From: Andreas Gruenbacher <agruenba@redhat.com>
To: cluster-devel@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Catalin Marinas <catalin.marinas@arm.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Christoph Hellwig <hch@infradead.org>,
"Darrick J. Wong" <djwong@kernel.org>,
Paul Mackerras <paulus@ozlabs.org>, Jan Kara <jack@suse.cz>,
Matthew Wilcox <willy@infradead.org>,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
ocfs2-devel@oss.oracle.com, kvm-ppc@vger.kernel.org,
linux-btrfs@vger.kernel.org,
Andreas Gruenbacher <agruenba@redhat.com>
Subject: [PATCH v9 14/17] iomap: Add done_before argument to iomap_dio_rw
Date: Tue, 2 Nov 2021 13:29:42 +0100 [thread overview]
Message-ID: <20211102122945.117744-15-agruenba@redhat.com> (raw)
In-Reply-To: <20211102122945.117744-1-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>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
fs/btrfs/file.c | 5 +++--
fs/erofs/data.c | 2 +-
fs/ext4/file.c | 5 +++--
fs/gfs2/file.c | 4 ++--
fs/iomap/direct-io.c | 19 ++++++++++++++++---
fs/xfs/xfs_file.c | 6 +++---
fs/zonefs/super.c | 4 ++--
include/linux/iomap.h | 4 ++--
8 files changed, 32 insertions(+), 17 deletions(-)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f37211d3bb69..9d41b28c67ba 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1957,7 +1957,7 @@ 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);
@@ -3658,7 +3658,8 @@ 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/erofs/data.c b/fs/erofs/data.c
index 9db829715652..16a41d0db55a 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -287,7 +287,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
if (!err)
return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
- NULL, 0);
+ NULL, 0, 0);
if (err < 0)
return err;
}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ac0e11bbb445..b25c1f8f7c4f 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 d9126e3e6dd6..f772ee0fcae3 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -822,7 +822,7 @@ 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);
@@ -856,7 +856,7 @@ 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 a434fb7887b2..468dcbba45bc 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 {
@@ -124,6 +125,9 @@ 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;
@@ -450,13 +454,21 @@ static loff_t iomap_dio_iter(const struct iomap_iter *iter,
* may be pure data writes. In that case, we still need to do a full data sync
* completion.
*
+ * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL,
+ * __iomap_dio_rw can return a partial result if it encounters a non-resident
+ * page in @iter after preparing a transfer. In that case, the non-resident
+ * pages can be faulted in and the request resumed with @done_before set to the
+ * number of bytes previously transferred. The request will then complete with
+ * the correct total number of bytes transferred; this is essential for
+ * completing partial requests asynchronously.
+ *
* Returns -ENOTBLK In case of a page invalidation invalidation failure for
* writes. The callers needs to fall back to buffered I/O in this case.
*/
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);
@@ -486,6 +498,7 @@ __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;
@@ -652,11 +665,11 @@ 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 7aa943edfc02..240eb932c014 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 ddc346a9df9b..6122c38ab44d 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -852,7 +852,7 @@ 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)
@@ -987,7 +987,7 @@ 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 2a213b0d1e1f..829f2325ecba 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -339,10 +339,10 @@ 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);
--
2.31.1
next prev parent reply other threads:[~2021-11-02 12:31 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-02 12:29 [PATCH v9 00/17] gfs2: Fix mmap + page fault deadlocks Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 01/17] iov_iter: Fix iov_iter_get_pages{,_alloc} page fault return value Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 02/17] powerpc/kvm: Fix kvm_use_magic_page Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 03/17] gup: Turn fault_in_pages_{readable,writeable} into fault_in_{readable,writeable} Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 04/17] iov_iter: Turn iov_iter_fault_in_readable into fault_in_iov_iter_readable Andreas Gruenbacher
2021-11-04 18:22 ` Catalin Marinas
2021-11-04 20:31 ` Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 05/17] iov_iter: Introduce fault_in_iov_iter_writeable Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 06/17] gfs2: Add wrapper for iomap_file_buffered_write Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 07/17] gfs2: Clean up function may_grant Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 08/17] gfs2: Introduce flag for glock holder auto-demotion Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 09/17] gfs2: Move the inode glock locking to gfs2_file_buffered_write Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 10/17] gfs2: Eliminate ip->i_gh Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 11/17] gfs2: Fix mmap + page fault deadlocks for buffered I/O Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 12/17] iomap: Fix iomap_dio_rw return value for user copies Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 13/17] iomap: Support partial direct I/O on user copy failures Andreas Gruenbacher
2021-11-02 12:29 ` Andreas Gruenbacher [this message]
2021-11-02 12:29 ` [PATCH v9 15/17] gup: Introduce FOLL_NOFAULT flag to disable page faults Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 16/17] iov_iter: Introduce nofault " Andreas Gruenbacher
2021-11-02 12:29 ` [PATCH v9 17/17] 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=20211102122945.117744-15-agruenba@redhat.com \
--to=agruenba@redhat.com \
--cc=catalin.marinas@arm.com \
--cc=cluster-devel@redhat.com \
--cc=djwong@kernel.org \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=kvm-ppc@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ocfs2-devel@oss.oracle.com \
--cc=paulus@ozlabs.org \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/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).