From e352625796b343cc85b7648a74a57e739b12dc27 Mon Sep 17 00:00:00 2001
From: Monk Liu <Monk.Liu@amd.com>
Date: Tue, 27 Aug 2019 16:32:55 +0800
Subject: drm/amdgpu: introduce vram lost for reset (v2)
Git-commit: e352625796b343cc85b7648a74a57e739b12dc27
Patch-mainline: v5.4-rc1
References: bsc#1152489
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>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++--
drivers/gpu/drm/amd/amdgpu/nv.c | 7 +++++--
drivers/gpu/drm/amd/amdgpu/soc15.c | 2 ++
4 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b2c801fb4ab5..bd37df5dd6d0 100644
--- 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 2f884699eaef..b8c33df3f4c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3483,7 +3483,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
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 e150c281feb6..1b476fcd2197 100644
--- 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 53f21c567e97..c357bec3558f 100644
--- 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);
}
}
--
2.28.0