10 files changed, 425 insertions, 112 deletions

diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index e6b72d355151..68c0f517c60e 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -124,12 +124,11 @@ the default being 204800 sectors (or 100MB).
 Updating on-disk metadata
 -------------------------
 
-On-disk metadata is committed every time a REQ_SYNC or REQ_FUA bio is
-written.  If no such requests are made then commits will occur every
-second.  This means the cache behaves like a physical disk that has a
-write cache (the same is true of the thin-provisioning target).  If
-power is lost you may lose some recent writes.  The metadata should
-always be consistent in spite of any crash.
+On-disk metadata is committed every time a FLUSH or FUA bio is written.
+If no such requests are made then commits will occur every second.  This
+means the cache behaves like a physical disk that has a volatile write
+cache.  If power is lost you may lose some recent writes.  The metadata
+should always be consistent in spite of any crash.
 
 The 'dirty' state for a cache block changes far too frequently for us
 to keep updating it on the fly.  So we treat it as a hint.  In normal
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 8a7a3d46e0da..05a27e9442bd 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -116,6 +116,35 @@ Resuming a device with a new table itself triggers an event so the
 userspace daemon can use this to detect a situation where a new table
 already exceeds the threshold.
 
+A low water mark for the metadata device is maintained in the kernel and
+will trigger a dm event if free space on the metadata device drops below
+it.
+
+Updating on-disk metadata
+-------------------------
+
+On-disk metadata is committed every time a FLUSH or FUA bio is written.
+If no such requests are made then commits will occur every second.  This
+means the thin-provisioning target behaves like a physical disk that has
+a volatile write cache.  If power is lost you may lose some recent
+writes.  The metadata should always be consistent in spite of any crash.
+
+If data space is exhausted the pool will either error or queue IO
+according to the configuration (see: error_if_no_space).  If metadata
+space is exhausted or a metadata operation fails: the pool will error IO
+until the pool is taken offline and repair is performed to 1) fix any
+potential inconsistencies and 2) clear the flag that imposes repair.
+Once the pool's metadata device is repaired it may be resized, which
+will allow the pool to return to normal operation.  Note that if a pool
+is flagged as needing repair, the pool's data and metadata devices
+cannot be resized until repair is performed.  It should also be noted
+that when the pool's metadata space is exhausted the current metadata
+transaction is aborted.  Given that the pool will cache IO whose
+completion may have already been acknowledged to upper IO layers
+(e.g. filesystem) it is strongly suggested that consistency checks
+(e.g. fsck) be performed on those layers when repair of the pool is
+required.
+
 Thin provisioning
 -----------------
 
@@ -258,10 +287,9 @@ ii) Status
         should register for the event and then check the target's status.
 
     held metadata root:
-        The location, in sectors, of the metadata root that has been
+        The location, in blocks, of the metadata root that has been
         'held' for userspace read access.  '-' indicates there is no
-        held root.  This feature is not yet implemented so '-' is
-        always returned.
+        held root.
 
     discard_passdown|no_discard_passdown
         Whether or not discards are actually being passed down to the
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 9a06fe883766..95ad936e6048 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -254,16 +254,6 @@ config DM_THIN_PROVISIONING
        ---help---
          Provides thin provisioning and snapshots that share a data store.
 
-config DM_DEBUG_BLOCK_STACK_TRACING
-        boolean "Keep stack trace of persistent data block lock holders"
-        depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
-        select STACKTRACE
-        ---help---
-          Enable this for messages that may help debug problems with the
-          block manager locking used by thin provisioning and caching.
-
-          If unsure, say N.
-
 config DM_CACHE
        tristate "Cache target (EXPERIMENTAL)"
        depends on BLK_DEV_DM
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
index 1e018e986610..0e385e40909e 100644
--- a/drivers/md/dm-cache-policy-mq.c
+++ b/drivers/md/dm-cache-policy-mq.c
@@ -872,7 +872,7 @@ static void mq_destroy(struct dm_cache_policy *p)
 {
         struct mq_policy *mq = to_mq_policy(p);
 
-        kfree(mq->table);
+        vfree(mq->table);
         epool_exit(&mq->cache_pool);
         epool_exit(&mq->pre_cache_pool);
         kfree(mq);
@@ -1245,7 +1245,7 @@ static struct dm_cache_policy *mq_create(dm_cblock_t cache_size,
 
         mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16);
         mq->hash_bits = ffs(mq->nr_buckets) - 1;
-        mq->table = kzalloc(sizeof(*mq->table) * mq->nr_buckets, GFP_KERNEL);
+        mq->table = vzalloc(sizeof(*mq->table) * mq->nr_buckets);
         if (!mq->table)
                 goto bad_alloc_table;
 
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index afc3d017de4c..d6e88178d22c 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -546,6 +546,9 @@ static int read_exceptions(struct pstore *ps,
                 r = insert_exceptions(ps, area, callback, callback_context,
                                       &full);
 
+                if (!full)
+                        memcpy(ps->area, area, ps->store->chunk_size << SECTOR_SHIFT);
+
                 dm_bufio_release(bp);
 
                 dm_bufio_forget(client, chunk);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index baa87ff12816..fb9efc829182 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -76,7 +76,7 @@
 
 #define THIN_SUPERBLOCK_MAGIC 27022010
 #define THIN_SUPERBLOCK_LOCATION 0
-#define THIN_VERSION 1
+#define THIN_VERSION 2
 #define THIN_METADATA_CACHE_SIZE 64
 #define SECTOR_TO_BLOCK_SHIFT 3
 
@@ -1755,3 +1755,38 @@ int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd,
 
         return r;
 }
+
+int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd)
+{
+        int r;
+        struct dm_block *sblock;
+        struct thin_disk_superblock *disk_super;
+
+        down_write(&pmd->root_lock);
+        pmd->flags |= THIN_METADATA_NEEDS_CHECK_FLAG;
+
+        r = superblock_lock(pmd, &sblock);
+        if (r) {
+                DMERR("couldn't read superblock");
+                goto out;
+        }
+
+        disk_super = dm_block_data(sblock);
+        disk_super->flags = cpu_to_le32(pmd->flags);
+
+        dm_bm_unlock(sblock);