KVM: implement multiple address spaces

Only two ioctls have to be modified; the address space id is
placed in the higher 16 bits of their slot id argument.

As of this patch, no architecture defines more than one
address space; x86 will be the first.
Reviewed-by: NRadim Krčmář <rkrcmar@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Documentation/virtual/kvm/api.txt

@@ -254,6 +254,11 @@ since the last call to this ioctl.  Bit 0 is the first page in the
 memory slot.  Ensure the entire structure is cleared to avoid padding
 issues.
 
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
+the address space for which you want to return the dirty bitmap.
+They must be less than the value that KVM_CHECK_EXTENSION returns for
+the KVM_CAP_MULTI_ADDRESS_SPACE capability.
+
 
 4.9 KVM_SET_MEMORY_ALIAS
 
@@ -924,6 +929,13 @@ slot.  When changing an existing slot, it may be moved in the guest
 physical memory space, or its flags may be modified.  It may not be
 resized.  Slots may not overlap in guest physical address space.
 
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
+specifies the address space which is being modified.  They must be
+less than the value that KVM_CHECK_EXTENSION returns for the
+KVM_CAP_MULTI_ADDRESS_SPACE capability.  Slots in separate address spaces
+are unrelated; the restriction on overlapping slots only applies within
+each address space.
+
 Memory for the region is taken starting at the address denoted by the
 field userspace_addr, which must point at user addressable memory for
 the entire memory slot size.  Any object may back this memory, including

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -430,7 +430,7 @@ static inline void note_hpte_modification(struct kvm *kvm,
  */
 static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
 {
-	return rcu_dereference_raw_notrace(kvm->memslots);
+	return rcu_dereference_raw_notrace(kvm->memslots[0]);
 }
 
 extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);

include/linux/kvm_host.h

@@ -44,6 +44,10 @@
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
 
+#ifndef KVM_ADDRESS_SPACE_NUM
+#define KVM_ADDRESS_SPACE_NUM	1
+#endif
+
 /*
  * For the normal pfn, the highest 12 bits should be zero,
  * so we can mask bit 62 ~ bit 52  to indicate the error pfn,
@@ -331,6 +335,13 @@ struct kvm_kernel_irq_routing_entry {
 #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 #endif
 
+#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+#endif
+
 /*
  * Note:
  * memslots are not sorted by id anymore, please use id_to_memslot()
@@ -349,7 +360,7 @@ struct kvm {
 	spinlock_t mmu_lock;
 	struct mutex slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
-	struct kvm_memslots *memslots;
+	struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM];
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
@@ -464,16 +475,23 @@ void kvm_exit(void);
 void kvm_get_kvm(struct kvm *kvm);
 void kvm_put_kvm(struct kvm *kvm);
 
-static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
+static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	return rcu_dereference_check(kvm->memslots,
+	return rcu_dereference_check(kvm->memslots[as_id],
 			srcu_read_lock_held(&kvm->srcu)
 			|| lockdep_is_held(&kvm->slots_lock));
 }
 
+static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
+{
+	return __kvm_memslots(kvm, 0);
+}
+
 static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu)
 {
-	return kvm_memslots(vcpu->kvm);
+	int as_id = kvm_arch_vcpu_memslots_id(vcpu);
+
+	return __kvm_memslots(vcpu->kvm, as_id);
 }
 
 static inline struct kvm_memory_slot *

include/uapi/linux/kvm.h

@@ -816,6 +816,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_HWRNG 115
 #define KVM_CAP_DISABLE_QUIRKS 116
 #define KVM_CAP_X86_SMM 117
+#define KVM_CAP_MULTI_ADDRESS_SPACE 118
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

virt/kvm/kvm_main.c

@@ -518,9 +518,11 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
 	r = -ENOMEM;
-	kvm->memslots = kvm_alloc_memslots();
-	if (!kvm->memslots)
-		goto out_err_no_srcu;
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		kvm->memslots[i] = kvm_alloc_memslots();
+		if (!kvm->memslots[i])
+			goto out_err_no_srcu;
+	}
 
 	if (init_srcu_struct(&kvm->srcu))
 		goto out_err_no_srcu;
@@ -562,7 +564,8 @@ static struct kvm *kvm_create_vm(unsigned long type)
 out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
-	kvm_free_memslots(kvm, kvm->memslots);
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
+		kvm_free_memslots(kvm, kvm->memslots[i]);
 	kvm_arch_free_vm(kvm);
 	return ERR_PTR(r);
 }
@@ -612,7 +615,8 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
-	kvm_free_memslots(kvm, kvm->memslots);
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
+		kvm_free_memslots(kvm, kvm->memslots[i]);
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
@@ -729,9 +733,9 @@ static int check_memory_region_flags(const struct kvm_userspace_memory_region *m
 }
 
 static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
-		struct kvm_memslots *slots)
+		int as_id, struct kvm_memslots *slots)
 {
-	struct kvm_memslots *old_memslots = kvm_memslots(kvm);
+	struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id);
 
 	/*
 	 * Set the low bit in the generation, which disables SPTE caching
@@ -740,7 +744,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 	WARN_ON(old_memslots->generation & 1);
 	slots->generation = old_memslots->generation + 1;
 
-	rcu_assign_pointer(kvm->memslots, slots);
+	rcu_assign_pointer(kvm->memslots[as_id], slots);
 	synchronize_srcu_expedited(&kvm->srcu);
 
 	/*
@@ -772,6 +776,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	struct kvm_memory_slot *slot;
 	struct kvm_memory_slot old, new;
 	struct kvm_memslots *slots = NULL, *old_memslots;
+	int as_id, id;
 	enum kvm_mr_change change;
 
 	r = check_memory_region_flags(mem);
@@ -779,24 +784,27 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		goto out;
 
 	r = -EINVAL;
+	as_id = mem->slot >> 16;
+	id = (u16)mem->slot;
+
 	/* General sanity checks */
 	if (mem->memory_size & (PAGE_SIZE - 1))
 		goto out;
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		goto out;
 	/* We can read the guest memory with __xxx_user() later on. */
-	if ((mem->slot < KVM_USER_MEM_SLOTS) &&
+	if ((id < KVM_USER_MEM_SLOTS) &&
 	    ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
 	     !access_ok(VERIFY_WRITE,
 			(void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size)))
 		goto out;
-	if (mem->slot >= KVM_MEM_SLOTS_NUM)
+	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
 		goto out;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		goto out;
 
-	slot = id_to_memslot(kvm_memslots(kvm), mem->slot);
+	slot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
@@ -805,7 +813,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	new = old = *slot;
 
-	new.id = mem->slot;
+	new.id = id;
 	new.base_gfn = base_gfn;
 	new.npages = npages;
 	new.flags = mem->flags;
@@ -840,9 +848,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
 		/* Check for overlaps */
 		r = -EEXIST;
-		kvm_for_each_memslot(slot, kvm_memslots(kvm)) {
+		kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) {
 			if ((slot->id >= KVM_USER_MEM_SLOTS) ||
-			    (slot->id == mem->slot))
+			    (slot->id == id))
 				continue;
 			if (!((base_gfn + npages <= slot->base_gfn) ||
 			      (base_gfn >= slot->base_gfn + slot->npages)))
@@ -871,13 +879,13 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	slots = kvm_kvzalloc(sizeof(struct kvm_memslots));
 	if (!slots)
 		goto out_free;
-	memcpy(slots, kvm_memslots(kvm), sizeof(struct kvm_memslots));
+	memcpy(slots, __kvm_memslots(kvm, as_id), sizeof(struct kvm_memslots));
 
 	if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
-		slot = id_to_memslot(slots, mem->slot);
+		slot = id_to_memslot(slots, id);
 		slot->flags |= KVM_MEMSLOT_INVALID;
 
-		old_memslots = install_new_memslots(kvm, slots);
+		old_memslots = install_new_memslots(kvm, as_id, slots);
 
 		/* slot was deleted or moved, clear iommu mapping */
 		kvm_iommu_unmap_pages(kvm, &old);
@@ -909,7 +917,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	}
 
 	update_memslots(slots, &new);
-	old_memslots = install_new_memslots(kvm, slots);
+	old_memslots = install_new_memslots(kvm, as_id, slots);
 
 	kvm_arch_commit_memory_region(kvm, mem, &old, &new, change);
 
@@ -956,7 +964,7 @@ EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
 					  struct kvm_userspace_memory_region *mem)
 {
-	if (mem->slot >= KVM_USER_MEM_SLOTS)
+	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	return kvm_set_memory_region(kvm, mem);
@@ -967,16 +975,18 @@ int kvm_get_dirty_log(struct kvm *kvm,
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
-	int r, i;
+	int r, i, as_id, id;
 	unsigned long n;
 	unsigned long any = 0;
 
 	r = -EINVAL;
-	if (log->slot >= KVM_USER_MEM_SLOTS)
+	as_id = log->slot >> 16;
+	id = (u16)log->slot;
+	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
 		goto out;
 
-	slots = kvm_memslots(kvm);
-	memslot = id_to_memslot(slots, log->slot);
+	slots = __kvm_memslots(kvm, as_id);
+	memslot = id_to_memslot(slots, id);
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
@@ -1027,17 +1037,19 @@ int kvm_get_dirty_log_protect(struct kvm *kvm,
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
-	int r, i;
+	int r, i, as_id, id;
 	unsigned long n;
 	unsigned long *dirty_bitmap;
 	unsigned long *dirty_bitmap_buffer;
 
 	r = -EINVAL;
-	if (log->slot >= KVM_USER_MEM_SLOTS)
+	as_id = log->slot >> 16;
+	id = (u16)log->slot;
+	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
 		goto out;
 
-	slots = kvm_memslots(kvm);
-	memslot = id_to_memslot(slots, log->slot);
+	slots = __kvm_memslots(kvm, as_id);
+	memslot = id_to_memslot(slots, id);
 
 	dirty_bitmap = memslot->dirty_bitmap;
 	r = -ENOENT;
@@ -2619,6 +2631,10 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
+#endif
+#if KVM_ADDRESS_SPACE_NUM > 1
+	case KVM_CAP_MULTI_ADDRESS_SPACE:
+		return KVM_ADDRESS_SPACE_NUM;
 #endif
 	default:
 		break;