Merge tag 'amd-drm-next-5.20-2022-07-05' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.20-2022-07-05:

amdgpu:
- Various spelling and grammer fixes
- Various eDP fixes
- Various DMCUB fixes
- VCN fixes
- GMC 11 fixes
- RAS fixes
- TMZ support for GC 10.3.7
- GPUVM TLB flush fixes
- SMU 13.0.x updates
- DCN 3.2 Support
- DCN 3.2.1 Support
- MES updates
- GFX11 modifiers support
- USB-C fixes
- MMHUB 3.0.1 support
- SDMA 6.0 doorbell fixes
- Initial devcoredump support
- Enable high priority gfx queue on asics which support it
- Enable GPU reset for SMU 13.0.4
- OLED display fixes
- MPO fixes
- DC frame size fixes
- ASPM support for PCIE 7.4/7.6
- GPU reset support for SMU 13.0.0
- GFX11 updates
- VCN JPEG fix
- BACO support for SMU 13.0.7
- VCN instance handling fix
- GFX8 GPUVM TLB flush fix
- GPU reset rework
- VCN 4.0.2 support
- GTT size fixes
- DP link training fixes
- LSDMA 6.0.1 support
- Various backlight fixes
- Color encoding fixes
- Backlight config cleanup
- VCN 4.x unified queue cleanup

amdkfd:
- MMU notifier fixes
- Updates for GC 10.3.6 and 10.3.7
- P2P DMA support using dma-buf
- Add available memory IOCTL
- SDMA 6.0.1 fix
- MES fixes
- HMM profiler support

radeon:
- License fix
- Backlight config cleanup

UAPI:
- Add available memory IOCTL to amdkfd
  Proposed userspace: https://www.mail-archive.com/amd-gfx@lists.freedesktop.org/msg75743.html
- HMM profiler support for amdkfd
  Proposed userspace: https://lists.freedesktop.org/archives/amd-gfx/2022-June/080805.html

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220705212633.6037-1-alexander.deucher@amd.com

1 files changed, 44 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index d16c8c1f72db..39597ab807d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -39,6 +39,7 @@
 #include <drm/drm_drv.h>
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
+#include "amdgpu_reset.h"
 
 /*
  * Fences
@@ -163,11 +164,16 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
 	if (job && job->job_run_counter) {
 		/* reinit seq for resubmitted jobs */
 		fence->seqno = seq;
+		/* TO be inline with external fence creation and other drivers */
+		dma_fence_get(fence);
 	} else {
-		if (job)
+		if (job) {
 			dma_fence_init(fence, &amdgpu_job_fence_ops,
 				       &ring->fence_drv.lock,
 				       adev->fence_context + ring->idx, seq);
+			/* Against remove in amdgpu_job_{free, free_cb} */
+			dma_fence_get(fence);
+		}
 		else
 			dma_fence_init(fence, &amdgpu_fence_ops,
 				       &ring->fence_drv.lock,
@@ -531,6 +537,24 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 	}
 }
 
+/* Will either stop and flush handlers for amdgpu interrupt or reanble it */
+void amdgpu_fence_driver_isr_toggle(struct amdgpu_device *adev, bool stop)
+{
+	int i;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->fence_drv.initialized || !ring->fence_drv.irq_src)
+			continue;
+
+		if (stop)
+			disable_irq(adev->irq.irq);
+		else
+			enable_irq(adev->irq.irq);
+	}
+}
+
 void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
 {
 	unsigned int i, j;
@@ -594,8 +618,10 @@ void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
 	for (i = 0; i <= ring->fence_drv.num_fences_mask; i++) {
 		ptr = &ring->fence_drv.fences[i];
 		old = rcu_dereference_protected(*ptr, 1);
-		if (old && old->ops == &amdgpu_job_fence_ops)
+		if (old && old->ops == &amdgpu_job_fence_ops) {
 			RCU_INIT_POINTER(*ptr, NULL);
+			dma_fence_put(old);
+		}
 	}
 }
 
@@ -798,7 +824,10 @@ static int gpu_recover_get(void *data, u64 *val)
 		return 0;
 	}
 
-	*val = amdgpu_device_gpu_recover(adev, NULL);
+	if (amdgpu_reset_domain_schedule(adev->reset_domain, &adev->reset_work))
+		flush_work(&adev->reset_work);
+
+	*val = atomic_read(&adev->reset_domain->reset_res);
 
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
@@ -810,6 +839,14 @@ DEFINE_SHOW_ATTRIBUTE(amdgpu_debugfs_fence_info);
 DEFINE_DEBUGFS_ATTRIBUTE(amdgpu_debugfs_gpu_recover_fops, gpu_recover_get, NULL,
 			 "%lld\n");
 
+static void amdgpu_debugfs_reset_work(struct work_struct *work)
+{
+	struct amdgpu_device *adev = container_of(work, struct amdgpu_device,
+						  reset_work);
+
+	amdgpu_device_gpu_recover(adev, NULL);
+}
+
 #endif
 
 void amdgpu_debugfs_fence_init(struct amdgpu_device *adev)
@@ -821,9 +858,12 @@ void amdgpu_debugfs_fence_init(struct amdgpu_device *adev)
 	debugfs_create_file("amdgpu_fence_info", 0444, root, adev,
 			    &amdgpu_debugfs_fence_info_fops);
 
-	if (!amdgpu_sriov_vf(adev))
+	if (!amdgpu_sriov_vf(adev)) {
+
+		INIT_WORK(&adev->reset_work, amdgpu_debugfs_reset_work);
 		debugfs_create_file("amdgpu_gpu_recover", 0444, root, adev,
 				    &amdgpu_debugfs_gpu_recover_fops);
+	}
 #endif
 }