Merge tag 'v3.12'

Linux 3.12

81 files changed, 3684 insertions, 2757 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 35ef1185e359..1ce47553fb02 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -26,6 +26,7 @@ obj-y += sched/
 obj-y += power/
 obj-y += printk/
 obj-y += cpu/
+obj-y += irq/
 
 obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -79,7 +80,6 @@ obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
-obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += rcutree.o
diff --git a/kernel/audit.c b/kernel/audit.c
index 91e53d04b6a9..7b0e23a740ce 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 			sleep_time = timeout_start + audit_backlog_wait_time -
 					jiffies;
-			if ((long)sleep_time > 0)
+			if ((long)sleep_time > 0) {
 				wait_for_auditd(sleep_time);
-			continue;
+				continue;
+			}
 		}
 		if (audit_rate_check() && printk_ratelimit())
 			printk(KERN_WARNING
diff --git a/kernel/capability.c b/kernel/capability.c
index f6c2ce5701e1..4e66bf9275b0 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -433,18 +433,6 @@ bool capable(int cap)
 EXPORT_SYMBOL(capable);
 
 /**
- * nsown_capable - Check superior capability to one's own user_ns
- * @cap: The capability in question
- *
- * Return true if the current task has the given superior capability
- * targeted at its own user namespace.
- */
-bool nsown_capable(int cap)
-{
-	return ns_capable(current_user_ns(), cap);
-}
-
-/**
  * inode_capable - Check superior capability over inode
  * @inode: The inode in question
  * @cap: The capability in question
@@ -464,3 +452,4 @@ bool inode_capable(const struct inode *inode, int cap)
 
 	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid);
 }
+EXPORT_SYMBOL(inode_capable);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e91963302c0d..8bd9cfdc70d7 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -60,6 +60,7 @@
 #include <linux/poll.h>
 #include <linux/flex_array.h> /* used in cgroup_attach_task */
 #include <linux/kthread.h>
+#include <linux/file.h>
 
 #include <linux/atomic.h>
 
@@ -81,7 +82,7 @@
  */
 #ifdef CONFIG_PROVE_RCU
 DEFINE_MUTEX(cgroup_mutex);
-EXPORT_SYMBOL_GPL(cgroup_mutex);	/* only for task_subsys_state_check() */
+EXPORT_SYMBOL_GPL(cgroup_mutex);	/* only for lockdep */
 #else
 static DEFINE_MUTEX(cgroup_mutex);
 #endif
@@ -117,6 +118,7 @@ struct cfent {
 	struct list_head		node;
 	struct dentry			*dentry;
 	struct cftype			*type;
+	struct cgroup_subsys_state	*css;
 
 	/* file xattrs */
 	struct simple_xattrs		xattrs;
@@ -159,9 +161,9 @@ struct css_id {
  */
 struct cgroup_event {
 	/*
-	 * Cgroup which the event belongs to.
+	 * css which the event belongs to.
 	 */
-	struct cgroup *cgrp;
+	struct cgroup_subsys_state *css;
 	/*
 	 * Control file which the event associated.
 	 */
@@ -215,10 +217,33 @@ static u64 cgroup_serial_nr_next = 1;
  */
 static int need_forkexit_callback __read_mostly;
 
-static void cgroup_offline_fn(struct work_struct *work);
+static struct cftype cgroup_base_files[];
+
+static void cgroup_destroy_css_killed(struct cgroup *cgrp);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
-static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
-			      struct cftype cfts[], bool is_add);
+static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
+			      bool is_add);
+
+/**
+ * cgroup_css - obtain a cgroup's css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest (%NULL returns the dummy_css)
+ *
+ * Return @cgrp's css (cgroup_subsys_state) associated with @ss.  This
+ * function must be called either under cgroup_mutex or rcu_read_lock() and
+ * the caller is responsible for pinning the returned css if it wants to
+ * keep accessing it outside the said locks.  This function may return
+ * %NULL if @cgrp doesn't have @subsys_id enabled.
+ */
+static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
+					      struct cgroup_subsys *ss)
+{
+	if (ss)
+		return rcu_dereference_check(cgrp->subsys[ss->subsys_id],
+					     lockdep_is_held(&cgroup_mutex));
+	else
+		return &cgrp->dummy_css;
+}
 
 /* convenient tests for these bits */
 static inline bool cgroup_is_dead(const struct cgroup *cgrp)
@@ -365,9 +390,11 @@ static struct cgrp_cset_link init_cgrp_cset_link;
 static int cgroup_init_idr(struct cgroup_subsys *ss,
 			   struct cgroup_subsys_state *css);
 
-/* css_set_lock protects the list of css_set objects, and the
- * chain of tasks off each css_set.  Nests outside task->alloc_lock
- * due to cgroup_iter_start() */
+/*
+ * css_set_lock protects the list of css_set objects, and the chain of
+ * tasks off each css_set.  Nests outside task->alloc_lock due to
+ * css_task_iter_start().
+ */
 static DEFINE_RWLOCK(css_set_lock);
 static int css_set_count;
 
@@ -392,10 +419,12 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
 	return key;
 }
 
-/* We don't maintain the lists running through each css_set to its
- * task until after the first call to cgroup_iter_start(). This
- * reduces the fork()/exit() overhead for people who have cgroups
- * compiled into their kernel but not actually in use */
+/*
+ * We don't maintain the lists running through each css_set to its task
+ * until after the first call to css_task_iter_start().  This reduces the
+ * fork()/exit() overhead for people who have cgroups compiled into their
+ * kernel but not actually in use.
+ */
 static int use_task_css_set_links __read_mostly;
 
 static void __put_css_set(struct css_set *cset, int taskexit)
@@ -464,7 +493,7 @@ static inline void put_css_set_taskexit(struct css_set *cset)
  * @new_cgrp: cgroup that's being entered by the task
  * @template: desired set of css pointers in css_set (pre-calculated)
  *
- * Returns true if "cg" matches "old_cg" except for the hierarchy
+ * Returns true if "cset" matches "old_cset" except for the hierarchy
  * which "new_cgrp" belongs to, for which it should match "new_cgrp".
  */
 static bool compare_css_sets(struct css_set *cset,
@@ -555,7 +584,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 			/* Subsystem is in this hierarchy. So we want
 			 * the subsystem state from the new
 			 * cgroup */
-			template[i] = cgrp->subsys[i];
+			template[i] = cgroup_css(cgrp, ss);
 		} else {
 			/* Subsystem is not in this hierarchy, so we
 			 * don't want to change the subsystem state */
@@ -803,8 +832,7 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
 
 static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
-static int cgroup_populate_dir(struct cgroup *cgrp, bool base_files,
-			       unsigned long subsys_mask);
+static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask);
 static const struct inode_operations cgroup_dir_inode_operations;
 static const struct file_operations proc_cgroupstats_operations;
 
@@ -813,8 +841,7 @@ static struct backing_dev_info cgroup_backing_dev_info = {
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
-static int alloc_css_id(struct cgroup_subsys *ss,
-			struct cgroup *parent, struct cgroup *child);
+static int alloc_css_id(struct cgroup_subsys_state *child_css);
 
 static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 {
@@ -845,15 +872,8 @@ static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry)
 static void cgroup_free_fn(struct work_struct *work)
 {
 	struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
-	struct cgroup_subsys *ss;
 
 	mutex_lock(&cgroup_mutex);
-	/*
-	 * Release the subsystem state objects.
-	 */
-	for_each_root_subsys(cgrp->root, ss)
-		ss->css_free(cgrp);
-
 	cgrp->root->number_of_cgroups--;
 	mutex_unlock(&cgroup_mutex);
 
@@ -864,8 +884,6 @@ static void cgroup_free_fn(struct work_struct *work)
 	 */
 	dput(cgrp->parent->dentry);
 
-	ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
-
 	/*
 	 * Drop the active superblock reference that we took when we
 	 * created the cgroup. This will free cgrp->root, if we are
@@ -956,27 +974,22 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 }
 
 /**
- * cgroup_clear_directory - selective removal of base and subsystem files
- * @dir: directory containing the files
- * @base_files: true if the base files should be removed
+ * cgroup_clear_dir - remove subsys files in a cgroup directory
+ * @cgrp: target cgroup
  * @subsys_mask: mask of the subsystem ids whose files should be removed
  */
-static void cgroup_clear_directory(struct dentry *dir, bool base_files,
-				   unsigned long subsys_mask)
+static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 {
-	struct cgroup *cgrp = __d_cgrp(dir);
 	struct cgroup_subsys *ss;
+	int i;
 
-	for_each_root_subsys(cgrp->root, ss) {
+	for_each_subsys(ss, i) {
 		struct cftype_set *set;
-		if (!test_bit(ss->subsys_id, &subsys_mask))
+
+		if (!test_bit(i, &subsys_mask))
 			continue;
 		list_for_each_entry(set, &ss->cftsets, node)
-			cgroup_addrm_files(cgrp, NULL, set->cfts, false);
-	}
-	if (base_files) {
-		while (!list_empty(&cgrp->files))
-			cgroup_rm_file(cgrp, NULL);
+			cgroup_addrm_files(cgrp, set->cfts, false);
 	}
 }
 
@@ -986,9 +999,6 @@ static void cgroup_clear_directory(struct dentry *dir, bool base_files,
 static void cgroup_d_remove_dir(struct dentry *dentry)
 {
 	struct dentry *parent;
-	struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
-
-	cgroup_clear_directory(dentry, true, root->subsys_mask);
 
 	parent = dentry->d_parent;
 	spin_lock(&parent->d_lock);
@@ -1009,79 +1019,84 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 {
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgroup_subsys *ss;
-	int i;
+	unsigned long pinned = 0;
+	int i, ret;
 
 	BUG_ON(!mutex_is_locked(&cgroup_mutex));
 	BUG_ON(!mutex_is_locked(&cgroup_root_mutex));
 
 	/* Check that any added subsystems are currently free */
 	for_each_subsys(ss, i) {
-		unsigned long bit = 1UL << i;
-
-		if (!(bit & added_mask))
+		if (!(added_mask & (1 << i)))
 			continue;
 
+		/* is the subsystem mounted elsewhere? */
 		if (ss->root != &cgroup_dummy_root) {
-			/* Subsystem isn't free */
-			return -EBUSY;
+			ret = -EBUSY;
+			goto out_put;
+		}
+
+		/* pin the module */
+		if (!try_module_get(ss->module)) {
+			ret = -ENOENT;
+			goto out_put;
 		}
+		pinned |= 1 << i;
 	}
 
-	/* Currently we don't handle adding/removing subsystems when
-	 * any child cgroups exist. This is theoretically supportable
-	 * but involves complex error handling, so it's being left until
-	 * later */
-	if (root->number_of_cgroups > 1)
-		return -EBUSY;
+	/* subsys could be missing if unloaded between parsing and here */
+	if (added_mask != pinned) {
+		ret = -ENOENT;
+		goto out_put;
+	}
+
+	ret = cgroup_populate_dir(cgrp, added_mask);
+	if (ret)
+		goto out_put;
+
+	/*
+	 * Nothing can fail from this point on.  Remove files for the
+	 * removed subsystems and rebind each subsystem.
+	 */
+	cgroup_clear_dir(cgrp, removed_mask);
 
-	/* Process each subsystem */
 	for_each_subsys(ss, i) {
 		unsigned long bit = 1UL << i;
 
 		if (bit & added_mask) {
 			/* We're binding this subsystem to this hierarchy */
-			BUG_ON(cgrp->subsys[i]);
-			BUG_ON(!cgroup_dummy_top->subsys[i]);
-			BUG_ON(cgroup_dummy_top->subsys[i]->cgroup != cgroup_dummy_top);
+			BUG_ON(cgroup_css(cgrp, ss));
+			BUG_ON(!cgroup_css(cgroup_dummy_top, ss));
+			BUG_ON(cgroup_css(cgroup_dummy_top, ss)->cgroup != cgroup_dummy_top);
+
+			rcu_assign_pointer(cgrp->subsys[i],
+					   cgroup_css(cgroup_dummy_top, ss));
+			cgroup_css(cgrp, ss)->cgroup = cgrp;
 
-			cgrp->subsys[i] = cgroup_dummy_top->subsys[i];
-			cgrp->subsys[i]->cgroup = cgrp;
 			list_move(&ss->sibling, &root->subsys_list);
 			ss->root = root;
 			if (ss->bind)
-				ss->bind(cgrp);
+				ss->bind(cgroup_css(cgrp, ss));
 
 			/* refcount was already taken, and we're keeping it */
 			root->subsys_mask |= bit;
 		} else if (bit & removed_mask) {
 			/* We're removing this subsystem */
-			BUG_ON(cgrp->subsys[i] != cgroup_dummy_top->subsys[i]);
-			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
+			BUG_ON(cgroup_css(cgrp, ss) != cgroup_css(cgroup_dummy_top, ss));
+			BUG_ON(cgroup_css(cgrp, ss)->cgroup != cgrp);
 
 			if (ss->bind)
-				ss->bind(cgroup_dummy_top);
-			cgroup_dummy_top->subsys[i]->cgroup = cgroup_dummy_top;
-			cgrp->subsys[i] = NULL;
+				ss->bind(cgroup_css(cgroup_dummy_top, ss));
+
+			cgroup_css(cgroup_dummy_top, ss)->cgroup = cgroup_dummy_top;
+			RCU_INIT_POINTER(cgrp->subsys[i], NULL);
+
 			cgroup_subsys[i]->root = &cgroup_dummy_root;
 			list_move(&ss->sibling, &cgroup_dummy_root.subsys_list);
 
 			/* subsystem is now free - drop reference on module */
 			module_put(ss->module);
 			root->subsys_mask &= ~bit;
-		} else if (bit & root->subsys_mask) {
-			/* Subsystem state should already exist */
-			BUG_ON(!cgrp->subsys[i]);
-			/*
-			 * a refcount was taken, but we already had one, so
-			 * drop the extra reference.
-			 */
-			module_put(ss->module);
-#ifdef CONFIG_MODULE_UNLOAD
-			BUG_ON(ss->module && !module_refcount(ss->module));
-#endif
-		} else {
-			/* Subsystem state shouldn't exist */
-			BUG_ON(cgrp->subsys[i]);
 		}
 	}
 
@@ -1092,6 +1107,12 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 	root->flags |= CGRP_ROOT_SUBSYS_BOUND;
 
 	return 0;
+
+out_put:
+	for_each_subsys(ss, i)
+		if (pinned & (1 << i))
+			module_put(ss->module);
+	return ret;
 }
 
 static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
@@ -1142,7 +1163,6 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	char *token, *o = data;
 	bool all_ss = false, one_ss = false;
 	unsigned long mask = (unsigned long)-1;
-	bool module_pin_failed = false;
 	struct cgroup_subsys *ss;
 	int i;
 
@@ -1285,52 +1305,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	if (!opts->subsys_mask && !opts->name)
 		return -EINVAL;
 
-	/*
-	 * Grab references on all the modules we'll need, so the subsystems
-	 * don't dance around before rebind_s