I guess I should clarify (for my future sake, at least) that the Jailhouse
driver automatically passes this Linux-derived frequency into each cell's
config, while I'm planning on measuring frequency information from the MSRs
directly within an inmate.
--
You received this message because you
Hello,
I notice that on my machine (Coffee Lake architecture, Intel 8th
Generation), apparently Linux detects a TSC frequency of 3,696,003,000 Hz.
However, the Intel SDM Vol. 4 Table 2-20, under bits 8-15 of the
PLATFORM_INFO_MSR (0xCE), says that the invariant TSC runs at the Maximum
Hey Jan,
Here are the generated cells and their corresponding .o files for GCC 7, 8,
and 9, as well as the original .c config file.
Quick overview of the beginning of each .o file, with changes bolded:
GCC 7:
7f45 4c46 0201 0100
0100 3e00 0100
Hi all,
I'm not sure if this is relevant in this case, but I have noticed that on
Intel x86-64, if hardware p-states (HWP) are enabled in the CPU (which they
are by default if the CPU supports it), this introduces frequency scaling
coupling between cores, even when the cores are isolated in
Hello,
After updating to Kubuntu 19.10 (kernel 5.3) from 19.04, I get the
following error when trying to enable the root cell:
JAILHOUSE_ENABLE: Invalid argument
dmesg shows:
[ 475.080776] jailhouse: Not a system configuration
which comes from this code in
Thank you! That did the trick.
-Michael
On Saturday, October 5, 2019 at 1:41:02 AM UTC-6, Jan Kiszka wrote:
>
> On 05.10.19 02:08, michael...@gmail.com wrote:
> > Hello,
> >
> >
> > I want to increase how much memory my inmate can use to 10 MB.
> >
> >
> > Here’s the relevant memory
Hello,
I want to increase how much memory my inmate can use to 10 MB.
Here’s the relevant memory regions of the root config:
/* MemRegion: 3a60-3f1f : JAILHOUSE Inmate Memory */
{
.phys_start = 0x3a60,
.virt_start = 0x3a60,
// MGH: Leave a 1 MB region for IVSHMEM (4c ->
On Saturday, May 25, 2019 at 12:00:15 PM UTC-6, michael...@gmail.com wrote:
> On Thursday, May 23, 2019 at 3:55:24 AM UTC-6, jeanne@gmail.com wrote:
> > Le samedi 9 février 2019 06:26:29 UTC+1, michael...@gmail.com a écrit :
> > > On Friday, February 8, 2019 at 8:40:18 AM UTC-7, Henning Schild
On Thursday, May 23, 2019 at 3:55:24 AM UTC-6, jeanne@gmail.com wrote:
> Le samedi 9 février 2019 06:26:29 UTC+1, michael...@gmail.com a écrit :
> > On Friday, February 8, 2019 at 8:40:18 AM UTC-7, Henning Schild wrote:
> > > Am Thu, 7 Feb 2019 16:53:41 -0800
> > > schrieb :
> > >
> > > > On
Hi Jan,
Thank you for your detailed response! That was a great explanation. After
digesting that, things make a lot more sense. I’ll also try to implement your
suggestions regarding the preemption timer.
I do have a follow-up question:
I understand now that the preemption timer is only needed
Hello,
As part of my research, I’ve been looking to modify Jailhouse slightly to take
advantage of the preemption timer provided by VMX for Intel x86-64. I know
Jailhouse already uses it, but I was hoping to also use it to have the root
cell periodically “check up” on the inmate (the intended
Hey guys,
Thanks so much for the help.
0xef didn't work, so I just did 0x00 instead:
[ 0x3e0/8 ... 0x92f/8] = -1,
[ 0x930/8 ... 0x937/8] = 0x00, /* PNP0C09:00 - EC cmd */
[ 0x938/8 ... 0xcff/8] = -1,
and that solved the issue.
I ran into another invalid PIO 1-byte access for 0xb2 (when I
Hello,
I used the root config generator to create a root config for my x86-64 Dell
Inspiron running Kubuntu 18.04 (kernel 4.14). However, starting up the root
cell usually causes the entire laptop to freeze soon after.
I don’t have access to a serial console, but I am briefly able to see the
On Friday, March 22, 2019 at 6:02:02 AM UTC-6, J. Kiszka wrote:
> > +except OSError as e:
> > +print(' ERROR: %s' % e)
>
> Now we have the same error reported twice: once here, and once for the access
> that fails because we couldn't initialize self.mmap. I'll drop this one
hardware check: Catch errors opening /dev/mem during MMIO check
Catch error, print, and continue, instead of exiting test.
Signed-off-by: Michael Hinton
diff --git a/tools/jailhouse-hardware-check b/tools/jailhouse-hardware-check
index 51dea82d..517175c5 100755
---
Catch error, print, and continue, instead of exiting entire test.
Kernel config CONFIG_STRICT_DEVMEM is enabled by default on newer
kernels, causing these failures.
Here is what it looks like before applying the patch on my Kubuntu 18.04 system:
hintron@inspiron:~/code/jailhouse$ sudo
Catch error, print, and continue, instead of exiting test.
Signed-off-by: Michael Hinton
---
tools/jailhouse-hardware-check | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/tools/jailhouse-hardware-check b/tools/jailhouse-hardware-check
index 51dea82d..1c73011b 100755
On Monday, March 4, 2019 at 3:42:47 AM UTC-7, J. Kiszka wrote:
> On 03.03.19 08:42, michael.g.hin...@gmail.com wrote:
> > Thank you for the responses. I tried your suggestions, but I haven't got it
> > working yet.
> >
> > The issue is that I'm still getting errors trying to mmap /dev/uio0 at
>
Thank you for the responses. I tried your suggestions, but I haven't got it
working yet.
The issue is that I'm still getting errors trying to mmap /dev/uio0 at offset
0. No matter what I do (change page size, etc.), I keep getting a "No such
device" error. See
Hello,
I've got most everything working with ivshmem: the inmate is modifying shared
memory and sending interrupts to the root cell, the root cell is receiving the
interrupts and seeing the shared memory and PCI config space, and the root is
writing to shared memory, which the inmate sees.
Hello,
I have a few questions about the scope and future of Jailhouse:
Could Jailhouse be used to create lightweight VM "containers" on the fly, a la
Docker?
Is this use case on the radar, and if so, what would need to be done to make it
a reality?
How does Jailhouse compare to a solution
On Friday, February 8, 2019 at 8:40:18 AM UTC-7, Henning Schild wrote:
> Am Thu, 7 Feb 2019 16:53:41 -0800
> schrieb :
>
> > On Wednesday, February 6, 2019 at 5:59:09 AM UTC-7, Henning Schild
> > wrote:
> > > Am Tue, 5 Feb 2019 19:25:28 -0800
> > > schrieb :
> > >
> > > > On Friday, February
Hello,
So I've been debugging uio_ivshmem.c with print statements, and I think have a
theory for what's going wrong:
I believe the ivshem-net driver is being attached to the root cell's ivshmem
PCI device before the uio_ivshmem driver can, since I compiled the kernel with
On Wednesday, February 6, 2019 at 7:00:35 AM UTC-7, J. Kiszka wrote:
> On 06.02.19 13:59, Henning Schild wrote:
> > Am Tue, 5 Feb 2019 19:25:28 -0800
> > schrieb :
> >
> >> On Friday, February 1, 2019 at 12:32:40 AM UTC-7, J. Kiszka wrote:
> >>> You likely want
> >>>
On Friday, February 1, 2019 at 12:32:40 AM UTC-7, J. Kiszka wrote:
> You likely want
> https://github.com/siemens/linux/commits/jailhouse-enabling/4.14
> or the 4.19-variant that is jailhouse-prepared. That's what jailhouse-images
> is
> building for you.
> If you just rebuild the kernel that
Jan,
Thanks for the advice.
I went and downloaded Linux 4.14.73 and recompiled with CONFIG_UIO=y and
CONFIG_UIO_PCI_GENERIC=y (`make -j4`, `make modules_install`, and `make
install`). I was then able to build uio_ivshmem.ko.
However, now when I build Jailhouse, I hit the following errors:
On Tuesday, January 22, 2019 at 2:19:20 AM UTC-7, Henning Schild wrote:
> Am Mon, 21 Jan 2019 15:46:25 -0800
> schrieb :
>
> > So here's what happened: I increased the memory from 1 GB to 4 GB in
> > the QEMU command (from `-m 1G` to `-m 4G`). The Jailhouse-images's
> > qemu-x86.cell root cell
So here's what happened: I increased the memory from 1 GB to 4 GB in the QEMU
command (from `-m 1G` to `-m 4G`). The Jailhouse-images's qemu-x86.cell root
cell didn't like that.
So I guess if I want to increase the memory to 4 GB, I'll need to update
configs/x86/qemu-x86.c accordingly.
How
On Friday, January 18, 2019 at 5:26:50 AM UTC-7, Jan Kiszka wrote:
> Looks like your virtual machine configuration (that of QEMU) somehow changed -
> new QEMU version? Or did you touch the startup script?
>
> Jan
I did play around with the start-up script. It's also possible I somehow
changed
After waiting on a frozen QEMU, I did get this additional output:
qemu: vtd_iova_to_slpte: detected slpte permission error (iova=0x178e36110,
level=0x3, slpte=0x0, write=0)
qemu: vtd_iommu_translate: detected translation failure (dev=00:02:00, iova=0x0)
qemu: New fault is not recorded due to
On Wednesday, January 16, 2019 at 11:02:33 PM UTC-7, michael@gmail.com
wrote:
> I *did* recently manually resize the jailhouse QEMU image (see
> https://groups.google.com/forum/#!topic/jailhouse-dev/3IMPKkNUguQ). So that
> probably broke something. I'm pretty sure it was running before the
Hello,
I'm trying to run the jailhouse-images demo, I'm running into this error that
freezes the system when I do `jailhouse enable /etc/jailhouse/qemu-x86.cell`:
Initializing Jailhouse hypervisor v0.10 (0-gf596aa73) on CPU 0
Code location: 0xf050
Using x2APIC
Page pool
On Thursday, January 10, 2019 at 7:04:16 PM UTC-7, J. Kiszka wrote:
> I suppose you are referring to a QEMU image created by jailhouse-images,
> correct? Those images consist of a plain rootfs image, no partitioning
> involved
> there. So you can simply run "resizefs " after the "qemu-img
>
I'm pretty sure everything is AT/EVEREX header layout when I checked the first
time. I'll double check, though.
--
You received this message because you are subscribed to the Google Groups
"Jailhouse" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to
Hello,
I'm struggling to figure out how to read out the serial port output of
Jailhouse from my Kubuntu 18.04 Intel x86-64 box. Apparently, this is the only
way to read out Jailhouse console logs in a cell in real hardware. Does anyone
have any instructions for how to do this?
Here is what I
On Wednesday, September 26, 2018 at 1:00:29 AM UTC-6, J. Kiszka wrote:
> On 26.09.18 08:51, Jan Kiszka wrote:
> > On 26.09.18 07:55, michael.g.hin...@gmail.com wrote:
> >> I have two questions:
> >>
> >> 1) For Jailhouse images: is there any way I can rebuild Jailhouse one
> >> inside
> >> the
I have two questions:
1) For Jailhouse images: is there any way I can rebuild Jailhouse one inside
the x86 image? When I clone jailhouse inside the image and try to make it, the
necessary linux-header stuff isn't there, and there doesn't seem to be a
linux-header package for 4.14.50.
2) For
Jan,
I fixed the issue. It turns out that VT-d actually *was* disabled in the bios.
Once I enabled it in the bios, /sys/firmware/acpi/tables/DMAR appeared and the
config generation seemed to work!
Thanks for the assistance!
-Michael
Details:
My motherboard is a B360M Bazooka for an Intel
On Tuesday, August 28, 2018 at 12:31:59 AM UTC-6, J. Kiszka wrote:
> On 2018-08-27 22:39, michael.g.hin...@gmail.com wrote:
> > On Monday, August 20, 2018 at 11:36:47 PM UTC-6, J. Kiszka wrote:
> >> On 2018-08-21 02:53, michael.g.hin...@gmail.com wrote:
> >>> When I try to create a root config for
On Monday, August 20, 2018 at 11:36:47 PM UTC-6, J. Kiszka wrote:
> On 2018-08-21 02:53, michael.g.hin...@gmail.com wrote:
> > When I try to create a root config for my Ubuntu 18.04 Intel x86 machine, I
> > get the following error:
> >
> > hintron@bazooka:~/code/jailhouse$ sudo jailhouse config
When I try to create a root config for my Ubuntu 18.04 Intel x86 machine, I get
the following error:
hintron@bazooka:~/code/jailhouse$ sudo jailhouse config create bazooka.c
Traceback (most recent call last):
File "/usr/local/sbin/jailhouse-config-create", line 1185, in
dmar_regions)
On Tuesday, May 15, 2018 at 3:53:14 PM UTC-6, Jan Kiszka wrote:
> On 2018-05-11 16:52, michael.g.hin...@gmail.com wrote:
> >> Could you check in the guest Linux if the clocksources is tsc?
> >> cat /sys/devices/system/clocksource/clocksource0/current_clocksource
> >
> > It says hpet.
> Could you check in the guest Linux if the clocksources is tsc?
> cat /sys/devices/system/clocksource/clocksource0/current_clocksource
It says hpet. avaliable_clocksource shows hpet and acpi_pm.
> If not, please provide dmesg from inside the guest.
I've attached a screenshot of the dmesg
Is there a reason why my original response was deleted? I'm confused.
--
You received this message because you are subscribed to the Google Groups
"Jailhouse" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to jailhouse-dev+unsubscr...@googlegroups.com.
Hello,
I'm struggling to get a Jailhouse demo up and running in QEMU using
jailhouse-images.
In jailhouse-images/, I was able to build the QEMU images via the
`build-images.sh` script on an Ubuntu 17 machine, and I was able to start my
custom-built QEMU 2.11 by setting the path of the
45 matches
Mail list logo