summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-04-11 23:38:16 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-04-11 23:38:16 -0700
commit06ea4c38bce80f3eb99b01d7c17419eb1a49fec2 (patch)
tree2af3797bce33f38ecfe39aa34ecec01e8ccd4b9c /kernel
parentaf94bdfa798b7da92cc82609acca61a287a004a4 (diff)
parentbfb0b80db5f9dca5ac0a5fd0edb765ee555e5a8e (diff)
Merge branch 'for-4.11-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup fixes from Tejun Heo: "This contains fixes for two long standing subtle bugs: - kthread_bind() on a new kthread binds it to specific CPUs and prevents userland from messing with the affinity or cgroup membership. Unfortunately, for cgroup membership, there's a window between kthread creation and kthread_bind*() invocation where the kthread can be moved into a non-root cgroup by userland. Depending on what controllers are in effect, this can assign the kthread unexpected attributes. For example, in the reported case, workqueue workers ended up in a non-root cpuset cgroups and had their CPU affinities overridden. This broke workqueue invariants and led to workqueue stalls. Fixed by closing the window between kthread creation and kthread_bind() as suggested by Oleg. - There was a bug in cgroup mount path which could allow two competing mount attempts to attach the same cgroup_root to two different superblocks. This was caused by mishandling return value from kernfs_pin_sb(). Fixed" * 'for-4.11-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: cgroup: avoid attaching a cgroup root to two different superblocks cgroup, kthread: close race window where new kthreads can be migrated to non-root cgroups
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup/cgroup-v1.c2
-rw-r--r--kernel/cgroup/cgroup.c9
-rw-r--r--kernel/kthread.c3
3 files changed, 9 insertions, 5 deletions
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 1dc22f6b49f5..12e19f0636ea 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1146,7 +1146,7 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
* path is super cold. Let's just sleep a bit and retry.
*/
pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
- if (IS_ERR(pinned_sb) ||
+ if (IS_ERR_OR_NULL(pinned_sb) ||
!percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
mutex_unlock(&cgroup_mutex);
if (!IS_ERR_OR_NULL(pinned_sb))
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 48851327a15e..687f5e0194ef 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2425,11 +2425,12 @@ ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
tsk = tsk->group_leader;
/*
- * Workqueue threads may acquire PF_NO_SETAFFINITY and become
- * trapped in a cpuset, or RT worker may be born in a cgroup
- * with no rt_runtime allocated. Just say no.
+ * kthreads may acquire PF_NO_SETAFFINITY during initialization.
+ * If userland migrates such a kthread to a non-root cgroup, it can
+ * become trapped in a cpuset, or RT kthread may be born in a
+ * cgroup with no rt_runtime allocated. Just say no.
*/
- if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
+ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
ret = -EINVAL;
goto out_unlock_rcu;
}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 2f26adea0f84..26db528c1d88 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -20,6 +20,7 @@
#include <linux/freezer.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
+#include <linux/cgroup.h>
#include <trace/events/sched.h>
static DEFINE_SPINLOCK(kthread_create_lock);
@@ -225,6 +226,7 @@ static int kthread(void *_create)
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
+ cgroup_kthread_ready();
__kthread_parkme(self);
ret = threadfn(data);
}
@@ -538,6 +540,7 @@ int kthreadd(void *unused)
set_mems_allowed(node_states[N_MEMORY]);
current->flags |= PF_NOFREEZE;
+ cgroup_init_kthreadd();
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);