ext4: introduce direct I/O write using iomap infrastructure

This patch introduces a new direct I/O write path which makes use of
the iomap infrastructure.

All direct I/O writes are now passed from the ->write_iter() callback
through to the new direct I/O handler ext4_dio_write_iter(). This
function is responsible for calling into the iomap infrastructure via
iomap_dio_rw().

Code snippets from the existing direct I/O write code within
ext4_file_write_iter() such as, checking whether the I/O request is
unaligned asynchronous I/O, or whether the write will result in an
overwrite have effectively been moved out and into the new direct I/O
->write_iter() handler.
The block mapping flags that are eventually passed down to
ext4_map_blocks() from the *_get_block_*() suite of routines have been
taken out and introduced within ext4_iomap_alloc().

For inode extension cases, ext4_handle_inode_extension() is
effectively the function responsible for performing such metadata
updates. This is called after iomap_dio_rw() has returned so that we
can safely determine whether we need to potentially truncate any
allocated blocks that may have been prepared for this direct I/O
write. We don't perform the inode extension, or truncate operations
from the ->end_io() handler as we don't have the original I/O 'length'
available there. The ->end_io() however is responsible fo converting
allocated unwritten extents to written extents.

In the instance of a short write, we fallback and complete the
remainder of the I/O using buffered I/O via
ext4_buffered_write_iter().

The existing buffer_head direct I/O implementation has been removed as
it's now redundant.

[ Fix up ext4_dio_write_iter() per Jan's comments at
  https://lore.kernel.org/r/20191105135932.GN22379@quack2.suse.cz -- TYT ]
Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
Link: https://lore.kernel.org/r/e55db6f12ae6ff017f36774135e79f3e7b0333da.1572949325.git.mbobrowski@mbobrowski.orgSigned-off-by: Theodore Ts'o <tytso@mit.edu>

fs/ext4/ext4.h

@@ -1584,7 +1584,6 @@ enum {
 	EXT4_STATE_NO_EXPAND,		/* No space for expansion */
 	EXT4_STATE_DA_ALLOC_CLOSE,	/* Alloc DA blks on close */
 	EXT4_STATE_EXT_MIGRATE,		/* Inode is migrating */
-	EXT4_STATE_DIO_UNWRITTEN,	/* need convert on dio done*/
 	EXT4_STATE_NEWENTRY,		/* File just added to dir */
 	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
 	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
@@ -2565,8 +2564,6 @@ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
 			     struct buffer_head *bh_result, int create);
 int ext4_get_block(struct inode *inode, sector_t iblock,
 		   struct buffer_head *bh_result, int create);
-int ext4_dio_get_block(struct inode *inode, sector_t iblock,
-		       struct buffer_head *bh_result, int create);
 int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int create);
 int ext4_walk_page_buffers(handle_t *handle,

fs/ext4/extents.c

@@ -1753,16 +1753,9 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 	 */
 	if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
 		return 0;
-	/*
-	 * The check for IO to unwritten extent is somewhat racy as we
-	 * increment i_unwritten / set EXT4_STATE_DIO_UNWRITTEN only after
-	 * dropping i_data_sem. But reserved blocks should save us in that
-	 * case.
-	 */
+
 	if (ext4_ext_is_unwritten(ex1) &&
-	    (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
-	     atomic_read(&EXT4_I(inode)->i_unwritten) ||
-	     (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)))
+	    ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)
 		return 0;
 #ifdef AGGRESSIVE_TEST
 	if (ext1_ee_len >= 4)

fs/ext4/file.c

@@ -29,6 +29,7 @@
 #include <linux/pagevec.h>
 #include <linux/uio.h>
 #include <linux/mman.h>
+#include <linux/backing-dev.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -155,13 +156,6 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static void ext4_unwritten_wait(struct inode *inode)
-{
-	wait_queue_head_t *wq = ext4_ioend_wq(inode);
-
-	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
-}
-
 /*
  * This tests whether the IO in question is block-aligned or not.
  * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
@@ -214,13 +208,13 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return -EPERM;
+
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0)
 		return ret;
 
-	if (unlikely(IS_IMMUTABLE(inode)))
-		return -EPERM;
-
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
 	 * is smaller than s_maxbytes, which is for extent-mapped files.
@@ -232,9 +226,42 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
 			return -EFBIG;
 		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
 	}
+
+	ret = file_modified(iocb->ki_filp);
+	if (ret)
+		return ret;
+
 	return iov_iter_count(from);
 }
 
+static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
+					struct iov_iter *from)
+{
+	ssize_t ret;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
+	inode_lock(inode);
+	ret = ext4_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	current->backing_dev_info = inode_to_bdi(inode);
+	ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos);
+	current->backing_dev_info = NULL;
+
+out:
+	inode_unlock(inode);
+	if (likely(ret > 0)) {
+		iocb->ki_pos += ret;
+		ret = generic_write_sync(iocb, ret);
+	}
+
+	return ret;
+}
+
 static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
 					   ssize_t written, size_t count)
 {
@@ -316,6 +343,139 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
 	return written;
 }
 
+static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+				 int error, unsigned int flags)
+{
+	loff_t offset = iocb->ki_pos;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (error)
+		return error;
+
+	if (size && flags & IOMAP_DIO_UNWRITTEN)
+		return ext4_convert_unwritten_extents(NULL, inode,
+						      offset, size);
+
+	return 0;
+}
+
+static const struct iomap_dio_ops ext4_dio_write_ops = {
+	.end_io = ext4_dio_write_end_io,
+};
+
+static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	ssize_t ret;
+	size_t count;
+	loff_t offset;
+	handle_t *handle;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	bool extend = false, overwrite = false, unaligned_aio = false;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock(inode);
+	}
+
+	if (!ext4_dio_supported(inode)) {
+		inode_unlock(inode);
+		/*
+		 * Fallback to buffered I/O if the inode does not support
+		 * direct I/O.
+		 */
+		return ext4_buffered_write_iter(iocb, from);
+	}
+
+	ret = ext4_write_checks(iocb, from);
+	if (ret <= 0) {
+		inode_unlock(inode);
+		return ret;
+	}
+
+	/*
+	 * Unaligned asynchronous direct I/O must be serialized among each
+	 * other as the zeroing of partial blocks of two competing unaligned
+	 * asynchronous direct I/O writes can result in data corruption.
+	 */
+	offset = iocb->ki_pos;
+	count = iov_iter_count(from);
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+	    !is_sync_kiocb(iocb) && ext4_unaligned_aio(inode, from, offset)) {
+		unaligned_aio = true;
+		inode_dio_wait(inode);
+	}
+
+	/*
+	 * Determine whether the I/O will overwrite allocated and initialized
+	 * blocks. If so, check to see whether it is possible to take the
+	 * dioread_nolock path.
+	 */
+	if (!unaligned_aio && ext4_overwrite_io(inode, offset, count) &&
+	    ext4_should_dioread_nolock(inode)) {
+		overwrite = true;
+		downgrade_write(&inode->i_rwsem);
+	}
+
+	if (offset + count > EXT4_I(inode)->i_disksize) {
+		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			goto out;
+		}
+
+		ret = ext4_orphan_add(handle, inode);
+		if (ret) {
+			ext4_journal_stop(handle);
+			goto out;
+		}
+
+		extend = true;
+		ext4_journal_stop(handle);
+	}
+
+	ret = iomap_dio_rw(iocb, from, &ext4_iomap_ops, &ext4_dio_write_ops,
+			   is_sync_kiocb(iocb) || unaligned_aio || extend);
+
+	if (extend)
+		ret = ext4_handle_inode_extension(inode, offset, ret, count);
+
+out:
+	if (overwrite)
+		inode_unlock_shared(inode);
+	else
+		inode_unlock(inode);
+
+	if (ret >= 0 && iov_iter_count(from)) {
+		ssize_t err;
+		loff_t endbyte;
+
+		offset = iocb->ki_pos;
+		err = ext4_buffered_write_iter(iocb, from);
+		if (err < 0)
+			return err;
+
+		/*
+		 * We need to ensure that the pages within the page cache for
+		 * the range covered by this I/O are written to disk and
+		 * invalidated. This is in attempt to preserve the expected
+		 * direct I/O semantics in the case we fallback to buffered I/O
+		 * to complete off the I/O request.
+		 */
+		ret += err;
+		endbyte = offset + err - 1;
+		err = filemap_write_and_wait_range(iocb->ki_filp->f_mapping,
+						   offset, endbyte);
+		if (!err)
+			invalidate_mapping_pages(iocb->ki_filp->f_mapping,
+						 offset >> PAGE_SHIFT,
+						 endbyte >> PAGE_SHIFT);
+	}
+
+	return ret;
+}
+
 #ifdef CONFIG_FS_DAX
 static ssize_t
 ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
@@ -332,15 +492,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			return -EAGAIN;
 		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;
 
 	offset = iocb->ki_pos;
 	count = iov_iter_count(from);
@@ -378,10 +533,6 @@ static ssize_t
 ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
-	int o_direct = iocb->ki_flags & IOCB_DIRECT;
-	int unaligned_aio = 0;
-	int overwrite = 0;
-	ssize_t ret;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
@@ -390,59 +541,10 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (IS_DAX(inode))
 		return ext4_dax_write_iter(iocb, from);
 #endif
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext4_dio_write_iter(iocb, from);
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
-			return -EAGAIN;
-		inode_lock(inode);
-	}
-
-	ret = ext4_write_checks(iocb, from);
-	if (ret <= 0)
-		goto out;
-
-	/*
-	 * Unaligned direct AIO must be serialized among each other as zeroing
-	 * of partial blocks of two competing unaligned AIOs can result in data
-	 * corruption.
-	 */
-	if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
-	    !is_sync_kiocb(iocb) &&
-	    ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
-		unaligned_aio = 1;
-		ext4_unwritten_wait(inode);
-	}
-
-	iocb->private = &overwrite;
-	/* Check whether we do a DIO overwrite or not */
-	if (o_direct && !unaligned_aio) {
-		if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
-			if (ext4_should_dioread_nolock(inode))
-				overwrite = 1;
-		} else if (iocb->ki_flags & IOCB_NOWAIT) {
-			ret = -EAGAIN;
-			goto out;
-		}
-	}
-
-	ret = __generic_file_write_iter(iocb, from);
-	/*
-	 * Unaligned direct AIO must be the only IO in flight. Otherwise
-	 * overlapping aligned IO after unaligned might result in data
-	 * corruption.
-	 */
-	if (ret == -EIOCBQUEUED && unaligned_aio)
-		ext4_unwritten_wait(inode);
-	inode_unlock(inode);
-
-	if (ret > 0)
-		ret = generic_write_sync(iocb, ret);
-
-	return ret;
-
-out:
-	inode_unlock(inode);
-	return ret;
+	return ext4_buffered_write_iter(iocb, from);
 }
 
 #ifdef CONFIG_FS_DAX