Merge branch 'for-3.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "The bulk of changes are cleanups and preparations for the upcoming
  kernfs conversion.

   - cgroup_event mechanism which is and will be used only by memcg is
     moved to memcg.

   - pidlist handling is updated so that it can be served by seq_file.

     Also, the list is not sorted if sane_behavior.  cgroup
     documentation explicitly states that the file is not sorted but it
     has been for quite some time.

   - All cgroup file handling now happens on top of seq_file.  This is
     to prepare for kernfs conversion.  In addition, all operations are
     restructured so that they map 1-1 to kernfs operations.

   - Other cleanups and low-pri fixes"

* 'for-3.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (40 commits)
  cgroup: trivial style updates
  cgroup: remove stray references to css_id
  doc: cgroups: Fix typo in doc/cgroups
  cgroup: fix fail path in cgroup_load_subsys()
  cgroup: fix missing unlock on error in cgroup_load_subsys()
  cgroup: remove for_each_root_subsys()
  cgroup: implement for_each_css()
  cgroup: factor out cgroup_subsys_state creation into create_css()
  cgroup: combine css handling loops in cgroup_create()
  cgroup: reorder operations in cgroup_create()
  cgroup: make for_each_subsys() useable under cgroup_root_mutex
  cgroup: css iterations and css_from_dir() are safe under cgroup_mutex
  cgroup: unify pidlist and other file handling
  cgroup: replace cftype->read_seq_string() with cftype->seq_show()
  cgroup: attach cgroup_open_file to all cgroup files
  cgroup: generalize cgroup_pidlist_open_file
  cgroup: unify read path so that seq_file is always used
  cgroup: unify cgroup_write_X64() and cgroup_write_string()
  cgroup: remove cftype->read(), ->read_map() and ->write()
  hugetlb_cgroup: convert away from cftype->read()
  ...

20 files changed, 1022 insertions, 1098 deletions

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 638bf17ff869..821de56d1580 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/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
 =============
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index e2bc132608fd..2622115276aa 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -577,7 +577,7 @@ Each memcg's numa_stat file includes "total", "file", "anon" and "unevictable"
 per-node page counts including "hierarchical_<counter>" which sums up all
 hierarchical children's values in addition to the memcg's own value.
 
-The ouput format of memory.numa_stat is:
+The output format of memory.numa_stat is:
 
 total=<total pages> N0=<node 0 pages> N1=<node 1 pages> ...
 file=<total file pages> N0=<node 0 pages> N1=<node 1 pages> ...
@@ -670,7 +670,7 @@ page tables.
 
 8.1 Interface
 
-This feature is disabled by default. It can be enabledi (and disabled again) by
+This feature is disabled by default. It can be enabled (and disabled again) by
 writing to memory.move_charge_at_immigrate of the destination cgroup.
 
 If you want to enable it:
diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
index c4d99ed0b418..52e1da16a309 100644
--- a/Documentation/cgroups/resource_counter.txt
+++ b/Documentation/cgroups/resource_counter.txt
@@ -97,8 +97,8 @@ to work with it.
 		(struct res_counter *rc, struct res_counter *top,
 		 unsinged long val)
 
-	Almost same as res_cunter_uncharge() but propagation of uncharge
-	stops when rc == top. This is useful when kill a res_coutner in
+	Almost same as res_counter_uncharge() but propagation of uncharge
+	stops when rc == top. This is useful when kill a res_counter in
 	child cgroup.
 
  2.1 Other accounting routines
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 06534049afba..a760857e6b62 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1303,13 +1303,10 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf,
 	return __blkg_prfill_rwstat(sf, pd, &rwstat);
 }
 
-static int tg_print_cpu_rwstat(struct cgroup_subsys_state *css,
-			       struct cftype *cft, struct seq_file *sf)
+static int tg_print_cpu_rwstat(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, tg_prfill_cpu_rwstat, &blkcg_policy_throtl,
-			  cft->private, true);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_cpu_rwstat,
+			  &blkcg_policy_throtl, seq_cft(sf)->private, true);
 	return 0;
 }
 
@@ -1335,19 +1332,17 @@ static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd,
 	return __blkg_prfill_u64(sf, pd, v);
 }
 
-static int tg_print_conf_u64(struct cgroup_subsys_state *css,
-			     struct cftype *cft, struct seq_file *sf)
+static int tg_print_conf_u64(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_u64,
-			  &blkcg_policy_throtl, cft->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_u64,
+			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
 	return 0;
 }
 
-static int tg_print_conf_uint(struct cgroup_subsys_state *css,
-			      struct cftype *cft, struct seq_file *sf)
+static int tg_print_conf_uint(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_uint,
-			  &blkcg_policy_throtl, cft->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_uint,
+			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
 	return 0;
 }
 
@@ -1428,40 +1423,40 @@ static struct cftype throtl_files[] = {
 	{
 		.name = "throttle.read_bps_device",
 		.private = offsetof(struct throtl_grp, bps[READ]),
-		.read_seq_string = tg_print_conf_u64,
+		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
 		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_bps_device",
 		.private = offsetof(struct throtl_grp, bps[WRITE]),
-		.read_seq_string = tg_print_conf_u64,
+		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
 		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.read_iops_device",
 		.private = offsetof(struct throtl_grp, iops[READ]),
-		.read_seq_string = tg_print_conf_uint,
+		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
 		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_iops_device",
 		.private = offsetof(struct throtl_grp, iops[WRITE]),
-		.read_seq_string = tg_print_conf_uint,
+		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
 		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.io_service_bytes",
 		.private = offsetof(struct tg_stats_cpu, service_bytes),
-		.read_seq_string = tg_print_cpu_rwstat,
+		.seq_show = tg_print_cpu_rwstat,
 	},
 	{
 		.name = "throttle.io_serviced",
 		.private = offsetof(struct tg_stats_cpu, serviced),
-		.read_seq_string = tg_print_cpu_rwstat,
+		.seq_show = tg_print_cpu_rwstat,
 	},
 	{ }	/* terminate */
 };
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 4d5cec1ad80d..744833b630c6 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1632,11 +1632,11 @@ static u64 cfqg_prfill_weight_device(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, cfqg->dev_weight);
 }
 
-static int cfqg_print_weight_device(struct cgroup_subsys_state *css,
-				    struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_weight_device(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_weight_device,
-			  &blkcg_policy_cfq, 0, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_weight_device, &blkcg_policy_cfq,
+			  0, false);
 	return 0;
 }
 
@@ -1650,26 +1650,23 @@ static u64 cfqg_prfill_leaf_weight_device(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, cfqg->dev_leaf_weight);
 }
 
-static int cfqg_print_leaf_weight_device(struct cgroup_subsys_state *css,
-					 struct cftype *cft,
-					 struct seq_file *sf)
+static int cfqg_print_leaf_weight_device(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_leaf_weight_device,
-			  &blkcg_policy_cfq, 0, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_leaf_weight_device, &blkcg_policy_cfq,
+			  0, false);
 	return 0;
 }
 
-static int cfq_print_weight(struct cgroup_subsys_state *css, struct cftype *cft,
-			    struct seq_file *sf)
+static int cfq_print_weight(struct seq_file *sf, void *v)
 {
-	seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_weight);
+	seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_weight);
 	return 0;
 }
 
-static int cfq_print_leaf_weight(struct cgroup_subsys_state *css,
-				 struct cftype *cft, struct seq_file *sf)
+static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
 {
-	seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_leaf_weight);
+	seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_leaf_weight);
 	return 0;
 }
 
@@ -1762,23 +1759,17 @@ static int cfq_set_leaf_weight(struct cgroup_subsys_state *css,
 	return __cfq_set_weight(css, cft, val, true);
 }
 
-static int cfqg_print_stat(struct cgroup_subsys_state *css, struct cftype *cft,
-			   struct seq_file *sf)
+static int cfqg_print_stat(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, blkg_prfill_stat, &blkcg_policy_cfq,
-			  cft->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+			  &blkcg_policy_cfq, seq_cft(sf)->private, false);
 	return 0;
 }
 
-static int cfqg_print_rwstat(struct cgroup_subsys_state *css,
-			     struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_rwstat(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, blkg_prfill_rwstat, &blkcg_policy_cfq,
-			  cft->private, true);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+			  &blkcg_policy_cfq, seq_cft(sf)->private, true);
 	return 0;
 }
 
@@ -1798,23 +1789,19 @@ static u64 cfqg_prfill_rwstat_recursive(struct seq_file *sf,
 	return __blkg_prfill_rwstat(sf, pd, &sum);
 }
 
-static int cfqg_print_stat_recursive(struct cgroup_subsys_state *css,
-				     struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_stat_recursive(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_stat_recursive,
-			  &blkcg_policy_cfq, cft->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_stat_recursive, &blkcg_policy_cfq,
+			  seq_cft(sf)->private, false);
 	return 0;
 }
 
-static int cfqg_print_rwstat_recursive(struct cgroup_subsys_state *css,
-				       struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_rwstat_recursive,
-			  &blkcg_policy_cfq, cft->private, true);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_rwstat_recursive, &blkcg_policy_cfq,
+			  seq_cft(sf)->private, true);
 	return 0;
 }
 
@@ -1835,13 +1822,11 @@ static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf,
 }
 
 /* print avg_queue_size */
-static int cfqg_print_avg_queue_size(struct cgroup_subsys_state *css,
-				     struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_avg_queue_size(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_avg_queue_size,
-			  &blkcg_policy_cfq, 0, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_avg_queue_size, &blkcg_policy_cfq,
+			  0, false);
 	return 0;
 }
 #endif	/* CONFIG_DEBUG_BLK_CGROUP */
@@ -1851,14 +1836,14 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "weight_device",
 		.flags = CFTYPE_ONLY_ON_ROOT,
-		.read_seq_string = cfqg_print_leaf_weight_device,
+		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
 		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
 		.flags = CFTYPE_ONLY_ON_ROOT,
-		.read_seq_string = cfq_print_leaf_weight,
+		.seq_show = cfq_print_leaf_weight,
 		.write_u64 = cfq_set_leaf_weight,
 	},
 
@@ -1866,26 +1851,26 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "weight_device",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.read_seq_string = cfqg_print_weight_device,
+		.seq_show = cfqg_print_weight_device,
 		.write_string = cfqg_set_weight_device,
 		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.read_seq_string = cfq_print_weight,
+		.seq_show = cfq_print_weight,
 		.write_u64 = cfq_set_weight,
 	},
 
 	{
 		.name = "leaf_weight_device",
-		.read_seq_string = cfqg_print_leaf_weight_device,
+		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
 		.max_write_len = 256,
 	},
 	{
 		.name = "leaf_weight",
-		.read_seq_string = cfq_print_leaf_weight,
+		.seq_show = cfq_print_leaf_weight,
 		.write_u64 = cfq_set_leaf_weight,
 	},
 
@@ -1893,114 +1878,114 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "time",
 		.private = offsetof(struct cfq_group, stats.time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "sectors",
 		.private = offsetof(struct cfq_group, stats.sectors),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "io_service_bytes",
 		.private = offsetof(struct cfq_group, stats.service_bytes),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_serviced",
 		.private = offsetof(struct cfq_group, stats.serviced),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_service_time",
 		.private = offsetof(struct cfq_group, stats.service_time),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_wait_time",
 		.private = offsetof(struct cfq_group, stats.wait_time),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_merged",
 		.private = offsetof(struct cfq_group, stats.merged),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_queued",
 		.private = offsetof(struct cfq_group, stats.queued),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 
 	/* the same statictics which cover the cfqg and its descendants */
 	{
 		.name = "time_recursive",
 		.private = offsetof(struct cfq_group, stats.time),
-		.read_seq_string = cfqg_print_stat_recursive,
+		.seq_show = cfqg_print_stat_recursive,
 	},
 	{
 		.name = "sectors_recursive",
 		.private = offsetof(struct cfq_group, stats.sectors),
-		.read_seq_string = cfqg_print_stat_recursive,
+		.seq_show = cfqg_print_stat_recursive,
 	},
 	{
 		.name = "io_service_bytes_recursive",
 		.private = offsetof(struct cfq_group, stats.service_bytes),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_serviced_recursive",
 		.private = offsetof(struct cfq_group, stats.serviced),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_service_time_recursive",
 		.private = offsetof(struct cfq_group, stats.service_time),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_wait_time_recursive",
 		.private = offsetof(struct cfq_group, stats.wait_time),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_merged_recursive",
 		.private = offsetof(struct cfq_group, stats.merged),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_queued_recursive",
 		.private = offsetof(struct cfq_group, stats.queued),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 	{
 		.name = "avg_queue_size",
-		.read_seq_string = cfqg_print_avg_queue_size,
+		.seq_show = cfqg_print_avg_queue_size,
 	},
 	{
 		.name = "group_wait_time",
 		.private = offsetof(struct cfq_group, stats.group_wait_time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "idle_time",
 		.private = offsetof(struct cfq_group, stats.idle_time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "empty_time",
 		.private = offsetof(struct cfq_group, stats.empty_time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "dequeue",
 		.private = offsetof(struct cfq_group, stats.dequeue),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "unaccounted_time",
 		.private = offsetof(struct cfq_group, stats.unaccounted_time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 #endif	/* CONFIG_DEBUG_BLK_CGROUP */
 	{ }	/* terminate */
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index fbcc851ed5a5..61bcfc21d2a0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -163,7 +163,6 @@ static struct cgroup_subsys_state *bcachecg_create(struct cgroup *cgroup)
 static void bcachecg_destroy(struct cgroup *cgroup)
 {
 	struct bch_cgroup *cg = cgroup_to_bcache(cgroup);
-	free_css_id(&bcache_subsys, &cg->css);
 	kfree(cg);
 }
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 39c1d9469677..5c097596104b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -21,6 +21,7 @@
 #include <linux/xattr.h>
 #include <linux/fs.h>
 #include <linux/percpu-refcount.h>
+#include <linux/seq_file.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -28,8 +29,6 @@ struct cgroupfs_root;
 struct cgroup_subsys;
 struct inode;
 struct cgroup;
-struct css_id;
-struct eventfd_ctx;
 
 extern int cgroup_init_early(void);
 extern int cgroup_init(void);
@@ -79,8 +78,6 @@ struct cgroup_subsys_state {
 	struct cgroup_subsys_state *parent;
 
 	unsigned long flags;
-	/* ID for this css, if possible */
-	struct css_id __rcu *id;
 
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
@@ -239,10 +236,6 @@ 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;
 };
@@ -280,6 +273,9 @@ enum {
 	 * - "tasks" is removed.  Everything should be at process
 	 *   granularity.  Use "cgroup.procs" instead.
 	 *
+	 * - "cgroup.procs" is not sorted.  pids will be unique unless they
+	 *   got recycled inbetween reads.
+	 *
 	 * - "release_agent" and "notify_on_release" are removed.
 	 *   Replacement notification mechanism will be implemented.
 	 *
@@ -320,9 +316,6 @@ struct cgroupfs_root {
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
-	/* A list running through the attached subsystems */
-	struct list_head subsys_list;
-
 	/* The root cgroup for this hierarchy */
 	struct cgroup top_cgroup;
 
@@ -389,16 +382,6 @@ struct css_set {
 };
 
 /*
- * cgroup_map_cb is an abstract callback API for reporting map-valued
- * control files
- */
-
-struct cgroup_map_cb {
-	int (*fill)(struct cgroup_map_cb *cb, const char *key, u64 value);
-	void *state;
-};
-
-/*
  * struct cftype: handler definitions for cgroup control files
  *
  * When reading/writing to a file:
@@ -445,10 +428,6 @@ struct cftype {
 	 */
 	struct cgroup_subsys *ss;
 
-	int (*open)(struct inode *inode, struct file *file);
-	ssize_t (*read)(struct cgroup_subsys_state *css, struct cftype *cft,
-			struct file *file,
-			char __user *buf, size_t nbytes, loff_t *ppos);
 	/*
 	 * read_u64() is a shortcut for the common case of returning a
 	 * single integer. Use it in place of read()
@@ -458,24 +437,14 @@ struct cftype {
 	 * read_s64() is a signed version of read_u64()
 	 */
 	s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft);
-	/*
-	 * read_map() is used for defining a map of key/value
-	 * pairs. It should call cb->fill(cb, key, value) for each
-	 * entry. The key/value pairs (and their ordering) should not
-	 * change between reboots.
-	 */
-	int (*read_map)(struct cgroup_subsys_state *css, struct cftype *cft,
-			struct cgroup_map_cb *cb);
-	/*
-	 * read_seq_string() is used for outputting a simple sequence
-	 * using seqfile.
-	 */
-	int (*read_seq_string)(struct cgroup_subsys_state *css,
-			       struct cftype *cft, struct seq_file *m);
 
-	ssize_t (*write)(struct cgroup_subsys_state *css, struct cftype *cft,
-			 struct file *file,
-			 const char __user *buf, size_t nbytes, loff_t *ppos);
+	/* generic seq_file read interface */
+	int (*seq_show)(struct seq_file *sf, void *v);
+
+	/* optional ops, implement all or none */
+	void *(*seq_start)(struct seq_file *sf, loff_t *ppos);
+	void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos);
+	void (*seq_stop)(struct seq_file *sf, void *v);
 
 	/*
 	 * write_u64() is a shortcut for the common case of accepting
@@ -504,27 +473,6 @@ struct cftype {
 	 * kick type for multiplexing.
 	 */
 	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);
 };
 
 /*
@@ -538,6 +486,26 @@ struct cftype_set {
 };
 
 /*
+ * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.  Don't
+ * access directly.
+ */
+struct cfent {
+	struct list_head		node;
+	struct dentry			*dentry;
+	struct cftype			*type;
+	struct cgroup_subsys_state	*css;
+
+	/* file xattrs */
+	struct simple_xattrs		xattrs;
+};
+
+/* seq_file->private points to the following, only ->priv is public */
+struct cgroup_open_file {
+	struct cfent			*cfe;
+	void				*priv;
+};
+
+/*
  * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details.  This
  * function can be called as long as @cgrp is accessible.
  */
@@ -552,6 +520,18 @@ static inline const char *cgroup_name(const struct cgroup *cgrp)
 	return rcu_dereference(cgrp->name)->name;
 }
 
+static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+{
+	struct cgroup_open_file *of = seq->private;
+	return of->cfe->css;
+}
+
+static inline struct cftype *seq_cft(struct seq_file *seq)
+{
+	struct cgroup_open_file *of = seq->private;
+	return of->cfe->type;
+}
+
 int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
 
@@ -631,12 +611,8 @@ struct cgroup_subsys {
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
 
-	/*
-	 * Link to parent, and list entry in parent's children.
-	 * Protected by cgroup_lock()
-	 */
+	/* link to parent, protected by cgroup_lock() */
 	struct cgroupfs_root *root;
-	struct list_head sibling;
 
 	/* list of cftype_sets */
 	struct list_head cftsets;
diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h
index 3f3788d49362..3e4535876d37 100644
--- a/include/linux/vmpressure.h
+++ b/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,
diff --git a/init/Kconfig b/init/Kconfig
index 5236dc562a36..8d402e33b7fc 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -854,7 +854,6 @@ 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
@@ -921,6 +920,7 @@ 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)
@@ -1160,7 +1160,6 @@ 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 bc1dcabe9217..e2f46ba37f72 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -41,7 +41,6 @@
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/backing-dev.h>
-#include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/magic.h>
 #include <linux/spinlock.h>
@@ -56,15 +55,20 @@
 #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>
 
 /*
+ * pidlists linger the following amount before being destroyed.  The goal
+ * is avoiding frequent destruction in the middle of consecutive read calls
+ * Expiring in the middle is a performance problem not a correctness one.
+ * 1 sec should be enough.
+ */
+#define CGROUP_PIDLIST_DESTROY_DELAY	HZ
+
+/*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
  *
@@ -89,6 +93,19 @@ static DEFINE_MUTEX(cgroup_mutex);
 
 static DEFINE_MUTEX(cgroup_root_mutex);
 
+#define cgroup_assert_mutex_or_rcu_locked()				\
+	rcu_lockdep_assert(rcu_read_lock_held() ||			\
+			   lockdep_is_held(&cgroup_mutex),		\
+			   "cgroup_mutex or RCU read lock required");
+
+#ifdef CONFIG_LOCKDEP
+#define cgroup_assert_mutex_or_root_locked()				\
+	WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&cgroup_mutex) &&	\
+				     !lockdep_is_held(&cgroup_root_mutex)))
+#else
+#define cgroup_assert_mutex_or_root_locked()	do { } while (0)
+#endif
+
 /*
  * cgroup destruction makes heavy use of work items and there can be a lot
  * of concurrent destructions.  Use a separate workqueue so that cgroup
@@ -98,6 +115,12 @@ static DEFINE_MUTEX(cgroup_root_mutex);
 static struct workqueue_struct *cgroup_destroy_wq;
 
 /*
+ * pidlist destructions need to be flushed on cgroup destruction.  Use a
+ * separate workqueue as flush domain.
+ */
+static struct workqueue_struct *cgroup_pidlist_destroy_wq;
+
+/*
  * Generate an array of cgroup subsystem pointers. At boot time, this is
  * populated with the built in subsystems, and modular subsystems are
  * registered after that. The mutable section of this array is protected by
@@ -119,49 +142,6 @@ static struct cgroupfs_root cgroup_dummy_root;
 /* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
 static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;