[RFC] c/r: prctl: Add ability to set new mm_struct::exe_file v3

[Cyrill Gorcunov <gorcunov@openvz.org>]

Hi Oleg, could you please take a look once you get a minute (no urgency).

	Cyrill
---
From: Cyrill Gorcunov <gorcunov@openvz.org>
Subject: c/r: prctl: Add ability to set new mm_struct::exe_file v3

When we do restore we would like to have a way to setup
a former mm_struct::exe_file so that /proc/pid/exe would
point to the original executable file a process had at
checkpoint time.

For this the PR_SET_MM_EXE_FILE code is introduced.
This option takes a file descriptor which will be
set as new /proc/$pid/exe symlink.

This feature is available iif CONFIG_CHECKPOINT_RESTORE is set.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
CC: Oleg Nesterov <oleg@redhat.com>
CC: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
CC: Pavel Emelyanov <xemul@parallels.com>
CC: Kees Cook <keescook@chromium.org>
CC: Tejun Heo <tj@kernel.org>
---
 include/linux/prctl.h |    1 +
 kernel/sys.c          |   50 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+)

Index: linux-2.6.git/include/linux/prctl.h
===================================================================
--- linux-2.6.git.orig/include/linux/prctl.h
+++ linux-2.6.git/include/linux/prctl.h
@@ -118,5 +118,6 @@
 # define PR_SET_MM_ENV_START		10
 # define PR_SET_MM_ENV_END		11
 # define PR_SET_MM_AUXV			12
+# define PR_SET_MM_EXE_FILE		13
 
 #endif /* _LINUX_PRCTL_H */
Index: linux-2.6.git/kernel/sys.c
===================================================================
--- linux-2.6.git.orig/kernel/sys.c
+++ linux-2.6.git/kernel/sys.c
@@ -36,6 +36,8 @@
 #include <linux/personality.h>
 #include <linux/ptrace.h>
 #include <linux/fs_struct.h>
+#include <linux/file.h>
+#include <linux/mount.h>
 #include <linux/gfp.h>
 #include <linux/syscore_ops.h>
 #include <linux/version.h>
@@ -1701,6 +1703,50 @@ static bool vma_flags_mismatch(struct vm
 		(vma->vm_flags & banned);
 }
 
+static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
+{
+	struct file *exe_file;
+	struct dentry *dentry;
+	int err;
+
+	exe_file = fget(fd);
+	if (!exe_file)
+		return -EBADF;
+
+	dentry = exe_file->f_path.dentry;
+
+	/*
+	 * Because the original mm->exe_file
+	 * points to executable file, make sure
+	 * this one is executable as well to not
+	 * break "big" picture and proc/pid/exe
+	 * symlink will be still pointing to
+	 * executable one.
+	 */
+	err = -EACCES;
+	if (!S_ISREG(dentry->d_inode->i_mode)	||
+	    exe_file->f_path.mnt->mnt_flags & MNT_NOEXEC)
+		goto exit;
+
+	err = inode_permission(dentry->d_inode, MAY_EXEC);
+	if (err)
+		goto exit;
+
+	down_write(&mm->mmap_sem);
+	if (mm->num_exe_file_vmas) {
+		fput(mm->exe_file);
+		mm->exe_file = exe_file;
+		exe_file = NULL;
+	} else
+		set_mm_exe_file(mm, exe_file);
+	up_write(&mm->mmap_sem);
+
+exit:
+	if (exe_file)
+		fput(exe_file);
+	return err;
+}
+
 static int prctl_set_mm(int opt, unsigned long addr,
 			unsigned long arg4, unsigned long arg5)
 {
@@ -1715,6 +1761,9 @@ static int prctl_set_mm(int opt, unsigne
 	if (!capable(CAP_SYS_RESOURCE))
 		return -EPERM;
 
+	if (opt == PR_SET_MM_EXE_FILE)
+		return prctl_set_mm_exe_file(mm, (unsigned int)addr);
+
 	if (addr >= TASK_SIZE)
 		return -EINVAL;
 
@@ -1837,6 +1886,7 @@ static int prctl_set_mm(int opt, unsigne
 
 		return 0;
 	}
+
 	default:
 		error = -EINVAL;
 		goto out;