9 files changed, 120 insertions, 79 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 04a5dfcee5a1..50634abef9b4 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2369,6 +2369,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root,
 int btrfs_block_rsv_refill(struct btrfs_root *root,
                           struct btrfs_block_rsv *block_rsv,
                           u64 min_reserved);
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+                                   struct btrfs_block_rsv *block_rsv,
+                                   u64 min_reserved);
 int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
                             struct btrfs_block_rsv *dst_rsv,
                             u64 num_bytes);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 930ae8949737..2ad813674d77 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3888,9 +3888,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root,
         return ret;
 }
 
-int btrfs_block_rsv_refill(struct btrfs_root *root,
-                          struct btrfs_block_rsv *block_rsv,
-                          u64 min_reserved)
+static inline int __btrfs_block_rsv_refill(struct btrfs_root *root,
+                                           struct btrfs_block_rsv *block_rsv,
+                                           u64 min_reserved, int flush)
 {
         u64 num_bytes = 0;
         int ret = -ENOSPC;
@@ -3909,7 +3909,7 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
         if (!ret)
                 return 0;
 
-        ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 1);
+        ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
         if (!ret) {
                 block_rsv_add_bytes(block_rsv, num_bytes, 0);
                 return 0;
@@ -3918,6 +3918,20 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
         return ret;
 }
 
+int btrfs_block_rsv_refill(struct btrfs_root *root,
+                           struct btrfs_block_rsv *block_rsv,
+                           u64 min_reserved)
+{
+        return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 1);
+}
+
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+                                   struct btrfs_block_rsv *block_rsv,
+                                   u64 min_reserved)
+{
+        return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 0);
+}
+
 int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
                             struct btrfs_block_rsv *dst_rsv,
                             u64 num_bytes)
@@ -5093,11 +5107,11 @@ 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) ?
@@ -5159,6 +5173,7 @@ 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.
@@ -5196,6 +5211,7 @@ search:
                 u64 offset;
                 int cached;
 
+                used_block_group = block_group;
                 btrfs_get_block_group(block_group);
                 search_start = block_group->key.objectid;
 
@@ -5265,84 +5281,73 @@ alloc:
                 spin_lock(&block_group->free_space_ctl->tree_lock);
                 if (cached &&
                     block_group->free_space_ctl->free_space <
-                    num_bytes + empty_size) {
+                    num_bytes + empty_cluster + empty_size) {
                         spin_unlock(&block_group->free_space_ctl->tree_lock);
                         goto loop;
                 }
                 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))) {
-                                offset = 0;
+                        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;
                         }
 
-                        offset = btrfs_alloc_from_cluster(block_group, last_ptr,
-                                                 num_bytes, search_start);
+                        if (used_block_group != block_group)
+                                btrfs_get_block_group(used_block_group);
+
+                        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,
-                                               offset, num_bytes,
+                                               search_start, num_bytes,
                                                empty_cluster + empty_size);
                         if (ret == 0) {
                                 /*
@@ -5378,6 +5383,7 @@ refill_cluster:
                         goto loop;
                 }
 
+unclustered_alloc:
                 offset = btrfs_find_space_for_alloc(block_group, search_start,
                                                     num_bytes, empty_size);
                 /*
@@ -5404,14 +5410,14 @@ 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;
                 }
 
@@ -5419,14 +5425,14 @@ 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;
                 }
 
@@ -5435,15 +5441,19 @@ 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);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9472d3de5e52..49f3c9dc09f4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -935,8 +935,10 @@ again:
         node = tree_search(tree, start);
         if (!node) {
                 prealloc = alloc_extent_state_atomic(prealloc);
-                if (!prealloc)
-                        return -ENOMEM;
+                if (!prealloc) {
+                        err = -ENOMEM;
+                        goto out;
+                }
                 err = insert_state(tree, prealloc, start, end, &bits);
                 prealloc = NULL;
                 BUG_ON(err == -EEXIST);
@@ -992,8 +994,10 @@ hit_next:
          */
         if (state->start < start) {
                 prealloc = alloc_extent_state_atomic(prealloc);
-                if (!prealloc)
-                        return -ENOMEM;
+                if (!prealloc) {
+                        err = -ENOMEM;
+                        goto out;
+                }
                 err = split_state(tree, state, prealloc, start);
                 BUG_ON(err == -EEXIST);
                 prealloc = NULL;
@@ -1024,8 +1028,10 @@ hit_next:
                         this_end = last_start - 1;
 
                 prealloc = alloc_extent_state_atomic(prealloc);
-                if (!prealloc)
-                        return -ENOMEM;
+                if (!prealloc) {
+                        err = -ENOMEM;
+                        goto out;
+                }
 
                 /*
                  * Avoid to free 'prealloc' if it can be merged with
@@ -1051,8 +1057,10 @@ hit_next:
          */
         if (state->start <= end && state->end > end) {
                 prealloc = alloc_extent_state_atomic(prealloc);
-                if (!prealloc)
-                        return -ENOMEM;
+                if (!prealloc) {
+                        err = -ENOMEM;
+                        goto out;
+                }
 
                 err = split_state(tree, state, prealloc, end + 1);
                 BUG_ON(err == -EEXIST);
@@ -2287,14 +2295,20 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
                 if (!uptodate) {
                         int failed_mirror;
                         failed_mirror = (int)(unsigned long)bio->bi_bdev;
-                        if (tree->ops && tree->ops->readpage_io_failed_hook)
-                                ret = tree->ops->readpage_io_failed_hook(
-                                                bio, page, start, end,
-                                                failed_mirror, state);
-                        else
-                                ret = bio_readpage_error(bio, page, start, end,
-                                                         failed_mirror, NULL);
+                        /*
+                         * The generic bio_readpage_error handles errors the
+                         * following way: If possible, new read requests are
+                         * created and submitted and will end up in
+                         * end_bio_extent_readpage as well (if we're lucky, not
+                         * in the !uptodate case). In that case it returns 0 and
+                         * we just go on with the next page in our bio. If it
+                         * can't handle the error it will return -EIO and we
+                         * remain responsible for that page.
+                         */
+                        ret = bio_readpage_error(bio, page, start, end,
+                                                        failed_mirror, NULL);
                         if (ret == 0) {
+error_handled:
                                 uptodate =
                                         test_bit(BIO_UPTODATE, &bio->bi_flags);
                                 if (err)
@@ -2302,6 +2316,13 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
                                 uncache_state(&cached);
                                 continue;
                         }
+                        if (tree->ops && tree->ops->readpage_io_failed_hook) {
+                                ret = tree->ops->readpage_io_failed_hook(
+                                                        bio, page, start, end,
+                                                        failed_mirror, state);
+                                if (ret == 0)
+                                        goto error_handled;
+                        }
                 }
 
                 if (uptodate) {
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6e5b7e463698..ec23d43d0c35 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1470,6 +1470,7 @@ static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
 {
         info->offset = offset_to_bitmap(ctl, offset);
         info->bytes = 0;
+        INIT_LIST_HEAD(&info->list);
         link_free_space(ctl, info);
         ctl->total_bitmaps++;
 
@@ -2319,6 +2320,7 @@ again:
 
         if (!found) {
                 start = i;
+                cluster->max_size = 0;
                 found = true;
         }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 526dd51a1966..2c984f7d4c2a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3490,7 +3490,7 @@ void btrfs_evict_inode(struct inode *inode)
          * doing the truncate.
          */
         while (1) {
-                ret = btrfs_block_rsv_refill(root, rsv, min_size);
+                ret = btrfs_block_rsv_refill_noflush(root, rsv, min_size);
 
                 /*
                  * Try and steal from the global reserve since we will
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a90e749ed6d2..72d461656f60 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1278,7 +1278,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
                 }
                 ret = btrfs_grow_device(trans, device, new_size);
                 btrfs_commit_transaction(trans, root);
-        } else {
+        } else if (new_size < old_size) {
                 ret = btrfs_shrink_device(device, new_size);
         }
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index fab420db5121..c27bcb67f330 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -256,6 +256,11 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx)
         btrfs_release_path(swarn->path);
 
         ipath = init_ipath(4096, local_root, swarn->path);
+        if (IS_ERR(ipath)) {
+                ret = PTR_ERR(ipath);
+                ipath = NULL;
+                goto err;
+        }
         ret = paths_from_inode(inum, ipath);
 
         if (ret < 0)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 17ee7fc5e64e..e28ad4baf483 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1057,7 +1057,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
         int i = 0, nr_devices;
         int ret;
 
-        nr_devices = fs_info->fs_devices->rw_devices;
+        nr_devices = fs_info->fs_devices->open_devices;
         BUG_ON(!nr_devices);
 
         devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
@@ -1079,8 +1079,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
         else
                 min_stripe_size = BTRFS_STRIPE_LEN;
 
-        list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
-                if (!device->in_fs_metadata)
+        list_for_each_entry(device, &fs_devices->devices, dev_list) {
+                if (!device->in_fs_metadata || !device->bdev)
                         continue;
 
                 avail_space = device->total_bytes - device->bytes_used;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c37433d3cd82..0a8c8f8304b1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1611,7 +1611,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
         if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
                 return -EINVAL;
 
-        bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+        bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
                                   root->fs_info->bdev_holder);
         if (IS_ERR(bdev))
                 return PTR_ERR(bdev);