_by torn-state fix (#2222), and graph node attachment lifetimes (#2280). Highlights (per review): the .pyi type-stub support and the new cuda.core.texture module; NVLink enumeration is covered in New features / Bug fixes rather than as a highlight. Also adds a New features entry for the cuda.core.texture module (#467, #2095, #2307). * Reorder API refs + ensure each section has currentmodule the compilation toolchain is one of the unique selling points of cuda.core, but we are burying it deeply --------- Co-authored-by: Leo Fang <leof@nvidia.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.
Summary
Addresses Glasswing finding V2.2 (NVBUG 6268889): a peer-supplied
IPCBufferDescriptor.sizewas trusted asbuf._sizeand used as thecuMemcpyAsynclength without checking against the actual mapped allocation extent, enabling an oversized device copy when the receiver imported and copied a forged descriptor.Changes
cuda_core/cuda/core/_memory/_ipc.pyx: afterdeviceptr_import_ipc, queryCU_POINTER_ATTRIBUTE_RANGE_SIZEon the imported pointer and reject descriptors whose advertised size exceeds the mapped extent before callingBuffer_from_deviceptr_handlecuda_core/tests/memory_ipc/test_errors.py:TestImportOversizedBufferDescriptorSize— cross-process harness that forges an oversized size on a valid export payload and asserts import raisesValueErrorTest Coverage
TestImportOversizedBufferDescriptorSize— peer forges oversizedsizeon a valid 64-byte export blob; child import raisesValueError(DeviceMR and PinnedMR parametrizations)Related Work