[RFC][PATCH 1/3] Introduce a workqueue to deliver PIT timer interrupts.

[Chris Lalancette <clalance@redhat.com>]

We really want to "kvm_set_irq" during the hrtimer callback,
but that is risky because that is during interrupt context.
Instead, offload the work to a workqueue, which is a bit safer
and should provide most of the same functionality.

Signed-off-by: Chris Lalancette <clalance@redhat.com>
---
 arch/x86/kvm/i8254.c |  106 ++++++++++++++++++++++++++++++-------------------
 arch/x86/kvm/i8254.h |    4 ++
 arch/x86/kvm/irq.c   |    1 -
 arch/x86/kvm/x86.c   |    4 ++
 4 files changed, 73 insertions(+), 42 deletions(-)

diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 188d827..dd655ef 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -34,6 +34,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
 
 #include "irq.h"
 #include "i8254.h"
@@ -49,6 +50,8 @@
 #define RW_STATE_WORD0 3
 #define RW_STATE_WORD1 4
 
+static struct workqueue_struct *pit_wq;
+
 /* Compute with 96 bit intermediate result: (a*b)/c */
 static u64 muldiv64(u64 a, u32 b, u32 c)
 {
@@ -281,6 +284,58 @@ static struct kvm_timer_ops kpit_ops = {
 	.is_periodic = kpit_is_periodic,
 };
 
+static void pit_do_work(struct work_struct *work)
+{
+       struct kvm_pit *pit = container_of(work, struct kvm_pit, expired);
+       struct kvm *kvm = pit->kvm;
+       struct kvm_vcpu *vcpu;
+       int i;
+       struct kvm_kpit_state *ps = &pit->pit_state;
+       int inject = 0;
+
+       /* Try to inject pending interrupts when
+        * last one has been acked.
+        */
+       raw_spin_lock(&ps->inject_lock);
+       if (ps->irq_ack) {
+               ps->irq_ack = 0;
+               inject = 1;
+       }
+       raw_spin_unlock(&ps->inject_lock);
+       if (inject) {
+               kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1);
+               kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0);
+
+               /*
+                * Provides NMI watchdog support via Virtual Wire mode.
+                * The route is: PIT -> PIC -> LVT0 in NMI mode.
+                *
+                * Note: Our Virtual Wire implementation is simplified, only
+                * propagating PIT interrupts to all VCPUs when they have set
+                * LVT0 to NMI delivery. Other PIC interrupts are just sent to
+                * VCPU0, and only if its LVT0 is in EXTINT mode.
+                */
+               if (kvm->arch.vapics_in_nmi_mode > 0)
+                       kvm_for_each_vcpu(i, vcpu, kvm)
+                               kvm_apic_nmi_wd_deliver(vcpu);
+       }
+}
+
+static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
+{
+       struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+       struct kvm_pit *pt = ktimer->kvm->arch.vpit;
+
+       queue_work(pit_wq, &pt->expired);
+
+       if (ktimer->t_ops->is_periodic(ktimer)) {
+               hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+              return HRTIMER_RESTART;
+       }
+       else
+              return HRTIMER_NORESTART;
+}
+
 static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
 {
 	struct kvm_timer *pt = &ps->pit_timer;
@@ -295,10 +350,9 @@ static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
 	pt->period = interval;
 	ps->is_periodic = is_period;
 
-	pt->timer.function = kvm_timer_fn;
+	pt->timer.function = pit_timer_fn;
 	pt->t_ops = &kpit_ops;
 	pt->kvm = ps->pit->kvm;
-	pt->vcpu = pt->kvm->bsp_vcpu;
 
 	atomic_set(&pt->pending, 0);
 	ps->irq_ack = 1;
@@ -628,6 +682,8 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	mutex_lock(&pit->pit_state.lock);
 	raw_spin_lock_init(&pit->pit_state.inject_lock);
 
+	INIT_WORK(&pit->expired, pit_do_work);
+
 	kvm->arch.vpit = pit;
 	pit->kvm = kvm;
 
@@ -691,48 +747,16 @@ void kvm_free_pit(struct kvm *kvm)
 	}
 }
 
-static void __inject_pit_timer_intr(struct kvm *kvm)
+int kvm_pit_create(void)
 {
-	struct kvm_vcpu *vcpu;
-	int i;
+       pit_wq = create_singlethread_workqueue("kvm-pit-wq");
+       if (!pit_wq)
+               return -ENOMEM;
 
-	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1);
-	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0);
-
-	/*
-	 * Provides NMI watchdog support via Virtual Wire mode.
-	 * The route is: PIT -> PIC -> LVT0 in NMI mode.
-	 *
-	 * Note: Our Virtual Wire implementation is simplified, only
-	 * propagating PIT interrupts to all VCPUs when they have set
-	 * LVT0 to NMI delivery. Other PIC interrupts are just sent to
-	 * VCPU0, and only if its LVT0 is in EXTINT mode.
-	 */
-	if (kvm->arch.vapics_in_nmi_mode > 0)
-		kvm_for_each_vcpu(i, vcpu, kvm)
-			kvm_apic_nmi_wd_deliver(vcpu);
+       return 0;
 }
 
-void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
+void kvm_pit_cleanup(void)
 {
-	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
-	struct kvm *kvm = vcpu->kvm;
-	struct kvm_kpit_state *ps;
-
-	if (pit) {
-		int inject = 0;
-		ps = &pit->pit_state;
-
-		/* Try to inject pending interrupts when
-		 * last one has been acked.
-		 */
-		raw_spin_lock(&ps->inject_lock);
-		if (atomic_read(&ps->pit_timer.pending) && ps->irq_ack) {
-			ps->irq_ack = 0;
-			inject = 1;
-		}
-		raw_spin_unlock(&ps->inject_lock);
-		if (inject)
-			__inject_pit_timer_intr(kvm);
-	}
+       destroy_workqueue(pit_wq);
 }
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 900d6b0..78db13d 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -40,6 +40,7 @@ struct kvm_pit {
 	struct kvm_kpit_state pit_state;
 	int irq_source_id;
 	struct kvm_irq_mask_notifier mask_notifier;
+	struct work_struct expired;
 };
 
 #define KVM_PIT_BASE_ADDRESS	    0x40
@@ -55,4 +56,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags);
 void kvm_free_pit(struct kvm *kvm);
 void kvm_pit_reset(struct kvm_pit *pit);
 
+int kvm_pit_create(void);
+void kvm_pit_cleanup(void);
+
 #endif
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 0f4e488..2095a04 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -90,7 +90,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {
 	kvm_inject_apic_timer_irqs(vcpu);
-	kvm_inject_pit_timer_irqs(vcpu);
 	/* TODO: PIT, RTC etc. */
 }
 EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5fa8684..a8cf1e1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4125,6 +4125,8 @@ int kvm_arch_init(void *opaque)
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);
 
+	kvm_pit_create();
+
 	return 0;
 
 out:
@@ -4133,6 +4135,8 @@ out:
 
 void kvm_arch_exit(void)
 {
+	kvm_pit_cleanup();
+
 	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
-- 
1.6.6.1