Re: [PATCH 3/7] drm/radeon: cope with foreign fences inside the reservation object

["Christian König" <deathsimple@vodafone.de>]

Am 04.09.2014 um 13:40 schrieb Maarten Lankhorst:
> Not the whole world is a radeon! :-)
>
> Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
> ---
>   drivers/gpu/drm/radeon/radeon.h         | 11 ---------
>   drivers/gpu/drm/radeon/radeon_cs.c      | 32 +++++++++++++++++++++----
>   drivers/gpu/drm/radeon/radeon_display.c | 41 ++++++++++++++++++++++++---------
>   drivers/gpu/drm/radeon/radeon_fence.c   |  3 +++
>   drivers/gpu/drm/radeon/radeon_mode.h    |  1 +
>   5 files changed, 61 insertions(+), 27 deletions(-)
>
> diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
> index d80dc547a105..dddb2b7dd752 100644
> --- a/drivers/gpu/drm/radeon/radeon.h
> +++ b/drivers/gpu/drm/radeon/radeon.h
> @@ -699,17 +699,6 @@ void radeon_doorbell_free(struct radeon_device *rdev, u32 doorbell);
>    * IRQS.
>    */
>   
> -struct radeon_flip_work {
> -	struct work_struct		flip_work;
> -	struct work_struct		unpin_work;
> -	struct radeon_device		*rdev;
> -	int				crtc_id;
> -	uint64_t			base;
> -	struct drm_pending_vblank_event *event;
> -	struct radeon_bo		*old_rbo;
> -	struct radeon_fence		*fence;
> -};
> -

Please keep this structure were it was, apart from that the patch looks 
good on first glance.

Christian.

>   struct r500_irq_stat_regs {
>   	u32 disp_int;
>   	u32 hdmi0_status;
> diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
> index 6e3d1c8f3483..8ad4e2cfae15 100644
> --- a/drivers/gpu/drm/radeon/radeon_cs.c
> +++ b/drivers/gpu/drm/radeon/radeon_cs.c
> @@ -248,23 +248,34 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority
>   	return 0;
>   }
>   
> -static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
> +static int radeon_cs_sync_rings(struct radeon_cs_parser *p)
>   {
>   	int i;
>   
>   	for (i = 0; i < p->nrelocs; i++) {
>   		struct reservation_object *resv;
>   		struct fence *fence;
> +		struct radeon_fence *rfence;
> +		int r;
>   
>   		if (!p->relocs[i].robj)
>   			continue;
>   
>   		resv = p->relocs[i].robj->tbo.resv;
>   		fence = reservation_object_get_excl(resv);
> +		if (!fence)
> +			continue;
> +		rfence = to_radeon_fence(fence);
> +		if (!rfence || rfence->rdev != p->rdev) {
> +			r = fence_wait(fence, true);
> +			if (r)
> +				return r;
> +			continue;
> +		}
>   
> -		radeon_semaphore_sync_to(p->ib.semaphore,
> -					 (struct radeon_fence *)fence);
> +		radeon_semaphore_sync_to(p->ib.semaphore, rfence);
>   	}
> +	return 0;
>   }
>   
>   /* XXX: note that this is called from the legacy UMS CS ioctl as well */
> @@ -474,13 +485,19 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
>   		return r;
>   	}
>   
> +	r = radeon_cs_sync_rings(parser);
> +	if (r) {
> +		if (r != -ERESTARTSYS)
> +			DRM_ERROR("Failed to sync rings: %i\n", r);
> +		return r;
> +	}
> +
>   	if (parser->ring == R600_RING_TYPE_UVD_INDEX)
>   		radeon_uvd_note_usage(rdev);
>   	else if ((parser->ring == TN_RING_TYPE_VCE1_INDEX) ||
>   		 (parser->ring == TN_RING_TYPE_VCE2_INDEX))
>   		radeon_vce_note_usage(rdev);
>   
> -	radeon_cs_sync_rings(parser);
>   	r = radeon_ib_schedule(rdev, &parser->ib, NULL, true);
>   	if (r) {
>   		DRM_ERROR("Failed to schedule IB !\n");
> @@ -567,7 +584,12 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
>   	if (r) {
>   		goto out;
>   	}
> -	radeon_cs_sync_rings(parser);
> +	r = radeon_cs_sync_rings(parser);
> +	if (r) {
> +		if (r != -ERESTARTSYS)
> +			DRM_ERROR("Failed to sync rings: %i\n", r);
> +		goto out;
> +	}
>   	radeon_semaphore_sync_to(parser->ib.semaphore, vm->fence);
>   
>   	if ((rdev->family >= CHIP_TAHITI) &&
> diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
> index bc894c17b2f9..715b2d95346c 100644
> --- a/drivers/gpu/drm/radeon/radeon_display.c
> +++ b/drivers/gpu/drm/radeon/radeon_display.c
> @@ -36,6 +36,17 @@
>   
>   #include <linux/gcd.h>
>   
> +struct radeon_flip_work {
> +	struct work_struct		flip_work;
> +	struct work_struct		unpin_work;
> +	struct radeon_device		*rdev;
> +	int				crtc_id;
> +	uint64_t			base;
> +	struct drm_pending_vblank_event *event;
> +	struct radeon_bo		*old_rbo;
> +	struct fence			*fence;
> +};
> +
>   static void avivo_crtc_load_lut(struct drm_crtc *crtc)
>   {
>   	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
> @@ -402,14 +413,21 @@ static void radeon_flip_work_func(struct work_struct *__work)
>   
>           down_read(&rdev->exclusive_lock);
>   	if (work->fence) {
> -		r = radeon_fence_wait(work->fence, false);
> -		if (r == -EDEADLK) {
> -			up_read(&rdev->exclusive_lock);
> -			do {
> -				r = radeon_gpu_reset(rdev);
> -			} while (r == -EAGAIN);
> -			down_read(&rdev->exclusive_lock);
> -		}
> +		struct radeon_fence *fence;
> +
> +		fence = to_radeon_fence(work->fence);
> +		if (fence && fence->rdev == rdev) {
> +			r = radeon_fence_wait(fence, false);
> +			if (r == -EDEADLK) {
> +				up_read(&rdev->exclusive_lock);
> +				do {
> +					r = radeon_gpu_reset(rdev);
> +				} while (r == -EAGAIN);
> +				down_read(&rdev->exclusive_lock);
> +			}
> +		} else
> +			r = fence_wait(fence, false);
> +
>   		if (r)
>   			DRM_ERROR("failed to wait on page flip fence (%d)!\n", r);
>   
> @@ -418,7 +436,8 @@ static void radeon_flip_work_func(struct work_struct *__work)
>   		 * confused about which BO the CRTC is scanning out
>   		 */
>   
> -		radeon_fence_unref(&work->fence);
> +		fence_put(work->fence);
> +		work->fence = NULL;
>   	}
>   
>   	/* We borrow the event spin lock for protecting flip_status */
> @@ -494,7 +513,7 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
>   		DRM_ERROR("failed to pin new rbo buffer before flip\n");
>   		goto cleanup;
>   	}
> -	work->fence = (struct radeon_fence *)fence_get(reservation_object_get_excl(new_rbo->tbo.resv));
> +	work->fence = fence_get(reservation_object_get_excl(new_rbo->tbo.resv));
>   	radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL);
>   	radeon_bo_unreserve(new_rbo);
>   
> @@ -576,7 +595,7 @@ pflip_cleanup:
>   
>   cleanup:
>   	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
> -	radeon_fence_unref(&work->fence);
> +	fence_put(work->fence);
>   	kfree(work);
>   	return r;
>   }
> diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
> index af9f2d6bd7d0..0262fe2580d2 100644
> --- a/drivers/gpu/drm/radeon/radeon_fence.c
> +++ b/drivers/gpu/drm/radeon/radeon_fence.c
> @@ -541,6 +541,9 @@ int radeon_fence_wait(struct radeon_fence *fence, bool intr)
>   	uint64_t seq[RADEON_NUM_RINGS] = {};
>   	long r;
>   
> +	if (unlikely(!to_radeon_fence(&fence->base)))
> +		return fence_wait(&fence->base, intr);
> +
>   	seq[fence->ring] = fence->seq;
>   	r = radeon_fence_wait_seq_timeout(fence->rdev, seq, intr, MAX_SCHEDULE_TIMEOUT);
>   	if (r < 0) {
> diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
> index e27608c29c11..f6e9ee573de2 100644
> --- a/drivers/gpu/drm/radeon/radeon_mode.h
> +++ b/drivers/gpu/drm/radeon/radeon_mode.h
> @@ -40,6 +40,7 @@
>   
>   struct radeon_bo;
>   struct radeon_device;
> +struct radeon_flip_work;
>   
>   #define to_radeon_crtc(x) container_of(x, struct radeon_crtc, base)
>   #define to_radeon_connector(x) container_of(x, struct radeon_connector, base)