dm thin: fix discard support to a previously shared block

commit 19fa1a6756ed9e92daa9537c03b47d6b55cc2316 upstream.

If a snapshot is created and later deleted the origin dm_thin_device's
snapshotted_time will have been updated to reflect the snapshot's
creation time.  The 'shared' flag in the dm_thin_lookup_result struct
returned from dm_thin_find_block() is an approximation based on
snapshotted_time -- this is done to avoid 0(n), or worse, time
complexity.  In this case, the shared flag would be true.

But because the 'shared' flag reflects an approximation a block can be
incorrectly assumed to be shared (e.g. false positive for 'shared'
because the snapshot no longer exists).  This could result in discards
issued to a thin device not being passed down to the pool's underlying
data device.

To fix this we double check that a thin block is really still in-use
after a mapping is removed using dm_pool_block_is_used().  If the
reference count for a block is now zero the discard is allowed to be
passed down.

Also add a 'definitely_not_shared' member to the dm_thin_new_mapping
structure -- reflects that the 'shared' flag in the response from
dm_thin_find_block() can only be held as definitive if false is
returned.

Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1043527

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 34 insertions, 2 deletions

diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 60bce435f4fa..33ac3be2e836 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1349,6 +1349,12 @@ dm_thin_id dm_thin_dev_id(struct dm_thin_device *td)
         return td->id;
 }
 
+/*
+ * Check whether @time (of block creation) is older than @td's last snapshot.
+ * If so then the associated block is shared with the last snapshot device.
+ * Any block on a device created *after* the device last got snapshotted is
+ * necessarily not shared.
+ */
 static bool __snapshotted_since(struct dm_thin_device *td, uint32_t time)
 {
         return td->snapshotted_time > time;
@@ -1458,6 +1464,20 @@ int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block)
         return r;
 }
 
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result)
+{
+        int r;
+        uint32_t ref_count;
+
+        down_read(&pmd->root_lock);
+        r = dm_sm_get_count(pmd->data_sm, b, &ref_count);
+        if (!r)
+                *result = (ref_count != 0);
+        up_read(&pmd->root_lock);
+
+        return r;
+}
+
 bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
 {
         int r;
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 845ebbe589a9..125c09444019 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -181,6 +181,8 @@ int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result);
 
 int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
 
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result);
+
 /*
  * Returns -ENOSPC if the new size is too small and already allocated
  * blocks would be lost.
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index e36f81e282eb..d8f1d4e673f6 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -512,6 +512,7 @@ struct dm_thin_new_mapping {
         unsigned quiesced:1;
         unsigned prepared:1;
         unsigned pass_discard:1;
+        unsigned definitely_not_shared:1;
 
         struct thin_c *tc;
         dm_block_t virt_block;
@@ -683,7 +684,15 @@ static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
         cell_defer_no_holder(tc, m->cell2);
 
         if (m->pass_discard)
-                remap_and_issue(tc, m->bio, m->data_block);
+                if (m->definitely_not_shared)
+                        remap_and_issue(tc, m->bio, m->data_block);
+                else {
+                        bool used = false;
+                        if (dm_pool_block_is_used(tc->pool->pmd, m->data_block, &used) || used)
+                                bio_endio(m->bio, 0);
+                        else
+                                remap_and_issue(tc, m->bio, m->data_block);
+                }
         else
                 bio_endio(m->bio, 0);
 
@@ -1032,7 +1041,8 @@ static void process_discard(struct thin_c *tc, struct bio *bio)
                          */
                         m = get_next_mapping(pool);
                         m->tc = tc;
-                        m->pass_discard = (!lookup_result.shared) && pool->pf.discard_passdown;
+                        m->pass_discard = pool->pf.discard_passdown;
+                        m->definitely_not_shared = !lookup_result.shared;
                         m->virt_block = block;
                         m->data_block = lookup_result.block;
                         m->cell = cell;