gpu_vaspace.c assertions and dmaAllocMapping_GM107 failures under high VRAM usage
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 新手友好度
- 35/100
- Issue 类型
- 缺陷
- 描述清晰度
- 需要澄清
- 活跃度
- 活跃
- 技术栈
- c, linux
调研方向
Start with gpu_vaspace.c and the dmaAllocMapping_GM107 call path implicated by the reported assertion. Reproduce the failure with Substance Painter at high VRAM usage using a 4K textureset while comparing 1K and 2K workloads, and inspect the attached NVIDIA bug report. Done means identifying and fixing the mapping failure, with a regression test or repeatable verification showing the 4K workload no longer produces the assertion.
由索引模型根据 Issue 内容生成。
描述
NVIDIA Open GPU Kernel Modules Version
615.78.08
Please confirm this issue does not happen with the proprietary driver (of the same version). This issue tracker is only for bugs specific to the open kernel driver.
- I confirm that this does not happen with the proprietary driver package.
Operating System and Version
CachyOS
Kernel Release
Linux ZOS 7.2.9-2-cachyos #1 SMP PREEMPT_DYNAMIC Fri, 09 Oct 2026 15:36:46 +0000 x86_64 GNU/Linux
Please confirm you are running a stable release kernel (e.g. not a -rc). We do not accept bug reports for unreleased kernels.
- I am running on a stable kernel release.
Hardware: GPU
NVIDIA GeForce RTX 3060 Ti (UUID: GPU-9370f5e5-6960-c726-81de-17a10ead47b4)
Describe the bug
Under high GPU memory usage, I repeatedly encounter NVIDIA kernel errors involving GPU virtual-address-space mapping failures. GPU memory usage reached approximately 7871 MiB out of 8192 MiB when observed.
The errors include:
intermapRegisterDmaMapping: Failed to insert new mapping node
nvAssertFailedNoLog: Assertion failed: NV_OK == status @ gpu_vaspace.c
NV_ERR_INVALID_ARGUMENT
_gvaspaceMappingInsert
dmaAllocMapping_GM107: can't update VA space for mapping
The issue occurs during a workload involving 4K textures; the same workload does not trigger the problem with 1K or 2K textures.
I found other reports mentioning similar errors and suspect that high VRAM usage may expose a GPU virtual-address-space or DMA mapping problem.
To Reproduce
I have this on Substance Painter (both 2025 and 2026), I set my resolution to 4k for only one textureset, while using the path tool for stitching.
Bug Incidence
Always
nvidia-bug-report.log.gz
More Info
No response
- 主要语言
- C
- 星标
- 17.5k
- 派生
- 1.9k
- PR 合并指标
- 30 天内没有已合并 PR
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 没有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
NVIDIA/open-gpu-kernel-modules 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 76/100
NVIDIA/open-gpu-kernel-modules#1479 · 2 条评论 ·
维护者通常 1 天内回复
-
PlatformRequestHandler: missing !bInit guard on bSystemParamLimitUpdate causes NV_ERR_INVALID_DATA at boot可能已有人在做 @SammyTourani 于 38 天前认领。 未关闭
难度 1/5 1 小时以内 新手友好度 88/100
NVIDIA/open-gpu-kernel-modules#1360 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 72/100
NVIDIA/open-gpu-kernel-modules#1343 · 3 条评论 ·
维护者通常 1 天内回复
-
HKC G27H7Pro redundant long-HPD loop after DisplayPort link training (RTX 5060 Laptop, 610.57.04)未关闭bug
难度 2/5 1-3 小时 新手友好度 88/100
NVIDIA/open-gpu-kernel-modules#1323 ·
维护者通常 1 天内回复
-
build-problem
难度 2/5 1-3 小时 新手友好度 74/100
NVIDIA/open-gpu-kernel-modules#1155 · 1 条评论 ·
维护者通常 1 天内回复
查看 NVIDIA/open-gpu-kernel-modules 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复
-
ai-driven-fuzzing bug claude Minor
难度 2/5 1-3 小时 新手友好度 78/100
linagora/open-bastion#425 ·
维护者通常 1 天内回复
-
question
难度 1/5 1 小时以内 新手友好度 68/100
-
follow-up Prio 📌
难度 2/5 1-3 小时 新手友好度 75/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 84/100
moonbitlang/async#713 ·
维护者通常 1 天内回复