5 files changed, 58 insertions, 35 deletions

diff --git a/drivers/md/linear.h b/drivers/md/linear.h
index 0ce29b61605a..2f2da05b2ce9 100644
--- a/drivers/md/linear.h
+++ b/drivers/md/linear.h
@@ -10,9 +10,9 @@ typedef struct dev_info dev_info_t;
 
 struct linear_private_data
 {
+        struct rcu_head         rcu;
         sector_t                array_sectors;
         dev_info_t              disks[0];
-        struct rcu_head         rcu;
 };
 
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8e221a20f5d9..5404b2295820 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -848,7 +848,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
         bio->bi_end_io = super_written;
 
         atomic_inc(&mddev->pending_writes);
-        submit_bio(REQ_WRITE | REQ_SYNC | REQ_FLUSH | REQ_FUA, bio);
+        submit_bio(WRITE_FLUSH_FUA, bio);
 }
 
 void md_super_wait(mddev_t *mddev)
@@ -1138,8 +1138,11 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
                         ret = 0;
         }
         rdev->sectors = rdev->sb_start;
+        /* Limit to 4TB as metadata cannot record more than that */
+        if (rdev->sectors >= (2ULL << 32))
+                rdev->sectors = (2ULL << 32) - 2;
 
-        if (rdev->sectors < sb->size * 2 && sb->level > 1)
+        if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
                 /* "this cannot possibly happen" ... */
                 ret = -EINVAL;
 
@@ -1173,7 +1176,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
                 mddev->clevel[0] = 0;
                 mddev->layout = sb->layout;
                 mddev->raid_disks = sb->raid_disks;
-                mddev->dev_sectors = sb->size * 2;
+                mddev->dev_sectors = ((sector_t)sb->size) * 2;
                 mddev->events = ev1;
                 mddev->bitmap_info.offset = 0;
                 mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
@@ -1415,6 +1418,11 @@ super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
         rdev->sb_start = calc_dev_sboffset(rdev);
         if (!num_sectors || num_sectors > rdev->sb_start)
                 num_sectors = rdev->sb_start;
+        /* Limit to 4TB as metadata cannot record more than that.
+         * 4TB == 2^32 KB, or 2*2^32 sectors.
+         */
+        if (num_sectors >= (2ULL << 32))
+                num_sectors = (2ULL << 32) - 2;
         md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
                        rdev->sb_page);
         md_super_wait(rdev->mddev);
@@ -1738,6 +1746,11 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
         sb->level = cpu_to_le32(mddev->level);
         sb->layout = cpu_to_le32(mddev->layout);
 
+        if (test_bit(WriteMostly, &rdev->flags))
+                sb->devflags |= WriteMostly1;
+        else
+                sb->devflags &= ~WriteMostly1;
+
         if (mddev->bitmap && mddev->bitmap_info.file == NULL) {
                 sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_info.offset);
                 sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
@@ -2561,7 +2574,10 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
         int err = -EINVAL;
         if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
                 md_error(rdev->mddev, rdev);
-                err = 0;
+                if (test_bit(Faulty, &rdev->flags))
+                        err = 0;
+                else
+                        err = -EBUSY;
         } else if (cmd_match(buf, "remove")) {
                 if (rdev->raid_disk >= 0)
                         err = -EBUSY;
@@ -2584,7 +2600,7 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
                 err = 0;
         } else if (cmd_match(buf, "-blocked")) {
                 if (!test_bit(Faulty, &rdev->flags) &&
-                    test_bit(BlockedBadBlocks, &rdev->flags)) {
+                    rdev->badblocks.unacked_exist) {
                         /* metadata handler doesn't understand badblocks,
                          * so we need to fail the device
                          */
@@ -5983,6 +5999,8 @@ static int set_disk_faulty(mddev_t *mddev, dev_t dev)
                 return -ENODEV;
 
         md_error(mddev, rdev);
+        if (!test_bit(Faulty, &rdev->flags))
+                return -EBUSY;
         return 0;
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 32323f0afd89..f4622dd8fc59 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1099,12 +1099,11 @@ read_again:
                 bio_list_add(&conf->pending_bio_list, mbio);
                 spin_unlock_irqrestore(&conf->device_lock, flags);
         }
-        r1_bio_write_done(r1_bio);
-
-        /* In case raid1d snuck in to freeze_array */
-        wake_up(&conf->wait_barrier);
-
+        /* Mustn't call r1_bio_write_done before this next test,
+         * as it could result in the bio being freed.
+         */
         if (sectors_handled < (bio->bi_size >> 9)) {
+                r1_bio_write_done(r1_bio);
                 /* We need another r1_bio.  It has already been counted
                  * in bio->bi_phys_segments
                  */
@@ -1117,6 +1116,11 @@ read_again:
                 goto retry_write;
         }
 
+        r1_bio_write_done(r1_bio);
+
+        /* In case raid1d snuck in to freeze_array */
+        wake_up(&conf->wait_barrier);
+
         if (do_sync || !bitmap || !plugged)
                 md_wakeup_thread(mddev->thread);
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8b29cd4f01c8..d7a8468ddeab 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -337,6 +337,21 @@ static void close_write(r10bio_t *r10_bio)
         md_write_end(r10_bio->mddev);
 }
 
+static void one_write_done(r10bio_t *r10_bio)
+{
+        if (atomic_dec_and_test(&r10_bio->remaining)) {
+                if (test_bit(R10BIO_WriteError, &r10_bio->state))
+                        reschedule_retry(r10_bio);
+                else {
+                        close_write(r10_bio);
+                        if (test_bit(R10BIO_MadeGood, &r10_bio->state))
+                                reschedule_retry(r10_bio);
+                        else
+                                raid_end_bio_io(r10_bio);
+                }
+        }
+}
+
 static void raid10_end_write_request(struct bio *bio, int error)
 {
         int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -387,17 +402,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
          * Let's see if all mirrored write operations have finished
          * already.
          */
-        if (atomic_dec_and_test(&r10_bio->remaining)) {
-                if (test_bit(R10BIO_WriteError, &r10_bio->state))
-                        reschedule_retry(r10_bio);
-                else {
-                        close_write(r10_bio);
-                        if (test_bit(R10BIO_MadeGood, &r10_bio->state))
-                                reschedule_retry(r10_bio);
-                        else
-                                raid_end_bio_io(r10_bio);
-                }
-        }
+        one_write_done(r10_bio);
         if (dec_rdev)
                 rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
 }
@@ -1127,20 +1132,12 @@ retry_write:
                 spin_unlock_irqrestore(&conf->device_lock, flags);
         }
 
-        if (atomic_dec_and_test(&r10_bio->remaining)) {
-                /* This matches the end of raid10_end_write_request() */
-                bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
-                                r10_bio->sectors,
-                                !test_bit(R10BIO_Degraded, &r10_bio->state),
-                                0);
-                md_write_end(mddev);
-                raid_end_bio_io(r10_bio);
-        }
-
-        /* In case raid10d snuck in to freeze_array */
-        wake_up(&conf->wait_barrier);
+        /* Don't remove the bias on 'remaining' (one_write_done) until
+         * after checking if we need to go around again.
+         */
 
         if (sectors_handled < (bio->bi_size >> 9)) {
+                one_write_done(r10_bio);
                 /* We need another r10_bio.  It has already been counted
                  * in bio->bi_phys_segments.
                  */
@@ -1154,6 +1151,10 @@ retry_write:
                 r10_bio->state = 0;
                 goto retry_write;
         }
+        one_write_done(r10_bio);
+
+        /* In case raid10d snuck in to freeze_array */
+        wake_up(&conf->wait_barrier);
 
         if (do_sync || !mddev->bitmap || !plugged)
                 md_wakeup_thread(mddev->thread);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dbae459fb02d..43709fa6b6df 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3336,7 +3336,7 @@ static void handle_stripe(struct stripe_head *sh)
 
 finish:
         /* wait for this device to become unblocked */
-        if (unlikely(s.blocked_rdev))
+        if (conf->mddev->external && unlikely(s.blocked_rdev))
                 md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev);
 
         if (s.handle_bad_blocks)