From f9f9e7b776142fb1c0782cade004cc8e0147a199 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 16 Sep 2015 11:51:12 -0400 Subject: Revert "cgroup: simplify threadgroup locking" This reverts commit b5ba75b5fc0e8404e2c50cb68f39bb6a53fc916f. d59cfc09c32a ("sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem") and b5ba75b5fc0e ("cgroup: simplify threadgroup locking") changed how cgroup synchronizes against task fork and exits so that it uses global percpu_rwsem instead of per-process rwsem; unfortunately, the write [un]lock paths of percpu_rwsem always involve synchronize_rcu_expedited() which turned out to be too expensive. Improvements for percpu_rwsem are scheduled to be merged in the coming v4.4-rc1 merge window which alleviates this issue. For now, revert the two commits to restore per-process rwsem. They will be re-applied for the v4.4-rc1 merge window. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/g/55F8097A.7000206@de.ibm.com Reported-by: Christian Borntraeger Cc: Oleg Nesterov Cc: "Paul E. McKenney" Cc: Peter Zijlstra Cc: Paolo Bonzini Cc: stable@vger.kernel.org # v4.2+ --- kernel/cgroup.c | 45 +++++++++++++++++++++++++++++++++------------ 1 file changed, 33 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2cf0f79f1fc9..115091efa889 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2460,13 +2460,14 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, if (!cgrp) return -ENODEV; - percpu_down_write(&cgroup_threadgroup_rwsem); +retry_find_task: rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { + rcu_read_unlock(); ret = -ESRCH; - goto out_unlock_rcu; + goto out_unlock_cgroup; } } else { tsk = current; @@ -2482,23 +2483,37 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, */ if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; - goto out_unlock_rcu; + rcu_read_unlock(); + goto out_unlock_cgroup; } get_task_struct(tsk); rcu_read_unlock(); + percpu_down_write(&cgroup_threadgroup_rwsem); + if (threadgroup) { + if (!thread_group_leader(tsk)) { + /* + * a race with de_thread from another thread's exec() + * may strip us of our leadership, if this happens, + * there is no choice but to throw this task away and + * try again; this is + * "double-double-toil-and-trouble-check locking". + */ + percpu_up_write(&cgroup_threadgroup_rwsem); + put_task_struct(tsk); + goto retry_find_task; + } + } + ret = cgroup_procs_write_permission(tsk, cgrp, of); if (!ret) ret = cgroup_attach_task(cgrp, tsk, threadgroup); - put_task_struct(tsk); - goto out_unlock_threadgroup; - -out_unlock_rcu: - rcu_read_unlock(); -out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); + + put_task_struct(tsk); +out_unlock_cgroup: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } @@ -2643,8 +2658,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); - percpu_down_write(&cgroup_threadgroup_rwsem); - /* look up all csses currently attached to @cgrp's subtree */ down_read(&css_set_rwsem); css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) { @@ -2700,8 +2713,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) goto out_finish; last_task = task; + percpu_down_write(&cgroup_threadgroup_rwsem); + /* raced against de_thread() from another thread? */ + if (!thread_group_leader(task)) { + percpu_up_write(&cgroup_threadgroup_rwsem); + put_task_struct(task); + continue; + } + ret = cgroup_migrate(src_cset->dfl_cgrp, task, true); + percpu_up_write(&cgroup_threadgroup_rwsem); put_task_struct(task); if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret)) @@ -2711,7 +2733,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) out_finish: cgroup_migrate_finish(&preloaded_csets); - percpu_up_write(&cgroup_threadgroup_rwsem); return ret; } -- cgit v1.2.3 From 0c986253b939cc14c69d4adbe2b4121bdf4aa220 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 16 Sep 2015 11:51:12 -0400 Subject: Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem" This reverts commit d59cfc09c32a2ae31f1c3bc2983a0cd79afb3f14. d59cfc09c32a ("sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem") and b5ba75b5fc0e ("cgroup: simplify threadgroup locking") changed how cgroup synchronizes against task fork and exits so that it uses global percpu_rwsem instead of per-process rwsem; unfortunately, the write [un]lock paths of percpu_rwsem always involve synchronize_rcu_expedited() which turned out to be too expensive. Improvements for percpu_rwsem are scheduled to be merged in the coming v4.4-rc1 merge window which alleviates this issue. For now, revert the two commits to restore per-process rwsem. They will be re-applied for the v4.4-rc1 merge window. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/g/55F8097A.7000206@de.ibm.com Reported-by: Christian Borntraeger Cc: Oleg Nesterov Cc: "Paul E. McKenney" Cc: Peter Zijlstra Cc: Paolo Bonzini Cc: stable@vger.kernel.org # v4.2+ --- kernel/cgroup.c | 77 ++++++++++++++++++++++++++++++++++++++++++--------------- kernel/fork.c | 4 +++ 2 files changed, 61 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 115091efa889..2c9eae6ad970 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -46,7 +46,6 @@ #include #include #include -#include #include #include #include @@ -104,8 +103,6 @@ static DEFINE_SPINLOCK(cgroup_idr_lock); */ static DEFINE_SPINLOCK(release_agent_path_lock); -struct percpu_rw_semaphore cgroup_threadgroup_rwsem; - #define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ @@ -874,6 +871,48 @@ static struct css_set *find_css_set(struct css_set *old_cset, return cset; } +void cgroup_threadgroup_change_begin(struct task_struct *tsk) +{ + down_read(&tsk->signal->group_rwsem); +} + +void cgroup_threadgroup_change_end(struct task_struct *tsk) +{ + up_read(&tsk->signal->group_rwsem); +} + +/** + * threadgroup_lock - lock threadgroup + * @tsk: member task of the threadgroup to lock + * + * Lock the threadgroup @tsk belongs to. No new task is allowed to enter + * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or + * change ->group_leader/pid. This is useful for cases where the threadgroup + * needs to stay stable across blockable operations. + * + * fork and exit explicitly call threadgroup_change_{begin|end}() for + * synchronization. While held, no new task will be added to threadgroup + * and no existing live task will have its PF_EXITING set. + * + * de_thread() does threadgroup_change_{begin|end}() when a non-leader + * sub-thread becomes a new leader. + */ +static void threadgroup_lock(struct task_struct *tsk) +{ + down_write(&tsk->signal->group_rwsem); +} + +/** + * threadgroup_unlock - unlock threadgroup + * @tsk: member task of the threadgroup to unlock + * + * Reverse threadgroup_lock(). + */ +static inline void threadgroup_unlock(struct task_struct *tsk) +{ + up_write(&tsk->signal->group_rwsem); +} + static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kf_root->kn->priv; @@ -2074,9 +2113,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp, lockdep_assert_held(&css_set_rwsem); /* - * We are synchronized through cgroup_threadgroup_rwsem against - * PF_EXITING setting such that we can't race against cgroup_exit() - * changing the css_set to init_css_set and dropping the old one. + * We are synchronized through threadgroup_lock() against PF_EXITING + * setting such that we can't race against cgroup_exit() changing the + * css_set to init_css_set and dropping the old one. */ WARN_ON_ONCE(tsk->flags & PF_EXITING); old_cset = task_css_set(tsk); @@ -2133,11 +2172,10 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) * @src_cset and add it to @preloaded_csets, which should later be cleaned * up by cgroup_migrate_finish(). * - * This function may be called without holding cgroup_threadgroup_rwsem - * even if the target is a process. Threads may be created and destroyed - * but as long as cgroup_mutex is not dropped, no new css_set can be put - * into play and the preloaded css_sets are guaranteed to cover all - * migrations. + * This function may be called without holding threadgroup_lock even if the + * target is a process. Threads may be created and destroyed but as long + * as cgroup_mutex is not dropped, no new css_set can be put into play and + * the preloaded css_sets are guaranteed to cover all migrations. */ static void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, @@ -2240,7 +2278,7 @@ err: * @threadgroup: whether @leader points to the whole process or a single task * * Migrate a process or task denoted by @leader to @cgrp. If migrating a - * process, the caller must be holding cgroup_threadgroup_rwsem. The + * process, the caller must be holding threadgroup_lock of @leader. The * caller is also responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). @@ -2368,7 +2406,7 @@ out_release_tset: * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * - * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. + * Call holding cgroup_mutex and threadgroup_lock of @leader. */ static int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) @@ -2490,7 +2528,7 @@ retry_find_task: get_task_struct(tsk); rcu_read_unlock(); - percpu_down_write(&cgroup_threadgroup_rwsem); + threadgroup_lock(tsk); if (threadgroup) { if (!thread_group_leader(tsk)) { /* @@ -2500,7 +2538,7 @@ retry_find_task: * try again; this is * "double-double-toil-and-trouble-check locking". */ - percpu_up_write(&cgroup_threadgroup_rwsem); + threadgroup_unlock(tsk); put_task_struct(tsk); goto retry_find_task; } @@ -2510,7 +2548,7 @@ retry_find_task: if (!ret) ret = cgroup_attach_task(cgrp, tsk, threadgroup); - percpu_up_write(&cgroup_threadgroup_rwsem); + threadgroup_unlock(tsk); put_task_struct(tsk); out_unlock_cgroup: @@ -2713,17 +2751,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) goto out_finish; last_task = task; - percpu_down_write(&cgroup_threadgroup_rwsem); + threadgroup_lock(task); /* raced against de_thread() from another thread? */ if (!thread_group_leader(task)) { - percpu_up_write(&cgroup_threadgroup_rwsem); + threadgroup_unlock(task); put_task_struct(task); continue; } ret = cgroup_migrate(src_cset->dfl_cgrp, task, true); - percpu_up_write(&cgroup_threadgroup_rwsem); + threadgroup_unlock(task); put_task_struct(task); if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret)) @@ -5045,7 +5083,6 @@ int __init cgroup_init(void) unsigned long key; int ssid, err; - BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); diff --git a/kernel/fork.c b/kernel/fork.c index 7d5f0f118a63..2845623fb582 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1149,6 +1149,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) tty_audit_fork(sig); sched_autogroup_fork(sig); +#ifdef CONFIG_CGROUPS + init_rwsem(&sig->group_rwsem); +#endif + sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; -- cgit v1.2.3 From ac5be6b47e8bd25b62bed2c82cda7398999f59e9 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 22 Sep 2015 14:58:49 -0700 Subject: userfaultfd: revert "userfaultfd: waitqueue: add nr wake parameter to __wake_up_locked_key" This reverts commit 51360155eccb907ff8635bd10fc7de876408c2e0 and adapts fs/userfaultfd.c to use the old version of that function. It didn't look robust to call __wake_up_common with "nr == 1" when we absolutely require wakeall semantics, but we've full control of what we insert in the two waitqueue heads of the blocked userfaults. No exclusive waitqueue risks to be inserted into those two waitqueue heads so we can as well stick to "nr == 1" of the old code and we can rely purely on the fact no waitqueue inserted in one of the two waitqueue heads we must enforce as wakeall, has wait->flags WQ_FLAG_EXCLUSIVE set. Signed-off-by: Andrea Arcangeli Cc: Dr. David Alan Gilbert Cc: Michael Ellerman Cc: Shuah Khan Cc: Thierry Reding Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/wait.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 272d9322bc5d..052e02672d12 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -106,10 +106,9 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) } EXPORT_SYMBOL_GPL(__wake_up_locked); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr, - void *key) +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) { - __wake_up_common(q, mode, nr, 0, key); + __wake_up_common(q, mode, 1, 0, key); } EXPORT_SYMBOL_GPL(__wake_up_locked_key); @@ -284,7 +283,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, if (!list_empty(&wait->task_list)) list_del_init(&wait->task_list); else if (waitqueue_active(q)) - __wake_up_locked_key(q, mode, 1, key); + __wake_up_locked_key(q, mode, key); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL(abort_exclusive_wait); -- cgit v1.2.3