[libvirt-users] pci-assign fails with read error on config-space file
Hey, i am running an unusual setup where i assign pci devices behind the back of libvirt. I have two options to do that: 1. a wrapper script for qemu that takes care of suid-root and appends arguments for pci-assign 2. virsh qemu-monitor-command ... 'device_add pci-assign...' I know i should probably not be doing this, it is a workaround to introduce fine-grained pci-assignment in an openstack setup, where vendor and device id are not enough to pick the right device for a vm. In both cases qemu will crash with the following output:
qemu: hardware error: pci read failed, ret = 0 errno = 22
followed by the usual machine state dump. With strace i found it to be a failing read on the config space file of my device. /sys/bus/pci/devices/0000:xx:xx.x/config A few reads out of that file succeeded, as well as accesses on vendor etc. Manually launching a qemu with the pci-assign works without a problem, so i "blame" libvirt and the cgroup environment the qemu ends up in. So i put a bash into the exact same cgroup setup - next to a running qemu, expecting a dd or hexdump on the config-space file to fail. But from that bash i can read the file without a problem. Has anyone seen that problem before? Right now i do not know what i am missing, maybe qemu is hitting some limits configured for the cgroups or whatever. I can not use pci-assign from libvirt, but if i did would it configure cgroups in a different way or relax some limits? What would be a good next step to debug that? Right now i am looking at kernel event traces, but the machine is pretty big and so is the trace. That assignment used to work and i do not know how it broke, i have tried combinations of several kernels, versions of libvirt and qemu. (kernel 3.18 and 4.4, libvirt 1.3.2 and 2.0.0, and qemu 2.2.1 and 2.7) All combinations show the same problem, even the ones that work on other machines. So when it comes to software versions the problem could well be caused by a software update of another component, that i got with the package manager and did not compile myself. It is a debian 8.6 with all recent updates installed. My guess would be that systemd could have an influence on cgroups or limits causing such a problem. regards, Henning
On 10/28/16 13:28, Henning Schild wrote:
Hey,
i am running an unusual setup where i assign pci devices behind the back of libvirt. I have two options to do that: 1. a wrapper script for qemu that takes care of suid-root and appends arguments for pci-assign 2. virsh qemu-monitor-command ... 'device_add pci-assign...'
I know i should probably not be doing this, it is a workaround to introduce fine-grained pci-assignment in an openstack setup, where vendor and device id are not enough to pick the right device for a vm.
(1) The libvirt domain XML identifies the host PCI device to assign by full PCI address (see the <source> element: <http://libvirt.org/formatdomain.html#elementsHostDev>); it does not filter with vendor/device ID. So, I believe your comment refers to the pci-stub host kernel driver not being flexible enough for binding vs. not binding different instances of the same vendor/device ID. If that's the case, would you be helped by the following host kernel patch? [PATCH] PCI: pci-stub: accept exceptions to the ID- and class-based matching <http://www.spinics.net/lists/linux-pci/msg55497.html> (2) Is there any reason (other than (1)) that you are using the legacy / deprecated pci-assign method, rather than VFIO? I suggest to evaluate whether the "pci-stub.except=..." kernel parameter helped your use case, and if (consequently) you could move to a fully libvirt + VFIO based config. Thanks Laszlo
In both cases qemu will crash with the following output:
qemu: hardware error: pci read failed, ret = 0 errno = 22
followed by the usual machine state dump. With strace i found it to be a failing read on the config space file of my device. /sys/bus/pci/devices/0000:xx:xx.x/config A few reads out of that file succeeded, as well as accesses on vendor etc.
Manually launching a qemu with the pci-assign works without a problem, so i "blame" libvirt and the cgroup environment the qemu ends up in. So i put a bash into the exact same cgroup setup - next to a running qemu, expecting a dd or hexdump on the config-space file to fail. But from that bash i can read the file without a problem.
Has anyone seen that problem before? Right now i do not know what i am missing, maybe qemu is hitting some limits configured for the cgroups or whatever. I can not use pci-assign from libvirt, but if i did would it configure cgroups in a different way or relax some limits?
What would be a good next step to debug that? Right now i am looking at kernel event traces, but the machine is pretty big and so is the trace.
That assignment used to work and i do not know how it broke, i have tried combinations of several kernels, versions of libvirt and qemu. (kernel 3.18 and 4.4, libvirt 1.3.2 and 2.0.0, and qemu 2.2.1 and 2.7) All combinations show the same problem, even the ones that work on other machines. So when it comes to software versions the problem could well be caused by a software update of another component, that i got with the package manager and did not compile myself. It is a debian 8.6 with all recent updates installed. My guess would be that systemd could have an influence on cgroups or limits causing such a problem.
regards, Henning
Am Fri, 28 Oct 2016 17:22:41 +0200 schrieb Laszlo Ersek <lersek@redhat.com>:
On 10/28/16 13:28, Henning Schild wrote:
Hey,
i am running an unusual setup where i assign pci devices behind the back of libvirt. I have two options to do that: 1. a wrapper script for qemu that takes care of suid-root and appends arguments for pci-assign 2. virsh qemu-monitor-command ... 'device_add pci-assign...'
I know i should probably not be doing this, it is a workaround to introduce fine-grained pci-assignment in an openstack setup, where vendor and device id are not enough to pick the right device for a vm.
(1) The libvirt domain XML identifies the host PCI device to assign by full PCI address (see the <source> element: <http://libvirt.org/formatdomain.html#elementsHostDev>); it does not filter with vendor/device ID.
So, I believe your comment refers to the pci-stub host kernel driver not being flexible enough for binding vs. not binding different instances of the same vendor/device ID.
My comment referred to OpenStack. The version we are using assigns PCI devices purely by device and vendor ID. The pci stub is no problem at all, you can always bind/unbind by address.
If that's the case, would you be helped by the following host kernel patch?
[PATCH] PCI: pci-stub: accept exceptions to the ID- and class-based matching
<http://www.spinics.net/lists/linux-pci/msg55497.html>
(2) Is there any reason (other than (1)) that you are using the legacy / deprecated pci-assign method, rather than VFIO?
I suggest to evaluate whether the "pci-stub.except=..." kernel parameter helped your use case, and if (consequently) you could move to a fully libvirt + VFIO based config.
I would like to do that in the long run and will look into the options. But for now i was hoping for a quick answer to make the hacky version work again. Thanks, Henning
Thanks Laszlo
In both cases qemu will crash with the following output:
qemu: hardware error: pci read failed, ret = 0 errno = 22
followed by the usual machine state dump. With strace i found it to be a failing read on the config space file of my device. /sys/bus/pci/devices/0000:xx:xx.x/config A few reads out of that file succeeded, as well as accesses on vendor etc.
Manually launching a qemu with the pci-assign works without a problem, so i "blame" libvirt and the cgroup environment the qemu ends up in. So i put a bash into the exact same cgroup setup - next to a running qemu, expecting a dd or hexdump on the config-space file to fail. But from that bash i can read the file without a problem.
Has anyone seen that problem before? Right now i do not know what i am missing, maybe qemu is hitting some limits configured for the cgroups or whatever. I can not use pci-assign from libvirt, but if i did would it configure cgroups in a different way or relax some limits?
What would be a good next step to debug that? Right now i am looking at kernel event traces, but the machine is pretty big and so is the trace.
That assignment used to work and i do not know how it broke, i have tried combinations of several kernels, versions of libvirt and qemu. (kernel 3.18 and 4.4, libvirt 1.3.2 and 2.0.0, and qemu 2.2.1 and 2.7) All combinations show the same problem, even the ones that work on other machines. So when it comes to software versions the problem could well be caused by a software update of another component, that i got with the package manager and did not compile myself. It is a debian 8.6 with all recent updates installed. My guess would be that systemd could have an influence on cgroups or limits causing such a problem.
regards, Henning
On 10/28/2016 07:28 AM, Henning Schild wrote:
Hey,
i am running an unusual setup where i assign pci devices behind the back of libvirt. I have two options to do that: 1. a wrapper script for qemu that takes care of suid-root and appends arguments for pci-assign 2. virsh qemu-monitor-command ... 'device_add pci-assign...'
With any reasonably modern version of Linux/qemu/libvirt, you should not be using pci-assign, but should use vfio-pci instead. pci-assign is old, unmaintained, and deprecated (and any other bad words you can think of). Also, have you done anything to lock the guest's memory in host RAM? This is necessary so that the source/destination of DMA reads/writes is always present. It is done automatically by libvirt as required *when libvirt knows that a device is being assigned to the guest*, but if you're going behind libvirt's back, you need to take care of that yourself (or alternately, don't go behind libvirt's back, which is the greatly preferred alternative!)
I know i should probably not be doing this,
Yes, that is a serious understatement :-) And I suspect that it isn't necessary.
it is a workaround to introduce fine-grained pci-assignment in an openstack setup, where vendor and device id are not enough to pick the right device for a vm.
libvirt selects the device according to its PCI address, not vendor and device id. Is that not "fine-grained" enough? (And does OpenStack not let you select devices based on their PCI address?)
In both cases qemu will crash with the following output:
qemu: hardware error: pci read failed, ret = 0 errno = 22 followed by the usual machine state dump. With strace i found it to be a failing read on the config space file of my device. /sys/bus/pci/devices/0000:xx:xx.x/config A few reads out of that file succeeded, as well as accesses on vendor etc.
Manually launching a qemu with the pci-assign works without a problem, so i "blame" libvirt and the cgroup environment the qemu ends up in. So i put a bash into the exact same cgroup setup - next to a running qemu, expecting a dd or hexdump on the config-space file to fail. But from that bash i can read the file without a problem.
Has anyone seen that problem before?
No, because nobody else (that I've ever heard) is doing what you are doing. You're going around behind the back of libvirt (and OpenStack) to do device assignment with a method that was replaced with something newer/better/etc about 3 years ago, and in the process are likely missing a lot of the details that would otherwise be automatically handled by libvirt.
Right now i do not know what i am missing, maybe qemu is hitting some limits configured for the cgroups or whatever. I can not use pci-assign from libvirt, but if i did would it configure cgroups in a different way or relax some limits?
What would be a good next step to debug that? Right now i am looking at kernel event traces, but the machine is pretty big and so is the trace.
My recommendation would be this: 1) look at OpenStack to see if it allows selecting the device to assign by PCI address. If so, use that (it will just tell libvirt "assign this device", and libvirt will automatically use VFIO for the device assignment if it's available (which it will be)) 2) if (1) is a deadend (i.e. OpenStack doesn't allow you to select based on PCI address), use your "sneaky backdoor method" to do "virsh attach-device somexmlfile.xml", where somexmlfile.xml has a proper <hostdev> element to select and assign the host device you want. Again, libvirt will automatically figure out if VFIO can be used, and will properly setup everything necessary related to cgroups, locked memory, etc.
That assignment used to work and i do not know how it broke, i have tried combinations of several kernels, versions of libvirt and qemu. (kernel 3.18 and 4.4, libvirt 1.3.2 and 2.0.0, and qemu 2.2.1 and 2.7) All combinations show the same problem, even the ones that work on other machines. So when it comes to software versions the problem could well be caused by a software update of another component, that i got with the package manager and did not compile myself. It is a debian 8.6 with all recent updates installed. My guess would be that systemd could have an influence on cgroups or limits causing such a problem.
That you would need to think of such things points out that your current setup is fragile and ultimately unmaintainable. Please consider "coloring inside the lines" :-) (We'd be happy to help if there are any hangups along the way, either on the libvirt-users mailing list or in the #virt channel on irc.oftc.net).
On Fri, 28 Oct 2016 11:25:55 -0400 Laine Stump <laine@redhat.com> wrote:
On 10/28/2016 07:28 AM, Henning Schild wrote:
Hey,
i am running an unusual setup where i assign pci devices behind the back of libvirt. I have two options to do that: 1. a wrapper script for qemu that takes care of suid-root and appends arguments for pci-assign 2. virsh qemu-monitor-command ... 'device_add pci-assign...'
With any reasonably modern version of Linux/qemu/libvirt, you should not be using pci-assign, but should use vfio-pci instead. pci-assign is old, unmaintained, and deprecated (and any other bad words you can think of).
Also, have you done anything to lock the guest's memory in host RAM? This is necessary so that the source/destination of DMA reads/writes is always present. It is done automatically by libvirt as required *when libvirt knows that a device is being assigned to the guest*, but if you're going behind libvirt's back, you need to take care of that yourself (or alternately, don't go behind libvirt's back, which is the greatly preferred alternative!)
Note that pci-assign doesn't care about user locked memory limits, so that much is not required for this deprecated use case, but I fully agree that going behind libvirt's back is completely unadvised and pci-assign is deprecated and likely broken. Maybe we should even consider removing it in the QEMU2.8 release cycle. Use vfio-pci and use the mechanisms provided in libvirt to attach the device to the VM, if these don't work, file bugs and improve the environment to meet your needs rather than working around it. I can't figure out from the original report what specifically about the environment prevents use of libvirt <hostdev> entries. Thanks, Alex
I know i should probably not be doing this,
Yes, that is a serious understatement :-) And I suspect that it isn't necessary.
it is a workaround to introduce fine-grained pci-assignment in an openstack setup, where vendor and device id are not enough to pick the right device for a vm.
libvirt selects the device according to its PCI address, not vendor and device id. Is that not "fine-grained" enough? (And does OpenStack not let you select devices based on their PCI address?)
In both cases qemu will crash with the following output:
qemu: hardware error: pci read failed, ret = 0 errno = 22 followed by the usual machine state dump. With strace i found it to be a failing read on the config space file of my device. /sys/bus/pci/devices/0000:xx:xx.x/config A few reads out of that file succeeded, as well as accesses on vendor etc.
Manually launching a qemu with the pci-assign works without a problem, so i "blame" libvirt and the cgroup environment the qemu ends up in. So i put a bash into the exact same cgroup setup - next to a running qemu, expecting a dd or hexdump on the config-space file to fail. But from that bash i can read the file without a problem.
Has anyone seen that problem before?
No, because nobody else (that I've ever heard) is doing what you are doing. You're going around behind the back of libvirt (and OpenStack) to do device assignment with a method that was replaced with something newer/better/etc about 3 years ago, and in the process are likely missing a lot of the details that would otherwise be automatically handled by libvirt.
Right now i do not know what i am missing, maybe qemu is hitting some limits configured for the cgroups or whatever. I can not use pci-assign from libvirt, but if i did would it configure cgroups in a different way or relax some limits?
What would be a good next step to debug that? Right now i am looking at kernel event traces, but the machine is pretty big and so is the trace.
My recommendation would be this:
1) look at OpenStack to see if it allows selecting the device to assign by PCI address. If so, use that (it will just tell libvirt "assign this device", and libvirt will automatically use VFIO for the device assignment if it's available (which it will be))
2) if (1) is a deadend (i.e. OpenStack doesn't allow you to select based on PCI address), use your "sneaky backdoor method" to do "virsh attach-device somexmlfile.xml", where somexmlfile.xml has a proper <hostdev> element to select and assign the host device you want. Again, libvirt will automatically figure out if VFIO can be used, and will properly setup everything necessary related to cgroups, locked memory, etc.
That assignment used to work and i do not know how it broke, i have tried combinations of several kernels, versions of libvirt and qemu. (kernel 3.18 and 4.4, libvirt 1.3.2 and 2.0.0, and qemu 2.2.1 and 2.7) All combinations show the same problem, even the ones that work on other machines. So when it comes to software versions the problem could well be caused by a software update of another component, that i got with the package manager and did not compile myself. It is a debian 8.6 with all recent updates installed. My guess would be that systemd could have an influence on cgroups or limits causing such a problem.
That you would need to think of such things points out that your current setup is fragile and ultimately unmaintainable. Please consider "coloring inside the lines" :-) (We'd be happy to help if there are any hangups along the way, either on the libvirt-users mailing list or in the #virt channel on irc.oftc.net).
Am Fri, 28 Oct 2016 11:25:55 -0400 schrieb Laine Stump <laine@redhat.com>:
On 10/28/2016 07:28 AM, Henning Schild wrote:
Hey,
i am running an unusual setup where i assign pci devices behind the back of libvirt. I have two options to do that: 1. a wrapper script for qemu that takes care of suid-root and appends arguments for pci-assign 2. virsh qemu-monitor-command ... 'device_add pci-assign...'
With any reasonably modern version of Linux/qemu/libvirt, you should not be using pci-assign, but should use vfio-pci instead. pci-assign is old, unmaintained, and deprecated (and any other bad words you can think of).
Also, have you done anything to lock the guest's memory in host RAM? This is necessary so that the source/destination of DMA reads/writes is always present. It is done automatically by libvirt as required *when libvirt knows that a device is being assigned to the guest*, but if you're going behind libvirt's back, you need to take care of that yourself (or alternately, don't go behind libvirt's back, which is the greatly preferred alternative!)
Memory locking is taken care of with "-realtime mlock=on".
I know i should probably not be doing this,
Yes, that is a serious understatement :-) And I suspect that it isn't necessary.
I know, but that was never the question ;).
it is a workaround to introduce fine-grained pci-assignment in an openstack setup, where vendor and device id are not enough to pick the right device for a vm.
libvirt selects the device according to its PCI address, not vendor and device id. Is that not "fine-grained" enough? (And does OpenStack not let you select devices based on their PCI address?)
The workaround is indeed for the version of OpenStack we are using. Recent versions might have support for more fine-grained assignment, but updating OpenStack is not something i would like to do right now. Another item on the TODO-list that i would like to keep seperate from the problem at hand.
In both cases qemu will crash with the following output:
qemu: hardware error: pci read failed, ret = 0 errno = 22 followed by the usual machine state dump. With strace i found it to be a failing read on the config space file of my device. /sys/bus/pci/devices/0000:xx:xx.x/config A few reads out of that file succeeded, as well as accesses on vendor etc.
Manually launching a qemu with the pci-assign works without a problem, so i "blame" libvirt and the cgroup environment the qemu ends up in. So i put a bash into the exact same cgroup setup - next to a running qemu, expecting a dd or hexdump on the config-space file to fail. But from that bash i can read the file without a problem.
Has anyone seen that problem before?
No, because nobody else (that I've ever heard) is doing what you are doing. You're going around behind the back of libvirt (and OpenStack) to do device assignment with a method that was replaced with something newer/better/etc about 3 years ago, and in the process are likely missing a lot of the details that would otherwise be automatically handled by libvirt.
Sure, and my question was aiming at what exactly i could be missing. That is just to fix a system that used to work and get a better understanding of "a lot of the details that would otherwise be automatically handled by libvirt".
Right now i do not know what i am missing, maybe qemu is hitting some limits configured for the cgroups or whatever. I can not use pci-assign from libvirt, but if i did would it configure cgroups in a different way or relax some limits?
What would be a good next step to debug that? Right now i am looking at kernel event traces, but the machine is pretty big and so is the trace.
My recommendation would be this:
1) look at OpenStack to see if it allows selecting the device to assign by PCI address. If so, use that (it will just tell libvirt "assign this device", and libvirt will automatically use VFIO for the device assignment if it's available (which it will be))
The version currently in use does not allow that.
2) if (1) is a deadend (i.e. OpenStack doesn't allow you to select based on PCI address), use your "sneaky backdoor method" to do "virsh attach-device somexmlfile.xml", where somexmlfile.xml has a proper <hostdev> element to select and assign the host device you want. Again, libvirt will automatically figure out if VFIO can be used, and will properly setup everything necessary related to cgroups, locked memory, etc.
Thanks! I will try the sneaky .xml method, in that case i will only have to play tricks on OpenStack and hopefully get all the libvirt details.
That assignment used to work and i do not know how it broke, i have tried combinations of several kernels, versions of libvirt and qemu. (kernel 3.18 and 4.4, libvirt 1.3.2 and 2.0.0, and qemu 2.2.1 and 2.7) All combinations show the same problem, even the ones that work on other machines. So when it comes to software versions the problem could well be caused by a software update of another component, that i got with the package manager and did not compile myself. It is a debian 8.6 with all recent updates installed. My guess would be that systemd could have an influence on cgroups or limits causing such a problem.
That you would need to think of such things points out that your current setup is fragile and ultimately unmaintainable. Please consider "coloring inside the lines" :-) (We'd be happy to help if there are any hangups along the way, either on the libvirt-users mailing list or in the #virt channel on irc.oftc.net).
It is a legacy reference/demo/proof-of-concept setup for realtime-enabled VMs, that somehow broke. PCI assignment was used for NICs when guests did not support virtio. https://archive.fosdem.org/2016/schedule/event/virt_iaas_real_time_cloud/ Since it is a hack and unmaintainable and does not scale, we do not use it anymore. But i was curious why it suddenly stopped working in that old demo setup. regards, Henning
On Fri, Oct 28, 2016 at 01:28:19PM +0200, Henning Schild wrote:
Hey,
i am running an unusual setup where i assign pci devices behind the back of libvirt. I have two options to do that: 1. a wrapper script for qemu that takes care of suid-root and appends arguments for pci-assign 2. virsh qemu-monitor-command ... 'device_add pci-assign...'
I know i should probably not be doing this, it is a workaround to introduce fine-grained pci-assignment in an openstack setup, where vendor and device id are not enough to pick the right device for a vm.
In both cases qemu will crash with the following output:
qemu: hardware error: pci read failed, ret = 0 errno = 22
followed by the usual machine state dump. With strace i found it to be a failing read on the config space file of my device. /sys/bus/pci/devices/0000:xx:xx.x/config A few reads out of that file succeeded, as well as accesses on vendor etc.
errno == 22, means EINVAL, so it feels unlikely to be a permissions problem unless the kernel or QEMU is reporting the wrong errno.
Manually launching a qemu with the pci-assign works without a problem, so i "blame" libvirt and the cgroup environment the qemu ends up in.
The 'config' file is a plain file, so not affected by cgroups - that only affects block devices. When libvirt runs QEMU, it runs unprivileged qemu:qemu user/group, so perhaps it is a permissions thing, despite the fact that you're getting EINVAL, not EACCESS. It would be interesting to know just what part of the config space QEMU was trying to read I guess, to better understand why it might be failing Regards, Daniel -- |: http://berrange.com -o- http://www.flickr.com/photos/dberrange/ :| |: http://libvirt.org -o- http://virt-manager.org :| |: http://entangle-photo.org -o- http://search.cpan.org/~danberr/ :|
Am Wed, 2 Nov 2016 09:54:16 +0000 schrieb "Daniel P. Berrange" <berrange@redhat.com>:
On Fri, Oct 28, 2016 at 01:28:19PM +0200, Henning Schild wrote:
Hey,
i am running an unusual setup where i assign pci devices behind the back of libvirt. I have two options to do that: 1. a wrapper script for qemu that takes care of suid-root and appends arguments for pci-assign 2. virsh qemu-monitor-command ... 'device_add pci-assign...'
I know i should probably not be doing this, it is a workaround to introduce fine-grained pci-assignment in an openstack setup, where vendor and device id are not enough to pick the right device for a vm.
In both cases qemu will crash with the following output:
qemu: hardware error: pci read failed, ret = 0 errno = 22
followed by the usual machine state dump. With strace i found it to be a failing read on the config space file of my device. /sys/bus/pci/devices/0000:xx:xx.x/config A few reads out of that file succeeded, as well as accesses on vendor etc.
errno == 22, means EINVAL, so it feels unlikely to be a permissions problem unless the kernel or QEMU is reporting the wrong errno.
Manually launching a qemu with the pci-assign works without a problem, so i "blame" libvirt and the cgroup environment the qemu ends up in.
The 'config' file is a plain file, so not affected by cgroups - that only affects block devices.
When libvirt runs QEMU, it runs unprivileged qemu:qemu user/group, so perhaps it is a permissions thing, despite the fact that you're getting EINVAL, not EACCESS.
If the wrapper qemu decides to assign a PCI device it will use a suid-root qemu to do so. So it is no EACCESS, as i said other reads worked fine.
It would be interesting to know just what part of the config space QEMU was trying to read I guess, to better understand why it might be failing
I should have said that before, it is a one byte read on offest 64. So just behind the regular cfg-space. regards, Henning
participants (5)
-
Alex Williamson -
Daniel P. Berrange -
Henning Schild -
Laine Stump -
Laszlo Ersek