register: 0.878 TCG: 0.836 graphic: 0.731 device: 0.728 architecture: 0.663 mistranslation: 0.635 kernel: 0.577 performance: 0.568 semantic: 0.551 network: 0.544 permissions: 0.525 peripherals: 0.492 files: 0.482 socket: 0.467 ppc: 0.453 risc-v: 0.451 vnc: 0.421 user-level: 0.417 debug: 0.408 hypervisor: 0.399 i386: 0.398 PID: 0.398 boot: 0.390 arm: 0.373 VMM: 0.346 assembly: 0.341 KVM: 0.339 x86: 0.282 virtual: 0.270 -------------------- TCG: 0.974 x86: 0.931 register: 0.679 assembly: 0.573 debug: 0.193 architecture: 0.057 kernel: 0.048 virtual: 0.042 i386: 0.032 semantic: 0.022 files: 0.021 hypervisor: 0.018 arm: 0.012 device: 0.011 user-level: 0.008 network: 0.008 socket: 0.006 risc-v: 0.005 performance: 0.005 ppc: 0.004 PID: 0.003 boot: 0.003 peripherals: 0.003 permissions: 0.002 vnc: 0.001 graphic: 0.001 VMM: 0.001 mistranslation: 0.000 KVM: 0.000 TCG: mov to segment register is incorrectly emulated for AMD CPUs In TCG mode, the effect of: xorl %eax, %eax movl %eax, %gs is to mark the GS segment unusable and set its base to zero. After doing this, reading MSR_GS_BASE will return zero and using a GS prefix in long mode will treat the GS base as zero. This is correct for Intel CPUs but is incorrect for AMD CPUs. On an AMD CPU, writing 0 to %gs using mov, pop, or (I think) lgs will leave the base unchanged. To make it easier to use TCG to validate behavior on different CPUs, please consider changing the TCG behavior to match actual CPU behavior when emulating an AMD CPU. The QEMU project is currently considering to move its bug tracking to another system. For this we need to know which bugs are still valid and which could be closed already. Thus we are setting older bugs to "Incomplete" now. If you still think this bug report here is valid, then please switch the state back to "New" within the next 60 days, otherwise this report will be marked as "Expired". Or please mark it as "Fix Released" if the problem has been solved with a newer version of QEMU already. Thank you and sorry for the inconvenience. [Expired for QEMU because there has been no activity for 60 days.]