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 (cherry picked from commit 1a80dbcb2dbaf6e4c216e62e30fa7d3daa8001ce) --- include/linux/bpf.h | 16 +++++++++++++++- kernel/bpf/syscall.c | 35 ++++++++++++++++++++++++++++++++--- kernel/trace/bpf_trace.c | 4 ++-- 3 files changed, 49 insertions(+), 6 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e30100597d0a..7d719976b564 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1568,12 +1568,26 @@ 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); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a1f18681721c..0f90b6b27430 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2895,17 +2895,46 @@ void bpf_link_inc(struct bpf_link *link) atomic64_inc(&link->refcnt); }
+static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) +{ + struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); + + /* free bpf_link and its containing memory */ + link->ops->dealloc_deferred(link); +} + +static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_link_defer_dealloc_rcu_gp(rcu); + else + call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp); +} + /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { + bool sleepable = false; + bpf_link_free_id(link->id); if (link->prog) { + sleepable = link->prog->aux->sleepable; /* detach BPF program, clean up used resources */ link->ops->release(link); bpf_prog_put(link->prog); } - /* free bpf_link and its containing memory */ - link->ops->dealloc(link); + if (link->ops->dealloc_deferred) { + /* schedule BPF link deallocation; if underlying BPF program + * is sleepable, we need to first wait for RCU tasks trace + * sync, then go through "classic" RCU grace period + */ + if (sleepable) + call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); + else + call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); + } + if (link->ops->dealloc) + link->ops->dealloc(link); }
static void bpf_link_put_deferred(struct work_struct *work) @@ -3415,7 +3444,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, - .dealloc = bpf_raw_tp_link_dealloc, + .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 45de8a4923e2..c8d1ebc43838 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2713,7 +2713,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .release = bpf_kprobe_multi_link_release, - .dealloc = bpf_kprobe_multi_link_dealloc, + .dealloc_deferred = bpf_kprobe_multi_link_dealloc, .fill_link_info = bpf_kprobe_multi_link_fill_link_info, };
@@ -3227,7 +3227,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_uprobe_multi_link_lops = { .release = bpf_uprobe_multi_link_release, - .dealloc = bpf_uprobe_multi_link_dealloc, + .dealloc_deferred = bpf_uprobe_multi_link_dealloc, .fill_link_info = bpf_uprobe_multi_link_fill_link_info, };