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()
  ...

2 files changed, 47 insertions, 73 deletions

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,