initial merge with 3.2.72

1 files changed, 230 insertions, 30 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index caa3bb1..53c1746 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -47,9 +47,12 @@
 #include <linux/srcu.h>
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/bsearch.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
+#include <asm/ioctl.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
@@ -84,6 +87,10 @@ struct dentry *kvm_debugfs_dir;
 
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
+#ifdef CONFIG_COMPAT
+static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
+				  unsigned long arg);
+#endif
 static int hardware_enable_all(void);
 static void hardware_disable_all(void);
 
@@ -97,8 +104,8 @@ static bool largepages_enabled = true;
 static struct page *hwpoison_page;
 static pfn_t hwpoison_pfn;
 
-static struct page *fault_page;
-static pfn_t fault_pfn;
+struct page *fault_page;
+pfn_t fault_pfn;
 
 inline int kvm_is_mmio_pfn(pfn_t pfn)
 {
@@ -283,15 +290,15 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
 	 */
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
+
 	kvm->mmu_notifier_seq++;
 	need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty;
-	spin_unlock(&kvm->mmu_lock);
-	srcu_read_unlock(&kvm->srcu, idx);
-
 	/* we've to flush the tlb before the pages can be freed */
 	if (need_tlb_flush)
 		kvm_flush_remote_tlbs(kvm);
 
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
 }
 
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
@@ -329,12 +336,12 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	for (; start < end; start += PAGE_SIZE)
 		need_tlb_flush |= kvm_unmap_hva(kvm, start);
 	need_tlb_flush |= kvm->tlbs_dirty;
-	spin_unlock(&kvm->mmu_lock);
-	srcu_read_unlock(&kvm->srcu, idx);
-
 	/* we've to flush the tlb before the pages can be freed */
 	if (need_tlb_flush)
 		kvm_flush_remote_tlbs(kvm);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
@@ -372,13 +379,14 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
-	young = kvm_age_hva(kvm, address);
-	spin_unlock(&kvm->mmu_lock);
-	srcu_read_unlock(&kvm->srcu, idx);
 
+	young = kvm_age_hva(kvm, address);
 	if (young)
 		kvm_flush_remote_tlbs(kvm);
 
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+
 	return young;
 }
 
@@ -767,7 +775,7 @@ skip_lpage:
 		new.userspace_addr = mem->userspace_addr;
 #endif /* not defined CONFIG_S390 */
 
-	if (!npages) {
+	if (!npages || base_gfn != old.base_gfn) {
 		r = -ENOMEM;
 		slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 		if (!slots)
@@ -781,8 +789,10 @@ skip_lpage:
 		old_memslots = kvm->memslots;
 		rcu_assign_pointer(kvm->memslots, slots);
 		synchronize_srcu_expedited(&kvm->srcu);
-		/* From this point no new shadow pages pointing to a deleted
-		 * memslot will be created.
+		/* slot was deleted or moved, clear iommu mapping */
+		kvm_iommu_unmap_pages(kvm, &old);
+		/* From this point no new shadow pages pointing to a deleted,
+		 * or moved, memslot will be created.
 		 *
 		 * validation of sp->gfn happens in:
 		 * 	- gfn_to_hva (kvm_read_guest, gfn_to_pfn)
@@ -813,6 +823,13 @@ skip_lpage:
 		slots->nmemslots = mem->slot + 1;
 	slots->generation++;
 
+	/* map new memory slot into the iommu */
+	if (npages) {
+		r = kvm_iommu_map_pages(kvm, &new);
+		if (r)
+			goto out_slots;
+	}
+
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
 	if (!npages) {
 		new.rmap = NULL;
@@ -828,11 +845,20 @@ skip_lpage:
 
 	kvm_arch_commit_memory_region(kvm, mem, old, user_alloc);
 
+	/*
+	 * If the new memory slot is created, we need to clear all
+	 * mmio sptes.
+	 */
+	if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT)
+		kvm_arch_flush_shadow(kvm);
+
 	kvm_free_physmem_slot(&old, &new);
 	kfree(old_memslots);
 
 	return 0;
 
+out_slots:
+	kfree(slots);
 out_free:
 	kvm_free_physmem_slot(&new, &old);
 out:
@@ -928,6 +954,18 @@ int is_fault_pfn(pfn_t pfn)
 }
 EXPORT_SYMBOL_GPL(is_fault_pfn);
 
+int is_noslot_pfn(pfn_t pfn)
+{
+	return pfn == bad_pfn;
+}
+EXPORT_SYMBOL_GPL(is_noslot_pfn);
+
+int is_invalid_pfn(pfn_t pfn)
+{
+	return pfn == hwpoison_pfn || pfn == fault_pfn;
+}
+EXPORT_SYMBOL_GPL(is_invalid_pfn);
+
 static inline unsigned long bad_hva(void)
 {
 	return PAGE_OFFSET;
@@ -1346,7 +1384,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
 	addr = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
-	r = copy_to_user((void __user *)addr + offset, data, len);
+	r = __copy_to_user((void __user *)addr + offset, data, len);
 	if (r)
 		return -EFAULT;
 	mark_page_dirty(kvm, gfn);
@@ -1407,7 +1445,6 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 		/* Use the slow path for cross page reads and writes. */
 		ghc->memslot = NULL;
 	}
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
@@ -1429,7 +1466,7 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
 
-	r = copy_to_user((void __user *)ghc->hva, data, len);
+	r = __copy_to_user((void __user *)ghc->hva, data, len);
 	if (r)
 		return -EFAULT;
 	mark_page_dirty_in_slot(kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT);
@@ -1438,6 +1475,31 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
 
+int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, unsigned long len)
+{
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	int r;
+
+	BUG_ON(len > ghc->len);
+
+	if (slots->generation != ghc->generation)
+		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+	if (unlikely(!ghc->memslot))
+		return kvm_read_guest(kvm, ghc->gpa, data, len);
+
+	if (kvm_is_error_hva(ghc->hva))
+		return -EFAULT;
+
+	r = __copy_from_user(data, (void __user *)ghc->hva, len);
+	if (r)
+		return -EFAULT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
+
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
 {
 	return kvm_write_guest_page(kvm, gfn, (const void *) empty_zero_page,
@@ -1610,7 +1672,9 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp)
 static struct file_operations kvm_vcpu_fops = {
 	.release        = kvm_vcpu_release,
 	.unlocked_ioctl = kvm_vcpu_ioctl,
-	.compat_ioctl   = kvm_vcpu_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = kvm_vcpu_compat_ioctl,
+#endif
 	.mmap           = kvm_vcpu_mmap,
 	.llseek		= noop_llseek,
 };
@@ -1631,6 +1695,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	int r;
 	struct kvm_vcpu *vcpu, *v;
 
+	if (id >= KVM_MAX_VCPUS)
+		return -EINVAL;
+
 	vcpu = kvm_arch_vcpu_create(kvm, id);
 	if (IS_ERR(vcpu))
 		return PTR_ERR(vcpu);
@@ -1708,6 +1775,9 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	if (vcpu->kvm->mm != current->mm)
 		return -EIO;
 
+	if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
+		return -EINVAL;
+
 #if defined(CONFIG_S390) || defined(CONFIG_PPC)
 	/*
 	 * Special cases: vcpu ioctls that are asynchronous to vcpu execution,
@@ -1903,6 +1973,50 @@ out:
 	return r;
 }
 
+#ifdef CONFIG_COMPAT
+static long kvm_vcpu_compat_ioctl(struct file *filp,
+				  unsigned int ioctl, unsigned long arg)
+{
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = compat_ptr(arg);
+	int r;
+
+	if (vcpu->kvm->mm != current->mm)
+		return -EIO;
+
+	switch (ioctl) {
+	case KVM_SET_SIGNAL_MASK: {
+		struct kvm_signal_mask __user *sigmask_arg = argp;
+		struct kvm_signal_mask kvm_sigmask;
+		compat_sigset_t csigset;
+		sigset_t sigset;
+
+		if (argp) {
+			r = -EFAULT;
+			if (copy_from_user(&kvm_sigmask, argp,
+					   sizeof kvm_sigmask))
+				goto out;
+			r = -EINVAL;
+			if (kvm_sigmask.len != sizeof csigset)
+				goto out;
+			r = -EFAULT;
+			if (copy_from_user(&csigset, sigmask_arg->sigset,
+					   sizeof csigset))
+				goto out;
+		}
+		sigset_from_compat(&sigset, &csigset);
+		r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
+		break;
+	}
+	default:
+		r = kvm_vcpu_ioctl(filp, ioctl, arg);
+	}
+
+out:
+	return r;
+}
+#endif
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -2330,24 +2444,92 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 	int i;
 
 	for (i = 0; i < bus->dev_count; i++) {
-		struct kvm_io_device *pos = bus->devs[i];
+		struct kvm_io_device *pos = bus->range[i].dev;
 
 		kvm_iodevice_destructor(pos);
 	}
 	kfree(bus);
 }
 
+int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
+{
+	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)
+		return 1;
+	return 0;
+}
+
+int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
+			  gpa_t addr, int len)
+{
+	if (bus->dev_count == NR_IOBUS_DEVS)
+		return -ENOSPC;
+
+	bus->range[bus->dev_count++] = (struct kvm_io_range) {
+		.addr = addr,
+		.len = len,
+		.dev = dev,
+	};
+
+	sort(bus->range, bus->dev_count, sizeof(struct kvm_io_range),
+		kvm_io_bus_sort_cmp, NULL);
+
+	return 0;
+}
+
+int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
+			     gpa_t addr, int len)
+{
+	struct kvm_io_range *range, key;
+	int off;
+
+	key = (struct kvm_io_range) {
+		.addr = addr,
+		.len = len,
+	};
+
+	range = bsearch(&key, bus->range, bus->dev_count,
+			sizeof(struct kvm_io_range), kvm_io_bus_sort_cmp);
+	if (range == NULL)
+		return -ENOENT;
+
+	off = range - bus->range;
+
+	while (off > 0 && kvm_io_bus_sort_cmp(&key, &bus->range[off-1]) == 0)
+		off--;
+
+	return off;
+}
+
 /* 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 i;
+	int idx;
 	struct kvm_io_bus *bus;
+	struct kvm_io_range range;
+
+	range = (struct kvm_io_range) {
+		.addr = addr,
+		.len = len,
+	};
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	for (i = 0; i < bus->dev_count; i++)
-		if (!kvm_iodevice_write(bus->devs[i], addr, len, val))
+	idx = kvm_io_bus_get_first_dev(bus, addr, 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;
+		idx++;
+	}
+
 	return -EOPNOTSUPP;
 }
 
@@ -2355,19 +2537,33 @@ 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 i;
+	int idx;
 	struct kvm_io_bus *bus;
+	struct kvm_io_range range;
+
+	range = (struct kvm_io_range) {
+		.addr = addr,
+		.len = len,
+	};
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	for (i = 0; i < bus->dev_count; i++)
-		if (!kvm_iodevice_read(bus->devs[i], addr, len, val))
+	idx = kvm_io_bus_get_first_dev(bus, addr, len);
+	if (idx < 0)
+		return -EOPNOTSUPP;
+
+	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++;
+	}
+
 	return -EOPNOTSUPP;
 }
 
 /* Caller must hold slots_lock. */
-int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx,
-			    struct kvm_io_device *dev)
+int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
+			    int len, struct kvm_io_device *dev)
 {
 	struct kvm_io_bus *new_bus, *bus;
 
@@ -2379,7 +2575,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	if (!new_bus)
 		return -ENOMEM;
 	memcpy(new_bus, bus, sizeof(struct kvm_io_bus));
-	new_bus->devs[new_bus->dev_count++] = dev;
+	kvm_io_bus_insert_dev(new_bus, dev, addr, len);
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);
@@ -2403,9 +2599,13 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 
 	r = -ENOENT;
 	for (i = 0; i < new_bus->dev_count; i++)
-		if (new_bus->devs[i] == dev) {
+		if (new_bus->range[i].dev == dev) {
 			r = 0;
-			new_bus->devs[i] = new_bus->devs[--new_bus->dev_count];
+			new_bus->dev_count--;
+			new_bus->range[i] = new_bus->range[new_bus->dev_count];
+			sort(new_bus->range, new_bus->dev_count,
+			     sizeof(struct kvm_io_range),
+			     kvm_io_bus_sort_cmp, NULL);
 			break;
 		}