Merge tag 'v5.2-rc6' into for-5.3/block

Merge 5.2-rc6 into for-5.3/block, so we get the same page merge leak
fix. Otherwise we end up having conflicts with future patches between
for-5.3/block and master that touch this area. In particular, it makes
the bio_full() fix hard to backport to stable.

* tag 'v5.2-rc6': (482 commits)
  Linux 5.2-rc6
  Revert "iommu/vt-d: Fix lock inversion between iommu->lock and device_domain_lock"
  Bluetooth: Fix regression with minimum encryption key size alignment
  tcp: refine memory limit test in tcp_fragment()
  x86/vdso: Prevent segfaults due to hoisted vclock reads
  SUNRPC: Fix a credential refcount leak
  Revert "SUNRPC: Declare RPC timers as TIMER_DEFERRABLE"
  net :sunrpc :clnt :Fix xps refcount imbalance on the error path
  NFS4: Only set creation opendata if O_CREAT
  ARM: 8867/1: vdso: pass --be8 to linker if necessary
  KVM: nVMX: reorganize initial steps of vmx_set_nested_state
  KVM: PPC: Book3S HV: Invalidate ERAT when flushing guest TLB entries
  habanalabs: use u64_to_user_ptr() for reading user pointers
  nfsd: replace Jeff by Chuck as nfsd co-maintainer
  inet: clear num_timeout reqsk_alloc()
  PCI/P2PDMA: Ignore root complex whitelist when an IOMMU is present
  net: mvpp2: debugfs: Add pmap to fs dump
  ipv6: Default fib6_type to RTN_UNICAST when not set
  net: hns3: Fix inconsistent indenting
  net/af_iucv: always register net_device notifier
  ...

4 files changed, 92 insertions, 39 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 30aba80858e3..e98df19655dc 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -215,7 +215,8 @@ static struct cftype cgroup_base_files[];
 
 static int cgroup_apply_control(struct cgroup *cgrp);
 static void cgroup_finalize_control(struct cgroup *cgrp, int ret);
-static void css_task_iter_advance(struct css_task_iter *it);
+static void css_task_iter_skip(struct css_task_iter *it,
+			       struct task_struct *task);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
 static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 					      struct cgroup_subsys *ss);
@@ -738,6 +739,7 @@ struct css_set init_css_set = {
 	.dom_cset		= &init_css_set,
 	.tasks			= LIST_HEAD_INIT(init_css_set.tasks),
 	.mg_tasks		= LIST_HEAD_INIT(init_css_set.mg_tasks),
+	.dying_tasks		= LIST_HEAD_INIT(init_css_set.dying_tasks),
 	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
 	.threaded_csets		= LIST_HEAD_INIT(init_css_set.threaded_csets),
 	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
@@ -843,6 +845,21 @@ static void css_set_update_populated(struct css_set *cset, bool populated)
 		cgroup_update_populated(link->cgrp, populated);
 }
 
+/*
+ * @task is leaving, advance task iterators which are pointing to it so
+ * that they can resume at the next position.  Advancing an iterator might
+ * remove it from the list, use safe walk.  See css_task_iter_skip() for
+ * details.
+ */
+static void css_set_skip_task_iters(struct css_set *cset,
+				    struct task_struct *task)
+{
+	struct css_task_iter *it, *pos;
+
+	list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node)
+		css_task_iter_skip(it, task);
+}
+
 /**
  * css_set_move_task - move a task from one css_set to another
  * @task: task being moved
@@ -868,22 +885,9 @@ static void css_set_move_task(struct task_struct *task,
 		css_set_update_populated(to_cset, true);
 
 	if (from_cset) {
-		struct css_task_iter *it, *pos;
-
 		WARN_ON_ONCE(list_empty(&task->cg_list));
 
-		/*
-		 * @task is leaving, advance task iterators which are
-		 * pointing to it so that they can resume at the next
-		 * position.  Advancing an iterator might remove it from
-		 * the list, use safe walk.  See css_task_iter_advance*()
-		 * for details.
-		 */
-		list_for_each_entry_safe(it, pos, &from_cset->task_iters,
-					 iters_node)
-			if (it->task_pos == &task->cg_list)
-				css_task_iter_advance(it);
-
+		css_set_skip_task_iters(from_cset, task);
 		list_del_init(&task->cg_list);
 		if (!css_set_populated(from_cset))
 			css_set_update_populated(from_cset, false);
@@ -1210,6 +1214,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	cset->dom_cset = cset;
 	INIT_LIST_HEAD(&cset->tasks);
 	INIT_LIST_HEAD(&cset->mg_tasks);
+	INIT_LIST_HEAD(&cset->dying_tasks);
 	INIT_LIST_HEAD(&cset->task_iters);
 	INIT_LIST_HEAD(&cset->threaded_csets);
 	INIT_HLIST_NODE(&cset->hlist);
@@ -4409,15 +4414,18 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 			it->task_pos = NULL;
 			return;
 		}
-	} while (!css_set_populated(cset));
+	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
 
 	if (!list_empty(&cset->tasks))
 		it->task_pos = cset->tasks.next;
-	else
+	else if (!list_empty(&cset->mg_tasks))
 		it->task_pos = cset->mg_tasks.next;
+	else
+		it->task_pos = cset->dying_tasks.next;
 
 	it->tasks_head = &cset->tasks;
 	it->mg_tasks_head = &cset->mg_tasks;
+	it->dying_tasks_head = &cset->dying_tasks;
 
 	/*
 	 * We don't keep css_sets locked across iteration steps and thus
@@ -4443,9 +4451,20 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 	list_add(&it->iters_node, &cset->task_iters);
 }
 
+static void css_task_iter_skip(struct css_task_iter *it,
+			       struct task_struct *task)
+{
+	lockdep_assert_held(&css_set_lock);
+
+	if (it->task_pos == &task->cg_list) {
+		it->task_pos = it->task_pos->next;
+		it->flags |= CSS_TASK_ITER_SKIPPED;
+	}
+}
+
 static void css_task_iter_advance(struct css_task_iter *it)
 {
-	struct list_head *next;
+	struct task_struct *task;
 
 	lockdep_assert_held(&css_set_lock);
 repeat:
@@ -4455,25 +4474,40 @@ repeat:
 		 * consumed first and then ->mg_tasks.  After ->mg_tasks,
 		 * we move onto the next cset.
 		 */
-		next = it->task_pos->next;
-
-		if (next == it->tasks_head)
-			next = it->mg_tasks_head->next;
+		if (it->flags & CSS_TASK_ITER_SKIPPED)
+			it->flags &= ~CSS_TASK_ITER_SKIPPED;
+		else
+			it->task_pos = it->task_pos->next;
 
-		if (next == it->mg_tasks_head)
+		if (it->task_pos == it->tasks_head)
+			it->task_pos = it->mg_tasks_head->next;
+		if (it->task_pos == it->mg_tasks_head)
+			it->task_pos = it->dying_tasks_head->next;
+		if (it->task_pos == it->dying_tasks_head)
 			css_task_iter_advance_css_set(it);
-		else
-			it->task_pos = next;
 	} else {
 		/* called from start, proceed to the first cset */
 		css_task_iter_advance_css_set(it);
 	}
 
-	/* if PROCS, skip over tasks which aren't group leaders */
-	if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&
-	    !thread_group_leader(list_entry(it->task_pos, struct task_struct,
-					    cg_list)))
-		goto repeat;
+	if (!it->task_pos)
+		return;
+
+	task = list_entry(it->task_pos, struct task_struct, cg_list);
+
+	if (it->flags & CSS_TASK_ITER_PROCS) {
+		/* if PROCS, skip over tasks which aren't group leaders */
+		if (!thread_group_leader(task))
+			goto repeat;
+
+		/* and dying leaders w/o live member threads */
+		if (!atomic_read(&task->signal->live))
+			goto repeat;
+	} else {
+		/* skip all dying ones */
+		if (task->flags & PF_EXITING)
+			goto repeat;
+	}
 }
 
 /**
@@ -4529,6 +4563,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 
 	spin_lock_irq(&css_set_lock);
 
+	/* @it may be half-advanced by skips, finish advancing */
+	if (it->flags & CSS_TASK_ITER_SKIPPED)
+		css_task_iter_advance(it);
+
 	if (it->task_pos) {
 		it->cur_task = list_entry(it->task_pos, struct task_struct,
 					  cg_list);
@@ -6010,6 +6048,7 @@ void cgroup_exit(struct task_struct *tsk)
 	if (!list_empty(&tsk->cg_list)) {
 		spin_lock_irq(&css_set_lock);
 		css_set_move_task(tsk, cset, NULL, false);
+		list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 		cset->nr_tasks--;
 
 		WARN_ON_ONCE(cgroup_task_frozen(tsk));
@@ -6035,6 +6074,13 @@ void cgroup_release(struct task_struct *task)
 	do_each_subsys_mask(ss, ssid, have_release_callback) {
 		ss->release(task);
 	} while_each_subsys_mask();
+
+	if (use_task_css_set_links) {
+		spin_lock_irq(&css_set_lock);
+		css_set_skip_task_iters(task_css_set(task), task);
+		list_del_init(&task->cg_list);
+		spin_unlock_irq(&css_set_lock);
+	}
 }
 
 void cgroup_free(struct task_struct *task)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 6a1942ed781c..515525ff1cfd 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3254,10 +3254,23 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 	spin_unlock_irqrestore(&callback_lock, flags);
 }
 
+/**
+ * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe.
+ * @tsk: pointer to task_struct with which the scheduler is struggling
+ *
+ * Description: In the case that the scheduler cannot find an allowed cpu in
+ * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy
+ * mode however, this value is the same as task_cs(tsk)->effective_cpus,
+ * which will not contain a sane cpumask during cases such as cpu hotplugging.
+ * This is the absolute last resort for the scheduler and it is only used if
+ * _every_ other avenue has been traveled.
+ **/
+
 void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
 	rcu_read_lock();
-	do_set_cpus_allowed(tsk, task_cs(tsk)->effective_cpus);
+	do_set_cpus_allowed(tsk, is_in_v2_mode() ?
+		task_cs(tsk)->cpus_allowed : cpu_possible_mask);
 	rcu_read_unlock();
 
 	/*
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index c9960baaa14f..8e513a573fe9 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Process number limiting controller for cgroups.
  *
@@ -25,10 +26,6 @@
  * a superset of parent/child/pids.current.
  *
  * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com>
- *
- * This file is subject to the terms and conditions of version 2 of the GNU
- * General Public License.  See the file COPYING in the main directory of the
- * Linux distribution for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c
index 1d75ae7f1cb7..ae042c347c64 100644
--- a/kernel/cgroup/rdma.c
+++ b/kernel/cgroup/rdma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * RDMA resource limiting controller for cgroups.
  *
@@ -5,10 +6,6 @@
  * additional RDMA resources after a certain limit is reached.
  *
  * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com>
- *
- * This file is subject to the terms and conditions of version 2 of the GNU
- * General Public License. See the file COPYING in the main directory of the
- * Linux distribution for more details.
  */
 
 #include <linux/bitops.h>