drm/radeon: convert fence to uint64_t v4

This convert fence to use uint64_t sequence number intention is
to use the fact that uin64_t is big enough that we don't need to
care about wrap around.

Tested with and without writeback using 0xFFFFF000 as initial
fence sequence and thus allowing to test the wrap around from
32bits to 64bits.

v2: Add comment about possible race btw CPU & GPU, add comment
    stressing that we need 2 dword aligned for R600_WB_EVENT_OFFSET
    Read fence sequenc in reverse order of GPU write them so we
    mitigate the race btw CPU and GPU.

v3: Drop the need for ring to emit the 64bits fence, and just have
    each ring emit the lower 32bits of the fence sequence. We
    handle the wrap over 32bits in fence_process.

v4: Just a small optimization: Don't reread the last_seq value
    if loop restarts, since we already know its value anyway.
    Also start at zero not one for seq value and use pre instead
    of post increment in emmit, otherwise wait_empty will deadlock.

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 5 insertions, 4 deletions

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index a4d60ae524b1..4ae222bb3ec5 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -82,7 +82,7 @@ bool radeon_ib_try_free(struct radeon_device *rdev, struct radeon_ib *ib)
 	bool done = false;
 
 	/* only free ib which have been emited */
-	if (ib->fence && ib->fence->emitted) {
+	if (ib->fence && ib->fence->seq < RADEON_FENCE_NOTEMITED_SEQ) {
 		if (radeon_fence_signaled(ib->fence)) {
 			radeon_fence_unref(&ib->fence);
 			radeon_sa_bo_free(rdev, &ib->sa_bo);
@@ -149,8 +149,9 @@ retry:
 	/* this should be rare event, ie all ib scheduled none signaled yet.
 	 */
 	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		if (rdev->ib_pool.ibs[idx].fence && rdev->ib_pool.ibs[idx].fence->emitted) {
-			r = radeon_fence_wait(rdev->ib_pool.ibs[idx].fence, false);
+		struct radeon_fence *fence = rdev->ib_pool.ibs[idx].fence;
+		if (fence && fence->seq < RADEON_FENCE_NOTEMITED_SEQ) {
+			r = radeon_fence_wait(fence, false);
 			if (!r) {
 				goto retry;
 			}
@@ -173,7 +174,7 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
 		return;
 	}
 	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (tmp->fence && !tmp->fence->emitted) {
+	if (tmp->fence && tmp->fence->seq == RADEON_FENCE_NOTEMITED_SEQ) {
 		radeon_sa_bo_free(rdev, &tmp->sa_bo);
 		radeon_fence_unref(&tmp->fence);
 	}