Currently various places test if direct IO is possible on a file by
checking for the existence of the direct_IO address space operation.
This is a poor choice, as the direct_IO operation may not be used - it is
only used if the generic_file_*_iter functions are called for direct IO
and some filesystems - particularly NFS - don't do this.
Instead, introduce a new f_mode flag: FMODE_CAN_ODIRECT and change the
various places to check this (avoiding pointer dereferences).
do_dentry_open() will set this flag if ->direct_IO is present, so
filesystems do not need to be changed.
NFS *is* changed, to set the flag explicitly and discard the direct_IO
entry in the address_space_operations for files.
Signed-off-by: NeilBrown <[email protected]>
---
drivers/block/loop.c | 4 ++--
fs/fcntl.c | 9 ++++-----
fs/nfs/file.c | 3 ++-
fs/open.c | 9 ++++-----
fs/overlayfs/file.c | 13 ++++---------
include/linux/fs.h | 3 +++
6 files changed, 19 insertions(+), 22 deletions(-)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 01cbbfc4e9e2..a2609dd79370 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -184,8 +184,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
*/
if (dio) {
if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
- !(lo->lo_offset & dio_align) &&
- mapping->a_ops->direct_IO)
+ !(lo->lo_offset & dio_align) &&
+ (file->f_mode & FMODE_CAN_ODIRECT))
use_dio = true;
else
use_dio = false;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 9c6c6a3e2de5..11e665242a76 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -56,11 +56,10 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
arg |= O_NONBLOCK;
/* Pipe packetized mode is controlled by O_DIRECT flag */
- if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) {
- if (!filp->f_mapping || !filp->f_mapping->a_ops ||
- !filp->f_mapping->a_ops->direct_IO)
- return -EINVAL;
- }
+ if (!S_ISFIFO(inode->i_mode) &&
+ (arg & O_DIRECT) &&
+ !(filp->f_mode & FMODE_CAN_ODIRECT))
+ return -EINVAL;
if (filp->f_op->check_flags)
error = filp->f_op->check_flags(arg);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 3dbef2c31567..9e2def045111 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -74,6 +74,8 @@ nfs_file_open(struct inode *inode, struct file *filp)
return res;
res = nfs_open(inode, filp);
+ if (res == 0)
+ filp->f_mode |= FMODE_CAN_ODIRECT;
return res;
}
@@ -535,7 +537,6 @@ const struct address_space_operations nfs_file_aops = {
.write_end = nfs_write_end,
.invalidatepage = nfs_invalidate_page,
.releasepage = nfs_release_page,
- .direct_IO = nfs_direct_IO,
#ifdef CONFIG_MIGRATION
.migratepage = nfs_migrate_page,
#endif
diff --git a/fs/open.c b/fs/open.c
index 9ff2f621b760..76ddf9014499 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -834,17 +834,16 @@ static int do_dentry_open(struct file *f,
if ((f->f_mode & FMODE_WRITE) &&
likely(f->f_op->write || f->f_op->write_iter))
f->f_mode |= FMODE_CAN_WRITE;
+ if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO)
+ f->f_mode |= FMODE_CAN_ODIRECT;
f->f_write_hint = WRITE_LIFE_NOT_SET;
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
- /* NB: we're sure to have correct a_ops only after f_op->open */
- if (f->f_flags & O_DIRECT) {
- if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
- return -EINVAL;
- }
+ if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT))
+ return -EINVAL;
/*
* XXX: Huge page cache doesn't support writing yet. Drop all page
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index fa125feed0ff..9d69b4dbb8c4 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -82,11 +82,8 @@ static int ovl_change_flags(struct file *file, unsigned int flags)
if (((flags ^ file->f_flags) & O_APPEND) && IS_APPEND(inode))
return -EPERM;
- if (flags & O_DIRECT) {
- if (!file->f_mapping->a_ops ||
- !file->f_mapping->a_ops->direct_IO)
- return -EINVAL;
- }
+ if ((flags & O_DIRECT) && !(file->f_mode & FMODE_CAN_ODIRECT))
+ return -EINVAL;
if (file->f_op->check_flags) {
err = file->f_op->check_flags(flags);
@@ -306,8 +303,7 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
ret = -EINVAL;
if (iocb->ki_flags & IOCB_DIRECT &&
- (!real.file->f_mapping->a_ops ||
- !real.file->f_mapping->a_ops->direct_IO))
+ !(real.file->f_mode & FMODE_CAN_ODIRECT))
goto out_fdput;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
@@ -367,8 +363,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
ret = -EINVAL;
if (iocb->ki_flags & IOCB_DIRECT &&
- (!real.file->f_mapping->a_ops ||
- !real.file->f_mapping->a_ops->direct_IO))
+ !(real.file->f_mode & FMODE_CAN_ODIRECT))
goto out_fdput;
if (!ovl_should_sync(OVL_FS(inode->i_sb)))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4fade3b20c87..48c021cbe327 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -161,6 +161,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
/* File is stream-like */
#define FMODE_STREAM ((__force fmode_t)0x200000)
+/* File supports DIRECT IO */
+#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000)
+
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
On Mon, Jan 24, 2022 at 02:48:32PM +1100, NeilBrown wrote:
> Currently various places test if direct IO is possible on a file by
> checking for the existence of the direct_IO address space operation.
> This is a poor choice, as the direct_IO operation may not be used - it is
> only used if the generic_file_*_iter functions are called for direct IO
> and some filesystems - particularly NFS - don't do this.
>
> Instead, introduce a new f_mode flag: FMODE_CAN_ODIRECT and change the
> various places to check this (avoiding pointer dereferences).
> do_dentry_open() will set this flag if ->direct_IO is present, so
> filesystems do not need to be changed.
>
> NFS *is* changed, to set the flag explicitly and discard the direct_IO
> entry in the address_space_operations for files.
Looks good:
Reviewed-by: Christoph Hellwig <[email protected]>
It would be nice to throw in a cleanup to remove noop_direct_IO as well.
On Mon, 24 Jan 2022, Christoph Hellwig wrote:
> On Mon, Jan 24, 2022 at 02:48:32PM +1100, NeilBrown wrote:
> > Currently various places test if direct IO is possible on a file by
> > checking for the existence of the direct_IO address space operation.
> > This is a poor choice, as the direct_IO operation may not be used - it is
> > only used if the generic_file_*_iter functions are called for direct IO
> > and some filesystems - particularly NFS - don't do this.
> >
> > Instead, introduce a new f_mode flag: FMODE_CAN_ODIRECT and change the
> > various places to check this (avoiding pointer dereferences).
> > do_dentry_open() will set this flag if ->direct_IO is present, so
> > filesystems do not need to be changed.
> >
> > NFS *is* changed, to set the flag explicitly and discard the direct_IO
> > entry in the address_space_operations for files.
>
> Looks good:
>
> Reviewed-by: Christoph Hellwig <[email protected]>
>
> It would be nice to throw in a cleanup to remove noop_direct_IO as well.
I don't want to add this to the present series. When it lands I'll send
patches to the various filesystems to switch to using FMODE_CAN_ODIRECT.
Thanks,
NeilBrown