Re: [PATCH v5 10/13] nvme-pci: Add support for P2P memory in requests

[Jason Gunthorpe]

On Thu, Aug 30, 2018 at 12:53:49PM -0600, Logan Gunthorpe wrote:
> For P2P requests, we must use the pci_p2pmem_map_sg() function
> instead of the dma_map_sg functions.
> 
> With that, we can then indicate PCI_P2P support in the request queue.
> For this, we create an NVME_F_PCI_P2P flag which tells the core to
> set QUEUE_FLAG_PCI_P2P in the request queue.
> 
> Signed-off-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
> Reviewed-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
> Reviewed-by: Christoph Hellwig <hch@xxxxxx>
>  drivers/nvme/host/core.c |  4 ++++
>  drivers/nvme/host/nvme.h |  1 +
>  drivers/nvme/host/pci.c  | 17 +++++++++++++----
>  3 files changed, 18 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
> index dd8ec1dd9219..6033ce2fd3e9 100644
> +++ b/drivers/nvme/host/core.c
> @@ -3051,7 +3051,11 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
>  	ns->queue = blk_mq_init_queue(ctrl->tagset);
>  	if (IS_ERR(ns->queue))
>  		goto out_free_ns;
> +
>  	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
> +	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
> +		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
> +
>  	ns->queue->queuedata = ns;
>  	ns->ctrl = ctrl;
>  
> diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
> index bb4a2003c097..4030743c90aa 100644
> +++ b/drivers/nvme/host/nvme.h
> @@ -343,6 +343,7 @@ struct nvme_ctrl_ops {
>  	unsigned int flags;
>  #define NVME_F_FABRICS			(1 << 0)
>  #define NVME_F_METADATA_SUPPORTED	(1 << 1)
> +#define NVME_F_PCI_P2PDMA		(1 << 2)
>  	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
>  	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
>  	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index 2902585c6ddf..bb2120d30e39 100644
> +++ b/drivers/nvme/host/pci.c
> @@ -737,8 +737,13 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
>  		goto out;
>  
>  	ret = BLK_STS_RESOURCE;
> -	nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, dma_dir,
> -			DMA_ATTR_NO_WARN);
> +
> +	if (is_pci_p2pdma_page(sg_page(iod->sg)))
> +		nr_mapped = pci_p2pdma_map_sg(dev->dev, iod->sg, iod->nents,
> +					  dma_dir);
> +	else
> +		nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents,
> +					     dma_dir,  DMA_ATTR_NO_WARN);
>  	if (!nr_mapped)
>  		goto out;
>  
> @@ -780,7 +785,10 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
>  			DMA_TO_DEVICE : DMA_FROM_DEVICE;
>  
>  	if (iod->nents) {
> -		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
> +		/* P2PDMA requests do not need to be unmapped */
> +		if (!is_pci_p2pdma_page(sg_page(iod->sg)))
> +			dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);

This seems like a poor direction, if we add IOMMU hairpin support we
will need unmapping.

Jason