summaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bitmap.c12
-rw-r--r--drivers/md/dm.c27
-rw-r--r--drivers/md/md.c45
-rw-r--r--drivers/md/raid1.c20
-rw-r--r--drivers/md/raid10.c11
-rw-r--r--drivers/md/raid5.c5
6 files changed, 94 insertions, 26 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 5432d07c074..11108165e26 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -479,9 +479,12 @@ static int bitmap_read_sb(struct bitmap *bitmap)
int err = -EINVAL;
/* page 0 is the superblock, read it... */
- if (bitmap->file)
- bitmap->sb_page = read_page(bitmap->file, 0, bitmap, PAGE_SIZE);
- else {
+ if (bitmap->file) {
+ loff_t isize = i_size_read(bitmap->file->f_mapping->host);
+ int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;
+
+ bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes);
+ } else {
bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, 0);
}
if (IS_ERR(bitmap->sb_page)) {
@@ -877,7 +880,8 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
int count;
/* unmap the old page, we're done with it */
if (index == num_pages-1)
- count = bytes - index * PAGE_SIZE;
+ count = bytes + sizeof(bitmap_super_t)
+ - index * PAGE_SIZE;
else
count = PAGE_SIZE;
if (index == 0) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index fe7c56e1043..3668b170ea6 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1116,7 +1116,8 @@ static int __bind(struct mapped_device *md, struct dm_table *t)
if (size != get_capacity(md->disk))
memset(&md->geometry, 0, sizeof(md->geometry));
- __set_size(md, size);
+ if (md->suspended_bdev)
+ __set_size(md, size);
if (size == 0)
return 0;
@@ -1264,6 +1265,11 @@ int dm_swap_table(struct mapped_device *md, struct dm_table *table)
if (!dm_suspended(md))
goto out;
+ /* without bdev, the device size cannot be changed */
+ if (!md->suspended_bdev)
+ if (get_capacity(md->disk) != dm_table_get_size(table))
+ goto out;
+
__unbind(md);
r = __bind(md, table);
@@ -1341,11 +1347,14 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
/* This does not get reverted if there's an error later. */
dm_table_presuspend_targets(map);
- md->suspended_bdev = bdget_disk(md->disk, 0);
- if (!md->suspended_bdev) {
- DMWARN("bdget failed in dm_suspend");
- r = -ENOMEM;
- goto flush_and_out;
+ /* bdget() can stall if the pending I/Os are not flushed */
+ if (!noflush) {
+ md->suspended_bdev = bdget_disk(md->disk, 0);
+ if (!md->suspended_bdev) {
+ DMWARN("bdget failed in dm_suspend");
+ r = -ENOMEM;
+ goto flush_and_out;
+ }
}
/*
@@ -1473,8 +1482,10 @@ int dm_resume(struct mapped_device *md)
unlock_fs(md);
- bdput(md->suspended_bdev);
- md->suspended_bdev = NULL;
+ if (md->suspended_bdev) {
+ bdput(md->suspended_bdev);
+ md->suspended_bdev = NULL;
+ }
clear_bit(DMF_SUSPENDED, &md->flags);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 21e2a7b0884..e8807ea5377 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1633,7 +1633,8 @@ repeat:
* and 'events' is odd, we can roll back to the previous clean state */
if (nospares
&& (mddev->in_sync && mddev->recovery_cp == MaxSector)
- && (mddev->events & 1))
+ && (mddev->events & 1)
+ && mddev->events != 1)
mddev->events--;
else {
/* otherwise we have to go forward and ... */
@@ -1792,7 +1793,8 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
else {
mddev_t *mddev = rdev->mddev;
kick_rdev_from_array(rdev);
- md_update_sb(mddev, 1);
+ if (mddev->pers)
+ md_update_sb(mddev, 1);
md_new_event(mddev);
err = 0;
}
@@ -2004,6 +2006,7 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
rdev->desc_nr = -1;
rdev->saved_raid_disk = -1;
+ rdev->raid_disk = -1;
rdev->flags = 0;
rdev->data_offset = 0;
rdev->sb_events = 0;
@@ -2233,7 +2236,6 @@ static int update_raid_disks(mddev_t *mddev, int raid_disks);
static ssize_t
raid_disks_store(mddev_t *mddev, const char *buf, size_t len)
{
- /* can only set raid_disks if array is not yet active */
char *e;
int rv = 0;
unsigned long n = simple_strtoul(buf, &e, 10);
@@ -2631,7 +2633,7 @@ metadata_store(mddev_t *mddev, const char *buf, size_t len)
return -EINVAL;
buf = e+1;
minor = simple_strtoul(buf, &e, 10);
- if (e==buf || *e != '\n')
+ if (e==buf || (*e && *e != '\n') )
return -EINVAL;
if (major >= sizeof(super_types)/sizeof(super_types[0]) ||
super_types[major].name == NULL)
@@ -3562,6 +3564,8 @@ static int get_bitmap_file(mddev_t * mddev, void __user * arg)
char *ptr, *buf = NULL;
int err = -ENOMEM;
+ md_allow_write(mddev);
+
file = kmalloc(sizeof(*file), GFP_KERNEL);
if (!file)
goto out;
@@ -3980,6 +3984,7 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
mddev->major_version = info->major_version;
mddev->minor_version = info->minor_version;
mddev->patch_version = info->patch_version;
+ mddev->persistent = !info->not_persistent;
return 0;
}
mddev->major_version = MD_MAJOR_VERSION;
@@ -4304,9 +4309,10 @@ static int md_ioctl(struct inode *inode, struct file *file,
* Commands querying/configuring an existing array:
*/
/* if we are not initialised yet, only ADD_NEW_DISK, STOP_ARRAY,
- * RUN_ARRAY, and SET_BITMAP_FILE are allowed */
+ * RUN_ARRAY, and GET_ and SET_BITMAP_FILE are allowed */
if (!mddev->raid_disks && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY
- && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE) {
+ && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE
+ && cmd != GET_BITMAP_FILE) {
err = -ENODEV;
goto abort_unlock;
}
@@ -5028,6 +5034,33 @@ void md_write_end(mddev_t *mddev)
}
}
+/* md_allow_write(mddev)
+ * Calling this ensures that the array is marked 'active' so that writes
+ * may proceed without blocking. It is important to call this before
+ * attempting a GFP_KERNEL allocation while holding the mddev lock.
+ * Must be called with mddev_lock held.
+ */
+void md_allow_write(mddev_t *mddev)
+{
+ if (!mddev->pers)
+ return;
+ if (mddev->ro)
+ return;
+
+ spin_lock_irq(&mddev->write_lock);
+ if (mddev->in_sync) {
+ mddev->in_sync = 0;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->safemode_delay &&
+ mddev->safemode == 0)
+ mddev->safemode = 1;
+ spin_unlock_irq(&mddev->write_lock);
+ md_update_sb(mddev, 0);
+ } else
+ spin_unlock_irq(&mddev->write_lock);
+}
+EXPORT_SYMBOL_GPL(md_allow_write);
+
static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
#define SYNC_MARKS 10
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index b30f74be398..97ee870b265 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -775,6 +775,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
struct bio_list bl;
struct page **behind_pages = NULL;
const int rw = bio_data_dir(bio);
+ const int do_sync = bio_sync(bio);
int do_barriers;
/*
@@ -835,7 +836,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
read_bio->bi_bdev = mirror->rdev->bdev;
read_bio->bi_end_io = raid1_end_read_request;
- read_bio->bi_rw = READ;
+ read_bio->bi_rw = READ | do_sync;
read_bio->bi_private = r1_bio;
generic_make_request(read_bio);
@@ -906,7 +907,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset;
mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
mbio->bi_end_io = raid1_end_write_request;
- mbio->bi_rw = WRITE | do_barriers;
+ mbio->bi_rw = WRITE | do_barriers | do_sync;
mbio->bi_private = r1_bio;
if (behind_pages) {
@@ -941,6 +942,8 @@ static int make_request(request_queue_t *q, struct bio * bio)
blk_plug_device(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
+ if (do_sync)
+ md_wakeup_thread(mddev->thread);
#if 0
while ((bio = bio_list_pop(&bl)) != NULL)
generic_make_request(bio);
@@ -1263,6 +1266,11 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
sbio->bi_sector = r1_bio->sector +
conf->mirrors[i].rdev->data_offset;
sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
+ for (j = 0; j < vcnt ; j++)
+ memcpy(page_address(sbio->bi_io_vec[j].bv_page),
+ page_address(pbio->bi_io_vec[j].bv_page),
+ PAGE_SIZE);
+
}
}
}
@@ -1541,6 +1549,7 @@ static void raid1d(mddev_t *mddev)
* We already have a nr_pending reference on these rdevs.
*/
int i;
+ const int do_sync = bio_sync(r1_bio->master_bio);
clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
clear_bit(R1BIO_Barrier, &r1_bio->state);
for (i=0; i < conf->raid_disks; i++)
@@ -1561,7 +1570,7 @@ static void raid1d(mddev_t *mddev)
conf->mirrors[i].rdev->data_offset;
bio->bi_bdev = conf->mirrors[i].rdev->bdev;
bio->bi_end_io = raid1_end_write_request;
- bio->bi_rw = WRITE;
+ bio->bi_rw = WRITE | do_sync;
bio->bi_private = r1_bio;
r1_bio->bios[i] = bio;
generic_make_request(bio);
@@ -1593,6 +1602,7 @@ static void raid1d(mddev_t *mddev)
(unsigned long long)r1_bio->sector);
raid_end_bio_io(r1_bio);
} else {
+ const int do_sync = bio_sync(r1_bio->master_bio);
r1_bio->bios[r1_bio->read_disk] =
mddev->ro ? IO_BLOCKED : NULL;
r1_bio->read_disk = disk;
@@ -1608,7 +1618,7 @@ static void raid1d(mddev_t *mddev)
bio->bi_sector = r1_bio->sector + rdev->data_offset;
bio->bi_bdev = rdev->bdev;
bio->bi_end_io = raid1_end_read_request;
- bio->bi_rw = READ;
+ bio->bi_rw = READ | do_sync;
bio->bi_private = r1_bio;
unplug = 1;
generic_make_request(bio);
@@ -2094,6 +2104,8 @@ static int raid1_reshape(mddev_t *mddev)
return -EINVAL;
}
+ md_allow_write(mddev);
+
raid_disks = mddev->raid_disks + mddev->delta_disks;
if (raid_disks < conf->raid_disks) {
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index f0141910bb8..a9401c017e3 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -782,6 +782,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
int i;
int chunk_sects = conf->chunk_mask + 1;
const int rw = bio_data_dir(bio);
+ const int do_sync = bio_sync(bio);
struct bio_list bl;
unsigned long flags;
@@ -863,7 +864,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
mirror->rdev->data_offset;
read_bio->bi_bdev = mirror->rdev->bdev;
read_bio->bi_end_io = raid10_end_read_request;
- read_bio->bi_rw = READ;
+ read_bio->bi_rw = READ | do_sync;
read_bio->bi_private = r10_bio;
generic_make_request(read_bio);
@@ -909,7 +910,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
conf->mirrors[d].rdev->data_offset;
mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE;
+ mbio->bi_rw = WRITE | do_sync;
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
@@ -922,6 +923,9 @@ static int make_request(request_queue_t *q, struct bio * bio)
blk_plug_device(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
+ if (do_sync)
+ md_wakeup_thread(mddev->thread);
+
return 0;
}
@@ -1563,6 +1567,7 @@ static void raid10d(mddev_t *mddev)
(unsigned long long)r10_bio->sector);
raid_end_bio_io(r10_bio);
} else {
+ const int do_sync = bio_sync(r10_bio->master_bio);
rdev = conf->mirrors[mirror].rdev;
if (printk_ratelimit())
printk(KERN_ERR "raid10: %s: redirecting sector %llu to"
@@ -1574,7 +1579,7 @@ static void raid10d(mddev_t *mddev)
bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr
+ rdev->data_offset;
bio->bi_bdev = rdev->bdev;
- bio->bi_rw = READ;
+ bio->bi_rw = READ | do_sync;
bio->bi_private = r10_bio;
bio->bi_end_io = raid10_end_read_request;
unplug = 1;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index be008f034ad..467c16982d0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -405,6 +405,8 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
if (newsize <= conf->pool_size)
return 0; /* never bother to shrink */
+ md_allow_write(conf->mddev);
+
/* Step 1 */
sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev),
@@ -2678,7 +2680,7 @@ static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio)
mdk_rdev_t *rdev;
if (!in_chunk_boundary(mddev, raid_bio)) {
- printk("chunk_aligned_read : non aligned\n");
+ PRINTK("chunk_aligned_read : non aligned\n");
return 0;
}
/*
@@ -3250,6 +3252,7 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
else
break;
}
+ md_allow_write(mddev);
while (new > conf->max_nr_stripes) {
if (grow_one_stripe(conf))
conf->max_nr_stripes++;