*/
static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
{
- struct linear_hash *hash;
+ 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;
+ block >>= conf->preshift;
+ (void)sector_div(block, conf->hash_spacing);
+ hash = conf->hash_table[block];
- if ((sector>>1) >= (hash->dev0->size + hash->dev0->offset))
- return hash->dev1;
- else
- return hash->dev0;
+ while ((sector>>1) >= (hash->size + hash->offset))
+ 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
* @biovec: the request that could be merged to it.
}
}
+static int linear_issue_flush(request_queue_t *q, struct gendisk *disk,
+ sector_t *error_sector)
+{
+ mddev_t *mddev = q->queuedata;
+ linear_conf_t *conf = mddev_to_conf(mddev);
+ int i, ret = 0;
-static int linear_run (mddev_t *mddev)
+ 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);
+ }
+ return ret;
+}
+
+static int linear_congested(void *data, int bits)
+{
+ mddev_t *mddev = data;
+ linear_conf_t *conf = mddev_to_conf(mddev);
+ int i, ret = 0;
+
+ for (i = 0; i < mddev->raid_disks && !ret ; i++) {
+ request_queue_t *q = bdev_get_queue(conf->disks[i].rdev->bdev);
+ ret |= bdi_congested(&q->backing_dev_info, bits);
+ }
+ return ret;
+}
+
+static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
{
linear_conf_t *conf;
- struct linear_hash *table;
+ dev_info_t **table;
mdk_rdev_t *rdev;
- int size, i, nb_zone, cnt;
- unsigned int curr_offset;
+ int i, nb_zone, cnt;
+ sector_t min_spacing;
+ sector_t curr_offset;
struct list_head *tmp;
- 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.
- */
+ mddev->private = conf;
- conf->smallest = NULL;
cnt = 0;
- mddev->array_size = 0;
+ conf->array_size = 0;
ITERATE_RDEV(mddev,rdev,tmp) {
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;
}
*/
if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
mddev->queue->max_sectors > (PAGE_SIZE>>9))
- 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;
+ conf->array_size += rdev->size;
- 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_spacing = conf->array_size;
+ sector_div(min_spacing, PAGE_SIZE/sizeof(struct dev_info *));
+
+ /* min_spacing 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_spacing as use the size of that as
+ * the actual spacing
+ */
+ conf->hash_spacing = conf->array_size;
+ for (i=0; i < cnt-1 ; i++) {
+ sector_t sz = 0;
+ int j;
+ for (j = i; j < cnt - 1 && sz < min_spacing; j++)
+ sz += conf->disks[j].size;
+ if (sz >= min_spacing && sz < conf->hash_spacing)
+ conf->hash_spacing = sz;
+ }
+
+ /* hash_spacing may be too large for sector_div to work with,
+ * so we might need to pre-shift
+ */
+ conf->preshift = 0;
+ if (sizeof(sector_t) > sizeof(u32)) {
+ sector_t space = conf->hash_spacing;
+ while (space > (sector_t)(~(u32)0)) {
+ space >>= 1;
+ conf->preshift++;
+ }
+ }
/*
* 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_size >> conf->preshift;
+ sz += 1; /* force round-up */
+ base = conf->hash_spacing >> conf->preshift;
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 (struct linear_hash) * 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].offset = 0;
+ for (i=1; i<mddev->raid_disks; i++)
+ conf->disks[i].offset =
+ conf->disks[i-1].offset +
+ conf->disks[i-1].size;
+
table = conf->hash_table;
- size = 0;
curr_offset = 0;
- for (i = 0; i < cnt; i++) {
- dev_info_t *disk = conf->disks + i;
+ i = 0;
+ for (curr_offset = 0;
+ curr_offset < conf->array_size;
+ curr_offset += conf->hash_spacing) {
- disk->offset = curr_offset;
- curr_offset += disk->size;
+ while (i < mddev->raid_disks-1 &&
+ curr_offset >= conf->disks[i+1].offset)
+ i++;
- if (size < 0) {
- table[-1].dev1 = disk;
- }
- size += disk->size;
+ *table ++ = conf->disks + i;
+ }
- while (size>0) {
- table->dev0 = disk;
- table->dev1 = NULL;
- size -= conf->smallest->size;
- table++;
- }
+ if (conf->preshift) {
+ conf->hash_spacing >>= conf->preshift;
+ /* round hash_spacing up so that when we divide by it,
+ * we err on the side of "too-low", which is safest.
+ */
+ conf->hash_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;
+
+ conf = linear_conf(mddev, mddev->raid_disks);
+
+ if (!conf)
+ return 1;
+ mddev->private = conf;
+ mddev->array_size = conf->array_size;
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:
- if (conf)
- 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->raid_disk != mddev->raid_disks)
+ return -EINVAL;
+
+ 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_size = newconf->array_size;
+ set_capacity(mddev->gendisk, mddev->array_size << 1);
+ return 0;
}
static int linear_stop (mddev_t *mddev)
{
linear_conf_t *conf = mddev_to_conf(mddev);
- kfree(conf->hash_table);
- kfree(conf);
+ 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);
return 0;
}
static int linear_make_request (request_queue_t *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));
+ if (unlikely(bio_barrier(bio))) {
+ bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+ return 0;
}
+ disk_stat_inc(mddev->gendisk, ios[rw]);
+ disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio));
+
tmp_dev = which_dev(mddev, bio->bi_sector);
block = bio->bi_sector >> 1;
-
- if (unlikely(!tmp_dev)) {
- printk("linear_make_request: hash->dev1==NULL for block %llu\n",
- (unsigned long long)block);
- bio_io_error(bio, bio->bi_size);
- return 0;
- }
if (unlikely(block >= (tmp_dev->size + tmp_dev->offset)
|| block < tmp_dev->offset)) {
char b[BDEVNAME_SIZE];
printk("linear_make_request: Block %llu out of bounds on "
- "dev %s size %ld offset %ld\n",
+ "dev %s size %llu offset %llu\n",
(unsigned long long)block,
bdevname(tmp_dev->rdev->bdev, b),
- tmp_dev->size, tmp_dev->offset);
+ (unsigned long long)tmp_dev->size,
+ (unsigned long long)tmp_dev->offset);
bio_io_error(bio, bio->bi_size);
return 0;
}
* split it.
*/
struct bio_pair *bp;
- bp = bio_split(bio, bio_split_pool,
- (bio->bi_sector + (bio->bi_size >> 9) -
- (tmp_dev->offset + tmp_dev->size))<<1);
+ bp = bio_split(bio, bio_split_pool,
+ ((tmp_dev->offset + tmp_dev->size)<<1) - bio->bi_sector);
if (linear_make_request(q, &bp->bio1))
generic_make_request(&bp->bio1);
if (linear_make_request(q, &bp->bio2))
#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++)
+ for (j = 0; j < mddev->raid_disks; j++)
{
char b[BDEVNAME_SIZE];
+ s += conf->smallest_size;
seq_printf(seq, "[%s",
- bdevname(conf->hash_table[j].dev0->rdev->bdev,b));
+ bdevname(conf->hash_table[j][0].rdev->bdev,b));
- if (conf->hash_table[j].dev1)
+ while (s > conf->hash_table[j][0].offset +
+ conf->hash_table[j][0].size)
seq_printf(seq, "/%s] ",
- bdevname(conf->hash_table[j].dev1->rdev->bdev,b));
+ bdevname(conf->hash_table[j][1].rdev->bdev,b));
else
seq_printf(seq, "] ");
}
}
-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://git.onelab.eu / linux-2.6.git / blobdiff