From baed82c8e4893a3258267dad198e04691d2f7c09 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 8 Oct 2021 19:12:21 -0700 Subject: [PATCH] KVM: VMX: Remove vCPU from PI wakeup list before updating PID.NV Remove the vCPU from the wakeup list before updating the notification vector in the posted interrupt post-block helper. There is no need to wake the current vCPU as it is by definition not blocking. Practically speaking this is a nop as it only shaves a few meager cycles in the unlikely case that the vCPU was migrated and the previous pCPU gets a wakeup IRQ right before PID.NV is updated. The real motivation is to allow for more readable code in the future, when post-block is merged with vmx_vcpu_pi_load(), at which point removal from the list will be conditional on the old notification vector. Opportunistically add comments to document why KVM has a per-CPU spinlock that, at first glance, appears to be taken only on the owning CPU. Explicitly call out that the spinlock must be taken with IRQs disabled, a detail that was "lost" when KVM switched from spin_lock_irqsave() to spin_lock(), with IRQs disabled for the entirety of the relevant path. Signed-off-by: Sean Christopherson Message-Id: <20211009021236.4122790-29-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/posted_intr.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index e29a40042978d..4db2b14ee7c6d 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -11,10 +11,22 @@ #include "vmx.h" /* - * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we - * can find which vCPU should be waken up. + * Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler() + * when a WAKEUP_VECTOR interrupted is posted. vCPUs are added to the list when + * the vCPU is scheduled out and is blocking (e.g. in HLT) with IRQs enabled. + * The vCPUs posted interrupt descriptor is updated at the same time to set its + * notification vector to WAKEUP_VECTOR, so that posted interrupt from devices + * wake the target vCPUs. vCPUs are removed from the list and the notification + * vector is reset when the vCPU is scheduled in. */ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +/* + * Protect the per-CPU list with a per-CPU spinlock to handle task migration. + * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the + * ->sched_in() path will need to take the vCPU off the list of the _previous_ + * CPU. IRQs must be disabled when taking this lock, otherwise deadlock will + * occur if a wakeup IRQ arrives and attempts to acquire the lock. + */ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) @@ -104,6 +116,14 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; unsigned int dest; + /* + * Remove the vCPU from the wakeup list of the _previous_ pCPU, which + * will not be the same as the current pCPU if the task was migrated. + */ + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + dest = cpu_physical_id(vcpu->cpu); if (!x2apic_mode) dest = (dest << 8) & 0xFF00; @@ -120,9 +140,6 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) } while (cmpxchg64(&pi_desc->control, old.control, new.control) != old.control); - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); vcpu->pre_pcpu = -1; } -- 2.30.2