shm: add memfd_create() syscall

memfd_create() is similar to mmap(MAP_ANON), but returns a file-descriptor
that you can pass to mmap().  It can support sealing and avoids any
connection to user-visible mount-points.  Thus, it's not subject to quotas
on mounted file-systems, but can be used like malloc()'ed memory, but with
a file-descriptor to it.

memfd_create() returns the raw shmem file, so calls like ftruncate() can
be used to modify the underlying inode.  Also calls like fstat() will
return proper information and mark the file as regular file.  If you want
sealing, you can specify MFD_ALLOW_SEALING.  Otherwise, sealing is not
supported (like on all other regular files).

Compared to O_TMPFILE, it does not require a tmpfs mount-point and is not
subject to a filesystem size limit.  It is still properly accounted to
memcg limits, though, and to the same overcommit or no-overcommit
accounting as all user memory.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ryan Lortie <desrt@desrt.ca>
Cc: Lennart Poettering <lennart@poettering.net>
Cc: Daniel Mack <zonque@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index d1b4a119d4a5aa22c23c7722de632f921299d988..028b78168d85ac51d70c6b750d59fc23ae7cc028 100644 (file)
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -362,3 +362,4 @@
 353    i386    renameat2               sys_renameat2
 354    i386    seccomp                 sys_seccomp
 355    i386    getrandom               sys_getrandom
+356    i386    memfd_create            sys_memfd_create

diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 252c804bb1aa7e2d74502d6a67fe67c8d06ae402..ca2b9aa78c8180903998428c60f1523fa309f3b2 100644 (file)
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -325,6 +325,7 @@
 316    common  renameat2               sys_renameat2
 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

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 701daff5d899ebabae0cdcabb5d2a381beffc38f..15a069425cbf93732f6683fa2311a01b1f2658d0 100644 (file)
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -802,6 +802,7 @@ 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 *,

diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h
new file mode 100644 (file)
index 0000000..534e364
--- /dev/null
+++ b/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 */

diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 2904a21059145b61e55a3fee9204a64fce48c9ea..1f79e3714533e9ff3080013cafddb1e3697d318e 100644 (file)
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -197,6 +197,7 @@ 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);

diff --git a/mm/shmem.c b/mm/shmem.c
index 8b43bb7a4efe8631130782bd02426abaeea47476..4a5498795a2bfa00fcff4c24b55991b0725df046 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -66,7 +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>
@@ -2732,6 +2734,77 @@ 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)