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.

7 files changed, 133 insertions, 73 deletions

diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 21eacd7..60d900f 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -238,11 +238,11 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 }
 
 int
-ext4_check_acl(struct inode *inode, int mask, unsigned int flags)
+ext4_check_acl(struct inode *inode, int mask)
 {
 	struct posix_acl *acl;
 
-	if (flags & IPERM_FLAG_RCU) {
+	if (mask & MAY_NOT_BLOCK) {
 		if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
 			return -ECHILD;
 		return -EAGAIN;
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index dec8211..9d843d5 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -54,7 +54,7 @@ static inline int ext4_acl_count(size_t size)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 
 /* acl.c */
-extern int ext4_check_acl(struct inode *, int, unsigned int);
+extern int ext4_check_acl(struct inode *, int);
 extern int ext4_acl_chmod(struct inode *);
 extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1921392..fa44df8 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1758,7 +1758,7 @@ extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 extern void ext4_htree_free_dir_info(struct dir_private_info *p);
 
 /* fsync.c */
-extern int ext4_sync_file(struct file *, int);
+extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
 extern int ext4_flush_completed_IO(struct inode *);
 
 /* hash.c */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 2c09723..ce766f9 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -236,6 +236,27 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
 		}
 		offset += file->f_pos;
 		break;
+	case SEEK_DATA:
+		/*
+		 * In the generic case the entire file is data, so as long as
+		 * offset isn't at the end of the file then the offset is data.
+		 */
+		if (offset >= inode->i_size) {
+			mutex_unlock(&inode->i_mutex);
+			return -ENXIO;
+		}
+		break;
+	case SEEK_HOLE:
+		/*
+		 * There is a virtual hole at the end of the file, so as long as
+		 * offset isn't i_size or larger, return i_size.
+		 */
+		if (offset >= inode->i_size) {
+			mutex_unlock(&inode->i_mutex);
+			return -ENXIO;
+		}
+		offset = inode->i_size;
+		break;
 	}
 
 	if (offset < 0 || offset > maxbytes) {
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index ce66d2f..da3bed3 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -151,6 +151,32 @@ static int ext4_sync_parent(struct inode *inode)
 	return ret;
 }
 
+/**
+ * __sync_file - generic_file_fsync without the locking and filemap_write
+ * @inode:	inode to sync
+ * @datasync:	only sync essential metadata if true
+ *
+ * This is just generic_file_fsync without the locking.  This is needed for
+ * nojournal mode to make sure this inodes data/metadata makes it to disk
+ * properly.  The i_mutex should be held already.
+ */
+static int __sync_inode(struct inode *inode, int datasync)
+{
+	int err;
+	int ret;
+
+	ret = sync_mapping_buffers(inode->i_mapping);
+	if (!(inode->i_state & I_DIRTY))
+		return ret;
+	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+		return ret;
+
+	err = sync_inode_metadata(inode, 1);
+	if (ret == 0)
+		ret = err;
+	return ret;
+}
+
 /*
  * akpm: A new design for ext4_sync_file().
  *
@@ -165,7 +191,7 @@ static int ext4_sync_parent(struct inode *inode)
  * i_mutex lock is held when entering and exiting this function
  */
 
-int ext4_sync_file(struct file *file, int datasync)
+int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -178,15 +204,20 @@ int ext4_sync_file(struct file *file, int datasync)
 
 	trace_ext4_sync_file_enter(file, datasync);
 
+	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (ret)
+		return ret;
+	mutex_lock(&inode->i_mutex);
+
 	if (inode->i_sb->s_flags & MS_RDONLY)
-		return 0;
+		goto out;
 
 	ret = ext4_flush_completed_IO(inode);
 	if (ret < 0)
 		goto out;
 
 	if (!journal) {
-		ret = generic_file_fsync(file, datasync);
+		ret = __sync_inode(inode, datasync);
 		if (!ret && !list_empty(&inode->i_dentry))
 			ret = ext4_sync_parent(inode);
 		goto out;
@@ -220,6 +251,7 @@ int ext4_sync_file(struct file *file, int datasync)
 	if (needs_barrier)
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
  out:
+	mutex_unlock(&inode->i_mutex);
 	trace_ext4_sync_file_exit(inode, ret);
 	return ret;
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e3126c0..678cde8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3501,10 +3501,8 @@ retry:
 				 offset, nr_segs,
 				 ext4_get_block, NULL, NULL, 0);
 	else {
-		ret = blockdev_direct_IO(rw, iocb, inode,
-				 inode->i_sb->s_bdev, iov,
-				 offset, nr_segs,
-				 ext4_get_block, NULL);
+		ret = blockdev_direct_IO(rw, iocb, inode, iov,
+				 offset, nr_segs, ext4_get_block);
 
 		if (unlikely((rw & WRITE) && ret < 0)) {
 			loff_t isize = i_size_read(inode);
@@ -3575,6 +3573,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 			    ssize_t size, void *private, int ret,
 			    bool is_async)
 {
+	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
         ext4_io_end_t *io_end = iocb->private;
 	struct workqueue_struct *wq;
 	unsigned long flags;
@@ -3596,6 +3595,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 out:
 		if (is_async)
 			aio_complete(iocb, ret, 0);
+		inode_dio_done(inode);
 		return;
 	}
 
@@ -3616,6 +3616,9 @@ out:
 	/* queue the work to convert unwritten extents to written */
 	queue_work(wq, &io_end->work);
 	iocb->private = NULL;
+
+	/* XXX: probably should move into the real I/O completion handler */
+	inode_dio_done(inode);
 }
 
 static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
@@ -3748,11 +3751,13 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 			EXT4_I(inode)->cur_aio_dio = iocb->private;
 		}
 
-		ret = blockdev_direct_IO(rw, iocb, inode,
+		ret = __blockdev_direct_IO(rw, iocb, inode,
 					 inode->i_sb->s_bdev, iov,
 					 offset, nr_segs,
 					 ext4_get_block_write,
-					 ext4_end_io_dio);
+					 ext4_end_io_dio,
+					 NULL,
+					 DIO_LOCKING | DIO_SKIP_HOLES);
 		if (iocb->private)
 			EXT4_I(inode)->cur_aio_dio = NULL;
 		/*
@@ -5351,6 +5356,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
+		inode_dio_wait(inode);
+
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
@@ -5843,80 +5850,84 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	loff_t size;
 	unsigned long len;
-	int ret = -EINVAL;
-	void *fsdata;
+	int ret;
 	struct file *file = vma->vm_file;
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct address_space *mapping = inode->i_mapping;
+	handle_t *handle;
+	get_block_t *get_block;
+	int retries = 0;
 
 	/*
-	 * Get i_alloc_sem to stop truncates messing with the inode. We cannot
-	 * get i_mutex because we are already holding mmap_sem.
+	 * This check is racy but catches the common case. We rely on
+	 * __block_page_mkwrite() to do a reliable check.
 	 */
-	down_read(&inode->i_alloc_sem);
-	size = i_size_read(inode);
-	if (page->mapping != mapping || size <= page_offset(page)
-	    || !PageUptodate(page)) {
-		/* page got truncated from under us? */
-		goto out_unlock;
+	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	/* Delalloc case is easy... */
+	if (test_opt(inode->i_sb, DELALLOC) &&
+	    !ext4_should_journal_data(inode) &&
+	    !ext4_nonda_switch(inode->i_sb)) {
+		do {
+			ret = __block_page_mkwrite(vma, vmf,
+						   ext4_da_get_block_prep);
+		} while (ret == -ENOSPC &&
+		       ext4_should_retry_alloc(inode->i_sb, &retries));
+		goto out_ret;
 	}
-	ret = 0;
 
 	lock_page(page);
-	wait_on_page_writeback(page);
-	if (PageMappedToDisk(page)) {
-		up_read(&inode->i_alloc_sem);
-		return VM_FAULT_LOCKED;
+	size = i_size_read(inode);
+	/* Page got truncated from under us? */
+	if (page->mapping != mapping || page_offset(page) > size) {
+		unlock_page(page);
+		ret = VM_FAULT_NOPAGE;
+		goto out;
 	}
 
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
 	else
 		len = PAGE_CACHE_SIZE;
-
 	/*
-	 * return if we have all the buffers mapped. This avoid
-	 * the need to call write_begin/write_end which does a
-	 * journal_start/journal_stop which can block and take
-	 * long time
+	 * Return if we have all the buffers mapped. This avoids the need to do
+	 * journal_start/journal_stop which can block and take a long time
 	 */
 	if (page_has_buffers(page)) {
 		if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
 					ext4_bh_unmapped)) {
-			up_read(&inode->i_alloc_sem);
-			return VM_FAULT_LOCKED;
+			/* Wait so that we don't change page under IO */
+			wait_on_page_writeback(page);
+			ret = VM_FAULT_LOCKED;
+			goto out;
 		}
 	}
 	unlock_page(page);
-	/*
-	 * OK, we need to fill the hole... Do write_begin write_end
-	 * to do block allocation/reservation.We are not holding
-	 * inode.i__mutex here. That allow * parallel write_begin,
-	 * write_end call. lock_page prevent this from happening
-	 * on the same page though
-	 */
-	ret = mapping->a_ops->write_begin(file, mapping, page_offset(page),
-			len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
-	if (ret < 0)
-		goto out_unlock;
-	ret = mapping->a_ops->write_end(file, mapping, page_offset(page),
-			len, len, page, fsdata);
-	if (ret < 0)
-		goto out_unlock;
-	ret = 0;
-
-	/*
-	 * write_begin/end might have created a dirty page and someone
-	 * could wander in and start the IO.  Make sure that hasn't
-	 * happened.
-	 */
-	lock_page(page);
-	wait_on_page_writeback(page);
-	up_read(&inode->i_alloc_sem);
-	return VM_FAULT_LOCKED;
-out_unlock:
-	if (ret)
+	/* OK, we need to fill the hole... */
+	if (ext4_should_dioread_nolock(inode))
+		get_block = ext4_get_block_write;
+	else
+		get_block = ext4_get_block;
+retry_alloc:
+	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+	if (IS_ERR(handle)) {
 		ret = VM_FAULT_SIGBUS;
-	up_read(&inode->i_alloc_sem);
+		goto out;
+	}
+	ret = __block_page_mkwrite(vma, vmf, get_block);
+	if (!ret && ext4_should_journal_data(inode)) {
+		if (walk_page_buffers(handle, page_buffers(page), 0,
+			  PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
+			unlock_page(page);
+			ret = VM_FAULT_SIGBUS;
+			goto out;
+		}
+		ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+	}
+	ext4_journal_stop(handle);
+	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry_alloc;
+out_ret:
+	ret = block_page_mkwrite_return(ret);
+out:
 	return ret;
 }
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b754b77..707d605 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1037,15 +1037,11 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru
 			return ERR_PTR(-EIO);
 		}
 		inode = ext4_iget(dir->i_sb, ino);
-		if (IS_ERR(inode)) {
-			if (PTR_ERR(inode) == -ESTALE) {
-				EXT4_ERROR_INODE(dir,
-						 "deleted inode referenced: %u",
-						 ino);
-				return ERR_PTR(-EIO);
-			} else {
-				return ERR_CAST(inode);
-			}
+		if (inode == ERR_PTR(-ESTALE)) {
+			EXT4_ERROR_INODE(dir,
+					 "deleted inode referenced: %u",
+					 ino);
+			return ERR_PTR(-EIO);
 		}
 	}
 	return d_splice_alias(inode, dentry);