an update on this: it was actually pcie_aspm=off what helped to solve the problem.
I think the problem is related to the power management of PCIe ports. Without pcie_aspm=off I started seeing errors like the following ones: - [drm:intel_pipe_update_end [i915]] *ERROR* Atomic update failure on pipe A (start=7841 end=7842) time 291 us, min 1063, max 1079, scanline start 1044, end 1092 pcieport 0000:00:1d.0: AER: Corrected error received: 0000:00:1d.0 pcieport 0000:00:1d.0: AER: PCIe Bus Error: severity=Corrected, type=Physical Layer, (Receiver ID) pcieport 0000:00:1d.0: AER: device [8086:a330] error status/mask=00000001/00002000 I think the bug is not with the nvme controller but somewhere in ASPM. But I am not a kernel developer. -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1746340 Title: Samsung SSD corruption (fsck needed) To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1746340/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs