This is a note to let you know that I've just added the patch titled cpuset: make mm migration asynchronous to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: cpuset-make-mm-migration-asynchronous.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From e93ad19d05648397ef3bcb838d26aec06c245dc0 Mon Sep 17 00:00:00 2001 From: Tejun Heo <tj@xxxxxxxxxx> Date: Tue, 19 Jan 2016 12:18:41 -0500 Subject: cpuset: make mm migration asynchronous From: Tejun Heo <tj@xxxxxxxxxx> commit e93ad19d05648397ef3bcb838d26aec06c245dc0 upstream. If "cpuset.memory_migrate" is set, when a process is moved from one cpuset to another with a different memory node mask, pages in used by the process are migrated to the new set of nodes. This was performed synchronously in the ->attach() callback, which is synchronized against process management. Recently, the synchronization was changed from per-process rwsem to global percpu rwsem for simplicity and optimization. Combined with the synchronous mm migration, this led to deadlocks because mm migration could schedule a work item which may in turn try to create a new worker blocking on the process management lock held from cgroup process migration path. This heavy an operation shouldn't be performed synchronously from that deep inside cgroup migration in the first place. This patch punts the actual migration to an ordered workqueue and updates cgroup process migration and cpuset config update paths to flush the workqueue after all locks are released. This way, the operations still seem synchronous to userland without entangling mm migration with process management synchronization. CPU hotplug can also invoke mm migration but there's no reason for it to wait for mm migrations and thus doesn't synchronize against their completions. Signed-off-by: Tejun Heo <tj@xxxxxxxxxx> Reported-and-tested-by: Christian Borntraeger <borntraeger@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- include/linux/cpuset.h | 6 ++++ kernel/cgroup.c | 3 +- kernel/cpuset.c | 71 +++++++++++++++++++++++++++++++++---------------- 3 files changed, 57 insertions(+), 23 deletions(-) --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -137,6 +137,8 @@ static inline void set_mems_allowed(node task_unlock(current); } +extern void cpuset_post_attach_flush(void); + #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } @@ -243,6 +245,10 @@ static inline bool read_mems_allowed_ret return false; } +static inline void cpuset_post_attach_flush(void) +{ +} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -57,7 +57,7 @@ #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */ #include <linux/kthread.h> #include <linux/delay.h> - +#include <linux/cpuset.h> #include <linux/atomic.h> /* @@ -2764,6 +2764,7 @@ out_unlock_rcu: out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); cgroup_kn_unlock(of->kn); + cpuset_post_attach_flush(); return ret ?: nbytes; } --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -286,6 +286,8 @@ static struct cpuset top_cpuset = { static DEFINE_MUTEX(cpuset_mutex); static DEFINE_SPINLOCK(callback_lock); +static struct workqueue_struct *cpuset_migrate_mm_wq; + /* * CPU / memory hotplug is handled asynchronously. */ @@ -971,31 +973,51 @@ static int update_cpumask(struct cpuset } /* - * cpuset_migrate_mm - * - * Migrate memory region from one set of nodes to another. - * - * Temporarilly set tasks mems_allowed to target nodes of migration, - * so that the migration code can allocate pages on these nodes. - * - * While the mm_struct we are migrating is typically from some - * other task, the task_struct mems_allowed that we are hacking - * is for our current task, which must allocate new pages for that - * migrating memory region. + * Migrate memory region from one set of nodes to another. This is + * performed asynchronously as it can be called from process migration path + * holding locks involved in process management. All mm migrations are + * performed in the queued order and can be waited for by flushing + * cpuset_migrate_mm_wq. */ +struct cpuset_migrate_mm_work { + struct work_struct work; + struct mm_struct *mm; + nodemask_t from; + nodemask_t to; +}; + +static void cpuset_migrate_mm_workfn(struct work_struct *work) +{ + struct cpuset_migrate_mm_work *mwork = + container_of(work, struct cpuset_migrate_mm_work, work); + + /* on a wq worker, no need to worry about %current's mems_allowed */ + do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); + mmput(mwork->mm); + kfree(mwork); +} + static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { - struct task_struct *tsk = current; - - tsk->mems_allowed = *to; + struct cpuset_migrate_mm_work *mwork; - do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); + mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); + if (mwork) { + mwork->mm = mm; + mwork->from = *from; + mwork->to = *to; + INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); + queue_work(cpuset_migrate_mm_wq, &mwork->work); + } else { + mmput(mm); + } +} - rcu_read_lock(); - guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed); - rcu_read_unlock(); +void cpuset_post_attach_flush(void) +{ + flush_workqueue(cpuset_migrate_mm_wq); } /* @@ -1096,7 +1118,8 @@ static void update_tasks_nodemask(struct mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); - mmput(mm); + else + mmput(mm); } css_task_iter_end(&it); @@ -1541,11 +1564,11 @@ static void cpuset_attach(struct cgroup_ * @old_mems_allowed is the right nodesets that we * migrate mm from. */ - if (is_memory_migrate(cs)) { + if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); - } - mmput(mm); + else + mmput(mm); } } @@ -1710,6 +1733,7 @@ out_unlock: mutex_unlock(&cpuset_mutex); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); + flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } @@ -2355,6 +2379,9 @@ void __init cpuset_init_smp(void) top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); + + cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); + BUG_ON(!cpuset_migrate_mm_wq); } /** Patches currently in stable-queue which might be from tj@xxxxxxxxxx are queue-4.4/workqueue-handle-numa_no_node-for-unbound-pool_workqueue-lookup.patch queue-4.4/cpuset-make-mm-migration-asynchronous.patch queue-4.4/libata-fix-sff-host-state-machine-locking-while-polling.patch queue-4.4/revert-workqueue-make-sure-delayed-work-run-in-local-cpu.patch -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html