[Xen-changelog] [xen stable-4.8] x86/apicv: fix wrong IPI suppression during posted interrupt delivery

[patchbot@xxxxxxx]

commit 14217cba9d9f3b4cdd20bcfb7fd324977e2d6bbf
Author:     Quan Xu <xuquan8@xxxxxxxxxx>
AuthorDate: Tue Mar 20 14:37:34 2018 +0100
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Tue Mar 20 14:37:34 2018 +0100

    x86/apicv: fix wrong IPI suppression during posted interrupt delivery
    
    __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@xxxxxxxxxx>
    Signed-off-by: Chao Gao <chao.gao@xxxxxxxxx>
    Acked-by: Kevin Tian <kevin.tian@xxxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
    master commit: b151125b4d89d7ec139ac34470e3c709fb4b1b4d
    master date: 2017-03-03 12:00:35 +0100
---
 xen/arch/x86/hvm/vmx/vmx.c | 50 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 43 insertions(+), 7 deletions(-)

diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index c604672bf8..955643c036 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -1952,13 +1952,53 @@ static void __vmx_deliver_posted_interrupt(struct vcpu 
*v)
     bool_t running = v->is_running;
 
     vcpu_unblock(v);
+    /*
+     * Just like vcpu_kick(), nothing is needed for the following two cases:
+     * 1. The target vCPU is not running, meaning it is blocked or runnable.
+     * 2. The target vCPU is the current vCPU and we're in non-interrupt
+     * context.
+     */
     if ( running && (in_irq() || (v != current)) )
     {
+        /*
+         * Note: Only two cases will reach here:
+         * 1. The target vCPU is running on other pCPU.
+         * 2. The target vCPU is the current vCPU.
+         *
+         * Note2: Don't worry the v->processor may change. The vCPU being
+         * moved to another processor is guaranteed to sync PIR to vIRR,
+         * due to the involved scheduling cycle.
+         */
         unsigned int cpu = v->processor;
 
-        if ( !test_and_set_bit(VCPU_KICK_SOFTIRQ, &softirq_pending(cpu))
-             && (cpu != smp_processor_id()) )
+        /*
+         * For case 1, we send an IPI to the pCPU. When an IPI arrives, the
+         * target vCPU maybe is running in non-root mode, running in root
+         * mode, runnable or blocked. If the target vCPU is running in
+         * non-root mode, the hardware will sync PIR to vIRR for
+         * 'posted_intr_vector' is special to the pCPU. If the target vCPU is
+         * running in root-mode, the interrupt handler starts to run.
+         * Considering an IPI may arrive in the window between the call to
+         * vmx_intr_assist() and interrupts getting disabled, the interrupt
+         * handler should raise a softirq to ensure events will be delivered
+         * in time. If the target vCPU is runnable, it will sync PIR to
+         * vIRR next time it is chose to run. In this case, a IPI and a
+         * softirq is sent to a wrong vCPU which will not have any adverse
+         * effect. If the target vCPU is blocked, since vcpu_block() checks
+         * whether there is an event to be delivered through
+         * local_events_need_delivery() just after blocking, the vCPU must
+         * have synced PIR to vIRR. Similarly, there is a IPI and a softirq
+         * sent to a wrong vCPU.
+         */
+        if ( cpu != smp_processor_id() )
             send_IPI_mask(cpumask_of(cpu), posted_intr_vector);
+        /*
+         * For case 2, raising a softirq ensures PIR will be synced to vIRR.
+         * As any softirq will do, as an optimization we only raise one if
+         * none is pending already.
+         */
+        else if ( !softirq_pending(cpu) )
+            raise_softirq(VCPU_KICK_SOFTIRQ);
     }
 }
 
@@ -2388,13 +2428,9 @@ const struct hvm_function_table * __init start_vmx(void)
 
     if ( cpu_has_vmx_posted_intr_processing )
     {
+        alloc_direct_apic_vector(&posted_intr_vector, 
pi_notification_interrupt);
         if ( iommu_intpost )
-        {
-            alloc_direct_apic_vector(&posted_intr_vector, 
pi_notification_interrupt);
             alloc_direct_apic_vector(&pi_wakeup_vector, pi_wakeup_interrupt);
-        }
-        else
-            alloc_direct_apic_vector(&posted_intr_vector, 
event_check_interrupt);
     }
     else
     {
--
generated by git-patchbot for /home/xen/git/xen.git#stable-4.8

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/xen-changelog