Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (107 commits)
  vfs: use ERR_CAST for err-ptr tossing in lookup_instantiate_filp
  isofs: Remove global fs lock
  jffs2: fix IN_DELETE_SELF on overwriting rename() killing a directory
  fix IN_DELETE_SELF on overwriting rename() on ramfs et.al.
  mm/truncate.c: fix build for CONFIG_BLOCK not enabled
  fs:update the NOTE of the file_operations structure
  Remove dead code in dget_parent()
  AFS: Fix silly characters in a comment
  switch d_add_ci() to d_splice_alias() in "found negative" case as well
  simplify gfs2_lookup()
  jfs_lookup(): don't bother with . or ..
  get rid of useless dget_parent() in btrfs rename() and link()
  get rid of useless dget_parent() in fs/btrfs/ioctl.c
  fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers
  drivers: fix up various ->llseek() implementations
  fs: handle SEEK_HOLE/SEEK_DATA properly in all fs's that define their own llseek
  Ext4: handle SEEK_HOLE/SEEK_DATA generically
  Btrfs: implement our own ->llseek
  fs: add SEEK_HOLE and SEEK_DATA flags
  reiserfs: make reiserfs default to barrier=flush
  ...

Fix up trivial conflicts in fs/xfs/linux-2.6/xfs_super.c due to the new
shrinker callout for the inode cache, that clashed with the xfs code to
start the periodic workers later.

6 files changed, 189 insertions, 50 deletions

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index f66fc9959733..9f62ab2a7282 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -195,14 +195,13 @@ out:
         return ret;
 }
 
-int btrfs_check_acl(struct inode *inode, int mask, unsigned int flags)
+int btrfs_check_acl(struct inode *inode, int mask)
 {
         int error = -EAGAIN;
 
-        if (flags & IPERM_FLAG_RCU) {
+        if (mask & MAY_NOT_BLOCK) {
                 if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
                         error = -ECHILD;
-
         } else {
                 struct posix_acl *acl;
                 acl = btrfs_get_acl(inode, ACL_TYPE_ACCESS);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 3b859a3e6a0e..82be74efbb26 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1219,7 +1219,7 @@ struct btrfs_root {
          * right now this just gets used so that a root has its own devid
          * for stat.  It may be used for more later
          */
-        struct super_block anon_super;
+        dev_t anon_dev;
 };
 
 struct btrfs_ioctl_defrag_range_args {
@@ -2510,6 +2510,9 @@ int btrfs_csum_truncate(struct btrfs_trans_handle *trans,
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
                              struct list_head *list, int search_commit);
 /* inode.c */
+struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
+                                           size_t pg_offset, u64 start, u64 len,
+                                           int create);
 
 /* RHEL and EL kernels have a patch that renames PG_checked to FsMisc */
 #if defined(ClearPageFsMisc) && !defined(ClearPageChecked)
@@ -2602,7 +2605,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
                            struct inode *inode);
 int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
-int btrfs_sync_file(struct file *file, int datasync);
+int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
 int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
                             int skip_pinned);
 extern const struct file_operations btrfs_file_operations;
@@ -2642,7 +2645,7 @@ do {								\
 
 /* acl.c */
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
-int btrfs_check_acl(struct inode *inode, int mask, unsigned int flags);
+int btrfs_check_acl(struct inode *inode, int mask);
 #else
 #define btrfs_check_acl NULL
 #endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1ac8db5dc0a3..b231ae13b269 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1077,12 +1077,7 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
         init_completion(&root->kobj_unregister);
         root->defrag_running = 0;
         root->root_key.objectid = objectid;
-        root->anon_super.s_root = NULL;
-        root->anon_super.s_dev = 0;
-        INIT_LIST_HEAD(&root->anon_super.s_list);
-        INIT_LIST_HEAD(&root->anon_super.s_instances);
-        init_rwsem(&root->anon_super.s_umount);
-
+        root->anon_dev = 0;
         return 0;
 }
 
@@ -1311,7 +1306,7 @@ again:
         spin_lock_init(&root->cache_lock);
         init_waitqueue_head(&root->cache_wait);
 
-        ret = set_anon_super(&root->anon_super, NULL);
+        ret = get_anon_bdev(&root->anon_dev);
         if (ret)
                 goto fail;
 
@@ -2393,10 +2388,8 @@ static void free_fs_root(struct btrfs_root *root)
 {
         iput(root->cache_inode);
         WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
-        if (root->anon_super.s_dev) {
-                down_write(&root->anon_super.s_umount);
-                kill_anon_super(&root->anon_super);
-        }
+        if (root->anon_dev)
+                free_anon_bdev(root->anon_dev);
         free_extent_buffer(root->node);
         free_extent_buffer(root->commit_root);
         kfree(root->free_ino_ctl);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index fa4ef18b66b1..59cbdb120ad0 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1452,7 +1452,7 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
  * important optimization for directories because holding the mutex prevents
  * new operations on the dir while we write to disk.
  */
-int btrfs_sync_file(struct file *file, int datasync)
+int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
         struct dentry *dentry = file->f_path.dentry;
         struct inode *inode = dentry->d_inode;
@@ -1462,9 +1462,13 @@ int btrfs_sync_file(struct file *file, int datasync)
 
         trace_btrfs_sync_file(file, datasync);
 
+        ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+        if (ret)
+                return ret;
+        mutex_lock(&inode->i_mutex);
+
         /* we wait first, since the writeback may change the inode */
         root->log_batch++;
-        /* the VFS called filemap_fdatawrite for us */
         btrfs_wait_ordered_range(inode, 0, (u64)-1);
         root->log_batch++;
 
@@ -1472,8 +1476,10 @@ int btrfs_sync_file(struct file *file, int datasync)
          * check the transaction that last modified this inode
          * and see if its already been committed
          */
-        if (!BTRFS_I(inode)->last_trans)
+        if (!BTRFS_I(inode)->last_trans) {
+                mutex_unlock(&inode->i_mutex);
                 goto out;
+        }
 
         /*
          * if the last transaction that changed this file was before
@@ -1484,6 +1490,7 @@ int btrfs_sync_file(struct file *file, int datasync)
         if (BTRFS_I(inode)->last_trans <=
             root->fs_info->last_trans_committed) {
                 BTRFS_I(inode)->last_trans = 0;
+                mutex_unlock(&inode->i_mutex);
                 goto out;
         }
 
@@ -1496,12 +1503,15 @@ int btrfs_sync_file(struct file *file, int datasync)
         trans = btrfs_start_transaction(root, 0);
         if (IS_ERR(trans)) {
                 ret = PTR_ERR(trans);
+                mutex_unlock(&inode->i_mutex);
                 goto out;
         }
 
         ret = btrfs_log_dentry_safe(trans, root, dentry);
-        if (ret < 0)
+        if (ret < 0) {
+                mutex_unlock(&inode->i_mutex);
                 goto out;
+        }
 
         /* we've logged all the items and now have a consistent
          * version of the file in the log.  It is possible that
@@ -1513,7 +1523,7 @@ int btrfs_sync_file(struct file *file, int datasync)
          * file again, but that will end up using the synchronization
          * inside btrfs_sync_log to keep things safe.
          */
-        mutex_unlock(&dentry->d_inode->i_mutex);
+        mutex_unlock(&inode->i_mutex);
 
         if (ret != BTRFS_NO_LOG_SYNC) {
                 if (ret > 0) {
@@ -1528,7 +1538,6 @@ int btrfs_sync_file(struct file *file, int datasync)
         } else {
                 ret = btrfs_end_transaction(trans, root);
         }
-        mutex_lock(&dentry->d_inode->i_mutex);
 out:
         return ret > 0 ? -EIO : ret;
 }
@@ -1664,8 +1673,154 @@ out:
         return ret;
 }
 
+static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
+{
+        struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct extent_map *em;
+        struct extent_state *cached_state = NULL;
+        u64 lockstart = *offset;
+        u64 lockend = i_size_read(inode);
+        u64 start = *offset;
+        u64 orig_start = *offset;
+        u64 len = i_size_read(inode);
+        u64 last_end = 0;
+        int ret = 0;
+
+        lockend = max_t(u64, root->sectorsize, lockend);
+        if (lockend <= lockstart)
+                lockend = lockstart + root->sectorsize;
+
+        len = lockend - lockstart + 1;
+
+        len = max_t(u64, len, root->sectorsize);
+        if (inode->i_size == 0)
+                return -ENXIO;
+
+        lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0,
+                         &cached_state, GFP_NOFS);
+
+        /*
+         * Delalloc is such a pain.  If we have a hole and we have pending
+         * delalloc for a portion of the hole we will get back a hole that
+         * exists for the entire range since it hasn't been actually written
+         * yet.  So to take care of this case we need to look for an extent just
+         * before the position we want in case there is outstanding delalloc
+         * going on here.
+         */
+        if (origin == SEEK_HOLE && start != 0) {
+                if (start <= root->sectorsize)
+                        em = btrfs_get_extent_fiemap(inode, NULL, 0, 0,
+                                                     root->sectorsize, 0);
+                else
+                        em = btrfs_get_extent_fiemap(inode, NULL, 0,
+                                                     start - root->sectorsize,
+                                                     root->sectorsize, 0);
+                if (IS_ERR(em)) {
+                        ret = -ENXIO;
+                        goto out;
+                }
+                last_end = em->start + em->len;
+                if (em->block_start == EXTENT_MAP_DELALLOC)
+                        last_end = min_t(u64, last_end, inode->i_size);
+                free_extent_map(em);
+        }
+
+        while (1) {
+                em = btrfs_get_extent_fiemap(inode, NULL, 0, start, len, 0);
+                if (IS_ERR(em)) {
+                        ret = -ENXIO;
+                        break;
+                }
+
+                if (em->block_start == EXTENT_MAP_HOLE) {
+                        if (test_bit(EXTENT_FLAG_VACANCY, &em->flags)) {
+                                if (last_end <= orig_start) {
+                                        free_extent_map(em);
+                                        ret = -ENXIO;
+                                        break;
+                                }
+                        }
+
+                        if (origin == SEEK_HOLE) {
+                                *offset = start;
+                                free_extent_map(em);
+                                break;
+                        }
+                } else {
+                        if (origin == SEEK_DATA) {
+                                if (em->block_start == EXTENT_MAP_DELALLOC) {
+                                        if (start >= inode->i_size) {
+                                                free_extent_map(em);
+                                                ret = -ENXIO;
+                                                break;
+                                        }
+                                }
+
+                                *offset = start;
+                                free_extent_map(em);
+                                break;
+                        }
+                }
+
+                start = em->start + em->len;
+                last_end = em->start + em->len;
+
+                if (em->block_start == EXTENT_MAP_DELALLOC)
+                        last_end = min_t(u64, last_end, inode->i_size);
+
+                if (test_bit(EXTENT_FLAG_VACANCY, &em->flags)) {
+                        free_extent_map(em);
+                        ret = -ENXIO;
+                        break;
+                }
+                free_extent_map(em);
+                cond_resched();
+        }
+        if (!ret)
+                *offset = min(*offset, inode->i_size);
+out:
+        unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
+                             &cached_state, GFP_NOFS);
+        return ret;
+}
+
+static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
+{
+        struct inode *inode = file->f_mapping->host;
+        int ret;
+
+        mutex_lock(&inode->i_mutex);
+        switch (origin) {
+        case SEEK_END:
+        case SEEK_CUR:
+                offset = generic_file_llseek_unlocked(file, offset, origin);
+                goto out;
+        case SEEK_DATA:
+        case SEEK_HOLE:
+                ret = find_desired_extent(inode, &offset, origin);
+                if (ret) {
+                        mutex_unlock(&inode->i_mutex);
+                        return ret;
+                }
+        }
+
+        if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
+                return -EINVAL;
+        if (offset > inode->i_sb->s_maxbytes)
+                return -EINVAL;
+
+        /* Special lock needed here? */
+        if (offset != file->f_pos) {
+                file->f_pos = offset;
+                file->f_version = 0;
+        }
+out:
+        mutex_unlock(&inode->i_mutex);
+        return offset;
+}
+
 const struct file_operations btrfs_file_operations = {
-        .llseek         = generic_file_llseek,
+        .llseek         = btrfs_file_llseek,
         .read           = do_sync_read,
         .write          = do_sync_write,
         .aio_read       = generic_file_aio_read,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3601f0aebddf..2548a04a0230 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4079,13 +4079,7 @@ static int btrfs_dentry_delete(const struct dentry *dentry)
 static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
                                    struct nameidata *nd)
 {
-        struct inode *inode;
-
-        inode = btrfs_lookup_dentry(dir, dentry);
-        if (IS_ERR(inode))
-                return ERR_CAST(inode);
-
-        return d_splice_alias(inode, dentry);
+        return d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
 }
 
 unsigned char btrfs_filetype_table[] = {
@@ -4772,11 +4766,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
         if (err) {
                 drop_inode = 1;
         } else {
-                struct dentry *parent = dget_parent(dentry);
+                struct dentry *parent = dentry->d_parent;
                 err = btrfs_update_inode(trans, root, inode);
                 BUG_ON(err);
                 btrfs_log_new_name(trans, inode, NULL, parent);
-                dput(parent);
         }
 
         nr = trans->blocks_used;
@@ -6900,7 +6893,7 @@ static int btrfs_getattr(struct vfsmount *mnt,
 {
         struct inode *inode = dentry->d_inode;
         generic_fillattr(inode, stat);
-        stat->dev = BTRFS_I(inode)->root->anon_super.s_dev;
+        stat->dev = BTRFS_I(inode)->root->anon_dev;
         stat->blksize = PAGE_CACHE_SIZE;
         stat->blocks = (inode_get_bytes(inode) +
                         BTRFS_I(inode)->delalloc_bytes) >> 9;
@@ -7068,9 +7061,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         BUG_ON(ret);
 
         if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
-                struct dentry *parent = dget_parent(new_dentry);
+                struct dentry *parent = new_dentry->d_parent;
                 btrfs_log_new_name(trans, old_inode, old_dir, parent);
-                dput(parent);
                 btrfs_end_log_trans(root);
         }
 out_fail:
@@ -7331,7 +7323,7 @@ static int btrfs_set_page_dirty(struct page *page)
         return __set_page_dirty_nobuffers(page);
 }
 
-static int btrfs_permission(struct inode *inode, int mask, unsigned int flags)
+static int btrfs_permission(struct inode *inode, int mask)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
 
@@ -7339,7 +7331,7 @@ static int btrfs_permission(struct inode *inode, int mask, unsigned int flags)
                 return -EROFS;
         if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
                 return -EACCES;
-        return generic_permission(inode, mask, flags, btrfs_check_acl);
+        return generic_permission(inode, mask);
 }
 
 static const struct inode_operations btrfs_dir_inode_operations = {
@@ -7359,10 +7351,12 @@ static const struct inode_operations btrfs_dir_inode_operations = {
         .listxattr      = btrfs_listxattr,
         .removexattr    = btrfs_removexattr,
         .permission     = btrfs_permission,
+        .check_acl      = btrfs_check_acl,
 };
 static const struct inode_operations btrfs_dir_ro_inode_operations = {
         .lookup         = btrfs_lookup,
         .permission     = btrfs_permission,
+        .check_acl      = btrfs_check_acl,
 };
 
 static const struct file_operations btrfs_dir_file_operations = {
@@ -7431,6 +7425,7 @@ static const struct inode_operations btrfs_file_inode_operations = {
         .removexattr    = btrfs_removexattr,
         .permission     = btrfs_permission,
         .fiemap         = btrfs_fiemap,
+        .check_acl      = btrfs_check_acl,
 };
 static const struct inode_operations btrfs_special_inode_operations = {
         .getattr        = btrfs_getattr,
@@ -7440,6 +7435,7 @@ static const struct inode_operations btrfs_special_inode_operations = {
         .getxattr       = btrfs_getxattr,
         .listxattr      = btrfs_listxattr,
         .removexattr    = btrfs_removexattr,
+        .check_acl      = btrfs_check_acl,
 };
 static const struct inode_operations btrfs_symlink_inode_operations = {
         .readlink       = generic_readlink,
@@ -7451,6 +7447,7 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
         .getxattr       = btrfs_getxattr,
         .listxattr      = btrfs_listxattr,
         .removexattr    = btrfs_removexattr,
+        .check_acl      = btrfs_check_acl,
 };
 
 const struct dentry_operations btrfs_dentry_operations = {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a3c4751e07db..622543309eb2 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -323,7 +323,7 @@ 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 dentry *parent = dget_parent(dentry);
+        struct dentry *parent = dentry->d_parent;
         struct inode *dir;
         int ret;
         int err;
@@ -332,10 +332,8 @@ static noinline int create_subvol(struct btrfs_root *root,
         u64 index = 0;
 
         ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
-        if (ret) {
-                dput(parent);
+        if (ret)
                 return ret;
-        }
 
         dir = parent->d_inode;
 
@@ -346,10 +344,8 @@ static noinline int create_subvol(struct btrfs_root *root,
          * 2 - dir items
          */
         trans = btrfs_start_transaction(root, 6);
-        if (IS_ERR(trans)) {
-                dput(parent);
+        if (IS_ERR(trans))
                 return PTR_ERR(trans);
-        }
 
         leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
                                       0, objectid, NULL, 0, 0, 0);
@@ -439,7 +435,6 @@ static noinline int create_subvol(struct btrfs_root *root,
 
         d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
 fail:
-        dput(parent);
         if (async_transid) {
                 *async_transid = trans->transid;
                 err = btrfs_commit_transaction_async(trans, root, 1);
@@ -456,7 +451,6 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
                            bool readonly)
 {
         struct inode *inode;
-        struct dentry *parent;
         struct btrfs_pending_snapshot *pending_snapshot;
         struct btrfs_trans_handle *trans;
         int ret;
@@ -504,9 +498,7 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
         if (ret)
                 goto fail;
 
-        parent = dget_parent(dentry);
-        inode = btrfs_lookup_dentry(parent->d_inode, dentry);
-        dput(parent);
+        inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
         if (IS_ERR(inode)) {
                 ret = PTR_ERR(inode);
                 goto fail;