summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorAndrii Nakryiko <andrii@kernel.org>2024-03-28 08:24:26 +0300
committerAlexei Starovoitov <ast@kernel.org>2024-03-29 04:47:45 +0300
commit1a80dbcb2dbaf6e4c216e62e30fa7d3daa8001ce (patch)
tree7276f8f65e83ccafdc154e29f5db8bc9821272f1 /include
parente9c856cabefb71d47b2eeb197f72c9c88e9b45b0 (diff)
downloadlinux-1a80dbcb2dbaf6e4c216e62e30fa7d3daa8001ce.tar.xz
bpf: support deferring bpf_link dealloc to after RCU grace period
BPF link for some program types is passed as a "context" which can be used by those BPF programs to look up additional information. E.g., for multi-kprobes and multi-uprobes, link is used to fetch BPF cookie values. Because of this runtime dependency, when bpf_link refcnt drops to zero there could still be active BPF programs running accessing link data. This patch adds generic support to defer bpf_link dealloc callback to after RCU GP, if requested. This is done by exposing two different deallocation callbacks, one synchronous and one deferred. If deferred one is provided, bpf_link_free() will schedule dealloc_deferred() callback to happen after RCU GP. BPF is using two flavors of RCU: "classic" non-sleepable one and RCU tasks trace one. The latter is used when sleepable BPF programs are used. bpf_link_free() accommodates that by checking underlying BPF program's sleepable flag, and goes either through normal RCU GP only for non-sleepable, or through RCU tasks trace GP *and* then normal RCU GP (taking into account rcu_trace_implies_rcu_gp() optimization), if BPF program is sleepable. We use this for multi-kprobe and multi-uprobe links, which dereference link during program run. We also preventively switch raw_tp link to use deferred dealloc callback, as upcoming changes in bpf-next tree expose raw_tp link data (specifically, cookie value) to BPF program at runtime as well. Fixes: 0dcac2725406 ("bpf: Add multi kprobe link") Fixes: 89ae89f53d20 ("bpf: Add multi uprobe link") Reported-by: syzbot+981935d9485a560bfbcb@syzkaller.appspotmail.com Reported-by: syzbot+2cb5a6c573e98db598cc@syzkaller.appspotmail.com Reported-by: syzbot+62d8b26793e8a2bd0516@syzkaller.appspotmail.com Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20240328052426.3042617-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/bpf.h16
1 files changed, 15 insertions, 1 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4f20f62f9d63..890e152d553e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1574,12 +1574,26 @@ struct bpf_link {
enum bpf_link_type type;
const struct bpf_link_ops *ops;
struct bpf_prog *prog;
- struct work_struct work;
+ /* rcu is used before freeing, work can be used to schedule that
+ * RCU-based freeing before that, so they never overlap
+ */
+ union {
+ struct rcu_head rcu;
+ struct work_struct work;
+ };
};
struct bpf_link_ops {
void (*release)(struct bpf_link *link);
+ /* deallocate link resources callback, called without RCU grace period
+ * waiting
+ */
void (*dealloc)(struct bpf_link *link);
+ /* deallocate link resources callback, called after RCU grace period;
+ * if underlying BPF program is sleepable we go through tasks trace
+ * RCU GP and then "classic" RCU GP
+ */
+ void (*dealloc_deferred)(struct bpf_link *link);
int (*detach)(struct bpf_link *link);
int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
struct bpf_prog *old_prog);