[PATCH] drm/amdgpu: reset asic after system-wide suspend aborted

[Prike Liang]

Do ASIC reset at the moment Sx suspend aborted behind of amdgpu suspend
to keep AMDGPU in a clean reset state and that can avoid re-initialize
device improperly error.

Signed-off-by: Prike Liang <prike.li...@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  4 ++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    | 19 +++++++++++++++++++
 3 files changed, 24 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h 
b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b85b67a..8bd9833 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1053,6 +1053,7 @@ struct amdgpu_device {
        bool                            in_s3;
        bool                            in_s4;
        bool                            in_s0ix;
+       bool                            pm_completed;
 
        atomic_t                        in_gpu_reset;
        enum pp_mp1_state               mp1_state;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ec42a6f..a12ed54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3983,6 +3983,10 @@ int amdgpu_device_resume(struct drm_device *dev, bool 
fbcon)
        if (adev->in_s0ix)
                amdgpu_gfx_state_change_set(adev, sGpuChangeState_D0Entry);
 
+       if (!adev->pm_completed) {
+               dev_warn(adev->dev, "suspend aborted will do asic reset\n");
+               amdgpu_asic_reset(adev);
+       }
        /* post card */
        if (amdgpu_device_need_post(adev)) {
                r = amdgpu_device_asic_init(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index eee3cf8..9f90017 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2168,6 +2168,23 @@ static int amdgpu_pmops_suspend(struct device *dev)
        return r;
 }
 
+/*
+ * Actually the PM suspend whether is completed should be confirmed
+ * by checking the sysfs sys/power/suspend_stats/failed_suspend.However,
+ * in this function only check the AMDGPU device whether is suspended
+ * completely in the system-wide suspend process.
+ */
+static int amdgpu_pmops_noirq_suspend(struct device *dev)
+{
+       struct drm_device *drm_dev = dev_get_drvdata(dev);
+       struct amdgpu_device *adev = drm_to_adev(drm_dev);
+
+       dev_dbg(dev, "amdgpu suspend completely.\n");
+       adev->pm_completed = true;
+
+       return 0;
+}
+
 static int amdgpu_pmops_resume(struct device *dev)
 {
        struct drm_device *drm_dev = dev_get_drvdata(dev);
@@ -2181,6 +2198,7 @@ static int amdgpu_pmops_resume(struct device *dev)
        r = amdgpu_device_resume(drm_dev, true);
        if (amdgpu_acpi_is_s0ix_active(adev))
                adev->in_s0ix = false;
+       adev->pm_completed = false;
        return r;
 }
 
@@ -2397,6 +2415,7 @@ static const struct dev_pm_ops amdgpu_pm_ops = {
        .runtime_suspend = amdgpu_pmops_runtime_suspend,
        .runtime_resume = amdgpu_pmops_runtime_resume,
        .runtime_idle = amdgpu_pmops_runtime_idle,
+       .suspend_noirq = amdgpu_pmops_noirq_suspend,
 };
 
 static int amdgpu_flush(struct file *f, fl_owner_t id)
-- 
2.7.4