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

Documentation/cgroups/unified-hierarchy.txt

@@ -23,10 +23,13 @@ CONTENTS
 5. Other Changes
   5-1. [Un]populated Notification
   5-2. Other Core Changes
-  5-3. Per-Controller Changes
+  5-3. Controller File Conventions
-    5-3-1. blkio
+    5-3-1. Format
-    5-3-2. cpuset
+    5-3-2. Control Knobs
-    5-3-3. memory
+  5-4. Per-Controller Changes
+    5-4-1. blkio
+    5-4-2. cpuset
+    5-4-3. memory
 6. Planned Changes
   6-1. CAP for resource control
 
@@ -372,14 +375,75 @@ supported and the interface files "release_agent" and
 - The "cgroup.clone_children" file is removed.
 
 
-5-3. Per-Controller Changes
+5-3. Controller File Conventions
 
-5-3-1. blkio
+5-3-1. Format
+
+In general, all controller files should be in one of the following
+formats whenever possible.
+
+- Values only files
+
+  VAL0 VAL1...\n
+
+- Flat keyed files
+
+  KEY0 VAL0\n
+  KEY1 VAL1\n
+  ...
+
+- Nested keyed files
+
+  KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
+  KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
+  ...
+
+For a writeable file, the format for writing should generally match
+reading; however, controllers may allow omitting later fields or
+implement restricted shortcuts for most common use cases.
+
+For both flat and nested keyed files, only the values for a single key
+can be written at a time.  For nested keyed files, the sub key pairs
+may be specified in any order and not all pairs have to be specified.
+
+
+5-3-2. Control Knobs
+
+- Settings for a single feature should generally be implemented in a
+  single file.
+
+- In general, the root cgroup should be exempt from resource control
+  and thus shouldn't have resource control knobs.
+
+- If a controller implements ratio based resource distribution, the
+  control knob should be named "weight" and have the range [1, 10000]
+  and 100 should be the default value.  The values are chosen to allow
+  enough and symmetric bias in both directions while keeping it
+  intuitive (the default is 100%).
+
+- If a controller implements an absolute resource guarantee and/or
+  limit, the control knobs should be named "min" and "max"
+  respectively.  If a controller implements best effort resource
+  gurantee and/or limit, the control knobs should be named "low" and
+  "high" respectively.
+
+  In the above four control files, the special token "max" should be
+  used to represent upward infinity for both reading and writing.
+
+- If a setting has configurable default value and specific overrides,
+  the default settings should be keyed with "default" and appear as
+  the first entry in the file.  Specific entries can use "default" as
+  its value to indicate inheritance of the default value.
+
+
+5-4. Per-Controller Changes
+
+5-4-1. blkio
 
 - blk-throttle becomes properly hierarchical.
 
 
-5-3-2. cpuset
+5-4-2. cpuset
 
 - Tasks are kept in empty cpusets after hotplug and take on the masks
   of the nearest non-empty ancestor, instead of being moved to it.
@@ -388,7 +452,7 @@ supported and the interface files "release_agent" and
   masks of the nearest non-empty ancestor.
 
 
-5-3-3. memory
+5-4-3. memory
 
 - use_hierarchy is on by default and the cgroup file for the flag is
   not created.

include/linux/cgroup-defs.h

@@ -318,7 +318,7 @@ 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
@@ -434,6 +434,9 @@ 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;
 

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;

kernel/cgroup.c

@@ -145,6 +145,7 @@ static const char *cgroup_subsys_name[] = {
  * part of that cgroup.
  */
 struct cgroup_root cgrp_dfl_root;
+EXPORT_SYMBOL_GPL(cgrp_dfl_root);
 
 /*
  * The default hierarchy always exists but is hidden until mounted for the
@@ -1027,10 +1028,13 @@ static const struct file_operations proc_cgroupstats_operations;
 static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
 			      char *buf)
 {
+	struct cgroup_subsys *ss = cft->ss;
+
 	if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
 	    !(cgrp->root->flags & CGRP_ROOT_NOPREFIX))
 		snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
-			 cft->ss->name, cft->name);
+			 cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
+			 cft->name);
 	else
 		strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
 	return buf;
@@ -1332,9 +1336,10 @@ static int cgroup_show_options(struct seq_file *seq,
 	struct cgroup_subsys *ss;
 	int ssid;
 
-	for_each_subsys(ss, ssid)
+	if (root != &cgrp_dfl_root)
-		if (root->subsys_mask & (1 << ssid))
+		for_each_subsys(ss, ssid)
-			seq_printf(seq, ",%s", ss->name);
+			if (root->subsys_mask & (1 << ssid))
+				seq_printf(seq, ",%s", ss->legacy_name);
 	if (root->flags & CGRP_ROOT_NOPREFIX)
 		seq_puts(seq, ",noprefix");
 	if (root->flags & CGRP_ROOT_XATTR)
@@ -1447,7 +1452,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 		}
 
 		for_each_subsys(ss, i) {
-			if (strcmp(token, ss->name))
+			if (strcmp(token, ss->legacy_name))
 				continue;
 			if (ss->disabled)
 				continue;
@@ -4993,6 +4998,8 @@ int __init cgroup_init_early(void)
 
 		ss->id = i;
 		ss->name = cgroup_subsys_name[i];
+		if (!ss->legacy_name)
+			ss->legacy_name = cgroup_subsys_name[i];
 
 		if (ss->early_init)
 			cgroup_init_subsys(ss, true);
@@ -5136,9 +5143,11 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 			continue;
 
 		seq_printf(m, "%d:", root->hierarchy_id);
-		for_each_subsys(ss, ssid)
+		if (root != &cgrp_dfl_root)
-			if (root->subsys_mask & (1 << ssid))
+			for_each_subsys(ss, ssid)
-				seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+				if (root->subsys_mask & (1 << ssid))
+					seq_printf(m, "%s%s", count++ ? "," : "",
+						   ss->legacy_name);
 		if (strlen(root->name))
 			seq_printf(m, "%sname=%s", count ? "," : "",
 				   root->name);
@@ -5178,7 +5187,7 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
 
 	for_each_subsys(ss, i)
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
-			   ss->name, ss->root->hierarchy_id,
+			   ss->legacy_name, ss->root->hierarchy_id,
 			   atomic_read(&ss->root->nr_cgrps), !ss->disabled);
 
 	mutex_unlock(&cgroup_mutex);
@@ -5400,12 +5409,14 @@ static int __init cgroup_disable(char *str)
 			continue;
 
 		for_each_subsys(ss, i) {
-			if (!strcmp(token, ss->name)) {
+			if (strcmp(token, ss->name) &&
-				ss->disabled = 1;
+			    strcmp(token, ss->legacy_name))
-				printk(KERN_INFO "Disabling %s control group"
+				continue;
-					" subsystem\n", ss->name);
+
-				break;
+			ss->disabled = 1;
-			}
+			printk(KERN_INFO "Disabling %s control group subsystem\n",
+			       ss->name);
+			break;
 		}
 	}
 	return 1;