bpf: Fix mmap_lock deadlock in VMA iterators using per-VMA locks #10633
+132
−123
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
BPF VMA iterators and bpf_find_vma() hold mmap_lock, which deadlocks when BPF programs call bpf_copy_from_user_task() on the same task (recursive lock acquisition). Holding per-VMA locks during BPF execution also deadlocks due to circular locking: kernel has mmap_lock → vm_lock dependency (vma_expand), our code creates vm_lock → mmap_lock (callback → bpf_copy_from_user_task). Solution: Use per-VMA locks to validate VMAs are stable, then release vm_lock BEFORE returning to BPF or calling callbacks. VMA structures remain RCU-protected during BPF execution. Trade-off: VMA fields may be stale between lock release and BPF access. This is acceptable for tracing/profiling use cases. Signed-off-by: Paul Jia <pjy@meta.com>
kernel-patches-daemon-bpf
bot
force-pushed
the
bpf-next_base
branch
3 times, most recently
from
e7b5368 to
1e194b1
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
BPF VMA iterators and bpf_find_vma() hold mmap_lock, which deadlocks when BPF programs call bpf_copy_from_user_task() on the same task (recursive lock acquisition).
Holding per-VMA locks during BPF execution also deadlocks due to circular locking: kernel has mmap_lock → vm_lock dependency (vma_expand), our code creates vm_lock → mmap_lock (callback → bpf_copy_from_user_task).
Solution: Use per-VMA locks to validate VMAs are stable, then release vm_lock BEFORE returning to BPF or calling callbacks. VMA structures remain RCU-protected during BPF execution.
Trade-off: VMA fields may be stale between lock release and BPF access. This is acceptable for tracing/profiling use cases.