There's a bunch of flags that are purely based on what the file
operations support while also never being conditionally set or unset.
IOW, they're not subject to change for individual files. Imho, such
flags don't need to live in f_mode they might as well live in the fops
structs itself. And the fops struct already has that lonely
mmap_supported_flags member. We might as well turn that into a generic
fop_flags member and move a few flags from FMODE_* space into FOP_*
space. That gets us four FMODE_* bits back and the ability for new
static flags that are about file ops to not have to live in FMODE_*
space but in their own FOP_* space. It's not the most beautiful thing
ever but it gets the job done. Yes, there'll be an additional pointer
chase but hopefully that won't matter for these flags.
I suspect there's a few more we can move into there and that we can also
redirect a bunch of new flag suggestions that follow this pattern into
the fop_flags field instead of f_mode.
Link: https://lore.kernel.org/r/20240328-gewendet-spargel-aa60a030ef74@brauner
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
disk_unblock_events(disk);
bdev_file->f_flags |= O_LARGEFILE;
- bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
+ bdev_file->f_mode |= FMODE_CAN_ODIRECT;
if (bdev_nowait(bdev))
bdev_file->f_mode |= FMODE_NOWAIT;
bdev_file->f_mapping = bdev->bd_inode->i_mapping;
.splice_read = filemap_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = blkdev_fallocate,
+ .fop_flags = FOP_BUFFER_RASYNC,
};
static __init int blkdev_init(void)
.release = dax_release,
.get_unmapped_area = dax_get_unmapped_area,
.mmap = dax_mmap,
- .mmap_supported_flags = MAP_SYNC,
+ .fop_flags = FOP_MMAP_SYNC,
};
static void dev_dax_cdev_del(void *cdev)
{
int ret;
- filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC |
- FMODE_CAN_ODIRECT;
+ filp->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
ret = fsverity_file_open(inode, filp);
if (ret)
.compat_ioctl = btrfs_compat_ioctl,
#endif
.remap_file_range = btrfs_remap_file_range,
+ .fop_flags = FOP_BUFFER_RASYNC | FOP_BUFFER_WASYNC,
};
int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end)
return ret;
}
- filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC |
- FMODE_DIO_PARALLEL_WRITE;
+ filp->f_mode |= FMODE_NOWAIT;
return dquot_file_open(inode, filp);
}
.compat_ioctl = ext4_compat_ioctl,
#endif
.mmap = ext4_file_mmap,
- .mmap_supported_flags = MAP_SYNC,
.open = ext4_file_open,
.release = ext4_release_file,
.fsync = ext4_sync_file,
.splice_read = ext4_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ext4_fallocate,
+ .fop_flags = FOP_MMAP_SYNC | FOP_BUFFER_RASYNC |
+ FOP_DIO_PARALLEL_WRITE,
};
const struct inode_operations ext4_file_inode_operations = {
if (err)
return err;
- filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
+ filp->f_mode |= FMODE_NOWAIT;
filp->f_mode |= FMODE_CAN_ODIRECT;
return dquot_file_open(inode, filp);
.splice_read = f2fs_file_splice_read,
.splice_write = iter_file_splice_write,
.fadvise = f2fs_file_fadvise,
+ .fop_flags = FOP_BUFFER_RASYNC,
};
if ((iocb->ki_flags & IOCB_NOWAIT) &&
!((iocb->ki_flags & IOCB_DIRECT) ||
- (file->f_mode & FMODE_BUF_WASYNC)))
+ (file->f_op->fop_flags & FOP_BUFFER_WASYNC)))
return -EINVAL;
return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count);
{
if (xfs_is_shutdown(XFS_M(inode->i_sb)))
return -EIO;
- file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC |
- FMODE_DIO_PARALLEL_WRITE | FMODE_CAN_ODIRECT;
+ file->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
return generic_file_open(inode, file);
}
.compat_ioctl = xfs_file_compat_ioctl,
#endif
.mmap = xfs_file_mmap,
- .mmap_supported_flags = MAP_SYNC,
.open = xfs_file_open,
.release = xfs_file_release,
.fsync = xfs_file_fsync,
.fallocate = xfs_file_fallocate,
.fadvise = xfs_file_fadvise,
.remap_file_range = xfs_file_remap_range,
+ .fop_flags = FOP_MMAP_SYNC | FOP_BUFFER_RASYNC | FOP_BUFFER_WASYNC |
+ FOP_DIO_PARALLEL_WRITE,
};
const struct file_operations xfs_dir_file_operations = {
.compat_ioctl = xfs_file_compat_ioctl,
#endif
.fsync = xfs_dir_fsync,
+ .fop_flags = FOP_MMAP_SYNC | FOP_BUFFER_RASYNC | FOP_BUFFER_WASYNC |
+ FOP_DIO_PARALLEL_WRITE,
};
#define FMODE_NOREUSE ((__force fmode_t)0x800000)
-/* File supports non-exclusive O_DIRECT writes from multiple threads */
-#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000)
-
/* File is embedded in backing_file object */
#define FMODE_BACKING ((__force fmode_t)0x2000000)
/* File does not contribute to nr_files count */
#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000)
-/* File supports async buffered reads */
-#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000)
-
-/* File supports async nowait buffered writes */
-#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000)
-
/*
* Attribute flags. These should be or-ed together to figure out what
* has been changed!
struct io_uring_cmd;
struct offset_ctx;
+typedef unsigned int __bitwise fop_flags_t;
+
struct file_operations {
struct module *owner;
+ fop_flags_t fop_flags;
loff_t (*llseek) (struct file *, loff_t, int);
ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
- unsigned long mmap_supported_flags;
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
unsigned int poll_flags);
} __randomize_layout;
+/* Supports async buffered reads */
+#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0))
+/* Supports async buffered writes */
+#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1))
+/* Supports synchronous page faults for mappings */
+#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2))
+/* Supports non-exclusive O_DIRECT writes from multiple threads */
+#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3))
+
/* Wrap a directory iterator that needs exclusive inode access */
int wrap_directory_iterator(struct file *, struct dir_context *,
int (*) (struct file *, struct dir_context *));
/* don't serialize this request if the fs doesn't need it */
if (should_hash && (req->file->f_flags & O_DIRECT) &&
- (req->file->f_mode & FMODE_DIO_PARALLEL_WRITE))
+ (req->file->f_op->fop_flags & FOP_DIO_PARALLEL_WRITE))
should_hash = false;
if (should_hash || (ctx->flags & IORING_SETUP_IOPOLL))
io_wq_hash_work(&req->work, file_inode(req->file));
* just use poll if we can, and don't attempt if the fs doesn't
* support callback based unlocks
*/
- if (io_file_can_poll(req) || !(req->file->f_mode & FMODE_BUF_RASYNC))
+ if (io_file_can_poll(req) ||
+ !(req->file->f_op->fop_flags & FOP_BUFFER_RASYNC))
return false;
wait->wait.func = io_async_buf_func;
if (unlikely(!io_file_supports_nowait(req)))
goto copy_iov;
- /* File path supports NOWAIT for non-direct_IO only for block devices. */
+ /* Check if we can support NOWAIT. */
if (!(kiocb->ki_flags & IOCB_DIRECT) &&
- !(kiocb->ki_filp->f_mode & FMODE_BUF_WASYNC) &&
- (req->flags & REQ_F_ISREG))
+ !(req->file->f_op->fop_flags & FOP_BUFFER_WASYNC) &&
+ (req->flags & REQ_F_ISREG))
goto copy_iov;
kiocb->ki_flags |= IOCB_NOWAIT;
if (!file_mmap_ok(file, inode, pgoff, len))
return -EOVERFLOW;
- flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
+ flags_mask = LEGACY_MAP_MASK;
+ if (file->f_op->fop_flags & FOP_MMAP_SYNC)
+ flags_mask |= MAP_SYNC;
switch (flags & MAP_TYPE) {
case MAP_SHARED: