[SRU][Xenial][PATCH 2/3] KVM: VMX: avoid double list add with VT-d posted interrupts
Ioanna Alifieraki
ioanna-maria.alifieraki at canonical.com
Wed Dec 16 19:41:44 UTC 2020
From: Paolo Bonzini <pbonzini at redhat.com>
BugLink: https://bugs.launchpad.net/bugs/1908428
In some cases, for example involving hot-unplug of assigned
devices, pi_post_block can forget to remove the vCPU from the
blocked_vcpu_list. When this happens, the next call to
pi_pre_block corrupts the list.
Fix this in two ways. First, check vcpu->pre_pcpu in pi_pre_block
and WARN instead of adding the element twice in the list. Second,
always do the list removal in pi_post_block if vcpu->pre_pcpu is
set (not -1).
The new code keeps interrupts disabled for the whole duration of
pi_pre_block/pi_post_block. This is not strictly necessary, but
easier to follow. For the same reason, PI.ON is checked only
after the cmpxchg, and to handle it we just call the post-block
code. This removes duplication of the list removal code.
Cc: Huangweidong <weidong.huang at huawei.com>
Cc: Gonglei <arei.gonglei at huawei.com>
Cc: wangxin <wangxinxin.wang at huawei.com>
Cc: Radim Krčmář <rkrcmar at redhat.com>
Tested-by: Longpeng (Mike) <longpeng2 at huawei.com>
Cc: stable at vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini at redhat.com>
(backported from commit 8b306e2f3c41939ea528e6174c88cfbfff893ce1)
[hunk 4 and 5 : Original commit changes pi_pre_block function.
This function is not present in 4.4 kernel, see upstream commit
bc22512bb24c(kvm: vmx: rename vmx_pre/post_block to pi_pre/post_block).
Make relevant changes in vmx_pre_block function.]
Signed-off-by: Ioanna Alifieraki <ioanna-maria.alifieraki at canonical.com>
---
arch/x86/kvm/vmx.c | 65 +++++++++++++++++++---------------------------
1 file changed, 27 insertions(+), 38 deletions(-)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 472d089f0bd2..19589b1107b2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11150,10 +11150,11 @@ static void __pi_post_block(struct kvm_vcpu *vcpu)
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
struct pi_desc old, new;
unsigned int dest;
- unsigned long flags;
do {
old.control = new.control = pi_desc->control;
+ WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+ "Wakeup handler not enabled while the VCPU is blocked\n");
dest = cpu_physical_id(vcpu->cpu);
@@ -11170,14 +11171,10 @@ static void __pi_post_block(struct kvm_vcpu *vcpu)
} while (cmpxchg(&pi_desc->control, old.control,
new.control) != old.control);
- if(vcpu->pre_pcpu != -1) {
- spin_lock_irqsave(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
vcpu->pre_pcpu = -1;
}
}
@@ -11197,7 +11194,6 @@ static void __pi_post_block(struct kvm_vcpu *vcpu)
*/
static int vmx_pre_block(struct kvm_vcpu *vcpu)
{
- unsigned long flags;
unsigned int dest;
struct pi_desc old, new;
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -11206,34 +11202,20 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
!irq_remapping_cap(IRQ_POSTING_CAP))
return 0;
- vcpu->pre_pcpu = vcpu->cpu;
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_add_tail(&vcpu->blocked_vcpu_list,
- &per_cpu(blocked_vcpu_on_cpu,
- vcpu->pre_pcpu));
- spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+ vcpu->pre_pcpu = vcpu->cpu;
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_add_tail(&vcpu->blocked_vcpu_list,
+ &per_cpu(blocked_vcpu_on_cpu,
+ vcpu->pre_pcpu));
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ }
do {
old.control = new.control = pi_desc->control;
- /*
- * We should not block the vCPU if
- * an interrupt is posted for it.
- */
- if (pi_test_on(pi_desc) == 1) {
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
-
- return 1;
- }
-
WARN((pi_desc->sn == 1),
"Warning: SN field of posted-interrupts "
"is set before blocking\n");
@@ -11255,19 +11237,26 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
/* set 'NV' to 'wakeup vector' */
new.nv = POSTED_INTR_WAKEUP_VECTOR;
- } while (cmpxchg64(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg(&pi_desc->control, old.control,
+ new.control) != old.control);
- return 0;
+ /* We should not block the vCPU if an interrupt is posted for it. */
+ if (pi_test_on(pi_desc) == 1)
+ __pi_post_block(vcpu);
+
+ local_irq_enable();
+ return (vcpu->pre_pcpu == -1);
}
static void vmx_post_block(struct kvm_vcpu *vcpu)
{
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ if (vcpu->pre_pcpu == -1)
return;
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
__pi_post_block(vcpu);
+ local_irq_enable();
}
/*
--
2.17.1
More information about the kernel-team
mailing list