Merge tag 'v5.1-rc6' into for-5.2/block

Pull in v5.1-rc6 to resolve two conflicts. One is in BFQ, in just a
comment, and is trivial. The other one is a conflict due to a later fix
in the bio multi-page work, and needs a bit more care.

* tag 'v5.1-rc6': (770 commits)
  Linux 5.1-rc6
  block: make sure that bvec length can't be overflow
  block: kill all_q_node in request_queue
  x86/cpu/intel: Lower the "ENERGY_PERF_BIAS: Set to normal" message's log priority
  coredump: fix race condition between mmget_not_zero()/get_task_mm() and core dumping
  mm/kmemleak.c: fix unused-function warning
  init: initialize jump labels before command line option parsing
  kernel/watchdog_hld.c: hard lockup message should end with a newline
  kcov: improve CONFIG_ARCH_HAS_KCOV help text
  mm: fix inactive list balancing between NUMA nodes and cgroups
  mm/hotplug: treat CMA pages as unmovable
  proc: fixup proc-pid-vm test
  proc: fix map_files test on F29
  mm/vmstat.c: fix /proc/vmstat format for CONFIG_DEBUG_TLBFLUSH=y CONFIG_SMP=n
  mm/memory_hotplug: do not unlock after failing to take the device_hotplug_lock
  mm: swapoff: shmem_unuse() stop eviction without igrab()
  mm: swapoff: take notice of completion sooner
  mm: swapoff: remove too limiting SWAP_UNUSE_MAX_TRIES
  mm: swapoff: shmem_find_swap_entries() filter out other types
  slab: store tagged freelist for off-slab slabmgmt
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

8 files changed, 119 insertions, 84 deletions

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index bcaa4bde3961..b85a4ab8b9db 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -3054,7 +3054,7 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
 	bfq_remove_request(q, rq);
 }
 
-static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	/*
 	 * If this bfqq is shared between multiple processes, check
@@ -3089,9 +3089,11 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	/*
 	 * All in-service entities must have been properly deactivated
 	 * or requeued before executing the next function, which
-	 * resets all in-service entities as no more in service.
+	 * resets all in-service entities as no more in service. This
+	 * may cause bfqq to be freed. If this happens, the next
+	 * function returns true.
 	 */
-	__bfq_bfqd_reset_in_service(bfqd);
+	return __bfq_bfqd_reset_in_service(bfqd);
 }
 
 /**
@@ -3489,7 +3491,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	bool slow;
 	unsigned long delta = 0;
 	struct bfq_entity *entity = &bfqq->entity;
-	int ref;
 
 	/*
 	 * Check whether the process is slow (see bfq_bfqq_is_slow).
@@ -3582,10 +3583,8 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	 * reason.
 	 */
 	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
-	ref = bfqq->ref;
-	__bfq_bfqq_expire(bfqd, bfqq);
-
-	if (ref == 1) /* bfqq is gone, no more actions on it */
+	if (__bfq_bfqq_expire(bfqd, bfqq))
+		/* bfqq is gone, no more actions on it */
 		return;
 
 	/* mark bfqq as waiting a request only if a bic still points to it */
@@ -5894,7 +5893,7 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	return min_shallow;
 }
 
-static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 	struct blk_mq_tags *tags = hctx->sched_tags;
@@ -5902,6 +5901,11 @@ static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
 
 	min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
 	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
+}
+
+static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+{
+	bfq_depth_updated(hctx);
 	return 0;
 }
 
@@ -6325,6 +6329,7 @@ static struct elevator_type iosched_bfq_mq = {
 		.requests_merged	= bfq_requests_merged,
 		.request_merged		= bfq_request_merged,
 		.has_work		= bfq_has_work,
+		.depth_updated		= bfq_depth_updated,
 		.init_hctx		= bfq_init_hctx,
 		.init_sched		= bfq_init_queue,
 		.exit_sched		= bfq_exit_queue,
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index e7dc07cf9a57..eba7cd449ab4 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -1014,7 +1014,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity,
 			     bool ins_into_idle_tree);
 bool next_queue_may_preempt(struct bfq_data *bfqd);
 struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
-void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
+bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
 void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			 bool ins_into_idle_tree, bool expiration);
 void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index d2ea98ef26a3..48d899cfbe03 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -1605,7 +1605,8 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 	return bfqq;
 }
 
-void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+/* returns true if the in-service queue gets freed */
+bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 {
 	struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
 	struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
@@ -1629,8 +1630,20 @@ void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 	 * service tree either, then release the service reference to
 	 * the queue it represents (taken with bfq_get_entity).
 	 */
-	if (!in_serv_entity->on_st)
+	if (!in_serv_entity->on_st) {
+		/*
+		 * If no process is referencing in_serv_bfqq any
+		 * longer, then the service reference may be the only
+		 * reference to the queue. If this is the case, then
+		 * bfqq gets freed here.
+		 */
+		int ref = in_serv_bfqq->ref;
 		bfq_put_queue(in_serv_bfqq);
+		if (ref == 1)
+			return true;
+	}
+
+	return false;
 }
 
 void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
diff --git a/block/bio.c b/block/bio.c
index 8adc2a20d57d..5959141d4e46 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1333,8 +1333,11 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 			}
 		}
 
-		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
+		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+			if (!map_data)
+				__free_page(page);
 			break;
+		}
 
 		len -= bytes;
 		offset = 0;
diff --git a/block/blk-core.c b/block/blk-core.c
index 4673ebe42255..a55389ba8779 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1245,8 +1245,6 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
  */
 blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 {
-	blk_qc_t unused;
-
 	if (blk_cloned_rq_check_limits(q, rq))
 		return BLK_STS_IOERR;
 
@@ -1262,7 +1260,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	 * bypass a potential scheduler on the bottom device for
 	 * insert.
 	 */
-	return blk_mq_try_issue_directly(rq->mq_hctx, rq, &unused, true, true);
+	return blk_mq_request_issue_directly(rq, true);
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 40905539afed..aa6bc5c02643 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -423,10 +423,12 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
 		 * busy in case of 'none' scheduler, and this way may save
 		 * us one extra enqueue & dequeue to sw queue.
 		 */
-		if (!hctx->dispatch_busy && !e && !run_queue_async)
+		if (!hctx->dispatch_busy && !e && !run_queue_async) {
 			blk_mq_try_issue_list_directly(hctx, list);
-		else
-			blk_mq_insert_requests(hctx, ctx, list);
+			if (list_empty(list))
+				return;
+		}
+		blk_mq_insert_requests(hctx, ctx, list);
 	}
 
 	blk_mq_run_hw_queue(hctx, run_queue_async);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3ff3d7b49969..fc60ed7e940e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -654,6 +654,13 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
+void blk_mq_complete_request_sync(struct request *rq)
+{
+	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
+	rq->q->mq_ops->complete(rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
+
 int blk_mq_request_started(struct request *rq)
 {
 	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
@@ -1711,11 +1718,12 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	unsigned int depth;
 
 	list_splice_init(&plug->mq_list, &list);
-	plug->rq_count = 0;
 
 	if (plug->rq_count > 2 && plug->multiple_queues)
 		list_sort(NULL, &list, plug_rq_cmp);
 
+	plug->rq_count = 0;
+
 	this_q = NULL;
 	this_hctx = NULL;
 	this_ctx = NULL;
@@ -1800,74 +1808,76 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
-blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 						struct request *rq,
 						blk_qc_t *cookie,
-						bool bypass, bool last)
+						bool bypass_insert, bool last)
 {
 	struct request_queue *q = rq->q;
 	bool run_queue = true;
-	blk_status_t ret = BLK_STS_RESOURCE;
-	int srcu_idx;
-	bool force = false;
 
-	hctx_lock(hctx, &srcu_idx);
 	/*
-	 * hctx_lock is needed before checking quiesced flag.
+	 * RCU or SRCU read lock is needed before checking quiesced flag.
 	 *
-	 * When queue is stopped or quiesced, ignore 'bypass', insert
-	 * and return BLK_STS_OK to caller, and avoid driver to try to
-	 * dispatch again.
+	 * When queue is stopped or quiesced, ignore 'bypass_insert' from
+	 * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller,
+	 * and avoid driver to try to dispatch again.
 	 */
-	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) {
+	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
 		run_queue = false;
-		bypass = false;
-		goto out_unlock;
+		bypass_insert = false;
+		goto insert;
 	}
 
-	if (unlikely(q->elevator && !bypass))
-		goto out_unlock;
+	if (q->elevator && !bypass_insert)
+		goto insert;
 
 	if (!blk_mq_get_dispatch_budget(hctx))
-		goto out_unlock;
+		goto insert;
 
 	if (!blk_mq_get_driver_tag(rq)) {
 		blk_mq_put_dispatch_budget(hctx);
-		goto out_unlock;
+		goto insert;
 	}
 
-	/*
-	 * Always add a request that has been through
-	 *.queue_rq() to the hardware dispatch list.
-	 */
-	force = true;
-	ret = __blk_mq_issue_directly(hctx, rq, cookie, last);
-out_unlock:
+	return __blk_mq_issue_directly(hctx, rq, cookie, last);
+insert:
+	if (bypass_insert)
+		return BLK_STS_RESOURCE;
+
+	blk_mq_request_bypass_insert(rq, run_queue);
+	return BLK_STS_OK;
+}
+
+static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, blk_qc_t *cookie)
+{
+	blk_status_t ret;
+	int srcu_idx;
+
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
+	hctx_lock(hctx, &srcu_idx);
+
+	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
+	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+		blk_mq_request_bypass_insert(rq, true);
+	else if (ret != BLK_STS_OK)
+		blk_mq_end_request(rq, ret);
+
+	hctx_unlock(hctx, srcu_idx);
+}
+
+blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
+{
+	blk_status_t ret;
+	int srcu_idx;
+	blk_qc_t unused_cookie;
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	hctx_lock(hctx, &srcu_idx);
+	ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last);
 	hctx_unlock(hctx, srcu_idx);
-	switch (ret) {
-	case BLK_STS_OK:
-		break;
-	case BLK_STS_DEV_RESOURCE:
-	case BLK_STS_RESOURCE:
-		if (force) {
-			blk_mq_request_bypass_insert(rq, run_queue);
-			/*
-			 * We have to return BLK_STS_OK for the DM
-			 * to avoid livelock. Otherwise, we return
-			 * the real result to indicate whether the
-			 * request is direct-issued successfully.
-			 */
-			ret = bypass ? BLK_STS_OK : ret;
-		} else if (!bypass) {
-			blk_mq_sched_insert_request(rq, false,
-						    run_queue, false);
-		}
-		break;
-	default:
-		if (!bypass)
-			blk_mq_end_request(rq, ret);
-		break;
-	}
 
 	return ret;
 }
@@ -1875,20 +1885,22 @@ out_unlock:
 void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list)
 {
-	blk_qc_t unused;
-	blk_status_t ret = BLK_STS_OK;
-
 	while (!list_empty(list)) {
+		blk_status_t ret;
 		struct request *rq = list_first_entry(list, struct request,
 				queuelist);
 
 		list_del_init(&rq->queuelist);
-		if (ret == BLK_STS_OK)
-			ret = blk_mq_try_issue_directly(hctx, rq, &unused,
-							false,
+		ret = blk_mq_request_issue_directly(rq, list_empty(list));
+		if (ret != BLK_STS_OK) {
+			if (ret == BLK_STS_RESOURCE ||
+					ret == BLK_STS_DEV_RESOURCE) {
+				blk_mq_request_bypass_insert(rq,
 							list_empty(list));
-		else
-			blk_mq_sched_insert_request(rq, false, true, false);
+				break;
+			}
+			blk_mq_end_request(rq, ret);
+		}
 	}
 
 	/*
@@ -1896,7 +1908,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 	 * the driver there was more coming, but that turned out to
 	 * be a lie.
 	 */
-	if (ret != BLK_STS_OK && hctx->queue->mq_ops->commit_rqs)
+	if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs)
 		hctx->queue->mq_ops->commit_rqs(hctx);
 }
 
@@ -2003,19 +2015,21 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 			plug->rq_count--;
 		}
 		blk_add_rq_to_plug(plug, rq);
+		trace_block_plug(q);
 
 		blk_mq_put_ctx(data.ctx);
 
 		if (same_queue_rq) {
 			data.hctx = same_queue_rq->mq_hctx;
+			trace_block_unplug(q, 1, true);
 			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
-					&cookie, false, true);
+					&cookie);
 		}
 	} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
 			!data.hctx->dispatch_busy)) {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_try_issue_directly(data.hctx, rq, &cookie, false, true);
+		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
 	} else {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
@@ -2332,7 +2346,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	return 0;
 
  free_fq:
-	kfree(hctx->fq);
+	blk_free_flush_queue(hctx->fq);
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
@@ -3121,6 +3135,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		}
 		if (ret)
 			break;
+		if (q->elevator && q->elevator->type->ops.depth_updated)
+			q->elevator->type->ops.depth_updated(hctx);
 	}
 
 	if (!ret)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index d704fc7766f4..423ea88ab6fb 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -70,10 +70,8 @@ void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
 
-blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
-						struct request *rq,
-						blk_qc_t *cookie,
-						bool bypass, bool last);
+/* Used by blk_insert_cloned_request() to issue request directly */
+blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last);
 void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				    struct list_head *list);