Interacting with the vcpu itself should be protected by vcpu_pause().
Buggy/naive toolstacks might encounter adverse interaction with a vcpu context
switch, or increase of xcr0_accum. There are no much problems with current
in-tree code.
Explicitly permit a NULL guest handle as being a request for size. It is the
prevailing Xen style, and without it, valgrind's ioctl handler is unable to
determine whether evc->buffer actually got written to.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
x86/domctl: further fix to XEN_DOMCTL_[gs]etvcpuextstate
Do not clobber errors from certain codepaths. Clobbering of -EINVAL from
failing "evc->size <= PV_XSAVE_SIZE(_xcr0_accum)" was a pre-existing bug.
However, clobbering -EINVAL/-EFAULT from the get codepath was a bug
unintentionally introduced by 090ca8c1 "x86/domctl: two functional fixes to
XEN_DOMCTL_[gs]etvcpuextstate".
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: 090ca8c155
master date: 2014-06-05 17:52:57 +0200
master commit: 895661ae98
master date: 2014-06-10 12:03:16 +0200
When firmware-first mode is being indicated by firmware, we shouldn't
be modifying AER registers - these are considered to be owned by
firmware in that case. Violating this is being reported to result in
SMI storms. While circumventing the workaround means re-exposing
affected hosts to the XSA-59 issues, this in any event seems better
than not booting at all. Respective messages are being issued to the
log, so the situation can be diagnosed.
The basic building blocks were taken from Linux 3.15-rc. Note that
this includes a block of code enclosed in #ifdef CONFIG_X86_MCE - we
don't define that symbol, and that code also wouldn't build without
suitable machine check side code added; that should happen eventually,
but isn't subject of this change.
Reported-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reported-by: Malcolm Crossley <malcolm.crossley@citrix.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Tested-by: Malcolm Crossley <malcolm.crossley@citrix.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Yang Zhang <yang.z.zhang@intel.com>
master commit: 1cc37ba8db
master date: 2014-06-05 17:49:14 +0200
If a buggy BIOS programs an ACPI table with to small an entry length
then acpi_table_entries gets stuck in an infinite loop.
To aid debugging, report the error and exit the loop.
Based on Linux kernel commit 369d913b242cae2205471b11b6e33ac368ed33ec
Signed-off-by: Malcolm Crossley <malcolm.crossley@citrix.com>
Use < instead of <= (which I wrongly suggested), return -ENODATA
instead of -EINVAL, and make description match code.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
master commit: 9c1e8cae65
master date: 2014-06-04 11:26:15 +0200
A failure would result in log message like so-
(XEN) microcode: CPU0 update from revision 0x6000637 to 0x6000626 failed
^^^^^^^^^^^^^^^^^^^^^^
The above message has the revision numbers inverted. Fix this.
Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
master commit: 071a4c70a6
master date: 2014-06-02 10:19:27 +0200
... unless they're part of a fully separate pool (and hence can't ever
be used for guest allocations).
This is CVE-2014-4021 / XSA-100.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Keir Fraser <keir@xen.org>
master commit: 4bd78937ec
master date: 2014-06-17 15:21:10 +0200
- pirq_info() returns NULL for a non-allocated pIRQ, and hence we
mustn't unconditionally de-reference it, and we need to invoke it
another time after having called map_domain_emuirq_pirq()
- don't use printk(), namely without XENLOG_GUEST, for error reporting
This is XSA-96.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
master commit: 6f4cc0ac41
master date: 2014-06-03 15:17:14 +0200
Program the timer to the deadline of the closest timer if it is further
than 50us ahead, otherwise set it 50us ahead. This way a single event
fires on time rather than 50us late (as it would have previously) while
still preventing too many timer wakeups in the case of having many
timers scheduled close together.
(where 50us is the timer_slop)
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
master commit: 054b6dfb61
master date: 2014-05-28 10:07:50 +0200
Doing both flushes at once is a strong indication for the address
mapping to either having got dropped (in which case the cache flush,
when done via INVLPG, would fault) or its physical address having
changed (in which case the cache flush would end up being done on the
wrong address range). There is no adverse effect (other than the
obvious performance one) using WBINVD in this case regardless of the
range's size; only map_pages_to_xen() uses combined flushes at present.
This problem was observed with the 2nd try backport of d6cb14b3 ("VT-d:
suppress UR signaling for desktop chipsets") to 4.2 (where ioremap()
needs to be replaced with set_fixmap_nocache(); the now commented out
__set_fixmap(, 0, 0) there to undo the mapping resulted in the first of
the above two scenarios).
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
master commit: 50df6f7429
master date: 2014-05-28 09:51:07 +0200
iommu_merge_pages() still wants to look at the next level page table,
the TLB flush necessary before freeing too happens in that function,
and if it fails no free should happen at all. Hence the freeing must
be done after that function returned successfully, not before it's
being called.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Tested-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
master commit: 6b4d71d028
master date: 2014-05-28 09:50:33 +0200
In commit ("VT-d: suppress UR signaling for desktop chipsets")
the mask applied to the value read from DMIBAR is to narrow, only the
comment accompanying it was correct. Fix that and tag the literal
number as "long" at once to avoid eventual compiler warnings.
The widest possible value so far is 39 bits; all chipsets covered here
but having less than this number of bits have the remaining bits marked
reserved (zero), and hence there's no need for making the mask chipset
specific.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Yang Zhang <yang.z.zhang@intel.com>
master commit: f8ecf31c31
master date: 2014-05-26 12:28:46 +0200
acpi_get_table(), when executed before reaching SYS_STATE_active, will
return a mapping valid only until the next invocation of that funciton.
Consequently storing the returned pointer for later use is incorrect.
Copy the logic used in VT-d's DMAR handling.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
master commit: fca69b1fc6
master date: 2014-05-26 12:25:01 +0200
Currently when a domain is destroyed it is removed from the domain_list
before all of it's resources, including the cpupool membership, are freed.
This can lead to a situation where the domain is still member of a cpupool
without for_each_domain_in_cpupool() (or even for_each_domain()) being
able to find it any more. This in turn can result in rejection of removing
the last cpu from a cpupool, because there seems to be still a domain in
the cpupool, even if it can't be found by scanning through all domains.
This situation can be avoided by moving the domain to be destroyed to
cpupool0 first and then remove it from this cpupool BEFORE deleting it from
the domain_list. As cpupool0 is always active and a domain without any cpupool
membership is implicitly regarded as belonging to cpupool0, this poses no
problem.
Signed-off-by: Juergen Gross <juergen.gross@ts.fujitsu.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: George Dunlap <george.dunlap@eu.citrix.com>
master commit: bac6334b51
master date: 2014-05-20 15:55:42 +0200
Add two more PCI IDs to the set that has been taken care of with a
different workaround long before XSA-59, and (for constency with the
newer workarounds) log a message here too.
Also move the function wide comment to the cases it applies to; this
should really have been done by d061d200 ("VT-d: suppress UR signaling
for server chipsets").
This is CVE-2013-3495 / XSA-59.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Xiantao Zhang <xiantao.zhang@intel.com>
Acked-by: Yang Zhang <yang.z.zhang@intel.com>
master commit: 04734664eb
master date: 2014-05-20 15:54:01 +0200
Accessing extended config space may not be possible at boot time, e.g.
when the memory space used by MMCFG is reserved only via ACPI tables,
but not in the E820/UEFI memory maps (which we need Dom0 to tell us
about). Consequently the change here still leaves the issue unaddressed
for systems where the extended config space remains inaccessible (due
to firmware bugs, i.e. not properly reserving the address space of
those regions).
With the respective messages now potentially getting logged more than
once, we ought to consider whether we should issue them only if we in
fact were required to do any masking (i.e. if the relevant mask bits
weren't already set).
This is CVE-2013-3495 / XSA-59.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Xiantao Zhang <xiantao.zhang@intel.com>
Acked-by: Yang Zhang <yang.z.zhang@intel.com>
master commit: 5786718fba
master date: 2014-05-20 15:53:20 +0200
Dom0 may bring up less number of vCPUs than xen hypervisor actually created for
it, and in this case, on Intel platform, vMCE injection to dom0 will fail due to
injecting vMCE to uninitialized vcpu, and cause dom0 crash.
Signed-off-by: Kai Huang <kai.huang@linux.intel.com>
Acked-by: Christoph Egger <chegger@amazon.de>
master commit: a07084525c
master date: 2014-05-14 10:54:39 +0200
We should be able to continue using native RDTSC(P) execution on
HVM/PVH guests after migration if host and guest frequencies are
equal (this includes the case when the frequencies are made equal
by TSC scaling feature).
This also allows us to revert main part of commit 4aab59a3 (svm: Do not
intercept RDTSC(P) when TSC scaling is supported by hardware) which
was wrong: while RDTSC intercepts were disabled domain's vtsc could
still be set, leading to inconsistent view of guest's TSC.
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
master commit: 82713ec8d2
master date: 2014-04-22 12:07:37 +0200
Even in no-ack mode, there's no reason to leave the line asserted
after an explicit ack of the interrupt.
Furthermore, rtc_update_irq() is an unconditional noop having just cleared
REG_C.
Signed-off-by: Tim Deegan <tim@xen.org>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: 6d27a53772
master date: 2014-02-25 09:30:21 +0100
Let the vpt code drive the RTC's timer interrupts directly, as it does
for other periodic time sources, and fix up the register state in a
vpt callback when the interrupt is injected.
This fixes a hang seen on Windows 2003 in no-missed-ticks mode, where
when a tick was pending, the early callback from the VPT code would
always set REG_C.PF on every VMENTER; meanwhile the guest was in its
interrupt handler reading REG_C in a loop and waiting to see it clear.
One drawback is that a guest that attempts to suppress RTC periodic
interrupts by failing to read REG_C will receive up to 10 spurious
interrupts, even in 'strict' mode. However:
- since all previous RTC models have had this property (including
the current one, since 'no-ack' mode is hard-coded on) we're
pretty sure that all guests can handle this; and
- we're already playing some other interesting games with this
interrupt in the vpt code.
One other corner case: a guest that enables the PF timer interrupt,
masks the interupt in the APIC and then polls REG_C looking for PF
will not see PF getting set. The more likely case of enabling the
timers and masking the interrupt with REG_B.PIE is already handled
correctly.
Signed-off-by: Tim Deegan <tim@xen.org>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: c7e35c6ec7
master date: 2014-02-25 09:29:26 +0100
If the guest has not asked for interrupts, don't run the vpt timer
to generate them. This is a prerequisite for a patch to simplify how
the vpt interacts with the RTC, and also gets rid of a timer series in
Xen in a case where it's unlikely to be needed.
Instead, calculate the correct value for REG_C.PF whenever REG_C is
read or PIE is enabled. This allow a guest to poll for the PF bit
while not asking for actual timer interrupts. Such a guest would no
longer get the benefit of the vpt's timer modes.
Signed-off-by: Tim Deegan <tim@xen.org>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: 4c15a82f03
master date: 2014-02-25 09:26:45 +0100
It is very common for BIOSes to advertise more cpus than are actually present
on the system, and mark some of them as offline. This is what Xen does to
allow for later CPU hotplug, and what BIOSes common to multiple different
systems do to to save fully rewriting the MADT in memory.
An excerpt from `xl info` might look like:
...
nr_cpus : 2
max_cpu_id : 3
...
Which shows 4 CPUs in the MADT, but only 2 online (as this particular box is
the dual-core rather than the quad-core SKU of its particular brand)
Because of the way Xen exposes this information, a libxl_cputopology array is
bounded by 'nr_cpus', while cpu bitmaps are bounded by 'max_cpu_id + 1'.
The current libxl code has two places which erroneously assume that a
libxl_cputopology array is as long as the number of bits found in a cpu
bitmap, and valgrind complains:
==14961== Invalid read of size 4
==14961== at 0x407AB7F: libxl__get_numa_candidate (libxl_numa.c:230)
==14961== by 0x407030B: libxl__build_pre (libxl_dom.c:167)
==14961== by 0x406246F: libxl__domain_build (libxl_create.c:371)
...
==14961== Address 0x4324788 is 8 bytes after a block of size 24 alloc'd
==14961== at 0x402669D: calloc (in/usr/lib/valgrind/vgpreload_memcheck-x86-linux.so)
==14961== by 0x4075BB9: libxl__zalloc (libxl_internal.c:83)
==14961== by 0x4052F87: libxl_get_cpu_topology (libxl.c:4408)
==14961== by 0x407A899: libxl__get_numa_candidate (libxl_numa.c:342)
...
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Dario Faggioli <dario.faggioli@citrix.com>
Acked-by: Ian Campbell <Ian.Campbell@citrix.com>
CC: Ian Jackson <Ian.Jackson@eu.citrix.com>
(cherry picked from commit 81b0305048)
(cherry picked from commit 3aaa40fd58)
If no partitions at all are found, pygrub never creates the name 'fs',
resulting in a NameError indicating the lack of fs, rather than a
RuntimeError explaining that no partitions were found.
Set fs to None right at the start, and use the pythonic idiom "if fs is None:"
to protect against otherwise valid values for fs which compare equal to
0/False.
Reported-by: Sven Köhler <sven.koehler@gmail.com>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
CC: Ian Campbell <Ian.Campbell@citrix.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
(cherry picked from commit d75215805c)
(cherry picked from commit 5ee75ef147)
do_tmem_destroy_pool is checking if pools == NULL. But, pools is a fixed
array.
Clang 3.5 will fail to compile xen/common/tmem.c with the following error:
tmem.c:1848:18: error: comparison of array 'client->pools' equal to a null
pointer is always false [-Werror,-Wtautological-pointer-compare]
if ( client->pools == NULL )
Coverity-ID:1055632
Signed-off-by: Julien Grall <julien.grall@linaro.org>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
(cherry picked from commit ac0f56a2fa)
(cherry picked from commit 6ce0c3fca9)
The way XEN_DOMCTL_set_cpuid got handled so far allowed for surprises
to the caller. With this set of operations
- set leaf A (using array index 0)
- set leaf B (using array index 1)
- clear leaf A (clearing array index 0)
- set leaf B (using array index 0)
- clear leaf B (clearing array index 0)
the entry for leaf B at array index 1 would still be in place, while
the caller would expect it to be cleared.
While looking at the use sites of d->arch.cpuid[] I also noticed that
the allocation of the array needlessly uses the zeroing form - the
relevant fields of the array elements get set in a loop immediately
following the allocation.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Tim Deegan <tim@xen.org>
master commit: 4c0ff6bd54
master date: 2014-05-02 12:09:03 +0200
The function calls prepare_ring_for_helper() to acquire a mapping for the
given gmfn, then checks (under lock) to see if the ioreq page is already
set up but, if it is, the function then releases the in-use ioreq page
mapping on the error path rather than the one it just acquired. This patch
fixes this bug.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
master commit: 16e2a7596e
master date: 2014-05-02 11:46:32 +0200
When checking the SMEP feature for HVM guests, we should check the
VCPU instead of the host CPU.
Signed-off-by: Feng Wu <feng.wu@intel.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
master commit: 31ee951a3b
master date: 2014-04-28 12:47:24 +0200
Unsupported Requests can be signaled for malformed writes to the MSI
address region, e.g. due to buggy or malicious DMA set up to that
region. These should normally result in IOMMU faults, but don't on
the desktop chipsets dealt with here.
This is CVE-2013-3495 / XSA-59.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Don Dugger <donald.d.dugger@intel.com>
Acked-by: Tim Deegan <tim@xen.org>
Acked-by: Xiantao Zhang <xiantao.zhang@intel.com>
master commit: d6cb14b34f
master date: 2014-04-25 12:12:38 +0200
Unsupported Requests can be signaled for malformed writes to the MSI
address region, e.g. due to buggy or malicious DMA set up to that
region. These should normally result in IOMMU faults, but don't on
the server chipsets dealt with here.
IDs 0xe00, 0xe01, and 0xe04 ... 0xe0b (Ivytown) aren't needed here -
Intel confirmed the issue to be fixed in hardware there.
This is CVE-2013-3495 / XSA-59.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Don Dugger <donald.d.dugger@intel.com>
Acked-by: Tim Deegan <tim@xen.org>
Acked-by: Xiantao Zhang <xiantao.zhang@intel.com>
master commit: d061d200eb
master date: 2014-04-25 12:11:55 +0200
p2m_set_entry() can fail without there being a bug in the code - crash
the domain rather than the host in that case.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Tim Deegan <tim@xen.org>
master commit: 1ca73aaf51
master date: 2014-04-14 12:50:56 +0200
This value is an inclusive one, i.e. this fixes an off-by-one in memory
sharing and an off-by-two in shadow code.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Tim Deegan <tim@xen.org>
master commit: 088ee1d47b
master date: 2014-04-03 12:08:43 +0100
Permitting arbitrary type changes here has the potential of creating
present P2M (and hence EPT/NPT/IOMMU) entries pointing to an invalid
MFN (INVALID_MFN truncated to the respective hardware structure field's
width). This would become a problem the latest when something real sat
at the end of the physical address space; I'm suspecting though that
other things might break with such bogus entries.
Along with that drop a bogus (and otherwise becoming stale) log
message.
Afaict the similar operation in p2m_set_mem_access() is safe.
This is XSA-92.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Tim Deegan <tim@xen.org>
master commit: 83bb5eb4d3
master date: 2014-04-29 15:11:31 +0200
CPUID[80000008].EAX[23:16] have been given the meaning of the guest
physical address restriction (in case it needs to be smaller than the
host's), hence we need to mirror that into vCPUID[80000008].EAX[7:0].
Enforce a lower limit at the same time, as well as a fixed value for
the virtual address bits, and zero for the guest physical address ones.
In order for the vMTRR code to see these overrides we need to make it
call hvm_cpuid() instead of domain_cpuid(), which in turn requires
special casing (and relaxing) the controlling domain.
This additionally should hide an ordering problem in the tools: Both
xend and xl appear to be restoring a guest from its image before
setting up the CPUID policy in the hypervisor, resulting in
domain_cpuid() returning all zeros and hence the check in
mtrr_var_range_msr_set() failing if the guest previously had more than
the minimum 36 physical address bits.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Tim Deegan <tim@xen.org>
master commit: ef437690af
master date: 2014-03-28 13:33:34 +0100
GRUB usually always loads a whole disk track, even if that means going
beyond the end of the disk. We thus have to gracefully return an error,
instead of letting the blkfront go panic.
Signed-off-by: Samuel Thibault <samuel.thibault@ens-lyon.org>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
(cherry picked from commit 51e18e41e3)
(cherry picked from commit 03eb513405)
menuentry in grub2/grub.cfg uses linux16 and initrd16 commands
instead of linux and initrd. Due to this RHEL 7 (beta) guest failed to
boot after the installation.
In addition to this, RHEL 7 menu entries have two different single-quote
delimited strings on the same line, and the greedy grouping for menuentry
parsing gets both strings, and the options inbetween.
Signed-off-by: Joby Poriyath <joby.poriyath@citrix.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Cc: george.dunlap@citrix.com
(cherry picked from commit dd03048708)
(cherry picked from commit 607d9c98e8)
If libxl_pipe fails we leave the carefd locked, which translates to
the atfork lock remaining held. This would probably cause the process
to deadlock shortly afterwards.
Of course libxl_pipe is very unlikely to fail unless things are
already going very badly. This bug has not been observed anywhere as
far as we are aware.
Signed-off-by: Ian Jackson <Ian.Jackson@eu.citrix.com>
Acked-by: Ian Campbell <Ian.Campbell@citrix.com>
CC: George Dunlap <george.dunlap@eu.citrix.com>
(cherry picked from commit 7eb73add5d)
(cherry picked from commit 4bb3a17449)
This avoids the process being forked while a carefd is recorded in the
list but the actual fd has been closed. If that happened, a
subsequent libxl_postfork_child_noexec would attempt to close the fd
again. If we are lucky that results in a harmless warning; but if we
are unlucky the fd number has been reused and we close an unrelated
fd.
This race has not been observed anywhere as far as we are aware.
Signed-off-by: Ian Jackson <Ian.Jackson@eu.citrix.com>
Acked-by: Ian Campbell <Ian.Campbell@citrix.com>
CC: George Dunlap <george.dunlap@eu.citrix.com>
(cherry picked from commit 2a0c3a62ea)
(cherry picked from commit 86c00cb6e2)
The XSA-60 fixes introduced a window during which the guest PAT gets
forced to all zeros. This shouldn't be visible to the guest. Therefore
we need to intercept PAT MSR accesses during that time period.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Liu Jinsong <jinsong.liu@intel.com>
master commit: fce79f8ce9
master date: 2014-04-01 16:49:18 +0200
There's no point in this being mapped UC by the guest due to using a
respective PAT index - set the ignore-PAT flag to true.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Tim Deegan <tim@xen.org>
master commit: 1f8b577797
master date: 2014-03-28 13:43:25 +0100
CPUID[80000008].EAX[23:16] have been given the meaning of the guest
physical address restriction (in case it needs to be smaller than the
host's), hence we need to mirror that into vCPUID[80000008].EAX[7:0].
Enforce a lower limit at the same time, as well as a fixed value for
the virtual address bits, and zero for the guest physical address ones.
In order for the vMTRR code to see these overrides we need to make it
call hvm_cpuid() instead of domain_cpuid(), which in turn requires
special casing (and relaxing) the controlling domain.
This additionally should hide an ordering problem in the tools: Both
xend and xl appear to be restoring a guest from its image before
setting up the CPUID policy in the hypervisor, resulting in
domain_cpuid() returning all zeros and hence the check in
mtrr_var_range_msr_set() failing if the guest previously had more than
the minimum 36 physical address bits.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Tim Deegan <tim@xen.org>
master commit: ef437690af
master date: 2014-03-28 13:33:34 +0100
We can't just add in the hole shift value, as the hole may be at or
above the 44-bit boundary. Instead we need to determine the total bit
count until reaching 32 significant (not squashed out) bits in PFN
representations.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
master commit: b3d2f8b2cb
master date: 2014-03-24 10:48:03 +0100
Linux commit 40e2d7f9b5dae048789c64672bf3027fbb663ffa ("x86 idle:
Repair large-server 50-watt idle-power regression") tells us that this
applies not just to the named Xeon 7400 series, but also NHM-EX and
WSM-EX; sadly Intel's documentation is so badly searchable that I
wasn't able to locate the respective errata (and hence can't quote
their numbers here).
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
master commit: 96d1b237ae
master date: 2014-03-17 16:47:22 +0100
Removing mapped RMRR tracking structures in dma_pte_clear_one() is
wrong for two reasons: First, these regions may cover more than a
single page. And second, multiple devices (and hence multiple devices
assigned to any particular guest) may share a single RMRR (whether
assigning such devices to distinct guests is a safe thing to do is
another question).
Therefore move the removal of the tracking structures into the
counterpart function to the one doing the insertion -
intel_iommu_remove_device(), and add a reference count to the tracking
structure.
Further, for the handling of the mappings of the respective memory
regions to be correct, RMRRs must not overlap. Add a respective check
to acpi_parse_one_rmrr().
And finally, with all of this being VT-d specific, move the cleanup
of the list as well as the structure type definition where it belongs -
in VT-d specific rather than IOMMU generic code.
Note that this doesn't address yet another issue associated with RMRR
handling: The purpose of the RMRRs as well as the way the respective
IOMMU page table mappings get inserted both suggest that these regions
would need to be marked E820_RESERVED in all (HVM?) guests' memory
maps, yet nothing like this is being done in hvmloader. (For PV guests
this would also seem to be necessary, but may conflict with PV guests
possibly assuming there to be just a single E820 entry representing all
of its RAM.)
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Xiantao Zhang <xiantao.zhang@intel.com>
master commit: dd52706177
master date: 2014-03-17 16:45:04 +0100
- never preempt on the first iteration (ensure forward progress)
- never preempt on the last iteration (pointless/wasteful)
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Tim Deegan <tim@xen.org>
Acked-by: Keir Fraser <keir@xen.org>
master commit: fd7bfce039
master date: 2014-03-13 14:27:51 +0100
Andrew Cooper
Jan Beulich
Malcolm Crossley
Aravind Gopalakrishnan
Ross Lagerwall
Juergen Gross
Kai Huang
Edmund H White
Boris Ostrovsky
Tim Deegan
Wei Liu
Julien Grall
Paul Durrant
Feng Wu
Samuel Thibault
Joby Poriyath
Ian Jackson