cgroup: implement eventfd-based generic API for notifications

This patchset introduces eventfd-based API for notifications in cgroups
and implements memory notifications on top of it.

It uses statistics in memory controler to track memory usage.

Output of time(1) on building kernel on tmpfs:

Root cgroup before changes:
	make -j2  506.37 user 60.93s system 193% cpu 4:52.77 total
Non-root cgroup before changes:
	make -j2  507.14 user 62.66s system 193% cpu 4:54.74 total
Root cgroup after changes (0 thresholds):
	make -j2  507.13 user 62.20s system 193% cpu 4:53.55 total
Non-root cgroup after changes (0 thresholds):
	make -j2  507.70 user 64.20s system 193% cpu 4:55.70 total
Root cgroup after changes (1 thresholds, never crossed):
	make -j2  506.97 user 62.20s system 193% cpu 4:53.90 total
Non-root cgroup after changes (1 thresholds, never crossed):
	make -j2  507.55 user 64.08s system 193% cpu 4:55.63 total

This patch:

Introduce the write-only file "cgroup.event_control" in every cgroup.

To register new notification handler you need:
- create an eventfd;
- open a control file to be monitored. Callbacks register_event() and
  unregister_event() must be defined for the control file;
- 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 notification handler just close eventfd.

If you need notification functionality for a control file you have to
implement callbacks register_event() and unregister_event() in the
struct cftype.

[kamezawa.hiroyu@jp.fujitsu.com: Kconfig fix]
Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Paul Menage <menage@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Dan Malek <dan@embeddedalley.com>
Cc: Vladislav Buzov <vbuzov@embeddedalley.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Alexander Shishkin <virtuoso@slind.org>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 227 insertions, 1 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 1bf4d6db54ab..ea94984a3895 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4,6 +4,10 @@
  *  Based originally on the cpuset system, extracted by Paul Menage
  *  Copyright (C) 2006 Google, Inc
  *
+ *  Notifications support
+ *  Copyright (C) 2009 Nokia Corporation
+ *  Author: Kirill A. Shutemov
+ *
  *  Copyright notices from the original cpuset code:
  *  --------------------------------------------------
  *  Copyright (C) 2003 BULL SA.
@@ -53,6 +57,8 @@
 #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 <asm/atomic.h>
 
@@ -152,6 +158,35 @@ struct css_id {
 	unsigned short stack[0]; /* Array of Length (depth+1) */
 };
 
+/*
+ * cgroup_event represents events which userspace want to recieve.
+ */
+struct cgroup_event {
+	/*
+	 * Cgroup which the event belongs to.
+	 */
+	struct cgroup *cgrp;
+	/*
+	 * 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 */
 
@@ -760,14 +795,28 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 {
 	struct cgroup_subsys *ss;
+	struct cgroup_event *event, *tmp;
 	int ret = 0;
 
 	for_each_subsys(cgrp->root, ss)
 		if (ss->pre_destroy) {
 			ret = ss->pre_destroy(ss, cgrp);
 			if (ret)
-				break;
+				goto out;
 		}
+
+	/*
+	 * Unregister events and notify userspace.
+	 */
+	spin_lock(&cgrp->event_list_lock);
+	list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
+		list_del(&event->list);
+		eventfd_signal(event->eventfd, 1);
+		schedule_work(&event->remove);
+	}
+	spin_unlock(&cgrp->event_list_lock);
+
+out:
 	return ret;
 }
 
@@ -1239,6 +1288,8 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
+	INIT_LIST_HEAD(&cgrp->event_list);
+	spin_lock_init(&cgrp->event_list_lock);
 }
 
 static void init_cgroup_root(struct cgroupfs_root *root)
@@ -2077,6 +2128,16 @@ static const struct inode_operations cgroup_dir_inode_operations = {
 	.rename = cgroup_rename,
 };
 
+/*
+ * Check if a file is a control file
+ */
+static inline struct cftype *__file_cft(struct file *file)
+{
+	if (file->f_dentry->d_inode->i_fop != &cgroup_file_operations)
+		return ERR_PTR(-EINVAL);
+	return __d_cft(file->f_dentry);
+}
+
 static int cgroup_create_file(struct dentry *dentry, mode_t mode,
 				struct super_block *sb)
 {
@@ -2931,6 +2992,166 @@ static int cgroup_write_notify_on_release(struct cgroup *cgrp,
 }
 
 /*
+ * 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 *cgrp = event->cgrp;
+
+	/* TODO: check return code */
+	event->cft->unregister_event(cgrp, event->cft, event->eventfd);
+
+	eventfd_ctx_put(event->eventfd);
+	remove_wait_queue(event->wqh, &event->wait);
+	kfree(event);
+}
+
+/*
+ * 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->cgrp;
+	unsigned long flags = (unsigned long)key;
+
+	if (flags & POLLHUP) {
+		spin_lock(&cgrp->event_list_lock);
+		list_del(&event->list);
+		spin_unlock(&cgrp->event_list_lock);
+		/*
+		 * We are in atomic context, but cgroup_event_remove() may
+		 * sleep, so we have to call it in workqueue.
+		 */
+		schedule_work(&event->remove);
+	}
+
+	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 *cgrp, struct cftype *cft,
+				      const char *buffer)
+{
+	struct cgroup_event *event = NULL;
+	unsigned int efd, cfd;
+	struct file *efile = NULL;
+	struct file *cfile = NULL;
+	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->cgrp = cgrp;
+	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 = eventfd_fget(efd);
+	if (IS_ERR(efile)) {
+		ret = PTR_ERR(efile);
+		goto fail;
+	}
+
+	event->eventfd = eventfd_ctx_fileget(efile);
+	if (IS_ERR(event->eventfd)) {
+		ret = PTR_ERR(event->eventfd);
+		goto fail;
+	}
+
+	cfile = fget(cfd);
+	if (!cfile) {
+		ret = -EBADF;
+		goto fail;
+	}
+
+	/* the process need read permission on control file */
+	ret = file_permission(cfile, MAY_READ);
+	if (ret < 0)
+		goto fail;
+
+	event->cft = __file_cft(cfile);
+	if (IS_ERR(event->cft)) {
+		ret = PTR_ERR(event->cft);
+		goto fail;
+	}
+
+	if (!event->cft->register_event || !event->cft->unregister_event) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	ret = event->cft->register_event(cgrp, event->cft,
+			event->eventfd, buffer);
+	if (ret)
+		goto fail;
+
+	if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
+		event->cft->unregister_event(cgrp, event->cft, event->eventfd);
+		ret = 0;
+		goto fail;
+	}
+
+	spin_lock(&cgrp->event_list_lock);
+	list_add(&event->list, &cgrp->event_list);
+	spin_unlock(&cgrp->event_list_lock);
+
+	fput(cfile);
+	fput(efile);
+
+	return 0;
+
+fail:
+	if (cfile)
+		fput(cfile);
+
+	if (event && event->eventfd && !IS_ERR(event->eventfd))
+		eventfd_ctx_put(event->eventfd);
+
+	if (!IS_ERR_OR_NULL(efile))
+		fput(efile);
+
+	kfree(event);
+
+	return ret;
+}
+
+/*
  * for the common functions, 'private' gives the type of file
  */
 /* for hysterical raisins, we can't put this on the older files */
@@ -2955,6 +3176,11 @@ static struct cftype files[] = {
 		.read_u64 = cgroup_read_notify_on_release,
 		.write_u64 = cgroup_write_notify_on_release,
 	},
+	{
+		.name = CGROUP_FILE_GENERIC_PREFIX "event_control",
+		.write_string = cgroup_write_event_control,
+		.mode = S_IWUGO,
+	},
 };
 
 static struct cftype cft_release_agent = {