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,
	riteshh@linux.ibm.com
Subject: [PATCH v7 10/11] ext4: update ext4_sync_file() to not use __generic_file_fsync()
Date: Tue, 5 Nov 2019 23:02:23 +1100
Message-ID: <3495f35ef67f2021b567e28e6f59222e583689b8.1572949325.git.mbobrowski@mbobrowski.org> (raw)
In-Reply-To: <cover.1572949325.git.mbobrowski@mbobrowski.org>

When the filesystem is created without a journal, we eventually call
into __generic_file_fsync() in order to write out all the modified
in-core data to the permanent storage device. This function happens to
try and obtain an inode_lock() while synchronizing the files buffer
and it's associated metadata.

Generally, this is fine, however it becomes a problem when there is
higher level code that has already obtained an inode_lock() as this
leads to a recursive lock situation. This case is especially true when
porting across direct I/O to iomap infrastructure as we obtain an
inode_lock() early on in the I/O within ext4_dio_write_iter() and hold
it until the I/O has been completed. Consequently, to not run into
this specific issue, we move away from calling into
__generic_file_fsync() and perform the necessary synchronization tasks
within ext4_sync_file().

Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>
Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/ext4/fsync.c | 72 ++++++++++++++++++++++++++++++++-----------------
 1 file changed, 47 insertions(+), 25 deletions(-)

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 5508baa11bb6..e10206e7f4bb 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -80,6 +80,43 @@ static int ext4_sync_parent(struct inode *inode)
 	return ret;
 }
 
+static int ext4_fsync_nojournal(struct inode *inode, bool datasync,
+				bool *needs_barrier)
+{
+	int ret, err;
+
+	ret = sync_mapping_buffers(inode->i_mapping);
+	if (!(inode->i_state & I_DIRTY_ALL))
+		return ret;
+	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+		return ret;
+
+	err = sync_inode_metadata(inode, 1);
+	if (!ret)
+		ret = err;
+
+	if (!ret)
+		ret = ext4_sync_parent(inode);
+	if (test_opt(inode->i_sb, BARRIER))
+		*needs_barrier = true;
+
+	return ret;
+}
+
+static int ext4_fsync_journal(struct inode *inode, bool datasync,
+			     bool *needs_barrier)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+	tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+
+	if (journal->j_flags & JBD2_BARRIER &&
+	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
+		*needs_barrier = true;
+
+	return jbd2_complete_transaction(journal, commit_tid);
+}
+
 /*
  * akpm: A new design for ext4_sync_file().
  *
@@ -91,17 +128,14 @@ static int ext4_sync_parent(struct inode *inode)
  * What we do is just kick off a commit and wait on it.  This will snapshot the
  * inode to disk.
  */
-
 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);
-	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 	int ret = 0, err;
-	tid_t commit_tid;
 	bool needs_barrier = false;
+	struct inode *inode = file->f_mapping->host;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(sbi)))
 		return -EIO;
 
 	J_ASSERT(ext4_journal_current_handle() == NULL);
@@ -111,23 +145,15 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (sb_rdonly(inode->i_sb)) {
 		/* Make sure that we read updated s_mount_flags value */
 		smp_rmb();
-		if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
 			ret = -EROFS;
 		goto out;
 	}
 
-	if (!journal) {
-		ret = __generic_file_fsync(file, start, end, datasync);
-		if (!ret)
-			ret = ext4_sync_parent(inode);
-		if (test_opt(inode->i_sb, BARRIER))
-			goto issue_flush;
-		goto out;
-	}
-
 	ret = file_write_and_wait_range(file, start, end);
 	if (ret)
 		return ret;
+
 	/*
 	 * data=writeback,ordered:
 	 *  The caller's filemap_fdatawrite()/wait will sync the data.
@@ -142,18 +168,14 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 *  (they were dirtied by commit).  But that's OK - the blocks are
 	 *  safe in-journal, which is all fsync() needs to ensure.
 	 */
-	if (ext4_should_journal_data(inode)) {
+	if (!sbi->s_journal)
+		ret = ext4_fsync_nojournal(inode, datasync, &needs_barrier);
+	else if (ext4_should_journal_data(inode))
 		ret = ext4_force_commit(inode->i_sb);
-		goto out;
-	}
+	else
+		ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
 
-	commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
-	if (journal->j_flags & JBD2_BARRIER &&
-	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
-		needs_barrier = true;
-	ret = jbd2_complete_transaction(journal, commit_tid);
 	if (needs_barrier) {
-	issue_flush:
 		err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 		if (!ret)
 			ret = err;
-- 
2.20.1


  parent reply index

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-05 11:58 [PATCH v7 00/11] ext4: port direct I/O to iomap infrastructure Matthew Bobrowski
2019-11-05 11:58 ` [PATCH v7 01/11] ext4: reorder map.m_flags checks within ext4_iomap_begin() Matthew Bobrowski
2019-11-05 11:59 ` [PATCH v7 02/11] ext4: update direct I/O read lock pattern for IOCB_NOWAIT Matthew Bobrowski
2019-11-05 11:59 ` [PATCH v7 03/11] ext4: iomap that extends beyond EOF should be marked dirty Matthew Bobrowski
2019-11-05 11:59 ` [PATCH v7 04/11] ext4: move set iomap routines into a separate helper ext4_set_iomap() Matthew Bobrowski
2019-11-05 12:00 ` [PATCH v7 05/11] ext4: split IOMAP_WRITE branch in ext4_iomap_begin() into helper Matthew Bobrowski
2019-11-05 12:01 ` [PATCH v7 07/11] ext4: introduce direct I/O read using iomap infrastructure Matthew Bobrowski
2019-11-05 12:01 ` [PATCH v7 08/11] ext4: move inode extension/truncate code out from ->iomap_end() callback Matthew Bobrowski
2019-11-05 15:49   ` Darrick J. Wong
2019-11-05 21:10     ` Matthew Bobrowski
2019-11-05 12:02 ` [PATCH v7 09/11] ext4: move inode extension check out from ext4_iomap_alloc() Matthew Bobrowski
2019-11-05 12:02 ` Matthew Bobrowski [this message]
2019-11-05 12:02 ` [PATCH v7 11/11] ext4: introduce direct I/O write using iomap infrastructure Matthew Bobrowski
2019-11-05 13:59   ` Jan Kara
2019-11-05 20:32     ` Matthew Bobrowski
2019-11-05 20:53       ` Theodore Y. Ts'o
2019-11-05 21:00         ` Matthew Bobrowski
2019-11-06  0:59           ` Theodore Y. Ts'o
2019-11-05 16:28   ` Theodore Y. Ts'o
2019-11-05 20:57     ` Matthew Bobrowski
2019-11-05 12:03 ` [PATCH v7 06/11] ext4: introduce new callback for IOMAP_REPORT Matthew Bobrowski
2019-11-05 15:43   ` Darrick J. Wong

Reply instructions:

You may reply publicly 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=3495f35ef67f2021b567e28e6f59222e583689b8.1572949325.git.mbobrowski@mbobrowski.org \
    --to=mbobrowski@mbobrowski.org \
    --cc=adilger.kernel@dilger.ca \
    --cc=jack@suse.cz \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=riteshh@linux.ibm.com \
    --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