Add two members in libxl_domain_remus_info:
netbuf: whether netbuf is enabled
netbufscript: the path of the script which will be run to setup
and tear down the guest's interface.
Add cmdline switches to 'xl remus' command to enable or disable
network buffering and a domain-specific hotplug script to setup
network buffering.
Add a new config var 'remus.default.netbufscript' to xl.conf, that
allows the user to override the default global script used to
setup network buffering.
Note: Network buffering is enabled by default. Disabling network
buffering requires enabling unsafe mode.
Signed-off-by: Shriram Rajagopalan <rshriram@cs.ubc.ca>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Reviewed-by: Wen Congyang <wency@cn.fujitsu.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
By default, network buffering and disk replication are enabled;
checkpoints are replicated to another standby VM.
This patch allows the user to disable any of these features by
explicitly specifying a 'run in unsafe mode' switch when invoking
the 'xl remus' command. While running Remus in an unsafe mode
makes little sense under normal circumstances, it is useful to be
able to disable one or more features mentioned above for
testing/debugging/profiling purposes.
Unless this option is enabled, it will not be possible to
replicate memory checkpoints to /dev/null (blackhole replication),
disable network buffering or disk replication.
As a starter, the use of blackhole replication now requires that
the unsafe mode be enabled. Subsequent patches will add support
for disabling network buffering and disk replication in a similar
manner.
Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com>
Signed-off-by: Shriram Rajagopalan <rshriram@cs.ubc.ca>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Signed-off-by: Ian Jackson <Ian.Jackson@eu.citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
This patch adds the machinery required for protecting a guest's
disk state, when the guest disk uses a DRBD disk backend.
This patch comprises of two parts:
1. Hotplug scripts: The block-drbd-probe script is responsible for
performing sanity checks on the state of the DRBD disk before the
checkpointing process begins. This script should be invoked by
libxl for each of the guest's disk devices, when starting Remus.
2. Remus drbd disk device: Implements the interfaces required by the
remus abstract device layer. A note about the implementation:
a) setup() is called for each disk attached to the guest.
During setup():
i) The hotplug script is called to perform the sanity check.
ii) Libxl obtains a handle to the DRBD device (/dev/drbd*) and
and subsequently controls disk checkpoint replication using
this handle in the checkpoint callbacks.
c) The preresume() checkpoint callback is executed asynchronously
using libxl__ev_child_fork(), as it may potentially block for more
than few seconds in case of backup failure.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com>
Signed-off-by: Ian Jackson <Ian.Jackson@eu.citrix.com>
Signed-off-by: Shriram Rajagopalan <rshriram@cs.ubc.ca>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
This patch adds the machinery required for protecting a guest's
network device state. This patch comprises of two parts:
1. Hotplug scripts: The remus-netbuf-setup script is responsible for
setting up and tearing down the necessary infrastructure required for
network output buffering. This script should be invoked by libxl for
each of the guest's network interfaces, when starting or stopping Remus.
Apart from returning success/failure indication via the usual hotplug
entries in xenstore, this script also writes to xenstore, the name of
the REMUS_IFB device to be used to control the vif's network output.
The script relies on libnl3 command line utilities to perform various
setup/teardown functions. The script is confined to Linux platforms only
since NetBSD does not seem to have libnl3.
2. Remus network device: Implements the interfaces required by the
remus abstract device layer. A note about the implementation:
a) init_subkind_nic() & cleanup_subkind_nic() are called once per Remus
invocation. They establish and free netlink related state respectively.
b) setup() and teardown are called for each vif attached to the
guest.
During setup():
i) The hotplug script is called to setup a network buffer on a
given vif. The script chooses an available IFB device from
the system, redirects vif egress traffic to the IFB device
and sets up the plug qdisc (output buffer) on the IFB device.
The name of the IFB device is communicated via xenstore to
libxl.
ii) Libxl obtains a handle to the plug qdisc using the libnl3 API
and subsequently controls output buffering using this handle
in the checkpoint callbacks.
During teardown(), the hotplug scripts are called again to remove
the vif->ifb traffic redirection, release the ifb and the plug
qdisc associated with it.
c) The checkpoint callbacks [postsuspend(), preresume() and commit()]
are implemented as synchronous ops as the netlink calls associated
with the qdisc subsystem are very fast.
Signed-off-by: Shriram Rajagopalan <rshriram@cs.ubc.ca>
Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com>
Signed-off-by: Ian Jackson <Ian.Jackson@eu.citrix.com>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Libnl3 is required for controlling Remus network buffering.
This patch adds dependency on libnl3 (>= 3.2.8) to autoconf scripts.
It also provides the ability to configure tools without libnl3 support
i.e., without network buffering support.
When there is no network buffering support, libxl__netbuffer_enabled()
returns 0, otherwise returns 1. The callers of this api will be
introduced in the rest of the series.
NOTE: This patch changes tools/configure.ac, please rerun
autogen.sh while applying the patch.
Signed-off-by: Shriram Rajagopalan <rshriram@cs.ubc.ca>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com>
Reviewed-by: Wen Congyang <wency@cn.fujitsu.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Analysis of XSAs 105 and 106 show that is possible to force a race condition
which causes any arbitrary instruction to be emulated.
To aid testing, explicitly introduce the Forced Emulation Prefix for debug
builds alone.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
This patch optionally re-instates support for the partition time reference
counter that was previously introduced by commit
e36cd2cdc9 and reverted by commit
1cd4fab14c. The previous implementation was
non-optional and flawed.
This implementation uses the tsc of vcpu0, which is preserved across
save/restore as part of the architectural state, and then converts that
to a 100ns tick using the domain's tsc_khz.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Keir Fraser <keir@xen.org>
Acked-by: Jan Beulich <jbeulich@suse.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Christoph Egger <chegger@amazon.de>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
The following commits introduced the time reference counter MSR and
TSC/APIC frequency MSRs into the viridian feature set respectively:
e36cd2cdc984657efd91
The time reference counter MSR feature was then reverted by commit
1cd4fab14c
because a flaw in the implementation meant the counter was reset on
migration.
All of these changes were made without any addtional options being
added to the VM configuration, or any compatibility checks being made
in the domain save/restore code. Hence setting the single boolean
'viridian' option in the VM configuration yields a different set of
features depending on which version of Xen the VM is started on, and the
feature set can change across migration (so new MSRs can magically appear).
This patch grandfathers in the current viridian features set and calls them
the 'base' and 'freq' feature sets. HVM_PARAM_VIRIDIAN is re-purposed as
a feature mask. The hypervisor has only ever allowed it ot be set to 0
or 1, so the presence of the base and freq sets are indicated by setting
bit 0. The freq set can then be turned off by setting bit 1, thus
restoring the pre-Xen-4.4 base set. Newly implemented viridian features
can be optionally enabled in future by setting further bits.
The viridian option in xl.cfg(5) has also been changed to a list so
that the sets can be individually enabled or disabled. For compatibility,
if the option is specified as a boolean, then a true (1) value will enable
the base and freq sets and a false (0) value will not enable any
enlightenments.
This patch also alters the allowed write accesses to HVM_PARAM_VIRIDIAN.
Currently there is nothing to stop the guest writing this value (which,
while harmless to anything else, should not happen) and nothing to
stop a toolstack from setting the value back to zero whilst the guest is
running, causing CPUID leaves to disappear and MSR accesses to start
causing GPFs in the guest. Both of these possibilities are now disallowed:
Once the parameter is set to a non-zero value it may not be modified (only
re-written with the same value), and guests no longer have any write
access.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Keir Fraser <keir@xen.org>
Acked-by: Jan Beulich <jbeulich@suse.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: David Scott <dave.scott@eu.citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
/var/run is a runtime directory. It is not supposed to be packaged.
Remove unused SUBSYS_DIR variable from Config.mk and distro_mapping.txt.
Signed-off-by: Olaf Hering <olaf@aepfle.de>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Before this change, xl stores domain configuration in "xl" format, which
is in fact a verbatim copy of user supplied domain config.
Now libxl provides a new API to retrieve domain configuration, switch to
that new API, store configuration in JSON format.
Tests done so far (xl.{new,old} denotes xl with{,out} "libxl-json"
support):
1. xl.new create then xl.new save, hexdump saved file: domain config
saved in JSON format
2. xl.new create, xl.new save then xl.old restore: failed on
mandatory flag check
3. xl.new create, xl.new save then xl.new restore: succeeded
4. xl.old create, xl.old save then xl.new restore: succeeded
5. xl.new create then local migrate, receiving end xl.new: succeeded
6. xl.old create then local migrate, receiving end xl.new: succeeded
Note that "xl" config is still supported and handled when restarting a
domain. "xl" config file takes precedence over "libxl-json" in that
case, so that user who uses "config-update" to store new config file
won't have regression. All other scenarios (migration, domain listing
etc.) now use the new API.
Lastly, print out warning when users invoke "config-update" to
discourage them from using this command.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Change NMI processing so that if watchdog=force is passed on the
command-line and the NMI is not caused by a perf counter overflow (i.e.
likely not a watchdog "tick"), the NMI is handled by the unknown NMI
handler.
This allows injection of NMIs from IPMI controllers that don't set the
IOCK/SERR bits to trigger the unknown NMI handler rather than be
ignored.
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Fix command line parsing (don't enable the watchdog on e.g.
"watchdog=xyz").
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Xen cannot safely use any ATS functionality until it gains asynchronous queued
invalidation support, because of the current synchronous wait for completion.
Do not turn ATS on by default.
While editing the default in the command line documentation, correct the
statement regarding PCI Passthrough. ATS is purely a performance
optimisation, and is certainly not required for PCI Passthrough to function.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Currently in xl.cfg, use 'root' and 'extra' to generate the command
line. 'cmdline' could be a more generic equivalent. So, add 'cmdline'
in xl.cfg and let it be preferred. 'root' and 'extra' still works.
But when 'cmdline' is specified, 'root' and 'extra' will be ignored.
[HVM config example]
[snip]
builder="hvm"
device_model_override="/home/cyliu/git/qemu/x86_64-softmmu/qemu-system-x86_64"
kernel="/mnt/vmlinuz-3.0.13-0.27-default"
ramdisk="/mnt/initrd-3.0.13-0.27-default"
root="/dev/hda2"
extra="console=tty0 console=ttyS0"
[snip]
or:
[snip]
builder="hvm"
device_model_override="/home/cyliu/git/qemu/x86_64-softmmu/qemu-system-x86_64"
kernel="/mnt/vmlinuz-3.0.13-0.27-default"
ramdisk="/mnt/initrd-3.0.13-0.27-default"
cmdline="root=/dev/hda2 console=tty0 console=ttyS0"
[snip]
Signed-off-by: Chunyan Liu <cyliu@suse.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
xen side patch to support xen HVM direct kernel boot:
support 'kernel', 'ramdisk', 'cmdline' (and 'root', 'extra' as well
which would be deprecated later) in HVM config file, parse config file,
pass -kernel, -initrd, -append parameters to qemu.
It's working with qemu-xen when using the default BIOS (seabios).
[HVM config example]
name="sles11_sp2"
description="None"
uuid="5c84adcc-bd59-788a-96d2-195f9b599cfe"
memory=512
maxmem=512
vcpus=4
on_poweroff="destroy"
on_reboot="restart"
on_crash="destroy"
localtime=0
keymap="en-us"
builder="hvm"
device_model_override="/home/cyliu/git/qemu/x86_64-softmmu/qemu-system-x86_64"
kernel="/mnt/vmlinuz-3.0.13-0.27-default"
ramdisk="/mnt/initrd-3.0.13-0.27-default"
root="/dev/hda2"
extra="console=tty0 console=ttyS0"
disk=[ 'file:/mnt/images/sles11_sp2/disk0.raw,hda,w', ]
vif=[ 'mac=00:16:3e:56:af:69,bridge=br0,type=netfront', ]
stdvga=0
vnc=1
vncunused=1
viridian=0
acpi=1
pae=1
serial="pty"
Signed-off-by: Chunyan Liu <cyliu@suse.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Allow the "serial" key to accept a list of serial ports, and pass
them in using the new serial_list domain build element.
For backwards compatibility, still accept singleton values.
Also update the xl.cfg manpage.
This patch borrows substantially from the multiple USB device patch
c3a2148192.
Signed-off-by: Ed White <edmund.h.white@intel.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Adding actual descriptions for them, hiding the hvm_debug= one from
non-debug builds (the option was recognized but didn't take any effect
so far), and adjusting some debug level specifiers to their purpose.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
HP is setting the ACPI_FADT_NO_CMOS_RTC flag on newer systems,
regardless of whether they're being booted from UEFI. Add a command
line option to allow probing for a working RTC in that case.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Otherwise an incremental build will fail to overwrite the destination
files.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
vCPU soft affinity and NUMA-aware scheduling does not have
to be related. However, soft affinity is how NUMA-aware
scheduling is actually implemented, and therefore, by default,
the results of automatic NUMA placement (at VM creation time)
are also used to set the soft affinity of all the vCPUs of
the domain.
Of course, this only happens if automatic NUMA placement is
enabled and actually takes place (for instance, if the user
does not specify any hard and soft affiniy in the xl config
file).
This also takes care of the vice-versa, i.e., don't trigger
automatic placement if the config file specifies either an
hard (the check for which was already there) or a soft (the
check for which is introduced by this commit) affinity.
Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Acked-by: George Dunlap <george.dunlap@eu.citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
To do so, we add the vcpu_soft_affinity array to build_info, and
treat it much like vcpu_hard_affinity. The new config option is
called "cpus_soft".
Note that the vcpu_hard_affinity array, introduced in a previous
patch, and the vcpu_soft_affinity array, introduced here, share
the same LIBXL_HAVE_xxx macro, in libxl.h. That is called
LIBXL_HAVE_BUILDINFO_VCPU_AFFINITY_ARRAYS, and was introduced
together with vcpu_hard_affinity, but only inside a comment.
In this change, we uncomment, and hence properly define it.
In order to avoid having to issue separate calls to
libxl_set_vcpuaffinity() (one for hard affinity and one for soft
affinity) in libxl__build_pre(), in case the caller uses
b_info->cpumap (for the former) and b_info->vcpu_soft_affinity (for
the latter), we also set (again!) a new default for b_info->cpumap.
This allows, from this change on, to always and only deal with
b_info->vcpu_hard_affinity all around libxl internals.
Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
and start using the vcpu_hard_affinity array instead. This is done
as when, in a subsequent patch ("libxl/xl: make it possible to
specify soft-affinity in domain config file") we will become able
to deal with soft affinity, code can be shared.
This change also enables more advanced VCPU to PCPU (hard, for now)
affinity specification, in case a list is used, like:
cpus = ["3-4", "2-6,^4"]
What it means is that VCPU 0 must be pinned to PCPU 3,4 and VCPU 1
to PCPUs 2,3,5,6 (before this change, cpus=[xx, yy] only supported
single values). Of course, the old (e.g., cpus=[2, 3]) syntax
continues to work.
Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Getting happens via `xl vcpu-list', which now looks like this:
# xl vcpu-list -s
Name ID VCPU CPU State Time(s) Affinity (Hard / Soft)
Domain-0 0 0 11 -b- 5.4 8-15 / all
Domain-0 0 1 11 -b- 1.0 8-15 / all
Domain-0 0 14 13 -b- 1.4 8-15 / all
Domain-0 0 15 8 -b- 1.6 8-15 / all
vm-test 3 0 4 -b- 2.5 0-12 / 0-7
vm-test 3 1 0 -b- 3.2 0-12 / 0-7
Setting happens by specifying two pCPU masks to the `xl vcpu-pin'
command, the first one will be hard affinity, the second soft
affinity. If only one mask is specified, it is only hard affinity
that is affected. To change only soft affinity, '-' can be used
as the hard affinity mask parameter, and it will be left alone.
xl manual page is updated accordingly.
Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
XEN_DOMCTL_gdbsx_domstatus is already safe. It loops at most over every vcpu
in a domain and breaks at the first vcpu with an event pending, marking it as
not-pending.
XEN_DOMCTL_gdbsx_pausevcpu had an incorrect bounds check against the vcpu id,
allowing an overflow of d->vcpu[] with an id between d->max_vcpus and
MAX_VIRT_CPUS. It was also able to overflow a vcpus pause count by many
repeated hypercalls.
The bounds check is fixed, and vcpu_pause() has been replaced with
vcpu_pause_by_systemcontroller() which cuts out at 255 uses.
XEN_DOMCTL_gdbsx_unpausevcpu suffered from the same bounds problems as its
pause counterpart, and is fixed in exactly the same way. Despite the
atomic_read(&v->pause_count), this code didn't successfully prevent against an
underflow of the vcpu pause count.
The vcpu_unpause() has been replaced with vcpu_pause_by_systemcontroller()
which correctly prevents against underflow. The printk() is updated to have a
proper guest logging level, and provide more useful information in the XSM
case of one domain having debugger privileges over another.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Tim Deegan <tim@xen.org>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
When using a multiboot capable bootloader this is exactly the field which
should be used.
Replace the deprecation wording with a reference to the information on the
priority of the bootargs fields.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Julien Grall <julien.grall@linaro.org>
If the "generation_id" option is set in the domain configuration,
generate and set a new random VM generation ID every time a domain is
created or restored.
xl lacks the infrastructure to fully track the lifecycle of VM images
as they are snapshotted and cloned (etc) so always using a new ID is
the safe option and ensures that a new one will be used where it matters.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Before this change, each vcpu had its own vcpu-affinity
(in v->cpu_affinity), representing the set of pcpus where
the vcpu is allowed to run. Since when NUMA-aware scheduling
was introduced the (credit1 only, for now) scheduler also
tries as much as it can to run all the vcpus of a domain
on one of the nodes that constitutes the domain's
node-affinity.
The idea here is making the mechanism more general by:
* allowing for this 'preference' for some pcpus/nodes to be
expressed on a per-vcpu basis, instead than for the domain
as a whole. That is to say, each vcpu should have its own
set of preferred pcpus/nodes, instead than it being the
very same for all the vcpus of the domain;
* generalizing the idea of 'preferred pcpus' to not only NUMA
awareness and support. That is to say, independently from
it being or not (mostly) useful on NUMA systems, it should
be possible to specify, for each vcpu, a set of pcpus where
it prefers to run (in addition, and possibly unrelated to,
the set of pcpus where it is allowed to run).
We will be calling this set of *preferred* pcpus the vcpu's
soft affinity, and this changes introduce it, and starts using it
for scheduling, replacing the indirect use of the domain's NUMA
node-affinity. This is more general, as soft affinity does not
have to be related to NUMA. Nevertheless, it allows to achieve the
same results of NUMA-aware scheduling, just by making soft affinity
equal to the domain's node affinity, for all the vCPUs (e.g.,
from the toolstack).
This also means renaming most of the NUMA-aware scheduling related
functions, in credit1, to something more generic, hinting toward
the concept of soft affinity rather than directly to NUMA awareness.
As a side effects, this simplifies the code quit a bit. In fact,
prior to this change, we needed to cache the translation of
d->node_affinity (which is a nodemask_t) to a cpumask_t, since that
is what scheduling decisions require (we used to keep it in
node_affinity_cpumask). This, and all the complicated logic
required to keep it updated, is not necessary any longer.
The high level description of NUMA placement and scheduling in
docs/misc/xl-numa-placement.markdown is being updated too, to match
the new architecture.
Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Reviewed-by: George Dunlap <george.dunlap@eu.citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
The page scrubbing is done in 128MB chunks in lockstep across all the
non-SMT CPU's. This allows for the boot CPU to hold the heap_lock whilst each
chunk is being scrubbed and then release the heap_lock when the CPU's are
finished scrubing their individual chunk. This allows for the heap_lock to
not be held continously and for pending softirqs are to be serviced
periodically across the CPU's.
The page scrub memory chunks are allocated to the CPU's in a NUMA aware
fashion to reduce socket interconnect overhead and improve performance.
Specifically in the first phase we scrub at the same time on all the
NUMA nodes that have CPUs - we also weed out the SMT threads so that
we only use cores (that gives a 50% boost). The second phase is for NUMA
nodes that have no CPUs - for that we use the closest NUMA node's CPUs
(non-SMT again) to do the job.
This patch reduces the boot page scrub time on a 128GB 64 core AMD Opteron
6386 machine from 49 seconds to 3 seconds.
On a IvyBridge-EX 8 socket box with 1.5TB it cuts it down from 15 minutes
to 63 seconds.
Signed-off-by: Malcolm Crossley <malcolm.crossley@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Tim Deegan <tim@xen.org>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Print out a warning and suggest user use "-V" option when invoking "xl
create". Also remove that option in manpage. This will introduce a
minor functional regression but it's very easy to work around.
The rationale behind this change is that, this option is actually not
part of domain configuration. It just affects whether a vncviewer
should be automatically spawn, but has nothing to do with how a domain
should be constructed. And this option is also bogus, considering if you
migrate a domain to a remote host and the receiver spawns a vncviewer on
the receiving side then it either dies silently or occupies resource.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
cpufreq parameter can take more options than currently
documented. Include these with some comments regarding
their intention.
Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Finally last patch in the series to enable creation of pvh dom0.
A pvh dom0 is created by adding dom0pvh to grub xen command line.
Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Handle new boolean option discard/no-discard for disk configuration. It
is supposed to disable discard support if file based backing storage was
intentionally created non-sparse to avoid fragmentation of the file.
The option intended for the backend driver. A new boolean property
"discard-enable" is written to the backend node. An upcoming patch for
qemu will make use of this property. The kernel blkback driver may be
updated as well to disable discard for phy based backing storage.
Signed-off-by: Olaf Hering <olaf@aepfle.de>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Supervisor Mode Access Prevention (SMAP) is a new security
feature disclosed by Intel, please refer to the following
document:
http://software.intel.com/sites/default/files/319433-014.pdf
If CR4.SMAP = 1, supervisor-mode data accesses are not allowed
to linear addresses that are accessible in user mode. If CPL < 3,
SMAP protections are disabled if EFLAGS.AC = 1. If CPL = 3, SMAP
applies to all supervisor-mode data accesses (these are implicit
supervisor accesses) regardless of the value of EFLAGS.AC.
This patch enables SMAP in Xen to prevent Xen hypervisor from
accessing pv guest data, whose translation paging-structure
entries' U/S flags are all set.
Signed-off-by: Feng Wu <feng.wu@intel.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
With proper permission (and, for the I/O port case, wrap-around) checks
added (note that for the I/O port case a count of zero is now being
disallowed, in line with I/O memory handling):
XEN_DOMCTL_irq_permission:
XEN_DOMCTL_ioport_permission:
Of both IRQs and I/O ports there is only a reasonably small amount, so
there's no excess resource consumption involved here. Additionally
they both have a specialized XSM hook associated.
XEN_DOMCTL_iomem_permission:
While this also has a specialized XSM hook associated (just like
XEN_DOMCTL_{irq,ioport}_permission), it's not clear whether it's
reasonable to expect XSM to restrict the number of ranges associated
with a domain via this hook (which is the main resource consumption
item here).
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Tim Deegan <tim@xen.org>
Document and implement a new option that permits disk backends which
would otherwise have to avoid O_DIRECT (because of the network memory
lifetime bug) to use it anyway. This is:
direct-io-safe in the xl domain disk config specification
direct_io_safe in the libxl disk API
direct-io-safe in the backend xenstore interface
Add a reference to xen/include/public/io/blkif.h in
docs/misc/vbd-interface.txt.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Ian Jackson <ian.jackson@eu.citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Tested-by: Felipe Franciosi <felipe@paradoxo.org>
In a number of cases, loops over each vCPU in a domain are involved
here. For large numbers of vCPU-s these may still take some time to
complete, but we're limiting them at a couple of thousand at most, so I
would think this should not by itself be an issue. I wonder though
whether it shouldn't be possible to have XSM restrict the vCPU count
that can be set through XEN_DOMCTL_max_vcpus.
XEN_DOMCTL_pausedomain:
A loop over vcpu_sleep_sync() for each of vCPU in the domain. That
function itself has a loop waiting for the subject vCPU to become non-
runnable, which ought to complete quickly (involving an IPI to be sent
and acted on). No other unbounded resource usage.
XEN_DOMCTL_unpausedomain:
Simply a loop calling vcpu_wake() (not having any loops or other
resource usage itself) for each of vCPU in the domain.
XEN_DOMCTL_getdomaininfo:
Two loops (one over all domains, i.e. bounded by the limit of 32k
domains, and another over all vCPU-s in the domain); no other
unbounded resource usage.
XEN_DOMCTL_getpageframeinfo:
Inquiring just a single MFN, i.e. no loops and no other unbounded
resource usage.
XEN_DOMCTL_getpageframeinfo{2,3}:
Number of inquired MFNs is limited to 1024. Beyond that just like
XEN_DOMCTL_getpageframeinfo.
XEN_DOMCTL_getvcpuinfo:
Only obtaining information on the vCPU, no loops or other resource
usage.
XEN_DOMCTL_setdomainhandle:
Simply a memcpy() of a very limited amount of data.
XEN_DOMCTL_setdebugging:
A domain_{,un}pause() pair (see XEN_DOMCTL_{,un}pausedomain) framing
the setting of a flag.
XEN_DOMCTL_hypercall_init:
Initializing a guest provided page with hypercall stubs. No other
resource consumption.
XEN_DOMCTL_arch_setup:
IA64 leftover, interface structure being removed from the public
header.
XEN_DOMCTL_settimeoffset:
Setting a couple of guest state fields. No other resource consumption.
XEN_DOMCTL_getvcpuaffinity:
XEN_DOMCTL_getnodeaffinity:
Involve temporary memory allocations (approximately) bounded by the
number of CPUs in the system / number of nodes built for, which is
okay. Beyond that trivial operation.
XEN_DOMCTL_real_mode_area:
PPC leftover, interface structure being removed from the public
header.
XEN_DOMCTL_resumedomain:
A domain_{,un}pause() pair framing operation very similar to
XEN_DOMCTL_unpausedomain (see above).
XEN_DOMCTL_sendtrigger:
Injects an interrupt (SCI or NMI) without any other resource
consumption.
XEN_DOMCTL_subscribe:
Updates the suspend event channel, i.e. affecting only the controlled
domain.
XEN_DOMCTL_disable_migrate:
XEN_DOMCTL_suppress_spurious_page_faults:
Just setting respective flags on the domain.
XEN_DOMCTL_get_address_size:
Simply reading the guest property.
XEN_DOMCTL_set_opt_feature:
Was already tagged IA64-only.
XEN_DOMCTL_set_cpuid:
MAX_CPUID_INPUT bounded loop, which is okay. No other resource
consumption.
XEN_DOMCTL_get_machine_address_size:
Simply obtaining the value set by XEN_DOMCTL_set_machine_address_size
(or the default set at domain creation time).
XEN_DOMCTL_gettscinfo:
XEN_DOMCTL_settscinfo:
Reading/writing of a couple of guest state fields wrapped in a
domain_{,un}pause() pair.
XEN_DOMCTL_audit_p2m:
Enabled only in debug builds.
XEN_DOMCTL_set_max_evtchn:
While the limit set here implies other (subsequent) resource usage,
this is the purpose of the operation.
I also verified that all removed domctls' handlers don't leak
hypervisor memory contents .
Inspected but questionable (and hence left in place for now):
XEN_DOMCTL_max_mem:
While only setting the field capping a domain's allocation (this
implies potential successive resource usage, but that's the purpose of
the operation). However, XSM doesn't see the value that's being set
here, so the net effect would be potential unbounded memory use.
XEN_DOMCTL_set_virq_handler:
This modifies a global array. While that is the purpose of the
operation, if multiple domains are granted permission they can badly
interfere with one another. Hence I'd appreciate a second opinion
here. [Andrew confirms that this being the nature of the operation,
it's fine to be removed from the list - will be done in a 2nd round.]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Tim Deegan <tim@xen.org>
Add support for changing max number of hypervisor leaves from configuration
file.
This number can be specified using xl's standard 'cpuid' option. Only lowest
8 bits of leaf's 0x4000xx00 eax register are processed, all others are ignored.
The changes allow us to revert commit 80ecb40362
which is most likely no longer needed now anyway (Solaris bug that it addressed
has been fixed and backported to earlier releases) but leave possibility of
running unpatched version of Solaris by forcing number of leaves to 2 in the
configuration file.
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Yang Hongyang
Andrew Cooper
Roger Pau Monne
Paul Durrant
Meng Xu
Olaf Hering
Wei Liu
Arianna Avanzini
Ross Lagerwall
Chunyan Liu
White, Edmund H
Jan Beulich
Dario Faggioli
Ian Campbell
David Vrabel
Malcolm Crossley
Aravind Gopalakrishnan
Mukesh Rathor
Zhigang Wang
Feng Wu
Stefano Stabellini
Boris Ostrovsky