Mirror-bot/darling-lol
1
0 Fork 0
mirror of https://github.com/lucannez64/darling-lol.git synced 2026-10-26 19:47:42 +00:00
Code Issues Projects Releases Activity

Allocate League's Metal drawables in VRAM

Browse Source 
League sets framebufferOnly=NO on its CAMetalLayer, and QuartzCore read
that as needing host-visible coherent memory, so the game's final
render target and the linear image handed to OpenGL both lived in
system RAM (type 2 on the RX 6600) and crossed PCIe every frame.
framebufferOnly=NO only lets Metal sample or blit the texture: nothing
maps either image (replaceRegion aborts, getBytes is a stub, Indium
maps only Shared/Managed buffers).

Drawables now take the first allowed DEVICE_LOCAL type whatever
framebufferOnly says; the guest file /tmp/metal-no-drawable-vram
restores the old placement. metal-device.log shows drawable-vram=on and
storage=vram.

A native EGL/RADV test exported the drawable's linear image from VRAM
and imported it into GL with no errors and identical pixels. In a
practice-tool baron fight on the RX 6600 with the same champion it ran
about 20 FPS faster and the same when idle; not yet measured in an ARAM.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
lucannez64andClaude Opus 5.5 committed 2026-10-16 02:17:51 +02:00
1 parent 6d06adf71a
commit 908f88bad7
3 files changed
+54 -23
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/SETUP.md
+1
View File
@@ -101,6 +101,7 @@ Indium also contains experimental hand-off changes. They are **off by default**:
| `/tmp/metal-skip-cpu-devices` | software Vulkan devices (lavapipe) are skipped while a hardware device exists |
| `/tmp/metal-gpu` | diagnostic: selects the Vulkan device used for Metal by index or case-insensitive name substring instead of the loader's first device. The OpenGL context that presents does not follow it; see [hybrid laptops](TROUBLESHOOTING.md#hybrid-graphics-laptops-amdintel-igpu--nvidia). `METAL_INDIUM_GPU` is the environment equivalent; the file wins |
| `/tmp/metal-all-devices` | a `VkDevice` is created for every supported Vulkan device, as before 2026-10-16. Without it only the selected device gets one; on a machine with lavapipe installed this also drops lavapipe's idle rasterizer threads |
| `/tmp/metal-no-drawable-vram` | drawables of a layer with `framebufferOnly` off (League sets it off) go back to host-visible system RAM, as before 2026-10-16. Without the file they are allocated in GPU memory like `framebufferOnly` drawables; nothing maps drawable memory from the CPU. On the RX 6600 this gave about 20 FPS more in a practice-tool fight and the same FPS when idle, not yet measured in an ARAM. `/tmp/metal-device.log` shows `drawable-vram=on` and `storage=vram` |
| `/tmp/metal-debug-waits` | diagnostic: counts how often and how long threads block at the hand-off waits and in `nextDrawable`, every 5 s in `/tmp/metal-trace.log`; the first check writes a `waits enabled` line |
Create these files from inside the guest, for example `darling shell touch /tmp/metal-debug-waits`, or while Darling is shut down. The guest `/tmp` is `~/.darling/private/tmp` seen through Darling's overlay mount. A file created on the host in that directory while Darling runs may stay invisible to guest processes that already looked for it. The same applies to removing a file. The older `/tmp/metal-no-present-dispatch-wait`, `/tmp/metal-no-deferred-blit` and `/tmp/metal-no-skip-cpu-devices` files are ignored.
docs/TROUBLESHOOTING.md
+1 -1
View File
@@ -193,7 +193,7 @@ The log also lists the selected device's memory heaps and types, and one line th
[MetalDevice] pid=… memory alloc kind=texture storage=private typeBits=0x… type=1 flags=0x1(DEVICE_LOCAL) heap=0 heapDeviceLocal=yes firstFit=0 flags=0x0(none) heap=1 heapDeviceLocal=no changed=yes
```
Resources only the GPU uses (`private`, `memoryless`, and `framebufferOnly` drawables) take the first allowed `DEVICE_LOCAL` type. Before 2026-10-16 they took the first allowed type (`firstFit`), which on NVIDIA can be system RAM; `changed=yes` marks where the two differ. `shared` and `managed` resources keep the first host-visible type. On the RX 6600 (RADV) type 0 is `DEVICE_LOCAL`, so nothing changes there.
Resources only the GPU uses (`private`, `memoryless`, and drawables, including League's `framebufferOnly`-off ones unless `/tmp/metal-no-drawable-vram` exists) take the first allowed `DEVICE_LOCAL` type. Before 2026-10-16 they took the first allowed type (`firstFit`), which on NVIDIA can be system RAM; `changed=yes` marks where the two differ. `shared` and `managed` resources keep the first host-visible type. On the RX 6600 (RADV) type 0 is `DEVICE_LOCAL`, so nothing changes there.
The first import of a drawable into the presenting OpenGL context, and the first semaphore import, are logged too; later ones only when they fail (at most five):
patches/cocotron.patch
+52 -22
View File
@@ -7105,7 +7105,7 @@ index 5ad375f8..c8e83814 100644
+- (BOOL) _treeHasAnimations;
@end
diff --git a/QuartzCore/CAMetalDrawable.mm b/QuartzCore/CAMetalDrawable.mm
index d6f86b31..2bdc198d 100644
index d6f86b31..20e4e88b 100644
--- a/QuartzCore/CAMetalDrawable.mm
+++ b/QuartzCore/CAMetalDrawable.mm
@@ -31,6 +31,13 @@
@@ -7221,7 +7221,7 @@ index d6f86b31..2bdc198d 100644
//
// helper classes
//
@@ -129,13 +226,39 @@ public:
@@ -129,27 +226,109 @@ public:
// texture
//
@@ -7250,9 +7250,26 @@ index d6f86b31..2bdc198d 100644
+// (see reportGpuDeviceMatch) -- so they take the first allowed DEVICE_LOCAL type,
+// falling back to first fit. Without framebufferOnly they still need host-visible,
+// coherent memory and keep first fit. On RADV type 0 is DEVICE_LOCAL: unchanged.
+//
+// League sets framebufferOnly=NO, so its drawables lived in system RAM and crossed
+// PCIe every frame. framebufferOnly=NO lets Metal sample or blit the texture; it
+// does not make it CPU-mapped, and nothing here maps either image (replaceRegion
+// aborts, getBytes is a stub), so those drawables are placed like framebufferOnly
+// ones too. On the RX 6600 that gave about 20 FPS more in a practice-tool fight and
+// the same FPS when idle. The guest flag file /tmp/metal-no-drawable-vram restores
+// host-visible memory. Read once per process, when the first drawable is created.
+static size_t findSharedMemory(const VkMemoryRequirements& reqs, std::shared_ptr<Indium::PrivateDevice> device, bool framebufferOnly, bool internal) {
+ static const bool drawableVram = access("/tmp/metal-no-drawable-vram", F_OK) != 0;
+ static std::once_flag logSwitch;
+ std::call_once(logSwitch, []() {
+ appendDeviceLog(std::string("drawable-vram=") + (drawableVram ? "on" : "off (file:/tmp/metal-no-drawable-vram)"));
+ });
+
+ const bool vramDrawable = !framebufferOnly && drawableVram;
+ const bool gpuOnly = framebufferOnly || vramDrawable;
+ const auto& memory = device->memoryProperties();
+ size_t firstFit = SIZE_MAX;
+ size_t legacy = SIZE_MAX; // the choice before 2026-10-16 (host-visible drawables), for the log
size_t targetIndex = SIZE_MAX;
- for (size_t i = 0; i < device->memoryProperties().memoryTypeCount; ++i) {
@@ -7265,7 +7282,15 @@ index d6f86b31..2bdc198d 100644
continue;
}
@@ -147,9 +270,42 @@ static size_t findSharedMemory(const VkMemoryRequirements& reqs, std::shared_ptr
- if (!framebufferOnly && (type.propertyFlags & VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT) == 0) {
- continue;
+ const bool hostVisible = (type.propertyFlags & VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT) != 0 && (type.propertyFlags & VK_MEMORY_PROPERTY_HOST_COHERENT_BIT) != 0;
+ if (legacy == SIZE_MAX && (framebufferOnly || hostVisible)) {
+ legacy = i;
}
- if (!framebufferOnly && (type.propertyFlags & VK_MEMORY_PROPERTY_HOST_COHERENT_BIT) == 0) {
+ if (!gpuOnly && !hostVisible) {
continue;
}
@@ -7276,9 +7301,9 @@ index d6f86b31..2bdc198d 100644
+ firstFit = i;
+ }
+
+ if (!framebufferOnly || (type.propertyFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT) != 0) {
+ // no early exit: the scan continues to find the legacy choice for the log
+ if (targetIndex == SIZE_MAX && (!gpuOnly || (type.propertyFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT) != 0)) {
+ targetIndex = i;
+ break;
+ }
+ }
+
@@ -7289,29 +7314,34 @@ index d6f86b31..2bdc198d 100644
+ return targetIndex;
+ }
+
+ // Once per (image, framebufferOnly, type) in the process, in Indium's device log.
+ static std::atomic<uint64_t> logged[2] {};
+ const size_t bit = ((internal ? 2u : 0u) + (framebufferOnly ? 1u : 0u)) * 32 + targetIndex;
+ // Once per (image, storage, type) in the process, in Indium's device log.
+ static std::atomic<uint64_t> logged[3] {};
+ const size_t storage = vramDrawable ? 2 : (framebufferOnly ? 1 : 0);
+ const size_t bit = ((internal ? 3u : 0u) + storage) * 32 + targetIndex;
+ const uint64_t mask = uint64_t(1) << (bit & 63);
+ if ((logged[bit >> 6].load(std::memory_order_relaxed) & mask) == 0 && (logged[bit >> 6].fetch_or(mask) & mask) == 0) {
+ auto describe = [&](size_t index) {
+ if (index == SIZE_MAX) {
+ return std::string("none");
+ }
+ const auto& type = memory.memoryTypes[index];
+ return std::to_string(index) + " flags=" + memoryFlagsString(type.propertyFlags)
+ + " heap=" + std::to_string(type.heapIndex)
+ + " heapDeviceLocal=" + ((memory.memoryHeaps[type.heapIndex].flags & VK_MEMORY_HEAP_DEVICE_LOCAL_BIT) ? "yes" : "no");
+ };
+ static const char* storageNames[] = { "hostVisible", "framebufferOnly", "vram" };
+ char typeBits[16];
+ snprintf(typeBits, sizeof(typeBits), "0x%08x", (unsigned) reqs.memoryTypeBits);
+ appendDeviceLog(std::string("memory alloc kind=") + (internal ? "drawable-internal" : "drawable")
+ + " storage=" + (framebufferOnly ? "framebufferOnly" : "hostVisible")
+ + " storage=" + storageNames[storage]
+ + " typeBits=" + typeBits
+ + " type=" + describe(targetIndex)
+ + " firstFit=" + describe(firstFit)
+ + (targetIndex != firstFit ? " changed=yes" : " changed=no"));
+ + " firstFit=" + describe(legacy)
+ + (targetIndex != legacy ? " changed=yes" : " changed=no"));
}
return targetIndex;
@@ -161,6 +317,11 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
@@ -161,6 +340,11 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
_pixelFormat(pixelFormat),
_framebufferOnly(framebufferOnly)
{
@@ -7323,7 +7353,7 @@ index d6f86b31..2bdc198d 100644
//
// create the images
//
@@ -219,7 +380,7 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
@@ -219,7 +403,7 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
DynamicVK::vkGetImageMemoryRequirements(_device->device(), _image, &reqs);
@@ -7332,7 +7362,7 @@ index d6f86b31..2bdc198d 100644
if (targetIndex == SIZE_MAX) {
throw std::runtime_error("No suitable memory region found for image");
@@ -242,7 +403,7 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
@@ -242,7 +426,7 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
DynamicVK::vkGetImageMemoryRequirements(_device->device(), _internalImage, &reqs);
@@ -7341,7 +7371,7 @@ index d6f86b31..2bdc198d 100644
if (targetIndex == SIZE_MAX) {
throw std::runtime_error("No suitable memory region found for internal image");
@@ -380,16 +541,26 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
@@ -380,16 +564,26 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
abort();
}
@@ -7370,7 +7400,7 @@ index d6f86b31..2bdc198d 100644
GLint prevTex = 0;
glGetIntegerv(GL_TEXTURE_BINDING_2D, &prevTex);
@@ -401,10 +572,36 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
@@ -401,10 +595,36 @@ CAMetalDrawableTexture::CAMetalDrawableTexture(CGSize size, Indium::PixelFormat
glTextureParameteri(_textureID, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
glTextureParameteri(_textureID, GL_TEXTURE_WRAP_S, GL_REPEAT);
glTextureParameteri(_textureID, GL_TEXTURE_WRAP_T, GL_REPEAT);
@@ -7409,7 +7439,7 @@ index d6f86b31..2bdc198d 100644
glBindTexture(GL_TEXTURE_2D, prevTex);
};
@@ -605,35 +802,16 @@ void CAMetalDrawableActual::present() {
@@ -605,35 +825,16 @@ void CAMetalDrawableActual::present() {
return;
}
@@ -7420,16 +7450,16 @@ index d6f86b31..2bdc198d 100644
- if (_semaphore) {
- int fd = -1;
- VkSemaphoreGetFdInfoKHR info {};
-
- info.sType = VK_STRUCTURE_TYPE_SEMAPHORE_GET_FD_INFO_KHR;
- info.semaphore = _semaphore->semaphore;
- info.handleType = VK_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD_BIT;
+ // present() may run on the deferred encoding worker. The window's
+ // EGL context remains current on the main thread, so attempting to
+ // import a semaphore here fails and leaks the exported syncobj FD.
+ // Import it in synchronizeRender(), with the compositor context
+ // current, immediately before the GPU-side wait.
- info.sType = VK_STRUCTURE_TYPE_SEMAPHORE_GET_FD_INFO_KHR;
- info.semaphore = _semaphore->semaphore;
- info.handleType = VK_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD_BIT;
-
- if (DynamicVK::vkGetSemaphoreFdKHR(_semaphore->device->device(), &info, &fd) != VK_SUCCESS) {
- // TODO
- abort();
@@ -7451,7 +7481,7 @@ index d6f86b31..2bdc198d 100644
}
}
@@ -702,9 +880,46 @@ void CAMetalDrawableActual::reset() {
@@ -702,9 +903,46 @@ void CAMetalDrawableActual::reset() {
};
void CAMetalDrawableActual::synchronizeRender() {