[PATCH 1/2] nvme-pci: Use size_t for length fields to handle larger sizes

[David Laight]

On Sat, 15 Nov 2025 18:22:45 +0200
Leon Romanovsky <leon at kernel.org> wrote:

> From: Leon Romanovsky <leonro at nvidia.com>
> 
> This patch changes the length variables from unsigned int to size_t.
> Using size_t ensures that we can handle larger sizes, as size_t is
> always equal to or larger than the previously used u32 type.

Where are requests larger than 4GB going to come from?

> Originally, u32 was used because blk-mq-dma code evolved from
> scatter-gather implementation, which uses unsigned int to describe length.
> This change will also allow us to reuse the existing struct phys_vec in places
> that don't need scatter-gather.
> 
> Signed-off-by: Leon Romanovsky <leonro at nvidia.com>
> ---
>  block/blk-mq-dma.c      | 14 +++++++++-----
>  drivers/nvme/host/pci.c |  4 ++--
>  2 files changed, 11 insertions(+), 7 deletions(-)
> 
> diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c
> index e9108ccaf4b0..cc3e2548cc30 100644
> --- a/block/blk-mq-dma.c
> +++ b/block/blk-mq-dma.c
> @@ -8,7 +8,7 @@
>  
>  struct phys_vec {
>  	phys_addr_t	paddr;
> -	u32		len;
> +	size_t		len;
>  };
>  
>  static bool __blk_map_iter_next(struct blk_map_iter *iter)
> @@ -112,8 +112,8 @@ static bool blk_rq_dma_map_iova(struct request *req, struct device *dma_dev,
>  		struct phys_vec *vec)
>  {
>  	enum dma_data_direction dir = rq_dma_dir(req);
> -	unsigned int mapped = 0;
>  	unsigned int attrs = 0;
> +	size_t mapped = 0;
>  	int error;
>  
>  	iter->addr = state->addr;
> @@ -296,8 +296,10 @@ int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist,
>  	blk_rq_map_iter_init(rq, &iter);
>  	while (blk_map_iter_next(rq, &iter, &vec)) {
>  		*last_sg = blk_next_sg(last_sg, sglist);
> -		sg_set_page(*last_sg, phys_to_page(vec.paddr), vec.len,
> -				offset_in_page(vec.paddr));
> +
> +		WARN_ON_ONCE(overflows_type(vec.len, unsigned int));

I'm not at all sure you need that test.
blk_map_iter_next() has to guarantee that vec.len is valid.
(probably even less than a page size?)
Perhaps this code should be using a different type for the addr:len pair?

> +		sg_set_page(*last_sg, phys_to_page(vec.paddr),
> +			    (unsigned int)vec.len, offset_in_page(vec.paddr));

You definitely don't need the explicit cast.

	David

>  		nsegs++;
>  	}
>  
> @@ -416,7 +418,9 @@ int blk_rq_map_integrity_sg(struct request *rq, struct scatterlist *sglist)
>  
>  	while (blk_map_iter_next(rq, &iter, &vec)) {
>  		sg = blk_next_sg(&sg, sglist);
> -		sg_set_page(sg, phys_to_page(vec.paddr), vec.len,
> +
> +		WARN_ON_ONCE(overflows_type(vec.len, unsigned int));
> +		sg_set_page(sg, phys_to_page(vec.paddr), (unsigned int)vec.len,
>  				offset_in_page(vec.paddr));
>  		segments++;
>  	}
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index 9085bed107fd..de512efa742d 100644
> --- a/drivers/nvme/host/pci.c
> +++ b/drivers/nvme/host/pci.c
> @@ -290,14 +290,14 @@ struct nvme_iod {
>  	u8 flags;
>  	u8 nr_descriptors;
>  
> -	unsigned int total_len;
> +	size_t total_len;
>  	struct dma_iova_state dma_state;
>  	void *descriptors[NVME_MAX_NR_DESCRIPTORS];
>  	struct nvme_dma_vec *dma_vecs;
>  	unsigned int nr_dma_vecs;
>  
>  	dma_addr_t meta_dma;
> -	unsigned int meta_total_len;
> +	size_t meta_total_len;
>  	struct dma_iova_state meta_dma_state;
>  	struct nvme_sgl_desc *meta_descriptor;
>  };
>