1 files changed, 143 insertions, 142 deletions

diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 3f299d835a2..849ad39f547 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -19,23 +19,20 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include <linux/blkdev.h>
 #include <linux/module.h>
+#include <linux/raid/md_u.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/raid/multipath.h>
-#include <linux/buffer_head.h>
-#include <asm/atomic.h>
-
-#define MAJOR_NR MD_MAJOR
-#define MD_DRIVER
-#define MD_PERSONALITY
+#include "md.h"
+#include "multipath.h"
 
 #define MAX_WORK_PER_DISK 128
 
 #define	NR_RESERVED_BUFS	32
 
 
-static int multipath_map (multipath_conf_t *conf)
+static int multipath_map (struct mpconf *conf)
 {
 	int i, disks = conf->raid_disks;
 
@@ -46,7 +43,7 @@ static int multipath_map (multipath_conf_t *conf)
 
 	rcu_read_lock();
 	for (i = 0; i < disks; i++) {
-		mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
+		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
 		if (rdev && test_bit(In_sync, &rdev->flags)) {
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
@@ -62,8 +59,8 @@ static int multipath_map (multipath_conf_t *conf)
 static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
 {
 	unsigned long flags;
-	mddev_t *mddev = mp_bh->mddev;
-	multipath_conf_t *conf = mddev_to_conf(mddev);
+	struct mddev *mddev = mp_bh->mddev;
+	struct mpconf *conf = mddev->private;
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 	list_add(&mp_bh->retry_list, &conf->retry_list);
@@ -80,7 +77,7 @@ static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
 static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
 {
 	struct bio *bio = mp_bh->master_bio;
-	multipath_conf_t *conf = mddev_to_conf(mp_bh->mddev);
+	struct mpconf *conf = mp_bh->mddev->private;
 
 	bio_endio(bio, err);
 	mempool_free(mp_bh, conf->pool);
@@ -89,13 +86,13 @@ static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
 static void multipath_end_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct multipath_bh * mp_bh = (struct multipath_bh *)(bio->bi_private);
-	multipath_conf_t *conf = mddev_to_conf(mp_bh->mddev);
-	mdk_rdev_t *rdev = conf->multipaths[mp_bh->path].rdev;
+	struct multipath_bh *mp_bh = bio->bi_private;
+	struct mpconf *conf = mp_bh->mddev->private;
+	struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
 
 	if (uptodate)
 		multipath_end_bh_io(mp_bh, 0);
-	else if (!bio_rw_ahead(bio)) {
+	else if (!(bio->bi_rw & REQ_RAHEAD)) {
 		/*
 		 * oops, IO error:
 		 */
@@ -103,54 +100,22 @@ static void multipath_end_request(struct bio *bio, int error)
 		md_error (mp_bh->mddev, rdev);
 		printk(KERN_ERR "multipath: %s: rescheduling sector %llu\n", 
 		       bdevname(rdev->bdev,b), 
-		       (unsigned long long)bio->bi_sector);
+		       (unsigned long long)bio->bi_iter.bi_sector);
 		multipath_reschedule_retry(mp_bh);
 	} else
 		multipath_end_bh_io(mp_bh, error);
 	rdev_dec_pending(rdev, conf->mddev);
 }
 
-static void unplug_slaves(mddev_t *mddev)
+static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 {
-	multipath_conf_t *conf = mddev_to_conf(mddev);
-	int i;
-
-	rcu_read_lock();
-	for (i=0; i<mddev->raid_disks; i++) {
-		mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
-		if (rdev && !test_bit(Faulty, &rdev->flags)
-		    && atomic_read(&rdev->nr_pending)) {
-			struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
-
-			atomic_inc(&rdev->nr_pending);
-			rcu_read_unlock();
-
-			blk_unplug(r_queue);
-
-			rdev_dec_pending(rdev, mddev);
-			rcu_read_lock();
-		}
-	}
-	rcu_read_unlock();
-}
-
-static void multipath_unplug(struct request_queue *q)
-{
-	unplug_slaves(q->queuedata);
-}
-
-
-static int multipath_make_request (struct request_queue *q, struct bio * bio)
-{
-	mddev_t *mddev = q->queuedata;
-	multipath_conf_t *conf = mddev_to_conf(mddev);
+	struct mpconf *conf = mddev->private;
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
-	const int rw = bio_data_dir(bio);
 
-	if (unlikely(bio_barrier(bio))) {
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
+		return;
 	}
 
 	mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
@@ -158,34 +123,31 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
 	mp_bh->master_bio = bio;
 	mp_bh->mddev = mddev;
 
-	disk_stat_inc(mddev->gendisk, ios[rw]);
-	disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio));
-
 	mp_bh->path = multipath_map(conf);
 	if (mp_bh->path < 0) {
 		bio_endio(bio, -EIO);
 		mempool_free(mp_bh, conf->pool);
-		return 0;
+		return;
 	}
 	multipath = conf->multipaths + mp_bh->path;
 
 	mp_bh->bio = *bio;
-	mp_bh->bio.bi_sector += multipath->rdev->data_offset;
+	mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
 	mp_bh->bio.bi_bdev = multipath->rdev->bdev;
-	mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST);
+	mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT;
 	mp_bh->bio.bi_end_io = multipath_end_request;
 	mp_bh->bio.bi_private = mp_bh;
 	generic_make_request(&mp_bh->bio);
-	return 0;
+	return;
 }
 
-static void multipath_status (struct seq_file *seq, mddev_t *mddev)
+static void multipath_status (struct seq_file *seq, struct mddev *mddev)
 {
-	multipath_conf_t *conf = mddev_to_conf(mddev);
+	struct mpconf *conf = mddev->private;
 	int i;
 	
 	seq_printf (seq, " [%d/%d] [", conf->raid_disks,
-						 conf->working_disks);
+		    conf->raid_disks - mddev->degraded);
 	for (i = 0; i < conf->raid_disks; i++)
 		seq_printf (seq, "%s",
 			       conf->multipaths[i].rdev && 
@@ -195,13 +157,16 @@ static void multipath_status (struct seq_file *seq, mddev_t *mddev)
 
 static int multipath_congested(void *data, int bits)
 {
-	mddev_t *mddev = data;
-	multipath_conf_t *conf = mddev_to_conf(mddev);
+	struct mddev *mddev = data;
+	struct mpconf *conf = mddev->private;
 	int i, ret = 0;
 
+	if (mddev_congested(mddev, bits))
+		return 1;
+
 	rcu_read_lock();
 	for (i = 0; i < mddev->raid_disks ; i++) {
-		mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
+		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
@@ -219,40 +184,42 @@ static int multipath_congested(void *data, int bits)
 /*
  * Careful, this can execute in IRQ contexts as well!
  */
-static void multipath_error (mddev_t *mddev, mdk_rdev_t *rdev)
+static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
 {
-	multipath_conf_t *conf = mddev_to_conf(mddev);
+	struct mpconf *conf = mddev->private;
+	char b[BDEVNAME_SIZE];
 
-	if (conf->working_disks <= 1) {
+	if (conf->raid_disks - mddev->degraded <= 1) {
 		/*
 		 * Uh oh, we can do nothing if this is our last path, but
 		 * first check if this is a queued request for a device
 		 * which has just failed.
 		 */
 		printk(KERN_ALERT 
-			"multipath: only one IO path left and IO error.\n");
+		       "multipath: only one IO path left and IO error.\n");
 		/* leave it active... it's all we have */
-	} else {
-		/*
-		 * Mark disk as unusable
-		 */
-		if (!test_bit(Faulty, &rdev->flags)) {
-			char b[BDEVNAME_SIZE];
-			clear_bit(In_sync, &rdev->flags);
-			set_bit(Faulty, &rdev->flags);
-			set_bit(MD_CHANGE_DEVS, &mddev->flags);
-			conf->working_disks--;
-			mddev->degraded++;
-			printk(KERN_ALERT "multipath: IO failure on %s,"
-				" disabling IO path. \n	Operation continuing"
-				" on %d IO paths.\n",
-				bdevname (rdev->bdev,b),
-				conf->working_disks);
-		}
+		return;
+	}
+	/*
+	 * Mark disk as unusable
+	 */
+	if (test_and_clear_bit(In_sync, &rdev->flags)) {
+		unsigned long flags;
+		spin_lock_irqsave(&conf->device_lock, flags);
+		mddev->degraded++;
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
+	set_bit(Faulty, &rdev->flags);
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	printk(KERN_ALERT "multipath: IO failure on %s,"
+	       " disabling IO path.\n"
+	       "multipath: Operation continuing"
+	       " on %d IO paths.\n",
+	       bdevname(rdev->bdev, b),
+	       conf->raid_disks - mddev->degraded);
 }
 
-static void print_multipath_conf (multipath_conf_t *conf)
+static void print_multipath_conf (struct mpconf *conf)
 {
 	int i;
 	struct multipath_info *tmp;
@@ -262,7 +229,7 @@ static void print_multipath_conf (multipath_conf_t *conf)
 		printk("(conf==NULL)\n");
 		return;
 	}
-	printk(" --- wd:%d rd:%d\n", conf->working_disks,
+	printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
 			 conf->raid_disks);
 
 	for (i = 0; i < conf->raid_disks; i++) {
@@ -276,57 +243,69 @@ static void print_multipath_conf (multipath_conf_t *conf)
 }
 
 
-static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
+static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
-	multipath_conf_t *conf = mddev->private;
+	struct mpconf *conf = mddev->private;
 	struct request_queue *q;
-	int found = 0;
+	int err = -EEXIST;
 	int path;
 	struct multipath_info *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
+
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
 
 	print_multipath_conf(conf);
 
-	for (path=0; path<mddev->raid_disks; path++) 
+	for (path = first; path <= last; path++)
 		if ((p=conf->multipaths+path)->rdev == NULL) {
 			q = rdev->bdev->bd_disk->queue;
-			blk_queue_stack_limits(mddev->queue, q);
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
 
 		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, so limit ->max_sector to one PAGE, as
-		 * a one page request is never in violation.
+		 * violating it, so limit ->max_segments to one, lying
+		 * within a single page.
 		 * (Note: it is very unlikely that a device with
 		 * merge_bvec_fn will be involved in multipath.)
 		 */
-			if (q->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
-				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+			if (q->merge_bvec_fn) {
+				blk_queue_max_segments(mddev->queue, 1);
+				blk_queue_segment_boundary(mddev->queue,
+							   PAGE_CACHE_SIZE - 1);
+			}
 
-			conf->working_disks++;
+			spin_lock_irq(&conf->device_lock);
 			mddev->degraded--;
 			rdev->raid_disk = path;
 			set_bit(In_sync, &rdev->flags);
+			spin_unlock_irq(&conf->device_lock);
 			rcu_assign_pointer(p->rdev, rdev);
-			found = 1;
+			err = 0;
+			md_integrity_add_rdev(rdev, mddev);
+			break;
 		}
 
 	print_multipath_conf(conf);
-	return found;
+
+	return err;
 }
 
-static int multipath_remove_disk(mddev_t *mddev, int number)
+static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
-	multipath_conf_t *conf = mddev->private;
+	struct mpconf *conf = mddev->private;
 	int err = 0;
-	mdk_rdev_t *rdev;
+	int number = rdev->raid_disk;
 	struct multipath_info *p = conf->multipaths + number;
 
 	print_multipath_conf(conf);
 
-	rdev = p->rdev;
-	if (rdev) {
+	if (rdev == p->rdev) {
 		if (test_bit(In_sync, &rdev->flags) ||
 		    atomic_read(&rdev->nr_pending)) {
-			printk(KERN_ERR "hot-remove-disk, slot %d is identified"				" but is still operational!\n", number);
+			printk(KERN_ERR "hot-remove-disk, slot %d is identified"
+			       " but is still operational!\n", number);
 			err = -EBUSY;
 			goto abort;
 		}
@@ -336,7 +315,9 @@ static int multipath_remove_disk(mddev_t *mddev, int number)
 			/* lost the race, try later */
 			err = -EBUSY;
 			p->rdev = rdev;
+			goto abort;
 		}
+		err = md_integrity_register(mddev);
 	}
 abort:
 
@@ -354,12 +335,13 @@ abort:
  *	3.	Performs writes following reads for array syncronising.
  */
 
-static void multipathd (mddev_t *mddev)
+static void multipathd(struct md_thread *thread)
 {
+	struct mddev *mddev = thread->mddev;
 	struct multipath_bh *mp_bh;
 	struct bio *bio;
 	unsigned long flags;
-	multipath_conf_t *conf = mddev_to_conf(mddev);
+	struct mpconf *conf = mddev->private;
 	struct list_head *head = &conf->retry_list;
 
 	md_check_recovery(mddev);
@@ -373,23 +355,24 @@ static void multipathd (mddev_t *mddev)
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 
 		bio = &mp_bh->bio;
-		bio->bi_sector = mp_bh->master_bio->bi_sector;
+		bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector;
 		
 		if ((mp_bh->path = multipath_map (conf))<0) {
 			printk(KERN_ALERT "multipath: %s: unrecoverable IO read"
 				" error for block %llu\n",
 				bdevname(bio->bi_bdev,b),
-				(unsigned long long)bio->bi_sector);
+				(unsigned long long)bio->bi_iter.bi_sector);
 			multipath_end_bh_io(mp_bh, -EIO);
 		} else {
 			printk(KERN_ERR "multipath: %s: redirecting sector %llu"
 				" to another IO path\n",
 				bdevname(bio->bi_bdev,b),
-				(unsigned long long)bio->bi_sector);
+				(unsigned long long)bio->bi_iter.bi_sector);
 			*bio = *(mp_bh->master_bio);
-			bio->bi_sector += conf->multipaths[mp_bh->path].rdev->data_offset;
+			bio->bi_iter.bi_sector +=
+				conf->multipaths[mp_bh->path].rdev->data_offset;
 			bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev;
-			bio->bi_rw |= (1 << BIO_RW_FAILFAST);
+			bio->bi_rw |= REQ_FAILFAST_TRANSPORT;
 			bio->bi_end_io = multipath_end_request;
 			bio->bi_private = mp_bh;
 			generic_make_request(bio);
@@ -398,13 +381,24 @@ static void multipathd (mddev_t *mddev)
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 }
 
-static int multipath_run (mddev_t *mddev)
+static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 {
-	multipath_conf_t *conf;
+	WARN_ONCE(sectors || raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+
+	return mddev->dev_sectors;
+}
+
+static int multipath_run (struct mddev *mddev)
+{
+	struct mpconf *conf;
 	int disk_idx;
 	struct multipath_info *disk;
-	mdk_rdev_t *rdev;
-	struct list_head *tmp;
+	struct md_rdev *rdev;
+	int working_disks;
+
+	if (md_check_no_bitmap(mddev))
+		return -EINVAL;
 
 	if (mddev->level != LEVEL_MULTIPATH) {
 		printk("multipath: %s: raid level not set to multipath IO (%d)\n",
@@ -417,7 +411,7 @@ static int multipath_run (mddev_t *mddev)
 	 * should be freed in multipath_stop()]
 	 */
 
-	conf = kzalloc(sizeof(multipath_conf_t), GFP_KERNEL);
+	conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
 	mddev->private = conf;
 	if (!conf) {
 		printk(KERN_ERR 
@@ -435,8 +429,8 @@ static int multipath_run (mddev_t *mddev)
 		goto out_free_conf;
 	}
 
-	conf->working_disks = 0;
-	rdev_for_each(rdev, tmp, mddev) {
+	working_disks = 0;
+	rdev_for_each(rdev, mddev) {
 		disk_idx = rdev->raid_disk;
 		if (disk_idx < 0 ||
 		    disk_idx >= mddev->raid_disks)
@@ -444,18 +438,20 @@ static int multipath_run (mddev_t *mddev)
 
 		disk = conf->multipaths + disk_idx;
 		disk->rdev = rdev;
+		disk_stack_limits(mddev->gendisk, rdev->bdev,
+				  rdev->data_offset << 9);
 
-		blk_queue_stack_limits(mddev->queue,
-				       rdev->bdev->bd_disk->queue);
 		/* as we don't honour merge_bvec_fn, we must never risk
 		 * violating it, not that we ever expect a device with
 		 * a merge_bvec_fn to be involved in multipath */
-		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
-			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+			blk_queue_max_segments(mddev->queue, 1);
+			blk_queue_segment_boundary(mddev->queue,
+						   PAGE_CACHE_SIZE - 1);
+		}
 
 		if (!test_bit(Faulty, &rdev->flags))
-			conf->working_disks++;
+			working_disks++;
 	}
 
 	conf->raid_disks = mddev->raid_disks;
@@ -463,14 +459,14 @@ static int multipath_run (mddev_t *mddev)
 	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
 
-	if (!conf->working_disks) {
+	if (!working_disks) {
 		printk(KERN_ERR "multipath: no operational IO paths for %s\n",
 			mdname(mddev));
 		goto out_free_conf;
 	}
-	mddev->degraded = conf->raid_disks - conf->working_disks;
+	mddev->degraded = conf->raid_disks - working_disks;
 
-	conf->pool = mempool_create_kzalloc_pool(NR_RESERVED_BUFS,
+	conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS,
 						 sizeof(struct multipath_bh));
 	if (conf->pool == NULL) {
 		printk(KERN_ERR 
@@ -480,7 +476,8 @@ static int multipath_run (mddev_t *mddev)
 	}
 
 	{
-		mddev->thread = md_register_thread(multipathd, mddev, "%s_multipath");
+		mddev->thread = md_register_thread(multipathd, mddev,
+						   "multipath");
 		if (!mddev->thread) {
 			printk(KERN_ERR "multipath: couldn't allocate thread"
 				" for %s\n", mdname(mddev));
@@ -490,16 +487,19 @@ static int multipath_run (mddev_t *mddev)
 
 	printk(KERN_INFO 
 		"multipath: array %s active with %d out of %d IO paths\n",
-		mdname(mddev), conf->working_disks, mddev->raid_disks);
+		mdname(mddev), conf->raid_disks - mddev->degraded,
+	       mddev->raid_disks);
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = mddev->size;
+	md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
 
-	mddev->queue->unplug_fn = multipath_unplug;
 	mddev->queue->backing_dev_info.congested_fn = multipath_congested;
 	mddev->queue->backing_dev_info.congested_data = mddev;
 
+	if (md_integrity_register(mddev))
+		goto out_free_conf;
+
 	return 0;
 
 out_free_conf:
@@ -513,12 +513,11 @@ out:
 }
 
 
-static int multipath_stop (mddev_t *mddev)
+static int multipath_stop (struct mddev *mddev)
 {
-	multipath_conf_t *conf = mddev_to_conf(mddev);
+	struct mpconf *conf = mddev->private;
 
-	md_unregister_thread(mddev->thread);
-	mddev->thread = NULL;
+	md_unregister_thread(&mddev->thread);
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	mempool_destroy(conf->pool);
 	kfree(conf->multipaths);
@@ -527,7 +526,7 @@ static int multipath_stop (mddev_t *mddev)
 	return 0;
 }
 
-static struct mdk_personality multipath_personality =
+static struct md_personality multipath_personality =
 {
 	.name		= "multipath",
 	.level		= LEVEL_MULTIPATH,
@@ -539,6 +538,7 @@ static struct mdk_personality multipath_personality =
 	.error_handler	= multipath_error,
 	.hot_add_disk	= multipath_add_disk,
 	.hot_remove_disk= multipath_remove_disk,
+	.size		= multipath_size,
 };
 
 static int __init multipath_init (void)
@@ -554,6 +554,7 @@ static void __exit multipath_exit (void)
 module_init(multipath_init);
 module_exit(multipath_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("simple multi-path personality for MD");
 MODULE_ALIAS("md-personality-7"); /* MULTIPATH */
 MODULE_ALIAS("md-multipath");
 MODULE_ALIAS("md-level--4");