[PATCH v13 08/35] KVM: Introduce KVM_SET_USER_MEMORY_REGION2

Sean Christopherson seanjc at google.com
Mon Oct 30 13:25:50 PDT 2023


On Mon, Oct 30, 2023, Paolo Bonzini wrote:
> On 10/27/23 20:21, Sean Christopherson wrote:
> > 
> > +		if (ioctl == KVM_SET_USER_MEMORY_REGION)
> > +			size = sizeof(struct kvm_userspace_memory_region);
> 
> This also needs a memset(&mem, 0, sizeof(mem)), otherwise the out-of-bounds
> access of the commit message becomes a kernel stack read.

Ouch.  There's some irony.  Might be worth doing memset(&mem, -1, sizeof(mem))
though as '0' is a valid file descriptor and a valid file offset.

> Probably worth adding a check on valid flags here.

Definitely needed.  There's a very real bug here.  But rather than duplicate flags
checking or plumb @ioctl all the way to __kvm_set_memory_region(), now that we
have the fancy guard(mutex) and there are no internal calls to kvm_set_memory_region(),
what if we:

  1. Acquire/release slots_lock in __kvm_set_memory_region()
  2. Call kvm_set_memory_region() from x86 code for the internal memslots
  3. Disallow *any* flags for internal memslots
  4. Open code check_memory_region_flags in kvm_vm_ioctl_set_memory_region()
  5. Pass @ioctl to kvm_vm_ioctl_set_memory_region() and allow KVM_MEM_PRIVATE
     only for KVM_SET_USER_MEMORY_REGION2

E.g. this over ~5 patches

---
 arch/x86/kvm/x86.c       |  2 +-
 include/linux/kvm_host.h |  4 +--
 virt/kvm/kvm_main.c      | 65 +++++++++++++++++-----------------------
 3 files changed, 29 insertions(+), 42 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e3eb608b6692..dd3e2017366c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12478,7 +12478,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 		m.guest_phys_addr = gpa;
 		m.userspace_addr = hva;
 		m.memory_size = size;
-		r = __kvm_set_memory_region(kvm, &m);
+		r = kvm_set_memory_region(kvm, &m);
 		if (r < 0)
 			return ERR_PTR_USR(r);
 	}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 687589ce9f63..fbb98efe8200 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1170,7 +1170,7 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_
  *   -- just change its flags
  *
  * Since flags can be changed by some of these operations, the following
- * differentiation is the best we can do for __kvm_set_memory_region():
+ * differentiation is the best we can do for __kvm_set_memory_region().
  */
 enum kvm_mr_change {
 	KVM_MR_CREATE,
@@ -1181,8 +1181,6 @@ enum kvm_mr_change {
 
 int kvm_set_memory_region(struct kvm *kvm,
 			  const struct kvm_userspace_memory_region2 *mem);
-int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region2 *mem);
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 23633984142f..39ceee2f67f2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1608,28 +1608,6 @@ static void kvm_replace_memslot(struct kvm *kvm,
 	}
 }
 
-static int check_memory_region_flags(struct kvm *kvm,
-				     const struct kvm_userspace_memory_region2 *mem)
-{
-	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
-
-	if (kvm_arch_has_private_mem(kvm))
-		valid_flags |= KVM_MEM_PRIVATE;
-
-	/* Dirty logging private memory is not currently supported. */
-	if (mem->flags & KVM_MEM_PRIVATE)
-		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
-
-#ifdef __KVM_HAVE_READONLY_MEM
-	valid_flags |= KVM_MEM_READONLY;
-#endif
-
-	if (mem->flags & ~valid_flags)
-		return -EINVAL;
-
-	return 0;
-}
-
 static void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
 {
 	struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id);
@@ -2014,11 +1992,9 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
  * space.
  *
  * Discontiguous memory is allowed, mostly for framebuffers.
- *
- * Must be called holding kvm->slots_lock for write.
  */
-int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region2 *mem)
+static int __kvm_set_memory_region(struct kvm *kvm,
+				   const struct kvm_userspace_memory_region2 *mem)
 {
 	struct kvm_memory_slot *old, *new;
 	struct kvm_memslots *slots;
@@ -2028,9 +2004,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int as_id, id;
 	int r;
 
-	r = check_memory_region_flags(kvm, mem);
-	if (r)
-		return r;
+	guard(mutex)(&kvm->slots_lock);
 
 	as_id = mem->slot >> 16;
 	id = (u16)mem->slot;
@@ -2139,27 +2113,42 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	kfree(new);
 	return r;
 }
-EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
 			  const struct kvm_userspace_memory_region2 *mem)
 {
-	int r;
+	/* Flags aren't supported for KVM-internal memslots. */
+	if (WARN_ON_ONCE(mem->flags))
+		return -EINVAL;
 
-	mutex_lock(&kvm->slots_lock);
-	r = __kvm_set_memory_region(kvm, mem);
-	mutex_unlock(&kvm->slots_lock);
-	return r;
+	return __kvm_set_memory_region(kvm, mem);
 }
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
-static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
+static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, unsigned int ioctl,
 					  struct kvm_userspace_memory_region2 *mem)
 {
+	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
+
+	if (ioctl == KVM_SET_USER_MEMORY_REGION2 &&
+	    kvm_arch_has_private_mem(kvm))
+		valid_flags |= KVM_MEM_PRIVATE;
+
+	/* Dirty logging private memory is not currently supported. */
+	if (mem->flags & KVM_MEM_PRIVATE)
+		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
+
+#ifdef __KVM_HAVE_READONLY_MEM
+	valid_flags |= KVM_MEM_READONLY;
+#endif
+
+	if (mem->flags & ~valid_flags)
+		return -EINVAL;
+
 	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
-	return kvm_set_memory_region(kvm, mem);
+	return __kvm_set_memory_region(kvm, mem);
 }
 
 #ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
@@ -5145,7 +5134,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&mem, argp, size))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
+		r = kvm_vm_ioctl_set_memory_region(kvm, ioctl, &mem);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {

base-commit: 881375a408c0f4ea451ff14545b59216d2923881
-- 




More information about the linux-riscv mailing list