diff options
author | Tejun Heo | 2012-11-05 09:16:58 -0800 |
---|---|---|
committer | Tejun Heo | 2012-11-05 09:16:58 -0800 |
commit | e93160803ffda2e67d9ff9cacb63bb6868c8398f (patch) | |
tree | e3305bb56336c32862f1970882f030caca7f11b2 | |
parent | ed95779340b50e362245c81b5dec0d11a1debfa8 (diff) |
cgroup: kill CSS_REMOVED
CSS_REMOVED is one of the several contortions which were necessary to
support css reference draining on cgroup removal. All css->refcnts
which need draining should be deactivated and verified to equal zero
atomically w.r.t. css_tryget(). If any one isn't zero, all refcnts
needed to be re-activated and css_tryget() shouldn't fail in the
process.
This was achieved by letting css_tryget() busy-loop until either the
refcnt is reactivated (failed removal attempt) or CSS_REMOVED is set
(committing to removal).
Now that css refcnt draining is no longer used, there's no need for
atomic rollback mechanism. css_tryget() simply can look at the
reference count and fail if it's deactivated - it's never getting
re-activated.
This patch removes CSS_REMOVED and updates __css_tryget() to fail if
the refcnt is deactivated. As deactivation and removal are a single
step now, they no longer need to be protected against css_tryget()
happening from irq context. Remove local_irq_disable/enable() from
cgroup_rmdir().
Note that this removes css_is_removed() whose only user is VM_BUG_ON()
in memcontrol.c. We can replace it with a check on the refcnt but
given that the only use case is a debug assert, I think it's better to
simply unexport it.
v2: Comment updated and explanation on local_irq_disable/enable()
added per Michal Hocko.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
-rw-r--r-- | include/linux/cgroup.h | 6 | ||||
-rw-r--r-- | kernel/cgroup.c | 31 | ||||
-rw-r--r-- | mm/memcontrol.c | 7 |
3 files changed, 15 insertions, 29 deletions
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 02e09c0e98ab..a3098046250b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -85,7 +85,6 @@ struct cgroup_subsys_state { /* bits in struct cgroup_subsys_state flags field */ enum { CSS_ROOT, /* This CSS is the root of the subsystem */ - CSS_REMOVED, /* This CSS is dead */ }; /* Caller must verify that the css is not for root cgroup */ @@ -108,11 +107,6 @@ static inline void css_get(struct cgroup_subsys_state *css) __css_get(css, 1); } -static inline bool css_is_removed(struct cgroup_subsys_state *css) -{ - return test_bit(CSS_REMOVED, &css->flags); -} - /* * Call css_tryget() to take a reference on a css if your existing * (known-valid) reference isn't already ref-counted. Returns false if diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8c605e2bdd1a..c194f9e4fc7b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -170,8 +170,8 @@ struct css_id { * The css to which this ID points. This pointer is set to valid value * after cgroup is populated. If cgroup is removed, this will be NULL. * This pointer is expected to be RCU-safe because destroy() - * is called after synchronize_rcu(). But for safe use, css_is_removed() - * css_tryget() should be used for avoiding race. + * is called after synchronize_rcu(). But for safe use, css_tryget() + * should be used for avoiding race. */ struct cgroup_subsys_state __rcu *css; /* @@ -4112,8 +4112,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) } prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE); - local_irq_disable(); - /* block new css_tryget() by deactivating refcnt */ for_each_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; @@ -4123,21 +4121,14 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) } /* - * Set REMOVED. All in-progress css_tryget() will be released. * Put all the base refs. Each css holds an extra reference to the * cgroup's dentry and cgroup removal proceeds regardless of css * refs. On the last put of each css, whenever that may be, the * extra dentry ref is put so that dentry destruction happens only * after all css's are released. */ - for_each_subsys(cgrp->root, ss) { - struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; - - set_bit(CSS_REMOVED, &css->flags); - css_put(css); - } - - local_irq_enable(); + for_each_subsys(cgrp->root, ss) + css_put(cgrp->subsys[ss->subsys_id]); finish_wait(&cgroup_rmdir_waitq, &wait); clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); @@ -4861,15 +4852,17 @@ static void check_for_release(struct cgroup *cgrp) /* Caller must verify that the css is not for root cgroup */ bool __css_tryget(struct cgroup_subsys_state *css) { - do { - int v = css_refcnt(css); + while (true) { + int t, v; - if (atomic_cmpxchg(&css->refcnt, v, v + 1) == v) + v = css_refcnt(css); + t = atomic_cmpxchg(&css->refcnt, v, v + 1); + if (likely(t == v)) return true; + else if (t < 0) + return false; cpu_relax(); - } while (!test_bit(CSS_REMOVED, &css->flags)); - - return false; + } } EXPORT_SYMBOL_GPL(__css_tryget); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5a1d584ffed3..37c356646544 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2343,7 +2343,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, again: if (*ptr) { /* css should be a valid one */ memcg = *ptr; - VM_BUG_ON(css_is_removed(&memcg->css)); if (mem_cgroup_is_root(memcg)) goto done; if (nr_pages == 1 && consume_stock(memcg)) @@ -2483,9 +2482,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg, /* * A helper function to get mem_cgroup from ID. must be called under - * rcu_read_lock(). The caller must check css_is_removed() or some if - * it's concern. (dropping refcnt from swap can be called against removed - * memcg.) + * rcu_read_lock(). The caller is responsible for calling css_tryget if + * the mem_cgroup is used for charging. (dropping refcnt from swap can be + * called against removed memcg.) */ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) { |