[PATCH v4 15/22] drm/xe: Support pcie p2p dma as a fast interconnect

["Thomas Hellström" <thomas.hellstrom@linux.intel.com>]

Mimic the dma-buf method using dma_[map|unmap]_resource to map
for pcie-p2p dma.

There's an ongoing area of work upstream to sort out how this best
should be done. One method proposed is to add an additional
pci_p2p_dma_pagemap aliasing the device_private pagemap and use
the corresponding pci_p2p_dma_pagemap page as input for
dma_map_page(). However, that would incur double the amount of
memory and latency to set up the drm_pagemap and given the huge
amount of memory present on modern GPUs, that would really not work.
Hence the simple approach used in this patch.

v2:
- Simplify xe_page_to_pcie(). (Matt Brost)

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_svm.c | 34 +++++++++++++++++++++++++++++++---
 drivers/gpu/drm/xe/xe_svm.h |  1 +
 2 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 54eb04467163..6ebc1b43d0ca 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -3,6 +3,8 @@
  * Copyright © 2024 Intel Corporation
  */
 
+#include <linux/pci-p2pdma.h>
+
 #include <drm/drm_drv.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_pagemap.h>
@@ -452,6 +454,14 @@ static u64 xe_page_to_dpa(struct page *page)
 	return dpa;
 }
 
+static u64 xe_page_to_pcie(struct page *page)
+{
+	struct xe_pagemap *xpagemap = xe_page_to_pagemap(page);
+	struct xe_vram_region *vr = xe_pagemap_to_vr(xpagemap);
+
+	return xe_page_to_dpa(page) - vr->dpa_base + vr->io_start;
+}
+
 enum xe_svm_copy_dir {
 	XE_SVM_COPY_TO_VRAM,
 	XE_SVM_COPY_TO_SRAM,
@@ -839,7 +849,10 @@ static bool xe_has_interconnect(struct drm_pagemap_peer *peer1,
 	struct device *dev1 = xe_peer_to_dev(peer1);
 	struct device *dev2 = xe_peer_to_dev(peer2);
 
-	return dev1 == dev2;
+	if (dev1 == dev2)
+		return true;
+
+	return pci_p2pdma_distance(to_pci_dev(dev1), dev2, true) >= 0;
 }
 
 static DRM_PAGEMAP_OWNER_LIST_DEFINE(xe_owner_list);
@@ -1612,13 +1625,27 @@ xe_drm_pagemap_device_map(struct drm_pagemap *dpagemap,
 		addr = xe_page_to_dpa(page);
 		prot = XE_INTERCONNECT_VRAM;
 	} else {
-		addr = DMA_MAPPING_ERROR;
-		prot = 0;
+		addr = dma_map_resource(dev,
+					xe_page_to_pcie(page),
+					PAGE_SIZE << order, dir,
+					DMA_ATTR_SKIP_CPU_SYNC);
+		prot = XE_INTERCONNECT_P2P;
 	}
 
 	return drm_pagemap_addr_encode(addr, prot, order, dir);
 }
 
+static void xe_drm_pagemap_device_unmap(struct drm_pagemap *dpagemap,
+					struct device *dev,
+					struct drm_pagemap_addr addr)
+{
+	if (addr.proto != XE_INTERCONNECT_P2P)
+		return;
+
+	dma_unmap_resource(dev, addr.addr, PAGE_SIZE << addr.order,
+			   addr.dir, DMA_ATTR_SKIP_CPU_SYNC);
+}
+
 static void xe_pagemap_destroy_work(struct work_struct *work)
 {
 	struct xe_pagemap *xpagemap = container_of(work, typeof(*xpagemap), destroy_work);
@@ -1655,6 +1682,7 @@ static void xe_pagemap_destroy(struct drm_pagemap *dpagemap, bool from_atomic_or
 
 static const struct drm_pagemap_ops xe_drm_pagemap_ops = {
 	.device_map = xe_drm_pagemap_device_map,
+	.device_unmap = xe_drm_pagemap_device_unmap,
 	.populate_mm = xe_drm_pagemap_populate_mm,
 	.destroy = xe_pagemap_destroy,
 };
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index ec7c6751cc86..50e80bc892b6 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -13,6 +13,7 @@
 #include <drm/drm_pagemap_util.h>
 
 #define XE_INTERCONNECT_VRAM DRM_INTERCONNECT_DRIVER
+#define XE_INTERCONNECT_P2P (XE_INTERCONNECT_VRAM + 1)
 
 struct drm_device;
 struct drm_file;
-- 
2.51.1