Re: [PATCH v5 6/11] drm/amdkfd: Add unmap from GPU SMI event

[Felix Kuehling <felix.kuehling@xxxxxxx>]

Am 2022-06-28 um 10:50 schrieb Philip Yang:
> SVM range unmapped from GPUs when range is unmapped from CPU, or with
> xnack on from MMU notifier when range is evicted or migrated.
>
> Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>

Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>


> ---
>   drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c |  9 ++++++++
>   drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h |  3 +++
>   drivers/gpu/drm/amd/amdkfd/kfd_svm.c        | 25 +++++++++++++++------
>   3 files changed, 30 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
> index 3917c38204d0..e5896b7a16dd 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
> @@ -318,6 +318,15 @@ void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm)
>   	kfd_unref_process(p);
>   }
>   
> +void kfd_smi_event_unmap_from_gpu(struct kfd_dev *dev, pid_t pid,
> +				  unsigned long address, unsigned long last,
> +				  uint32_t trigger)
> +{
> +	kfd_smi_event_add(pid, dev, KFD_SMI_EVENT_UNMAP_FROM_GPU,
> +			  "%lld -%d @%lx(%lx) %x %d\n", ktime_get_boottime_ns(),
> +			  pid, address, last - address + 1, dev->id, trigger);
> +}
> +
>   int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd)
>   {
>   	struct kfd_smi_client *client;
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
> index b23292637239..76fe4e0ec2d2 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
> @@ -46,4 +46,7 @@ void kfd_smi_event_queue_eviction(struct kfd_dev *dev, pid_t pid,
>   				  uint32_t trigger);
>   void kfd_smi_event_queue_restore(struct kfd_dev *dev, pid_t pid);
>   void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm);
> +void kfd_smi_event_unmap_from_gpu(struct kfd_dev *dev, pid_t pid,
> +				  unsigned long address, unsigned long last,
> +				  uint32_t trigger);
>   #endif
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> index ddc1e4651919..bf888ae84c92 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> @@ -1200,7 +1200,7 @@ svm_range_unmap_from_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
>   
>   static int
>   svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
> -			  unsigned long last)
> +			  unsigned long last, uint32_t trigger)
>   {
>   	DECLARE_BITMAP(bitmap, MAX_GPU_INSTANCE);
>   	struct kfd_process_device *pdd;
> @@ -1232,6 +1232,9 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
>   			return -EINVAL;
>   		}
>   
> +		kfd_smi_event_unmap_from_gpu(pdd->dev, p->lead_thread->pid,
> +					     start, last, trigger);
> +
>   		r = svm_range_unmap_from_gpu(pdd->dev->adev,
>   					     drm_priv_to_vm(pdd->drm_priv),
>   					     start, last, &fence);
> @@ -1759,7 +1762,8 @@ static void svm_range_restore_work(struct work_struct *work)
>    */
>   static int
>   svm_range_evict(struct svm_range *prange, struct mm_struct *mm,
> -		unsigned long start, unsigned long last)
> +		unsigned long start, unsigned long last,
> +		enum mmu_notifier_event event)
>   {
>   	struct svm_range_list *svms = prange->svms;
>   	struct svm_range *pchild;
> @@ -1804,6 +1808,12 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm,
>   			msecs_to_jiffies(AMDGPU_SVM_RANGE_RESTORE_DELAY_MS));
>   	} else {
>   		unsigned long s, l;
> +		uint32_t trigger;
> +
> +		if (event == MMU_NOTIFY_MIGRATE)
> +			trigger = KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY_MIGRATE;
> +		else
> +			trigger = KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY;
>   
>   		pr_debug("invalidate unmap svms 0x%p [0x%lx 0x%lx] from GPUs\n",
>   			 prange->svms, start, last);
> @@ -1812,13 +1822,13 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm,
>   			s = max(start, pchild->start);
>   			l = min(last, pchild->last);
>   			if (l >= s)
> -				svm_range_unmap_from_gpus(pchild, s, l);
> +				svm_range_unmap_from_gpus(pchild, s, l, trigger);
>   			mutex_unlock(&pchild->lock);
>   		}
>   		s = max(start, prange->start);
>   		l = min(last, prange->last);
>   		if (l >= s)
> -			svm_range_unmap_from_gpus(prange, s, l);
> +			svm_range_unmap_from_gpus(prange, s, l, trigger);
>   	}
>   
>   	return r;
> @@ -2232,6 +2242,7 @@ static void
>   svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,
>   			 unsigned long start, unsigned long last)
>   {
> +	uint32_t trigger = KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU;
>   	struct svm_range_list *svms;
>   	struct svm_range *pchild;
>   	struct kfd_process *p;
> @@ -2259,14 +2270,14 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,
>   		s = max(start, pchild->start);
>   		l = min(last, pchild->last);
>   		if (l >= s)
> -			svm_range_unmap_from_gpus(pchild, s, l);
> +			svm_range_unmap_from_gpus(pchild, s, l, trigger);
>   		svm_range_unmap_split(mm, prange, pchild, start, last);
>   		mutex_unlock(&pchild->lock);
>   	}
>   	s = max(start, prange->start);
>   	l = min(last, prange->last);
>   	if (l >= s)
> -		svm_range_unmap_from_gpus(prange, s, l);
> +		svm_range_unmap_from_gpus(prange, s, l, trigger);
>   	svm_range_unmap_split(mm, prange, prange, start, last);
>   
>   	if (unmap_parent)
> @@ -2333,7 +2344,7 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni,
>   		svm_range_unmap_from_cpu(mni->mm, prange, start, last);
>   		break;
>   	default:
> -		svm_range_evict(prange, mni->mm, start, last);
> +		svm_range_evict(prange, mni->mm, start, last, range->event);
>   		break;
>   	}
>