4 files changed, 257 insertions, 252 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3561d305b1e0..40c2427806c9 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -907,6 +907,11 @@ unsigned short css_id(struct cgroup_subsys_state *css);
 struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
                                          struct cgroup_subsys *ss);
 
+/* XXX: temporary */
+struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
+                                       struct cgroup_subsys *ss);
+struct cftype *__file_cft(struct file *file);
+
 #else /* !CONFIG_CGROUPS */
 
 static inline int cgroup_init_early(void) { return 0; }
diff --git a/init/Kconfig b/init/Kconfig
index 3ecd8a1178f1..3ca5b8110b0c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -861,7 +861,6 @@ 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
@@ -928,6 +927,7 @@ 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)
@@ -1167,7 +1167,6 @@ config UIDGID_STRICT_TYPE_CHECKS
 
 config SCHED_AUTOGROUP
         bool "Automatic process group scheduling"
-        select EVENTFD
         select CGROUPS
         select CGROUP_SCHED
         select FAIR_GROUP_SCHED
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8bd9cfdc70d7..4bccaa7dda35 100644
--- a/kernel/cgroup.c
+++ b/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>
 
@@ -156,36 +153,6 @@ struct css_id {
         unsigned short stack[0]; /* Array of Length (depth+1) */
 };
 
-/*
- * 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);
@@ -235,8 +202,8 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
  * keep accessing it outside the said locks.  This function may return
  * %NULL if @cgrp doesn't have @subsys_id enabled.
  */
-static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
-                                              struct cgroup_subsys *ss)
+struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
+                                       struct cgroup_subsys *ss)
 {
         if (ss)
                 return rcu_dereference_check(cgrp->subsys[ss->subsys_id],
@@ -2663,7 +2630,7 @@ static const struct inode_operations cgroup_dir_inode_operations = {
 /*
  * Check if a file is a control file
  */
-static inline struct cftype *__file_cft(struct file *file)
+struct cftype *__file_cft(struct file *file)
 {
         if (file_inode(file)->i_fop != &cgroup_file_operations)
                 return ERR_PTR(-EINVAL);
@@ -3949,202 +3916,6 @@ 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)
 {
@@ -4170,11 +3941,6 @@ static struct cftype cgroup_base_files[] = {
                 .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,
                 .read_u64 = cgroup_clone_children_read,
@@ -4666,7 +4432,6 @@ 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;
@@ -4741,18 +4506,6 @@ 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;
 };
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 13b9d0f221b8..02dae3292668 100644
--- a/mm/memcontrol.c
+++ b/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>
@@ -226,6 +228,36 @@ struct mem_cgroup_eventfd_list {
         struct eventfd_ctx *eventfd;
 };
 
+/*
+ * 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;
+};
+
 static void mem_cgroup_threshold(struct mem_cgroup *memcg);
 static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
 
@@ -5947,6 +5979,202 @@ static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
 }
 #endif
 
+/*
+ * 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 struct cftype mem_cgroup_files[] = {
         {
                 .name = "usage_in_bytes",
@@ -5994,6 +6222,12 @@ static struct cftype mem_cgroup_files[] = {
                 .read_u64 = mem_cgroup_hierarchy_read,
         },
         {
+                .name = "cgroup.event_control",
+                .write_string = cgroup_write_event_control,
+                .flags = CFTYPE_NO_PREFIX,
+                .mode = S_IWUGO,
+        },
+        {
                 .name = "swappiness",
                 .read_u64 = mem_cgroup_swappiness_read,
                 .write_u64 = mem_cgroup_swappiness_write,
@@ -6326,6 +6560,20 @@ 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 cgroup *cgrp = css->cgroup;
+        struct 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(&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);
 
         kmem_cgroup_css_offline(memcg);