drm/amdgpu: Take IOMMU remapping into account for p2p checks

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

v5: (Felix, Alex)
- fixing comment as per Alex feedback
- refactor code as per Felix

v4: (Alex)
- fix the comment and description

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@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Rahul Jain 2024-08-13 13:41:11 +05:30 committed by Alex Deucher
parent 01bfabc2d1
commit 75f0efbc4b

View File

@ -3957,6 +3957,27 @@ static void amdgpu_device_check_iommu_direct_map(struct amdgpu_device *adev)
adev->ram_is_direct_mapped = true;
}
#if defined(CONFIG_HSA_AMD_P2P)
/**
* amdgpu_device_check_iommu_remap - Check if DMA remapping is enabled.
*
* @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;
}
#endif
static const struct attribute *amdgpu_dev_attributes[] = {
&dev_attr_pcie_replay_count.attr,
NULL
@ -6151,18 +6172,24 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
struct amdgpu_device *peer_adev)
{
#ifdef CONFIG_HSA_AMD_P2P
uint64_t address_mask = peer_adev->dev->dma_mask ?
~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1);
resource_size_t aper_limit =
adev->gmc.aper_base + adev->gmc.aper_size - 1;
bool p2p_access =
!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));
bool is_large_bar = adev->gmc.visible_vram_size &&
adev->gmc.real_vram_size == adev->gmc.visible_vram_size;
bool p2p_addressable = amdgpu_device_check_iommu_remap(peer_adev);
if (!p2p_addressable) {
uint64_t address_mask = peer_adev->dev->dma_mask ?
~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1);
resource_size_t aper_limit =
adev->gmc.aper_base + adev->gmc.aper_size - 1;
p2p_addressable = !(adev->gmc.aper_base & address_mask ||
aper_limit & address_mask);
}
return is_large_bar && p2p_access && p2p_addressable;
#else
return false;
#endif