[PATCH v3 kvm/queue 16/16] KVM: Register/unregister private memory slot to memfd

[Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>]

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 on it by implementing kvm_arch_private_memory_supported().

Signed-off-by: Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>
Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
---
 include/linux/kvm_host.h |  1 +
 virt/kvm/kvm_main.c      | 34 ++++++++++++++++++++++++++++++++--
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index fabab3b77d57..5173c52e70d4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1229,6 +1229,7 @@ bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
 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_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 cf8dcb3b8c7f..1caebded52c4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1514,10 +1514,19 @@ static void kvm_replace_memslot(struct kvm *kvm,
 	}
 }
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region_ext *mem)
+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)
 {
 	u32 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
@@ -1756,6 +1765,8 @@ static void kvm_delete_memslot(struct kvm *kvm,
 			       struct kvm_memory_slot *old,
 			       struct kvm_memory_slot *invalid_slot)
 {
+	if (old->flags & KVM_MEM_PRIVATE)
+		kvm_memfd_unregister(old);
 	/*
 	 * Remove the old memslot (in the inactive memslots) by passing NULL as
 	 * the "new" slot, and for the invalid version in the active slots.
@@ -1836,6 +1847,14 @@ static int kvm_set_memslot(struct kvm *kvm,
 		kvm_invalidate_memslot(kvm, old, invalid_slot);
 	}
 
+	if (new->flags & KVM_MEM_PRIVATE && change == KVM_MR_CREATE) {
+		r = kvm_memfd_register(kvm, new);
+		if (r) {
+			mutex_unlock(&kvm->slots_arch_lock);
+			return r;
+		}
+	}
+
 	r = kvm_prepare_memory_region(kvm, old, new, change);
 	if (r) {
 		/*
@@ -1850,6 +1869,10 @@ static int kvm_set_memslot(struct kvm *kvm,
 		} else {
 			mutex_unlock(&kvm->slots_arch_lock);
 		}
+
+		if (new->flags & KVM_MEM_PRIVATE && change == KVM_MR_CREATE)
+			kvm_memfd_unregister(new);
+
 		return r;
 	}
 
@@ -1917,7 +1940,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int as_id, id;
 	int r;
 
-	r = check_memory_region_flags(mem);
+	r = check_memory_region_flags(kvm, mem);
 	if (r)
 		return r;
 
@@ -1974,6 +1997,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
 			return -EINVAL;
 	} else { /* Modify an existing slot. */
+		/* Private memslots are immutable, they can only be deleted. */
+		if (mem->flags & KVM_MEM_PRIVATE)
+			return -EINVAL;
+
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
 		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -2002,6 +2029,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new->npages = npages;
 	new->flags = mem->flags;
 	new->userspace_addr = mem->userspace_addr;
+	new->fd = mem->fd;
+	new->file = NULL;
+	new->ofs = mem->ofs;
 
 	r = kvm_set_memslot(kvm, old, new, change);
 	if (r)
-- 
2.17.1