Merge tag 'amd-drm-next-6.6-2023-07-28' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.6-2023-07-28:

amdgpu:
- Lots of checkpatch cleanups
- GFX 9.4.3 updates
- Add USB PD and IFWI flashing documentation
- GPUVM updates
- RAS fixes
- DRR fixes
- FAMS fixes
- Virtual display fixes
- Soft IH fixes
- SMU13 fixes
- Rework PSP firmware loading for other IPs
- Kernel doc fixes
- DCN 3.0.1 fixes
- LTTPR fixes
- DP MST fixes
- DCN 3.1.6 fixes
- SubVP fixes
- Display bandwidth calculation fixes
- VCN4 secure submission fixes
- Allow building DC on RISC-V
- Add visible FB info to bo_print_info
- HBR3 fixes
- Add PSP 14.0 support
- GFX9 MCBP fix
- GMC10 vmhub index fix
- GMC11 vmhub index fix
- Create a new doorbell manager
- SR-IOV fixes

amdkfd:
- Cleanup CRIU dma-buf handling
- Use KIQ to unmap HIQ
- GFX 9.4.3 debugger updates
- GFX 9.4.2 debugger fixes
- Enable cooperative groups fof gfx11
- SVM fixes

radeon:
- Lots of checkpatch cleanups

Merge conflicts:
- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
	The switch to drm eu helpers in 8a206685d36f ("drm/amdgpu: use
	drm_exec for GEM and CSA handling v2") clashed with the
	cosmetic cleanups from 30953c4d000b ("drm/amdgpu: Fix style
	issues in amdgpu_gem.c"). I
	kept the former since the cleanup up code is gone.
- drivers/gpu/drm/amd/amdgpu/atom.c.
	adf64e214280 ("drm/amd: Avoid reading the VBIOS part number
	twice") removed code that 992b8fe106ab ("drm/radeon: Replace
	all non-returning strlcpy with strscpy") polished.

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230728214228.8102-1-alexander.deucher@amd.com
[sima: some merge conflict wrangling as noted]
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

1 files changed, 19 insertions, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 65577eca58f1..458faf657042 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -762,6 +762,8 @@ static void gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 static int gfx_v9_0_ras_error_inject(struct amdgpu_device *adev,
 				     void *inject_if, uint32_t instance_mask);
 static void gfx_v9_0_reset_ras_error_count(struct amdgpu_device *adev);
+static void gfx_v9_0_update_spm_vmid_internal(struct amdgpu_device *adev,
+					      unsigned int vmid);
 
 static void gfx_v9_0_kiq_set_resources(struct amdgpu_ring *kiq_ring,
 				uint64_t queue_mask)
@@ -1632,7 +1634,7 @@ static void gfx_v9_0_init_rlcg_reg_access_ctrl(struct amdgpu_device *adev)
 {
 	struct amdgpu_rlcg_reg_access_ctrl *reg_access_ctrl;
 
-	reg_access_ctrl = &adev->gfx.rlc.reg_access_ctrl;
+	reg_access_ctrl = &adev->gfx.rlc.reg_access_ctrl[0];
 	reg_access_ctrl->scratch_reg0 = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG0);
 	reg_access_ctrl->scratch_reg1 = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG1);
 	reg_access_ctrl->scratch_reg2 = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG2);
@@ -1667,22 +1669,6 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 			return r;
 	}
 
-	switch (adev->ip_versions[GC_HWIP][0]) {
-	case IP_VERSION(9, 2, 2):
-	case IP_VERSION(9, 1, 0):
-		gfx_v9_0_init_lbpw(adev);
-		break;
-	case IP_VERSION(9, 4, 0):
-		gfx_v9_4_init_lbpw(adev);
-		break;
-	default:
-		break;
-	}
-
-	/* init spm vmid with 0xf */
-	if (adev->gfx.rlc.funcs->update_spm_vmid)
-		adev->gfx.rlc.funcs->update_spm_vmid(adev, 0xf);
-
 	return 0;
 }
 
@@ -2942,12 +2928,14 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(9, 2, 2):
 	case IP_VERSION(9, 1, 0):
+		gfx_v9_0_init_lbpw(adev);
 		if (amdgpu_lbpw == 0)
 			gfx_v9_0_enable_lbpw(adev, false);
 		else
 			gfx_v9_0_enable_lbpw(adev, true);
 		break;
 	case IP_VERSION(9, 4, 0):
+		gfx_v9_4_init_lbpw(adev);
 		if (amdgpu_lbpw > 0)
 			gfx_v9_0_enable_lbpw(adev, true);
 		else
@@ -2957,6 +2945,8 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 		break;
 	}
 
+	gfx_v9_0_update_spm_vmid_internal(adev, 0xf);
+
 	adev->gfx.rlc.funcs->start(adev);
 
 	return 0;
@@ -4881,12 +4871,11 @@ static int gfx_v9_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 	return 0;
 }
 
-static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
+static void gfx_v9_0_update_spm_vmid_internal(struct amdgpu_device *adev,
+					      unsigned int vmid)
 {
 	u32 reg, data;
 
-	amdgpu_gfx_off_ctrl(adev, false);
-
 	reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(reg);
@@ -4900,6 +4889,13 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 		WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
 	else
 		WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+}
+
+static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned int vmid)
+{
+	amdgpu_gfx_off_ctrl(adev, false);
+
+	gfx_v9_0_update_spm_vmid_internal(adev, vmid);
 
 	amdgpu_gfx_off_ctrl(adev, true);
 }
@@ -5230,6 +5226,9 @@ static void gfx_v9_0_ring_patch_de_meta(struct amdgpu_ring *ring,
 		de_payload_cpu_addr = adev->virt.csa_cpu_addr + payload_offset;
 	}
 
+	((struct v9_de_ib_state *)de_payload_cpu_addr)->ib_completion_status =
+		IB_COMPLETION_STATUS_PREEMPTED;
+
 	if (offset + (payload_size >> 2) <= ring->buf_mask + 1) {
 		memcpy((void *)&ring->ring[offset], de_payload_cpu_addr, payload_size);
 	} else {