5 files changed, 91 insertions, 23 deletions

diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index af8e117c8978..cb97174e2366 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -325,7 +325,7 @@ again:
                         run_ordered_completions(worker->workers, work);
 
                         check_pending_worker_creates(worker);
-
+                        cond_resched();
                 }
 
                 spin_lock_irq(&worker->lock);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6a1a6800776c..c7ddf8a01c54 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -640,8 +640,8 @@ static int btrfs_delayed_inode_reserve_metadata(
          * Now if src_rsv == delalloc_block_rsv we'll let it just steal since
          * we're accounted for.
          */
-        if (!trans->bytes_reserved &&
-            src_rsv != &root->fs_info->delalloc_block_rsv) {
+        if (!src_rsv || (!trans->bytes_reserved &&
+            src_rsv != &root->fs_info->delalloc_block_rsv)) {
                 ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
                 /*
                  * Since we're under a transaction reserve_metadata_bytes could
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b212f391ceab..740e67bbe249 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2159,6 +2159,38 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
                 if (ret && ret != -ESTALE)
                         goto out;
 
+                if (ret == -ESTALE && root == root->fs_info->tree_root) {
+                        struct btrfs_root *dead_root;
+                        struct btrfs_fs_info *fs_info = root->fs_info;
+                        int is_dead_root = 0;
+
+                        /*
+                         * this is an orphan in the tree root. Currently these
+                         * could come from 2 sources:
+                         *  a) a snapshot deletion in progress
+                         *  b) a free space cache inode
+                         * We need to distinguish those two, as the snapshot
+                         * orphan must not get deleted.
+                         * find_dead_roots already ran before us, so if this
+                         * is a snapshot deletion, we should find the root
+                         * in the dead_roots list
+                         */
+                        spin_lock(&fs_info->trans_lock);
+                        list_for_each_entry(dead_root, &fs_info->dead_roots,
+                                            root_list) {
+                                if (dead_root->root_key.objectid ==
+                                    found_key.objectid) {
+                                        is_dead_root = 1;
+                                        break;
+                                }
+                        }
+                        spin_unlock(&fs_info->trans_lock);
+                        if (is_dead_root) {
+                                /* prevent this orphan from being found again */
+                                key.offset = found_key.objectid - 1;
+                                continue;
+                        }
+                }
                 /*
                  * Inode is already gone but the orphan item is still there,
                  * kill the orphan item.
@@ -3335,7 +3367,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
                         u64 hint_byte = 0;
                         hole_size = last_byte - cur_offset;
 
-                        trans = btrfs_start_transaction(root, 2);
+                        trans = btrfs_start_transaction(root, 3);
                         if (IS_ERR(trans)) {
                                 err = PTR_ERR(trans);
                                 break;
@@ -3345,6 +3377,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
                                                  cur_offset + hole_size,
                                                  &hint_byte, 1);
                         if (err) {
+                                btrfs_update_inode(trans, root, inode);
                                 btrfs_end_transaction(trans, root);
                                 break;
                         }
@@ -3354,6 +3387,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
                                         0, hole_size, 0, hole_size,
                                         0, 0, 0);
                         if (err) {
+                                btrfs_update_inode(trans, root, inode);
                                 btrfs_end_transaction(trans, root);
                                 break;
                         }
@@ -3361,6 +3395,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
                         btrfs_drop_extent_cache(inode, hole_start,
                                         last_byte - 1, 0);
 
+                        btrfs_update_inode(trans, root, inode);
                         btrfs_end_transaction(trans, root);
                 }
                 free_extent_map(em);
@@ -3378,6 +3413,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 
 static int btrfs_setsize(struct inode *inode, loff_t newsize)
 {
+        struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct btrfs_trans_handle *trans;
         loff_t oldsize = i_size_read(inode);
         int ret;
 
@@ -3385,16 +3422,19 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
                 return 0;
 
         if (newsize > oldsize) {
-                i_size_write(inode, newsize);
-                btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
                 truncate_pagecache(inode, oldsize, newsize);
                 ret = btrfs_cont_expand(inode, oldsize, newsize);
-                if (ret) {
-                        btrfs_setsize(inode, oldsize);
+                if (ret)
                         return ret;
-                }
 
-                ret = btrfs_dirty_inode(inode);
+                trans = btrfs_start_transaction(root, 1);
+                if (IS_ERR(trans))
+                        return PTR_ERR(trans);
+
+                i_size_write(inode, newsize);
+                btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+                ret = btrfs_update_inode(trans, root, inode);
+                btrfs_end_transaction_throttle(trans, root);
         } else {
 
                 /*
@@ -4601,11 +4641,18 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
+        /*
+        * If the active LSM wants to access the inode during
+        * d_instantiate it needs these. Smack checks to see
+        * if the filesystem supports xattrs by looking at the
+        * ops vector.
+        */
+
+        inode->i_op = &btrfs_special_inode_operations;
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
         else {
-                inode->i_op = &btrfs_special_inode_operations;
                 init_special_inode(inode, inode->i_mode, rdev);
                 btrfs_update_inode(trans, root, inode);
         }
@@ -4659,14 +4706,21 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
+        /*
+        * If the active LSM wants to access the inode during
+        * d_instantiate it needs these. Smack checks to see
+        * if the filesystem supports xattrs by looking at the
+        * ops vector.
+        */
+        inode->i_fop = &btrfs_file_operations;
+        inode->i_op = &btrfs_file_inode_operations;
+
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
         else {
                 inode->i_mapping->a_ops = &btrfs_aops;
                 inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
-                inode->i_fop = &btrfs_file_operations;
-                inode->i_op = &btrfs_file_inode_operations;
                 BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
         }
 out_unlock:
@@ -7128,14 +7182,21 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
+        /*
+        * If the active LSM wants to access the inode during
+        * d_instantiate it needs these. Smack checks to see
+        * if the filesystem supports xattrs by looking at the
+        * ops vector.
+        */
+        inode->i_fop = &btrfs_file_operations;
+        inode->i_op = &btrfs_file_inode_operations;
+
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
         else {
                 inode->i_mapping->a_ops = &btrfs_aops;
                 inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
-                inode->i_fop = &btrfs_file_operations;
-                inode->i_op = &btrfs_file_inode_operations;
                 BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
         }
         if (drop_inode)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index dd8891662355..c04f02c7d5bb 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -252,11 +252,11 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
         trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
 
+        btrfs_update_iflags(inode);
+        inode->i_ctime = CURRENT_TIME;
         ret = btrfs_update_inode(trans, root, inode);
         BUG_ON(ret);
 
-        btrfs_update_iflags(inode);
-        inode->i_ctime = CURRENT_TIME;
         btrfs_end_transaction(trans, root);
 
         mnt_drop_write(file->f_path.mnt);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 05b40457e26c..34a8b6112ea4 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1080,7 +1080,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
         u64 avail_space;
         u64 used_space;
         u64 min_stripe_size;
-        int min_stripes = 1;
+        int min_stripes = 1, num_stripes = 1;
         int i = 0, nr_devices;
         int ret;
 
@@ -1094,12 +1094,16 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 
         /* calc min stripe number for data space alloction */
         type = btrfs_get_alloc_profile(root, 1);
-        if (type & BTRFS_BLOCK_GROUP_RAID0)
+        if (type & BTRFS_BLOCK_GROUP_RAID0) {
                 min_stripes = 2;
-        else if (type & BTRFS_BLOCK_GROUP_RAID1)
+                num_stripes = nr_devices;
+        } else if (type & BTRFS_BLOCK_GROUP_RAID1) {
                 min_stripes = 2;
-        else if (type & BTRFS_BLOCK_GROUP_RAID10)
+                num_stripes = 2;
+        } else if (type & BTRFS_BLOCK_GROUP_RAID10) {
                 min_stripes = 4;
+                num_stripes = 4;
+        }
 
         if (type & BTRFS_BLOCK_GROUP_DUP)
                 min_stripe_size = 2 * BTRFS_STRIPE_LEN;
@@ -1168,13 +1172,16 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
         i = nr_devices - 1;
         avail_space = 0;
         while (nr_devices >= min_stripes) {
+                if (num_stripes > nr_devices)
+                        num_stripes = nr_devices;
+
                 if (devices_info[i].max_avail >= min_stripe_size) {
                         int j;
                         u64 alloc_size;
 
-                        avail_space += devices_info[i].max_avail * min_stripes;
+                        avail_space += devices_info[i].max_avail * num_stripes;
                         alloc_size = devices_info[i].max_avail;
-                        for (j = i + 1 - min_stripes; j <= i; j++)
+                        for (j = i + 1 - num_stripes; j <= i; j++)
                                 devices_info[j].max_avail -= alloc_size;
                 }
                 i--;