Re: [PATCH v3 net-next] bpf: fix bpf_perf_event_read() helper
From: Peter Zijlstra <peterz@infradead.org>
Date: 2015-10-23 12:03:55
Also in:
lkml
On Thu, Oct 22, 2015 at 05:10:14PM -0700, Alexei Starovoitov wrote:
quoted hunk ↗ jump to hunk
+++ b/kernel/trace/bpf_trace.c@@ -199,6 +199,11 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) if (!event) return -ENOENT; + /* make sure event is local and doesn't have pmu::count */ + if (event->oncpu != smp_processor_id() || + event->pmu->count) + return -EINVAL; + /* * we don't know if the function is run successfully by the * return value. It can be judged in other places, such as
I might want to go turn that into a helper function to keep !perf code from poking around in the event itself, but its ok for now I suppose.
quoted hunk ↗ jump to hunk
@@ -207,7 +212,7 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) return perf_event_read_local(event); }
So the bpf_perf_event_read() returns the count value, does this not also mean that returning -EINVAL here is also 'wrong'? I mean, sure an actual count value that high is unlikely, but its still a broken interface.