summaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm.c8
-rw-r--r--drivers/md/faulty.c5
-rw-r--r--drivers/md/md.c287
-rw-r--r--drivers/md/md.h28
-rw-r--r--drivers/md/persistent-data/dm-block-manager.c4
-rw-r--r--drivers/md/persistent-data/dm-btree.h2
-rw-r--r--drivers/md/raid1.c19
-rw-r--r--drivers/md/raid10.c163
-rw-r--r--drivers/md/raid5.c136
9 files changed, 351 insertions, 301 deletions
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 02db9183ca0..77e6eff41ca 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -740,8 +740,14 @@ static void rq_completed(struct mapped_device *md, int rw, int run_queue)
if (!md_in_flight(md))
wake_up(&md->wait);
+ /*
+ * Run this off this callpath, as drivers could invoke end_io while
+ * inside their request_fn (and holding the queue lock). Calling
+ * back into ->request_fn() could deadlock attempting to grab the
+ * queue lock again.
+ */
if (run_queue)
- blk_run_queue(md->queue);
+ blk_run_queue_async(md->queue);
/*
* dm_put() must be at the end of this function. See the comment above
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index 45135f69509..5e7dc772f5d 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -315,8 +315,11 @@ static int run(struct mddev *mddev)
}
conf->nfaults = 0;
- rdev_for_each(rdev, mddev)
+ rdev_for_each(rdev, mddev) {
conf->rdev = rdev;
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
+ }
md_set_array_sectors(mddev, faulty_size(mddev, 0, 0));
mddev->private = conf;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9ab768acfb6..3db3d1b271f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -452,7 +452,7 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
spin_lock_irq(&mddev->write_lock);
wait_event_lock_irq(mddev->sb_wait,
!mddev->flush_bio,
- mddev->write_lock, /*nothing*/);
+ mddev->write_lock);
mddev->flush_bio = bio;
spin_unlock_irq(&mddev->write_lock);
@@ -1414,12 +1414,11 @@ static __le32 calc_sb_1_csum(struct mdp_superblock_1 * sb)
unsigned long long newcsum;
int size = 256 + le32_to_cpu(sb->max_dev)*2;
__le32 *isuper = (__le32*)sb;
- int i;
disk_csum = sb->sb_csum;
sb->sb_csum = 0;
newcsum = 0;
- for (i=0; size>=4; size -= 4 )
+ for (; size >= 4; size -= 4)
newcsum += le32_to_cpu(*isuper++);
if (size == 2)
@@ -1817,10 +1816,10 @@ retry:
memset(bbp, 0xff, PAGE_SIZE);
for (i = 0 ; i < bb->count ; i++) {
- u64 internal_bb = *p++;
+ u64 internal_bb = p[i];
u64 store_bb = ((BB_OFFSET(internal_bb) << 10)
| BB_LEN(internal_bb));
- *bbp++ = cpu_to_le64(store_bb);
+ bbp[i] = cpu_to_le64(store_bb);
}
bb->changed = 0;
if (read_seqretry(&bb->lock, seq))
@@ -4124,7 +4123,7 @@ static struct md_sysfs_entry md_size =
__ATTR(component_size, S_IRUGO|S_IWUSR, size_show, size_store);
-/* Metdata version.
+/* Metadata version.
* This is one of
* 'none' for arrays with no metadata (good luck...)
* 'external' for arrays with externally managed metadata,
@@ -4753,6 +4752,8 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
}
mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
+ if (entry->store == new_dev_store)
+ flush_workqueue(md_misc_wq);
rv = mddev_lock(mddev);
if (!rv) {
rv = entry->store(mddev, page, length);
@@ -5294,7 +5295,7 @@ void md_stop_writes(struct mddev *mddev)
}
EXPORT_SYMBOL_GPL(md_stop_writes);
-void md_stop(struct mddev *mddev)
+static void __md_stop(struct mddev *mddev)
{
mddev->ready = 0;
mddev->pers->stop(mddev);
@@ -5304,6 +5305,18 @@ void md_stop(struct mddev *mddev)
mddev->pers = NULL;
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
}
+
+void md_stop(struct mddev *mddev)
+{
+ /* stop the array and free an attached data structures.
+ * This is called from dm-raid
+ */
+ __md_stop(mddev);
+ bitmap_destroy(mddev);
+ if (mddev->bio_set)
+ bioset_free(mddev->bio_set);
+}
+
EXPORT_SYMBOL_GPL(md_stop);
static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
@@ -5364,7 +5377,7 @@ static int do_md_stop(struct mddev * mddev, int mode,
set_disk_ro(disk, 0);
__md_stop_writes(mddev);
- md_stop(mddev);
+ __md_stop(mddev);
mddev->queue->merge_bvec_fn = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
@@ -6334,24 +6347,23 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
* Commands dealing with the RAID driver but not any
* particular array:
*/
- switch (cmd)
- {
- case RAID_VERSION:
- err = get_version(argp);
- goto done;
+ switch (cmd) {
+ case RAID_VERSION:
+ err = get_version(argp);
+ goto done;
- case PRINT_RAID_DEBUG:
- err = 0;
- md_print_devices();
- goto done;
+ case PRINT_RAID_DEBUG:
+ err = 0;
+ md_print_devices();
+ goto done;
#ifndef MODULE
- case RAID_AUTORUN:
- err = 0;
- autostart_arrays(arg);
- goto done;
+ case RAID_AUTORUN:
+ err = 0;
+ autostart_arrays(arg);
+ goto done;
#endif
- default:;
+ default:;
}
/*
@@ -6386,6 +6398,10 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
goto abort;
}
+ if (cmd == ADD_NEW_DISK)
+ /* need to ensure md_delayed_delete() has completed */
+ flush_workqueue(md_misc_wq);
+
err = mddev_lock(mddev);
if (err) {
printk(KERN_INFO
@@ -6394,50 +6410,44 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
goto abort;
}
- switch (cmd)
- {
- case SET_ARRAY_INFO:
- {
- mdu_array_info_t info;
- if (!arg)
- memset(&info, 0, sizeof(info));
- else if (copy_from_user(&info, argp, sizeof(info))) {
- err = -EFAULT;
- goto abort_unlock;
- }
- if (mddev->pers) {
- err = update_array_info(mddev, &info);
- if (err) {
- printk(KERN_WARNING "md: couldn't update"
- " array info. %d\n", err);
- goto abort_unlock;
- }
- goto done_unlock;
- }
- if (!list_empty(&mddev->disks)) {
- printk(KERN_WARNING
- "md: array %s already has disks!\n",
- mdname(mddev));
- err = -EBUSY;
- goto abort_unlock;
- }
- if (mddev->raid_disks) {
- printk(KERN_WARNING
- "md: array %s already initialised!\n",
- mdname(mddev));
- err = -EBUSY;
- goto abort_unlock;
- }
- err = set_array_info(mddev, &info);
- if (err) {
- printk(KERN_WARNING "md: couldn't set"
- " array info. %d\n", err);
- goto abort_unlock;
- }
+ if (cmd == SET_ARRAY_INFO) {
+ mdu_array_info_t info;
+ if (!arg)
+ memset(&info, 0, sizeof(info));
+ else if (copy_from_user(&info, argp, sizeof(info))) {
+ err = -EFAULT;
+ goto abort_unlock;
+ }
+ if (mddev->pers) {
+ err = update_array_info(mddev, &info);
+ if (err) {
+ printk(KERN_WARNING "md: couldn't update"
+ " array info. %d\n", err);
+ goto abort_unlock;
}
goto done_unlock;
-
- default:;
+ }
+ if (!list_empty(&mddev->disks)) {
+ printk(KERN_WARNING
+ "md: array %s already has disks!\n",
+ mdname(mddev));
+ err = -EBUSY;
+ goto abort_unlock;
+ }
+ if (mddev->raid_disks) {
+ printk(KERN_WARNING
+ "md: array %s already initialised!\n",
+ mdname(mddev));
+ err = -EBUSY;
+ goto abort_unlock;
+ }
+ err = set_array_info(mddev, &info);
+ if (err) {
+ printk(KERN_WARNING "md: couldn't set"
+ " array info. %d\n", err);
+ goto abort_unlock;
+ }
+ goto done_unlock;
}
/*
@@ -6456,52 +6466,51 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
/*
* Commands even a read-only array can execute:
*/
- switch (cmd)
- {
- case GET_BITMAP_FILE:
- err = get_bitmap_file(mddev, argp);
- goto done_unlock;
+ switch (cmd) {
+ case GET_BITMAP_FILE:
+ err = get_bitmap_file(mddev, argp);
+ goto done_unlock;
- case RESTART_ARRAY_RW:
- err = restart_array(mddev);
- goto done_unlock;
+ case RESTART_ARRAY_RW:
+ err = restart_array(mddev);
+ goto done_unlock;
- case STOP_ARRAY:
- err = do_md_stop(mddev, 0, bdev);
- goto done_unlock;
+ case STOP_ARRAY:
+ err = do_md_stop(mddev, 0, bdev);
+ goto done_unlock;
- case STOP_ARRAY_RO:
- err = md_set_readonly(mddev, bdev);
- goto done_unlock;
+ case STOP_ARRAY_RO:
+ err = md_set_readonly(mddev, bdev);
+ goto done_unlock;
- case BLKROSET:
- if (get_user(ro, (int __user *)(arg))) {
- err = -EFAULT;
- goto done_unlock;
- }
- err = -EINVAL;
+ case BLKROSET:
+ if (get_user(ro, (int __user *)(arg))) {
+ err = -EFAULT;
+ goto done_unlock;
+ }
+ err = -EINVAL;
- /* if the bdev is going readonly the value of mddev->ro
- * does not matter, no writes are coming
- */
- if (ro)
- goto done_unlock;
+ /* if the bdev is going readonly the value of mddev->ro
+ * does not matter, no writes are coming
+ */
+ if (ro)
+ goto done_unlock;
- /* are we are already prepared for writes? */
- if (mddev->ro != 1)
- goto done_unlock;
+ /* are we are already prepared for writes? */
+ if (mddev->ro != 1)
+ goto done_unlock;
- /* transitioning to readauto need only happen for
- * arrays that call md_write_start
- */
- if (mddev->pers) {
- err = restart_array(mddev);
- if (err == 0) {
- mddev->ro = 2;
- set_disk_ro(mddev->gendisk, 0);
- }
+ /* transitioning to readauto need only happen for
+ * arrays that call md_write_start
+ */
+ if (mddev->pers) {
+ err = restart_array(mddev);
+ if (err == 0) {
+ mddev->ro = 2;
+ set_disk_ro(mddev->gendisk, 0);
}
- goto done_unlock;
+ }
+ goto done_unlock;
}
/*
@@ -6523,37 +6532,36 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
}
}
- switch (cmd)
+ switch (cmd) {
+ case ADD_NEW_DISK:
{
- case ADD_NEW_DISK:
- {
- mdu_disk_info_t info;
- if (copy_from_user(&info, argp, sizeof(info)))
- err = -EFAULT;
- else
- err = add_new_disk(mddev, &info);
- goto done_unlock;
- }
+ mdu_disk_info_t info;
+ if (copy_from_user(&info, argp, sizeof(info)))
+ err = -EFAULT;
+ else
+ err = add_new_disk(mddev, &info);
+ goto done_unlock;
+ }
- case HOT_REMOVE_DISK:
- err = hot_remove_disk(mddev, new_decode_dev(arg));
- goto done_unlock;
+ case HOT_REMOVE_DISK:
+ err = hot_remove_disk(mddev, new_decode_dev(arg));
+ goto done_unlock;
- case HOT_ADD_DISK:
- err = hot_add_disk(mddev, new_decode_dev(arg));
- goto done_unlock;
+ case HOT_ADD_DISK:
+ err = hot_add_disk(mddev, new_decode_dev(arg));
+ goto done_unlock;
- case RUN_ARRAY:
- err = do_md_run(mddev);
- goto done_unlock;
+ case RUN_ARRAY:
+ err = do_md_run(mddev);
+ goto done_unlock;
- case SET_BITMAP_FILE:
- err = set_bitmap_file(mddev, (int)arg);
- goto done_unlock;
+ case SET_BITMAP_FILE:
+ err = set_bitmap_file(mddev, (int)arg);
+ goto done_unlock;
- default:
- err = -EINVAL;
- goto abort_unlock;
+ default:
+ err = -EINVAL;
+ goto abort_unlock;
}
done_unlock:
@@ -7172,6 +7180,7 @@ void md_done_sync(struct mddev *mddev, int blocks, int ok)
wake_up(&mddev->recovery_wait);
if (!ok) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ set_bit(MD_RECOVERY_ERROR, &mddev->recovery);
md_wakeup_thread(mddev->thread);
// stop recovery, signal do_sync ....
}
@@ -7269,6 +7278,7 @@ EXPORT_SYMBOL_GPL(md_allow_write);
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
+#define UPDATE_FREQUENCY (5*60*HZ)
void md_do_sync(struct md_thread *thread)
{
struct mddev *mddev = thread->mddev;
@@ -7277,6 +7287,7 @@ void md_do_sync(struct md_thread *thread)
window;
sector_t max_sectors,j, io_sectors;
unsigned long mark[SYNC_MARKS];
+ unsigned long update_time;
sector_t mark_cnt[SYNC_MARKS];
int last_mark,m;
struct list_head *tmp;
@@ -7436,6 +7447,7 @@ void md_do_sync(struct md_thread *thread)
mddev->curr_resync_completed = j;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
md_new_event(mddev);
+ update_time = jiffies;
blk_start_plug(&plug);
while (j < max_sectors) {
@@ -7447,6 +7459,7 @@ void md_do_sync(struct md_thread *thread)
((mddev->curr_resync > mddev->curr_resync_completed &&
(mddev->curr_resync - mddev->curr_resync_completed)
> (max_sectors >> 4)) ||
+ time_after_eq(jiffies, update_time + UPDATE_FREQUENCY) ||
(j - mddev->curr_resync_completed)*2
>= mddev->resync_max - mddev->curr_resync_completed
)) {
@@ -7454,6 +7467,10 @@ void md_do_sync(struct md_thread *thread)
wait_event(mddev->recovery_wait,
atomic_read(&mddev->recovery_active) == 0);
mddev->curr_resync_completed = j;
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
+ j > mddev->recovery_cp)
+ mddev->recovery_cp = j;
+ update_time = jiffies;
set_bit(MD_CHANGE_CLEAN, &mddev->flags);
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
@@ -7558,8 +7575,13 @@ void md_do_sync(struct md_thread *thread)
printk(KERN_INFO
"md: checkpointing %s of %s.\n",
desc, mdname(mddev));
- mddev->recovery_cp =
- mddev->curr_resync_completed;
+ if (test_bit(MD_RECOVERY_ERROR,
+ &mddev->recovery))
+ mddev->recovery_cp =
+ mddev->curr_resync_completed;
+ else
+ mddev->recovery_cp =
+ mddev->curr_resync;
}
} else
mddev->recovery_cp = MaxSector;
@@ -7936,9 +7958,9 @@ int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
sector_t *first_bad, int *bad_sectors)
{
int hi;
- int lo = 0;
+ int lo;
u64 *p = bb->page;
- int rv = 0;
+ int rv;
sector_t target = s + sectors;
unsigned seq;
@@ -7953,7 +7975,8 @@ int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
retry:
seq = read_seqbegin(&bb->lock);
-
+ lo = 0;
+ rv = 0;
hi = bb->count;
/* Binary search between lo and hi for 'target'
diff --git a/drivers/md/md.h b/drivers/md/md.h
index af443ab868d..eca59c3074e 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -307,6 +307,7 @@ struct mddev {
* REQUEST: user-space has requested a sync (used with SYNC)
* CHECK: user-space request for check-only, no repair
* RESHAPE: A reshape is happening
+ * ERROR: sync-action interrupted because io-error
*
* If neither SYNC or RESHAPE are set, then it is a recovery.
*/
@@ -320,6 +321,7 @@ struct mddev {
#define MD_RECOVERY_CHECK 7
#define MD_RECOVERY_RESHAPE 8
#define MD_RECOVERY_FROZEN 9
+#define MD_RECOVERY_ERROR 10
unsigned long recovery;
/* If a RAID personality determines that recovery (of a particular
@@ -551,32 +553,6 @@ struct md_thread {
#define THREAD_WAKEUP 0
-#define __wait_event_lock_irq(wq, condition, lock, cmd) \
-do { \
- wait_queue_t __wait; \
- init_waitqueue_entry(&__wait, current); \
- \
- add_wait_queue(&wq, &__wait); \
- for (;;) { \
- set_current_state(TASK_UNINTERRUPTIBLE); \
- if (condition) \
- break; \
- spin_unlock_irq(&lock); \
- cmd; \
- schedule(); \
- spin_lock_irq(&lock); \
- } \
- current->state = TASK_RUNNING; \
- remove_wait_queue(&wq, &__wait); \
-} while (0)
-
-#define wait_event_lock_irq(wq, condition, lock, cmd) \
-do { \
- if (condition) \
- break; \
- __wait_event_lock_irq(wq, condition, lock, cmd); \
-} while (0)
-
static inline void safe_put_page(struct page *p)
{
if (p) put_page(p);
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 5ba277768d9..a3ae09124a6 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -25,7 +25,7 @@
* may be held at once. This is just an implementation detail.
*
* ii) Recursive locking attempts are detected and return EINVAL. A stack
- * trace is also emitted for the previous lock aquisition.
+ * trace is also emitted for the previous lock acquisition.
*
* iii) Priority is given to write locks.
*/
@@ -109,7 +109,7 @@ static int __check_holder(struct block_lock *lock)
DMERR("previously held here:");
print_stack_trace(lock->traces + i, 4);
- DMERR("subsequent aquisition attempted here:");
+ DMERR("subsequent acquisition attempted here:");
t.nr_entries = 0;
t.max_entries = MAX_STACK;
t.entries = entries;
diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h
index ae02c84410f..a2cd50441ca 100644
--- a/drivers/md/persistent-data/dm-btree.h
+++ b/drivers/md/persistent-data/dm-btree.h
@@ -35,7 +35,7 @@ struct dm_transaction_manager;
*/
/*
- * Infomation about the values stored within the btree.
+ * Information about the values stored within the btree.
*/
struct dm_btree_value_type {
void *context;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 8034fbd6190..d5bddfc4010 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -822,7 +822,7 @@ static void raise_barrier(struct r1conf *conf)
/* Wait until no block IO is waiting */
wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting,
- conf->resync_lock, );
+ conf->resync_lock);
/* block any new IO from starting */
conf->barrier++;
@@ -830,7 +830,7 @@ static void raise_barrier(struct r1conf *conf)
/* Now wait for all pending IO to complete */
wait_event_lock_irq(conf->wait_barrier,
!conf->nr_pending && conf->barrier < RESYNC_DEPTH,
- conf->resync_lock, );
+ conf->resync_lock);
spin_unlock_irq(&conf->resync_lock);
}
@@ -864,8 +864,7 @@ static void wait_barrier(struct r1conf *conf)
(conf->nr_pending &&
current->bio_list &&
!bio_list_empty(current->bio_list)),
- conf->resync_lock,
- );
+ conf->resync_lock);
conf->nr_waiting--;
}
conf->nr_pending++;
@@ -898,10 +897,10 @@ static void freeze_array(struct r1conf *conf)
spin_lock_irq(&conf->resync_lock);
conf->barrier++;
conf->nr_waiting++;
- wait_event_lock_irq(conf->wait_barrier,
- conf->nr_pending == conf->nr_queued+1,
- conf->resync_lock,
- flush_pending_writes(conf));
+ wait_event_lock_irq_cmd(conf->wait_barrier,
+ conf->nr_pending == conf->nr_queued+1,
+ conf->resync_lock,
+ flush_pending_writes(conf));
spin_unlock_irq(&conf->resync_lock);
}
static void unfreeze_array(struct r1conf *conf)
@@ -963,7 +962,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
struct r1conf *conf = mddev->private;
struct bio *bio;
- if (from_schedule) {
+ if (from_schedule || current->bio_list) {
spin_lock_irq(&conf->device_lock);
bio_list_merge(&conf->pending_bio_list, &plug->pending);
conf->pending_count += plug->pending_cnt;
@@ -2710,7 +2709,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
|| disk_idx < 0)
continue;
if (test_bit(Replacement, &rdev->flags))
- disk = conf->mirrors + conf->raid_disks + disk_idx;
+ disk = conf->mirrors + mddev->raid_disks + disk_idx;
else
disk = conf->mirrors + disk_idx;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 906ccbd0f7d..64d48249c03 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -499,7 +499,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
*/
one_write_done(r10_bio);
if (dec_rdev)
- rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
+ rdev_dec_pending(rdev, conf->mddev);
}
/*
@@ -952,7 +952,7 @@ static void raise_barrier(struct r10conf *conf, int force)
/* Wait until no block IO is waiting (unless 'force') */
wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
- conf->resync_lock, );
+ conf->resync_lock);
/* block any new IO from starting */
conf->barrier++;
@@ -960,7 +960,7 @@ static void raise_barrier(struct r10conf *conf, int force)
/* Now wait for all pending IO to complete */
wait_event_lock_irq(conf->wait_barrier,
!conf->nr_pending && conf->barrier < RESYNC_DEPTH,
- conf->resync_lock, );
+ conf->resync_lock);
spin_unlock_irq(&conf->resync_lock);
}
@@ -993,8 +993,7 @@ static void wait_barrier(struct r10conf *conf)
(conf->nr_pending &&
current->bio_list &&
!bio_list_empty(current->bio_list)),
- conf->resync_lock,
- );
+ conf->resync_lock);
conf->nr_waiting--;
}
conf->nr_pending++;
@@ -1027,10 +1026,10 @@ static void freeze_array(struct r10conf *conf)
spin_lock_irq(&conf->resync_lock);
conf->barrier++;
conf->nr_waiting++;
- wait_event_lock_irq(conf->wait_barrier,
- conf->nr_pending == conf->nr_queued+1,
- conf->resync_lock,
- flush_pending_writes(conf));
+ wait_event_lock_irq_cmd(conf->wait_barrier,
+ conf->nr_pending == conf->nr_queued+1,
+ conf->resync_lock,
+ flush_pending_writes(conf));
spin_unlock_irq(&conf->resync_lock);
}
@@ -1069,7 +1068,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
struct r10conf *conf = mddev->private;
struct bio *bio;
- if (from_schedule) {
+ if (from_schedule || current->bio_list) {
spin_lock_irq(&conf->device_lock);
bio_list_merge(&conf->pending_bio_list, &plug->pending);
conf->pending_count += plug->pending_cnt;
@@ -1334,18 +1333,21 @@ retry_write:
blocked_rdev = rrdev;
break;
}
+ if (rdev && (test_bit(Faulty, &rdev->flags)
+ || test_bit(Unmerged, &rdev->flags)))
+ rdev = NULL;
if (rrdev && (test_bit(Faulty, &rrdev->flags)
|| test_bit(Unmerged, &rrdev->flags)))
rrdev = NULL;
r10_bio->devs[i].bio = NULL;
r10_bio->devs[i].repl_bio = NULL;
- if (!rdev || test_bit(Faulty, &rdev->flags) ||
- test_bit(Unmerged, &rdev->flags)) {
+
+ if (!rdev && !rrdev) {
set_bit(R10BIO_Degraded, &r10_bio->state);
continue;
}
- if (test_bit(WriteErrorSeen, &rdev->flags)) {
+ if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
sector_t first_bad;
sector_t dev_sector = r10_bio->devs[i].addr;
int bad_sectors;
@@ -1387,8 +1389,10 @@ retry_write:
max_sectors = good_sectors;
}
}
- r10_bio->devs[i].bio = bio;
- atomic_inc(&rdev->nr_pending);
+ if (rdev) {
+ r10_bio->devs[i].bio = bio;
+ atomic_inc(&rdev->nr_pending);
+ }
if (rrdev) {
r10_bio->devs[i].repl_bio = bio;
atomic_inc(&rrdev->nr_pending);
@@ -1444,69 +1448,71 @@ retry_write:
for (i = 0; i < conf->copies; i++) {
struct bio *mbio;
int d = r10_bio->devs[i].devnum;
- if (!r10_bio->devs[i].bio)
- continue;
+ if (r10_bio->devs[i].bio) {
+ struct md_rdev *rdev = conf->mirrors[d].rdev;
+ mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+ md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
+ max_sectors);
+ r10_bio->devs[i].bio = mbio;
+
+ mbio->bi_sector = (r10_bio->devs[i].addr+
+ choose_data_offset(r10_bio,
+ rdev));
+ mbio->bi_bdev = rdev->bdev;
+ mbio->bi_end_io = raid10_end_write_request;
+ mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+ mbio->bi_private = r10_bio;
- mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
- md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
- max_sectors);
- r10_bio->devs[i].bio = mbio;
+ atomic_inc(&r10_bio->remaining);
- mbio->bi_sector = (r10_bio->devs[i].addr+
- choose_data_offset(r10_bio,
- conf->mirrors[d].rdev));
- mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
- mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
- mbio->bi_private = r10_bio;
+ cb = blk_check_plugged(raid10_unplug, mddev,
+ sizeof(*plug));
+ if (cb)
+ plug = container_of(cb, struct raid10_plug_cb,
+ cb);
+ else
+ plug = NULL;
+ spin_lock_irqsave(&conf->device_lock, flags);
+ if (plug) {
+ bio_list_add(&plug->pending, mbio);
+ plug->pending_cnt++;
+ } else {
+ bio_list_add(&conf->pending_bio_list, mbio);
+ conf->pending_count++;
+ }
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ if (!plug)
+ md_wakeup_thread(mddev->thread);
+ }
- atomic_inc(&r10_bio->remaining);
+ if (r10_bio->devs[i].repl_bio) {
+ struct md_rdev *rdev = conf->mirrors[d].replacement;
+ if (rdev == NULL) {
+ /* Replacement just got moved to main 'rdev' */
+ smp_mb();
+ rdev = conf->mirrors[d].rdev;
+ }
+ mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+ md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
+ max_sectors);
+ r10_bio->devs[i].repl_bio = mbio;
+
+ mbio->bi_sector = (r10_bio->devs[i].addr +
+ choose_data_offset(
+ r10_bio, rdev));
+ mbio->bi_bdev = rdev->bdev;
+ mbio->bi_end_io = raid10_end_write_request;
+ mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+ mbio->bi_private = r10_bio;
- cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug));
- if (cb)
- plug = container_of(cb, struct raid10_plug_cb, cb);
- else
- plug = NULL;
- spin_lock_irqsave(&conf->device_lock, flags);
- if (plug) {
- bio_list_add(&plug->pending, mbio);
- plug->pending_cnt++;
- } else {
+ atomic_inc(&r10_bio->remaining);
+ spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
conf->pending_count++;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ if (!mddev_check_plugged(mddev))
+ md_wakeup_thread(mddev->thread);
}
- spin_unlock_irqrestore(&conf->device_lock, flags);
- if (!plug)
- md_wakeup_thread(mddev->thread);
-
- if (!r10_bio->devs[i].repl_bio)
- continue;
-
- mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
- md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
- max_sectors);
- r10_bio->devs[i].repl_bio = mbio;
-
- /* We are actively writing to the original device
- * so it cannot disappear, so the replacement cannot
- * become NULL here
- */
- mbio->bi_sector = (r10_bio->devs[i].addr +
- choose_data_offset(
- r10_bio,
- conf->mirrors[d].replacement));
- mbio->bi_bdev = conf->mirrors[d].replacement->bdev;
- mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
- mbio->bi_private = r10_bio;
-
- atomic_inc(&r10_bio->remaining);
- spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_add(&conf->pending_bio_list, mbio);
- conf->pending_count++;
- spin_unlock_irqrestore(&conf->device_lock, flags);
- if (!mddev_check_plugged(mddev))
- md_wakeup_thread(mddev->thread);
}
/* Don't remove the bias on 'remaining' (one_write_done) until
@@ -1783,7 +1789,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
clear_bit(Unmerged, &rdev->flags);
}
md_integrity_add_rdev(rdev, mddev);
- if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+ if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
print_conf(conf);
@@ -3613,11 +3619,14 @@ static int run(struct mddev *mddev)
discard_supported = true;
}
- if (discard_supported)
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
- else
- queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
-
+ if (mddev->queue) {
+ if (discard_supported)
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
+ mddev->queue);
+ else
+ queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD,
+ mddev->queue);
+ }
/* need to check that every block has at least one working mirror */
if (!enough(conf, -1)) {
printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c5439dce029..19d77a02663 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -53,6 +53,8 @@
#include <linux/cpu.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
+#include <trace/events/block.h>
+
#include "md.h"
#include "raid5.h"
#include "raid0.h"
@@ -182,6 +184,8 @@ static void return_io(struct bio *return_bi)
return_bi = bi->bi_next;
bi->bi_next = NULL;
bi->bi_size = 0;
+ trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
+ bi, 0);
bio_endio(bi, 0);
bi = return_bi;
}
@@ -466,7 +470,7 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
do {
wait_event_lock_irq(conf->wait_for_stripe,
conf->quiesce == 0 || noquiesce,
- conf->device_lock, /* nothing */);
+ conf->device_lock);
sh = __find_stripe(conf, sector, conf->generation - previous);
if (!sh) {
if (!conf->inactive_blocked)
@@ -480,8 +484,7 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
(atomic_read(&conf->active_stripes)
< (conf->max_nr_stripes *3/4)
|| !conf->inactive_blocked),
- conf->device_lock,
- );
+ conf->device_lock);
conf->inactive_blocked = 0;
} else
init_stripe(sh, sector, previous);
@@ -671,6 +674,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
bi->bi_next = NULL;
if (rrdev)
set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
+ trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
+ bi, disk_devt(conf->mddev->gendisk),
+ sh->dev[i].sector);
generic_make_request(bi);
}
if (rrdev) {
@@ -698,6 +704,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
rbi->bi_io_vec[0].bv_offset = 0;
rbi->bi_size = STRIPE_SIZE;
rbi->bi_next = NULL;
+ trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
+ rbi, disk_devt(conf->mddev->gendisk),
+ sh->dev[i].sector);
generic_make_request(rbi);
}
if (!rdev && !rrdev) {
@@ -1576,7 +1585,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
* This happens in stages:
* 1/ create a new kmem_cache and allocate the required number of
* stripe_heads.
- * 2/ gather all the old stripe_heads and tranfer the pages across
+ * 2/ gather all the old stripe_heads and transfer the pages across
* to the new stripe_heads. This will have the side effect of
* freezing the array as once all stripe_heads have been collected,
* no IO will be possible. Old stripe heads are freed once their
@@ -1646,8 +1655,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
spin_lock_irq(&conf->device_lock);
wait_event_lock_irq(conf->wait_for_stripe,
!list_empty(&conf->inactive_list),
- conf->device_lock,
- );
+ conf->device_lock);
osh = get_free_stripe(conf);
spin_unlock_irq(&conf->device_lock);
atomic_set(&nsh->count, 1);
@@ -2774,10 +2782,12 @@ static void handle_stripe_clean_event(struct r5conf *conf,
dev = &sh->dev[i];
if (!test_bit(R5_LOCKED, &dev->flags) &&
(test_bit(R5_UPTODATE, &dev->flags) ||
- test_and_clear_bit(R5_Discard, &dev->flags))) {
+ test_bit(R5_Discard, &dev->flags))) {
/* We can return any write requests */
struct bio *wbi, *wbi2;
pr_debug("Return write for disc %d\n", i);
+ if (test_and_clear_bit(R5_Discard, &dev->flags))
+ clear_bit(R5_UPTODATE, &dev->flags);
wbi = dev->written;
dev->written = NULL;
while (wbi && wbi->bi_sector <
@@ -2795,7 +2805,8 @@ static void handle_stripe_clean_event(struct r5conf *conf,
!test_bit(STRIPE_DEGRADED, &sh->state),
0);
}
- }
+ } else if (test_bit(R5_Discard, &sh->dev[i].flags))
+ clear_bit(R5_Discard, &sh->dev[i].flags);
if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
if (atomic_dec_and_test(&conf->pending_full_writes))
@@ -2852,8 +2863,10 @@ static void handle_stripe_dirtying(struct r5conf *conf,
pr_debug("for sector %llu, rmw=%d rcw=%d\n",
(unsigned long long)sh->sector, rmw, rcw);
set_bit(STRIPE_HANDLE, &sh->state);
- if (rmw < rcw && rmw > 0)
+ if (rmw < rcw && rmw > 0) {
/* prefer read-modify-write, but need to get some data */
+ blk_add_trace_msg(conf->mddev->queue, "raid5 rmw %llu %d",
+ (unsigned long long)sh->sector, rmw);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if ((dev->towrite || i == sh->pd_idx) &&
@@ -2864,7 +2877,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
if (
test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
pr_debug("Read_old block "
- "%d for r-m-w\n", i);
+ "%d for r-m-w\n", i);
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
@@ -2874,8 +2887,10 @@ static void handle_stripe_dirtying(struct r5conf *conf,
}
}
}
+ }
if (rcw <= rmw && rcw > 0) {
/* want reconstruct write, but need to get some data */
+ int qread =0;
rcw = 0;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
@@ -2894,12 +2909,17 @@ static void handle_stripe_dirtying(struct r5conf *conf,
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
+ qread++;
} else {
set_bit(STRIPE_DELAYED, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
}
}
}
+ if (rcw)
+ blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
+ (unsigned long long)sh->sector,
+ rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
}
/* now if nothing is locked, and if we have enough data,
* we can start a write request
@@ -3221,10 +3241,7 @@ static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh)
}
/* done submitting copies, wait for them to complete */
- if (tx) {
- async_tx_ack(tx);
- dma_wait_for_async_tx(tx);
- }
+ async_tx_quiesce(&tx);
}
/*
@@ -3490,40 +3507,6 @@ static void handle_stripe(struct stripe_head *sh)
handle_failed_sync(conf, sh, &s);
}
- /*
- * might be able to return some write requests if the parity blocks
- * are safe, or on a failed drive
- */
- pdev = &sh->dev[sh->pd_idx];
- s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx)
- || (s.failed >= 2 && s.failed_num[1] == sh->pd_idx);
- qdev = &sh->dev[sh->qd_idx];
- s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx)
- || (s.failed >= 2 && s.failed_num[1] == sh->qd_idx)
- || conf->level < 6;
-
- if (s.written &&
- (s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
- && !test_bit(R5_LOCKED, &pdev->flags)
- && (test_bit(R5_UPTODATE, &pdev->flags) ||
- test_bit(R5_Discard, &pdev->flags))))) &&
- (s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
- && !test_bit(R5_LOCKED, &qdev->flags)
- && (test_bit(R5_UPTODATE, &qdev->flags) ||
- test_bit(R5_Discard, &qdev->flags))))))
- handle_stripe_clean_event(conf, sh, disks, &s.return_bi);
-
- /* Now we might consider reading some blocks, either to check/generate
- * parity, or to satisfy requests
- * or to load a block that is being partially written.
- */
- if (s.to_read || s.non_overwrite
- || (conf->level == 6 && s.to_write && s.failed)
- || (s.syncing && (s.uptodate + s.compute < disks))
- || s.replacing
- || s.expanding)
- handle_stripe_fill(sh, &s, disks);
-
/* Now we check to see if any write operations have recently
* completed
*/
@@ -3561,6 +3544,40 @@ static void handle_stripe(struct stripe_head *sh)
s.dec_preread_active = 1;
}
+ /*
+ * might be able to return some write requests if the parity blocks
+ * are safe, or on a failed drive
+ */
+ pdev = &sh->dev[sh->pd_idx];
+ s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx)
+ || (s.failed >= 2 && s.failed_num[1] == sh->pd_idx);
+ qdev = &sh->dev[sh->qd_idx];
+ s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx)
+ || (s.failed >= 2 && s.failed_num[1] == sh->qd_idx)
+ || conf->level < 6;
+
+ if (s.written &&
+ (s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
+ && !test_bit(R5_LOCKED, &pdev->flags)
+ && (test_bit(R5_UPTODATE, &pdev->flags) ||
+ test_bit(R5_Discard, &pdev->flags))))) &&
+ (s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
+ && !test_bit(R5_LOCKED, &qdev->flags)
+ && (test_bit(R5_UPTODATE, &qdev->flags) ||
+ test_bit(R5_Discard, &qdev->flags))))))
+ handle_stripe_clean_event(conf, sh, disks, &s.return_bi);
+
+ /* Now we might consider reading some blocks, either to check/generate
+ * parity, or to satisfy requests
+ * or to load a block that is being partially written.
+ */
+ if (s.to_read || s.non_overwrite
+ || (conf->level == 6 && s.to_write && s.failed)
+ || (s.syncing && (s.uptodate + s.compute < disks))
+ || s.replacing
+ || s.expanding)
+ handle_stripe_fill(sh, &s, disks);
+
/* Now to consider new write requests and what else, if anything
* should be read. We do not handle new writes when:
* 1/ A 'write' operation (copy+xor) is already in flight.
@@ -3900,6 +3917,8 @@ static void raid5_align_endio(struct bio *bi, int error)
rdev_dec_pending(rdev, conf->mddev);
if (!error && uptodate) {
+ trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
+ raid_bi, 0);
bio_endio(raid_bi, 0);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
@@ -4000,10 +4019,13 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
spin_lock_irq(&conf->device_lock);
wait_event_lock_irq(conf->wait_for_stripe,
conf->quiesce == 0,
- conf->device_lock, /* nothing */);
+ conf->device_lock);
atomic_inc(&conf->active_aligned_reads);
spin_unlock_irq(&conf->device_lock);
+ trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
+ align_bi, disk_devt(mddev->gendisk),
+ raid_bio->bi_sector);
generic_make_request(align_bi);
return 1;
} else {
@@ -4078,6 +4100,7 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
struct stripe_head *sh;
struct mddev *mddev = cb->cb.data;
struct r5conf *conf = mddev->private;
+ int cnt = 0;
if (cb->list.next && !list_empty(&cb->list)) {
spin_lock_irq(&conf->device_lock);
@@ -4092,9 +4115,11 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
smp_mb__before_clear_bit();
clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state);
__release_stripe(conf, sh);
+ cnt++;
}
spin_unlock_irq(&conf->device_lock);
}
+ trace_block_unplug(mddev->queue, cnt, !from_schedule);
kfree(cb);
}
@@ -4352,6 +4377,8 @@ static void make_request(struct mddev *mddev, struct bio * bi)
if ( rw == WRITE )
md_write_end(mddev);
+ trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
+ bi, 0);
bio_endio(bi, 0);
}
}
@@ -4728,8 +4755,11 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
handled++;
}
remaining = raid5_dec_bi_active_stripes(raid_bio);
- if (remaining == 0)
+ if (remaining == 0) {
+ trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
+ raid_bio, 0);
bio_endio(raid_bio, 0);
+ }
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
return handled;
@@ -5529,6 +5559,10 @@ static int run(struct mddev *mddev)
* discard data disk but write parity disk
*/
stripe = stripe * PAGE_SIZE;
+ /* Round up to power of 2, as discard handling
+ * currently assumes that */
+ while ((stripe-1) & stripe)
+ stripe = (stripe | (stripe-1)) + 1;
mddev->queue->limits.discard_alignment = stripe;
mddev->queue->limits.discard_granularity = stripe;
/*
@@ -6088,7 +6122,7 @@ static void raid5_quiesce(struct mddev *mddev, int state)
wait_event_lock_irq(conf->wait_for_stripe,
atomic_read(&conf->active_stripes) == 0 &&
atomic_read(&conf->active_aligned_reads) == 0,
- conf->device_lock, /* nothing */);
+ conf->device_lock);
conf->quiesce = 1;
spin_unlock_irq(&conf->device_lock);
/* allow reshape to continue */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-03-24 09:43:57 +0000