Re: [PATCH tip] perf/events/core: fix race in bpf program unregister
On Tue, May 19, 2015 at 10:27:05PM -0700, Alexei Starovoitov wrote: > On 5/15/15 12:15 PM, Alexei Starovoitov wrote: > >there is a race between perf_event_free_bpf_prog() and free_trace_kprobe(): > > > >__free_event() > > event->destroy(event) > > tp_perf_event_destroy() > > perf_trace_destroy() > > perf_trace_event_unreg() > > > >which is dropping event->tp_event->perf_refcount and allows to proceed in: > > > >unregister_trace_kprobe() > > unregister_kprobe_event() > > trace_remove_event_call() > > probe_remove_event_call() > >free_trace_kprobe() > > > >while __free_event does: > >call_rcu(>rcu_head, free_event_rcu); > > free_event_rcu() > > perf_event_free_bpf_prog() > > > >To fix the race simply move perf_event_free_bpf_prog() before > >event->destroy(), since event->tp_event is still valid at that point. > > > >Note, perf_trace_destroy() is not racing with trace_remove_event_call() > >since they both grab event_mutex. > > > >Fixes: 2541517c32be ("tracing, perf: Implement BPF programs attached to > >kprobes") > >Reported-by: Wang Nan > >Signed-off-by: Alexei Starovoitov > > ping. > This is needed in 4.1. Thanks, queued for perf/urgent. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH tip] perf/events/core: fix race in bpf program unregister
On Tue, May 19, 2015 at 10:27:05PM -0700, Alexei Starovoitov wrote: On 5/15/15 12:15 PM, Alexei Starovoitov wrote: there is a race between perf_event_free_bpf_prog() and free_trace_kprobe(): __free_event() event-destroy(event) tp_perf_event_destroy() perf_trace_destroy() perf_trace_event_unreg() which is dropping event-tp_event-perf_refcount and allows to proceed in: unregister_trace_kprobe() unregister_kprobe_event() trace_remove_event_call() probe_remove_event_call() free_trace_kprobe() while __free_event does: call_rcu(event-rcu_head, free_event_rcu); free_event_rcu() perf_event_free_bpf_prog() To fix the race simply move perf_event_free_bpf_prog() before event-destroy(), since event-tp_event is still valid at that point. Note, perf_trace_destroy() is not racing with trace_remove_event_call() since they both grab event_mutex. Fixes: 2541517c32be (tracing, perf: Implement BPF programs attached to kprobes) Reported-by: Wang Nan wangn...@huawei.com Signed-off-by: Alexei Starovoitov a...@plumgrid.com ping. This is needed in 4.1. Thanks, queued for perf/urgent. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH tip] perf/events/core: fix race in bpf program unregister
On 5/15/15 12:15 PM, Alexei Starovoitov wrote: there is a race between perf_event_free_bpf_prog() and free_trace_kprobe(): __free_event() event->destroy(event) tp_perf_event_destroy() perf_trace_destroy() perf_trace_event_unreg() which is dropping event->tp_event->perf_refcount and allows to proceed in: unregister_trace_kprobe() unregister_kprobe_event() trace_remove_event_call() probe_remove_event_call() free_trace_kprobe() while __free_event does: call_rcu(>rcu_head, free_event_rcu); free_event_rcu() perf_event_free_bpf_prog() To fix the race simply move perf_event_free_bpf_prog() before event->destroy(), since event->tp_event is still valid at that point. Note, perf_trace_destroy() is not racing with trace_remove_event_call() since they both grab event_mutex. Fixes: 2541517c32be ("tracing, perf: Implement BPF programs attached to kprobes") Reported-by: Wang Nan Signed-off-by: Alexei Starovoitov ping. This is needed in 4.1. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH tip] perf/events/core: fix race in bpf program unregister
On 5/15/15 12:15 PM, Alexei Starovoitov wrote: there is a race between perf_event_free_bpf_prog() and free_trace_kprobe(): __free_event() event-destroy(event) tp_perf_event_destroy() perf_trace_destroy() perf_trace_event_unreg() which is dropping event-tp_event-perf_refcount and allows to proceed in: unregister_trace_kprobe() unregister_kprobe_event() trace_remove_event_call() probe_remove_event_call() free_trace_kprobe() while __free_event does: call_rcu(event-rcu_head, free_event_rcu); free_event_rcu() perf_event_free_bpf_prog() To fix the race simply move perf_event_free_bpf_prog() before event-destroy(), since event-tp_event is still valid at that point. Note, perf_trace_destroy() is not racing with trace_remove_event_call() since they both grab event_mutex. Fixes: 2541517c32be (tracing, perf: Implement BPF programs attached to kprobes) Reported-by: Wang Nan wangn...@huawei.com Signed-off-by: Alexei Starovoitov a...@plumgrid.com ping. This is needed in 4.1. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[PATCH tip] perf/events/core: fix race in bpf program unregister
there is a race between perf_event_free_bpf_prog() and free_trace_kprobe(): __free_event() event->destroy(event) tp_perf_event_destroy() perf_trace_destroy() perf_trace_event_unreg() which is dropping event->tp_event->perf_refcount and allows to proceed in: unregister_trace_kprobe() unregister_kprobe_event() trace_remove_event_call() probe_remove_event_call() free_trace_kprobe() while __free_event does: call_rcu(>rcu_head, free_event_rcu); free_event_rcu() perf_event_free_bpf_prog() To fix the race simply move perf_event_free_bpf_prog() before event->destroy(), since event->tp_event is still valid at that point. Note, perf_trace_destroy() is not racing with trace_remove_event_call() since they both grab event_mutex. Fixes: 2541517c32be ("tracing, perf: Implement BPF programs attached to kprobes") Reported-by: Wang Nan Signed-off-by: Alexei Starovoitov --- Wang, please test the fix to double check. kernel/events/core.c |3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 84231a146dd5..b27bdc8b3558 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3415,7 +3415,6 @@ static void free_event_rcu(struct rcu_head *head) if (event->ns) put_pid_ns(event->ns); perf_event_free_filter(event); - perf_event_free_bpf_prog(event); kfree(event); } @@ -3546,6 +3545,8 @@ static void __free_event(struct perf_event *event) put_callchain_buffers(); } + perf_event_free_bpf_prog(event); + if (event->destroy) event->destroy(event); -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[PATCH tip] perf/events/core: fix race in bpf program unregister
there is a race between perf_event_free_bpf_prog() and free_trace_kprobe(): __free_event() event-destroy(event) tp_perf_event_destroy() perf_trace_destroy() perf_trace_event_unreg() which is dropping event-tp_event-perf_refcount and allows to proceed in: unregister_trace_kprobe() unregister_kprobe_event() trace_remove_event_call() probe_remove_event_call() free_trace_kprobe() while __free_event does: call_rcu(event-rcu_head, free_event_rcu); free_event_rcu() perf_event_free_bpf_prog() To fix the race simply move perf_event_free_bpf_prog() before event-destroy(), since event-tp_event is still valid at that point. Note, perf_trace_destroy() is not racing with trace_remove_event_call() since they both grab event_mutex. Fixes: 2541517c32be (tracing, perf: Implement BPF programs attached to kprobes) Reported-by: Wang Nan wangn...@huawei.com Signed-off-by: Alexei Starovoitov a...@plumgrid.com --- Wang, please test the fix to double check. kernel/events/core.c |3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 84231a146dd5..b27bdc8b3558 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3415,7 +3415,6 @@ static void free_event_rcu(struct rcu_head *head) if (event-ns) put_pid_ns(event-ns); perf_event_free_filter(event); - perf_event_free_bpf_prog(event); kfree(event); } @@ -3546,6 +3545,8 @@ static void __free_event(struct perf_event *event) put_callchain_buffers(); } + perf_event_free_bpf_prog(event); + if (event-destroy) event-destroy(event); -- 1.7.9.5 -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/