[RFC,v1,06/26] KVM: Implement kvm_(read|/write)_guest_page for private memory slots

Commit Message

Fuad Tabba Feb. 22, 2024, 4:10 p.m. UTC

Make __kvm_read_guest_page/__kvm_write_guest_page capable of
accessing guest memory if no userspace address is available.
Moreover, check that the memory being accessed is shared with the
host before attempting the access.

KVM at the host might need to access shared memory that is not
mapped in the host userspace but is in fact shared with the host,
e.g., when accounting for stolen time. This allows the access
without relying on the slot's userspace_addr being set.

This does not circumvent protection, since the access is only
attempted if the memory is shared with the host.

Signed-off-by: Fuad Tabba <[e-mail]>
---
 virt/kvm/kvm_main.c | 130 ++++++++++++++++++++++++++++++++++++++------
 1 file changed, 114 insertions(+), 16 deletions(-)

Patch

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index adfee6592f6c..f5a0619cb520 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3446,17 +3446,107 @@  static int next_segment(unsigned long len, int offset)
 		return len;
 }
 
-static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn,
-				 void *data, int offset, int len)
+#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM_MAPPABLE
+static int __kvm_read_private_guest_page(struct kvm *kvm,
+					 struct kvm_memory_slot *slot,
+					 gfn_t gfn, void *data, int offset,
+					 int len)
+{
+	u64 pfn;
+	struct page *page;
+	int r = 0;
+
+	if (size_add(offset, len) > PAGE_SIZE)
+		return -E2BIG;
+
+	mutex_lock(&kvm->slots_lock);
+	if (kvm_any_range_has_memory_attribute(kvm, gfn, gfn + 1,
+		KVM_MEMORY_ATTRIBUTE_NOT_MAPPABLE)) {
+		r = -EPERM;
+		goto out_unlock;
+	}
+
+	r = kvm_gmem_get_pfn_locked(kvm, slot, gfn, &pfn, NULL);
+	if (r)
+		goto out_unlock;
+
+	page = pfn_to_page(pfn);
+	memcpy(data, page_address(page) + offset, len);
+	unlock_page(page);
+	kvm_release_pfn_clean(pfn);
+out_unlock:
+	mutex_unlock(&kvm->slots_lock);
+
+	return r;
+}
+
+static int __kvm_write_private_guest_page(struct kvm *kvm,
+					  struct kvm_memory_slot *slot,
+					  gfn_t gfn, const void *data,
+					  int offset, int len)
+{
+	u64 pfn;
+	struct page *page;
+	int r = 0;
+
+	if (size_add(offset, len) > PAGE_SIZE)
+		return -E2BIG;
+
+	mutex_lock(&kvm->slots_lock);
+	if (kvm_any_range_has_memory_attribute(kvm, gfn, gfn + 1,
+		KVM_MEMORY_ATTRIBUTE_NOT_MAPPABLE)) {
+		r = -EPERM;
+		goto out_unlock;
+	}
+
+	r = kvm_gmem_get_pfn_locked(kvm, slot, gfn, &pfn, NULL);
+	if (r)
+		goto out_unlock;
+
+	page = pfn_to_page(pfn);
+	memcpy(page_address(page) + offset, data, len);
+	unlock_page(page);
+	kvm_release_pfn_dirty(pfn);
+out_unlock:
+	mutex_unlock(&kvm->slots_lock);
+
+	return r;
+}
+#else
+static int __kvm_read_private_guest_page(struct kvm *kvm,
+					 struct kvm_memory_slot *slot,
+					 gfn_t gfn, void *data, int offset,
+					 int len)
+{
+	BUG();
+	return -EIO;
+}
+
+static int __kvm_write_private_guest_page(struct kvm *kvm,
+					  struct kvm_memory_slot *slot,
+					  gfn_t gfn, const void *data,
+					  int offset, int len)
+{
+	BUG();
+	return -EIO;
+}
+#endif /* CONFIG_KVM_GENERIC_PRIVATE_MEM_MAPPABLE */
+
+static int __kvm_read_guest_page(struct kvm *kvm, struct kvm_memory_slot *slot,
+				 gfn_t gfn, void *data, int offset, int len)
 {
-	int r;
 	unsigned long addr;
 
+	if (IS_ENABLED(CONFIG_KVM_GENERIC_PRIVATE_MEM_MAPPABLE) &&
+	    kvm_slot_can_be_private(slot)) {
+		return __kvm_read_private_guest_page(kvm, slot, gfn, data,
+						     offset, len);
+	}
+
 	addr = gfn_to_hva_memslot_prot(slot, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
-	r = __copy_from_user(data, (void __user *)addr + offset, len);
-	if (r)
+	if (__copy_from_user(data, (void __user *)addr + offset, len))
 		return -EFAULT;
 	return 0;
 }
@@ -3466,7 +3556,7 @@  int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 {
 	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
 
-	return __kvm_read_guest_page(slot, gfn, data, offset, len);
+	return __kvm_read_guest_page(kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_read_guest_page);
 
@@ -3475,7 +3565,7 @@  int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data,
 {
 	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 
-	return __kvm_read_guest_page(slot, gfn, data, offset, len);
+	return __kvm_read_guest_page(vcpu->kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page);
 
@@ -3547,19 +3637,27 @@  int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic);
 
+
 static int __kvm_write_guest_page(struct kvm *kvm,
 				  struct kvm_memory_slot *memslot, gfn_t gfn,
-			          const void *data, int offset, int len)
+				  const void *data, int offset, int len)
 {
-	int r;
-	unsigned long addr;
+	if (IS_ENABLED(CONFIG_KVM_GENERIC_PRIVATE_MEM_MAPPABLE) &&
+	    kvm_slot_can_be_private(memslot)) {
+		int r = __kvm_write_private_guest_page(kvm, memslot, gfn, data,
+						       offset, len);
+
+		if (r)
+			return r;
+	} else {
+		unsigned long addr = gfn_to_hva_memslot(memslot, gfn);
+
+		if (kvm_is_error_hva(addr))
+			return -EFAULT;
+		if (__copy_to_user((void __user *)addr + offset, data, len))
+			return -EFAULT;
+	}
 
-	addr = gfn_to_hva_memslot(memslot, gfn);
-	if (kvm_is_error_hva(addr))
-		return -EFAULT;
-	r = __copy_to_user((void __user *)addr + offset, data, len);
-	if (r)
-		return -EFAULT;
 	mark_page_dirty_in_slot(kvm, memslot, gfn);
 	return 0;
 }