nvk: Plumb no_prefetch through to the DRM back-end

Instead of using bit 23 of nvk_cmd_push::range for this, pass it as a
separate bool.  This lets us use the actual kernel flag with the new
UAPI.

Reviewed-by: Danilo Krummrich <dakr@redhat.com>
Tested-by: Danilo Krummrich <dakr@redhat.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24840>

src/nouveau/vulkan/nvk_cmd_buffer.c

@@ -157,8 +157,6 @@ nvk_cmd_buffer_new_push(struct nvk_cmd_buffer *cmd)
    }
 }
 
-#define NVC0_IB_ENTRY_1_NO_PREFETCH (1 << (31 - 8))
-
 void
 nvk_cmd_buffer_push_indirect_buffer(struct nvk_cmd_buffer *cmd,
                                     struct nvk_buffer *buffer,
@@ -167,12 +165,12 @@ nvk_cmd_buffer_push_indirect_buffer(struct nvk_cmd_buffer *cmd,
    nvk_cmd_buffer_flush_push(cmd);
 
    uint64_t addr = nvk_buffer_address(buffer, offset);
-   assert(range < NVC0_IB_ENTRY_1_NO_PREFETCH);
 
 #if NVK_NEW_UAPI == 1
    struct nvk_cmd_push push = {
       .addr = addr,
-      .range = NVC0_IB_ENTRY_1_NO_PREFETCH | range,
+      .range = range,
+      .no_prefetch = true,
    };
 #else
    struct nouveau_ws_bo *bo = buffer->mem->bo;
@@ -180,7 +178,8 @@ nvk_cmd_buffer_push_indirect_buffer(struct nvk_cmd_buffer *cmd,
    struct nvk_cmd_push push = {
       .bo = bo,
       .bo_offset = bo_offset,
-      .range = NVC0_IB_ENTRY_1_NO_PREFETCH | range,
+      .range = range,
+      .no_prefetch = true,
    };
 #endif
 
@@ -555,7 +554,7 @@ nvk_cmd_buffer_dump(struct nvk_cmd_buffer *cmd, FILE *fp)
          const uint64_t addr = p->bo->offset + p->bo_offset;
 #endif
          fprintf(fp, "<%u B of INDIRECT DATA at 0x%" PRIx64 ">\n",
-                 p->range & ~NVC0_IB_ENTRY_1_NO_PREFETCH, addr);
+                 p->range, addr);
       }
    }
 }

src/nouveau/vulkan/nvk_cmd_buffer.h

@@ -111,6 +111,7 @@ struct nvk_cmd_push {
    uint64_t bo_offset;
 #endif
    uint32_t range;
+   bool no_prefetch;
 };
 
 struct nvk_cmd_bo_ref {

src/nouveau/vulkan/nvk_queue_drm_nouveau.c

@@ -265,24 +265,33 @@ push_add_image_opaque_bind(struct push_builder *pb,
 
 #if NVK_NEW_UAPI == 1
 static void
-push_add_push(struct push_builder *pb, uint64_t addr, uint32_t range)
+push_add_push(struct push_builder *pb, uint64_t addr, uint32_t range,
+              bool no_prefetch)
 {
    assert((addr % 4) == 0 && (range % 4) == 0);
 
    if (range == 0)
       return;
 
+   /* This is the hardware limit on all current GPUs */
+   assert(range < (1u << 23));
+
+   uint32_t flags = 0;
+   if (no_prefetch)
+      flags |= DRM_NOUVEAU_EXEC_PUSH_NO_PREFETCH;
+
    assert(pb->req.push_count < NVK_PUSH_MAX_PUSH);
    pb->req_push[pb->req.push_count++] = (struct drm_nouveau_exec_push) {
       .va = addr,
       .va_len = range,
+      .flags = flags,
    };
 }
 #endif
 
 static void
 push_add_push_bo(struct push_builder *pb, struct nouveau_ws_bo *bo,
-                 uint32_t offset, uint32_t range)
+                 uint32_t offset, uint32_t range, bool no_prefetch)
 {
 #if NVK_NEW_UAPI == 0
    assert((offset % 4) == 0 && (range % 4) == 0);
@@ -290,6 +299,10 @@ push_add_push_bo(struct push_builder *pb, struct nouveau_ws_bo *bo,
    if (range == 0)
       return;
 
+   assert(range < NOUVEAU_GEM_PUSHBUF_NO_PREFETCH);
+   if (no_prefetch)
+      range |= NOUVEAU_GEM_PUSHBUF_NO_PREFETCH;
+
    uint32_t bo_index = push_add_bo(pb, bo, NOUVEAU_WS_BO_RD);
 
    pb->req_push[pb->req.nr_push++] = (struct drm_nouveau_gem_pushbuf_push) {
@@ -298,7 +311,7 @@ push_add_push_bo(struct push_builder *pb, struct nouveau_ws_bo *bo,
       .length = range,
    };
 #else
-   push_add_push(pb, bo->offset + offset, range);
+   push_add_push(pb, bo->offset + offset, range, no_prefetch);
 #endif
 }
 
@@ -391,7 +404,7 @@ nvk_queue_submit_simple_drm_nouveau(struct nvk_queue *queue,
    struct push_builder pb;
    push_builder_init(dev, &pb, false);
 
-   push_add_push_bo(&pb, push_bo, 0, push_dw_count * 4);
+   push_add_push_bo(&pb, push_bo, 0, push_dw_count * 4, false);
    for (uint32_t i = 0; i < extra_bo_count; i++)
       push_add_bo(&pb, extra_bos[i], NOUVEAU_WS_BO_RDWR);
 
@@ -408,7 +421,7 @@ push_add_queue_state(struct push_builder *pb, struct nvk_queue_state *qs)
    if (qs->slm.bo)
       push_add_bo(pb, qs->slm.bo, NOUVEAU_WS_BO_RDWR);
    if (qs->push.bo)
-      push_add_push_bo(pb, qs->push.bo, 0, qs->push.dw_count * 4);
+      push_add_push_bo(pb, qs->push.bo, 0, qs->push.dw_count * 4, false);
 }
 
 static void
@@ -460,7 +473,7 @@ nvk_queue_submit_drm_nouveau(struct nvk_queue *queue,
    } else if (submit->command_buffer_count == 0) {
 #if NVK_NEW_UAPI == 0
       push_add_push_bo(&pb, queue->empty_push, 0,
-                       queue->empty_push_dw_count * 4);
+                       queue->empty_push_dw_count * 4, false);
 #endif
    } else {
       push_add_queue_state(&pb, &queue->state);
@@ -483,10 +496,12 @@ nvk_queue_submit_drm_nouveau(struct nvk_queue *queue,
 
 #if NVK_NEW_UAPI == 1
          util_dynarray_foreach(&cmd->pushes, struct nvk_cmd_push, push)
-            push_add_push(&pb, push->addr, push->range);
+            push_add_push(&pb, push->addr, push->range, push->no_prefetch);
 #else
-         util_dynarray_foreach(&cmd->pushes, struct nvk_cmd_push, push)
+         util_dynarray_foreach(&cmd->pushes, struct nvk_cmd_push, push) {
-            push_add_push_bo(&pb, push->bo, push->bo_offset, push->range);
+            push_add_push_bo(&pb, push->bo, push->bo_offset, push->range,
+                             push->no_prefetch);
+         }
 #endif
 
          util_dynarray_foreach(&cmd->bo_refs, struct nvk_cmd_bo_ref, ref)