[PATCH] drm/amdgpu: add an INFO query for monitoring VRAM CPU page faults

[Deucher, Alexander]

> -----Original Message-----
> From: amd-gfx [mailto:amd-gfx-bounces at lists.freedesktop.org] On Behalf
> Of Marek Olšák
> Sent: Wednesday, May 17, 2017 2:06 PM
> To: amd-gfx at lists.freedesktop.org
> Subject: [PATCH] drm/amdgpu: add an INFO query for monitoring VRAM
> CPU page faults
> 
> From: Marek Olšák <marek.olsak at amd.com>
> 
> Signed-off-by: Marek Olšák <marek.olsak at amd.com>

Please bump the driver version as well.  With that fixed:
Reviewed-by: Alex Deucher <alexander.deucher at amd.com>

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 1 +
>  drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    | 3 +++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 1 +
>  include/uapi/drm/amdgpu_drm.h              | 2 ++
>  4 files changed, 7 insertions(+)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index fadeb55..251e5de 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1525,20 +1525,21 @@ struct amdgpu_device {
> 
>  	/* memory management */
>  	struct amdgpu_mman		mman;
>  	struct amdgpu_vram_scratch	vram_scratch;
>  	struct amdgpu_wb		wb;
>  	atomic64_t			vram_usage;
>  	atomic64_t			vram_vis_usage;
>  	atomic64_t			gtt_usage;
>  	atomic64_t			num_bytes_moved;
>  	atomic64_t			num_evictions;
> +	atomic64_t			num_vram_cpu_page_faults;
>  	atomic_t			gpu_reset_counter;
> 
>  	/* data for buffer migration throttling */
>  	struct {
>  		spinlock_t		lock;
>  		s64			last_update_us;
>  		s64			accum_us; /* accumulated
> microseconds */
>  		u32			log2_max_MBps;
>  	} mm_stats;
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> index d167949..81291d8 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> @@ -407,20 +407,23 @@ static int amdgpu_info_ioctl(struct drm_device
> *dev, void *data, struct drm_file
> 
>  		return copy_to_user(out, &fw_info,
>  				    min((size_t)size, sizeof(fw_info))) ? -
> EFAULT : 0;
>  	}
>  	case AMDGPU_INFO_NUM_BYTES_MOVED:
>  		ui64 = atomic64_read(&adev->num_bytes_moved);
>  		return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
>  	case AMDGPU_INFO_NUM_EVICTIONS:
>  		ui64 = atomic64_read(&adev->num_evictions);
>  		return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
> +	case AMDGPU_INFO_NUM_VRAM_CPU_PAGE_FAULTS:
> +		ui64 = atomic64_read(&adev->num_vram_cpu_page_faults);
> +		return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
>  	case AMDGPU_INFO_VRAM_USAGE:
>  		ui64 = atomic64_read(&adev->vram_usage);
>  		return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
>  	case AMDGPU_INFO_VIS_VRAM_USAGE:
>  		ui64 = atomic64_read(&adev->vram_vis_usage);
>  		return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
>  	case AMDGPU_INFO_GTT_USAGE:
>  		ui64 = atomic64_read(&adev->gtt_usage);
>  		return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
>  	case AMDGPU_INFO_GDS_CONFIG: {
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 6bc52cc..b6da86e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -953,20 +953,21 @@ int amdgpu_bo_fault_reserve_notify(struct
> ttm_buffer_object *bo)
>  	offset = bo->mem.start << PAGE_SHIFT;
>  	/* TODO: figure out how to map scattered VRAM to the CPU */
>  	if ((offset + size) <= adev->mc.visible_vram_size)
>  		return 0;
> 
>  	/* Can't move a pinned BO to visible VRAM */
>  	if (abo->pin_count > 0)
>  		return -EINVAL;
> 
>  	/* hurrah the memory is not visible ! */
> +	atomic64_inc(&adev->num_vram_cpu_page_faults);
>  	amdgpu_ttm_placement_from_domain(abo,
> AMDGPU_GEM_DOMAIN_VRAM);
>  	lpfn =	adev->mc.visible_vram_size >> PAGE_SHIFT;
>  	for (i = 0; i < abo->placement.num_placement; i++) {
>  		/* Force into visible VRAM */
>  		if ((abo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
>  		    (!abo->placements[i].lpfn ||
>  		     abo->placements[i].lpfn > lpfn))
>  			abo->placements[i].lpfn = lpfn;
>  	}
>  	r = ttm_bo_validate(bo, &abo->placement, false, false);
> diff --git a/include/uapi/drm/amdgpu_drm.h
> b/include/uapi/drm/amdgpu_drm.h
> index c99fe63..4f34394 100644
> --- a/include/uapi/drm/amdgpu_drm.h
> +++ b/include/uapi/drm/amdgpu_drm.h
> @@ -598,20 +598,22 @@ struct drm_amdgpu_cs_chunk_data {
>  	/* Subquery id: Query GPU temperature */
>  	#define AMDGPU_INFO_SENSOR_GPU_TEMP		0x3
>  	/* Subquery id: Query GPU load */
>  	#define AMDGPU_INFO_SENSOR_GPU_LOAD		0x4
>  	/* Subquery id: Query average GPU power	*/
>  	#define AMDGPU_INFO_SENSOR_GPU_AVG_POWER	0x5
>  	/* Subquery id: Query northbridge voltage */
>  	#define AMDGPU_INFO_SENSOR_VDDNB		0x6
>  	/* Subquery id: Query graphics voltage */
>  	#define AMDGPU_INFO_SENSOR_VDDGFX		0x7
> +/* Number of VRAM page faults on CPU access. */
> +#define AMDGPU_INFO_NUM_VRAM_CPU_PAGE_FAULTS	0x1E
> 
>  #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
>  #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
>  #define AMDGPU_INFO_MMR_SH_INDEX_SHIFT	8
>  #define AMDGPU_INFO_MMR_SH_INDEX_MASK	0xff
> 
>  struct drm_amdgpu_query_fw {
>  	/** AMDGPU_INFO_FW_* */
>  	__u32 fw_type;
>  	/**
> --
> 2.7.4
> 
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx