Linux-ext4 Archive on lore.kernel.org
 help / color / Atom feed
From: Matthew Bobrowski <mbobrowski@mbobrowski.org>
To: tytso@mit.edu, jack@suse.cz, adilger.kernel@dilger.ca
Cc: linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	hch@infradead.org, david@fromorbit.com, darrick.wong@oracle.com
Subject: [PATCH v4 4/8] ext4: introduce direct I/O read path using iomap infrastructure
Date: Thu, 3 Oct 2019 21:34:00 +1000
Message-ID: <df2b8a10641ec8a0509f137dcc2db1d3cc6087f1.1570100361.git.mbobrowski@mbobrowski.org> (raw)
In-Reply-To: <cover.1570100361.git.mbobrowski@mbobrowski.org>

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

The new function ext4_dio_read_iter() is responsible for calling into
the iomap infrastructure via iomap_dio_rw(). If the read operation
being performed on the inode does not pass the preliminary checks
performed within ext4_dio_supported(), then we simply fallback to
buffered I/O in order to fulfil the request.

Existing direct I/O read buffer_head code has been removed as it's now
redundant.

Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>
---
 fs/ext4/file.c  | 58 +++++++++++++++++++++++++++++++++++++++++++++----
 fs/ext4/inode.c | 32 +--------------------------
 2 files changed, 55 insertions(+), 35 deletions(-)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ab75aee3e687..69ac042fb74b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -34,6 +34,53 @@
 #include "xattr.h"
 #include "acl.h"
 
+static bool ext4_dio_supported(struct inode *inode)
+{
+	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
+		return false;
+	if (fsverity_active(inode))
+		return false;
+	if (ext4_should_journal_data(inode))
+		return false;
+	if (ext4_has_inline_data(inode))
+		return false;
+	return true;
+}
+
+static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	ssize_t ret;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	/*
+	 * Get exclusion from truncate and other inode operations.
+	 */
+	if (!inode_trylock_shared(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock_shared(inode);
+	}
+
+	if (!ext4_dio_supported(inode)) {
+		inode_unlock_shared(inode);
+		/*
+		 * Fallback to buffered I/O if the operation being
+		 * performed on the inode is not supported by direct
+		 * I/O. The IOCB_DIRECT flag needs to be cleared here
+		 * in order to ensure that the direct I/O path withiin
+		 * generic_file_read_iter() is not taken.
+		 */
+		iocb->ki_flags &= ~IOCB_DIRECT;
+		return generic_file_read_iter(iocb, to);
+	}
+
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL);
+	inode_unlock_shared(inode);
+
+	file_accessed(iocb->ki_filp);
+	return ret;
+}
+
 #ifdef CONFIG_FS_DAX
 static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
@@ -64,16 +111,19 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
 	if (!iov_iter_count(to))
 		return 0; /* skip atime */
 
-#ifdef CONFIG_FS_DAX
-	if (IS_DAX(file_inode(iocb->ki_filp)))
+	if (IS_DAX(inode))
 		return ext4_dax_read_iter(iocb, to);
-#endif
+
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext4_dio_read_iter(iocb, to);
 	return generic_file_read_iter(iocb, to);
 }
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1dace576b8bd..159ffb92f82d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -863,9 +863,6 @@ int ext4_dio_get_block(struct inode *inode, sector_t iblock,
 {
 	/* We don't expect handle for direct IO */
 	WARN_ON_ONCE(ext4_journal_current_handle());
-
-	if (!create)
-		return _ext4_get_block(inode, iblock, bh, 0);
 	return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
 }
 
@@ -3855,30 +3852,6 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 	return ret;
 }
 
-static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct address_space *mapping = iocb->ki_filp->f_mapping;
-	struct inode *inode = mapping->host;
-	size_t count = iov_iter_count(iter);
-	ssize_t ret;
-
-	/*
-	 * Shared inode_lock is enough for us - it protects against concurrent
-	 * writes & truncates and since we take care of writing back page cache,
-	 * we are protected against page writeback as well.
-	 */
-	inode_lock_shared(inode);
-	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
-					   iocb->ki_pos + count - 1);
-	if (ret)
-		goto out_unlock;
-	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
-				   iter, ext4_dio_get_block, NULL, NULL, 0);
-out_unlock:
-	inode_unlock_shared(inode);
-	return ret;
-}
-
 static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
@@ -3905,10 +3878,7 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		return 0;
 
 	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
-	if (iov_iter_rw(iter) == READ)
-		ret = ext4_direct_IO_read(iocb, iter);
-	else
-		ret = ext4_direct_IO_write(iocb, iter);
+	ret = ext4_direct_IO_write(iocb, iter);
 	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
 	return ret;
 }
-- 
2.20.1


  parent reply index

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-03 11:32 [PATCH v4 0/8] ext4: port direct I/O to " Matthew Bobrowski
2019-10-03 11:33 ` [PATCH v4 1/8] ext4: move out iomap field population into separate helper Matthew Bobrowski
2019-10-08 10:27   ` Jan Kara
2019-10-09  8:57     ` Matthew Bobrowski
2019-10-09 13:06       ` Jan Kara
2019-10-10  5:39         ` Matthew Bobrowski
2019-10-09  6:02   ` Ritesh Harjani
2019-10-09  7:07     ` Christoph Hellwig
2019-10-09  7:50       ` Ritesh Harjani
2019-10-09  9:09         ` Matthew Bobrowski
2019-10-03 11:33 ` [PATCH v4 2/8] ext4: move out IOMAP_WRITE path " Matthew Bobrowski
2019-10-08 10:31   ` Jan Kara
2019-10-09  9:18     ` Matthew Bobrowski
2019-10-09  6:22   ` Ritesh Harjani
2019-10-09  9:31     ` Matthew Bobrowski
2019-10-03 11:33 ` [PATCH v4 3/8] ext4: introduce new callback for IOMAP_REPORT operations Matthew Bobrowski
2019-10-08 10:42   ` Jan Kara
2019-10-09  9:41     ` Matthew Bobrowski
2019-10-09  6:00   ` Ritesh Harjani
2019-10-09 12:08     ` Matthew Bobrowski
2019-10-09 13:14       ` Ritesh Harjani
2019-10-03 11:34 ` Matthew Bobrowski [this message]
2019-10-08 10:52   ` [PATCH v4 4/8] ext4: introduce direct I/O read path using iomap infrastructure Jan Kara
2019-10-09 10:55     ` Matthew Bobrowski
2019-10-09  6:39   ` Ritesh Harjani
2019-10-03 11:34 ` [PATCH v4 5/8] ext4: move inode extension/truncate code out from ->iomap_end() callback Matthew Bobrowski
2019-10-08 11:25   ` Jan Kara
2019-10-09 10:18     ` Matthew Bobrowski
2019-10-09 12:51       ` Jan Kara
2019-10-10  5:44         ` Matthew Bobrowski
2019-10-09  6:27   ` Ritesh Harjani
2019-10-09 10:20     ` Matthew Bobrowski
2019-10-03 11:34 ` [PATCH v4 6/8] ext4: move inode extension checks out from ext4_iomap_alloc() Matthew Bobrowski
2019-10-08 11:27   ` Jan Kara
2019-10-09 10:21     ` Matthew Bobrowski
2019-10-09  6:30   ` Ritesh Harjani
2019-10-09 10:39     ` Matthew Bobrowski
2019-10-03 11:34 ` [PATCH v4 7/8] ext4: reorder map.m_flags checks in ext4_set_iomap() Matthew Bobrowski
2019-10-08 11:30   ` Jan Kara
2019-10-09 10:42     ` Matthew Bobrowski
2019-10-09  6:35   ` Ritesh Harjani
2019-10-09 10:43     ` Matthew Bobrowski
2019-10-03 11:35 ` [PATCH v4 8/8] ext4: introduce direct I/O write path using iomap infrastructure Matthew Bobrowski
2019-10-08 15:12   ` Jan Kara
2019-10-09  7:11     ` Christoph Hellwig
2019-10-09 13:41       ` Jan Kara
2019-10-09 11:53     ` Matthew Bobrowski

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=df2b8a10641ec8a0509f137dcc2db1d3cc6087f1.1570100361.git.mbobrowski@mbobrowski.org \
    --to=mbobrowski@mbobrowski.org \
    --cc=adilger.kernel@dilger.ca \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=tytso@mit.edu \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-ext4 Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-ext4/0 linux-ext4/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-ext4 linux-ext4/ https://lore.kernel.org/linux-ext4 \
		linux-ext4@vger.kernel.org
	public-inbox-index linux-ext4

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-ext4


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git