if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
struct bio *wbi;
- spin_lock(&sh->lock);
+ spin_lock_irq(&sh->raid_conf->device_lock);
chosen = dev->towrite;
dev->towrite = NULL;
BUG_ON(dev->written);
wbi = dev->written = chosen;
- spin_unlock(&sh->lock);
+ spin_unlock_irq(&sh->raid_conf->device_lock);
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
static int grow_one_stripe(raid5_conf_t *conf)
{
struct stripe_head *sh;
- sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
+ sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL);
if (!sh)
return 0;
- memset(sh, 0, sizeof(*sh) + (conf->pool_size-1)*sizeof(struct r5dev));
+
sh->raid_conf = conf;
- spin_lock_init(&sh->lock);
#ifdef CONFIG_MULTICORE_RAID456
init_waitqueue_head(&sh->ops.wait_for_ops);
#endif
return -ENOMEM;
for (i = conf->max_nr_stripes; i; i--) {
- nsh = kmem_cache_alloc(sc, GFP_KERNEL);
+ nsh = kmem_cache_zalloc(sc, GFP_KERNEL);
if (!nsh)
break;
- memset(nsh, 0, sizeof(*nsh) + (newsize-1)*sizeof(struct r5dev));
-
nsh->raid_conf = conf;
- spin_lock_init(&nsh->lock);
#ifdef CONFIG_MULTICORE_RAID456
init_waitqueue_head(&nsh->ops.wait_for_ops);
#endif
raid5_conf_t *conf = sh->raid_conf;
int firstwrite=0;
- pr_debug("adding bh b#%llu to stripe s#%llu\n",
+ pr_debug("adding bi b#%llu to stripe s#%llu\n",
(unsigned long long)bi->bi_sector,
(unsigned long long)sh->sector);
- spin_lock(&sh->lock);
spin_lock_irq(&conf->device_lock);
if (forwrite) {
bip = &sh->dev[dd_idx].towrite;
bi->bi_next = *bip;
*bip = bi;
bi->bi_phys_segments++;
- spin_unlock_irq(&conf->device_lock);
- spin_unlock(&sh->lock);
-
- pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
- (unsigned long long)bi->bi_sector,
- (unsigned long long)sh->sector, dd_idx);
-
- if (conf->mddev->bitmap && firstwrite) {
- bitmap_startwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS, 0);
- sh->bm_seq = conf->seq_flush+1;
- set_bit(STRIPE_BIT_DELAY, &sh->state);
- }
if (forwrite) {
/* check if page is covered */
if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
}
+ spin_unlock_irq(&conf->device_lock);
+
+ pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
+ (unsigned long long)(*bip)->bi_sector,
+ (unsigned long long)sh->sector, dd_idx);
+
+ if (conf->mddev->bitmap && firstwrite) {
+ bitmap_startwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS, 0);
+ sh->bm_seq = conf->seq_flush+1;
+ set_bit(STRIPE_BIT_DELAY, &sh->state);
+ }
return 1;
overlap:
set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
spin_unlock_irq(&conf->device_lock);
- spin_unlock(&sh->lock);
return 0;
}
int disk_idx, int disks)
{
struct r5dev *dev = &sh->dev[disk_idx];
- struct r5dev *failed_dev = &sh->dev[s->failed_num];
+ struct r5dev *failed_dev = &sh->dev[s->failed_num[0]];
/* is the data in this block needed, and can we get it? */
if (!test_bit(R5_LOCKED, &dev->flags) &&
* otherwise read it if the backing disk is insync
*/
if ((s->uptodate == disks - 1) &&
- (s->failed && disk_idx == s->failed_num)) {
+ (s->failed && disk_idx == s->failed_num[0])) {
set_bit(STRIPE_COMPUTE_RUN, &sh->state);
set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
set_bit(R5_Wantcompute, &dev->flags);
* 0 to tell the loop in handle_stripe_fill6 to continue
*/
static int fetch_block6(struct stripe_head *sh, struct stripe_head_state *s,
- struct r6_state *r6s, int disk_idx, int disks)
+ int disk_idx, int disks)
{
struct r5dev *dev = &sh->dev[disk_idx];
- struct r5dev *fdev[2] = { &sh->dev[r6s->failed_num[0]],
- &sh->dev[r6s->failed_num[1]] };
+ struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]],
+ &sh->dev[s->failed_num[1]] };
if (!test_bit(R5_LOCKED, &dev->flags) &&
!test_bit(R5_UPTODATE, &dev->flags) &&
BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
BUG_ON(test_bit(R5_Wantread, &dev->flags));
if ((s->uptodate == disks - 1) &&
- (s->failed && (disk_idx == r6s->failed_num[0] ||
- disk_idx == r6s->failed_num[1]))) {
+ (s->failed && (disk_idx == s->failed_num[0] ||
+ disk_idx == s->failed_num[1]))) {
/* have disk failed, and we're requested to fetch it;
* do compute it
*/
* handle_stripe_fill6 - read or compute data to satisfy pending requests.
*/
static void handle_stripe_fill6(struct stripe_head *sh,
- struct stripe_head_state *s, struct r6_state *r6s,
+ struct stripe_head_state *s,
int disks)
{
int i;
if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
!sh->reconstruct_state)
for (i = disks; i--; )
- if (fetch_block6(sh, s, r6s, i, disks))
+ if (fetch_block6(sh, s, i, disks))
break;
set_bit(STRIPE_HANDLE, &sh->state);
}
static void handle_stripe_dirtying6(raid5_conf_t *conf,
struct stripe_head *sh, struct stripe_head_state *s,
- struct r6_state *r6s, int disks)
+ int disks)
{
int rcw = 0, pd_idx = sh->pd_idx, i;
int qd_idx = sh->qd_idx;
s->uptodate--;
break;
}
- dev = &sh->dev[s->failed_num];
+ dev = &sh->dev[s->failed_num[0]];
/* fall through */
case check_state_compute_result:
sh->check_state = check_state_idle;
static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
struct stripe_head_state *s,
- struct r6_state *r6s, int disks)
+ int disks)
{
int pd_idx = sh->pd_idx;
int qd_idx = sh->qd_idx;
switch (sh->check_state) {
case check_state_idle:
/* start a new check operation if there are < 2 failures */
- if (s->failed == r6s->q_failed) {
+ if (s->failed == s->q_failed) {
/* The only possible failed device holds Q, so it
* makes sense to check P (If anything else were failed,
* we would have used P to recreate it).
*/
sh->check_state = check_state_run;
}
- if (!r6s->q_failed && s->failed < 2) {
+ if (!s->q_failed && s->failed < 2) {
/* Q is not failed, and we didn't use it to generate
* anything, so it makes sense to check it
*/
*/
BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */
if (s->failed == 2) {
- dev = &sh->dev[r6s->failed_num[1]];
+ dev = &sh->dev[s->failed_num[1]];
s->locked++;
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
}
if (s->failed >= 1) {
- dev = &sh->dev[r6s->failed_num[0]];
+ dev = &sh->dev[s->failed_num[0]];
s->locked++;
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
}
}
-static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
- struct r6_state *r6s)
+static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh)
{
int i;
set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
for (j = 0; j < conf->raid_disks; j++)
if (j != sh2->pd_idx &&
- (!r6s || j != sh2->qd_idx) &&
+ j != sh2->qd_idx &&
!test_bit(R5_Expanded, &sh2->dev[j].flags))
break;
if (j == conf->raid_disks) {
*
*/
-static void handle_stripe5(struct stripe_head *sh)
+static int handle_stripe5(struct stripe_head *sh, struct stripe_head_state *s)
{
raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks, i;
- struct bio *return_bi = NULL;
- struct stripe_head_state s;
struct r5dev *dev;
- mdk_rdev_t *blocked_rdev = NULL;
int prexor;
- int dec_preread_active = 0;
-
- memset(&s, 0, sizeof(s));
- pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
- "reconstruct:%d\n", (unsigned long long)sh->sector, sh->state,
- atomic_read(&sh->count), sh->pd_idx, sh->check_state,
- sh->reconstruct_state);
-
- spin_lock(&sh->lock);
- clear_bit(STRIPE_HANDLE, &sh->state);
- clear_bit(STRIPE_DELAYED, &sh->state);
-
- s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
- s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
- s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
/* Now to look around and see what can be done */
rcu_read_lock();
+ spin_lock_irq(&conf->device_lock);
for (i=disks; i--; ) {
mdk_rdev_t *rdev;
set_bit(R5_Wantfill, &dev->flags);
/* now count some things */
- if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
- if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
- if (test_bit(R5_Wantcompute, &dev->flags)) s.compute++;
+ if (test_bit(R5_LOCKED, &dev->flags))
+ s->locked++;
+ if (test_bit(R5_UPTODATE, &dev->flags))
+ s->uptodate++;
+ if (test_bit(R5_Wantcompute, &dev->flags))
+ s->compute++;
if (test_bit(R5_Wantfill, &dev->flags))
- s.to_fill++;
+ s->to_fill++;
else if (dev->toread)
- s.to_read++;
+ s->to_read++;
if (dev->towrite) {
- s.to_write++;
+ s->to_write++;
if (!test_bit(R5_OVERWRITE, &dev->flags))
- s.non_overwrite++;
+ s->non_overwrite++;
}
if (dev->written)
- s.written++;
+ s->written++;
rdev = rcu_dereference(conf->disks[i].rdev);
- if (blocked_rdev == NULL &&
+ if (s->blocked_rdev == NULL &&
rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
- blocked_rdev = rdev;
+ s->blocked_rdev = rdev;
atomic_inc(&rdev->nr_pending);
}
clear_bit(R5_Insync, &dev->flags);
if (test_bit(R5_ReadError, &dev->flags))
clear_bit(R5_Insync, &dev->flags);
if (!test_bit(R5_Insync, &dev->flags)) {
- s.failed++;
- s.failed_num = i;
+ s->failed++;
+ s->failed_num[0] = i;
}
}
+ spin_unlock_irq(&conf->device_lock);
rcu_read_unlock();
- if (unlikely(blocked_rdev)) {
- if (s.syncing || s.expanding || s.expanded ||
- s.to_write || s.written) {
+ if (unlikely(s->blocked_rdev)) {
+ if (s->syncing || s->expanding || s->expanded ||
+ s->to_write || s->written) {
set_bit(STRIPE_HANDLE, &sh->state);
- goto unlock;
+ return 1;
}
/* There is nothing for the blocked_rdev to block */
- rdev_dec_pending(blocked_rdev, conf->mddev);
- blocked_rdev = NULL;
+ rdev_dec_pending(s->blocked_rdev, conf->mddev);
+ s->blocked_rdev = NULL;
}
- if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
- set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+ if (s->to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
+ set_bit(STRIPE_OP_BIOFILL, &s->ops_request);
set_bit(STRIPE_BIOFILL_RUN, &sh->state);
}
pr_debug("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d\n",
- s.locked, s.uptodate, s.to_read, s.to_write,
- s.failed, s.failed_num);
+ s->locked, s->uptodate, s->to_read, s->to_write,
+ s->failed, s->failed_num[0]);
/* check if the array has lost two devices and, if so, some requests might
* need to be failed
*/
- if (s.failed > 1 && s.to_read+s.to_write+s.written)
- handle_failed_stripe(conf, sh, &s, disks, &return_bi);
- if (s.failed > 1 && s.syncing) {
+ if (s->failed > 1 && s->to_read+s->to_write+s->written)
+ handle_failed_stripe(conf, sh, s, disks, &s->return_bi);
+ if (s->failed > 1 && s->syncing) {
md_done_sync(conf->mddev, STRIPE_SECTORS,0);
clear_bit(STRIPE_SYNCING, &sh->state);
- s.syncing = 0;
+ s->syncing = 0;
}
/* might be able to return some write requests if the parity block
* is safe, or on a failed drive
*/
dev = &sh->dev[sh->pd_idx];
- if ( s.written &&
- ((test_bit(R5_Insync, &dev->flags) &&
- !test_bit(R5_LOCKED, &dev->flags) &&
- test_bit(R5_UPTODATE, &dev->flags)) ||
- (s.failed == 1 && s.failed_num == sh->pd_idx)))
- handle_stripe_clean_event(conf, sh, disks, &return_bi);
+ if (s->written &&
+ ((test_bit(R5_Insync, &dev->flags) &&
+ !test_bit(R5_LOCKED, &dev->flags) &&
+ test_bit(R5_UPTODATE, &dev->flags)) ||
+ (s->failed == 1 && s->failed_num[0] == sh->pd_idx)))
+ 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 ||
- (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
- handle_stripe_fill5(sh, &s, disks);
+ if (s->to_read || s->non_overwrite ||
+ (s->syncing && (s->uptodate + s->compute < disks)) || s->expanding)
+ handle_stripe_fill5(sh, s, disks);
/* Now we check to see if any write operations have recently
* completed
if (prexor)
continue;
if (!test_bit(R5_Insync, &dev->flags) ||
- (i == sh->pd_idx && s.failed == 0))
+ (i == sh->pd_idx && s->failed == 0))
set_bit(STRIPE_INSYNC, &sh->state);
}
}
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- dec_preread_active = 1;
+ s->dec_preread_active = 1;
}
/* Now to consider new write requests and what else, if anything
* 2/ A 'check' operation is in flight, as it may clobber the parity
* block.
*/
- if (s.to_write && !sh->reconstruct_state && !sh->check_state)
- handle_stripe_dirtying5(conf, sh, &s, disks);
+ if (s->to_write && !sh->reconstruct_state && !sh->check_state)
+ handle_stripe_dirtying5(conf, sh, s, disks);
/* maybe we need to check and possibly fix the parity for this stripe
* Any reads will already have been scheduled, so we just see if enough
* dependent operations are in flight.
*/
if (sh->check_state ||
- (s.syncing && s.locked == 0 &&
+ (s->syncing && s->locked == 0 &&
!test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
!test_bit(STRIPE_INSYNC, &sh->state)))
- handle_parity_checks5(conf, sh, &s, disks);
+ handle_parity_checks5(conf, sh, s, disks);
- if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
+ if (s->syncing && s->locked == 0
+ && test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS,1);
clear_bit(STRIPE_SYNCING, &sh->state);
}
/* If the failed drive is just a ReadError, then we might need to progress
* the repair/check process
*/
- if (s.failed == 1 && !conf->mddev->ro &&
- test_bit(R5_ReadError, &sh->dev[s.failed_num].flags)
- && !test_bit(R5_LOCKED, &sh->dev[s.failed_num].flags)
- && test_bit(R5_UPTODATE, &sh->dev[s.failed_num].flags)
+ if (s->failed == 1 && !conf->mddev->ro &&
+ test_bit(R5_ReadError, &sh->dev[s->failed_num[0]].flags)
+ && !test_bit(R5_LOCKED, &sh->dev[s->failed_num[0]].flags)
+ && test_bit(R5_UPTODATE, &sh->dev[s->failed_num[0]].flags)
) {
- dev = &sh->dev[s.failed_num];
+ dev = &sh->dev[s->failed_num[0]];
if (!test_bit(R5_ReWrite, &dev->flags)) {
set_bit(R5_Wantwrite, &dev->flags);
set_bit(R5_ReWrite, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
- s.locked++;
+ s->locked++;
} else {
/* let's read it back */
set_bit(R5_Wantread, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
- s.locked++;
- }
- }
-
- /* Finish reconstruct operations initiated by the expansion process */
- if (sh->reconstruct_state == reconstruct_state_result) {
- struct stripe_head *sh2
- = get_active_stripe(conf, sh->sector, 1, 1, 1);
- if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
- /* sh cannot be written until sh2 has been read.
- * so arrange for sh to be delayed a little
- */
- set_bit(STRIPE_DELAYED, &sh->state);
- set_bit(STRIPE_HANDLE, &sh->state);
- if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
- &sh2->state))
- atomic_inc(&conf->preread_active_stripes);
- release_stripe(sh2);
- goto unlock;
- }
- if (sh2)
- release_stripe(sh2);
-
- sh->reconstruct_state = reconstruct_state_idle;
- clear_bit(STRIPE_EXPANDING, &sh->state);
- for (i = conf->raid_disks; i--; ) {
- set_bit(R5_Wantwrite, &sh->dev[i].flags);
- set_bit(R5_LOCKED, &sh->dev[i].flags);
- s.locked++;
+ s->locked++;
}
}
-
- if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
- !sh->reconstruct_state) {
- /* Need to write out all blocks after computing parity */
- sh->disks = conf->raid_disks;
- stripe_set_idx(sh->sector, conf, 0, sh);
- schedule_reconstruction(sh, &s, 1, 1);
- } else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
- clear_bit(STRIPE_EXPAND_READY, &sh->state);
- atomic_dec(&conf->reshape_stripes);
- wake_up(&conf->wait_for_overlap);
- md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
- }
-
- if (s.expanding && s.locked == 0 &&
- !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
- handle_stripe_expansion(conf, sh, NULL);
-
- unlock:
- spin_unlock(&sh->lock);
-
- /* wait for this device to become unblocked */
- if (unlikely(blocked_rdev))
- md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
-
- if (s.ops_request)
- raid_run_ops(sh, s.ops_request);
-
- ops_run_io(sh, &s);
-
- if (dec_preread_active) {
- /* We delay this until after ops_run_io so that if make_request
- * is waiting on a flush, it won't continue until the writes
- * have actually been submitted.
- */
- atomic_dec(&conf->preread_active_stripes);
- if (atomic_read(&conf->preread_active_stripes) <
- IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
- }
- return_io(return_bi);
+ return 0;
}
-static void handle_stripe6(struct stripe_head *sh)
+static int handle_stripe6(struct stripe_head *sh, struct stripe_head_state *s)
{
raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks;
- struct bio *return_bi = NULL;
int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx;
- struct stripe_head_state s;
- struct r6_state r6s;
struct r5dev *dev, *pdev, *qdev;
- mdk_rdev_t *blocked_rdev = NULL;
- int dec_preread_active = 0;
- pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
- "pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
- (unsigned long long)sh->sector, sh->state,
- atomic_read(&sh->count), pd_idx, qd_idx,
- sh->check_state, sh->reconstruct_state);
- memset(&s, 0, sizeof(s));
-
- spin_lock(&sh->lock);
- clear_bit(STRIPE_HANDLE, &sh->state);
- clear_bit(STRIPE_DELAYED, &sh->state);
-
- s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
- s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
- s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
/* Now to look around and see what can be done */
rcu_read_lock();
+ spin_lock_irq(&conf->device_lock);
for (i=disks; i--; ) {
mdk_rdev_t *rdev;
dev = &sh->dev[i];
set_bit(R5_Wantfill, &dev->flags);
/* now count some things */
- if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
- if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
+ if (test_bit(R5_LOCKED, &dev->flags))
+ s->locked++;
+ if (test_bit(R5_UPTODATE, &dev->flags))
+ s->uptodate++;
if (test_bit(R5_Wantcompute, &dev->flags)) {
- s.compute++;
- BUG_ON(s.compute > 2);
+ s->compute++;
+ BUG_ON(s->compute > 2);
}
if (test_bit(R5_Wantfill, &dev->flags)) {
- s.to_fill++;
+ s->to_fill++;
} else if (dev->toread)
- s.to_read++;
+ s->to_read++;
if (dev->towrite) {
- s.to_write++;
+ s->to_write++;
if (!test_bit(R5_OVERWRITE, &dev->flags))
- s.non_overwrite++;
+ s->non_overwrite++;
}
if (dev->written)
- s.written++;
+ s->written++;
rdev = rcu_dereference(conf->disks[i].rdev);
- if (blocked_rdev == NULL &&
+ if (s->blocked_rdev == NULL &&
rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
- blocked_rdev = rdev;
+ s->blocked_rdev = rdev;
atomic_inc(&rdev->nr_pending);
}
clear_bit(R5_Insync, &dev->flags);
if (test_bit(R5_ReadError, &dev->flags))
clear_bit(R5_Insync, &dev->flags);
if (!test_bit(R5_Insync, &dev->flags)) {
- if (s.failed < 2)
- r6s.failed_num[s.failed] = i;
- s.failed++;
+ if (s->failed < 2)
+ s->failed_num[s->failed] = i;
+ s->failed++;
}
}
+ spin_unlock_irq(&conf->device_lock);
rcu_read_unlock();
- if (unlikely(blocked_rdev)) {
- if (s.syncing || s.expanding || s.expanded ||
- s.to_write || s.written) {
+ if (unlikely(s->blocked_rdev)) {
+ if (s->syncing || s->expanding || s->expanded ||
+ s->to_write || s->written) {
set_bit(STRIPE_HANDLE, &sh->state);
- goto unlock;
+ return 1;
}
/* There is nothing for the blocked_rdev to block */
- rdev_dec_pending(blocked_rdev, conf->mddev);
- blocked_rdev = NULL;
+ rdev_dec_pending(s->blocked_rdev, conf->mddev);
+ s->blocked_rdev = NULL;
}
- if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
- set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+ if (s->to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
+ set_bit(STRIPE_OP_BIOFILL, &s->ops_request);
set_bit(STRIPE_BIOFILL_RUN, &sh->state);
}
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,
- r6s.failed_num[0], r6s.failed_num[1]);
+ s->locked, s->uptodate, s->to_read, s->to_write, s->failed,
+ s->failed_num[0], s->failed_num[1]);
/* check if the array has lost >2 devices and, if so, some requests
* might need to be failed
*/
- if (s.failed > 2 && s.to_read+s.to_write+s.written)
- handle_failed_stripe(conf, sh, &s, disks, &return_bi);
- if (s.failed > 2 && s.syncing) {
+ if (s->failed > 2 && s->to_read+s->to_write+s->written)
+ handle_failed_stripe(conf, sh, s, disks, &s->return_bi);
+ if (s->failed > 2 && s->syncing) {
md_done_sync(conf->mddev, STRIPE_SECTORS,0);
clear_bit(STRIPE_SYNCING, &sh->state);
- s.syncing = 0;
+ s->syncing = 0;
}
/*
* are safe, or on a failed drive
*/
pdev = &sh->dev[pd_idx];
- r6s.p_failed = (s.failed >= 1 && r6s.failed_num[0] == pd_idx)
- || (s.failed >= 2 && r6s.failed_num[1] == pd_idx);
+ s->p_failed = (s->failed >= 1 && s->failed_num[0] == pd_idx)
+ || (s->failed >= 2 && s->failed_num[1] == pd_idx);
qdev = &sh->dev[qd_idx];
- r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == qd_idx)
- || (s.failed >= 2 && r6s.failed_num[1] == qd_idx);
+ s->q_failed = (s->failed >= 1 && s->failed_num[0] == qd_idx)
+ || (s->failed >= 2 && s->failed_num[1] == qd_idx);
- if ( s.written &&
- ( r6s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
+ if (s->written &&
+ (s->p_failed || ((test_bit(R5_Insync, &pdev->flags)
&& !test_bit(R5_LOCKED, &pdev->flags)
&& test_bit(R5_UPTODATE, &pdev->flags)))) &&
- ( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
+ (s->q_failed || ((test_bit(R5_Insync, &qdev->flags)
&& !test_bit(R5_LOCKED, &qdev->flags)
&& test_bit(R5_UPTODATE, &qdev->flags)))))
- handle_stripe_clean_event(conf, sh, disks, &return_bi);
+ 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 || (s.to_write && s.failed) ||
- (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
- handle_stripe_fill6(sh, &s, &r6s, disks);
+ if (s->to_read || s->non_overwrite || (s->to_write && s->failed) ||
+ (s->syncing && (s->uptodate + s->compute < disks)) || s->expanding)
+ handle_stripe_fill6(sh, s, disks);
/* Now we check to see if any write operations have recently
* completed
set_bit(R5_Wantwrite, &dev->flags);
if (!test_bit(R5_Insync, &dev->flags) ||
((i == sh->pd_idx || i == qd_idx) &&
- s.failed == 0))
+ s->failed == 0))
set_bit(STRIPE_INSYNC, &sh->state);
}
}
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- dec_preread_active = 1;
+ s->dec_preread_active = 1;
}
/* Now to consider new write requests and what else, if anything
* 2/ A 'check' operation is in flight, as it may clobber the parity
* block.
*/
- if (s.to_write && !sh->reconstruct_state && !sh->check_state)
- handle_stripe_dirtying6(conf, sh, &s, &r6s, disks);
+ if (s->to_write && !sh->reconstruct_state && !sh->check_state)
+ handle_stripe_dirtying6(conf, sh, s, disks);
/* maybe we need to check and possibly fix the parity for this stripe
* Any reads will already have been scheduled, so we just see if enough
* dependent operations are in flight.
*/
if (sh->check_state ||
- (s.syncing && s.locked == 0 &&
+ (s->syncing && s->locked == 0 &&
!test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
!test_bit(STRIPE_INSYNC, &sh->state)))
- handle_parity_checks6(conf, sh, &s, &r6s, disks);
+ handle_parity_checks6(conf, sh, s, disks);
- if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
+ if (s->syncing && s->locked == 0
+ && test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS,1);
clear_bit(STRIPE_SYNCING, &sh->state);
}
/* If the failed drives are just a ReadError, then we might need
* to progress the repair/check process
*/
- if (s.failed <= 2 && !conf->mddev->ro)
- for (i = 0; i < s.failed; i++) {
- dev = &sh->dev[r6s.failed_num[i]];
+ if (s->failed <= 2 && !conf->mddev->ro)
+ for (i = 0; i < s->failed; i++) {
+ dev = &sh->dev[s->failed_num[i]];
if (test_bit(R5_ReadError, &dev->flags)
&& !test_bit(R5_LOCKED, &dev->flags)
&& test_bit(R5_UPTODATE, &dev->flags)
set_bit(R5_Wantwrite, &dev->flags);
set_bit(R5_ReWrite, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
- s.locked++;
+ s->locked++;
} else {
/* let's read it back */
set_bit(R5_Wantread, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
- s.locked++;
+ s->locked++;
}
}
}
+ return 0;
+}
+
+static void handle_stripe(struct stripe_head *sh)
+{
+ struct stripe_head_state s;
+ int done;
+ int i;
+ raid5_conf_t *conf = sh->raid_conf;
+
+ clear_bit(STRIPE_HANDLE, &sh->state);
+ if (test_and_set_bit(STRIPE_ACTIVE, &sh->state)) {
+ /* already being handled, ensure it gets handled
+ * again when current action finishes */
+ set_bit(STRIPE_HANDLE, &sh->state);
+ return;
+ }
+
+ if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+ set_bit(STRIPE_SYNCING, &sh->state);
+ clear_bit(STRIPE_INSYNC, &sh->state);
+ }
+ clear_bit(STRIPE_DELAYED, &sh->state);
+
+ pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
+ "pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
+ (unsigned long long)sh->sector, sh->state,
+ atomic_read(&sh->count), sh->pd_idx, sh->qd_idx,
+ sh->check_state, sh->reconstruct_state);
+ memset(&s, 0, sizeof(s));
+ s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
+ s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
+ s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
+
+ if (conf->level == 6)
+ done = handle_stripe6(sh, &s);
+ else
+ done = handle_stripe5(sh, &s);
+
+ if (done)
+ goto finish;
/* Finish reconstruct operations initiated by the expansion process */
if (sh->reconstruct_state == reconstruct_state_result) {
+ struct stripe_head *sh_src
+ = get_active_stripe(conf, sh->sector, 1, 1, 1);
+ if (sh_src && test_bit(STRIPE_EXPAND_SOURCE, &sh_src->state)) {
+ /* sh cannot be written until sh_src has been read.
+ * so arrange for sh to be delayed a little
+ */
+ set_bit(STRIPE_DELAYED, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
+ &sh_src->state))
+ atomic_inc(&conf->preread_active_stripes);
+ release_stripe(sh_src);
+ goto finish;
+ }
+ if (sh_src)
+ release_stripe(sh_src);
+
sh->reconstruct_state = reconstruct_state_idle;
clear_bit(STRIPE_EXPANDING, &sh->state);
for (i = conf->raid_disks; i--; ) {
if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
!sh->reconstruct_state) {
- struct stripe_head *sh2
- = get_active_stripe(conf, sh->sector, 1, 1, 1);
- if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
- /* sh cannot be written until sh2 has been read.
- * so arrange for sh to be delayed a little
- */
- set_bit(STRIPE_DELAYED, &sh->state);
- set_bit(STRIPE_HANDLE, &sh->state);
- if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
- &sh2->state))
- atomic_inc(&conf->preread_active_stripes);
- release_stripe(sh2);
- goto unlock;
- }
- if (sh2)
- release_stripe(sh2);
-
- /* Need to write out all blocks after computing P&Q */
+ /* Need to write out all blocks after computing parity */
sh->disks = conf->raid_disks;
stripe_set_idx(sh->sector, conf, 0, sh);
schedule_reconstruction(sh, &s, 1, 1);
if (s.expanding && s.locked == 0 &&
!test_bit(STRIPE_COMPUTE_RUN, &sh->state))
- handle_stripe_expansion(conf, sh, &r6s);
-
- unlock:
- spin_unlock(&sh->lock);
+ handle_stripe_expansion(conf, sh);
+finish:
/* wait for this device to become unblocked */
- if (unlikely(blocked_rdev))
- md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+ if (unlikely(s.blocked_rdev))
+ md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev);
if (s.ops_request)
raid_run_ops(sh, s.ops_request);
ops_run_io(sh, &s);
- if (dec_preread_active) {
+ if (s.dec_preread_active) {
/* We delay this until after ops_run_io so that if make_request
* is waiting on a flush, it won't continue until the writes
* have actually been submitted.
md_wakeup_thread(conf->mddev->thread);
}
- return_io(return_bi);
-}
+ return_io(s.return_bi);
-static void handle_stripe(struct stripe_head *sh)
-{
- if (sh->raid_conf->level == 6)
- handle_stripe6(sh);
- else
- handle_stripe5(sh);
+ clear_bit(STRIPE_ACTIVE, &sh->state);
}
static void raid5_activate_delayed(raid5_conf_t *conf)
}
}
- if (bio_data_dir(bi) == WRITE &&
+ if (rw == WRITE &&
logical_sector >= mddev->suspend_lo &&
logical_sector < mddev->suspend_hi) {
release_stripe(sh);
}
if (test_bit(STRIPE_EXPANDING, &sh->state) ||
- !add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
+ !add_stripe_bio(sh, bi, dd_idx, rw)) {
/* Stripe is busy expanding or
* add failed due to overlap. Flush everything
* and wait a while
bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
- spin_lock(&sh->lock);
- set_bit(STRIPE_SYNCING, &sh->state);
- clear_bit(STRIPE_INSYNC, &sh->state);
- spin_unlock(&sh->lock);
+ set_bit(STRIPE_SYNC_REQUESTED, &sh->state);
handle_stripe(sh);
release_stripe(sh);