lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Fri, 18 Nov 2016 09:47:05 +0100
From:   Jan Kara <jack@...e.cz>
To:     Ted Tso <tytso@....edu>
Cc:     <linux-ext4@...r.kernel.org>,
        Ross Zwisler <ross.zwisler@...ux.intel.com>,
        Jan Kara <jack@...e.cz>
Subject: [PATCH 05/10] ext4: DAX iomap write support

Implement DAX writes using the new iomap infrastructure instead of
overloading the direct IO path.

Signed-off-by: Jan Kara <jack@...e.cz>
---
 fs/ext4/file.c  |  40 ++++++++++++++++++
 fs/ext4/inode.c | 126 +++++++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 160 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1f25c644cb12..1953fe34f9fe 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -169,6 +169,41 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	return iov_iter_count(from);
 }
 
+#ifdef CONFIG_FS_DAX
+static ssize_t
+ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+	bool overwrite = false;
+
+	inode_lock(inode);
+	ret = ext4_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+	ret = file_remove_privs(iocb->ki_filp);
+	if (ret)
+		goto out;
+	ret = file_update_time(iocb->ki_filp);
+	if (ret)
+		goto out;
+
+	if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
+		overwrite = true;
+		downgrade_write(&inode->i_rwsem);
+	}
+	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
+out:
+	if (!overwrite)
+		inode_unlock(inode);
+	else
+		inode_unlock_shared(inode);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	return ret;
+}
+#endif
+
 static ssize_t
 ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
@@ -178,6 +213,11 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	int overwrite = 0;
 	ssize_t ret;
 
+#ifdef CONFIG_FS_DAX
+	if (IS_DAX(inode))
+		return ext4_dax_write_iter(iocb, from);
+#endif
+
 	inode_lock(inode);
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index df017ce3e52d..a7079cab645a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3321,18 +3321,79 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	struct ext4_map_blocks map;
 	int ret;
 
-	if (flags & IOMAP_WRITE)
-		return -EIO;
-
 	if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
 		return -ERANGE;
 
 	map.m_lblk = first_block;
 	map.m_len = last_block - first_block + 1;
 
-	ret = ext4_map_blocks(NULL, inode, &map, 0);
-	if (ret < 0)
-		return ret;
+	if (!(flags & IOMAP_WRITE)) {
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+	} else {
+		int dio_credits;
+		handle_t *handle;
+		int retries = 0;
+
+		/* Trim mapping request to maximum we can map at once for DIO */
+		if (map.m_len > DIO_MAX_BLOCKS)
+			map.m_len = DIO_MAX_BLOCKS;
+		dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
+retry:
+		/*
+		 * Either we allocate blocks and then we don't get unwritten
+		 * extent so we have reserved enough credits, or the blocks
+		 * are already allocated and unwritten and in that case
+		 * extent conversion fits in the credits as well.
+		 */
+		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+					    dio_credits);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+
+		ret = ext4_map_blocks(handle, inode, &map,
+				      EXT4_GET_BLOCKS_PRE_IO |
+				      EXT4_GET_BLOCKS_CREATE_ZERO);
+		if (ret < 0) {
+			ext4_journal_stop(handle);
+			if (ret == -ENOSPC &&
+			    ext4_should_retry_alloc(inode->i_sb, &retries))
+				goto retry;
+			return ret;
+		}
+		/* For DAX writes we need to zero out unwritten extents */
+		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+			/*
+			 * We are protected by i_mmap_sem or i_rwsem so we know
+			 * block cannot go away from under us even though we
+			 * dropped i_data_sem. Convert extent to written and
+			 * write zeros there.
+			 */
+			ret = ext4_map_blocks(handle, inode, &map,
+					      EXT4_GET_BLOCKS_CONVERT |
+					      EXT4_GET_BLOCKS_CREATE_ZERO);
+			if (ret < 0) {
+				ext4_journal_stop(handle);
+				return ret;
+			}
+		}
+
+		/*
+		 * If we added blocks beyond i_size we need to make sure they
+		 * will get truncated if we crash before updating i_size in
+		 * ext4_iomap_end().
+		 */
+		if (first_block + map.m_len >
+		    (inode->i_size + (1 << blkbits) - 1) >> blkbits) {
+			int err;
+
+			err = ext4_orphan_add(handle, inode);
+			if (err < 0) {
+				ext4_journal_stop(handle);
+				return err;
+			}
+		}
+		ext4_journal_stop(handle);
+	}
 
 	iomap->flags = 0;
 	iomap->bdev = inode->i_sb->s_bdev;
@@ -3360,8 +3421,61 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	return 0;
 }
 
+static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
+			  ssize_t written, unsigned flags, struct iomap *iomap)
+{
+	int ret = 0;
+	handle_t *handle;
+	int blkbits = inode->i_blkbits;
+	bool truncate = false;
+
+	if (!(flags & IOMAP_WRITE))
+		return 0;
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto orphan_del;
+	}
+	if (ext4_update_inode_size(inode, offset + written))
+		ext4_mark_inode_dirty(handle, inode);
+	/*
+	 * We may need to truncate allocated but not written blocks beyond EOF.
+	 */
+	if (iomap->offset + iomap->length > 
+	    ALIGN(inode->i_size, 1 << blkbits)) {
+		ext4_lblk_t written_blk, end_blk;
+
+		written_blk = (offset + written) >> blkbits;
+		end_blk = (offset + length) >> blkbits;
+		if (written_blk < end_blk && ext4_can_truncate(inode))
+			truncate = true;
+	}
+	/*
+	 * Remove inode from orphan list if we were extending a inode and
+	 * everything went fine.
+	 */
+	if (!truncate && inode->i_nlink &&
+	    !list_empty(&EXT4_I(inode)->i_orphan))
+		ext4_orphan_del(handle, inode);
+	ext4_journal_stop(handle);
+	if (truncate) {
+		ext4_truncate_failed_write(inode);
+orphan_del:
+		/*
+		 * If truncate failed early the inode might still be on the
+		 * orphan list; we need to make sure the inode is removed from
+		 * the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+	return ret;
+}
+
 struct iomap_ops ext4_iomap_ops = {
 	.iomap_begin		= ext4_iomap_begin,
+	.iomap_end		= ext4_iomap_end,
 };
 
 #else
-- 
2.6.6

--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists