Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Minor overlapping changes, nothing serious.

Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/cgroup/cgroup-v1.c

@@ -471,6 +471,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 	 */
 	p++;
 	if (p >= end) {
+		(*pos)++;
 		return NULL;
 	} else {
 		*pos = *p;
@@ -782,7 +783,7 @@ void cgroup1_release_agent(struct work_struct *work)
 
 	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
 	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-	if (!pathbuf || !agentbuf)
+	if (!pathbuf || !agentbuf || !strlen(agentbuf))
 		goto out;
 
 	spin_lock_irq(&css_set_lock);

kernel/cgroup/cgroup.c

@@ -3542,21 +3542,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_IO);
 }
 static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_MEM);
 }
 static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_CPU);
 }
@@ -4400,12 +4400,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 		}
 	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
 
-	if (!list_empty(&cset->tasks))
+	if (!list_empty(&cset->tasks)) {
 		it->task_pos = cset->tasks.next;
-	else if (!list_empty(&cset->mg_tasks))
+		it->cur_tasks_head = &cset->tasks;
+	} else if (!list_empty(&cset->mg_tasks)) {
 		it->task_pos = cset->mg_tasks.next;
-	else
+		it->cur_tasks_head = &cset->mg_tasks;
+	} else {
 		it->task_pos = cset->dying_tasks.next;
+		it->cur_tasks_head = &cset->dying_tasks;
+	}
 
 	it->tasks_head = &cset->tasks;
 	it->mg_tasks_head = &cset->mg_tasks;
@@ -4463,10 +4467,14 @@ repeat:
 		else
 			it->task_pos = it->task_pos->next;
 
-		if (it->task_pos == it->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->cur_tasks_head = it->mg_tasks_head;
+		}
+		if (it->task_pos == it->mg_tasks_head) {
 			it->task_pos = it->dying_tasks_head->next;
+			it->cur_tasks_head = it->dying_tasks_head;
+		}
 		if (it->task_pos == it->dying_tasks_head)
 			css_task_iter_advance_css_set(it);
 	} else {
@@ -4485,11 +4493,12 @@ repeat:
 			goto repeat;
 
 		/* and dying leaders w/o live member threads */
-		if (!atomic_read(&task->signal->live))
+		if (it->cur_tasks_head == it->dying_tasks_head &&
+		    !atomic_read(&task->signal->live))
 			goto repeat;
 	} else {
 		/* skip all dying ones */
-		if (task->flags & PF_EXITING)
+		if (it->cur_tasks_head == it->dying_tasks_head)
 			goto repeat;
 	}
 }
@@ -4595,6 +4604,9 @@ static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos)
 	struct kernfs_open_file *of = s->private;
 	struct css_task_iter *it = of->priv;
 
+	if (pos)
+		(*pos)++;
+
 	return css_task_iter_next(it);
 }
 
@@ -4610,7 +4622,7 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 	 * from position 0, so we can simply keep iterating on !0 *pos.
 	 */
 	if (!it) {
-		if (WARN_ON_ONCE((*pos)++))
+		if (WARN_ON_ONCE((*pos)))
 			return ERR_PTR(-EINVAL);
 
 		it = kzalloc(sizeof(*it), GFP_KERNEL);
@@ -4618,10 +4630,11 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 			return ERR_PTR(-ENOMEM);
 		of->priv = it;
 		css_task_iter_start(&cgrp->self, iter_flags, it);
-	} else if (!(*pos)++) {
+	} else if (!(*pos)) {
 		css_task_iter_end(it);
 		css_task_iter_start(&cgrp->self, iter_flags, it);
-	}
+	} else
+		return it->cur_task;
 
 	return cgroup_procs_next(s, NULL, NULL);
 }
@@ -6258,6 +6271,10 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 		return;
 	}
 
+	/* Don't associate the sock with unrelated interrupted task's cgroup. */
+	if (in_interrupt())
+		return;
+
 	rcu_read_lock();
 
 	while (true) {

kernel/exit.c

@@ -619,8 +619,8 @@ static void forget_original_parent(struct task_struct *father,
 	reaper = find_new_reaper(father, reaper);
 	list_for_each_entry(p, &father->children, sibling) {
 		for_each_thread(p, t) {
-			t->real_parent = reaper;
-			BUG_ON((!t->ptrace) != (t->parent == father));
+			RCU_INIT_POINTER(t->real_parent, reaper);
+			BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father));
 			if (likely(!t->ptrace))
 				t->parent = t->real_parent;
 			if (t->pdeath_signal)

kernel/fork.c

@@ -1508,7 +1508,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 		return 0;
 	}
 	sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
-	rcu_assign_pointer(tsk->sighand, sig);
+	RCU_INIT_POINTER(tsk->sighand, sig);
 	if (!sig)
 		return -ENOMEM;
 

kernel/pid.c

@@ -247,6 +247,16 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 		tmp = tmp->parent;
 	}
 
+	/*
+	 * ENOMEM is not the most obvious choice especially for the case
+	 * where the child subreaper has already exited and the pid
+	 * namespace denies the creation of any new processes. But ENOMEM
+	 * is what we have exposed to userspace for a long time and it is
+	 * documented behavior for pid namespaces. So we can't easily
+	 * change it even if there were an error code better suited.
+	 */
+	retval = -ENOMEM;
+
 	if (unlikely(is_child_reaper(pid))) {
 		if (pid_ns_prepare_proc(ns))
 			goto out_free;

kernel/power/snapshot.c

@@ -1681,7 +1681,7 @@ static unsigned long minimum_image_size(unsigned long saveable)
  * hibernation for allocations made while saving the image and for device
  * drivers, in case they need to allocate memory from their hibernation
  * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough
- * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through
+ * estimate) and reserved_size divided by PAGE_SIZE (which is tunable through
  * /sys/power/reserved_size, respectively).  To make this happen, we compute the
  * total number of available page frames and allocate at least
  *

kernel/sched/fair.c

@@ -8337,6 +8337,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 
 	sgs->group_capacity = group->sgc->capacity;
 
+	sgs->group_weight = group->group_weight;
+
 	sgs->group_type = group_classify(sd->imbalance_pct, group, sgs);
 
 	/*

kernel/trace/blktrace.c

@@ -335,6 +335,7 @@ static void put_probe_ref(void)
 
 static void blk_trace_cleanup(struct blk_trace *bt)
 {
+	synchronize_rcu();
 	blk_trace_free(bt);
 	put_probe_ref();
 }
@@ -629,8 +630,10 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 static int __blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	bt = rcu_dereference_protected(q->blk_trace,
+				       lockdep_is_held(&q->blk_trace_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -740,8 +743,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 void blk_trace_shutdown(struct request_queue *q)
 {
 	mutex_lock(&q->blk_trace_mutex);
-
-	if (q->blk_trace) {
+	if (rcu_dereference_protected(q->blk_trace,
+				      lockdep_is_held(&q->blk_trace_mutex))) {
 		__blk_trace_startstop(q, 0);
 		__blk_trace_remove(q);
 	}
@@ -752,8 +755,10 @@ void blk_trace_shutdown(struct request_queue *q)
 #ifdef CONFIG_BLK_CGROUP
 static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	/* We don't use the 'bt' value here except as an optimization... */
+	bt = rcu_dereference_protected(q->blk_trace, 1);
 	if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
 		return 0;
 
@@ -796,10 +801,14 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq)
 static void blk_add_trace_rq(struct request *rq, int error,
 			     unsigned int nr_bytes, u32 what, u64 cgid)
 {
-	struct blk_trace *bt = rq->q->blk_trace;
+	struct blk_trace *bt;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(rq->q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	if (blk_rq_is_passthrough(rq))
 		what |= BLK_TC_ACT(BLK_TC_PC);
@@ -808,6 +817,7 @@ static void blk_add_trace_rq(struct request *rq, int error,
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
 			rq->cmd_flags, what, error, 0, NULL, cgid);
+	rcu_read_unlock();
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
@@ -853,14 +863,19 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
 static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 			      u32 what, int error)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
 			bio_op(bio), bio->bi_opf, what, error, 0, NULL,
 			blk_trace_bio_get_cgid(q, bio));
+	rcu_read_unlock();
 }
 
 static void blk_add_trace_bio_bounce(void *ignore,
@@ -905,11 +920,14 @@ static void blk_add_trace_getrq(void *ignore,
 	if (bio)
 		blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
 	else {
-		struct blk_trace *bt = q->blk_trace;
+		struct blk_trace *bt;
 
+		rcu_read_lock();
+		bt = rcu_dereference(q->blk_trace);
 		if (bt)
 			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
 					NULL, 0);
+		rcu_read_unlock();
 	}
 }
 
@@ -921,27 +939,35 @@ static void blk_add_trace_sleeprq(void *ignore,
 	if (bio)
 		blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
 	else {
-		struct blk_trace *bt = q->blk_trace;
+		struct blk_trace *bt;
 
+		rcu_read_lock();
+		bt = rcu_dereference(q->blk_trace);
 		if (bt)
 			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
 					0, 0, NULL, 0);
+		rcu_read_unlock();
 	}
 }
 
 static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
 	if (bt)
 		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
+	rcu_read_unlock();
 }
 
 static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 				    unsigned int depth, bool explicit)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
 	if (bt) {
 		__be64 rpdu = cpu_to_be64(depth);
 		u32 what;
@@ -953,14 +979,17 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 
 		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
 	}
+	rcu_read_unlock();
 }
 
 static void blk_add_trace_split(void *ignore,
 				struct request_queue *q, struct bio *bio,
 				unsigned int pdu)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
 	if (bt) {
 		__be64 rpdu = cpu_to_be64(pdu);
 
@@ -969,6 +998,7 @@ static void blk_add_trace_split(void *ignore,
 				BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu),
 				&rpdu, blk_trace_bio_get_cgid(q, bio));
 	}
+	rcu_read_unlock();
 }
 
 /**
@@ -988,11 +1018,15 @@ static void blk_add_trace_bio_remap(void *ignore,
 				    struct request_queue *q, struct bio *bio,
 				    dev_t dev, sector_t from)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 	struct blk_io_trace_remap r;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	r.device_from = cpu_to_be32(dev);
 	r.device_to   = cpu_to_be32(bio_dev(bio));
@@ -1001,6 +1035,7 @@ static void blk_add_trace_bio_remap(void *ignore,
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
 			bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status,
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
+	rcu_read_unlock();
 }
 
 /**
@@ -1021,11 +1056,15 @@ static void blk_add_trace_rq_remap(void *ignore,
 				   struct request *rq, dev_t dev,
 				   sector_t from)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 	struct blk_io_trace_remap r;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	r.device_from = cpu_to_be32(dev);
 	r.device_to   = cpu_to_be32(disk_devt(rq->rq_disk));
@@ -1034,6 +1073,7 @@ static void blk_add_trace_rq_remap(void *ignore,
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
 			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
 			sizeof(r), &r, blk_trace_request_get_cgid(q, rq));
+	rcu_read_unlock();
 }
 
 /**
@@ -1051,14 +1091,19 @@ void blk_add_driver_data(struct request_queue *q,
 			 struct request *rq,
 			 void *data, size_t len)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, 0, len, data,
 				blk_trace_request_get_cgid(q, rq));
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
 
@@ -1597,6 +1642,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 		return -EINVAL;
 
 	put_probe_ref();
+	synchronize_rcu();
 	blk_trace_free(bt);
 	return 0;
 }
@@ -1758,6 +1804,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	struct hd_struct *p = dev_to_part(dev);
 	struct request_queue *q;
 	struct block_device *bdev;
+	struct blk_trace *bt;
 	ssize_t ret = -ENXIO;
 
 	bdev = bdget(part_devt(p));
@@ -1770,21 +1817,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 
 	mutex_lock(&q->blk_trace_mutex);
 
+	bt = rcu_dereference_protected(q->blk_trace,
+				       lockdep_is_held(&q->blk_trace_mutex));
 	if (attr == &dev_attr_enable) {
-		ret = sprintf(buf, "%u\n", !!q->blk_trace);
+		ret = sprintf(buf, "%u\n", !!bt);
 		goto out_unlock_bdev;
 	}
 
-	if (q->blk_trace == NULL)
+	if (bt == NULL)
 		ret = sprintf(buf, "disabled\n");
 	else if (attr == &dev_attr_act_mask)
-		ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
+		ret = blk_trace_mask2str(buf, bt->act_mask);
 	else if (attr == &dev_attr_pid)
-		ret = sprintf(buf, "%u\n", q->blk_trace->pid);
+		ret = sprintf(buf, "%u\n", bt->pid);
 	else if (attr == &dev_attr_start_lba)
-		ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
+		ret = sprintf(buf, "%llu\n", bt->start_lba);
 	else if (attr == &dev_attr_end_lba)
-		ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+		ret = sprintf(buf, "%llu\n", bt->end_lba);
 
 out_unlock_bdev:
 	mutex_unlock(&q->blk_trace_mutex);
@@ -1801,6 +1850,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	struct block_device *bdev;
 	struct request_queue *q;
 	struct hd_struct *p;
+	struct blk_trace *bt;
 	u64 value;
 	ssize_t ret = -EINVAL;
 
@@ -1831,8 +1881,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
 	mutex_lock(&q->blk_trace_mutex);
 
+	bt = rcu_dereference_protected(q->blk_trace,
+				       lockdep_is_held(&q->blk_trace_mutex));
 	if (attr == &dev_attr_enable) {
-		if (!!value == !!q->blk_trace) {
+		if (!!value == !!bt) {
 			ret = 0;
 			goto out_unlock_bdev;
 		}
@@ -1844,18 +1896,21 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 	ret = 0;
-	if (q->blk_trace == NULL)
+	if (bt == NULL) {
 		ret = blk_trace_setup_queue(q, bdev);
+		bt = rcu_dereference_protected(q->blk_trace,
+				lockdep_is_held(&q->blk_trace_mutex));
+	}
 
 	if (ret == 0) {
 		if (attr == &dev_attr_act_mask)
-			q->blk_trace->act_mask = value;
+			bt->act_mask = value;
 		else if (attr == &dev_attr_pid)
-			q->blk_trace->pid = value;
+			bt->pid = value;
 		else if (attr == &dev_attr_start_lba)
-			q->blk_trace->start_lba = value;
+			bt->start_lba = value;
 		else if (attr == &dev_attr_end_lba)
-			q->blk_trace->end_lba = value;
+			bt->end_lba = value;
 	}
 
 out_unlock_bdev:

kernel/trace/ftrace.c

@@ -1547,6 +1547,8 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end)
 		rec = bsearch(&key, pg->records, pg->index,
 			      sizeof(struct dyn_ftrace),
 			      ftrace_cmp_recs);
+		if (rec)
+			break;
 	}
 	return rec;
 }

kernel/workqueue.c

@@ -1411,14 +1411,16 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 		return;
 	rcu_read_lock();
 retry:
-	if (req_cpu == WORK_CPU_UNBOUND)
-		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
-
 	/* pwq which will be used unless @work is executing elsewhere */
-	if (!(wq->flags & WQ_UNBOUND))
-		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
-	else
+	if (wq->flags & WQ_UNBOUND) {
+		if (req_cpu == WORK_CPU_UNBOUND)
+			cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 		pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
+	} else {
+		if (req_cpu == WORK_CPU_UNBOUND)
+			cpu = raw_smp_processor_id();
+		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
+	}
 
 	/*
 	 * If @work was previously on a different pool, it might still be