cgroup, memcg: move cgroup_event implementation to memcg

cgroup_event is way over-designed and tries to build a generic
flexible event mechanism into cgroup - fully customizable event
specification for each user of the interface.  This is utterly
unnecessary and overboard especially in the light of the planned
unified hierarchy as there's gonna be single agent.  Simply generating
events at fixed points, or if that's too restrictive, configureable
cadence or single set of configureable points should be enough.

Thankfully, memcg is the only user and gets to keep it.  Replacing it
with something simpler on sane_behavior is strongly recommended.

This patch moves cgroup_event and "cgroup.event_control"
implementation to mm/memcontrol.c.  Clearing of events on cgroup
destruction is moved from cgroup_destroy_locked() to
mem_cgroup_css_offline(), which shouldn't make any noticeable
difference.

cgroup_css() and __file_cft() are exported to enable the move;
however, this will soon be reverted once the event code is updated to
be memcg specific.

Note that "cgroup.event_control" will now exist only on the hierarchy
with memcg attached to it.  While this change is visible to userland,
it is unlikely to be noticeable as the file has never been meaningful
outside memcg.

Aside from the above change, this is pure code relocation.

v2: Per Li Zefan's comments, init/Kconfig updated accordingly and
    poll.h inclusion moved from cgroup.c to memcontrol.c.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>

1 files changed, 248 insertions, 0 deletions

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);