Merge tag 'amd-drm-next-6.14-2024-12-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.14-2024-12-18:

amdgpu:
- RAS updates
- ISP updates
- SDMA queue reset support
- Rework DPM powergating interfaces
- Documentation updates and cleanups
- Panel replay fixes
- DCN 3.5 updates
- DP tunneling fixes
- Use a pm notifier to more gracefully handle VRAM eviction on suspend or hibernate
- Add debugfs interfaces for forcing scheduling to specific engine instances
- GG 9.5 updates
- IH 4.4 updates
- Make missing optional firmware less noisy
- PSP 13.x updates
- SMU 13.x updates
- VCN 5.x updates
- JPEG 5.x updates
- Misc cleanups
- GC 12.x updates
- DRM panic support
- DC FAMS updates
- DSC fixes
- job handling fixes

amdkfd:
- GG 9.5 updates
- Logging improvements
- Misc cleanups
- Various Optimizations

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241218201758.2580723-1-alexander.deucher@amd.com

1 files changed, 21 insertions, 6 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c
index be96de92b2f5..6b8e078ee7c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc24.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc24.c
@@ -444,8 +444,18 @@ static int soc24_common_late_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev)) {
 		xgpu_nv_mailbox_get_irq(adev);
+	} else {
+		if (adev->nbio.ras &&
+		    adev->nbio.ras_err_event_athub_irq.funcs)
+			/* don't need to fail gpu late init
+			 * if enabling athub_err_event interrupt failed
+			 * nbif v6_3_1 only support fatal error hanlding
+			 * just enable the interrupt directly
+			 */
+			amdgpu_irq_get(adev, &adev->nbio.ras_err_event_athub_irq, 0);
+	}
 
 	/* Enable selfring doorbell aperture late because doorbell BAR
 	 * aperture will change if resize BAR successfully in gmc sw_init.
@@ -501,8 +511,13 @@ static int soc24_common_hw_fini(struct amdgpu_ip_block *ip_block)
 	adev->nbio.funcs->enable_doorbell_aperture(adev, false);
 	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false);
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev)) {
 		xgpu_nv_mailbox_put_irq(adev);
+	} else {
+		if (adev->nbio.ras &&
+		    adev->nbio.ras_err_event_athub_irq.funcs)
+			amdgpu_irq_put(adev, &adev->nbio.ras_err_event_athub_irq, 0);
+	}
 
 	return 0;
 }
@@ -522,10 +537,10 @@ static bool soc24_common_is_idle(void *handle)
 	return true;
 }
 
-static int soc24_common_set_clockgating_state(void *handle,
+static int soc24_common_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 					      enum amd_clockgating_state state)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) {
 	case IP_VERSION(6, 3, 1):
@@ -542,10 +557,10 @@ static int soc24_common_set_clockgating_state(void *handle,
 	return 0;
 }
 
-static int soc24_common_set_powergating_state(void *handle,
+static int soc24_common_set_powergating_state(struct amdgpu_ip_block *ip_block,
 					      enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	switch (amdgpu_ip_version(adev, LSDMA_HWIP, 0)) {
 	case IP_VERSION(7, 0, 0):