cgroup: Merge branch 'memcg_event' into for-3.14

Merge v3.12 based patch series to move cgroup_event implementation to
memcg into for-3.14.  The following two commits cause a conflict in
kernel/cgroup.c

  2ff2a7d03bbe4 ("cgroup: kill css_id")
  79bd9814e5ec9 ("cgroup, memcg: move cgroup_event implementation to memcg")

Each patch removes a struct definition from kernel/cgroup.c.  As the
two are adjacent, they cause a context conflict.  Easily resolved by
removing both structs.

Signed-off-by: Tejun Heo <tj@kernel.org>

Documentation/cgroups/cgroups.txt

@@ -24,7 +24,6 @@ CONTENTS:
   2.1 Basic Usage
   2.2 Attaching processes
   2.3 Mounting hierarchies by name
-  2.4 Notification API
 3. Kernel API
   3.1 Overview
   3.2 Synchronization
@@ -472,25 +471,6 @@ you give a subsystem a name.
 The name of the subsystem appears as part of the hierarchy description
 in /proc/mounts and /proc/<pid>/cgroups.
 
-2.4 Notification API
---------------------
-
-There is mechanism which allows to get notifications about changing
-status of a cgroup.
-
-To register a new notification handler you need to:
- - create a file descriptor for event notification using eventfd(2);
- - open a control file to be monitored (e.g. memory.usage_in_bytes);
- - write "<event_fd> <control_fd> <args>" to cgroup.event_control.
-   Interpretation of args is defined by control file implementation;
-
-eventfd will be woken up by control file implementation or when the
-cgroup is removed.
-
-To unregister a notification handler just close eventfd.
-
-NOTE: Support of notifications should be implemented for the control
-file. See documentation for the subsystem.
 
 3. Kernel API
 =============

include/linux/cgroup.h

@@ -29,7 +29,6 @@ struct cgroup_subsys;
 struct inode;
 struct cgroup;
 struct css_id;
-struct eventfd_ctx;
 
 extern int cgroup_init_early(void);
 extern int cgroup_init(void);
@@ -239,10 +238,6 @@ struct cgroup {
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
 
-	/* List of events which userspace want to receive */
-	struct list_head event_list;
-	spinlock_t event_list_lock;
-
 	/* directory xattrs */
 	struct simple_xattrs xattrs;
 };
@@ -506,25 +501,6 @@ struct cftype {
 	int (*trigger)(struct cgroup_subsys_state *css, unsigned int event);
 
 	int (*release)(struct inode *inode, struct file *file);
-
-	/*
-	 * register_event() callback will be used to add new userspace
-	 * waiter for changes related to the cftype. Implement it if
-	 * you want to provide this functionality. Use eventfd_signal()
-	 * on eventfd to send notification to userspace.
-	 */
-	int (*register_event)(struct cgroup_subsys_state *css,
-			      struct cftype *cft, struct eventfd_ctx *eventfd,
-			      const char *args);
-	/*
-	 * unregister_event() callback will be called when userspace
-	 * closes the eventfd or on cgroup removing.
-	 * This callback must be implemented, if you want provide
-	 * notification functionality.
-	 */
-	void (*unregister_event)(struct cgroup_subsys_state *css,
-				 struct cftype *cft,
-				 struct eventfd_ctx *eventfd);
 };
 
 /*

include/linux/vmpressure.h

@@ -7,6 +7,7 @@
 #include <linux/gfp.h>
 #include <linux/types.h>
 #include <linux/cgroup.h>
+#include <linux/eventfd.h>
 
 struct vmpressure {
 	unsigned long scanned;
@@ -33,13 +34,10 @@ extern void vmpressure_init(struct vmpressure *vmpr);
 extern void vmpressure_cleanup(struct vmpressure *vmpr);
 extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg);
 extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr);
-extern struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css);
-extern int vmpressure_register_event(struct cgroup_subsys_state *css,
-				     struct cftype *cft,
+extern int vmpressure_register_event(struct mem_cgroup *memcg,
 				     struct eventfd_ctx *eventfd,
 				     const char *args);
-extern void vmpressure_unregister_event(struct cgroup_subsys_state *css,
-					struct cftype *cft,
+extern void vmpressure_unregister_event(struct mem_cgroup *memcg,
 					struct eventfd_ctx *eventfd);
 #else
 static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,

init/Kconfig

@@ -848,7 +848,6 @@ config NUMA_BALANCING
 
 menuconfig CGROUPS
 	boolean "Control Group support"
-	depends on EVENTFD
 	help
 	  This option adds support for grouping sets of processes together, for
 	  use with process control subsystems such as Cpusets, CFS, memory
@@ -915,6 +914,7 @@ config MEMCG
 	bool "Memory Resource Controller for Control Groups"
 	depends on RESOURCE_COUNTERS
 	select MM_OWNER
+	select EVENTFD
 	help
 	  Provides a memory resource controller that manages both anonymous
 	  memory and page cache. (See Documentation/cgroups/memory.txt)
@@ -1154,7 +1154,6 @@ config UIDGID_STRICT_TYPE_CHECKS
 
 config SCHED_AUTOGROUP
 	bool "Automatic process group scheduling"
-	select EVENTFD
 	select CGROUPS
 	select CGROUP_SCHED
 	select FAIR_GROUP_SCHED

kernel/cgroup.c

@@ -56,11 +56,8 @@
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
-#include <linux/eventfd.h>
-#include <linux/poll.h>
 #include <linux/flex_array.h> /* used in cgroup_attach_task */
 #include <linux/kthread.h>
-#include <linux/file.h>
 
 #include <linux/atomic.h>
 
@@ -132,36 +129,6 @@ struct cfent {
 	struct simple_xattrs		xattrs;
 };
 
-/*
- * cgroup_event represents events which userspace want to receive.
- */
-struct cgroup_event {
-	/*
-	 * css which the event belongs to.
-	 */
-	struct cgroup_subsys_state *css;
-	/*
-	 * Control file which the event associated.
-	 */
-	struct cftype *cft;
-	/*
-	 * eventfd to signal userspace about the event.
-	 */
-	struct eventfd_ctx *eventfd;
-	/*
-	 * Each of these stored in a list by the cgroup.
-	 */
-	struct list_head list;
-	/*
-	 * All fields below needed to unregister event when
-	 * userspace closes eventfd.
-	 */
-	poll_table pt;
-	wait_queue_head_t *wqh;
-	wait_queue_t wait;
-	struct work_struct remove;
-};
-
 /* The list of hierarchy roots */
 
 static LIST_HEAD(cgroup_roots);
@@ -1351,8 +1318,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
 	cgrp->dummy_css.cgroup = cgrp;
-	INIT_LIST_HEAD(&cgrp->event_list);
-	spin_lock_init(&cgrp->event_list_lock);
 	simple_xattrs_init(&cgrp->xattrs);
 }
 
@@ -2626,16 +2591,6 @@ static const struct inode_operations cgroup_dir_inode_operations = {
 	.removexattr = cgroup_removexattr,
 };
 
-/*
- * Check if a file is a control file
- */
-static inline struct cftype *__file_cft(struct file *file)
-{
-	if (file_inode(file)->i_fop != &cgroup_file_operations)
-		return ERR_PTR(-EINVAL);
-	return __d_cft(file->f_dentry);
-}
-
 static int cgroup_create_file(struct dentry *dentry, umode_t mode,
 				struct super_block *sb)
 {
@@ -3915,202 +3870,6 @@ static void cgroup_dput(struct cgroup *cgrp)
 	deactivate_super(sb);
 }
 
-/*
- * Unregister event and free resources.
- *
- * Gets called from workqueue.
- */
-static void cgroup_event_remove(struct work_struct *work)
-{
-	struct cgroup_event *event = container_of(work, struct cgroup_event,
-			remove);
-	struct cgroup_subsys_state *css = event->css;
-
-	remove_wait_queue(event->wqh, &event->wait);
-
-	event->cft->unregister_event(css, event->cft, event->eventfd);
-
-	/* Notify userspace the event is going away. */
-	eventfd_signal(event->eventfd, 1);
-
-	eventfd_ctx_put(event->eventfd);
-	kfree(event);
-	css_put(css);
-}
-
-/*
- * Gets called on POLLHUP on eventfd when user closes it.
- *
- * Called with wqh->lock held and interrupts disabled.
- */
-static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
-		int sync, void *key)
-{
-	struct cgroup_event *event = container_of(wait,
-			struct cgroup_event, wait);
-	struct cgroup *cgrp = event->css->cgroup;
-	unsigned long flags = (unsigned long)key;
-
-	if (flags & POLLHUP) {
-		/*
-		 * If the event has been detached at cgroup removal, we
-		 * can simply return knowing the other side will cleanup
-		 * for us.
-		 *
-		 * We can't race against event freeing since the other
-		 * side will require wqh->lock via remove_wait_queue(),
-		 * which we hold.
-		 */
-		spin_lock(&cgrp->event_list_lock);
-		if (!list_empty(&event->list)) {
-			list_del_init(&event->list);
-			/*
-			 * We are in atomic context, but cgroup_event_remove()
-			 * may sleep, so we have to call it in workqueue.
-			 */
-			schedule_work(&event->remove);
-		}
-		spin_unlock(&cgrp->event_list_lock);
-	}
-
-	return 0;
-}
-
-static void cgroup_event_ptable_queue_proc(struct file *file,
-		wait_queue_head_t *wqh, poll_table *pt)
-{
-	struct cgroup_event *event = container_of(pt,
-			struct cgroup_event, pt);
-
-	event->wqh = wqh;
-	add_wait_queue(wqh, &event->wait);
-}
-
-/*
- * Parse input and register new cgroup event handler.
- *
- * Input must be in format '<event_fd> <control_fd> <args>'.
- * Interpretation of args is defined by control file implementation.
- */
-static int cgroup_write_event_control(struct cgroup_subsys_state *dummy_css,
-				      struct cftype *cft, const char *buffer)
-{
-	struct cgroup *cgrp = dummy_css->cgroup;
-	struct cgroup_event *event;
-	struct cgroup_subsys_state *cfile_css;
-	unsigned int efd, cfd;
-	struct fd efile;
-	struct fd cfile;
-	char *endp;
-	int ret;
-
-	efd = simple_strtoul(buffer, &endp, 10);
-	if (*endp != ' ')
-		return -EINVAL;
-	buffer = endp + 1;
-
-	cfd = simple_strtoul(buffer, &endp, 10);
-	if ((*endp != ' ') && (*endp != '\0'))
-		return -EINVAL;
-	buffer = endp + 1;
-
-	event = kzalloc(sizeof(*event), GFP_KERNEL);
-	if (!event)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&event->list);
-	init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
-	init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
-	INIT_WORK(&event->remove, cgroup_event_remove);
-
-	efile = fdget(efd);
-	if (!efile.file) {
-		ret = -EBADF;
-		goto out_kfree;
-	}
-
-	event->eventfd = eventfd_ctx_fileget(efile.file);
-	if (IS_ERR(event->eventfd)) {
-		ret = PTR_ERR(event->eventfd);
-		goto out_put_efile;
-	}
-
-	cfile = fdget(cfd);
-	if (!cfile.file) {
-		ret = -EBADF;
-		goto out_put_eventfd;
-	}
-
-	/* the process need read permission on control file */
-	/* AV: shouldn't we check that it's been opened for read instead? */
-	ret = inode_permission(file_inode(cfile.file), MAY_READ);
-	if (ret < 0)
-		goto out_put_cfile;
-
-	event->cft = __file_cft(cfile.file);
-	if (IS_ERR(event->cft)) {
-		ret = PTR_ERR(event->cft);
-		goto out_put_cfile;
-	}
-
-	if (!event->cft->ss) {
-		ret = -EBADF;
-		goto out_put_cfile;
-	}
-
-	/*
-	 * Determine the css of @cfile, verify it belongs to the same
-	 * cgroup as cgroup.event_control, and associate @event with it.
-	 * Remaining events are automatically removed on cgroup destruction
-	 * but the removal is asynchronous, so take an extra ref.
-	 */
-	rcu_read_lock();
-
-	ret = -EINVAL;
-	event->css = cgroup_css(cgrp, event->cft->ss);
-	cfile_css = css_from_dir(cfile.file->f_dentry->d_parent, event->cft->ss);
-	if (event->css && event->css == cfile_css && css_tryget(event->css))
-		ret = 0;
-
-	rcu_read_unlock();
-	if (ret)
-		goto out_put_cfile;
-
-	if (!event->cft->register_event || !event->cft->unregister_event) {
-		ret = -EINVAL;
-		goto out_put_css;
-	}
-
-	ret = event->cft->register_event(event->css, event->cft,
-			event->eventfd, buffer);
-	if (ret)
-		goto out_put_css;
-
-	efile.file->f_op->poll(efile.file, &event->pt);
-
-	spin_lock(&cgrp->event_list_lock);
-	list_add(&event->list, &cgrp->event_list);
-	spin_unlock(&cgrp->event_list_lock);
-
-	fdput(cfile);
-	fdput(efile);
-
-	return 0;
-
-out_put_css:
-	css_put(event->css);
-out_put_cfile:
-	fdput(cfile);
-out_put_eventfd:
-	eventfd_ctx_put(event->eventfd);
-out_put_efile:
-	fdput(efile);
-out_kfree:
-	kfree(event);
-
-	return ret;
-}
-
 static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
 				      struct cftype *cft)
 {
@@ -4135,11 +3894,6 @@ static struct cftype cgroup_base_files[] = {
 		.release = cgroup_pidlist_release,
 		.mode = S_IRUGO | S_IWUSR,
 	},
-	{
-		.name = "cgroup.event_control",
-		.write_string = cgroup_write_event_control,
-		.mode = S_IWUGO,
-	},
 	{
 		.name = "cgroup.clone_children",
 		.flags = CFTYPE_INSANE,
@@ -4610,7 +4364,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
 	struct dentry *d = cgrp->dentry;
-	struct cgroup_event *event, *tmp;
 	struct cgroup_subsys *ss;
 	struct cgroup *child;
 	bool empty;
@@ -4685,18 +4438,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	dget(d);
 	cgroup_d_remove_dir(d);
 
-	/*
-	 * Unregister events and notify userspace.
-	 * Notify userspace about cgroup removing only after rmdir of cgroup
-	 * directory to avoid race between userspace and kernelspace.
-	 */
-	spin_lock(&cgrp->event_list_lock);
-	list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
-		list_del_init(&event->list);
-		schedule_work(&event->remove);
-	}
-	spin_unlock(&cgrp->event_list_lock);
-
 	return 0;
 };
 

mm/memcontrol.c

@@ -45,6 +45,7 @@
 #include <linux/swapops.h>
 #include <linux/spinlock.h>
 #include <linux/eventfd.h>
+#include <linux/poll.h>
 #include <linux/sort.h>
 #include <linux/fs.h>
 #include <linux/seq_file.h>
@@ -55,6 +56,7 @@
 #include <linux/cpu.h>
 #include <linux/oom.h>
 #include <linux/lockdep.h>
+#include <linux/file.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -227,6 +229,46 @@ struct mem_cgroup_eventfd_list {
 	struct eventfd_ctx *eventfd;
 };
 
+/*
+ * cgroup_event represents events which userspace want to receive.
+ */
+struct mem_cgroup_event {
+	/*
+	 * memcg which the event belongs to.
+	 */
+	struct mem_cgroup *memcg;
+	/*
+	 * eventfd to signal userspace about the event.
+	 */
+	struct eventfd_ctx *eventfd;
+	/*
+	 * Each of these stored in a list by the cgroup.
+	 */
+	struct list_head list;
+	/*
+	 * register_event() callback will be used to add new userspace
+	 * waiter for changes related to this event.  Use eventfd_signal()
+	 * on eventfd to send notification to userspace.
+	 */
+	int (*register_event)(struct mem_cgroup *memcg,
+			      struct eventfd_ctx *eventfd, const char *args);
+	/*
+	 * unregister_event() callback will be called when userspace closes
+	 * the eventfd or on cgroup removing.  This callback must be set,
+	 * if you want provide notification functionality.
+	 */
+	void (*unregister_event)(struct mem_cgroup *memcg,
+				 struct eventfd_ctx *eventfd);
+	/*
+	 * All fields below needed to unregister event when
+	 * userspace closes eventfd.
+	 */
+	poll_table pt;
+	wait_queue_head_t *wqh;
+	wait_queue_t wait;
+	struct work_struct remove;
+};
+
 static void mem_cgroup_threshold(struct mem_cgroup *memcg);
 static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
 
@@ -331,6 +373,10 @@ struct mem_cgroup {
 	atomic_t	numainfo_updating;
 #endif
 
+	/* List of events which userspace want to receive */
+	struct list_head event_list;
+	spinlock_t event_list_lock;
+
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
 };
@@ -490,11 +536,6 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
 	return &container_of(vmpr, struct mem_cgroup, vmpressure)->css;
 }
 
-struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css)
-{
-	return &mem_cgroup_from_css(css)->vmpressure;
-}
-
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return (memcg == root_mem_cgroup);
@@ -5648,13 +5689,11 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg)
 		mem_cgroup_oom_notify_cb(iter);
 }
 
-static int mem_cgroup_usage_register_event(struct cgroup_subsys_state *css,
-	struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
+static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
+	struct eventfd_ctx *eventfd, const char *args, enum res_type type)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	enum res_type type = MEMFILE_TYPE(cft->private);
 	u64 threshold, usage;
 	int i, size, ret;
 
@@ -5731,13 +5770,23 @@ unlock:
 	return ret;
 }
 
-static void mem_cgroup_usage_unregister_event(struct cgroup_subsys_state *css,
-	struct cftype *cft, struct eventfd_ctx *eventfd)
+static int mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
+	struct eventfd_ctx *eventfd, const char *args)
+{
+	return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEM);
+}
+
+static int memsw_cgroup_usage_register_event(struct mem_cgroup *memcg,
+	struct eventfd_ctx *eventfd, const char *args)
+{
+	return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEMSWAP);
+}
+
+static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
+	struct eventfd_ctx *eventfd, enum res_type type)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	enum res_type type = MEMFILE_TYPE(cft->private);
 	u64 usage;
 	int i, j, size;
 
@@ -5810,14 +5859,23 @@ unlock:
 	mutex_unlock(&memcg->thresholds_lock);
 }
 
-static int mem_cgroup_oom_register_event(struct cgroup_subsys_state *css,
-	struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
+static void mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
+	struct eventfd_ctx *eventfd)
+{
+	return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEM);
+}
+
+static void memsw_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
+	struct eventfd_ctx *eventfd)
+{
+	return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEMSWAP);
+}
+
+static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg,
+	struct eventfd_ctx *eventfd, const char *args)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_eventfd_list *event;
-	enum res_type type = MEMFILE_TYPE(cft->private);
 
-	BUG_ON(type != _OOM_TYPE);
 	event = kmalloc(sizeof(*event),	GFP_KERNEL);
 	if (!event)
 		return -ENOMEM;
@@ -5835,14 +5893,10 @@ static int mem_cgroup_oom_register_event(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static void mem_cgroup_oom_unregister_event(struct cgroup_subsys_state *css,
-	struct cftype *cft, struct eventfd_ctx *eventfd)
+static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg,
+	struct eventfd_ctx *eventfd)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_eventfd_list *ev, *tmp;
-	enum res_type type = MEMFILE_TYPE(cft->private);
-
-	BUG_ON(type != _OOM_TYPE);
 
 	spin_lock(&memcg_oom_lock);
 
@@ -5959,13 +6013,233 @@ static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
 }
 #endif
 
+/*
+ * DO NOT USE IN NEW FILES.
+ *
+ * "cgroup.event_control" implementation.
+ *
+ * This is way over-engineered.  It tries to support fully configurable
+ * events for each user.  Such level of flexibility is completely
+ * unnecessary especially in the light of the planned unified hierarchy.
+ *
+ * Please deprecate this and replace with something simpler if at all
+ * possible.
+ */
+
+/*
+ * Unregister event and free resources.
+ *
+ * Gets called from workqueue.
+ */
+static void memcg_event_remove(struct work_struct *work)
+{
+	struct mem_cgroup_event *event =
+		container_of(work, struct mem_cgroup_event, remove);
+	struct mem_cgroup *memcg = event->memcg;
+
+	remove_wait_queue(event->wqh, &event->wait);
+
+	event->unregister_event(memcg, event->eventfd);
+
+	/* Notify userspace the event is going away. */
+	eventfd_signal(event->eventfd, 1);
+
+	eventfd_ctx_put(event->eventfd);
+	kfree(event);
+	css_put(&memcg->css);
+}
+
+/*
+ * Gets called on POLLHUP on eventfd when user closes it.
+ *
+ * Called with wqh->lock held and interrupts disabled.
+ */
+static int memcg_event_wake(wait_queue_t *wait, unsigned mode,
+			    int sync, void *key)
+{
+	struct mem_cgroup_event *event =
+		container_of(wait, struct mem_cgroup_event, wait);
+	struct mem_cgroup *memcg = event->memcg;
+	unsigned long flags = (unsigned long)key;
+
+	if (flags & POLLHUP) {
+		/*
+		 * If the event has been detached at cgroup removal, we
+		 * can simply return knowing the other side will cleanup
+		 * for us.
+		 *
+		 * We can't race against event freeing since the other
+		 * side will require wqh->lock via remove_wait_queue(),
+		 * which we hold.
+		 */
+		spin_lock(&memcg->event_list_lock);
+		if (!list_empty(&event->list)) {
+			list_del_init(&event->list);
+			/*
+			 * We are in atomic context, but cgroup_event_remove()
+			 * may sleep, so we have to call it in workqueue.
+			 */
+			schedule_work(&event->remove);
+		}
+		spin_unlock(&memcg->event_list_lock);
+	}
+
+	return 0;
+}
+
+static void memcg_event_ptable_queue_proc(struct file *file,
+		wait_queue_head_t *wqh, poll_table *pt)
+{
+	struct mem_cgroup_event *event =
+		container_of(pt, struct mem_cgroup_event, pt);
+
+	event->wqh = wqh;
+	add_wait_queue(wqh, &event->wait);
+}
+
+/*
+ * DO NOT USE IN NEW FILES.
+ *
+ * Parse input and register new cgroup event handler.
+ *
+ * Input must be in format '<event_fd> <control_fd> <args>'.
+ * Interpretation of args is defined by control file implementation.
+ */
+static int memcg_write_event_control(struct cgroup_subsys_state *css,
+				     struct cftype *cft, const char *buffer)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup_event *event;
+	struct cgroup_subsys_state *cfile_css;
+	unsigned int efd, cfd;
+	struct fd efile;
+	struct fd cfile;
+	const char *name;
+	char *endp;
+	int ret;
+
+	efd = simple_strtoul(buffer, &endp, 10);
+	if (*endp != ' ')
+		return -EINVAL;
+	buffer = endp + 1;
+
+	cfd = simple_strtoul(buffer, &endp, 10);
+	if ((*endp != ' ') && (*endp != '\0'))
+		return -EINVAL;
+	buffer = endp + 1;
+
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
+
+	event->memcg = memcg;
+	INIT_LIST_HEAD(&event->list);
+	init_poll_funcptr(&event->pt, memcg_event_ptable_queue_proc);
+	init_waitqueue_func_entry(&event->wait, memcg_event_wake);
+	INIT_WORK(&event->remove, memcg_event_remove);
+
+	efile = fdget(efd);
+	if (!efile.file) {
+		ret = -EBADF;
+		goto out_kfree;
+	}
+
+	event->eventfd = eventfd_ctx_fileget(efile.file);
+	if (IS_ERR(event->eventfd)) {
+		ret = PTR_ERR(event->eventfd);
+		goto out_put_efile;
+	}
+
+	cfile = fdget(cfd);
+	if (!cfile.file) {
+		ret = -EBADF;
+		goto out_put_eventfd;
+	}
+
+	/* the process need read permission on control file */
+	/* AV: shouldn't we check that it's been opened for read instead? */
+	ret = inode_permission(file_inode(cfile.file), MAY_READ);
+	if (ret < 0)
+		goto out_put_cfile;
+
+	/*
+	 * Determine the event callbacks and set them in @event.  This used
+	 * to be done via struct cftype but cgroup core no longer knows
+	 * about these events.  The following is crude but the whole thing
+	 * is for compatibility anyway.
+	 *
+	 * DO NOT ADD NEW FILES.
+	 */
+	name = cfile.file->f_dentry->d_name.name;
+
+	if (!strcmp(name, "memory.usage_in_bytes")) {
+		event->register_event = mem_cgroup_usage_register_event;
+		event->unregister_event = mem_cgroup_usage_unregister_event;
+	} else if (!strcmp(name, "memory.oom_control")) {
+		event->register_event = mem_cgroup_oom_register_event;
+		event->unregister_event = mem_cgroup_oom_unregister_event;
+	} else if (!strcmp(name, "memory.pressure_level")) {
+		event->register_event = vmpressure_register_event;
+		event->unregister_event = vmpressure_unregister_event;
+	} else if (!strcmp(name, "memory.memsw.usage_in_bytes")) {
+		event->register_event = memsw_cgroup_usage_register_event;
+		event->unregister_event = memsw_cgroup_usage_unregister_event;
+	} else {
+		ret = -EINVAL;
+		goto out_put_cfile;
+	}
+
+	/*
+	 * Verify @cfile should belong to @css.  Also, remaining events are
+	 * automatically removed on cgroup destruction but the removal is
+	 * asynchronous, so take an extra ref on @css.
+	 */
+	rcu_read_lock();
+
+	ret = -EINVAL;
+	cfile_css = css_from_dir(cfile.file->f_dentry->d_parent,
+				 &mem_cgroup_subsys);
+	if (cfile_css == css && css_tryget(css))
+		ret = 0;
+
+	rcu_read_unlock();
+	if (ret)
+		goto out_put_cfile;
+
+	ret = event->register_event(memcg, event->eventfd, buffer);
+	if (ret)
+		goto out_put_css;
+
+	efile.file->f_op->poll(efile.file, &event->pt);
+
+	spin_lock(&memcg->event_list_lock);
+	list_add(&event->list, &memcg->event_list);
+	spin_unlock(&memcg->event_list_lock);
+
+	fdput(cfile);
+	fdput(efile);
+
+	return 0;
+
+out_put_css:
+	css_put(css);
+out_put_cfile:
+	fdput(cfile);
+out_put_eventfd:
+	eventfd_ctx_put(event->eventfd);
+out_put_efile:
+	fdput(efile);
+out_kfree:
+	kfree(event);
+
+	return ret;
+}
+
 static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
 		.read = mem_cgroup_read,
-		.register_event = mem_cgroup_usage_register_event,
-		.unregister_event = mem_cgroup_usage_unregister_event,
 	},
 	{
 		.name = "max_usage_in_bytes",
@@ -6005,6 +6279,12 @@ static struct cftype mem_cgroup_files[] = {
 		.write_u64 = mem_cgroup_hierarchy_write,
 		.read_u64 = mem_cgroup_hierarchy_read,
 	},
+	{
+		.name = "cgroup.event_control",		/* XXX: for compat */
+		.write_string = memcg_write_event_control,
+		.flags = CFTYPE_NO_PREFIX,
+		.mode = S_IWUGO,
+	},
 	{
 		.name = "swappiness",
 		.read_u64 = mem_cgroup_swappiness_read,
@@ -6019,14 +6299,10 @@ static struct cftype mem_cgroup_files[] = {
 		.name = "oom_control",
 		.read_map = mem_cgroup_oom_control_read,
 		.write_u64 = mem_cgroup_oom_control_write,
-		.register_event = mem_cgroup_oom_register_event,
-		.unregister_event = mem_cgroup_oom_unregister_event,
 		.private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL),
 	},
 	{
 		.name = "pressure_level",
-		.register_event = vmpressure_register_event,
-		.unregister_event = vmpressure_unregister_event,
 	},
 #ifdef CONFIG_NUMA
 	{
@@ -6074,8 +6350,6 @@ static struct cftype memsw_cgroup_files[] = {
 		.name = "memsw.usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
 		.read = mem_cgroup_read,
-		.register_event = mem_cgroup_usage_register_event,
-		.unregister_event = mem_cgroup_usage_unregister_event,
 	},
 	{
 		.name = "memsw.max_usage_in_bytes",
@@ -6265,6 +6539,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	mutex_init(&memcg->thresholds_lock);
 	spin_lock_init(&memcg->move_lock);
 	vmpressure_init(&memcg->vmpressure);
+	INIT_LIST_HEAD(&memcg->event_list);
+	spin_lock_init(&memcg->event_list_lock);
 
 	return &memcg->css;
 
@@ -6340,6 +6616,19 @@ static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
 static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup_event *event, *tmp;
+
+	/*
+	 * Unregister events and notify userspace.
+	 * Notify userspace about cgroup removing only after rmdir of cgroup
+	 * directory to avoid race between userspace and kernelspace.
+	 */
+	spin_lock(&memcg->event_list_lock);
+	list_for_each_entry_safe(event, tmp, &memcg->event_list, list) {
+		list_del_init(&event->list);
+		schedule_work(&event->remove);
+	}
+	spin_unlock(&memcg->event_list_lock);
 
 	kmem_cgroup_css_offline(memcg);
 

mm/vmpressure.c

@@ -278,8 +278,7 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
 
 /**
  * vmpressure_register_event() - Bind vmpressure notifications to an eventfd
- * @css:	css that is interested in vmpressure notifications
- * @cft:	cgroup control files handle
+ * @memcg:	memcg that is interested in vmpressure notifications
  * @eventfd:	eventfd context to link notifications with
  * @args:	event arguments (used to set up a pressure level threshold)
  *
@@ -289,15 +288,12 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
  * threshold (one of vmpressure_str_levels, i.e. "low", "medium", or
  * "critical").
  *
- * This function should not be used directly, just pass it to (struct
- * cftype).register_event, and then cgroup core will handle everything by
- * itself.
+ * To be used as memcg event method.
  */
-int vmpressure_register_event(struct cgroup_subsys_state *css,
-			      struct cftype *cft, struct eventfd_ctx *eventfd,
-			      const char *args)
+int vmpressure_register_event(struct mem_cgroup *memcg,
+			      struct eventfd_ctx *eventfd, const char *args)
 {
-	struct vmpressure *vmpr = css_to_vmpressure(css);
+	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
 	struct vmpressure_event *ev;
 	int level;
 
@@ -325,23 +321,19 @@ int vmpressure_register_event(struct cgroup_subsys_state *css,
 
 /**
  * vmpressure_unregister_event() - Unbind eventfd from vmpressure
- * @css:	css handle
- * @cft:	cgroup control files handle
+ * @memcg:	memcg handle
  * @eventfd:	eventfd context that was used to link vmpressure with the @cg
  *
  * This function does internal manipulations to detach the @eventfd from
  * the vmpressure notifications, and then frees internal resources
  * associated with the @eventfd (but the @eventfd itself is not freed).
  *
- * This function should not be used directly, just pass it to (struct
- * cftype).unregister_event, and then cgroup core will handle everything
- * by itself.
+ * To be used as memcg event method.
  */
-void vmpressure_unregister_event(struct cgroup_subsys_state *css,
-				 struct cftype *cft,
+void vmpressure_unregister_event(struct mem_cgroup *memcg,
 				 struct eventfd_ctx *eventfd)
 {
-	struct vmpressure *vmpr = css_to_vmpressure(css);
+	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
 	struct vmpressure_event *ev;
 
 	mutex_lock(&vmpr->events_lock);