drm/etnaviv: add cmdbuf suballocator

There are 3 big benefits to suballocating a single big DMA buffer
for command submission:

1. Avoid hammering CMA. The old way of allocating and freeing a DMA
   buffer for each submission was hitting some of the real slow
   pathes in CMA, as this allocator was not designed for a concurrent
   small buffers load.

2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into
   the GPU address space the MMU TLBs need to be flushed. By having
   one big buffer statically mapped to the GPU, a lot of those flushes
   can be avoided.

3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't
   reliable. To work around that we tried to lay out the cmdbufs in
   the GPU address space in a way to avoid this issue. This hasn't
   always worked if the address space is crowded. A single statically
   mapped buffer avoids the erratum completely.

Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>

1 files changed, 2 insertions, 3 deletions

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 9c10ffeff77e..1c0606ea7d5e 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -92,6 +92,7 @@ struct etnaviv_event {
 	struct dma_fence *fence;
 };
 
+struct etnaviv_cmdbuf_suballoc;
 struct etnaviv_cmdbuf;
 
 struct etnaviv_gpu {
@@ -135,6 +136,7 @@ struct etnaviv_gpu {
 	int irq;
 
 	struct etnaviv_iommu *mmu;
+	struct etnaviv_cmdbuf_suballoc *cmdbuf_suballoc;
 
 	/* Power Control: */
 	struct clk *clk_bus;
@@ -188,9 +190,6 @@ int etnaviv_gpu_wait_obj_inactive(struct etnaviv_gpu *gpu,
 	struct etnaviv_gem_object *etnaviv_obj, struct timespec *timeout);
 int etnaviv_gpu_submit(struct etnaviv_gpu *gpu,
 	struct etnaviv_gem_submit *submit, struct etnaviv_cmdbuf *cmdbuf);
-struct etnaviv_cmdbuf *etnaviv_cmdbuf_new(struct etnaviv_gpu *gpu,
-					      u32 size, size_t nr_bos);
-void etnaviv_cmdbuf_free(struct etnaviv_cmdbuf *cmdbuf);
 int etnaviv_gpu_pm_get_sync(struct etnaviv_gpu *gpu);
 void etnaviv_gpu_pm_put(struct etnaviv_gpu *gpu);
 int etnaviv_gpu_wait_idle(struct etnaviv_gpu *gpu, unsigned int timeout_ms);