Merge branch 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "Several noteworthy changes.

   - Parav's rdma controller is finally merged. It is very straight
     forward and can limit the abosolute numbers of common rdma
     constructs used by different cgroups.

   - kernel/cgroup.c got too chubby and disorganized. Created
     kernel/cgroup/ subdirectory and moved all cgroup related files
     under kernel/ there and reorganized the core code. This hurts for
     backporting patches but was long overdue.

   - cgroup v2 process listing reimplemented so that it no longer
     depends on allocating a buffer large enough to cache the entire
     result to sort and uniq the output. v2 has always mangled the sort
     order to ensure that users don't depend on the sorted output, so
     this shouldn't surprise anybody. This makes the pid listing
     functions use the same iterators that are used internally, which
     have to have the same iterating capabilities anyway.

   - perf cgroup filtering now works automatically on cgroup v2. This
     patch was posted a long time ago but somehow fell through the
     cracks.

   - misc fixes asnd documentation updates"

* 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (27 commits)
  kernfs: fix locking around kernfs_ops->release() callback
  cgroup: drop the matching uid requirement on migration for cgroup v2
  cgroup, perf_event: make perf_event controller work on cgroup2 hierarchy
  cgroup: misc cleanups
  cgroup: call subsys->*attach() only for subsystems which are actually affected by migration
  cgroup: track migration context in cgroup_mgctx
  cgroup: cosmetic update to cgroup_taskset_add()
  rdmacg: Fixed uninitialized current resource usage
  cgroup: Add missing cgroup-v2 PID controller documentation.
  rdmacg: Added documentation for rdmacg
  IB/core: added support to use rdma cgroup controller
  rdmacg: Added rdma cgroup controller
  cgroup: fix a comment typo
  cgroup: fix RCU related sparse warnings
  cgroup: move namespace code to kernel/cgroup/namespace.c
  cgroup: rename functions for consistency
  cgroup: move v1 mount functions to kernel/cgroup/cgroup-v1.c
  cgroup: separate out cgroup1_kf_syscall_ops
  cgroup: refactor mount path and clearly distinguish v1 and v2 paths
  cgroup: move cgroup v1 specific code to kernel/cgroup/cgroup-v1.c
  ...

6 files changed, 113 insertions, 29 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 861b4677fc5b..3c02404cfce9 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -148,14 +148,18 @@ struct cgroup_subsys_state {
  * set for a task.
  */
 struct css_set {
-	/* Reference count */
-	atomic_t refcount;
-
 	/*
-	 * List running through all cgroup groups in the same hash
-	 * slot. Protected by css_set_lock
+	 * Set of subsystem states, one for each subsystem. This array is
+	 * immutable after creation apart from the init_css_set during
+	 * subsystem registration (at boot time).
 	 */
-	struct hlist_node hlist;
+	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
+
+	/* reference count */
+	atomic_t refcount;
+
+	/* the default cgroup associated with this css_set */
+	struct cgroup *dfl_cgrp;
 
 	/*
 	 * Lists running through all tasks using this cgroup group.
@@ -167,21 +171,29 @@ struct css_set {
 	struct list_head tasks;
 	struct list_head mg_tasks;
 
+	/* all css_task_iters currently walking this cset */
+	struct list_head task_iters;
+
 	/*
-	 * List of cgrp_cset_links pointing at cgroups referenced from this
-	 * css_set.  Protected by css_set_lock.
+	 * On the default hierarhcy, ->subsys[ssid] may point to a css
+	 * attached to an ancestor instead of the cgroup this css_set is
+	 * associated with.  The following node is anchored at
+	 * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to
+	 * iterate through all css's attached to a given cgroup.
 	 */
-	struct list_head cgrp_links;
+	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];
 
-	/* the default cgroup associated with this css_set */
-	struct cgroup *dfl_cgrp;
+	/*
+	 * List running through all cgroup groups in the same hash
+	 * slot. Protected by css_set_lock
+	 */
+	struct hlist_node hlist;
 
 	/*
-	 * Set of subsystem states, one for each subsystem. This array is
-	 * immutable after creation apart from the init_css_set during
-	 * subsystem registration (at boot time).
+	 * List of cgrp_cset_links pointing at cgroups referenced from this
+	 * css_set.  Protected by css_set_lock.
 	 */
-	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
+	struct list_head cgrp_links;
 
 	/*
 	 * List of csets participating in the on-going migration either as
@@ -201,18 +213,6 @@ struct css_set {
 	struct cgroup *mg_dst_cgrp;
 	struct css_set *mg_dst_cset;
 
-	/*
-	 * On the default hierarhcy, ->subsys[ssid] may point to a css
-	 * attached to an ancestor instead of the cgroup this css_set is
-	 * associated with.  The following node is anchored at
-	 * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to
-	 * iterate through all css's attached to a given cgroup.
-	 */
-	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];
-
-	/* all css_task_iters currently walking this cset */
-	struct list_head task_iters;
-
 	/* dead and being drained, ignore for migration */
 	bool dead;
 
@@ -388,6 +388,9 @@ struct cftype {
 	struct list_head node;		/* anchored at ss->cfts */
 	struct kernfs_ops *kf_ops;
 
+	int (*open)(struct kernfs_open_file *of);
+	void (*release)(struct kernfs_open_file *of);
+
 	/*
 	 * read_u64() is a shortcut for the common case of returning a
 	 * single integer. Use it in place of read()
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c83c23f0577b..f6b43fbb141c 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -266,7 +266,7 @@ void css_task_iter_end(struct css_task_iter *it);
  * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
  * @leader: the loop cursor
  * @dst_css: the destination css
- * @tset: takset to iterate
+ * @tset: taskset to iterate
  *
  * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
  * may not contain any.
diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h
new file mode 100644
index 000000000000..e94290b29e99
--- /dev/null
+++ b/include/linux/cgroup_rdma.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com>
+ *
+ * This file is subject to the terms and conditions of version 2 of the GNU
+ * General Public License. See the file COPYING in the main directory of the
+ * Linux distribution for more details.
+ */
+
+#ifndef _CGROUP_RDMA_H
+#define _CGROUP_RDMA_H
+
+#include <linux/cgroup.h>
+
+enum rdmacg_resource_type {
+	RDMACG_RESOURCE_HCA_HANDLE,
+	RDMACG_RESOURCE_HCA_OBJECT,
+	RDMACG_RESOURCE_MAX,
+};
+
+#ifdef CONFIG_CGROUP_RDMA
+
+struct rdma_cgroup {
+	struct cgroup_subsys_state	css;
+
+	/*
+	 * head to keep track of all resource pools
+	 * that belongs to this cgroup.
+	 */
+	struct list_head		rpools;
+};
+
+struct rdmacg_device {
+	struct list_head	dev_node;
+	struct list_head	rpools;
+	char			*name;
+};
+
+/*
+ * APIs for RDMA/IB stack to publish when a device wants to
+ * participate in resource accounting
+ */
+int rdmacg_register_device(struct rdmacg_device *device);
+void rdmacg_unregister_device(struct rdmacg_device *device);
+
+/* APIs for RDMA/IB stack to charge/uncharge pool specific resources */
+int rdmacg_try_charge(struct rdma_cgroup **rdmacg,
+		      struct rdmacg_device *device,
+		      enum rdmacg_resource_type index);
+void rdmacg_uncharge(struct rdma_cgroup *cg,
+		     struct rdmacg_device *device,
+		     enum rdmacg_resource_type index);
+#endif	/* CONFIG_CGROUP_RDMA */
+#endif	/* _CGROUP_RDMA_H */
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 0df0336acee9..d0e597c44585 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -56,6 +56,10 @@ SUBSYS(hugetlb)
 SUBSYS(pids)
 #endif
 
+#if IS_ENABLED(CONFIG_CGROUP_RDMA)
+SUBSYS(rdma)
+#endif
+
 /*
  * The following subsystems are not supported on the default hierarchy.
  */
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 7056238fd9f5..a9b11b8d06f2 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -46,6 +46,7 @@ enum kernfs_node_flag {
 	KERNFS_SUICIDAL		= 0x0400,
 	KERNFS_SUICIDED		= 0x0800,
 	KERNFS_EMPTY_DIR	= 0x1000,
+	KERNFS_HAS_RELEASE	= 0x2000,
 };
 
 /* @flags for kernfs_create_root() */
@@ -175,6 +176,7 @@ struct kernfs_open_file {
 	/* published fields */
 	struct kernfs_node	*kn;
 	struct file		*file;
+	struct seq_file		*seq_file;
 	void			*priv;
 
 	/* private fields, do not use outside kernfs proper */
@@ -185,12 +187,20 @@ struct kernfs_open_file {
 	char			*prealloc_buf;
 
 	size_t			atomic_write_len;
-	bool			mmapped;
+	bool			mmapped:1;
+	bool			released:1;
 	const struct vm_operations_struct *vm_ops;
 };
 
 struct kernfs_ops {
 	/*
+	 * Optional open/release methods.  Both are called with
+	 * @of->seq_file populated.
+	 */
+	int (*open)(struct kernfs_open_file *of);
+	void (*release)(struct kernfs_open_file *of);
+
+	/*
 	 * Read is handled by either seq_file or raw_read().
 	 *
 	 * If seq_show() is present, seq_file path is active.  Other seq
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index d84849c5dc05..0f1813c13687 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -60,6 +60,7 @@
 #include <linux/atomic.h>
 #include <linux/mmu_notifier.h>
 #include <linux/uaccess.h>
+#include <linux/cgroup_rdma.h>
 
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
@@ -1356,6 +1357,12 @@ struct ib_fmr_attr {
 
 struct ib_umem;
 
+struct ib_rdmacg_object {
+#ifdef CONFIG_CGROUP_RDMA
+	struct rdma_cgroup	*cg;		/* owner rdma cgroup */
+#endif
+};
+
 struct ib_ucontext {
 	struct ib_device       *device;
 	struct list_head	pd_list;
@@ -1388,6 +1395,8 @@ struct ib_ucontext {
 	struct list_head	no_private_counters;
 	int                     odp_mrs_count;
 #endif
+
+	struct ib_rdmacg_object	cg_obj;
 };
 
 struct ib_uobject {
@@ -1395,6 +1404,7 @@ struct ib_uobject {
 	struct ib_ucontext     *context;	/* associated user context */
 	void		       *object;		/* containing object */
 	struct list_head	list;		/* link to context's list */
+	struct ib_rdmacg_object	cg_obj;		/* rdmacg object */
 	int			id;		/* index into kernel idr */
 	struct kref		ref;
 	struct rw_semaphore	mutex;		/* protects .live */
@@ -2128,6 +2138,10 @@ struct ib_device {
 	struct attribute_group	     *hw_stats_ag;
 	struct rdma_hw_stats         *hw_stats;
 
+#ifdef CONFIG_CGROUP_RDMA
+	struct rdmacg_device         cg_device;
+#endif
+
 	/**
 	 * The following mandatory functions are used only at device
 	 * registration.  Keep functions such as these at the end of this