Merge tag 'for-linus-20191115' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few fixes that should make it into this release. This contains:

   - io_uring:
        - The timeout command assumes sequence == 0 means that we want
          one completion, but this kind of overloading is unfortunate as
          it prevents users from doing a pure time based wait. Since
          this operation was introduced in this cycle, let's correct it
          now, while we can. (me)
        - One-liner to fix an issue with dependent links and fixed
          buffer reads. The actual IO completed fine, but the link got
          severed since we stored the wrong expected value. (me)
        - Add TIMEOUT to list of opcodes that don't need a file. (Pavel)

   - rsxx missing workqueue destry calls. Old bug. (Chuhong)

   - Fix blk-iocost active list check (Jiufei)

   - Fix impossible-to-hit overflow merge condition, that still hit some
     folks very rarely (Junichi)

   - Fix bfq hang issue from 5.3. This didn't get marked for stable, but
     will go into stable post this merge (Paolo)"

* tag 'for-linus-20191115' of git://git.kernel.dk/linux-block:
  rsxx: add missed destroy_workqueue calls in remove
  iocost: check active_list of all the ancestors in iocg_activate()
  block, bfq: deschedule empty bfq_queues not referred by any process
  io_uring: ensure registered buffer import returns the IO length
  io_uring: Fix getting file for timeout
  block: check bi_size overflow before merge
  io_uring: make timeout sequence == 0 mean no sequence

5 files changed, 59 insertions, 17 deletions

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 0319d6339822..0c6214497fcc 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2713,6 +2713,28 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	}
 }
 
+
+static
+void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * To prevent bfqq's service guarantees from being violated,
+	 * bfqq may be left busy, i.e., queued for service, even if
+	 * empty (see comments in __bfq_bfqq_expire() for
+	 * details). But, if no process will send requests to bfqq any
+	 * longer, then there is no point in keeping bfqq queued for
+	 * service. In addition, keeping bfqq queued for service, but
+	 * with no process ref any longer, may have caused bfqq to be
+	 * freed when dequeued from service. But this is assumed to
+	 * never happen.
+	 */
+	if (bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) &&
+	    bfqq != bfqd->in_service_queue)
+		bfq_del_bfqq_busy(bfqd, bfqq, false);
+
+	bfq_put_queue(bfqq);
+}
+
 static void
 bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
@@ -2783,8 +2805,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	 */
 	new_bfqq->pid = -1;
 	bfqq->bic = NULL;
-	/* release process reference to bfqq */
-	bfq_put_queue(bfqq);
+	bfq_release_process_ref(bfqd, bfqq);
 }
 
 static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
@@ -4899,7 +4920,7 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 	bfq_put_cooperator(bfqq);
 
-	bfq_put_queue(bfqq); /* release process reference */
+	bfq_release_process_ref(bfqd, bfqq);
 }
 
 static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
@@ -5001,8 +5022,7 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
 
 	bfqq = bic_to_bfqq(bic, false);
 	if (bfqq) {
-		/* release process reference on this queue */
-		bfq_put_queue(bfqq);
+		bfq_release_process_ref(bfqd, bfqq);
 		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
 		bic_set_bfqq(bic, bfqq, false);
 	}
@@ -5963,7 +5983,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
 
 	bfq_put_cooperator(bfqq);
 
-	bfq_put_queue(bfqq);
+	bfq_release_process_ref(bfqq->bfqd, bfqq);
 	return NULL;
 }
 
diff --git a/block/bio.c b/block/bio.c
index 8f0ed6228fc5..b1170ec18464 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -751,7 +751,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return false;
 
-	if (bio->bi_vcnt > 0) {
+	if (bio->bi_vcnt > 0 && !bio_full(bio, len)) {
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index a7ed434eae03..e01267f99183 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1057,9 +1057,12 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 	atomic64_set(&iocg->active_period, cur_period);
 
 	/* already activated or breaking leaf-only constraint? */
-	for (i = iocg->level; i > 0; i--)
-		if (!list_empty(&iocg->active_list))
+	if (!list_empty(&iocg->active_list))
+		goto succeed_unlock;
+	for (i = iocg->level - 1; i > 0; i--)
+		if (!list_empty(&iocg->ancestors[i]->active_list))
 			goto fail_unlock;
+
 	if (iocg->child_active_sum)
 		goto fail_unlock;
 
@@ -1101,6 +1104,7 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 		ioc_start_period(ioc, now);
 	}
 
+succeed_unlock:
 	spin_unlock_irq(&ioc->lock);
 	return true;
 
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 76b73ddf8fd7..10f6368117d8 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -1000,8 +1000,10 @@ static void rsxx_pci_remove(struct pci_dev *dev)
 
 	cancel_work_sync(&card->event_work);
 
+	destroy_workqueue(card->event_wq);
 	rsxx_destroy_dev(card);
 	rsxx_dma_destroy(card);
+	destroy_workqueue(card->creg_ctrl.creg_wq);
 
 	spin_lock_irqsave(&card->irq_lock, flags);
 	rsxx_disable_ier_and_isr(card, CR_INTR_ALL);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index f9a38998f2fc..2c819c3c855d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -326,6 +326,7 @@ struct io_kiocb {
 #define REQ_F_TIMEOUT		1024	/* timeout request */
 #define REQ_F_ISREG		2048	/* regular file */
 #define REQ_F_MUST_PUNT		4096	/* must be punted even for NONBLOCK */
+#define REQ_F_TIMEOUT_NOSEQ	8192	/* no timeout sequence */
 	u64			user_data;
 	u32			result;
 	u32			sequence;
@@ -453,9 +454,13 @@ static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx)
 	struct io_kiocb *req;
 
 	req = list_first_entry_or_null(&ctx->timeout_list, struct io_kiocb, list);
-	if (req && !__io_sequence_defer(ctx, req)) {
-		list_del_init(&req->list);
-		return req;
+	if (req) {
+		if (req->flags & REQ_F_TIMEOUT_NOSEQ)
+			return NULL;
+		if (!__io_sequence_defer(ctx, req)) {
+			list_del_init(&req->list);
+			return req;
+		}
 	}
 
 	return NULL;
@@ -1225,7 +1230,7 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
 		}
 	}
 
-	return 0;
+	return len;
 }
 
 static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw,
@@ -1941,18 +1946,24 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr)))
 		return -EFAULT;
 
+	req->flags |= REQ_F_TIMEOUT;
+
 	/*
 	 * sqe->off holds how many events that need to occur for this
-	 * timeout event to be satisfied.
+	 * timeout event to be satisfied. If it isn't set, then this is
+	 * a pure timeout request, sequence isn't used.
 	 */
 	count = READ_ONCE(sqe->off);
-	if (!count)
-		count = 1;
+	if (!count) {
+		req->flags |= REQ_F_TIMEOUT_NOSEQ;
+		spin_lock_irq(&ctx->completion_lock);
+		entry = ctx->timeout_list.prev;
+		goto add;
+	}
 
 	req->sequence = ctx->cached_sq_head + count - 1;
 	/* reuse it to store the count */
 	req->submit.sequence = count;
-	req->flags |= REQ_F_TIMEOUT;
 
 	/*
 	 * Insertion sort, ensuring the first entry in the list is always
@@ -1964,6 +1975,9 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		unsigned nxt_sq_head;
 		long long tmp, tmp_nxt;
 
+		if (nxt->flags & REQ_F_TIMEOUT_NOSEQ)
+			continue;
+
 		/*
 		 * Since cached_sq_head + count - 1 can overflow, use type long
 		 * long to store it.
@@ -1990,6 +2004,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		nxt->sequence++;
 	}
 	req->sequence -= span;
+add:
 	list_add(&req->list, entry);
 	spin_unlock_irq(&ctx->completion_lock);
 
@@ -2283,6 +2298,7 @@ static bool io_op_needs_file(const struct io_uring_sqe *sqe)
 	switch (op) {
 	case IORING_OP_NOP:
 	case IORING_OP_POLL_REMOVE:
+	case IORING_OP_TIMEOUT:
 		return false;
 	default:
 		return true;