Merge tag 'kvm-x86-apic-6.20' of https://github.com/kvm-x86/linux into HEAD

KVM x86 APIC-ish changes for 6.20

 - Fix a benign bug where KVM could use the wrong memslots (ignored SMM) when
   creating a vCPU-specific mapping of guest memory.

 - Clean up KVM's handling of marking mapped vCPU pages dirty.

 - Drop a pile of *ancient* sanity checks hidden behind in KVM's unused
   ASSERT() macro, most of which could be trivially triggered by the guest
   and/or user, and all of which were useless.

 - Fold "struct dest_map" into its sole user, "struct rtc_status", to make it
   more obvious what the weird parameter is used for, and to allow burying the
   RTC shenanigans behind CONFIG_KVM_IOAPIC=y.

 - Bury all of ioapic.h and KVM_IRQCHIP_KERNEL behind CONFIG_KVM_IOAPIC=y.

 - Add a regression test for recent APICv update fixes.

 - Rework KVM's handling of VMCS updates while L2 is active to temporarily
   switch to vmcs01 instead of deferring the update until the next nested
   VM-Exit.  The deferred updates approach directly contributed to several
   bugs, was proving to be a maintenance burden due to the difficulty in
   auditing the correctness of deferred updates, and was polluting
   "struct nested_vmx" with a growing pile of booleans.

 - Handle "hardware APIC ISR", a.k.a. SVI, updates in kvm_apic_update_apicv()
   to consolidate the updates, and to co-locate SVI updates with the updates
   for KVM's own cache of ISR information.

 - Drop a dead function declaration.

Author: bonzini

arch/x86/include/asm/kvm_host.h

@@ -1232,7 +1232,9 @@ struct kvm_xen {
 
 enum kvm_irqchip_mode {
 	KVM_IRQCHIP_NONE,
+#ifdef CONFIG_KVM_IOAPIC
 	KVM_IRQCHIP_KERNEL,       /* created with KVM_CREATE_IRQCHIP */
+#endif
 	KVM_IRQCHIP_SPLIT,        /* created with KVM_CAP_SPLIT_IRQCHIP */
 };
 

arch/x86/kvm/hyperv.c

@@ -492,7 +492,7 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
 	irq.vector = vector;
 	irq.level = 1;
 
-	ret = kvm_irq_delivery_to_apic(vcpu->kvm, vcpu->arch.apic, &irq, NULL);
+	ret = kvm_irq_delivery_to_apic(vcpu->kvm, vcpu->arch.apic, &irq);
 	trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret);
 	return ret;
 }

arch/x86/kvm/ioapic.c

@@ -37,11 +37,6 @@
 static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
 		bool line_status);
 
-static void kvm_ioapic_update_eoi_one(struct kvm_vcpu *vcpu,
-				      struct kvm_ioapic *ioapic,
-				      int trigger_mode,
-				      int pin);
-
 static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic)
 {
 	unsigned long result = 0;
@@ -82,7 +77,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic)
 static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 {
 	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_IDS);
+	bitmap_zero(ioapic->rtc_status.map, KVM_MAX_VCPU_IDS);
 }
 
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
@@ -97,7 +92,7 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 {
 	bool new_val, old_val;
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
-	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
+	struct rtc_status *status = &ioapic->rtc_status;
 	union kvm_ioapic_redirect_entry *e;
 
 	e = &ioapic->redirtbl[RTC_GSI];
@@ -107,17 +102,17 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 		return;
 
 	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
-	old_val = test_bit(vcpu->vcpu_id, dest_map->map);
+	old_val = test_bit(vcpu->vcpu_id, status->map);
 
 	if (new_val == old_val)
 		return;
 
 	if (new_val) {
-		__set_bit(vcpu->vcpu_id, dest_map->map);
-		dest_map->vectors[vcpu->vcpu_id] = e->fields.vector;
+		__set_bit(vcpu->vcpu_id, status->map);
+		status->vectors[vcpu->vcpu_id] = e->fields.vector;
 		ioapic->rtc_status.pending_eoi++;
 	} else {
-		__clear_bit(vcpu->vcpu_id, dest_map->map);
+		__clear_bit(vcpu->vcpu_id, status->map);
 		ioapic->rtc_status.pending_eoi--;
 		rtc_status_pending_eoi_check_valid(ioapic);
 	}
@@ -148,13 +143,12 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
 static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu,
 			int vector)
 {
-	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
+	struct rtc_status *status = &ioapic->rtc_status;
 
 	/* RTC special handling */
-	if (test_bit(vcpu->vcpu_id, dest_map->map) &&
-	    (vector == dest_map->vectors[vcpu->vcpu_id]) &&
-	    (test_and_clear_bit(vcpu->vcpu_id,
-				ioapic->rtc_status.dest_map.map))) {
+	if (test_bit(vcpu->vcpu_id, status->map) &&
+	    (vector == status->vectors[vcpu->vcpu_id]) &&
+	    (test_and_clear_bit(vcpu->vcpu_id, status->map))) {
 		--ioapic->rtc_status.pending_eoi;
 		rtc_status_pending_eoi_check_valid(ioapic);
 	}
@@ -265,15 +259,15 @@ static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr)
 void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
 {
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
-	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
+	struct rtc_status *status = &ioapic->rtc_status;
 	union kvm_ioapic_redirect_entry *e;
 	int index;
 
 	spin_lock(&ioapic->lock);
 
 	/* Make sure we see any missing RTC EOI */
-	if (test_bit(vcpu->vcpu_id, dest_map->map))
-		__set_bit(dest_map->vectors[vcpu->vcpu_id],
+	if (test_bit(vcpu->vcpu_id, status->map))
+		__set_bit(status->vectors[vcpu->vcpu_id],
 			  ioapic_handled_vectors);
 
 	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
@@ -490,11 +484,11 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 		 * if rtc_irq_check_coalesced returns false).
 		 */
 		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
-		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
-					       &ioapic->rtc_status.dest_map);
+		ret = __kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
+						 &ioapic->rtc_status);
 		ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
 	} else
-		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
+		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
 
 	if (ret && irqe.trig_mode == IOAPIC_LEVEL_TRIG)
 		entry->fields.remote_irr = 1;
@@ -564,7 +558,6 @@ static void kvm_ioapic_update_eoi_one(struct kvm_vcpu *vcpu,
 	    kvm_lapic_suppress_eoi_broadcast(apic))
 		return;
 
-	ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
 	ent->fields.remote_irr = 0;
 	if (!ent->fields.mask && (ioapic->irr & (1 << pin))) {
 		++ioapic->irq_eoi[pin];
@@ -624,8 +617,6 @@ static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!ioapic_in_range(ioapic, addr))
 		return -EOPNOTSUPP;
 
-	ASSERT(!(addr & 0xf));	/* check alignment */
-
 	addr &= 0xff;
 	spin_lock(&ioapic->lock);
 	switch (addr) {
@@ -666,8 +657,6 @@ static int ioapic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!ioapic_in_range(ioapic, addr))
 		return -EOPNOTSUPP;
 
-	ASSERT(!(addr & 0xf));	/* check alignment */
-
 	switch (len) {
 	case 8:
 	case 4:

arch/x86/kvm/ioapic.h

@@ -6,11 +6,12 @@
 #include <kvm/iodev.h>
 #include "irq.h"
 
+#ifdef CONFIG_KVM_IOAPIC
+
 struct kvm;
 struct kvm_vcpu;
 
 #define IOAPIC_NUM_PINS  KVM_IOAPIC_NUM_PINS
-#define MAX_NR_RESERVED_IOAPIC_PINS KVM_MAX_IRQ_ROUTES
 #define IOAPIC_VERSION_ID 0x11	/* IOAPIC version */
 #define IOAPIC_EDGE_TRIG  0
 #define IOAPIC_LEVEL_TRIG 1
@@ -37,7 +38,9 @@ struct kvm_vcpu;
 
 #define RTC_GSI 8
 
-struct dest_map {
+struct rtc_status {
+	int pending_eoi;
+
 	/* vcpu bitmap where IRQ has been sent */
 	DECLARE_BITMAP(map, KVM_MAX_VCPU_IDS);
 
@@ -48,12 +51,6 @@ struct dest_map {
 	u8 vectors[KVM_MAX_VCPU_IDS];
 };
 
-
-struct rtc_status {
-	int pending_eoi;
-	struct dest_map dest_map;
-};
-
 union kvm_ioapic_redirect_entry {
 	u64 bits;
 	struct {
@@ -104,24 +101,6 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 			     bool mask);
 
-#ifdef DEBUG
-#define ASSERT(x)  							\
-do {									\
-	if (!(x)) {							\
-		printk(KERN_EMERG "assertion failed %s: %d: %s\n",	\
-		       __FILE__, __LINE__, #x);				\
-		BUG();							\
-	}								\
-} while (0)
-#else
-#define ASSERT(x) do { } while (0)
-#endif
-
-static inline int ioapic_in_kernel(struct kvm *kvm)
-{
-	return irqchip_full(kvm);
-}
-
 void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
 void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,
 			int trigger_mode);
@@ -134,6 +113,13 @@ void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu,
 			   ulong *ioapic_handled_vectors);
+#endif /* CONFIG_KVM_IOAPIC */
+
+static inline int ioapic_in_kernel(struct kvm *kvm)
+{
+	return irqchip_full(kvm);
+}
+
 void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 			    ulong *ioapic_handled_vectors);
 void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode,

arch/x86/kvm/irq.c

@@ -235,7 +235,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 
 	kvm_msi_to_lapic_irq(kvm, e, &irq);
 
-	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
+	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
@@ -258,7 +258,7 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 
 		kvm_msi_to_lapic_irq(kvm, e, &irq);
 
-		if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+		if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r))
 			return r;
 		break;