From fa6c46e7c271f155c9ba3ba3457175c0a71eb918 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 22 May 2023 14:50:05 +0100
Subject: ext4: Provide a splice-read wrapper

Provide a splice_read wrapper for Ext4.  This does the inode shutdown check
before proceeding.  Splicing from DAX files and O_DIRECT fds is handled by
the caller.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Theodore Ts'o <tytso@mit.edu>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Andreas Dilger <adilger.kernel@dilger.ca>
cc: linux-ext4@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-block@vger.kernel.org
cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20230522135018.2742245-19-dhowells@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/ext4/file.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'fs/ext4/file.c')

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d101b3b0c7da..9f8bbd9d131c 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -147,6 +147,17 @@ static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	return generic_file_read_iter(iocb, to);
 }
 
+static ssize_t ext4_file_splice_read(struct file *in, loff_t *ppos,
+				     struct pipe_inode_info *pipe,
+				     size_t len, unsigned int flags)
+{
+	struct inode *inode = file_inode(in);
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+	return generic_file_splice_read(in, ppos, pipe, len, flags);
+}
+
 /*
  * Called when an inode is released. Note that this is different
  * from ext4_file_open: open gets called at every open, but release
@@ -957,7 +968,7 @@ const struct file_operations ext4_file_operations = {
 	.release	= ext4_release_file,
 	.fsync		= ext4_sync_file,
 	.get_unmapped_area = thp_get_unmapped_area,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= ext4_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ext4_fallocate,
 };
-- 
cgit v1.2.3


From 2cb1e08985e3dc59d0a4ebf770a87e3e2410d985 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 22 May 2023 14:50:15 +0100
Subject: splice: Use filemap_splice_read() instead of
 generic_file_splice_read()

Replace pointers to generic_file_splice_read() with calls to
filemap_splice_read().

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christian Brauner <brauner@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: David Hildenbrand <david@redhat.com>
cc: John Hubbard <jhubbard@nvidia.com>
cc: linux-mm@kvack.org
cc: linux-block@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
Link: https://lore.kernel.org/r/20230522135018.2742245-29-dhowells@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/fops.c            | 2 +-
 fs/adfs/file.c          | 2 +-
 fs/affs/file.c          | 2 +-
 fs/afs/file.c           | 2 +-
 fs/bfs/file.c           | 2 +-
 fs/btrfs/file.c         | 2 +-
 fs/cramfs/inode.c       | 2 +-
 fs/ecryptfs/file.c      | 4 ++--
 fs/erofs/data.c         | 2 +-
 fs/exfat/file.c         | 2 +-
 fs/ext2/file.c          | 2 +-
 fs/ext4/file.c          | 2 +-
 fs/fat/file.c           | 2 +-
 fs/fuse/file.c          | 2 +-
 fs/gfs2/file.c          | 4 ++--
 fs/hfs/inode.c          | 2 +-
 fs/hfsplus/inode.c      | 2 +-
 fs/hostfs/hostfs_kern.c | 2 +-
 fs/hpfs/file.c          | 2 +-
 fs/jffs2/file.c         | 2 +-
 fs/jfs/file.c           | 2 +-
 fs/minix/file.c         | 2 +-
 fs/nilfs2/file.c        | 2 +-
 fs/ntfs/file.c          | 2 +-
 fs/ntfs3/file.c         | 2 +-
 fs/ocfs2/file.c         | 2 +-
 fs/omfs/file.c          | 2 +-
 fs/ramfs/file-mmu.c     | 2 +-
 fs/ramfs/file-nommu.c   | 2 +-
 fs/read_write.c         | 2 +-
 fs/reiserfs/file.c      | 2 +-
 fs/romfs/mmap-nommu.c   | 2 +-
 fs/sysv/file.c          | 2 +-
 fs/ubifs/file.c         | 2 +-
 fs/udf/file.c           | 2 +-
 fs/ufs/file.c           | 2 +-
 fs/vboxsf/file.c        | 2 +-
 37 files changed, 39 insertions(+), 39 deletions(-)

(limited to 'fs/ext4/file.c')

diff --git a/block/fops.c b/block/fops.c
index d2e6be4e3d1c..6c9aa028af6e 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -691,7 +691,7 @@ const struct file_operations def_blk_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= compat_blkdev_ioctl,
 #endif
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= blkdev_fallocate,
 };
diff --git a/fs/adfs/file.c b/fs/adfs/file.c
index 754afb14a6ff..ee80718aaeec 100644
--- a/fs/adfs/file.c
+++ b/fs/adfs/file.c
@@ -28,7 +28,7 @@ const struct file_operations adfs_file_operations = {
 	.mmap		= generic_file_mmap,
 	.fsync		= generic_file_fsync,
 	.write_iter	= generic_file_write_iter,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
 
 const struct inode_operations adfs_file_inode_operations = {
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 8daeed31e1af..e43f2f007ac1 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -1001,7 +1001,7 @@ const struct file_operations affs_file_operations = {
 	.open		= affs_file_open,
 	.release	= affs_file_release,
 	.fsync		= affs_file_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
 
 const struct inode_operations affs_file_inode_operations = {
diff --git a/fs/afs/file.c b/fs/afs/file.c
index d8a6b09dadf7..d37dd201752b 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -603,5 +603,5 @@ static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos,
 	if (ret < 0)
 		return ret;
 
-	return generic_file_splice_read(in, ppos, pipe, len, flags);
+	return filemap_splice_read(in, ppos, pipe, len, flags);
 }
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index 57ae5ee6deec..adc2230079c6 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -27,7 +27,7 @@ const struct file_operations bfs_file_operations = {
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
 
 static int bfs_move_block(unsigned long from, unsigned long to,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f649647392e0..71426c6408fa 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3825,7 +3825,7 @@ static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 const struct file_operations btrfs_file_operations = {
 	.llseek		= btrfs_file_llseek,
 	.read_iter      = btrfs_file_read_iter,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.write_iter	= btrfs_file_write_iter,
 	.splice_write	= iter_file_splice_write,
 	.mmap		= btrfs_file_mmap,
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 006ef68d7ff6..27c6597aa1be 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -473,7 +473,7 @@ static unsigned int cramfs_physmem_mmap_capabilities(struct file *file)
 static const struct file_operations cramfs_physmem_fops = {
 	.llseek			= generic_file_llseek,
 	.read_iter		= generic_file_read_iter,
-	.splice_read		= generic_file_splice_read,
+	.splice_read		= filemap_splice_read,
 	.mmap			= cramfs_physmem_mmap,
 #ifndef CONFIG_MMU
 	.get_unmapped_area	= cramfs_physmem_get_unmapped_area,
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 284395587be0..ce0a3c5ed0ca 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -47,7 +47,7 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
 /*
  * ecryptfs_splice_read_update_atime
  *
- * generic_file_splice_read updates the atime of upper layer inode.  But, it
+ * filemap_splice_read updates the atime of upper layer inode.  But, it
  * doesn't give us a chance to update the atime of the lower layer inode.  This
  * function is a wrapper to generic_file_read.  It updates the atime of the
  * lower level inode if generic_file_read returns without any errors. This is
@@ -61,7 +61,7 @@ static ssize_t ecryptfs_splice_read_update_atime(struct file *in, loff_t *ppos,
 	ssize_t rc;
 	const struct path *path;
 
-	rc = generic_file_splice_read(in, ppos, pipe, len, flags);
+	rc = filemap_splice_read(in, ppos, pipe, len, flags);
 	if (rc >= 0) {
 		path = ecryptfs_dentry_to_lower_path(in->f_path.dentry);
 		touch_atime(path);
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 6fe9a779fa91..db5e4b7636ec 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -448,5 +448,5 @@ const struct file_operations erofs_file_fops = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= erofs_file_read_iter,
 	.mmap		= erofs_file_mmap,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index e99183a74611..3cbd270e0cba 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -389,7 +389,7 @@ const struct file_operations exfat_file_operations = {
 #endif
 	.mmap		= generic_file_mmap,
 	.fsync		= exfat_file_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 };
 
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 6b4bebe982ca..d1ae0f0a3726 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -192,7 +192,7 @@ const struct file_operations ext2_file_operations = {
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,
 	.get_unmapped_area = thp_get_unmapped_area,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 };
 
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 9f8bbd9d131c..e8261900f4f3 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -155,7 +155,7 @@ static ssize_t ext4_file_splice_read(struct file *in, loff_t *ppos,
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
-	return generic_file_splice_read(in, ppos, pipe, len, flags);
+	return filemap_splice_read(in, ppos, pipe, len, flags);
 }
 
 /*
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 795a4fad5c40..456477946dd9 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -209,7 +209,7 @@ const struct file_operations fat_file_operations = {
 	.unlocked_ioctl	= fat_generic_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
 	.fsync		= fat_file_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= fat_fallocate,
 };
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 89d97f6188e0..4553124f5406 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -3252,7 +3252,7 @@ static const struct file_operations fuse_file_operations = {
 	.lock		= fuse_file_lock,
 	.get_unmapped_area = thp_get_unmapped_area,
 	.flock		= fuse_file_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.unlocked_ioctl	= fuse_file_ioctl,
 	.compat_ioctl	= fuse_file_compat_ioctl,
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 300844f50dcd..0f5ad5165361 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1568,7 +1568,7 @@ const struct file_operations gfs2_file_fops = {
 	.fsync		= gfs2_fsync,
 	.lock		= gfs2_lock,
 	.flock		= gfs2_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= gfs2_file_splice_write,
 	.setlease	= simple_nosetlease,
 	.fallocate	= gfs2_fallocate,
@@ -1599,7 +1599,7 @@ const struct file_operations gfs2_file_fops_nolock = {
 	.open		= gfs2_open,
 	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= gfs2_file_splice_write,
 	.setlease	= generic_setlease,
 	.fallocate	= gfs2_fallocate,
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 1f7bd068acf0..441d7fc952e3 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -694,7 +694,7 @@ static const struct file_operations hfs_file_operations = {
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.fsync		= hfs_file_fsync,
 	.open		= hfs_file_open,
 	.release	= hfs_file_release,
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index b21660475ac1..7d1a675e037d 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -372,7 +372,7 @@ static const struct file_operations hfsplus_file_operations = {
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.fsync		= hfsplus_file_fsync,
 	.open		= hfsplus_file_open,
 	.release	= hfsplus_file_release,
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 28b4f15c19eb..87998df499f4 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -381,7 +381,7 @@ static int hostfs_fsync(struct file *file, loff_t start, loff_t end,
 
 static const struct file_operations hostfs_file_fops = {
 	.llseek		= generic_file_llseek,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 88952d4a631e..1bb8d97cd9ae 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -259,7 +259,7 @@ const struct file_operations hpfs_file_ops =
 	.mmap		= generic_file_mmap,
 	.release	= hpfs_file_release,
 	.fsync		= hpfs_file_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.unlocked_ioctl	= hpfs_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
 };
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 96b0275ce957..2345ca3f09ee 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -56,7 +56,7 @@ const struct file_operations jffs2_file_operations =
 	.unlocked_ioctl=jffs2_ioctl,
 	.mmap =		generic_file_readonly_mmap,
 	.fsync =	jffs2_fsync,
-	.splice_read =	generic_file_splice_read,
+	.splice_read =	filemap_splice_read,
 	.splice_write = iter_file_splice_write,
 };
 
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index 2ee35be49de1..01b6912e60f8 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -144,7 +144,7 @@ const struct file_operations jfs_file_operations = {
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fsync		= jfs_fsync,
 	.release	= jfs_release,
diff --git a/fs/minix/file.c b/fs/minix/file.c
index 0dd05d47724a..906d192ab7f3 100644
--- a/fs/minix/file.c
+++ b/fs/minix/file.c
@@ -19,7 +19,7 @@ const struct file_operations minix_file_operations = {
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= generic_file_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
 
 static int minix_setattr(struct mnt_idmap *idmap,
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index a265d391ffe9..a9eb3487efb2 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -140,7 +140,7 @@ const struct file_operations nilfs_file_operations = {
 	.open		= generic_file_open,
 	/* .release	= nilfs_release_file, */
 	.fsync		= nilfs_sync_file,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write   = iter_file_splice_write,
 };
 
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index c481b14e4fd9..e5e0ed58670b 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1992,7 +1992,7 @@ const struct file_operations ntfs_file_ops = {
 #endif /* NTFS_RW */
 	.mmap		= generic_file_mmap,
 	.open		= ntfs_file_open,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
 
 const struct inode_operations ntfs_file_inode_ops = {
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 667c9dc68b58..036efd85f60c 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -770,7 +770,7 @@ static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos,
 		return -EOPNOTSUPP;
 	}
 
-	return generic_file_splice_read(in, ppos, pipe, len, flags);
+	return filemap_splice_read(in, ppos, pipe, len, flags);
 }
 
 /*
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 86add13b5f23..42549fc81468 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2827,7 +2827,7 @@ const struct file_operations ocfs2_fops_no_plocks = {
 	.compat_ioctl   = ocfs2_compat_ioctl,
 #endif
 	.flock		= ocfs2_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
 	.remap_file_range = ocfs2_remap_file_range,
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 0101f1f87b56..de8f57ee39ec 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -334,7 +334,7 @@ const struct file_operations omfs_file_operations = {
 	.write_iter = generic_file_write_iter,
 	.mmap = generic_file_mmap,
 	.fsync = generic_file_fsync,
-	.splice_read = generic_file_splice_read,
+	.splice_read = filemap_splice_read,
 };
 
 static int omfs_setattr(struct mnt_idmap *idmap,
diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c
index 12af0490322f..c7a1aa3c882b 100644
--- a/fs/ramfs/file-mmu.c
+++ b/fs/ramfs/file-mmu.c
@@ -43,7 +43,7 @@ const struct file_operations ramfs_file_operations = {
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= noop_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.llseek		= generic_file_llseek,
 	.get_unmapped_area	= ramfs_mmu_get_unmapped_area,
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 9fbb9b5256f7..efb1b4c1a0a4 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -43,7 +43,7 @@ const struct file_operations ramfs_file_operations = {
 	.read_iter		= generic_file_read_iter,
 	.write_iter		= generic_file_write_iter,
 	.fsync			= noop_fsync,
-	.splice_read		= generic_file_splice_read,
+	.splice_read		= filemap_splice_read,
 	.splice_write		= iter_file_splice_write,
 	.llseek			= generic_file_llseek,
 };
diff --git a/fs/read_write.c b/fs/read_write.c
index a21ba3be7dbe..b07de77ef126 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -29,7 +29,7 @@ const struct file_operations generic_ro_fops = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
 	.mmap		= generic_file_readonly_mmap,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
 
 EXPORT_SYMBOL(generic_ro_fops);
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index b54cc7048f02..8eb3ad3e8ae9 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -247,7 +247,7 @@ const struct file_operations reiserfs_file_operations = {
 	.fsync = reiserfs_sync_file,
 	.read_iter = generic_file_read_iter,
 	.write_iter = generic_file_write_iter,
-	.splice_read = generic_file_splice_read,
+	.splice_read = filemap_splice_read,
 	.splice_write = iter_file_splice_write,
 	.llseek = generic_file_llseek,
 };
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index 4578dc45e50a..4520ca413867 100644
--- a/fs/romfs/mmap-nommu.c
+++ b/fs/romfs/mmap-nommu.c
@@ -78,7 +78,7 @@ static unsigned romfs_mmap_capabilities(struct file *file)
 const struct file_operations romfs_ro_fops = {
 	.llseek			= generic_file_llseek,
 	.read_iter		= generic_file_read_iter,
-	.splice_read		= generic_file_splice_read,
+	.splice_read		= filemap_splice_read,
 	.mmap			= romfs_mmap,
 	.get_unmapped_area	= romfs_get_unmapped_area,
 	.mmap_capabilities	= romfs_mmap_capabilities,
diff --git a/fs/sysv/file.c b/fs/sysv/file.c
index 50eb92557a0f..c645f60bdb7f 100644
--- a/fs/sysv/file.c
+++ b/fs/sysv/file.c
@@ -26,7 +26,7 @@ const struct file_operations sysv_file_operations = {
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= generic_file_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
 
 static int sysv_setattr(struct mnt_idmap *idmap,
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 979ab1d9d0c3..6738fe43040b 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1669,7 +1669,7 @@ const struct file_operations ubifs_file_operations = {
 	.mmap           = ubifs_file_mmap,
 	.fsync          = ubifs_fsync,
 	.unlocked_ioctl = ubifs_ioctl,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.open		= fscrypt_file_open,
 #ifdef CONFIG_COMPAT
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 8238f742377b..29daf5d5cb67 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -209,7 +209,7 @@ const struct file_operations udf_file_operations = {
 	.write_iter		= udf_file_write_iter,
 	.release		= udf_release_file,
 	.fsync			= generic_file_fsync,
-	.splice_read		= generic_file_splice_read,
+	.splice_read		= filemap_splice_read,
 	.splice_write		= iter_file_splice_write,
 	.llseek			= generic_file_llseek,
 };
diff --git a/fs/ufs/file.c b/fs/ufs/file.c
index 7e087581be7e..6558882a89ef 100644
--- a/fs/ufs/file.c
+++ b/fs/ufs/file.c
@@ -41,5 +41,5 @@ const struct file_operations ufs_file_operations = {
 	.mmap		= generic_file_mmap,
 	.open           = generic_file_open,
 	.fsync		= generic_file_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 };
diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c
index 572aa1c43b37..2307f8037efc 100644
--- a/fs/vboxsf/file.c
+++ b/fs/vboxsf/file.c
@@ -217,7 +217,7 @@ const struct file_operations vboxsf_reg_fops = {
 	.open = vboxsf_file_open,
 	.release = vboxsf_file_release,
 	.fsync = noop_fsync,
-	.splice_read = generic_file_splice_read,
+	.splice_read = filemap_splice_read,
 };
 
 const struct inode_operations vboxsf_reg_iops = {
-- 
cgit v1.2.3


From 0d625446d0a451a683a357799912b9e688629707 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 1 Jun 2023 16:58:53 +0200
Subject: backing_dev: remove current->backing_dev_info

Patch series "cleanup the filemap / direct I/O interaction", v4.

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.


This patch (of 12):

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.

Link: https://lkml.kernel.org/r/20230601145904.1385409-1-hch@lst.de
Link: https://lkml.kernel.org/r/20230601145904.1385409-2-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Acked-by: Theodore Ts'o <tytso@mit.edu>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Chao Yu <chao@kernel.org>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.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(-)

(limited to 'fs/ext4/file.c')

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f649647392e0..ecd43ab66fa6 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 f4d8bf7dec88..c8ef72f723ba 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1791,9 +1791,6 @@ retry_snap:
 	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 @@ out:
 		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 d101b3b0c7da..bc430270c23c 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 5ac53d2627d2..4f423d367a44 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 89d97f6188e0..97d435874b14 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 @@ writethrough:
 			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 300844f50dcd..904a0d6ac1a1 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1041,11 +1041,9 @@ retry:
 			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 f0edf5a36237..665ce3fc62ea 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 c481b14e4fd9..e296f804a9c4 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 9a3d55c367d9..86d16a2c8339 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 aede746541f8..431c3fd0e2b5 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -717,9 +717,6 @@ write_retry:
 	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 @@ write_retry:
 		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 eed5d65b8d1f..54780571fe9a 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 570bc8c3db87..0d371ed91a68 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3964,8 +3964,6 @@ 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;
@@ -4026,7 +4024,6 @@ 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);
-- 
cgit v1.2.3


From 182c25e9c157f37bd0ab5a82fe2417e2223df459 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 1 Jun 2023 16:58:55 +0200
Subject: filemap: update ki_pos in generic_perform_write

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

Link: https://lkml.kernel.org/r/20230601145904.1385409-4-hch@lst.de
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: Theodore Ts'o <tytso@mit.edu>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Chao Yu <chao@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.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(-)

(limited to 'fs/ext4/file.c')

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index c8ef72f723ba..767f4dfe7def 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1891,8 +1891,6 @@ retry_snap:
 		 * 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 bc430270c23c..ea0ada3985cb 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 4f423d367a44..7134fe8bd008 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 665ce3fc62ea..e8bb4c48a321 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 0d371ed91a68..3a80a69fa9fa 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3930,7 +3930,10 @@ again:
 		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);
 
@@ -4007,7 +4010,6 @@ 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,
@@ -4020,8 +4022,6 @@ 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;
-- 
cgit v1.2.3


From 310ee0902b8d9d0a13a5a13e94688a5863fa29c2 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 14 Mar 2023 09:07:59 -0400
Subject: ext4: allow concurrent unaligned dio overwrites

We've had reports of significant performance regression of sub-block
(unaligned) direct writes due to the added exclusivity restrictions
in ext4. The purpose of the exclusivity requirement for unaligned
direct writes is to avoid data corruption caused by unserialized
partial block zeroing in the iomap dio layer across overlapping
writes.

XFS has similar requirements for the same underlying reasons, yet
doesn't suffer the extreme performance regression that ext4 does.
The reason for this is that XFS utilizes IOMAP_DIO_OVERWRITE_ONLY
mode, which allows for optimistic submission of concurrent unaligned
I/O and kicks back writes that require partial block zeroing such
that they can be submitted in a safe, exclusive context. Since ext4
already performs most of these checks pre-submission, it can support
something similar without necessarily relying on the iomap flag and
associated retry mechanism.

Update the dio write submission path to allow concurrent submission
of unaligned direct writes that are purely overwrite and so will not
require block zeroing. To improve readability of the various related
checks, move the unaligned I/O handling down into
ext4_dio_write_checks(), where the dio draining and force wait logic
can immediately follow the locking requirement checks. Finally, the
IOMAP_DIO_OVERWRITE_ONLY flag is set to enable a warning check as a
precaution should the ext4 overwrite logic ever become inconsistent
with the zeroing expectations of iomap dio.

The performance improvement of sub-block direct write I/O is shown
in the following fio test on a 64xcpu guest vm:

Test: fio --name=test --ioengine=libaio --direct=1 --group_reporting
--overwrite=1 --thread --size=10G --filename=/mnt/fio
--readwrite=write --ramp_time=10s --runtime=60s --numjobs=8
--blocksize=2k --iodepth=256 --allow_file_create=0

v6.2:		write: IOPS=4328, BW=8724KiB/s
v6.2 (patched):	write: IOPS=801k, BW=1565MiB/s

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20230314130759.642710-1-bfoster@redhat.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/file.c | 86 +++++++++++++++++++++++++++++++---------------------------
 1 file changed, 46 insertions(+), 40 deletions(-)

(limited to 'fs/ext4/file.c')

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d101b3b0c7da..b18a63e8dbbc 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -444,13 +444,14 @@ static const struct iomap_dio_ops ext4_dio_write_ops = {
  */
 static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
 				     bool *ilock_shared, bool *extend,
-				     bool *unwritten)
+				     bool *unwritten, int *dio_flags)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	loff_t offset;
 	size_t count;
 	ssize_t ret;
+	bool overwrite, unaligned_io;
 
 restart:
 	ret = ext4_generic_write_checks(iocb, from);
@@ -459,16 +460,20 @@ restart:
 
 	offset = iocb->ki_pos;
 	count = ret;
-	if (ext4_extending_io(inode, offset, count))
-		*extend = true;
+
+	unaligned_io = ext4_unaligned_io(inode, from, offset);
+	*extend = ext4_extending_io(inode, offset, count);
+	overwrite = ext4_overwrite_io(inode, offset, count, unwritten);
+
 	/*
-	 * Determine whether the IO operation will overwrite allocated
-	 * and initialized blocks.
-	 * We need exclusive i_rwsem for changing security info
-	 * in file_modified().
+	 * Determine whether we need to upgrade to an exclusive lock. This is
+	 * required to change security info in file_modified(), for extending
+	 * I/O, any form of non-overwrite I/O, and unaligned I/O to unwritten
+	 * extents (as partial block zeroing may be required).
 	 */
-	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
-	     !ext4_overwrite_io(inode, offset, count, unwritten))) {
+	if (*ilock_shared &&
+	    ((!IS_NOSEC(inode) || *extend || !overwrite ||
+	     (unaligned_io && *unwritten)))) {
 		if (iocb->ki_flags & IOCB_NOWAIT) {
 			ret = -EAGAIN;
 			goto out;
@@ -479,6 +484,32 @@ restart:
 		goto restart;
 	}
 
+	/*
+	 * Now that locking is settled, determine dio flags and exclusivity
+	 * requirements. Unaligned writes are allowed under shared lock so long
+	 * as they are pure overwrites. Set the iomap overwrite only flag as an
+	 * added precaution in this case. Even though this is unnecessary, we
+	 * can detect and warn on unexpected -EAGAIN if an unsafe unaligned
+	 * write is ever submitted.
+	 *
+	 * Otherwise, concurrent unaligned writes risk data corruption due to
+	 * partial block zeroing in the dio layer, and so the I/O must occur
+	 * exclusively. The inode lock is already held exclusive if the write is
+	 * non-overwrite or extending, so drain all outstanding dio and set the
+	 * force wait dio flag.
+	 */
+	if (*ilock_shared && unaligned_io) {
+		*dio_flags = IOMAP_DIO_OVERWRITE_ONLY;
+	} else if (!*ilock_shared && (unaligned_io || *extend)) {
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
+		}
+		if (unaligned_io && (!overwrite || *unwritten))
+			inode_dio_wait(inode);
+		*dio_flags = IOMAP_DIO_FORCE_WAIT;
+	}
+
 	ret = file_modified(file);
 	if (ret < 0)
 		goto out;
@@ -500,17 +531,10 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	loff_t offset = iocb->ki_pos;
 	size_t count = iov_iter_count(from);
 	const struct iomap_ops *iomap_ops = &ext4_iomap_ops;
-	bool extend = false, unaligned_io = false, unwritten = false;
+	bool extend = false, unwritten = false;
 	bool ilock_shared = true;
+	int dio_flags = 0;
 
-	/*
-	 * We initially start with shared inode lock unless it is
-	 * unaligned IO which needs exclusive lock anyways.
-	 */
-	if (ext4_unaligned_io(inode, from, offset)) {
-		unaligned_io = true;
-		ilock_shared = false;
-	}
 	/*
 	 * Quick check here without any i_rwsem lock to see if it is extending
 	 * IO. A more reliable check is done in ext4_dio_write_checks() with
@@ -543,16 +567,11 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		return ext4_buffered_write_iter(iocb, from);
 	}
 
-	ret = ext4_dio_write_checks(iocb, from,
-				    &ilock_shared, &extend, &unwritten);
+	ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend,
+				    &unwritten, &dio_flags);
 	if (ret <= 0)
 		return ret;
 
-	/* if we're going to block and IOCB_NOWAIT is set, return -EAGAIN */
-	if ((iocb->ki_flags & IOCB_NOWAIT) && (unaligned_io || extend)) {
-		ret = -EAGAIN;
-		goto out;
-	}
 	/*
 	 * Make sure inline data cannot be created anymore since we are going
 	 * to allocate blocks for DIO. We know the inode does not have any
@@ -563,19 +582,6 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	offset = iocb->ki_pos;
 	count = ret;
 
-	/*
-	 * Unaligned direct IO must be serialized among each other as zeroing
-	 * of partial blocks of two competing unaligned IOs can result in data
-	 * corruption.
-	 *
-	 * So we make sure we don't allow any unaligned IO in flight.
-	 * For IOs where we need not wait (like unaligned non-AIO DIO),
-	 * below inode_dio_wait() may anyway become a no-op, since we start
-	 * with exclusive lock.
-	 */
-	if (unaligned_io)
-		inode_dio_wait(inode);
-
 	if (extend) {
 		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
 		if (IS_ERR(handle)) {
@@ -595,8 +601,8 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ilock_shared && !unwritten)
 		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,
-			   NULL, 0);
+			   dio_flags, NULL, 0);
+	WARN_ON_ONCE(ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT));
 	if (ret == -ENOTBLK)
 		ret = 0;
 
-- 
cgit v1.2.3