[RFC PATCH v2 06/11] dma-direct: Support PCI P2PDMA pages in dma-direct map_sg

[Robin Murphy]

On 2021-03-11 23:31, Logan Gunthorpe wrote:
> Add PCI P2PDMA support for dma_direct_map_sg() so that it can map
> PCI P2PDMA pages directly without a hack in the callers. This allows
> for heterogeneous SGLs that contain both P2PDMA and regular pages.
> 
> SGL segments that contain PCI bus addresses are marked with
> sg_mark_pci_p2pdma() and are ignored when unmapped.
> 
> Signed-off-by: Logan Gunthorpe <logang at deltatee.com>
> ---
>   kernel/dma/direct.c  | 35 ++++++++++++++++++++++++++++++++---
>   kernel/dma/mapping.c | 13 ++++++++++---
>   2 files changed, 42 insertions(+), 6 deletions(-)
> 
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index 002268262c9a..f326d32062dd 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -13,6 +13,7 @@
>   #include <linux/vmalloc.h>
>   #include <linux/set_memory.h>
>   #include <linux/slab.h>
> +#include <linux/pci-p2pdma.h>
>   #include "direct.h"
>   
>   /*
> @@ -387,19 +388,47 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
>   	struct scatterlist *sg;
>   	int i;
>   
> -	for_each_sg(sgl, sg, nents, i)
> +	for_each_sg(sgl, sg, nents, i) {
> +		if (sg_is_pci_p2pdma(sg))
> +			continue;
> +
>   		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
>   			     attrs);
> +	}
>   }
>   #endif
>   
>   int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
>   		enum dma_data_direction dir, unsigned long attrs)
>   {
> -	int i;
> +	struct dev_pagemap *pgmap = NULL;
> +	int i, map = -1, ret = 0;
>   	struct scatterlist *sg;
> +	u64 bus_off;
>   
>   	for_each_sg(sgl, sg, nents, i) {
> +		if (is_pci_p2pdma_page(sg_page(sg))) {
> +			if (sg_page(sg)->pgmap != pgmap) {
> +				pgmap = sg_page(sg)->pgmap;
> +				map = pci_p2pdma_dma_map_type(dev, pgmap);
> +				bus_off = pci_p2pdma_bus_offset(sg_page(sg));
> +			}
> +
> +			if (map < 0) {
> +				sg->dma_address = DMA_MAPPING_ERROR;
> +				ret = -EREMOTEIO;
> +				goto out_unmap;
> +			}
> +
> +			if (map) {
> +				sg->dma_address = sg_phys(sg) + sg->offset -
> +					bus_off;
> +				sg_dma_len(sg) = sg->length;
> +				sg_mark_pci_p2pdma(sg);
> +				continue;
> +			}
> +		}
> +
>   		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
>   				sg->offset, sg->length, dir, attrs);
>   		if (sg->dma_address == DMA_MAPPING_ERROR)
> @@ -411,7 +440,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
>   
>   out_unmap:
>   	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
> -	return 0;
> +	return ret;
>   }
>   
>   dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
> diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
> index b6a633679933..adc1a83950be 100644
> --- a/kernel/dma/mapping.c
> +++ b/kernel/dma/mapping.c
> @@ -178,8 +178,15 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
>   EXPORT_SYMBOL(dma_unmap_page_attrs);
>   
>   /*
> - * dma_maps_sg_attrs returns 0 on error and > 0 on success.
> - * It should never return a value < 0.
> + * dma_maps_sg_attrs returns 0 on any resource error and > 0 on success.
> + *
> + * If 0 is returned, the mapping can be retried and will succeed once
> + * sufficient resources are available.

That's not a guarantee we can uphold. Retrying forever in the vain hope 
that a device might evolve some extra address bits, or a bounce buffer 
might magically grow big enough for a gigantic mapping, isn't 
necessarily the best idea.

> + *
> + * If there are P2PDMA pages in the scatterlist then this function may
> + * return -EREMOTEIO to indicate that the pages are not mappable by the
> + * device. In this case, an error should be returned for the IO as it
> + * will never be successfully retried.
>    */
>   int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
>   		enum dma_data_direction dir, unsigned long attrs)
> @@ -197,7 +204,7 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
>   		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
>   	else
>   		ents = ops->map_sg(dev, sg, nents, dir, attrs);
> -	BUG_ON(ents < 0);
> +

This scares me - I hesitate to imagine the amount of driver/subsystem 
code out there that will see nonzero and merrily set off iterating a 
negative number of segments, if we open the floodgates of allowing 
implementations to return error codes here.

Robin.

>   	debug_dma_map_sg(dev, sg, nents, ents, dir);
>   
>   	return ents;
>