Merge tag 'drm-next-2022-12-23' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Holiday fixes!

  Two batches from amd, and one group of i915 changes.

  amdgpu:
   - Spelling fix
   - BO pin fix
   - Properly handle polaris 10/11 overlap asics
   - GMC9 fix
   - SR-IOV suspend fix
   - DCN 3.1.4 fix
   - KFD userptr locking fix
   - SMU13.x fixes
   - GDS/GWS/OA handling fix
   - Reserved VMID handling fixes
   - FRU EEPROM fix
   - BO validation fixes
   - Avoid large variable on the stack
   - S0ix fixes
   - SMU 13.x fixes
   - VCN fix
   - Add missing fence reference

  amdkfd:
   - Fix init vm error handling
   - Fix double release of compute pasid

  i915
   - Documentation fixes
   - OA-perf related fix
   - VLV/CHV HDMI/DP audio fix
   - Display DDI/Transcoder fix
   - Migrate fixes"

* tag 'drm-next-2022-12-23' of git://anongit.freedesktop.org/drm/drm: (39 commits)
  drm/amdgpu: grab extra fence reference for drm_sched_job_add_dependency
  drm/amdgpu: enable VCN DPG for GC IP v11.0.4
  drm/amdgpu: skip mes self test after s0i3 resume for MES IP v11.0
  drm/amd/pm: correct the fan speed retrieving in PWM for some SMU13 asics
  drm/amd/pm: bump SMU13.0.0 driver_if header to version 0x34
  drm/amdgpu: skip MES for S0ix as well since it's part of GFX
  drm/amd/pm: avoid large variable on kernel stack
  drm/amdkfd: Fix double release compute pasid
  drm/amdkfd: Fix kfd_process_device_init_vm error handling
  drm/amd/pm: update SMU13.0.0 reported maximum shader clock
  drm/amd/pm: correct SMU13.0.0 pstate profiling clock settings
  drm/amd/pm: enable GPO dynamic control support for SMU13.0.7
  drm/amd/pm: enable GPO dynamic control support for SMU13.0.0
  drm/amdgpu: revert "generally allow over-commit during BO allocation"
  drm/amdgpu: Remove unnecessary domain argument
  drm/amdgpu: Fix size validation for non-exclusive domains (v4)
  drm/amdgpu: Check if fru_addr is not NULL (v2)
  drm/i915/ttm: consider CCS for backup objects
  drm/i915/migrate: fix corner case in CCS aux copying
  drm/amdgpu: rework reserved VMID handling
  ...

1 files changed, 24 insertions, 55 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c05cff979004..dc379dc22c77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -484,25 +484,20 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 	unsigned vmhub = ring->funcs->vmhub;
 	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
-	struct amdgpu_vmid *id;
-	bool gds_switch_needed;
-	bool vm_flush_needed = job->vm_needs_flush || ring->has_compute_vm_bug;
 
 	if (job->vmid == 0)
 		return false;
-	id = &id_mgr->ids[job->vmid];
-	gds_switch_needed = ring->funcs->emit_gds_switch && (
-		id->gds_base != job->gds_base ||
-		id->gds_size != job->gds_size ||
-		id->gws_base != job->gws_base ||
-		id->gws_size != job->gws_size ||
-		id->oa_base != job->oa_base ||
-		id->oa_size != job->oa_size);
-
-	if (amdgpu_vmid_had_gpu_reset(adev, id))
+
+	if (job->vm_needs_flush || ring->has_compute_vm_bug)
+		return true;
+
+	if (ring->funcs->emit_gds_switch && job->gds_switch_needed)
+		return true;
+
+	if (amdgpu_vmid_had_gpu_reset(adev, &id_mgr->ids[job->vmid]))
 		return true;
 
-	return vm_flush_needed || gds_switch_needed;
+	return false;
 }
 
 /**
@@ -524,27 +519,20 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 	unsigned vmhub = ring->funcs->vmhub;
 	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
 	struct amdgpu_vmid *id = &id_mgr->ids[job->vmid];
-	bool gds_switch_needed = ring->funcs->emit_gds_switch && (
-		id->gds_base != job->gds_base ||
-		id->gds_size != job->gds_size ||
-		id->gws_base != job->gws_base ||
-		id->gws_size != job->gws_size ||
-		id->oa_base != job->oa_base ||
-		id->oa_size != job->oa_size);
+	bool spm_update_needed = job->spm_update_needed;
+	bool gds_switch_needed = ring->funcs->emit_gds_switch &&
+		job->gds_switch_needed;
 	bool vm_flush_needed = job->vm_needs_flush;
 	struct dma_fence *fence = NULL;
 	bool pasid_mapping_needed = false;
 	unsigned patch_offset = 0;
-	bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] != NULL));
 	int r;
 
-	if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid)
-		adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid);
-
 	if (amdgpu_vmid_had_gpu_reset(adev, id)) {
 		gds_switch_needed = true;
 		vm_flush_needed = true;
 		pasid_mapping_needed = true;
+		spm_update_needed = true;
 	}
 
 	mutex_lock(&id_mgr->lock);
@@ -577,6 +565,17 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 	if (pasid_mapping_needed)
 		amdgpu_gmc_emit_pasid_mapping(ring, job->vmid, job->pasid);
 
+	if (spm_update_needed && adev->gfx.rlc.funcs->update_spm_vmid)
+		adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid);
+
+	if (!ring->is_mes_queue && ring->funcs->emit_gds_switch &&
+	    gds_switch_needed) {
+		amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base,
+					    job->gds_size, job->gws_base,
+					    job->gws_size, job->oa_base,
+					    job->oa_size);
+	}
+
 	if (vm_flush_needed || pasid_mapping_needed) {
 		r = amdgpu_fence_emit(ring, &fence, NULL, 0);
 		if (r)
@@ -601,20 +600,6 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 	}
 	dma_fence_put(fence);
 
-	if (!ring->is_mes_queue && ring->funcs->emit_gds_switch &&
-	    gds_switch_needed) {
-		id->gds_base = job->gds_base;
-		id->gds_size = job->gds_size;
-		id->gws_base = job->gws_base;
-		id->gws_size = job->gws_size;
-		id->oa_base = job->oa_base;
-		id->oa_size = job->oa_size;
-		amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base,
-					    job->gds_size, job->gws_base,
-					    job->gws_size, job->oa_base,
-					    job->oa_size);
-	}
-
 	if (ring->funcs->patch_cond_exec)
 		amdgpu_ring_patch_cond_exec(ring, patch_offset);
 
@@ -2383,7 +2368,6 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	union drm_amdgpu_vm *args = data;
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	long timeout = msecs_to_jiffies(2000);
 	int r;
 
 	switch (args->in.op) {
@@ -2395,21 +2379,6 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			return r;
 		break;
 	case AMDGPU_VM_OP_UNRESERVE_VMID:
-		if (amdgpu_sriov_runtime(adev))
-			timeout = 8 * timeout;
-
-		/* Wait vm idle to make sure the vmid set in SPM_VMID is
-		 * not referenced anymore.
-		 */
-		r = amdgpu_bo_reserve(fpriv->vm.root.bo, true);
-		if (r)
-			return r;
-
-		r = amdgpu_vm_wait_idle(&fpriv->vm, timeout);
-		if (r < 0)
-			return r;
-
-		amdgpu_bo_unreserve(fpriv->vm.root.bo);
 		amdgpu_vmid_free_reserved(adev, &fpriv->vm, AMDGPU_GFXHUB_0);
 		break;
 	default: