KVM: guest_memfd: Use guest mem inodes instead of anonymous inodes

guest_memfd's inode represents memory the guest_memfd is
providing. guest_memfd's file represents a struct kvm's view of that
memory.

Using a custom inode allows customization of the inode teardown
process via callbacks. For example, ->evict_inode() allows
customization of the truncation process on file close, and
->destroy_inode() and ->free_inode() allow customization of the inode
freeing process.

Customizing the truncation process allows flexibility in management of
guest_memfd memory and customization of the inode freeing process
allows proper cleanup of memory metadata stored on the inode.

Memory metadata is more appropriately stored on the inode (as opposed
to the file), since the metadata is for the memory and is not unique
to a specific binding and struct kvm.

Acked-by: David Hildenbrand <[e-mail]>
Co-developed-by: Fuad Tabba <[e-mail]>
Signed-off-by: Fuad Tabba <[e-mail]>
Signed-off-by: Ackerley Tng <[e-mail]>
Signed-off-by: Shivank Garg <[e-mail]>
Tested-by: Ashish Kalra <[e-mail]>
[sean: drop helpers, open code logic in __kvm_gmem_create()]
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Sean Christopherson <[e-mail]>

include/uapi/linux/magic.h

···
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
 #define PID_FS_MAGIC		0x50494446	/* "PIDF" */
+#define GUEST_MEMFD_MAGIC	0x474d454d	/* "GMEM" */
 
 #endif /* __LINUX_MAGIC_H__ */

virt/kvm/guest_memfd.c

···
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/anon_inodes.h>
 #include <linux/backing-dev.h>
 #include <linux/falloc.h>
+#include <linux/fs.h>
 #include <linux/kvm_host.h>
+#include <linux/pseudo_fs.h>
 #include <linux/pagemap.h>
-#include <linux/anon_inodes.h>
 
 #include "kvm_mm.h"
+
+static struct vfsmount *kvm_gmem_mnt;
 
 /*
  * A guest_memfd instance can be associated multiple VMs, each with its own
···
 	.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)
···
 
 static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 {
-	const char *anon_name = "[kvm-gmem]";
+	static const char *name = "[kvm-gmem]";
 	struct gmem_file *f;
 	struct inode *inode;
 	struct file *file;
···
 		goto err_fd;
 	}
 
-	file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, f, O_RDWR, NULL);
-	if (IS_ERR(file)) {
-		err = PTR_ERR(file);
+	/* __fput() will take care of fops_put(). */
+	if (!fops_get(&kvm_gmem_fops)) {
+		err = -ENOENT;
 		goto err_gmem;
 	}
 
-	file->f_flags |= O_LARGEFILE;
-
-	inode = file->f_inode;
-	WARN_ON(file->f_mapping != inode->i_mapping);
+	inode = anon_inode_make_secure_inode(kvm_gmem_mnt->mnt_sb, name, NULL);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		goto err_fops;
+	}
 
 	inode->i_private = (void *)(unsigned long)flags;
 	inode->i_op = &kvm_gmem_iops;
···
 	/* Unmovable mappings are supposed to be marked unevictable as well. */
 	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
 
+	file = alloc_file_pseudo(inode, kvm_gmem_mnt, name, O_RDWR, &kvm_gmem_fops);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_inode;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+	file->private_data = f;
+
 	kvm_get_kvm(kvm);
 	f->kvm = kvm;
 	xa_init(&f->bindings);
···
 	fd_install(fd, file);
 	return fd;
 
+err_inode:
+	iput(inode);
+err_fops:
+	fops_put(&kvm_gmem_fops);
 err_gmem:
 	kfree(f);
 err_fd:
···
 }
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_populate);
 #endif
+
+static int kvm_gmem_init_fs_context(struct fs_context *fc)
+{
+	if (!init_pseudo(fc, GUEST_MEMFD_MAGIC))
+		return -ENOMEM;
+
+	fc->s_iflags |= SB_I_NOEXEC;
+	fc->s_iflags |= SB_I_NODEV;
+
+	return 0;
+}
+
+static struct file_system_type kvm_gmem_fs = {
+	.name		 = "guest_memfd",
+	.init_fs_context = kvm_gmem_init_fs_context,
+	.kill_sb	 = kill_anon_super,
+};
+
+static int kvm_gmem_init_mount(void)
+{
+	kvm_gmem_mnt = kern_mount(&kvm_gmem_fs);
+
+	if (IS_ERR(kvm_gmem_mnt))
+		return PTR_ERR(kvm_gmem_mnt);
+
+	kvm_gmem_mnt->mnt_flags |= MNT_NOEXEC;
+	return 0;
+}
+
+int kvm_gmem_init(struct module *module)
+{
+	kvm_gmem_fops.owner = module;
+
+	return kvm_gmem_init_mount();
+}
+
+void kvm_gmem_exit(void)
+{
+	kern_unmount(kvm_gmem_mnt);
+	kvm_gmem_mnt = NULL;
+}

virt/kvm/kvm_main.c

···
 	if (WARN_ON_ONCE(r))
 		goto err_vfio;
 
-	kvm_gmem_init(module);
+	r = kvm_gmem_init(module);
+	if (r)
+		goto err_gmem;
 
 	r = kvm_init_virtualization();
 	if (r)
···
 err_register:
 	kvm_uninit_virtualization();
 err_virt:
+	kvm_gmem_exit();
+err_gmem:
 	kvm_vfio_ops_exit();
 err_vfio:
 	kvm_async_pf_deinit();
···
 	for_each_possible_cpu(cpu)
 		free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
 	kmem_cache_destroy(kvm_vcpu_cache);
+	kvm_gmem_exit();
 	kvm_vfio_ops_exit();
 	kvm_async_pf_deinit();
 	kvm_irqfd_exit();

virt/kvm/kvm_mm.h

···
 #endif /* HAVE_KVM_PFNCACHE */
 
 #ifdef CONFIG_KVM_GUEST_MEMFD
-void kvm_gmem_init(struct module *module);
+int kvm_gmem_init(struct module *module);
+void kvm_gmem_exit(void);
 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_init(struct module *module)
 {
-
+	return 0;
 }
-
+static inline void kvm_gmem_exit(void) {};
 static inline int kvm_gmem_bind(struct kvm *kvm,
 					 struct kvm_memory_slot *slot,
 					 unsigned int fd, loff_t offset)