drm/amdgpu: introduce vram lost for reset (v2)

for SOC15/vega10 the BACO reset & mode1 would introduce vram lost
in high end address range, current kmd's vram lost checking cannot
catch it since it only check very ahead visible frame buffer

v2:
cover NV as well

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b2c801f..bd37df5 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1151,6 +1151,7 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define amdgpu_asic_get_pcie_usage(adev, cnt0, cnt1) ((adev)->asic_funcs->get_pcie_usage((adev), (cnt0), (cnt1)))
 #define amdgpu_asic_need_reset_on_init(adev) (adev)->asic_funcs->need_reset_on_init((adev))
 #define amdgpu_asic_get_pcie_replay_count(adev) ((adev)->asic_funcs->get_pcie_replay_count((adev)))
+#define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
 /* Common functions */
 bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2f88469..b8c33df 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3483,7 +3483,7 @@ error:
        amdgpu_virt_init_data_exchange(adev);
        amdgpu_virt_release_full_gpu(adev, true);
        if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
-               atomic_inc(&adev->vram_lost_counter);
+               amdgpu_inc_vram_lost(adev);
                r = amdgpu_device_recover_vram(adev);
        }
 
@@ -3649,7 +3649,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
                                vram_lost = amdgpu_device_check_vram_lost(tmp_adev);
                                if (vram_lost) {
                                        DRM_INFO("VRAM is lost due to GPU reset!\n");
-                                       atomic_inc(&tmp_adev->vram_lost_counter);
+                                       amdgpu_inc_vram_lost(tmp_adev);
                                }
 
                                r = amdgpu_gtt_mgr_recover(

diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index e150c28..1b476fc 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -316,10 +316,13 @@ static int nv_asic_reset(struct amdgpu_device *adev)
        int ret = 0;
        struct smu_context *smu = &adev->smu;
 
-       if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)
+       if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+               amdgpu_inc_vram_lost(adev);
                ret = smu_baco_reset(smu);
-       else
+       } else {
+               amdgpu_inc_vram_lost(adev);
                ret = nv_asic_mode1_reset(adev);
+       }
 
        return ret;
 }

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 53f21c5..c357bec 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -558,10 +558,12 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 {
        switch (soc15_asic_reset_method(adev)) {
                case AMD_RESET_METHOD_BACO:
+                       amdgpu_inc_vram_lost(adev);
                        return soc15_asic_baco_reset(adev);
                case AMD_RESET_METHOD_MODE2:
                        return soc15_mode2_reset(adev);
                default:
+                       amdgpu_inc_vram_lost(adev);
                        return soc15_asic_mode1_reset(adev);
        }
 }