Merge tag 'v4.17-rc4' into rproc-next

Pick up fixes from rproc-v4.17-1

Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>

7 files changed, 119 insertions, 44 deletions

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index f0ecd98509d8..771ae9730ac6 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -4934,8 +4934,16 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio)
 	bool new_queue = false;
 	bool bfqq_already_existing = false, split = false;
 
-	if (!rq->elv.icq)
+	/*
+	 * Even if we don't have an icq attached, we should still clear
+	 * the scheduler pointers, as they might point to previously
+	 * allocated bic/bfqq structs.
+	 */
+	if (!rq->elv.icq) {
+		rq->elv.priv[0] = rq->elv.priv[1] = NULL;
 		return;
+	}
+
 	bic = icq_to_bic(rq->elv.icq);
 
 	spin_lock_irq(&bfqd->lock);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1c16694ae145..eb85cb87c40f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1177,26 +1177,20 @@ int blkcg_init_queue(struct request_queue *q)
 
 	preloaded = !radix_tree_preload(GFP_KERNEL);
 
-	/*
-	 * Make sure the root blkg exists and count the existing blkgs.  As
-	 * @q is bypassing at this point, blkg_lookup_create() can't be
-	 * used.  Open code insertion.
-	 */
+	/* Make sure the root blkg exists. */
 	rcu_read_lock();
 	spin_lock_irq(q->queue_lock);
 	blkg = blkg_create(&blkcg_root, q, new_blkg);
+	if (IS_ERR(blkg))
+		goto err_unlock;
+	q->root_blkg = blkg;
+	q->root_rl.blkg = blkg;
 	spin_unlock_irq(q->queue_lock);
 	rcu_read_unlock();
 
 	if (preloaded)
 		radix_tree_preload_end();
 
-	if (IS_ERR(blkg))
-		return PTR_ERR(blkg);
-
-	q->root_blkg = blkg;
-	q->root_rl.blkg = blkg;
-
 	ret = blk_throtl_init(q);
 	if (ret) {
 		spin_lock_irq(q->queue_lock);
@@ -1204,6 +1198,13 @@ int blkcg_init_queue(struct request_queue *q)
 		spin_unlock_irq(q->queue_lock);
 	}
 	return ret;
+
+err_unlock:
+	spin_unlock_irq(q->queue_lock);
+	rcu_read_unlock();
+	if (preloaded)
+		radix_tree_preload_end();
+	return PTR_ERR(blkg);
 }
 
 /**
@@ -1410,9 +1411,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	__clear_bit(pol->plid, q->blkcg_pols);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
-		/* grab blkcg lock too while removing @pd from @blkg */
-		spin_lock(&blkg->blkcg->lock);
-
 		if (blkg->pd[pol->plid]) {
 			if (!blkg->pd[pol->plid]->offline &&
 			    pol->pd_offline_fn) {
@@ -1422,8 +1420,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}
-
-		spin_unlock(&blkg->blkcg->lock);
 	}
 
 	spin_unlock_irq(q->queue_lock);
diff --git a/block/blk-core.c b/block/blk-core.c
index 806ce2442819..85909b431eb0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -201,6 +201,10 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->part = NULL;
 	seqcount_init(&rq->gstate_seq);
 	u64_stats_init(&rq->aborted_gstate_sync);
+	/*
+	 * See comment of blk_mq_init_request
+	 */
+	WRITE_ONCE(rq->gstate, MQ_RQ_GEN_INC);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -915,7 +919,6 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 
 	while (true) {
 		bool success = false;
-		int ret;
 
 		rcu_read_lock();
 		if (percpu_ref_tryget_live(&q->q_usage_counter)) {
@@ -947,14 +950,12 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 		 */
 		smp_rmb();
 
-		ret = wait_event_interruptible(q->mq_freeze_wq,
-				(atomic_read(&q->mq_freeze_depth) == 0 &&
-				 (preempt || !blk_queue_preempt_only(q))) ||
-				blk_queue_dying(q));
+		wait_event(q->mq_freeze_wq,
+			   (atomic_read(&q->mq_freeze_depth) == 0 &&
+			    (preempt || !blk_queue_preempt_only(q))) ||
+			   blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
-		if (ret)
-			return ret;
 	}
 }
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0dc9e341c2a7..9ce9cac16c3f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -95,18 +95,15 @@ static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	if (blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) {
-		/*
-		 * index[0] counts the specific partition that was asked
-		 * for. index[1] counts the ones that are active on the
-		 * whole device, so increment that if mi->part is indeed
-		 * a partition, and not a whole device.
-		 */
-		if (rq->part == mi->part)
-			mi->inflight[0]++;
-		if (mi->part->partno)
-			mi->inflight[1]++;
-	}
+	/*
+	 * index[0] counts the specific partition that was asked for. index[1]
+	 * counts the ones that are active on the whole device, so increment
+	 * that if mi->part is indeed a partition, and not a whole device.
+	 */
+	if (rq->part == mi->part)
+		mi->inflight[0]++;
+	if (mi->part->partno)
+		mi->inflight[1]++;
 }
 
 void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
@@ -118,6 +115,25 @@ void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
 }
 
+static void blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
+				     struct request *rq, void *priv,
+				     bool reserved)
+{
+	struct mq_inflight *mi = priv;
+
+	if (rq->part == mi->part)
+		mi->inflight[rq_data_dir(rq)]++;
+}
+
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+			 unsigned int inflight[2])
+{
+	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+
+	inflight[0] = inflight[1] = 0;
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+}
+
 void blk_freeze_queue_start(struct request_queue *q)
 {
 	int freeze_depth;
@@ -2042,6 +2058,13 @@ static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
 
 	seqcount_init(&rq->gstate_seq);
 	u64_stats_init(&rq->aborted_gstate_sync);
+	/*
+	 * start gstate with gen 1 instead of 0, otherwise it will be equal
+	 * to aborted_gstate, and be identified timed out by
+	 * blk_mq_terminate_expired.
+	 */
+	WRITE_ONCE(rq->gstate, MQ_RQ_GEN_INC);
+
 	return 0;
 }
 
@@ -2329,7 +2352,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 
 static void blk_mq_map_swqueue(struct request_queue *q)
 {
-	unsigned int i;
+	unsigned int i, hctx_idx;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
@@ -2346,8 +2369,23 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 
 	/*
 	 * Map software to hardware queues.
+	 *
+	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
 	for_each_possible_cpu(i) {
+		hctx_idx = q->mq_map[i];
+		/* unmapped hw queue can be remapped after CPU topo changed */
+		if (!set->tags[hctx_idx] &&
+		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
+			/*
+			 * If tags initialization fail for some hctx,
+			 * that hctx won't be brought online.  In this
+			 * case, remap the current ctx to hctx[0] which
+			 * is guaranteed to always have tags allocated
+			 */
+			q->mq_map[i] = 0;
+		}
+
 		ctx = per_cpu_ptr(q->queue_ctx, i);
 		hctx = blk_mq_map_queue(q, i);
 
@@ -2359,8 +2397,21 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	mutex_unlock(&q->sysfs_lock);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		/* every hctx should get mapped by at least one CPU */
-		WARN_ON(!hctx->nr_ctx);
+		/*
+		 * If no software queues are mapped to this hardware queue,
+		 * disable it and free the request entries.
+		 */
+		if (!hctx->nr_ctx) {
+			/* Never unmap queue 0.  We need it as a
+			 * fallback in case of a new remap fails
+			 * allocation
+			 */
+			if (i && set->tags[i])
+				blk_mq_free_map_and_requests(set, i);
+
+			hctx->tags = NULL;
+			continue;
+		}
 
 		hctx->tags = set->tags[i];
 		WARN_ON(!hctx->tags);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 88c558f71819..e1bb420dc5d6 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -7,6 +7,9 @@
 
 struct blk_mq_tag_set;
 
+/**
+ * struct blk_mq_ctx - State for a software queue facing the submitting CPUs
+ */
 struct blk_mq_ctx {
 	struct {
 		spinlock_t		lock;
@@ -185,7 +188,9 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
 }
 
 void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
-			unsigned int inflight[2]);
+		      unsigned int inflight[2]);
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+			 unsigned int inflight[2]);
 
 static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
 {
diff --git a/block/genhd.c b/block/genhd.c
index dc7e089373b9..c4513fe1adda 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -82,6 +82,18 @@ void part_in_flight(struct request_queue *q, struct hd_struct *part,
 	}
 }
 
+void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+		       unsigned int inflight[2])
+{
+	if (q->mq_ops) {
+		blk_mq_in_flight_rw(q, part, inflight);
+		return;
+	}
+
+	inflight[0] = atomic_read(&part->in_flight[0]);
+	inflight[1] = atomic_read(&part->in_flight[1]);
+}
+
 struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
 {
 	struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 08dabcd8b6ae..db57cced9b98 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -145,13 +145,15 @@ ssize_t part_stat_show(struct device *dev,
 		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
 }
 
-ssize_t part_inflight_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
+	struct request_queue *q = part_to_disk(p)->queue;
+	unsigned int inflight[2];
 
-	return sprintf(buf, "%8u %8u\n", atomic_read(&p->in_flight[0]),
-		atomic_read(&p->in_flight[1]));
+	part_in_flight_rw(q, p, inflight);
+	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
 }
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST