From ed95779340b50e362245c81b5dec0d11a1debfa8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Nov 2012 09:16:58 -0800 Subject: cgroup: kill cgroup_subsys->__DEPRECATED_clear_css_refs 2ef37d3fe4 ("memcg: Simplify mem_cgroup_force_empty_list error handling") removed the last user of __DEPRECATED_clear_css_refs. This patch removes __DEPRECATED_clear_css_refs and mechanisms to support it. * Conditionals dependent on __DEPRECATED_clear_css_refs removed. * cgroup_clear_css_refs() can no longer fail. All that needs to be done are deactivating refcnts, setting CSS_REMOVED and putting the base reference on each css. Remove cgroup_clear_css_refs() and the failure path, and open-code the loops into cgroup_rmdir(). This patch keeps the two for_each_subsys() loops separate while open coding them. They can be merged now but there are scheduled changes which need them to be separate, so keep them separate to reduce the amount of churn. local_irq_save/restore() from cgroup_clear_css_refs() are replaced with local_irq_disable/enable() for simplicity. This is safe as cgroup_rmdir() is always called with IRQ enabled. Note that this IRQ switching is necessary to ensure that css_tryget() isn't called from IRQ context on the same CPU while lower context is between CSS deactivation and setting CSS_REMOVED as css_tryget() would hang forever in such cases waiting for CSS to be re-activated or CSS_REMOVED set. This will go away soon. v2: cgroup_call_pre_destroy() removal dropped per Michal. Commit message updated to explain local_irq_disable/enable() conversion. Signed-off-by: Tejun Heo Reviewed-by: Michal Hocko Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Li Zefan --- kernel/cgroup.c | 131 ++++++++++++++++---------------------------------------- 1 file changed, 36 insertions(+), 95 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7981850..8c605e2 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -865,11 +865,8 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp) continue; ret = ss->pre_destroy(cgrp); - if (ret) { - /* ->pre_destroy() failure is being deprecated */ - WARN_ON_ONCE(!ss->__DEPRECATED_clear_css_refs); + if (WARN_ON_ONCE(ret)) break; - } } return ret; @@ -3901,14 +3898,12 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, cgrp->subsys[ss->subsys_id] = css; /* - * If !clear_css_refs, css holds an extra ref to @cgrp->dentry - * which is put on the last css_put(). dput() requires process - * context, which css_put() may be called without. @css->dput_work - * will be used to invoke dput() asynchronously from css_put(). + * css holds an extra ref to @cgrp->dentry which is put on the last + * css_put(). dput() requires process context, which css_put() may + * be called without. @css->dput_work will be used to invoke + * dput() asynchronously from css_put(). */ INIT_WORK(&css->dput_work, css_dput_fn); - if (ss->__DEPRECATED_clear_css_refs) - set_bit(CSS_CLEAR_CSS_REFS, &css->flags); } /* @@ -3978,10 +3973,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, if (err < 0) goto err_remove; - /* If !clear_css_refs, each css holds a ref to the cgroup's dentry */ + /* each css holds a ref to the cgroup's dentry */ for_each_subsys(root, ss) - if (!ss->__DEPRECATED_clear_css_refs) - dget(dentry); + dget(dentry); /* The cgroup directory was pre-locked for us */ BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex)); @@ -4066,71 +4060,6 @@ static int cgroup_has_css_refs(struct cgroup *cgrp) return 0; } -/* - * Atomically mark all (or else none) of the cgroup's CSS objects as - * CSS_REMOVED. Return true on success, or false if the cgroup has - * busy subsystems. Call with cgroup_mutex held - * - * Depending on whether a subsys has __DEPRECATED_clear_css_refs set or - * not, cgroup removal behaves differently. - * - * If clear is set, css refcnt for the subsystem should be zero before - * cgroup removal can be committed. This is implemented by - * CGRP_WAIT_ON_RMDIR and retry logic around ->pre_destroy(), which may be - * called multiple times until all css refcnts reach zero and is allowed to - * veto removal on any invocation. This behavior is deprecated and will be - * removed as soon as the existing user (memcg) is updated. - * - * If clear is not set, each css holds an extra reference to the cgroup's - * dentry and cgroup removal proceeds regardless of css refs. - * ->pre_destroy() will be called at least once and is not allowed to fail. - * 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. - */ -static int cgroup_clear_css_refs(struct cgroup *cgrp) -{ - struct cgroup_subsys *ss; - unsigned long flags; - bool failed = false; - - local_irq_save(flags); - - /* - * Block new css_tryget() by deactivating refcnt. If all refcnts - * for subsystems w/ clear_css_refs set were 1 at the moment of - * deactivation, we succeeded. - */ - for_each_subsys(cgrp->root, ss) { - struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; - - WARN_ON(atomic_read(&css->refcnt) < 0); - atomic_add(CSS_DEACT_BIAS, &css->refcnt); - - if (ss->__DEPRECATED_clear_css_refs) - failed |= css_refcnt(css) != 1; - } - - /* - * If succeeded, set REMOVED and put all the base refs; otherwise, - * restore refcnts to positive values. Either way, all in-progress - * css_tryget() will be released. - */ - for_each_subsys(cgrp->root, ss) { - struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; - - if (!failed) { - set_bit(CSS_REMOVED, &css->flags); - css_put(css); - } else { - atomic_sub(CSS_DEACT_BIAS, &css->refcnt); - } - } - - local_irq_restore(flags); - return !failed; -} - static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) { struct cgroup *cgrp = dentry->d_fsdata; @@ -4138,10 +4067,10 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) struct cgroup *parent; DEFINE_WAIT(wait); struct cgroup_event *event, *tmp; + struct cgroup_subsys *ss; int ret; /* the vfs holds both inode->i_mutex already */ -again: mutex_lock(&cgroup_mutex); if (atomic_read(&cgrp->count) != 0) { mutex_unlock(&cgroup_mutex); @@ -4182,21 +4111,34 @@ again: return -EBUSY; } prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE); - if (!cgroup_clear_css_refs(cgrp)) { - mutex_unlock(&cgroup_mutex); - /* - * Because someone may call cgroup_wakeup_rmdir_waiter() before - * prepare_to_wait(), we need to check this flag. - */ - if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)) - schedule(); - finish_wait(&cgroup_rmdir_waitq, &wait); - clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); - if (signal_pending(current)) - return -EINTR; - goto again; + + 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]; + + WARN_ON(atomic_read(&css->refcnt) < 0); + atomic_add(CSS_DEACT_BIAS, &css->refcnt); + } + + /* + * 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); } - /* NO css_tryget() can success after here. */ + + local_irq_enable(); + finish_wait(&cgroup_rmdir_waitq, &wait); clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); @@ -4949,8 +4891,7 @@ void __css_put(struct cgroup_subsys_state *css) cgroup_wakeup_rmdir_waiter(cgrp); break; case 0: - if (!test_bit(CSS_CLEAR_CSS_REFS, &css->flags)) - schedule_work(&css->dput_work); + schedule_work(&css->dput_work); break; } rcu_read_unlock(); -- cgit v1.1 From e93160803ffda2e67d9ff9cacb63bb6868c8398f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Nov 2012 09:16:58 -0800 Subject: 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 Reviewed-by: Michal Hocko Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Li Zefan Cc: Johannes Weiner Cc: Balbir Singh --- kernel/cgroup.c | 31 ++++++++++++------------------- 1 file changed, 12 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8c605e2..c194f9e 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); -- cgit v1.1 From 976c06bcccc50573997609fa7ec842479bd96ffb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Nov 2012 09:16:59 -0800 Subject: cgroup: use cgroup_lock_live_group(parent) in cgroup_create() This patch makes cgroup_create() fail if @parent is marked removed. This is to prepare for further updates to cgroup_rmdir() path. Note that this change isn't strictly necessary. cgroup can only be created via mkdir and the removed marking and dentry removal happen without releasing cgroup_mutex, so cgroup_create() can never race with cgroup_rmdir(). Even after the scheduled updates to cgroup_rmdir(), cgroup_mkdir() and cgroup_rmdir() are synchronized by i_mutex rendering the added liveliness check unnecessary. Do it anyway such that locking is contained inside cgroup proper and we don't get nasty surprises if we ever grow another caller of cgroup_create(). Signed-off-by: Tejun Heo Reviewed-by: Michal Hocko Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Li Zefan --- kernel/cgroup.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c194f9e..f22e3cd 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3927,6 +3927,18 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, if (!cgrp) return -ENOMEM; + /* + * Only live parents can have children. Note that the liveliness + * check isn't strictly necessary because cgroup_mkdir() and + * cgroup_rmdir() are fully synchronized by i_mutex; however, do it + * anyway so that locking is contained inside cgroup proper and we + * don't get nasty surprises if we ever grow another caller. + */ + if (!cgroup_lock_live_group(parent)) { + err = -ENODEV; + goto err_free; + } + /* Grab a reference on the superblock so the hierarchy doesn't * get deleted on unmount if there are child cgroups. This * can be done outside cgroup_mutex, since the sb can't @@ -3934,8 +3946,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, * fs */ atomic_inc(&sb->s_active); - mutex_lock(&cgroup_mutex); - init_cgroup_housekeeping(cgrp); cgrp->parent = parent; @@ -4006,7 +4016,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, /* Release the reference count that we took on the superblock */ deactivate_super(sb); - +err_free: kfree(cgrp); return err; } -- cgit v1.1 From 1a90dd508b0b00e382fd61a46f55dc889ac21b39 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Nov 2012 09:16:59 -0800 Subject: cgroup: deactivate CSS's and mark cgroup dead before invoking ->pre_destroy() Because ->pre_destroy() could fail and can't be called under cgroup_mutex, cgroup destruction did something very ugly. 1. Grab cgroup_mutex and verify it can be destroyed; fail otherwise. 2. Release cgroup_mutex and call ->pre_destroy(). 3. Re-grab cgroup_mutex and verify it can still be destroyed; fail otherwise. 4. Continue destroying. In addition to being ugly, it has been always broken in various ways. For example, memcg ->pre_destroy() expects the cgroup to be inactive after it's done but tasks can be attached and detached between #2 and #3 and the conditions that memcg verified in ->pre_destroy() might no longer hold by the time control reaches #3. Now that ->pre_destroy() is no longer allowed to fail. We can switch to the following. 1. Grab cgroup_mutex and verify it can be destroyed; fail otherwise. 2. Deactivate CSS's and mark the cgroup removed thus preventing any further operations which can invalidate the verification from #1. 3. Release cgroup_mutex and call ->pre_destroy(). 4. Re-grab cgroup_mutex and continue destroying. After this change, controllers can safely assume that ->pre_destroy() will only be called only once for a given cgroup and, once ->pre_destroy() is called, the cgroup will stay dormant till it's destroyed. This removes the only reason ->pre_destroy() can fail - new task being attached or child cgroup being created inbetween. Error out path is removed and ->pre_destroy() invocation is open coded in cgroup_rmdir(). v2: cgroup_call_pre_destroy() removal moved to this patch per Michal. Commit message updated per Glauber. Signed-off-by: Tejun Heo Reviewed-by: Michal Hocko Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Li Zefan Cc: Glauber Costa --- kernel/cgroup.c | 65 +++++++++++++++++---------------------------------------- 1 file changed, 19 insertions(+), 46 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f22e3cd..66204a6 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -851,27 +851,6 @@ static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb) return inode; } -/* - * Call subsys's pre_destroy handler. - * This is called before css refcnt check. - */ -static int cgroup_call_pre_destroy(struct cgroup *cgrp) -{ - struct cgroup_subsys *ss; - int ret = 0; - - for_each_subsys(cgrp->root, ss) { - if (!ss->pre_destroy) - continue; - - ret = ss->pre_destroy(cgrp); - if (WARN_ON_ONCE(ret)) - break; - } - - return ret; -} - static void cgroup_diput(struct dentry *dentry, struct inode *inode) { /* is dentry a directory ? if so, kfree() associated cgroup */ @@ -4078,19 +4057,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) DEFINE_WAIT(wait); struct cgroup_event *event, *tmp; struct cgroup_subsys *ss; - int ret; - - /* the vfs holds both inode->i_mutex already */ - mutex_lock(&cgroup_mutex); - if (atomic_read(&cgrp->count) != 0) { - mutex_unlock(&cgroup_mutex); - return -EBUSY; - } - if (!list_empty(&cgrp->children)) { - mutex_unlock(&cgroup_mutex); - return -EBUSY; - } - mutex_unlock(&cgroup_mutex); /* * In general, subsystem has no css->refcnt after pre_destroy(). But @@ -4103,16 +4069,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) */ set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); - /* - * Call pre_destroy handlers of subsys. Notify subsystems - * that rmdir() request comes. - */ - ret = cgroup_call_pre_destroy(cgrp); - if (ret) { - clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); - return ret; - } - + /* the vfs holds both inode->i_mutex already */ mutex_lock(&cgroup_mutex); parent = cgrp->parent; if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) { @@ -4122,13 +4079,30 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) } prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE); - /* block new css_tryget() by deactivating refcnt */ + /* + * Block new css_tryget() by deactivating refcnt and mark @cgrp + * removed. This makes future css_tryget() and child creation + * attempts fail thus maintaining the removal conditions verified + * above. + */ for_each_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; WARN_ON(atomic_read(&css->refcnt) < 0); atomic_add(CSS_DEACT_BIAS, &css->refcnt); } + set_bit(CGRP_REMOVED, &cgrp->flags); + + /* + * Tell subsystems to initate destruction. pre_destroy() should be + * called with cgroup_mutex unlocked. See 3fa59dfbc3 ("cgroup: fix + * potential deadlock in pre_destroy") for details. + */ + mutex_unlock(&cgroup_mutex); + for_each_subsys(cgrp->root, ss) + if (ss->pre_destroy) + WARN_ON_ONCE(ss->pre_destroy(cgrp)); + mutex_lock(&cgroup_mutex); /* * Put all the base refs. Each css holds an extra reference to the @@ -4144,7 +4118,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); raw_spin_lock(&release_list_lock); - set_bit(CGRP_REMOVED, &cgrp->flags); if (!list_empty(&cgrp->release_list)) list_del_init(&cgrp->release_list); raw_spin_unlock(&release_list_lock); -- cgit v1.1 From b25ed609d0eecf077db607e88ea70bae83b6adb2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Nov 2012 09:16:59 -0800 Subject: cgroup: remove CGRP_WAIT_ON_RMDIR, cgroup_exclude_rmdir() and cgroup_release_and_wakeup_rmdir() CGRP_WAIT_ON_RMDIR is another kludge which was added to make cgroup destruction rollback somewhat working. cgroup_rmdir() used to drain CSS references and CGRP_WAIT_ON_RMDIR and the associated waitqueue and helpers were used to allow the task performing rmdir to wait for the next relevant event. Unfortunately, the wait is visible to controllers too and the mechanism got exposed to memcg by 887032670d ("cgroup avoid permanent sleep at rmdir"). Now that the draining and retries are gone, CGRP_WAIT_ON_RMDIR is unnecessary. Remove it and all the mechanisms supporting it. Note that memcontrol.c changes are essentially revert of 887032670d ("cgroup avoid permanent sleep at rmdir"). Signed-off-by: Tejun Heo Reviewed-by: Michal Hocko Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Li Zefan Cc: Balbir Singh --- kernel/cgroup.c | 51 --------------------------------------------------- 1 file changed, 51 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 66204a6..c5f6fb2 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -966,33 +966,6 @@ static void cgroup_d_remove_dir(struct dentry *dentry) } /* - * A queue for waiters to do rmdir() cgroup. A tasks will sleep when - * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some - * reference to css->refcnt. In general, this refcnt is expected to goes down - * to zero, soon. - * - * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex; - */ -static DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq); - -static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp) -{ - if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))) - wake_up_all(&cgroup_rmdir_waitq); -} - -void cgroup_exclude_rmdir(struct cgroup_subsys_state *css) -{ - css_get(css); -} - -void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css) -{ - cgroup_wakeup_rmdir_waiter(css->cgroup); - css_put(css); -} - -/* * Call with cgroup_mutex held. Drops reference counts on modules, including * any duplicate ones that parse_cgroupfs_options took. If this function * returns an error, no reference counts are touched. @@ -1963,12 +1936,6 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) } synchronize_rcu(); - - /* - * wake up rmdir() waiter. the rmdir should fail since the cgroup - * is no longer empty. - */ - cgroup_wakeup_rmdir_waiter(cgrp); out: if (retval) { for_each_subsys(root, ss) { @@ -2138,7 +2105,6 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) * step 5: success! and cleanup */ synchronize_rcu(); - cgroup_wakeup_rmdir_waiter(cgrp); retval = 0; out_put_css_set_refs: if (retval) { @@ -4058,26 +4024,13 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) struct cgroup_event *event, *tmp; struct cgroup_subsys *ss; - /* - * In general, subsystem has no css->refcnt after pre_destroy(). But - * in racy cases, subsystem may have to get css->refcnt after - * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes - * make rmdir return -EBUSY too often. To avoid that, we use waitqueue - * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir - * and subsystem's reference count handling. Please see css_get/put - * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation. - */ - set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); - /* the vfs holds both inode->i_mutex already */ mutex_lock(&cgroup_mutex); parent = cgrp->parent; if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) { - clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); mutex_unlock(&cgroup_mutex); return -EBUSY; } - prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE); /* * Block new css_tryget() by deactivating refcnt and mark @cgrp @@ -4114,9 +4067,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) 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); - raw_spin_lock(&release_list_lock); if (!list_empty(&cgrp->release_list)) list_del_init(&cgrp->release_list); @@ -4864,7 +4814,6 @@ void __css_put(struct cgroup_subsys_state *css) set_bit(CGRP_RELEASABLE, &cgrp->flags); check_for_release(cgrp); } - cgroup_wakeup_rmdir_waiter(cgrp); break; case 0: schedule_work(&css->dput_work); -- cgit v1.1 From bcf6de1b9129531215d26dd9af8331e84973bc52 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Nov 2012 09:16:59 -0800 Subject: cgroup: make ->pre_destroy() return void All ->pre_destory() implementations return 0 now, which is the only allowed return value. Make it return void. Signed-off-by: Tejun Heo Reviewed-by: Michal Hocko Acked-by: KAMEZAWA Hiroyuki Acked-by: Li Zefan Cc: Balbir Singh Cc: Vivek Goyal --- kernel/cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c5f6fb2..83cd7d0 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4054,7 +4054,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) mutex_unlock(&cgroup_mutex); for_each_subsys(cgrp->root, ss) if (ss->pre_destroy) - WARN_ON_ONCE(ss->pre_destroy(cgrp)); + ss->pre_destroy(cgrp); mutex_lock(&cgroup_mutex); /* -- cgit v1.1