KVM: X86: Don't track dirty for KVM_SET_[TSS_ADDR|IDENTITY_MAP_ADDR]

Originally, we have three code paths that can dirty a page without
vcpu context for X86:

  - init_rmode_identity_map
  - init_rmode_tss
  - kvmgt_rw_gpa

init_rmode_identity_map and init_rmode_tss will be setup on
destination VM no matter what (and the guest cannot even see them), so
it does not make sense to track them at all.

To do this, allow __x86_set_memory_region() to return the userspace
address that just allocated to the caller.  Then in both of the
functions we directly write to the userspace address instead of
calling kvm_write_*() APIs.

Another trivial change is that we don't need to explicitly clear the
identity page table root in init_rmode_identity_map() because no
matter what we'll write to the whole page with 4M huge page entries.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012044.5151-4-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 31 insertions, 6 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 773cb52cb775..b4ac726526f8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10354,7 +10354,32 @@ void kvm_arch_sync_events(struct kvm *kvm)
 	kvm_free_pit(kvm);
 }
 
-int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
+#define  ERR_PTR_USR(e)  ((void __user *)ERR_PTR(e))
+
+/**
+ * __x86_set_memory_region: Setup KVM internal memory slot
+ *
+ * @kvm: the kvm pointer to the VM.
+ * @id: the slot ID to setup.
+ * @gpa: the GPA to install the slot (unused when @size == 0).
+ * @size: the size of the slot. Set to zero to uninstall a slot.
+ *
+ * This function helps to setup a KVM internal memory slot.  Specify
+ * @size > 0 to install a new slot, while @size == 0 to uninstall a
+ * slot.  The return code can be one of the following:
+ *
+ *   HVA:           on success (uninstall will return a bogus HVA)
+ *   -errno:        on error
+ *
+ * The caller should always use IS_ERR() to check the return value
+ * before use.  Note, the KVM internal memory slots are guaranteed to
+ * remain valid and unchanged until the VM is destroyed, i.e., the
+ * GPA->HVA translation will not change.  However, the HVA is a user
+ * address, i.e. its accessibility is not guaranteed, and must be
+ * accessed via __copy_{to,from}_user().
+ */
+void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
+				      u32 size)
 {
 	int i, r;
 	unsigned long hva, old_npages;
@@ -10363,12 +10388,12 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 
 	/* Called with kvm->slots_lock held.  */
 	if (WARN_ON(id >= KVM_MEM_SLOTS_NUM))
-		return -EINVAL;
+		return ERR_PTR_USR(-EINVAL);
 
 	slot = id_to_memslot(slots, id);
 	if (size) {
 		if (slot && slot->npages)
-			return -EEXIST;
+			return ERR_PTR_USR(-EEXIST);
 
 		/*
 		 * MAP_SHARED to prevent internal slot pages from being moved
@@ -10377,7 +10402,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 		hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE,
 			      MAP_SHARED | MAP_ANONYMOUS, 0);
 		if (IS_ERR((void *)hva))
-			return PTR_ERR((void *)hva);
+			return (void __user *)hva;
 	} else {
 		if (!slot || !slot->npages)
 			return 0;
@@ -10396,13 +10421,13 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 		m.memory_size = size;
 		r = __kvm_set_memory_region(kvm, &m);
 		if (r < 0)
-			return r;
+			return ERR_PTR_USR(r);
 	}
 
 	if (!size)
 		vm_munmap(hva, old_npages * PAGE_SIZE);
 
-	return 0;
+	return (void __user *)hva;
 }
 EXPORT_SYMBOL_GPL(__x86_set_memory_region);