** Description changed: Ubuntu kernel 7.0.0-30-generic repeatedly crashes during sustained NVIDIA CUDA/AI training workload. - kdump successfully captured the crash. + full log is available in the dmesg logs.txt file The crash contains: UBSAN: array-index-out-of-bounds in drivers/iommu/dma-iommu.c:193:25 index -1523926064 is out of range for type 'long unsigned int [8192]' BUG: unable to handle page fault for address: fffffffcd2dccf60 Oops: Oops: 0000 [#1] SMP NOPTI RIP: fq_flush_timeout+0x57/0x120 CPU: 3 UID: 1000 PID: 12348 Comm: python Hardware: MSI PRO Z890-P WIFI (MS-7E34) NVIDIA GPU PCI ID 10de:2684 NVIDIA open kernel module 580.173.02 The failure is reproducible under AI training load and has caused multiple unclean reboots. A kdump from the latest occurrence is available at: /var/crash/202608271339/ ProblemType: Bug DistroRelease: Ubuntu 26.04 Package: linux-image-7.0.0-30-generic 7.0.0-30.30 ProcVersionSignature: Ubuntu 7.0.0-30.30-generic 7.0.12 Uname: Linux 7.0.0-30-generic x86_64 ApportVersion: 2.34.1-0ubuntu0.1 Architecture: amd64 AudioDevicesInUse: Error: command ['fuser', '-v', '/dev/snd/controlC1', '/dev/snd/hwC1D2', '/dev/snd/hwC1D0', '/dev/snd/pcmC1D9p', '/dev/snd/pcmC1D8p', '/dev/snd/pcmC1D7p', '/dev/snd/pcmC1D3p', '/dev/snd/pcmC1D2c', '/dev/snd/pcmC1D0c', '/dev/snd/pcmC1D0p', '/dev/snd/by-path', '/dev/snd/controlC0', '/dev/snd/hwC0D0', '/dev/snd/pcmC0D9p', '/dev/snd/pcmC0D8p', '/dev/snd/pcmC0D7p', '/dev/snd/pcmC0D3p', '/dev/snd/seq', '/dev/snd/timer'] failed with exit code 1: CasperMD5CheckResult: pass CurrentDesktop: ubuntu:GNOME Date: Thu Aug 27 13:46:04 2026 InstallationDate: Installed on 2026-02-24 (184 days ago) InstallationMedia: Ubuntu 25.10 "Questing Quokka" - Release amd64 (20251007) MachineType: Micro-Star International Co., Ltd. MS-7E34 ProcEnviron: - LANG=en_US.UTF-8 - PATH=(custom, no user) - SHELL=/bin/bash - TERM=xterm-256color - XDG_RUNTIME_DIR=<set> + LANG=en_US.UTF-8 + PATH=(custom, no user) + SHELL=/bin/bash + TERM=xterm-256color + XDG_RUNTIME_DIR=<set> ProcFB: - + ProcKernelCmdLine: BOOT_IMAGE=/boot/vmlinuz-7.0.0-30-generic root=UUID=2559f3ff-5281-4fdf-ac70-83f5c8203c91 ro quiet splash crashkernel=2G-4G:320M,4G-32G:512M,32G-64G:1024M,64G-128G:2048M,128G-:4096M SourcePackage: linux UpgradeStatus: Upgraded to resolute on 2026-08-03 (24 days ago) dmi.bios.date: 03/05/2026 dmi.bios.release: 5.32 dmi.bios.vendor: American Megatrends International, LLC. dmi.bios.version: 1.AC1 dmi.board.asset.tag: Default string dmi.board.name: PRO Z890-P WIFI (MS-7E34) dmi.board.vendor: Micro-Star International Co., Ltd. dmi.board.version: 1.0 dmi.chassis.asset.tag: Default string dmi.chassis.type: 3 dmi.chassis.vendor: Micro-Star International Co., Ltd. dmi.chassis.version: 1.0 dmi.modalias: dmi:bvnAmericanMegatrendsInternational,LLC.:bvr1.AC1:bd03/05/2026:br5.32:svnMicro-StarInternationalCo.,Ltd.:pnMS-7E34:pvr1.0:rvnMicro-StarInternationalCo.,Ltd.:rnPROZ890-PWIFI(MS-7E34):rvr1.0:cvnMicro-StarInternationalCo.,Ltd.:ct3:cvr1.0:skuDefaultstring:pfaDefaultstring: dmi.product.family: Default string dmi.product.name: MS-7E34 dmi.product.sku: Default string dmi.product.version: 1.0 dmi.sys.vendor: Micro-Star International Co., Ltd.
-- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/2165247 Title: dma-iommu.c kernel crash To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2165247/+subscriptions -- ubuntu-bugs mailing list [email protected] https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
