[PATCH v3 05/11] perf: Move cgroup init before PMU ->event_init()

From: Matt Fleming
Date: Thu Nov 06 2014 - 07:24:50 EST


From: Matt Fleming <matt.fleming@xxxxxxxxx>

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.

Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Matt Fleming <matt.fleming@xxxxxxxxx>
---
Changes in v3:

- Only use 'int cgroup_fd' to pass cgroup file descriptor instead of
'bool cgroup, pid_t cgroup_fd'

kernel/events/core.c | 28 ++++++++++++++++------------
1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index a2ea4a52dbbf..540d995322dd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6884,7 +6884,7 @@ 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;
@@ -6977,6 +6977,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
goto err_ns;

+ 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;
@@ -7000,6 +7006,8 @@ 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);
@@ -7207,6 +7215,7 @@ 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)
@@ -7272,21 +7281,16 @@ 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;
@@ -7486,7 +7490,7 @@ 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;
@@ -7812,7 +7816,7 @@ 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;

--
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/