1 files changed, 47 insertions, 20 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d26767246d2..04348d76bb3 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -196,12 +196,14 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
                 BUG_ON(!list_empty(&sh->lru));
                 BUG_ON(atomic_read(&conf->active_stripes)==0);
                 if (test_bit(STRIPE_HANDLE, &sh->state)) {
-                        if (test_bit(STRIPE_DELAYED, &sh->state))
+                        if (test_bit(STRIPE_DELAYED, &sh->state) &&
+                            !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
                                 list_add_tail(&sh->lru, &conf->delayed_list);
                         else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
                                    sh->bm_seq - conf->seq_write > 0)
                                 list_add_tail(&sh->lru, &conf->bitmap_list);
                         else {
+                                clear_bit(STRIPE_DELAYED, &sh->state);
                                 clear_bit(STRIPE_BIT_DELAY, &sh->state);
                                 list_add_tail(&sh->lru, &conf->handle_list);
                         }
@@ -606,6 +608,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
                                          * a chance*/
                                         md_check_recovery(conf->mddev);
                                 }
+                                /*
+                                 * Because md_wait_for_blocked_rdev
+                                 * will dec nr_pending, we must
+                                 * increment it first.
+                                 */
+                                atomic_inc(&rdev->nr_pending);
                                 md_wait_for_blocked_rdev(rdev, conf->mddev);
                         } else {
                                 /* Acknowledged bad block - skip the write */
@@ -1737,6 +1745,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
         } else {
                 const char *bdn = bdevname(rdev->bdev, b);
                 int retry = 0;
+                int set_bad = 0;
 
                 clear_bit(R5_UPTODATE, &sh->dev[i].flags);
                 atomic_inc(&rdev->read_errors);
@@ -1748,7 +1757,8 @@ static void raid5_end_read_request(struct bio * bi, int error)
                                 mdname(conf->mddev),
                                 (unsigned long long)s,
                                 bdn);
-                else if (conf->mddev->degraded >= conf->max_degraded)
+                else if (conf->mddev->degraded >= conf->max_degraded) {
+                        set_bad = 1;
                         printk_ratelimited(
                                 KERN_WARNING
                                 "md/raid:%s: read error not correctable "
@@ -1756,8 +1766,9 @@ static void raid5_end_read_request(struct bio * bi, int error)
                                 mdname(conf->mddev),
                                 (unsigned long long)s,
                                 bdn);
-                else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
+                } else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) {
                         /* Oh, no!!! */
+                        set_bad = 1;
                         printk_ratelimited(
                                 KERN_WARNING
                                 "md/raid:%s: read error NOT corrected!! "
@@ -1765,7 +1776,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
                                 mdname(conf->mddev),
                                 (unsigned long long)s,
                                 bdn);
-                else if (atomic_read(&rdev->read_errors)
+                } else if (atomic_read(&rdev->read_errors)
                          > conf->max_nr_stripes)
                         printk(KERN_WARNING
                                "md/raid:%s: Too many read errors, failing device %s.\n",
@@ -1777,7 +1788,11 @@ static void raid5_end_read_request(struct bio * bi, int error)
                 else {
                         clear_bit(R5_ReadError, &sh->dev[i].flags);
                         clear_bit(R5_ReWrite, &sh->dev[i].flags);
-                        md_error(conf->mddev, rdev);
+                        if (!(set_bad
+                              && test_bit(In_sync, &rdev->flags)
+                              && rdev_set_badblocks(
+                                      rdev, sh->sector, STRIPE_SECTORS, 0)))
+                                md_error(conf->mddev, rdev);
                 }
         }
         rdev_dec_pending(rdev, conf->mddev);
@@ -3582,8 +3597,18 @@ static void handle_stripe(struct stripe_head *sh)
 
 finish:
         /* wait for this device to become unblocked */
-        if (conf->mddev->external && unlikely(s.blocked_rdev))
-                md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev);
+        if (unlikely(s.blocked_rdev)) {
+                if (conf->mddev->external)
+                        md_wait_for_blocked_rdev(s.blocked_rdev,
+                                                 conf->mddev);
+                else
+                        /* Internal metadata will immediately
+                         * be written by raid5d, so we don't
+                         * need to wait here.
+                         */
+                        rdev_dec_pending(s.blocked_rdev,
+                                         conf->mddev);
+        }
 
         if (s.handle_bad_blocks)
                 for (i = disks; i--; ) {
@@ -3881,8 +3906,6 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
                 raid_bio->bi_next = (void*)rdev;
                 align_bi->bi_bdev =  rdev->bdev;
                 align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
-                /* No reshape active, so we can trust rdev->data_offset */
-                align_bi->bi_sector += rdev->data_offset;
 
                 if (!bio_fits_rdev(align_bi) ||
                     is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9,
@@ -3893,6 +3916,9 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
                         return 0;
                 }
 
+                /* No reshape active, so we can trust rdev->data_offset */
+                align_bi->bi_sector += rdev->data_offset;
+
                 spin_lock_irq(&conf->device_lock);
                 wait_event_lock_irq(conf->wait_for_stripe,
                                     conf->quiesce == 0,
@@ -3971,7 +3997,6 @@ static void make_request(struct mddev *mddev, struct bio * bi)
         struct stripe_head *sh;
         const int rw = bio_data_dir(bi);
         int remaining;
-        int plugged;
 
         if (unlikely(bi->bi_rw & REQ_FLUSH)) {
                 md_flush_request(mddev, bi);
@@ -3990,7 +4015,6 @@ static void make_request(struct mddev *mddev, struct bio * bi)
         bi->bi_next = NULL;
         bi->bi_phys_segments = 1;       /* over-loaded to count active stripes */
 
-        plugged = mddev_check_plugged(mddev);
         for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
                 DEFINE_WAIT(w);
                 int previous;
@@ -4092,6 +4116,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
                         if ((bi->bi_rw & REQ_SYNC) &&
                             !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
                                 atomic_inc(&conf->preread_active_stripes);
+                        mddev_check_plugged(mddev);
                         release_stripe(sh);
                 } else {
                         /* cannot get stripe for read-ahead, just give-up */
@@ -4099,10 +4124,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
                         finish_wait(&conf->wait_for_overlap, &w);
                         break;
                 }
-                        
         }
-        if (!plugged)
-                md_wakeup_thread(mddev->thread);
 
         spin_lock_irq(&conf->device_lock);
         remaining = raid5_dec_bi_phys_segments(bi);
@@ -4823,6 +4845,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
         int raid_disk, memory, max_disks;
         struct md_rdev *rdev;
         struct disk_info *disk;
+        char pers_name[6];
 
         if (mddev->new_level != 5
             && mddev->new_level != 4
@@ -4946,7 +4969,8 @@ static struct r5conf *setup_conf(struct mddev *mddev)
                 printk(KERN_INFO "md/raid:%s: allocated %dkB\n",
                        mdname(mddev), memory);
 
-        conf->thread = md_register_thread(raid5d, mddev, NULL);
+        sprintf(pers_name, "raid%d", mddev->new_level);
+        conf->thread = md_register_thread(raid5d, mddev, pers_name);
         if (!conf->thread) {
                 printk(KERN_ERR
                        "md/raid:%s: couldn't allocate thread.\n",
@@ -5465,10 +5489,9 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
         if (rdev->saved_raid_disk >= 0 &&
             rdev->saved_raid_disk >= first &&
             conf->disks[rdev->saved_raid_disk].rdev == NULL)
-                disk = rdev->saved_raid_disk;
-        else
-                disk = first;
-        for ( ; disk <= last ; disk++) {
+                first = rdev->saved_raid_disk;
+
+        for (disk = first; disk <= last; disk++) {
                 p = conf->disks + disk;
                 if (p->rdev == NULL) {
                         clear_bit(In_sync, &rdev->flags);
@@ -5477,8 +5500,11 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
                         if (rdev->saved_raid_disk != disk)
                                 conf->fullsync = 1;
                         rcu_assign_pointer(p->rdev, rdev);
-                        break;
+                        goto out;
                 }
+        }
+        for (disk = first; disk <= last; disk++) {
+                p = conf->disks + disk;
                 if (test_bit(WantReplacement, &p->rdev->flags) &&
                     p->replacement == NULL) {
                         clear_bit(In_sync, &rdev->flags);
@@ -5490,6 +5516,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
                         break;
                 }
         }
+out:
         print_raid5_conf(conf);
         return err;
 }