1 files changed, 204 insertions, 217 deletions

diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 09658b21847..56f534b4a2d 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -16,26 +16,40 @@
    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
 */
 
-#include <linux/raid/linear.h>
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "md.h"
+#include "linear.h"
 
 /*
  * find which device holds a particular offset 
  */
-static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
+static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 {
-	dev_info_t *hash;
-	linear_conf_t *conf = mddev_to_conf(mddev);
-	sector_t idx = sector >> conf->sector_shift;
+	int lo, mid, hi;
+	struct linear_conf *conf;
+
+	lo = 0;
+	hi = mddev->raid_disks - 1;
+	conf = rcu_dereference(mddev->private);
 
 	/*
-	 * sector_div(a,b) returns the remainer and sets a to a/b
+	 * Binary Search
 	 */
-	(void)sector_div(idx, conf->spacing);
-	hash = conf->hash_table[idx];
 
-	while (sector >= hash->num_sectors + hash->start_sector)
-		hash++;
-	return hash;
+	while (hi > lo) {
+
+		mid = (hi + lo) / 2;
+		if (sector < conf->disks[mid].end_sector)
+			hi = mid;
+		else
+			lo = mid + 1;
+	}
+
+	return conf->disks + lo;
 }
 
 /**
@@ -50,13 +64,24 @@ static int linear_mergeable_bvec(struct request_queue *q,
 				 struct bvec_merge_data *bvm,
 				 struct bio_vec *biovec)
 {
-	mddev_t *mddev = q->queuedata;
-	dev_info_t *dev0;
+	struct mddev *mddev = q->queuedata;
+	struct dev_info *dev0;
 	unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
+	int maxbytes = biovec->bv_len;
+	struct request_queue *subq;
 
+	rcu_read_lock();
 	dev0 = which_dev(mddev, sector);
-	maxsectors = dev0->num_sectors - (sector - dev0->start_sector);
+	maxsectors = dev0->end_sector - sector;
+	subq = bdev_get_queue(dev0->rdev->bdev);
+	if (subq->merge_bvec_fn) {
+		bvm->bi_bdev = dev0->rdev->bdev;
+		bvm->bi_sector -= dev0->end_sector - dev0->rdev->sectors;
+		maxbytes = min(maxbytes, subq->merge_bvec_fn(subq, bvm,
+							     biovec));
+	}
+	rcu_read_unlock();
 
 	if (maxsectors < bio_sectors)
 		maxsectors = 0;
@@ -64,49 +89,58 @@ static int linear_mergeable_bvec(struct request_queue *q,
 		maxsectors -= bio_sectors;
 
 	if (maxsectors <= (PAGE_SIZE >> 9 ) && bio_sectors == 0)
-		return biovec->bv_len;
-	/* The bytes available at this offset could be really big,
-	 * so we cap at 2^31 to avoid overflow */
-	if (maxsectors > (1 << (31-9)))
-		return 1<<31;
-	return maxsectors << 9;
-}
-
-static void linear_unplug(struct request_queue *q)
-{
-	mddev_t *mddev = q->queuedata;
-	linear_conf_t *conf = mddev_to_conf(mddev);
-	int i;
+		return maxbytes;
 
-	for (i=0; i < mddev->raid_disks; i++) {
-		struct request_queue *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev);
-		blk_unplug(r_queue);
-	}
+	if (maxsectors > (maxbytes >> 9))
+		return maxbytes;
+	else
+		return maxsectors << 9;
 }
 
 static int linear_congested(void *data, int bits)
 {
-	mddev_t *mddev = data;
-	linear_conf_t *conf = mddev_to_conf(mddev);
+	struct mddev *mddev = data;
+	struct linear_conf *conf;
 	int i, ret = 0;
 
+	if (mddev_congested(mddev, bits))
+		return 1;
+
+	rcu_read_lock();
+	conf = rcu_dereference(mddev->private);
+
 	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
 		ret |= bdi_congested(&q->backing_dev_info, bits);
 	}
+
+	rcu_read_unlock();
 	return ret;
 }
 
-static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
+static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 {
-	linear_conf_t *conf;
-	dev_info_t **table;
-	mdk_rdev_t *rdev;
-	int i, nb_zone, cnt;
-	sector_t min_sectors;
-	sector_t curr_sector;
-
-	conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(dev_info_t),
+	struct linear_conf *conf;
+	sector_t array_sectors;
+
+	rcu_read_lock();
+	conf = rcu_dereference(mddev->private);
+	WARN_ONCE(sectors || raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+	array_sectors = conf->array_sectors;
+	rcu_read_unlock();
+
+	return array_sectors;
+}
+
+static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
+{
+	struct linear_conf *conf;
+	struct md_rdev *rdev;
+	int i, cnt;
+	bool discard_supported = false;
+
+	conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(struct dev_info),
 			GFP_KERNEL);
 	if (!conf)
 		return NULL;
@@ -114,123 +148,53 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 	cnt = 0;
 	conf->array_sectors = 0;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		int j = rdev->raid_disk;
-		dev_info_t *disk = conf->disks + j;
+		struct dev_info *disk = conf->disks + j;
+		sector_t sectors;
 
 		if (j < 0 || j >= raid_disks || disk->rdev) {
-			printk("linear: disk numbering problem. Aborting!\n");
+			printk(KERN_ERR "md/linear:%s: disk numbering problem. Aborting!\n",
+			       mdname(mddev));
 			goto out;
 		}
 
 		disk->rdev = rdev;
+		if (mddev->chunk_sectors) {
+			sectors = rdev->sectors;
+			sector_div(sectors, mddev->chunk_sectors);
+			rdev->sectors = sectors * mddev->chunk_sectors;
+		}
 
-		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, so limit ->max_sector to one PAGE, as
-		 * a one page request is never in violation.
-		 */
-		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);
-
-		disk->num_sectors = rdev->size * 2;
-		conf->array_sectors += rdev->size * 2;
+		disk_stack_limits(mddev->gendisk, rdev->bdev,
+				  rdev->data_offset << 9);
 
+		conf->array_sectors += rdev->sectors;
 		cnt++;
+
+		if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+			discard_supported = true;
 	}
 	if (cnt != raid_disks) {
-		printk("linear: not enough drives present. Aborting!\n");
+		printk(KERN_ERR "md/linear:%s: not enough drives present. Aborting!\n",
+		       mdname(mddev));
 		goto out;
 	}
 
-	min_sectors = conf->array_sectors;
-	sector_div(min_sectors, PAGE_SIZE/sizeof(struct dev_info *));
-	if (min_sectors == 0)
-		min_sectors = 1;
-
-	/* min_sectors is the minimum spacing that will fit the hash
-	 * table in one PAGE.  This may be much smaller than needed.
-	 * We find the smallest non-terminal set of consecutive devices
-	 * that is larger than min_sectors and use the size of that as
-	 * the actual spacing
-	 */
-	conf->spacing = conf->array_sectors;
-	for (i=0; i < cnt-1 ; i++) {
-		sector_t tmp = 0;
-		int j;
-		for (j = i; j < cnt - 1 && tmp < min_sectors; j++)
-			tmp += conf->disks[j].num_sectors;
-		if (tmp >= min_sectors && tmp < conf->spacing)
-			conf->spacing = tmp;
-	}
+	if (!discard_supported)
+		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+	else
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
 
-	/* spacing may be too large for sector_div to work with,
-	 * so we might need to pre-shift
-	 */
-	conf->sector_shift = 0;
-	if (sizeof(sector_t) > sizeof(u32)) {
-		sector_t space = conf->spacing;
-		while (space > (sector_t)(~(u32)0)) {
-			space >>= 1;
-			conf->sector_shift++;
-		}
-	}
 	/*
-	 * This code was restructured to work around a gcc-2.95.3 internal
-	 * compiler error.  Alter it with care.
+	 * Here we calculate the device offsets.
 	 */
-	{
-		sector_t sz;
-		unsigned round;
-		unsigned long base;
-
-		sz = conf->array_sectors >> conf->sector_shift;
-		sz += 1; /* force round-up */
-		base = conf->spacing >> conf->sector_shift;
-		round = sector_div(sz, base);
-		nb_zone = sz + (round ? 1 : 0);
-	}
-	BUG_ON(nb_zone > PAGE_SIZE / sizeof(struct dev_info *));
-
-	conf->hash_table = kmalloc (sizeof (struct dev_info *) * nb_zone,
-					GFP_KERNEL);
-	if (!conf->hash_table)
-		goto out;
+	conf->disks[0].end_sector = conf->disks[0].rdev->sectors;
 
-	/*
-	 * Here we generate the linear hash table
-	 * First calculate the device offsets.
-	 */
-	conf->disks[0].start_sector = 0;
 	for (i = 1; i < raid_disks; i++)
-		conf->disks[i].start_sector =
-			conf->disks[i-1].start_sector +
-			conf->disks[i-1].num_sectors;
-
-	table = conf->hash_table;
-	i = 0;
-	for (curr_sector = 0;
-	     curr_sector < conf->array_sectors;
-	     curr_sector += conf->spacing) {
-
-		while (i < raid_disks-1 &&
-		       curr_sector >= conf->disks[i+1].start_sector)
-			i++;
-
-		*table ++ = conf->disks + i;
-	}
-
-	if (conf->sector_shift) {
-		conf->spacing >>= conf->sector_shift;
-		/* round spacing up so that when we divide by it,
-		 * we err on the side of "too-low", which is safest.
-		 */
-		conf->spacing++;
-	}
-
-	BUG_ON(table - conf->hash_table > nb_zone);
+		conf->disks[i].end_sector =
+			conf->disks[i-1].end_sector +
+			conf->disks[i].rdev->sectors;
 
 	return conf;
 
@@ -239,26 +203,33 @@ out:
 	return NULL;
 }
 
-static int linear_run (mddev_t *mddev)
+static int linear_run (struct mddev *mddev)
 {
-	linear_conf_t *conf;
+	struct linear_conf *conf;
+	int ret;
 
-	mddev->queue->queue_lock = &mddev->queue->__queue_lock;
+	if (md_check_no_bitmap(mddev))
+		return -EINVAL;
 	conf = linear_conf(mddev, mddev->raid_disks);
 
 	if (!conf)
 		return 1;
 	mddev->private = conf;
-	mddev->array_sectors = conf->array_sectors;
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 
 	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
-	mddev->queue->unplug_fn = linear_unplug;
 	mddev->queue->backing_dev_info.congested_fn = linear_congested;
 	mddev->queue->backing_dev_info.congested_data = mddev;
-	return 0;
+
+	ret =  md_integrity_register(mddev);
+	if (ret) {
+		kfree(conf);
+		mddev->private = NULL;
+	}
+	return ret;
 }
 
-static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
+static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 {
 	/* Adding a drive to a linear array allows the array to grow.
 	 * It is permitted if the new drive has a matching superblock
@@ -268,110 +239,124 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
 	 * The current one is never freed until the array is stopped.
 	 * This avoids races.
 	 */
-	linear_conf_t *newconf;
+	struct linear_conf *newconf, *oldconf;
 
 	if (rdev->saved_raid_disk != mddev->raid_disks)
 		return -EINVAL;
 
 	rdev->raid_disk = rdev->saved_raid_disk;
+	rdev->saved_raid_disk = -1;
 
 	newconf = linear_conf(mddev,mddev->raid_disks+1);
 
 	if (!newconf)
 		return -ENOMEM;
 
-	newconf->prev = mddev_to_conf(mddev);
-	mddev->private = newconf;
+	oldconf = rcu_dereference_protected(mddev->private,
+					    lockdep_is_held(
+						    &mddev->reconfig_mutex));
 	mddev->raid_disks++;
-	mddev->array_sectors = newconf->array_sectors;
+	rcu_assign_pointer(mddev->private, newconf);
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
+	revalidate_disk(mddev->gendisk);
+	kfree_rcu(oldconf, rcu);
 	return 0;
 }
 
-static int linear_stop (mddev_t *mddev)
+static int linear_stop (struct mddev *mddev)
 {
-	linear_conf_t *conf = mddev_to_conf(mddev);
-  
+	struct linear_conf *conf =
+		rcu_dereference_protected(mddev->private,
+					  lockdep_is_held(
+						  &mddev->reconfig_mutex));
+
+	/*
+	 * We do not require rcu protection here since
+	 * we hold reconfig_mutex for both linear_add and
+	 * linear_stop, so they cannot race.
+	 * We should make sure any old 'conf's are properly
+	 * freed though.
+	 */
+	rcu_barrier();
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
-	do {
-		linear_conf_t *t = conf->prev;
-		kfree(conf->hash_table);
-		kfree(conf);
-		conf = t;
-	} while (conf);
+	kfree(conf);
+	mddev->private = NULL;
 
 	return 0;
 }
 
-static int linear_make_request (struct request_queue *q, struct bio *bio)
+static void linear_make_request(struct mddev *mddev, struct bio *bio)
 {
-	const int rw = bio_data_dir(bio);
-	mddev_t *mddev = q->queuedata;
-	dev_info_t *tmp_dev;
-	int cpu;
-
-	if (unlikely(bio_barrier(bio))) {
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
+	char b[BDEVNAME_SIZE];
+	struct dev_info *tmp_dev;
+	struct bio *split;
+	sector_t start_sector, end_sector, data_offset;
+
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
+		return;
 	}
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
-	tmp_dev = which_dev(mddev, bio->bi_sector);
-    
-	if (unlikely(bio->bi_sector >= (tmp_dev->num_sectors +
-					tmp_dev->start_sector)
-		     || (bio->bi_sector <
-			 tmp_dev->start_sector))) {
-		char b[BDEVNAME_SIZE];
-
-		printk("linear_make_request: Sector %llu out of bounds on "
-			"dev %s: %llu sectors, offset %llu\n",
-			(unsigned long long)bio->bi_sector,
-			bdevname(tmp_dev->rdev->bdev, b),
-			(unsigned long long)tmp_dev->num_sectors,
-			(unsigned long long)tmp_dev->start_sector);
-		bio_io_error(bio);
-		return 0;
-	}
-	if (unlikely(bio->bi_sector + (bio->bi_size >> 9) >
-		     tmp_dev->start_sector + tmp_dev->num_sectors)) {
-		/* This bio crosses a device boundary, so we have to
-		 * split it.
-		 */
-		struct bio_pair *bp;
-
-		bp = bio_split(bio,
-			       tmp_dev->start_sector + tmp_dev->num_sectors
-			       - bio->bi_sector);
-
-		if (linear_make_request(q, &bp->bio1))
-			generic_make_request(&bp->bio1);
-		if (linear_make_request(q, &bp->bio2))
-			generic_make_request(&bp->bio2);
-		bio_pair_release(bp);
-		return 0;
-	}
-		    
-	bio->bi_bdev = tmp_dev->rdev->bdev;
-	bio->bi_sector = bio->bi_sector - tmp_dev->start_sector
-		+ tmp_dev->rdev->data_offset;
+	do {
+		rcu_read_lock();
+
+		tmp_dev = which_dev(mddev, bio->bi_iter.bi_sector);
+		start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
+		end_sector = tmp_dev->end_sector;
+		data_offset = tmp_dev->rdev->data_offset;
+		bio->bi_bdev = tmp_dev->rdev->bdev;
+
+		rcu_read_unlock();
+
+		if (unlikely(bio->bi_iter.bi_sector >= end_sector ||
+			     bio->bi_iter.bi_sector < start_sector))
+			goto out_of_bounds;
+
+		if (unlikely(bio_end_sector(bio) > end_sector)) {
+			/* This bio crosses a device boundary, so we have to
+			 * split it.
+			 */
+			split = bio_split(bio, end_sector -
+					  bio->bi_iter.bi_sector,
+					  GFP_NOIO, fs_bio_set);
+			bio_chain(split, bio);
+		} else {
+			split = bio;
+		}
 
-	return 1;
+		split->bi_iter.bi_sector = split->bi_iter.bi_sector -
+			start_sector + data_offset;
+
+		if (unlikely((split->bi_rw & REQ_DISCARD) &&
+			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
+			/* Just ignore it */
+			bio_endio(split, 0);
+		} else
+			generic_make_request(split);
+	} while (split != bio);
+	return;
+
+out_of_bounds:
+	printk(KERN_ERR
+	       "md/linear:%s: make_request: Sector %llu out of bounds on "
+	       "dev %s: %llu sectors, offset %llu\n",
+	       mdname(mddev),
+	       (unsigned long long)bio->bi_iter.bi_sector,
+	       bdevname(tmp_dev->rdev->bdev, b),
+	       (unsigned long long)tmp_dev->rdev->sectors,
+	       (unsigned long long)start_sector);
+	bio_io_error(bio);
 }
 
-static void linear_status (struct seq_file *seq, mddev_t *mddev)
+static void linear_status (struct seq_file *seq, struct mddev *mddev)
 {
 
-	seq_printf(seq, " %dk rounding", mddev->chunk_size/1024);
+	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
 }
 
 
-static struct mdk_personality linear_personality =
+static struct md_personality linear_personality =
 {
 	.name		= "linear",
 	.level		= LEVEL_LINEAR,
@@ -381,6 +366,7 @@ static struct mdk_personality linear_personality =
 	.stop		= linear_stop,
 	.status		= linear_status,
 	.hot_add_disk	= linear_add,
+	.size		= linear_size,
 };
 
 static int __init linear_init (void)
@@ -397,6 +383,7 @@ static void linear_exit (void)
 module_init(linear_init);
 module_exit(linear_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Linear device concatenation personality for MD");
 MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
 MODULE_ALIAS("md-linear");
 MODULE_ALIAS("md-level--1");