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.

Change-Id: Iaf959293e2c490523aeb46d56cc45b0e7bbe7bf5
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>
Signed-off-by: Angelo G. Del Regno <kholk11@gmail.com>

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index ee83ba269a650a7fe7308ee4167ec6382f639380..094bc171fa4c978689d043b2f8c9964c199cfd06 100644 (file)
--- a/include/linux/syscalls.h
+++ b/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 *,

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 7e7fc0a082c4517b5b604dac039f01e4c2da2a10..9c37e7a20436642a4bd7f8665bb263e403abb065 100644 (file)
--- a/kernel/sys_ni.c
+++ b/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);

diff --git a/mm/shmem.c b/mm/shmem.c
index 4bb28c9bd0fdd18f50ed39971f6fe5cb7dd76bc2..e85a8ee3d4dad815d77a2ec0d0e667844a0804e1 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -65,7 +65,9 @@ static struct vfsmount *shm_mnt;
 #include <linux/migrate.h>
 #include <linux/highmem.h>
 #include <linux/seq_file.h>
+#include <linux/syscalls.h>
 #include <linux/magic.h>
+#include <uapi/linux/memfd.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -2679,6 +2681,75 @@ 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->f_path.dentry->d_inode);
+       file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
+       file->f_flags |= O_RDWR | O_LARGEFILE;
+
+       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)