1 files changed, 1217 insertions, 141 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 645a17927a8f..a506a22b522a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -39,6 +39,7 @@
 #include <linux/security.h>
 #include <linux/xattr.h>
 #include <linux/vmalloc.h>
+#include <linux/slab.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
@@ -146,6 +147,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
         unsigned int flags, oldflags;
         int ret;
 
+        if (btrfs_root_readonly(root))
+                return -EROFS;
+
         if (copy_from_user(&flags, arg, sizeof(flags)))
                 return -EFAULT;
 
@@ -223,7 +227,8 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
 
 static noinline int create_subvol(struct btrfs_root *root,
                                   struct dentry *dentry,
-                                  char *name, int namelen)
+                                  char *name, int namelen,
+                                  u64 *async_transid)
 {
         struct btrfs_trans_handle *trans;
         struct btrfs_key key;
@@ -231,30 +236,34 @@ static noinline int create_subvol(struct btrfs_root *root,
         struct btrfs_inode_item *inode_item;
         struct extent_buffer *leaf;
         struct btrfs_root *new_root;
-        struct inode *dir = dentry->d_parent->d_inode;
+        struct dentry *parent = dget_parent(dentry);
+        struct inode *dir;
         int ret;
         int err;
         u64 objectid;
         u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
         u64 index = 0;
 
+        ret = btrfs_find_free_objectid(NULL, root->fs_info->tree_root,
+                                       0, &objectid);
+        if (ret) {
+                dput(parent);
+                return ret;
+        }
+
+        dir = parent->d_inode;
+
         /*
          * 1 - inode item
          * 2 - refs
          * 1 - root item
          * 2 - dir items
          */
-        ret = btrfs_reserve_metadata_space(root, 6);
-        if (ret)
-                return ret;
-
-        trans = btrfs_start_transaction(root, 1);
-        BUG_ON(!trans);
-
-        ret = btrfs_find_free_objectid(trans, root->fs_info->tree_root,
-                                       0, &objectid);
-        if (ret)
-                goto fail;
+        trans = btrfs_start_transaction(root, 6);
+        if (IS_ERR(trans)) {
+                dput(parent);
+                return PTR_ERR(trans);
+        }
 
         leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
                                       0, objectid, NULL, 0, 0, 0);
@@ -341,18 +350,24 @@ static noinline int create_subvol(struct btrfs_root *root,
 
         d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
 fail:
-        err = btrfs_commit_transaction(trans, root);
+        dput(parent);
+        if (async_transid) {
+                *async_transid = trans->transid;
+                err = btrfs_commit_transaction_async(trans, root, 1);
+        } else {
+                err = btrfs_commit_transaction(trans, root);
+        }
         if (err && !ret)
                 ret = err;
-
-        btrfs_unreserve_metadata_space(root, 6);
         return ret;
 }
 
 static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
-                           char *name, int namelen)
+                           char *name, int namelen, u64 *async_transid,
+                           bool readonly)
 {
         struct inode *inode;
+        struct dentry *parent;
         struct btrfs_pending_snapshot *pending_snapshot;
         struct btrfs_trans_handle *trans;
         int ret;
@@ -360,42 +375,45 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
         if (!root->ref_cows)
                 return -EINVAL;
 
-        /*
-         * 1 - inode item
-         * 2 - refs
-         * 1 - root item
-         * 2 - dir items
-         */
-        ret = btrfs_reserve_metadata_space(root, 6);
-        if (ret)
-                goto fail;
-
         pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
-        if (!pending_snapshot) {
-                ret = -ENOMEM;
-                btrfs_unreserve_metadata_space(root, 6);
-                goto fail;
-        }
-        pending_snapshot->name = kmalloc(namelen + 1, GFP_NOFS);
-        if (!pending_snapshot->name) {
-                ret = -ENOMEM;
-                kfree(pending_snapshot);
-                btrfs_unreserve_metadata_space(root, 6);
-                goto fail;
-        }
-        memcpy(pending_snapshot->name, name, namelen);
-        pending_snapshot->name[namelen] = '\0';
+        if (!pending_snapshot)
+                return -ENOMEM;
+
+        btrfs_init_block_rsv(&pending_snapshot->block_rsv);
         pending_snapshot->dentry = dentry;
-        trans = btrfs_start_transaction(root, 1);
-        BUG_ON(!trans);
         pending_snapshot->root = root;
+        pending_snapshot->readonly = readonly;
+
+        trans = btrfs_start_transaction(root->fs_info->extent_root, 5);
+        if (IS_ERR(trans)) {
+                ret = PTR_ERR(trans);
+                goto fail;
+        }
+
+        ret = btrfs_snap_reserve_metadata(trans, pending_snapshot);
+        BUG_ON(ret);
+
         list_add(&pending_snapshot->list,
                  &trans->transaction->pending_snapshots);
-        ret = btrfs_commit_transaction(trans, root);
+        if (async_transid) {
+                *async_transid = trans->transid;
+                ret = btrfs_commit_transaction_async(trans,
+                                     root->fs_info->extent_root, 1);
+        } else {
+                ret = btrfs_commit_transaction(trans,
+                                               root->fs_info->extent_root);
+        }
         BUG_ON(ret);
-        btrfs_unreserve_metadata_space(root, 6);
 
-        inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
+        ret = pending_snapshot->error;
+        if (ret)
+                goto fail;
+
+        btrfs_orphan_cleanup(pending_snapshot->snap);
+
+        parent = dget_parent(dentry);
+        inode = btrfs_lookup_dentry(parent->d_inode, dentry);
+        dput(parent);
         if (IS_ERR(inode)) {
                 ret = PTR_ERR(inode);
                 goto fail;
@@ -404,9 +422,80 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
         d_instantiate(dentry, inode);
         ret = 0;
 fail:
+        kfree(pending_snapshot);
         return ret;
 }
 
+/*  copy of check_sticky in fs/namei.c()
+* It's inline, so penalty for filesystems that don't use sticky bit is
+* minimal.
+*/
+static inline int btrfs_check_sticky(struct inode *dir, struct inode *inode)
+{
+        uid_t fsuid = current_fsuid();
+
+        if (!(dir->i_mode & S_ISVTX))
+                return 0;
+        if (inode->i_uid == fsuid)
+                return 0;
+        if (dir->i_uid == fsuid)
+                return 0;
+        return !capable(CAP_FOWNER);
+}
+
+/*  copy of may_delete in fs/namei.c()
+ *      Check whether we can remove a link victim from directory dir, check
+ *  whether the type of victim is right.
+ *  1. We can't do it if dir is read-only (done in permission())
+ *  2. We should have write and exec permissions on dir
+ *  3. We can't remove anything from append-only dir
+ *  4. We can't do anything with immutable dir (done in permission())
+ *  5. If the sticky bit on dir is set we should either
+ *      a. be owner of dir, or
+ *      b. be owner of victim, or
+ *      c. have CAP_FOWNER capability
+ *  6. If the victim is append-only or immutable we can't do antyhing with
+ *     links pointing to it.
+ *  7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
+ *  8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
+ *  9. We can't remove a root or mountpoint.
+ * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
+ *     nfs_async_unlink().
+ */
+
+static int btrfs_may_delete(struct inode *dir,struct dentry *victim,int isdir)
+{
+        int error;
+
+        if (!victim->d_inode)
+                return -ENOENT;
+
+        BUG_ON(victim->d_parent->d_inode != dir);
+        audit_inode_child(victim, dir);
+
+        error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+        if (error)
+                return error;
+        if (IS_APPEND(dir))
+                return -EPERM;
+        if (btrfs_check_sticky(dir, victim->d_inode)||
+                IS_APPEND(victim->d_inode)||
+            IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
+                return -EPERM;
+        if (isdir) {
+                if (!S_ISDIR(victim->d_inode->i_mode))
+                        return -ENOTDIR;
+                if (IS_ROOT(victim))
+                        return -EBUSY;
+        } else if (S_ISDIR(victim->d_inode->i_mode))
+                return -EISDIR;
+        if (IS_DEADDIR(dir))
+                return -ENOENT;
+        if (victim->d_flags & DCACHE_NFSFS_RENAMED)
+                return -EBUSY;
+        return 0;
+}
+
 /* copy of may_create in fs/namei.c() */
 static inline int btrfs_may_create(struct inode *dir, struct dentry *child)
 {
@@ -424,7 +513,8 @@ static inline int btrfs_may_create(struct inode *dir, struct dentry *child)
  */
 static noinline int btrfs_mksubvol(struct path *parent,
                                    char *name, int namelen,
-                                   struct btrfs_root *snap_src)
+                                   struct btrfs_root *snap_src,
+                                   u64 *async_transid, bool readonly)
 {
         struct inode *dir  = parent->dentry->d_inode;
         struct dentry *dentry;
@@ -456,10 +546,10 @@ static noinline int btrfs_mksubvol(struct path *parent,
 
         if (snap_src) {
                 error = create_snapshot(snap_src, dentry,
-                                        name, namelen);
+                                        name, namelen, async_transid, readonly);
         } else {
                 error = create_subvol(BTRFS_I(dir)->root, dentry,
-                                      name, namelen);
+                                      name, namelen, async_transid);
         }
         if (!error)
                 fsnotify_mkdir(dir, dentry);
@@ -474,49 +564,182 @@ out_unlock:
         return error;
 }
 
-static int btrfs_defrag_file(struct file *file)
+static int should_defrag_range(struct inode *inode, u64 start, u64 len,
+                               int thresh, u64 *last_len, u64 *skip,
+                               u64 *defrag_end)
+{
+        struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+        struct extent_map *em = NULL;
+        struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+        int ret = 1;
+
+
+        if (thresh == 0)
+                thresh = 256 * 1024;
+
+        /*
+         * make sure that once we start defragging and extent, we keep on
+         * defragging it
+         */
+        if (start < *defrag_end)
+                return 1;
+
+        *skip = 0;
+
+        /*
+         * hopefully we have this extent in the tree already, try without
+         * the full extent lock
+         */
+        read_lock(&em_tree->lock);
+        em = lookup_extent_mapping(em_tree, start, len);
+        read_unlock(&em_tree->lock);
+
+        if (!em) {
+                /* get the big lock and read metadata off disk */
+                lock_extent(io_tree, start, start + len - 1, GFP_NOFS);
+                em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
+                unlock_extent(io_tree, start, start + len - 1, GFP_NOFS);
+
+                if (IS_ERR(em))
+                        return 0;
+        }
+
+        /* this will cover holes, and inline extents */
+        if (em->block_start >= EXTENT_MAP_LAST_BYTE)
+                ret = 0;
+
+        /*
+         * we hit a real extent, if it is big don't bother defragging it again
+         */
+        if ((*last_len == 0 || *last_len >= thresh) && em->len >= thresh)
+                ret = 0;
+
+        /*
+         * last_len ends up being a counter of how many bytes we've defragged.
+         * every time we choose not to defrag an extent, we reset *last_len
+         * so that the next tiny extent will force a defrag.
+         *
+         * The end result of this is that tiny extents before a single big
+         * extent will force at least part of that big extent to be defragged.
+         */
+        if (ret) {
+                *last_len += len;
+                *defrag_end = extent_map_end(em);
+        } else {
+                *last_len = 0;
+                *skip = extent_map_end(em);
+                *defrag_end = 0;
+        }
+
+        free_extent_map(em);
+        return ret;
+}
+
+static int btrfs_defrag_file(struct file *file,
+                             struct btrfs_ioctl_defrag_range_args *range)
 {
         struct inode *inode = fdentry(file)->d_inode;
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
         struct btrfs_ordered_extent *ordered;
         struct page *page;
+        struct btrfs_super_block *disk_super;
         unsigned long last_index;
         unsigned long ra_pages = root->fs_info->bdi.ra_pages;
         unsigned long total_read = 0;
+        u64 features;
         u64 page_start;
         u64 page_end;
+        u64 last_len = 0;
+        u64 skip = 0;
+        u64 defrag_end = 0;
         unsigned long i;
         int ret;
+        int compress_type = BTRFS_COMPRESS_ZLIB;
 
-        ret = btrfs_check_data_free_space(root, inode, inode->i_size);
-        if (ret)
-                return -ENOSPC;
+        if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
+                if (range->compress_type > BTRFS_COMPRESS_TYPES)
+                        return -EINVAL;
+                if (range->compress_type)
+                        compress_type = range->compress_type;
+        }
+
+        if (inode->i_size == 0)
+                return 0;
+
+        if (range->start + range->len > range->start) {
+                last_index = min_t(u64, inode->i_size - 1,
+                         range->start + range->len - 1) >> PAGE_CACHE_SHIFT;
+        } else {
+                last_index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT;
+        }
+
+        i = range->start >> PAGE_CACHE_SHIFT;
+        while (i <= last_index) {
+                if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
+                                        PAGE_CACHE_SIZE,
+                                        range->extent_thresh,
+                                        &last_len, &skip,
+                                        &defrag_end)) {
+                        unsigned long next;
+                        /*
+                         * the should_defrag function tells us how much to skip
+                         * bump our counter by the suggested amount
+                         */
+                        next = (skip + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+                        i = max(i + 1, next);
+                        continue;
+                }
 
-        mutex_lock(&inode->i_mutex);
-        last_index = inode->i_size >> PAGE_CACHE_SHIFT;
-        for (i = 0; i <= last_index; i++) {
                 if (total_read % ra_pages == 0) {
                         btrfs_force_ra(inode->i_mapping, &file->f_ra, file, i,
                                        min(last_index, i + ra_pages - 1));
                 }
                 total_read++;
+                mutex_lock(&inode->i_mutex);
+                if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
+                        BTRFS_I(inode)->force_compress = compress_type;
+
+                ret  = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+                if (ret)
+                        goto err_unlock;
 again:
+                if (inode->i_size == 0 ||
+                    i > ((inode->i_size - 1) >> PAGE_CACHE_SHIFT)) {
+                        ret = 0;
+                        goto err_reservations;
+                }
+
                 page = grab_cache_page(inode->i_mapping, i);
-                if (!page)
-                        goto out_unlock;
+                if (!page) {
+                        ret = -ENOMEM;
+                        goto err_reservations;
+                }
+
                 if (!PageUptodate(page)) {
                         btrfs_readpage(NULL, page);
                         lock_page(page);
                         if (!PageUptodate(page)) {
                                 unlock_page(page);
                                 page_cache_release(page);
-                                goto out_unlock;
+                                ret = -EIO;
+                                goto err_reservations;
                         }
                 }
 
+                if (page->mapping != inode->i_mapping) {
+                        unlock_page(page);
+                        page_cache_release(page);
+                        goto again;
+                }
+
                 wait_on_page_writeback(page);
 
+                if (PageDirty(page)) {
+                        btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+                        goto loop_unlock;
+                }
+
                 page_start = (u64)page->index << PAGE_CACHE_SHIFT;
                 page_end = page_start + PAGE_CACHE_SIZE - 1;
                 lock_extent(io_tree, page_start, page_end, GFP_NOFS);
@@ -537,18 +760,60 @@ again:
                  * page if it is dirtied again later
                  */
                 clear_page_dirty_for_io(page);
+                clear_extent_bits(&BTRFS_I(inode)->io_tree, page_start,
+                                  page_end, EXTENT_DIRTY | EXTENT_DELALLOC |
+                                  EXTENT_DO_ACCOUNTING, GFP_NOFS);
 
-                btrfs_set_extent_delalloc(inode, page_start, page_end);
+                btrfs_set_extent_delalloc(inode, page_start, page_end, NULL);
+                ClearPageChecked(page);
                 set_page_dirty(page);
                 unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
+
+loop_unlock:
                 unlock_page(page);
                 page_cache_release(page);
+                mutex_unlock(&inode->i_mutex);
+
                 balance_dirty_pages_ratelimited_nr(inode->i_mapping, 1);
+                i++;
+        }
+
+        if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO))
+                filemap_flush(inode->i_mapping);
+
+        if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
+                /* the filemap_flush will queue IO into the worker threads, but
+                 * we have to make sure the IO is actually started and that
+                 * ordered extents get created before we return
+                 */
+                atomic_inc(&root->fs_info->async_submit_draining);
+                while (atomic_read(&root->fs_info->nr_async_submits) ||
+                      atomic_read(&root->fs_info->async_delalloc_pages)) {
+                        wait_event(root->fs_info->async_submit_wait,
+                           (atomic_read(&root->fs_info->nr_async_submits) == 0 &&
+                            atomic_read(&root->fs_info->async_delalloc_pages) == 0));
+                }
+                atomic_dec(&root->fs_info->async_submit_draining);
+
+                mutex_lock(&inode->i_mutex);
+                BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
+                mutex_unlock(&inode->i_mutex);
+        }
+
+        disk_super = &root->fs_info->super_copy;
+        features = btrfs_super_incompat_flags(disk_super);
+        if (range->compress_type == BTRFS_COMPRESS_LZO) {
+                features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+                btrfs_set_super_incompat_flags(disk_super, features);
         }
 
-out_unlock:
-        mutex_unlock(&inode->i_mutex);
         return 0;
+
+err_reservations:
+        btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+err_unlock:
+        mutex_unlock(&inode->i_mutex);
+        return ret;
 }
 
 static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
@@ -563,7 +828,6 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
         char *sizestr;
         char *devstr = NULL;
         int ret = 0;
-        int namelen;
         int mod = 0;
 
         if (root->fs_info->sb->s_flags & MS_RDONLY)
@@ -577,7 +841,6 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
                 return PTR_ERR(vol_args);
 
         vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
-        namelen = strlen(vol_args->name);
 
         mutex_lock(&root->fs_info->volume_mutex);
         sizestr = vol_args->name;
@@ -608,7 +871,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
                         mod = 1;
                         sizestr++;
                 }
-                new_size = btrfs_parse_size(sizestr);
+                new_size = memparse(sizestr, NULL);
                 if (new_size == 0) {
                         ret = -EINVAL;
                         goto out_unlock;
@@ -643,7 +906,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
                 device->name, (unsigned long long)new_size);
 
         if (new_size > old_size) {
-                trans = btrfs_start_transaction(root, 1);
+                trans = btrfs_start_transaction(root, 0);
                 ret = btrfs_grow_device(trans, device, new_size);
                 btrfs_commit_transaction(trans, root);
         } else {
@@ -656,11 +919,14 @@ out_unlock:
         return ret;
 }
 
-static noinline int btrfs_ioctl_snap_create(struct file *file,
-                                            void __user *arg, int subvol)
+static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
+                                                    char *name,
+                                                    unsigned long fd,
+                                                    int subvol,
+                                                    u64 *transid,
+                                                    bool readonly)
 {
         struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
-        struct btrfs_ioctl_vol_args *vol_args;
         struct file *src_file;
         int namelen;
         int ret = 0;
@@ -668,23 +934,18 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
         if (root->fs_info->sb->s_flags & MS_RDONLY)
                 return -EROFS;
 
-        vol_args = memdup_user(arg, sizeof(*vol_args));
-        if (IS_ERR(vol_args))
-                return PTR_ERR(vol_args);
-
-        vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
-        namelen = strlen(vol_args->name);
-        if (strchr(vol_args->name, '/')) {
+        namelen = strlen(name);
+        if (strchr(name, '/')) {
                 ret = -EINVAL;
                 goto out;
         }
 
         if (subvol) {
-                ret = btrfs_mksubvol(&file->f_path, vol_args->name, namelen,
-                                     NULL);
+                ret = btrfs_mksubvol(&file->f_path, name, namelen,
+                                     NULL, transid, readonly);
         } else {
                 struct inode *src_inode;
-                src_file = fget(vol_args->fd);
+                src_file = fget(fd);
                 if (!src_file) {
                         ret = -EINVAL;
                         goto out;
@@ -698,15 +959,152 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
                         fput(src_file);
                         goto out;
                 }
-                ret = btrfs_mksubvol(&file->f_path, vol_args->name, namelen,
-                                     BTRFS_I(src_inode)->root);
+                ret = btrfs_mksubvol(&file->f_path, name, namelen,
+                                     BTRFS_I(src_inode)->root,
+                                     transid, readonly);
                 fput(src_file);
         }
 out:
+        return ret;
+}
+
+static noinline int btrfs_ioctl_snap_create(struct file *file,
+                                            void __user *arg, int subvol)
+{
+        struct btrfs_ioctl_vol_args *vol_args;
+        int ret;
+
+        vol_args = memdup_user(arg, sizeof(*vol_args));
+        if (IS_ERR(vol_args))
+                return PTR_ERR(vol_args);
+        vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+
+        ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
+                                              vol_args->fd, subvol,
+                                              NULL, false);
+
         kfree(vol_args);
         return ret;
 }
 
+static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
+                                               void __user *arg, int subvol)
+{
+        struct btrfs_ioctl_vol_args_v2 *vol_args;
+        int ret;
+        u64 transid = 0;
+        u64 *ptr = NULL;
+        bool readonly = false;
+
+        vol_args = memdup_user(arg, sizeof(*vol_args));
+        if (IS_ERR(vol_args))
+                return PTR_ERR(vol_args);
+        vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+
+        if (vol_args->flags &
+            ~(BTRFS_SUBVOL_CREATE_ASYNC | BTRFS_SUBVOL_RDONLY)) {
+                ret = -EOPNOTSUPP;
+                goto out;
+        }
+
+        if (vol_args->flags & BTRFS_SUBVOL_CREATE_ASYNC)
+                ptr = &transid;
+        if (vol_args->flags & BTRFS_SUBVOL_RDONLY)
+                readonly = true;
+
+        ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
+                                              vol_args->fd, subvol,
+                                              ptr, readonly);
+
+        if (ret == 0 && ptr &&
+            copy_to_user(arg +
+                         offsetof(struct btrfs_ioctl_vol_args_v2,
+                                  transid), ptr, sizeof(*ptr)))
+                ret = -EFAULT;
+out:
+        kfree(vol_args);
+        return ret;
+}
+
+static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
+                                                void __user *arg)
+{
+        struct inode *inode = fdentry(file)->d_inode;
+        struct btrfs_root *root = BTRFS_I(inode)->root;
+        int ret = 0;
+        u64 flags = 0;
+
+        if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID)
+                return -EINVAL;
+
+        down_read(&root->fs_info->subvol_sem);
+        if (btrfs_root_readonly(root))
+                flags |= BTRFS_SUBVOL_RDONLY;
+        up_read(&root->fs_info->subvol_sem);
+
+        if (copy_to_user(arg, &flags, sizeof(flags)))
+                ret = -EFAULT;
+
+        return ret;
+}
+
+static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
+                                              void __user *arg)
+{
+        struct inode *inode = fdentry(file)->d_inode;
+        struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct btrfs_trans_handle *trans;
+        u64 root_flags;
+        u64 flags;
+        int ret = 0;
+
+        if (root->fs_info->sb->s_flags & MS_RDONLY)
+                return -EROFS;
+
+        if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID)
+                return -EINVAL;
+
+        if (copy_from_user(&flags, arg, sizeof(flags)))
+                return -EFAULT;
+
+        if (flags & ~BTRFS_SUBVOL_CREATE_ASYNC)
+                return -EINVAL;
+
+        if (flags & ~BTRFS_SUBVOL_RDONLY)
+                return -EOPNOTSUPP;
+
+        down_write(&root->fs_info->subvol_sem);
+
+        /* nothing to do */
+        if (!!(flags & BTRFS_SUBVOL_RDONLY) == btrfs_root_readonly(root))
+                goto out;
+
+        root_flags = btrfs_root_flags(&root->root_item);
+        if (flags & BTRFS_SUBVOL_RDONLY)
+                btrfs_set_root_flags(&root->root_item,
+                                     root_flags | BTRFS_ROOT_SUBVOL_RDONLY);
+        else
+                btrfs_set_root_flags(&root->root_item,
+                                     root_flags & ~BTRFS_ROOT_SUBVOL_RDONLY);
+
+        trans = btrfs_start_transaction(root, 1);
+        if (IS_ERR(trans)) {
+                ret = PTR_ERR(trans);
+                goto out_reset;
+        }
+
+        ret = btrfs_update_root(trans, root,
+                                &root->root_key, &root->root_item);
+
+        btrfs_commit_transaction(trans, root);
+out_reset:
+        if (ret)
+                btrfs_set_root_flags(&root->root_item, root_flags);
+out:
+        up_write(&root->fs_info->subvol_sem);
+        return ret;
+}
+
 /*
  * helper to check if the subvolume references other subvolumes
  */
@@ -743,6 +1141,322 @@ out:
         return ret;
 }
 
+static noinline int key_in_sk(struct btrfs_key *key,
+                              struct btrfs_ioctl_search_key *sk)
+{
+        struct btrfs_key test;
+        int ret;
+
+        test.objectid = sk->min_objectid;
+        test.type = sk->min_type;
+        test.offset = sk->min_offset;
+
+        ret = btrfs_comp_cpu_keys(key, &test);
+        if (ret < 0)
+                return 0;
+
+        test.objectid = sk->max_objectid;
+        test.type = sk->max_type;
+        test.offset = sk->max_offset;
+
+        ret = btrfs_comp_cpu_keys(key, &test);
+        if (ret > 0)
+                return 0;
+        return 1;
+}
+
+static noinline int copy_to_sk(struct btrfs_root *root,
+                               struct btrfs_path *path,
+                               struct btrfs_key *key,
+                               struct btrfs_ioctl_search_key *sk,
+                               char *buf,
+                               unsigned long *sk_offset,
+                               int *num_found)
+{
+        u64 found_transid;
+        struct extent_buffer *leaf;
+        struct btrfs_ioctl_search_header sh;
+        unsigned long item_off;
+        unsigned long item_len;
+        int nritems;
+        int i;
+        int slot;
+        int found = 0;
+        int ret = 0;
+
+        leaf = path->nodes[0];
+        slot = path->slots[0];
+        nritems = btrfs_header_nritems(leaf);
+
+        if (btrfs_header_generation(leaf) > sk->max_transid) {
+                i = nritems;
+                goto advance_key;
+        }
+        found_transid = btrfs_header_generation(leaf);
+
+        for (i = slot; i < nritems; i++) {
+                item_off = btrfs_item_ptr_offset(leaf, i);
+                item_len = btrfs_item_size_nr(leaf, i);
+
+                if (item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
+                        item_len = 0;
+
+                if (sizeof(sh) + item_len + *sk_offset >
+                    BTRFS_SEARCH_ARGS_BUFSIZE) {
+                        ret = 1;
+                        goto overflow;
+                }
+
+                btrfs_item_key_to_cpu(leaf, key, i);
+                if (!key_in_sk(key, sk))
+                        continue;
+
+                sh.objectid = key->objectid;
+                sh.offset = key->offset;
+                sh.type = key->type;
+                sh.len = item_len;
+                sh.transid = found_transid;
+
+                /* copy search result header */
+                memcpy(buf + *sk_offset, &sh, sizeof(sh));
+                *sk_offset += sizeof(sh);
+
+                if (item_len) {
+                        char *p = buf + *sk_offset;
+                        /* copy the item */
+                        read_extent_buffer(leaf, p,
+                                           item_off, item_len);
+                        *sk_offset += item_len;
+                }
+                found++;
+
+                if (*num_found >= sk->nr_items)
+                        break;
+        }
+advance_key:
+        ret = 0;
+        if (key->offset < (u64)-1 && key->offset < sk->max_offset)
+                key->offset++;
+        else if (key->type < (u8)-1 && key->type < sk->max_type) {
+                key->offset = 0;
+                key->type++;
+        } else if (key->objectid < (u64)-1 && key->objectid < sk->max_objectid) {
+                key->offset = 0;
+                key->type = 0;
+                key->objectid++;
+        } else
+                ret = 1;
+overflow:
+        *num_found += found;
+        return ret;
+}
+
+static noinline int search_ioctl(struct inode *inode,
+                                 struct btrfs_ioctl_search_args *args)
+{
+        struct btrfs_root *root;
+        struct btrfs_key key;
+        struct btrfs_key max_key;
+        struct btrfs_path *path;
+        struct btrfs_ioctl_search_key *sk = &args->key;
+        struct btrfs_fs_info *info = BTRFS_I(inode)->root->fs_info;
+        int ret;
+        int num_found = 0;
+        unsigned long sk_offset = 0;
+
+        path = btrfs_alloc_path();
+        if (!path)
+                return -ENOMEM;
+
+        if (sk->tree_id == 0) {
+                /* search the root of the inode that was passed */
+                root = BTRFS_I(inode)->root;
+        } else {
+                key.objectid = sk->tree_id;
+                key.type = BTRFS_ROOT_ITEM_KEY;
+                key.offset = (u64)-1;
+                root = btrfs_read_fs_root_no_name(info, &key);
+                if (IS_ERR(root)) {
+                        printk(KERN_ERR "could not find root %llu\n",
+                               sk->tree_id);
+                        btrfs_free_path(path);
+                        return -ENOENT;
+                }
+        }
+
+        key.objectid = sk->min_objectid;
+        key.type = sk->min_type;
+        key.offset = sk->min_offset;
+
+        max_key.objectid = sk->max_objectid;
+        max_key.type = sk->max_type;
+        max_key.offset = sk->max_offset;
+
+        path->keep_locks = 1;
+
+        while(1) {
+                ret = btrfs_search_forward(root, &key, &max_key, path, 0,
+                                           sk->min_transid);
+                if (ret != 0) {
+                        if (ret > 0)
+                                ret = 0;
+                        goto err;
+                }
+                ret = copy_to_sk(root, path, &key, sk, args->buf,
+                                 &sk_offset, &num_found);
+                btrfs_release_path(root, path);
+                if (ret || num_found >= sk->nr_items)
+                        break;
+
+        }
+        ret = 0;
+err:
+        sk->nr_items = num_found;
+        btrfs_free_path(path);
+        return ret;
+}
+
+static noinline int btrfs_ioctl_tree_search(struct file *file,
+                                           void __user *argp)
+{
+         struct btrfs_ioctl_search_args *args;
+         struct inode *inode;
+         int ret;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        args = memdup_user(argp, sizeof(*args));
+        if (IS_ERR(args))
+                return PTR_ERR(args);
+
+        inode = fdentry(file)->d_inode;
+        ret = search_ioctl(inode, args);
+        if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
+                ret = -EFAULT;
+        kfree(args);
+        return ret;
+}
+
+/*
+ * Search INODE_REFs to identify path name of 'dirid' directory
+ * in a 'tree_id' tree. and sets path name to 'name'.
+ */
+static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info,
+                                u64 tree_id, u64 dirid, char *name)
+{
+        struct btrfs_root *root;
+        struct btrfs_key key;
+        char *ptr;
+        int ret = -1;
+        int slot;
+        int len;
+        int total_len = 0;
+        struct btrfs_inode_ref *iref;
+        struct extent_buffer *l;
+        struct btrfs_path *path;
+
+        if (dirid == BTRFS_FIRST_FREE_OBJECTID) {
+                name[0]='\0';
+                return 0;
+        }
+
+        path = btrfs_alloc_path();
+        if (!path)
+                return -ENOMEM;
+
+        ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX];
+
+        key.objectid = tree_id;
+        key.type = BTRFS_ROOT_ITEM_KEY;
+        key.offset = (u64)-1;
+        root = btrfs_read_fs_root_no_name(info, &key);
+        if (IS_ERR(root)) {
+                printk(KERN_ERR "could not find root %llu\n", tree_id);
+                ret = -ENOENT;
+                goto out;
+        }
+
+        key.objectid = dirid;
+        key.type = BTRFS_INODE_REF_KEY;
+        key.offset = (u64)-1;
+
+        while(1) {
+                ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+                if (ret < 0)
+                        goto out;
+
+                l = path->nodes[0];
+                slot = path->slots[0];
+                if (ret > 0 && slot > 0)
+                        slot--;
+                btrfs_item_key_to_cpu(l, &key, slot);
+
+                if (ret > 0 && (key.objectid != dirid ||
+                                key.type != BTRFS_INODE_REF_KEY)) {
+                        ret = -ENOENT;
+                        goto out;
+                }
+
+                iref = btrfs_item_ptr(l, slot, struct btrfs_inode_ref);
+                len = btrfs_inode_ref_name_len(l, iref);
+                ptr -= len + 1;
+                total_len += len + 1;
+                if (ptr < name)
+                        goto out;
+
+                *(ptr + len) = '/';
+                read_extent_buffer(l, ptr,(unsigned long)(iref + 1), len);
+
+                if (key.offset == BTRFS_FIRST_FREE_OBJECTID)
+                        break;
+
+                btrfs_release_path(root, path);
+                key.objectid = key.offset;
+                key.offset = (u64)-1;
+                dirid = key.objectid;
+
+        }
+        if (ptr < name)
+                goto out;
+        memcpy(name, ptr, total_len);
+        name[total_len]='\0';
+        ret = 0;
+out:
+        btrfs_free_path(path);
+        return ret;
+}
+
+static noinline int btrfs_ioctl_ino_lookup(struct file *file,
+                                           void __user *argp)
+{
+         struct btrfs_ioctl_ino_lookup_args *args;
+         struct inode *inode;
+         int ret;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        args = memdup_user(argp, sizeof(*args));
+        if (IS_ERR(args))
+                return PTR_ERR(args);
+
+        inode = fdentry(file)->d_inode;
+
+        if (args->treeid == 0)
+                args->treeid = BTRFS_I(inode)->root->root_key.objectid;
+
+        ret = btrfs_search_path_in_tree(BTRFS_I(inode)->root->fs_info,
+                                        args->treeid, args->objectid,
+                                        args->name);
+
+        if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
+                ret = -EFAULT;
+
+        kfree(args);
+        return ret;
+}
+
 static noinline int btrfs_ioctl_snap_destroy(struct file *file,
                                              void __user *arg)
 {
@@ -758,9 +1472,6 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
         int ret;
         int err = 0;
 
-        if (!capable(CAP_SYS_ADMIN))
-                return -EPERM;
-
         vol_args = memdup_user(arg, sizeof(*vol_args));
         if (IS_ERR(vol_args))
                 return PTR_ERR(vol_args);
@@ -790,13 +1501,51 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
         }
 
         inode = dentry->d_inode;
+        dest = BTRFS_I(inode)->root;
+        if (!capable(CAP_SYS_ADMIN)){
+                /*
+                 * Regular user.  Only allow this with a special mount
+                 * option, when the user has write+exec access to the
+                 * subvol root, and when rmdir(2) would have been
+                 * allowed.
+                 *
+                 * Note that this is _not_ check that the subvol is
+                 * empty or doesn't contain data that we wouldn't
+                 * otherwise be able to delete.
+                 *
+                 * Users who want to delete empty subvols should try
+                 * rmdir(2).
+                 */
+                err = -EPERM;
+                if (!btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED))
+                        goto out_dput;
+
+                /*
+                 * Do not allow deletion if the parent dir is the same
+                 * as the dir to be deleted.  That means the ioctl
+                 * must be called on the dentry referencing the root
+                 * of the subvol, not a random directory contained
+                 * within it.
+                 */
+                err = -EINVAL;
+                if (root == dest)
+                        goto out_dput;
+
+                err = inode_permission(inode, MAY_WRITE | MAY_EXEC);
+                if (err)
+                        goto out_dput;
+
+                /* check if subvolume may be deleted by a non-root user */
+                err = btrfs_may_delete(dir, dentry, 1);
+                if (err)
+                        goto out_dput;
+        }
+
         if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID) {
                 err = -EINVAL;
                 goto out_dput;
         }
 
-        dest = BTRFS_I(inode)->root;
-
         mutex_lock(&inode->i_mutex);
         err = d_invalidate(dentry);
         if (err)
@@ -808,7 +1557,13 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
         if (err)
                 goto out_up_write;
 
-        trans = btrfs_start_transaction(root, 1);
+        trans = btrfs_start_transaction(root, 0);
+        if (IS_ERR(trans)) {
+                err = PTR_ERR(trans);
+                goto out_up_write;
+        }
+        trans->block_rsv = &root->fs_info->global_block_rsv;
+
         ret = btrfs_unlink_subvol(trans, root, dir,
                                 dest->root_key.objectid,
                                 dentry->d_name.name,
@@ -822,12 +1577,14 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
         dest->root_item.drop_level = 0;
         btrfs_set_root_refs(&dest->root_item, 0);
 
-        ret = btrfs_insert_orphan_item(trans,
-                                root->fs_info->tree_root,
-                                dest->root_key.objectid);
-        BUG_ON(ret);
+        if (!xchg(&dest->orphan_item_inserted, 1)) {
+                ret = btrfs_insert_orphan_item(trans,
+                                        root->fs_info->tree_root,
+                                        dest->root_key.objectid);
+                BUG_ON(ret);
+        }
 
-        ret = btrfs_commit_transaction(trans, root);
+        ret = btrfs_end_transaction(trans, root);
         BUG_ON(ret);
         inode->i_flags |= S_DEAD;
 out_up_write:
@@ -849,12 +1606,16 @@ out:
         return err;
 }
 
-static int btrfs_ioctl_defrag(struct file *file)
+static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 {
         struct inode *inode = fdentry(file)->d_inode;
         struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct btrfs_ioctl_defrag_range_args *range;
         int ret;
 
+        if (btrfs_root_readonly(root))
+                return -EROFS;
+
         ret = mnt_want_write(file->f_path.mnt);
         if (ret)
                 return ret;
@@ -865,16 +1626,44 @@ static int btrfs_ioctl_defrag(struct file *file)
                         ret = -EPERM;
                         goto out;
                 }
-                btrfs_defrag_root(root, 0);
-                btrfs_defrag_root(root->fs_info->extent_root, 0);
+                ret = btrfs_defrag_root(root, 0);
+                if (ret)
+                        goto out;
+                ret = btrfs_defrag_root(root->fs_info->extent_root, 0);
                 break;
         case S_IFREG:
                 if (!(file->f_mode & FMODE_WRITE)) {
                         ret = -EINVAL;
                         goto out;
                 }
-                btrfs_defrag_file(file);
+
+                range = kzalloc(sizeof(*range), GFP_KERNEL);
+                if (!range) {
+                        ret = -ENOMEM;
+                        goto out;
+                }
+
+                if (argp) {
+                        if (copy_from_user(range, argp,
+                                           sizeof(*range))) {
+                                ret = -EFAULT;
+                                kfree(range);
+                                goto out;
+                        }
+                        /* compression requires us to start the IO */
+                        if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
+                                range->flags |= BTRFS_DEFRAG_RANGE_START_IO;
+                                range->extent_thresh = (u32)-1;
+                        }
+                } else {
+                        /* the rest are all set to zero by kzalloc */
+                        range->len = (u64)-1;
+                }
+                ret = btrfs_defrag_file(file, range);
+                kfree(range);
                 break;
+        default:
+                ret = -EINVAL;
         }
 out:
         mnt_drop_write(file->f_path.mnt);
@@ -952,9 +1741,12 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
          */
 
         /* the destination must be opened for writing */
-        if (!(file->f_mode & FMODE_WRITE))
+        if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
                 return -EINVAL;
 
+        if (btrfs_root_readonly(root))
+                return -EROFS;
+
         ret = mnt_want_write(file->f_path.mnt);
         if (ret)
                 return ret;
@@ -964,12 +1756,17 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                 ret = -EBADF;
                 goto out_drop_write;
         }
+
         src = src_file->f_dentry->d_inode;
 
         ret = -EINVAL;
         if (src == inode)
                 goto out_fput;
 
+        /* the src must be open for reading */
+        if (!(src_file->f_mode & FMODE_READ))
+                goto out_fput;
+
         ret = -EISDIR;
         if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
                 goto out_fput;
@@ -991,27 +1788,26 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
         path->reada = 2;
 
         if (inode < src) {
-                mutex_lock(&inode->i_mutex);
-                mutex_lock(&src->i_mutex);
+                mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
+                mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD);
         } else {
-                mutex_lock(&src->i_mutex);
-                mutex_lock(&inode->i_mutex);
+                mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT);
+                mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
         }
 
         /* determine range to clone */
         ret = -EINVAL;
-        if (off >= src->i_size || off + len > src->i_size)
+        if (off + len > src->i_size || off + len < off)
                 goto out_unlock;
         if (len == 0)
                 olen = len = src->i_size - off;
         /* if we extend to eof, continue to block boundary */
         if (off + len == src->i_size)
-                len = ((src->i_size + bs-1) & ~(bs-1))
-                        - off;
+                len = ALIGN(src->i_size, bs) - off;
 
         /* verify the end result is block aligned */
-        if ((off & (bs-1)) ||
-            ((off + len) & (bs-1)))
+        if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
+            !IS_ALIGNED(destoff, bs))
                 goto out_unlock;
 
         /* do any pending delalloc/csum calc on src, one way or
@@ -1019,21 +1815,17 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
         while (1) {
                 struct btrfs_ordered_extent *ordered;
                 lock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
-                ordered = btrfs_lookup_first_ordered_extent(inode, off+len);
-                if (BTRFS_I(src)->delalloc_bytes == 0 && !ordered)
+                ordered = btrfs_lookup_first_ordered_extent(src, off+len);
+                if (!ordered &&
+                    !test_range_bit(&BTRFS_I(src)->io_tree, off, off+len,
+                                   EXTENT_DELALLOC, 0, NULL))
                         break;
                 unlock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
                 if (ordered)
                         btrfs_put_ordered_extent(ordered);
-                btrfs_wait_ordered_range(src, off, off+len);
+                btrfs_wait_ordered_range(src, off, len);
         }
 
-        trans = btrfs_start_transaction(root, 1);
-        BUG_ON(!trans);
-
-        /* punch hole in destination first */
-        btrfs_drop_extents(trans, inode, off, off + len, &hint_byte, 1);
-
         /* clone data */
         key.objectid = src->i_ino;
         key.type = BTRFS_EXTENT_DATA_KEY;
@@ -1044,7 +1836,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                  * note the key will change type as we walk through the
                  * tree.
                  */
-                ret = btrfs_search_slot(trans, root, &key, path, 0, 0);
+                ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
                 if (ret < 0)
                         goto out;
 
@@ -1073,6 +1865,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                         u64 disko = 0, diskl = 0;
                         u64 datao = 0, datal = 0;
                         u8 comp;
+                        u64 endoff;
 
                         size = btrfs_item_size_nr(leaf, slot);
                         read_extent_buffer(leaf, buf,
@@ -1099,7 +1892,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                         }
                         btrfs_release_path(root, path);
 
-                        if (key.offset + datal < off ||
+                        if (key.offset + datal <= off ||
                             key.offset >= off+len)
                                 goto next;
 
@@ -1107,12 +1900,31 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                         new_key.objectid = inode->i_ino;
                         new_key.offset = key.offset + destoff - off;
 
+                        trans = btrfs_start_transaction(root, 1);
+                        if (IS_ERR(trans)) {
+                                ret = PTR_ERR(trans);
+                                goto out;
+                        }
+
                         if (type == BTRFS_FILE_EXTENT_REG ||
                             type == BTRFS_FILE_EXTENT_PREALLOC) {
+                                if (off > key.offset) {
+                                        datao += off - key.offset;
+                                        datal -= off - key.offset;
+                                }
+
+                                if (key.offset + datal > off + len)
+                                        datal = off + len - key.offset;
+
+                                ret = btrfs_drop_extents(trans, inode,
+                                                         new_key.offset,
+                                                         new_key.offset + datal,
+                                                         &hint_byte, 1);
+                                BUG_ON(ret);
+
                                 ret = btrfs_insert_empty_item(trans, root, path,
                                                               &new_key, size);
-                                if (ret)
-                                        goto out;
+                                BUG_ON(ret);
 
                                 leaf = path->nodes[0];
                                 slot = path->slots[0];
@@ -1123,14 +1935,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                                 extent = btrfs_item_ptr(leaf, slot,
                                                 struct btrfs_file_extent_item);
 
-                                if (off > key.offset) {
-                                        datao += off - key.offset;
-                                        datal -= off - key.offset;
-                                }
-
-                                if (key.offset + datal > off + len)
-                                        datal = off + len - key.offset;
-
                                 /* disko == 0 means it's a hole */
                                 if (!disko)
                                         datao = 0;
@@ -1161,14 +1965,21 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 
                                 if (comp && (skip || trim)) {
                                         ret = -EINVAL;
+                                        btrfs_end_transaction(trans, root);
                                         goto out;
                                 }
                                 size -= skip + trim;
                                 datal -= skip + trim;
+
+                                ret = btrfs_drop_extents(trans, inode,
+                                                         new_key.offset,
+                                                         new_key.offset + datal,
+                                                         &hint_byte, 1);
+                                BUG_ON(ret);
+
                                 ret = btrfs_insert_empty_item(trans, root, path,
                                                               &new_key, size);
-                                if (ret)
-                                        goto out;
+                                BUG_ON(ret);
 
                                 if (skip) {
                                         u32 start =
@@ -1186,8 +1997,26 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                         }
 
                         btrfs_mark_buffer_dirty(leaf);
-                }
+                        btrfs_release_path(root, path);
 
+                        inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+
+                        /*
+                         * we round up to the block size at eof when
+                         * determining which extents to clone above,
+                         * but shouldn't round up the file size
+                         */
+                        endoff = new_key.offset + datal;
+                        if (endoff > destoff+olen)
+                                endoff = destoff+olen;
+                        if (endoff > inode->i_size)
+                                btrfs_i_size_write(inode, endoff);
+
+                        BTRFS_I(inode)->flags = BTRFS_I(src)->flags;
+                        ret = btrfs_update_inode(trans, root, inode);
+                        BUG_ON(ret);
+                        btrfs_end_transaction(trans, root);
+                }
 next:
                 btrfs_release_path(root, path);
                 key.offset++;
@@ -1195,17 +2024,7 @@ next:
         ret = 0;
 out:
         btrfs_release_path(root, path);
-        if (ret == 0) {
-                inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-                if (destoff + olen > inode->i_size)
-                        btrfs_i_size_write(inode, destoff + olen);
-                BTRFS_I(inode)->flags = BTRFS_I(src)->flags;
-                ret = btrfs_update_inode(trans, root, inode);
-        }
-        btrfs_end_transaction(trans, root);
         unlock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
-        if (ret)
-                vmtruncate(inode, 0);
 out_unlock:
         mutex_unlock(&src->i_mutex);
         mutex_unlock(&inode->i_mutex);
@@ -1249,6 +2068,10 @@ static long btrfs_ioctl_trans_start(struct file *file)
         if (file->private_data)
                 goto out;
 
+        ret = -EROFS;
+        if (btrfs_root_readonly(root))
+                goto out;
+
         ret = mnt_want_write(file->f_path.mnt);
         if (ret)
                 goto out;
@@ -1274,6 +2097,209 @@ out:
         return ret;
 }
 
+static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
+{
+        struct inode *inode = fdentry(file)->d_inode;
+        struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct btrfs_root *new_root;
+        struct btrfs_dir_item *di;
+        struct btrfs_trans_handle *trans;
+        struct btrfs_path *path;
+        struct btrfs_key location;
+        struct btrfs_disk_key disk_key;
+        struct btrfs_super_block *disk_super;
+        u64 features;
+        u64 objectid = 0;
+        u64 dir_id;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        if (copy_from_user(&objectid, argp, sizeof(objectid)))
+                return -EFAULT;
+
+        if (!objectid)
+                objectid = root->root_key.objectid;
+
+        location.objectid = objectid;
+        location.type = BTRFS_ROOT_ITEM_KEY;
+        location.offset = (u64)-1;
+
+        new_root = btrfs_read_fs_root_no_name(root->fs_info, &location);
+        if (IS_ERR(new_root))
+                return PTR_ERR(new_root);
+
+        if (btrfs_root_refs(&new_root->root_item) == 0)
+                return -ENOENT;
+
+        path = btrfs_alloc_path();
+        if (!path)
+                return -ENOMEM;
+        path->leave_spinning = 1;
+
+        trans = btrfs_start_transaction(root, 1);
+        if (!trans) {
+                btrfs_free_path(path);
+                return -ENOMEM;
+        }
+
+        dir_id = btrfs_super_root_dir(&root->fs_info->super_copy);
+        di = btrfs_lookup_dir_item(trans, root->fs_info->tree_root, path,
+                                   dir_id, "default", 7, 1);
+        if (IS_ERR_OR_NULL(di)) {
+                btrfs_free_path(path);
+                btrfs_end_transaction(trans, root);
+                printk(KERN_ERR "Umm, you don't have the default dir item, "
+                       "this isn't going to work\n");
+                return -ENOENT;
+        }
+
+        btrfs_cpu_key_to_disk(&disk_key, &new_root->root_key);
+        btrfs_set_dir_item_key(path->nodes[0], di, &disk_key);
+        btrfs_mark_buffer_dirty(path->nodes[0]);
+        btrfs_free_path(path);
+
+        disk_super = &root->fs_info->super_copy;
+        features = btrfs_super_incompat_flags(disk_super);
+        if (!(features & BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL)) {
+                features |= BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL;
+                btrfs_set_super_incompat_flags(disk_super, features);
+        }
+        btrfs_end_transaction(trans, root);
+
+        return 0;
+}
+
+static void get_block_group_info(struct list_head *groups_list,
+                                 struct btrfs_ioctl_space_info *space)
+{
+        struct btrfs_block_group_cache *block_group;
+
+        space->total_bytes = 0;
+        space->used_bytes = 0;
+        space->flags = 0;
+        list_for_each_entry(block_group, groups_list, list) {
+                space->flags = block_group->flags;
+                space->total_bytes += block_group->key.offset;
+                space->used_bytes +=
+                        btrfs_block_group_used(&block_group->item);
+        }
+}
+
+long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
+{
+        struct btrfs_ioctl_space_args space_args;
+        struct btrfs_ioctl_space_info space;
+        struct btrfs_ioctl_space_info *dest;
+        struct btrfs_ioctl_space_info *dest_orig;
+        struct btrfs_ioctl_space_info *user_dest;
+        struct btrfs_space_info *info;
+        u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
+                       BTRFS_BLOCK_GROUP_SYSTEM,
+                       BTRFS_BLOCK_GROUP_METADATA,
+                       BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
+        int num_types = 4;
+        int alloc_size;
+        int ret = 0;
+        int slot_count = 0;
+        int i, c;
+
+        if (copy_from_user(&space_args,
+                           (struct btrfs_ioctl_space_args __user *)arg,
+                           sizeof(space_args)))
+                return -EFAULT;
+
+        for (i = 0; i < num_types; i++) {
+                struct btrfs_space_info *tmp;
+
+                info = NULL;
+                rcu_read_lock();
+                list_for_each_entry_rcu(tmp, &root->fs_info->space_info,
+                                        list) {
+                        if (tmp->flags == types[i]) {
+                                info = tmp;
+                                break;
+                        }
+                }
+                rcu_read_unlock();
+
+                if (!info)
+                        continue;
+
+                down_read(&info->groups_sem);
+                for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
+                        if (!list_empty(&info->block_groups[c]))
+                                slot_count++;
+                }
+                up_read(&info->groups_sem);
+        }
+
+        /* space_slots == 0 means they are asking for a count */
+        if (space_args.space_slots == 0) {
+                space_args.total_spaces = slot_count;
+                goto out;
+        }
+
+        slot_count = min_t(int, space_args.space_slots, slot_count);
+
+        alloc_size = sizeof(*dest) * slot_count;
+
+        /* we generally have at most 6 or so space infos, one for each raid
+         * level.  So, a whole page should be more than enough for everyone
+         */
+        if (alloc_size > PAGE_CACHE_SIZE)
+                return -ENOMEM;
+
+        space_args.total_spaces = 0;
+        dest = kmalloc(alloc_size, GFP_NOFS);
+        if (!dest)
+                return -ENOMEM;
+        dest_orig = dest;
+
+        /* now we have a buffer to copy into */
+        for (i = 0; i < num_types; i++) {
+                struct btrfs_space_info *tmp;
+
+                info = NULL;
+                rcu_read_lock();
+                list_for_each_entry_rcu(tmp, &root->fs_info->space_info,
+                                        list) {
+                        if (tmp->flags == types[i]) {
+                                info = tmp;
+                                break;
+                        }
+                }
+                rcu_read_unlock();
+
+                if (!info)
+                        continue;
+                down_read(&info->groups_sem);
+                for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
+                        if (!list_empty(&info->block_groups[c])) {
+                                get_block_group_info(&info->block_groups[c],
+                                                     &space);
+                                memcpy(dest, &space, sizeof(space));
+                                dest++;
+                                space_args.total_spaces++;
+                        }
+                }
+                up_read(&info->groups_sem);
+        }
+
+        user_dest = (struct btrfs_ioctl_space_info *)
+                (arg + sizeof(struct btrfs_ioctl_space_args));
+
+        if (copy_to_user(user_dest, dest_orig, alloc_size))
+                ret = -EFAULT;
+
+        kfree(dest_orig);
+out:
+        if (ret == 0 && copy_to_user(arg, &space_args, sizeof(space_args)))
+                ret = -EFAULT;
+
+        return ret;
+}
+
 /*
  * there are many ways the trans_start and trans_end ioctls can lead
  * to deadlocks.  They should only be used by applications that
@@ -1301,6 +2327,36 @@ long btrfs_ioctl_trans_end(struct file *file)
         return 0;
 }
 
+static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp)
+{
+        struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root;
+        struct btrfs_trans_handle *trans;
+        u64 transid;
+
+        trans = btrfs_start_transaction(root, 0);
+        transid = trans->transid;
+        btrfs_commit_transaction_async(trans, root, 0);
+
+        if (argp)
+                if (copy_to_user(argp, &transid, sizeof(transid)))
+                        return -EFAULT;
+        return 0;
+}
+
+static noinline long btrfs_ioctl_wait_sync(struct file *file, void __user *argp)
+{
+        struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root;
+        u64 transid;
+
+        if (argp) {
+                if (copy_from_user(&transid, argp, sizeof(transid)))
+                        return -EFAULT;
+        } else {
+                transid = 0;  /* current trans */
+        }
+        return btrfs_wait_for_commit(root, transid);
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
                 cmd, unsigned long arg)
 {
@@ -1316,12 +2372,22 @@ long btrfs_ioctl(struct file *file, unsigned int
                 return btrfs_ioctl_getversion(file, argp);
         case BTRFS_IOC_SNAP_CREATE:
                 return btrfs_ioctl_snap_create(file, argp, 0);
+        case BTRFS_IOC_SNAP_CREATE_V2:
+                return btrfs_ioctl_snap_create_v2(file, argp, 0);
         case BTRFS_IOC_SUBVOL_CREATE:
                 return btrfs_ioctl_snap_create(file, argp, 1);
         case BTRFS_IOC_SNAP_DESTROY:
                 return btrfs_ioctl_snap_destroy(file, argp);
+        case BTRFS_IOC_SUBVOL_GETFLAGS:
+                return btrfs_ioctl_subvol_getflags(file, argp);
+        case BTRFS_IOC_SUBVOL_SETFLAGS:
+                return btrfs_ioctl_subvol_setflags(file, argp);
+        case BTRFS_IOC_DEFAULT_SUBVOL:
+                return btrfs_ioctl_default_subvol(file, argp);
         case BTRFS_IOC_DEFRAG:
-                return btrfs_ioctl_defrag(file);
+                return btrfs_ioctl_defrag(file, NULL);
+        case BTRFS_IOC_DEFRAG_RANGE:
+                return btrfs_ioctl_defrag(file, argp);
         case BTRFS_IOC_RESIZE:
                 return btrfs_ioctl_resize(root, argp);
         case BTRFS_IOC_ADD_DEV:
@@ -1338,9 +2404,19 @@ long btrfs_ioctl(struct file *file, unsigned int
                 return btrfs_ioctl_trans_start(file);
         case BTRFS_IOC_TRANS_END:
                 return btrfs_ioctl_trans_end(file);
+        case BTRFS_IOC_TREE_SEARCH:
+                return btrfs_ioctl_tree_search(file, argp);
+        case BTRFS_IOC_INO_LOOKUP:
+                return btrfs_ioctl_ino_lookup(file, argp);
+        case BTRFS_IOC_SPACE_INFO:
+                return btrfs_ioctl_space_info(root, argp);
         case BTRFS_IOC_SYNC:
                 btrfs_sync_fs(file->f_dentry->d_sb, 1);
                 return 0;
+        case BTRFS_IOC_START_SYNC:
+                return btrfs_ioctl_start_sync(file, argp);
+        case BTRFS_IOC_WAIT_SYNC:
+                return btrfs_ioctl_wait_sync(file, argp);
         }
 
         return -ENOTTY;