Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1478639
| From | Francis Giraldeau <francis.giraldeau@gmail.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: Ping: [PATCH v15 00/13] support "task_isolation" mode |
| Date | 2016-09-07 23:50 +0200 |
| Message-ID | <seSTf-5pg-3@gated-at.bofh.it> (permalink) |
| References | <s6U5P-8nJ-3@gated-at.bofh.it> <seSqd-5fu-9@gated-at.bofh.it> <seSqd-5fu-7@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
On 2016-09-07 05:11 PM, Francis Giraldeau wrote:
> The syscall test fails on x86:
> $ sudo ./isolation
> [...]
> test_syscall: FAIL (0x100)
> test_syscall (SIGUSR1): FAIL (0x100)
>
> I wanted to debug this problem with gdb and a KVM virtual machine. However, the TSC clock source is detected as non reliable, even with the boot parameter tsc=reliable, and therefore prctl(PR_SET_TASK_ISOLATION, PR_TASK_ISOLATION_ENABLE) always returns EAGAIN. Is there a trick to run task isolation in a VM (at least for debugging purposes)?
OK, got it. The guest kernel must be compiled with CONFIG_KVM_GUEST, and then with virsh edit, set the clock configuration of the VM (under <domain>):
<clock offset='utc'>
<timer name='kvmclock'/>
</clock>
Of course, the jitter is horrible, but at least it is possible to debug with GDB.
Cheers,
Francis
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
Re: Ping: [PATCH v15 00/13] support "task_isolation" mode Francis Giraldeau <francis.giraldeau@gmail.com> - 2016-09-07 23:20 +0200 Re: Ping: [PATCH v15 00/13] support "task_isolation" mode Francis Giraldeau <francis.giraldeau@gmail.com> - 2016-09-07 23:50 +0200 Re: Ping: [PATCH v15 00/13] support "task_isolation" mode Francis Giraldeau <francis.giraldeau@gmail.com> - 2016-09-08 18:30 +0200
csiph-web