aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm-log-userspace-transfer.c10
-rw-r--r--drivers/md/dm-raid1.c2
-rw-r--r--drivers/md/dm-region-hash.c5
-rw-r--r--drivers/md/dm-snap-persistent.c2
-rw-r--r--drivers/md/dm-stripe.c2
-rw-r--r--drivers/md/dm-sysfs.c8
-rw-r--r--drivers/md/dm-table.c20
-rw-r--r--drivers/md/dm.c21
-rw-r--r--drivers/md/md.c56
-rw-r--r--drivers/md/raid5.c14
10 files changed, 58 insertions, 82 deletions
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 54abf9e..f1c8cae 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -172,11 +172,15 @@ int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type,
{
int r = 0;
size_t dummy = 0;
- int overhead_size =
- sizeof(struct dm_ulog_request *) + sizeof(struct cn_msg);
+ int overhead_size = sizeof(struct dm_ulog_request) + sizeof(struct cn_msg);
struct dm_ulog_request *tfr = prealloced_ulog_tfr;
struct receiving_pkg pkg;
+ /*
+ * Given the space needed to hold the 'struct cn_msg' and
+ * 'struct dm_ulog_request' - do we have enough payload
+ * space remaining?
+ */
if (data_size > (DM_ULOG_PREALLOCED_SIZE - overhead_size)) {
DMINFO("Size of tfr exceeds preallocated size");
return -EINVAL;
@@ -191,7 +195,7 @@ resend:
*/
mutex_lock(&dm_ulog_lock);
- memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - overhead_size);
+ memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - sizeof(struct cn_msg));
memcpy(tfr->uuid, uuid, DM_UUID_LEN);
tfr->luid = luid;
tfr->seq = dm_ulog_seq++;
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index ad779bd..6c1046d 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -724,7 +724,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
/*
* Dispatch io.
*/
- if (unlikely(ms->log_failure)) {
+ if (unlikely(ms->log_failure) && errors_handled(ms)) {
spin_lock_irq(&ms->lock);
bio_list_merge(&ms->failures, &sync);
spin_unlock_irq(&ms->lock);
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index 5f19ceb..168bd38 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -660,10 +660,9 @@ void dm_rh_recovery_end(struct dm_region *reg, int success)
spin_lock_irq(&rh->region_lock);
if (success)
list_add(&reg->list, &reg->rh->recovered_regions);
- else {
- reg->state = DM_RH_NOSYNC;
+ else
list_add(&reg->list, &reg->rh->failed_recovered_regions);
- }
+
spin_unlock_irq(&rh->region_lock);
rh->wakeup_workers(rh->context);
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 7d08879..c097d8a 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -254,7 +254,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
* Issue the synchronous I/O from a different thread
* to avoid generic_make_request recursion.
*/
- INIT_WORK(&req.work, do_metadata);
+ INIT_WORK_ON_STACK(&req.work, do_metadata);
queue_work(ps->metadata_wq, &req.work);
flush_workqueue(ps->metadata_wq);
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index e0efc1a..bd58703 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -110,7 +110,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
}
stripes = simple_strtoul(argv[0], &end, 10);
- if (*end) {
+ if (!stripes || *end) {
ti->error = "Invalid stripe count";
return -EINVAL;
}
diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c
index f53392d..f91b409 100644
--- a/drivers/md/dm-sysfs.c
+++ b/drivers/md/dm-sysfs.c
@@ -80,20 +80,12 @@ static struct sysfs_ops dm_sysfs_ops = {
};
/*
- * The sysfs structure is embedded in md struct, nothing to do here
- */
-static void dm_sysfs_release(struct kobject *kobj)
-{
-}
-
-/*
* dm kobject is embedded in mapped_device structure
* no need to define release function here
*/
static struct kobj_type dm_ktype = {
.sysfs_ops = &dm_sysfs_ops,
.default_attrs = dm_attrs,
- .release = dm_sysfs_release
};
/*
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index be62547..4b22feb 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -503,16 +503,15 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
return 0;
}
- if (blk_stack_limits(limits, &q->limits, start << 9) < 0)
- DMWARN("%s: target device %s is misaligned: "
+ if (bdev_stack_limits(limits, bdev, start) < 0)
+ DMWARN("%s: adding target device %s caused an alignment inconsistency: "
"physical_block_size=%u, logical_block_size=%u, "
"alignment_offset=%u, start=%llu",
dm_device_name(ti->table->md), bdevname(bdev, b),
q->limits.physical_block_size,
q->limits.logical_block_size,
q->limits.alignment_offset,
- (unsigned long long) start << 9);
-
+ (unsigned long long) start << SECTOR_SHIFT);
/*
* Check if merge fn is supported.
@@ -1026,9 +1025,9 @@ combine_limits:
* for the table.
*/
if (blk_stack_limits(limits, &ti_limits, 0) < 0)
- DMWARN("%s: target device "
+ DMWARN("%s: adding target device "
"(start sect %llu len %llu) "
- "is misaligned",
+ "caused an alignment inconsistency",
dm_device_name(table->md),
(unsigned long long) ti->begin,
(unsigned long long) ti->len);
@@ -1080,15 +1079,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
struct queue_limits *limits)
{
/*
- * Each target device in the table has a data area that should normally
- * be aligned such that the DM device's alignment_offset is 0.
- * FIXME: Propagate alignment_offsets up the stack and warn of
- * sub-optimal or inconsistent settings.
- */
- limits->alignment_offset = 0;
- limits->misaligned = 0;
-
- /*
* Copy table's limits to the DM device's request_queue
*/
q->limits = *limits;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3167480..aa4e2aa 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1595,10 +1595,15 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq)
return BLKPREP_OK;
}
-static void map_request(struct dm_target *ti, struct request *clone,
- struct mapped_device *md)
+/*
+ * Returns:
+ * 0 : the request has been processed (not requeued)
+ * !0 : the request has been requeued
+ */
+static int map_request(struct dm_target *ti, struct request *clone,
+ struct mapped_device *md)
{
- int r;
+ int r, requeued = 0;
struct dm_rq_target_io *tio = clone->end_io_data;
/*
@@ -1625,6 +1630,7 @@ static void map_request(struct dm_target *ti, struct request *clone,
case DM_MAPIO_REQUEUE:
/* The target wants to requeue the I/O */
dm_requeue_unmapped_request(clone);
+ requeued = 1;
break;
default:
if (r > 0) {
@@ -1636,6 +1642,8 @@ static void map_request(struct dm_target *ti, struct request *clone,
dm_kill_unmapped_request(clone, r);
break;
}
+
+ return requeued;
}
/*
@@ -1677,12 +1685,17 @@ static void dm_request_fn(struct request_queue *q)
atomic_inc(&md->pending[rq_data_dir(clone)]);
spin_unlock(q->queue_lock);
- map_request(ti, clone, md);
+ if (map_request(ti, clone, md))
+ goto requeued;
+
spin_lock_irq(q->queue_lock);
}
goto out;
+requeued:
+ spin_lock_irq(q->queue_lock);
+
plug_and_out:
if (!elv_queue_empty(q))
/* Some requests still remain, retry later */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f4f5f82..a20a71e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -386,7 +386,9 @@ static void mddev_put(mddev_t *mddev)
if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
return;
if (!mddev->raid_disks && list_empty(&mddev->disks) &&
- !mddev->hold_active) {
+ mddev->ctime == 0 && !mddev->hold_active) {
+ /* Array is not configured at all, and not held active,
+ * so destroy it */
list_del(&mddev->all_mddevs);
if (mddev->gendisk) {
/* we did a probe so need to clean up.
@@ -4073,8 +4075,10 @@ static void mddev_delayed_delete(struct work_struct *ws)
{
mddev_t *mddev = container_of(ws, mddev_t, del_work);
- if (mddev->private == &md_redundancy_group) {
+ if (mddev->private) {
sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+ if (mddev->private != (void*)1)
+ sysfs_remove_group(&mddev->kobj, mddev->private);
if (mddev->sysfs_action)
sysfs_put(mddev->sysfs_action);
mddev->sysfs_action = NULL;
@@ -4285,10 +4289,7 @@ static int do_md_run(mddev_t * mddev)
sysfs_notify_dirent(rdev->sysfs_state);
}
- md_probe(mddev->unit, NULL, NULL);
disk = mddev->gendisk;
- if (!disk)
- return -ENOMEM;
spin_lock(&pers_lock);
pers = find_pers(mddev->level, mddev->clevel);
@@ -4355,7 +4356,7 @@ static int do_md_run(mddev_t * mddev)
mddev->barriers_work = 1;
mddev->ok_start_degraded = start_dirty_degraded;
- if (start_readonly)
+ if (start_readonly && mddev->ro == 0)
mddev->ro = 2; /* read-only, but switch on first write */
err = mddev->pers->run(mddev);
@@ -4419,33 +4420,6 @@ static int do_md_run(mddev_t * mddev)
set_capacity(disk, mddev->array_sectors);
- /* If there is a partially-recovered drive we need to
- * start recovery here. If we leave it to md_check_recovery,
- * it will remove the drives and not do the right thing
- */
- if (mddev->degraded && !mddev->sync_thread) {
- int spares = 0;
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (rdev->raid_disk >= 0 &&
- !test_bit(In_sync, &rdev->flags) &&
- !test_bit(Faulty, &rdev->flags))
- /* complete an interrupted recovery */
- spares++;
- if (spares && mddev->pers->sync_request) {
- mddev->recovery = 0;
- set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
- mddev->sync_thread = md_register_thread(md_do_sync,
- mddev,
- "resync");
- if (!mddev->sync_thread) {
- printk(KERN_ERR "%s: could not start resync"
- " thread...\n",
- mdname(mddev));
- /* leave the spares where they are, it shouldn't hurt */
- mddev->recovery = 0;
- }
- }
- }
md_wakeup_thread(mddev->thread);
md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
@@ -4555,8 +4529,8 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
mddev->queue->unplug_fn = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
module_put(mddev->pers->owner);
- if (mddev->pers->sync_request)
- mddev->private = &md_redundancy_group;
+ if (mddev->pers->sync_request && mddev->private == NULL)
+ mddev->private = (void*)1;
mddev->pers = NULL;
/* tell userspace to handle 'inactive' */
sysfs_notify_dirent(mddev->sysfs_state);
@@ -4603,9 +4577,6 @@ out:
}
mddev->bitmap_info.offset = 0;
- /* make sure all md_delayed_delete calls have finished */
- flush_scheduled_work();
-
export_array(mddev);
mddev->array_sectors = 0;
@@ -5262,6 +5233,10 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
mddev->minor_version = info->minor_version;
mddev->patch_version = info->patch_version;
mddev->persistent = !info->not_persistent;
+ /* ensure mddev_put doesn't delete this now that there
+ * is some minimal configuration.
+ */
+ mddev->ctime = get_seconds();
return 0;
}
mddev->major_version = MD_MAJOR_VERSION;
@@ -6494,10 +6469,11 @@ void md_do_sync(mddev_t *mddev)
mddev->curr_resync = 2;
try_again:
- if (kthread_should_stop()) {
+ if (kthread_should_stop())
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+
+ if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
goto skip;
- }
for_each_mddev(mddev2, tmp) {
if (mddev2 == mddev)
continue;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e84204e..ceb24af 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5136,9 +5136,8 @@ static int stop(mddev_t *mddev)
mddev->thread = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
- sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
free_conf(conf);
- mddev->private = NULL;
+ mddev->private = &raid5_attrs_group;
return 0;
}
@@ -5464,11 +5463,11 @@ static int raid5_start_reshape(mddev_t *mddev)
!test_bit(Faulty, &rdev->flags)) {
if (raid5_add_disk(mddev, rdev) == 0) {
char nm[20];
- if (rdev->raid_disk >= conf->previous_raid_disks)
+ if (rdev->raid_disk >= conf->previous_raid_disks) {
set_bit(In_sync, &rdev->flags);
- else
+ added_devices++;
+ } else
rdev->recovery_offset = 0;
- added_devices++;
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj,
&rdev->kobj, nm))
@@ -5480,9 +5479,12 @@ static int raid5_start_reshape(mddev_t *mddev)
break;
}
+ /* When a reshape changes the number of devices, ->degraded
+ * is measured against the large of the pre and post number of
+ * devices.*/
if (mddev->delta_disks > 0) {
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = (conf->raid_disks - conf->previous_raid_disks)
+ mddev->degraded += (conf->raid_disks - conf->previous_raid_disks)
- added_devices;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
generated by cgit v1.1 at 2024-09-22 00:40:02 +0000