[patch 0/4] Resending, c/r series v2

[patch 0/4] Resending, c/r series v2

[Cyrill Gorcunov]

Hi, this series hopefully in a good shape

 - sys_kcmp now depends on CONFIG_CHECKPOINT_RESTORE

 - the extension of /proc/pid/stat now done against
   linux-next/master

Please letme know if I've missed something.

Thanks,
	Cyrill

[patch 1/4] fs, proc: Introduce /proc/<pid>/task/<tid>/children entry v9

[Cyrill Gorcunov]

[-- Attachment #1: fs-proc-tid-children-13 --]
[-- Type: text/plain, Size: 7087 bytes --]

When we do checkpoint of a task we need to know the list of children
the task, has but there is no easy and fast way to generate reverse
parent->children chain from arbitrary <pid> (while a parent pid is
provided in "PPid" field of /proc/<pid>/status).

So instead of walking over all pids in the system (creating one big process
tree in memory, just to figure out which children a task has) -- we add
explicit /proc/<pid>/task/<tid>/children entry, because the kernel already has
this kind of information but it is not yet exported.

This is a first level children, not the whole process tree.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
 Documentation/filesystems/proc.txt |   18 +++++
 fs/proc/array.c                    |  123 +++++++++++++++++++++++++++++++++++++
 fs/proc/base.c                     |    3 
 fs/proc/internal.h                 |    1 
 4 files changed, 145 insertions(+)

Index: linux-2.6.git/Documentation/filesystems/proc.txt
===================================================================
--- linux-2.6.git.orig/Documentation/filesystems/proc.txt
+++ linux-2.6.git/Documentation/filesystems/proc.txt
@@ -40,6 +40,7 @@ Table of Contents
   3.4	/proc/<pid>/coredump_filter - Core dump filtering settings
   3.5	/proc/<pid>/mountinfo - Information about mounts
   3.6	/proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
+  3.7   /proc/<pid>/task/<tid>/children - Information about task children
 
   4	Configuring procfs
   4.1	Mount options
@@ -1549,6 +1550,23 @@ then the kernel's TASK_COMM_LEN (current
 comm value.
 
 
+3.7	/proc/<pid>/task/<tid>/children - Information about task children
+-------------------------------------------------------------------------
+This file provides a fast way to retrieve first level children pids
+of a task pointed by <pid>/<tid> pair. The format is a space separated
+stream of pids.
+
+Note the "first level" here -- if a child has own children they will
+not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
+to obtain the descendants.
+
+Since this interface is intended to be fast and cheap it doesn't
+guarantee to provide precise results and some children might be
+skipped, especially if they've exited right after we printed their
+pids, so one need to either stop or freeze processes being inspected
+if precise results are needed.
+
+
 ------------------------------------------------------------------------------
 Configuring procfs
 ------------------------------------------------------------------------------
Index: linux-2.6.git/fs/proc/array.c
===================================================================
--- linux-2.6.git.orig/fs/proc/array.c
+++ linux-2.6.git/fs/proc/array.c
@@ -556,3 +556,126 @@ int proc_pid_statm(struct seq_file *m, s
 
 	return 0;
 }
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static struct pid *
+get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
+{
+	struct task_struct *start, *task;
+	struct pid *pid = NULL;
+
+	read_lock(&tasklist_lock);
+
+	start = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (!start)
+		goto out;
+
+	/*
+	 * Lets try to continue searching first, this gives
+	 * us significant speedup on children-rich processes.
+	 */
+	if (pid_prev) {
+		task = pid_task(pid_prev, PIDTYPE_PID);
+		if (task && task->real_parent == start &&
+		    !(list_empty(&task->sibling))) {
+			if (list_is_last(&task->sibling, &start->children))
+				goto out;
+			task = list_first_entry(&task->sibling,
+						struct task_struct, sibling);
+			pid = get_pid(task_pid(task));
+			goto out;
+		}
+	}
+
+	/*
+	 * Slow search case.
+	 *
+	 * We might miss some children here if children
+	 * are exited while we were not holding the lock,
+	 * but it was never promised to be accurate that
+	 * much.
+	 *
+	 * "Just suppose that the parent sleeps, but N children
+	 *  exit after we printed their tids. Now the slow paths
+	 *  skips N extra children, we miss N tasks." (c)
+	 *
+	 * So one need to stop or freeze the leader and all
+	 * its children to get a precise result.
+	 */
+	list_for_each_entry(task, &start->children, sibling) {
+		if (pos-- == 0) {
+			pid = get_pid(task_pid(task));
+			break;
+		}
+	}
+
+out:
+	read_unlock(&tasklist_lock);
+	return pid;
+}
+
+static int children_seq_show(struct seq_file *seq, void *v)
+{
+	struct inode *inode = seq->private;
+	pid_t pid;
+
+	pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
+	return seq_printf(seq, "%d ", pid);
+}
+
+static void *children_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return get_children_pid(seq->private, NULL, *pos);
+}
+
+static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct pid *pid;
+
+	pid = get_children_pid(seq->private, v, *pos + 1);
+	put_pid(v);
+
+	++*pos;
+	return pid;
+}
+
+static void children_seq_stop(struct seq_file *seq, void *v)
+{
+	put_pid(v);
+}
+
+static const struct seq_operations children_seq_ops = {
+	.start	= children_seq_start,
+	.next	= children_seq_next,
+	.stop	= children_seq_stop,
+	.show	= children_seq_show,
+};
+
+static int children_seq_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &children_seq_ops);
+	if (ret)
+		return ret;
+
+	m = file->private_data;
+	m->private = inode;
+
+	return ret;
+}
+
+int children_seq_release(struct inode *inode, struct file *file)
+{
+	seq_release(inode, file);
+	return 0;
+}
+
+const struct file_operations proc_tid_children_operations = {
+	.open    = children_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = children_seq_release,
+};
+#endif /* CONFIG_CHECKPOINT_RESTORE */
Index: linux-2.6.git/fs/proc/base.c
===================================================================
--- linux-2.6.git.orig/fs/proc/base.c
+++ linux-2.6.git/fs/proc/base.c
@@ -3350,6 +3350,9 @@ static const struct pid_entry tid_base_s
 	ONE("stat",      S_IRUGO, proc_tid_stat),
 	ONE("statm",     S_IRUGO, proc_pid_statm),
 	REG("maps",      S_IRUGO, proc_maps_operations),
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	REG("children",  S_IRUGO, proc_tid_children_operations),
+#endif
 #ifdef CONFIG_NUMA
 	REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
 #endif
Index: linux-2.6.git/fs/proc/internal.h
===================================================================
--- linux-2.6.git.orig/fs/proc/internal.h
+++ linux-2.6.git/fs/proc/internal.h
@@ -53,6 +53,7 @@ extern int proc_pid_statm(struct seq_fil
 				struct pid *pid, struct task_struct *task);
 extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
 
+extern const struct file_operations proc_tid_children_operations;
 extern const struct file_operations proc_maps_operations;
 extern const struct file_operations proc_numa_maps_operations;
 extern const struct file_operations proc_smaps_operations;

[patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[Cyrill Gorcunov]

[-- Attachment #1: sys-kcmp-15 --]
[-- Type: text/plain, Size: 11942 bytes --]

While doing the checkpoint-restore in the user space one need to determine
whether various kernel objects (like mm_struct-s of file_struct-s) are shared
between tasks and restore this state.

The 2nd step can be solved by using appropriate CLONE_ flags and the unshare
syscall, while there's currently no ways for solving the 1st one.

One of the ways for checking whether two tasks share e.g. mm_struct is to
provide some mm_struct ID of a task to its proc file, but showing such
info considered to be not that good for security reasons.

Thus after some debates we end up in conclusion that using that named
'comparison' syscall might be the best candidate. So here is it --
__NR_kcmp.

It takes up to 5 arguments - the pids of the two tasks (which
characteristics should be compared), the comparison type and
(in case of comparison of files) two file descriptors.

Lookups for pids are done in the caller's PID namespace only.

At moment only x86 is supported and tested.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
CC: "Eric W. Biederman" <ebiederm@xmission.com>
CC: Pavel Emelyanov <xemul@parallels.com>
CC: Andrey Vagin <avagin@openvz.org>
CC: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
CC: Ingo Molnar <mingo@elte.hu>
CC: H. Peter Anvin <hpa@zytor.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Glauber Costa <glommer@parallels.com>
CC: Andi Kleen <andi@firstfloor.org>
CC: Tejun Heo <tj@kernel.org>
CC: Matt Helsley <matthltc@us.ibm.com>
CC: Pekka Enberg <penberg@kernel.org>
CC: Eric Dumazet <eric.dumazet@gmail.com>
CC: Vasiliy Kulikov <segoon@openwall.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Alexey Dobriyan <adobriyan@gmail.com>
CC: Valdis.Kletnieks@vt.edu
CC: Michal Marek <mmarek@suse.cz>
---
 arch/x86/syscalls/syscall_32.tbl         |    1 
 arch/x86/syscalls/syscall_64.tbl         |    1 
 include/linux/kcmp.h                     |   17 +++
 include/linux/syscalls.h                 |    2 
 kernel/Makefile                          |    3 
 kernel/kcmp.c                            |  155 +++++++++++++++++++++++++++++++
 kernel/sys_ni.c                          |    3 
 tools/testing/selftests/kcmp/Makefile    |   36 +++++++
 tools/testing/selftests/kcmp/kcmp_test.c |   84 ++++++++++++++++
 tools/testing/selftests/run_tests        |    2 
 10 files changed, 303 insertions(+), 1 deletion(-)

Index: linux-2.6.git/arch/x86/syscalls/syscall_32.tbl
===================================================================
--- linux-2.6.git.orig/arch/x86/syscalls/syscall_32.tbl
+++ linux-2.6.git/arch/x86/syscalls/syscall_32.tbl
@@ -355,3 +355,4 @@
 346	i386	setns			sys_setns
 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
+349	i386	kcmp			sys_kcmp
Index: linux-2.6.git/arch/x86/syscalls/syscall_64.tbl
===================================================================
--- linux-2.6.git.orig/arch/x86/syscalls/syscall_64.tbl
+++ linux-2.6.git/arch/x86/syscalls/syscall_64.tbl
@@ -318,3 +318,4 @@
 309	64	getcpu			sys_getcpu
 310	64	process_vm_readv	sys_process_vm_readv
 311	64	process_vm_writev	sys_process_vm_writev
+312	64	kcmp			sys_kcmp
Index: linux-2.6.git/include/linux/kcmp.h
===================================================================
--- /dev/null
+++ linux-2.6.git/include/linux/kcmp.h
@@ -0,0 +1,17 @@
+#ifndef _LINUX_KCMP_H
+#define _LINUX_KCMP_H
+
+/* Comparison type */
+enum kcmp_type {
+	KCMP_FILE,
+	KCMP_VM,
+	KCMP_FILES,
+	KCMP_FS,
+	KCMP_SIGHAND,
+	KCMP_IO,
+	KCMP_SYSVSEM,
+
+	KCMP_TYPES,
+};
+
+#endif /* _LINUX_KCMP_H */
Index: linux-2.6.git/include/linux/syscalls.h
===================================================================
--- linux-2.6.git.orig/include/linux/syscalls.h
+++ linux-2.6.git/include/linux/syscalls.h
@@ -857,4 +857,6 @@ asmlinkage long sys_process_vm_writev(pi
 				      unsigned long riovcnt,
 				      unsigned long flags);
 
+asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
+			 unsigned long idx1, unsigned long idx2);
 #endif
Index: linux-2.6.git/kernel/Makefile
===================================================================
--- linux-2.6.git.orig/kernel/Makefile
+++ linux-2.6.git/kernel/Makefile
@@ -25,6 +25,9 @@ endif
 obj-y += sched/
 obj-y += power/
 
+ifeq ($(CONFIG_CHECKPOINT_RESTORE),y)
+obj-$(CONFIG_X86) += kcmp.o
+endif
 obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
Index: linux-2.6.git/kernel/kcmp.c
===================================================================
--- /dev/null
+++ linux-2.6.git/kernel/kcmp.c
@@ -0,0 +1,155 @@
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+#include <linux/fdtable.h>
+#include <linux/string.h>
+#include <linux/random.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/cache.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/kcmp.h>
+
+#include <asm/unistd.h>
+
+/*
+ * We don't expose real in-memory order of objects for security
+ * reasons, still the comparison results should be suitable for
+ * sorting. Thus, we obfuscate kernel pointers values and compare
+ * the production instead.
+ */
+static unsigned long cookies[KCMP_TYPES][2] __read_mostly;
+
+static long kptr_obfuscate(long v, int type)
+{
+	return (v ^ cookies[type][0]) * cookies[type][1];
+}
+
+/*
+ * 0 - equal, i.e. v1 = v2
+ * 1 - less than, i.e. v1 < v2
+ * 2 - greater than, i.e. v1 > v2
+ * 3 - not equal but ordering unavailable (reserved for future)
+ */
+static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
+{
+	long ret;
+
+	ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+
+	return (ret < 0) | ((ret > 0) << 1);
+}
+
+/* The caller must have pinned the task */
+static struct file *
+get_file_raw_ptr(struct task_struct *task, unsigned int idx)
+{
+	struct fdtable *fdt;
+	struct file *file;
+
+	spin_lock(&task->files->file_lock);
+	fdt = files_fdtable(task->files);
+	if (idx < fdt->max_fds)
+		file = fdt->fd[idx];
+	else
+		file = NULL;
+	spin_unlock(&task->files->file_lock);
+
+	return file;
+}
+
+SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
+		unsigned long, idx1, unsigned long, idx2)
+{
+	struct task_struct *task1, *task2;
+	int ret;
+
+	rcu_read_lock();
+
+	/*
+	 * Tasks are looked up in caller's PID namespace only.
+	 */
+	task1 = find_task_by_vpid(pid1);
+	task2 = find_task_by_vpid(pid2);
+	if (!task1 || !task2)
+		goto err_no_task;
+
+	get_task_struct(task1);
+	get_task_struct(task2);
+
+	rcu_read_unlock();
+
+	/*
+	 * One should have enough rights to inspect task details.
+	 */
+	if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
+	    !ptrace_may_access(task2, PTRACE_MODE_READ)) {
+		ret = -EACCES;
+		goto err;
+	}
+
+	switch (type) {
+	case KCMP_FILE: {
+		struct file *filp1, *filp2;
+
+		filp1 = get_file_raw_ptr(task1, idx1);
+		filp2 = get_file_raw_ptr(task2, idx2);
+
+		if (filp1 && filp2)
+			ret = kcmp_ptr(filp1, filp2, KCMP_FILE);
+		else
+			ret = -EBADF;
+		break;
+	}
+	case KCMP_VM:
+		ret = kcmp_ptr(task1->mm, task2->mm, KCMP_VM);
+		break;
+	case KCMP_FILES:
+		ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES);
+		break;
+	case KCMP_FS:
+		ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS);
+		break;
+	case KCMP_SIGHAND:
+		ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND);
+		break;
+	case KCMP_IO:
+		ret = kcmp_ptr(task1->io_context, task2->io_context, KCMP_IO);
+		break;
+	case KCMP_SYSVSEM:
+#ifdef CONFIG_SYSVIPC
+		ret = kcmp_ptr(task1->sysvsem.undo_list,
+			       task2->sysvsem.undo_list,
+			       KCMP_SYSVSEM);
+#else
+		ret = -EOPNOTSUP;
+#endif
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+err:
+	put_task_struct(task1);
+	put_task_struct(task2);
+
+	return ret;
+
+err_no_task:
+	rcu_read_unlock();
+	return -ESRCH;
+}
+
+static __init int kcmp_cookies_init(void)
+{
+	int i;
+
+	get_random_bytes(cookies, sizeof(cookies));
+
+	for (i = 0; i < KCMP_TYPES; i++)
+		cookies[i][1] |= (~(~0UL >>  1) | 1);
+
+	return 0;
+}
+arch_initcall(kcmp_cookies_init);
Index: linux-2.6.git/kernel/sys_ni.c
===================================================================
--- linux-2.6.git.orig/kernel/sys_ni.c
+++ linux-2.6.git/kernel/sys_ni.c
@@ -203,3 +203,6 @@ cond_syscall(sys_fanotify_mark);
 cond_syscall(sys_name_to_handle_at);
 cond_syscall(sys_open_by_handle_at);
 cond_syscall(compat_sys_open_by_handle_at);
+
+/* compare kernel pointers */
+cond_syscall(sys_kcmp);
Index: linux-2.6.git/tools/testing/selftests/kcmp/Makefile
===================================================================
--- /dev/null
+++ linux-2.6.git/tools/testing/selftests/kcmp/Makefile
@@ -0,0 +1,36 @@
+ifeq ($(strip $(V)),)
+	E = @echo
+	Q = @
+else
+	E = @\#
+	Q =
+endif
+export E Q
+
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
+ifeq ($(ARCH),i386)
+        ARCH := X86
+	CFLAGS := -DCONFIG_X86_32 -D__i386__
+endif
+ifeq ($(ARCH),x86_64)
+	ARCH := X86
+	CFLAGS := -DCONFIG_X86_64 -D__x86_64__
+endif
+
+CFLAGS += -I../../../../arch/x86/include/generated/
+CFLAGS += -I../../../../include/
+CFLAGS += -I../../../../usr/include/
+
+all:
+ifeq ($(ARCH),X86)
+	$(E) "  CC run_test"
+	$(Q) gcc $(CFLAGS) kcmp_test.c -o run_test
+else
+	$(E) "Not an x86 target, can't build kcmp selftest"
+endif
+
+clean:
+	$(E) "  CLEAN"
+	$(Q) rm -fr ./run_test
+	$(Q) rm -fr ./test-file
Index: linux-2.6.git/tools/testing/selftests/kcmp/kcmp_test.c
===================================================================
--- /dev/null
+++ linux-2.6.git/tools/testing/selftests/kcmp/kcmp_test.c
@@ -0,0 +1,84 @@
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <limits.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <fcntl.h>
+
+#include <linux/unistd.h>
+#include <linux/kcmp.h>
+
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+
+static long sys_kcmp(int pid1, int pid2, int type, int fd1, int fd2)
+{
+	return syscall(__NR_kcmp, pid1, pid2, type, fd1, fd2);
+}
+
+int main(int argc, char **argv)
+{
+	const char kpath[] = "kcmp-test-file";
+	int pid1, pid2;
+	int fd1, fd2;
+	int status;
+
+	fd1 = open(kpath, O_RDWR | O_CREAT | O_TRUNC, 0644);
+	pid1 = getpid();
+
+	if (fd1 < 0) {
+		perror("Can't create file");
+		exit(1);
+	}
+
+	pid2 = fork();
+	if (pid2 < 0) {
+		perror("fork failed");
+		exit(1);
+	}
+
+	if (!pid2) {
+		int pid2 = getpid();
+		int ret;
+
+		fd2 = open(kpath, O_RDWR, 0644);
+		if (fd2 < 0) {
+			perror("Can't open file");
+			exit(1);
+		}
+
+		/* An example of output and arguments */
+		printf("pid1: %6d pid2: %6d FD: %2d FILES: %2d VM: %2d FS: %2d "
+		       "SIGHAND: %2d IO: %2d SYSVSEM: %2d INV: %2d\n",
+		       pid1, pid2,
+		       sys_kcmp(pid1, pid2, KCMP_FILE,		fd1, fd2),
+		       sys_kcmp(pid1, pid2, KCMP_FILES,		0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_VM,		0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_FS,		0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_SIGHAND,	0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_IO,		0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_SYSVSEM,	0, 0),
+
+			/* This one should fail */
+		       sys_kcmp(pid1, pid2, KCMP_TYPES + 1,	0, 0));
+
+		/* This one should return same fd */
+		ret = sys_kcmp(pid1, pid2, KCMP_FILE, fd1, fd1);
+		if (ret) {
+			printf("FAIL: 0 expected but %d returned\n", ret);
+			ret = -1;
+		} else
+			printf("PASS: 0 returned as expected\n");
+		exit(ret);
+	}
+
+	waitpid(pid2, &status, P_ALL);
+
+	return 0;
+}
Index: linux-2.6.git/tools/testing/selftests/run_tests
===================================================================
--- linux-2.6.git.orig/tools/testing/selftests/run_tests
+++ linux-2.6.git/tools/testing/selftests/run_tests
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-TARGETS=breakpoints
+TARGETS="breakpoints kcmp"
 
 for TARGET in $TARGETS
 do

Re: [patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[Andrew Morton]

On Mon, 13 Feb 2012 20:48:24 +0400
Cyrill Gorcunov <gorcunov@openvz.org> wrote:

> While doing the checkpoint-restore in the user space one need to determine
> whether various kernel objects (like mm_struct-s of file_struct-s) are shared
> between tasks and restore this state.
> 
> The 2nd step can be solved by using appropriate CLONE_ flags and the unshare
> syscall, while there's currently no ways for solving the 1st one.
> 
> One of the ways for checking whether two tasks share e.g. mm_struct is to
> provide some mm_struct ID of a task to its proc file, but showing such
> info considered to be not that good for security reasons.
> 
> Thus after some debates we end up in conclusion that using that named
> 'comparison' syscall might be the best candidate. So here is it --
> __NR_kcmp.
> 
> It takes up to 5 arguments - the pids of the two tasks (which
> characteristics should be compared), the comparison type and
> (in case of comparison of files) two file descriptors.
> 
> Lookups for pids are done in the caller's PID namespace only.
> 
> At moment only x86 is supported and tested.
> 
>
> ...
>
> --- /dev/null
> +++ linux-2.6.git/tools/testing/selftests/kcmp/Makefile
> @@ -0,0 +1,36 @@
> +ifeq ($(strip $(V)),)
> +	E = @echo
> +	Q = @
> +else
> +	E = @\#
> +	Q =
> +endif
> +export E Q
> +
> +uname_M := $(shell uname -m 2>/dev/null || echo not)
> +ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
> +ifeq ($(ARCH),i386)
> +        ARCH := X86
> +	CFLAGS := -DCONFIG_X86_32 -D__i386__
> +endif
> +ifeq ($(ARCH),x86_64)
> +	ARCH := X86
> +	CFLAGS := -DCONFIG_X86_64 -D__x86_64__
> +endif
> +
> +CFLAGS += -I../../../../arch/x86/include/generated/
> +CFLAGS += -I../../../../include/
> +CFLAGS += -I../../../../usr/include/
> +
> +all:
> +ifeq ($(ARCH),X86)
> +	$(E) "  CC run_test"
> +	$(Q) gcc $(CFLAGS) kcmp_test.c -o run_test
> +else
> +	$(E) "Not an x86 target, can't build kcmp selftest"
> +endif
> +
> +clean:
> +	$(E) "  CLEAN"
> +	$(Q) rm -fr ./run_test
> +	$(Q) rm -fr ./test-file

hm, what does all this stuff in the selftest makefile do?


The selftests code has undergone some changes since you last looked. 
The rules are, roughly:

- In tools/testing/selftests, a "make" will compile but not run all
  selftest code.

- In tools/testing/selftests, a "make run_tests" will compile all
  selftest code (if needed) and will then run all the tests.

  If a test is not applicable (eg wrong architecture, kernel feature
  not enabled, etc) then it should try to avoid breaking the build and,
  when executed it should emit a diagnostic and then exit(0) (ie:
  success) so as to avoid breaking the overall test run.

  IOW, the test should only fail if the feature is present but isn't
  working correctly.

Also, I hate with a passion Makefiles which hide the command lines from
me!  So I nuked all that E and Q stuff.

Result:

--- a/tools/testing/selftests/kcmp/Makefile~syscalls-x86-add-__nr_kcmp-syscall-v8-fix
+++ a/tools/testing/selftests/kcmp/Makefile
@@ -1,12 +1,3 @@
-ifeq ($(strip $(V)),)
-	E = @echo
-	Q = @
-else
-	E = @\#
-	Q =
-endif
-export E Q
-
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
 ifeq ($(ARCH),i386)
@@ -24,13 +15,14 @@ CFLAGS += -I../../../../usr/include/
 
 all:
 ifeq ($(ARCH),X86)
-	$(E) "  CC run_test"
-	$(Q) gcc $(CFLAGS) kcmp_test.c -o run_test
+	gcc $(CFLAGS) kcmp_test.c -o run_test
 else
-	$(E) "Not an x86 target, can't build kcmp selftest"
+	echo "Not an x86 target, can't build kcmp selftest"
 endif
 
+run-tests: all
+	./kcmp_test
+
 clean:
-	$(E) "  CLEAN"
-	$(Q) rm -fr ./run_test
-	$(Q) rm -fr ./test-file
+	rm -fr ./run_test
+	rm -fr ./test-file
--- a/tools/testing/selftests/Makefile~syscalls-x86-add-__nr_kcmp-syscall-v8-fix
+++ a/tools/testing/selftests/Makefile
@@ -1,4 +1,4 @@
-TARGETS = breakpoints vm
+TARGETS = breakpoints vm kcmp
 
 all:
 	for TARGET in $(TARGETS); do \
_


However that didn't work for me:

akpm:/usr/src/25/tools/testing/selftests/kcmp> make
gcc -DCONFIG_X86_64 -D__x86_64__ -I../../../../arch/x86/include/generated/ -I../../../../include/ -I../../../../usr/include/ kcmp_test.c -o run_test
kcmp_test.c: In function 'sys_kcmp':
kcmp_test.c:22: error: '__NR_kcmp' undeclared (first use in this function)
kcmp_test.c:22: error: (Each undeclared identifier is reported only once
kcmp_test.c:22: error: for each function it appears in.)
kcmp_test.c: In function 'main':
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 4 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 5 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 6 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 7 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 8 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 9 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 10 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 11 has type 'long int'


How are we supposed to be picking up __NR_kcmp?

Re: [patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[Cyrill Gorcunov]

On Tue, Feb 14, 2012 at 03:13:12PM -0800, Andrew Morton wrote:
...
> 
> hm, what does all this stuff in the selftest makefile do?
> 
> The selftests code has undergone some changes since you last looked. 

Hmm, thanks for pointing.

> The rules are, roughly:
> 
> - In tools/testing/selftests, a "make" will compile but not run all
>   selftest code.
> 
> - In tools/testing/selftests, a "make run_tests" will compile all
>   selftest code (if needed) and will then run all the tests.
> 
>   If a test is not applicable (eg wrong architecture, kernel feature
>   not enabled, etc) then it should try to avoid breaking the build and,
>   when executed it should emit a diagnostic and then exit(0) (ie:
>   success) so as to avoid breaking the overall test run.
> 
>   IOW, the test should only fail if the feature is present but isn't
>   working correctly.
> 
> Also, I hate with a passion Makefiles which hide the command lines from
> me!  So I nuked all that E and Q stuff.
> 

make V=1 will show the command line, I tried to make the output to look
the same as in case of building kernel.

> 
> However that didn't work for me:
> 
> akpm:/usr/src/25/tools/testing/selftests/kcmp> make
> gcc -DCONFIG_X86_64 -D__x86_64__ -I../../../../arch/x86/include/generated/ ...
> kcmp_test.c: In function 'sys_kcmp':
> kcmp_test.c:22: error: '__NR_kcmp' undeclared (first use in this function)
...
> How are we supposed to be picking up __NR_kcmp?
> 

Initially I made it to look into arch/x86 directory and find __NR_kcmp
definition there but then I realised (and someone pointed me as
well) that headers should be taken from those which are generated
by kernel, ie the result of 'make headers_install'. So if you run
make headers_install then the test program should work. If this is
wrong, I can fix it and make a patch on top.

Ie instead of

+#include <linux/unistd.h>

there will be

+#ifdef CONFIG_X86_64
+#include <asm/unistd_64.h>
+#else
+#include <asm/unistd_32.h>
+#endif

	Cyrill

Re: [patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[hpanvin@gmail.com]

What?  <linux/unistd.h> should be used, and it should handle the.inclusions.

Cyrill Gorcunov <gorcunov@openvz.org> wrote:

>On Tue, Feb 14, 2012 at 03:13:12PM -0800, Andrew Morton wrote:
>...
>> 
>> hm, what does all this stuff in the selftest makefile do?
>> 
>> The selftests code has undergone some changes since you last looked. 
>
>Hmm, thanks for pointing.
>
>> The rules are, roughly:
>> 
>> - In tools/testing/selftests, a "make" will compile but not run all
>>   selftest code.
>> 
>> - In tools/testing/selftests, a "make run_tests" will compile all
>>   selftest code (if needed) and will then run all the tests.
>> 
>>   If a test is not applicable (eg wrong architecture, kernel feature
>>   not enabled, etc) then it should try to avoid breaking the build
>and,
>>   when executed it should emit a diagnostic and then exit(0) (ie:
>>   success) so as to avoid breaking the overall test run.
>> 
>>   IOW, the test should only fail if the feature is present but isn't
>>   working correctly.
>> 
>> Also, I hate with a passion Makefiles which hide the command lines
>from
>> me!  So I nuked all that E and Q stuff.
>> 
>
>make V=1 will show the command line, I tried to make the output to look
>the same as in case of building kernel.
>
>> 
>> However that didn't work for me:
>> 
>> akpm:/usr/src/25/tools/testing/selftests/kcmp> make
>> gcc -DCONFIG_X86_64 -D__x86_64__
>-I../../../../arch/x86/include/generated/ ...
>> kcmp_test.c: In function 'sys_kcmp':
>> kcmp_test.c:22: error: '__NR_kcmp' undeclared (first use in this
>function)
>...
>> How are we supposed to be picking up __NR_kcmp?
>> 
>
>Initially I made it to look into arch/x86 directory and find __NR_kcmp
>definition there but then I realised (and someone pointed me as
>well) that headers should be taken from those which are generated
>by kernel, ie the result of 'make headers_install'. So if you run
>make headers_install then the test program should work. If this is
>wrong, I can fix it and make a patch on top.
>
>Ie instead of
>
>+#include <linux/unistd.h>
>
>there will be
>
>+#ifdef CONFIG_X86_64
>+#include <asm/unistd_64.h>
>+#else
>+#include <asm/unistd_32.h>
>+#endif
>
>	Cyrill

-- 
Sent from my Android phone with K-9 Mail. Please excuse my brevity.

Re: [patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[Cyrill Gorcunov]

On Tue, Feb 14, 2012 at 10:55:55PM -0800, hpanvin@gmail.com wrote:
>
> What?  <linux/unistd.h> should be used, and it should handle
> the inclusions.
>

Peter, I maybe missing something which directories I should
add to -I option, letme recheck (but without headers_intall
target the syscall number is unresolved for me).

	Cyrill

Re: [patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[Cyrill Gorcunov]

On Wed, Feb 15, 2012 at 11:04:27AM +0400, Cyrill Gorcunov wrote:
> On Tue, Feb 14, 2012 at 10:55:55PM -0800, hpanvin@gmail.com wrote:
> >
> > What?  <linux/unistd.h> should be used, and it should handle
> > the inclusions.
> >
> 
> Peter, I maybe missing something which directories I should
> add to -I option, letme recheck (but without headers_intall
> target the syscall number is unresolved for me).
> 

Ah, I missed to add

+CFLAGS += -I../../../../arch/x86/include/

into Makefile. Andrew, should I send update as a separate
patch?

	Cyrill

Re: [patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[Andrew Morton]

On Wed, 15 Feb 2012 11:24:54 +0400
Cyrill Gorcunov <gorcunov@openvz.org> wrote:

> On Wed, Feb 15, 2012 at 11:04:27AM +0400, Cyrill Gorcunov wrote:
> > On Tue, Feb 14, 2012 at 10:55:55PM -0800, hpanvin@gmail.com wrote:
> > >
> > > What?  <linux/unistd.h> should be used, and it should handle
> > > the inclusions.
> > >
> > 
> > Peter, I maybe missing something which directories I should
> > add to -I option, letme recheck (but without headers_intall
> > target the syscall number is unresolved for me).
> > 
> 
> Ah, I missed to add
> 
> +CFLAGS += -I../../../../arch/x86/include/
> 
> into Makefile. Andrew, should I send update as a separate
> patch?
> 

That worked.

What's with all those warnings, btw?


From: Andrew Morton <akpm@linux-foundation.org>
Subject: syscalls-x86-add-__nr_kcmp-syscall-v8-fix-fix-fix

kcmp_test.c: In function 'main':
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 4 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 5 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 6 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 7 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 8 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 9 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 10 has type 'long int'
kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 11 has type 'long int'

Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 tools/testing/selftests/kcmp/kcmp_test.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/kcmp/kcmp_test.c~syscalls-x86-add-__nr_kcmp-syscall-v8-fix-fix-fix
+++ a/tools/testing/selftests/kcmp/kcmp_test.c
@@ -54,8 +54,9 @@ int main(int argc, char **argv)
 		}
 
 		/* An example of output and arguments */
-		printf("pid1: %6d pid2: %6d FD: %2d FILES: %2d VM: %2d FS: %2d "
-		       "SIGHAND: %2d IO: %2d SYSVSEM: %2d INV: %2d\n",
+		printf("pid1: %6d pid2: %6d FD: %2ld FILES: %2ld VM: %2ld "
+		       "FS: %2ld SIGHAND: %2ld IO: %2ld SYSVSEM: %2ld "
+		       "INV: %2ld\n",
 		       pid1, pid2,
 		       sys_kcmp(pid1, pid2, KCMP_FILE,		fd1, fd2),
 		       sys_kcmp(pid1, pid2, KCMP_FILES,		0, 0),
_

Re: [patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[Cyrill Gorcunov]

On Wed, Feb 15, 2012 at 01:53:13PM -0800, Andrew Morton wrote:
> That worked.
> 
> What's with all those warnings, btw?
> 
> From: Andrew Morton <akpm@linux-foundation.org>
> Subject: syscalls-x86-add-__nr_kcmp-syscall-v8-fix-fix-fix
> 
> kcmp_test.c: In function 'main':
> kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 4 has type 'long int'

Indeed it's nit, wonder why I've not beed warned by compiler before
(nothing serious since results do fit integer anyway but _must_
 be fixed). I'll update shortly. Sorry for that.

	Cyrill

Re: [patch 2/4] syscalls, x86: Add __NR_kcmp syscall v8

[Cyrill Gorcunov]

On Thu, Feb 16, 2012 at 02:00:40AM +0400, Cyrill Gorcunov wrote:
> On Wed, Feb 15, 2012 at 01:53:13PM -0800, Andrew Morton wrote:
> > That worked.
> > 
> > What's with all those warnings, btw?
> > 
> > From: Andrew Morton <akpm@linux-foundation.org>
> > Subject: syscalls-x86-add-__nr_kcmp-syscall-v8-fix-fix-fix
> > 
> > kcmp_test.c: In function 'main':
> > kcmp_test.c:69: warning: format '%2d' expects type 'int', but argument 4 has type 'long int'
> 
> Indeed it's nit, wonder why I've not beed warned by compiler before
> (nothing serious since results do fit integer anyway but _must_
>  be fixed). I'll update shortly. Sorry for that.
> 

Heh, I just realized that you've fixed it already. Thanks a lot!

	Cyrill

[patch 3/4] c/r: procfs: add arg_start/end, env_start/end and exit_code members to /proc/$pid/stat

[Cyrill Gorcunov]

[-- Attachment #1: fs-proc-extend-state-2-linux-next --]
[-- Type: text/plain, Size: 3085 bytes --]

We would like to have an ability to restore command line
arguments and program environment pointers but first we
need to obtain them somehow. Thus we put these values into
/proc/$pid/stat. The exit_code is needed to restore zombie
tasks.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Vasiliy Kulikov <segoon@openwall.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
---
 Documentation/filesystems/proc.txt |    5 +++++
 fs/proc/array.c                    |   20 +++++++++++++++++---
 2 files changed, 22 insertions(+), 3 deletions(-)

Index: linux-2.6.git/Documentation/filesystems/proc.txt
===================================================================
--- linux-2.6.git.orig/Documentation/filesystems/proc.txt
+++ linux-2.6.git/Documentation/filesystems/proc.txt
@@ -311,6 +311,11 @@ Table 1-4: Contents of the stat files (a
   start_data    address above which program data+bss is placed
   end_data      address below which program data+bss is placed
   start_brk     address above which program heap can be expanded with brk()
+  arg_start     address above which program command line is placed
+  arg_end       address below which program command line is placed
+  env_start     address above which program environment is placed
+  env_end       address below which program environment is placed
+  exit_code     the thread's exit_code in the form reported by the waitpid system call
 ..............................................................................
 
 The /proc/PID/maps file containing the currently mapped memory regions and
Index: linux-2.6.git/fs/proc/array.c
===================================================================
--- linux-2.6.git.orig/fs/proc/array.c
+++ linux-2.6.git/fs/proc/array.c
@@ -508,9 +508,23 @@ static int do_task_stat(struct seq_file
 	seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task));
 	seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime));
 	seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime));
-	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_data : 0);
-	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->end_data : 0);
-	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_brk : 0);
+
+	if (mm && permitted) {
+		seq_put_decimal_ull(m, ' ', mm->start_data);
+		seq_put_decimal_ull(m, ' ', mm->end_data);
+		seq_put_decimal_ull(m, ' ', mm->start_brk);
+		seq_put_decimal_ull(m, ' ', mm->arg_start);
+		seq_put_decimal_ull(m, ' ', mm->arg_end);
+		seq_put_decimal_ull(m, ' ', mm->env_start);
+		seq_put_decimal_ull(m, ' ', mm->env_end);
+	} else
+		seq_printf(m, " 0 0 0 0 0 0 0");
+
+	if (permitted)
+		seq_put_decimal_ll(m, ' ', task->exit_code);
+	else
+		seq_put_decimal_ll(m, ' ', 0);
+
 	seq_putc(m, '\n');
 	if (mm)
 		mmput(mm);

[patch 4/4] c/r: prctl: Extend PR_SET_MM to set up more mm_struct entries v2

[Cyrill Gorcunov]

[-- Attachment #1: prctl-restore-mm-members-7 --]
[-- Type: text/plain, Size: 6413 bytes --]

During checkpoint we dump whole process memory to a file and
the dump includes process stack memory. But among stack data
itself, the stack carries additional parameters such as command
line arguments, environment data and auxiliary vector.

So when we do restore procedure and once we've restored stack
data itself we need to setup mm_struct::arg_start/end,
env_start/end, so restored process would be able to find
command line arguments and environment data it had at checkpoint
time. The same applies to auxiliary vector.

For this reason additional PR_SET_MM_(ARG_START | ARG_END |
ENV_START | ENV_END | AUXV) codes are introduced.

v2: Add BUILD_BUG_ON guard

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Vasiliy Kulikov <segoon@openwall.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/prctl.h |    5 ++
 kernel/sys.c          |  113 +++++++++++++++++++++++++++++++++++---------------
 2 files changed, 85 insertions(+), 33 deletions(-)

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
@@ -113,5 +113,10 @@
 # define PR_SET_MM_START_STACK		5
 # define PR_SET_MM_START_BRK		6
 # define PR_SET_MM_BRK			7
+# define PR_SET_MM_ARG_START		8
+# define PR_SET_MM_ARG_END		9
+# define PR_SET_MM_ENV_START		10
+# define PR_SET_MM_ENV_END		11
+# define PR_SET_MM_AUXV			12
 
 #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
@@ -1693,17 +1693,23 @@ SYSCALL_DEFINE1(umask, int, mask)
 }
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
+static bool vma_flags_mismatch(struct vm_area_struct *vma,
+			       unsigned long required,
+			       unsigned long banned)
+{
+	return (vma->vm_flags & required) != required ||
+		(vma->vm_flags & banned);
+}
+
 static int prctl_set_mm(int opt, unsigned long addr,
 			unsigned long arg4, unsigned long arg5)
 {
 	unsigned long rlim = rlimit(RLIMIT_DATA);
-	unsigned long vm_req_flags;
-	unsigned long vm_bad_flags;
-	struct vm_area_struct *vma;
-	int error = 0;
 	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int error;
 
-	if (arg4 | arg5)
+	if (arg5 || (arg4 && opt != PR_SET_MM_AUXV))
 		return -EINVAL;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -1712,24 +1718,24 @@ static int prctl_set_mm(int opt, unsigne
 	if (addr >= TASK_SIZE)
 		return -EINVAL;
 
+	error = -EINVAL;
+
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, addr);
 
-	if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) {
+	if (opt != PR_SET_MM_START_BRK &&
+	    opt != PR_SET_MM_BRK &&
+	    opt != PR_SET_MM_AUXV) {
 		/* It must be existing VMA */
 		if (!vma || vma->vm_start > addr)
 			goto out;
 	}
 
-	error = -EINVAL;
 	switch (opt) {
 	case PR_SET_MM_START_CODE:
 	case PR_SET_MM_END_CODE:
-		vm_req_flags = VM_READ | VM_EXEC;
-		vm_bad_flags = VM_WRITE | VM_MAYSHARE;
-
-		if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
-		    (vma->vm_flags & vm_bad_flags))
+		if (vma_flags_mismatch(vma, VM_READ | VM_EXEC,
+				       VM_WRITE | VM_MAYSHARE))
 			goto out;
 
 		if (opt == PR_SET_MM_START_CODE)
@@ -1740,11 +1746,8 @@ static int prctl_set_mm(int opt, unsigne
 
 	case PR_SET_MM_START_DATA:
 	case PR_SET_MM_END_DATA:
-		vm_req_flags = VM_READ | VM_WRITE;
-		vm_bad_flags = VM_EXEC | VM_MAYSHARE;
-
-		if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
-		    (vma->vm_flags & vm_bad_flags))
+		if (vma_flags_mismatch(vma, VM_READ | VM_WRITE,
+				       VM_EXEC | VM_MAYSHARE))
 			goto out;
 
 		if (opt == PR_SET_MM_START_DATA)
@@ -1753,19 +1756,6 @@ static int prctl_set_mm(int opt, unsigne
 			mm->end_data = addr;
 		break;
 
-	case PR_SET_MM_START_STACK:
-
-#ifdef CONFIG_STACK_GROWSUP
-		vm_req_flags = VM_READ | VM_WRITE | VM_GROWSUP;
-#else
-		vm_req_flags = VM_READ | VM_WRITE | VM_GROWSDOWN;
-#endif
-		if ((vma->vm_flags & vm_req_flags) != vm_req_flags)
-			goto out;
-
-		mm->start_stack = addr;
-		break;
-
 	case PR_SET_MM_START_BRK:
 		if (addr <= mm->end_data)
 			goto out;
@@ -1790,16 +1780,73 @@ static int prctl_set_mm(int opt, unsigne
 		mm->brk = addr;
 		break;
 
+	/*
+	 * If command line arguments and environment
+	 * are placed somewhere else on stack, we can
+	 * set them up here, ARG_START/END to setup
+	 * command line argumets and ENV_START/END
+	 * for environment.
+	 */
+	case PR_SET_MM_START_STACK:
+	case PR_SET_MM_ARG_START:
+	case PR_SET_MM_ARG_END:
+	case PR_SET_MM_ENV_START:
+	case PR_SET_MM_ENV_END:
+#ifdef CONFIG_STACK_GROWSUP
+		if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSUP, 0))
+#else
+		if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSDOWN, 0))
+#endif
+			goto out;
+		if (opt == PR_SET_MM_START_STACK)
+			mm->start_stack = addr;
+		else if (opt == PR_SET_MM_ARG_START)
+			mm->arg_start = addr;
+		else if (opt == PR_SET_MM_ARG_END)
+			mm->arg_end = addr;
+		else if (opt == PR_SET_MM_ENV_START)
+			mm->env_start = addr;
+		else if (opt == PR_SET_MM_ENV_END)
+			mm->env_end = addr;
+		break;
+
+	/*
+	 * This doesn't move auxiliary vector itself
+	 * since it's pinned to mm_struct, but allow
+	 * to fill vector with new values. It's up
+	 * to a caller to provide sane values here
+	 * otherwise user space tools which use this
+	 * vector might be unhappy.
+	 */
+	case PR_SET_MM_AUXV: {
+		unsigned long user_auxv[AT_VECTOR_SIZE];
+
+		if (arg4 > sizeof(user_auxv))
+			goto out;
+		up_read(&mm->mmap_sem);
+
+		if (copy_from_user(user_auxv, (const void __user *)addr, arg4))
+			return -EFAULT;
+
+		/* Make sure the last entry is always AT_NULL */
+		user_auxv[AT_VECTOR_SIZE - 2] = 0;
+		user_auxv[AT_VECTOR_SIZE - 1] = 0;
+
+		BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
+
+		task_lock(current);
+		memcpy(mm->saved_auxv, user_auxv, arg4);
+		task_unlock(current);
+
+		return 0;
+	}
 	default:
-		error = -EINVAL;
 		goto out;
 	}
 
 	error = 0;
-
 out:
 	up_read(&mm->mmap_sem);
-
 	return error;
 }
 #else /* CONFIG_CHECKPOINT_RESTORE */

Re: [patch 0/4] Resending, c/r series v2

[Andrew Morton]

On Mon, 13 Feb 2012 20:48:22 +0400
Cyrill Gorcunov <gorcunov@openvz.org> wrote:

> Hi, this series hopefully in a good shape
> 
>  - sys_kcmp now depends on CONFIG_CHECKPOINT_RESTORE
> 
>  - the extension of /proc/pid/stat now done against
>    linux-next/master
> 
> Please letme know if I've missed something.

Thus far our (my) approach has been to trickle the c/r support code
into mainline as it is developed.  Under the assumption that the end
result will be acceptable and useful kernel code.

I'm afraid that I'm losing confidence in that approach.  We have this
patchset, we have Stanislav's "IPC: checkpoint/restore in userspace
enhancements" (which apparently needs to get more complex to support
LSM context c/r).  I simply *don't know* what additional patchsets are
expected.  And from what you told me it sounds like networking support
is at a very early stage and I fear for what the end result of that
will look like.

So I don't feel that I can continue feeding these things into mainline
until someone can convince me that we won't have a nasty mess (and/or
an unsufficiently useful feature) at the end of the project.


The traditional approach is to develop the feature out-of-tree until it
is "finished".  That's a lot more hackwork for you guys and it leads to
a poorer feature - this approach inevitably has a lower level of review
and inhibits code rework.


An alternative is for me to buffer the patches in my tree until it is
all sufficiently finished.  That also is more work for your team, but
it will produce better code, because of additional review and code
rework resulting from that review.

I don't know how many patches that would end up being (this is part of
the problem!) nor how long they would be carried for.


So.  Please talk to me.  How long is this all going to take, and what
will the final result look like?

Re: [patch 0/4] Resending, c/r series v2

[Pavel Emelyanov]

On 02/15/2012 02:51 AM, Andrew Morton wrote:
> On Mon, 13 Feb 2012 20:48:22 +0400
> Cyrill Gorcunov <gorcunov@openvz.org> wrote:
> 
>> Hi, this series hopefully in a good shape
>>
>>  - sys_kcmp now depends on CONFIG_CHECKPOINT_RESTORE
>>
>>  - the extension of /proc/pid/stat now done against
>>    linux-next/master
>>
>> Please letme know if I've missed something.
> 
> Thus far our (my) approach has been to trickle the c/r support code
> into mainline as it is developed.  Under the assumption that the end
> result will be acceptable and useful kernel code.
> 
> I'm afraid that I'm losing confidence in that approach.  We have this
> patchset, we have Stanislav's "IPC: checkpoint/restore in userspace
> enhancements" (which apparently needs to get more complex to support
> LSM context c/r).  I simply *don't know* what additional patchsets are
> expected.  And from what you told me it sounds like networking support
> is at a very early stage and I fear for what the end result of that
> will look like.

I understand. But there was a confidence that nobody wanted the c/r stuff to 
be the "one big kernel subsystem", but it should rather be "a bunch of small 
API-s for what is required". The amount of code for the initial C/R attempt was
~100 patches. The amount of code to support our user-space C/R implementation
*only* is ~10 and the feature-set of both is already comparable.


As far as the networking is concerned -- we will not require any additional
patches to implement the basic netns configuration migration (ip can show and
re-configure all we need about routing, interfaces, devices, etc. and the
iptables-save/iptables-restore will handle 99.9% of the netfilter part). For
what we currently need is the ability to explore sockets queues, but currently
this doesn't turn out to be a lot of code -- I have 60-lines patch for unix
sockets and Tejun showed the way how to do the same with TCP using 130 lines
of code. UDP won't require anything, its queues can be silently dropped. The
recent 50 patches with *_diag stuff doesn't count, because it works not for C/R
only, the ss tool can benefit from 100% of the added functionality (this, btw, 
shows that not every piece of code we add for C/R is for C/R *only*).

> So I don't feel that I can continue feeding these things into mainline
> until someone can convince me that we won't have a nasty mess (and/or
> an unsufficiently useful feature) at the end of the project.

Isn't the CONFIG_CHECKPOINT_RESTORE option turned off by default enough?

> The traditional approach is to develop the feature out-of-tree until it
> is "finished".  That's a lot more hackwork for you guys and it leads to
> a poorer feature - this approach inevitably has a lower level of review
> and inhibits code rework.

That's why we started sending patches early.

> An alternative is for me to buffer the patches in my tree until it is
> all sufficiently finished.  That also is more work for your team, but
> it will produce better code, because of additional review and code
> rework resulting from that review.
> 
> I don't know how many patches that would end up being (this is part of
> the problem!) nor how long they would be carried for.

Neither do I :(

> So.  Please talk to me.  How long is this all going to take, and what
> will the final result look like?

The Big Intermediate Result we're trying to achieve is -- take a basic
OpenVZ or LXC container based on e.g. rhel6 template and make sure we can
checkpoint and restore it without breaking one.


The More-or-less Finished state of the project would be when it's able to
do all the stuff that the OpenVZ's implementation can. The list of major
features which are yet absent in the CRIU and for which we will require the
kernel support includes

* shared kernel objects (this thread)
* tcp connection
* pty stuff
* sysvipc
* iterative working set migration

The latter one is an ability to find out which pages processes use and catch
when they change data on them. I planned to discuss this on LSF, but we can
start earlier if you want.

Other currently missing stuff is quite minor or doesn't require any new things
form the kernel like signalfd-s or netfilter.


The Ultimate Goal is hard to describe because we have the variety of ideas
about what the CRIU can do including such things as checkpointing desktop apps'
with their xserver state or live-migrating parts of a multi-process app from
one box to another.


Thanks,
Pavel

Re: [patch 0/4] Resending, c/r series v2

[Cyrill Gorcunov]

On Wed, Feb 15, 2012 at 08:52:36AM +0400, Pavel Emelyanov wrote:
> On 02/15/2012 02:51 AM, Andrew Morton wrote:
> > On Mon, 13 Feb 2012 20:48:22 +0400
> > Cyrill Gorcunov <gorcunov@openvz.org> wrote:
> > 
> >> Hi, this series hopefully in a good shape
> >>
> >>  - sys_kcmp now depends on CONFIG_CHECKPOINT_RESTORE
> >>
> >>  - the extension of /proc/pid/stat now done against
> >>    linux-next/master
> >>
> >> Please letme know if I've missed something.
> > 
> > Thus far our (my) approach has been to trickle the c/r support code
> > into mainline as it is developed.  Under the assumption that the end
> > result will be acceptable and useful kernel code.
> > 
> > I'm afraid that I'm losing confidence in that approach.  We have this
> > patchset, we have Stanislav's "IPC: checkpoint/restore in userspace
> > enhancements" (which apparently needs to get more complex to support
> > LSM context c/r).  I simply *don't know* what additional patchsets are
> > expected.  And from what you told me it sounds like networking support
> > is at a very early stage and I fear for what the end result of that
> > will look like.
> 
> I understand. But there was a confidence that nobody wanted the c/r stuff to 
> be the "one big kernel subsystem", but it should rather be "a bunch of small 
> API-s for what is required". The amount of code for the initial C/R attempt was
> ~100 patches. The amount of code to support our user-space C/R implementation
> *only* is ~10 and the feature-set of both is already comparable.
> 

Andrew, I hope Pavel has addressed all your concerns? What I personally
trying to achieve mostly -- the patches should be as minimum as possible,
still usable. I believe the patches which are already in tree are useful for
other projects as well (for example -- /proc/pid/task/tid/"children" to find
all children and build process topology fast). prctl extension look a bit
redundant for kernel in general, but they are easily turnable off via Kconfig
option. /proc/pid/map_files/ might be redundant too but it could be eliminated
via Kconfig as well. So I think the both series actually do not bring much noise
into kernel itself.

	Cyrill

[patch 0/4] [patch 0/4] A pile in c/r sake v2

[Cyrill Gorcunov]

Hi, hope this time I've addressed more or less all concerns,
still please say me if something is not yet good enough.

 - sys_kcmp now depends on CONFIG_CHECKPOINT_RESTORE
   (Ingo, I suppose arch_initcall for kcmp_cookies_init
    should be better than late_initcall, but I'm not
    sure)

 - the extension of /proc/pid/stat now done against
   linux-next/master

Please review, thanks,

	Cyrill

[patch 1/4] fs, proc: Introduce /proc/<pid>/task/<tid>/children entry v9

[Cyrill Gorcunov]

[-- Attachment #1: fs-proc-tid-children-13 --]
[-- Type: text/plain, Size: 7087 bytes --]

When we do checkpoint of a task we need to know the list of children
the task, has but there is no easy and fast way to generate reverse
parent->children chain from arbitrary <pid> (while a parent pid is
provided in "PPid" field of /proc/<pid>/status).

So instead of walking over all pids in the system (creating one big process
tree in memory, just to figure out which children a task has) -- we add
explicit /proc/<pid>/task/<tid>/children entry, because the kernel already has
this kind of information but it is not yet exported.

This is a first level children, not the whole process tree.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
 Documentation/filesystems/proc.txt |   18 +++++
 fs/proc/array.c                    |  123 +++++++++++++++++++++++++++++++++++++
 fs/proc/base.c                     |    3 
 fs/proc/internal.h                 |    1 
 4 files changed, 145 insertions(+)

Index: linux-2.6.git/Documentation/filesystems/proc.txt
===================================================================
--- linux-2.6.git.orig/Documentation/filesystems/proc.txt
+++ linux-2.6.git/Documentation/filesystems/proc.txt
@@ -40,6 +40,7 @@ Table of Contents
   3.4	/proc/<pid>/coredump_filter - Core dump filtering settings
   3.5	/proc/<pid>/mountinfo - Information about mounts
   3.6	/proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
+  3.7   /proc/<pid>/task/<tid>/children - Information about task children
 
   4	Configuring procfs
   4.1	Mount options
@@ -1549,6 +1550,23 @@ then the kernel's TASK_COMM_LEN (current
 comm value.
 
 
+3.7	/proc/<pid>/task/<tid>/children - Information about task children
+-------------------------------------------------------------------------
+This file provides a fast way to retrieve first level children pids
+of a task pointed by <pid>/<tid> pair. The format is a space separated
+stream of pids.
+
+Note the "first level" here -- if a child has own children they will
+not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
+to obtain the descendants.
+
+Since this interface is intended to be fast and cheap it doesn't
+guarantee to provide precise results and some children might be
+skipped, especially if they've exited right after we printed their
+pids, so one need to either stop or freeze processes being inspected
+if precise results are needed.
+
+
 ------------------------------------------------------------------------------
 Configuring procfs
 ------------------------------------------------------------------------------
Index: linux-2.6.git/fs/proc/array.c
===================================================================
--- linux-2.6.git.orig/fs/proc/array.c
+++ linux-2.6.git/fs/proc/array.c
@@ -556,3 +556,126 @@ int proc_pid_statm(struct seq_file *m, s
 
 	return 0;
 }
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static struct pid *
+get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
+{
+	struct task_struct *start, *task;
+	struct pid *pid = NULL;
+
+	read_lock(&tasklist_lock);
+
+	start = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (!start)
+		goto out;
+
+	/*
+	 * Lets try to continue searching first, this gives
+	 * us significant speedup on children-rich processes.
+	 */
+	if (pid_prev) {
+		task = pid_task(pid_prev, PIDTYPE_PID);
+		if (task && task->real_parent == start &&
+		    !(list_empty(&task->sibling))) {
+			if (list_is_last(&task->sibling, &start->children))
+				goto out;
+			task = list_first_entry(&task->sibling,
+						struct task_struct, sibling);
+			pid = get_pid(task_pid(task));
+			goto out;
+		}
+	}
+
+	/*
+	 * Slow search case.
+	 *
+	 * We might miss some children here if children
+	 * are exited while we were not holding the lock,
+	 * but it was never promised to be accurate that
+	 * much.
+	 *
+	 * "Just suppose that the parent sleeps, but N children
+	 *  exit after we printed their tids. Now the slow paths
+	 *  skips N extra children, we miss N tasks." (c)
+	 *
+	 * So one need to stop or freeze the leader and all
+	 * its children to get a precise result.
+	 */
+	list_for_each_entry(task, &start->children, sibling) {
+		if (pos-- == 0) {
+			pid = get_pid(task_pid(task));
+			break;
+		}
+	}
+
+out:
+	read_unlock(&tasklist_lock);
+	return pid;
+}
+
+static int children_seq_show(struct seq_file *seq, void *v)
+{
+	struct inode *inode = seq->private;
+	pid_t pid;
+
+	pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
+	return seq_printf(seq, "%d ", pid);
+}
+
+static void *children_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return get_children_pid(seq->private, NULL, *pos);
+}
+
+static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct pid *pid;
+
+	pid = get_children_pid(seq->private, v, *pos + 1);
+	put_pid(v);
+
+	++*pos;
+	return pid;
+}
+
+static void children_seq_stop(struct seq_file *seq, void *v)
+{
+	put_pid(v);
+}
+
+static const struct seq_operations children_seq_ops = {
+	.start	= children_seq_start,
+	.next	= children_seq_next,
+	.stop	= children_seq_stop,
+	.show	= children_seq_show,
+};
+
+static int children_seq_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &children_seq_ops);
+	if (ret)
+		return ret;
+
+	m = file->private_data;
+	m->private = inode;
+
+	return ret;
+}
+
+int children_seq_release(struct inode *inode, struct file *file)
+{
+	seq_release(inode, file);
+	return 0;
+}
+
+const struct file_operations proc_tid_children_operations = {
+	.open    = children_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = children_seq_release,
+};
+#endif /* CONFIG_CHECKPOINT_RESTORE */
Index: linux-2.6.git/fs/proc/base.c
===================================================================
--- linux-2.6.git.orig/fs/proc/base.c
+++ linux-2.6.git/fs/proc/base.c
@@ -3350,6 +3350,9 @@ static const struct pid_entry tid_base_s
 	ONE("stat",      S_IRUGO, proc_tid_stat),
 	ONE("statm",     S_IRUGO, proc_pid_statm),
 	REG("maps",      S_IRUGO, proc_maps_operations),
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	REG("children",  S_IRUGO, proc_tid_children_operations),
+#endif
 #ifdef CONFIG_NUMA
 	REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
 #endif
Index: linux-2.6.git/fs/proc/internal.h
===================================================================
--- linux-2.6.git.orig/fs/proc/internal.h
+++ linux-2.6.git/fs/proc/internal.h
@@ -53,6 +53,7 @@ extern int proc_pid_statm(struct seq_fil
 				struct pid *pid, struct task_struct *task);
 extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
 
+extern const struct file_operations proc_tid_children_operations;
 extern const struct file_operations proc_maps_operations;
 extern const struct file_operations proc_numa_maps_operations;
 extern const struct file_operations proc_smaps_operations;