| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 25 Jun 2019 19:02:53 +0200
From: Paolo Bonzini <pbonzini@...hat.com>
To: Marcelo Tosatti <mtosatti@...hat.com>,
Wanpeng Li <kernellwp@...il.com>
Cc: LKML <linux-kernel@...r.kernel.org>, kvm <kvm@...r.kernel.org>,
Radim Krčmář <rkrcmar@...hat.com>
Subject: Re: [PATCH v4 2/5] KVM: LAPIC: inject lapic timer interrupt by posted
interrupt
On 21/06/19 23:42, Marcelo Tosatti wrote:
> On Fri, Jun 21, 2019 at 09:42:39AM +0800, Wanpeng Li wrote:
>> On Thu, 20 Jun 2019 at 05:04, Marcelo Tosatti <mtosatti@...hat.com> wrote:
>>>
>>> Hi Li,
>>>
>>> On Wed, Jun 19, 2019 at 08:36:06AM +0800, Wanpeng Li wrote:
>>>> On Tue, 18 Jun 2019 at 21:36, Marcelo Tosatti <mtosatti@...hat.com> wrote:
>>>>>
>>>>> On Mon, Jun 17, 2019 at 07:24:44PM +0800, Wanpeng Li wrote:
>>>>>> From: Wanpeng Li <wanpengli@...cent.com>
>>>>>>
>>>>>> Dedicated instances are currently disturbed by unnecessary jitter due
>>>>>> to the emulated lapic timers fire on the same pCPUs which vCPUs resident.
>>>>>> There is no hardware virtual timer on Intel for guest like ARM. Both
>>>>>> programming timer in guest and the emulated timer fires incur vmexits.
>>>>>> This patch tries to avoid vmexit which is incurred by the emulated
>>>>>> timer fires in dedicated instance scenario.
>>>>>>
>>>>>> When nohz_full is enabled in dedicated instances scenario, the emulated
>>>>>> timers can be offload to the nearest busy housekeeping cpus since APICv
>>>>>> is really common in recent years. The guest timer interrupt is injected
>>>>>> by posted-interrupt which is delivered by housekeeping cpu once the emulated
>>>>>> timer fires.
>>>>>>
>>>>>> The host admin should fine tuned, e.g. dedicated instances scenario w/
>>>>>> nohz_full cover the pCPUs which vCPUs resident, several pCPUs surplus
>>>>>> for busy housekeeping, disable mwait/hlt/pause vmexits to keep in non-root
>>>>>> mode, ~3% redis performance benefit can be observed on Skylake server.
>>>>>>
>>>>>> w/o patch:
>>>>>>
>>>>>> VM-EXIT Samples Samples% Time% Min Time Max Time Avg time
>>>>>>
>>>>>> EXTERNAL_INTERRUPT 42916 49.43% 39.30% 0.47us 106.09us 0.71us ( +- 1.09% )
>>>>>>
>>>>>> w/ patch:
>>>>>>
>>>>>> VM-EXIT Samples Samples% Time% Min Time Max Time Avg time
>>>>>>
>>>>>> EXTERNAL_INTERRUPT 6871 9.29% 2.96% 0.44us 57.88us 0.72us ( +- 4.02% )
>>>>>>
>>>>>> Cc: Paolo Bonzini <pbonzini@...hat.com>
>>>>>> Cc: Radim Krčmář <rkrcmar@...hat.com>
>>>>>> Cc: Marcelo Tosatti <mtosatti@...hat.com>
>>>>>> Signed-off-by: Wanpeng Li <wanpengli@...cent.com>
>>>>>> ---
>>>>>> arch/x86/kvm/lapic.c | 33 ++++++++++++++++++++++++++-------
>>>>>> arch/x86/kvm/lapic.h | 1 +
>>>>>> arch/x86/kvm/vmx/vmx.c | 3 ++-
>>>>>> arch/x86/kvm/x86.c | 5 +++++
>>>>>> arch/x86/kvm/x86.h | 2 ++
>>>>>> include/linux/sched/isolation.h | 2 ++
>>>>>> kernel/sched/isolation.c | 6 ++++++
>>>>>> 7 files changed, 44 insertions(+), 8 deletions(-)
>>>>>>
>>>>>> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
>>>>>> index 87ecb56..9ceeee5 100644
>>>>>> --- a/arch/x86/kvm/lapic.c
>>>>>> +++ b/arch/x86/kvm/lapic.c
>>>>>> @@ -122,6 +122,13 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
>>>>>> return apic->vcpu->vcpu_id;
>>>>>> }
>>>>>>
>>>>>> +bool posted_interrupt_inject_timer(struct kvm_vcpu *vcpu)
>>>>>> +{
>>>>>> + return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) &&
>>>>>> + kvm_hlt_in_guest(vcpu->kvm);
>>>>>> +}
>>>>>> +EXPORT_SYMBOL_GPL(posted_interrupt_inject_timer);
>>>>>
>>>>> Paolo, can you explain the reasoning behind this?
>>>>>
>>>>> Should not be necessary...
>>
>> https://lkml.org/lkml/2019/6/5/436 "Here you need to check
>> kvm_halt_in_guest, not kvm_mwait_in_guest, because you need to go
>> through kvm_apic_expired if the guest needs to be woken up from
>> kvm_vcpu_block."
>
> Ah, i think he means that a sleeping vcpu (in kvm_vcpu_block) must
> be woken up, if it receives a timer interrupt.
Yes, this is true.
Paolo
> But your patch will go through:
>
> kvm_apic_inject_pending_timer_irqs
> __apic_accept_irq ->
> vmx_deliver_posted_interrupt ->
> kvm_vcpu_trigger_posted_interrupt returns false
> (because vcpu->mode != IN_GUEST_MODE) ->
> kvm_vcpu_kick
>
> Which will wakeup the vcpu.
>
> Apart from this oops, which triggers when running:
> taskset -c 1 ./cyclictest -D 3600 -p 99 -t 1 -h 30 -m -n -i 50000 -b 40
>
> Timer interruption from housekeeping vcpus is normal to me
> (without requiring kvm_hlt_in_guest).
>
> [ 1145.849646] BUG: kernel NULL pointer dereference, address:
> 0000000000000000
> [ 1145.850481] #PF: supervisor instruction fetch in kernel mode
> [ 1145.851161] #PF: error_code(0x0010) - not-present page
> [ 1145.851772] PGD 80000002a9fa5067 P4D 80000002a9fa5067 PUD 2abcbb067
> PMD 0
> [ 1145.852578] Oops: 0010 [#1] PREEMPT SMP PTI
> [ 1145.853066] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.2.0-rc1+ #11
> [ 1145.853809] Hardware name: Red Hat KVM, BIOS 1.11.0-2.el7 04/01/2014
> [ 1145.854554] RIP: 0010:0x0
> [ 1145.854879] Code: Bad RIP value.
> [ 1145.855270] RSP: 0018:ffffc90001903e68 EFLAGS: 00010013
> [ 1145.855902] RAX: 0000010ac9f60043 RBX: ffff8882b58a8320 RCX:
> 00000000c526b7c4
> [ 1145.856726] RDX: 0000000000000000 RSI: ffffffff820d9640 RDI:
> ffff8882b58a8320
> [ 1145.857560] RBP: ffffffff820d9640 R08: 00000000c526b7c4 R09:
> 0000000000000832
> [ 1145.858390] R10: 0000000000000000 R11: 0000000000000000 R12:
> 0000000000000000
> [ 1145.859222] R13: ffffffff820d9658 R14: ffff8881063b2880 R15:
> 0000000000000002
> [ 1145.860047] FS: 0000000000000000(0000) GS:ffff8882b5880000(0000)
> knlGS:0000000000000000
> [ 1145.860994] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 1145.861692] CR2: ffffffffffffffd6 CR3: 00000002ab1de001 CR4:
> 0000000000160ee0
> [ 1145.862570] Call Trace:
> [ 1145.862877] cpuidle_enter_state+0x7c/0x3e0
> [ 1145.863392] cpuidle_enter+0x29/0x40
>
>
>> I think we can still be woken up from kvm_vcpu_block() if pir is set.
>
> Exactly.
>
Powered by blists - more mailing lists