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]>
---

 kernel/perf_event.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- git/kernel/perf_event.c~1_find_get_context  2011-01-14 18:21:05.000000000 
+0100
+++ git/kernel/perf_event.c     2011-01-18 16:56:40.000000000 +0100
@@ -2228,7 +2228,7 @@ 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

Reply via email to