1 files changed, 364 insertions, 193 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 512c3d1da083..fcd66b6a8086 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -50,6 +50,7 @@
 #include "tree-log.h"
 #include "compression.h"
 #include "locking.h"
+#include "free-space-cache.h"
 
 struct btrfs_iget_args {
         u64 ino;
@@ -70,6 +71,7 @@ static struct kmem_cache *btrfs_inode_cachep;
 struct kmem_cache *btrfs_trans_handle_cachep;
 struct kmem_cache *btrfs_transaction_cachep;
 struct kmem_cache *btrfs_path_cachep;
+struct kmem_cache *btrfs_free_space_cachep;
 
 #define S_SHIFT 12
 static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
@@ -82,7 +84,8 @@ static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
         [S_IFLNK >> S_SHIFT]    = BTRFS_FT_SYMLINK,
 };
 
-static void btrfs_truncate(struct inode *inode);
+static int btrfs_setsize(struct inode *inode, loff_t newsize);
+static int btrfs_truncate(struct inode *inode);
 static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end);
 static noinline int cow_file_range(struct inode *inode,
                                    struct page *locked_page,
@@ -109,6 +112,7 @@ static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
 static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
                                 struct btrfs_root *root, struct inode *inode,
                                 u64 start, size_t size, size_t compressed_size,
+                                int compress_type,
                                 struct page **compressed_pages)
 {
         struct btrfs_key key;
@@ -123,12 +127,9 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
         size_t cur_size = size;
         size_t datasize;
         unsigned long offset;
-        int compress_type = BTRFS_COMPRESS_NONE;
 
-        if (compressed_size && compressed_pages) {
-                compress_type = root->fs_info->compress_type;
+        if (compressed_size && compressed_pages)
                 cur_size = compressed_size;
-        }
 
         path = btrfs_alloc_path();
         if (!path)
@@ -218,7 +219,7 @@ fail:
 static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root,
                                  struct inode *inode, u64 start, u64 end,
-                                 size_t compressed_size,
+                                 size_t compressed_size, int compress_type,
                                  struct page **compressed_pages)
 {
         u64 isize = i_size_read(inode);
@@ -251,7 +252,7 @@ static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans,
                 inline_len = min_t(u64, isize, actual_end);
         ret = insert_inline_extent(trans, root, inode, start,
                                    inline_len, compressed_size,
-                                   compressed_pages);
+                                   compress_type, compressed_pages);
         BUG_ON(ret);
         btrfs_delalloc_release_metadata(inode, end + 1 - start);
         btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
@@ -288,6 +289,7 @@ static noinline int add_async_extent(struct async_cow *cow,
         struct async_extent *async_extent;
 
         async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
+        BUG_ON(!async_extent);
         async_extent->start = start;
         async_extent->ram_size = ram_size;
         async_extent->compressed_size = compressed_size;
@@ -382,9 +384,11 @@ again:
          */
         if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) &&
             (btrfs_test_opt(root, COMPRESS) ||
-             (BTRFS_I(inode)->force_compress))) {
+             (BTRFS_I(inode)->force_compress) ||
+             (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))) {
                 WARN_ON(pages);
                 pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+                BUG_ON(!pages);
 
                 if (BTRFS_I(inode)->force_compress)
                         compress_type = BTRFS_I(inode)->force_compress;
@@ -427,12 +431,13 @@ again:
                          * to make an uncompressed inline extent.
                          */
                         ret = cow_file_range_inline(trans, root, inode,
-                                                    start, end, 0, NULL);
+                                                    start, end, 0, 0, NULL);
                 } else {
                         /* try making a compressed inline extent */
                         ret = cow_file_range_inline(trans, root, inode,
                                                     start, end,
-                                                    total_compressed, pages);
+                                                    total_compressed,
+                                                    compress_type, pages);
                 }
                 if (ret == 0) {
                         /*
@@ -786,7 +791,7 @@ static noinline int cow_file_range(struct inode *inode,
         if (start == 0) {
                 /* lets try to make an inline extent */
                 ret = cow_file_range_inline(trans, root, inode,
-                                            start, end, 0, NULL);
+                                            start, end, 0, 0, NULL);
                 if (ret == 0) {
                         extent_clear_unlock_delalloc(inode,
                                      &BTRFS_I(inode)->io_tree,
@@ -1254,7 +1259,8 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
                 ret = run_delalloc_nocow(inode, locked_page, start, end,
                                          page_started, 0, nr_written);
         else if (!btrfs_test_opt(root, COMPRESS) &&
-                 !(BTRFS_I(inode)->force_compress))
+                 !(BTRFS_I(inode)->force_compress) &&
+                 !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))
                 ret = cow_file_range(inode, locked_page, start, end,
                                       page_started, nr_written, 1);
         else
@@ -1461,8 +1467,11 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
                 if (bio_flags & EXTENT_BIO_COMPRESSED) {
                         return btrfs_submit_compressed_read(inode, bio,
                                                     mirror_num, bio_flags);
-                } else if (!skip_sum)
-                        btrfs_lookup_bio_sums(root, inode, bio, NULL);
+                } else if (!skip_sum) {
+                        ret = btrfs_lookup_bio_sums(root, inode, bio, NULL);
+                        if (ret)
+                                return ret;
+                }
                 goto mapit;
         } else if (!skip_sum) {
                 /* csum items have already been cloned */
@@ -1761,9 +1770,12 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
         add_pending_csums(trans, inode, ordered_extent->file_offset,
                           &ordered_extent->list);
 
-        btrfs_ordered_update_i_size(inode, 0, ordered_extent);
-        ret = btrfs_update_inode(trans, root, inode);
-        BUG_ON(ret);
+        ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
+        if (!ret) {
+                ret = btrfs_update_inode(trans, root, inode);
+                BUG_ON(ret);
+        }
+        ret = 0;
 out:
         if (nolock) {
                 if (trans)
@@ -1785,6 +1797,8 @@ out:
 static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
                                 struct extent_state *state, int uptodate)
 {
+        trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
+
         ClearPagePrivate2(page);
         return btrfs_finish_ordered_io(page->mapping->host, start, end);
 }
@@ -1895,10 +1909,10 @@ static int btrfs_io_failed_hook(struct bio *failed_bio,
         else
                 rw = READ;
 
-        BTRFS_I(inode)->io_tree.ops->submit_bio_hook(inode, rw, bio,
+        ret = BTRFS_I(inode)->io_tree.ops->submit_bio_hook(inode, rw, bio,
                                                       failrec->last_mirror,
                                                       failrec->bio_flags, 0);
-        return 0;
+        return ret;
 }
 
 /*
@@ -2210,8 +2224,6 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
                         insert = 1;
 #endif
                 insert = 1;
-        } else {
-                WARN_ON(!BTRFS_I(inode)->orphan_meta_reserved);
         }
 
         if (!BTRFS_I(inode)->orphan_meta_reserved) {
@@ -2282,7 +2294,7 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode)
  * this cleans up any orphans that may be left on the list from the last use
  * of this root.
  */
-void btrfs_orphan_cleanup(struct btrfs_root *root)
+int btrfs_orphan_cleanup(struct btrfs_root *root)
 {
         struct btrfs_path *path;
         struct extent_buffer *leaf;
@@ -2292,10 +2304,13 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
         int ret = 0, nr_unlink = 0, nr_truncate = 0;
 
         if (cmpxchg(&root->orphan_cleanup_state, 0, ORPHAN_CLEANUP_STARTED))
-                return;
+                return 0;
 
         path = btrfs_alloc_path();
-        BUG_ON(!path);
+        if (!path) {
+                ret = -ENOMEM;
+                goto out;
+        }
         path->reada = -1;
 
         key.objectid = BTRFS_ORPHAN_OBJECTID;
@@ -2304,18 +2319,16 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 
         while (1) {
                 ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-                if (ret < 0) {
-                        printk(KERN_ERR "Error searching slot for orphan: %d"
-                               "\n", ret);
-                        break;
-                }
+                if (ret < 0)
+                        goto out;
 
                 /*
                  * if ret == 0 means we found what we were searching for, which
-                 * is weird, but possible, so only screw with path if we didnt
+                 * is weird, but possible, so only screw with path if we didn't
                  * find the key and see if we have stuff that matches
                  */
                 if (ret > 0) {
+                        ret = 0;
                         if (path->slots[0] == 0)
                                 break;
                         path->slots[0]--;
@@ -2343,7 +2356,10 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
                 found_key.type = BTRFS_INODE_ITEM_KEY;
                 found_key.offset = 0;
                 inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL);
-                BUG_ON(IS_ERR(inode));
+                if (IS_ERR(inode)) {
+                        ret = PTR_ERR(inode);
+                        goto out;
+                }
 
                 /*
                  * add this inode to the orphan list so btrfs_orphan_del does
@@ -2361,7 +2377,10 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
                  */
                 if (is_bad_inode(inode)) {
                         trans = btrfs_start_transaction(root, 0);
-                        BUG_ON(IS_ERR(trans));
+                        if (IS_ERR(trans)) {
+                                ret = PTR_ERR(trans);
+                                goto out;
+                        }
                         btrfs_orphan_del(trans, inode);
                         btrfs_end_transaction(trans, root);
                         iput(inode);
@@ -2370,17 +2389,22 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 
                 /* if we have links, this was a truncate, lets do that */
                 if (inode->i_nlink) {
+                        if (!S_ISREG(inode->i_mode)) {
+                                WARN_ON(1);
+                                iput(inode);
+                                continue;
+                        }
                         nr_truncate++;
-                        btrfs_truncate(inode);
+                        ret = btrfs_truncate(inode);
                 } else {
                         nr_unlink++;
                 }
 
                 /* this will do delete_inode and everything for us */
                 iput(inode);
+                if (ret)
+                        goto out;
         }
-        btrfs_free_path(path);
-
         root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE;
 
         if (root->orphan_block_rsv)
@@ -2389,14 +2413,20 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 
         if (root->orphan_block_rsv || root->orphan_item_inserted) {
                 trans = btrfs_join_transaction(root, 1);
-                BUG_ON(IS_ERR(trans));
-                btrfs_end_transaction(trans, root);
+                if (!IS_ERR(trans))
+                        btrfs_end_transaction(trans, root);
         }
 
         if (nr_unlink)
                 printk(KERN_INFO "btrfs: unlinked %d orphans\n", nr_unlink);
         if (nr_truncate)
                 printk(KERN_INFO "btrfs: truncated %d orphans\n", nr_truncate);
+
+out:
+        if (ret)
+                printk(KERN_CRIT "btrfs: could not do orphan cleanup %d\n", ret);
+        btrfs_free_path(path);
+        return ret;
 }
 
 /*
@@ -2563,6 +2593,13 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
                             struct btrfs_inode_item *item,
                             struct inode *inode)
 {
+        if (!leaf->map_token)
+                map_private_extent_buffer(leaf, (unsigned long)item,
+                                          sizeof(struct btrfs_inode_item),
+                                          &leaf->map_token, &leaf->kaddr,
+                                          &leaf->map_start, &leaf->map_len,
+                                          KM_USER1);
+
         btrfs_set_inode_uid(leaf, item, inode->i_uid);
         btrfs_set_inode_gid(leaf, item, inode->i_gid);
         btrfs_set_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size);
@@ -2591,6 +2628,11 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
         btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
         btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
         btrfs_set_inode_block_group(leaf, item, BTRFS_I(inode)->block_group);
+
+        if (leaf->map_token) {
+                unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
+                leaf->map_token = NULL;
+        }
 }
 
 /*
@@ -2635,10 +2677,10 @@ failed:
  * recovery code.  It remove a link in a directory with a given name, and
  * also drops the back refs in the inode to the directory
  */
-int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
-                       struct btrfs_root *root,
-                       struct inode *dir, struct inode *inode,
-                       const char *name, int name_len)
+static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
+                                struct btrfs_root *root,
+                                struct inode *dir, struct inode *inode,
+                                const char *name, int name_len)
 {
         struct btrfs_path *path;
         int ret = 0;
@@ -2710,12 +2752,25 @@ err:
         btrfs_i_size_write(dir, dir->i_size - name_len * 2);
         inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
         btrfs_update_inode(trans, root, dir);
-        btrfs_drop_nlink(inode);
-        ret = btrfs_update_inode(trans, root, inode);
 out:
         return ret;
 }
 
+int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
+                       struct btrfs_root *root,
+                       struct inode *dir, struct inode *inode,
+                       const char *name, int name_len)
+{
+        int ret;
+        ret = __btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
+        if (!ret) {
+                btrfs_drop_nlink(inode);
+                ret = btrfs_update_inode(trans, root, inode);
+        }
+        return ret;
+}
+                
+
 /* helper to check if there is any shared block in the path */
 static int check_path_shared(struct btrfs_root *root,
                              struct btrfs_path *path)
@@ -3537,7 +3592,13 @@ out:
         return ret;
 }
 
-int btrfs_cont_expand(struct inode *inode, loff_t size)
+/*
+ * This function puts in dummy file extents for the area we're creating a hole
+ * for.  So if we are truncating this file to a larger size we need to insert
+ * these file extents so that btrfs_get_extent will return a EXTENT_MAP_HOLE for
+ * the range between oldsize and size
+ */
+int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 {
         struct btrfs_trans_handle *trans;
         struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -3545,7 +3606,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t size)
         struct extent_map *em = NULL;
         struct extent_state *cached_state = NULL;
         u64 mask = root->sectorsize - 1;
-        u64 hole_start = (inode->i_size + mask) & ~mask;
+        u64 hole_start = (oldsize + mask) & ~mask;
         u64 block_end = (size + mask) & ~mask;
         u64 last_byte;
         u64 cur_offset;
@@ -3590,13 +3651,15 @@ int btrfs_cont_expand(struct inode *inode, loff_t size)
                         err = btrfs_drop_extents(trans, inode, cur_offset,
                                                  cur_offset + hole_size,
                                                  &hint_byte, 1);
-                        BUG_ON(err);
+                        if (err)
+                                break;
 
                         err = btrfs_insert_file_extent(trans, root,
                                         inode->i_ino, cur_offset, 0,
                                         0, hole_size, 0, hole_size,
                                         0, 0, 0);
-                        BUG_ON(err);
+                        if (err)
+                                break;
 
                         btrfs_drop_extent_cache(inode, hole_start,
                                         last_byte - 1, 0);
@@ -3616,81 +3679,41 @@ int btrfs_cont_expand(struct inode *inode, loff_t size)
         return err;
 }
 
-static int btrfs_setattr_size(struct inode *inode, struct iattr *attr)
+static int btrfs_setsize(struct inode *inode, loff_t newsize)
 {
-        struct btrfs_root *root = BTRFS_I(inode)->root;
-        struct btrfs_trans_handle *trans;
-        unsigned long nr;
+        loff_t oldsize = i_size_read(inode);
         int ret;
 
-        if (attr->ia_size == inode->i_size)
+        if (newsize == oldsize)
                 return 0;
 
-        if (attr->ia_size > inode->i_size) {
-                unsigned long limit;
-                limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
-                if (attr->ia_size > inode->i_sb->s_maxbytes)
-                        return -EFBIG;
-                if (limit != RLIM_INFINITY && attr->ia_size > limit) {
-                        send_sig(SIGXFSZ, current, 0);
-                        return -EFBIG;
-                }
-        }
-
-        trans = btrfs_start_transaction(root, 5);
-        if (IS_ERR(trans))
-                return PTR_ERR(trans);
-
-        btrfs_set_trans_block_group(trans, inode);
-
-        ret = btrfs_orphan_add(trans, inode);
-        BUG_ON(ret);
-
-        nr = trans->blocks_used;
-        btrfs_end_transaction(trans, root);
-        btrfs_btree_balance_dirty(root, nr);
-
-        if (attr->ia_size > inode->i_size) {
-                ret = btrfs_cont_expand(inode, attr->ia_size);
+        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_truncate(inode);
+                        btrfs_setsize(inode, oldsize);
                         return ret;
                 }
 
-                i_size_write(inode, attr->ia_size);
-                btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
+                mark_inode_dirty(inode);
+        } else {
 
-                trans = btrfs_start_transaction(root, 0);
-                BUG_ON(IS_ERR(trans));
-                btrfs_set_trans_block_group(trans, inode);
-                trans->block_rsv = root->orphan_block_rsv;
-                BUG_ON(!trans->block_rsv);
+                /*
+                 * We're truncating a file that used to have good data down to
+                 * zero. Make sure it gets into the ordered flush list so that
+                 * any new writes get down to disk quickly.
+                 */
+                if (newsize == 0)
+                        BTRFS_I(inode)->ordered_data_close = 1;
 
-                ret = btrfs_update_inode(trans, root, inode);
-                BUG_ON(ret);
-                if (inode->i_nlink > 0) {
-                        ret = btrfs_orphan_del(trans, inode);
-                        BUG_ON(ret);
-                }
-                nr = trans->blocks_used;
-                btrfs_end_transaction(trans, root);
-                btrfs_btree_balance_dirty(root, nr);
-                return 0;
+                /* we don't support swapfiles, so vmtruncate shouldn't fail */
+                truncate_setsize(inode, newsize);
+                ret = btrfs_truncate(inode);
         }
 
-        /*
-         * We're truncating a file that used to have good data down to
-         * zero. Make sure it gets into the ordered flush list so that
-         * any new writes get down to disk quickly.
-         */
-        if (attr->ia_size == 0)
-                BTRFS_I(inode)->ordered_data_close = 1;
-
-        /* we don't support swapfiles, so vmtruncate shouldn't fail */
-        ret = vmtruncate(inode, attr->ia_size);
-        BUG_ON(ret);
-
-        return 0;
+        return ret;
 }
 
 static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
@@ -3707,7 +3730,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
                 return err;
 
         if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
-                err = btrfs_setattr_size(inode, attr);
+                err = btrfs_setsize(inode, attr->ia_size);
                 if (err)
                         return err;
         }
@@ -3730,6 +3753,8 @@ void btrfs_evict_inode(struct inode *inode)
         unsigned long nr;
         int ret;
 
+        trace_btrfs_inode_evict(inode);
+
         truncate_inode_pages(&inode->i_data, 0);
         if (inode->i_nlink && (btrfs_root_refs(&root->root_item) != 0 ||
                                root == root->fs_info->tree_root))
@@ -4072,7 +4097,6 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
                 BTRFS_I(inode)->root = root;
                 memcpy(&BTRFS_I(inode)->location, location, sizeof(*location));
                 btrfs_read_locked_inode(inode);
-
                 inode_tree_add(inode);
                 unlock_new_inode(inode);
                 if (new)
@@ -4147,8 +4171,10 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
         if (!IS_ERR(inode) && root != sub_root) {
                 down_read(&root->fs_info->cleanup_work_sem);
                 if (!(inode->i_sb->s_flags & MS_RDONLY))
-                        btrfs_orphan_cleanup(sub_root);
+                        ret = btrfs_orphan_cleanup(sub_root);
                 up_read(&root->fs_info->cleanup_work_sem);
+                if (ret)
+                        inode = ERR_PTR(ret);
         }
 
         return inode;
@@ -4196,10 +4222,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
         struct btrfs_key found_key;
         struct btrfs_path *path;
         int ret;
-        u32 nritems;
         struct extent_buffer *leaf;
         int slot;
-        int advance;
         unsigned char d_type;
         int over = 0;
         u32 di_cur;
@@ -4242,27 +4266,19 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
         ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
         if (ret < 0)
                 goto err;
-        advance = 0;
 
         while (1) {
                 leaf = path->nodes[0];
-                nritems = btrfs_header_nritems(leaf);
                 slot = path->slots[0];
-                if (advance || slot >= nritems) {
-                        if (slot >= nritems - 1) {
-                                ret = btrfs_next_leaf(root, path);
-                                if (ret)
-                                        break;
-                                leaf = path->nodes[0];
-                                nritems = btrfs_header_nritems(leaf);
-                                slot = path->slots[0];
-                        } else {
-                                slot++;
-                                path->slots[0]++;
-                        }
+                if (slot >= btrfs_header_nritems(leaf)) {
+                        ret = btrfs_next_leaf(root, path);
+                        if (ret < 0)
+                                goto err;
+                        else if (ret > 0)
+                                break;
+                        continue;
                 }
 
-                advance = 1;
                 item = btrfs_item_nr(leaf, slot);
                 btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
@@ -4271,7 +4287,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
                 if (btrfs_key_type(&found_key) != key_type)
                         break;
                 if (found_key.offset < filp->f_pos)
-                        continue;
+                        goto next;
 
                 filp->f_pos = found_key.offset;
 
@@ -4282,6 +4298,9 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
                 while (di_cur < di_total) {
                         struct btrfs_key location;
 
+                        if (verify_dir_item(root, leaf, di))
+                                break;
+
                         name_len = btrfs_dir_name_len(leaf, di);
                         if (name_len <= sizeof(tmp_name)) {
                                 name_ptr = tmp_name;
@@ -4321,6 +4340,8 @@ skip:
                         di_cur += di_len;
                         di = (struct btrfs_dir_item *)((char *)di + di_len);
                 }
+next:
+                path->slots[0]++;
         }
 
         /* Reached end of directory/root. Bump pos past the last item. */
@@ -4513,12 +4534,17 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
         BUG_ON(!path);
 
         inode = new_inode(root->fs_info->sb);
-        if (!inode)
+        if (!inode) {
+                btrfs_free_path(path);
                 return ERR_PTR(-ENOMEM);
+        }
 
         if (dir) {
+                trace_btrfs_inode_request(dir);
+
                 ret = btrfs_set_inode_index(dir, index);
                 if (ret) {
+                        btrfs_free_path(path);
                         iput(inode);
                         return ERR_PTR(ret);
                 }
@@ -4585,12 +4611,16 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
         if ((mode & S_IFREG)) {
                 if (btrfs_test_opt(root, NODATASUM))
                         BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
-                if (btrfs_test_opt(root, NODATACOW))
+                if (btrfs_test_opt(root, NODATACOW) ||
+                    (BTRFS_I(dir)->flags & BTRFS_INODE_NODATACOW))
                         BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW;
         }
 
         insert_inode_hash(inode);
         inode_tree_add(inode);
+
+        trace_btrfs_inode_new(inode);
+
         return inode;
 fail:
         if (dir)
@@ -4809,10 +4839,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 
         /* do not allow sys_link's with other subvols of the same device */
         if (root->objectid != BTRFS_I(inode)->root->objectid)
-                return -EPERM;
+                return -EXDEV;
 
-        btrfs_inc_nlink(inode);
-        inode->i_ctime = CURRENT_TIME;
+        if (inode->i_nlink == ~0U)
+                return -EMLINK;
 
         err = btrfs_set_inode_index(dir, &index);
         if (err)
@@ -4829,6 +4859,9 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
                 goto fail;
         }
 
+        btrfs_inc_nlink(inode);
+        inode->i_ctime = CURRENT_TIME;
+
         btrfs_set_trans_block_group(trans, dir);
         ihold(inode);
 
@@ -5198,7 +5231,7 @@ again:
                         btrfs_mark_buffer_dirty(leaf);
                 }
                 set_extent_uptodate(io_tree, em->start,
-                                    extent_map_end(em) - 1, GFP_NOFS);
+                                    extent_map_end(em) - 1, NULL, GFP_NOFS);
                 goto insert;
         } else {
                 printk(KERN_ERR "btrfs unknown found_type %d\n", found_type);
@@ -5265,6 +5298,9 @@ insert:
         }
         write_unlock(&em_tree->lock);
 out:
+
+        trace_btrfs_get_extent(root, em);
+
         if (path)
                 btrfs_free_path(path);
         if (trans) {
@@ -5402,17 +5438,30 @@ out:
 }
 
 static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
+                                                  struct extent_map *em,
                                                   u64 start, u64 len)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_trans_handle *trans;
-        struct extent_map *em;
         struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
         struct btrfs_key ins;
         u64 alloc_hint;
         int ret;
+        bool insert = false;
 
-        btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
+        /*
+         * Ok if the extent map we looked up is a hole and is for the exact
+         * range we want, there is no reason to allocate a new one, however if
+         * it is not right then we need to free this one and drop the cache for
+         * our range.
+         */
+        if (em->block_start != EXTENT_MAP_HOLE || em->start != start ||
+            em->len != len) {
+                free_extent_map(em);
+                em = NULL;
+                insert = true;
+                btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
+        }
 
         trans = btrfs_join_transaction(root, 0);
         if (IS_ERR(trans))
@@ -5428,10 +5477,12 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
                 goto out;
         }
 
-        em = alloc_extent_map(GFP_NOFS);
         if (!em) {
-                em = ERR_PTR(-ENOMEM);
-                goto out;
+                em = alloc_extent_map(GFP_NOFS);
+                if (!em) {
+                        em = ERR_PTR(-ENOMEM);
+                        goto out;
+                }
         }
 
         em->start = start;
@@ -5441,9 +5492,15 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
         em->block_start = ins.objectid;
         em->block_len = ins.offset;
         em->bdev = root->fs_info->fs_devices->latest_bdev;
+
+        /*
+         * We need to do this because if we're using the original em we searched
+         * for, we could have EXTENT_FLAG_VACANCY set, and we don't want that.
+         */
+        em->flags = 0;
         set_bit(EXTENT_FLAG_PINNED, &em->flags);
 
-        while (1) {
+        while (insert) {
                 write_lock(&em_tree->lock);
                 ret = add_extent_mapping(em_tree, em);
                 write_unlock(&em_tree->lock);
@@ -5661,8 +5718,7 @@ must_cow:
          * it above
          */
         len = bh_result->b_size;
-        free_extent_map(em);
-        em = btrfs_new_extent_direct(inode, start, len);
+        em = btrfs_new_extent_direct(inode, em, start, len);
         if (IS_ERR(em))
                 return PTR_ERR(em);
         len = min(len, em->len - (start - em->start));
@@ -5748,6 +5804,10 @@ static void btrfs_endio_direct_read(struct bio *bio, int err)
 
         kfree(dip->csums);
         kfree(dip);
+
+        /* If we had a csum failure make sure to clear the uptodate flag */
+        if (err)
+                clear_bit(BIO_UPTODATE, &bio->bi_flags);
         dio_end_io(bio, err);
 }
 
@@ -5821,8 +5881,10 @@ again:
         }
 
         add_pending_csums(trans, inode, ordered->file_offset, &ordered->list);
-        btrfs_ordered_update_i_size(inode, 0, ordered);
-        btrfs_update_inode(trans, root, inode);
+        ret = btrfs_ordered_update_i_size(inode, 0, ordered);
+        if (!ret)
+                btrfs_update_inode(trans, root, inode);
+        ret = 0;
 out_unlock:
         unlock_extent_cached(&BTRFS_I(inode)->io_tree, ordered->file_offset,
                              ordered->file_offset + ordered->len - 1,
@@ -5849,6 +5911,10 @@ out_done:
 
         kfree(dip->csums);
         kfree(dip);
+
+        /* If we had an error make sure to clear the uptodate flag */
+        if (err)
+                clear_bit(BIO_UPTODATE, &bio->bi_flags);
         dio_end_io(bio, err);
 }
 
@@ -5904,7 +5970,7 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
 
 static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
                                          int rw, u64 file_offset, int skip_sum,
-                                         u32 *csums)
+                                         u32 *csums, int async_submit)
 {
         int write = rw & REQ_WRITE;
         struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -5915,18 +5981,33 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
         if (ret)
                 goto err;
 
-        if (write && !skip_sum) {
+        if (skip_sum)
+                goto map;
+
+        if (write && async_submit) {
                 ret = btrfs_wq_submit_bio(root->fs_info,
                                    inode, rw, bio, 0, 0,
                                    file_offset,
                                    __btrfs_submit_bio_start_direct_io,
                                    __btrfs_submit_bio_done);
                 goto err;
-        } else if (!skip_sum)
-                btrfs_lookup_bio_sums_dio(root, inode, bio,
+        } else if (write) {
+                /*
+                 * If we aren't doing async submit, calculate the csum of the
+                 * bio now.
+                 */
+                ret = btrfs_csum_one_bio(root, inode, bio, file_offset, 1);
+                if (ret)
+                        goto err;
+        } else if (!skip_sum) {
+                ret = btrfs_lookup_bio_sums_dio(root, inode, bio,
                                           file_offset, csums);
+                if (ret)
+                        goto err;
+        }
 
-        ret = btrfs_map_bio(root, rw, bio, 0, 1);
+map:
+        ret = btrfs_map_bio(root, rw, bio, 0, async_submit);
 err:
         bio_put(bio);
         return ret;
@@ -5948,13 +6029,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
         int nr_pages = 0;
         u32 *csums = dip->csums;
         int ret = 0;
-
-        bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
-        if (!bio)
-                return -ENOMEM;
-        bio->bi_private = dip;
-        bio->bi_end_io = btrfs_end_dio_bio;
-        atomic_inc(&dip->pending_bios);
+        int async_submit = 0;
+        int write = rw & REQ_WRITE;
 
         map_length = orig_bio->bi_size;
         ret = btrfs_map_block(map_tree, READ, start_sector << 9,
@@ -5964,6 +6040,19 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
                 return -EIO;
         }
 
+        if (map_length >= orig_bio->bi_size) {
+                bio = orig_bio;
+                goto submit;
+        }
+
+        async_submit = 1;
+        bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
+        if (!bio)
+                return -ENOMEM;
+        bio->bi_private = dip;
+        bio->bi_end_io = btrfs_end_dio_bio;
+        atomic_inc(&dip->pending_bios);
+
         while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
                 if (unlikely(map_length < submit_len + bvec->bv_len ||
                     bio_add_page(bio, bvec->bv_page, bvec->bv_len,
@@ -5977,14 +6066,15 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
                         atomic_inc(&dip->pending_bios);
                         ret = __btrfs_submit_dio_bio(bio, inode, rw,
                                                      file_offset, skip_sum,
-                                                     csums);
+                                                     csums, async_submit);
                         if (ret) {
                                 bio_put(bio);
                                 atomic_dec(&dip->pending_bios);
                                 goto out_err;
                         }
 
-                        if (!skip_sum)
+                        /* Write's use the ordered csums */
+                        if (!write && !skip_sum)
                                 csums = csums + nr_pages;
                         start_sector += submit_len >> 9;
                         file_offset += submit_len;
@@ -6013,8 +6103,9 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
                 }
         }
 
+submit:
         ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum,
-                                     csums);
+                                     csums, async_submit);
         if (!ret)
                 return 0;
 
@@ -6052,7 +6143,8 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode,
         }
         dip->csums = NULL;
 
-        if (!skip_sum) {
+        /* Write's use the ordered csum stuff, so we don't need dip->csums */
+        if (!write && !skip_sum) {
                 dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS);
                 if (!dip->csums) {
                         kfree(dip);
@@ -6108,6 +6200,7 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io
                         unsigned long nr_segs)
 {
         int seg;
+        int i;
         size_t size;
         unsigned long addr;
         unsigned blocksize_mask = root->sectorsize - 1;
@@ -6122,8 +6215,22 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io
                 addr = (unsigned long)iov[seg].iov_base;
                 size = iov[seg].iov_len;
                 end += size;
-                if ((addr & blocksize_mask) || (size & blocksize_mask)) 
+                if ((addr & blocksize_mask) || (size & blocksize_mask))
                         goto out;
+
+                /* If this is a write we don't need to check anymore */
+                if (rw & WRITE)
+                        continue;
+
+                /*
+                 * Check to make sure we don't have duplicate iov_base's in this
+                 * iovec, if so return EINVAL, otherwise we'll get csum errors
+                 * when reading back.
+                 */
+                for (i = seg + 1; i < nr_segs; i++) {
+                        if (iov[seg].iov_base == iov[i].iov_base)
+                                goto out;
+                }
         }
         retval = 0;
 out:
@@ -6474,28 +6581,42 @@ out:
         return ret;
 }
 
-static void btrfs_truncate(struct inode *inode)
+static int btrfs_truncate(struct inode *inode)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
         int ret;
+        int err = 0;
         struct btrfs_trans_handle *trans;
         unsigned long nr;
         u64 mask = root->sectorsize - 1;
 
-        if (!S_ISREG(inode->i_mode)) {
-                WARN_ON(1);
-                return;
-        }
-
         ret = btrfs_truncate_page(inode->i_mapping, inode->i_size);
         if (ret)
-                return;
+                return ret;
 
         btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
         btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
 
+        trans = btrfs_start_transaction(root, 5);
+        if (IS_ERR(trans))
+                return PTR_ERR(trans);
+
+        btrfs_set_trans_block_group(trans, inode);
+
+        ret = btrfs_orphan_add(trans, inode);
+        if (ret) {
+                btrfs_end_transaction(trans, root);
+                return ret;
+        }
+
+        nr = trans->blocks_used;
+        btrfs_end_transaction(trans, root);
+        btrfs_btree_balance_dirty(root, nr);
+
+        /* Now start a transaction for the truncate */
         trans = btrfs_start_transaction(root, 0);
-        BUG_ON(IS_ERR(trans));
+        if (IS_ERR(trans))
+                return PTR_ERR(trans);
         btrfs_set_trans_block_group(trans, inode);
         trans->block_rsv = root->orphan_block_rsv;
 
@@ -6522,29 +6643,38 @@ static void btrfs_truncate(struct inode *inode)
         while (1) {
                 if (!trans) {
                         trans = btrfs_start_transaction(root, 0);
-                        BUG_ON(IS_ERR(trans));
+                        if (IS_ERR(trans))
+                                return PTR_ERR(trans);
                         btrfs_set_trans_block_group(trans, inode);
                         trans->block_rsv = root->orphan_block_rsv;
                 }
 
                 ret = btrfs_block_rsv_check(trans, root,
                                             root->orphan_block_rsv, 0, 5);
-                if (ret) {
-                        BUG_ON(ret != -EAGAIN);
+                if (ret == -EAGAIN) {
                         ret = btrfs_commit_transaction(trans, root);
-                        BUG_ON(ret);
+                        if (ret)
+                                return ret;
                         trans = NULL;
                         continue;
+                } else if (ret) {
+                        err = ret;
+                        break;
                 }
 
                 ret = btrfs_truncate_inode_items(trans, root, inode,
                                                  inode->i_size,
                                                  BTRFS_EXTENT_DATA_KEY);
-                if (ret != -EAGAIN)
+                if (ret != -EAGAIN) {
+                        err = ret;
                         break;
+                }
 
                 ret = btrfs_update_inode(trans, root, inode);
-                BUG_ON(ret);
+                if (ret) {
+                        err = ret;
+                        break;
+                }
 
                 nr = trans->blocks_used;
                 btrfs_end_transaction(trans, root);
@@ -6554,16 +6684,27 @@ static void btrfs_truncate(struct inode *inode)
 
         if (ret == 0 && inode->i_nlink > 0) {
                 ret = btrfs_orphan_del(trans, inode);
-                BUG_ON(ret);
+                if (ret)
+                        err = ret;
+        } else if (ret && inode->i_nlink > 0) {
+                /*
+                 * Failed to do the truncate, remove us from the in memory
+                 * orphan list.
+                 */
+                ret = btrfs_orphan_del(NULL, inode);
         }
 
         ret = btrfs_update_inode(trans, root, inode);
-        BUG_ON(ret);
+        if (ret && !err)
+                err = ret;
 
         nr = trans->blocks_used;
         ret = btrfs_end_transaction_throttle(trans, root);
-        BUG_ON(ret);
+        if (ret && !err)
+                err = ret;
         btrfs_btree_balance_dirty(root, nr);
+
+        return err;
 }
 
 /*
@@ -6630,9 +6771,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
         ei->index_cnt = (u64)-1;
         ei->last_unlink_trans = 0;
 
-        spin_lock_init(&ei->accounting_lock);
         atomic_set(&ei->outstanding_extents, 0);
-        ei->reserved_extents = 0;
+        atomic_set(&ei->reserved_extents, 0);
 
         ei->ordered_data_close = 0;
         ei->orphan_meta_reserved = 0;
@@ -6668,7 +6808,7 @@ void btrfs_destroy_inode(struct inode *inode)
         WARN_ON(!list_empty(&inode->i_dentry));
         WARN_ON(inode->i_data.nrpages);
         WARN_ON(atomic_read(&BTRFS_I(inode)->outstanding_extents));
-        WARN_ON(BTRFS_I(inode)->reserved_extents);
+        WARN_ON(atomic_read(&BTRFS_I(inode)->reserved_extents));
 
         /*
          * This can happen where we create an inode, but somebody else also
@@ -6760,6 +6900,8 @@ void btrfs_destroy_cachep(void)
                 kmem_cache_destroy(btrfs_transaction_cachep);
         if (btrfs_path_cachep)
                 kmem_cache_destroy(btrfs_path_cachep);
+        if (btrfs_free_space_cachep)
+                kmem_cache_destroy(btrfs_free_space_cachep);
 }
 
 int btrfs_init_cachep(void)
@@ -6788,6 +6930,12 @@ int btrfs_init_cachep(void)
         if (!btrfs_path_cachep)
                 goto fail;
 
+        btrfs_free_space_cachep = kmem_cache_create("btrfs_free_space_cache",
+                        sizeof(struct btrfs_free_space), 0,
+                        SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+        if (!btrfs_free_space_cachep)
+                goto fail;
+
         return 0;
 fail:
         btrfs_destroy_cachep();
@@ -6806,6 +6954,26 @@ static int btrfs_getattr(struct vfsmount *mnt,
         return 0;
 }
 
+/*
+ * If a file is moved, it will inherit the cow and compression flags of the new
+ * directory.
+ */
+static void fixup_inode_flags(struct inode *dir, struct inode *inode)
+{
+        struct btrfs_inode *b_dir = BTRFS_I(dir);
+        struct btrfs_inode *b_inode = BTRFS_I(inode);
+
+        if (b_dir->flags & BTRFS_INODE_NODATACOW)
+                b_inode->flags |= BTRFS_INODE_NODATACOW;
+        else
+                b_inode->flags &= ~BTRFS_INODE_NODATACOW;
+
+        if (b_dir->flags & BTRFS_INODE_COMPRESS)
+                b_inode->flags |= BTRFS_INODE_COMPRESS;
+        else
+                b_inode->flags &= ~BTRFS_INODE_COMPRESS;
+}
+
 static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                            struct inode *new_dir, struct dentry *new_dentry)
 {
@@ -6854,8 +7022,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
          * should cover the worst case number of items we'll modify.
          */
         trans = btrfs_start_transaction(root, 20);
-        if (IS_ERR(trans))
-                return PTR_ERR(trans);
+        if (IS_ERR(trans)) {
+                ret = PTR_ERR(trans);
+                goto out_notrans;
+        }
 
         btrfs_set_trans_block_group(trans, new_dir);
 
@@ -6908,11 +7078,12 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                                         old_dentry->d_name.name,
                                         old_dentry->d_name.len);
         } else {
-                btrfs_inc_nlink(old_dentry->d_inode);
-                ret = btrfs_unlink_inode(trans, root, old_dir,
-                                         old_dentry->d_inode,
-                                         old_dentry->d_name.name,
-                                         old_dentry->d_name.len);
+                ret = __btrfs_unlink_inode(trans, root, old_dir,
+                                        old_dentry->d_inode,
+                                        old_dentry->d_name.name,
+                                        old_dentry->d_name.len);
+                if (!ret)
+                        ret = btrfs_update_inode(trans, root, old_inode);
         }
         BUG_ON(ret);
 
@@ -6939,6 +7110,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                 }
         }
 
+        fixup_inode_flags(new_dir, old_inode);
+
         ret = btrfs_add_link(trans, new_dir, old_inode,
                              new_dentry->d_name.name,
                              new_dentry->d_name.len, 0, index);
@@ -6952,7 +7125,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         }
 out_fail:
         btrfs_end_transaction_throttle(trans, root);
-
+out_notrans:
         if (old_inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
                 up_read(&root->fs_info->subvol_sem);
 
@@ -7340,7 +7513,6 @@ static const struct address_space_operations btrfs_aops = {
         .writepage      = btrfs_writepage,
         .writepages     = btrfs_writepages,
         .readpages      = btrfs_readpages,
-        .sync_page      = block_sync_page,
         .direct_IO      = btrfs_direct_IO,
         .invalidatepage = btrfs_invalidatepage,
         .releasepage    = btrfs_releasepage,
@@ -7356,7 +7528,6 @@ static const struct address_space_operations btrfs_symlink_aops = {
 };
 
 static const struct inode_operations btrfs_file_inode_operations = {
-        .truncate       = btrfs_truncate,
         .getattr        = btrfs_getattr,
         .setattr        = btrfs_setattr,
         .setxattr       = btrfs_setxattr,