Merge branch 'linus' into timers/urgent

Get upstream changes so we can apply fixes against them

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

62 files changed, 3927 insertions, 2553 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 271fd3119af9..470839d1a30e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,7 @@ obj-y     = fork.o exec_domain.o panic.o printk.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-	    notifier.o ksysfs.o cred.o \
+	    notifier.o ksysfs.o cred.o reboot.o \
 	    async.o range.o groups.o lglock.o smpboot.o
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/audit.h b/kernel/audit.h
index 1c95131ef760..123c9b7c3979 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -85,6 +85,7 @@ struct audit_names {
 
 	struct filename		*name;
 	int			name_len;	/* number of chars to log */
+	bool			hidden;		/* don't log this record */
 	bool			name_put;	/* call __putname()? */
 
 	unsigned long		ino;
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 6bd4a90d1991..f7aee8be7fb2 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -423,7 +423,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		f->lsm_rule = NULL;
 
 		/* Support legacy tests for a valid loginuid */
-		if ((f->type == AUDIT_LOGINUID) && (f->val == 4294967295)) {
+		if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) {
 			f->type = AUDIT_LOGINUID_SET;
 			f->val = 0;
 		}
@@ -865,6 +865,12 @@ static inline int audit_add_rule(struct audit_entry *entry)
 		err = audit_add_watch(&entry->rule, &list);
 		if (err) {
 			mutex_unlock(&audit_filter_mutex);
+			/*
+			 * normally audit_add_tree_rule() will free it
+			 * on failure
+			 */
+			if (tree)
+				audit_put_tree(tree);
 			goto error;
 		}
 	}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 3c8a601324a2..9845cb32b60a 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1399,8 +1399,11 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 	}
 
 	i = 0;
-	list_for_each_entry(n, &context->names_list, list)
+	list_for_each_entry(n, &context->names_list, list) {
+		if (n->hidden)
+			continue;
 		audit_log_name(context, n, NULL, i++, &call_panic);
+	}
 
 	/* Send end of event record to help user space know we are finished */
 	ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
@@ -1769,14 +1772,15 @@ void audit_putname(struct filename *name)
  * __audit_inode - store the inode and device from a lookup
  * @name: name being audited
  * @dentry: dentry being audited
- * @parent: does this dentry represent the parent?
+ * @flags: attributes for this particular entry
  */
 void __audit_inode(struct filename *name, const struct dentry *dentry,
-		   unsigned int parent)
+		   unsigned int flags)
 {
 	struct audit_context *context = current->audit_context;
 	const struct inode *inode = dentry->d_inode;
 	struct audit_names *n;
+	bool parent = flags & AUDIT_INODE_PARENT;
 
 	if (!context->in_syscall)
 		return;
@@ -1831,6 +1835,8 @@ out:
 	if (parent) {
 		n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
 		n->type = AUDIT_TYPE_PARENT;
+		if (flags & AUDIT_INODE_HIDDEN)
+			n->hidden = true;
 	} else {
 		n->name_len = AUDIT_NAME_FULL;
 		n->type = AUDIT_TYPE_NORMAL;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a7c9e6ddb979..e5583d10a325 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -63,9 +63,6 @@
 
 #include <linux/atomic.h>
 
-/* css deactivation bias, makes css->refcnt negative to deny new trygets */
-#define CSS_DEACT_BIAS		INT_MIN
-
 /*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
@@ -99,16 +96,19 @@ static DEFINE_MUTEX(cgroup_root_mutex);
  */
 #define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys,
 #define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
-static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = {
+static struct cgroup_subsys *cgroup_subsys[CGROUP_SUBSYS_COUNT] = {
 #include <linux/cgroup_subsys.h>
 };
 
 /*
- * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
- * subsystems that are otherwise unattached - it never has more than a
- * single cgroup, and all tasks are part of that cgroup.
+ * The dummy hierarchy, reserved for the subsystems that are otherwise
+ * unattached - it never has more than a single cgroup, and all tasks are
+ * part of that cgroup.
  */
-static struct cgroupfs_root rootnode;
+static struct cgroupfs_root cgroup_dummy_root;
+
+/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
+static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;
 
 /*
  * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.
@@ -186,18 +186,28 @@ struct cgroup_event {
 
 /* The list of hierarchy roots */
 
-static LIST_HEAD(roots);
-static int root_count;
+static LIST_HEAD(cgroup_roots);
+static int cgroup_root_count;
 
-static DEFINE_IDA(hierarchy_ida);
-static int next_hierarchy_id;
-static DEFINE_SPINLOCK(hierarchy_id_lock);
-
-/* dummytop is a shorthand for the dummy hierarchy's top cgroup */
-#define dummytop (&rootnode.top_cgroup)
+/*
+ * Hierarchy ID allocation and mapping.  It follows the same exclusion
+ * rules as other root ops - both cgroup_mutex and cgroup_root_mutex for
+ * writes, either for reads.
+ */
+static DEFINE_IDR(cgroup_hierarchy_idr);
 
 static struct cgroup_name root_cgroup_name = { .name = "/" };
 
+/*
+ * Assign a monotonically increasing serial number to cgroups.  It
+ * guarantees cgroups with bigger numbers are newer than those with smaller
+ * numbers.  Also, as cgroups are always appended to the parent's
+ * ->children list, it guarantees that sibling cgroups are always sorted in
+ * the ascending serial number order on the list.  Protected by
+ * cgroup_mutex.
+ */
+static u64 cgroup_serial_nr_next = 1;
+
 /* This flag indicates whether tasks in the fork and exit paths should
  * check for fork/exit handlers to call. This avoids us having to do
  * extra work in the fork/exit path if none of the subsystems need to
@@ -205,27 +215,15 @@ static struct cgroup_name root_cgroup_name = { .name = "/" };
  */
 static int need_forkexit_callback __read_mostly;
 
+static void cgroup_offline_fn(struct work_struct *work);
 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 css_unbias_refcnt(int refcnt)
-{
-	return refcnt >= 0 ? refcnt : refcnt - CSS_DEACT_BIAS;
-}
-
-/* the current nr of refs, always >= 0 whether @css is deactivated or not */
-static int css_refcnt(struct cgroup_subsys_state *css)
-{
-	int v = atomic_read(&css->refcnt);
-
-	return css_unbias_refcnt(v);
-}
-
 /* convenient tests for these bits */
-inline int cgroup_is_removed(const struct cgroup *cgrp)
+static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 {
-	return test_bit(CGRP_REMOVED, &cgrp->flags);
+	return test_bit(CGRP_DEAD, &cgrp->flags);
 }
 
 /**
@@ -261,16 +259,38 @@ static int notify_on_release(const struct cgroup *cgrp)
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
-/*
- * for_each_subsys() allows you to iterate on each subsystem attached to
- * an active hierarchy
+/**
+ * for_each_subsys - iterate all loaded cgroup subsystems
+ * @ss: the iteration cursor
+ * @i: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
+ *
+ * Should be called under cgroup_mutex.
  */
-#define for_each_subsys(_root, _ss) \
-list_for_each_entry(_ss, &_root->subsys_list, sibling)
+#define for_each_subsys(ss, i)						\
+	for ((i) = 0; (i) < CGROUP_SUBSYS_COUNT; (i)++)			\
+		if (({ lockdep_assert_held(&cgroup_mutex);		\
+		       !((ss) = cgroup_subsys[i]); })) { }		\
+		else
+
+/**
+ * for_each_builtin_subsys - iterate all built-in cgroup subsystems
+ * @ss: the iteration cursor
+ * @i: the index of @ss, CGROUP_BUILTIN_SUBSYS_COUNT after reaching the end
+ *
+ * Bulit-in subsystems are always present and iteration itself doesn't
+ * require any synchronization.
+ */
+#define for_each_builtin_subsys(ss, i)					\
+	for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT &&		\
+	     (((ss) = cgroup_subsys[i]) || true); (i)++)
+
+/* iterate each subsystem attached to a hierarchy */
+#define for_each_root_subsys(root, ss)					\
+	list_for_each_entry((ss), &(root)->subsys_list, sibling)
 
-/* for_each_active_root() allows you to iterate across the active hierarchies */
-#define for_each_active_root(_root) \
-list_for_each_entry(_root, &roots, root_list)
+/* iterate across the active hierarchies */
+#define for_each_active_root(root)					\
+	list_for_each_entry((root), &cgroup_roots, root_list)
 
 static inline struct cgroup *__d_cgrp(struct dentry *dentry)
 {
@@ -297,7 +317,7 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
 static bool cgroup_lock_live_group(struct cgroup *cgrp)
 {
 	mutex_lock(&cgroup_mutex);
-	if (cgroup_is_removed(cgrp)) {
+	if (cgroup_is_dead(cgrp)) {
 		mutex_unlock(&cgroup_mutex);
 		return false;
 	}
@@ -312,20 +332,24 @@ static void cgroup_release_agent(struct work_struct *work);
 static DECLARE_WORK(release_agent_work, cgroup_release_agent);
 static void check_for_release(struct cgroup *cgrp);
 
-/* Link structure for associating css_set objects with cgroups */
-struct cg_cgroup_link {
-	/*
-	 * List running through cg_cgroup_links associated with a
-	 * cgroup, anchored on cgroup->css_sets
-	 */
-	struct list_head cgrp_link_list;
-	struct cgroup *cgrp;
-	/*
-	 * List running through cg_cgroup_links pointing at a
-	 * single css_set object, anchored on css_set->cg_links
-	 */
-	struct list_head cg_link_list;
-	struct css_set *cg;
+/*
+ * A cgroup can be associated with multiple css_sets as different tasks may
+ * belong to different cgroups on different hierarchies.  In the other
+ * direction, a css_set is naturally associated with multiple cgroups.
+ * This M:N relationship is represented by the following link structure
+ * which exists for each association and allows traversing the associations
+ * from both sides.
+ */
+struct cgrp_cset_link {
+	/* the cgroup and css_set this link associates */
+	struct cgroup		*cgrp;
+	struct css_set		*cset;
+
+	/* list of cgrp_cset_links anchored at cgrp->cset_links */
+	struct list_head	cset_link;
+
+	/* list of cgrp_cset_links anchored at css_set->cgrp_links */
+	struct list_head	cgrp_link;
 };
 
 /* The default css_set - used by init and its children prior to any
@@ -336,7 +360,7 @@ struct cg_cgroup_link {
  */
 
 static struct css_set init_css_set;
-static struct cg_cgroup_link init_css_set_link;
+static struct cgrp_cset_link init_cgrp_cset_link;
 
 static int cgroup_init_idr(struct cgroup_subsys *ss,
 			   struct cgroup_subsys_state *css);
@@ -357,10 +381,11 @@ static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS);
 
 static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
 {
-	int i;
 	unsigned long key = 0UL;
+	struct cgroup_subsys *ss;
+	int i;
 
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
+	for_each_subsys(ss, i)
 		key += (unsigned long)css[i];
 	key = (key >> 16) ^ key;
 
@@ -373,90 +398,83 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
  * 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 *cg, int taskexit)
+static void __put_css_set(struct css_set *cset, int taskexit)
 {
-	struct cg_cgroup_link *link;
-	struct cg_cgroup_link *saved_link;
+	struct cgrp_cset_link *link, *tmp_link;
+
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
 	 * can see it. Similar to atomic_dec_and_lock(), but for an
 	 * rwlock
 	 */
-	if (atomic_add_unless(&cg->refcount, -1, 1))
+	if (atomic_add_unless(&cset->refcount, -1, 1))
 		return;
 	write_lock(&css_set_lock);
-	if (!atomic_dec_and_test(&cg->refcount)) {
+	if (!atomic_dec_and_test(&cset->refcount)) {
 		write_unlock(&css_set_lock);
 		return;
 	}
 
 	/* This css_set is dead. unlink it and release cgroup refcounts */
-	hash_del(&cg->hlist);
+	hash_del(&cset->hlist);
 	css_set_count--;
 
-	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
-				 cg_link_list) {
+	list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) {
 		struct cgroup *cgrp = link->cgrp;
-		list_del(&link->cg_link_list);
-		list_del(&link->cgrp_link_list);
 
-		/*
-		 * We may not be holding cgroup_mutex, and if cgrp->count is
-		 * dropped to 0 the cgroup can be destroyed at any time, hence
-		 * rcu_read_lock is used to keep it alive.
-		 */
-		rcu_read_lock();
-		if (atomic_dec_and_test(&cgrp->count) &&
-		    notify_on_release(cgrp)) {
+		list_del(&link->cset_link);
+		list_del(&link->cgrp_link);
+
+		/* @cgrp can't go away while we're holding css_set_lock */
+		if (list_empty(&cgrp->cset_links) && notify_on_release(cgrp)) {
 			if (taskexit)
 				set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
 		}
-		rcu_read_unlock();
 
 		kfree(link);
 	}
 
 	write_unlock(&css_set_lock);
-	kfree_rcu(cg, rcu_head);
+	kfree_rcu(cset, rcu_head);
 }
 
 /*
  * refcounted get/put for css_set objects
  */
-static inline void get_css_set(struct css_set *cg)
+static inline void get_css_set(struct css_set *cset)
 {
-	atomic_inc(&cg->refcount);
+	atomic_inc(&cset->refcount);
 }
 
-static inline void put_css_set(struct css_set *cg)
+static inline void put_css_set(struct css_set *cset)
 {
-	__put_css_set(cg, 0);
+	__put_css_set(cset, 0);
 }
 
-static inline void put_css_set_taskexit(struct css_set *cg)
+static inline void put_css_set_taskexit(struct css_set *cset)
 {
-	__put_css_set(cg, 1);
+	__put_css_set(cset, 1);
 }
 
-/*
+/**
  * compare_css_sets - helper function for find_existing_css_set().
- * @cg: candidate css_set being tested
- * @old_cg: existing css_set for a task
+ * @cset: candidate css_set being tested
+ * @old_cset: existing css_set for a task
  * @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
  * which "new_cgrp" belongs to, for which it should match "new_cgrp".
  */
-static bool compare_css_sets(struct css_set *cg,
-			     struct css_set *old_cg,
+static bool compare_css_sets(struct css_set *cset,
+			     struct css_set *old_cset,
 			     struct cgroup *new_cgrp,
 			     struct cgroup_subsys_state *template[])
 {
 	struct list_head *l1, *l2;
 
-	if (memcmp(template, cg->subsys, sizeof(cg->subsys))) {
+	if (memcmp(template, cset->subsys, sizeof(cset->subsys))) {
 		/* Not all subsystems matched */
 		return false;
 	}
@@ -470,28 +488,28 @@ static bool compare_css_sets(struct css_set *cg,
 	 * candidates.
 	 */
 
-	l1 = &cg->cg_links;
-	l2 = &old_cg->cg_links;
+	l1 = &cset->cgrp_links;
+	l2 = &old_cset->cgrp_links;
 	while (1) {
-		struct cg_cgroup_link *cgl1, *cgl2;
-		struct cgroup *cg1, *cg2;
+		struct cgrp_cset_link *link1, *link2;
+		struct cgroup *cgrp1, *cgrp2;
 
 		l1 = l1->next;
 		l2 = l2->next;
 		/* See if we reached the end - both lists are equal length. */
-		if (l1 == &cg->cg_links) {
-			BUG_ON(l2 != &old_cg->cg_links);
+		if (l1 == &cset->cgrp_links) {
+			BUG_ON(l2 != &old_cset->cgrp_links);
 			break;
 		} else {
-			BUG_ON(l2 == &old_cg->cg_links);
+			BUG_ON(l2 == &old_cset->cgrp_links);
 		}
 		/* Locate the cgroups associated with these links. */
-		cgl1 = list_entry(l1, struct cg_cgroup_link, cg_link_list);
-		cgl2 = list_entry(l2, struct cg_cgroup_link, cg_link_list);
-		cg1 = cgl1->cgrp;
-		cg2 = cgl2->cgrp;
+		link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link);
+		link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link);
+		cgrp1 = link1->cgrp;
+		cgrp2 = link2->cgrp;
 		/* Hierarchies should be linked in the same order. */
-		BUG_ON(cg1->root != cg2->root);
+		BUG_ON(cgrp1->root != cgrp2->root);
 
 		/*
 		 * If this hierarchy is the hierarchy of the cgroup
@@ -500,46 +518,39 @@ static bool compare_css_sets(struct css_set *cg,
 		 * hierarchy, then this css_set should point to the
 		 * same cgroup as the old css_set.
 		 */
-		if (cg1->root == new_cgrp->root) {
-			if (cg1 != new_cgrp)
+		if (cgrp1->root == new_cgrp->root) {
+			if (cgrp1 != new_cgrp)
 				return false;
 		} else {
-			if (cg1 != cg2)
+			if (cgrp1 != cgrp2)
 				return false;
 		}
 	}
 	return true;
 }
 
-/*
- * find_existing_css_set() is a helper for
- * find_css_set(), and checks to see whether an existing
- * css_set is suitable.
- *
- * oldcg: the cgroup group that we're using before the cgroup
- * transition
- *
- * cgrp: the cgroup that we're moving into
- *
- * template: location in which to build the desired set of subsystem
- * state objects for the new cgroup group
+/**
+ * find_existing_css_set - init css array and find the matching css_set
+ * @old_cset: the css_set that we're using before the cgroup transition
+ * @cgrp: the cgroup that we're moving into
+ * @template: out param for the new set of csses, should be clear on entry
  */
-static struct css_set *find_existing_css_set(
-	struct css_set *oldcg,
-	struct cgroup *cgrp,
-	struct cgroup_subsys_state *template[])
+static struct css_set *find_existing_css_set(struct css_set *old_cset,
+					struct cgroup *cgrp,
+					struct cgroup_subsys_state *template[])
 {
-	int i;
 	struct cgroupfs_root *root = cgrp->root;
-	struct css_set *cg;
+	struct cgroup_subsys *ss;
+	struct css_set *cset;
 	unsigned long key;
+	int i;
 
 	/*
 	 * Build the set of subsystem state objects that we want to see in the
 	 * new css_set. while subsystems can change globally, the entries here
 	 * won't change, so no need for locking.
 	 */
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+	for_each_subsys(ss, i) {
 		if (root->subsys_mask & (1UL << i)) {
 			/* Subsystem is in this hierarchy. So we want
 			 * the subsystem state from the new
@@ -548,148 +559,152 @@ static struct css_set *find_existing_css_set(
 		} else {
 			/* Subsystem is not in this hierarchy, so we
 			 * don't want to change the subsystem state */
-			template[i] = oldcg->subsys[i];
+			template[i] = old_cset->subsys[i];
 		}
 	}
 
 	key = css_set_hash(template);
-	hash_for_each_possible(css_set_table, cg, hlist, key) {
-		if (!compare_css_sets(cg, oldcg, cgrp, template))
+	hash_for_each_possible(css_set_table, cset, hlist, key) {
+		if (!compare_css_sets(cset, old_cset, cgrp, template))
 			continue;
 
 		/* This css_set matches what we need */
-		return cg;
+		return cset;
 	}
 
 	/* No existing cgroup group matched */
 	return NULL;
 }
 
-static void free_cg_links(struct list_head *tmp)
+static void free_cgrp_cset_links(struct list_head *links_to_free)
 {
-	struct cg_cgroup_link *link;
-	struct cg_cgroup_link *saved_link;
+	struct cgrp_cset_link *link, *tmp_link;
 
-	list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) {
-		list_d