[patch 0/2] c/r update to prctl

[patch 0/2] c/r update to prctl

[Cyrill Gorcunov]

Hi,

this is a series to extend prctl a bit for c/r needs.

 - new PR_SET_MM_EXE_FILE option to setup /proc/pid/exe
   symlink on restored program
 - new PR_GET_TID_ADDRESS option to retrieve process'
   clear_tid_address

Andrew, please drop Oleg's exe_path patch from -mm tree

 | The patch titled
 |    Subject: mm/exec: rename mm->exe_file to mm->exe_path
 | has been added to the -mm tree.  Its filename is
 |    mm-exec-rename-mm-exe_file-to-mm-exe_path.patch

This patch was deprecated.

	Cyrill

[patch 1/2] c/r: prctl: Add ability to set new mm_struct::exe_file v6

[Cyrill Gorcunov]

[-- Attachment #1: c-r-prctl-add-SET_MM-new-4 --]
[-- Type: text/plain, Size: 3370 bytes --]

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 a source for new /proc/$pid/exe symlink.

Note it allows to change /proc/$pid/exe iif there
are no VM_EXECUTABLE vmas present for current process,
simply because this feature is a special to C/R
and mm::num_exe_file_vmas become meaningless after
that.

This feature is available iif CONFIG_CHECKPOINT_RESTORE is set.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Reviewed-by: 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>
CC: Matt Helsley <matthltc@us.ibm.com>
---
 include/linux/prctl.h |    1 
 kernel/sys.c          |   52 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 53 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 +1703,53 @@ 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;
+
+	/*
+	 * Setting new mm::exe_file is only allowed
+	 * when no VM_EXECUTABLE vma's left. This is
+	 * a special C/R case when a restored program
+	 * need to change own /proc/$pid/exe symlink.
+	 * After this call mm::num_exe_file_vmas become
+	 * meaningless.
+	 */
+	if (mm->num_exe_file_vmas)
+		return -EBUSY;
+
+	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 an overall picture.
+	 */
+	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);
+	set_mm_exe_file(mm, exe_file);
+	up_write(&mm->mmap_sem);
+
+exit:
+	fput(exe_file);
+	return err;
+}
+
 static int prctl_set_mm(int opt, unsigned long addr,
 			unsigned long arg4, unsigned long arg5)
 {
@@ -1715,6 +1764,9 @@ 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;
 

[patch 2/2] c/r: prctl: Add ability to get clear_tid_address

[Cyrill Gorcunov]

[-- Attachment #1: c-r-prctl-add-PR_GET_TID_ADDRESS --]
[-- Type: text/plain, Size: 2295 bytes --]

Zero is written at clear_tid_address, when
the process exits. This functionality is used
by pthread_join().

We already have sys_set_tid_address() to change this
address for current task but there is no way to obtain
it from a user space.

Without ability to find this address and dump it we can't
restore pthread'ed apps which do call pthread_join() once
they have been restored.

This patch introduces PR_GET_TID_ADDRESS prctl option
which allow current process to obtain own clear_tid_address.

This feature is available iif CONFIG_CHECKPOINT_RESTORE is set.

Signed-off-by: Andrew Vagin <avagin@openvz.org>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
CC: Pedro Alves <palves@redhat.com>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Pavel Emelyanov <xemul@parallels.com>
CC: Tejun Heo <tj@kernel.org>
---
 include/linux/prctl.h |    2 ++
 kernel/sys.c          |   13 +++++++++++++
 2 files changed, 15 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
@@ -120,4 +120,6 @@
 # define PR_SET_MM_AUXV			12
 # define PR_SET_MM_EXE_FILE		13
 
+#define PR_GET_TID_ADDRESS		36
+
 #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
@@ -1897,12 +1897,22 @@ out:
 	up_read(&mm->mmap_sem);
 	return error;
 }
+
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+	return put_user(me->clear_child_tid, tid_addr);
+}
+
 #else /* CONFIG_CHECKPOINT_RESTORE */
 static int prctl_set_mm(int opt, unsigned long addr,
 			unsigned long arg4, unsigned long arg5)
 {
 	return -EINVAL;
 }
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+	return -EINVAL;
+}
 #endif
 
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
@@ -2057,6 +2067,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsi
 		case PR_SET_MM:
 			error = prctl_set_mm(arg2, arg3, arg4, arg5);
 			break;
+		case PR_GET_TID_ADDRESS:
+			error = prctl_get_tid_address(me, (int __user **)arg2);
+			break;
 		default:
 			error = -EINVAL;
 			break;