Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Gleb Natapov:
 "The highlights of the release are nested EPT and pv-ticketlocks
  support (hypervisor part, guest part, which is most of the code, goes
  through tip tree).  Apart of that there are many fixes for all arches"

Fix up semantic conflicts as discussed in the pull request thread..

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (88 commits)
  ARM: KVM: Add newlines to panic strings
  ARM: KVM: Work around older compiler bug
  ARM: KVM: Simplify tracepoint text
  ARM: KVM: Fix kvm_set_pte assignment
  ARM: KVM: vgic: Bump VGIC_NR_IRQS to 256
  ARM: KVM: Bugfix: vgic_bytemap_get_reg per cpu regs
  ARM: KVM: vgic: fix GICD_ICFGRn access
  ARM: KVM: vgic: simplify vgic_get_target_reg
  KVM: MMU: remove unused parameter
  KVM: PPC: Book3S PR: Rework kvmppc_mmu_book3s_64_xlate()
  KVM: PPC: Book3S PR: Make instruction fetch fallback work for system calls
  KVM: PPC: Book3S PR: Don't corrupt guest state when kernel uses VMX
  KVM: x86: update masterclock when kvmclock_offset is calculated (v2)
  KVM: PPC: Book3S: Fix compile error in XICS emulation
  KVM: PPC: Book3S PR: return appropriate error when allocation fails
  arch: powerpc: kvm: add signed type cast for comparation
  KVM: x86: add comments where MMIO does not return to the emulator
  KVM: vmx: count exits to userspace during invalid guest emulation
  KVM: rename __kvm_io_bus_sort_cmp to kvm_io_bus_cmp
  kvm: optimize away THP checks in kvm_is_mmio_pfn()
  ...

2 files changed, 119 insertions, 59 deletions

diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 17c5ac7..685fc72 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -149,7 +149,7 @@ static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
 {
 	offset >>= 2;
 	BUG_ON(offset > (VGIC_NR_IRQS / 4));
-	if (offset < 4)
+	if (offset < 8)
 		return x->percpu[cpuid] + offset;
 	else
 		return x->shared + offset - 8;
@@ -432,19 +432,13 @@ static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu,
 static u32 vgic_get_target_reg(struct kvm *kvm, int irq)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
-	struct kvm_vcpu *vcpu;
-	int i, c;
-	unsigned long *bmap;
+	int i;
 	u32 val = 0;
 
 	irq -= VGIC_NR_PRIVATE_IRQS;
 
-	kvm_for_each_vcpu(c, vcpu, kvm) {
-		bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]);
-		for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++)
-			if (test_bit(irq + i, bmap))
-				val |= 1 << (c + i * 8);
-	}
+	for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++)
+		val |= 1 << (dist->irq_spi_cpu[irq + i] + i * 8);
 
 	return val;
 }
@@ -547,8 +541,12 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
 				struct kvm_exit_mmio *mmio, phys_addr_t offset)
 {
 	u32 val;
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
-				       vcpu->vcpu_id, offset >> 1);
+	u32 *reg;
+
+	offset >>= 1;
+	reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
+				  vcpu->vcpu_id, offset);
+
 	if (offset & 2)
 		val = *reg >> 16;
 	else
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1580dd4..bf040c4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -102,28 +102,8 @@ static bool largepages_enabled = true;
 
 bool kvm_is_mmio_pfn(pfn_t pfn)
 {
-	if (pfn_valid(pfn)) {
-		int reserved;
-		struct page *tail = pfn_to_page(pfn);
-		struct page *head = compound_trans_head(tail);
-		reserved = PageReserved(head);
-		if (head != tail) {
-			/*
-			 * "head" is not a dangling pointer
-			 * (compound_trans_head takes care of that)
-			 * but the hugepage may have been splitted
-			 * from under us (and we may not hold a
-			 * reference count on the head page so it can
-			 * be reused before we run PageReferenced), so
-			 * we've to check PageTail before returning
-			 * what we just read.
-			 */
-			smp_rmb();
-			if (PageTail(tail))
-				return reserved;
-		}
-		return PageReserved(tail);
-	}
+	if (pfn_valid(pfn))
+		return PageReserved(pfn_to_page(pfn));
 
 	return true;
 }
@@ -731,7 +711,10 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 	update_memslots(slots, new, kvm->memslots->generation);
 	rcu_assign_pointer(kvm->memslots, slots);
 	synchronize_srcu_expedited(&kvm->srcu);
-	return old_memslots; 
+
+	kvm_arch_memslots_updated(kvm);
+
+	return old_memslots;
 }
 
 /*
@@ -1893,7 +1876,7 @@ static struct file_operations kvm_vcpu_fops = {
  */
 static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 {
-	return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR);
+	return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
 }
 
 /*
@@ -2302,7 +2285,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 		return ret;
 	}
 
-	ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR);
+	ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
 	if (ret < 0) {
 		ops->destroy(dev);
 		return ret;
@@ -2586,7 +2569,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		return r;
 	}
 #endif
-	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
 	if (r < 0)
 		kvm_put_kvm(kvm);
 
@@ -2812,11 +2795,9 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 	kfree(bus);
 }
 
-static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
+static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
+                                 const struct kvm_io_range *r2)
 {
-	const struct kvm_io_range *r1 = p1;
-	const struct kvm_io_range *r2 = p2;
-
 	if (r1->addr < r2->addr)
 		return -1;
 	if (r1->addr + r1->len > r2->addr + r2->len)
@@ -2824,6 +2805,11 @@ static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
 	return 0;
 }
 
+static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
+{
+	return kvm_io_bus_cmp(p1, p2);
+}
+
 static int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
 			  gpa_t addr, int len)
 {
@@ -2857,17 +2843,54 @@ static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
 
 	off = range - bus->range;
 
-	while (off > 0 && kvm_io_bus_sort_cmp(&key, &bus->range[off-1]) == 0)
+	while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0)
 		off--;
 
 	return off;
 }
 
+static int __kvm_io_bus_write(struct kvm_io_bus *bus,
+			      struct kvm_io_range *range, const void *val)
+{
+	int idx;
+
+	idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len);
+	if (idx < 0)
+		return -EOPNOTSUPP;
+
+	while (idx < bus->dev_count &&
+		kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
+		if (!kvm_iodevice_write(bus->range[idx].dev, range->addr,
+					range->len, val))
+			return idx;
+		idx++;
+	}
+
+	return -EOPNOTSUPP;
+}
+
 /* kvm_io_bus_write - called under kvm->slots_lock */
 int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		     int len, const void *val)
 {
-	int idx;
+	struct kvm_io_bus *bus;
+	struct kvm_io_range range;
+	int r;
+
+	range = (struct kvm_io_range) {
+		.addr = addr,
+		.len = len,
+	};
+
+	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+	r = __kvm_io_bus_write(bus, &range, val);
+	return r < 0 ? r : 0;
+}
+
+/* kvm_io_bus_write_cookie - called under kvm->slots_lock */
+int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
+			    int len, const void *val, long cookie)
+{
 	struct kvm_io_bus *bus;
 	struct kvm_io_range range;
 
@@ -2877,14 +2900,35 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	idx = kvm_io_bus_get_first_dev(bus, addr, len);
+
+	/* First try the device referenced by cookie. */
+	if ((cookie >= 0) && (cookie < bus->dev_count) &&
+	    (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
+		if (!kvm_iodevice_write(bus->range[cookie].dev, addr, len,
+					val))
+			return cookie;
+
+	/*
+	 * cookie contained garbage; fall back to search and return the
+	 * correct cookie value.
+	 */
+	return __kvm_io_bus_write(bus, &range, val);
+}
+
+static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
+			     void *val)
+{
+	int idx;
+
+	idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len);
 	if (idx < 0)
 		return -EOPNOTSUPP;
 
 	while (idx < bus->dev_count &&
-		kvm_io_bus_sort_cmp(&range, &bus->range[idx]) == 0) {
-		if (!kvm_iodevice_write(bus->range[idx].dev, addr, len, val))
-			return 0;
+		kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
+		if (!kvm_iodevice_read(bus->range[idx].dev, range->addr,
+				       range->len, val))
+			return idx;
 		idx++;
 	}
 
@@ -2895,9 +2939,9 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		    int len, void *val)
 {
-	int idx;
 	struct kvm_io_bus *bus;
 	struct kvm_io_range range;
+	int r;
 
 	range = (struct kvm_io_range) {
 		.addr = addr,
@@ -2905,18 +2949,36 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	idx = kvm_io_bus_get_first_dev(bus, addr, len);
-	if (idx < 0)
-		return -EOPNOTSUPP;
+	r = __kvm_io_bus_read(bus, &range, val);
+	return r < 0 ? r : 0;
+}
 
-	while (idx < bus->dev_count &&
-		kvm_io_bus_sort_cmp(&range, &bus->range[idx]) == 0) {
-		if (!kvm_iodevice_read(bus->range[idx].dev, addr, len, val))
-			return 0;
-		idx++;
-	}
+/* kvm_io_bus_read_cookie - called under kvm->slots_lock */
+int kvm_io_bus_read_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
+			   int len, void *val, long cookie)
+{
+	struct kvm_io_bus *bus;
+	struct kvm_io_range range;
 
-	return -EOPNOTSUPP;
+	range = (struct kvm_io_range) {
+		.addr = addr,
+		.len = len,
+	};
+
+	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+
+	/* First try the device referenced by cookie. */
+	if ((cookie >= 0) && (cookie < bus->dev_count) &&
+	    (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
+		if (!kvm_iodevice_read(bus->range[cookie].dev, addr, len,
+				       val))
+			return cookie;
+
+	/*
+	 * cookie contained garbage; fall back to search and return the
+	 * correct cookie value.
+	 */
+	return __kvm_io_bus_read(bus, &range, val);
 }
 
 /* Caller must hold slots_lock. */