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

* 'for-linus' of git://git.kernel.dk/linux-block:
floppy: use del_timer_sync() in init cleanup
blk-cgroup: be able to remove the record of unplugged device
block: Don't check QUEUE_FLAG_SAME_COMP in __blk_complete_request
mm: Add comment explaining task state setting in bdi_forker_thread()
mm: Cleanup clearing of BDI_pending bit in bdi_forker_thread()
block: simplify force plug flush code a little bit
block: change force plug flush call order
block: Fix queue_flag update when rq_affinity goes from 2 to 1
block: separate priority boosting from REQ_META
block: remove READ_META and WRITE_META
xen-blkback: fixed indentation and comments
xen-blkback: Don't disconnect backend until state switched to XenbusStateClosed.

block/blk-cgroup.c

···
 {
 	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
 	int ret;
-	unsigned long major, minor, temp;
+	unsigned long major, minor;
 	int i = 0;
 	dev_t dev;
-	u64 bps, iops;
+	u64 temp;
 
 	memset(s, 0, sizeof(s));
 
···
 
 	dev = MKDEV(major, minor);
 
-	ret = blkio_check_dev_num(dev);
+	ret = strict_strtoull(s[1], 10, &temp);
 	if (ret)
-		return ret;
+		return -EINVAL;
+
+	/* For rule removal, do not check for device presence. */
+	if (temp) {
+		ret = blkio_check_dev_num(dev);
+		if (ret)
+			return ret;
+	}
 
 	newpn->dev = dev;
 
-	if (s[1] == NULL)
-		return -EINVAL;
-
 	switch (plid) {
 	case BLKIO_POLICY_PROP:
-		ret = strict_strtoul(s[1], 10, &temp);
-		if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
-			temp > BLKIO_WEIGHT_MAX)
+		if ((temp < BLKIO_WEIGHT_MIN && temp > 0) ||
+		     temp > BLKIO_WEIGHT_MAX)
 			return -EINVAL;
 
 		newpn->plid = plid;
···
 		switch(fileid) {
 		case BLKIO_THROTL_read_bps_device:
 		case BLKIO_THROTL_write_bps_device:
-			ret = strict_strtoull(s[1], 10, &bps);
-			if (ret)
-				return -EINVAL;
-
 			newpn->plid = plid;
 			newpn->fileid = fileid;
-			newpn->val.bps = bps;
+			newpn->val.bps = temp;
 			break;
 		case BLKIO_THROTL_read_iops_device:
 		case BLKIO_THROTL_write_iops_device:
-			ret = strict_strtoull(s[1], 10, &iops);
-			if (ret)
-				return -EINVAL;
-
-			if (iops > THROTL_IOPS_MAX)
+			if (temp > THROTL_IOPS_MAX)
 				return -EINVAL;
 
 			newpn->plid = plid;
 			newpn->fileid = fileid;
-			newpn->val.iops = (unsigned int)iops;
+			newpn->val.iops = (unsigned int)temp;
 			break;
 		}
 		break;

block/blk-core.c

···
  * true if merge was successful, otherwise false.
  */
 static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
-			       struct bio *bio)
+			       struct bio *bio, unsigned int *request_count)
 {
 	struct blk_plug *plug;
 	struct request *rq;
···
 	plug = tsk->plug;
 	if (!plug)
 		goto out;
+	*request_count = 0;
 
 	list_for_each_entry_reverse(rq, &plug->list, queuelist) {
 		int el_ret;
+
+		(*request_count)++;
 
 		if (rq->q != q)
 			continue;
···
 	struct blk_plug *plug;
 	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
+	unsigned int request_count = 0;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
···
 	 * Check if we can merge with the plugged list before grabbing
 	 * any locks.
 	 */
-	if (attempt_plug_merge(current, q, bio))
+	if (attempt_plug_merge(current, q, bio, &request_count))
 		goto out;
 
 	spin_lock_irq(q->queue_lock);
···
 			if (__rq->q != q)
 				plug->should_sort = 1;
 		}
-		list_add_tail(&req->queuelist, &plug->list);
-		plug->count++;
-		drive_stat_acct(req, 1);
-		if (plug->count >= BLK_MAX_REQUEST_COUNT)
+		if (request_count >= BLK_MAX_REQUEST_COUNT)
 			blk_flush_plug_list(plug, false);
+		list_add_tail(&req->queuelist, &plug->list);
+		drive_stat_acct(req, 1);
 	} else {
 		spin_lock_irq(q->queue_lock);
 		add_acct_request(q, req, where);
···
 	INIT_LIST_HEAD(&plug->list);
 	INIT_LIST_HEAD(&plug->cb_list);
 	plug->should_sort = 0;
-	plug->count = 0;
 
 	/*
 	 * If this is a nested plug, don't actually assign it. It will be
···
 		return;
 
 	list_splice_init(&plug->list, &list);
-	plug->count = 0;
 
 	if (plug->should_sort) {
 		list_sort(NULL, &list, plug_rq_cmp);

block/blk-softirq.c

···
 	/*
 	 * Select completion CPU
 	 */
-	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && req->cpu != -1) {
+	if (req->cpu != -1) {
 		ccpu = req->cpu;
 		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) {
 			ccpu = blk_cpu_to_group(ccpu);

block/blk-sysfs.c

···
 
 	ret = queue_var_store(&val, page, count);
 	spin_lock_irq(q->queue_lock);
-	if (val) {
+	if (val == 2) {
 		queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
-		if (val == 2)
-			queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
-	} else {
+		queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
+	} else if (val == 1) {
+		queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
+		queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
+	} else if (val == 0) {
 		queue_flag_clear(QUEUE_FLAG_SAME_COMP, q);
 		queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
 	}

block/cfq-iosched.c

···
 	unsigned long slice_end;
 	long slice_resid;
 
-	/* pending metadata requests */
-	int meta_pending;
+	/* pending priority requests */
+	int prio_pending;
 	/* number of requests that are on the dispatch list or inside driver */
 	int dispatched;
 
···
 	if (rq_is_sync(rq1) != rq_is_sync(rq2))
 		return rq_is_sync(rq1) ? rq1 : rq2;
 
-	if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_META)
-		return rq1->cmd_flags & REQ_META ? rq1 : rq2;
+	if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_PRIO)
+		return rq1->cmd_flags & REQ_PRIO ? rq1 : rq2;
 
 	s1 = blk_rq_pos(rq1);
 	s2 = blk_rq_pos(rq2);
···
 	cfqq->cfqd->rq_queued--;
 	cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg,
 					rq_data_dir(rq), rq_is_sync(rq));
-	if (rq->cmd_flags & REQ_META) {
-		WARN_ON(!cfqq->meta_pending);
-		cfqq->meta_pending--;
+	if (rq->cmd_flags & REQ_PRIO) {
+		WARN_ON(!cfqq->prio_pending);
+		cfqq->prio_pending--;
 	}
 }
 
···
 	 * So both queues are sync. Let the new request get disk time if
 	 * it's a metadata request and the current queue is doing regular IO.
 	 */
-	if ((rq->cmd_flags & REQ_META) && !cfqq->meta_pending)
+	if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending)
 		return true;
 
 	/*
···
 	struct cfq_io_context *cic = RQ_CIC(rq);
 
 	cfqd->rq_queued++;
-	if (rq->cmd_flags & REQ_META)
-		cfqq->meta_pending++;
+	if (rq->cmd_flags & REQ_PRIO)
+		cfqq->prio_pending++;
 
 	cfq_update_io_thinktime(cfqd, cfqq, cic);
 	cfq_update_io_seektime(cfqd, cfqq, rq);

drivers/block/floppy.c

···
 	use_virtual_dma = can_use_virtual_dma & 1;
 	fdc_state[0].address = FDC1;
 	if (fdc_state[0].address == -1) {
-		del_timer(&fd_timeout);
+		del_timer_sync(&fd_timeout);
 		err = -ENODEV;
 		goto out_unreg_region;
 	}
···
 	fdc = 0;		/* reset fdc in case of unexpected interrupt */
 	err = floppy_grab_irq_and_dma();
 	if (err) {
-		del_timer(&fd_timeout);
+		del_timer_sync(&fd_timeout);
 		err = -EBUSY;
 		goto out_unreg_region;
 	}
···
 		user_reset_fdc(-1, FD_RESET_ALWAYS, false);
 	}
 	fdc = 0;
-	del_timer(&fd_timeout);
+	del_timer_sync(&fd_timeout);
 	current_drive = 0;
 	initialized = true;
 	if (have_no_fdc) {
···
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 out_put_disk:
 	while (dr--) {
-		del_timer(&motor_off_timer[dr]);
+		del_timer_sync(&motor_off_timer[dr]);
 		if (disks[dr]->queue)
 			blk_cleanup_queue(disks[dr]->queue);
 		put_disk(disks[dr]);

drivers/block/xen-blkback/common.h

···
 
 #define DRV_PFX "xen-blkback:"
 #define DPRINTK(fmt, args...)				\
-	pr_debug(DRV_PFX "(%s:%d) " fmt ".\n",	\
+	pr_debug(DRV_PFX "(%s:%d) " fmt ".\n",		\
 		 __func__, __LINE__, ##args)
 
 

drivers/block/xen-blkback/xenbus.c

···
 
 		/*
 		 * Enforce precondition before potential leak point.
-		 * blkif_disconnect() is idempotent.
+		 * xen_blkif_disconnect() is idempotent.
 		 */
 		xen_blkif_disconnect(be->blkif);
 
···
 		break;
 
 	case XenbusStateClosing:
-		xen_blkif_disconnect(be->blkif);
 		xenbus_switch_state(dev, XenbusStateClosing);
 		break;
 
 	case XenbusStateClosed:
+		xen_blkif_disconnect(be->blkif);
 		xenbus_switch_state(dev, XenbusStateClosed);
 		if (xenbus_dev_is_online(dev))
 			break;
 		/* fall through if not online */
 	case XenbusStateUnknown:
-		/* implies blkif_disconnect() via blkback_remove() */
+		/* implies xen_blkif_disconnect() via xen_blkbk_remove() */
 		device_unregister(&dev->dev);
 		break;
 

drivers/mmc/card/block.c

···
 	/*
 	 * Reliable writes are used to implement Forced Unit Access and
 	 * REQ_META accesses, and are supported only on MMCs.
+	 *
+	 * XXX: this really needs a good explanation of why REQ_META
+	 * is treated special.
 	 */
 	bool do_rel_wr = ((req->cmd_flags & REQ_FUA) ||
 			  (req->cmd_flags & REQ_META)) &&

fs/ext3/inode.c

···
 		return bh;
 	if (buffer_uptodate(bh))
 		return bh;
-	ll_rw_block(READ_META, 1, &bh);
+	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return bh;
···
 		trace_ext3_load_inode(inode);
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ_META, bh);
+		submit_bh(READ | REQ_META | REQ_PRIO, bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			ext3_error(inode->i_sb, "ext3_get_inode_loc",

fs/ext3/namei.c

···
 				bh = ext3_getblk(NULL, dir, b++, 0, &err);
 				bh_use[ra_max] = bh;
 				if (bh)
-					ll_rw_block(READ_META, 1, &bh);
+					ll_rw_block(READ | REQ_META | REQ_PRIO,
+						    1, &bh);
 			}
 		}
 		if ((bh = bh_use[ra_ptr++]) == NULL)

fs/ext4/inode.c

···
 		return bh;
 	if (buffer_uptodate(bh))
 		return bh;
-	ll_rw_block(READ_META, 1, &bh);
+	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return bh;
···
 		trace_ext4_load_inode(inode);
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ_META, bh);
+		submit_bh(READ | REQ_META | REQ_PRIO, bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			EXT4_ERROR_INODE_BLOCK(inode, block,

fs/ext4/namei.c

···
 				bh = ext4_getblk(NULL, dir, b++, 0, &err);
 				bh_use[ra_max] = bh;
 				if (bh)
-					ll_rw_block(READ_META, 1, &bh);
+					ll_rw_block(READ | REQ_META | REQ_PRIO,
+						    1, &bh);
 			}
 		}
 		if ((bh = bh_use[ra_ptr++]) == NULL)

fs/gfs2/log.c

···
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
 	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
-		submit_bh(WRITE_SYNC | REQ_META, bh);
+		submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
 	else
-		submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
+		submit_bh(WRITE_FLUSH_FUA | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
 
 	if (!buffer_uptodate(bh))

fs/gfs2/meta_io.c

···
 {
 	struct buffer_head *bh, *head;
 	int nr_underway = 0;
-	int write_op = REQ_META |
+	int write_op = REQ_META | REQ_PRIO |
 		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
 
 	BUG_ON(!PageLocked(page));
···
 	}
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(READ_SYNC | REQ_META, bh);
+	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh);
 	if (!(flags & DIO_WAIT))
 		return 0;
 
···
 	if (buffer_uptodate(first_bh))
 		goto out;
 	if (!buffer_locked(first_bh))
-		ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh);
+		ll_rw_block(READ_SYNC | REQ_META | REQ_PRIO, 1, &first_bh);
 
 	dblock++;
 	extlen--;

fs/gfs2/ops_fstype.c

···
 
 	bio->bi_end_io = end_bio_io_page;
 	bio->bi_private = page;
-	submit_bio(READ_SYNC | REQ_META, bio);
+	submit_bio(READ_SYNC | REQ_META | REQ_PRIO, bio);
 	wait_on_page_locked(page);
 	bio_put(bio);
 	if (!PageUptodate(page)) {

fs/gfs2/quota.c

···
 		set_buffer_uptodate(bh);
 
 	if (!buffer_uptodate(bh)) {
-		ll_rw_block(READ_META, 1, &bh);
+		ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh))
 			goto unlock_out;

include/linux/blk_types.h

···
 
 	__REQ_SYNC,		/* request is sync (sync write or read) */
 	__REQ_META,		/* metadata io request */
+	__REQ_PRIO,		/* boost priority in cfq */
 	__REQ_DISCARD,		/* request to discard sectors */
 	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
 
···
 #define REQ_FAILFAST_DRIVER	(1 << __REQ_FAILFAST_DRIVER)
 #define REQ_SYNC		(1 << __REQ_SYNC)
 #define REQ_META		(1 << __REQ_META)
+#define REQ_PRIO		(1 << __REQ_PRIO)
 #define REQ_DISCARD		(1 << __REQ_DISCARD)
 #define REQ_NOIDLE		(1 << __REQ_NOIDLE)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
-	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \
-	 REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE)
+	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \
+	 REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)

include/linux/blkdev.h

···
 	struct list_head list;
 	struct list_head cb_list;
 	unsigned int should_sort;
-	unsigned int count;
 };
 #define BLK_MAX_REQUEST_COUNT 16
 

include/linux/fs.h

···
 #define READA			RWA_MASK
 
 #define READ_SYNC		(READ | REQ_SYNC)
-#define READ_META		(READ | REQ_META)
 #define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
 #define WRITE_ODIRECT		(WRITE | REQ_SYNC)
-#define WRITE_META		(WRITE | REQ_META)
 #define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
 #define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
 #define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)

mm/backing-dev.c

···
 	return max(5UL * 60 * HZ, interval);
 }
 
+/*
+ * Clear pending bit and wakeup anybody waiting for flusher thread creation or
+ * shutdown
+ */
+static void bdi_clear_pending(struct backing_dev_info *bdi)
+{
+	clear_bit(BDI_pending, &bdi->state);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&bdi->state, BDI_pending);
+}
+
 static int bdi_forker_thread(void *ptr)
 {
 	struct bdi_writeback *me = ptr;
···
 		}
 
 		spin_lock_bh(&bdi_lock);
+		/*
+		 * In the following loop we are going to check whether we have
+		 * some work to do without any synchronization with tasks
+		 * waking us up to do work for them. So we have to set task
+		 * state already here so that we don't miss wakeups coming
+		 * after we verify some condition.
+		 */
 		set_current_state(TASK_INTERRUPTIBLE);
 
 		list_for_each_entry(bdi, &bdi_list, bdi_list) {
···
 				spin_unlock_bh(&bdi->wb_lock);
 				wake_up_process(task);
 			}
+			bdi_clear_pending(bdi);
 			break;
 
 		case KILL_THREAD:
 			__set_current_state(TASK_RUNNING);
 			kthread_stop(task);
+			bdi_clear_pending(bdi);
 			break;
 
 		case NO_ACTION:
···
 			else
 				schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
 			try_to_freeze();
-			/* Back to the main loop */
-			continue;
+			break;
 		}
-
-		/*
-		 * Clear pending bit and wakeup anybody waiting to tear us down.
-		 */
-		clear_bit(BDI_pending, &bdi->state);
-		smp_mb__after_clear_bit();
-		wake_up_bit(&bdi->state, BDI_pending);
 	}
 
 	return 0;