Merge tag 'amd-drm-next-6.4-2023-03-17' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.4-2023-03-17:

amdgpu:
- Misc code cleanups
- Documentation fixes
- Make kobj structures const
- Add thermal throttling adjustments for supported APUs
- UMC RAS fixes
- Display reset fixes
- DCN 3.2 fixes
- Freesync fixes
- DC code reorg
- Generalize dmabuf import to work with KFD
- DC DML fixes
- SRIOV fixes
- UVD code cleanups
- IH 4.4.2 updates
- HDP 4.4.2 updates
- SDMA 4.4.2 updates
- PSP 13.0.6 updates
- Add capped/uncapped workload handling for supported APUs
- DCN 3.1.4 updates
- Re-org DC Kconfig
- USB4 fixes
- Reorg DC plane and stream handling
- Register vga_switcheroo for apple-gmux
- SMU 13.0.6 updates
- Fix error checking in read_mm_registers functions for affected families
- VCN 4.0.4 fix
- Drop redundant pci_enable_pcie_error_reporting() call
- RDNA2 SMU OD suspend/resume fix
- Expose additional memory stats via fdinfo
- RAS fixes
- Misc display fixes
- DP MST fixes
- IOMMU regression fix for KFD

amdkfd:
- Make kobj structures const
- Support for exporting buffers via dmabuf
- Multi-VMA page migration fixes
- NBIO fixes
- Misc code cleanups
- Fix possible double free
- Fix possible UAF

radeon:
- iMac fix

UAPI:
- KFD dmabuf export support.  Required for importing KFD buffers into GEM contexts and for RDMA P2P support.
  Proposed user mode changes: https://github.com/fxkamd/ROCT-Thunk-Interface/commits/fxkamd/dmabuf

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230317164416.138340-1-alexander.deucher@amd.com

1 files changed, 11 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 63dfcc98152d..11df6ee052b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2554,21 +2554,24 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 	/* initialize nbio ras function ahead of any other
 	 * ras functions so hardware fatal error interrupt
 	 * can be enabled as early as possible */
-	switch (adev->asic_type) {
-	case CHIP_VEGA20:
-	case CHIP_ARCTURUS:
-	case CHIP_ALDEBARAN:
-		if (!adev->gmc.xgmi.connected_to_cpu) {
+	switch (adev->ip_versions[NBIO_HWIP][0]) {
+	case IP_VERSION(7, 4, 0):
+	case IP_VERSION(7, 4, 1):
+	case IP_VERSION(7, 4, 4):
+		if (!adev->gmc.xgmi.connected_to_cpu)
 			adev->nbio.ras = &nbio_v7_4_ras;
-			amdgpu_ras_register_ras_block(adev, &adev->nbio.ras->ras_block);
-			adev->nbio.ras_if = &adev->nbio.ras->ras_block.ras_comm;
-		}
 		break;
 	default:
 		/* nbio ras is not available */
 		break;
 	}
 
+	/* nbio ras block needs to be enabled ahead of other ras blocks
+	 * to handle fatal error */
+	r = amdgpu_nbio_ras_sw_init(adev);
+	if (r)
+		return r;
+
 	if (adev->nbio.ras &&
 	    adev->nbio.ras->init_ras_controller_interrupt) {
 		r = adev->nbio.ras->init_ras_controller_interrupt(adev);
@@ -3073,9 +3076,6 @@ int amdgpu_ras_register_ras_block(struct amdgpu_device *adev,
 	if (!adev || !ras_block_obj)
 		return -EINVAL;
 
-	if (!amdgpu_ras_asic_supported(adev))
-		return 0;
-
 	ras_node = kzalloc(sizeof(*ras_node), GFP_KERNEL);
 	if (!ras_node)
 		return -ENOMEM;