Merge tag 'drm-misc-next-2021-06-01' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for 5.14:

UAPI Changes:

 * Use DRM driver names for fbdev

Cross-subsystem Changes:

Core Changes:

 * Fix leaked DMA handles

 * Improve documentation around DRM_CLIENT_CAP_*

 * Cleanups

 * dp_mst: Use kHz as link-rate unit during init

 * fourcc: Remove drm_gem_format_name() and drm_format_name_buf

 * gem-cma: Fix mmap for buffers with write combining

 * ttm: Don't override pre-set vm_ops; ttm_bo_mmap() removal and cleanups

Driver Changes:

 * drm/amdgpu: Fix hot unplug during suspend; Implement mmap as GEM object
   function; Use %p4cc format-string modifier; Cleanups

 * drm/bridge: Cdns: Fix PM reference leak, Cleanups; Lt8912b: Fix Coccinelle
   warnings; Fix Kconfig dependencies; Fixes and cleanups

 * drm/hisilicon/kirin: Cleanups

 * drm/nouveau: Implement mmap as GEM object function

 * drm/radeon: Implement mmap as GEM object function

 * drm/rockchip: Remove generic drivers during init; Add scaling for RK3036
   win1; Fix missing registers for RK3066 and 3188; Add alpha support for
   RK3036, RK3066, RK3126 and RK3188; Fixes and cleanups

 * drm/simpledrm: Use %p4cc: format-string modifier

 * drm/vmwgfx: Cleanups

 * fbdev/matrox: Use modern module_init()

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

From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/YLZOKiYE6XFmE/MH@linux-uq9g.fritz.box

1 files changed, 16 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 759b34799221..d33e6d97cc89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -25,6 +25,8 @@
 #include <linux/wait.h>
 #include <linux/sched.h>
 
+#include <drm/drm_drv.h>
+
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 
@@ -34,6 +36,15 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	struct amdgpu_job *job = to_amdgpu_job(s_job);
 	struct amdgpu_task_info ti;
 	struct amdgpu_device *adev = ring->adev;
+	int idx;
+
+	if (!drm_dev_enter(&adev->ddev, &idx)) {
+		DRM_INFO("%s - device unplugged skipping recovery on scheduler:%s",
+			 __func__, s_job->sched->name);
+
+		/* Effectively the job is aborted as the device is gone */
+		return DRM_GPU_SCHED_STAT_ENODEV;
+	}
 
 	memset(&ti, 0, sizeof(struct amdgpu_task_info));
 
@@ -41,7 +52,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	    amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
 		DRM_ERROR("ring %s timeout, but soft recovered\n",
 			  s_job->sched->name);
-		return DRM_GPU_SCHED_STAT_NOMINAL;
+		goto exit;
 	}
 
 	amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti);
@@ -53,13 +64,15 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 	if (amdgpu_device_should_recover_gpu(ring->adev)) {
 		amdgpu_device_gpu_recover(ring->adev, job);
-		return DRM_GPU_SCHED_STAT_NOMINAL;
 	} else {
 		drm_sched_suspend_timeout(&ring->sched);
 		if (amdgpu_sriov_vf(adev))
 			adev->virt.tdr_debug = true;
-		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
+
+exit:
+	drm_dev_exit(idx);
+	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,