• MSAA Fixes: Fixes upload/download for MSAA textures using temporary non-MSAA images. Ensures compatibility with color formats and adds fallbacks for depth/stencil.
• Memory fix misallocation: Adds checks for null/zero-length operations in memory management and improves cleanup to avoid crashes (Related to crash issues due to misallocation, RP5 and 865)
• Vulkan Initialization (RAII): this almost rewrites the way vulkan initializes to avoid crashes, using a correct order now (thanks @crueter for the initial fix)
•Please check before merging:
- Test MSAA workflows (especially color/depth transitions and low memory cases).
- Verify memory operations (e.g., unmapping zero-length regions).
- Check Vulkan object lifetimes and platform-specific behavior.
- Check others plataforms beyond android
Why is everything in one PR? Otherwise, this is all a big fix, by checking the points above we can create a branch for each one and check them by themselves. I'm not standing still while I'm away, I'm just out of time for now.
Reviewed-on: eden-emu/eden#116
Co-authored-by: MrPurple666 <mrpurple666@noreply.localhost>
Co-committed-by: MrPurple666 <mrpurple666@noreply.localhost>
Track the private anonymous placeholder mappings created by Unmap() and
wherever possible, replace existing placeholders with larger ones
instead of creating many small ones.
This helps with the buildup of mappings in /proc/YUZU_PID/maps after a
longer gaming session, improving stability without having to increase
vm.max_map_count to a ridiculous value. The amount of placeholder
mappings will no longer outgrow the amount of actual memfd mappings in
cases of high memory fragmentation.
This formats all copyright comments according to SPDX formatting guidelines.
Additionally, this resolves the remaining GPLv2 only licensed files by relicensing them to GPLv2.0-or-later.
It is possible for virtual_offset to not be 0 when the iterator is at the beginning, and thus, std::prev(it) may be evaluated, leading to a crash in debug mode.
Co-Authored-By: Fernando S. <1731197+FernandoS27@users.noreply.github.com>
This falls back to the old approach of using a virtual buffer.
Windows is untested, but this build should fix support for Windows < 10 v1803. However without fastmem support at all.
