drm/radeon: multiple ring allocator v3

A startover with a new idea for a multiple ring allocator.
Should perform as well as a normal ring allocator as long
as only one ring does somthing, but falls back to a more
complex algorithm if more complex things start to happen.

We store the last allocated bo in last, we always try to allocate
after the last allocated bo. Principle is that in a linear GPU ring
progression was is after last is the oldest bo we allocated and thus
the first one that should no longer be in use by the GPU.

If it's not the case we skip over the bo after last to the closest
done bo if such one exist. If none exist and we are not asked to
block we report failure to allocate.

If we are asked to block we wait on all the oldest fence of all
rings. We just wait for any of those fence to complete.

v2: We need to be able to let hole point to the list_head, otherwise
    try free will never free the first allocation of the list. Also
    stop calling radeon_fence_signalled more than necessary.

v3: Don't free allocations without considering them as a hole,
    otherwise we might lose holes. Also return ENOMEM instead of ENOENT
    when running out of fences to wait for. Limit the number of holes
    we try for each ring to 3.
Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/radeon.h

@@ -385,7 +385,9 @@ struct radeon_bo_list {
 struct radeon_sa_manager {
 	spinlock_t		lock;
 	struct radeon_bo	*bo;
-	struct list_head	sa_bo;
+	struct list_head	*hole;
+	struct list_head	flist[RADEON_NUM_RINGS];
+	struct list_head	olist;
 	unsigned		size;
 	uint64_t		gpu_addr;
 	void			*cpu_ptr;
@@ -396,7 +398,8 @@ struct radeon_sa_bo;
 
 /* sub-allocation buffer */
 struct radeon_sa_bo {
-	struct list_head		list;
+	struct list_head		olist;
+	struct list_head		flist;
 	struct radeon_sa_manager	*manager;
 	unsigned			soffset;
 	unsigned			eoffset;

drivers/gpu/drm/radeon/radeon_ring.c

@@ -204,25 +204,22 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 
 int radeon_ib_pool_init(struct radeon_device *rdev)
 {
-	struct radeon_sa_manager tmp;
 	int i, r;
 
-	r = radeon_sa_bo_manager_init(rdev, &tmp,
-				      RADEON_IB_POOL_SIZE*64*1024,
-				      RADEON_GEM_DOMAIN_GTT);
-	if (r) {
-		return r;
-	}
-
 	radeon_mutex_lock(&rdev->ib_pool.mutex);
 	if (rdev->ib_pool.ready) {
 		radeon_mutex_unlock(&rdev->ib_pool.mutex);
-		radeon_sa_bo_manager_fini(rdev, &tmp);
 		return 0;
 	}
 
-	rdev->ib_pool.sa_manager = tmp;
-	INIT_LIST_HEAD(&rdev->ib_pool.sa_manager.sa_bo);
+	r = radeon_sa_bo_manager_init(rdev, &rdev->ib_pool.sa_manager,
+				      RADEON_IB_POOL_SIZE*64*1024,
+				      RADEON_GEM_DOMAIN_GTT);
+	if (r) {
+		radeon_mutex_unlock(&rdev->ib_pool.mutex);
+		return r;
+	}
+
 	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
 		rdev->ib_pool.ibs[i].fence = NULL;
 		rdev->ib_pool.ibs[i].idx = i;