[RFC PATCH v2 3/5] mm: extend memfd with ability to create "secret" memory areas

@@ -13,4 +13,13 @@ static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a)
 }
 #endif
 
+#ifdef CONFIG_MEMFD_SECRETMEM
+extern struct file *secretmem_file_create(const char *name, unsigned int flags);
+#else
+static inline struct file *secretmem_file_create(const char *name, unsigned int flags)
+{
+	return ERR_PTR(-EINVAL);
+}
+#endif
+
 #endif /* __LINUX_MEMFD_H */

@@ -97,5 +97,6 @@
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define Z3FOLD_MAGIC		0x33
 #define PPC_CMM_MAGIC		0xc7571590
+#define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
 
 #endif /* __LINUX_MAGIC_H__ */

@@ -8,6 +8,12 @@
 #define MFD_CLOEXEC		0x0001U
 #define MFD_ALLOW_SEALING	0x0002U
 #define MFD_HUGETLB		0x0004U
+#define MFD_SECRET		0x0008U
+
+/* ioctls for secret memory */
+#define MFD_SECRET_IOCTL '-'
+#define MFD_SECRET_EXCLUSIVE	_IOW(MFD_SECRET_IOCTL, 0x13, unsigned long)
+#define MFD_SECRET_UNCACHED	_IOW(MFD_SECRET_IOCTL, 0x14, unsigned long)
 
 /*
  * Huge page size encoding when MFD_HUGETLB is specified, and a huge page

@@ -872,4 +872,7 @@ config ARCH_HAS_HUGEPD
 config MAPPING_DIRTY_HELPERS
         bool
 
+config MEMFD_SECRETMEM
+        def_bool MEMFD_CREATE && ARCH_HAS_SET_DIRECT_MAP
+
 endmenu

@@ -121,3 +121,4 @@ obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
 obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
 obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
+obj-$(CONFIG_MEMFD_SECRETMEM) += secretmem.o

@@ -245,7 +245,8 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
 #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
 
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
+#define MFD_SECRET_MASK (MFD_CLOEXEC | MFD_SECRET)
+#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_SECRET)
 
 SYSCALL_DEFINE2(memfd_create,
 		const char __user *, uname,

@@ -257,6 +258,9 @@ SYSCALL_DEFINE2(memfd_create,
 	char *name;
 	long len;
 
+	if (flags & ~(unsigned int)MFD_SECRET_MASK)
+		return -EINVAL;
+
 	if (!(flags & MFD_HUGETLB)) {
 		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
 			return -EINVAL;

@@ -296,7 +300,9 @@ SYSCALL_DEFINE2(memfd_create,
 		goto err_name;
 	}
 
-	if (flags & MFD_HUGETLB) {
+	if (flags & MFD_SECRET) {
+		file = secretmem_file_create(name, flags);
+	} else if (flags & MFD_HUGETLB) {
 		struct user_struct *user = NULL;
 
 		file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user,

@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/memfd.h>
+#include <linux/printk.h>
+#include <linux/pagemap.h>
+#include <linux/pseudo_fs.h>
+#include <linux/set_memory.h>
+#include <linux/sched/signal.h>
+
+#include <uapi/linux/memfd.h>
+#include <uapi/linux/magic.h>
+
+#include <asm/tlbflush.h>
+
+#include "internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "secretmem: " fmt
+
+#define SECRETMEM_EXCLUSIVE	0x1
+#define SECRETMEM_UNCACHED	0x2
+
+struct secretmem_ctx {
+	unsigned int mode;
+};
+
+static struct page *secretmem_alloc_page(gfp_t gfp)
+{
+	/*
+	 * FIXME: use a cache of large pages to reduce the direct map
+	 * fragmentation
+	 */
+	return alloc_page(gfp);
+}
+
+static vm_fault_t secretmem_fault(struct vm_fault *vmf)
+{
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	pgoff_t offset = vmf->pgoff;
+	unsigned long addr;
+	struct page *page;
+	int ret = 0;
+
+	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
+		return vmf_error(-EINVAL);
+
+	page = find_get_entry(mapping, offset);
+	if (!page) {
+		page = secretmem_alloc_page(vmf->gfp_mask);
+		if (!page)
+			return vmf_error(-ENOMEM);
+
+		ret = add_to_page_cache_lru(page, mapping, offset, vmf->gfp_mask);
+		if (unlikely(ret))
+			goto err_put_page;
+
+		ret = set_direct_map_invalid_noflush(page);
+		if (ret)
+			goto err_del_page_cache;
+
+		addr = (unsigned long)page_address(page);
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+		__SetPageUptodate(page);
+
+		ret = VM_FAULT_LOCKED;
+	}
+
+	vmf->page = page;
+	return ret;
+
+err_del_page_cache:
+	delete_from_page_cache(page);
+err_put_page:
+	put_page(page);
+	return vmf_error(ret);
+}
+
+static const struct vm_operations_struct secretmem_vm_ops = {
+	.fault = secretmem_fault,
+};
+
+static int secretmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct secretmem_ctx *ctx = file->private_data;
+	unsigned long mode = ctx->mode;
+	unsigned long len = vma->vm_end - vma->vm_start;
+
+	if (!mode)
+		return -EINVAL;
+
+	if (mlock_future_check(vma->vm_mm, vma->vm_flags | VM_LOCKED, len))
+		return -EAGAIN;
+
+	switch (mode) {
+	case SECRETMEM_UNCACHED:
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+		fallthrough;
+	case SECRETMEM_EXCLUSIVE:
+		vma->vm_ops = &secretmem_vm_ops;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	vma->vm_flags |= VM_LOCKED;
+
+	return 0;
+}
+
+static long secretmem_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	struct secretmem_ctx *ctx = file->private_data;
+	unsigned long mode = ctx->mode;
+
+	if (mode)
+		return -EINVAL;
+
+	switch (cmd) {
+	case MFD_SECRET_EXCLUSIVE:
+		mode = SECRETMEM_EXCLUSIVE;
+		break;
+	case MFD_SECRET_UNCACHED:
+		mode = SECRETMEM_UNCACHED;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ctx->mode = mode;
+
+	return 0;
+}
+
+const struct file_operations secretmem_fops = {
+	.mmap		= secretmem_mmap,
+	.unlocked_ioctl = secretmem_ioctl,
+	.compat_ioctl	= secretmem_ioctl,
+};
+
+static bool secretmem_isolate_page(struct page *page, isolate_mode_t mode)
+{
+	return false;
+}
+
+static int secretmem_migratepage(struct address_space *mapping,
+				 struct page *newpage, struct page *page,
+				 enum migrate_mode mode)
+{
+	return -EBUSY;
+}
+
+static void secretmem_freepage(struct page *page)
+{
+	set_direct_map_default_noflush(page);
+}
+
+static const struct address_space_operations secretmem_aops = {
+	.freepage	= secretmem_freepage,
+	.migratepage	= secretmem_migratepage,
+	.isolate_page	= secretmem_isolate_page,
+};
+
+static struct vfsmount *secretmem_mnt;
+
+struct file *secretmem_file_create(const char *name, unsigned int flags)
+{
+	struct inode *inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
+	struct file *file = ERR_PTR(-ENOMEM);
+	struct secretmem_ctx *ctx;
+
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		goto err_free_inode;
+
+	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
+				 O_RDWR, &secretmem_fops);
+	if (IS_ERR(file))
+		goto err_free_ctx;
+
+	mapping_set_unevictable(inode->i_mapping);
+
+	inode->i_mapping->private_data = ctx;
+	inode->i_mapping->a_ops = &secretmem_aops;
+
+	/* pretend we are a normal file with zero size */
+	inode->i_mode |= S_IFREG;
+	inode->i_size = 0;
+
+	file->private_data = ctx;
+
+	return file;
+
+err_free_ctx:
+	kfree(ctx);
+err_free_inode:
+	iput(inode);
+	return file;
+}
+
+static void secretmem_evict_inode(struct inode *inode)
+{
+	struct secretmem_ctx *ctx = inode->i_private;
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+	kfree(ctx);
+}
+
+static const struct super_operations secretmem_super_ops = {
+	.evict_inode = secretmem_evict_inode,
+};
+
+static int secretmem_init_fs_context(struct fs_context *fc)
+{
+	struct pseudo_fs_context *ctx = init_pseudo(fc, SECRETMEM_MAGIC);
+
+	if (!ctx)
+		return -ENOMEM;
+	ctx->ops = &secretmem_super_ops;
+
+	return 0;
+}
+
+static struct file_system_type secretmem_fs = {
+	.name		= "secretmem",
+	.init_fs_context = secretmem_init_fs_context,
+	.kill_sb	= kill_anon_super,
+};
+
+static int secretmem_init(void)
+{
+	int ret = 0;
+
+	secretmem_mnt = kern_mount(&secretmem_fs);
+	if (IS_ERR(secretmem_mnt))
+		ret = PTR_ERR(secretmem_mnt);
+
+	return ret;
+}
+fs_initcall(secretmem_init);