VFS: add FMODE_CAN_ODIRECT file flag

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.

Other filesystems which currently use noop_direct_IO could usefully be
changed to set this flag instead.

Link: https://lkml.kernel.org/r/164859778128.29473.15189737957277399416.stgit@noble.brown
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: NeilBrown <neilb@suse.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a58595f5ee2c8f450a03b651fd6650ddc79f5e0a..75ef2e177e1b54776506889662d318c86a470c17 100644 (file)
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -186,8 +186,8 @@ 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 f15d885b97961fe3bcdfcc1e0a42b290506bab5f..34a3faa4886dcbf5413694b9917d0ccfa1980ed8 100644 (file)
--- 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 0e7686a5d0de34ffa5163b17101d1da4cb816499..bfb4b707b07ea1fc37c3a84943b7b02b442ce0d5 100644 (file)
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -69,6 +69,8 @@ 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;
 }
 
@@ -536,7 +538,6 @@ const struct address_space_operations nfs_file_aops = {
        .write_end = nfs_write_end,
        .invalidate_folio = nfs_invalidate_folio,
        .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 1315253e024739de4b1c592dabfcd04224a427c9..7b50d7a2f51d6e6a89730e9e695b0cb680700975 100644 (file)
--- a/fs/open.c
+++ b/fs/open.c
@@ -834,16 +834,15 @@ 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_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 fa125feed0ffd7ebe93f6162cbbe21d808d1be30..9d69b4dbb8c4cbc269598676540e1cf3c34f0e15 100644 (file)
--- 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 dbc5d10328dfa7b7d5b6eca17d1489f58bebb3ba..b81cacc51d2f3fedfd87bfd15677f90b0c2e09f9 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -162,6 +162,9 @@ 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)