xenbus_read() and xenbus_write() will allocate memory for error
message if any error occurs, this memory should be freed.
Signed-off-by: Yu Zhiguo <yuzg@cn.fujitsu.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
If we want to avoid that a C++ compiler becomes a requirement for a
Xen build, we should disable the (unneeded) C++ library generation for
the embedded libconfig.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
the "guest to a single NUMA node" constrain algorithm does not work
well when we do ballooning. Ballooning and NUMA don't play together
anyway, as Dom0 and thus ballooning is not NUMA aware, I am working on
this but it will not be ready for the Xen 4.0 release window. The
usual ballooning situation will result in an empty candidate list, as
no node has enough free memory to host the guest. In this case the
code will simply pick the first node: again and again, because all
nodes without enough memory will be ultimately penalized with the same
maxint value (regardless of the actual load). The attached patch will
change this to use a relative penalty in case of not-enough memory, so
that low-load low-memory nodes will be used at one point. A half
loaded node has shown to be a good value, as an unbalanced system is
much worse than non-local memory access for guests. Regardless of
that you should restrict the Dom0 on a NUMA system to a reasonable
memory size, so that ballooning is not necessary most of the time. In
this case the guest's memory will be NUMA local.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
The basic work flow to handle the memory hotadd is:
Update node information
Map new pages to xen 1:1 mapping
Setup frametable for new memory range
Setup m2p table for new memory range
Put the new pages to domheap
Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
memory hotplug is supported.
Hot-added memory may need a new L4 entry for 1:1 mapping. This patch
setup all L4 entry for 1:1 mapping if memory hotadd is needed, so that
we don't need sync the guest page table in page fault handler.
Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
hotplug in page fault handler.
In compact guest situation, the compat m2p table is copied, not
directly mapped in L3, so we have to sync it. Direct mapping range
may changes, and we need sync it with guest's table.
Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
We can't use alloc_boot_pages for memory hot-add, so change it to use
the pages range passed in.
One changes need notice is, when memory hotplug needed, we have to
setup initial frametable as pdx index (i.e. the pdx_gorund_valid)
aligned, to make sure mfn_valid() still works after the max_page is
not maximum anymore.
Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
The m2p tables should be shared by guest as they will be read-only
mapped by guest. This logical is similar to what happens in
subarch_init_memory(). But we need check the mapping is just setup.
Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
As when we destroy the m2p table, it should not be used, so we don't
need consider clean the head/tail mapping that may exits before hot-add.
Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
When new memory added to the system, we need to update the m2p table
to cover the new memory range.
When memory add, it is difficult to allocate continous pages, so we
allocate the memory from the new added memory range. This also improve
the locality in numa situation.
We don't support 1G mapping for hot memory, because AFAIK currently
hot-plug memory will not be that large.
Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
You can see the following slides to understand the usage.
http://www.xen.org/files/xensummit_intel09/PVUSBStatusUpdate.pdf
Limitations:
"xm usb-hc-create" accepts up to 16 ports, but, current usbfront
can work with up to 15 ports. This may be bug and I'm preparing
to fix it.
This xm/xend support requires linux-2.6.18-xen.hg c/s 939 or above.
I recommend latest tip.
Signed-off-by: Noboru Iwamatsu <n_iwamatsu@jp.fujitsu.com>
This patch adds a command line option in xl to exit right after domain
creation and not wait in background for the death of the domain.
Users should be aware that if they use this option, they always have
to destroy the domain manually after the guest shuts down.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
- LIBXL_MAXMEM_CONSTANT is 1MB but must be expressed in KB;
- xc_dom_linux_build should take target_memkb instead of max_memkb as
an argument.
Thanks to Andres for spotting the latter.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
This defines how multiple modules can be passed to a domain by packing
them together into a "multiboot module" in a way very similar to the
multiboot standard. An SIF_ flag is added to announce such package.
This also adds a packing implementation to PV-GRUB.
Signed-Off-By: Samuel Thibault <samuel.thibault@ens-lyon.org>
BUG_ON(d->is_dying) in p2m_pod_cache_add() which is introduced in
c/s 20426 is not proper. Since dom->is_dying is set asynchronously.
For example, MMU_UPDATE hypercalls from qemu and the
DOMCTL_destroydomain hypercall from xend can be issued simultaneously.
Also this patch lets p2m_pod_empty_cache() wait by spin_barrier
until another PoD operation ceases.
Signed-off-by: Kouya Shimura <kouya@jp.fujitsu.com>
Acked-by: George Dunlap <george.dunlap@eu.citrix.com>
The 'continue' in the if() part of the conditional at the end of
p2m_pod_zero_check() was causing this, but there also really is no
point in retaining the mapping after having checked page contents,
so fix it both ways. Additionally there is no point in updating
map[] at this point anymore.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Doesn't work when build-time python path differs from install-time. Do
we care about this given tools should be packaged/built for the
specific run-time distro?
Signed-off-by: Christoph Egger <Christoph.Egger@amd.com>
When a single domain is using most/all of tmem memory
for ephemeral pages belonging to the same object, e.g.
when copying a single huge file larger than ephemeral
memory, long lists are traversed looking for a page to
evict that doesn't belong to this object (as pages in
the object for which a page is currently being inserted
are locked and cannot be evicted). This is essentially
a livelock.
Avoid this by proactively ensuring there is a margin
of available memory (1MB) before locks are taken on
the object.
Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
This patch adds a target_memkb parameter to libxl_domain_build_info to
set the target memory for the VM at build time and a new function
called libxl_set_memory_target to dynamically modify the memory target
of a VM at run time. Finally a new command "mem-set" is added to xl
that calls directly libxl_set_memory_target.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Make the data path on xenstore writable by the guest
because Citrix pv drivers requires it.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Currently xen hypervisor use nodes to keep start/end address of
node. It assume memory among nodes has no overlap, this is not always
true, especially if we have memory hotplug support in the system.
This patch backport Linux kernel's memblks to support overlapping
among node. The memblks will be used both for checking conflict, and
caculate memnode_shift.
Also, currently if there is no memory populated in a node when system
booting, the node will be unparsed later, and the corresponding CPU's
numa information will be removed also. This patch will keep the CPU
information.
One thing need notice is, currently we caculate memnode_shift with all
memory, including un-populated ones. This should work if the smallest
chuck is not so small. Other option can be flags in the page_info
structure, etc.
The memnodemap is changed from paddr to pdx, both to save space, and
also because currently most access is from pfn.
A flag is mem_hotplug added if there is hotplug memory range.
Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
Trying to fix a livelock condition in tmem that occurs
only when the system is totally out of memory requires
the ability to easily determine if all zones in all
nodes are empty, and this must be checked at a fairly
high frequency. So to avoid walking all the zones in
all the nodes each time, I'd like a fast way to determine
if "free_pages" is zero. This patch tracks the sum
of the free pages in all nodes/zones. Since I think
the value is modified only when heap_lock is held,
it need not be atomic.
I don't know this for sure, but suspect this will be
useful in other future memory utilization code, e.g.
page sharing.
This has had limited testing, though I did drive free
memory down to zero and up and down a few times with
debug on and no asserts were triggered.
Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
Currently, xen uses shared iommu domain-id across all the VT-d units
in the platform. The number of iommu domain-ids (NR_DID, e.g. 256)
supported by each VT-d unit is reported in Capability register. The
limitation of current implementation is it only can support at most
NR_DID domains with VT-d in the entire platform, even though the
platform can support N * NR_DID (where N is the number of VT-d
units). Imagine a platform with several SR_IOV NICs, and each NIC
supports 128 VFs. It possibly beyond the NR_DID.
This patch implements iommu domain-id management per iommu (VT-d
unit), hence solves above limitation. It removes the global domain-id
bitmap, instead use domain-id bitmap in struct iommu, and also involve
an array to map guest domain-id and iommu domain-id, which is used to
iommu domain-id when flush context cache or IOTLB. When a device is
assigned to a guest, choose an available iommu domain-id from the
device's iommu, and map guest domain id to the domain-id mapping
array. When a device is deassigned from a guest, clear the domain-id
bit in domain-id bitmap and clear the corresponding entry in domain-id
map array if there is no other devices under the same iommu owned by
the guest.
Signed-off-by: Weidong Han <weidong.han@intel.com>
I submitted a patch a while back to add keymap to vfb config for hvm
guests. This patch works fine for new config (xm create|new) but not
existing, managed guests. To cover the latter case I've introduced a
validator method in XendConfig.
Signed-off-by: Jim Fehlig <jfehlig@novell.com>
Initial tsc_mode patch contained a rough cut at pvrdtscp mode. This
patch gets it working correctly. For the record, pvrdtscp mode allows
an application to obtain information from Xen to descale/de-offset
a physical tsc value to obtain "nsec since VM start". Though the
raw tsc value may change across migration due to different Hz rates
and different start times of different physical machines, applying
the pvrdtscp algorithm to a raw tsc value guarantees that the result
will always be both a fixed known rate (nanoseconds) and monotonically
increasing. BUT, pvrdtscp will only be fast on physical machines that
support the rdtscp instruction AND on which tsc is "safe"; on other
machines both the rdtsc and rdtscp instructions will be emulated.
Also note that when tsc_mode=3 is enabled, tsc-sensitive applications
that do NOT implement the pvrdtscp algorithm will behave incorrectly.
So, tsc_mode=3 should only be used when all apps are either
tsc-resilient
or pvrdtscp-modified, and only has a performance advantage on very
recent generation processors.
Signed-off-by: Dan Magenheiemer <dan.magenheimer@oracle.com>
This patch implements functions in libxenlight to change the cdrom in
a VM at run time and to handle cdrom eject requests from guests.
This patch adds two new commands to xl: cd-insert and cd-eject; it
also modifies xl to handle cdrom eject requests coming from guests
(actually coming from qemu).
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
This patch implements a backend cleanup function in fs-backend so that
when the connection to the frontend is closed we don't leak nodes on
xenstore.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
This patch adds minimal support for fs-backend and minios' fs-front
to libxenlight:
- it creates a vfs directory on the stubdom's xenstore
device path and allows the stubdom to write to it;
- it doesn't try to cleany shutdown the vfs backend.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Contemplate a memory space slack for PV domains,
since they do ballooning (or flipping network rx)
and need some extra room in their pfn space.
Note that this does not allocate any extra memory
to the domain, it simply extends the physmap with
some extra room for "bounce bufffering back" pfn's
that are yielded to dom0.
The default slack is set at 8MB.
Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.com>
Acked-by: Vincent Hanquez <vincent.hanquez@eu.citrix.com>
Added libxenlight implementation for resume domain.
This brings back a cooperative pv domain from the
shutdown state after save, enabling checkpointing.
Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.com>
Prevent segmentation fault caused by empty values
in key-value pairs for the /vm/ subdirectory
when restoring a pv domain.
Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.com>
Expose disk and nic device destroy calls
Also removes the obsolete device shutdown calls.
Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.com>
Refactor libxl device destroy code. Abstract function
waiting for the watch on the state node to fire.
Create a generic device delete function.
Only a single LIBXL_DESTROY_TIMEOUT elapses when
waiting for destruction of all the devices of a
domain.
Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.com>
Provide a function to clone a context. This is necessary
because simply copying the structs will eventually
corrup the GC: maxsize is updated in the cloned context
but not in the originating, yet they have the same array
of referenced pointers alloc_ptrs.
Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.com>
Keir Fraser