mirror of
https://github.com/Droid-Deck/DroidDeck.git
synced 2026-11-18 20:36:04 +00:00
From DavidCimo/droiddeck-mali, branch mali-venus @ 4f838891 (prototype 13; his 12 commits on top of DroidDeck 0.3.1, GPL-3.0), by David Cimo: - tools/venus: Mesa Venus vtest patch (incl. the per-queue submit_mutex fix and the cached-memory frame readback), virglrenderer Android patch, the Mali compatibility layer (the six features DXVK needs: fill modes, multi-viewport, robustness2, clip/cull distance, BC1-BC7) and his tools. - tools/linuxfs/preload/venus.c: keeps Zink's kopper under Venus. - tools/gamescope/patches/0127 (his 0114): shm buffers uploaded on every commit. - docs/development/mali-venus.md: his design notes. - tools/venus/ci-build.sh and build-venus.yml: his build recipes as one CI job that packs the component (vtest server, ICD, layer) as venus.tzst for the apk. Co-authored-by: Dersim Abbas <derabb0620@gmail.com>
154 lines
6.5 KiB
Diff
154 lines
6.5 KiB
Diff
diff --git a/src/virtio/vulkan/vn_wsi.c b/src/virtio/vulkan/vn_wsi.c
|
|
index f0b41b1..5c08312 100644
|
|
--- a/src/virtio/vulkan/vn_wsi.c
|
|
+++ b/src/virtio/vulkan/vn_wsi.c
|
|
@@ -23,6 +23,33 @@
|
|
#define DRM_FORMAT_MOD_LINEAR 0
|
|
#endif
|
|
|
|
+/* MEASURE: async present costs, logged every 120 presents. */
|
|
+static struct {
|
|
+ uint32_t presents, fence_waits, flushes;
|
|
+ int64_t present_sum, present_max, fence_sum, fence_max, flush_sum, flush_max;
|
|
+} vn_measure;
|
|
+
|
|
+#define VN_MEASURE_ADD(name, ns) \
|
|
+ do { \
|
|
+ vn_measure.name##_sum += (ns); \
|
|
+ vn_measure.name##_max = MAX2(vn_measure.name##_max, (ns)); \
|
|
+ } while (0)
|
|
+
|
|
+static void
|
|
+vn_measure_present(int64_t ns)
|
|
+{
|
|
+ VN_MEASURE_ADD(present, ns);
|
|
+ if (++vn_measure.presents < 120)
|
|
+ return;
|
|
+ fprintf(stderr, "MEASURE vn: present thread %.2f/%.2f ms | fence wait %.2f/%.2f ms (%u) | app blocked in flush %.2f/%.2f ms (%u)\n",
|
|
+ vn_measure.present_sum / 120 / 1e6, vn_measure.present_max / 1e6,
|
|
+ vn_measure.fence_waits ? vn_measure.fence_sum / vn_measure.fence_waits / 1e6 : 0.0,
|
|
+ vn_measure.fence_max / 1e6, vn_measure.fence_waits,
|
|
+ vn_measure.flushes ? vn_measure.flush_sum / vn_measure.flushes / 1e6 : 0.0,
|
|
+ vn_measure.flush_max / 1e6, vn_measure.flushes);
|
|
+ memset(&vn_measure, 0, sizeof(vn_measure));
|
|
+}
|
|
+
|
|
/* The common WSI support makes some assumptions about the driver.
|
|
*
|
|
* In wsi_device_init, it assumes VK_EXT_pci_bus_info is available. In
|
|
@@ -331,6 +358,7 @@ vn_wsi_memory_type_index(const struct vn_device *dev,
|
|
!(type_bits & BITFIELD_BIT(readback_type)))
|
|
return alloc_info->memoryTypeIndex;
|
|
|
|
+ fprintf(stderr, "MEASURE vn: WSI readback buffer in memory type %d\n", readback_type);
|
|
return readback_type;
|
|
}
|
|
|
|
@@ -479,8 +507,11 @@ vn_wsi_fence_wait(VkQueue queue_handle)
|
|
simple_mtx_unlock(&queue->async_present.queue_mutex);
|
|
vn_wsi_chains_unlock(dev, queue->async_present.info, /*all=*/false);
|
|
|
|
+ int64_t measure_start = os_time_get_nano();
|
|
result = vn_WaitForFences(dev_handle, 1, &queue->async_present.fence, true,
|
|
UINT64_MAX);
|
|
+ VN_MEASURE_ADD(fence, os_time_get_nano() - measure_start);
|
|
+ vn_measure.fence_waits++;
|
|
|
|
vn_wsi_chains_lock(dev, queue->async_present.info, /*all=*/false);
|
|
if (can_unlock_queue)
|
|
@@ -537,8 +568,11 @@ vn_wsi_flush(VkQueue queue_handle)
|
|
/* Being able to acquire the lock ensures async present queue access
|
|
* has completed.
|
|
*/
|
|
+ int64_t measure_start = os_time_get_nano();
|
|
simple_mtx_lock(&queue->async_present.queue_mutex);
|
|
simple_mtx_unlock(&queue->async_present.queue_mutex);
|
|
+ VN_MEASURE_ADD(flush, os_time_get_nano() - measure_start);
|
|
+ vn_measure.flushes++;
|
|
}
|
|
|
|
static VkPresentInfoKHR *
|
|
@@ -811,9 +845,11 @@ vn_wsi_present_thread(void *data)
|
|
|
|
queue->async_present.pending = false;
|
|
|
|
+ int64_t measure_start = os_time_get_nano();
|
|
queue->async_present.result =
|
|
wsi_common_queue_present(queue_vk->base.device->physical->wsi_device,
|
|
queue_vk, queue->async_present.info);
|
|
+ vn_measure_present(os_time_get_nano() - measure_start);
|
|
|
|
vn_wsi_chains_unlock(dev, queue->async_present.info, /*all=*/true);
|
|
simple_mtx_unlock(&queue->async_present.queue_mutex);
|
|
diff --git a/src/vulkan/wsi/wsi_common_wayland.c b/src/vulkan/wsi/wsi_common_wayland.c
|
|
index 047c8b3..a153a39 100644
|
|
--- a/src/vulkan/wsi/wsi_common_wayland.c
|
|
+++ b/src/vulkan/wsi/wsi_common_wayland.c
|
|
@@ -3277,6 +3277,38 @@ set_timestamp(struct wsi_wl_swapchain *chain,
|
|
return true;
|
|
}
|
|
|
|
+/* MEASURE: per-frame cost of the shm copy, logged every 120 presents. */
|
|
+static struct {
|
|
+ uint32_t frames;
|
|
+ int64_t last_present, interval_sum, interval_max, copy_sum, copy_max, total_sum, total_max;
|
|
+} wl_measure;
|
|
+
|
|
+static void
|
|
+wl_measure_frame(struct wsi_wl_swapchain *chain, int64_t start, int64_t copy_ns, int64_t end)
|
|
+{
|
|
+ if (wl_measure.last_present) {
|
|
+ int64_t interval = start - wl_measure.last_present;
|
|
+ wl_measure.interval_sum += interval;
|
|
+ wl_measure.interval_max = MAX2(wl_measure.interval_max, interval);
|
|
+ }
|
|
+ wl_measure.last_present = start;
|
|
+ wl_measure.copy_sum += copy_ns;
|
|
+ wl_measure.copy_max = MAX2(wl_measure.copy_max, copy_ns);
|
|
+ wl_measure.total_sum += end - start;
|
|
+ wl_measure.total_max = MAX2(wl_measure.total_max, end - start);
|
|
+ if (++wl_measure.frames < 120)
|
|
+ return;
|
|
+ fprintf(stderr, "MEASURE wl: %ux%u type %d | interval %.2f/%.2f ms | copy %.2f/%.2f ms (%u KB) | present %.2f/%.2f ms\n",
|
|
+ chain->extent.width, chain->extent.height, chain->buffer_type,
|
|
+ wl_measure.interval_sum / 119 / 1e6, wl_measure.interval_max / 1e6,
|
|
+ wl_measure.copy_sum / 120 / 1e6, wl_measure.copy_max / 1e6,
|
|
+ chain->images[0].base.row_pitches[0] * chain->extent.height / 1024,
|
|
+ wl_measure.total_sum / 120 / 1e6, wl_measure.total_max / 1e6);
|
|
+ int64_t last = wl_measure.last_present;
|
|
+ memset(&wl_measure, 0, sizeof(wl_measure));
|
|
+ wl_measure.last_present = last;
|
|
+}
|
|
+
|
|
static VkResult
|
|
wsi_wl_swapchain_queue_present(struct wsi_swapchain *wsi_chain,
|
|
uint32_t image_index,
|
|
@@ -3286,6 +3318,7 @@ wsi_wl_swapchain_queue_present(struct wsi_swapchain *wsi_chain,
|
|
struct wsi_wl_swapchain *chain = (struct wsi_wl_swapchain *)wsi_chain;
|
|
bool timestamped = false;
|
|
bool queue_dispatched = false;
|
|
+ int64_t measure_start = os_time_get_nano(), measure_copy = 0;
|
|
|
|
MESA_TRACE_FUNC_FLOW(&chain->images[image_index].wayland_buffer.flow);
|
|
|
|
@@ -3314,9 +3347,11 @@ wsi_wl_swapchain_queue_present(struct wsi_swapchain *wsi_chain,
|
|
|
|
if (chain->buffer_type == WSI_WL_BUFFER_SHM_MEMCPY) {
|
|
struct wsi_wl_image *image = &chain->images[image_index];
|
|
+ int64_t copy_start = os_time_get_nano();
|
|
wsi_image_invalidate_cpu_map(&chain->base, &image->base);
|
|
memcpy(image->shm_ptr, image->base.cpu_map,
|
|
image->base.row_pitches[0] * chain->extent.height);
|
|
+ measure_copy = os_time_get_nano() - copy_start;
|
|
}
|
|
|
|
VkResult ret = wsi_wl_swapchain_update_colorspace(chain);
|
|
@@ -3515,6 +3550,7 @@ wsi_wl_swapchain_queue_present(struct wsi_swapchain *wsi_chain,
|
|
|
|
memset(&chain->timing_request, 0, sizeof(chain->timing_request));
|
|
|
|
+ wl_measure_frame(chain, measure_start, measure_copy, os_time_get_nano());
|
|
return VK_SUCCESS;
|
|
}
|
|
|