This being a strict (MMX register only) subset of SSE, we can simply
adjust the respective checks while making the new predicate look at
both flags.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
... and their AVX equivalents. Note that a few instructions aren't
covered (yet), but those all fall into common pattern groups, so I
would hope that for now we can do with what is there.
MMX insns aren't being covered at all, as they're not easy to deal
with: The compiler refuses to emit such for other than uses of built-in
functions.
The current way of testing AVX insns is meant to be temporary only:
Once we fully support that feature, the present tests should rather be
replaced than full ones simply added.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
Note that other than most scalar instructions, vcvt{,t}s{s,d}2si do #UD
when VEX.l is set on at least some Intel models. To be on the safe
side, implement the most restrictive mode here for now when emulating
an Intel CPU, and simply clear the bit when emulating an AMD one.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Previously supported insns are being converted to the new model, and
several new ones are being added.
To keep the stub handling reasonably simple, integrate SET_SSE_PREFIX()
into copy_REX_VEX(), at once switching the stubs to use an empty REX
prefix instead of a double DS: one (no byte registers are being
accessed, so an empty REX prefix has no effect), except (of course) for
the 32-bit test harness build.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
This aims at covering most MMX/SSEn/AVX instructions in the 0x0f-escape
space with memory operands. Not covered here are irregular moves,
converts, and {,U}COMIS{S,D} (modifying EFLAGS).
Note that the distinction between simd_*_fp isn't strictly needed, but
I've kept them as separate entries since in an earlier version I needed
them to be separate, and we may well find it useful down the road to
have that distinction.
Also take the opportunity and adjust the vmovdqu test case the new
LDDQU one here has been cloned from: To zero a ymm register we don't
need to go through hoops, as 128-bit AVX insns zero the upper portion
of the destination register, and in the disabled AVX2 code there was a
wrong YMM register used.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
clean_dcache_va_range and clean_and_invalidate_dcache_va_range don't
calculate the range correctly when "end" is not cacheline aligned. As a
result, the last cacheline is not skipped. Fix the issue by aligning the
start address to the cacheline size.
In addition, make the code simpler and faster in
invalidate_dcache_va_range, by removing the module operation and using
bitmasks instead. Also remove the size adjustments in
invalidate_dcache_va_range, because the size variable is not used later
on.
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
Reviewed-by: Julien Grall <julien.grall@arm.com>
Tested-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
Currently, p2m_mem_access_emulate_check() uses p2m_get_mem_access()
to check if the page restrictions have been lifted between the time
of sending the vm_event out and the reception of the reply - in
which case emulation is no longer required. Unfortunately,
p2m_get_mem_access() uses p2m_get_hostp2m(d) which only checks the
default EPT (view 0 in altp2m parlance). This patch fixes this by
checking the active altp2m view instead, whenever applicable.
Signed-off-by: Razvan Cojocaru <rcojocaru@bitdefender.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Tamas K Lengyel <tamas@tklengyel.com>
c/s 5cecf60f4 "x86/cpuid: Handle leaf 0x1 in guest_cpuid()" causes Linux 4.10
to crash during boot.
It turns out to be because of the reported apic_id, which was altered to be
more consistent across guests. Revert back to the previous behaviour, by
limiting the apic_id adjustment to HVM guests only. Whomever gets to fixes
topology representation is going to have a lot of fun with non-power-of-2 AMD
boxes.
Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Tested-by: Sander Eikelenboom <linux@eikelenboom.it>
Introduce new Xen command line parameter called "vwfi", which stands for
virtual wfi. The default is "trap": Xen traps guest wfi and wfe
instructions. In the case of wfi, Xen calls vcpu_block on the guest
vcpu; in the case of guest wfe, Xen calls vcpu_yield on the guest vcpu.
The behavior can be changed by setting vwfi to "native", in that case
Xen doesn't trap neither wfi nor wfe, running them in guest context.
The result is strong reduction in irq latency (from 5000ns to 2000ns,
measured using https://github.com/edgarigl/tbm, the physical timer, and
1 pcpu dedicated to 1 vcpu). The downside is that the scheduler thinks
that the guest is busy when actually is sleeping, leading to suboptimal
scheduling decisions.
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Reviewed-by: Dario Faggioli <dario.faggioli@citrix.com>
Reviewed-by: Julien Grall <julien.grall@arm.com>
start_svm() already runs after cpu_data[] was set up, so it shouldn't
modify it anymore (at least not directly). Constify the involved
pointers.
Furthermore LMSLE feature detection was broken by 566ddbe833 ("x86:
Fail CPU bringup cleanly if it cannot initialise HVM"), as Andrew
Cooper has pointed out: c couldn't possibly equal &boot_cpu_data
anymore. (But since it's unsafe migration-wise for some more time,
suppress the feature actually being enabled for us.)
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper@citrix.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
This patch handles some corner cases when the last assigned device
is removed from the domain. In this case we should carefully handle
pi descriptor and the per-cpu blocking list, to make sure:
- all the PI descriptor are in the right state when next time a
devices is assigned to the domain again.
- No remaining vcpus of the domain in the per-cpu blocking list.
Here we call vmx_pi_unblock_vcpu() to remove the vCPU from the blocking list
if it is on the list. However, this could happen when vmx_vcpu_block() is
being called, hence we might incorrectly add the vCPU to the blocking list
while the last devcie is detached from the domain. Consider that the situation
can only occur when detaching the last device from the domain and it is not
a frequent operation, so we use domain_pause before that, which is considered
as an clean and maintainable solution for the situation.
Signed-off-by: Feng Wu <feng.wu@intel.com>
Signed-off-by: Chao Gao <chao.gao@intel.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
The public header expects a few types to be present.
This works in the code base only because types.h is included by some
other headers which happen to be placed before the inclusion of
domain.h.
Include types.h before xen.h in domain.h to fix it properly.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
They are going to be needed in multiple places. Instead of replicating
more, move them to pfn.h.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
All known paths raising faults behind the back of the emulator have been
fixed. Reinstate the original intended assertion concerning the behaviour of
X86EMUL_EXCEPTION and ctxt->event_pending.
As x86_emulate_wrapper() now covers both PV and HVM guests properly, there is
no need for the PV assertions following calls to x86_emulate().
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
hvm_set_cr{0,4}() are reachable from the emulator, but use
hvm_inject_hw_exception() directly.
Alter the API to make the callers of hvm_set_cr{0,3,4}() responsible for
raising #GP, and apply this change to all existing callers.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
---
Issues identified which I am purposefully not fixing in this patch:
(I will try to get around to them, but probably not in the 4.9 timeframe, at
this point.)
* hvm_set_cr3() doesn't handle bad 32bit PAE PDPTRs properly, as it doesn't
actually have a path which raises #GP.
* There is a lot of redundancy in our HVM CR setting routines, but not enough
to trivially dedup at this point.
* Both nested VT-x and SVM are liable raise #GP with L1, rather than failing
the virtual vmentry/vmexit. This is not a change in behaviour, but is far
more obvious now.
* The hvm_do_resume() path for vm_event processing has the same bug as the
MSR side, where exceptions are raised after %rip has moved forwards. This
is also not a change in behaviour.
Making PV and HVM guests individually compilable is useful as a reduction in
hypervisor size, and as an aid to enforcing clean API boundaries.
Introduce CONFIG_PV and CONFIG_HVM, although there is a lot of work to do
until either can actually be disabled.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
__vmx_deliver_posted_interrupt() wrongly used a softirq bit to decide whether
to suppress an IPI. Its logic was: the first time an IPI was sent, we set
the softirq bit. Next time, we would check that softirq bit before sending
another IPI. If the 1st IPI arrived at the pCPU which was in
non-root mode, the hardware would consume the IPI and sync PIR to vIRR.
During the process, no one (both hardware and software) will clear the
softirq bit. As a result, the following IPI would be wrongly suppressed.
This patch discards the suppression check, always sending an IPI.
The softirq also need to be raised. But there is a little change.
This patch moves the place where we raise a softirq for
'cpu != smp_processor_id()' case to the IPI interrupt handler.
Namely, don't raise a softirq for this case and set the interrupt handler
to pi_notification_interrupt()(in which a softirq is raised) regardless of
VT-d PI enabled or not. The only difference is when an IPI arrives at the
pCPU which is happened in non-root mode, the code will not raise a useless
softirq since the IPI is consumed by hardware rather than raise a softirq
unconditionally.
Signed-off-by: Quan Xu <xuquan8@huawei.com>
Signed-off-by: Chao Gao <chao.gao@intel.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
If a guest will do vmptrld with an incorrect vmcs id:
(XEN) Xen BUG at .../git/upstream/xen/xen/include/asm/hvm/vmx/vmx.h:333
(XEN) ----[ Xen-4.9-unstable x86_64 debug=y Tainted: H ]----
(XEN) Xen call trace:
(XEN) [<ffff82d0801f925e>] vmcs.c#arch/x86/hvm/vmx/vmcs.o.unlikely+0x28/0x19a
(XEN) [<ffff82d0801f602c>] virtual_vmcs_vmread+0x11/0x2c
(XEN) [<ffff82d0802002cc>] vvmx.c#_map_io_bitmap+0x86/0x88
(XEN) [<ffff82d080202399>] nvmx_handle_vmptrld+0xf0/0x1fb
(XEN) [<ffff82d0801fe93c>] vmx_vmexit_handler+0x132b/0x1c49
(XEN) [<ffff82d080203e6c>] vmx_asm_vmexit_handler+0x3c/0x120
Fix this by adding appropriate checks for vmcs id during vmptrld
emulation.
Signed-off-by: Sergey Dyasli <sergey.dyasli@citrix.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
If nested vmcs's address is invalid, virtual_vmcs_enter() will fail
during vmread/vmwrite:
(XEN) Xen BUG at .../git/upstream/xen/xen/include/asm/hvm/vmx/vmx.h:333
(XEN) ----[ Xen-4.9-unstable x86_64 debug=y Tainted: H ]----
(XEN) Xen call trace:
(XEN) [<ffff82d0801f925e>] vmcs.c#arch/x86/hvm/vmx/vmcs.o.unlikely+0x28/0x19a
(XEN) [<ffff82d0801f60e3>] virtual_vmcs_vmwrite_safe+0x16/0x52
(XEN) [<ffff82d080202cb2>] nvmx_handle_vmwrite+0x70/0xfe
(XEN) [<ffff82d0801fe98a>] vmx_vmexit_handler+0x1379/0x1c49
(XEN) [<ffff82d08020427c>] vmx_asm_vmexit_handler+0x3c/0x120
Fix this by emulating VMfailInvalid if the address is invalid.
Signed-off-by: Sergey Dyasli <sergey.dyasli@citrix.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
We may hit the last ASSERT() in vmx_vcpu_block in the current code,
since vmx_vcpu_block() may get called before vmx_pi_switch_to()
has been installed or executed. Here We use cmpxchg to update
the NDST field, this can make sure we only update the NDST when
vmx_pi_switch_to() has not been called. So the NDST is in a
proper state in vmx_vcpu_block().
Suggested-by: Jan Beulich <JBeulich@suse.com>
Signed-off-by: Feng Wu <feng.wu@intel.com>
Signed-off-by: Chao Gao <chao.gao@intel.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
PI hook vmx_pi_switch_to() is needed even after any previously
assigned device is detached from the domain. Since 'SN' bit is
also used to control the CPU side PI and we change the state of
SN bit in vmx_pi_switch_to() and vmx_pi_switch_from(), then
evaluate this bit in vmx_deliver_posted_intr() when trying to
deliver the interrupt in posted way via software. The problem
is if we deassign the hooks while the vCPU is runnable in the
runqueue with 'SN' set, all the furture notificaton event will
be suppressed. This patch makes the hook permanently assigned.
Signed-off-by: Feng Wu <feng.wu@intel.com>
Signed-off-by: Chao Gao <chao.gao@intel.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>).
Acked-by: Kevin Tian <kevin.tian@intel.com>
On Intel hardware, EFER is not fully switched between host and guest contexts.
In practice, this means that Xen's EFER.NX setting leaks into guest context,
and influences the behaviour of the hardware pagewalker.
When servicing a pagefault, Xen's model of guests behaviour should match
hardware's behaviour, to allow correct interpretation of the pagefault error
code, and to avoid creating observable difference in behaviour from the guests
point of view.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
The Intel microcode driver is using sync_core() to mean "do CPUID
with EAX=1".
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Borislav Petkov <bp@alien8.de>
[Linux commit 484d0e5c7943644cc46e7308a8f9d83be598f2b9]
[Ported to Xen]
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
It is a non-standard heap-sort algorithm implementation because the index
of child node is wrong . The sort function still outputs right result, but
the performance is O( n * ( log(n) + 1 ) ) , about 10% ~ 20% worse than
standard algorithm.
Signed-off-by: keios <keios.cn@gmail.com>
[Linux commit: d3717bdf8f08a0e1039158c8bab2c24d20f492b6]
[Ported to Xen]
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Copy the one in libxl, remove the irrelevant bits about libxl. Replace
libxl with xl where appropriate.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
When calling configure for qemu provide the local pkg-config directory
in order to let the configure process find the libxenctrl version.
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Instead of using the downloaded git tree as target directory for the
qemu build create a dedicated directory for that purpose.
This way it is possible to use the same source directory of qemu to
configure and build qemu upstream in a stubdom environment in future.
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
When configuring the build of qemu the configure script is building
various test programs to determine the exact version of libxencontrol.
Instead of a try and error approach needing updates for nearly each
new version of Xen just provide xencontrol.pc to be used via
pkg-config.
In the end we need two different variants of that file: one for the
target system where eventually someone wants to build qemu, and one
for the local system to be used for building qemu as part of the Xen
build process.
The local variant is created in a dedicated directory in order to be
able to collect more pkg-config files used for building tools there.
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
A stubdom app using xenctrl.h must use the latest interface version of
Xen in order to avoid compatibility issues. Add the related config
item to the stubdom config files where needed.
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
Some libc headers don't have O_CLOEXEC, we need to take care of it by
defining to 0 (on the ground that such glibc might barf on O_CLOEXEC).
Fixes e7745d8ef5 ("tools/libxendevicemodel: introduce a Linux-specific
implementation")
Signed-off-by: Olaf Hering <olaf@aepfle.de>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Jan Beulich
Stefano Stabellini
Razvan Cojocaru
Andrew Cooper
Olaf Hering
Feng Wu
Wei Liu
Quan Xu
Sergey Dyasli
Andy Lutomirski
keios
Juergen Gross
Anthony PERARD