perf: Move cgroup init before PMU ->event_init()

The Intel QoS PMU needs to know whether an event is part of a cgroup
during ->event_init(), because tasks in the same cgroup share a
monitoring ID.

Move the cgroup initialisation before calling into the PMU driver.

Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kanaka Juvva <kanaka.d.juvva@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com>
Link: http://lkml.kernel.org/r/1422038748-21397-4-git-send-email-matt@codeblueprint.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4e8dc596f101dd7be684d191f53313ba194b833e..1fc3bae5904ac77ede9889db98ba40f8a3881409 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7116,7 +7116,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
                 struct perf_event *group_leader,
                 struct perf_event *parent_event,
                 perf_overflow_handler_t overflow_handler,
-                void *context)
+                void *context, int cgroup_fd)
 {
        struct pmu *pmu;
        struct perf_event *event;
@@ -7212,6 +7212,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
        if (!has_branch_stack(event))
                event->attr.branch_sample_type = 0;
 
+       if (cgroup_fd != -1) {
+               err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
+               if (err)
+                       goto err_ns;
+       }
+
        pmu = perf_init_event(event);
        if (!pmu)
                goto err_ns;
@@ -7235,6 +7241,8 @@ err_pmu:
                event->destroy(event);
        module_put(pmu->module);
 err_ns:
+       if (is_cgroup_event(event))
+               perf_detach_cgroup(event);
        if (event->ns)
                put_pid_ns(event->ns);
        kfree(event);
@@ -7453,6 +7461,7 @@ SYSCALL_DEFINE5(perf_event_open,
        int move_group = 0;
        int err;
        int f_flags = O_RDWR;
+       int cgroup_fd = -1;
 
        /* for future expandability... */
        if (flags & ~PERF_FLAG_ALL)
@@ -7518,21 +7527,16 @@ SYSCALL_DEFINE5(perf_event_open,
 
        get_online_cpus();
 
+       if (flags & PERF_FLAG_PID_CGROUP)
+               cgroup_fd = pid;
+
        event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
-                                NULL, NULL);
+                                NULL, NULL, cgroup_fd);
        if (IS_ERR(event)) {
                err = PTR_ERR(event);
                goto err_cpus;
        }
 
-       if (flags & PERF_FLAG_PID_CGROUP) {
-               err = perf_cgroup_connect(pid, event, &attr, group_leader);
-               if (err) {
-                       __free_event(event);
-                       goto err_cpus;
-               }
-       }
-
        if (is_sampling_event(event)) {
                if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) {
                        err = -ENOTSUPP;
@@ -7769,7 +7773,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
         */
 
        event = perf_event_alloc(attr, cpu, task, NULL, NULL,
-                                overflow_handler, context);
+                                overflow_handler, context, -1);
        if (IS_ERR(event)) {
                err = PTR_ERR(event);
                goto err;
@@ -8130,7 +8134,7 @@ inherit_event(struct perf_event *parent_event,
                                           parent_event->cpu,
                                           child,
                                           group_leader, parent_event,
-                                          NULL, NULL);
+                                          NULL, NULL, -1);
        if (IS_ERR(child_event))
                return child_event;