Merge tag 'drm-misc-next-2019-05-24' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for v5.3, try #2:

UAPI Changes:
- Add HDR source metadata property.
- Make drm.h compile on GNU/kFreeBSD by including stdint.h
- Clarify how the userspace reviewer has to review new kernel UAPI.
- Clarify that for using new UAPI, merging to drm-next or drm-misc-next should be enough.

Cross-subsystem Changes:
- video/hdmi: Add unpack function for DRM infoframes.
- Device tree bindings:
  * Updating a property for Mali Midgard GPUs
  * Updating a property for STM32 DSI panel
  * Adding support for FriendlyELEC HD702E 800x1280 panel
  * Adding support for Evervision VGG804821 800x480 5.0" WVGA TFT panel
  * Adding support for the EDT ET035012DM6 3.5" 320x240 QVGA 24-bit RGB TFT.
  * Adding support for Three Five displays TFC S9700RTWV43TR-01B 800x480 panel
    with resistive touch found on TI's AM335X-EVM.
  * Adding support for EDT ETM0430G0DH6 480x272 panel.
- Add OSD101T2587-53TS driver with DT bindings.
- Add Samsung S6E63M0 panel driver with DT bindings.
- Add VXT VL050-8048NT-C01 800x480 panel with DT bindings.
- Dma-buf:
  - Make mmap callback actually optional.
  - Documentation updates.
  - Fix debugfs refcount inbalance.
  - Remove unused sync_dump function.
- Fix device tree bindings in drm-misc-next after a botched merge.

Core Changes:
- Add support for HDR infoframes and related EDID parsing.
- Remove prime sg_table caching, now done inside dma-buf.
- Add shiny new drm_gem_vram helpers for simple VRAM drivers;
  with some fixes to the new API on top.
- Small fix to job cleanup without timeout handler.
- Documentation fixes to drm_fourcc.
- Replace lookups of drm_format with struct drm_format_info;
  remove functions that become obsolete by this conversion.
- Remove double include in bridge/panel.c and some drivers.
- Remove drmP.h include from drm/edid and drm/dp.
- Fix null pointer deref in drm_fb_helper_hotplug_event().
- Remove most members from drm_fb_helper_crtc, only mode_set is kept.
- Remove race of fb helpers with userspace; only restore mode
  when userspace is not master.
- Move legacy setup from drm_file.c to drm_legacy_misc.c
- Rework scheduler job destruction.
- drm/bus was removed, remove from TODO.
- Add __drm_atomic_helper_crtc_reset() to subclass crtc_state,
  and convert some drivers to use it (conversion is not complete yet).
- Bump vblank timeout wait to 100 ms for atomic.
- Docbook fix for drm_hdmi_infoframe_set_hdr_metadata.

Driver Changes:
- sun4i: Use DRM_GEM_CMA_VMAP_DRIVER_OPS instead of definining manually.
- v3d: Small cleanups, adding support for compute shaders,
       reservation/synchronization fixes and job management refactoring,
       fixes MMU and debugfs.
- lima: Fix null pointer in irq handler on startup, set default timeout for scheduled jobs.
- stm/ltdc: Assorted fixes and adding FB modifier support.
- amdgpu: Avoid hw reset if guilty job was already signaled.
- virtio: Add seqno to fences, add trace events, use correct flags for fence allocation.
- Convert AST, bochs, mgag200, vboxvideo, hisilicon to the new drm_gem_vram API.
- sun6i_mipi_dsi: Support DSI GENERIC_SHORT_WRITE_2 transfers.
- bochs: Small fix to use PTR_RET_OR_ZERO and driver unload.
- gma500: header fixes
- cirrus: Remove unused files.
- mediatek: Fix compiler warning after merging the HDR series.
- vc4: Rework binner bo handling.

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/052875a5-27ba-3832-60c2-193d950afdff@linux.intel.com

1 files changed, 95 insertions, 51 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index cc8ad3831982..9f282e971197 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3341,8 +3341,6 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 		if (!ring || !ring->sched.thread)
 			continue;
 
-		drm_sched_stop(&ring->sched);
-
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
 	}
@@ -3350,8 +3348,7 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	if(job)
 		drm_sched_increase_karma(&job->base);
 
-
-
+	/* Don't suspend on bare metal if we are not going to HW reset the ASIC */
 	if (!amdgpu_sriov_vf(adev)) {
 
 		if (!need_full_reset)
@@ -3489,38 +3486,21 @@ end:
 	return r;
 }
 
-static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev,
-					  struct amdgpu_job *job)
+static bool amdgpu_device_lock_adev(struct amdgpu_device *adev, bool trylock)
 {
-	int i;
-
-	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
-		struct amdgpu_ring *ring = adev->rings[i];
-
-		if (!ring || !ring->sched.thread)
-			continue;
+	if (trylock) {
+		if (!mutex_trylock(&adev->lock_reset))
+			return false;
+	} else
+		mutex_lock(&adev->lock_reset);
 
-		if (!adev->asic_reset_res)
-			drm_sched_resubmit_jobs(&ring->sched);
-
-		drm_sched_start(&ring->sched, !adev->asic_reset_res);
-	}
-
-	if (!amdgpu_device_has_dc_support(adev)) {
-		drm_helper_resume_force_mode(adev->ddev);
-	}
-
-	adev->asic_reset_res = 0;
-}
-
-static void amdgpu_device_lock_adev(struct amdgpu_device *adev)
-{
-	mutex_lock(&adev->lock_reset);
 	atomic_inc(&adev->gpu_reset_counter);
 	adev->in_gpu_reset = 1;
 	/* Block kfd: SRIOV would do it separately */
 	if (!amdgpu_sriov_vf(adev))
                 amdgpu_amdkfd_pre_reset(adev);
+
+	return true;
 }
 
 static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
@@ -3548,40 +3528,42 @@ static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
 int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			      struct amdgpu_job *job)
 {
-	int r;
+	struct list_head device_list, *device_list_handle =  NULL;
+	bool need_full_reset, job_signaled;
 	struct amdgpu_hive_info *hive = NULL;
-	bool need_full_reset = false;
 	struct amdgpu_device *tmp_adev = NULL;
-	struct list_head device_list, *device_list_handle =  NULL;
+	int i, r = 0;
 
+	need_full_reset = job_signaled = false;
 	INIT_LIST_HEAD(&device_list);
 
 	dev_info(adev->dev, "GPU reset begin!\n");
 
+	hive = amdgpu_get_xgmi_hive(adev, false);
+
 	/*
-	 * In case of XGMI hive disallow concurrent resets to be triggered
-	 * by different nodes. No point also since the one node already executing
-	 * reset will also reset all the other nodes in the hive.
+	 * Here we trylock to avoid chain of resets executing from
+	 * either trigger by jobs on different adevs in XGMI hive or jobs on
+	 * different schedulers for same device while this TO handler is running.
+	 * We always reset all schedulers for device and all devices for XGMI
+	 * hive so that should take care of them too.
 	 */
-	hive = amdgpu_get_xgmi_hive(adev, 0);
-	if (hive && adev->gmc.xgmi.num_physical_nodes > 1 &&
-	    !mutex_trylock(&hive->reset_lock))
+
+	if (hive && !mutex_trylock(&hive->reset_lock)) {
+		DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
+			 job->base.id, hive->hive_id);
 		return 0;
+	}
 
 	/* Start with adev pre asic reset first for soft reset check.*/
-	amdgpu_device_lock_adev(adev);
-	r = amdgpu_device_pre_asic_reset(adev,
-					 job,
-					 &need_full_reset);
-	if (r) {
-		/*TODO Should we stop ?*/
-		DRM_ERROR("GPU pre asic reset failed with err, %d for drm dev, %s ",
-			  r, adev->ddev->unique);
-		adev->asic_reset_res = r;
+	if (!amdgpu_device_lock_adev(adev, !hive)) {
+		DRM_INFO("Bailing on TDR for s_job:%llx, as another already in progress",
+					 job->base.id);
+		return 0;
 	}
 
 	/* Build list of devices to reset */
-	if  (need_full_reset && adev->gmc.xgmi.num_physical_nodes > 1) {
+	if  (adev->gmc.xgmi.num_physical_nodes > 1) {
 		if (!hive) {
 			amdgpu_device_unlock_adev(adev);
 			return -ENODEV;
@@ -3598,13 +3580,56 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		device_list_handle = &device_list;
 	}
 
+	/* block all schedulers and reset given job's ring */
+	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
+		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+			struct amdgpu_ring *ring = tmp_adev->rings[i];
+
+			if (!ring || !ring->sched.thread)
+				continue;
+
+			drm_sched_stop(&ring->sched, &job->base);
+		}
+	}
+
+
+	/*
+	 * Must check guilty signal here since after this point all old
+	 * HW fences are force signaled.
+	 *
+	 * job->base holds a reference to parent fence
+	 */
+	if (job && job->base.s_fence->parent &&
+	    dma_fence_is_signaled(job->base.s_fence->parent))
+		job_signaled = true;
+
+	if (!amdgpu_device_ip_need_full_reset(adev))
+		device_list_handle = &device_list;
+
+	if (job_signaled) {
+		dev_info(adev->dev, "Guilty job already signaled, skipping HW reset");
+		goto skip_hw_reset;
+	}
+
+
+	/* Guilty job will be freed after this*/
+	r = amdgpu_device_pre_asic_reset(adev,
+					 job,
+					 &need_full_reset);
+	if (r) {
+		/*TODO Should we stop ?*/
+		DRM_ERROR("GPU pre asic reset failed with err, %d for drm dev, %s ",
+			  r, adev->ddev->unique);
+		adev->asic_reset_res = r;
+	}
+
 retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 
 		if (tmp_adev == adev)
 			continue;
 
-		amdgpu_device_lock_adev(tmp_adev);
+		amdgpu_device_lock_adev(tmp_adev, false);
 		r = amdgpu_device_pre_asic_reset(tmp_adev,
 						 NULL,
 						 &need_full_reset);
@@ -3628,9 +3653,28 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 			goto retry;
 	}
 
+skip_hw_reset:
+
 	/* Post ASIC reset for all devs .*/
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
-		amdgpu_device_post_asic_reset(tmp_adev, tmp_adev == adev ? job : NULL);
+		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+			struct amdgpu_ring *ring = tmp_adev->rings[i];
+
+			if (!ring || !ring->sched.thread)
+				continue;
+
+			/* No point to resubmit jobs if we didn't HW reset*/
+			if (!tmp_adev->asic_reset_res && !job_signaled)
+				drm_sched_resubmit_jobs(&ring->sched);
+
+			drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
+		}
+
+		if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) {
+			drm_helper_resume_force_mode(tmp_adev->ddev);
+		}
+
+		tmp_adev->asic_reset_res = 0;
 
 		if (r) {
 			/* bad news, how to tell it to userspace ? */
@@ -3643,7 +3687,7 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 		amdgpu_device_unlock_adev(tmp_adev);
 	}
 
-	if (hive && adev->gmc.xgmi.num_physical_nodes > 1)
+	if (hive)
 		mutex_unlock(&hive->reset_lock);
 
 	if (r)