5 files changed, 623 insertions, 5 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 5bd7fcaf9089..08afef022db9 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -100,3 +100,7 @@ config KVM_GENERIC_MMU_NOTIFIER
 config KVM_GENERIC_MEMORY_ATTRIBUTES
        select KVM_GENERIC_MMU_NOTIFIER
        bool
+
+config KVM_PRIVATE_MEM
+       select XARRAY_MULTI
+       bool
diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm
index 2c27d5d0c367..724c89af78af 100644
--- a/virt/kvm/Makefile.kvm
+++ b/virt/kvm/Makefile.kvm
@@ -12,3 +12,4 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
 kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o
 kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o
 kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o
+kvm-$(CONFIG_KVM_PRIVATE_MEM) += $(KVM)/guest_memfd.o
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
new file mode 100644
index 000000000000..e65f4170425c
--- /dev/null
+++ b/virt/kvm/guest_memfd.c
@@ -0,0 +1,538 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/backing-dev.h>
+#include <linux/falloc.h>
+#include <linux/kvm_host.h>
+#include <linux/pagemap.h>
+#include <linux/anon_inodes.h>
+
+#include "kvm_mm.h"
+
+struct kvm_gmem {
+	struct kvm *kvm;
+	struct xarray bindings;
+	struct list_head entry;
+};
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+{
+	struct folio *folio;
+
+	/* TODO: Support huge pages. */
+	folio = filemap_grab_folio(inode->i_mapping, index);
+	if (IS_ERR_OR_NULL(folio))
+		return NULL;
+
+	/*
+	 * Use the up-to-date flag to track whether or not the memory has been
+	 * zeroed before being handed off to the guest.  There is no backing
+	 * storage for the memory, so the folio will remain up-to-date until
+	 * it's removed.
+	 *
+	 * TODO: Skip clearing pages when trusted firmware will do it when
+	 * assigning memory to the guest.
+	 */
+	if (!folio_test_uptodate(folio)) {
+		unsigned long nr_pages = folio_nr_pages(folio);
+		unsigned long i;
+
+		for (i = 0; i < nr_pages; i++)
+			clear_highpage(folio_page(folio, i));
+
+		folio_mark_uptodate(folio);
+	}
+
+	/*
+	 * Ignore accessed, referenced, and dirty flags.  The memory is
+	 * unevictable and there is no storage to write back to.
+	 */
+	return folio;
+}
+
+static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
+				      pgoff_t end)
+{
+	bool flush = false, found_memslot = false;
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = gmem->kvm;
+	unsigned long index;
+
+	xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) {
+		pgoff_t pgoff = slot->gmem.pgoff;
+
+		struct kvm_gfn_range gfn_range = {
+			.start = slot->base_gfn + max(pgoff, start) - pgoff,
+			.end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff,
+			.slot = slot,
+			.may_block = true,
+		};
+
+		if (!found_memslot) {
+			found_memslot = true;
+
+			KVM_MMU_LOCK(kvm);
+			kvm_mmu_invalidate_begin(kvm);
+		}
+
+		flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range);
+	}
+
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	if (found_memslot)
+		KVM_MMU_UNLOCK(kvm);
+}
+
+static void kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start,
+				    pgoff_t end)
+{
+	struct kvm *kvm = gmem->kvm;
+
+	if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+		KVM_MMU_LOCK(kvm);
+		kvm_mmu_invalidate_end(kvm);
+		KVM_MMU_UNLOCK(kvm);
+	}
+}
+
+static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct list_head *gmem_list = &inode->i_mapping->private_list;
+	pgoff_t start = offset >> PAGE_SHIFT;
+	pgoff_t end = (offset + len) >> PAGE_SHIFT;
+	struct kvm_gmem *gmem;
+
+	/*
+	 * Bindings must be stable across invalidation to ensure the start+end
+	 * are balanced.
+	 */
+	filemap_invalidate_lock(inode->i_mapping);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_begin(gmem, start, end);
+
+	truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_end(gmem, start, end);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	return 0;
+}
+
+static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t start, index, end;
+	int r;
+
+	/* Dedicated guest is immutable by default. */
+	if (offset + len > i_size_read(inode))
+		return -EINVAL;
+
+	filemap_invalidate_lock_shared(mapping);
+
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len) >> PAGE_SHIFT;
+
+	r = 0;
+	for (index = start; index < end; ) {
+		struct folio *folio;
+
+		if (signal_pending(current)) {
+			r = -EINTR;
+			break;
+		}
+
+		folio = kvm_gmem_get_folio(inode, index);
+		if (!folio) {
+			r = -ENOMEM;
+			break;
+		}
+
+		index = folio_next_index(folio);
+
+		folio_unlock(folio);
+		folio_put(folio);
+
+		/* 64-bit only, wrapping the index should be impossible. */
+		if (WARN_ON_ONCE(!index))
+			break;
+
+		cond_resched();
+	}
+
+	filemap_invalidate_unlock_shared(mapping);
+
+	return r;
+}
+
+static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset,
+			       loff_t len)
+{
+	int ret;
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE))
+		return -EOPNOTSUPP;
+
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))
+		return -EINVAL;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		ret = kvm_gmem_punch_hole(file_inode(file), offset, len);
+	else
+		ret = kvm_gmem_allocate(file_inode(file), offset, len);
+
+	if (!ret)
+		file_modified(file);
+	return ret;
+}
+
+static int kvm_gmem_release(struct inode *inode, struct file *file)
+{
+	struct kvm_gmem *gmem = file->private_data;
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = gmem->kvm;
+	unsigned long index;
+
+	/*
+	 * Prevent concurrent attempts to *unbind* a memslot.  This is the last
+	 * reference to the file and thus no new bindings can be created, but
+	 * dereferencing the slot for existing bindings needs to be protected
+	 * against memslot updates, specifically so that unbind doesn't race
+	 * and free the memslot (kvm_gmem_get_file() will return NULL).
+	 */
+	mutex_lock(&kvm->slots_lock);
+
+	filemap_invalidate_lock(inode->i_mapping);
+
+	xa_for_each(&gmem->bindings, index, slot)
+		rcu_assign_pointer(slot->gmem.file, NULL);
+
+	synchronize_rcu();
+
+	/*
+	 * All in-flight operations are gone and new bindings can be created.
+	 * Zap all SPTEs pointed at by this file.  Do not free the backing
+	 * memory, as its lifetime is associated with the inode, not the file.
+	 */
+	kvm_gmem_invalidate_begin(gmem, 0, -1ul);
+	kvm_gmem_invalidate_end(gmem, 0, -1ul);
+
+	list_del(&gmem->entry);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	mutex_unlock(&kvm->slots_lock);
+
+	xa_destroy(&gmem->bindings);
+	kfree(gmem);
+
+	kvm_put_kvm(kvm);
+
+	return 0;
+}
+
+static struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot)
+{
+	struct file *file;
+
+	rcu_read_lock();
+
+	file = rcu_dereference(slot->gmem.file);
+	if (file && !get_file_rcu(file))
+		file = NULL;
+
+	rcu_read_unlock();
+
+	return file;
+}
+
+static struct file_operations kvm_gmem_fops = {
+	.open		= generic_file_open,
+	.release	= kvm_gmem_release,
+	.fallocate	= kvm_gmem_fallocate,
+};
+
+void kvm_gmem_init(struct module *module)
+{
+	kvm_gmem_fops.owner = module;
+}
+
+static int kvm_gmem_migrate_folio(struct address_space *mapping,
+				  struct folio *dst, struct folio *src,
+				  enum migrate_mode mode)
+{
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
+static int kvm_gmem_error_page(struct address_space *mapping, struct page *page)
+{
+	struct list_head *gmem_list = &mapping->private_list;
+	struct kvm_gmem *gmem;
+	pgoff_t start, end;
+
+	filemap_invalidate_lock_shared(mapping);
+
+	start = page->index;
+	end = start + thp_nr_pages(page);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_begin(gmem, start, end);
+
+	/*
+	 * Do not truncate the range, what action is taken in response to the
+	 * error is userspace's decision (assuming the architecture supports
+	 * gracefully handling memory errors).  If/when the guest attempts to
+	 * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON,
+	 * at which point KVM can either terminate the VM or propagate the
+	 * error to userspace.
+	 */
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_end(gmem, start, end);
+
+	filemap_invalidate_unlock_shared(mapping);
+
+	return MF_DELAYED;
+}
+
+static const struct address_space_operations kvm_gmem_aops = {
+	.dirty_folio = noop_dirty_folio,
+#ifdef CONFIG_MIGRATION
+	.migrate_folio	= kvm_gmem_migrate_folio,
+#endif
+	.error_remove_page = kvm_gmem_error_page,
+};
+
+static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,
+			    struct kstat *stat, u32 request_mask,
+			    unsigned int query_flags)
+{
+	struct inode *inode = path->dentry->d_inode;
+
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			    struct iattr *attr)
+{
+	return -EINVAL;
+}
+static const struct inode_operations kvm_gmem_iops = {
+	.getattr	= kvm_gmem_getattr,
+	.setattr	= kvm_gmem_setattr,
+};
+
+static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
+{
+	const char *anon_name = "[kvm-gmem]";
+	struct kvm_gmem *gmem;
+	struct inode *inode;
+	struct file *file;
+	int fd, err;
+
+	fd = get_unused_fd_flags(0);
+	if (fd < 0)
+		return fd;
+
+	gmem = kzalloc(sizeof(*gmem), GFP_KERNEL);
+	if (!gmem) {
+		err = -ENOMEM;
+		goto err_fd;
+	}
+
+	file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem,
+					 O_RDWR, NULL);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_gmem;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+
+	inode = file->f_inode;
+	WARN_ON(file->f_mapping != inode->i_mapping);
+
+	inode->i_private = (void *)(unsigned long)flags;
+	inode->i_op = &kvm_gmem_iops;
+	inode->i_mapping->a_ops = &kvm_gmem_aops;
+	inode->i_mode |= S_IFREG;
+	inode->i_size = size;
+	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+	mapping_set_unmovable(inode->i_mapping);
+	/* Unmovable mappings are supposed to be marked unevictable as well. */
+	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
+
+	kvm_get_kvm(kvm);
+	gmem->kvm = kvm;
+	xa_init(&gmem->bindings);
+	list_add(&gmem->entry, &inode->i_mapping->private_list);
+
+	fd_install(fd, file);
+	return fd;
+
+err_gmem:
+	kfree(gmem);
+err_fd:
+	put_unused_fd(fd);
+	return err;
+}
+
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
+{
+	loff_t size = args->size;
+	u64 flags = args->flags;
+	u64 valid_flags = 0;
+
+	if (flags & ~valid_flags)
+		return -EINVAL;
+
+	if (size <= 0 || !PAGE_ALIGNED(size))
+		return -EINVAL;
+
+	return __kvm_gmem_create(kvm, size, flags);
+}
+
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+		  unsigned int fd, loff_t offset)
+{
+	loff_t size = slot->npages << PAGE_SHIFT;
+	unsigned long start, end;
+	struct kvm_gmem *gmem;
+	struct inode *inode;
+	struct file *file;
+	int r = -EINVAL;
+
+	BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff));
+
+	file = fget(fd);
+	if (!file)
+		return -EBADF;
+
+	if (file->f_op != &kvm_gmem_fops)
+		goto err;
+
+	gmem = file->private_data;
+	if (gmem->kvm != kvm)
+		goto err;
+
+	inode = file_inode(file);
+
+	if (offset < 0 || !PAGE_ALIGNED(offset) ||
+	    offset + size > i_size_read(inode))
+		goto err;
+
+	filemap_invalidate_lock(inode->i_mapping);
+
+	start = offset >> PAGE_SHIFT;
+	end = start + slot->npages;
+
+	if (!xa_empty(&gmem->bindings) &&
+	    xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+		filemap_invalidate_unlock(inode->i_mapping);
+		goto err;
+	}
+
+	/*
+	 * No synchronize_rcu() needed, any in-flight readers are guaranteed to
+	 * be see either a NULL file or this new file, no need for them to go
+	 * away.
+	 */
+	rcu_assign_pointer(slot->gmem.file, file);
+	slot->gmem.pgoff = start;
+
+	xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL);
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	/*
+	 * Drop the reference to the file, even on success.  The file pins KVM,
+	 * not the other way 'round.  Active bindings are invalidated if the
+	 * file is closed before memslots are destroyed.
+	 */
+	r = 0;
+err:
+	fput(file);
+	return r;
+}
+
+void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	unsigned long start = slot->gmem.pgoff;
+	unsigned long end = start + slot->npages;
+	struct kvm_gmem *gmem;
+	struct file *file;
+
+	/*
+	 * Nothing to do if the underlying file was already closed (or is being
+	 * closed right now), kvm_gmem_release() invalidates all bindings.
+	 */
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return;
+
+	gmem = file->private_data;
+
+	filemap_invalidate_lock(file->f_mapping);
+	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
+	rcu_assign_pointer(slot->gmem.file, NULL);
+	synchronize_rcu();
+	filemap_invalidate_unlock(file->f_mapping);
+
+	fput(file);
+}
+
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+{
+	pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
+	struct kvm_gmem *gmem;
+	struct folio *folio;
+	struct page *page;
+	struct file *file;
+	int r;
+
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return -EFAULT;
+
+	gmem = file->private_data;
+
+	if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) {
+		r = -EIO;
+		goto out_fput;
+	}
+
+	folio = kvm_gmem_get_folio(file_inode(file), index);
+	if (!folio) {
+		r = -ENOMEM;
+		goto out_fput;
+	}
+
+	if (folio_test_hwpoison(folio)) {
+		r = -EHWPOISON;
+		goto out_unlock;
+	}
+
+	page = folio_file_page(folio, index);
+
+	*pfn = page_to_pfn(page);
+	if (max_order)
+		*max_order = 0;
+
+	r = 0;
+
+out_unlock:
+	folio_unlock(folio);
+out_fput:
+	fput(file);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f1a575d39b3b..8f46d757a2c5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -791,7 +791,7 @@ void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
 	}
 }
 
-static bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
 	return kvm_unmap_gfn_range(kvm, range);
@@ -1027,6 +1027,9 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /* This does not remove the slot from struct kvm_memslots data structures */
 static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
+	if (slot->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(slot);
+
 	kvm_destroy_dirty_bitmap(slot);
 
 	kvm_arch_free_memslot(kvm, slot);
@@ -1606,10 +1609,18 @@ static void kvm_replace_memslot(struct kvm *kvm,
 #define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
 	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem)
+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_GUEST_MEMFD;
+
+	/* Dirty logging private memory is not currently supported. */
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
+
 #ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
@@ -2018,7 +2029,7 @@ 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;
 
@@ -2037,6 +2048,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;
+	if (mem->flags & KVM_MEM_GUEST_MEMFD &&
+	    (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
+	     mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
+		return -EINVAL;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
@@ -2075,6 +2090,9 @@ 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_GUEST_MEMFD)
+			return -EINVAL;
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
 		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -2103,10 +2121,23 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new->npages = npages;
 	new->flags = mem->flags;
 	new->userspace_addr = mem->userspace_addr;
+	if (mem->flags & KVM_MEM_GUEST_MEMFD) {
+		r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset);
+		if (r)
+			goto out;
+	}
 
 	r = kvm_set_memslot(kvm, old, new, change);
 	if (r)
-		kfree(new);
+		goto out_unbind;
+
+	return 0;
+
+out_unbind:
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(new);
+out:
+	kfree(new);
 	return r;
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
@@ -2442,7 +2473,7 @@ out:
 
 static u64 kvm_supported_mem_attributes(struct kvm *kvm)
 {
-	if (!kvm)
+	if (!kvm || kvm_arch_has_private_mem(kvm))
 		return KVM_MEMORY_ATTRIBUTE_PRIVATE;
 
 	return 0;
@@ -4845,6 +4876,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_MEMORY_ATTRIBUTES:
 		return kvm_supported_mem_attributes(kvm);
 #endif
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CAP_GUEST_MEMFD:
+		return !kvm || kvm_arch_has_private_mem(kvm);
+#endif
 	default:
 		break;
 	}
@@ -5277,6 +5312,18 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_GET_STATS_FD:
 		r = kvm_vm_ioctl_get_stats_fd(kvm);
 		break;
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CREATE_GUEST_MEMFD: {
+		struct kvm_create_guest_memfd guest_memfd;
+
+		r = -EFAULT;
+		if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd)))
+			goto out;
+
+		r = kvm_gmem_create(kvm, &guest_memfd);
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -6409,6 +6456,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (WARN_ON_ONCE(r))
 		goto err_vfio;
 
+	kvm_gmem_init(module);
+
 	/*
 	 * Registration _must_ be the very last thing done, as this exposes
 	 * /dev/kvm to userspace, i.e. all infrastructure must be setup!
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index 180f1a09e6ba..ecefc7ec51af 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -37,4 +37,30 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 }
 #endif /* HAVE_KVM_PFNCACHE */
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+void kvm_gmem_init(struct module *module);
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args);
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+		  unsigned int fd, loff_t offset);
+void kvm_gmem_unbind(struct kvm_memory_slot *slot);
+#else
+static inline void kvm_gmem_init(struct module *module)
+{
+
+}
+
+static inline int kvm_gmem_bind(struct kvm *kvm,
+					 struct kvm_memory_slot *slot,
+					 unsigned int fd, loff_t offset)
+{
+	WARN_ON_ONCE(1);
+	return -EIO;
+}
+
+static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	WARN_ON_ONCE(1);
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif /* __KVM_MM_H__ */