diff mbox series

[v7,06/21] dma-direct: support PCI P2PDMA pages in dma-direct map_sg

Message ID 20220615161233.17527-7-logang@deltatee.com (mailing list archive)
State New, archived
Headers show
Series Userspace P2PDMA with O_DIRECT NVMe devices | expand

Commit Message

Logan Gunthorpe June 15, 2022, 4:12 p.m. UTC
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.

A P2PDMA page may have three possible outcomes when being mapped:
  1) If the data path between the two devices doesn't go through the
     root port, then it should be mapped with a PCI bus address
  2) If the data path goes through the host bridge, it should be mapped
     normally, as though it were a CPU physical address
  3) It is not possible for the two devices to communicate and thus
     the mapping operation should fail (and it will return -EREMOTEIO).

SGL segments that contain PCI bus addresses are marked with
sg_dma_mark_pci_p2pdma() and are ignored when unmapped.

P2PDMA mappings are also failed if swiotlb needs to be used on the
mapping.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
---
 kernel/dma/direct.c | 43 +++++++++++++++++++++++++++++++++++++------
 kernel/dma/direct.h |  8 +++++++-
 2 files changed, 44 insertions(+), 7 deletions(-)

Comments

Christoph Hellwig June 29, 2022, 6:40 a.m. UTC | #1
Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>
diff mbox series

Patch

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index e978f36e6be8..133a4be2d3e5 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -454,29 +454,60 @@  void dma_direct_sync_sg_for_cpu(struct device *dev,
 		arch_sync_dma_for_cpu_all();
 }
 
+/*
+ * Unmaps segments, except for ones marked as pci_p2pdma which do not
+ * require any further action as they contain a bus address.
+ */
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct scatterlist *sg;
 	int i;
 
-	for_each_sg(sgl, sg, nents, i)
-		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
-			     attrs);
+	for_each_sg(sgl,  sg, nents, i) {
+		if (sg_is_dma_bus_address(sg))
+			sg_dma_unmark_bus_address(sg);
+		else
+			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 pci_p2pdma_map_state p2pdma_state = {};
+	enum pci_p2pdma_map_type map;
 	struct scatterlist *sg;
+	int i, ret;
 
 	for_each_sg(sgl, sg, nents, i) {
+		if (is_pci_p2pdma_page(sg_page(sg))) {
+			map = pci_p2pdma_map_segment(&p2pdma_state, dev, sg);
+			switch (map) {
+			case PCI_P2PDMA_MAP_BUS_ADDR:
+				continue;
+			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+				/*
+				 * Any P2P mapping that traverses the PCI
+				 * host bridge must be mapped with CPU physical
+				 * address and not PCI bus addresses. This is
+				 * done with dma_direct_map_page() below.
+				 */
+				break;
+			default:
+				ret = -EREMOTEIO;
+				goto out_unmap;
+			}
+		}
+
 		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
 				sg->offset, sg->length, dir, attrs);
-		if (sg->dma_address == DMA_MAPPING_ERROR)
+		if (sg->dma_address == DMA_MAPPING_ERROR) {
+			ret = -EIO;
 			goto out_unmap;
+		}
 		sg_dma_len(sg) = sg->length;
 	}
 
@@ -484,7 +515,7 @@  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 -EIO;
+	return ret;
 }
 
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index a78c0ba70645..e38ffc5e6bdd 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -8,6 +8,7 @@ 
 #define _KERNEL_DMA_DIRECT_H
 
 #include <linux/dma-direct.h>
+#include <linux/memremap.h>
 
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
@@ -87,10 +88,15 @@  static inline dma_addr_t dma_direct_map_page(struct device *dev,
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (is_swiotlb_force_bounce(dev))
+	if (is_swiotlb_force_bounce(dev)) {
+		if (is_pci_p2pdma_page(page))
+			return DMA_MAPPING_ERROR;
 		return swiotlb_map(dev, phys, size, dir, attrs);
+	}
 
 	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (is_pci_p2pdma_page(page))
+			return DMA_MAPPING_ERROR;
 		if (is_swiotlb_active(dev))
 			return swiotlb_map(dev, phys, size, dir, attrs);