#define STRIPE_SHIFT (PAGE_SHIFT - 9)
#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#define IO_THRESHOLD 1
-#define HASH_PAGES 1
-#define HASH_PAGES_ORDER 0
-#define NR_HASH (HASH_PAGES * PAGE_SIZE / sizeof(struct stripe_head *))
+#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
-#define stripe_hash(conf, sect) ((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK])
+#define stripe_hash(conf, sect) (&((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK]))
/* bio's attached to a stripe+device for I/O are linked together in bi_sector
* order without overlap. There may be several bio's per stripe+device, and
static void print_raid5_conf (raid5_conf_t *conf);
-static inline void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
+static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count)) {
if (!list_empty(&sh->lru))
spin_unlock_irqrestore(&conf->device_lock, flags);
}
-static void remove_hash(struct stripe_head *sh)
+static inline void remove_hash(struct stripe_head *sh)
{
PRINTK("remove_hash(), stripe %llu\n", (unsigned long long)sh->sector);
- if (sh->hash_pprev) {
- if (sh->hash_next)
- sh->hash_next->hash_pprev = sh->hash_pprev;
- *sh->hash_pprev = sh->hash_next;
- sh->hash_pprev = NULL;
- }
+ hlist_del_init(&sh->hash);
}
-static __inline__ void insert_hash(raid5_conf_t *conf, struct stripe_head *sh)
+static void insert_hash(raid5_conf_t *conf, struct stripe_head *sh)
{
- struct stripe_head **shp = &stripe_hash(conf, sh->sector);
+ struct hlist_head *hp = stripe_hash(conf, sh->sector);
PRINTK("insert_hash(), stripe %llu\n", (unsigned long long)sh->sector);
CHECK_DEVLOCK();
- if ((sh->hash_next = *shp) != NULL)
- (*shp)->hash_pprev = &sh->hash_next;
- *shp = sh;
- sh->hash_pprev = shp;
+ hlist_add_head(&sh->hash, hp);
}
if (!p)
continue;
sh->dev[i].page = NULL;
- page_cache_release(p);
+ put_page(p);
}
}
static void raid5_build_block (struct stripe_head *sh, int i);
-static inline void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
+static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
{
raid5_conf_t *conf = sh->raid_conf;
int disks = conf->raid_disks, i;
static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector)
{
struct stripe_head *sh;
+ struct hlist_node *hn;
CHECK_DEVLOCK();
PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector);
- for (sh = stripe_hash(conf, sector); sh; sh = sh->hash_next)
+ hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
if (sh->sector == sector)
return sh;
PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector);
while (drop_one_stripe(conf))
;
- kmem_cache_destroy(conf->slab_cache);
+ if (conf->slab_cache)
+ kmem_cache_destroy(conf->slab_cache);
conf->slab_cache = NULL;
}
syncing = test_bit(STRIPE_SYNCING, &sh->state);
/* Now to look around and see what can be done */
+ rcu_read_lock();
for (i=disks; i--; ) {
mdk_rdev_t *rdev;
dev = &sh->dev[i];
clear_bit(R5_Insync, &dev->flags);
- clear_bit(R5_Syncio, &dev->flags);
PRINTK("check %d: state 0x%lx read %p write %p written %p\n",
i, dev->flags, dev->toread, dev->towrite, dev->written);
non_overwrite++;
}
if (dev->written) written++;
- rdev = conf->disks[i].rdev; /* FIXME, should I be looking rdev */
+ rdev = rcu_dereference(conf->disks[i].rdev);
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
} else
set_bit(R5_Insync, &dev->flags);
}
+ rcu_read_unlock();
PRINTK("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d\n",
locked, uptodate, to_read, to_write, failed, failed_num);
int bitmap_end = 0;
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
- mdk_rdev_t *rdev = conf->disks[i].rdev;
+ mdk_rdev_t *rdev;
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && test_bit(In_sync, &rdev->flags))
/* multiple read failures in one stripe */
md_error(conf->mddev, rdev);
+ rcu_read_unlock();
}
spin_lock_irq(&conf->device_lock);
locked++;
PRINTK("Reading block %d (sync=%d)\n",
i, syncing);
- if (syncing)
- md_sync_acct(conf->disks[i].rdev->bdev,
- STRIPE_SECTORS);
}
}
}
clear_bit(STRIPE_DEGRADED, &sh->state);
locked++;
set_bit(STRIPE_INSYNC, &sh->state);
- set_bit(R5_Syncio, &dev->flags);
}
}
if (syncing && locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
rcu_read_unlock();
if (rdev) {
- if (test_bit(R5_Syncio, &sh->dev[i].flags))
+ if (syncing)
md_sync_acct(rdev->bdev, STRIPE_SECTORS);
bi->bi_bdev = rdev->bdev;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
bi->bi_next = NULL;
+ if (rw == WRITE &&
+ test_bit(R5_ReWrite, &sh->dev[i].flags))
+ atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
generic_make_request(bi);
} else {
if (rw == 1)
}
}
-static inline void raid5_activate_delayed(raid5_conf_t *conf)
+static void raid5_activate_delayed(raid5_conf_t *conf)
{
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
while (!list_empty(&conf->delayed_list)) {
}
}
-static inline void activate_bit_delay(raid5_conf_t *conf)
+static void activate_bit_delay(raid5_conf_t *conf)
{
/* device_lock is held */
struct list_head head;
return -EIO;
}
- mddev->private = kmalloc (sizeof (raid5_conf_t)
- + mddev->raid_disks * sizeof(struct disk_info),
- GFP_KERNEL);
+ mddev->private = kzalloc(sizeof (raid5_conf_t)
+ + mddev->raid_disks * sizeof(struct disk_info),
+ GFP_KERNEL);
if ((conf = mddev->private) == NULL)
goto abort;
- memset (conf, 0, sizeof (*conf) + mddev->raid_disks * sizeof(struct disk_info) );
+
conf->mddev = mddev;
- if ((conf->stripe_hashtbl = (struct stripe_head **) __get_free_pages(GFP_ATOMIC, HASH_PAGES_ORDER)) == NULL)
+ if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
goto abort;
- memset(conf->stripe_hashtbl, 0, HASH_PAGES * PAGE_SIZE);
spin_lock_init(&conf->device_lock);
init_waitqueue_head(&conf->wait_for_stripe);
*/
{
int stripe = (mddev->raid_disks-1) * mddev->chunk_size
- / PAGE_CACHE_SIZE;
+ / PAGE_SIZE;
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
}
/* Ok, everything is just fine now */
sysfs_create_group(&mddev->kobj, &raid5_attrs_group);
- if (mddev->bitmap)
- mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
-
mddev->queue->unplug_fn = raid5_unplug_device;
mddev->queue->issue_flush_fn = raid5_issue_flush;
abort:
if (conf) {
print_raid5_conf(conf);
- if (conf->stripe_hashtbl)
- free_pages((unsigned long) conf->stripe_hashtbl,
- HASH_PAGES_ORDER);
+ kfree(conf->stripe_hashtbl);
kfree(conf);
}
mddev->private = NULL;
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
shrink_stripes(conf);
- free_pages((unsigned long) conf->stripe_hashtbl, HASH_PAGES_ORDER);
+ kfree(conf->stripe_hashtbl);
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
kfree(conf);
static void printall (raid5_conf_t *conf)
{
struct stripe_head *sh;
+ struct hlist_node *hn;
int i;
spin_lock_irq(&conf->device_lock);
for (i = 0; i < NR_HASH; i++) {
- sh = conf->stripe_hashtbl[i];
- for (; sh; sh = sh->hash_next) {
+ hlist_for_each_entry(sh, hn, &conf->stripe_hashtbl[i], hash) {
if (sh->raid_conf != conf)
continue;
print_sh(sh);
spin_unlock_irq(&conf->device_lock);
break;
}
- if (mddev->thread) {
- if (mddev->bitmap)
- mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
- else
- mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
- md_wakeup_thread(mddev->thread);
- }
}
-static mdk_personality_t raid5_personality=
+
+static struct mdk_personality raid5_personality =
{
.name = "raid5",
+ .level = 5,
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
.quiesce = raid5_quiesce,
};
-static int __init raid5_init (void)
+static struct mdk_personality raid4_personality =
{
- return register_md_personality (RAID5, &raid5_personality);
+ .name = "raid4",
+ .level = 4,
+ .owner = THIS_MODULE,
+ .make_request = make_request,
+ .run = run,
+ .stop = stop,
+ .status = status,
+ .error_handler = error,
+ .hot_add_disk = raid5_add_disk,
+ .hot_remove_disk= raid5_remove_disk,
+ .spare_active = raid5_spare_active,
+ .sync_request = sync_request,
+ .resize = raid5_resize,
+ .quiesce = raid5_quiesce,
+};
+
+static int __init raid5_init(void)
+{
+ register_md_personality(&raid5_personality);
+ register_md_personality(&raid4_personality);
+ return 0;
}
-static void raid5_exit (void)
+static void raid5_exit(void)
{
- unregister_md_personality (RAID5);
+ unregister_md_personality(&raid5_personality);
+ unregister_md_personality(&raid4_personality);
}
module_init(raid5_init);
module_exit(raid5_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-4"); /* RAID5 */
+MODULE_ALIAS("md-raid5");
+MODULE_ALIAS("md-raid4");
+MODULE_ALIAS("md-level-5");
+MODULE_ALIAS("md-level-4");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff