[v3,15/15] KVM: Register/unregister private memory slot to memfd

Commit Message

Chao Peng Dec. 21, 2021, 3:11 p.m. UTC

Expose KVM_MEM_PRIVATE flag and register/unregister private memory
slot to memfd when userspace sets the flag.

KVM_MEM_PRIVATE is disallowed by default but architecture code can
turn it on by implementing kvm_arch_private_memory_supported().

Signed-off-by: Yu Zhang <[e-mail]>
Signed-off-by: Chao Peng <[e-mail]>
---
 include/linux/kvm_host.h |  2 ++
 virt/kvm/kvm_main.c      | 35 +++++++++++++++++++++++++++++++----
 2 files changed, 33 insertions(+), 4 deletions(-)

Patch

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0c53df0a6b2e..0f0e24f19892 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1096,6 +1096,8 @@  int kvm_arch_post_init_vm(struct kvm *kvm);
 void kvm_arch_pre_destroy_vm(struct kvm *kvm);
 int kvm_arch_create_vm_debugfs(struct kvm *kvm);
 bool kvm_arch_dirty_log_supported(struct kvm *kvm);
+bool kvm_arch_private_memory_supported(struct kvm *kvm);
+
 
 #ifndef __KVM_HAVE_ARCH_VM_ALLOC
 /*
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 79313c549fb9..6eb0d86abdcf 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1509,6 +1509,11 @@  bool __weak kvm_arch_dirty_log_supported(struct kvm *kvm)
 	return true;
 }
 
+bool __weak kvm_arch_private_memory_supported(struct kvm *kvm)
+{
+	return false;
+}
+
 static int check_memory_region_flags(struct kvm *kvm,
 			     const struct kvm_userspace_memory_region_ext *mem)
 {
@@ -1517,6 +1522,9 @@  static int check_memory_region_flags(struct kvm *kvm,
 	if (kvm_arch_dirty_log_supported(kvm))
 		valid_flags |= KVM_MEM_LOG_DIRTY_PAGES;
 
+	if (kvm_arch_private_memory_supported(kvm))
+		valid_flags |= KVM_MEM_PRIVATE;
+
 #ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
@@ -1708,9 +1716,21 @@  static int kvm_set_memslot(struct kvm *kvm,
 	/* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */
 	memcpy(&new->arch, &old.arch, sizeof(old.arch));
 
+	if (mem->flags & KVM_MEM_PRIVATE && change == KVM_MR_CREATE) {
+		r = kvm_memfd_register(kvm, mem, new);
+		if (r)
+			goto out_slots;
+	}
+
 	r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
-	if (r)
+	if (r) {
+		if (mem->flags & KVM_MEM_PRIVATE && change == KVM_MR_CREATE)
+			kvm_memfd_unregister(kvm, new);
 		goto out_slots;
+	}
+
+	if (mem->flags & KVM_MEM_PRIVATE && change == KVM_MR_DELETE)
+		kvm_memfd_unregister(kvm, new);
 
 	update_memslots(slots, new, change);
 	slots = install_new_memslots(kvm, as_id, slots);
@@ -1786,10 +1806,12 @@  int __kvm_set_memory_region(struct kvm *kvm,
 		return -EINVAL;
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		return -EINVAL;
-	/* We can read the guest memory with __xxx_user() later on. */
 	if ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
-	    (mem->userspace_addr != untagged_addr(mem->userspace_addr)) ||
-	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
+	    (mem->userspace_addr != untagged_addr(mem->userspace_addr)))
+		return -EINVAL;
+	/* We can read the guest memory with __xxx_user() later on. */
+	if (!(mem->flags & KVM_MEM_PRIVATE) &&
+	    !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
@@ -1821,6 +1843,8 @@  int __kvm_set_memory_region(struct kvm *kvm,
 	new.npages = mem->memory_size >> PAGE_SHIFT;
 	new.flags = mem->flags;
 	new.userspace_addr = mem->userspace_addr;
+	new.file = NULL;
+	new.file_ofs = 0;
 
 	if (new.npages > KVM_MEM_MAX_NR_PAGES)
 		return -EINVAL;
@@ -1829,6 +1853,9 @@  int __kvm_set_memory_region(struct kvm *kvm,
 		change = KVM_MR_CREATE;
 		new.dirty_bitmap = NULL;
 	} else { /* Modify an existing slot. */
+		/* Private memslots are immutable, they can only be deleted. */
+		if (mem->flags & KVM_MEM_PRIVATE)
+			return -EINVAL;
 		if ((new.userspace_addr != old.userspace_addr) ||
 		    (new.npages != old.npages) ||
 		    ((new.flags ^ old.flags) & KVM_MEM_READONLY))