Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull ext3 & udf fixes from Jan Kara:
 "Shortlog pretty much says it all.

  The interesting bits are UDF support for direct IO and ext3 fix for a
  long standing oops in data=journal mode."

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  jbd: Fix assertion failure in commit code due to lacking transaction credits
  UDF: Add support for O_DIRECT
  ext3: Replace 0 with NULL for pointer in super.c file
  udf: add writepages support for udf
  ext3: don't clear orphan list on ro mount with errors
  reiserfs: Make reiserfs_xattr_handlers static

6 files changed, 136 insertions, 51 deletions

diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index bd29894c8fbc..17ae5c83d234 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -980,7 +980,7 @@ static int parse_options (char *options, struct super_block *sb,
 		 * Initialize args struct so we know whether arg was
 		 * found; some options take optional arguments.
 		 */
-		args[0].to = args[0].from = 0;
+		args[0].to = args[0].from = NULL;
 		token = match_token(p, tokens, args);
 		switch (token) {
 		case Opt_bsd_df:
@@ -1484,10 +1484,12 @@ static void ext3_orphan_cleanup (struct super_block * sb,
 	}
 
 	if (EXT3_SB(sb)->s_mount_state & EXT3_ERROR_FS) {
-		if (es->s_last_orphan)
+		/* don't clear list on RO mount w/ errors */
+		if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
 			jbd_debug(1, "Errors on filesystem, "
 				  "clearing orphan list.\n");
-		es->s_last_orphan = 0;
+			es->s_last_orphan = 0;
+		}
 		jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
 		return;
 	}
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 52c15c776029..86b39b167c23 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -86,7 +86,12 @@ nope:
 static void release_data_buffer(struct buffer_head *bh)
 {
 	if (buffer_freed(bh)) {
+		WARN_ON_ONCE(buffer_dirty(bh));
 		clear_buffer_freed(bh);
+		clear_buffer_mapped(bh);
+		clear_buffer_new(bh);
+		clear_buffer_req(bh);
+		bh->b_bdev = NULL;
 		release_buffer_page(bh);
 	} else
 		put_bh(bh);
@@ -866,17 +871,35 @@ restart_loop:
 		 * there's no point in keeping a checkpoint record for
 		 * it. */
 
-		/* A buffer which has been freed while still being
-		 * journaled by a previous transaction may end up still
-		 * being dirty here, but we want to avoid writing back
-		 * that buffer in the future after the "add to orphan"
-		 * operation been committed,  That's not only a performance
-		 * gain, it also stops aliasing problems if the buffer is
-		 * left behind for writeback and gets reallocated for another
-		 * use in a different page. */
-		if (buffer_freed(bh) && !jh->b_next_transaction) {
-			clear_buffer_freed(bh);
-			clear_buffer_jbddirty(bh);
+		/*
+		 * A buffer which has been freed while still being journaled by
+		 * a previous transaction.
+		 */
+		if (buffer_freed(bh)) {
+			/*
+			 * If the running transaction is the one containing
+			 * "add to orphan" operation (b_next_transaction !=
+			 * NULL), we have to wait for that transaction to
+			 * commit before we can really get rid of the buffer.
+			 * So just clear b_modified to not confuse transaction
+			 * credit accounting and refile the buffer to
+			 * BJ_Forget of the running transaction. If the just
+			 * committed transaction contains "add to orphan"
+			 * operation, we can completely invalidate the buffer
+			 * now. We are rather throughout in that since the
+			 * buffer may be still accessible when blocksize <
+			 * pagesize and it is attached to the last partial
+			 * page.
+			 */
+			jh->b_modified = 0;
+			if (!jh->b_next_transaction) {
+				clear_buffer_freed(bh);
+				clear_buffer_jbddirty(bh);
+				clear_buffer_mapped(bh);
+				clear_buffer_new(bh);
+				clear_buffer_req(bh);
+				bh->b_bdev = NULL;
+			}
 		}
 
 		if (buffer_jbddirty(bh)) {
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index febc10db5ced..78b7f84241d4 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -1843,15 +1843,16 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
  * We're outside-transaction here.  Either or both of j_running_transaction
  * and j_committing_transaction may be NULL.
  */
-static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
+static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
+				int partial_page)
 {
 	transaction_t *transaction;
 	struct journal_head *jh;
 	int may_free = 1;
-	int ret;
 
 	BUFFER_TRACE(bh, "entry");
 
+retry:
 	/*
 	 * It is safe to proceed here without the j_list_lock because the
 	 * buffers cannot be stolen by try_to_free_buffers as long as we are
@@ -1879,10 +1880,18 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 	 * clear the buffer dirty bit at latest at the moment when the
 	 * transaction marking the buffer as freed in the filesystem
 	 * structures is committed because from that moment on the
-	 * buffer can be reallocated and used by a different page.
+	 * block can be reallocated and used by a different page.
 	 * Since the block hasn't been freed yet but the inode has
 	 * already been added to orphan list, it is safe for us to add
 	 * the buffer to BJ_Forget list of the newest transaction.
+	 *
+	 * Also we have to clear buffer_mapped flag of a truncated buffer
+	 * because the buffer_head may be attached to the page straddling
+	 * i_size (can happen only when blocksize < pagesize) and thus the
+	 * buffer_head can be reused when the file is extended again. So we end
+	 * up keeping around invalidated buffers attached to transactions'
+	 * BJ_Forget list just to stop checkpointing code from cleaning up
+	 * the transaction this buffer was modified in.
 	 */
 	transaction = jh->b_transaction;
 	if (transaction == NULL) {
@@ -1909,13 +1918,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 			 * committed, the buffer won't be needed any
 			 * longer. */
 			JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget");
-			ret = __dispose_buffer(jh,
+			may_free = __dispose_buffer(jh,
 					journal->j_running_transaction);
-			journal_put_journal_head(jh);
-			spin_unlock(&journal->j_list_lock);
-			jbd_unlock_bh_state(bh);
-			spin_unlock(&journal->j_state_lock);
-			return ret;
+			goto zap_buffer;
 		} else {
 			/* There is no currently-running transaction. So the
 			 * orphan record which we wrote for this file must have
@@ -1923,13 +1928,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 			 * the committing transaction, if it exists. */
 			if (journal->j_committing_transaction) {
 				JBUFFER_TRACE(jh, "give to committing trans");
-				ret = __dispose_buffer(jh,
+				may_free = __dispose_buffer(jh,
 					journal->j_committing_transaction);
-				journal_put_journal_head(jh);
-				spin_unlock(&journal->j_list_lock);
-				jbd_unlock_bh_state(bh);
-				spin_unlock(&journal->j_state_lock);
-				return ret;
+				goto zap_buffer;
 			} else {
 				/* The orphan record's transaction has
 				 * committed.  We can cleanse this buffer */
@@ -1950,10 +1951,24 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 		}
 		/*
 		 * The buffer is committing, we simply cannot touch
-		 * it. So we just set j_next_transaction to the
-		 * running transaction (if there is one) and mark
-		 * buffer as freed so that commit code knows it should
-		 * clear dirty bits when it is done with the buffer.
+		 * it. If the page is straddling i_size we have to wait
+		 * for commit and try again.
+		 */
+		if (partial_page) {
+			tid_t tid = journal->j_committing_transaction->t_tid;
+
+			journal_put_journal_head(jh);
+			spin_unlock(&journal->j_list_lock);
+			jbd_unlock_bh_state(bh);
+			spin_unlock(&journal->j_state_lock);
+			log_wait_commit(journal, tid);
+			goto retry;
+		}
+		/*
+		 * OK, buffer won't be reachable after truncate. We just set
+		 * j_next_transaction to the running transaction (if there is
+		 * one) and mark buffer as freed so that commit code knows it
+		 * should clear dirty bits when it is done with the buffer.
 		 */
 		set_buffer_freed(bh);
 		if (journal->j_running_transaction && buffer_jbddirty(bh))
@@ -1976,6 +1991,14 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 	}
 
 zap_buffer:
+	/*
+	 * This is tricky. Although the buffer is truncated, it may be reused
+	 * if blocksize < pagesize and it is attached to the page straddling
+	 * EOF. Since the buffer might have been added to BJ_Forget list of the
+	 * running transaction, journal_get_write_access() won't clear
+	 * b_modified and credit accounting gets confused. So clear b_modified
+	 * here. */
+	jh->b_modified = 0;
 	journal_put_journal_head(jh);
 zap_buffer_no_jh:
 	spin_unlock(&journal->j_list_lock);
@@ -2024,7 +2047,8 @@ void journal_invalidatepage(journal_t *journal,
 		if (offset <= curr_off) {
 			/* This block is wholly outside the truncation point */
 			lock_buffer(bh);
-			may_free &= journal_unmap_buffer(journal, bh);
+			may_free &= journal_unmap_buffer(journal, bh,
+							 offset > 0);
 			unlock_buffer(bh);
 		}
 		curr_off = next_off;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index d319963aeb11..c196369fe408 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -896,7 +896,7 @@ static int create_privroot(struct dentry *dentry) { return 0; }
 #endif
 
 /* Actual operations that are exported to VFS-land */
-const struct xattr_handler *reiserfs_xattr_handlers[] = {
+static const struct xattr_handler *reiserfs_xattr_handlers[] = {
 #ifdef CONFIG_REISERFS_FS_XATTR
 	&reiserfs_xattr_user_handler,
 	&reiserfs_xattr_trusted_handler,
diff --git a/fs/udf/file.c b/fs/udf/file.c
index d1c6093fd3d3..77b5953eaac8 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -118,11 +118,20 @@ static int udf_adinicb_write_end(struct file *file,
 	return simple_write_end(file, mapping, pos, len, copied, page, fsdata);
 }
 
+static ssize_t udf_adinicb_direct_IO(int rw, struct kiocb *iocb,
+				     const struct iovec *iov,
+				     loff_t offset, unsigned long nr_segs)
+{
+	/* Fallback to buffered I/O. */
+	return 0;
+}
+
 const struct address_space_operations udf_adinicb_aops = {
 	.readpage	= udf_adinicb_readpage,
 	.writepage	= udf_adinicb_writepage,
 	.write_begin	= udf_adinicb_write_begin,
 	.write_end	= udf_adinicb_write_end,
+	.direct_IO	= udf_adinicb_direct_IO,
 };
 
 static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 287ef9f587b7..df88b957ccf0 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -95,11 +95,33 @@ void udf_evict_inode(struct inode *inode)
 	}
 }
 
+static void udf_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+	struct udf_inode_info *iinfo = UDF_I(inode);
+	loff_t isize = inode->i_size;
+
+	if (to > isize) {
+		truncate_pagecache(inode, to, isize);
+		if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
+			down_write(&iinfo->i_data_sem);
+			udf_truncate_extents(inode);
+			up_write(&iinfo->i_data_sem);
+		}
+	}
+}
+
 static int udf_writepage(struct page *page, struct writeback_control *wbc)
 {
 	return block_write_full_page(page, udf_get_block, wbc);
 }
 
+static int udf_writepages(struct address_space *mapping,
+			struct writeback_control *wbc)
+{
+	return mpage_writepages(mapping, wbc, udf_get_block);
+}
+
 static int udf_readpage(struct file *file, struct page *page)
 {
 	return mpage_readpage(page, udf_get_block);
@@ -118,21 +140,24 @@ static int udf_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	ret = block_write_begin(mapping, pos, len, flags, pagep, udf_get_block);
-	if (unlikely(ret)) {
-		struct inode *inode = mapping->host;
-		struct udf_inode_info *iinfo = UDF_I(inode);
-		loff_t isize = inode->i_size;
-
-		if (pos + len > isize) {
-			truncate_pagecache(inode, pos + len, isize);
-			if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
-				down_write(&iinfo->i_data_sem);
-				udf_truncate_extents(inode);
-				up_write(&iinfo->i_data_sem);
-			}
-		}
-	}
+	if (unlikely(ret))
+		udf_write_failed(mapping, pos + len);
+	return ret;
+}
 
+static ssize_t udf_direct_IO(int rw, struct kiocb *iocb,
+			     const struct iovec *iov,
+			     loff_t offset, unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	ssize_t ret;
+
+	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+				  udf_get_block);
+	if (unlikely(ret < 0 && (rw & WRITE)))
+		udf_write_failed(mapping, offset + iov_length(iov, nr_segs));
 	return ret;
 }
 
@@ -145,8 +170,10 @@ const struct address_space_operations udf_aops = {
 	.readpage	= udf_readpage,
 	.readpages	= udf_readpages,
 	.writepage	= udf_writepage,
-	.write_begin		= udf_write_begin,
-	.write_end		= generic_write_end,
+	.writepages	= udf_writepages,
+	.write_begin	= udf_write_begin,
+	.write_end	= generic_write_end,
+	.direct_IO	= udf_direct_IO,
 	.bmap		= udf_bmap,
 };