[PATCH v3 8/8] drm/amdgpu: fix missing reset domain locks

[Christian König]

Am 30.05.24 um 23:48 schrieb Yunxiang Li:
> These functions are missing the lock for reset domain.

Please separate the GART changes from the KFD changes. Apart from that 
looks good to me.

Thanks,
Christian.

>
> Signed-off-by: Yunxiang Li <Yunxiang.Li at amd.com>
> ---
> v3: only bracket amdgpu_device_flush_hdp with the read lock,
>      amdgpu_gmc_flush_gpu_tlb already takes the lock
>
>   drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c               | 6 +++++-
>   drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 9 +++++++--
>   2 files changed, 12 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> index eb172388d99e..256b95232de5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> @@ -34,6 +34,7 @@
>   #include <asm/set_memory.h>
>   #endif
>   #include "amdgpu.h"
> +#include "amdgpu_reset.h"
>   #include <drm/drm_drv.h>
>   #include <drm/ttm/ttm_tt.h>
>   
> @@ -405,7 +406,10 @@ void amdgpu_gart_invalidate_tlb(struct amdgpu_device *adev)
>   		return;
>   
>   	mb();
> -	amdgpu_device_flush_hdp(adev, NULL);
> +	if (down_read_trylock(&adev->reset_domain->sem)) {
> +		amdgpu_device_flush_hdp(adev, NULL);
> +		up_read(&adev->reset_domain->sem);
> +	}
>   	for_each_set_bit(i, adev->vmhubs_mask, AMDGPU_MAX_VMHUBS)
>   		amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
>   }
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> index 86ea610b16f3..21f5a1fb3bf8 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> @@ -28,6 +28,7 @@
>   #include "kfd_priv.h"
>   #include "kfd_kernel_queue.h"
>   #include "amdgpu_amdkfd.h"
> +#include "amdgpu_reset.h"
>   
>   static inline struct process_queue_node *get_queue_by_qid(
>   			struct process_queue_manager *pqm, unsigned int qid)
> @@ -87,8 +88,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
>   		return;
>   
>   	dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd);
> -	if (dev->kfd->shared_resources.enable_mes)
> -		amdgpu_mes_flush_shader_debugger(dev->adev, pdd->proc_ctx_gpu_addr);
> +	if (dev->kfd->shared_resources.enable_mes &&
> +	    down_read_trylock(&dev->adev->reset_domain->sem)) {
> +		amdgpu_mes_flush_shader_debugger(dev->adev,
> +						 pdd->proc_ctx_gpu_addr);
> +		up_read(&dev->adev->reset_domain->sem);
> +	}
>   	pdd->already_dequeued = true;
>   }
>