p2p_api: add construct cleanup/unwind path (Bug 4016670)#1172
Open
fo40225 wants to merge 1 commit into
Open
Conversation
p2papiConstruct_IMPL created the P2P mapping (kbusCreateP2PMapping) but, on any later failure, returned the error WITHOUT removing it - leaking the peer IOMMU mapping and the bus P2P refcount. That leak is what trips the "left-over mappings in IOVAS" (io_vaspace.c) and "Sysmemdesc outlived its attached pGpu" (mem_desc.c) asserts on teardown. Route every post-create failure exit to a single cleanup: label that removes the mapping(s): the EGM mapping create, both kbusGetBar1P2PDmaInfo queries, the SR-IOV _p2papiReservePeerID reservations, the vGPU NV_RM_RPC_ALLOC_OBJECT, both kbusSetupBindFla local/remote binds (and the bare-metal early return between them), refAddDependant, and the alive-refcount overflow checks. On success the label is reached with status == NV_OK and nothing is removed. Mapping removal mirrors p2papiDestruct (FLA bind / RPC object are not reversed there either, so they are not reversed here). Compile-verified on Linux 6.17 + gcc 13.3 (src/nvidia/.../p2p_api.o). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
p2papiConstruct_IMPL created the P2P mapping (kbusCreateP2PMapping) but, on any later failure, returned the error WITHOUT removing it - leaking the peer IOMMU mapping and the bus P2P refcount. That leak is what trips the "left-over mappings in IOVAS" (io_vaspace.c) and "Sysmemdesc outlived its attached pGpu" (mem_desc.c) asserts on teardown.
Route every post-create failure exit to a single cleanup: label that removes the mapping(s): the EGM mapping create, both kbusGetBar1P2PDmaInfo queries, the SR-IOV _p2papiReservePeerID reservations, the vGPU NV_RM_RPC_ALLOC_OBJECT, both kbusSetupBindFla local/remote binds (and the bare-metal early return between them), refAddDependant, and the alive-refcount overflow checks. On success the label is reached with status == NV_OK and nothing is removed. Mapping removal mirrors p2papiDestruct (FLA bind / RPC object are not reversed there either, so they are not reversed here).
Compile-verified on Linux 6.17 + gcc 13.3 (src/nvidia/.../p2p_api.o).