[PATCH v3] drm/amdgpu: Take IOMMU remapping into account for p2p checks

Rahul Jain Rahul.Jain at amd.com
Wed Aug 14 09:08:49 UTC 2024


when trying to enable p2p the amdgpu_device_is_peer_accessible()
checks the condition where address_mask overlaps the aper_base
and hence returns 0, due to which the p2p disables for this platform

IOMMU should remap the BAR addresses so the device can access
them. Hence check if peer_adev is remapping DMA

v3:
- remove iommu_remap variable

v2: (Alex)
- Fix as per review comments
- add new function amdgpu_device_check_iommu_remap to check if iommu
  remap

Signed-off-by: Rahul Jain <Rahul.Jain at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 46 +++++++++++++++++++---
 1 file changed, 40 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a6b8d0ba4758..040c75c491cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3952,6 +3952,25 @@ static void amdgpu_device_check_iommu_direct_map(struct amdgpu_device *adev)
 		adev->ram_is_direct_mapped = true;
 }
 
+/**
+ * amdgpu_device_check_iommu_remap - check if iommu remaped BAR
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * return if IOMMU remapping bar address
+ */
+static bool amdgpu_device_check_iommu_remap(struct amdgpu_device *adev)
+{
+	struct iommu_domain *domain;
+
+	domain = iommu_get_domain_for_dev(adev->dev);
+	if (domain && (domain->type == IOMMU_DOMAIN_DMA ||
+		domain->type ==	IOMMU_DOMAIN_DMA_FQ))
+		return true;
+
+	return false;
+}
+
 static const struct attribute *amdgpu_dev_attributes[] = {
 	&dev_attr_pcie_replay_count.attr,
 	NULL
@@ -6127,6 +6146,8 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 				      struct amdgpu_device *peer_adev)
 {
 #ifdef CONFIG_HSA_AMD_P2P
+	bool peer_remap = amdgpu_device_check_iommu_remap(peer_adev);
+
 	uint64_t address_mask = peer_adev->dev->dma_mask ?
 		~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1);
 	resource_size_t aper_limit =
@@ -6135,13 +6156,26 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 		!adev->gmc.xgmi.connected_to_cpu &&
 		!(pci_p2pdma_distance(adev->pdev, peer_adev->dev, false) < 0);
 
-	return pcie_p2p && p2p_access && (adev->gmc.visible_vram_size &&
-		adev->gmc.real_vram_size == adev->gmc.visible_vram_size &&
-		!(adev->gmc.aper_base & address_mask ||
-		  aper_limit & address_mask));
-#else
-	return false;
+	if (peer_remap)
+		/**
+		 * IOMMU is remapping DMA for peer_adev so all accesses
+		 * should be within peer_adev's DMA mask
+		 */
+		return pcie_p2p && p2p_access &&
+			(adev->gmc.visible_vram_size &&
+			 adev->gmc.real_vram_size == adev->gmc.visible_vram_size);
+	else
+		/**
+		 * No IOMMU remapping so make sure the adev's aperture
+		 * fits into peer_adev's dma mask
+		 */
+		return pcie_p2p && p2p_access &&
+			(adev->gmc.visible_vram_size &&
+			adev->gmc.real_vram_size == adev->gmc.visible_vram_size &&
+			!(adev->gmc.aper_base & address_mask ||
+			aper_limit & address_mask));
 #endif
+	return false;
 }
 
 int amdgpu_device_baco_enter(struct drm_device *dev)
-- 
2.34.1



More information about the amd-gfx mailing list