Received-SPF: pass (google.com: domain of linux-kernel+bounces-80093-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Date: Sun, 25 Feb 2024 19:50:06 +0530
Message-Id: <87frxg1v8p.fsf@doe.com>
From: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
To: John Garry <john.g.garry@oracle.com>, axboe@kernel.dk, kbusch@kernel.org, hch@lst.de, sagi@grimberg.me, jejb@linux.ibm.com, martin.petersen@oracle.com, djwong@kernel.org, viro@zeniv.linux.org.uk, brauner@kernel.org, dchinner@redhat.com, jack@suse.cz
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org, linux-fsdevel@vger.kernel.org, tytso@mit.edu, jbongio@google.com, linux-scsi@vger.kernel.org, ojaswin@linux.ibm.com, linux-aio@kvack.org, linux-btrfs@vger.kernel.org, io-uring@vger.kernel.org, nilay@linux.ibm.com, Prasad Singamsetty <prasad.singamsetty@oracle.com>, John Garry <john.g.garry@oracle.com>
Subject: Re: [PATCH v4 06/11] block: Add atomic write support for statx
In-Reply-To: <20240219130109.341523-7-john.g.garry@oracle.com>
Precedence: bulk

John Garry <john.g.garry@oracle.com> writes:

> From: Prasad Singamsetty <prasad.singamsetty@oracle.com>
>
> Extend statx system call to return additional info for atomic write support
> support if the specified file is a block device.
>
> Signed-off-by: Prasad Singamsetty <prasad.singamsetty@oracle.com>
> Signed-off-by: John Garry <john.g.garry@oracle.com>
> ---
>  block/bdev.c           | 37 +++++++++++++++++++++++++++----------
>  fs/stat.c              | 13 ++++++-------
>  include/linux/blkdev.h |  5 +++--
>  3 files changed, 36 insertions(+), 19 deletions(-)
>
> diff --git a/block/bdev.c b/block/bdev.c
> index e9f1b12bd75c..0dada9902bd4 100644
> --- a/block/bdev.c
> +++ b/block/bdev.c
> @@ -1116,24 +1116,41 @@ void sync_bdevs(bool wait)
>  	iput(old_inode);
>  }
>  
> +#define BDEV_STATX_SUPPORTED_MASK (STATX_DIOALIGN | STATX_WRITE_ATOMIC)
> +
>  /*
> - * 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.
> + * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices.
>   */
> -void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
> +void bdev_statx(struct dentry *dentry, struct kstat *stat, u32 request_mask)

why change this to dentry? Why not keep it as inode itself?

-ritesh

>  {
>  	struct block_device *bdev;
>  
> -	bdev = blkdev_get_no_open(inode->i_rdev);
> +	if (!(request_mask & BDEV_STATX_SUPPORTED_MASK))
> +		return;
> +
> +	/*
> +	 * Note that d_backing_inode() returns 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.
> +	 */
> +	bdev = blkdev_get_no_open(d_backing_inode(dentry)->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;
> +	if (request_mask & STATX_DIOALIGN) {
> +		stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
> +		stat->dio_offset_align = bdev_logical_block_size(bdev);
> +		stat->result_mask |= STATX_DIOALIGN;
> +	}
> +
> +	if (request_mask & STATX_WRITE_ATOMIC && bdev_can_atomic_write(bdev)) {
> +		struct request_queue *bd_queue = bdev->bd_queue;
> +
> +		generic_fill_statx_atomic_writes(stat,
> +			queue_atomic_write_unit_min_bytes(bd_queue),
> +			queue_atomic_write_unit_max_bytes(bd_queue));
> +	}
>  
>  	blkdev_put_no_open(bdev);
>  }
> diff --git a/fs/stat.c b/fs/stat.c
> index 522787a4ab6a..bd0618477702 100644
> --- a/fs/stat.c
> +++ b/fs/stat.c
> @@ -290,13 +290,12 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
>  		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);
> -	}
> +	/* If this is a block device inode, override the filesystem
> +	 * attributes with the block device specific parameters
> +	 * that need to be obtained from the bdev backing inode
> +	 */
> +	if (S_ISBLK(d_backing_inode(path.dentry)->i_mode))
> +		bdev_statx(path.dentry, stat, request_mask);
>  
>  	path_put(&path);
>  	if (retry_estale(error, lookup_flags)) {
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index 40ed56ef4937..4f04456f1250 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -1541,7 +1541,7 @@ 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 bdev_statx(struct dentry *dentry, struct kstat *stat, u32 request_mask);
>  void printk_all_partitions(void);
>  int __init early_lookup_bdev(const char *pathname, dev_t *dev);
>  #else
> @@ -1559,7 +1559,8 @@ 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 bdev_statx(struct dentry *dentry, struct kstat *stat,
> +				u32 request_mask)
>  {
>  }
>  static inline void printk_all_partitions(void)
> -- 
> 2.31.1