This is a note to let you know that I've just added the patch titled
KVM: VMX: simplify and fix vmx_vcpu_pi_load
to the 4.13-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
kvm-vmx-simplify-and-fix-vmx_vcpu_pi_load.patch
and it can be found in the queue-4.13 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 31afb2ea2b10a7d17ce3db4cdb0a12b63b2fe08a Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Date: Tue, 6 Jun 2017 12:57:06 +0200
Subject: KVM: VMX: simplify and fix vmx_vcpu_pi_load
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
From: Paolo Bonzini <pbonzini@xxxxxxxxxx>
commit 31afb2ea2b10a7d17ce3db4cdb0a12b63b2fe08a upstream.
The simplify part: do not touch pi_desc.nv, we can set it when the
VCPU is first created. Likewise, pi_desc.sn is only handled by
vmx_vcpu_pi_load, do not touch it in __pi_post_block.
The fix part: do not check kvm_arch_has_assigned_device, instead
check the SN bit to figure out whether vmx_vcpu_pi_put ran before.
This matches what the previous patch did in pi_post_block.
Cc: Huangweidong <weidong.huang@xxxxxxxxxx>
Cc: Gonglei <arei.gonglei@xxxxxxxxxx>
Cc: wangxin <wangxinxin.wang@xxxxxxxxxx>
Cc: Radim Krčmář <rkrcmar@xxxxxxxxxx>
Tested-by: Longpeng (Mike) <longpeng2@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/kvm/vmx.c | 68 +++++++++++++++++++++++++++--------------------------
1 file changed, 35 insertions(+), 33 deletions(-)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2187,43 +2187,41 @@ static void vmx_vcpu_pi_load(struct kvm_
struct pi_desc old, new;
unsigned int dest;
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ /*
+ * In case of hot-plug or hot-unplug, we may have to undo
+ * vmx_vcpu_pi_put even if there is no assigned device. And we
+ * always keep PI.NDST up to date for simplicity: it makes the
+ * code easier, and CPU migration is not a fast path.
+ */
+ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
+ return;
+
+ /*
+ * First handle the simple case where no cmpxchg is necessary; just
+ * allow posting non-urgent interrupts.
+ *
+ * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+ * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+ * expects the VCPU to be on the blocked_vcpu_list that matches
+ * PI.NDST.
+ */
+ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+ vcpu->cpu == cpu) {
+ pi_clear_sn(pi_desc);
return;
+ }
+ /* The full case. */
do {
old.control = new.control = pi_desc->control;
- /*
- * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
- * are two possible cases:
- * 1. After running 'pre_block', context switch
- * happened. For this case, 'sn' was set in
- * vmx_vcpu_put(), so we need to clear it here.
- * 2. After running 'pre_block', we were blocked,
- * and woken up by some other guy. For this case,
- * we don't need to do anything, 'pi_post_block'
- * will do everything for us. However, we cannot
- * check whether it is case #1 or case #2 here
- * (maybe, not needed), so we also clear sn here,
- * I think it is not a big deal.
- */
- if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
- if (vcpu->cpu != cpu) {
- dest = cpu_physical_id(cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
- }
+ dest = cpu_physical_id(cpu);
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- }
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;
- /* Allow posting non-urgent interrupts */
new.sn = 0;
} while (cmpxchg(&pi_desc->control, old.control,
new.control) != old.control);
@@ -9310,6 +9308,13 @@ static struct kvm_vcpu *vmx_create_vcpu(
vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
+ /*
+ * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+ * or POSTED_INTR_WAKEUP_VECTOR.
+ */
+ vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+ vmx->pi_desc.sn = 1;
+
return &vmx->vcpu;
free_vmcs:
@@ -11407,9 +11412,6 @@ static void __pi_post_block(struct kvm_v
else
new.ndst = (dest << 8) & 0xFF00;
- /* Allow posting non-urgent interrupts */
- new.sn = 0;
-
/* set 'NV' to 'notification vector' */
new.nv = POSTED_INTR_VECTOR;
} while (cmpxchg(&pi_desc->control, old.control,
Patches currently in stable-queue which might be from pbonzini@xxxxxxxxxx are
queue-4.13/kvm-vmx-simplify-and-fix-vmx_vcpu_pi_load.patch
queue-4.13/kvm-vmx-avoid-double-list-add-with-vt-d-posted-interrupts.patch
queue-4.13/genirq-fix-cpumask-check-in-__irq_startup_managed.patch
queue-4.13/kvm-nvmx-don-t-allow-l2-to-access-the-hardware-cr8.patch
queue-4.13/kvm-x86-handle-async-pf-in-rcu-read-side-critical-sections.patch
queue-4.13/kvm-vmx-extract-__pi_post_block.patch
queue-4.13/kvm-nvmx-fix-host_cr3-host_cr4-cache.patch
queue-4.13/kvm-vmx-do-not-bug-on-out-of-bounds-guest-irq.patch