forge/pmaports
1
0
Fork 0
Code Issues 2 Pull requests Projects Releases Packages Wiki Activity Actions
pmaports/device/linux-samsung-klte/0011-Backport-shm-add-memfd_create-syscall.patch
Alexey Min 2fb18b5d30
samsung-klte: backport memfd_create() syscall (!479) 
This brings in several patches needed to add support for a
memfd_create() syscall into kernel version 3.4 from kernel
version 3.17. This is required for running lxc >= 3.1.0-r1
with security patch that fixes CVE-2019-5736.

In short, security issue was: in a privileged container root
process could overwrite lxc-start executable by opening its
file descriptor and rewriting executable contents. This is
where memfd comes to help: you can create an in-memory file,
copy your executable there, and place a set of SEALS to protect
it from modifying at a deep level. Then you fexecve() that fd
and you're safe.

For example, pulseaudio also can benefit from having
memfd_create() implemented.

This backports the following commits from upstream linux:
 - dd37978c50bc8b354e5c4633f69387f16572fdac: cache the value
   of file_inode() in struct file

   commit from linux-3.10 to have an f_inode member inside
   struct file and a helper function file_inode() that is
   used in some of the following commits

 - 40e041a2c858b3caefc757e26cb85bfceae5062b shm: add sealing API

   from 3.17: security measure called SEALS, that you can put
   on memfd file to restrict operations on it

 - 9183df25fe7b194563db3fec6dc3202a5855839c shm: add memfd_create()
   syscall

   also from 3.17

 - 503e6636b6f96056210062be703356f4253b6db9 asm-generic: add
   memfd_create system call to unistd.h

 - e57e41931134e09fc6c03c8d4eb19d516cc6e59b ARM: wire up
   memfd_create syscall

The last two are needed to make the syscall visible/usable from
userspace, one in generic context, other for ARM arch.

The test program (https://github.com/minlexx/test_memfd/) was
written to verify that this works.

[ci:skip-build]: already built successfully in CI
2019-07-09 21:17:33 +02:00

198 lines
6.5 KiB
Diff
Raw Blame History

From 01fc0d7a8df67bd3a1f2cf7ffd5f74c6fadd7c85 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Tue, 2 Jul 2019 02:36:29 +0300
Subject: [PATCH 3/5] 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>
---
arch/x86/syscalls/syscall_32.tbl | 2 +
arch/x86/syscalls/syscall_64.tbl | 2 +
include/linux/syscalls.h | 1 +
include/uapi/linux/memfd.h | 8 ++++
kernel/sys_ni.c | 1 +
mm/shmem.c | 74 ++++++++++++++++++++++++++++++++
6 files changed, 88 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 64e55260fbc..498d12b9af8 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -356,3 +356,5 @@
347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv
348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
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 33335d11d7b..4887a0fa042 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -319,6 +319,8 @@
310 64 process_vm_readv sys_process_vm_readv
311 64 process_vm_writev sys_process_vm_writev
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 da352d5a271..c1cc0e12cf4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -813,6 +813,7 @@ 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 00000000000..9a772654307
--- /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 026f30a8985..b97ab3a6dc9 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -191,6 +191,7 @@ 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 1a232f8d8cb..3b9580b0808 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -63,7 +63,9 @@ 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>
@@ -2492,6 +2494,78 @@ 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)
--
2.20.1
Reference in a new issue View git blame Copy permalink