Backported memfd_create() system call

arch/arm/include/uapi/asm/unistd.h

@@ -411,6 +411,7 @@
 #define __NR_renameat2			(__NR_SYSCALL_BASE+382)
 #define __NR_seccomp			(__NR_SYSCALL_BASE+383)
 #define __NR_getrandom			(__NR_SYSCALL_BASE+384)
+#define __NR_memfd_create		(__NR_SYSCALL_BASE+385)
 
 /*
  * This may need to be greater than __NR_last_syscall+1 in order to

arch/arm/kernel/calls.S

@@ -394,6 +394,7 @@
 		CALL(sys_ni_syscall) /* CALL(sys_renameat2) */
 		CALL(sys_seccomp)
 		CALL(sys_getrandom)
+/* 385 */	CALL(sys_memfd_create)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted

arch/x86/syscalls/syscall_32.tbl

@@ -362,3 +362,4 @@
 353	i386	renameat2		sys_ni_syscall
 354	i386	seccomp			sys_seccomp
 355	i386	getrandom		sys_getrandom
+356	i386	memfd_create		sys_memfd_create

arch/x86/syscalls/syscall_64.tbl

@@ -325,6 +325,7 @@
 316	common	renameat2		sys_ni_syscall
 317	common	seccomp			sys_seccomp
 318	common	getrandom		sys_getrandom
+319	common	memfd_create		sys_memfd_create
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

fs/fcntl.c

@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
+#include <linux/shmem_fs.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
@@ -327,6 +328,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_GETPIPE_SZ:
 		err = pipe_fcntl(filp, cmd, arg);
 		break;
+	case F_ADD_SEALS:
+	case F_GET_SEALS:
+		err = shmem_fcntl(filp, cmd, arg);
+		break;
 	default:
 		break;
 	}

include/linux/shmem_fs.h

@@ -1,6 +1,7 @@
 #ifndef __SHMEM_FS_H
 #define __SHMEM_FS_H
 
+#include <linux/file.h>
 #include <linux/swap.h>
 #include <linux/mempolicy.h>
 #include <linux/pagemap.h>
@@ -11,6 +12,7 @@
 
 struct shmem_inode_info {
 	spinlock_t		lock;
+	unsigned int		seals;		/* shmem seals */
 	unsigned long		flags;
 	unsigned long		alloced;	/* data pages alloced to file */
 	union {
@@ -62,4 +64,19 @@ static inline struct page *shmem_read_mapping_page(
 					mapping_gfp_mask(mapping));
 }
 
+#ifdef CONFIG_TMPFS
+
+extern int shmem_add_seals(struct file *file, unsigned int seals);
+extern int shmem_get_seals(struct file *file);
+extern long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
+
+#else
+
+static inline long shmem_fcntl(struct file *f, unsigned int c, unsigned long a)
+{
+	return -EINVAL;
+}
+
+#endif
+
 #endif

include/linux/syscalls.h

@@ -782,6 +782,7 @@ asmlinkage long sys_timerfd_settime(int ufd, int flags,
 asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr);
 asmlinkage long sys_eventfd(unsigned int count);
 asmlinkage long sys_eventfd2(unsigned int count, int flags);
+asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags);
 asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
 asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int);
 asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *,

include/uapi/asm-generic/unistd.h

@@ -704,9 +704,11 @@ __SYSCALL(__NR_renameat2, sys_renameat2)
 __SYSCALL(__NR_seccomp, sys_seccomp)
 #define __NR_getrandom 278
 __SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
 
 #undef __NR_syscalls
-#define __NR_syscalls 279
+#define __NR_syscalls 280
 
 /*
  * All syscalls below here should go away really,

include/uapi/linux/fcntl.h

@@ -27,6 +27,21 @@
 #define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
 #define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
 
+/*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS	(F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS	(F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL	0x0001	/* prevent further seals from being set */
+#define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
+#define F_SEAL_GROW	0x0004	/* prevent file from growing */
+#define F_SEAL_WRITE	0x0008	/* prevent writes */
+/* (1U << 31) is reserved for signed error codes */
+
 /*
  * Types of directory notifications that may be requested.
  */

include/uapi/linux/memfd.h

@@ -0,0 +1,8 @@
+#ifndef _UAPI_LINUX_MEMFD_H
+#define _UAPI_LINUX_MEMFD_H
+
+/* flags for memfd_create(2) (unsigned int) */
+#define MFD_CLOEXEC		0x0001U
+#define MFD_ALLOW_SEALING	0x0002U
+
+#endif /* _UAPI_LINUX_MEMFD_H */

kernel/sys_ni.c

@@ -193,6 +193,7 @@ cond_syscall(compat_sys_timerfd_settime);
 cond_syscall(compat_sys_timerfd_gettime);
 cond_syscall(sys_eventfd);
 cond_syscall(sys_eventfd2);
+cond_syscall(sys_memfd_create);
 
 /* performance counters: */
 cond_syscall(sys_perf_event_open);

mm/shmem.c

@@ -66,6 +66,9 @@ static struct vfsmount *shm_mnt;
 #include <linux/highmem.h>
 #include <linux/seq_file.h>
 #include <linux/magic.h>
+#include <linux/syscalls.h>
+#include <linux/fcntl.h>
+#include <uapi/linux/memfd.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -603,6 +606,7 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
 static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	int error;
 
 	error = inode_change_ok(inode, attr);
@@ -613,6 +617,11 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 		loff_t oldsize = inode->i_size;
 		loff_t newsize = attr->ia_size;
 
+		/* protected by i_mutex */
+		if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
+		    (newsize > oldsize && (info->seals & F_SEAL_GROW)))
+			return -EPERM;
+
 		if (newsize != oldsize) {
 			i_size_write(inode, newsize);
 			inode->i_ctime = inode->i_mtime = CURRENT_TIME;
@@ -1448,6 +1457,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		info = SHMEM_I(inode);
 		memset(info, 0, (char *)inode - (char *)info);
 		spin_lock_init(&info->lock);
+		info->seals = F_SEAL_SEAL;
 		info->flags = flags & VM_NORESERVE;
 		INIT_LIST_HEAD(&info->swaplist);
 		simple_xattrs_init(&info->xattrs);
@@ -1501,7 +1511,17 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 			struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+
+	/* i_mutex is held by caller */
+	if (unlikely(info->seals)) {
+		if (info->seals & F_SEAL_WRITE)
+			return -EPERM;
+		if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
+			return -EPERM;
+	}
+
 	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
 }
 
@@ -1872,11 +1892,113 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 	return offset;
 }
 
+static int shmem_wait_for_pins(struct address_space *mapping)
+{
+	return 0;
+}
+
+#define F_ALL_SEALS (F_SEAL_SEAL | \
+		     F_SEAL_SHRINK | \
+		     F_SEAL_GROW | \
+		     F_SEAL_WRITE)
+
+int shmem_add_seals(struct file *file, unsigned int seals)
+{
+	struct inode *inode = file_inode(file);
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	int error;
+
+	/*
+	 * SEALING
+	 * Sealing allows multiple parties to share a shmem-file but restrict
+	 * access to a specific subset of file operations. Seals can only be
+	 * added, but never removed. This way, mutually untrusted parties can
+	 * share common memory regions with a well-defined policy. A malicious
+	 * peer can thus never perform unwanted operations on a shared object.
+	 *
+	 * Seals are only supported on special shmem-files and always affect
+	 * the whole underlying inode. Once a seal is set, it may prevent some
+	 * kinds of access to the file. Currently, the following seals are
+	 * defined:
+	 *   SEAL_SEAL: Prevent further seals from being set on this file
+	 *   SEAL_SHRINK: Prevent the file from shrinking
+	 *   SEAL_GROW: Prevent the file from growing
+	 *   SEAL_WRITE: Prevent write access to the file
+	 *
+	 * As we don't require any trust relationship between two parties, we
+	 * must prevent seals from being removed. Therefore, sealing a file
+	 * only adds a given set of seals to the file, it never touches
+	 * existing seals. Furthermore, the "setting seals"-operation can be
+	 * sealed itself, which basically prevents any further seal from being
+	 * added.
+	 *
+	 * Semantics of sealing are only defined on volatile files. Only
+	 * anonymous shmem files support sealing. More importantly, seals are
+	 * never written to disk. Therefore, there's no plan to support it on
+	 * other file types.
+	 */
+
+	if (file->f_op != &shmem_file_operations)
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EPERM;
+	if (seals & ~(unsigned int)F_ALL_SEALS)
+		return -EINVAL;
+
+	mutex_lock(&inode->i_mutex);
+
+	if (info->seals & F_SEAL_SEAL) {
+		error = -EPERM;
+		goto unlock;
+	}
+
+	info->seals |= seals;
+	error = 0;
+
+unlock:
+	mutex_unlock(&inode->i_mutex);
+	return error;
+}
+EXPORT_SYMBOL_GPL(shmem_add_seals);
+
+int shmem_get_seals(struct file *file)
+{
+	if (file->f_op != &shmem_file_operations)
+		return -EINVAL;
+
+	return SHMEM_I(file_inode(file))->seals;
+}
+EXPORT_SYMBOL_GPL(shmem_get_seals);
+
+long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long error;
+
+	switch (cmd) {
+	case F_ADD_SEALS:
+		/* disallow upper 32bit */
+		if (arg > UINT_MAX)
+			return -EINVAL;
+
+		error = shmem_add_seals(file, arg);
+		break;
+	case F_GET_SEALS:
+		error = shmem_get_seals(file);
+		break;
+	default:
+		error = -EINVAL;
+		break;
+	}
+
+	return error;
+}
+
 static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 							 loff_t len)
 {
 	struct inode *inode = file_inode(file);
 	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct shmem_falloc shmem_falloc;
 	pgoff_t start, index, end;
 	int error;
@@ -1889,6 +2011,12 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
 		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
 
+		/* protected by i_mutex */
+		if (info->seals & F_SEAL_WRITE) {
+			error = -EPERM;
+			goto out;
+		}
+
 		shmem_falloc.waitq = &shmem_falloc_waitq;
 		shmem_falloc.start = unmap_start >> PAGE_SHIFT;
 		shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
@@ -1915,6 +2043,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 	if (error)
 		goto out;
 
+	if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) {
+		error = -EPERM;
+		goto out;
+	}
+
 	start = offset >> PAGE_CACHE_SHIFT;
 	end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	/* Try to avoid a swapstorm if len is impossible to satisfy */
@@ -2631,6 +2764,77 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root)
 	shmem_show_mpol(seq, sbinfo->mpol);
 	return 0;
 }
+
+#define MFD_NAME_PREFIX "memfd:"
+#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)
+
+SYSCALL_DEFINE2(memfd_create,
+		const char __user *, uname,
+		unsigned int, flags)
+{
+	struct shmem_inode_info *info;
+	struct file *file;
+	int fd, error;
+	char *name;
+	long len;
+
+	if (flags & ~(unsigned int)MFD_ALL_FLAGS)
+		return -EINVAL;
+
+	/* length includes terminating zero */
+	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
+	if (len <= 0)
+		return -EFAULT;
+	if (len > MFD_NAME_MAX_LEN + 1)
+		return -EINVAL;
+
+	name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_TEMPORARY);
+	if (!name)
+		return -ENOMEM;
+
+	strcpy(name, MFD_NAME_PREFIX);
+	if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) {
+		error = -EFAULT;
+		goto err_name;
+	}
+
+	/* terminating-zero may have changed after strnlen_user() returned */
+	if (name[len + MFD_NAME_PREFIX_LEN - 1]) {
+		error = -EFAULT;
+		goto err_name;
+	}
+
+	fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0);
+	if (fd < 0) {
+		error = fd;
+		goto err_name;
+	}
+
+	file = shmem_file_setup(name, 0, VM_NORESERVE);
+	if (IS_ERR(file)) {
+		error = PTR_ERR(file);
+		goto err_fd;
+	}
+	info = SHMEM_I(file_inode(file));
+	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
+	file->f_flags |= O_RDWR | O_LARGEFILE;
+	if (flags & MFD_ALLOW_SEALING)
+		info->seals &= ~F_SEAL_SEAL;
+
+	fd_install(fd, file);
+	kfree(name);
+	return fd;
+
+err_fd:
+	put_unused_fd(fd);
+err_name:
+	kfree(name);
+	return error;
+}
+
 #endif /* CONFIG_TMPFS */
 
 static void shmem_put_super(struct super_block *sb)