From: David Herrmann <dh.herrmann@gmail.com>
To: linux-kernel@vger.kernel.org
Cc: Michael Kerrisk <mtk.manpages@gmail.com>,
Ryan Lortie <desrt@desrt.ca>,
Linus Torvalds <torvalds@linux-foundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
linux-api@vger.kernel.org, Greg Kroah-Hartman <greg@kroah.com>,
john.stultz@linaro.org,
Lennart Poettering <lennart@poettering.net>,
Daniel Mack <zonque@gmail.com>, Kay Sievers <kay@vrfy.org>,
Hugh Dickins <hughd@google.com>,
Andy Lutomirski <luto@amacapital.net>,
Alexander Viro <viro@zeniv.linux.org.uk>,
David Herrmann <dh.herrmann@gmail.com>
Subject: [PATCH v4 3/6] shm: add memfd_create() syscall
Date: Sun, 20 Jul 2014 19:34:37 +0200 [thread overview]
Message-ID: <1405877680-999-4-git-send-email-dh.herrmann@gmail.com> (raw)
In-Reply-To: <1405877680-999-1-git-send-email-dh.herrmann@gmail.com>
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>
---
arch/x86/syscalls/syscall_32.tbl | 1 +
arch/x86/syscalls/syscall_64.tbl | 1 +
include/linux/syscalls.h | 1 +
include/uapi/linux/memfd.h | 8 +++++
kernel/sys_ni.c | 1 +
mm/shmem.c | 73 ++++++++++++++++++++++++++++++++++++++++
6 files changed, 85 insertions(+)
create mode 100644 include/uapi/linux/memfd.h
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index d6b8679..e7495b4 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -360,3 +360,4 @@
351 i386 sched_setattr sys_sched_setattr
352 i386 sched_getattr sys_sched_getattr
353 i386 renameat2 sys_renameat2
+354 i386 memfd_create sys_memfd_create
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index ec255a1..28be0e1 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -323,6 +323,7 @@
314 common sched_setattr sys_sched_setattr
315 common sched_getattr sys_sched_getattr
316 common renameat2 sys_renameat2
+317 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 b0881a0..de00585 100644
--- 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
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 36441b5..489a4e6 100644
--- 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 51dccd0..770e072 100644
--- 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>
@@ -2678,6 +2680,77 @@ 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)
--
2.0.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2014-07-20 17:34 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-20 17:34 [PATCH v4 0/6] File Sealing & memfd_create() David Herrmann
2014-07-20 17:34 ` [PATCH v4 1/6] mm: allow drivers to prevent new writable mappings David Herrmann
2014-07-24 4:07 ` Hugh Dickins
2014-07-20 17:34 ` [PATCH v4 2/6] shm: add sealing API David Herrmann
2014-07-24 4:11 ` Hugh Dickins
2014-07-20 17:34 ` David Herrmann [this message]
2014-07-24 4:19 ` [PATCH v4 3/6] shm: add memfd_create() syscall Hugh Dickins
2014-07-20 17:34 ` [PATCH v4 4/6] selftests: add memfd_create() + sealing tests David Herrmann
2014-07-24 4:20 ` Hugh Dickins
2014-07-20 17:34 ` [PATCH v4 5/6] selftests: add memfd/sealing page-pinning tests David Herrmann
2014-07-24 4:28 ` Hugh Dickins
2014-07-20 17:34 ` [PATCH v4 6/6] shm: wait for pins to be released when sealing David Herrmann
2014-07-24 4:32 ` Hugh Dickins
2014-07-24 4:48 ` [PATCH v4 0/6] File Sealing & memfd_create() Hugh Dickins
2014-07-24 21:47 ` Andrew Morton
2014-07-24 22:44 ` David Herrmann
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1405877680-999-4-git-send-email-dh.herrmann@gmail.com \
--to=dh.herrmann@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=desrt@desrt.ca \
--cc=greg@kroah.com \
--cc=hughd@google.com \
--cc=john.stultz@linaro.org \
--cc=kay@vrfy.org \
--cc=lennart@poettering.net \
--cc=linux-api@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@amacapital.net \
--cc=mtk.manpages@gmail.com \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=zonque@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).