Merge tag 'for-linus-20180830' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Small collection of fixes that should go into this series. This pull
  contains:

   - NVMe pull request with three small fixes (via Christoph)

   - Kill useless NULL check before kmem_cache_destroy (Chengguang Xu)

   - Xen block driver pull request with persistent grant flushing fixes
     (Juergen Gross)

   - Final wbt fixes, wrapping up the changes for this series. These
     have been heavily tested (me)

   - cdrom info leak fix (Scott Bauer)

   - ATA dma quirk for SQ201 (Linus Walleij)

   - Straight forward bsg refcount_t conversion (John Pittman)"

* tag 'for-linus-20180830' of git://git.kernel.dk/linux-block:
  cdrom: Fix info leak/OOB read in cdrom_ioctl_drive_status
  nvmet: free workqueue object if module init fails
  nvme-fcloop: Fix dropped LS's to removed target port
  nvme-pci: add a memory barrier to nvme_dbbuf_update_and_check_event
  block: bsg: move atomic_t ref_count variable to refcount API
  block: remove unnecessary condition check
  ata: ftide010: Add a quirk for SQ201
  blk-wbt: remove dead code
  blk-wbt: improve waking of tasks
  blk-wbt: abstract out end IO completion handler
  xen/blkback: remove unused pers_gnts_lock from struct xen_blkif_ring
  xen/blkback: move persistent grants flags to bool
  xen/blkfront: reorder tests in xlblk_init()
  xen/blkfront: cleanup stale persistent grants
  xen/blkback: don't keep persistent grants too long

Documentation/ABI/testing/sysfs-driver-xen-blkback

@@ -15,3 +15,13 @@ Description:
                 blkback. If the frontend tries to use more than
                 max_persistent_grants, the LRU kicks in and starts
                 removing 5% of max_persistent_grants every 100ms.
+
+What:           /sys/module/xen_blkback/parameters/persistent_grant_unused_seconds
+Date:           August 2018
+KernelVersion:  4.19
+Contact:        Roger Pau Monné <[email protected]>
+Description:
+                How long a persistent grant is allowed to remain
+                allocated without being in use. The time is in
+                seconds, 0 means indefinitely long.
+                The default is 60 seconds.

block/blk-wbt.c

@@ -123,16 +123,11 @@ static void rwb_wake_all(struct rq_wb *rwb)
 	}
 }
 
-static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
+static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw,
+			 enum wbt_flags wb_acct)
 {
-	struct rq_wb *rwb = RQWB(rqos);
-	struct rq_wait *rqw;
 	int inflight, limit;
 
-	if (!(wb_acct & WBT_TRACKED))
-		return;
-
-	rqw = get_rq_wait(rwb, wb_acct);
 	inflight = atomic_dec_return(&rqw->inflight);
 
 	/*
@@ -166,10 +161,22 @@ static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
 		int diff = limit - inflight;
 
 		if (!inflight || diff >= rwb->wb_background / 2)
-			wake_up(&rqw->wait);
+			wake_up_all(&rqw->wait);
 	}
 }
 
+static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	struct rq_wait *rqw;
+
+	if (!(wb_acct & WBT_TRACKED))
+		return;
+
+	rqw = get_rq_wait(rwb, wb_acct);
+	wbt_rqw_done(rwb, rqw, wb_acct);
+}
+
 /*
  * Called on completion of a request. Note that it's also called when
  * a request is merged, when the request gets freed.
@@ -481,6 +488,34 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 	return limit;
 }
 
+struct wbt_wait_data {
+	struct wait_queue_entry wq;
+	struct task_struct *task;
+	struct rq_wb *rwb;
+	struct rq_wait *rqw;
+	unsigned long rw;
+	bool got_token;
+};
+
+static int wbt_wake_function(struct wait_queue_entry *curr, unsigned int mode,
+			     int wake_flags, void *key)
+{
+	struct wbt_wait_data *data = container_of(curr, struct wbt_wait_data,
+							wq);
+
+	/*
+	 * If we fail to get a budget, return -1 to interrupt the wake up
+	 * loop in __wake_up_common.
+	 */
+	if (!rq_wait_inc_below(data->rqw, get_limit(data->rwb, data->rw)))
+		return -1;
+
+	data->got_token = true;
+	list_del_init(&curr->entry);
+	wake_up_process(data->task);
+	return 1;
+}
+
 /*
  * Block if we will exceed our limit, or if we are currently waiting for
  * the timer to kick off queuing again.
@@ -491,31 +526,52 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
 	__acquires(lock)
 {
 	struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
-	DECLARE_WAITQUEUE(wait, current);
+	struct wbt_wait_data data = {
+		.wq = {
+			.func	= wbt_wake_function,
+			.entry	= LIST_HEAD_INIT(data.wq.entry),
+		},
+		.task = current,
+		.rwb = rwb,
+		.rqw = rqw,
+		.rw = rw,
+	};
 	bool has_sleeper;
 
 	has_sleeper = wq_has_sleeper(&rqw->wait);
 	if (!has_sleeper && rq_wait_inc_below(rqw, get_limit(rwb, rw)))
 		return;
 
-	add_wait_queue_exclusive(&rqw->wait, &wait);
+	prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE);
 	do {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (data.got_token)
+			break;
 
-		if (!has_sleeper && rq_wait_inc_below(rqw, get_limit(rwb, rw)))
+		if (!has_sleeper &&
+		    rq_wait_inc_below(rqw, get_limit(rwb, rw))) {
+			finish_wait(&rqw->wait, &data.wq);
+
+			/*
+			 * We raced with wbt_wake_function() getting a token,
+			 * which means we now have two. Put our local token
+			 * and wake anyone else potentially waiting for one.
+			 */
+			if (data.got_token)
+				wbt_rqw_done(rwb, rqw, wb_acct);
 			break;
+		}
 
 		if (lock) {
 			spin_unlock_irq(lock);
 			io_schedule();
 			spin_lock_irq(lock);
 		} else
 			io_schedule();
+
 		has_sleeper = false;
 	} while (1);
 
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&rqw->wait, &wait);
+	finish_wait(&rqw->wait, &data.wq);
 }
 
 static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
@@ -580,11 +636,6 @@ static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock)
 		return;
 	}
 
-	if (current_is_kswapd())
-		flags |= WBT_KSWAPD;
-	if (bio_op(bio) == REQ_OP_DISCARD)
-		flags |= WBT_DISCARD;
-
 	__wbt_wait(rwb, flags, bio->bi_opf, lock);
 
 	if (!blk_stat_is_active(rwb->cb))

block/bsg.c

@@ -37,7 +37,7 @@ struct bsg_device {
 	struct request_queue *queue;
 	spinlock_t lock;
 	struct hlist_node dev_list;
-	atomic_t ref_count;
+	refcount_t ref_count;
 	char name[20];
 	int max_queue;
 };
@@ -252,7 +252,7 @@ static int bsg_put_device(struct bsg_device *bd)
 
 	mutex_lock(&bsg_mutex);
 
-	if (!atomic_dec_and_test(&bd->ref_count)) {
+	if (!refcount_dec_and_test(&bd->ref_count)) {
 		mutex_unlock(&bsg_mutex);
 		return 0;
 	}
@@ -290,7 +290,7 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 
 	bd->queue = rq;
 
-	atomic_set(&bd->ref_count, 1);
+	refcount_set(&bd->ref_count, 1);
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
 	strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
@@ -308,7 +308,7 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
 
 	hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) {
 		if (bd->queue == q) {
-			atomic_inc(&bd->ref_count);
+			refcount_inc(&bd->ref_count);
 			goto found;
 		}
 	}

block/elevator.c

@@ -895,8 +895,7 @@ int elv_register(struct elevator_type *e)
 	spin_lock(&elv_list_lock);
 	if (elevator_find(e->elevator_name, e->uses_mq)) {
 		spin_unlock(&elv_list_lock);
-		if (e->icq_cache)
-			kmem_cache_destroy(e->icq_cache);
+		kmem_cache_destroy(e->icq_cache);
 		return -EBUSY;
 	}
 	list_add_tail(&e->list, &elv_list);

drivers/ata/pata_ftide010.c

@@ -256,14 +256,12 @@ static struct ata_port_operations pata_ftide010_port_ops = {
 	.qc_issue	= ftide010_qc_issue,
 };
 
-static struct ata_port_info ftide010_port_info[] = {
-	{
-		.flags		= ATA_FLAG_SLAVE_POSS,
-		.mwdma_mask	= ATA_MWDMA2,
-		.udma_mask	= ATA_UDMA6,
-		.pio_mask	= ATA_PIO4,
-		.port_ops	= &pata_ftide010_port_ops,
-	},
+static struct ata_port_info ftide010_port_info = {
+	.flags		= ATA_FLAG_SLAVE_POSS,
+	.mwdma_mask	= ATA_MWDMA2,
+	.udma_mask	= ATA_UDMA6,
+	.pio_mask	= ATA_PIO4,
+	.port_ops	= &pata_ftide010_port_ops,
 };
 
 #if IS_ENABLED(CONFIG_SATA_GEMINI)
@@ -349,6 +347,7 @@ static int pata_ftide010_gemini_cable_detect(struct ata_port *ap)
 }
 
 static int pata_ftide010_gemini_init(struct ftide010 *ftide,
+				     struct ata_port_info *pi,
 				     bool is_ata1)
 {
 	struct device *dev = ftide->dev;
@@ -373,7 +372,13 @@ static int pata_ftide010_gemini_init(struct ftide010 *ftide,
 
 	/* Flag port as SATA-capable */
 	if (gemini_sata_bridge_enabled(sg, is_ata1))
-		ftide010_port_info[0].flags |= ATA_FLAG_SATA;
+		pi->flags |= ATA_FLAG_SATA;
+
+	/* This device has broken DMA, only PIO works */
+	if (of_machine_is_compatible("itian,sq201")) {
+		pi->mwdma_mask = 0;
+		pi->udma_mask = 0;
+	}
 
 	/*
 	 * We assume that a simple 40-wire cable is used in the PATA mode.
@@ -435,6 +440,7 @@ static int pata_ftide010_gemini_init(struct ftide010 *ftide,
 }
 #else
 static int pata_ftide010_gemini_init(struct ftide010 *ftide,
+				     struct ata_port_info *pi,
 				     bool is_ata1)
 {
 	return -ENOTSUPP;
@@ -446,7 +452,7 @@ static int pata_ftide010_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
-	const struct ata_port_info pi = ftide010_port_info[0];
+	struct ata_port_info pi = ftide010_port_info;
 	const struct ata_port_info *ppi[] = { &pi, NULL };
 	struct ftide010 *ftide;
 	struct resource *res;
@@ -490,6 +496,7 @@ static int pata_ftide010_probe(struct platform_device *pdev)
 		 * are ATA0. This will also set up the cable types.
 		 */
 		ret = pata_ftide010_gemini_init(ftide,
+				&pi,
 				(res->start == 0x63400000));
 		if (ret)
 			goto err_dis_clk;