Merge tag 'dm-3.18' of git://git.kernel.org/pub/scm/linux/kernel/git/…

…device-mapper/linux-dm

Pull device-mapper updates from Mike Snitzer:
 "I rebased the DM tree ontop of linux-block.git's 'for-3.18/core' at
  the beginning of October because DM core now depends on the newly
  introduced bioset_create_nobvec() interface.

  Summary:

   - fix DM's long-standing excessive use of memory by leveraging the
     new bioset_create_nobvec() interface when creating the DM's bioset

   - fix a few bugs in dm-bufio and dm-log-userspace

   - add DM core support for a DM multipath use-case that requires
     loading DM tables that contain devices that have failed (by
     allowing active and inactive DM tables to share dm_devs)

   - add discard support to the DM raid target; like MD raid456 the user
     must opt-in to raid456 discard support be specifying the
     devices_handle_discard_safely=Y module param"

* tag 'dm-3.18' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm log userspace: fix memory leak in dm_ulog_tfr_init failure path
  dm bufio: when done scanning return from __scan immediately
  dm bufio: update last_accessed when relinking a buffer
  dm raid: add discard support for RAID levels 4, 5 and 6
  dm raid: add discard support for RAID levels 1 and 10
  dm: allow active and inactive tables to share dm_devs
  dm mpath: stop queueing IO when no valid paths exist
  dm: use bioset_create_nobvec()
  dm: remove nr_iovecs parameter from alloc_tio()

drivers/md/dm-bufio.c

@@ -465,6 +465,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty)
 	c->n_buffers[dirty]++;
 	b->list_mode = dirty;
 	list_move(&b->lru_list, &c->lru[dirty]);
+	b->last_accessed = jiffies;
 }
 
 /*----------------------------------------------------------------
@@ -1471,9 +1472,9 @@ static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
 		list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
 			freed += __cleanup_old_buffer(b, gfp_mask, 0);
 			if (!--nr_to_scan)
-				break;
+				return freed;
+			dm_bufio_cond_resched();
 		}
-		dm_bufio_cond_resched();
 	}
 	return freed;
 }

drivers/md/dm-ioctl.c

@@ -1418,7 +1418,7 @@ static void retrieve_deps(struct dm_table *table,
 	deps->count = count;
 	count = 0;
 	list_for_each_entry (dd, dm_table_get_devices(table), list)
-		deps->dev[count++] = huge_encode_dev(dd->dm_dev.bdev->bd_dev);
+		deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev);
 
 	param->data_size = param->data_start + needed;
 }

drivers/md/dm-log-userspace-transfer.c

@@ -272,7 +272,7 @@ int dm_ulog_tfr_init(void)
 
 	r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback);
 	if (r) {
-		cn_del_callback(&ulog_cn_id);
+		kfree(prealloced_cn_msg);
 		return r;
 	}
 

drivers/md/dm-mpath.c

@@ -317,8 +317,10 @@ static void __choose_pgpath(struct multipath *m, size_t nr_bytes)
 	struct priority_group *pg;
 	unsigned bypassed = 1;
 
-	if (!m->nr_valid_paths)
+	if (!m->nr_valid_paths) {
+		m->queue_io = 0;
 		goto failed;
+	}
 
 	/* Were we instructed to switch PG? */
 	if (m->next_pg) {

drivers/md/dm-raid.c

@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010-2011 Neil Brown
- * Copyright (C) 2010-2011 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2010-2014 Red Hat, Inc. All rights reserved.
  *
  * This file is released under the GPL.
  */
@@ -18,6 +18,8 @@
 
 #define DM_MSG_PREFIX "raid"
 
+static bool devices_handle_discard_safely = false;
+
 /*
  * The following flags are used by dm-raid.c to set up the array state.
  * They must be cleared before md_run is called.
@@ -475,6 +477,8 @@ static int validate_raid_redundancy(struct raid_set *rs)
  *                                      will form the "stripe"
  *    [[no]sync]			Force or prevent recovery of the
  *                                      entire array
+ *    [devices_handle_discard_safely]	Allow discards on RAID4/5/6; useful if RAID
+ *					member device(s) properly support TRIM/UNMAP
  *    [rebuild <idx>]			Rebuild the drive indicated by the index
  *    [daemon_sleep <ms>]		Time between bitmap daemon work to
  *                                      clear bits
@@ -1149,6 +1153,49 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 	return 0;
 }
 
+/*
+ * Enable/disable discard support on RAID set depending on
+ * RAID level and discard properties of underlying RAID members.
+ */
+static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
+{
+	int i;
+	bool raid456;
+
+	/* Assume discards not supported until after checks below. */
+	ti->discards_supported = false;
+
+	/* RAID level 4,5,6 require discard_zeroes_data for data integrity! */
+	raid456 = (rs->md.level == 4 || rs->md.level == 5 || rs->md.level == 6);
+
+	for (i = 0; i < rs->md.raid_disks; i++) {
+		struct request_queue *q = bdev_get_queue(rs->dev[i].rdev.bdev);
+
+		if (!q || !blk_queue_discard(q))
+			return;
+
+		if (raid456) {
+			if (!q->limits.discard_zeroes_data)
+				return;
+			if (!devices_handle_discard_safely) {
+				DMERR("raid456 discard support disabled due to discard_zeroes_data uncertainty.");
+				DMERR("Set dm-raid.devices_handle_discard_safely=Y to override.");
+				return;
+			}
+		}
+	}
+
+	/* All RAID members properly support discards */
+	ti->discards_supported = true;
+
+	/*
+	 * RAID1 and RAID10 personalities require bio splitting,
+	 * RAID0/4/5/6 don't and process large discard bios properly.
+	 */
+	ti->split_discard_bios = !!(rs->md.level == 1 || rs->md.level == 10);
+	ti->num_discard_bios = 1;
+}
+
 /*
  * Construct a RAID4/5/6 mapping:
  * Args:
@@ -1231,6 +1278,11 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->private = rs;
 	ti->num_flush_bios = 1;
 
+	/*
+	 * Disable/enable discard support on RAID set.
+	 */
+	configure_discard_support(ti, rs);
+
 	mutex_lock(&rs->md.reconfig_mutex);
 	ret = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
@@ -1652,7 +1704,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 5, 2},
+	.version = {1, 6, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
@@ -1683,6 +1735,10 @@ static void __exit dm_raid_exit(void)
 module_init(dm_raid_init);
 module_exit(dm_raid_exit);
 
+module_param(devices_handle_discard_safely, bool, 0644);
+MODULE_PARM_DESC(devices_handle_discard_safely,
+		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
+
 MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target");
 MODULE_ALIAS("dm-raid1");
 MODULE_ALIAS("dm-raid10");

drivers/md/dm-table.c

@@ -210,15 +210,16 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 	return 0;
 }
 
-static void free_devices(struct list_head *devices)
+static void free_devices(struct list_head *devices, struct mapped_device *md)
 {
 	struct list_head *tmp, *next;
 
 	list_for_each_safe(tmp, next, devices) {
 		struct dm_dev_internal *dd =
 		    list_entry(tmp, struct dm_dev_internal, list);
-		DMWARN("dm_table_destroy: dm_put_device call missing for %s",
-		       dd->dm_dev.name);
+		DMWARN("%s: dm_table_destroy: dm_put_device call missing for %s",
+		       dm_device_name(md), dd->dm_dev->name);
+		dm_put_table_device(md, dd->dm_dev);
 		kfree(dd);
 	}
 }
@@ -247,7 +248,7 @@ void dm_table_destroy(struct dm_table *t)
 	vfree(t->highs);
 
 	/* free the device list */
-	free_devices(&t->devices);
+	free_devices(&t->devices, t->md);
 
 	dm_free_md_mempools(t->mempools);
 
@@ -262,52 +263,12 @@ static struct dm_dev_internal *find_device(struct list_head *l, dev_t dev)
 	struct dm_dev_internal *dd;
 
 	list_for_each_entry (dd, l, list)
-		if (dd->dm_dev.bdev->bd_dev == dev)
+		if (dd->dm_dev->bdev->bd_dev == dev)
 			return dd;
 
 	return NULL;
 }
 
-/*
- * Open a device so we can use it as a map destination.
- */
-static int open_dev(struct dm_dev_internal *d, dev_t dev,
-		    struct mapped_device *md)
-{
-	static char *_claim_ptr = "I belong to device-mapper";
-	struct block_device *bdev;
-
-	int r;
-
-	BUG_ON(d->dm_dev.bdev);
-
-	bdev = blkdev_get_by_dev(dev, d->dm_dev.mode | FMODE_EXCL, _claim_ptr);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
-
-	r = bd_link_disk_holder(bdev, dm_disk(md));
-	if (r) {
-		blkdev_put(bdev, d->dm_dev.mode | FMODE_EXCL);
-		return r;
-	}
-
-	d->dm_dev.bdev = bdev;
-	return 0;
-}
-
-/*
- * Close a device that we've been using.
- */
-static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
-{
-	if (!d->dm_dev.bdev)
-		return;
-
-	bd_unlink_disk_holder(d->dm_dev.bdev, dm_disk(md));
-	blkdev_put(d->dm_dev.bdev, d->dm_dev.mode | FMODE_EXCL);
-	d->dm_dev.bdev = NULL;
-}
-
 /*
  * If possible, this checks an area of a destination device is invalid.
  */
@@ -386,19 +347,17 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 			struct mapped_device *md)
 {
 	int r;
-	struct dm_dev_internal dd_new, dd_old;
+	struct dm_dev *old_dev, *new_dev;
 
-	dd_new = dd_old = *dd;
+	old_dev = dd->dm_dev;
 
-	dd_new.dm_dev.mode |= new_mode;
-	dd_new.dm_dev.bdev = NULL;
-
-	r = open_dev(&dd_new, dd->dm_dev.bdev->bd_dev, md);
+	r = dm_get_table_device(md, dd->dm_dev->bdev->bd_dev,
+				dd->dm_dev->mode | new_mode, &new_dev);
 	if (r)
 		return r;
 
-	dd->dm_dev.mode |= new_mode;
-	close_dev(&dd_old, md);
+	dd->dm_dev = new_dev;
+	dm_put_table_device(md, old_dev);
 
 	return 0;
 }
@@ -440,27 +399,22 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 		if (!dd)
 			return -ENOMEM;
 
-		dd->dm_dev.mode = mode;
-		dd->dm_dev.bdev = NULL;
-
-		if ((r = open_dev(dd, dev, t->md))) {
+		if ((r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev))) {
 			kfree(dd);
 			return r;
 		}
 
-		format_dev_t(dd->dm_dev.name, dev);
-
 		atomic_set(&dd->count, 0);
 		list_add(&dd->list, &t->devices);
 
-	} else if (dd->dm_dev.mode != (mode | dd->dm_dev.mode)) {
+	} else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) {
 		r = upgrade_mode(dd, mode, t->md);
 		if (r)
 			return r;
 	}
 	atomic_inc(&dd->count);
 
-	*result = &dd->dm_dev;
+	*result = dd->dm_dev;
 	return 0;
 }
 EXPORT_SYMBOL(dm_get_device);
@@ -505,11 +459,23 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
  */
 void dm_put_device(struct dm_target *ti, struct dm_dev *d)
 {
-	struct dm_dev_internal *dd = container_of(d, struct dm_dev_internal,
-						  dm_dev);
+	int found = 0;
+	struct list_head *devices = &ti->table->devices;
+	struct dm_dev_internal *dd;
 
+	list_for_each_entry(dd, devices, list) {
+		if (dd->dm_dev == d) {
+			found = 1;
+			break;
+		}
+	}
+	if (!found) {
+		DMWARN("%s: device %s not in table devices list",
+		       dm_device_name(ti->table->md), d->name);
+		return;
+	}
 	if (atomic_dec_and_test(&dd->count)) {
-		close_dev(dd, ti->table->md);
+		dm_put_table_device(ti->table->md, d);
 		list_del(&dd->list);
 		kfree(dd);
 	}
@@ -906,7 +872,7 @@ static int dm_table_set_type(struct dm_table *t)
 	/* Non-request-stackable devices can't be used for request-based dm */
 	devices = dm_table_get_devices(t);
 	list_for_each_entry(dd, devices, list) {
-		if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev.bdev))) {
+		if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev->bdev))) {
 			DMWARN("table load rejected: including"
 			       " non-request-stackable devices");
 			return -EINVAL;
@@ -1043,7 +1009,7 @@ static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
 	struct gendisk *prev_disk = NULL, *template_disk = NULL;
 
 	list_for_each_entry(dd, devices, list) {
-		template_disk = dd->dm_dev.bdev->bd_disk;
+		template_disk = dd->dm_dev->bdev->bd_disk;
 		if (!blk_get_integrity(template_disk))
 			goto no_integrity;
 		if (!match_all && !blk_integrity_is_initialized(template_disk))
@@ -1629,15 +1595,15 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 	int r = 0;
 
 	list_for_each_entry(dd, devices, list) {
-		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
+		struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
 		char b[BDEVNAME_SIZE];
 
 		if (likely(q))
 			r |= bdi_congested(&q->backing_dev_info, bdi_bits);
 		else
 			DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
 				     dm_device_name(t->md),
-				     bdevname(dd->dm_dev.bdev, b));
+				     bdevname(dd->dm_dev->bdev, b));
 	}
 
 	list_for_each_entry(cb, &t->target_callbacks, list)