Merge tag 'amd-drm-next-6.9-2024-02-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.9-2024-02-09:

amdgpu:
- Validate DMABuf imports in compute VMs
- Add RAS ACA framework
- PSP 13 fixes
- Misc code cleanups
- Replay fixes
- Atom interpretor PS, WS bounds checking
- DML2 fixes
- Audio fixes
- DCN 3.5 Z state fixes
- Remove deprecated ida_simple usage
- UBSAN fixes
- RAS fixes
- Enable seq64 infrastructure
- DC color block enablement
- Documentation updates
- DC documentation updates
- DMCUB updates
- S3 fixes
- VCN 4.0.5 fixes
- DP MST fixes
- SR-IOV fixes

amdkfd:
- Validate DMABuf imports in compute VMs
- SVM fixes
- Trap handler updates

radeon:
- Atom interpretor PS, WS bounds checking
- Misc code cleanups

UAPI:
- Bump KFD version so UMDs know that the fixes that enable the management of
  VA mappings in compute VMs using the GEM_VA ioctl for DMABufs exported from KFD are present
- Add INFO query for input power.  This matches the existing INFO query for average
  power.  Used in gaming HUDs, etc.
  Example userspace: https://github.com/Umio-Yasuno/libdrm-amdgpu-sys-rs/tree/input_power

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240209221459.5453-1-alexander.deucher@amd.com

1 files changed, 20 insertions, 63 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 0dcff2889e25..6ff7d3fb2008 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -71,59 +71,6 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
 		amdgpu_num_kcq = 2;
 }
 
-void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
-					uint32_t reg0, uint32_t reg1,
-					uint32_t ref, uint32_t mask,
-					uint32_t xcc_inst)
-{
-	struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_inst];
-	struct amdgpu_ring *ring = &kiq->ring;
-	signed long r, cnt = 0;
-	unsigned long flags;
-	uint32_t seq;
-
-	if (adev->mes.ring.sched.ready) {
-		amdgpu_mes_reg_write_reg_wait(adev, reg0, reg1,
-					      ref, mask);
-		return;
-	}
-
-	spin_lock_irqsave(&kiq->ring_lock, flags);
-	amdgpu_ring_alloc(ring, 32);
-	amdgpu_ring_emit_reg_write_reg_wait(ring, reg0, reg1,
-					    ref, mask);
-	r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
-	if (r)
-		goto failed_undo;
-
-	amdgpu_ring_commit(ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
-	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
-
-	/* don't wait anymore for IRQ context */
-	if (r < 1 && in_interrupt())
-		goto failed_kiq;
-
-	might_sleep();
-	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
-
-		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
-		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
-	}
-
-	if (cnt > MAX_KIQ_REG_TRY)
-		goto failed_kiq;
-
-	return;
-
-failed_undo:
-	amdgpu_ring_undo(ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-failed_kiq:
-	dev_err(adev->dev, "failed to write reg %x wait reg %x\n", reg0, reg1);
-}
-
 /**
  * amdgpu_virt_request_full_gpu() - request full gpu access
  * @adev:	amdgpu device.
@@ -303,11 +250,11 @@ static int amdgpu_virt_init_ras_err_handler_data(struct amdgpu_device *adev)
 	if (!*data)
 		goto data_failure;
 
-	bps = kmalloc_array(align_space, sizeof((*data)->bps), GFP_KERNEL);
+	bps = kmalloc_array(align_space, sizeof(*(*data)->bps), GFP_KERNEL);
 	if (!bps)
 		goto bps_failure;
 
-	bps_bo = kmalloc_array(align_space, sizeof((*data)->bps_bo), GFP_KERNEL);
+	bps_bo = kmalloc_array(align_space, sizeof(*(*data)->bps_bo), GFP_KERNEL);
 	if (!bps_bo)
 		goto bps_bo_failure;
 
@@ -340,8 +287,10 @@ static void amdgpu_virt_ras_release_bp(struct amdgpu_device *adev)
 
 	for (i = data->last_reserved - 1; i >= 0; i--) {
 		bo = data->bps_bo[i];
-		amdgpu_bo_free_kernel(&bo, NULL, NULL);
-		data->bps_bo[i] = bo;
+		if (bo) {
+			amdgpu_bo_free_kernel(&bo, NULL, NULL);
+			data->bps_bo[i] = bo;
+		}
 		data->last_reserved = i;
 	}
 }
@@ -381,6 +330,8 @@ static void amdgpu_virt_ras_reserve_bps(struct amdgpu_device *adev)
 {
 	struct amdgpu_virt *virt = &adev->virt;
 	struct amdgpu_virt_ras_err_handler_data *data = virt->virt_eh_data;
+	struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr;
+	struct ttm_resource_manager *man = &mgr->manager;
 	struct amdgpu_bo *bo = NULL;
 	uint64_t bp;
 	int i;
@@ -396,12 +347,18 @@ static void amdgpu_virt_ras_reserve_bps(struct amdgpu_device *adev)
 		 * 2) a ras bad page has been reserved (duplicate error injection
 		 *    for one page);
 		 */
-		if (amdgpu_bo_create_kernel_at(adev, bp << AMDGPU_GPU_PAGE_SHIFT,
-					       AMDGPU_GPU_PAGE_SIZE,
-					       &bo, NULL))
-			DRM_DEBUG("RAS WARN: reserve vram for retired page %llx fail\n", bp);
-
-		data->bps_bo[i] = bo;
+		if  (ttm_resource_manager_used(man)) {
+			amdgpu_vram_mgr_reserve_range(&adev->mman.vram_mgr,
+				bp << AMDGPU_GPU_PAGE_SHIFT,
+				AMDGPU_GPU_PAGE_SIZE);
+			data->bps_bo[i] = NULL;
+		} else {
+			if (amdgpu_bo_create_kernel_at(adev, bp << AMDGPU_GPU_PAGE_SHIFT,
+							AMDGPU_GPU_PAGE_SIZE,
+							&bo, NULL))
+				DRM_DEBUG("RAS WARN: reserve vram for retired page %llx fail\n", bp);
+			data->bps_bo[i] = bo;
+		}
 		data->last_reserved = i + 1;
 		bo = NULL;
 	}