|
[AMD Official Use Only - General]
OK, I will remove it.
-----------------
Best Regards,
Thomas
From: Wang, Yang(Kevin) <KevinYang.Wang@xxxxxxx>
Sent: Thursday, January 18, 2024 9:15 PM
To: Chai, Thomas <YiPeng.Chai@xxxxxxx>; amd-gfx@xxxxxxxxxxxxxxxxxxxxx
Cc: Chai, Thomas <YiPeng.Chai@xxxxxxx>; Zhang, Hawking <Hawking.Zhang@xxxxxxx>; Zhou1, Tao <Tao.Zhou1@xxxxxxx>; Li, Candice <Candice.Li@xxxxxxx>; Yang, Stanley <Stanley.Yang@xxxxxxx>
Subject: Re: [PATCH V2 1/5] drm/amdgpu: Add log info for umc_v12_0 and smu_v13_0_6
[AMD Official Use Only - General]
The title and description don't seem right.
From: Chai, Thomas <YiPeng.Chai@xxxxxxx>
Sent: Thursday, January 18, 2024 14:43
To: amd-gfx@xxxxxxxxxxxxxxxxxxxxx <amd-gfx@xxxxxxxxxxxxxxxxxxxxx>
Cc: Chai, Thomas <YiPeng.Chai@xxxxxxx>; Zhang, Hawking <Hawking.Zhang@xxxxxxx>; Zhou1, Tao <Tao.Zhou1@xxxxxxx>; Li, Candice <Candice.Li@xxxxxxx>;
Wang, Yang(Kevin) <KevinYang.Wang@xxxxxxx>; Yang, Stanley <Stanley.Yang@xxxxxxx>; Chai, Thomas <YiPeng.Chai@xxxxxxx>
Subject: [PATCH V2 1/5] drm/amdgpu: Add log info for umc_v12_0 and smu_v13_0_6
Add log info for umc_v12_0 and smu_v13_0_6.
v2:
Delete redundant logs.
Signed-off-by: YiPeng Chai <YiPeng.Chai@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/umc_v12_0.c | 11 +++++++++++
drivers/gpu/drm/amd/amdkfd/kfd_events.c | 6 +++++-
2 files changed, 16 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index 6423dca5b777..fa2168f1d3bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -91,6 +91,17 @@ static void umc_v12_0_reset_error_count(struct amdgpu_device *adev)
bool umc_v12_0_is_deferred_error(struct amdgpu_device *adev, uint64_t mc_umc_status)
{
+ dev_info(adev->dev,
+ "MCA_UMC_STATUS(0x%llx): Val:%llu, Poison:%llu, Deferred:%llu, PCC:%llu, UC:%llu, TCC:%llu\n",
+ mc_umc_status,
+ REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val),
+ REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Poison),
+ REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred),
+ REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC),
+ REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC),
+ REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC)
+ );
+
return (amdgpu_ras_is_poison_mode_supported(adev) &&
(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1));
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 11923964ce9a..51bb98db5d7a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -1297,8 +1297,10 @@ void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid)
uint32_t id = KFD_FIRST_NONSIGNAL_EVENT_ID;
int user_gpu_id;
- if (!p)
+ if (!p) {
+ dev_warn(dev->adev->dev, "Not find process with pasid:%d\n", pasid);
return; /* Presumably process exited. */
+ }
user_gpu_id = kfd_process_get_user_gpu_id(p, dev->id);
if (unlikely(user_gpu_id == -EINVAL)) {
@@ -1334,6 +1336,8 @@ void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid)
}
}
+ dev_warn(dev->adev->dev, "Send SIGBUS to process %s(pasid:%d)\n",
+ p->lead_thread->comm, pasid);
rcu_read_unlock();
/* user application will handle SIGBUS signal */
--
2.34.1
|
