cgroup: ignore css_sets associated with dead cgroups during migration

commit 2b021cbf3cb6208f0d40fd2f1869f237934340ed upstream.

Before 2e91fa7f6d45 ("cgroup: keep zombies associated with their
original cgroups"), all dead tasks were associated with init_css_set.
If a zombie task is requested for migration, while migration prep
operations would still be performed on init_css_set, the actual
migration would ignore zombie tasks.  As init_css_set is always valid,
this worked fine.

However, after 2e91fa7f6d45, zombie tasks stay with the css_set it was
associated with at the time of death.  Let's say a task T associated
with cgroup A on hierarchy H-1 and cgroup B on hiearchy H-2.  After T
becomes a zombie, it would still remain associated with A and B.  If A
only contains zombie tasks, it can be removed.  On removal, A gets
marked offline but stays pinned until all zombies are drained.  At
this point, if migration is initiated on T to a cgroup C on hierarchy
H-2, migration path would try to prepare T's css_set for migration and
trigger the following.

 WARNING: CPU: 0 PID: 1576 at kernel/cgroup.c:474 cgroup_get+0x121/0x160()
 CPU: 0 PID: 1576 Comm: bash Not tainted 4.4.0-work+ #289
 ...
 Call Trace:
  [<ffffffff8127e63c>] dump_stack+0x4e/0x82
  [<ffffffff810445e8>] warn_slowpath_common+0x78/0xb0
  [<ffffffff810446d5>] warn_slowpath_null+0x15/0x20
  [<ffffffff810c33e1>] cgroup_get+0x121/0x160
  [<ffffffff810c349b>] link_css_set+0x7b/0x90
  [<ffffffff810c4fbc>] find_css_set+0x3bc/0x5e0
  [<ffffffff810c5269>] cgroup_migrate_prepare_dst+0x89/0x1f0
  [<ffffffff810c7547>] cgroup_attach_task+0x157/0x230
  [<ffffffff810c7a17>] __cgroup_procs_write+0x2b7/0x470
  [<ffffffff810c7bdc>] cgroup_tasks_write+0xc/0x10
  [<ffffffff810c4790>] cgroup_file_write+0x30/0x1b0
  [<ffffffff811c68fc>] kernfs_fop_write+0x13c/0x180
  [<ffffffff81151673>] __vfs_write+0x23/0xe0
  [<ffffffff81152494>] vfs_write+0xa4/0x1a0
  [<ffffffff811532d4>] SyS_write+0x44/0xa0
  [<ffffffff814af2d7>] entry_SYSCALL_64_fastpath+0x12/0x6f

It doesn't make sense to prepare migration for css_sets pointing to
dead cgroups as they are guaranteed to contain only zombies which are
ignored later during migration.  This patch makes cgroup destruction
path mark all affected css_sets as dead and updates the migration path
to ignore them during preparation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups")
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8e30faeab18363cf67be62e76f7ffa3fd2349046..a7c7f74808a4359ed079bb13b441fc2d0ded56c8 100644 (file)
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -216,6 +216,9 @@ struct css_set {
        /* all css_task_iters currently walking this cset */
        struct list_head task_iters;
 
+       /* dead and being drained, ignore for migration */
+       bool dead;
+
        /* For RCU-protected deletion */
        struct rcu_head rcu_head;
 };

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index fb1ecfd2decd907e907d1d68d74792cb6d07714e..dc94f8beb097ff03c0090b0195e206ef85c6bb9b 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2498,6 +2498,14 @@ static void cgroup_migrate_add_src(struct css_set *src_cset,
        lockdep_assert_held(&cgroup_mutex);
        lockdep_assert_held(&css_set_lock);
 
+       /*
+        * If ->dead, @src_set is associated with one or more dead cgroups
+        * and doesn't contain any migratable tasks.  Ignore it early so
+        * that the rest of migration path doesn't get confused by it.
+        */
+       if (src_cset->dead)
+               return;
+
        src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
 
        if (!list_empty(&src_cset->mg_preload_node))
@@ -5131,6 +5139,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
        __releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
        struct cgroup_subsys_state *css;
+       struct cgrp_cset_link *link;
        int ssid;
 
        lockdep_assert_held(&cgroup_mutex);
@@ -5151,11 +5160,18 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
                return -EBUSY;
 
        /*
-        * Mark @cgrp dead.  This prevents further task migration and child
-        * creation by disabling cgroup_lock_live_group().
+        * Mark @cgrp and the associated csets dead.  The former prevents
+        * further task migration and child creation by disabling
+        * cgroup_lock_live_group().  The latter makes the csets ignored by
+        * the migration path.
         */
        cgrp->self.flags &= ~CSS_ONLINE;
 
+       spin_lock_bh(&css_set_lock);
+       list_for_each_entry(link, &cgrp->cset_links, cset_link)
+               link->cset->dead = true;
+       spin_unlock_bh(&css_set_lock);
+
        /* initiate massacre of all css's */
        for_each_css(css, ssid, cgrp)
                kill_css(css);