summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bitmap.c45
-rw-r--r--drivers/md/dm-mpath.c16
-rw-r--r--drivers/md/dm.c12
-rw-r--r--drivers/md/md.c43
-rw-r--r--drivers/md/raid10.c9
-rw-r--r--drivers/md/raid5.c32
6 files changed, 127 insertions, 30 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 7e65bad522cb..ac89a5deaca2 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -238,15 +238,47 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde
}
+static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
+{
+ /* Iterate the disks of an mddev, using rcu to protect access to the
+ * linked list, and raising the refcount of devices we return to ensure
+ * they don't disappear while in use.
+ * As devices are only added or removed when raid_disk is < 0 and
+ * nr_pending is 0 and In_sync is clear, the entries we return will
+ * still be in the same position on the list when we re-enter
+ * list_for_each_continue_rcu.
+ */
+ struct list_head *pos;
+ rcu_read_lock();
+ if (rdev == NULL)
+ /* start at the beginning */
+ pos = &mddev->disks;
+ else {
+ /* release the previous rdev and start from there. */
+ rdev_dec_pending(rdev, mddev);
+ pos = &rdev->same_set;
+ }
+ list_for_each_continue_rcu(pos, &mddev->disks) {
+ rdev = list_entry(pos, mdk_rdev_t, same_set);
+ if (rdev->raid_disk >= 0 &&
+ test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags)) {
+ /* this is a usable devices */
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
+ return rdev;
+ }
+ }
+ rcu_read_unlock();
+ return NULL;
+}
+
static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
{
- mdk_rdev_t *rdev;
+ mdk_rdev_t *rdev = NULL;
mddev_t *mddev = bitmap->mddev;
- rcu_read_lock();
- rdev_for_each_rcu(rdev, mddev)
- if (test_bit(In_sync, &rdev->flags)
- && !test_bit(Faulty, &rdev->flags)) {
+ while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
int size = PAGE_SIZE;
if (page->index == bitmap->file_pages-1)
size = roundup(bitmap->last_page_size,
@@ -281,8 +313,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
+ page->index * (PAGE_SIZE/512),
size,
page);
- }
- rcu_read_unlock();
+ }
if (wait)
md_super_wait(mddev);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 71dd65aa31b6..c2fcf28b4c70 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -63,6 +63,7 @@ struct multipath {
const char *hw_handler_name;
struct work_struct activate_path;
+ struct pgpath *pgpath_to_activate;
unsigned nr_priority_groups;
struct list_head priority_groups;
unsigned pg_init_required; /* pg_init needs calling? */
@@ -146,6 +147,7 @@ static struct priority_group *alloc_priority_group(void)
static void free_pgpaths(struct list_head *pgpaths, struct dm_target *ti)
{
+ unsigned long flags;
struct pgpath *pgpath, *tmp;
struct multipath *m = ti->private;
@@ -154,6 +156,10 @@ static void free_pgpaths(struct list_head *pgpaths, struct dm_target *ti)
if (m->hw_handler_name)
scsi_dh_detach(bdev_get_queue(pgpath->path.dev->bdev));
dm_put_device(ti, pgpath->path.dev);
+ spin_lock_irqsave(&m->lock, flags);
+ if (m->pgpath_to_activate == pgpath)
+ m->pgpath_to_activate = NULL;
+ spin_unlock_irqrestore(&m->lock, flags);
free_pgpath(pgpath);
}
}
@@ -421,6 +427,7 @@ static void process_queued_ios(struct work_struct *work)
__choose_pgpath(m);
pgpath = m->current_pgpath;
+ m->pgpath_to_activate = m->current_pgpath;
if ((pgpath && !m->queue_io) ||
(!pgpath && !m->queue_if_no_path))
@@ -1093,8 +1100,15 @@ static void activate_path(struct work_struct *work)
int ret;
struct multipath *m =
container_of(work, struct multipath, activate_path);
- struct dm_path *path = &m->current_pgpath->path;
+ struct dm_path *path;
+ unsigned long flags;
+ spin_lock_irqsave(&m->lock, flags);
+ path = &m->pgpath_to_activate->path;
+ m->pgpath_to_activate = NULL;
+ spin_unlock_irqrestore(&m->lock, flags);
+ if (!path)
+ return;
ret = scsi_dh_activate(bdev_get_queue(path->dev->bdev));
pg_init_done(path, ret);
}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index bca448e11878..ace998ce59f6 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -837,12 +837,14 @@ static int dm_merge_bvec(struct request_queue *q,
struct dm_table *map = dm_get_table(md);
struct dm_target *ti;
sector_t max_sectors;
- int max_size;
+ int max_size = 0;
if (unlikely(!map))
- return 0;
+ goto out;
ti = dm_table_find_target(map, bvm->bi_sector);
+ if (!dm_target_is_valid(ti))
+ goto out_table;
/*
* Find maximum amount of I/O that won't need splitting
@@ -861,14 +863,16 @@ static int dm_merge_bvec(struct request_queue *q,
if (max_size && ti->type->merge)
max_size = ti->type->merge(ti, bvm, biovec, max_size);
+out_table:
+ dm_table_put(map);
+
+out:
/*
* Always allow an entire first page
*/
if (max_size <= biovec->bv_len && !(bvm->bi_size >> SECTOR_SHIFT))
max_size = biovec->bv_len;
- dm_table_put(map);
-
return max_size;
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index c7aae66c6f9b..deeac4b44173 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2393,6 +2393,8 @@ static void analyze_sbs(mddev_t * mddev)
}
+static void md_safemode_timeout(unsigned long data);
+
static ssize_t
safe_delay_show(mddev_t *mddev, char *page)
{
@@ -2432,9 +2434,12 @@ safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
if (msec == 0)
mddev->safemode_delay = 0;
else {
+ unsigned long old_delay = mddev->safemode_delay;
mddev->safemode_delay = (msec*HZ)/1000;
if (mddev->safemode_delay == 0)
mddev->safemode_delay = 1;
+ if (mddev->safemode_delay < old_delay)
+ md_safemode_timeout((unsigned long)mddev);
}
return len;
}
@@ -3836,8 +3841,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
del_timer_sync(&mddev->safemode_timer);
- invalidate_partition(disk, 0);
-
switch(mode) {
case 1: /* readonly */
err = -ENXIO;
@@ -4634,6 +4637,11 @@ static int update_size(mddev_t *mddev, sector_t num_sectors)
*/
if (mddev->sync_thread)
return -EBUSY;
+ if (mddev->bitmap)
+ /* Sorry, cannot grow a bitmap yet, just remove it,
+ * grow, and re-add.
+ */
+ return -EBUSY;
rdev_for_each(rdev, tmp, mddev) {
sector_t avail;
avail = rdev->size * 2;
@@ -5753,7 +5761,11 @@ void md_do_sync(mddev_t *mddev)
* time 'round when curr_resync == 2
*/
continue;
- prepare_to_wait(&resync_wait, &wq, TASK_UNINTERRUPTIBLE);
+ /* We need to wait 'interruptible' so as not to
+ * contribute to the load average, and not to
+ * be caught by 'softlockup'
+ */
+ prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
if (!kthread_should_stop() &&
mddev2->curr_resync >= mddev->curr_resync) {
printk(KERN_INFO "md: delaying %s of %s"
@@ -5761,6 +5773,8 @@ void md_do_sync(mddev_t *mddev)
" share one or more physical units)\n",
desc, mdname(mddev), mdname(mddev2));
mddev_put(mddev2);
+ if (signal_pending(current))
+ flush_signals(current);
schedule();
finish_wait(&resync_wait, &wq);
goto try_again;
@@ -5993,7 +6007,7 @@ static int remove_and_add_spares(mddev_t *mddev)
}
}
- if (mddev->degraded) {
+ if (mddev->degraded && ! mddev->ro) {
rdev_for_each(rdev, rtmp, mddev) {
if (rdev->raid_disk >= 0 &&
!test_bit(In_sync, &rdev->flags) &&
@@ -6067,6 +6081,8 @@ void md_check_recovery(mddev_t *mddev)
flush_signals(current);
}
+ if (mddev->ro && !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+ return;
if ( ! (
(mddev->flags && !mddev->external) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
@@ -6080,6 +6096,15 @@ void md_check_recovery(mddev_t *mddev)
if (mddev_trylock(mddev)) {
int spares = 0;
+ if (mddev->ro) {
+ /* Only thing we do on a ro array is remove
+ * failed devices.
+ */
+ remove_and_add_spares(mddev);
+ clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ goto unlock;
+ }
+
if (!mddev->external) {
int did_change = 0;
spin_lock_irq(&mddev->write_lock);
@@ -6117,7 +6142,8 @@ void md_check_recovery(mddev_t *mddev)
/* resync has finished, collect result */
md_unregister_thread(mddev->sync_thread);
mddev->sync_thread = NULL;
- if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+ !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
/* success...*/
/* activate any spares */
if (mddev->pers->spare_active(mddev))
@@ -6169,6 +6195,7 @@ void md_check_recovery(mddev_t *mddev)
} else if ((spares = remove_and_add_spares(mddev))) {
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
} else if (mddev->recovery_cp < MaxSector) {
set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
@@ -6232,7 +6259,11 @@ static int md_notify_reboot(struct notifier_block *this,
for_each_mddev(mddev, tmp)
if (mddev_trylock(mddev)) {
- do_md_stop (mddev, 1, 0);
+ /* Force a switch to readonly even array
+ * appears to still be in use. Hence
+ * the '100'.
+ */
+ do_md_stop (mddev, 1, 100);
mddev_unlock(mddev);
}
/*
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d41bebb6da0f..e34cd0e62473 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -76,11 +76,13 @@ static void r10bio_pool_free(void *r10_bio, void *data)
kfree(r10_bio);
}
+/* Maximum size of each resync request */
#define RESYNC_BLOCK_SIZE (64*1024)
-//#define RESYNC_BLOCK_SIZE PAGE_SIZE
-#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
-#define RESYNC_WINDOW (2048*1024)
+/* amount of memory to reserve for resync requests */
+#define RESYNC_WINDOW (1024*1024)
+/* maximum number of concurrent requests, memory permitting */
+#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE)
/*
* When performing a resync, we need to read and compare, so
@@ -690,7 +692,6 @@ static int flush_pending_writes(conf_t *conf)
* there is no normal IO happeing. It must arrange to call
* lower_barrier when the particular background IO completes.
*/
-#define RESYNC_DEPTH 32
static void raise_barrier(conf_t *conf, int force)
{
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 40e939675657..224de022e7c5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2568,10 +2568,10 @@ static bool handle_stripe5(struct stripe_head *sh)
if (dev->written)
s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ if (blocked_rdev == NULL &&
+ rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
blocked_rdev = rdev;
atomic_inc(&rdev->nr_pending);
- break;
}
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
@@ -2588,8 +2588,14 @@ static bool handle_stripe5(struct stripe_head *sh)
rcu_read_unlock();
if (unlikely(blocked_rdev)) {
- set_bit(STRIPE_HANDLE, &sh->state);
- goto unlock;
+ if (s.syncing || s.expanding || s.expanded ||
+ s.to_write || s.written) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
+ /* There is nothing for the blocked_rdev to block */
+ rdev_dec_pending(blocked_rdev, conf->mddev);
+ blocked_rdev = NULL;
}
if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
@@ -2832,10 +2838,10 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
if (dev->written)
s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ if (blocked_rdev == NULL &&
+ rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
blocked_rdev = rdev;
atomic_inc(&rdev->nr_pending);
- break;
}
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
@@ -2853,9 +2859,16 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
rcu_read_unlock();
if (unlikely(blocked_rdev)) {
- set_bit(STRIPE_HANDLE, &sh->state);
- goto unlock;
+ if (s.syncing || s.expanding || s.expanded ||
+ s.to_write || s.written) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
+ /* There is nothing for the blocked_rdev to block */
+ rdev_dec_pending(blocked_rdev, conf->mddev);
+ blocked_rdev = NULL;
}
+
pr_debug("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d,%d\n",
s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
@@ -4446,6 +4459,9 @@ static int raid5_check_reshape(mddev_t *mddev)
return -EINVAL; /* Cannot shrink array or change level yet */
if (mddev->delta_disks == 0)
return 0; /* nothing to do */
+ if (mddev->bitmap)
+ /* Cannot grow a bitmap yet */
+ return -EBUSY;
/* Can only proceed if there are plenty of stripe_heads.
* We need a minimum of one full stripe,, and for sensible progress
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-15 07:55:05 +0300