vfs: support STATX_DIOALIGN on block devices

Add support for STATX_DIOALIGN to block devices, so that direct I/O
alignment restrictions are exposed to userspace in a generic way.

Note that this breaks the tradition of stat operating only on the block
device node, not the block device itself.  However, it was felt that
doing this is preferable, in order to make the interface useful and
avoid needing separate interfaces for regular files and block devices.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Link: https://lore.kernel.org/r/20220827065851.135710-3-ebiggers@kernel.org
This commit is contained in:
Eric Biggers 2022-08-26 23:58:45 -07:00
parent 825cf206ed
commit 2d985f8c6b
3 changed files with 39 additions and 0 deletions

View File

@ -26,6 +26,7 @@
#include <linux/namei.h>
#include <linux/part_stat.h>
#include <linux/uaccess.h>
#include <linux/stat.h>
#include "../fs/internal.h"
#include "blk.h"
@ -1069,3 +1070,25 @@ void sync_bdevs(bool wait)
spin_unlock(&blockdev_superblock->s_inode_list_lock);
iput(old_inode);
}
/*
* Handle STATX_DIOALIGN for block devices.
*
* Note that the inode passed to this is the inode of a block device node file,
* not the block device's internal inode. Therefore it is *not* valid to use
* I_BDEV() here; the block device has to be looked up by i_rdev instead.
*/
void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
{
struct block_device *bdev;
bdev = blkdev_get_no_open(inode->i_rdev);
if (!bdev)
return;
stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
stat->dio_offset_align = bdev_logical_block_size(bdev);
stat->result_mask |= STATX_DIOALIGN;
blkdev_put_no_open(bdev);
}

View File

@ -5,6 +5,7 @@
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/blkdev.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/errno.h>
@ -230,11 +231,22 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
goto out;
error = vfs_getattr(&path, stat, request_mask, flags);
stat->mnt_id = real_mount(path.mnt)->mnt_id;
stat->result_mask |= STATX_MNT_ID;
if (path.mnt->mnt_root == path.dentry)
stat->attributes |= STATX_ATTR_MOUNT_ROOT;
stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
/* Handle STATX_DIOALIGN for block devices. */
if (request_mask & STATX_DIOALIGN) {
struct inode *inode = d_backing_inode(path.dentry);
if (S_ISBLK(inode->i_mode))
bdev_statx_dioalign(inode, stat);
}
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;

View File

@ -1498,6 +1498,7 @@ int sync_blockdev(struct block_device *bdev);
int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
int sync_blockdev_nowait(struct block_device *bdev);
void sync_bdevs(bool wait);
void bdev_statx_dioalign(struct inode *inode, struct kstat *stat);
void printk_all_partitions(void);
#else
static inline void invalidate_bdev(struct block_device *bdev)
@ -1514,6 +1515,9 @@ static inline int sync_blockdev_nowait(struct block_device *bdev)
static inline void sync_bdevs(bool wait)
{
}
static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
{
}
static inline void printk_all_partitions(void)
{
}