[f2fs-dev] cleanup the filemap / direct I/O interaction v3

[f2fs-dev] cleanup the filemap / direct I/O interaction v3

[Christoph Hellwig]

Hi all,

this series cleans up some of the generic write helper calling
conventions and the page cache writeback / invalidation for
direct I/O.  This is a spinoff from the no-bufferhead kernel
project, for which we'll want to an use iomap based buffered
write path in the block layer.

Changes since v2:
 - stick to the existing behavior of returning a short write
   if the buffer fallback write or sync fails
 - bring back "fuse: use direct_write_fallback" which accidentally
   got lost in v2

Changes since v1:
 - remove current->backing_dev_info entirely
 - fix the pos/end calculation in direct_write_fallback
 - rename kiocb_invalidate_post_write to
   kiocb_invalidate_post_direct_write
 - typo fixes

diffstat:
 block/fops.c            |   18 +-----
 fs/btrfs/file.c         |    6 --
 fs/ceph/file.c          |    6 --
 fs/direct-io.c          |   10 ---
 fs/ext4/file.c          |   11 +---
 fs/f2fs/file.c          |    3 -
 fs/fuse/file.c          |    4 -
 fs/gfs2/file.c          |    6 --
 fs/iomap/buffered-io.c  |    9 ++-
 fs/iomap/direct-io.c    |   88 ++++++++++++---------------------
 fs/nfs/file.c           |    6 --
 fs/ntfs/file.c          |    2 
 fs/ntfs3/file.c         |    3 -
 fs/xfs/xfs_file.c       |    6 --
 fs/zonefs/file.c        |    4 -
 include/linux/fs.h      |    5 -
 include/linux/pagemap.h |    4 +
 include/linux/sched.h   |    3 -
 mm/filemap.c            |  126 ++++++++++++++++++++++++++----------------------
 19 files changed, 125 insertions(+), 195 deletions(-)


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH 1/8] backing_dev: remove current->backing_dev_info

[Christoph Hellwig]

The last user of current->backing_dev_info disappeared in commit
b9b1335e6403 ("remove bdi_congested() and wb_congested() and related
functions").  Remove the field and all assignments to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/btrfs/file.c       | 6 +-----
 fs/ceph/file.c        | 4 ----
 fs/ext4/file.c        | 2 --
 fs/f2fs/file.c        | 2 --
 fs/fuse/file.c        | 4 ----
 fs/gfs2/file.c        | 2 --
 fs/nfs/file.c         | 5 +----
 fs/ntfs/file.c        | 2 --
 fs/ntfs3/file.c       | 3 ---
 fs/xfs/xfs_file.c     | 4 ----
 include/linux/sched.h | 3 ---
 mm/filemap.c          | 3 ---
 12 files changed, 2 insertions(+), 38 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f649647392e0e4..ecd43ab66fa6c7 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1145,7 +1145,6 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from,
 	    !(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)))
 		return -EAGAIN;
 
-	current->backing_dev_info = inode_to_bdi(inode);
 	ret = file_remove_privs(file);
 	if (ret)
 		return ret;
@@ -1165,10 +1164,8 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from,
 		loff_t end_pos = round_up(pos + count, fs_info->sectorsize);
 
 		ret = btrfs_cont_expand(BTRFS_I(inode), oldsize, end_pos);
-		if (ret) {
-			current->backing_dev_info = NULL;
+		if (ret)
 			return ret;
-		}
 	}
 
 	return 0;
@@ -1689,7 +1686,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
 	if (sync)
 		atomic_dec(&inode->sync_writers);
 
-	current->backing_dev_info = NULL;
 	return num_written;
 }
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index f4d8bf7dec88a8..c8ef72f723badd 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1791,9 +1791,6 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	else
 		ceph_start_io_write(inode);
 
-	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = inode_to_bdi(inode);
-
 	if (iocb->ki_flags & IOCB_APPEND) {
 		err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
 		if (err < 0)
@@ -1940,7 +1937,6 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		ceph_end_io_write(inode);
 out_unlocked:
 	ceph_free_cap_flush(prealloc_cf);
-	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
 
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d101b3b0c7dad8..bc430270c23c19 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -285,9 +285,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
 	if (ret <= 0)
 		goto out;
 
-	current->backing_dev_info = inode_to_bdi(inode);
 	ret = generic_perform_write(iocb, from);
-	current->backing_dev_info = NULL;
 
 out:
 	inode_unlock(inode);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5ac53d2627d20d..4f423d367a44b9 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -4517,9 +4517,7 @@ static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb,
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		return -EOPNOTSUPP;
 
-	current->backing_dev_info = inode_to_bdi(inode);
 	ret = generic_perform_write(iocb, from);
-	current->backing_dev_info = NULL;
 
 	if (ret > 0) {
 		iocb->ki_pos += ret;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 89d97f6188e05e..97d435874b14aa 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1362,9 +1362,6 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
 writethrough:
 	inode_lock(inode);
 
-	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = inode_to_bdi(inode);
-
 	err = generic_write_checks(iocb, from);
 	if (err <= 0)
 		goto out;
@@ -1409,7 +1406,6 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			iocb->ki_pos += written;
 	}
 out:
-	current->backing_dev_info = NULL;
 	inode_unlock(inode);
 	if (written > 0)
 		written = generic_write_sync(iocb, written);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 300844f50dcd28..904a0d6ac1a1a9 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1041,11 +1041,9 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb,
 			goto out_unlock;
 	}
 
-	current->backing_dev_info = inode_to_bdi(inode);
 	pagefault_disable();
 	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
 	pagefault_enable();
-	current->backing_dev_info = NULL;
 	if (ret > 0) {
 		iocb->ki_pos += ret;
 		written += ret;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index f0edf5a36237d1..665ce3fc62eaf4 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -648,11 +648,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	since = filemap_sample_wb_err(file->f_mapping);
 	nfs_start_io_write(inode);
 	result = generic_write_checks(iocb, from);
-	if (result > 0) {
-		current->backing_dev_info = inode_to_bdi(inode);
+	if (result > 0)
 		result = generic_perform_write(iocb, from);
-		current->backing_dev_info = NULL;
-	}
 	nfs_end_io_write(inode);
 	if (result <= 0)
 		goto out;
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index c481b14e4fd989..e296f804a9c442 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1911,11 +1911,9 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	inode_lock(vi);
 	/* We can write back this queue in page reclaim. */
-	current->backing_dev_info = inode_to_bdi(vi);
 	err = ntfs_prepare_file_for_write(iocb, from);
 	if (iov_iter_count(from) && !err)
 		written = ntfs_perform_write(file, from, iocb->ki_pos);
-	current->backing_dev_info = NULL;
 	inode_unlock(vi);
 	iocb->ki_pos += written;
 	if (likely(written > 0))
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 9a3d55c367d920..86d16a2c8339ca 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -820,7 +820,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 	if (!pages)
 		return -ENOMEM;
 
-	current->backing_dev_info = inode_to_bdi(inode);
 	err = file_remove_privs(file);
 	if (err)
 		goto out;
@@ -993,8 +992,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 out:
 	kfree(pages);
 
-	current->backing_dev_info = NULL;
-
 	if (err < 0)
 		return err;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index aede746541f8ae..431c3fd0e2b598 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -717,9 +717,6 @@ xfs_file_buffered_write(
 	if (ret)
 		goto out;
 
-	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = inode_to_bdi(inode);
-
 	trace_xfs_file_buffered_write(iocb, from);
 	ret = iomap_file_buffered_write(iocb, from,
 			&xfs_buffered_write_iomap_ops);
@@ -753,7 +750,6 @@ xfs_file_buffered_write(
 		goto write_retry;
 	}
 
-	current->backing_dev_info = NULL;
 out:
 	if (iolock)
 		xfs_iunlock(ip, iolock);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index eed5d65b8d1f4d..54780571fe9a07 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -41,7 +41,6 @@
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
-struct backing_dev_info;
 struct bio_list;
 struct blk_plug;
 struct bpf_local_storage;
@@ -1186,8 +1185,6 @@ struct task_struct {
 	/* VM state: */
 	struct reclaim_state		*reclaim_state;
 
-	struct backing_dev_info		*backing_dev_info;
-
 	struct io_context		*io_context;
 
 #ifdef CONFIG_COMPACTION
diff --git a/mm/filemap.c b/mm/filemap.c
index b4c9bd368b7e58..33b54660ad2b39 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3991,8 +3991,6 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t		err;
 	ssize_t		status;
 
-	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = inode_to_bdi(inode);
 	err = file_remove_privs(file);
 	if (err)
 		goto out;
@@ -4053,7 +4051,6 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			iocb->ki_pos += written;
 	}
 out:
-	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
 EXPORT_SYMBOL(__generic_file_write_iter);
-- 
2.39.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH 2/8] iomap: update ki_pos a little later in iomap_dio_complete

[Christoph Hellwig]

Move the ki_pos update down a bit to prepare for a better common
helper that invalidates pages based of an iocb.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/iomap/direct-io.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 019cc87d0fb339..6207a59d2162e1 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -94,7 +94,6 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 		if (offset + ret > dio->i_size &&
 		    !(dio->flags & IOMAP_DIO_WRITE))
 			ret = dio->i_size - offset;
-		iocb->ki_pos += ret;
 	}
 
 	/*
@@ -120,19 +119,21 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	}
 
 	inode_dio_end(file_inode(iocb->ki_filp));
-	/*
-	 * If this is a DSYNC write, make sure we push it to stable storage now
-	 * that we've written data.
-	 */
-	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
-		ret = generic_write_sync(iocb, ret);
 
-	if (ret > 0)
-		ret += dio->done_before;
+	if (ret > 0) {
+		iocb->ki_pos += ret;
 
+		/*
+		 * If this is a DSYNC write, make sure we push it to stable
+		 * storage now that we've written data.
+		 */
+		if (dio->flags & IOMAP_DIO_NEED_SYNC)
+			ret = generic_write_sync(iocb, ret);
+		if (ret > 0)
+			ret += dio->done_before;
+	}
 	trace_iomap_dio_complete(iocb, dio->error, ret);
 	kfree(dio);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_dio_complete);
-- 
2.39.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH 3/8] filemap: update ki_pos in generic_perform_write

[Christoph Hellwig]

All callers of generic_perform_write need to updated ki_pos, move it into
common code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/ceph/file.c | 2 --
 fs/ext4/file.c | 9 +++------
 fs/f2fs/file.c | 1 -
 fs/nfs/file.c  | 1 -
 mm/filemap.c   | 8 ++++----
 5 files changed, 7 insertions(+), 14 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index c8ef72f723badd..767f4dfe7def64 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1891,8 +1891,6 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		 * can not run at the same time
 		 */
 		written = generic_perform_write(iocb, from);
-		if (likely(written >= 0))
-			iocb->ki_pos = pos + written;
 		ceph_end_io_write(inode);
 	}
 
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index bc430270c23c19..ea0ada3985cba2 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -289,12 +289,9 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
 
 out:
 	inode_unlock(inode);
-	if (likely(ret > 0)) {
-		iocb->ki_pos += ret;
-		ret = generic_write_sync(iocb, ret);
-	}
-
-	return ret;
+	if (unlikely(ret <= 0))
+		return ret;
+	return generic_write_sync(iocb, ret);
 }
 
 static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 4f423d367a44b9..7134fe8bd008cb 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -4520,7 +4520,6 @@ static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb,
 	ret = generic_perform_write(iocb, from);
 
 	if (ret > 0) {
-		iocb->ki_pos += ret;
 		f2fs_update_iostat(F2FS_I_SB(inode), inode,
 						APP_BUFFERED_IO, ret);
 	}
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 665ce3fc62eaf4..e8bb4c48a3210a 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -655,7 +655,6 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 		goto out;
 
 	written = result;
-	iocb->ki_pos += written;
 	nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
 
 	if (mntflags & NFS_MOUNT_WRITE_EAGER) {
diff --git a/mm/filemap.c b/mm/filemap.c
index 33b54660ad2b39..15907af4a57ff5 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3957,7 +3957,10 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
 		balance_dirty_pages_ratelimited(mapping);
 	} while (iov_iter_count(i));
 
-	return written ? written : status;
+	if (!written)
+		return status;
+	iocb->ki_pos += written;
+	return written;
 }
 EXPORT_SYMBOL(generic_perform_write);
 
@@ -4034,7 +4037,6 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		endbyte = pos + status - 1;
 		err = filemap_write_and_wait_range(mapping, pos, endbyte);
 		if (err == 0) {
-			iocb->ki_pos = endbyte + 1;
 			written += status;
 			invalidate_mapping_pages(mapping,
 						 pos >> PAGE_SHIFT,
@@ -4047,8 +4049,6 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		}
 	} else {
 		written = generic_perform_write(iocb, from);
-		if (likely(written > 0))
-			iocb->ki_pos += written;
 	}
 out:
 	return written ? written : err;
-- 
2.39.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH 4/8] filemap: add a kiocb_write_and_wait helper

[Christoph Hellwig]

Factor out a helper that does filemap_write_and_wait_range for the range
covered by a read kiocb, or returns -EAGAIN if the kiocb is marked as
nowait and there would be pages to write.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Darrick J. Wong <djwong@kernel.org>
---
 block/fops.c            | 18 +++---------------
 include/linux/pagemap.h |  2 ++
 mm/filemap.c            | 30 ++++++++++++++++++------------
 3 files changed, 23 insertions(+), 27 deletions(-)

diff --git a/block/fops.c b/block/fops.c
index 58d0aebc7313a8..575171049c5d83 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -576,21 +576,9 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		goto reexpand; /* skip atime */
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
-		struct address_space *mapping = iocb->ki_filp->f_mapping;
-
-		if (iocb->ki_flags & IOCB_NOWAIT) {
-			if (filemap_range_needs_writeback(mapping, pos,
-							  pos + count - 1)) {
-				ret = -EAGAIN;
-				goto reexpand;
-			}
-		} else {
-			ret = filemap_write_and_wait_range(mapping, pos,
-							   pos + count - 1);
-			if (ret < 0)
-				goto reexpand;
-		}
-
+		ret = kiocb_write_and_wait(iocb, count);
+		if (ret < 0)
+			goto reexpand;
 		file_accessed(iocb->ki_filp);
 
 		ret = blkdev_direct_IO(iocb, to);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index a56308a9d1a450..36fc2cea13ce20 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -30,6 +30,7 @@ static inline void invalidate_remote_inode(struct inode *inode)
 int invalidate_inode_pages2(struct address_space *mapping);
 int invalidate_inode_pages2_range(struct address_space *mapping,
 		pgoff_t start, pgoff_t end);
+
 int write_inode_now(struct inode *, int sync);
 int filemap_fdatawrite(struct address_space *);
 int filemap_flush(struct address_space *);
@@ -54,6 +55,7 @@ int filemap_check_errors(struct address_space *mapping);
 void __filemap_set_wb_err(struct address_space *mapping, int err);
 int filemap_fdatawrite_wbc(struct address_space *mapping,
 			   struct writeback_control *wbc);
+int kiocb_write_and_wait(struct kiocb *iocb, size_t count);
 
 static inline int filemap_write_and_wait(struct address_space *mapping)
 {
diff --git a/mm/filemap.c b/mm/filemap.c
index 15907af4a57ff5..5fcd5227f9cae2 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2762,6 +2762,21 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(filemap_read);
 
+int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
+{
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
+	loff_t pos = iocb->ki_pos;
+	loff_t end = pos + count - 1;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (filemap_range_needs_writeback(mapping, pos, end))
+			return -EAGAIN;
+		return 0;
+	}
+
+	return filemap_write_and_wait_range(mapping, pos, end);
+}
+
 /**
  * generic_file_read_iter - generic filesystem read routine
  * @iocb:	kernel I/O control block
@@ -2797,18 +2812,9 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 		struct address_space *mapping = file->f_mapping;
 		struct inode *inode = mapping->host;
 
-		if (iocb->ki_flags & IOCB_NOWAIT) {
-			if (filemap_range_needs_writeback(mapping, iocb->ki_pos,
-						iocb->ki_pos + count - 1))
-				return -EAGAIN;
-		} else {
-			retval = filemap_write_and_wait_range(mapping,
-						iocb->ki_pos,
-					        iocb->ki_pos + count - 1);
-			if (retval < 0)
-				return retval;
-		}
-
+		retval = kiocb_write_and_wait(iocb, count);
+		if (retval < 0)
+			return retval;
 		file_accessed(file);
 
 		retval = mapping->a_ops->direct_IO(iocb, iter);
-- 
2.39.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH 5/8] filemap: add a kiocb_invalidate_pages helper

[Christoph Hellwig]

Factor out a helper that calls filemap_write_and_wait_range and
invalidate_inode_pages2_range for the range covered by a write kiocb or
returns -EAGAIN if the kiocb is marked as nowait and there would be pages
to write or invalidate.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Darrick J. Wong <djwong@kernel.org>
---
 include/linux/pagemap.h |  1 +
 mm/filemap.c            | 48 ++++++++++++++++++++++++-----------------
 2 files changed, 29 insertions(+), 20 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 36fc2cea13ce20..6e4c9ee40baa99 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -30,6 +30,7 @@ static inline void invalidate_remote_inode(struct inode *inode)
 int invalidate_inode_pages2(struct address_space *mapping);
 int invalidate_inode_pages2_range(struct address_space *mapping,
 		pgoff_t start, pgoff_t end);
+int kiocb_invalidate_pages(struct kiocb *iocb, size_t count);
 
 int write_inode_now(struct inode *, int sync);
 int filemap_fdatawrite(struct address_space *);
diff --git a/mm/filemap.c b/mm/filemap.c
index 5fcd5227f9cae2..a1cb01a4b8046a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2777,6 +2777,33 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
 	return filemap_write_and_wait_range(mapping, pos, end);
 }
 
+int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
+{
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
+	loff_t pos = iocb->ki_pos;
+	loff_t end = pos + count - 1;
+	int ret;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		/* we could block if there are any pages in the range */
+		if (filemap_range_has_page(mapping, pos, end))
+			return -EAGAIN;
+	} else {
+		ret = filemap_write_and_wait_range(mapping, pos, end);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * After a write we want buffered reads to be sure to go to disk to get
+	 * the new data.  We invalidate clean cached page from the region we're
+	 * about to write.  We do this *before* the write so that we can return
+	 * without clobbering -EIOCBQUEUED from ->direct_IO().
+	 */
+	return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
+					     end >> PAGE_SHIFT);
+}
+
 /**
  * generic_file_read_iter - generic filesystem read routine
  * @iocb:	kernel I/O control block
@@ -3820,30 +3847,11 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	write_len = iov_iter_count(from);
 	end = (pos + write_len - 1) >> PAGE_SHIFT;
 
-	if (iocb->ki_flags & IOCB_NOWAIT) {
-		/* If there are pages to writeback, return */
-		if (filemap_range_has_page(file->f_mapping, pos,
-					   pos + write_len - 1))
-			return -EAGAIN;
-	} else {
-		written = filemap_write_and_wait_range(mapping, pos,
-							pos + write_len - 1);
-		if (written)
-			goto out;
-	}
-
-	/*
-	 * After a write we want buffered reads to be sure to go to disk to get
-	 * the new data.  We invalidate clean cached page from the region we're
-	 * about to write.  We do this *before* the write so that we can return
-	 * without clobbering -EIOCBQUEUED from ->direct_IO().
-	 */
-	written = invalidate_inode_pages2_range(mapping,
-					pos >> PAGE_SHIFT, end);
 	/*
 	 * If a page can not be invalidated, return 0 to fall back
 	 * to buffered write.
 	 */
+	written = kiocb_invalidate_pages(iocb, write_len);
 	if (written) {
 		if (written == -EBUSY)
 			return 0;
-- 
2.39.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH 6/8] filemap: add a kiocb_invalidate_post_direct_write helper

[Christoph Hellwig]

Add a helper to invalidate page cache after a dio write.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/direct-io.c          | 10 ++--------
 fs/iomap/direct-io.c    | 12 ++----------
 include/linux/fs.h      |  5 -----
 include/linux/pagemap.h |  1 +
 mm/filemap.c            | 37 ++++++++++++++++++++-----------------
 5 files changed, 25 insertions(+), 40 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0b380bb8a81e11..4f9069aee0fe19 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -285,14 +285,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
 	 * zeros from unwritten extents.
 	 */
 	if (flags & DIO_COMPLETE_INVALIDATE &&
-	    ret > 0 && dio_op == REQ_OP_WRITE &&
-	    dio->inode->i_mapping->nrpages) {
-		err = invalidate_inode_pages2_range(dio->inode->i_mapping,
-					offset >> PAGE_SHIFT,
-					(offset + ret - 1) >> PAGE_SHIFT);
-		if (err)
-			dio_warn_stale_pagecache(dio->iocb->ki_filp);
-	}
+	    ret > 0 && dio_op == REQ_OP_WRITE)
+		kiocb_invalidate_post_direct_write(dio->iocb, ret);
 
 	inode_dio_end(dio->inode);
 
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 6207a59d2162e1..0795c54a745bca 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -81,7 +81,6 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
-	struct inode *inode = file_inode(iocb->ki_filp);
 	loff_t offset = iocb->ki_pos;
 	ssize_t ret = dio->error;
 
@@ -108,15 +107,8 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * ->end_io() when necessary, otherwise a racing buffer read would cache
 	 * zeros from unwritten extents.
 	 */
-	if (!dio->error && dio->size &&
-	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
-		int err;
-		err = invalidate_inode_pages2_range(inode->i_mapping,
-				offset >> PAGE_SHIFT,
-				(offset + dio->size - 1) >> PAGE_SHIFT);
-		if (err)
-			dio_warn_stale_pagecache(iocb->ki_filp);
-	}
+	if (!dio->error && dio->size && (dio->flags & IOMAP_DIO_WRITE))
+		kiocb_invalidate_post_direct_write(iocb, dio->size);
 
 	inode_dio_end(file_inode(iocb->ki_filp));
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 133f0640fb2411..91021b4e1f6f48 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2837,11 +2837,6 @@ static inline void inode_dio_end(struct inode *inode)
 		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
 }
 
-/*
- * Warn about a page cache invalidation failure diring a direct I/O write.
- */
-void dio_warn_stale_pagecache(struct file *filp);
-
 extern void inode_set_flags(struct inode *inode, unsigned int flags,
 			    unsigned int mask);
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 6e4c9ee40baa99..6ecc4aaf5e3d51 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -31,6 +31,7 @@ int invalidate_inode_pages2(struct address_space *mapping);
 int invalidate_inode_pages2_range(struct address_space *mapping,
 		pgoff_t start, pgoff_t end);
 int kiocb_invalidate_pages(struct kiocb *iocb, size_t count);
+void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count);
 
 int write_inode_now(struct inode *, int sync);
 int filemap_fdatawrite(struct address_space *);
diff --git a/mm/filemap.c b/mm/filemap.c
index a1cb01a4b8046a..ddb6f8aa86d6ca 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3816,7 +3816,7 @@ EXPORT_SYMBOL(read_cache_page_gfp);
 /*
  * Warn about a page cache invalidation failure during a direct I/O write.
  */
-void dio_warn_stale_pagecache(struct file *filp)
+static void dio_warn_stale_pagecache(struct file *filp)
 {
 	static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
 	char pathname[128];
@@ -3833,19 +3833,23 @@ void dio_warn_stale_pagecache(struct file *filp)
 	}
 }
 
+void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count)
+{
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
+
+	if (mapping->nrpages &&
+	    invalidate_inode_pages2_range(mapping,
+			iocb->ki_pos >> PAGE_SHIFT,
+			(iocb->ki_pos + count - 1) >> PAGE_SHIFT))
+		dio_warn_stale_pagecache(iocb->ki_filp);
+}
+
 ssize_t
 generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
-	struct file	*file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode	*inode = mapping->host;
-	loff_t		pos = iocb->ki_pos;
-	ssize_t		written;
-	size_t		write_len;
-	pgoff_t		end;
-
-	write_len = iov_iter_count(from);
-	end = (pos + write_len - 1) >> PAGE_SHIFT;
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
+	size_t write_len = iov_iter_count(from);
+	ssize_t written;
 
 	/*
 	 * If a page can not be invalidated, return 0 to fall back
@@ -3855,7 +3859,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (written) {
 		if (written == -EBUSY)
 			return 0;
-		goto out;
+		return written;
 	}
 
 	written = mapping->a_ops->direct_IO(iocb, from);
@@ -3877,11 +3881,11 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	 *
 	 * Skip invalidation for async writes or if mapping has no pages.
 	 */
-	if (written > 0 && mapping->nrpages &&
-	    invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end))
-		dio_warn_stale_pagecache(file);
-
 	if (written > 0) {
+		struct inode *inode = mapping->host;
+		loff_t pos = iocb->ki_pos;
+
+		kiocb_invalidate_post_direct_write(iocb, written);
 		pos += written;
 		write_len -= written;
 		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
@@ -3892,7 +3896,6 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	}
 	if (written != -EIOCBQUEUED)
 		iov_iter_revert(from, write_len - iov_iter_count(from));
-out:
 	return written;
 }
 EXPORT_SYMBOL(generic_file_direct_write);
-- 
2.39.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH 7/8] iomap: update ki_pos in iomap_file_buffered_write

[Christoph Hellwig]

All callers of iomap_file_buffered_write need to updated ki_pos, move it
into common code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Acked-by: Damien Le Moal <dlemoal@kernel.org>
---
 fs/gfs2/file.c         | 4 +---
 fs/iomap/buffered-io.c | 9 ++++++---
 fs/xfs/xfs_file.c      | 2 --
 fs/zonefs/file.c       | 4 +---
 4 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 904a0d6ac1a1a9..c6a7555d5ad8bb 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1044,10 +1044,8 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb,
 	pagefault_disable();
 	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
 	pagefault_enable();
-	if (ret > 0) {
-		iocb->ki_pos += ret;
+	if (ret > 0)
 		written += ret;
-	}
 
 	if (inode == sdp->sd_rindex)
 		gfs2_glock_dq_uninit(statfs_gh);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 063133ec77f49e..550525a525c45c 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -864,16 +864,19 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
 		.len		= iov_iter_count(i),
 		.flags		= IOMAP_WRITE,
 	};
-	int ret;
+	ssize_t ret;
 
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		iter.flags |= IOMAP_NOWAIT;
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
 		iter.processed = iomap_write_iter(&iter, i);
-	if (iter.pos == iocb->ki_pos)
+
+	if (unlikely(ret < 0))
 		return ret;
-	return iter.pos - iocb->ki_pos;
+	ret = iter.pos - iocb->ki_pos;
+	iocb->ki_pos += ret;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 431c3fd0e2b598..d57443db633637 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -720,8 +720,6 @@ xfs_file_buffered_write(
 	trace_xfs_file_buffered_write(iocb, from);
 	ret = iomap_file_buffered_write(iocb, from,
 			&xfs_buffered_write_iomap_ops);
-	if (likely(ret >= 0))
-		iocb->ki_pos += ret;
 
 	/*
 	 * If we hit a space limit, try to free up some lingering preallocated
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index 132f01d3461f14..e212d0636f848e 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -643,9 +643,7 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
 		goto inode_unlock;
 
 	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
-	if (ret > 0)
-		iocb->ki_pos += ret;
-	else if (ret == -EIO)
+	if (ret == -EIO)
 		zonefs_io_error(inode, true);
 
 inode_unlock:
-- 
2.39.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH 8/8] iomap: use kiocb_write_and_wait and kiocb_invalidate_pages

[Christoph Hellwig]

Use the common helpers for direct I/O page invalidation instead of
open coding the logic.  This leads to a slight reordering of checks
in __iomap_dio_rw to keep the logic straight.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/iomap/direct-io.c | 55 ++++++++++++++++----------------------------
 1 file changed, 20 insertions(+), 35 deletions(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 0795c54a745bca..6bd14691f96e07 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -472,7 +472,6 @@ __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, void *private, size_t done_before)
 {
-	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct iomap_iter iomi = {
 		.inode		= inode,
@@ -481,11 +480,11 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		.flags		= IOMAP_DIRECT,
 		.private	= private,
 	};
-	loff_t end = iomi.pos + iomi.len - 1, ret = 0;
 	bool wait_for_completion =
 		is_sync_kiocb(iocb) || (dio_flags & IOMAP_DIO_FORCE_WAIT);
 	struct blk_plug plug;
 	struct iomap_dio *dio;
+	loff_t ret = 0;
 
 	trace_iomap_dio_rw_begin(iocb, iter, dio_flags, done_before);
 
@@ -509,31 +508,29 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->submit.waiter = current;
 	dio->submit.poll_bio = NULL;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		iomi.flags |= IOMAP_NOWAIT;
+
 	if (iov_iter_rw(iter) == READ) {
 		if (iomi.pos >= dio->i_size)
 			goto out_free_dio;
 
-		if (iocb->ki_flags & IOCB_NOWAIT) {
-			if (filemap_range_needs_writeback(mapping, iomi.pos,
-					end)) {
-				ret = -EAGAIN;
-				goto out_free_dio;
-			}
-			iomi.flags |= IOMAP_NOWAIT;
-		}
-
 		if (user_backed_iter(iter))
 			dio->flags |= IOMAP_DIO_DIRTY;
+
+		ret = kiocb_write_and_wait(iocb, iomi.len);
+		if (ret)
+			goto out_free_dio;
 	} else {
 		iomi.flags |= IOMAP_WRITE;
 		dio->flags |= IOMAP_DIO_WRITE;
 
-		if (iocb->ki_flags & IOCB_NOWAIT) {
-			if (filemap_range_has_page(mapping, iomi.pos, end)) {
-				ret = -EAGAIN;
+		if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) {
+			ret = -EAGAIN;
+			if (iomi.pos >= dio->i_size ||
+			    iomi.pos + iomi.len > dio->i_size)
 				goto out_free_dio;
-			}
-			iomi.flags |= IOMAP_NOWAIT;
+			iomi.flags |= IOMAP_OVERWRITE_ONLY;
 		}
 
 		/* for data sync or sync, we need sync completion processing */
@@ -549,31 +546,19 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			if (!(iocb->ki_flags & IOCB_SYNC))
 				dio->flags |= IOMAP_DIO_WRITE_FUA;
 		}
-	}
-
-	if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) {
-		ret = -EAGAIN;
-		if (iomi.pos >= dio->i_size ||
-		    iomi.pos + iomi.len > dio->i_size)
-			goto out_free_dio;
-		iomi.flags |= IOMAP_OVERWRITE_ONLY;
-	}
 
-	ret = filemap_write_and_wait_range(mapping, iomi.pos, end);
-	if (ret)
-		goto out_free_dio;
-
-	if (iov_iter_rw(iter) == WRITE) {
 		/*
 		 * Try to invalidate cache pages for the range we are writing.
 		 * If this invalidation fails, let the caller fall back to
 		 * buffered I/O.
 		 */
-		if (invalidate_inode_pages2_range(mapping,
-				iomi.pos >> PAGE_SHIFT, end >> PAGE_SHIFT)) {
-			trace_iomap_dio_invalidate_fail(inode, iomi.pos,
-							iomi.len);
-			ret = -ENOTBLK;
+		ret = kiocb_invalidate_pages(iocb, iomi.len);
+		if (ret) {
+			if (ret != -EAGAIN) {
+				trace_iomap_dio_invalidate_fail(inode, iomi.pos,
+								iomi.len);
+				ret = -ENOTBLK;
+			}
 			goto out_free_dio;
 		}
 
-- 
2.39.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel