linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <djwong@kernel.org>
To: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Christoph Hellwig <hch@infradead.org>, 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
Subject: Re: [PATCH v7 16/19] iomap: Add done_before argument to iomap_dio_rw
Date: Fri, 3 Sep 2021 11:53:51 -0700	[thread overview]
Message-ID: <20210903185351.GD9892@magnolia> (raw)
In-Reply-To: <20210827164926.1726765-17-agruenba@redhat.com>

On Fri, Aug 27, 2021 at 06:49:23PM +0200, Andreas Gruenbacher wrote:
> 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 281c77cfe91a..8817fe6b5fc0 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 fce3a5249e19..64bf2f68e6d6 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 ba88fe51b77a..dcf9a2b4381f 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;

So, now that I actually understand the reason why the count of
previously transferred bytes has to be passed into the iomap_dio, I
would like this field to have a comment so that stupid maintainers like
me don't forget the subtleties again:

	/*
	 * For asynchronous IO, we have one chance to call the iocb
	 * completion method with the results of the directio operation.
	 * If this operation is a resubmission after a previous partial
	 * completion (e.g. page fault), we need to know about that
	 * progress so that we can report that and the result of the
	 * resubmission to the iocb completion.
	 */
	size_t			done_before;

With that added, I think I can live with this enough to:
Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

>  	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;
> @@ -648,11 +653,11 @@ 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
> 

  parent reply	other threads:[~2021-09-03 18:53 UTC|newest]

Thread overview: 99+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-27 16:49 [PATCH v7 00/19] gfs2: Fix mmap + page fault deadlocks Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 01/19] iov_iter: Fix iov_iter_get_pages{,_alloc} page fault return value Andreas Gruenbacher
2021-09-09 11:09   ` Christoph Hellwig
2021-08-27 16:49 ` [PATCH v7 02/19] powerpc/kvm: Fix kvm_use_magic_page Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 03/19] gup: Turn fault_in_pages_{readable,writeable} into fault_in_{readable,writeable} Andreas Gruenbacher
2021-08-27 19:08   ` Al Viro
2021-09-03 14:56   ` Filipe Manana
2021-09-28 15:02     ` Andreas Gruenbacher
2021-09-28 16:37       ` Matthew Wilcox
2021-09-28 20:41         ` Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 04/19] iov_iter: Turn iov_iter_fault_in_readable into fault_in_iov_iter_readable Andreas Gruenbacher
2021-08-27 18:53   ` Al Viro
2021-08-27 18:57     ` Linus Torvalds
2021-08-27 19:16       ` Al Viro
2021-08-27 20:56   ` Kari Argillander
2021-08-28 17:13     ` Linus Torvalds
2021-08-27 16:49 ` [PATCH v7 05/19] iov_iter: Introduce fault_in_iov_iter_writeable Andreas Gruenbacher
2021-08-27 18:49   ` Al Viro
2021-08-27 19:05     ` Linus Torvalds
2021-08-27 19:23       ` Al Viro
2021-08-27 19:33         ` Linus Torvalds
2021-08-27 19:37           ` Al Viro
2021-08-27 21:48             ` Al Viro
2021-08-27 21:57               ` Al Viro
2021-08-27 23:22                 ` Luck, Tony
2021-08-28  2:20                   ` Luck, Tony
2021-08-28 21:47                   ` Thomas Gleixner
2021-08-28 22:04                     ` Al Viro
2021-08-28 22:11                       ` Al Viro
2021-08-28 22:19                         ` Al Viro
2021-08-28 22:51                           ` Al Viro
2021-08-29 18:44                             ` Thomas Gleixner
2021-08-29 19:46                               ` Al Viro
2021-08-29 19:51                                 ` Thomas Gleixner
2021-08-28 22:20                         ` Tony Luck
2021-08-29  1:40                           ` Matthew Wilcox
2021-08-30 15:41                             ` Luck, Tony
2021-08-28 22:23                       ` Thomas Gleixner
2021-08-28 19:28               ` [RFC][arm64] possible infinite loop in btrfs search_ioctl() Al Viro
2021-08-31 13:54                 ` Catalin Marinas
2021-08-31 15:28                   ` Al Viro
2021-08-31 16:01                     ` Catalin Marinas
2021-10-11 17:37                     ` Catalin Marinas
2021-10-11 19:15                       ` Linus Torvalds
2021-10-11 21:08                         ` Catalin Marinas
2021-10-11 23:59                           ` Linus Torvalds
2021-10-12 17:27                             ` Catalin Marinas
2021-10-12 17:58                               ` Linus Torvalds
2021-10-18 17:13                                 ` Catalin Marinas
2021-10-21  0:46                             ` Andreas Gruenbacher
2021-10-21 10:05                               ` Catalin Marinas
2021-10-21 14:42                                 ` Andreas Gruenbacher
2021-10-21 17:09                                   ` Catalin Marinas
2021-10-21 18:00                                     ` Andreas Gruenbacher
2021-10-22 18:41                                       ` Catalin Marinas
2021-10-25 19:37                                         ` Andreas Gruenbacher
2021-10-22  2:30                                   ` Linus Torvalds
2021-10-22  9:34                                     ` Catalin Marinas
2021-08-29  0:58               ` [PATCH v7 05/19] iov_iter: Introduce fault_in_iov_iter_writeable Al Viro
2021-08-27 16:49 ` [PATCH v7 06/19] gfs2: Add wrapper for iomap_file_buffered_write Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 07/19] gfs2: Clean up function may_grant Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 08/19] gfs2: Eliminate vestigial HIF_FIRST Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 09/19] gfs2: Remove redundant check from gfs2_glock_dq Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 10/19] gfs2: Introduce flag for glock holder auto-demotion Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 11/19] gfs2: Move the inode glock locking to gfs2_file_buffered_write Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 12/19] gfs2: Eliminate ip->i_gh Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 13/19] gfs2: Fix mmap + page fault deadlocks for buffered I/O Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 14/19] iomap: Fix iomap_dio_rw return value for user copies Andreas Gruenbacher
2021-09-03 18:54   ` Darrick J. Wong
2021-09-09 11:17   ` Christoph Hellwig
2021-08-27 16:49 ` [PATCH v7 15/19] iomap: Support partial direct I/O on user copy failures Andreas Gruenbacher
2021-09-03 18:54   ` Darrick J. Wong
2021-09-09 11:20   ` Christoph Hellwig
2021-09-28 15:05     ` Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 16/19] iomap: Add done_before argument to iomap_dio_rw Andreas Gruenbacher
2021-08-27 18:30   ` Darrick J. Wong
2021-08-27 20:15     ` Andreas Gruenbacher
2021-08-27 21:32       ` Darrick J. Wong
2021-08-27 21:49         ` Andreas Grünbacher
2021-08-27 22:35         ` Linus Torvalds
2021-09-03 18:47           ` Darrick J. Wong
2021-09-03 18:53   ` Darrick J. Wong [this message]
2021-09-09 11:30   ` Christoph Hellwig
2021-09-09 17:22     ` Linus Torvalds
2021-09-10  7:36       ` Christoph Hellwig
2021-08-27 16:49 ` [PATCH v7 17/19] gup: Introduce FOLL_NOFAULT flag to disable page faults Andreas Gruenbacher
2021-09-09 11:36   ` Christoph Hellwig
2021-09-09 17:17     ` Linus Torvalds
2021-09-10  7:24       ` Christoph Hellwig
2021-08-27 16:49 ` [PATCH v7 18/19] iov_iter: Introduce nofault " Andreas Gruenbacher
2021-08-27 18:47   ` Al Viro
2021-08-27 19:56     ` Andreas Gruenbacher
2021-08-27 16:49 ` [PATCH v7 19/19] gfs2: Fix mmap + page fault deadlocks for direct I/O Andreas Gruenbacher
2021-08-27 17:16 ` [PATCH v7 00/19] gfs2: Fix mmap + page fault deadlocks Linus Torvalds
2021-09-01 19:52   ` Andreas Gruenbacher
2021-09-03 15:52     ` Linus Torvalds
2021-09-03 18:25       ` Al Viro
2021-09-03 18:47         ` Linus Torvalds
2021-09-03 15:07 ` Filipe Manana

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=20210903185351.GD9892@magnolia \
    --to=djwong@kernel.org \
    --cc=agruenba@redhat.com \
    --cc=cluster-devel@redhat.com \
    --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 v7 16/19] 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).