| Age | Commit message (Collapse) | Author |
|---|
|
To minimize the latency of timer interrupts as observed by the guest,
KVM adjusts the values it programs into the host timers to account for
the host's overhead of programming and handling the timer event. In
the event that the adjustments are too aggressive, i.e. the timer fires
earlier than the guest expects, KVM busy waits immediately prior to
entering the guest.
Currently, KVM manually converts the delay from nanoseconds to clock
cycles. But, the conversion is done in the guest's time domain, while
the delay occurs in the host's time domain. This is perfectly ok when
the guest and host are using the same TSC ratio, but if the guest is
using a different ratio then the delay may not be accurate and could
wait too little or too long.
When the guest is not using the host's ratio, convert the delay from
guest clock cycles to host nanoseconds and use ndelay() instead of
__delay() to provide more accurate timing. Because converting to
nanoseconds is relatively expensive, e.g. requires division and more
multiplication ops, continue using __delay() directly when guest and
host TSCs are running at the same ratio.
Cc: Liran Alon <liran.alon@oracle.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Cc: stable@vger.kernel.org
Fixes: 3b8a5df6c4dc6 ("KVM: LAPIC: Tune lapic_timer_advance_ns automatically")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The introduction of adaptive tuning of lapic timer advancement did not
allow for the scenario where userspace would want to disable adaptive
tuning but still employ timer advancement, e.g. for testing purposes or
to handle a use case where adaptive tuning is unable to settle on a
suitable time. This is epecially pertinent now that KVM places a hard
threshold on the maximum advancment time.
Rework the timer semantics to accept signed values, with a value of '-1'
being interpreted as "use adaptive tuning with KVM's internal default",
and any other value being used as an explicit advancement time, e.g. a
time of '0' effectively disables advancement.
Note, this does not completely restore the original behavior of
lapic_timer_advance_ns. Prior to tracking the advancement per vCPU,
which is necessary to support autotuning, userspace could adjust
lapic_timer_advance_ns for *running* vCPU. With per-vCPU tracking, the
module params are snapshotted at vCPU creation, i.e. applying a new
advancement effectively requires restarting a VM.
Dynamically updating a running vCPU is possible, e.g. a helper could be
added to retrieve the desired delay, choosing between the global module
param and the per-VCPU value depending on whether or not auto-tuning is
(globally) enabled, but introduces a great deal of complexity. The
wrapper itself is not complex, but understanding and documenting the
effects of dynamically toggling auto-tuning and/or adjusting the timer
advancement is nigh impossible since the behavior would be dependent on
KVM's implementation as well as compiler optimizations. In other words,
providing stable behavior would require extremely careful consideration
now and in the future.
Given that the expected use of a manually-tuned timer advancement is to
"tune once, run many", use the vastly simpler approach of recognizing
changes to the module params only when creating a new vCPU.
Cc: Liran Alon <liran.alon@oracle.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Cc: stable@vger.kernel.org
Fixes: 3b8a5df6c4dc6 ("KVM: LAPIC: Tune lapic_timer_advance_ns automatically")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Automatically adjusting the globally-shared timer advancement could
corrupt the timer, e.g. if multiple vCPUs are concurrently adjusting
the advancement value. That could be partially fixed by using a local
variable for the arithmetic, but it would still be susceptible to a
race when setting timer_advance_adjust_done.
And because virtual_tsc_khz and tsc_scaling_ratio are per-vCPU, the
correct calibration for a given vCPU may not apply to all vCPUs.
Furthermore, lapic_timer_advance_ns is marked __read_mostly, which is
effectively violated when finding a stable advancement takes an extended
amount of timer.
Opportunistically change the definition of lapic_timer_advance_ns to
a u32 so that it matches the style of struct kvm_timer. Explicitly
pass the param to kvm_create_lapic() so that it doesn't have to be
exposed to lapic.c, thus reducing the probability of unintentionally
using the global value instead of the per-vCPU value.
Cc: Liran Alon <liran.alon@oracle.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Cc: stable@vger.kernel.org
Fixes: 3b8a5df6c4dc6 ("KVM: LAPIC: Tune lapic_timer_advance_ns automatically")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
To minimize the latency of timer interrupts as observed by the guest,
KVM adjusts the values it programs into the host timers to account for
the host's overhead of programming and handling the timer event. Now
that the timer advancement is automatically tuned during runtime, it's
effectively unbounded by default, e.g. if KVM is running as L1 the
advancement can measure in hundreds of milliseconds.
Disable timer advancement if adaptive tuning yields an advancement of
more than 5000ns, as large advancements can break reasonable assumptions
of the guest, e.g. that a timer configured to fire after 1ms won't
arrive on the next instruction. Although KVM busy waits to mitigate the
case of a timer event arriving too early, complications can arise when
shifting the interrupt too far, e.g. kvm-unit-test's vmx.interrupt test
will fail when its "host" exits on interrupts as KVM may inject the INTR
before the guest executes STI+HLT. Arguably the unit test is "broken"
in the sense that delaying a timer interrupt by 1ms doesn't technically
guarantee the interrupt will arrive after STI+HLT, but it's a reasonable
assumption that KVM should support.
Furthermore, an unbounded advancement also effectively unbounds the time
spent busy waiting, e.g. if the guest programs a timer with a very large
delay.
5000ns is a somewhat arbitrary threshold. When running on bare metal,
which is the intended use case, timer advancement is expected to be in
the general vicinity of 1000ns. 5000ns is high enough that false
positives are unlikely, while not being so high as to negatively affect
the host's performance/stability.
Note, a future patch will enable userspace to disable KVM's adaptive
tuning, which will allow priveleged userspace will to specifying an
advancement value in excess of this arbitrary threshold in order to
satisfy an abnormal use case.
Cc: Liran Alon <liran.alon@oracle.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Cc: stable@vger.kernel.org
Fixes: 3b8a5df6c4dc6 ("KVM: LAPIC: Tune lapic_timer_advance_ns automatically")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
If guest sets MSR_IA32_TSCDEADLINE to value such that in host
time-domain it's shorter than lapic_timer_advance_ns, we can
reach a case that we call hrtimer_start() with expiration time set at
the past.
Because lapic_timer.timer is init with HRTIMER_MODE_ABS_PINNED, it
is not allowed to run in softirq and therefore will never expire.
To avoid such a scenario, verify that deadline expiration time is set on
host time-domain further than (now + lapic_timer_advance_ns).
A future patch can also consider adding a min_timer_deadline_ns module parameter,
similar to min_timer_period_us to avoid races that amount of ns it takes
to run logic could still call hrtimer_start() with expiration timer set
at the past.
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
These were found with smatch, and then generalized when applicable.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
There are many KVM kernel memory allocations which are tied to the life of
the VM process and should be charged to the VM process's cgroup. If the
allocations aren't tied to the process, the OOM killer will not know
that killing the process will free the associated kernel memory.
Add __GFP_ACCOUNT flags to many of the allocations which are not yet being
charged to the VM process's cgroup.
Tested:
Ran all kvm-unit-tests on a 64 bit Haswell machine, the patch
introduced no new failures.
Ran a kernel memory accounting test which creates a VM to touch
memory and then checks that the kernel memory allocated for the
process is within certain bounds.
With this patch we account for much more of the vmalloc and slab memory
allocated for the VM.
There remain a few allocations which should be charged to the VM's
cgroup but are not. In x86, they include:
vcpu->arch.pio_data
There allocations are unaccounted in this patch because they are mapped
to userspace, and accounting them to a cgroup causes problems. This
should be addressed in a future patch.
Signed-off-by: Ben Gardon <bgardon@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
In preparation to enabling -Wimplicit-fallthrough, mark switch
cases where we are expecting to fall through.
This patch fixes the following warnings:
arch/x86/kvm/lapic.c:1037:27: warning: this statement may fall through [-Wimplicit-fallthrough=]
arch/x86/kvm/lapic.c:1876:3: warning: this statement may fall through [-Wimplicit-fallthrough=]
arch/x86/kvm/hyperv.c:1637:6: warning: this statement may fall through [-Wimplicit-fallthrough=]
arch/x86/kvm/svm.c:4396:6: warning: this statement may fall through [-Wimplicit-fallthrough=]
arch/x86/kvm/mmu.c:4372:36: warning: this statement may fall through [-Wimplicit-fallthrough=]
arch/x86/kvm/x86.c:3835:6: warning: this statement may fall through [-Wimplicit-fallthrough=]
arch/x86/kvm/x86.c:7938:23: warning: this statement may fall through [-Wimplicit-fallthrough=]
arch/x86/kvm/vmx/vmx.c:2015:6: warning: this statement may fall through [-Wimplicit-fallthrough=]
arch/x86/kvm/vmx/vmx.c:1773:6: warning: this statement may fall through [-Wimplicit-fallthrough=]
Warning level 3 was used: -Wimplicit-fallthrough=3
This patch is part of the ongoing efforts to enabling -Wimplicit-fallthrough.
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
In the previous code, the variable apic_sw_disabled influences
recalculate_apic_map. But in "KVM: x86: simplify kvm_apic_map"
(commit: 3b5a5ffa928a3f875b0d5dd284eeb7c322e1688a),
the access to apic_sw_disabled in recalculate_apic_map has been
deleted.
Signed-off-by: Peng Hao <peng.hao2@zte.com.cn>
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
We get the following warnings about empty statements when building
with 'W=1':
arch/x86/kvm/lapic.c:632:53: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body]
arch/x86/kvm/lapic.c:1907:42: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body]
arch/x86/kvm/lapic.c:1936:65: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body]
arch/x86/kvm/lapic.c:1975:44: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body]
Rework the debug helper macro to get rid of these warnings.
Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Reported by syzkaller:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000014
PGD 800000040410c067 P4D 800000040410c067 PUD 40410d067 PMD 0
Oops: 0000 [#1] PREEMPT SMP PTI
CPU: 3 PID: 2567 Comm: poc Tainted: G OE 4.19.0-rc5 #16
RIP: 0010:kvm_pv_send_ipi+0x94/0x350 [kvm]
Call Trace:
kvm_emulate_hypercall+0x3cc/0x700 [kvm]
handle_vmcall+0xe/0x10 [kvm_intel]
vmx_handle_exit+0xc1/0x11b0 [kvm_intel]
vcpu_enter_guest+0x9fb/0x1910 [kvm]
kvm_arch_vcpu_ioctl_run+0x35c/0x610 [kvm]
kvm_vcpu_ioctl+0x3e9/0x6d0 [kvm]
do_vfs_ioctl+0xa5/0x690
ksys_ioctl+0x6d/0x80
__x64_sys_ioctl+0x1a/0x20
do_syscall_64+0x83/0x6e0
entry_SYSCALL_64_after_hwframe+0x49/0xbe
The reason is that the apic map has not yet been initialized, the testcase
triggers pv_send_ipi interface by vmcall which results in kvm->arch.apic_map
is dereferenced. This patch fixes it by checking whether or not apic map is
NULL and bailing out immediately if that is the case.
Fixes: 4180bf1b65 (KVM: X86: Implement "send IPI" hypercall)
Reported-by: Wei Wu <ww9210@gmail.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Wei Wu <ww9210@gmail.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
"sizeof(x)" is the canonical coding style used in arch/x86 most of the time.
Fix the few places that didn't follow the convention.
(Also do some whitespace cleanups in a few places while at it.)
[ mingo: Rewrote the changelog. ]
Signed-off-by: Jordan Borgner <mail@jordan-borgner.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20181028125828.7rgammkgzep2wpam@JordanDesktop
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
vcpu->arch.pv_eoi is accessible through both HV_X64_MSR_VP_ASSIST_PAGE and
MSR_KVM_PV_EOI_EN so on migration userspace may try to restore them in any
order. Values match, however, kvm_lapic_enable_pv_eoi() uses different
length: for Hyper-V case it's the whole struct hv_vp_assist_page, for KVM
native case it is 8. In case we restore KVM-native MSR last cache will
be reinitialized with len=8 so trying to access VP assist page beyond
8 bytes with kvm_read_guest_cached() will fail.
Check if we re-initializing cache for the same address and preserve length
in case it was greater.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The state related to the VP assist page is still managed by the LAPIC
code in the pv_eoi field.
Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
If kvm_apic_map_get_dest_lapic() finds a disabled LAPIC,
it will return with bitmap==0 and (*r == -1) will be returned to
userspace.
QEMU may then record "KVM: injection failed, MSI lost
(Operation not permitted)" in its log, which is quite puzzling.
Reported-by: Peng Hao <penghao122@sina.com.cn>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
In cloud environment, lapic_timer_advance_ns is needed to be tuned for every CPU
generations, and every host kernel versions(the kvm-unit-tests/tscdeadline_latency.flat
is 5700 cycles for upstream kernel and 9600 cycles for our 3.10 product kernel,
both preemption_timer=N, Skylake server).
This patch adds the capability to automatically tune lapic_timer_advance_ns
step by step, the initial value is 1000ns as 'commit d0659d946be0 ("KVM: x86:
add option to advance tscdeadline hrtimer expiration")' recommended, it will be
reduced when it is too early, and increased when it is too late. The guest_tsc
and tsc_deadline are hard to equal, so we assume we are done when the delta
is within a small scope e.g. 100 cycles. This patch reduces latency
(kvm-unit-tests/tscdeadline_latency, busy waits, preemption_timer enabled)
from ~2600 cyles to ~1200 cyles on our Skylake server.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When VMX is used with flexpriority disabled (because of no support or
if disabled with module parameter) MMIO interface to lAPIC is still
available in x2APIC mode while it shouldn't be (kvm-unit-tests):
PASS: apic_disable: Local apic enabled in x2APIC mode
PASS: apic_disable: CPUID.1H:EDX.APIC[bit 9] is set
FAIL: apic_disable: *0xfee00030: 50014
The issue appears because we basically do nothing while switching to
x2APIC mode when APIC access page is not used. apic_mmio_{read,write}
only check if lAPIC is disabled before proceeding to actual write.
When APIC access is virtualized we correctly manipulate with VMX controls
in vmx_set_virtual_apic_mode() and we don't get vmexits from memory writes
in x2APIC mode so there's no issue.
Disabling MMIO interface seems to be easy. The question is: what do we
do with these reads and writes? If we add apic_x2apic_mode() check to
apic_mmio_in_range() and return -EOPNOTSUPP these reads and writes will
go to userspace. When lAPIC is in kernel, Qemu uses this interface to
inject MSIs only (see kvm_apic_mem_write() in hw/i386/kvm/apic.c). This
somehow works with disabled lAPIC but when we're in xAPIC mode we will
get a real injected MSI from every write to lAPIC. Not good.
The simplest solution seems to be to just ignore writes to the region
and return ~0 for all reads when we're in x2APIC mode. This is what this
patch does. However, this approach is inconsistent with what currently
happens when flexpriority is enabled: we allocate APIC access page and
create KVM memory region so in x2APIC modes all reads and writes go to
this pre-allocated page which is, btw, the same for all vCPUs.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Dan Carpenter reported that the untrusted data returns from kvm_register_read()
results in the following static checker warning:
arch/x86/kvm/lapic.c:576 kvm_pv_send_ipi()
error: buffer underflow 'map->phys_map' 's32min-s32max'
KVM guest can easily trigger this by executing the following assembly sequence
in Ring0:
mov $10, %rax
mov $0xFFFFFFFF, %rbx
mov $0xFFFFFFFF, %rdx
mov $0, %rsi
vmcall
As this will cause KVM to execute the following code-path:
vmx_handle_exit() -> handle_vmcall() -> kvm_emulate_hypercall() -> kvm_pv_send_ipi()
which will reach out-of-bounds access.
This patch fixes it by adding a check to kvm_pv_send_ipi() against map->max_apic_id,
ignoring destinations that are not present and delivering the rest. We also check
whether or not map->phys_map[min + i] is NULL since the max_apic_id is set to the
max apic id, some phys_map maybe NULL when apic id is sparse, especially kvm
unconditionally set max_apic_id to 255 to reserve enough space for any xAPIC ID.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
[Add second "if (min > map->max_apic_id)" to complete the fix. -Radim]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
Pull first set of KVM updates from Paolo Bonzini:
"PPC:
- minor code cleanups
x86:
- PCID emulation and CR3 caching for shadow page tables
- nested VMX live migration
- nested VMCS shadowing
- optimized IPI hypercall
- some optimizations
ARM will come next week"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (85 commits)
kvm: x86: Set highest physical address bits in non-present/reserved SPTEs
KVM/x86: Use CC_SET()/CC_OUT in arch/x86/kvm/vmx.c
KVM: X86: Implement PV IPIs in linux guest
KVM: X86: Add kvm hypervisor init time platform setup callback
KVM: X86: Implement "send IPI" hypercall
KVM/x86: Move X86_CR4_OSXSAVE check into kvm_valid_sregs()
KVM: x86: Skip pae_root shadow allocation if tdp enabled
KVM/MMU: Combine flushing remote tlb in mmu_set_spte()
KVM: vmx: skip VMWRITE of HOST_{FS,GS}_BASE when possible
KVM: vmx: skip VMWRITE of HOST_{FS,GS}_SEL when possible
KVM: vmx: always initialize HOST_{FS,GS}_BASE to zero during setup
KVM: vmx: move struct host_state usage to struct loaded_vmcs
KVM: vmx: compute need to reload FS/GS/LDT on demand
KVM: nVMX: remove a misleading comment regarding vmcs02 fields
KVM: vmx: rename __vmx_load_host_state() and vmx_save_host_state()
KVM: vmx: add dedicated utility to access guest's kernel_gs_base
KVM: vmx: track host_state.loaded using a loaded_vmcs pointer
KVM: vmx: refactor segmentation code in vmx_save_host_state()
kvm: nVMX: Fix fault priority for VMX operations
kvm: nVMX: Fix fault vector for VMX operation at CPL > 0
...
|
|
Using hypercall to send IPIs by one vmexit instead of one by one for
xAPIC/x2APIC physical mode and one vmexit per-cluster for x2APIC cluster
mode. Intel guest can enter x2apic cluster mode when interrupt remmaping
is enabled in qemu, however, latest AMD EPYC still just supports xapic
mode which can get great improvement by Exit-less IPIs. This patchset
lets a guest send multicast IPIs, with at most 128 destinations per
hypercall in 64-bit mode and 64 vCPUs per hypercall in 32-bit mode.
Hardware: Xeon Skylake 2.5GHz, 2 sockets, 40 cores, 80 threads, the VM
is 80 vCPUs, IPI microbenchmark(https://lkml.org/lkml/2017/12/19/141):
x2apic cluster mode, vanilla
Dry-run: 0, 2392199 ns
Self-IPI: 6907514, 15027589 ns
Normal IPI: 223910476, 251301666 ns
Broadcast IPI: 0, 9282161150 ns
Broadcast lock: 0, 8812934104 ns
x2apic cluster mode, pv-ipi
Dry-run: 0, 2449341 ns
Self-IPI: 6720360, 15028732 ns
Normal IPI: 228643307, 255708477 ns
Broadcast IPI: 0, 7572293590 ns => 22% performance boost
Broadcast lock: 0, 8316124651 ns
x2apic physical mode, vanilla
Dry-run: 0, 3135933 ns
Self-IPI: 8572670, 17901757 ns
Normal IPI: 226444334, 255421709 ns
Broadcast IPI: 0, 19845070887 ns
Broadcast lock: 0, 19827383656 ns
x2apic physical mode, pv-ipi
Dry-run: 0, 2446381 ns
Self-IPI: 6788217, 15021056 ns
Normal IPI: 219454441, 249583458 ns
Broadcast IPI: 0, 7806540019 ns => 154% performance boost
Broadcast lock: 0, 9143618799 ns
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Since swait basically implemented exclusive waits only, make sure
the API reflects that.
$ git grep -l -e "\<swake_up\>"
-e "\<swait_event[^ (]*"
-e "\<prepare_to_swait\>" | while read file;
do
sed -i -e 's/\<swake_up\>/&_one/g'
-e 's/\<swait_event[^ (]*/&_exclusive/g'
-e 's/\<prepare_to_swait\>/&_exclusive/g' $file;
done
With a few manual touch-ups.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: bigeasy@linutronix.de
Cc: oleg@redhat.com
Cc: paulmck@linux.vnet.ibm.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180612083909.261946548@infradead.org
|
|
Pull KVM updates from Paolo Bonzini:
"Small update for KVM:
ARM:
- lazy context-switching of FPSIMD registers on arm64
- "split" regions for vGIC redistributor
s390:
- cleanups for nested
- clock handling
- crypto
- storage keys
- control register bits
x86:
- many bugfixes
- implement more Hyper-V super powers
- implement lapic_timer_advance_ns even when the LAPIC timer is
emulated using the processor's VMX preemption timer.
- two security-related bugfixes at the top of the branch"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (79 commits)
kvm: fix typo in flag name
kvm: x86: use correct privilege level for sgdt/sidt/fxsave/fxrstor access
KVM: x86: pass kvm_vcpu to kvm_read_guest_virt and kvm_write_guest_virt_system
KVM: x86: introduce linear_{read,write}_system
kvm: nVMX: Enforce cpl=0 for VMX instructions
kvm: nVMX: Add support for "VMWRITE to any supported field"
kvm: nVMX: Restrict VMX capability MSR changes
KVM: VMX: Optimize tscdeadline timer latency
KVM: docs: nVMX: Remove known limitations as they do not exist now
KVM: docs: mmu: KVM support exposing SLAT to guests
kvm: no need to check return value of debugfs_create functions
kvm: Make VM ioctl do valloc for some archs
kvm: Change return type to vm_fault_t
KVM: docs: mmu: Fix link to NPT presentation from KVM Forum 2008
kvm: x86: Amend the KVM_GET_SUPPORTED_CPUID API documentation
KVM: x86: hyperv: declare KVM_CAP_HYPERV_TLBFLUSH capability
KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}_EX implementation
KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} implementation
KVM: introduce kvm_make_vcpus_request_mask() API
KVM: x86: hyperv: do rep check for each hypercall separately
...
|
|
Since 4.10, commit 8003c9ae204e (KVM: LAPIC: add APIC Timer
periodic/oneshot mode VMX preemption timer support), guests using
periodic LAPIC timers (such as FreeBSD 8.4) would see their timers
drift significantly over time.
Differences in the underlying clocks and numerical errors means the
periods of the two timers (hv and sw) are not the same. This
difference will accumulate with every expiry resulting in a large
error between the hv and sw timer.
This means the sw timer may be running slow when compared to the hv
timer. When the timer is switched from hv to sw, the now active sw
timer will expire late. The guest VCPU is reentered and it switches to
using the hv timer. This timer catches up, injecting multiple IRQs
into the guest (of which the guest only sees one as it does not get to
run until the hv timer has caught up) and thus the guest's timer rate
is low (and becomes increasing slower over time as the sw timer lags
further and further behind).
I believe a similar problem would occur if the hv timer is the slower
one, but I have not observed this.
Fix this by synchronizing the deadlines for both timers to the same
time source on every tick. This prevents the errors from accumulating.
Fixes: 8003c9ae204e21204e49816c5ea629357e283b06
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: David Vrabel <david.vrabel@nutanix.com>
Cc: stable@vger.kernel.org
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
Previously, we toggled between SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE
and SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES, depending on whether or
not the EXTD bit was set in MSR_IA32_APICBASE. However, if the local
APIC is disabled, we should not set either of these APIC
virtualization control bits.
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Since the commit "8003c9ae204e: add APIC Timer periodic/oneshot mode VMX
preemption timer support", a Windows 10 guest has some erratic timer
spikes.
Here the results on a 150000 times 1ms timer without any load:
Before 8003c9ae204e | After 8003c9ae204e
Max 1834us | 86000us
Mean 1100us | 1021us
Deviation 59us | 149us
Here the results on a 150000 times 1ms timer with a cpu-z stress test:
Before 8003c9ae204e | After 8003c9ae204e
Max 32000us | 140000us
Mean 1006us | 1997us
Deviation 140us | 11095us
The root cause of the problem is starting hrtimer with an expiry time
already in the past can take more than 20 milliseconds to trigger the
timer function. It can be solved by forward such past timers
immediately, rather than submitting them to hrtimer_start().
In case the timer is periodic, update the target expiration and call
hrtimer_start with it.
v2: Check if the tsc deadline is already expired. Thank you Mika.
v3: Execute the past timers immediately rather than submitting them to
hrtimer_start().
v4: Rearm the periodic timer with advance_periodic_target_expiration() a
simpler version of set_target_expiration(). Thank you Paolo.
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Wanpeng Li <kernellwp@gmail.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Anthoine Bourgeois <anthoine.bourgeois@blade-group.com>
8003c9ae204e ("KVM: LAPIC: add APIC Timer periodic/oneshot mode VMX preemption timer support")
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
Devices which use level-triggered interrupts under Windows 2016 with
Hyper-V role enabled don't work: Windows disables EOI broadcast in SPIV
unconditionally. Our in-kernel IOAPIC implementation emulates an old IOAPIC
version which has no EOI register so EOI never happens.
The issue was discovered and discussed a while ago:
https://www.spinics.net/lists/kvm/msg148098.html
While this is a guest OS bug (it should check that IOAPIC has the required
capabilities before disabling EOI broadcast) we can workaround it in KVM:
advertising DIRECTED_EOI with in-kernel IOAPIC makes little sense anyway.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
Moving the code around broke this rare configuration.
Use this opportunity to finally call lapic reset from vcpu reset.
Reported-by: syzbot+fb7a33a4b6c35007a72b@syzkaller.appspotmail.com
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Fixes: 0b2e9904c159 ("KVM: x86: move LAPIC initialization after VMCS creation")
Cc: stable@vger.kernel.org
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
The initial reset of the local APIC is performed before the VMCS has been
created, but it tries to do a vmwrite:
vmwrite error: reg 810 value 4a00 (err 18944)
CPU: 54 PID: 38652 Comm: qemu-kvm Tainted: G W I 4.16.0-0.rc2.git0.1.fc28.x86_64 #1
Hardware name: Intel Corporation S2600CW/S2600CW, BIOS SE5C610.86B.01.01.0003.090520141303 09/05/2014
Call Trace:
vmx_set_rvi [kvm_intel]
vmx_hwapic_irr_update [kvm_intel]
kvm_lapic_reset [kvm]
kvm_create_lapic [kvm]
kvm_arch_vcpu_init [kvm]
kvm_vcpu_init [kvm]
vmx_create_vcpu [kvm_intel]
kvm_vm_ioctl [kvm]
Move it later, after the VMCS has been created.
Fixes: 4191db26b714 ("KVM: x86: Update APICv on APIC reset")
Cc: stable@vger.kernel.org
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This commit doesn't change semantics.
It is done as a preparation for future commits.
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Reviewed-by: Nikita Leshenko <nikita.leshchenko@oracle.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Signed-off-by: Liam Merwick <liam.merwick@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
sync_pir_to_irr() is only called if vcpu->arch.apicv_active()==true.
In case it is false, VMX code make sure to set sync_pir_to_irr
to NULL.
Therefore, having SVM stubs allows to remove check for if
sync_pir_to_irr != NULL from all calling sites.
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Nikita Leshenko <nikita.leshchenko@oracle.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
[Return highest IRR in the SVM case. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
In x2apic mode the LDR is fixed based on the ID rather
than separately loadable like it was before x2.
When kvm_apic_set_state is called, the base is set, and if
it has the X2APIC_ENABLE flag set then the LDR is calculated;
however that value gets overwritten by the memcpy a few lines
below overwriting it with the value that came from userland.
The symptom is a lack of EOI after loading the state
(e.g. after a QEMU migration) and is due to the EOI bitmap
being wrong due to the incorrect LDR. This was seen with
a Win2016 guest under Qemu with irqchip=split whose USB mouse
didn't work after a VM migration.
This corresponds to RH bug:
https://bugzilla.redhat.com/show_bug.cgi?id=1502591
Reported-by: Yiqian Wei <yiwei@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: stable@vger.kernel.org
[Applied fixup from Liran Alon. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Split out the ldr calculation from kvm_apic_set_x2apic_id
since we're about to reuse it in the following patch.
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Pull KVM updates from Radim Krčmář:
"First batch of KVM changes for 4.15
Common:
- Python 3 support in kvm_stat
- Accounting of slabs to kmemcg
ARM:
- Optimized arch timer handling for KVM/ARM
- Improvements to the VGIC ITS code and introduction of an ITS reset
ioctl
- Unification of the 32-bit fault injection logic
- More exact external abort matching logic
PPC:
- Support for running hashed page table (HPT) MMU mode on a host that
is using the radix MMU mode; single threaded mode on POWER 9 is
added as a pre-requisite
- Resolution of merge conflicts with the last second 4.14 HPT fixes
- Fixes and cleanups
s390:
- Some initial preparation patches for exitless interrupts and crypto
- New capability for AIS migration
- Fixes
x86:
- Improved emulation of LAPIC timer mode changes, MCi_STATUS MSRs,
and after-reset state
- Refined dependencies for VMX features
- Fixes for nested SMI injection
- A lot of cleanups"
* tag 'kvm-4.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (89 commits)
KVM: s390: provide a capability for AIS state migration
KVM: s390: clear_io_irq() requests are not expected for adapter interrupts
KVM: s390: abstract conversion between isc and enum irq_types
KVM: s390: vsie: use common code functions for pinning
KVM: s390: SIE considerations for AP Queue virtualization
KVM: s390: document memory ordering for kvm_s390_vcpu_wakeup
KVM: PPC: Book3S HV: Cosmetic post-merge cleanups
KVM: arm/arm64: fix the incompatible matching for external abort
KVM: arm/arm64: Unify 32bit fault injection
KVM: arm/arm64: vgic-its: Implement KVM_DEV_ARM_ITS_CTRL_RESET
KVM: arm/arm64: Document KVM_DEV_ARM_ITS_CTRL_RESET
KVM: arm/arm64: vgic-its: Free caches when GITS_BASER Valid bit is cleared
KVM: arm/arm64: vgic-its: New helper functions to free the caches
KVM: arm/arm64: vgic-its: Remove kvm_its_unmap_device
arm/arm64: KVM: Load the timer state when enabling the timer
KVM: arm/arm64: Rework kvm_timer_should_fire
KVM: arm/arm64: Get rid of kvm_timer_flush_hwstate
KVM: arm/arm64: Avoid phys timer emulation in vcpu entry/exit
KVM: arm/arm64: Move phys_timer_emulate function
KVM: arm/arm64: Use kvm_arm_timer_set/get_reg for guest register traps
...
|
|
In kvm_apic_set_state() we update the hardware virtualized APIC after
the full APIC state has been overwritten. Do the same, when the full
APIC state has been reset in kvm_lapic_reset().
This updates some hardware state that was previously forgotten, as
far as I can tell. Also, this allows removing some APIC-related reset
code from vmx_vcpu_reset().
Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Our routines look at tscdeadline and period when deciding state of a
timer. The timer is disarmed when switching between TSC deadline and
other modes, so we should set everything to disarmed state.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
preemption timer only looks at tscdeadline and could inject already
disarmed timer.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
0 should disable the timer, but start_hv_timer will recognize it as an
expired timer instead.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The description in the Intel SDM of how the divide configuration
register is used: "The APIC timer frequency will be the processor's bus
clock or core crystal clock frequency divided by the value specified in
the divide configuration register."
Observation of baremetal shown that when the TDCR is change, the TMCCT
does not change or make a big jump in value, but the rate at which it
count down change.
The patch update the emulation to APIC timer to so that a change to the
divide configuration would be reflected in the value of the counter and
when the next interrupt is triggered.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[Fixed some whitespace and added a check for negative delta and running
timer. - Radim]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
If we take TSC-deadline mode timer out of the picture, the Intel SDM
does not say that the timer is disable when the timer mode is change,
either from one-shot to periodic or vice versa.
After this patch, the timer is no longer disarmed on change of mode, so
the counter (TMCCT) keeps counting down.
So what does a write to LVTT changes ? On baremetal, the change of mode
is probably taken into account only when the counter reach 0. When this
happen, LVTT is use to figure out if the counter should restard counting
down from TMICT (so periodic mode) or stop counting (if one-shot mode).
This patch is based on observation of the behavior of the APIC timer on
baremetal as well as check that they does not go against the description
written in the Intel SDM.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[Fixed rate limiting of periodic timer.]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
Extract the logic of limit lapic periodic timer frequency to a new function,
this function will be used by later patches.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
SDM 10.5.4.1 TSC-Deadline Mode mentioned that "Transitioning between TSC-Deadline
mode and other timer modes also disarms the timer". So the APIC Timer Initial Count
Register for one-shot/periodic mode should be reset. This patch do it.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[Removed unnecessary definition of APIC_LVT_TIMER_MASK.]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
|
|
A comment might serve future readers.
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
It has been experimentally confirmed that supporting these two MSRs is one
of the necessary conditions for nested Hyper-V to use the TSC page. Modern
Windows guests are noticeably slower when they fall back to reading
timestamps from the HV_X64_MSR_TIME_REF_COUNT MSR instead of using the TSC
page.
The newly supported MSRs are advertised with the AccessFrequencyRegs
partition privilege flag and CPUID.40000003H:EDX[8] "Support for
determining timer frequencies is available" (both outside of the scope of
this KVM patch).
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Preempt can occur in the preemption timer expiration handler:
CPU0 CPU1
preemption timer vmexit
handle_preemption_timer(vCPU0)
kvm_lapic_expired_hv_timer
hv_timer_is_use == true
sched_out
sched_in
kvm_arch_vcpu_load
kvm_lapic_restart_hv_timer
restart_apic_timer
start_hv_timer
already-expired timer or sw timer triggerd in the window
start_sw_timer
cancel_hv_timer
/* back in kvm_lapic_expired_hv_timer */
cancel_hv_timer
WARN_ON(!apic->lapic_timer.hv_timer_in_use); ==> Oops
This can be reproduced if CONFIG_PREEMPT is enabled.
------------[ cut here ]------------
WARNING: CPU: 4 PID: 2972 at /home/kernel/linux/arch/x86/kvm//lapic.c:1563 kvm_lapic_expired_hv_timer+0x9e/0xb0 [kvm]
CPU: 4 PID: 2972 Comm: qemu-system-x86 Tainted: G OE 4.13.0-rc2+ #16
RIP: 0010:kvm_lapic_expired_hv_timer+0x9e/0xb0 [kvm]
Call Trace:
handle_preemption_timer+0xe/0x20 [kvm_intel]
vmx_handle_exit+0xb8/0xd70 [kvm_intel]
kvm_arch_vcpu_ioctl_run+0xdd1/0x1be0 [kvm]
? kvm_arch_vcpu_load+0x47/0x230 [kvm]
? kvm_arch_vcpu_load+0x62/0x230 [kvm]
kvm_vcpu_ioctl+0x340/0x700 [kvm]
? kvm_vcpu_ioctl+0x340/0x700 [kvm]
? __fget+0xfc/0x210
do_vfs_ioctl+0xa4/0x6a0
? __fget+0x11d/0x210
SyS_ioctl+0x79/0x90
do_syscall_64+0x81/0x220
entry_SYSCALL64_slow_path+0x25/0x25
------------[ cut here ]------------
WARNING: CPU: 4 PID: 2972 at /home/kernel/linux/arch/x86/kvm//lapic.c:1498 cancel_hv_timer.isra.40+0x4f/0x60 [kvm]
CPU: 4 PID: 2972 Comm: qemu-system-x86 Tainted: G W OE 4.13.0-rc2+ #16
RIP: 0010:cancel_hv_timer.isra.40+0x4f/0x60 [kvm]
Call Trace:
kvm_lapic_expired_hv_timer+0x3e/0xb0 [kvm]
handle_preemption_timer+0xe/0x20 [kvm_intel]
vmx_handle_exit+0xb8/0xd70 [kvm_intel]
kvm_arch_vcpu_ioctl_run+0xdd1/0x1be0 [kvm]
? kvm_arch_vcpu_load+0x47/0x230 [kvm]
? kvm_arch_vcpu_load+0x62/0x230 [kvm]
kvm_vcpu_ioctl+0x340/0x700 [kvm]
? kvm_vcpu_ioctl+0x340/0x700 [kvm]
? __fget+0xfc/0x210
do_vfs_ioctl+0xa4/0x6a0
? __fget+0x11d/0x210
SyS_ioctl+0x79/0x90
do_syscall_64+0x81/0x220
entry_SYSCALL64_slow_path+0x25/0x25
This patch fixes it by making the caller of cancel_hv_timer, start_hv_timer
and start_sw_timer be in preemption-disabled regions, which trivially
avoid any reentrancy issue with preempt notifier.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[Add more WARNs. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
If the TSC deadline timer is programmed really close to the deadline or
even in the past, the computation in vmx_set_hv_timer will program the
absolute target tsc value to vmcs preemption timer field w/ delta == 0,
then plays a vmentry and an upcoming vmx preemption timer fire vmexit
dance, the lapic timer injection is delayed due to this duration. Actually
the lapic timer which is emulated by hrtimer can handle this correctly.
This patch fixes it by firing the lapic timer and injecting a timer interrupt
immediately during the next vmentry if the TSC deadline timer is programmed
really close to the deadline or even in the past. This saves ~300 cycles on
the tsc_deadline_timer test of apic.flat.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Move the code to cancel the hv timer into the caller, just before
it starts the hrtimer. Check availability of the hv timer in
start_hv_timer.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
There are many cases in which the hv timer must be canceled. Split out
a new function to avoid duplication.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Intel SDM says, that at most one LAPIC should be configured with ExtINT
delivery. KVM configures all LAPICs this way. This causes pic_unlock()
to kick the first available vCPU from the internal KVM data structures.
If this vCPU is not the BSP, but some not-yet-booted AP, the BSP may
never realize that there is an interrupt.
Fix that by enabling ExtINT delivery only for the BSP.
This allows booting a Linux guest without a TSC in the above situation.
Otherwise the BSP gets stuck in calibrate_delay_converge().
Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>
Reviewed-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Preemption can occur during cancel preemption timer, and there will be
inconsistent status in lapic, vmx and vmcs field.
CPU0 CPU1
preemption timer vmexit
handle_preemption_timer(vCPU0)
kvm_lapic_expired_hv_timer
vmx_cancel_hv_timer
vmx->hv_deadline_tsc = -1
vmcs_clear_bits
/* hv_timer_in_use still true */
sched_out
sched_in
kvm_arch_vcpu_load
vmx_set_hv_timer
write vmx->hv_deadline_tsc
vmcs_set_bits
/* back in kvm_lapic_expired_hv_timer */
hv_timer_in_use = false
...
vmx_vcpu_run
vmx_arm_hv_run
write preemption timer deadline
spurious preemption timer vmexit
handle_preemption_timer(vCPU0)
kvm_lapic_expired_hv_timer
WARN_ON(!apic->lapic_timer.hv_timer_in_use);
This can be reproduced sporadically during boot of L2 on a
preemptible L1, causing a splat on L1.
WARNING: CPU: 3 PID: 1952 at arch/x86/kvm/lapic.c:1529 kvm_lapic_expired_hv_timer+0xb5/0xd0 [kvm]
CPU: 3 PID: 1952 Comm: qemu-system-x86 Not tainted 4.12.0-rc1+ #24 RIP: 0010:kvm_lapic_expired_hv_timer+0xb5/0xd0 [kvm]
Call Trace:
handle_preemption_timer+0xe/0x20 [kvm_intel]
vmx_handle_exit+0xc9/0x15f0 [kvm_intel]
? lock_acquire+0xdb/0x250
? lock_acquire+0xdb/0x250
? kvm_arch_vcpu_ioctl_run+0xdf3/0x1ce0 [kvm]
kvm_arch_vcpu_ioctl_run+0xe55/0x1ce0 [kvm]
kvm_vcpu_ioctl+0x384/0x7b0 [kvm]
? kvm_vcpu_ioctl+0x384/0x7b0 [kvm]
? __fget+0xf3/0x210
do_vfs_ioctl+0xa4/0x700
? __fget+0x114/0x210
SyS_ioctl+0x79/0x90
do_syscall_64+0x8f/0x750
? trace_hardirqs_on_thunk+0x1a/0x1c
entry_SYSCALL64_slow_path+0x25/0x25
This patch fixes it by disabling preemption while cancelling
preemption timer. This way cancel_hv_timer is atomic with
respect to kvm_arch_vcpu_load.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Merge more updates from Andrew Morton:
- the rest of MM
- various misc things
- procfs updates
- lib/ updates
- checkpatch updates
- kdump/kexec updates
- add kvmalloc helpers, use them
- time helper updates for Y2038 issues. We're almost ready to remove
current_fs_time() but that awaits a btrfs merge.
- add tracepoints to DAX
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (114 commits)
drivers/staging/ccree/ssi_hash.c: fix build with gcc-4.4.4
selftests/vm: add a test for virtual address range mapping
dax: add tracepoint to dax_insert_mapping()
dax: add tracepoint to dax_writeback_one()
dax: add tracepoints to dax_writeback_mapping_range()
dax: add tracepoints to dax_load_hole()
dax: add tracepoints to dax_pfn_mkwrite()
dax: add tracepoints to dax_iomap_pte_fault()
mtd: nand: nandsim: convert to memalloc_noreclaim_*()
treewide: convert PF_MEMALLOC manipulations to new helpers
mm: introduce memalloc_noreclaim_{save,restore}
mm: prevent potential recursive reclaim due to clearing PF_MEMALLOC
mm/huge_memory.c: deposit a pgtable for DAX PMD faults when required
mm/huge_memory.c: use zap_deposited_table() more
time: delete CURRENT_TIME_SEC and CURRENT_TIME
gfs2: replace CURRENT_TIME with current_time
apparmorfs: replace CURRENT_TIME with current_time()
lustre: replace CURRENT_TIME macro
fs: ubifs: replace CURRENT_TIME_SEC with current_time
fs: ufs: use ktime_get_real_ts64() for birthtime
...
|
