Merge tag 'v4.4-rc5' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

20 files changed, 285 insertions, 180 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 3f4c99e..b0799bc 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -28,11 +28,17 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	    attr->value_size == 0)
 		return ERR_PTR(-EINVAL);
 
+	if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1))
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements.
+		 */
+		return ERR_PTR(-E2BIG);
+
 	elem_size = round_up(attr->value_size, 8);
 
 	/* check round_up into zero and u32 overflow */
 	if (elem_size == 0 ||
-	    attr->max_entries > (U32_MAX - sizeof(*array)) / elem_size)
+	    attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size)
 		return ERR_PTR(-ENOMEM);
 
 	array_size = sizeof(*array) + attr->max_entries * elem_size;
@@ -105,7 +111,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* all elements already exist */
 		return -EEXIST;
 
-	memcpy(array->value + array->elem_size * index, value, array->elem_size);
+	memcpy(array->value + array->elem_size * index, value, map->value_size);
 	return 0;
 }
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 19909b2..34777b3 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -64,12 +64,35 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		 */
 		goto free_htab;
 
-	err = -ENOMEM;
+	if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) -
+	    MAX_BPF_STACK - sizeof(struct htab_elem))
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements via bpf syscall. This check also makes
+		 * sure that the elem_size doesn't overflow and it's
+		 * kmalloc-able later in htab_map_update_elem()
+		 */
+		goto free_htab;
+
+	htab->elem_size = sizeof(struct htab_elem) +
+			  round_up(htab->map.key_size, 8) +
+			  htab->map.value_size;
+
 	/* prevent zero size kmalloc and check for u32 overflow */
 	if (htab->n_buckets == 0 ||
 	    htab->n_buckets > U32_MAX / sizeof(struct hlist_head))
 		goto free_htab;
 
+	if ((u64) htab->n_buckets * sizeof(struct hlist_head) +
+	    (u64) htab->elem_size * htab->map.max_entries >=
+	    U32_MAX - PAGE_SIZE)
+		/* make sure page count doesn't overflow */
+		goto free_htab;
+
+	htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) +
+				   htab->elem_size * htab->map.max_entries,
+				   PAGE_SIZE) >> PAGE_SHIFT;
+
+	err = -ENOMEM;
 	htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head),
 				      GFP_USER | __GFP_NOWARN);
 
@@ -85,13 +108,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	raw_spin_lock_init(&htab->lock);
 	htab->count = 0;
 
-	htab->elem_size = sizeof(struct htab_elem) +
-			  round_up(htab->map.key_size, 8) +
-			  htab->map.value_size;
-
-	htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) +
-				   htab->elem_size * htab->map.max_entries,
-				   PAGE_SIZE) >> PAGE_SHIFT;
 	return &htab->map;
 
 free_htab:
@@ -222,7 +238,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* allocate new element outside of lock */
-	l_new = kmalloc(htab->elem_size, GFP_ATOMIC);
+	l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
 	if (!l_new)
 		return -ENOMEM;
 
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index be6d726..5a8a797 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -34,7 +34,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 		atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
 		break;
 	case BPF_TYPE_MAP:
-		atomic_inc(&((struct bpf_map *)raw)->refcnt);
+		bpf_map_inc(raw, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -51,7 +51,7 @@ static void bpf_any_put(void *raw, enum bpf_type type)
 		bpf_prog_put(raw);
 		break;
 	case BPF_TYPE_MAP:
-		bpf_map_put(raw);
+		bpf_map_put_with_uref(raw);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -64,7 +64,7 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type)
 	void *raw;
 
 	*type = BPF_TYPE_MAP;
-	raw = bpf_map_get(ufd);
+	raw = bpf_map_get_with_uref(ufd);
 	if (IS_ERR(raw)) {
 		*type = BPF_TYPE_PROG;
 		raw = bpf_prog_get(ufd);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0d3313d..3b39550 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -82,6 +82,14 @@ static void bpf_map_free_deferred(struct work_struct *work)
 	map->ops->map_free(map);
 }
 
+static void bpf_map_put_uref(struct bpf_map *map)
+{
+	if (atomic_dec_and_test(&map->usercnt)) {
+		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
+			bpf_fd_array_map_clear(map);
+	}
+}
+
 /* decrement map refcnt and schedule it for freeing via workqueue
  * (unrelying map implementation ops->map_free() might sleep)
  */
@@ -93,17 +101,15 @@ void bpf_map_put(struct bpf_map *map)
 	}
 }
 
-static int bpf_map_release(struct inode *inode, struct file *filp)
+void bpf_map_put_with_uref(struct bpf_map *map)
 {
-	struct bpf_map *map = filp->private_data;
-
-	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-		/* prog_array stores refcnt-ed bpf_prog pointers
-		 * release them all when user space closes prog_array_fd
-		 */
-		bpf_fd_array_map_clear(map);
-
+	bpf_map_put_uref(map);
 	bpf_map_put(map);
+}
+
+static int bpf_map_release(struct inode *inode, struct file *filp)
+{
+	bpf_map_put_with_uref(filp->private_data);
 	return 0;
 }
 
@@ -142,6 +148,7 @@ static int map_create(union bpf_attr *attr)
 		return PTR_ERR(map);
 
 	atomic_set(&map->refcnt, 1);
+	atomic_set(&map->usercnt, 1);
 
 	err = bpf_map_charge_memlock(map);
 	if (err)
@@ -174,7 +181,14 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-struct bpf_map *bpf_map_get(u32 ufd)
+void bpf_map_inc(struct bpf_map *map, bool uref)
+{
+	atomic_inc(&map->refcnt);
+	if (uref)
+		atomic_inc(&map->usercnt);
+}
+
+struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
 	struct fd f = fdget(ufd);
 	struct bpf_map *map;
@@ -183,7 +197,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	atomic_inc(&map->refcnt);
+	bpf_map_inc(map, true);
 	fdput(f);
 
 	return map;
@@ -226,7 +240,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 		goto free_key;
 
 	err = -ENOMEM;
-	value = kmalloc(map->value_size, GFP_USER);
+	value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
 	if (!value)
 		goto free_key;
 
@@ -285,7 +299,7 @@ static int map_update_elem(union bpf_attr *attr)
 		goto free_key;
 
 	err = -ENOMEM;
-	value = kmalloc(map->value_size, GFP_USER);
+	value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
 	if (!value)
 		goto free_key;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c607305..a7945d1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2021,8 +2021,7 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_bpf_prog_info()
 			 */
-			atomic_inc(&map->refcnt);
-
+			bpf_map_inc(map, false);
 			fdput(f);
 next_insn:
 			insn++;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f1603c1..470f653 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -98,6 +98,12 @@ static DEFINE_SPINLOCK(css_set_lock);
 static DEFINE_SPINLOCK(cgroup_idr_lock);
 
 /*
+ * Protects cgroup_file->kn for !self csses.  It synchronizes notifications
+ * against file removal/re-creation across css hiding.
+ */
+static DEFINE_SPINLOCK(cgroup_file_kn_lock);
+
+/*
  * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
  * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
  */
@@ -754,9 +760,11 @@ static void put_css_set_locked(struct css_set *cset)
 	if (!atomic_dec_and_test(&cset->refcount))
 		return;
 
-	/* This css_set is dead. unlink it and release cgroup refcounts */
-	for_each_subsys(ss, ssid)
+	/* This css_set is dead. unlink it and release cgroup and css refs */
+	for_each_subsys(ss, ssid) {
 		list_del(&cset->e_cset_node[ssid]);
+		css_put(cset->subsys[ssid]);
+	}
 	hash_del(&cset->hlist);
 	css_set_count--;
 
@@ -1056,9 +1064,13 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	key = css_set_hash(cset->subsys);
 	hash_add(css_set_table, &cset->hlist, key);
 
-	for_each_subsys(ss, ssid)
+	for_each_subsys(ss, ssid) {
+		struct cgroup_subsys_state *css = cset->subsys[ssid];
+
 		list_add_tail(&cset->e_cset_node[ssid],
-			      &cset->subsys[ssid]->cgroup->e_csets[ssid]);
+			      &css->cgroup->e_csets[ssid]);
+		css_get(css);
+	}
 
 	spin_unlock_bh(&css_set_lock);
 
@@ -1393,6 +1405,16 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 	char name[CGROUP_FILE_NAME_MAX];
 
 	lockdep_assert_held(&cgroup_mutex);
+
+	if (cft->file_offset) {
+		struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss);
+		struct cgroup_file *cfile = (void *)css + cft->file_offset;
+
+		spin_lock_irq(&cgroup_file_kn_lock);
+		cfile->kn = NULL;
+		spin_unlock_irq(&cgroup_file_kn_lock);
+	}
+
 	kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
 }
 
@@ -1856,7 +1878,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 
 	INIT_LIST_HEAD(&cgrp->self.sibling);
 	INIT_LIST_HEAD(&cgrp->self.children);
-	INIT_LIST_HEAD(&cgrp->self.files);
 	INIT_LIST_HEAD(&cgrp->cset_links);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
@@ -2216,6 +2237,9 @@ struct cgroup_taskset {
 	struct list_head	src_csets;
 	struct list_head	dst_csets;
 
+	/* the subsys currently being processed */
+	int			ssid;
+
 	/*
 	 * Fields for cgroup_taskset_*() iteration.
 	 *
@@ -2278,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task,
 /**
  * cgroup_taskset_first - reset taskset and return the first task
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * @tset iteration is initialized and the first task is returned.
  */
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+					 struct cgroup_subsys_state **dst_cssp)
 {
 	tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
 	tset->cur_task = NULL;
 
-	return cgroup_taskset_next(tset);
+	return cgroup_taskset_next(tset, dst_cssp);
 }
 
 /**
  * cgroup_taskset_next - iterate to the next task in taskset
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * Return the next task in @tset.  Iteration must have been initialized
  * with cgroup_taskset_first().
  */
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+					struct cgroup_subsys_state **dst_cssp)
 {
 	struct css_set *cset = tset->cur_cset;
 	struct task_struct *task = tset->cur_task;
@@ -2311,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
 		if (&task->cg_list != &cset->mg_tasks) {
 			tset->cur_cset = cset;
 			tset->cur_task = task;
+
+			/*
+			 * This function may be called both before and
+			 * after cgroup_taskset_migrate().  The two cases
+			 * can be distinguished by looking at whether @cset
+			 * has its ->mg_dst_cset set.
+			 */
+			if (cset->mg_dst_cset)
+				*dst_cssp = cset->mg_dst_cset->subsys[tset->ssid];
+			else
+				*dst_cssp = cset->subsys[tset->ssid];
+
 			return task;
 		}
 
@@ -2346,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 	/* check that we can legitimately attach to the cgroup */
 	for_each_e_css(css, i, dst_cgrp) {
 		if (css->ss->can_attach) {
-			ret = css->ss->can_attach(css, tset);
+			tset->ssid = i;
+			ret = css->ss->can_attach(tset);
 			if (ret) {
 				failed_css = css;
 				goto out_cancel_attach;
@@ -2379,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 	 */
 	tset->csets = &tset->dst_csets;
 
-	for_each_e_css(css, i, dst_cgrp)
-		if (css->ss->attach)
-			css->ss->attach(css, tset);
+	for_each_e_css(css, i, dst_cgrp) {
+		if (css->ss->attach) {
+			tset->ssid = i;
+			css->ss->attach(tset);
+		}
+	}
 
 	ret = 0;
 	goto out_release_tset;
@@ -2390,8 +2434,10 @@ out_cancel_attach:
 	for_each_e_css(css, i, dst_cgrp) {
 		if (css == failed_css)
 			break;
-		if (css->ss->cancel_attach)
-			css->ss->cancel_attach(css, tset);
+		if (css->ss->cancel_attach) {
+			tset->ssid = i;
+			css->ss->cancel_attach(tset);
+		}
 	}
 out_release_tset:
 	spin_lock_bh(&css_set_lock);
@@ -3313,9 +3359,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 	if (cft->file_offset) {
 		struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
-		kernfs_get(kn);
+		spin_lock_irq(&cgroup_file_kn_lock);
 		cfile->kn = kn;
-		list_add(&cfile->node, &css->files);
+		spin_unlock_irq(&cgroup_file_kn_lock);
 	}
 
 	return 0;
@@ -3553,6 +3599,22 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 }
 
 /**
+ * cgroup_file_notify - generate a file modified event for a cgroup_file
+ * @cfile: target cgroup_file
+ *
+ * @cfile must have been obtained by setting cftype->file_offset.
+ */
+void cgroup_file_notify(struct cgroup_file *cfile)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cgroup_file_kn_lock, flags);
+	if (cfile->kn)
+		kernfs_notify(cfile->kn);
+	spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
+}
+
+/**
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
  *
@@ -4613,13 +4675,9 @@ static void css_free_work_fn(struct work_struct *work)
 		container_of(work, struct cgroup_subsys_state, destroy_work);
 	struct cgroup_subsys *ss = css->ss;
 	struct cgroup *cgrp = css->cgroup;
-	struct cgroup_file *cfile;
 
 	percpu_ref_exit(&css->refcnt);
 
-	list_for_each_entry(cfile, &css->files, node)
-		kernfs_put(cfile->kn);
-
 	if (ss) {
 		/* css free path */
 		int id = css->id;
@@ -4724,7 +4782,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	css->ss = ss;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
-	INIT_LIST_HEAD(&css->files);
 	css->serial_nr = css_serial_nr_next++;
 
 	if (cgroup_parent(cgrp)) {
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index f1b30ad..2d3df82 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -155,12 +155,10 @@ static void freezer_css_free(struct cgroup_subsys_state *css)
  * @freezer->lock.  freezer_attach() makes the new tasks conform to the
  * current state and all following state changes can see the new tasks.
  */
-static void freezer_attach(struct cgroup_subsys_state *new_css,
-			   struct cgroup_taskset *tset)
+static void freezer_attach(struct cgroup_taskset *tset)
 {
-	struct freezer *freezer = css_freezer(new_css);
 	struct task_struct *task;
-	bool clear_frozen = false;
+	struct cgroup_subsys_state *new_css;
 
 	mutex_lock(&freezer_mutex);
 
@@ -174,22 +172,21 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 	 * current state before executing the following - !frozen tasks may
 	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
 	 */
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, new_css, tset) {
+		struct freezer *freezer = css_freezer(new_css);
+
 		if (!(freezer->state & CGROUP_FREEZING)) {
 			__thaw_task(task);
 		} else {
 			freeze_task(task);
-			freezer->state &= ~CGROUP_FROZEN;
-			clear_frozen = true;
+			/* clear FROZEN and propagate upwards */
+			while (freezer && (freezer->state & CGROUP_FROZEN)) {
+				freezer->state &= ~CGROUP_FROZEN;
+				freezer = parent_freezer(freezer);
+			}
 		}
 	}
 
-	/* propagate FROZEN clearing upwards */
-	while (clear_frozen && (freezer = parent_freezer(freezer))) {
-		freezer->state &= ~CGROUP_FROZEN;
-		clear_frozen = freezer->state & CGROUP_FREEZING;
-	}
-
 	mutex_unlock(&freezer_mutex);
 }
 
diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c
index cdd8df4..b50d5a1 100644
--- a/kernel/cgroup_pids.c
+++ b/kernel/cgroup_pids.c
@@ -106,7 +106,7 @@ static void pids_uncharge(struct pids_cgroup *pids, int num)
 {
 	struct pids_cgroup *p;
 
-	for (p = pids; p; p = parent_pids(p))
+	for (p = pids; parent_pids(p); p = parent_pids(p))
 		pids_cancel(p, num);
 }
 
@@ -123,7 +123,7 @@ static void pids_charge(struct pids_cgroup *pids, int num)
 {
 	struct pids_cgroup *p;
 
-	for (p = pids; p; p = parent_pids(p))
+	for (p = pids; parent_pids(p); p = parent_pids(p))
 		atomic64_add(num, &p->counter);
 }
 
@@ -140,7 +140,7 @@ static int pids_try_charge(struct pids_cgroup *pids, int num)
 {
 	struct pids_cgroup *p, *q;
 
-	for (p = pids; p; p = parent_pids(p)) {
+	for (p = pids; parent_pids(p); p = parent_pids(p)) {
 		int64_t new = atomic64_add_return(num, &p->counter);
 
 		/*
@@ -162,13 +162,13 @@ revert:
 	return -EAGAIN;
 }
 
-static int pids_can_attach(struct cgroup_subsys_state *css,
-			   struct cgroup_taskset *tset)
+static int pids_can_attach(struct cgroup_taskset *tset)
 {
-	struct pids_cgroup *pids = css_pids(css);
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
 		struct cgroup_subsys_state *old_css;
 		struct pids_cgroup *old_pids;
 
@@ -187,13 +187,13 @@ static int pids_can_attach(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static void pids_cancel_attach(struct cgroup_subsys_state *css,
-			       struct cgroup_taskset *tset)
+static void pids_cancel_attach(struct cgroup_taskset *tset)
 {
-	struct pids_cgroup *pids = css_pids(css);
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
 		struct cgroup_subsys_state *old_css;
 		struct pids_cgroup *old_pids;
 
@@ -205,65 +205,28 @@ static void pids_cancel_attach(struct cgroup_subsys_state *css,
 	}
 }
 
+/*
+ * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
+ * on threadgroup_change_begin() held by the copy_process().
+ */
 static int pids_can_fork(struct task_struct *task, void **priv_p)
 {
 	struct cgroup_subsys_state *css;
 	struct pids_cgroup *pids;
-	int err;
 
-	/*
-	 * Use the "current" task_css for the pids subsystem as the tentative
-	 * css. It is possible we will charge the wrong hierarchy, in which
-	 * case we will forcefully revert/reapply the charge on the right
-	 * hierarchy after it is committed to the task proper.
-	 */
-	css = task_get_css(current, pids_cgrp_id);
+	css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
-
-	err = pids_try_charge(pids, 1);
-	if (err)
-		goto err_css_put;
-
-	*priv_p = css;
-	return 0;
-
-err_css_put:
-	css_put(css);
-	return err;
+	return pids_try_charge(pids, 1);
 }
 
 static void pids_cancel_fork(struct task_struct *task, void *priv)
 {
-	struct cgroup_subsys_state *css = priv;
-	struct pids_cgroup *pids = css_pids(css);
-
-	pids_uncharge(pids, 1);
-	css_put(css);
-}
-
-static void pids_fork(struct task_struct *task, void *priv)
-{
 	struct cgroup_subsys_state *css;
-	struct cgroup_subsys_state *old_css = priv;
 	struct pids_cgroup *pids;
-	struct pids_cgroup *old_pids = css_pids(old_css);
 
-	css = task_get_css(task, pids_cgrp_id);
+	css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
-
-	/*
-	 * If the association has changed, we have to revert and reapply the
-	 * charge/uncharge on the wrong hierarchy to the current one. Since
-	 * the association can only change due to an organisation event, its
-	 * okay for us to ignore the limit in this case.
-	 */
-	if (pids != old_pids) {
-		pids_uncharge(old_pids, 1);
-		pids_charge(pids, 1);
-	}
-
-	css_put(css);
-	css_put(old_css);
+	pids_uncharge(pids, 1);
 }
 
 static void pids_free(struct task_struct *task)
@@ -335,6 +298,7 @@ static struct cftype pids_files[] = {
 	{
 		.name = "current",
 		.read_s64 = pids_current_read,
+		.flags = CFTYPE_NOT_ON_ROOT,
 	},
 	{ }	/* terminate */
 };
@@ -346,7 +310,6 @@ struct cgroup_subsys pids_cgrp_subsys = {
 	.cancel_attach 	= pids_cancel_attach,
 	.can_fork	= pids_can_fork,
 	.cancel_fork	= pids_cancel_fork,
-	.fork		= pids_fork,
 	.free		= pids_free,
 	.legacy_cftypes	= pids_files,
 	.dfl_cftypes	= pids_files,
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 10ae736..02a8ea5 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1429,15 +1429,16 @@ static int fmeter_getrate(struct fmeter *fmp)
 static struct cpuset *cpuset_attach_old_cs;
 
 /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys_state *css,
-			     struct cgroup_taskset *tset)
+static int cpuset_can_attach(struct cgroup_taskset *tset)
 {
-	struct cpuset *cs = css_cs(css);
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 	struct task_struct *task;
 	int ret;
 
 	/* used later by cpuset_attach() */
-	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset));
+	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
+	cs = css_cs(css);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -1447,7 +1448,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task, cs->cpus_allowed);
 		if (ret)
 			goto out_unlock;
@@ -1467,9 +1468,14 @@ out_unlock:
 	return ret;
 }
 
-static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 {
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
+
+	cgroup_taskset_first(tset, &css);
+	cs = css_cs(css);
+
 	mutex_lock(&cpuset_mutex);
 	css_cs(css)->attach_in_progress--;
 	mutex_unlock(&cpuset_mutex);
@@ -1482,16 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
  */
 static cpumask_var_t cpus_attach;
 
-static void cpuset_attach(struct cgroup_subsys_state *css,
-			  struct cgroup_taskset *tset)
+static void cpuset_attach(struct cgroup_taskset *tset)
 {
 	/* static buf protected by cpuset_mutex */
 	static nodemask_t cpuset_attach_nodemask_to;
 	struct task_struct *task;
 	struct task_struct *leader;
-	struct cpuset *cs = css_cs(css);
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 	struct cpuset *oldcs = cpuset_attach_old_cs;
 
+	cgroup_taskset_first(tset, &css);
+	cs = css_cs(css);
+
 	mutex_lock(&cpuset_mutex);
 
 	/* prepare for attach */
@@ -1502,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		/*
 		 * can_attach beforehand should guarantee that this doesn't
 		 * fail.  TODO: have a better way to handle failure here
@@ -1518,7 +1527,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	 * sleep and should be moved outside migration path proper.
 	 */
 	cpuset_attach_nodemask_to = cs->effective_mems;
-	cgroup_taskset_for_each_leader(leader, tset) {
+	cgroup_taskset_for_each_leader(leader, css, tset) {
 		struct mm_struct *mm = get_task_mm(leader);
 
 		if (mm) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c3d61b9..a627f36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9466,12 +9466,12 @@ static int __perf_cgroup_move(void *info)
 	return 0;
 }
 
-static void perf_cgroup_attach(struct cgroup_subsys_state *css,
-			       struct cgroup_taskset *tset)
+static void perf_cgroup_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset)
+	cgroup_taskset_for_each(task, css, tset)
 		task_function_call(task, __perf_cgroup_move, task);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index f97f2c4..fce002e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1368,8 +1368,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = ktime_get_boot_ns();
 	p->io_context = NULL;
 	p->audit_context = NULL;
-	if (clone_flags & CLONE_THREAD)
-		threadgroup_change_begin(current);
+	threadgroup_change_begin(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1610,8 +1609,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	proc_fork_connector(p);
 	cgroup_post_fork(p, cgrp_ss_priv);
-	if (clone_flags & CLONE_THREAD)
-		threadgroup_change_end(current);
+	threadgroup_change_end(current);
 	perf_event_fork(p);
 
 	trace_task_newtask(p, clone_flags);
@@ -1652,8 +1650,7 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-	if (clone_flags & CLONE_THREAD)
-		threadgroup_change_end(current);
+	threadgroup_change_end(current);
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
diff --git a/kernel/pid.c b/kernel/pid.c
index ca36879..78b3d9f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -467,7 +467,7 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
 	rcu_read_lock();
 	if (type != PIDTYPE_PID)
 		task = task->group_leader;
-	pid = get_pid(task->pids[type].pid);
+	pid = get_pid(rcu_dereference(task->pids[type].pid));
 	rcu_read_unlock();
 	return pid;
 }
@@ -528,7 +528,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 	if (likely(pid_alive(task))) {
 		if (type != PIDTYPE_PID)
 			task = task->group_leader;
-		nr = pid_nr_ns(task->pids[type].pid, ns);
+		nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
 	}
 	rcu_read_unlock();
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4d568ac..732e993 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1947,13 +1947,38 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 #ifdef CONFIG_SMP
 	/*
+	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
+	 * possible to, falsely, observe p->on_cpu == 0.
+	 *
+	 * One must be running (->on_cpu == 1) in order to remove oneself
+	 * from the runqueue.
+	 *
+	 *  [S] ->on_cpu = 1;	[L] ->on_rq
+	 *      UNLOCK rq->lock
+	 *			RMB
+	 *      LOCK   rq->lock
+	 *  [S] ->on_rq = 0;    [L] ->on_cpu
+	 *
+	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
+	 * from the consecutive calls to schedule(); the first switching to our
+	 * task, the second putting it to sleep.
+	 */
+	smp_rmb();
+
+	/*
 	 * If the owning (remote) cpu is still in the middle of schedule() with
 	 * this task as prev, wait until its done referencing the task.
 	 */
 	while (p->on_cpu)
 		cpu_relax();
 	/*
-	 * Pairs with the smp_wmb() in finish_lock_switch().
+	 * Combined with the control dependency above, we have an effective
+	 * smp_load_acquire() without the need for full barriers.
+	 *
+	 * Pairs with the smp_store_release() in finish_lock_switch().
+	 *
+	 * This ensures that tasks getting woken will be fully ordered against
+	 * their previous state and preserve Program Order.
 	 */
 	smp_rmb();
 
@@ -2039,7 +2064,6 @@ out:
  */
 int wake_up_process(struct task_struct *p)
 {
-	WARN_ON(task_is_stopped_or_traced(p));
 	return try_to_wake_up(p, TASK_NORMAL, 0);
 }
 EXPORT_SYMBOL(wake_up_process);
@@ -5847,13 +5871,13 @@ static int init_rootdomain(struct root_domain *rd)
 {
 	memset(rd, 0, sizeof(*rd));
 
-	if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
 		goto out;
-	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
 		goto free_online;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
 		goto free_dlo_mask;
 
 	init_dl_bw(&rd->dl_bw);
@@ -8217,12 +8241,12 @@ static void cpu_cgroup_fork(struct task_struct *task, void *private)
 	sched_move_task(task);
 }
 
-static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
@@ -8235,12 +8259,12 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
-			      struct cgroup_taskset *tset)
+static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset)
+	cgroup_taskset_for_each(task, css, tset)
 		sched_move_task(task);
 }
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 26a5446..05de80b 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -788,6 +788,9 @@ cputime_t task_gtime(struct task_struct *t)
 	unsigned int seq;
 	cputime_t gtime;
 
+	if (!context_tracking_is_enabled())
+		return t->gtime;
+
 	do {
 		seq = read_seqbegin(&t->vtime_seqlock);
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e3cc163..8ec86ab 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -64,7 +64,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(HAVE_RT_PUSH_IPI)
 static void push_irq_work_func(struct irq_work *work);
 #endif
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index efd3bfc..b242775 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1073,6 +1073,9 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 *
+	 * In particular, the load of prev->state in finish_task_switch() must
+	 * happen before this.
+	 *
 	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
 	smp_store_release(&prev->on_cpu, 0);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 052e026..f15d6b6 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -392,7 +392,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
 	do {
 		prepare_to_wait(wq, &q->wait, mode);
 		if (test_bit(q->key.bit_nr, q->key.flags))
-			ret = (*action)(&q->key);
+			ret = (*action)(&q->key, mode);
 	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
 	finish_wait(wq, &q->wait);
 	return ret;
@@ -431,7 +431,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 		prepare_to_wait_exclusive(wq, &q->wait, mode);
 		if (!test_bit(q->key.bit_nr, q->key.flags))
 			continue;
-		ret = action(&q->key);
+		ret = action(&q->key, mode);
 		if (!ret)
 			continue;
 		abort_exclusive_wait(wq, &q->wait, mode, &q->key);
@@ -581,44 +581,44 @@ void wake_up_atomic_t(atomic_t *p)
 }
 EXPORT_SYMBOL(wake_up_atomic_t);
 
-__sched int bit_wait(struct wait_bit_key *word)
+__sched int bit_wait(struct wait_bit_key *word, int mode)
 {
-	if (signal_pending_state(current->state, current))
-		return 1;
 	schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait);
 
-__sched int bit_wait_io(struct wait_bit_key *word)
+__sched int bit_wait_io(struct wait_bit_key *word, int mode)
 {
-	if (signal_pending_state(current->state, current))
-		return 1;
 	io_schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait_io);
 
-__sched int bit_wait_timeout(struct wait_bit_key *word)
+__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	if (signal_pending_state(current->state, current))
-		return 1;
 	if (time_after_eq(now, word->timeout))
 		return -EAGAIN;
 	schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_timeout);
 
-__sched int bit_wait_io_timeout(struct wait_bit_key *word)
+__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	if (signal_pending_state(current->state, current))
-		return 1;
 	if (time_after_eq(now, word->timeout))
 		return -EAGAIN;
 	io_schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_io_timeout);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 867bc20..a3bbaee 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -531,7 +531,7 @@ static int __init cpu_stop_init(void)
 }
 early_initcall(cpu_stop_init);
 
-#ifdef CONFIG_STOP_MACHINE
+#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 {
@@ -631,4 +631,4 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 	return ret ?: done.ret;
 }
 
-#endif	/* CONFIG_STOP_MACHINE */
+#endif	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 75f1d05..9c6045a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1887,12 +1887,6 @@ rb_event_index(struct ring_buffer_event *event)
 	return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
 }
 
-static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp;
-	cpu_buffer->reader_page->read = 0;
-}
-
 static void rb_inc_iter(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
@@ -2803,8 +2797,11 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 
 	event = __rb_reserve_next(cpu_buffer, &info);
 
-	if (unlikely(PTR_ERR(event) == -EAGAIN))
+	if (unlikely(PTR_ERR(event) == -EAGAIN)) {
+		if (info.add_timestamp)
+			info.length -= RB_LEN_TIME_EXTEND;
 		goto again;
+	}
 
 	if (!event)
 		goto out_fail;
@@ -3626,7 +3623,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 
 	/* Finally update the reader page to the new head */
 	cpu_buffer->reader_page = reader;
-	rb_reset_reader_page(cpu_buffer);
+	cpu_buffer->reader_page->read = 0;
 
 	if (overwrite != cpu_buffer->last_overrun) {
 		cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
@@ -3636,6 +3633,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	goto again;
 
  out:
+	/* Update the read_stamp on the first event */
+	if (reader && reader->read == 0)
+		cpu_buffer->read_stamp = reader->page->time_stamp;
+
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6bbc5f6..4f6ef69 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -582,6 +582,12 @@ static void __ftrace_clear_event_pids(struct trace_array *tr)
 	unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, tr);
 	unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr);
 
+	unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, tr);
+	unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, tr);
+
+	unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr);
+	unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr);
+
 	list_for_each_entry(file, &tr->events, list) {
 		clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
 	}
@@ -1729,6 +1735,16 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
 						 tr, INT_MAX);
 		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
 						 tr, 0);
+
+		register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre,
+						     tr, INT_MAX);
+		register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post,
+						     tr, 0);
+
+		register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre,
+						 tr, INT_MAX);
+		register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post,
+						 tr, 0);
 	}
 
 	/*