Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/module.h>
-
-#include <linux/raid/md.h>
-#include <linux/slab.h>
#include <linux/raid/linear.h>
-#define MAJOR_NR MD_MAJOR
-#define MD_DRIVER
-#define MD_PERSONALITY
-
/*
* find which device holds a particular offset
*/
{
dev_info_t *hash;
linear_conf_t *conf = mddev_to_conf(mddev);
- sector_t block = sector >> 1;
/*
* sector_div(a,b) returns the remainer and sets a to a/b
*/
- (void)sector_div(block, conf->smallest->size);
- hash = conf->hash_table[block];
+ sector >>= conf->sector_shift;
+ (void)sector_div(sector, conf->spacing);
+ hash = conf->hash_table[sector];
- while ((sector>>1) >= (hash->size + hash->offset))
+ while (sector >= hash->num_sectors + hash->start_sector)
hash++;
return hash;
}
/**
- * linear_mergeable_bvec -- tell bio layer if a two requests can be merged
+ * linear_mergeable_bvec -- tell bio layer if two requests can be merged
* @q: request queue
- * @bio: the buffer head that's been built up so far
+ * @bvm: properties of new bio
* @biovec: the request that could be merged to it.
*
* Return amount of bytes we can take at this offset
*/
-static int linear_mergeable_bvec(request_queue_t *q, struct bio *bio, struct bio_vec *biovec)
+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;
- unsigned long maxsectors, bio_sectors = bio->bi_size >> 9;
- sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+ unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
+ sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
dev0 = which_dev(mddev, sector);
- maxsectors = (dev0->size << 1) - (sector - (dev0->offset<<1));
+ maxsectors = dev0->num_sectors - (sector - dev0->start_sector);
if (maxsectors < bio_sectors)
maxsectors = 0;
return maxsectors << 9;
}
-static void linear_unplug(request_queue_t *q)
+static void linear_unplug(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
linear_conf_t *conf = mddev_to_conf(mddev);
int i;
for (i=0; i < mddev->raid_disks; i++) {
- request_queue_t *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev);
- if (r_queue->unplug_fn)
- r_queue->unplug_fn(r_queue);
+ struct request_queue *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev);
+ blk_unplug(r_queue);
}
}
-static int linear_issue_flush(request_queue_t *q, struct gendisk *disk,
- sector_t *error_sector)
+static int linear_congested(void *data, int bits)
{
- mddev_t *mddev = q->queuedata;
+ mddev_t *mddev = data;
linear_conf_t *conf = mddev_to_conf(mddev);
int i, ret = 0;
- for (i=0; i < mddev->raid_disks && ret == 0; i++) {
- struct block_device *bdev = conf->disks[i].rdev->bdev;
- request_queue_t *r_queue = bdev_get_queue(bdev);
-
- if (!r_queue->issue_flush_fn)
- ret = -EOPNOTSUPP;
- else
- ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk, error_sector);
+ 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);
}
return ret;
}
-static int linear_run (mddev_t *mddev)
+static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
{
linear_conf_t *conf;
dev_info_t **table;
mdk_rdev_t *rdev;
int i, nb_zone, cnt;
- sector_t start;
- sector_t curr_offset;
- struct list_head *tmp;
+ sector_t min_sectors;
+ sector_t curr_sector;
- conf = kmalloc (sizeof (*conf) + mddev->raid_disks*sizeof(dev_info_t),
+ conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(dev_info_t),
GFP_KERNEL);
if (!conf)
- goto out;
- memset(conf, 0, sizeof(*conf) + mddev->raid_disks*sizeof(dev_info_t));
- mddev->private = conf;
+ return NULL;
- /*
- * Find the smallest device.
- */
-
- conf->smallest = NULL;
cnt = 0;
- mddev->array_size = 0;
+ conf->array_sectors = 0;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
int j = rdev->raid_disk;
dev_info_t *disk = conf->disks + j;
- if (j < 0 || j > mddev->raid_disks || disk->rdev) {
+ if (j < 0 || j >= raid_disks || disk->rdev) {
printk("linear: disk numbering problem. Aborting!\n");
goto out;
}
mddev->queue->max_sectors > (PAGE_SIZE>>9))
blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
- disk->size = rdev->size;
- mddev->array_size += rdev->size;
+ disk->num_sectors = rdev->size * 2;
+ conf->array_sectors += rdev->size * 2;
- if (!conf->smallest || (disk->size < conf->smallest->size))
- conf->smallest = disk;
cnt++;
}
- if (cnt != mddev->raid_disks) {
+ if (cnt != raid_disks) {
printk("linear: not enough drives present. Aborting!\n");
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;
+ }
+
+ /* 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.
unsigned round;
unsigned long base;
- sz = mddev->array_size;
- base = conf->smallest->size;
+ 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 = conf->nr_zones = sz + (round ? 1 : 0);
+ nb_zone = sz + (round ? 1 : 0);
}
-
- conf->hash_table = kmalloc (sizeof (dev_info_t*) * nb_zone,
+ 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;
/*
* 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;
- start = 0;
- curr_offset = 0;
- for (i = 0; i < cnt; i++) {
- dev_info_t *disk = conf->disks + i;
+ i = 0;
+ for (curr_sector = 0;
+ curr_sector < conf->array_sectors;
+ curr_sector += conf->spacing) {
- disk->offset = curr_offset;
- curr_offset += disk->size;
+ while (i < raid_disks-1 &&
+ curr_sector >= conf->disks[i+1].start_sector)
+ i++;
- /* 'curr_offset' is the end of this disk
- * 'start' is the start of table
+ *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.
*/
- while (start < curr_offset) {
- *table++ = disk;
- start += conf->smallest->size;
- }
+ conf->spacing++;
}
- if (table-conf->hash_table != nb_zone)
- BUG();
+
+ BUG_ON(table - conf->hash_table > nb_zone);
+
+ return conf;
+
+out:
+ kfree(conf);
+ return NULL;
+}
+
+static int linear_run (mddev_t *mddev)
+{
+ linear_conf_t *conf;
+
+ mddev->queue->queue_lock = &mddev->queue->__queue_lock;
+ conf = linear_conf(mddev, mddev->raid_disks);
+
+ if (!conf)
+ return 1;
+ mddev->private = conf;
+ mddev->array_sectors = conf->array_sectors;
blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
mddev->queue->unplug_fn = linear_unplug;
- mddev->queue->issue_flush_fn = linear_issue_flush;
+ mddev->queue->backing_dev_info.congested_fn = linear_congested;
+ mddev->queue->backing_dev_info.congested_data = mddev;
return 0;
+}
-out:
- kfree(conf);
- return 1;
+static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+ /* Adding a drive to a linear array allows the array to grow.
+ * It is permitted if the new drive has a matching superblock
+ * already on it, with raid_disk equal to raid_disks.
+ * It is achieved by creating a new linear_private_data structure
+ * and swapping it in in-place of the current one.
+ * The current one is never freed until the array is stopped.
+ * This avoids races.
+ */
+ linear_conf_t *newconf;
+
+ if (rdev->saved_raid_disk != mddev->raid_disks)
+ return -EINVAL;
+
+ rdev->raid_disk = rdev->saved_raid_disk;
+
+ newconf = linear_conf(mddev,mddev->raid_disks+1);
+
+ if (!newconf)
+ return -ENOMEM;
+
+ newconf->prev = mddev_to_conf(mddev);
+ mddev->private = newconf;
+ mddev->raid_disks++;
+ mddev->array_sectors = newconf->array_sectors;
+ set_capacity(mddev->gendisk, mddev->array_sectors);
+ return 0;
}
static int linear_stop (mddev_t *mddev)
linear_conf_t *conf = mddev_to_conf(mddev);
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
- kfree(conf->hash_table);
- kfree(conf);
+ do {
+ linear_conf_t *t = conf->prev;
+ kfree(conf->hash_table);
+ kfree(conf);
+ conf = t;
+ } while (conf);
return 0;
}
-static int linear_make_request (request_queue_t *q, struct bio *bio)
+static int linear_make_request (struct request_queue *q, struct bio *bio)
{
+ const int rw = bio_data_dir(bio);
mddev_t *mddev = q->queuedata;
dev_info_t *tmp_dev;
- sector_t block;
-
- if (bio_data_dir(bio)==WRITE) {
- disk_stat_inc(mddev->gendisk, writes);
- disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio));
- } else {
- disk_stat_inc(mddev->gendisk, reads);
- disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio));
+ int cpu;
+
+ if (unlikely(bio_barrier(bio))) {
+ bio_endio(bio, -EOPNOTSUPP);
+ return 0;
}
+ 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);
- block = bio->bi_sector >> 1;
- if (unlikely(block >= (tmp_dev->size + tmp_dev->offset)
- || block < tmp_dev->offset)) {
+ 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: Block %llu out of bounds on "
- "dev %s size %llu offset %llu\n",
- (unsigned long long)block,
+ 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->size,
- (unsigned long long)tmp_dev->offset);
- bio_io_error(bio, bio->bi_size);
+ (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->offset + tmp_dev->size)<<1)) {
+ 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, bio_split_pool,
- ((tmp_dev->offset + tmp_dev->size)<<1) - bio->bi_sector);
+
+ 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))
}
bio->bi_bdev = tmp_dev->rdev->bdev;
- bio->bi_sector = bio->bi_sector - (tmp_dev->offset << 1) + tmp_dev->rdev->data_offset;
+ bio->bi_sector = bio->bi_sector - tmp_dev->start_sector
+ + tmp_dev->rdev->data_offset;
return 1;
}
static void linear_status (struct seq_file *seq, mddev_t *mddev)
{
-#undef MD_DEBUG
-#ifdef MD_DEBUG
- int j;
- linear_conf_t *conf = mddev_to_conf(mddev);
- sector_t s = 0;
-
- seq_printf(seq, " ");
- for (j = 0; j < conf->nr_zones; j++)
- {
- char b[BDEVNAME_SIZE];
- s += conf->smallest_size;
- seq_printf(seq, "[%s",
- bdevname(conf->hash_table[j][0].rdev->bdev,b));
-
- while (s > conf->hash_table[j][0].offset +
- conf->hash_table[j][0].size)
- seq_printf(seq, "/%s] ",
- bdevname(conf->hash_table[j][1].rdev->bdev,b));
- else
- seq_printf(seq, "] ");
- }
- seq_printf(seq, "\n");
-#endif
seq_printf(seq, " %dk rounding", mddev->chunk_size/1024);
}
-static mdk_personality_t linear_personality=
+static struct mdk_personality linear_personality =
{
.name = "linear",
+ .level = LEVEL_LINEAR,
.owner = THIS_MODULE,
.make_request = linear_make_request,
.run = linear_run,
.stop = linear_stop,
.status = linear_status,
+ .hot_add_disk = linear_add,
};
static int __init linear_init (void)
{
- return register_md_personality (LINEAR, &linear_personality);
+ return register_md_personality (&linear_personality);
}
static void linear_exit (void)
{
- unregister_md_personality (LINEAR);
+ unregister_md_personality (&linear_personality);
}
module_init(linear_init);
module_exit(linear_exit);
MODULE_LICENSE("GPL");
-MODULE_ALIAS("md-personality-1"); /* LINEAR */
+MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
+MODULE_ALIAS("md-linear");
+MODULE_ALIAS("md-level--1");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff