Re: [PATCH v4 03/10] block: Introduce a new ioctl for copy

[Damien Le Moal <damien.lemoal@opensource.wdc.com>]

On 4/26/22 19:12, Nitesh Shetty wrote:
> Add new BLKCOPY ioctl that offloads copying of one or more sources ranges
> to one or more destination in a device. COPY ioctl accepts a 'copy_range'
> structure that contains no of range, a reserved field , followed by an
> array of ranges. Each source range is represented by 'range_entry' that
> contains source start offset, destination start offset and length of
> source ranges (in bytes)
> 
> MAX_COPY_NR_RANGE, limits the number of entries for the IOCTL and
> MAX_COPY_TOTAL_LENGTH limits the total copy length, IOCTL can handle.
> 
> Example code, to issue BLKCOPY:
> /* Sample example to copy three entries with [dest,src,len],
> * [32768, 0, 4096] [36864, 4096, 4096] [40960,8192,4096] on same device */
> 
> int main(void)
> {
> 	int i, ret, fd;
> 	unsigned long src = 0, dst = 32768, len = 4096;
> 	struct copy_range *cr;
> 	cr = (struct copy_range *)malloc(sizeof(*cr)+
> 					(sizeof(struct range_entry)*3));
> 	cr->nr_range = 3;
> 	cr->reserved = 0;
> 	for (i = 0; i< cr->nr_range; i++, src += len, dst += len) {
> 		cr->range_list[i].dst = dst;
> 		cr->range_list[i].src = src;
> 		cr->range_list[i].len = len;
> 		cr->range_list[i].comp_len = 0;
> 	}
> 	fd = open("/dev/nvme0n1", O_RDWR);
> 	if (fd < 0) return 1;
> 	ret = ioctl(fd, BLKCOPY, cr);
> 	if (ret != 0)
> 	       printf("copy failed, ret= %d\n", ret);
> 	for (i=0; i< cr->nr_range; i++)
> 		if (cr->range_list[i].len != cr->range_list[i].comp_len)
> 			printf("Partial copy for entry %d: requested %llu, completed %llu\n",
> 								i, cr->range_list[i].len,
> 								cr->range_list[i].comp_len);
> 	close(fd);
> 	free(cr);
> 	return ret;
> }

Nice to have a code example. But please format it correctly.

> 
> Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
> Signed-off-by: Javier González <javier.gonz@samsung.com>
> Signed-off-by: Arnav Dawn <arnav.dawn@samsung.com>
> ---
>  block/ioctl.c           | 32 ++++++++++++++++++++++++++++++++
>  include/uapi/linux/fs.h |  9 +++++++++
>  2 files changed, 41 insertions(+)
> 
> diff --git a/block/ioctl.c b/block/ioctl.c
> index 46949f1b0dba..58d93c20ff30 100644
> --- a/block/ioctl.c
> +++ b/block/ioctl.c
> @@ -120,6 +120,36 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
>  	return err;
>  }
>  
> +static int blk_ioctl_copy(struct block_device *bdev, fmode_t mode,
> +		unsigned long arg)
> +{
> +	struct copy_range crange, *ranges = NULL;
> +	size_t payload_size = 0;
> +	int ret;
> +
> +	if (!(mode & FMODE_WRITE))
> +		return -EBADF;
> +
> +	if (copy_from_user(&crange, (void __user *)arg, sizeof(crange)))
> +		return -EFAULT;
> +
> +	if (unlikely(!crange.nr_range || crange.reserved || crange.nr_range >= MAX_COPY_NR_RANGE))
> +		return -EINVAL;
> +
> +	payload_size = (crange.nr_range * sizeof(struct range_entry)) + sizeof(crange);
> +
> +	ranges = memdup_user((void __user *)arg, payload_size);
> +	if (IS_ERR(ranges))
> +		return PTR_ERR(ranges);
> +
> +	ret = blkdev_issue_copy(bdev, ranges->nr_range, ranges->range_list, bdev, GFP_KERNEL);
> +	if (copy_to_user((void __user *)arg, ranges, payload_size))
> +		ret = -EFAULT;
> +
> +	kfree(ranges);
> +	return ret;
> +}
> +
>  static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode,
>  		void __user *argp)
>  {
> @@ -481,6 +511,8 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
>  		return blk_ioctl_discard(bdev, mode, arg);
>  	case BLKSECDISCARD:
>  		return blk_ioctl_secure_erase(bdev, mode, argp);
> +	case BLKCOPY:
> +		return blk_ioctl_copy(bdev, mode, arg);
>  	case BLKZEROOUT:
>  		return blk_ioctl_zeroout(bdev, mode, arg);
>  	case BLKGETDISKSEQ:
> diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
> index 822c28cebf3a..a3b13406ffb8 100644
> --- a/include/uapi/linux/fs.h
> +++ b/include/uapi/linux/fs.h
> @@ -78,6 +78,14 @@ struct range_entry {
>  	__u64 comp_len;
>  };
>  
> +struct copy_range {
> +	__u64 nr_range;
> +	__u64 reserved;
> +
> +	/* Range_list always must be at the end */
> +	struct range_entry range_list[];
> +};
> +
>  /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
>  #define FILE_DEDUPE_RANGE_SAME		0
>  #define FILE_DEDUPE_RANGE_DIFFERS	1
> @@ -199,6 +207,7 @@ struct fsxattr {
>  #define BLKROTATIONAL _IO(0x12,126)
>  #define BLKZEROOUT _IO(0x12,127)
>  #define BLKGETDISKSEQ _IOR(0x12,128,__u64)
> +#define BLKCOPY _IOWR(0x12, 129, struct copy_range)
>  /*
>   * A jump here: 130-136 are reserved for zoned block devices
>   * (see uapi/linux/blkzoned.h)


-- 
Damien Le Moal
Western Digital Research