4 files changed, 48 insertions, 38 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 06b0ded1ce23..3319c2fec28e 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1097,14 +1097,12 @@ void bitmap_daemon_work(struct bitmap *bitmap)
         }
         bitmap->allclean = 1;
 
+        spin_lock_irqsave(&bitmap->lock, flags);
         for (j = 0; j < bitmap->chunks; j++) {
                 bitmap_counter_t *bmc;
-                spin_lock_irqsave(&bitmap->lock, flags);
-                if (!bitmap->filemap) {
+                if (!bitmap->filemap)
                         /* error or shutdown */
-                        spin_unlock_irqrestore(&bitmap->lock, flags);
                         break;
-                }
 
                 page = filemap_get_page(bitmap, j);
 
@@ -1121,6 +1119,8 @@ void bitmap_daemon_work(struct bitmap *bitmap)
                                         write_page(bitmap, page, 0);
                                         bitmap->allclean = 0;
                                 }
+                                spin_lock_irqsave(&bitmap->lock, flags);
+                                j |= (PAGE_BITS - 1);
                                 continue;
                         }
 
@@ -1181,9 +1181,10 @@ void bitmap_daemon_work(struct bitmap *bitmap)
                                         ext2_clear_bit(file_page_offset(j), paddr);
                                 kunmap_atomic(paddr, KM_USER0);
                         }
-                }
-                spin_unlock_irqrestore(&bitmap->lock, flags);
+                } else
+                        j |= PAGE_COUNTER_MASK;
         }
+        spin_unlock_irqrestore(&bitmap->lock, flags);
 
         /* now sync the final page */
         if (lastpage != NULL) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 424f7b048c30..3fd8b1e65483 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -20,7 +20,8 @@
 #include <linux/idr.h>
 #include <linux/hdreg.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
+
+#include <trace/events/block.h>
 
 #define DM_MSG_PREFIX "core"
 
@@ -53,8 +54,6 @@ struct dm_target_io {
         union map_info info;
 };
 
-DEFINE_TRACE(block_bio_complete);
-
 /*
  * For request-based dm.
  * One of these is allocated per request.
@@ -656,8 +655,7 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
                 /* the bio has been remapped so dispatch it */
 
                 trace_block_remap(bdev_get_queue(clone->bi_bdev), clone,
-                                    tio->io->bio->bi_bdev->bd_dev,
-                                    clone->bi_sector, sector);
+                                    tio->io->bio->bi_bdev->bd_dev, sector);
 
                 generic_make_request(clone);
         } else if (r < 0 || r == DM_MAPIO_REQUEUE) {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4cbc19f5c304..20f6ac338349 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1375,6 +1375,9 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 
         sb->raid_disks = cpu_to_le32(mddev->raid_disks);
         sb->size = cpu_to_le64(mddev->dev_sectors);
+        sb->chunksize = cpu_to_le32(mddev->chunk_size >> 9);
+        sb->level = cpu_to_le32(mddev->level);
+        sb->layout = cpu_to_le32(mddev->layout);
 
         if (mddev->bitmap && mddev->bitmap_file == NULL) {
                 sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
@@ -3303,7 +3306,9 @@ static ssize_t
 action_show(mddev_t *mddev, char *page)
 {
         char *type = "idle";
-        if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+        if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+                type = "frozen";
+        else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
             (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
                 if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
                         type = "reshape";
@@ -3326,7 +3331,12 @@ action_store(mddev_t *mddev, const char *page, size_t len)
         if (!mddev->pers || !mddev->pers->sync_request)
                 return -EINVAL;
 
-        if (cmd_match(page, "idle")) {
+        if (cmd_match(page, "frozen"))
+                set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+        else
+                clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+
+        if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
                 if (mddev->sync_thread) {
                         set_bit(MD_RECOVERY_INTR, &mddev->recovery);
                         md_unregister_thread(mddev->sync_thread);
@@ -3680,7 +3690,7 @@ array_size_store(mddev_t *mddev, const char *buf, size_t len)
                 if (strict_blocks_to_sectors(buf, &sectors) < 0)
                         return -EINVAL;
                 if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
-                        return -EINVAL;
+                        return -E2BIG;
 
                 mddev->external_size = 1;
         }
@@ -5557,7 +5567,7 @@ static struct block_device_operations md_fops =
         .owner          = THIS_MODULE,
         .open           = md_open,
         .release        = md_release,
-        .locked_ioctl   = md_ioctl,
+        .ioctl          = md_ioctl,
         .getgeo         = md_getgeo,
         .media_changed  = md_media_changed,
         .revalidate_disk= md_revalidate,
@@ -6352,12 +6362,13 @@ void md_do_sync(mddev_t *mddev)
 
                 skipped = 0;
 
-                if ((mddev->curr_resync > mddev->curr_resync_completed &&
-                     (mddev->curr_resync - mddev->curr_resync_completed)
-                    > (max_sectors >> 4)) ||
-                    (j - mddev->curr_resync_completed)*2
-                    >= mddev->resync_max - mddev->curr_resync_completed
-                        ) {
+                if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+                    ((mddev->curr_resync > mddev->curr_resync_completed &&
+                      (mddev->curr_resync - mddev->curr_resync_completed)
+                      > (max_sectors >> 4)) ||
+                     (j - mddev->curr_resync_completed)*2
+                     >= mddev->resync_max - mddev->curr_resync_completed
+                            )) {
                         /* time to update curr_resync_completed */
                         blk_unplug(mddev->queue);
                         wait_event(mddev->recovery_wait,
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7970dc8c522e..bef876698232 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -362,7 +362,7 @@ static void raid5_unplug_device(struct request_queue *q);
 
 static struct stripe_head *
 get_active_stripe(raid5_conf_t *conf, sector_t sector,
-                  int previous, int noblock)
+                  int previous, int noblock, int noquiesce)
 {
         struct stripe_head *sh;
 
@@ -372,7 +372,7 @@ get_active_stripe(raid5_conf_t *conf, sector_t sector,
 
         do {
                 wait_event_lock_irq(conf->wait_for_stripe,
-                                    conf->quiesce == 0,
+                                    conf->quiesce == 0 || noquiesce,
                                     conf->device_lock, /* nothing */);
                 sh = __find_stripe(conf, sector, conf->generation - previous);
                 if (!sh) {
@@ -2671,7 +2671,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
                         sector_t bn = compute_blocknr(sh, i, 1);
                         sector_t s = raid5_compute_sector(conf, bn, 0,
                                                           &dd_idx, NULL);
-                        sh2 = get_active_stripe(conf, s, 0, 1);
+                        sh2 = get_active_stripe(conf, s, 0, 1, 1);
                         if (sh2 == NULL)
                                 /* so far only the early blocks of this stripe
                                  * have been requested.  When later blocks
@@ -2944,7 +2944,7 @@ static bool handle_stripe5(struct stripe_head *sh)
         /* 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);
+                        = 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
@@ -3189,7 +3189,7 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 
         if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
                 struct stripe_head *sh2
-                        = get_active_stripe(conf, sh->sector, 1, 1);
+                        = 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
@@ -3288,7 +3288,7 @@ static void unplug_slaves(mddev_t *mddev)
         int i;
 
         rcu_read_lock();
-        for (i=0; i<mddev->raid_disks; i++) {
+        for (i = 0; i < conf->raid_disks; i++) {
                 mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
                 if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
                         struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
@@ -3675,7 +3675,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
                         (unsigned long long)logical_sector);
 
                 sh = get_active_stripe(conf, new_sector, previous,
-                                       (bi->bi_rw&RWA_MASK));
+                                       (bi->bi_rw&RWA_MASK), 0);
                 if (sh) {
                         if (unlikely(previous)) {
                                 /* expansion might have moved on while waiting for a
@@ -3811,13 +3811,13 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
         safepos = conf->reshape_safe;
         sector_div(safepos, data_disks);
         if (mddev->delta_disks < 0) {
-                writepos -= reshape_sectors;
+                writepos -= min_t(sector_t, reshape_sectors, writepos);
                 readpos += reshape_sectors;
                 safepos += reshape_sectors;
         } else {
                 writepos += reshape_sectors;
-                readpos -= reshape_sectors;
-                safepos -= reshape_sectors;
+                readpos -= min_t(sector_t, reshape_sectors, readpos);
+                safepos -= min_t(sector_t, reshape_sectors, safepos);
         }
 
         /* 'writepos' is the most advanced device address we might write.
@@ -3873,7 +3873,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
         for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
                 int j;
                 int skipped = 0;
-                sh = get_active_stripe(conf, stripe_addr+i, 0, 0);
+                sh = get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
                 set_bit(STRIPE_EXPANDING, &sh->state);
                 atomic_inc(&conf->reshape_stripes);
                 /* If any of this stripe is beyond the end of the old
@@ -3916,13 +3916,13 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
                 raid5_compute_sector(conf, stripe_addr*(new_data_disks),
                                      1, &dd_idx, NULL);
         last_sector =
-                raid5_compute_sector(conf, ((stripe_addr+conf->chunk_size/512)
+                raid5_compute_sector(conf, ((stripe_addr+reshape_sectors)
                                             *(new_data_disks) - 1),
                                      1, &dd_idx, NULL);
         if (last_sector >= mddev->dev_sectors)
                 last_sector = mddev->dev_sectors - 1;
         while (first_sector <= last_sector) {
-                sh = get_active_stripe(conf, first_sector, 1, 0);
+                sh = get_active_stripe(conf, first_sector, 1, 0, 1);
                 set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
                 set_bit(STRIPE_HANDLE, &sh->state);
                 release_stripe(sh);
@@ -4022,9 +4022,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 
         bitmap_cond_end_sync(mddev->bitmap, sector_nr);
 
-        sh = get_active_stripe(conf, sector_nr, 0, 1);
+        sh = get_active_stripe(conf, sector_nr, 0, 1, 0);
         if (sh == NULL) {
-                sh = get_active_stripe(conf, sector_nr, 0, 0);
+                sh = get_active_stripe(conf, sector_nr, 0, 0, 0);
                 /* make sure we don't swamp the stripe cache if someone else
                  * is trying to get access
                  */
@@ -4034,7 +4034,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
          * We don't need to check the 'failed' flag as when that gets set,
          * recovery aborts.
          */
-        for (i=0; i<mddev->raid_disks; i++)
+        for (i = 0; i < conf->raid_disks; i++)
                 if (conf->disks[i].rdev == NULL)
                         still_degraded = 1;
 
@@ -4086,7 +4086,7 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
                         /* already done this stripe */
                         continue;
 
-                sh = get_active_stripe(conf, sector, 0, 1);
+                sh = get_active_stripe(conf, sector, 0, 1, 0);
 
                 if (!sh) {
                         /* failed to get a stripe - must wait */