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.

Author: torvalds

block/blk-cgroup.c

@@ -785,10 +785,10 @@ static int blkio_policy_parse_and_set(char *buf,
 {
 	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));
 
@@ -826,20 +826,23 @@ static int blkio_policy_parse_and_set(char *buf,
 
 	dev = MKDEV(major, minor);
 
-	ret = blkio_check_dev_num(dev);
+	ret = strict_strtoull(s[1], 10, &temp);
 	if (ret)
-		return ret;
+		return -EINVAL;
 
-	newpn->dev = dev;
+	/* For rule removal, do not check for device presence. */
+	if (temp) {
+		ret = blkio_check_dev_num(dev);
+		if (ret)
+			return ret;
+	}
 
-	if (s[1] == NULL)
-		return -EINVAL;
+	newpn->dev = dev;
 
 	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;
@@ -850,26 +853,18 @@ static int blkio_policy_parse_and_set(char *buf,
 		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

@@ -1167,7 +1167,7 @@ static bool bio_attempt_front_merge(struct request_queue *q,
  * 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;
@@ -1176,10 +1176,13 @@ static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
 	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;
 
@@ -1219,6 +1222,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	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
@@ -1237,7 +1241,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	 * 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);
@@ -1302,11 +1306,10 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 			if (__rq->q != q)
 				plug->should_sort = 1;
 		}
+		if (request_count >= BLK_MAX_REQUEST_COUNT)
+			blk_flush_plug_list(plug, false);
 		list_add_tail(&req->queuelist, &plug->list);
-		plug->count++;
 		drive_stat_acct(req, 1);
-		if (plug->count >= BLK_MAX_REQUEST_COUNT)
-			blk_flush_plug_list(plug, false);
 	} else {
 		spin_lock_irq(q->queue_lock);
 		add_acct_request(q, req, where);
@@ -2634,7 +2637,6 @@ void blk_start_plug(struct blk_plug *plug)
 	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
@@ -2718,7 +2720,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		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

@@ -115,7 +115,7 @@ void __blk_complete_request(struct request *req)
 	/*
 	 * 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

@@ -258,11 +258,13 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 
 	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

@@ -130,8 +130,8 @@ struct cfq_queue {
 	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;
 
@@ -684,8 +684,8 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2,
 	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);
@@ -1612,9 +1612,9 @@ static void cfq_remove_request(struct request *rq)
 	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--;
 	}
 }
 
@@ -3372,7 +3372,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	 * 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;
 
 	/*
@@ -3439,8 +3439,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	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

@@ -4250,7 +4250,7 @@ static int __init floppy_init(void)
 	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;
 	}
@@ -4261,7 +4261,7 @@ static int __init floppy_init(void)
 	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;
 	}
@@ -4318,7 +4318,7 @@ static int __init floppy_init(void)
 		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) {
@@ -4368,7 +4368,7 @@ static int __init floppy_init(void)
 	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

@@ -46,7 +46,7 @@
 
 #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

@@ -590,7 +590,7 @@ static void frontend_changed(struct xenbus_device *dev,
 
 		/*
 		 * Enforce precondition before potential leak point.
-		 * blkif_disconnect() is idempotent.
+		 * xen_blkif_disconnect() is idempotent.
 		 */
 		xen_blkif_disconnect(be->blkif);
 
@@ -601,17 +601,17 @@ static void frontend_changed(struct xenbus_device *dev,
 		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

@@ -926,6 +926,9 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 	/*
 	 * 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

@@ -1134,7 +1134,7 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode,
 		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;
@@ -2807,7 +2807,7 @@ static int __ext3_get_inode_loc(struct inode *inode,
 		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

@@ -922,7 +922,8 @@ static struct buffer_head *ext3_find_entry(struct inode *dir,
 				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

@@ -647,7 +647,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
 		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;
@@ -3298,7 +3298,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 		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

@@ -922,7 +922,8 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 				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

@@ -624,9 +624,9 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	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))