Merge task/uborder: #896 (order overlapping uniform overlay copies), #859, #860, #862, #863 (checks that failed on dev)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

docs/settings.md

@@ -74,6 +74,7 @@ Many rows below are developer tools that only act together with another setting
 | `menu_test_set` | `<frame>:<key>=<value>[,...][;...]` changes settings live at that frame, with or without the menu open; `SAVE=1` also writes `totk.ini`. | Settings change during play without input, and `SAVE=1` rewrites the file. | Caution |
 | `probe_movie` | Text that picks the movie for `totk.exe --probe-movie`: the first file whose path contains it. | Only used by the movie decoder probe; ignored in normal play. | Safe |
 | `probe_movie_shot` | Path of a `.ppm` file that the movie probe writes the middle frame to. | Only used by the movie decoder probe. | Safe |
+| `probe_movie_bench` | `1` makes the movie probe also time the resampler that fits a movie to a game resolution of another shape, and print the time per frame. | Only used by the movie decoder probe. | Safe |
 | `swkbd_answer` | `<text>`, `<cancel>` or `<initial>`: answers the on-screen keyboard (for example a horse name) without opening a window. | The game gets that answer every time it asks for text. | Caution |
 | `swkbd_test` | `ok` or `cancel` opens the keyboard window and presses OK or Cancel on the first timer tick. | The keyboard window closes by itself. | Caution |
 | `test_pad` | `<lx>,<ly>,<rx>,<ry>` attaches a virtual gamepad whose sticks rest at these raw SDL axis values (-32768 to 32767). | The game sees a controller with that drift or deflection; a malformed value is logged and ignored. | Caution |

runtime/ov_probe.c

@@ -929,8 +929,14 @@ static void probe_menu_text(void) {
     cfg_set("TOTK_MENU_LANG", "zh-Hans");
     CHECK(menu_text(UI_MENU_TITLE) == ui_text_in("zh-Hans", UI_MENU_TITLE), "menu_text ignores MENU_LANG=zh-Hans");
     cfg_set("TOTK_MENU_LANG", "");
+    // the system language as ui_text.c resolve_menu_lang takes it: the tag, else its base language (ru-RU: ru), else en
     const char *sys_lang = ui_text_lang(plat_ui_language());
-    const char *auto_lang = ui_text_defined(sys_lang, UI_MENU_TITLE) ? sys_lang : "en";
+    char sys_base[16] = "";
+    size_t base_n = strcspn(sys_lang, "-");
+    if (sys_lang[base_n] && base_n < sizeof sys_base) memcpy(sys_base, sys_lang, base_n);
+    const char *auto_lang = ui_text_defined(sys_lang, UI_MENU_TITLE) ? sys_lang
+                            : *sys_base && ui_text_defined(sys_base, UI_MENU_TITLE) ? sys_base
+                                                                                      : "en";
     CHECK(menu_text(UI_MENU_CONTINUE) == ui_text_in(auto_lang, UI_MENU_CONTINUE), "menu_text auto ignores the system language");
 }
 

runtime/ui_text.c

@@ -1100,6 +1100,10 @@ static const char *const text_pt_br[UI_TEXT_COUNT] = {
     [UI_MENU_MODE_DOCKED] = "Modo TV", [UI_MENU_MODE_HANDHELD] = "Modo portátil",
 
     [UI_MENU_VOLUME] = "Volume", [UI_MENU_VOLUME_DESC] = "Volume geral do jogo.",
+    [UI_MENU_AUDIO_CHANNELS] = "Alto-falantes",
+    [UI_MENU_AUDIO_CHANNELS_DESC] = "Saída estéreo ou surround 5.1. Automático escolhe 5.1 quando a configuração de "
+                                    "alto-falantes do Windows tem seis canais ou mais. Vale após reiniciar.",
+    [UI_MENU_CHANNELS_AUTO] = "Automático", [UI_MENU_CHANNELS_STEREO] = "Estéreo", [UI_MENU_CHANNELS_51] = "Surround 5.1",
 
     [UI_MENU_MOTION] = "Controles de movimento", [UI_MENU_MOTION_DESC] = "Mirar com o giroscópio do controle.",
     [UI_MENU_RUMBLE_STRENGTH] = "Intensidade da vibração",
@@ -1647,6 +1651,9 @@ static const char *const text_zh_hans[UI_TEXT_COUNT] = {
                                   "这样被打断的读取可能会永久卡住。",
     [UI_MENU_VOLUME] = "音量",
     [UI_MENU_VOLUME_DESC] = "游戏的主音量。",
+    [UI_MENU_AUDIO_CHANNELS] = "扬声器",
+    [UI_MENU_AUDIO_CHANNELS_DESC] = "立体声或 5.1 环绕声输出。选择自动时，若 Windows 扬声器设置有六个或更多声道则使用 5.1。重启后生效。",
+    [UI_MENU_CHANNELS_AUTO] = "自动", [UI_MENU_CHANNELS_STEREO] = "立体声", [UI_MENU_CHANNELS_51] = "5.1 环绕声",
     [UI_MENU_MOTION] = "体感操作",
     [UI_MENU_MOTION_DESC] = "用手柄的陀螺仪瞄准。",
     [UI_MENU_RUMBLE_STRENGTH] = "振动强度",

runtime/vk_exec_draw.c

@@ -175,7 +175,7 @@ static struct {
     struct { uint64_t dst; VkBuffer src; VkDeviceSize soff; VkMemSpan sp; uint64_t size; } p[OV_N];   // to copy
     struct { uint64_t lo, hi; } f[OV_FOREIGN];   // GPU writes of other kinds
     // since the last perf line (vk_exec_ub_perf)
-    uint64_t c_update, c_overlaid, c_flush, c_bind, c_merged, c_mixed, c_inpass, c_outside, c_early;
+    uint64_t c_update, c_overlaid, c_flush, c_bind, c_merged, c_mixed, c_inpass, c_outside, c_early, c_order;
 } OV = {.mode = -1};
 
 // A binding without a size reaches to the end of its backing: as far as the overlays go, for ov_at.
@@ -3349,7 +3349,22 @@ void vk_exec_ub_flush(VkExec *ex) {
     VkDependencyInfo di = {.sType = VK_STRUCTURE_TYPE_DEPENDENCY_INFO, .memoryBarrierCount = 1, .pMemoryBarriers = &mb};
     vkCmdPipelineBarrier2(ex->cb, &di);
     ex->recorded++;
+    // Copies without a barrier between them may run in any order, and ov_add only drops an older copy of exactly the
+    // same range: a copy that overlaps one recorded since the last barrier waits for it, so the newer bytes land last.
+    VkMemoryBarrier2 ww = {.sType = VK_STRUCTURE_TYPE_MEMORY_BARRIER_2,
+                           .srcStageMask = VK_PIPELINE_STAGE_2_COPY_BIT, .srcAccessMask = VK_ACCESS_2_TRANSFER_WRITE_BIT,
+                           .dstStageMask = VK_PIPELINE_STAGE_2_COPY_BIT, .dstAccessMask = VK_ACCESS_2_TRANSFER_WRITE_BIT};
+    VkDependencyInfo wdi = {.sType = VK_STRUCTURE_TYPE_DEPENDENCY_INFO, .memoryBarrierCount = 1, .pMemoryBarriers = &ww};
+    uint32_t since = 0;   // the first copy recorded after the last barrier
     for (uint32_t i = 0; i < OV.np; i++) {
+        for (uint32_t k = since; k < i; k++)
+            if (OV.p[i].dst < OV.p[k].dst + OV.p[k].size && OV.p[k].dst < OV.p[i].dst + OV.p[i].size) {
+                vkCmdPipelineBarrier2(ex->cb, &wdi);
+                ex->recorded++;
+                OV.c_order++;
+                since = i;
+                break;
+            }
         VkBufferCopy cp = {OV.p[i].soff, OV.p[i].sp.offset, OV.p[i].size};
         vkCmdCopyBuffer(ex->cb, OV.p[i].src, OV.p[i].sp.buffer, 1, &cp);
         ex->recorded++;
@@ -3365,11 +3380,11 @@ void vk_exec_ub_perf(void) {
     const double k = 1 / 600.0;
     rt_log("perf: uniform updates per submission %.1f: %.1f overlaid in a pass (copied in %.2f batches), %.1f copied "
            "in a pass, %.1f outside one; bindings from an overlay %.1f (%.1f merged, %.1f over other GPU writes), %.2f "
-           "batches brought forward for a storage write",
+           "batches brought forward for a storage write, %.2f barriers between overlapping copies",
            OV.c_update * k, OV.c_overlaid * k, OV.c_flush * k, OV.c_inpass * k, OV.c_outside * k, OV.c_bind * k,
-           OV.c_merged * k, OV.c_mixed * k, OV.c_early * k);
+           OV.c_merged * k, OV.c_mixed * k, OV.c_early * k, OV.c_order * k);
     OV.c_update = OV.c_overlaid = OV.c_flush = OV.c_bind = OV.c_merged = OV.c_mixed = 0;
-    OV.c_inpass = OV.c_outside = OV.c_early = 0;
+    OV.c_inpass = OV.c_outside = OV.c_early = OV.c_order = 0;
 }
 
 // The scratch bytes of a uniform or storage binding [addr, addr+n) an overlay of this submission touches: 1 with *out

tests/worktree_test.py

@@ -18,7 +18,7 @@ ROOT = Path(__file__).resolve().parent.parent
 sys.path.insert(0, str(ROOT / 'tools'))
 import worktree  # noqa: E402
 
-IGNORED = '\n'.join('/' + d + '/' for d in worktree.LINK_DIRS) + '\n/' + worktree.LINK_FILES[0] + '\n/.worktrees/\n'
+IGNORED = ''.join(f'/{p}\n' for p in [d + '/' for d in worktree.LINK_DIRS] + worktree.LINK_FILES + ['.worktrees/'])
 
 
 def git(cwd, *a):