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>,
Andreas Gruenbacher <agruenba@redhat.com>,
linux-kernel@vger.kernel.org, cluster-devel@redhat.com,
linux-fsdevel@vger.kernel.org, ocfs2-devel@oss.oracle.com
Subject: [Ocfs2-devel] [PATCH v5 10/12] iomap: Add done_before argument to iomap_dio_rw
Date: Tue, 3 Aug 2021 21:18:16 +0200 [thread overview]
Message-ID: <20210803191818.993968-11-agruenba@redhat.com> (raw)
In-Reply-To: <20210803191818.993968-1-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 | 11 ++++++++---
fs/xfs/xfs_file.c | 6 +++---
fs/zonefs/super.c | 4 ++--
include/linux/iomap.h | 4 ++--
7 files changed, 23 insertions(+), 16 deletions(-)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 8ff9e0bb5b0f..c20cc0fc61d9 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1946,7 +1946,7 @@ 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);
@@ -3638,7 +3638,8 @@ 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 c0f86a28f1bf..d98f690097e2 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 35c3f2bae65a..7564e740aff8 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 {
@@ -126,6 +127,9 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
ret = generic_write_sync(iocb, ret);
+ if (ret >= 0)
+ ret += dio->done_before;
+
kfree(dio);
return ret;
@@ -450,7 +454,7 @@ 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 +481,7 @@ __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;
@@ -655,11 +660,11 @@ 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 bcae4814b8e3..908bda10024c 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -276,10 +276,10 @@ 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
_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel@oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel
next prev parent reply other threads:[~2021-08-03 19:19 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-03 19:18 [Ocfs2-devel] [PATCH v5 00/12] gfs2: Fix mmap + page fault deadlocks Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 01/12] iov_iter: Fix iov_iter_get_pages{, _alloc} page fault return value Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 02/12] powerpc/kvm: Fix kvm_use_magic_page Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 03/12] Turn fault_in_pages_{readable, writeable} into fault_in_{readable, writeable} Andreas Gruenbacher
2021-08-03 19:43 ` Linus Torvalds
2021-08-03 20:57 ` Al Viro
2021-08-03 21:38 ` Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 04/12] Turn iov_iter_fault_in_readable into fault_in_iov_iter_readable Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 05/12] iov_iter: Introduce fault_in_iov_iter_writeable Andreas Gruenbacher
2021-08-04 15:24 ` Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 06/12] gfs2: Add wrapper for iomap_file_buffered_write Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 07/12] gfs2: Fix mmap + page fault deadlocks for buffered I/O Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 08/12] iomap: Fix iomap_dio_rw return value for user copies Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 09/12] iomap: Support restarting direct I/O requests after user copy failures Andreas Gruenbacher
2021-08-03 19:18 ` Andreas Gruenbacher [this message]
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 11/12] iov_iter: Introduce noio flag to disable page faults Andreas Gruenbacher
2021-08-03 19:18 ` [Ocfs2-devel] [PATCH v5 12/12] gfs2: Fix mmap + page fault deadlocks for direct I/O Andreas Gruenbacher
2021-08-03 19:45 ` [Ocfs2-devel] [PATCH v5 00/12] gfs2: Fix mmap + page fault deadlocks Linus Torvalds
2021-08-16 19:14 ` Andreas Gruenbacher
2021-08-18 21:49 ` Linus Torvalds
2021-08-19 19:40 ` Andreas Gruenbacher
2021-08-19 20:14 ` Linus Torvalds
2021-08-19 21:39 ` 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=20210803191818.993968-11-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 \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).