anv: switch khr perf query code to use query layout

This unifies performance data gathering between the GL & Vulkan
drivers.

v2: Also move all NOOPs to before the query, leaving none inside

v3: Capture the query beging registers in reverse order to ensure
    timestamp is as close as possible from measured draw call.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6518>

src/intel/vulkan/anv_cmd_buffer.c

@@ -279,6 +279,8 @@ static VkResult anv_create_cmd_buffer(
    anv_state_stream_init(&cmd_buffer->general_state_stream,
                          &device->general_state_pool, 16384);
 
+   cmd_buffer->self_mod_locations = NULL;
+
    anv_cmd_state_init(cmd_buffer);
 
    list_addtail(&cmd_buffer->pool_link, &pool->cmd_buffers);
@@ -338,6 +340,8 @@ anv_cmd_buffer_destroy(struct anv_cmd_buffer *cmd_buffer)
 
    anv_cmd_state_finish(cmd_buffer);
 
+   vk_free(&cmd_buffer->pool->alloc, cmd_buffer->self_mod_locations);
+
    vk_object_base_finish(&cmd_buffer->base);
    vk_free(&cmd_buffer->pool->alloc, cmd_buffer);
 }