Merge tag 'amd-drm-next-6.4-2023-04-14' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.4-2023-04-14:

amdgpu:
- S4 fixes for APUs
- GFX11 fixes
- Misc code cleanups
- DCN 3.2 fixes
- DCN 3.1.4 fixes
- FPO/FAMS work to improve display power savings
- DP fixes
- UMC 8.10 code cleanup
- SDMA v4 fix
- GPU clock counter fixes
- SMU 13 fixes
- Sdma v6 invalidation fix for preemption
- RAS fixes
- S0ix fix
- GC 9.4.3 updates

amdkfd:
- Fix user pointers with IOMMU
- Fix coherency flag handling

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230414204609.7942-1-alexander.deucher@amd.com

1 files changed, 18 insertions, 16 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fac9312b1695..a2292acf06d0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -602,7 +602,7 @@ u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index)
 	if (amdgpu_device_skip_hw_access(adev))
 		return 0;
 
-	if (index < adev->doorbell.num_doorbells) {
+	if (index < adev->doorbell.num_kernel_doorbells) {
 		return readl(adev->doorbell.ptr + index);
 	} else {
 		DRM_ERROR("reading beyond doorbell aperture: 0x%08x!\n", index);
@@ -625,7 +625,7 @@ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v)
 	if (amdgpu_device_skip_hw_access(adev))
 		return;
 
-	if (index < adev->doorbell.num_doorbells) {
+	if (index < adev->doorbell.num_kernel_doorbells) {
 		writel(v, adev->doorbell.ptr + index);
 	} else {
 		DRM_ERROR("writing beyond doorbell aperture: 0x%08x!\n", index);
@@ -646,7 +646,7 @@ u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index)
 	if (amdgpu_device_skip_hw_access(adev))
 		return 0;
 
-	if (index < adev->doorbell.num_doorbells) {
+	if (index < adev->doorbell.num_kernel_doorbells) {
 		return atomic64_read((atomic64_t *)(adev->doorbell.ptr + index));
 	} else {
 		DRM_ERROR("reading beyond doorbell aperture: 0x%08x!\n", index);
@@ -669,7 +669,7 @@ void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v)
 	if (amdgpu_device_skip_hw_access(adev))
 		return;
 
-	if (index < adev->doorbell.num_doorbells) {
+	if (index < adev->doorbell.num_kernel_doorbells) {
 		atomic64_set((atomic64_t *)(adev->doorbell.ptr + index), v);
 	} else {
 		DRM_ERROR("writing beyond doorbell aperture: 0x%08x!\n", index);
@@ -1060,7 +1060,7 @@ static int amdgpu_device_doorbell_init(struct amdgpu_device *adev)
 	if (adev->asic_type < CHIP_BONAIRE) {
 		adev->doorbell.base = 0;
 		adev->doorbell.size = 0;
-		adev->doorbell.num_doorbells = 0;
+		adev->doorbell.num_kernel_doorbells = 0;
 		adev->doorbell.ptr = NULL;
 		return 0;
 	}
@@ -1075,27 +1075,27 @@ static int amdgpu_device_doorbell_init(struct amdgpu_device *adev)
 	adev->doorbell.size = pci_resource_len(adev->pdev, 2);
 
 	if (adev->enable_mes) {
-		adev->doorbell.num_doorbells =
+		adev->doorbell.num_kernel_doorbells =
 			adev->doorbell.size / sizeof(u32);
 	} else {
-		adev->doorbell.num_doorbells =
+		adev->doorbell.num_kernel_doorbells =
 			min_t(u32, adev->doorbell.size / sizeof(u32),
 			      adev->doorbell_index.max_assignment+1);
-		if (adev->doorbell.num_doorbells == 0)
+		if (adev->doorbell.num_kernel_doorbells == 0)
 			return -EINVAL;
 
 		/* For Vega, reserve and map two pages on doorbell BAR since SDMA
 		 * paging queue doorbell use the second page. The
 		 * AMDGPU_DOORBELL64_MAX_ASSIGNMENT definition assumes all the
 		 * doorbells are in the first page. So with paging queue enabled,
-		 * the max num_doorbells should + 1 page (0x400 in dword)
+		 * the max num_kernel_doorbells should + 1 page (0x400 in dword)
 		 */
 		if (adev->asic_type >= CHIP_VEGA10)
-			adev->doorbell.num_doorbells += 0x400;
+			adev->doorbell.num_kernel_doorbells += 0x400;
 	}
 
 	adev->doorbell.ptr = ioremap(adev->doorbell.base,
-				     adev->doorbell.num_doorbells *
+				     adev->doorbell.num_kernel_doorbells *
 				     sizeof(u32));
 	if (adev->doorbell.ptr == NULL)
 		return -ENOMEM;
@@ -2184,7 +2184,6 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		adev->has_pr3 = parent ? pci_pr3_present(parent) : false;
 	}
 
-	amdgpu_amdkfd_device_probe(adev);
 
 	adev->pm.pp_feature = amdgpu_pp_feature_mask;
 	if (amdgpu_sriov_vf(adev) || sched_policy == KFD_SCHED_POLICY_NO_HWS)
@@ -2240,6 +2239,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (!total)
 		return -ENODEV;
 
+	amdgpu_amdkfd_device_probe(adev);
 	adev->cg_flags &= amdgpu_cg_mask;
 	adev->pg_flags &= amdgpu_pg_mask;
 
@@ -2365,7 +2365,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
 		}
 
 		r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
-				   ring->num_hw_submission, amdgpu_job_hang_limit,
+				   ring->num_hw_submission, 0,
 				   timeout, adev->reset_domain->wq,
 				   ring->sched_score, ring->name,
 				   adev->dev);
@@ -3305,9 +3305,11 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 {
 	int r;
 
-	r = amdgpu_amdkfd_resume_iommu(adev);
-	if (r)
-		return r;
+	if (!adev->in_s0ix) {
+		r = amdgpu_amdkfd_resume_iommu(adev);
+		if (r)
+			return r;
+	}
 
 	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)