bpf: Avoid hashtab deadlock with map_locked

Browse source

If a hashtab is accessed in both non-NMI and NMI context, the system may
deadlock on bucket->lock. Fix this issue with percpu counter map_locked.
map_locked rejects concurrent access to the same bucket from the same CPU.
To reduce memory overhead, map_locked is not added per bucket. Instead,
8 percpu counters are added to each hashtab. buckets are assigned to these
counters based on the lower bits of its hash.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201029071925.3103400-3-songliubraving@fb.com

...

This commit is contained in:

Song Liu 2020-10-29 00:19:25 -07:00 • committed by Alexei Starovoitov

parent c50eb518e2

commit 20b6cc34ea

1 changed files with 82 additions and 32 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

114

kernel/bpf/hashtab.c

View file