Merge branch 'for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - a new PIDs controller is added.  It turns out that PIDs are actually
   an independent resource from kmem due to the limited PID space.

 - more core preparations for the v2 interface.  Once cpu side interface
   is settled, it should be ready for lifting the devel mask.
   for-4.3-unified-base was temporarily branched so that other trees
   (block) can pull cgroup core changes that blkcg changes depend on.

 - a non-critical idr_preload usage bug fix.

* 'for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: pids: fix invalid get/put usage
  cgroup: introduce cgroup_subsys->legacy_name
  cgroup: don't print subsystems for the default hierarchy
  cgroup: make cftype->private a unsigned long
  cgroup: export cgrp_dfl_root
  cgroup: define controller file conventions
  cgroup: fix idr_preload usage
  cgroup: add documentation for the PIDs controller
  cgroup: implement the PIDs subsystem
  cgroup: allow a cgroup subsystem to reject a fork

3 files changed, 63 insertions, 4 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 93755a6..4d8fcf2 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -34,12 +34,17 @@ struct seq_file;
 
 /* define the enumeration of all cgroup subsystems */
 #define SUBSYS(_x) _x ## _cgrp_id,
+#define SUBSYS_TAG(_t) CGROUP_ ## _t, \
+	__unused_tag_ ## _t = CGROUP_ ## _t - 1,
 enum cgroup_subsys_id {
 #include <linux/cgroup_subsys.h>
 	CGROUP_SUBSYS_COUNT,
 };
+#undef SUBSYS_TAG
 #undef SUBSYS
 
+#define CGROUP_CANFORK_COUNT (CGROUP_CANFORK_END - CGROUP_CANFORK_START)
+
 /* bits in struct cgroup_subsys_state flags field */
 enum {
 	CSS_NO_REF	= (1 << 0), /* no reference counting for this css */
@@ -318,7 +323,7 @@ struct cftype {
 	 * end of cftype array.
 	 */
 	char name[MAX_CFTYPE_NAME];
-	int private;
+	unsigned long private;
 	/*
 	 * If not 0, file mode is set to this value, otherwise it will
 	 * be figured out automatically
@@ -406,7 +411,9 @@ struct cgroup_subsys {
 			      struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup_subsys_state *css,
 		       struct cgroup_taskset *tset);
-	void (*fork)(struct task_struct *task);
+	int (*can_fork)(struct task_struct *task, void **priv_p);
+	void (*cancel_fork)(struct task_struct *task, void *priv);
+	void (*fork)(struct task_struct *task, void *priv);
 	void (*exit)(struct cgroup_subsys_state *css,
 		     struct cgroup_subsys_state *old_css,
 		     struct task_struct *task);
@@ -434,6 +441,9 @@ struct cgroup_subsys {
 	int id;
 	const char *name;
 
+	/* optional, initialized automatically during boot if not set */
+	const char *legacy_name;
+
 	/* link to parent, protected by cgroup_lock() */
 	struct cgroup_root *root;
 
@@ -491,6 +501,7 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
 
 #else	/* CONFIG_CGROUPS */
 
+#define CGROUP_CANFORK_COUNT 0
 #define CGROUP_SUBSYS_COUNT 0
 
 static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {}
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index a593e29..eb7ca55 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -22,6 +22,15 @@
 
 #ifdef CONFIG_CGROUPS
 
+/*
+ * All weight knobs on the default hierarhcy should use the following min,
+ * default and max values.  The default value is the logarithmic center of
+ * MIN and MAX and allows 100x to be expressed in both directions.
+ */
+#define CGROUP_WEIGHT_MIN		1
+#define CGROUP_WEIGHT_DFL		100
+#define CGROUP_WEIGHT_MAX		10000
+
 /* a css_task_iter should be treated as an opaque object */
 struct css_task_iter {
 	struct cgroup_subsys		*ss;
@@ -62,7 +71,12 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		     struct pid *pid, struct task_struct *tsk);
 
 void cgroup_fork(struct task_struct *p);
-void cgroup_post_fork(struct task_struct *p);
+extern int cgroup_can_fork(struct task_struct *p,
+			   void *ss_priv[CGROUP_CANFORK_COUNT]);
+extern void cgroup_cancel_fork(struct task_struct *p,
+			       void *ss_priv[CGROUP_CANFORK_COUNT]);
+extern void cgroup_post_fork(struct task_struct *p,
+			     void *old_ss_priv[CGROUP_CANFORK_COUNT]);
 void cgroup_exit(struct task_struct *p);
 
 int cgroup_init_early(void);
@@ -524,7 +538,13 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 				    struct dentry *dentry) { return -EINVAL; }
 
 static inline void cgroup_fork(struct task_struct *p) {}
-static inline void cgroup_post_fork(struct task_struct *p) {}
+static inline int cgroup_can_fork(struct task_struct *p,
+				  void *ss_priv[CGROUP_CANFORK_COUNT])
+{ return 0; }
+static inline void cgroup_cancel_fork(struct task_struct *p,
+				      void *ss_priv[CGROUP_CANFORK_COUNT]) {}
+static inline void cgroup_post_fork(struct task_struct *p,
+				    void *ss_priv[CGROUP_CANFORK_COUNT]) {}
 static inline void cgroup_exit(struct task_struct *p) {}
 
 static inline int cgroup_init_early(void) { return 0; }
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index e4a96fb..1f36945 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -3,6 +3,17 @@
  *
  * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS.
  */
+
+/*
+ * This file *must* be included with SUBSYS() defined.
+ * SUBSYS_TAG() is a noop if undefined.
+ */
+
+#ifndef SUBSYS_TAG
+#define __TMP_SUBSYS_TAG
+#define SUBSYS_TAG(_x)
+#endif
+
 #if IS_ENABLED(CONFIG_CPUSETS)
 SUBSYS(cpuset)
 #endif
@@ -48,11 +59,28 @@ SUBSYS(hugetlb)
 #endif
 
 /*
+ * Subsystems that implement the can_fork() family of callbacks.
+ */
+SUBSYS_TAG(CANFORK_START)
+
+#if IS_ENABLED(CONFIG_CGROUP_PIDS)
+SUBSYS(pids)
+#endif
+
+SUBSYS_TAG(CANFORK_END)
+
+/*
  * The following subsystems are not supported on the default hierarchy.
  */
 #if IS_ENABLED(CONFIG_CGROUP_DEBUG)
 SUBSYS(debug)
 #endif
+
+#ifdef __TMP_SUBSYS_TAG
+#undef __TMP_SUBSYS_TAG
+#undef SUBSYS_TAG
+#endif
+
 /*
  * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS.
  */