diff options
Diffstat (limited to 'results/classifier/108/other/1904317')
| -rw-r--r-- | results/classifier/108/other/1904317 | 104 |
1 files changed, 104 insertions, 0 deletions
diff --git a/results/classifier/108/other/1904317 b/results/classifier/108/other/1904317 new file mode 100644 index 00000000..ddd4467b --- /dev/null +++ b/results/classifier/108/other/1904317 @@ -0,0 +1,104 @@ +graphic: 0.841 +other: 0.830 +device: 0.819 +semantic: 0.812 +permissions: 0.806 +network: 0.800 +socket: 0.792 +PID: 0.791 +performance: 0.780 +debug: 0.763 +KVM: 0.748 +boot: 0.706 +vnc: 0.704 +files: 0.701 + +cpu feature selection is not affected to guest 's cpuid with whpx + +On windows with -accel whpx, "-cpu" is ignored without any messages. +Guest recognizes features as same as host's. + +Confirmed on v5.2.0-rc1. + +I suggest qemu may do, + +- Warn with incompatible -cpu options were given. +- Enhance cpuid handling. + +Background: +I was investigated mmio and block copy issue in Linux kernel. +I met a problem that Linux went ill for touching mmio with whpx. (not with tcg) +I suspect erms(enhanced rep movs) might trigger. +I tried to mask erms on qemu with -feature,erms, but it was ineffective. + +At last, I disabled erms manually, to tweak whpx-all.c to mask erms in cpuid. + +FYI, qemu with whpx from/to mmio, "rep movsb" does byte access regardless of erms. +Linux kernel tends to choose not "rep movsq" but "rep movsb" with erms. + +Cc'ing Sunil (WHPX maintainer). + +On 11/15/20 10:06 AM, Takumi Nakamura wrote: +> Public bug reported: +> +> On windows with -accel whpx, "-cpu" is ignored without any messages. +> Guest recognizes features as same as host's. +> +> Confirmed on v5.2.0-rc1. +> +> I suggest qemu may do, +> +> - Warn with incompatible -cpu options were given. +> - Enhance cpuid handling. +> +> Background: +> I was investigated mmio and block copy issue in Linux kernel. +> I met a problem that Linux went ill for touching mmio with whpx. (not with tcg) +> I suspect erms(enhanced rep movs) might trigger. +> I tried to mask erms on qemu with -feature,erms, but it was ineffective. +> +> At last, I disabled erms manually, to tweak whpx-all.c to mask erms in +> cpuid. +> +> FYI, qemu with whpx from/to mmio, "rep movsb" does byte access regardless of erms. +> Linux kernel tends to choose not "rep movsq" but "rep movsb" with erms. +> +> ** Affects: qemu +> Importance: Undecided +> Status: New +> + + + +The QEMU project is currently moving 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 the bug state to "Incomplete" now. + +If the bug has already been fixed in the latest upstream version of QEMU, +then please close this ticket as "Fix released". + +If it is not fixed yet and you think that this bug report here is still +valid, then you have two options: + +1) If you already have an account on gitlab.com, please open a new ticket +for this problem in our new tracker here: + + https://gitlab.com/qemu-project/qemu/-/issues + +and then close this ticket here on Launchpad (or let it expire auto- +matically after 60 days). Please mention the URL of this bug ticket on +Launchpad in the new ticket on GitLab. + +2) If you don't have an account on gitlab.com and don't intend to get +one, but still would like to keep this ticket opened, then please switch +the state back to "New" or "Confirmed" within the next 60 days (other- +wise it will get closed as "Expired"). We will then eventually migrate +the ticket automatically to the new system (but you won't be the reporter +of the bug in the new system and thus you won't get notified on changes +anymore). + +Thank you and sorry for the inconvenience. + + +[Expired for QEMU because there has been no activity for 60 days.] + |