8 files changed, 98 insertions, 34 deletions

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 502b9e988679..d9f99a16edd6 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -176,7 +176,11 @@ static inline u64 btrfs_ino(struct inode *inode)
 {
         u64 ino = BTRFS_I(inode)->location.objectid;
 
-        if (ino <= BTRFS_FIRST_FREE_OBJECTID)
+        /*
+         * !ino: btree_inode
+         * type == BTRFS_ROOT_ITEM_KEY: subvol dir
+         */
+        if (!ino || BTRFS_I(inode)->location.type == BTRFS_ROOT_ITEM_KEY)
                 ino = inode->i_ino;
         return ino;
 }
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index b910694f61ed..a1cb7821becd 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -183,8 +183,10 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
          * read from the commit root and sidestep a nasty deadlock
          * between reading the free space cache and updating the csum tree.
          */
-        if (btrfs_is_free_space_inode(root, inode))
+        if (btrfs_is_free_space_inode(root, inode)) {
                 path->search_commit_root = 1;
+                path->skip_locking = 1;
+        }
 
         disk_bytenr = (u64)bio->bi_sector << 9;
         if (dio)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e7872e485f13..a381cd22f518 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1075,12 +1075,6 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
         start_pos = pos & ~((u64)root->sectorsize - 1);
         last_pos = ((u64)index + num_pages) << PAGE_CACHE_SHIFT;
 
-        if (start_pos > inode->i_size) {
-                err = btrfs_cont_expand(inode, i_size_read(inode), start_pos);
-                if (err)
-                        return err;
-        }
-
 again:
         for (i = 0; i < num_pages; i++) {
                 pages[i] = find_or_create_page(inode->i_mapping, index + i,
@@ -1338,6 +1332,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
         struct inode *inode = fdentry(file)->d_inode;
         struct btrfs_root *root = BTRFS_I(inode)->root;
         loff_t *ppos = &iocb->ki_pos;
+        u64 start_pos;
         ssize_t num_written = 0;
         ssize_t err = 0;
         size_t count, ocount;
@@ -1386,6 +1381,15 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
         file_update_time(file);
         BTRFS_I(inode)->sequence++;
 
+        start_pos = round_down(pos, root->sectorsize);
+        if (start_pos > i_size_read(inode)) {
+                err = btrfs_cont_expand(inode, i_size_read(inode), start_pos);
+                if (err) {
+                        mutex_unlock(&inode->i_mutex);
+                        goto out;
+                }
+        }
+
         if (unlikely(file->f_flags & O_DIRECT)) {
                 num_written = __btrfs_direct_write(iocb, iov, nr_segs,
                                                    pos, ppos, count, ocount);
@@ -1813,6 +1817,11 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
                 goto out;
         case SEEK_DATA:
         case SEEK_HOLE:
+                if (offset >= i_size_read(inode)) {
+                        mutex_unlock(&inode->i_mutex);
+                        return -ENXIO;
+                }
+
                 ret = find_desired_extent(inode, &offset, origin);
                 if (ret) {
                         mutex_unlock(&inode->i_mutex);
@@ -1821,11 +1830,11 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
         }
 
         if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) {
-                ret = -EINVAL;
+                offset = -EINVAL;
                 goto out;
         }
         if (offset > inode->i_sb->s_maxbytes) {
-                ret = -EINVAL;
+                offset = -EINVAL;
                 goto out;
         }
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6a265b9f85f2..41ac927401d0 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -190,9 +190,11 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
                                     struct btrfs_path *path,
                                     struct inode *inode)
 {
+        struct btrfs_block_rsv *rsv;
         loff_t oldsize;
         int ret = 0;
 
+        rsv = trans->block_rsv;
         trans->block_rsv = root->orphan_block_rsv;
         ret = btrfs_block_rsv_check(trans, root,
                                     root->orphan_block_rsv,
@@ -210,6 +212,8 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
          */
         ret = btrfs_truncate_inode_items(trans, root, inode,
                                          0, BTRFS_EXTENT_DATA_KEY);
+
+        trans->block_rsv = rsv;
         if (ret) {
                 WARN_ON(1);
                 return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0ccc7438ad34..b2d004ad66a0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1786,7 +1786,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
                           &ordered_extent->list);
 
         ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
-        if (!ret) {
+        if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
                 ret = btrfs_update_inode(trans, root, inode);
                 BUG_ON(ret);
         }
@@ -3510,15 +3510,19 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
                         err = btrfs_drop_extents(trans, inode, cur_offset,
                                                  cur_offset + hole_size,
                                                  &hint_byte, 1);
-                        if (err)
+                        if (err) {
+                                btrfs_end_transaction(trans, root);
                                 break;
+                        }
 
                         err = btrfs_insert_file_extent(trans, root,
                                         btrfs_ino(inode), cur_offset, 0,
                                         0, hole_size, 0, hole_size,
                                         0, 0, 0);
-                        if (err)
+                        if (err) {
+                                btrfs_end_transaction(trans, root);
                                 break;
+                        }
 
                         btrfs_drop_extent_cache(inode, hole_start,
                                         last_byte - 1, 0);
@@ -3952,7 +3956,6 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
                          struct btrfs_root *root, int *new)
 {
         struct inode *inode;
-        int bad_inode = 0;
 
         inode = btrfs_iget_locked(s, location->objectid, root);
         if (!inode)
@@ -3968,15 +3971,12 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
                         if (new)
                                 *new = 1;
                 } else {
-                        bad_inode = 1;
+                        unlock_new_inode(inode);
+                        iput(inode);
+                        inode = ERR_PTR(-ESTALE);
                 }
         }
 
-        if (bad_inode) {
-                iput(inode);
-                inode = ERR_PTR(-ESTALE);
-        }
-
         return inode;
 }
 
@@ -4018,7 +4018,8 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
                 memcpy(&location, dentry->d_fsdata, sizeof(struct btrfs_key));
                 kfree(dentry->d_fsdata);
                 dentry->d_fsdata = NULL;
-                d_clear_need_lookup(dentry);
+                /* This thing is hashed, drop it for now */
+                d_drop(dentry);
         } else {
                 ret = btrfs_inode_by_name(dir, dentry, &location);
         }
@@ -4085,7 +4086,15 @@ static void btrfs_dentry_release(struct dentry *dentry)
 static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
                                    struct nameidata *nd)
 {
-        return d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
+        struct dentry *ret;
+
+        ret = d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
+        if (unlikely(d_need_lookup(dentry))) {
+                spin_lock(&dentry->d_lock);
+                dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
+                spin_unlock(&dentry->d_lock);
+        }
+        return ret;
 }
 
 unsigned char btrfs_filetype_table[] = {
@@ -4125,7 +4134,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 
         /* special case for "." */
         if (filp->f_pos == 0) {
-                over = filldir(dirent, ".", 1, 1, btrfs_ino(inode), DT_DIR);
+                over = filldir(dirent, ".", 1,
+                               filp->f_pos, btrfs_ino(inode), DT_DIR);
                 if (over)
                         return 0;
                 filp->f_pos = 1;
@@ -4134,7 +4144,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
         if (filp->f_pos == 1) {
                 u64 pino = parent_ino(filp->f_path.dentry);
                 over = filldir(dirent, "..", 2,
-                               2, pino, DT_DIR);
+                               filp->f_pos, pino, DT_DIR);
                 if (over)
                         return 0;
                 filp->f_pos = 2;
@@ -5823,7 +5833,7 @@ again:
 
         add_pending_csums(trans, inode, ordered->file_offset, &ordered->list);
         ret = btrfs_ordered_update_i_size(inode, 0, ordered);
-        if (!ret)
+        if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags))
                 btrfs_update_inode(trans, root, inode);
         ret = 0;
 out_unlock:
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 970977aab224..538f65a79ec5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2177,6 +2177,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
         if (!(src_file->f_mode & FMODE_READ))
                 goto out_fput;
 
+        /* don't make the dst file partly checksummed */
+        if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+            (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
+                goto out_fput;
+
         ret = -EISDIR;
         if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
                 goto out_fput;
@@ -2220,6 +2225,16 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
             !IS_ALIGNED(destoff, bs))
                 goto out_unlock;
 
+        if (destoff > inode->i_size) {
+                ret = btrfs_cont_expand(inode, inode->i_size, destoff);
+                if (ret)
+                        goto out_unlock;
+        }
+
+        /* truncate page cache pages from target inode range */
+        truncate_inode_pages_range(&inode->i_data, destoff,
+                                   PAGE_CACHE_ALIGN(destoff + len) - 1);
+
         /* do any pending delalloc/csum calc on src, one way or
            another, and lock file content */
         while (1) {
@@ -2236,10 +2251,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                 btrfs_wait_ordered_range(src, off, len);
         }
 
-        /* truncate page cache pages from target inode range */
-        truncate_inode_pages_range(&inode->i_data, off,
-                                   ALIGN(off + len, PAGE_CACHE_SIZE) - 1);
-
         /* clone data */
         key.objectid = btrfs_ino(src);
         key.type = BTRFS_EXTENT_DATA_KEY;
@@ -2317,7 +2328,12 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                         else
                                 new_key.offset = destoff;
 
-                        trans = btrfs_start_transaction(root, 1);
+                        /*
+                         * 1 - adjusting old extent (we may have to split it)
+                         * 1 - add new extent
+                         * 1 - inode update
+                         */
+                        trans = btrfs_start_transaction(root, 3);
                         if (IS_ERR(trans)) {
                                 ret = PTR_ERR(trans);
                                 goto out;
@@ -2325,14 +2341,21 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 
                         if (type == BTRFS_FILE_EXTENT_REG ||
                             type == BTRFS_FILE_EXTENT_PREALLOC) {
+                                /*
+                                 *    a  | --- range to clone ---|  b
+                                 * | ------------- extent ------------- |
+                                 */
+
+                                /* substract range b */
+                                if (key.offset + datal > off + len)
+                                        datal = off + len - key.offset;
+
+                                /* substract range a */
                                 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,
@@ -2429,7 +2452,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
                         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);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 7dc36fab4afc..e24b7964a155 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -884,6 +884,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
         struct btrfs_root *tree_root = fs_info->tree_root;
         struct btrfs_root *root = pending->root;
         struct btrfs_root *parent_root;
+        struct btrfs_block_rsv *rsv;
         struct inode *parent_inode;
         struct dentry *parent;
         struct dentry *dentry;
@@ -895,6 +896,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
         u64 objectid;
         u64 root_flags;
 
+        rsv = trans->block_rsv;
+
         new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
         if (!new_root_item) {
                 pending->error = -ENOMEM;
@@ -1002,6 +1005,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
         btrfs_orphan_post_snapshot(trans, pending);
 fail:
         kfree(new_root_item);
+        trans->block_rsv = rsv;
         btrfs_block_rsv_release(root, &pending->block_rsv, (u64)-1);
         return 0;
 }
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index d733b9cfea34..69565e5fc6a0 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -116,6 +116,12 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
                 if (ret)
                         goto out;
                 btrfs_release_path(path);
+
+                /*
+                 * remove the attribute
+                 */
+                if (!value)
+                        goto out;
         }
 
 again:
@@ -158,6 +164,9 @@ out:
         return ret;
 }
 
+/*
+ * @value: "" makes the attribute to empty, NULL removes it
+ */
 int __btrfs_setxattr(struct btrfs_trans_handle *trans,
                      struct inode *inode, const char *name,
                      const void *value, size_t size, int flags)