The current logic for handling the non-root VMREAD/VMWRITE is by
VM-Exit and emulate, which may bring certain overhead.
On new Intel platform, it introduces a new feature called VMCS
shadowing, where non-root VMREAD/VMWRITE will not trigger VM-Exit,
and the hardware will read/write the virtual VMCS instead.
This is proved to have performance improvement with the feature.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Acked-by: Jun Nakajima <jun.nakajima@intel.com>
Acked-by Eddie Dong <eddie.dong@intel.com>
Committed-by: Jan Beulich <jbeulich@suse.com>
After we use the VMREAD/VMWRITE to build up the virtual VMCS, each
access to the virtual VMCS needs two VMPTRLD and one VMCLEAR to
switch the environment, which might be an overhead to performance.
This commit tries to handle multiple virtual VMCS access together
to improve the performance.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Acked-by Eddie Dong <eddie.dong@intel.com>
Committed-by: Jan Beulich <jbeulich@suse.com>
Before the VMCS shadowing feature, we use memory operation to build up
the virtual VMCS. This does work since this virtual VMCS will never be
loaded into real hardware. However after we introduce the VMCS
shadowing feature, this VMCS will be loaded into hardware, which
requires all fields in the VMCS accessed by VMREAD/VMWRITE.
Besides, the virtual VMCS revision identifer should also meet the
hardware's requirement, instead of using a faked one.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Acked-by Eddie Dong <eddie.dong@intel.com>
Committed-by: Jan Beulich <jbeulich@suse.com>
Originally we use a virtual VMCS field to store the launch state of
a certain vmcs. However if we introduce VMCS shadowing feature, this
virtual VMCS should also be able to load into real hardware,
and VMREAD/VMWRITE operate invalid fields.
The new approach is to store the launch state into a list for L1 VMM.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Acked-by Eddie Dong <eddie.dong@intel.com>
Committed-by: Jan Beulich <jbeulich@suse.com>
It is sometimes hard to discover all the optional tools that should be
on a system to build all available Xen documentation. By checking for
documentation generation tools at ./configure time and displaying a
warning, Xen packagers will more easily learn about new optional build
dependencies, like markdown, when they are introduced.
Based on a patch by Matt Wilson. Changed to use a separate
docs/configure which is called from the top-level in the same manner
as stubdoms.
Rerun autogen.sh and "git add docs/configure" after applying this patch.
Signed-off-by: Matt Wilson <msw@amazon.com>
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Matt Wilson <msw@amazon.com>
(For the change to introduce docs/configure)
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
In the 300+ page PDF this produces I couldn't see anything which
wasn't the autogenerated doxygen boilerplate stuff.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
This document is about an old unmaintained version of the XenAPI,
which bears little to no relation to what is implemented in xapi and
which is only partially implemented in xend (which is deprecated). The
doc hasn't seen much in the way of updates since 2009.
Anyone who is actually interested can continue to use the version
which was in 4.2.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
This removes the need for the "case 0: case 2:" boilerplate in every
main_foo(). Calls exit(3) directly which is OK since xl cleans up the
context etc in an atexit(3) handler.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
Improves consistency of option parsing and error handling.
Consistently support --help for all options.
Many users of getopt_long were needlessly passing an option_index
pointer which was not used.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
Prevent the compiler from re-ordering the reads and writes.
Suggested by Jan Beulich.
Signed-off-by: Razvan Cojocaru <rzvncj@gmail.com>
Acked-by: Tim Deegan <tim@xen.org>
Acked-by: Keir Fraser <keir@xen.org>
Committed-by: Jan Beulich <jbeulich@suse.com>
Additionally drop unused (and dangerous) defines and typedefs, plus
a minor legibility improvement to setup_pgtables_x86_{32_pae,64}().
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
Acked-by: Ian Campbell <Ian.Campbell@citrix.com>
In do_mmu_update() (in the hypervisor) the parameter 'foreigndom' is
'unsigned int' and both its high (bits 31-16) and low (bits 15-0) are
parts utilised, as explained here:
http://xenbits.xen.org/docs/unstable/hypercall/include,public,xen.h.html#Func_HYPERVISOR_mmu_update
However, the actual parameter, i.e., the 'subject' field in
struct xc_mmu is declared as domid_t, which typedef-s to uint16_t.
This means we are never able to pass anything via the higher 16 bits
of 'foreigndom', which in turns may cause the hypercall to fail when
called on an actual foreign domain.
Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
XENMAPSPACE_gmfn_foreign is not supported by XENMEM_add_to_physmap.
Although in theory XENMEM_add_to_physmap_range could support
XENMAPSPACE_gmfn_range this is no different to
XENMAPSPACE_gmfn in the context of the ranged hypercall so disallow it
to avoid any confusion.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Keir Fraser <keir@xen.org>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
The gva_to_{par,ipa} functions currently panic if the guest address
cannot be translated. Often the input comes from the guest so
panicing the host is a bit harsh!
Change the API of those functions to allow them to return a failure
and plumb it through where it is used.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
This is the defacto (or FHS mandated?) standard location for software
built from source, in order to avoid clashing with packaged software
which is installed under /usr/bin etc.
I think there is benefit in having Xen's install behave more like the
majority of other OSS software out there.
The major downside here is in the transition from 4.2 to 4.3 where
people who have built from source will innevitably discover breakage
because 4.3 no longer overwrites stuff in /usr like it used to so they
pickup old stale bits from /usr instead of new stuff from /usr/local.
Packages will use ./configure --prefix=/usr or whatever helper macro
their package manager gives them. I have confirmed that doing this
results in the same list of installed files as before this patch was
applied.
The hypervisor remains in /boot/ and there is no intention to move it.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by: Matt Wilson <msw@amazon.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
Because there is not necessarily any lock held at the point the
application (eg, libvirt) calls libxl_osevent_occurred_timeout, in a
multithreaded program those calls may be arbitrarily delayed in
relation to other activities within the program.
Specifically this means when ->timeout_deregister returns, libxl does
not know whether it can safely dispose of the for_libxl value or
whether it needs to retain it in case of an in-progress call to
_occurred_timeout.
The interface could be fixed by requiring the application to make a
new call into libxl to say that the deregistration was complete.
However that new call would have to be threaded through the
application's event loop; this is complicated and some application
authors are likely not to implement it properly. Furthermore the
easiest way to implement this facility in most event loops is to queue
up a time event for "now".
Shortcut all of this by having libxl always call timeout_modify
setting abs={0,0} (ie, ASAP) instead of timeout_deregister. This will
cause the application to call _occurred_timeout. When processing this
calldown we see that we were no longer actually interested and simply
throw it away.
Additionally, there is a race between _occurred_timeout and
->timeout_modify. If libxl ever adjusts the deadline for a timeout
the application may already be in the process of calling _occurred, in
which case the situation with for_app's lifetime becomes very
complicated. Therefore abolish libxl__ev_time_modify_{abs,rel} (which
have no callers) and promise to the application only ever to call
->timeout_modify with abs=={0,0}. The application still needs to cope
with ->timeout_modify racing with its internal function which calls
_occurred_timeout. Document this.
This is a forwards-compatible change for applications using the libxl
API, and will hopefully eliminate these races in callback-supplying
applications (such as libvirt) without the need for corresponding
changes to the application. (It is possible that this might expose
bugs in applications, though, as previously libxl would never call
libxl_osevent_hooks->timeout_modify and now it never calls
->timeout_deregister).
For clarity, fold the body of time_register_finite into its one
remaining call site. This makes the semantics of ev->infinite
slightly clearer.
Cc: Bamvor Jian Zhang <bjzhang@suse.com>
Cc: Ian Campbell <Ian.Campbell@citrix.com>
Tested-by: Jim Fehlig <jfehlig@suse.com>
Acked-by: Jim Fehlig <jfehlig@suse.com>
Signed-off-by: Ian Jackson <ian.jackson@eu.citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
Because there is not necessarily any lock held at the point the
application (eg, libvirt) calls libxl_osevent_occurred_timeout and
..._fd, in a multithreaded program those calls may be arbitrarily
delayed in relation to other activities within the program.
libxl therefore needs to be prepared to receive very old event
callbacks. Arrange for this to be the case for fd callbacks.
This requires a new layer of indirection through a "hook nexus" struct
which can outlive the libxl__ev_foo. Allocation and deallocation of
these nexi is mostly handled in the OSEVENT macros which wrap up
the application's callbacks.
Document the problem and the solution in a comment in libxl_event.c
just before the definition of struct libxl__osevent_hook_nexus.
There is still a race relating to libxl__osevent_occurred_timeout;
this will be addressed in the following patch.
Reported-by: Bamvor Jian Zhang <bjzhang@suse.com>
Cc: Bamvor Jian Zhang <bjzhang@suse.com>
Cc: Ian Campbell <Ian.Campbell@citrix.com>
Tested-by: Jim Fehlig <jfehlig@suse.com>
Acked-by: Jim Fehlig <jfehlig@suse.com>
Signed-off-by: Ian Jackson <ian.jackson@eu.citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
Introduce a function to map a range of physical memory into Xen virtual
memory.
It doesn't need domheap to be setup.
It is going to be used to map the videoram.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
Add flush_xen_data_tlb_range_va, that flushes a range of virtual addresses.
Replace all the calls to flush_xen_data_tlb_va with calls to
flush_xen_data_tlb_range_va and remove flush_xen_data_tlb_va.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Committed-by: Ian Campbell <ian.campbell@citrix.com>
Raise the RTC IRQ not only when UIE gets set while UF was already set,
but generalize this to cover AIE and PIE as well.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
Properly mask off bit 7 when retrieving the hour values in
alarm_timer_update(), and properly use RTC_HOURS_ALARM's bit 7 when
converting from 12- to 24-hour value.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
Don't look at RTC_PIE in rtc_timer_update(), and hence don't call the
function on REG_B writes at all.
Also handle the two other possible clock bases.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
Note that in the RTC_UIE/RTC_UF case, this also fixes the lack of
setting RTC_IRQF.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
This mainly involves adjusting the number of L4 entries needing copying
between page tables (which is now different between PV and HVM/idle
domains), and changing the cutoff point and method when more than the
supported amount of memory is found in a system.
Since TMEM doesn't currently cope with the full 1:1 map not always
being visible, it gets forcefully disabled in that case.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
Acked-by: Dan Magenheimer <dan.magenheimer@oracle.com>
Despite the changes below, tmem still has code assuming to be able to
directly access all memory, or mapping arbitrary amounts of not
directly accessible memory. I cannot see how to fix this without
converting _all_ its domheap allocations to xenheap ones. And even then
I wouldn't be certain about there not being other cases where the "all
memory is always mapped" assumption would be broken. Therefore, tmem
gets disabled by the next patch for the time being if the full 1:1
mapping isn't always visible.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Dan Magenheimer <dan.magenheimer@oracle.com>
Acked-by: Keir Fraser <keir@xen.org>
This eliminates a couple of incorrect/inconsistent uses of
map_domain_page() from VT-x code.
Note that this does _not_ add error handling where none was present
before, even though I think NULL returns from any of the mapping
operations touched here need to properly be handled. I just don't know
this code well enough to figure out what the right action in each case
would be.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
This involves no longer storing virtual addresses of the per-domain
mapping L2 and L3 page tables.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
So far this has been repeated in 3 places, requiring to remember to
update all of them if a change is being made.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
This requires a minor hack to allow the correct page tables to be used
while running on Dom0's page tables (as they can't be determined from
"current" at that time).
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
This is being done mostly in the form previously used on x86-32,
utilizing the second L3 page table slot within the per-domain mapping
area for those mappings. It remains to be determined whether that
concept is really suitable, or whether instead re-implementing at least
the non-global variant from scratch would be better.
Also add the helpers {clear,copy}_domain_page() as well as initial uses
of them.
One question is whether, to exercise the non-trivial code paths, we
shouldn't make the trivial shortcuts conditional upon NDEBUG being
defined. See the debugging patch at the end of the series.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
... to allow frames for up to 16Tb.
At the same time, add the super page frame table coordinates to the
comment describing the address space layout.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
There is no reason for this and doing so exposes a memory leak to
guests. Only toolstacks need write access to this HVM param.
This is XSA-35 / CVE-2013-0152.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Jan Beulich <JBeulich@suse.com>
Committed-by: Jan Beulich <jbeulich@suse.com>
Fix S3 regression introduced by cs 23013:65d26504e843 (ACPI: large
cleanup). The dmar virtual pointer returned from acpi_get_table cannot
be safely stored away and used later, as the underlying
acpi_os_map_memory / __acpi_map_table functions overwrite the mapping
causing it to point to different tables than dmar (last fetched table is
used). This subsequently causes acpi_dmar_reinstate() and
acpi_dmar_zap() to write data to wrong table, causing its corruption and
problems with consecutive s3 resumes.
Added a new function to fetch ACPI table physical address, and
establishing separate static mapping for dmar_table pointer instead of
using acpi_get_table().
Signed-off-by: Tomasz Wroblewski <tomasz.wroblewski@citrix.com>
Added call to acpi_tb_verify_table(). Fixed page count passed to
map_pages_to_xen(). Cosmetic changes.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Committed-by: Jan Beulich <jbeulich@suse.com>
Manipulation of a domain's pirq namespace was not fully protected by
XSM hooks because the XSM hooks for IRQs needed a physical IRQ. Since
this may not apply to HVM domains, a complete solution needs to split
the XSM hook for this operation, using one hook for the PIRQ
manipulation and one for controlling access to the hardware IRQ.
This reworking has the advantage of providing the same MSI data to
remove_irq that is provided to add_irq, allowing the PCI device to be
determined in both functions. It also eliminates the last callers of
rcu_lock_target_domain_by_id in x86 and common code in preparation for
this function's removal.
Signed-off-by: Daniel De Graaf <dgdegra@tycho.nsa.gov>
Committed-by: Keir Fraser <keir@xen.org>
These hypercalls are usable by HVM guests. Once connected, simple
functions of the Xen toolstack can be run from an HVM domain if that
domain is permitted access (which is currently only possible via XSM).
Signed-off-by: Daniel De Graaf <dgdegra@tycho.nsa.gov>
Committed-by: Keir Fraser <keir@xen.org>
c/s 22949:54fe1011f86b removed the forwarding of NMIs to Dom0 when they
were caused by PCI SERR. NMI buttons as well as BMCs (like HP's iLO)
may however want such events to be seen in Dom0 (e.g. to trigger a
dump).
Therefore restore most of the functionality which named c/s removed
(adjusted for subsequent changes, and adjusting the public interface to
use the modern term, retaining the old one for backwards
compatibility).
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Keir Fraser <keir@xen.org>
Dongxiao Xu
Ian Campbell
Ian Campbell
Roger Pau Monne
Razvan Cojocaru
Jan Beulich
Dario Faggioli
Ian Jackson
Stefano Stabellini
Tim Deegan
Tomasz Wroblewski
Daniel De Graaf