Merge branch 'for-3.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - xattr support added.  The implementation is shared with tmpfs.  The
   usage is restricted and intended to be used to manage per-cgroup
   metadata by system software.  tmpfs changes are routed through this
   branch with Hugh's permission.

 - cgroup subsystem ID handling simplified.

* 'for-3.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Define CGROUP_SUBSYS_COUNT according the configuration
  cgroup: Assign subsystem IDs during compile time
  cgroup: Do not depend on a given order when populating the subsys array
  cgroup: Wrap subsystem selection macro
  cgroup: Remove CGROUP_BUILTIN_SUBSYS_COUNT
  cgroup: net_prio: Do not define task_netpioidx() when not selected
  cgroup: net_cls: Do not define task_cls_classid() when not selected
  cgroup: net_cls: Move sock_update_classid() declaration to cls_cgroup.h
  cgroup: trivial fixes for Documentation/cgroups/cgroups.txt
  xattr: mark variable as uninitialized to make both gcc and smatch happy
  fs: add missing documentation to simple_xattr functions
  cgroup: add documentation on extended attributes usage
  cgroup: rename subsys_bits to subsys_mask
  cgroup: add xattr support
  cgroup: revise how we re-populate root directory
  xattr: extract simple_xattr code from tmpfs

7 files changed, 102 insertions, 63 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c90eaa80344..df354ae079c 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -17,6 +17,7 @@
 #include <linux/rwsem.h>
 #include <linux/idr.h>
 #include <linux/workqueue.h>
+#include <linux/xattr.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -45,17 +46,13 @@ extern const struct file_operations proc_cgroup_operations;
 
 /* Define the enumeration of all builtin cgroup subsystems */
 #define SUBSYS(_x) _x ## _subsys_id,
+#define IS_SUBSYS_ENABLED(option) IS_ENABLED(option)
 enum cgroup_subsys_id {
 #include <linux/cgroup_subsys.h>
-	CGROUP_BUILTIN_SUBSYS_COUNT
+	CGROUP_SUBSYS_COUNT,
 };
+#undef IS_SUBSYS_ENABLED
 #undef SUBSYS
-/*
- * This define indicates the maximum number of subsystems that can be loaded
- * at once. We limit to this many since cgroupfs_root has subsys_bits to keep
- * track of all of them.
- */
-#define CGROUP_SUBSYS_COUNT (BITS_PER_BYTE*sizeof(unsigned long))
 
 /* Per-subsystem/per-cgroup state maintained by the system. */
 struct cgroup_subsys_state {
@@ -216,6 +213,9 @@ struct cgroup {
 	/* List of events which userspace want to receive */
 	struct list_head event_list;
 	spinlock_t event_list_lock;
+
+	/* directory xattrs */
+	struct simple_xattrs xattrs;
 };
 
 /*
@@ -309,6 +309,9 @@ struct cftype {
 	/* CFTYPE_* flags */
 	unsigned int flags;
 
+	/* file xattrs */
+	struct simple_xattrs xattrs;
+
 	int (*open)(struct inode *inode, struct file *file);
 	ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft,
 			struct file *file,
@@ -394,7 +397,7 @@ struct cftype {
  */
 struct cftype_set {
 	struct list_head		node;	/* chained at subsys->cftsets */
-	const struct cftype		*cfts;
+	struct cftype			*cfts;
 };
 
 struct cgroup_scanner {
@@ -406,8 +409,8 @@ struct cgroup_scanner {
 	void *data;
 };
 
-int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts);
-int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts);
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
+int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 
 int cgroup_is_removed(const struct cgroup *cgrp);
 
@@ -521,7 +524,9 @@ struct cgroup_subsys {
 };
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
+#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
 #include <linux/cgroup_subsys.h>
+#undef IS_SUBSYS_ENABLED
 #undef SUBSYS
 
 static inline struct cgroup_subsys_state *cgroup_subsys_state(
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index dfae957398c..f204a7a9cf3 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -7,73 +7,73 @@
 
 /* */
 
-#ifdef CONFIG_CPUSETS
+#if IS_SUBSYS_ENABLED(CONFIG_CPUSETS)
 SUBSYS(cpuset)
 #endif
 
 /* */
 
-#ifdef CONFIG_CGROUP_DEBUG
+#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_DEBUG)
 SUBSYS(debug)
 #endif
 
 /* */
 
-#ifdef CONFIG_CGROUP_SCHED
+#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_SCHED)
 SUBSYS(cpu_cgroup)
 #endif
 
 /* */
 
-#ifdef CONFIG_CGROUP_CPUACCT
+#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_CPUACCT)
 SUBSYS(cpuacct)
 #endif
 
 /* */
 
-#ifdef CONFIG_MEMCG
+#if IS_SUBSYS_ENABLED(CONFIG_MEMCG)
 SUBSYS(mem_cgroup)
 #endif
 
 /* */
 
-#ifdef CONFIG_CGROUP_DEVICE
+#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_DEVICE)
 SUBSYS(devices)
 #endif
 
 /* */
 
-#ifdef CONFIG_CGROUP_FREEZER
+#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_FREEZER)
 SUBSYS(freezer)
 #endif
 
 /* */
 
-#ifdef CONFIG_NET_CLS_CGROUP
+#if IS_SUBSYS_ENABLED(CONFIG_NET_CLS_CGROUP)
 SUBSYS(net_cls)
 #endif
 
 /* */
 
-#ifdef CONFIG_BLK_CGROUP
+#if IS_SUBSYS_ENABLED(CONFIG_BLK_CGROUP)
 SUBSYS(blkio)
 #endif
 
 /* */
 
-#ifdef CONFIG_CGROUP_PERF
+#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_PERF)
 SUBSYS(perf)
 #endif
 
 /* */
 
-#ifdef CONFIG_NETPRIO_CGROUP
+#if IS_SUBSYS_ENABLED(CONFIG_NETPRIO_CGROUP)
 SUBSYS(net_prio)
 #endif
 
 /* */
 
-#ifdef CONFIG_CGROUP_HUGETLB
+#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_HUGETLB)
 SUBSYS(hugetlb)
 #endif
 
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index bef2cf00b3b..30aa0dc60d7 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -5,6 +5,7 @@
 #include <linux/mempolicy.h>
 #include <linux/pagemap.h>
 #include <linux/percpu_counter.h>
+#include <linux/xattr.h>
 
 /* inode in-kernel data */
 
@@ -18,7 +19,7 @@ struct shmem_inode_info {
 	};
 	struct shared_policy	policy;		/* NUMA memory alloc policy */
 	struct list_head	swaplist;	/* chain of maybes on swap */
-	struct list_head	xattr_list;	/* list of shmem_xattr */
+	struct simple_xattrs	xattrs;		/* list of xattrs */
 	struct inode		vfs_inode;
 };
 
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index e5d12203154..2ace7a60316 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -59,7 +59,9 @@
 
 #ifdef  __KERNEL__
 
+#include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/spinlock.h>
 
 struct inode;
 struct dentry;
@@ -96,6 +98,52 @@ ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name,
 			   char **xattr_value, size_t size, gfp_t flags);
 int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name,
 		  const char *value, size_t size, gfp_t flags);
+
+struct simple_xattrs {
+	struct list_head head;
+	spinlock_t lock;
+};
+
+struct simple_xattr {
+	struct list_head list;
+	char *name;
+	size_t size;
+	char value[0];
+};
+
+/*
+ * initialize the simple_xattrs structure
+ */
+static inline void simple_xattrs_init(struct simple_xattrs *xattrs)
+{
+	INIT_LIST_HEAD(&xattrs->head);
+	spin_lock_init(&xattrs->lock);
+}
+
+/*
+ * free all the xattrs
+ */
+static inline void simple_xattrs_free(struct simple_xattrs *xattrs)
+{
+	struct simple_xattr *xattr, *node;
+
+	list_for_each_entry_safe(xattr, node, &xattrs->head, list) {
+		kfree(xattr->name);
+		kfree(xattr);
+	}
+}
+
+struct simple_xattr *simple_xattr_alloc(const void *value, size_t size);
+int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
+		     void *buffer, size_t size);
+int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
+		     const void *value, size_t size, int flags);
+int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name);
+ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer,
+			  size_t size);
+void simple_xattr_list_add(struct simple_xattrs *xattrs,
+			   struct simple_xattr *new_xattr);
+
 #endif  /*  __KERNEL__  */
 
 #endif	/* _LINUX_XATTR_H */
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index a4dc5b027bd..b6a6eeb3905 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -17,14 +17,16 @@
 #include <linux/hardirq.h>
 #include <linux/rcupdate.h>
 
-#ifdef CONFIG_CGROUPS
+#if IS_ENABLED(CONFIG_NET_CLS_CGROUP)
 struct cgroup_cls_state
 {
 	struct cgroup_subsys_state css;
 	u32 classid;
 };
 
-#ifdef CONFIG_NET_CLS_CGROUP
+extern void sock_update_classid(struct sock *sk);
+
+#if IS_BUILTIN(CONFIG_NET_CLS_CGROUP)
 static inline u32 task_cls_classid(struct task_struct *p)
 {
 	int classid;
@@ -39,32 +41,33 @@ static inline u32 task_cls_classid(struct task_struct *p)
 
 	return classid;
 }
-#else
-extern int net_cls_subsys_id;
-
+#elif IS_MODULE(CONFIG_NET_CLS_CGROUP)
 static inline u32 task_cls_classid(struct task_struct *p)
 {
-	int id;
+	struct cgroup_subsys_state *css;
 	u32 classid = 0;
 
 	if (in_interrupt())
 		return 0;
 
 	rcu_read_lock();
-	id = rcu_dereference_index_check(net_cls_subsys_id,
-					 rcu_read_lock_held());
-	if (id >= 0)
-		classid = container_of(task_subsys_state(p, id),
+	css = task_subsys_state(p, net_cls_subsys_id);
+	if (css)
+		classid = container_of(css,
 				       struct cgroup_cls_state, css)->classid;
 	rcu_read_unlock();
 
 	return classid;
 }
 #endif
-#else
+#else /* !CGROUP_NET_CLS_CGROUP */
+static inline void sock_update_classid(struct sock *sk)
+{
+}
+
 static inline u32 task_cls_classid(struct task_struct *p)
 {
 	return 0;
 }
-#endif
+#endif /* CGROUP_NET_CLS_CGROUP */
 #endif  /* _NET_CLS_CGROUP_H */
diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h
index 2719dec6b5a..2760f4f4ae9 100644
--- a/include/net/netprio_cgroup.h
+++ b/include/net/netprio_cgroup.h
@@ -18,23 +18,18 @@
 #include <linux/rcupdate.h>
 
 
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
 struct netprio_map {
 	struct rcu_head rcu;
 	u32 priomap_len;
 	u32 priomap[];
 };
 
-#ifdef CONFIG_CGROUPS
-
 struct cgroup_netprio_state {
 	struct cgroup_subsys_state css;
 	u32 prioidx;
 };
 
-#ifndef CONFIG_NETPRIO_CGROUP
-extern int net_prio_subsys_id;
-#endif
-
 extern void sock_update_netprioidx(struct sock *sk, struct task_struct *task);
 
 #if IS_BUILTIN(CONFIG_NETPRIO_CGROUP)
@@ -56,33 +51,28 @@ static inline u32 task_netprioidx(struct task_struct *p)
 
 static inline u32 task_netprioidx(struct task_struct *p)
 {
-	struct cgroup_netprio_state *state;
-	int subsys_id;
+	struct cgroup_subsys_state *css;
 	u32 idx = 0;
 
 	rcu_read_lock();
-	subsys_id = rcu_dereference_index_check(net_prio_subsys_id,
-						rcu_read_lock_held());
-	if (subsys_id >= 0) {
-		state = container_of(task_subsys_state(p, subsys_id),
-				     struct cgroup_netprio_state, css);
-		idx = state->prioidx;
-	}
+	css = task_subsys_state(p, net_prio_subsys_id);
+	if (css)
+		idx = container_of(css,
+				   struct cgroup_netprio_state, css)->prioidx;
 	rcu_read_unlock();
 	return idx;
 }
+#endif
 
-#else
+#else /* !CONFIG_NETPRIO_CGROUP */
 
 static inline u32 task_netprioidx(struct task_struct *p)
 {
 	return 0;
 }
 
-#endif /* CONFIG_NETPRIO_CGROUP */
-
-#else
 #define sock_update_netprioidx(sk, task)
-#endif
+
+#endif /* CONFIG_NETPRIO_CGROUP */
 
 #endif  /* _NET_CLS_CGROUP_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index adb7da20b5a..6e6ec18fb6d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1486,14 +1486,6 @@ extern void *sock_kmalloc(struct sock *sk, int size,
 extern void sock_kfree_s(struct sock *sk, void *mem, int size);
 extern void sk_send_sigurg(struct sock *sk);
 
-#ifdef CONFIG_CGROUPS
-extern void sock_update_classid(struct sock *sk);
-#else
-static inline void sock_update_classid(struct sock *sk)
-{
-}
-#endif
-
 /*
  * Functions to fill in entries in struct proto_ops when a protocol
  * does not implement a particular function.