1 files changed, 80 insertions, 65 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f0d5718d2587..f5fbe576d2ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2822,7 +2822,7 @@ out_free:
         btrfs_release_path(path);
 out:
         spin_lock(&block_group->lock);
-        if (!ret)
+        if (!ret && dcs == BTRFS_DC_SETUP)
                 block_group->cache_generation = trans->transid;
         block_group->disk_cache_state = dcs;
         spin_unlock(&block_group->lock);
@@ -4204,12 +4204,17 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
         u64 to_reserve = 0;
+        u64 csum_bytes;
         unsigned nr_extents = 0;
+        int extra_reserve = 0;
         int flush = 1;
         int ret;
 
+        /* Need to be holding the i_mutex here if we aren't free space cache */
         if (btrfs_is_free_space_inode(root, inode))
                 flush = 0;
+        else
+                WARN_ON(!mutex_is_locked(&inode->i_mutex));
 
         if (flush && btrfs_transaction_in_commit(root->fs_info))
                 schedule_timeout(1);
@@ -4220,11 +4225,9 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
         BTRFS_I(inode)->outstanding_extents++;
 
         if (BTRFS_I(inode)->outstanding_extents >
-            BTRFS_I(inode)->reserved_extents) {
+            BTRFS_I(inode)->reserved_extents)
                 nr_extents = BTRFS_I(inode)->outstanding_extents -
                         BTRFS_I(inode)->reserved_extents;
-                BTRFS_I(inode)->reserved_extents += nr_extents;
-        }
 
         /*
          * Add an item to reserve for updating the inode when we complete the
@@ -4232,11 +4235,12 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
          */
         if (!BTRFS_I(inode)->delalloc_meta_reserved) {
                 nr_extents++;
-                BTRFS_I(inode)->delalloc_meta_reserved = 1;
+                extra_reserve = 1;
         }
 
         to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
         to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+        csum_bytes = BTRFS_I(inode)->csum_bytes;
         spin_unlock(&BTRFS_I(inode)->lock);
 
         ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
@@ -4246,22 +4250,35 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
                 spin_lock(&BTRFS_I(inode)->lock);
                 dropped = drop_outstanding_extent(inode);
-                to_free = calc_csum_metadata_size(inode, num_bytes, 0);
-                spin_unlock(&BTRFS_I(inode)->lock);
-                to_free += btrfs_calc_trans_metadata_size(root, dropped);
-
                 /*
-                 * Somebody could have come in and twiddled with the
-                 * reservation, so if we have to free more than we would have
-                 * reserved from this reservation go ahead and release those
-                 * bytes.
+                 * If the inodes csum_bytes is the same as the original
+                 * csum_bytes then we know we haven't raced with any free()ers
+                 * so we can just reduce our inodes csum bytes and carry on.
+                 * Otherwise we have to do the normal free thing to account for
+                 * the case that the free side didn't free up its reserve
+                 * because of this outstanding reservation.
                  */
-                to_free -= to_reserve;
+                if (BTRFS_I(inode)->csum_bytes == csum_bytes)
+                        calc_csum_metadata_size(inode, num_bytes, 0);
+                else
+                        to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+                spin_unlock(&BTRFS_I(inode)->lock);
+                if (dropped)
+                        to_free += btrfs_calc_trans_metadata_size(root, dropped);
+
                 if (to_free)
                         btrfs_block_rsv_release(root, block_rsv, to_free);
                 return ret;
         }
 
+        spin_lock(&BTRFS_I(inode)->lock);
+        if (extra_reserve) {
+                BTRFS_I(inode)->delalloc_meta_reserved = 1;
+                nr_extents--;
+        }
+        BTRFS_I(inode)->reserved_extents += nr_extents;
+        spin_unlock(&BTRFS_I(inode)->lock);
+
         block_rsv_add_bytes(block_rsv, to_reserve, 1);
 
         return 0;
@@ -5107,11 +5124,11 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
         struct btrfs_root *root = orig_root->fs_info->extent_root;
         struct btrfs_free_cluster *last_ptr = NULL;
         struct btrfs_block_group_cache *block_group = NULL;
+        struct btrfs_block_group_cache *used_block_group;
         int empty_cluster = 2 * 1024 * 1024;
         int allowed_chunk_alloc = 0;
         int done_chunk_alloc = 0;
         struct btrfs_space_info *space_info;
-        int last_ptr_loop = 0;
         int loop = 0;
         int index = 0;
         int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
@@ -5173,6 +5190,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 ideal_cache:
                 block_group = btrfs_lookup_block_group(root->fs_info,
                                                        search_start);
+                used_block_group = block_group;
                 /*
                  * we don't want to use the block group if it doesn't match our
                  * allocation bits, or if its not cached.
@@ -5210,6 +5228,7 @@ search:
                 u64 offset;
                 int cached;
 
+                used_block_group = block_group;
                 btrfs_get_block_group(block_group);
                 search_start = block_group->key.objectid;
 
@@ -5286,71 +5305,62 @@ alloc:
                 spin_unlock(&block_group->free_space_ctl->tree_lock);
 
                 /*
-                 * Ok we want to try and use the cluster allocator, so lets look
-                 * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
-                 * have tried the cluster allocator plenty of times at this
-                 * point and not have found anything, so we are likely way too
-                 * fragmented for the clustering stuff to find anything, so lets
-                 * just skip it and let the allocator find whatever block it can
-                 * find
+                 * Ok we want to try and use the cluster allocator, so
+                 * lets look there
                  */
-                if (last_ptr && loop < LOOP_NO_EMPTY_SIZE) {
+                if (last_ptr) {
                         /*
                          * the refill lock keeps out other
                          * people trying to start a new cluster
                          */
                         spin_lock(&last_ptr->refill_lock);
-                        if (!last_ptr->block_group ||
-                            last_ptr->block_group->ro ||
-                            !block_group_bits(last_ptr->block_group, data))
+                        used_block_group = last_ptr->block_group;
+                        if (used_block_group != block_group &&
+                            (!used_block_group ||
+                             used_block_group->ro ||
+                             !block_group_bits(used_block_group, data))) {
+                                used_block_group = block_group;
                                 goto refill_cluster;
+                        }
+
+                        if (used_block_group != block_group)
+                                btrfs_get_block_group(used_block_group);
 
-                        offset = btrfs_alloc_from_cluster(block_group, last_ptr,
-                                                 num_bytes, search_start);
+                        offset = btrfs_alloc_from_cluster(used_block_group,
+                          last_ptr, num_bytes, used_block_group->key.objectid);
                         if (offset) {
                                 /* we have a block, we're done */
                                 spin_unlock(&last_ptr->refill_lock);
                                 goto checks;
                         }
 
-                        spin_lock(&last_ptr->lock);
-                        /*
-                         * whoops, this cluster doesn't actually point to
-                         * this block group.  Get a ref on the block
-                         * group is does point to and try again
-                         */
-                        if (!last_ptr_loop && last_ptr->block_group &&
-                            last_ptr->block_group != block_group &&
-                            index <=
-                                 get_block_group_index(last_ptr->block_group)) {
-
-                                btrfs_put_block_group(block_group);
-                                block_group = last_ptr->block_group;
-                                btrfs_get_block_group(block_group);
-                                spin_unlock(&last_ptr->lock);
-                                spin_unlock(&last_ptr->refill_lock);
-
-                                last_ptr_loop = 1;
-                                search_start = block_group->key.objectid;
-                                /*
-                                 * we know this block group is properly
-                                 * in the list because
-                                 * btrfs_remove_block_group, drops the
-                                 * cluster before it removes the block
-                                 * group from the list
-                                 */
-                                goto have_block_group;
+                        WARN_ON(last_ptr->block_group != used_block_group);
+                        if (used_block_group != block_group) {
+                                btrfs_put_block_group(used_block_group);
+                                used_block_group = block_group;
                         }
-                        spin_unlock(&last_ptr->lock);
 refill_cluster:
+                        BUG_ON(used_block_group != block_group);
+                        /* If we are on LOOP_NO_EMPTY_SIZE, we can't
+                         * set up a new clusters, so lets just skip it
+                         * and let the allocator find whatever block
+                         * it can find.  If we reach this point, we
+                         * will have tried the cluster allocator
+                         * plenty of times and not have found
+                         * anything, so we are likely way too
+                         * fragmented for the clustering stuff to find
+                         * anything.  */
+                        if (loop >= LOOP_NO_EMPTY_SIZE) {
+                                spin_unlock(&last_ptr->refill_lock);
+                                goto unclustered_alloc;
+                        }
+
                         /*
                          * this cluster didn't work out, free it and
                          * start over
                          */
                         btrfs_return_cluster_to_free_space(NULL, last_ptr);
 
-                        last_ptr_loop = 0;
-
                         /* allocate a cluster in this block group */
                         ret = btrfs_find_space_cluster(trans, root,
                                                block_group, last_ptr,
@@ -5390,6 +5400,7 @@ refill_cluster:
                         goto loop;
                 }
 
+unclustered_alloc:
                 offset = btrfs_find_space_for_alloc(block_group, search_start,
                                                     num_bytes, empty_size);
                 /*
@@ -5416,14 +5427,14 @@ checks:
                 search_start = stripe_align(root, offset);
                 /* move on to the next group */
                 if (search_start + num_bytes >= search_end) {
-                        btrfs_add_free_space(block_group, offset, num_bytes);
+                        btrfs_add_free_space(used_block_group, offset, num_bytes);
                         goto loop;
                 }
 
                 /* move on to the next group */
                 if (search_start + num_bytes >
-                    block_group->key.objectid + block_group->key.offset) {
-                        btrfs_add_free_space(block_group, offset, num_bytes);
+                    used_block_group->key.objectid + used_block_group->key.offset) {
+                        btrfs_add_free_space(used_block_group, offset, num_bytes);
                         goto loop;
                 }
 
@@ -5431,14 +5442,14 @@ checks:
                 ins->offset = num_bytes;
 
                 if (offset < search_start)
-                        btrfs_add_free_space(block_group, offset,
+                        btrfs_add_free_space(used_block_group, offset,
                                              search_start - offset);
                 BUG_ON(offset > search_start);
 
-                ret = btrfs_update_reserved_bytes(block_group, num_bytes,
+                ret = btrfs_update_reserved_bytes(used_block_group, num_bytes,
                                                   alloc_type);
                 if (ret == -EAGAIN) {
-                        btrfs_add_free_space(block_group, offset, num_bytes);
+                        btrfs_add_free_space(used_block_group, offset, num_bytes);
                         goto loop;
                 }
 
@@ -5447,15 +5458,19 @@ checks:
                 ins->offset = num_bytes;
 
                 if (offset < search_start)
-                        btrfs_add_free_space(block_group, offset,
+                        btrfs_add_free_space(used_block_group, offset,
                                              search_start - offset);
                 BUG_ON(offset > search_start);
+                if (used_block_group != block_group)
+                        btrfs_put_block_group(used_block_group);
                 btrfs_put_block_group(block_group);
                 break;
 loop:
                 failed_cluster_refill = false;
                 failed_alloc = false;
                 BUG_ON(index != get_block_group_index(block_group));
+                if (used_block_group != block_group)
+                        btrfs_put_block_group(used_block_group);
                 btrfs_put_block_group(block_group);
         }
         up_read(&space_info->groups_sem);