2.6.37-stable review patch. If anyone has any objections, please let us know.
------------------ From: Oleg Nesterov <[email protected]> commit 22a4ec729017ba613337a28f306f94ba5023fe2e upstream. If task == NULL, find_get_context() should always check that cpu is correct. Afaics, the bug was introduced by 38a81da2 "perf events: Clean up pid passing", but even before that commit "&& cpu != -1" was not exactly right, -ESRCH from find_task_by_vpid() is not accurate. Signed-off-by: Oleg Nesterov <[email protected]> Acked-by: Peter Zijlstra <[email protected]> Cc: Alan Stern <[email protected]> Cc: Arnaldo Carvalho de Melo <[email protected]> Cc: Frederic Weisbecker <[email protected]> Cc: Paul Mackerras <[email protected]> Cc: Prasad <[email protected]> Cc: Roland McGrath <[email protected]> LKML-Reference: <[email protected]> Signed-off-by: Ingo Molnar <[email protected]> Signed-off-by: Greg Kroah-Hartman <[email protected]> --- kernel/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2100,7 +2100,7 @@ find_get_context(struct pmu *pmu, struct unsigned long flags; int ctxn, err; - if (!task && cpu != -1) { + if (!task) { /* Must be root to operate on a CPU event: */ if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); _______________________________________________ stable mailing list [email protected] http://linux.kernel.org/mailman/listinfo/stable
