Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "First batch of KVM changes for 4.1

  The most interesting bit here is irqfd/ioeventfd support for ARM and
  ARM64.

  Summary:

  ARM/ARM64:
     fixes for live migration, irqfd and ioeventfd support (enabling
     vhost, too), page aging

  s390:
     interrupt handling rework, allowing to inject all local interrupts
     via new ioctl and to get/set the full local irq state for migration
     and introspection.  New ioctls to access memory by virtual address,
     and to get/set the guest storage keys.  SIMD support.

  MIPS:
     FPU and MIPS SIMD Architecture (MSA) support.  Includes some
     patches from Ralf Baechle's MIPS tree.

  x86:
     bugfixes (notably for pvclock, the others are small) and cleanups.
     Another small latency improvement for the TSC deadline timer"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  KVM: use slowpath for cross page cached accesses
  kvm: mmu: lazy collapse small sptes into large sptes
  KVM: x86: Clear CR2 on VCPU reset
  KVM: x86: DR0-DR3 are not clear on reset
  KVM: x86: BSP in MSR_IA32_APICBASE is writable
  KVM: x86: simplify kvm_apic_map
  KVM: x86: avoid logical_map when it is invalid
  KVM: x86: fix mixed APIC mode broadcast
  KVM: x86: use MDA for interrupt matching
  kvm/ppc/mpic: drop unused IRQ_testbit
  KVM: nVMX: remove unnecessary double caching of MAXPHYADDR
  KVM: nVMX: checks for address bits beyond MAXPHYADDR on VM-entry
  KVM: x86: cache maxphyaddr CPUID leaf in struct kvm_vcpu
  KVM: vmx: pass error code with internal error #2
  x86: vdso: fix pvclock races with task migration
  KVM: remove kvm_read_hva and kvm_read_hva_atomic
  KVM: x86: optimize delivery of TSC deadline timer interrupt
  KVM: x86: extract blocking logic from __vcpu_run
  kvm: x86: fix x86 eflags fixed bit
  KVM: s390: migrate vcpu interrupt state
  ...

1 files changed, 85 insertions, 62 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4ee827d..d67206a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -133,6 +133,28 @@ static inline int kvm_apic_id(struct kvm_lapic *apic)
 	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
 }
 
+/* The logical map is definitely wrong if we have multiple
+ * modes at the same time.  (Physical map is always right.)
+ */
+static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map)
+{
+	return !(map->mode & (map->mode - 1));
+}
+
+static inline void
+apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid)
+{
+	unsigned lid_bits;
+
+	BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER !=  4);
+	BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT    !=  8);
+	BUILD_BUG_ON(KVM_APIC_MODE_X2APIC        != 16);
+	lid_bits = map->mode;
+
+	*cid = dest_id >> lid_bits;
+	*lid = dest_id & ((1 << lid_bits) - 1);
+}
+
 static void recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
@@ -146,48 +168,6 @@ static void recalculate_apic_map(struct kvm *kvm)
 	if (!new)
 		goto out;
 
-	new->ldr_bits = 8;
-	/* flat mode is default */
-	new->cid_shift = 8;
-	new->cid_mask = 0;
-	new->lid_mask = 0xff;
-	new->broadcast = APIC_BROADCAST;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct kvm_lapic *apic = vcpu->arch.apic;
-
-		if (!kvm_apic_present(vcpu))
-			continue;
-
-		if (apic_x2apic_mode(apic)) {
-			new->ldr_bits = 32;
-			new->cid_shift = 16;
-			new->cid_mask = new->lid_mask = 0xffff;
-			new->broadcast = X2APIC_BROADCAST;
-		} else if (kvm_apic_get_reg(apic, APIC_LDR)) {
-			if (kvm_apic_get_reg(apic, APIC_DFR) ==
-							APIC_DFR_CLUSTER) {
-				new->cid_shift = 4;
-				new->cid_mask = 0xf;
-				new->lid_mask = 0xf;
-			} else {
-				new->cid_shift = 8;
-				new->cid_mask = 0;
-				new->lid_mask = 0xff;
-			}
-		}
-
-		/*
-		 * All APICs have to be configured in the same mode by an OS.
-		 * We take advatage of this while building logical id loockup
-		 * table. After reset APICs are in software disabled mode, so if
-		 * we find apic with different setting we assume this is the mode
-		 * OS wants all apics to be in; build lookup table accordingly.
-		 */
-		if (kvm_apic_sw_enabled(apic))
-			break;
-	}
-
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		struct kvm_lapic *apic = vcpu->arch.apic;
 		u16 cid, lid;
@@ -198,11 +178,25 @@ static void recalculate_apic_map(struct kvm *kvm)
 
 		aid = kvm_apic_id(apic);
 		ldr = kvm_apic_get_reg(apic, APIC_LDR);
-		cid = apic_cluster_id(new, ldr);
-		lid = apic_logical_id(new, ldr);
 
 		if (aid < ARRAY_SIZE(new->phys_map))
 			new->phys_map[aid] = apic;
+
+		if (apic_x2apic_mode(apic)) {
+			new->mode |= KVM_APIC_MODE_X2APIC;
+		} else if (ldr) {
+			ldr = GET_APIC_LOGICAL_ID(ldr);
+			if (kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT)
+				new->mode |= KVM_APIC_MODE_XAPIC_FLAT;
+			else
+				new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER;
+		}
+
+		if (!kvm_apic_logical_map_valid(new))
+			continue;
+
+		apic_logical_id(new, ldr, &cid, &lid);
+
 		if (lid && cid < ARRAY_SIZE(new->logical_map))
 			new->logical_map[cid][ffs(lid) - 1] = apic;
 	}
@@ -588,15 +582,23 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr)
 	apic_update_ppr(apic);
 }
 
-static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 dest)
+static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda)
 {
-	return dest == (apic_x2apic_mode(apic) ?
-			X2APIC_BROADCAST : APIC_BROADCAST);
+	if (apic_x2apic_mode(apic))
+		return mda == X2APIC_BROADCAST;
+
+	return GET_APIC_DEST_FIELD(mda) == APIC_BROADCAST;
 }
 
-static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest)
+static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda)
 {
-	return kvm_apic_id(apic) == dest || kvm_apic_broadcast(apic, dest);
+	if (kvm_apic_broadcast(apic, mda))
+		return true;
+
+	if (apic_x2apic_mode(apic))
+		return mda == kvm_apic_id(apic);
+
+	return mda == SET_APIC_DEST_FIELD(kvm_apic_id(apic));
 }
 
 static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
@@ -613,6 +615,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
 		       && (logical_id & mda & 0xffff) != 0;
 
 	logical_id = GET_APIC_LOGICAL_ID(logical_id);
+	mda = GET_APIC_DEST_FIELD(mda);
 
 	switch (kvm_apic_get_reg(apic, APIC_DFR)) {
 	case APIC_DFR_FLAT:
@@ -627,10 +630,27 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
 	}
 }
 
+/* KVM APIC implementation has two quirks
+ *  - dest always begins at 0 while xAPIC MDA has offset 24,
+ *  - IOxAPIC messages have to be delivered (directly) to x2APIC.
+ */
+static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source,
+                                              struct kvm_lapic *target)
+{
+	bool ipi = source != NULL;
+	bool x2apic_mda = apic_x2apic_mode(ipi ? source : target);
+
+	if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda)
+		return X2APIC_BROADCAST;
+
+	return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id);
+}
+
 bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 			   int short_hand, unsigned int dest, int dest_mode)
 {
 	struct kvm_lapic *target = vcpu->arch.apic;
+	u32 mda = kvm_apic_mda(dest, source, target);
 
 	apic_debug("target %p, source %p, dest 0x%x, "
 		   "dest_mode 0x%x, short_hand 0x%x\n",
@@ -640,9 +660,9 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 	switch (short_hand) {
 	case APIC_DEST_NOSHORT:
 		if (dest_mode == APIC_DEST_PHYSICAL)
-			return kvm_apic_match_physical_addr(target, dest);
+			return kvm_apic_match_physical_addr(target, mda);
 		else
-			return kvm_apic_match_logical_addr(target, dest);
+			return kvm_apic_match_logical_addr(target, mda);
 	case APIC_DEST_SELF:
 		return target == source;
 	case APIC_DEST_ALLINC:
@@ -664,6 +684,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 	struct kvm_lapic **dst;
 	int i;
 	bool ret = false;
+	bool x2apic_ipi = src && apic_x2apic_mode(src);
 
 	*r = -1;
 
@@ -675,15 +696,15 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 	if (irq->shorthand)
 		return false;
 
+	if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST))
+		return false;
+
 	rcu_read_lock();
 	map = rcu_dereference(kvm->arch.apic_map);
 
 	if (!map)
 		goto out;
 
-	if (irq->dest_id == map->broadcast)
-		goto out;
-
 	ret = true;
 
 	if (irq->dest_mode == APIC_DEST_PHYSICAL) {
@@ -692,16 +713,20 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 
 		dst = &map->phys_map[irq->dest_id];
 	} else {
-		u32 mda = irq->dest_id << (32 - map->ldr_bits);
-		u16 cid = apic_cluster_id(map, mda);
+		u16 cid;
+
+		if (!kvm_apic_logical_map_valid(map)) {
+			ret = false;
+			goto out;
+		}
+
+		apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap);
 
 		if (cid >= ARRAY_SIZE(map->logical_map))
 			goto out;
 
 		dst = map->logical_map[cid];
 
-		bitmap = apic_logical_id(map, mda);
-
 		if (irq->delivery_mode == APIC_DM_LOWEST) {
 			int l = -1;
 			for_each_set_bit(i, &bitmap, 16) {
@@ -1037,7 +1062,7 @@ static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
 	    addr < apic->base_address + LAPIC_MMIO_LENGTH;
 }
 
-static int apic_mmio_read(struct kvm_io_device *this,
+static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 			   gpa_t address, int len, void *data)
 {
 	struct kvm_lapic *apic = to_lapic(this);
@@ -1357,7 +1382,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	return ret;
 }
 
-static int apic_mmio_write(struct kvm_io_device *this,
+static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 			    gpa_t address, int len, const void *data)
 {
 	struct kvm_lapic *apic = to_lapic(this);
@@ -1497,8 +1522,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		return;
 	}
 
-	if (!kvm_vcpu_is_bsp(apic->vcpu))
-		value &= ~MSR_IA32_APICBASE_BSP;
 	vcpu->arch.apic_base = value;
 
 	/* update jump label if enable bit changes */