On 2021-03-12 7:32 p.m., Ira Weiny wrote:

On Thu, Mar 11, 2021 at 04:31:34PM -0700, Logan Gunthorpe wrote:

quoted

Introduce pci_p2pdma_should_map_bus() which is meant to be called by

            ^^^^^^^^^^^^^^^^^^^^^^^^^
	    pci_p2pdma_dma_map_type() ???

FWIW I find this name confusing with pci_p2pdma_map_type() and looking at the
implementation I'm not clear why pci_p2pdma_dma_map_type() needs to exist?

Yeah, there are subtle differences in prototype. But yes, they can
probably be combined. Will do for future postings.

quoted

+ * pci_p2pdma_dma_map_type - determine if a DMA mapping should use the
+ *	bus address, be mapped normally or fail
+ * @dev: device doing the DMA request
+ * @pgmap: dev_pagemap structure for the mapping
+ *
+ * Returns:
+ *    1 - if the page should be mapped with a bus address,
+ *    0 - if the page should be mapped normally through an IOMMU mapping or
+ *        physical address; or
+ *   -1 - if the device should not map the pages and an error should be
+ *        returned
+ */
+int pci_p2pdma_dma_map_type(struct device *dev, struct dev_pagemap *pgmap)
+{
+	struct pci_p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(pgmap);
+	struct pci_dev *client;
+
+	if (!dev_is_pci(dev))
+		return -1;
+
+	client = to_pci_dev(dev);
+
+	switch (pci_p2pdma_map_type(p2p_pgmap->provider, client)) {
+	case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+		return 0;
+	case PCI_P2PDMA_MAP_BUS_ADDR:
+		return 1;
+	default:
+		return -1;
+	}
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_dma_map_type);

I guess the main point here is to export this to the DMA layer?

Yes, that's correct.

Logan