perf: Add cgroup support

This kernel patch adds the ability to filter monitoring based on
container groups (cgroups). This is for use in per-cpu mode only.

The cgroup to monitor is passed as a file descriptor in the pid
argument to the syscall. The file descriptor must be opened to
the cgroup name in the cgroup filesystem. For instance, if the
cgroup name is foo and cgroupfs is mounted in /cgroup, then the
file descriptor is opened to /cgroup/foo. Cgroup mode is
activated by passing PERF_FLAG_PID_CGROUP in the flags argument
to the syscall.

For instance to measure in cgroup foo on CPU1 assuming
cgroupfs is mounted under /cgroup:

struct perf_event_attr attr;
int cgroup_fd, fd;

cgroup_fd = open("/cgroup/foo", O_RDONLY);
fd = perf_event_open(&attr, cgroup_fd, 1, -1, PERF_FLAG_PID_CGROUP);
close(cgroup_fd);

Signed-off-by: Stephane Eranian <eranian@google.com>
[ added perf_cgroup_{exit,attach} ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590250.114ddf0a.689e.4482@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 23 insertions, 0 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f6495f33a355..95362d15128c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4818,6 +4818,29 @@ css_get_next(struct cgroup_subsys *ss, int id,
         return ret;
 }
 
+/*
+ * get corresponding css from file open on cgroupfs directory
+ */
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
+{
+        struct cgroup *cgrp;
+        struct inode *inode;
+        struct cgroup_subsys_state *css;
+
+        inode = f->f_dentry->d_inode;
+        /* check in cgroup filesystem dir */
+        if (inode->i_op != &cgroup_dir_inode_operations)
+                return ERR_PTR(-EBADF);
+
+        if (id < 0 || id >= CGROUP_SUBSYS_COUNT)
+                return ERR_PTR(-EINVAL);
+
+        /* get cgroup */
+        cgrp = __d_cgrp(f->f_dentry);
+        css = cgrp->subsys[id];
+        return css ? css : ERR_PTR(-ENOENT);
+}
+
 #ifdef CONFIG_CGROUP_DEBUG
 static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
                                                    struct cgroup *cont)