drm/amdgpu: check if vram is lost v2

backup first 64 byte of gart table as reset magic, check if magic is same
after gpu hw reset.
v2: use memcmp instead of manual innovation.

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 19 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 8eb162509c84..5a170071702a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1658,6 +1658,17 @@ static int amdgpu_init(struct amdgpu_device *adev)
         return 0;
 }
 
+static void amdgpu_fill_reset_magic(struct amdgpu_device *adev)
+{
+        memcpy(adev->reset_magic, adev->gart.ptr, AMDGPU_RESET_MAGIC_NUM);
+}
+
+static bool amdgpu_check_vram_lost(struct amdgpu_device *adev)
+{
+        return !!memcmp(adev->gart.ptr, adev->reset_magic,
+                        AMDGPU_RESET_MAGIC_NUM);
+}
+
 static int amdgpu_late_init(struct amdgpu_device *adev)
 {
         int i = 0, r;
@@ -1688,6 +1699,8 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
                 }
         }
 
+        amdgpu_fill_reset_magic(adev);
+
         return 0;
 }
 
@@ -2762,7 +2775,7 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
 {
         int i, r;
         int resched;
-        bool need_full_reset;
+        bool need_full_reset, vram_lost = false;
 
         if (!amdgpu_check_soft_reset(adev)) {
                 DRM_INFO("No hardware hang detected. Did some blocks stall?\n");
@@ -2825,12 +2838,17 @@ retry:
                         r = amdgpu_resume_phase1(adev);
                         if (r)
                                 goto out;
+                        vram_lost = amdgpu_check_vram_lost(adev);
+                        if (vram_lost)
+                                DRM_ERROR("VRAM is lost!\n");
                         r = amdgpu_ttm_recover_gart(adev);
                         if (r)
                                 goto out;
                         r = amdgpu_resume_phase2(adev);
                         if (r)
                                 goto out;
+                        if (vram_lost)
+                                amdgpu_fill_reset_magic(adev);
                 }
         }
 out: