linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andreas Gruenbacher <agruenba@redhat.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Christoph Hellwig <hch@infradead.org>,
	"Darrick J. Wong" <djwong@kernel.org>
Cc: Jan Kara <jack@suse.cz>, Matthew Wilcox <willy@infradead.org>,
	cluster-devel@redhat.com, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, ocfs2-devel@oss.oracle.com,
	Andreas Gruenbacher <agruenba@redhat.com>
Subject: [PATCH v4 5/8] iomap: Add done_before argument to iomap_dio_rw
Date: Sat, 24 Jul 2021 21:34:46 +0200	[thread overview]
Message-ID: <20210724193449.361667-6-agruenba@redhat.com> (raw)
In-Reply-To: <20210724193449.361667-1-agruenba@redhat.com>

Add a done_before argument to iomap_dio_rw that indicates how much of the
request has already been transferred.  When the request succeeds, we report
that done_before additional bytes were tranferred.  This is useful for
finishing a request asynchronously when part of the request has already been
completed synchronously.

We'll use that to allow iomap_dio_rw to be used with page faults disabled: when
a page fault occurs while submitting a request, we synchronously complete the
part of the request that has already been submitted.  The caller can then take
care of the page fault and call iomap_dio_rw again for the rest of the request,
passing in the number of bytes already tranferred.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/btrfs/file.c       |  5 +++--
 fs/ext4/file.c        |  5 +++--
 fs/gfs2/file.c        |  4 ++--
 fs/iomap/direct-io.c  | 12 ++++++++----
 fs/xfs/xfs_file.c     |  6 +++---
 fs/zonefs/super.c     |  4 ++--
 include/linux/iomap.h |  4 ++--
 7 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index ee34497500e1..ea13d88e8c14 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1945,7 +1945,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			     0);
+			     0, 0);
 
 	btrfs_inode_unlock(inode, ilock_flags);
 
@@ -3637,7 +3637,8 @@ static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to)
 		return 0;
 
 	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
-	ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, 0);
+	ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
+			   0, 0);
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 	return ret;
 }
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 816dedcbd541..4a5e7fd31fb5 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -74,7 +74,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		return generic_file_read_iter(iocb, to);
 	}
 
-	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, 0);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);
@@ -566,7 +566,8 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ilock_shared)
 		iomap_ops = &ext4_iomap_overwrite_ops;
 	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
-			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0);
+			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0,
+			   0);
 	if (ret == -ENOTBLK)
 		ret = 0;
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 3aa66d4de383..eea42cc94585 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -792,7 +792,7 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to,
 	if (ret)
 		goto out_uninit;
 
-	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0, 0);
 	gfs2_glock_dq(gh);
 out_uninit:
 	gfs2_holder_uninit(gh);
@@ -826,7 +826,7 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from,
 	if (offset + len > i_size_read(&ip->i_inode))
 		goto out;
 
-	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0, 0);
 	if (ret == -ENOTBLK)
 		ret = 0;
 out:
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index cc0b4bc8861b..51831ce93f6e 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -31,6 +31,7 @@ struct iomap_dio {
 	atomic_t		ref;
 	unsigned		flags;
 	int			error;
+	size_t			done_before;
 	bool			wait_for_completion;
 
 	union {
@@ -128,7 +129,9 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 
 	kfree(dio);
 
-	return ret;
+	if (ret < 0)
+		return ret;
+	return dio->done_before + ret;
 }
 EXPORT_SYMBOL_GPL(iomap_dio_complete);
 
@@ -450,7 +453,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 struct iomap_dio *
 __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
@@ -477,6 +480,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->dops = dops;
 	dio->error = 0;
 	dio->flags = 0;
+	dio->done_before = done_before;
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;
@@ -642,11 +646,11 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw);
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct iomap_dio *dio;
 
-	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags);
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before);
 	if (IS_ERR_OR_NULL(dio))
 		return PTR_ERR_OR_ZERO(dio);
 	return iomap_dio_complete(dio);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index cc3cfb12df53..3103d9bda466 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -259,7 +259,7 @@ xfs_file_dio_read(
 	ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED);
 	if (ret)
 		return ret;
-	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, 0);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;
@@ -569,7 +569,7 @@ xfs_file_dio_write_aligned(
 	}
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, 0);
+			   &xfs_dio_write_ops, 0, 0);
 out_unlock:
 	if (iolock)
 		xfs_iunlock(ip, iolock);
@@ -647,7 +647,7 @@ xfs_file_dio_write_unaligned(
 
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, flags);
+			   &xfs_dio_write_ops, flags, 0);
 
 	/*
 	 * Retry unaligned I/O with exclusive blocking semantics if the DIO
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 70055d486bf7..85ca2f5fe06e 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -864,7 +864,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 		ret = zonefs_file_dio_append(iocb, from);
 	else
 		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
-				   &zonefs_write_dio_ops, 0);
+				   &zonefs_write_dio_ops, 0, 0);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
 		if (ret > 0)
@@ -999,7 +999,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		}
 		file_accessed(iocb->ki_filp);
 		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
-				   &zonefs_read_dio_ops, 0);
+				   &zonefs_read_dio_ops, 0, 0);
 	} else {
 		ret = generic_file_read_iter(iocb, to);
 		if (ret == -EIO)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 479c1da3e221..8aea35f1a003 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -269,10 +269,10 @@ struct iomap_dio_ops {
 
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags);
+		unsigned int dio_flags, size_t done_before);
 struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags);
+		unsigned int dio_flags, size_t done_before);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
-- 
2.26.3


  parent reply	other threads:[~2021-07-24 19:35 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-24 19:34 [PATCH v4 0/8] gfs2: Fix mmap + page fault deadlocks Andreas Gruenbacher
2021-07-24 19:34 ` [PATCH v4 1/8] iov_iter: Introduce iov_iter_fault_in_writeable helper Andreas Gruenbacher
2021-07-24 19:52   ` Linus Torvalds
2021-07-24 20:24     ` Al Viro
2021-07-24 20:37       ` Linus Torvalds
2021-07-24 21:38       ` Andreas Gruenbacher
2021-07-24 21:57         ` Al Viro
2021-07-24 22:06           ` Andreas Gruenbacher
2021-07-24 23:39             ` Al Viro
2021-07-27  9:30     ` David Laight
2021-07-27 11:13       ` Andreas Gruenbacher
2021-07-27 17:51         ` Linus Torvalds
2021-07-24 19:34 ` [PATCH v4 2/8] gfs2: Add wrapper for iomap_file_buffered_write Andreas Gruenbacher
2021-07-24 19:34 ` [PATCH v4 3/8] gfs2: Fix mmap + page fault deadlocks for buffered I/O Andreas Gruenbacher
2021-07-24 19:34 ` [PATCH v4 4/8] iomap: Fix iomap_dio_rw return value for user copies Andreas Gruenbacher
2021-07-24 19:34 ` Andreas Gruenbacher [this message]
2021-07-24 19:34 ` [PATCH v4 6/8] iomap: Support restarting direct I/O requests after user copy failures Andreas Gruenbacher
2021-07-24 19:34 ` [PATCH v4 7/8] iov_iter: Introduce noio flag to disable page faults Andreas Gruenbacher
2021-07-24 19:34 ` [PATCH v4 8/8] gfs2: Fix mmap + page fault deadlocks for direct I/O Andreas Gruenbacher

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=20210724193449.361667-6-agruenba@redhat.com \
    --to=agruenba@redhat.com \
    --cc=cluster-devel@redhat.com \
    --cc=djwong@kernel.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ocfs2-devel@oss.oracle.com \
    --cc=torvalds@linux-foundation.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --subject='Re: [PATCH v4 5/8] iomap: Add done_before argument to iomap_dio_rw' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).