-
- if (unlikely(blocked_rdev)) {
- 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)) {
- 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);
- /* 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) {
- md_done_sync(conf->mddev, STRIPE_SECTORS,0);
- clear_bit(STRIPE_SYNCING, &sh->state);
- 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);
-
- /* 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);
-
- /* Now we check to see if any write operations have recently
- * completed
- */
- prexor = 0;
- if (sh->reconstruct_state == reconstruct_state_prexor_drain_result)
- prexor = 1;
- if (sh->reconstruct_state == reconstruct_state_drain_result ||
- sh->reconstruct_state == reconstruct_state_prexor_drain_result) {
- sh->reconstruct_state = reconstruct_state_idle;
-
- /* All the 'written' buffers and the parity block are ready to
- * be written back to disk
- */
- BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
- for (i = disks; i--; ) {
- dev = &sh->dev[i];
- if (test_bit(R5_LOCKED, &dev->flags) &&
- (i == sh->pd_idx || dev->written)) {
- pr_debug("Writing block %d\n", i);
- set_bit(R5_Wantwrite, &dev->flags);
- if (prexor)
- continue;
- if (!test_bit(R5_Insync, &dev->flags) ||
- (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;
- }
-
- /* 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.
- * 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);
-
- /* 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
- * data is available. The parity check is held off while parity
- * dependent operations are in flight.
- */
- if (sh->check_state ||
- (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);
-
- 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)
- ) {
- dev = &sh->dev[s.failed_num];
- 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++;
- } 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++;
- }
- }
-
- 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);