KVM: PPC: Book3S: Simplify external interrupt handling

Currently we use two bits in the vcpu pending_exceptions bitmap to
indicate that an external interrupt is pending for the guest, one
for "one-shot" interrupts that are cleared when delivered, and one
for interrupts that persist until cleared by an explicit action of
the OS (e.g. an acknowledge to an interrupt controller). The
BOOK3S_IRQPRIO_EXTERNAL bit is used for one-shot interrupt requests
and BOOK3S_IRQPRIO_EXTERNAL_LEVEL is used for persisting interrupts.

In practice BOOK3S_IRQPRIO_EXTERNAL never gets used, because our
Book3S platforms generally, and pseries in particular, expect
external interrupt requests to persist until they are acknowledged
at the interrupt controller. That combined with the confusion
introduced by having two bits for what is essentially the same thing
makes it attractive to simplify things by only using one bit. This
patch does that.

With this patch there is only BOOK3S_IRQPRIO_EXTERNAL, and by default
it has the semantics of a persisting interrupt. In order to avoid
breaking the ABI, we introduce a new "external_oneshot" flag which
preserves the behaviour of the KVM_INTERRUPT ioctl with the
KVM_INTERRUPT_SET argument.

Reviewed-by: David Gibson <[e-mail]>
Signed-off-by: Paul Mackerras <[e-mail]>
Signed-off-by: Michael Ellerman <[e-mail]>

arch/powerpc/include/asm/kvm_asm.h

···
 #define BOOK3S_INTERRUPT_INST_STORAGE	0x400
 #define BOOK3S_INTERRUPT_INST_SEGMENT	0x480
 #define BOOK3S_INTERRUPT_EXTERNAL	0x500
-#define BOOK3S_INTERRUPT_EXTERNAL_LEVEL	0x501
 #define BOOK3S_INTERRUPT_EXTERNAL_HV	0x502
 #define BOOK3S_INTERRUPT_ALIGNMENT	0x600
 #define BOOK3S_INTERRUPT_PROGRAM	0x700
···
 #define BOOK3S_IRQPRIO_EXTERNAL			14
 #define BOOK3S_IRQPRIO_DECREMENTER		15
 #define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR	16
-#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL		17
-#define BOOK3S_IRQPRIO_MAX			18
+#define BOOK3S_IRQPRIO_MAX			17
 
 #define BOOK3S_HFLAG_DCBZ32			0x1
 #define BOOK3S_HFLAG_SLB			0x2

arch/powerpc/include/asm/kvm_host.h

···
 	u8 hcall_needed;
 	u8 epr_flags; /* KVMPPC_EPR_xxx */
 	u8 epr_needed;
+	u8 external_oneshot;	/* clear external irq after delivery */
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 

arch/powerpc/kvm/book3s.c

···
 	case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE;		break;
 	case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT;		break;
 	case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL;		break;
-	case 0x501: prio = BOOK3S_IRQPRIO_EXTERNAL_LEVEL;	break;
 	case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT;		break;
 	case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM;		break;
 	case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL;		break;
···
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
 {
-	unsigned int vec = BOOK3S_INTERRUPT_EXTERNAL;
+	/*
+	 * This case (KVM_INTERRUPT_SET) should never actually arise for
+	 * a pseries guest (because pseries guests expect their interrupt
+	 * controllers to continue asserting an external interrupt request
+	 * until it is acknowledged at the interrupt controller), but is
+	 * included to avoid ABI breakage and potentially for other
+	 * sorts of guest.
+	 *
+	 * There is a subtlety here: HV KVM does not test the
+	 * external_oneshot flag in the code that synthesizes
+	 * external interrupts for the guest just before entering
+	 * the guest.  That is OK even if userspace did do a
+	 * KVM_INTERRUPT_SET on a pseries guest vcpu, because the
+	 * caller (kvm_vcpu_ioctl_interrupt) does a kvm_vcpu_kick()
+	 * which ends up doing a smp_send_reschedule(), which will
+	 * pull the guest all the way out to the host, meaning that
+	 * we will call kvmppc_core_prepare_to_enter() before entering
+	 * the guest again, and that will handle the external_oneshot
+	 * flag correctly.
+	 */
+	if (irq->irq == KVM_INTERRUPT_SET)
+		vcpu->arch.external_oneshot = 1;
 
-	if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
-		vec = BOOK3S_INTERRUPT_EXTERNAL_LEVEL;
-
-	kvmppc_book3s_queue_irqprio(vcpu, vec);
+	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 }
 
 void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
-	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
 }
 
 void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong dar,
···
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
-	case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
 		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
···
 		case BOOK3S_IRQPRIO_DECREMENTER:
 			/* DEC interrupts get cleared by mtdec */
 			return false;
-		case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
-			/* External interrupts get cleared by userspace */
+		case BOOK3S_IRQPRIO_EXTERNAL:
+			/*
+			 * External interrupts get cleared by userspace
+			 * except when set by the KVM_INTERRUPT ioctl with
+			 * KVM_INTERRUPT_SET (not KVM_INTERRUPT_SET_LEVEL).
+			 */
+			if (vcpu->arch.external_oneshot) {
+				vcpu->arch.external_oneshot = 0;
+				return true;
+			}
 			return false;
 	}
 

arch/powerpc/kvm/book3s_hv_rm_xics.c

···
 
 	/* Mark the target VCPU as having an interrupt pending */
 	vcpu->stat.queue_intr++;
-	set_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
+	set_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
 
 	/* Kick self ? Just set MER and return */
 	if (vcpu == this_vcpu) {
···
 static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu)
 {
 	/* Note: Only called on self ! */
-	clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
-		  &vcpu->arch.pending_exceptions);
+	clear_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_MER);
 }
 

arch/powerpc/kvm/book3s_hv_rmhandlers.S

···
 
 	/* Check if we can deliver an external or decrementer interrupt now */
 	ld	r0, VCPU_PENDING_EXC(r4)
-	rldicl	r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
+	rldicl	r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL, 63
 	cmpdi	cr1, r0, 0
 	andi.	r8, r11, MSR_EE
 	mfspr	r8, SPRN_LPCR
-	/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
+	/* Insert EXTERNAL bit into LPCR at the MER bit position */
 	rldimi	r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
 	mtspr	SPRN_LPCR, r8
 	isync

arch/powerpc/kvm/book3s_pr.c

···
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_EXTERNAL:
-	case BOOK3S_INTERRUPT_EXTERNAL_LEVEL:
 	case BOOK3S_INTERRUPT_EXTERNAL_HV:
 	case BOOK3S_INTERRUPT_H_VIRT:
 		vcpu->stat.ext_intr_exits++;

arch/powerpc/kvm/book3s_xics.c

···
 	 */
 	if (new.out_ee) {
 		kvmppc_book3s_queue_irqprio(icp->vcpu,
-					    BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+					    BOOK3S_INTERRUPT_EXTERNAL);
 		if (!change_self)
 			kvmppc_fast_vcpu_kick(icp->vcpu);
 	}
···
 	u32 xirr;
 
 	/* First, remove EE from the processor */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	/*
 	 * ICP State: Accept_Interrupt
···
 	 * We can remove EE from the current processor, the update
 	 * transaction will set it again if needed
 	 */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	do {
 		old_state = new_state = READ_ONCE(icp->state);
···
 	 * Deassert the CPU interrupt request.
 	 * icp_try_update will reassert it if necessary.
 	 */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	/*
 	 * Note that if we displace an interrupt from old_state.xisr,

arch/powerpc/kvm/book3s_xive_template.c

···
 	 * set by pull or an escalation interrupts).
 	 */
 	if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions))
-		clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
+		clear_bit(BOOK3S_IRQPRIO_EXTERNAL,
 			  &vcpu->arch.pending_exceptions);
 
 	pr_devel(" new pending=0x%02x hw_cppr=%d cppr=%d\n",

arch/powerpc/kvm/trace_book3s.h

···
 	{0x400, "INST_STORAGE"}, \
 	{0x480, "INST_SEGMENT"}, \
 	{0x500, "EXTERNAL"}, \
-	{0x501, "EXTERNAL_LEVEL"}, \
 	{0x502, "EXTERNAL_HV"}, \
 	{0x600, "ALIGNMENT"}, \
 	{0x700, "PROGRAM"}, \

tools/perf/arch/powerpc/util/book3s_hv_exits.h

···
 	{0x400, "INST_STORAGE"}, \
 	{0x480, "INST_SEGMENT"}, \
 	{0x500, "EXTERNAL"}, \
-	{0x501, "EXTERNAL_LEVEL"}, \
 	{0x502, "EXTERNAL_HV"}, \
 	{0x600, "ALIGNMENT"}, \
 	{0x700, "PROGRAM"}, \