kernel: Update kernel patches

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>

kernel/c-r-introduce-checkpoint_restore-symbol.patch

+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: c/r: introduce CHECKPOINT_RESTORE symbol
+
+For checkpoint/restore we need auxilary features being compiled into the
+kernel, such as additional prctl codes, /proc/<pid>/map_files and etc... 
+but same time these features are not mandatory for a regular kernel so
+CHECKPOINT_RESTORE config symbol should bring a way to disable them all at
+once if one wish to get rid of additional functionality.
+
+Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Andrew Vagin <avagin@openvz.org>
+Cc: Serge Hallyn <serge.hallyn@canonical.com>
+Cc: Vasiliy Kulikov <segoon@openwall.com>
+Reviewed-by: Kees Cook <keescook@chromium.org>
+Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
+Cc: Alexey Dobriyan <adobriyan@gmail.com>
+Cc: "Eric W. Biederman" <ebiederm@xmission.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+
+ init/Kconfig |   11 +++++++++++
+ 1 file changed, 11 insertions(+)
+
+Index: linux-2.6.git/init/Kconfig
+===================================================================
+--- linux-2.6.git.orig/init/Kconfig
++++ linux-2.6.git/init/Kconfig
+@@ -773,6 +773,17 @@ config DEBUG_BLK_CGROUP
+ 
+ endif # CGROUPS
+ 
++config CHECKPOINT_RESTORE
++	bool "Checkpoint/restore support" if EXPERT
++	default n
++	help
++	  Enables additional kernel features in a sake of checkpoint/restore.
++	  In particular it adds auxiliary prctl codes to setup process text,
++	  data and heap segment sizes, and a few additional /proc filesystem
++	  entries.
++
++	  If unsure, say N here.
++
+ menuconfig NAMESPACES
+ 	bool "Namespaces support" if EXPERT
+ 	default !EXPERT

kernel/c-r-prctl-add-pr_set_mm-codes-to-set-up-mm_struct-entries-fix.patch

+From: Andrew Morton <akpm@linux-foundation.org>
+Subject: c-r-prctl-add-pr_set_mm-codes-to-set-up-mm_struct-entries-fix
+
+cache current->mm in a local, saving 200 bytes text
+
+Cc: Andrew Vagin <avagin@openvz.org>
+Cc: Cyrill Gorcunov <gorcunov@openvz.org>
+Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
+Cc: Kees Cook <keescook@chromium.org>
+Cc: Michael Kerrisk <mtk.manpages@gmail.com>
+Cc: Pavel Emelyanov <xemul@parallels.com>
+Cc: Serge Hallyn <serge.hallyn@canonical.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vasiliy Kulikov <segoon@openwall.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+
+ kernel/sys.c |   33 +++++++++++++++++----------------
+ 1 file changed, 17 insertions(+), 16 deletions(-)
+
+Index: linux-2.6.git/kernel/sys.c
+===================================================================
+--- linux-2.6.git.orig/kernel/sys.c
++++ linux-2.6.git/kernel/sys.c
+@@ -1701,6 +1701,7 @@ static int prctl_set_mm(int opt, unsigne
+ 	unsigned long vm_bad_flags;
+ 	struct vm_area_struct *vma;
+ 	int error = 0;
++	struct mm_struct *mm = current->mm;
+ 
+ 	if (arg4 | arg5)
+ 		return -EINVAL;
+@@ -1711,8 +1712,8 @@ static int prctl_set_mm(int opt, unsigne
+ 	if (addr >= TASK_SIZE)
+ 		return -EINVAL;
+ 
+-	down_read(&current->mm->mmap_sem);
+-	vma = find_vma(current->mm, addr);
++	down_read(&mm->mmap_sem);
++	vma = find_vma(mm, addr);
+ 
+ 	if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) {
+ 		/* It must be existing VMA */
+@@ -1732,9 +1733,9 @@ static int prctl_set_mm(int opt, unsigne
+ 			goto out;
+ 
+ 		if (opt == PR_SET_MM_START_CODE)
+-			current->mm->start_code = addr;
++			mm->start_code = addr;
+ 		else
+-			current->mm->end_code = addr;
++			mm->end_code = addr;
+ 		break;
+ 
+ 	case PR_SET_MM_START_DATA:
+@@ -1747,9 +1748,9 @@ static int prctl_set_mm(int opt, unsigne
+ 			goto out;
+ 
+ 		if (opt == PR_SET_MM_START_DATA)
+-			current->mm->start_data = addr;
++			mm->start_data = addr;
+ 		else
+-			current->mm->end_data = addr;
++			mm->end_data = addr;
+ 		break;
+ 
+ 	case PR_SET_MM_START_STACK:
+@@ -1762,31 +1763,31 @@ static int prctl_set_mm(int opt, unsigne
+ 		if ((vma->vm_flags & vm_req_flags) != vm_req_flags)
+ 			goto out;
+ 
+-		current->mm->start_stack = addr;
++		mm->start_stack = addr;
+ 		break;
+ 
+ 	case PR_SET_MM_START_BRK:
+-		if (addr <= current->mm->end_data)
++		if (addr <= mm->end_data)
+ 			goto out;
+ 
+ 		if (rlim < RLIM_INFINITY &&
+-		    (current->mm->brk - addr) +
+-		    (current->mm->end_data - current->mm->start_data) > rlim)
++		    (mm->brk - addr) +
++		    (mm->end_data - mm->start_data) > rlim)
+ 			goto out;
+ 
+-		current->mm->start_brk = addr;
++		mm->start_brk = addr;
+ 		break;
+ 
+ 	case PR_SET_MM_BRK:
+-		if (addr <= current->mm->end_data)
++		if (addr <= mm->end_data)
+ 			goto out;
+ 
+ 		if (rlim < RLIM_INFINITY &&
+-		    (addr - current->mm->start_brk) +
+-		    (current->mm->end_data - current->mm->start_data) > rlim)
++		    (addr - mm->start_brk) +
++		    (mm->end_data - mm->start_data) > rlim)
+ 			goto out;
+ 
+-		current->mm->brk = addr;
++		mm->brk = addr;
+ 		break;
+ 
+ 	default:
+@@ -1797,7 +1798,7 @@ static int prctl_set_mm(int opt, unsigne
+ 	error = 0;
+ 
+ out:
+-	up_read(&current->mm->mmap_sem);
++	up_read(&mm->mmap_sem);
+ 
+ 	return error;
+ }

kernel/prctl-tune-up-mm_struct-members-2 → kernel/c-r-prctl-add-pr_set_mm-codes-to-set-up-mm_struct-entries.patch

-prctl: Add PR_SET_MM codes to tune up mm_struct entires v2
+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: c/r: prctl: add PR_SET_MM codes to set up mm_struct entries
 
-A few members of mm_struct such as start_code, end_code,
-start_data, end_data, start_stack, start_brk, brk provided
-by the kernel via /proc/$pid/stat and we use it at checkpoint
-time.
+When we restore a task we need to set up text, data and data heap sizes
+from userspace to the values a task had at checkpoint time.  This patch
+adds auxilary prctl codes for that.
 
-At restore time we need a mechanism to restore those values
-back and for this sake PR_SET_MM prctl code is introduced.
+While most of them have a statistical nature (their values are involved
+into calculation of /proc/<pid>/statm output) the start_brk and brk values
+are used to compute an allowed size of program data segment expansion. 
+Which means an arbitrary changes of this values might be dangerous
+operation.  So to restrict access the following requirements applied to
+prctl calls:
 
-Note because of being a dangerous operation this inteface
-is allowed for CAP_SYS_ADMIN only.
+ - The process has to have CAP_SYS_ADMIN capability granted.
+ - For all opcodes except start_brk/brk members an appropriate
+   VMA area must exist and should fit certain VMA flags,
+   such as:
+   - code segment must be executable but not writable;
+   - data segment must not be executable.
 
-v2:
- - Add a check for vma start address, testing for vma ending
-   address is not enough. From Kees Cook.
+start_brk/brk values must not intersect with data segment and must not
+exceed RLIMIT_DATA resource limit.
 
- - Add some sanity tests for assigned addresses.
+Still the main guard is CAP_SYS_ADMIN capability check.
+
+Note the kernel should be compiled with CONFIG_CHECKPOINT_RESTORE support
+otherwise these prctl calls will return -EINVAL.
 
 Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
-CC: Kees Cook <keescook@chromium.org>
+Cc: Andrew Morton <akpm@linux-foundation.org>
+Reviewed-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>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
 ---
+
  include/linux/prctl.h |   12 +++++
- kernel/sys.c          |  118 ++++++++++++++++++++++++++++++++++++++++++++++++++
- 2 files changed, 130 insertions(+)
+ kernel/sys.c          |  120 ++++++++++++++++++++++++++++++++++++++++++++++++++
+ 2 files changed, 132 insertions(+)
 
 Index: linux-2.6.git/include/linux/prctl.h
 ===================================================================
@@ -49,34 +69,33 @@ Index: linux-2.6.git/kernel/sys.c
 ===================================================================
 --- linux-2.6.git.orig/kernel/sys.c
 +++ linux-2.6.git/kernel/sys.c
-@@ -1692,6 +1692,118 @@ SYSCALL_DEFINE1(umask, int, mask)
+@@ -1692,6 +1692,123 @@ SYSCALL_DEFINE1(umask, int, mask)
  	return mask;
  }
  
-+static int prctl_set_mm(int opt, unsigned long addr)
++#ifdef CONFIG_CHECKPOINT_RESTORE
++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;
-+	struct mm_struct *mm;
 +	int error = 0;
 +
++	if (arg4 | arg5)
++		return -EINVAL;
++
 +	if (!capable(CAP_SYS_ADMIN))
 +		return -EPERM;
 +
 +	if (addr >= TASK_SIZE)
 +		return -EINVAL;
 +
-+	mm = get_task_mm(current);
-+	if (!mm)
-+		return -ENOENT;
-+
-+	down_read(&mm->mmap_sem);
-+	vma = find_vma(mm, addr);
++	down_read(&current->mm->mmap_sem);
++	vma = find_vma(current->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) {
 +		/* It must be existing VMA */
 +		if (!vma || vma->vm_start > addr)
 +			goto out;
@@ -86,7 +105,6 @@ Index: linux-2.6.git/kernel/sys.c
 +	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;
 +
@@ -102,7 +120,6 @@ Index: linux-2.6.git/kernel/sys.c
 +
 +	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;
 +
@@ -130,22 +147,24 @@ Index: linux-2.6.git/kernel/sys.c
 +		break;
 +
 +	case PR_SET_MM_START_BRK:
-+		if (addr <= mm->end_data)
++		if (addr <= current->mm->end_data)
 +			goto out;
 +
 +		if (rlim < RLIM_INFINITY &&
-+		    (mm->brk - addr) + (mm->end_data - mm->start_data) > rlim)
++		    (current->mm->brk - addr) +
++		    (current->mm->end_data - current->mm->start_data) > rlim)
 +			goto out;
 +
 +		current->mm->start_brk = addr;
 +		break;
 +
 +	case PR_SET_MM_BRK:
-+		if (addr <= mm->end_data)
++		if (addr <= current->mm->end_data)
 +			goto out;
 +
 +		if (rlim < RLIM_INFINITY &&
-+		    (addr - mm->start_brk) + (mm->end_data - mm->start_data) > rlim)
++		    (addr - current->mm->start_brk) +
++		    (current->mm->end_data - current->mm->start_data) > rlim)
 +			goto out;
 +
 +		current->mm->brk = addr;
@@ -159,25 +178,28 @@ Index: linux-2.6.git/kernel/sys.c
 +	error = 0;
 +
 +out:
-+	up_read(&mm->mmap_sem);
-+	mmput(mm);
++	up_read(&current->mm->mmap_sem);
 +
 +	return error;
 +}
++#else /* CONFIG_CHECKPOINT_RESTORE */
++static int prctl_set_mm(int opt, unsigned long addr,
++			unsigned long arg4, unsigned long arg5)
++{
++	return -EINVAL;
++}
++#endif
 +
  SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
  		unsigned long, arg4, unsigned long, arg5)
  {
-@@ -1841,6 +1953,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsi
+@@ -1841,6 +1958,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsi
  			else
  				error = PR_MCE_KILL_DEFAULT;
  			break;
-+		case PR_SET_MM: {
-+			if (arg4 | arg5)
-+				return -EINVAL;
-+			error = prctl_set_mm(arg2, arg3);
++		case PR_SET_MM:
++			error = prctl_set_mm(arg2, arg3, arg4, arg5);
 +			break;
-+		}
  		default:
  			error = -EINVAL;
  			break;

kernel/c-r-procfs-add-start_data-end_data-start_brk-members-to-proc-pid-stat-v4-fix.patch

+From: Andrew Morton <akpm@linux-foundation.org>
+Subject: c-r-procfs-add-start_data-end_data-start_brk-members-to-proc-pid-stat-v4-fix
+
+Cc: "Eric W. Biederman" <ebiederm@xmission.com>
+Cc: Alexey Dobriyan <adobriyan@gmail.com>
+Cc: Andrew Vagin <avagin@openvz.org>
+Cc: Cyrill Gorcunov <gorcunov@openvz.org>
+Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
+Cc: Kees Cook <keescook@chromium.org>
+Cc: Serge Hallyn <serge.hallyn@canonical.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vasiliy Kulikov <segoon@openwall.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+
+ Documentation/filesystems/proc.txt |    2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+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
+@@ -307,7 +307,7 @@ Table 1-4: Contents of the stat files (a
+   cgtime        guest time of the task children in jiffies
+   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 expaned with brk() call
++  start_brk     address above which program heap can be expanded with brk()
+ ..............................................................................
+ 
+ The /proc/PID/maps file containing the currently mapped memory regions and

kernel/fs-proc-Add-start_data-end_data-start_brk-members → kernel/c-r-procfs-add-start_data-end_data-start_brk-members-to-proc-pid-stat-v4.patch

-fs, proc: Add start_data, end_data, start_brk members to /proc/$pid/stat
+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: c/r: procfs: add start_data, end_data, start_brk members to /proc/$pid/stat v4
 
-It helps to dump and restore this mm_struct members.
+The mm->start_code/end_code, mm->start_data/end_data, mm->start_brk are
+involved into calculation of program text/data segment sizes (which might
+be seen in /proc/<pid>/statm) and into brk() call final address.
+
+For restore we need to know all these values.  While
+mm->start_code/end_code already present in /proc/$pid/stat, the rest
+members are not, so this patch brings them in.
+
+The restore procedure of these members is addressed in another patch using
+prctl().
 
 Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
 Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
 Reviewed-by: Kees Cook <keescook@chromium.org>
 Reviewed-by: 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>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
 ---
- fs/proc/array.c |    7 +++++--
- 1 file changed, 5 insertions(+), 2 deletions(-)
 
+ Documentation/filesystems/proc.txt |    3 +++
+ fs/proc/array.c                    |    7 +++++--
+ 2 files changed, 8 insertions(+), 2 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
+@@ -305,6 +305,9 @@ Table 1-4: Contents of the stat files (a
+   blkio_ticks   time spent waiting for block IO
+   gtime         guest time of the task in jiffies
+   cgtime        guest time of the task children in jiffies
++  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 expaned with brk() 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
@@ -29,9 +62,9 @@ Index: linux-2.6.git/fs/proc/array.c
  		cputime_to_clock_t(gtime),
 -		cputime_to_clock_t(cgtime));
 +		cputime_to_clock_t(cgtime),
-+		mm ? (permitted ? mm->start_data : 1) : 0,
-+		mm ? (permitted ? mm->end_data : 1) : 0,
-+		mm ? (permitted ? mm->start_brk : 1) : 0);
++		(mm && permitted) ? mm->start_data : 0,
++		(mm && permitted) ? mm->end_data : 0,
++		(mm && permitted) ? mm->start_brk : 0);
  	if (mm)
  		mmput(mm);
  	return 0;

kernel/fs-proc-Introduce-the-proc-pid-map_files-directory

-fs, proc: Introduce the /proc/<pid>/map_files/ directory v14
+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: [PATCH] fs, proc: Introduce the /proc/<pid>/map_files/ directory v14
 
 From: Pavel Emelyanov <xemul@parallels.com>
 

kernel/fs-proc-Make-proc_get_link-to-use-dentry

-fs, proc: Make proc_get_link to use dentry instead of inode
+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: [PATCH] fs, proc: Make proc_get_link to use dentry instead of inode
 
 From: Cyrill Gorcunov <gorcunov@openvz.org>
 

kernel/fs-proc-add-children-entry

-fs, proc: Introduce the /proc/<pid>/children entry
-
-There is no easy way to make a reverse parent->children chain
-from the task status, in turn children->parent provided with "PPid"
-field.
-
-So instead of walking over all pids in system to figure out what
-children the task have -- we add explicit /proc/<pid>/children entry,
-since kernel already knows this kind of information but it was not
-yet exported.
-
-Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
-Cc: Pavel Emelyanov <xemul@parallels.com>
-Cc: Serge Hallyn <serge.hallyn@canonical.com>
-Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
----
- fs/proc/array.c    |   14 ++++++++++++++
- fs/proc/base.c     |    1 +
- fs/proc/internal.h |    3 +++
- 3 files changed, 18 insertions(+)
-
-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
-@@ -547,3 +547,17 @@ int proc_pid_statm(struct seq_file *m, s
- 
- 	return 0;
- }
-+
-+int proc_pid_children(struct seq_file *m, struct pid_namespace *ns,
-+		      struct pid *pid, struct task_struct *task)
-+{
-+	struct task_struct *c;
-+
-+	read_lock(&tasklist_lock);
-+	list_for_each_entry(c, &task->children, sibling)
-+		seq_printf(m, " %d", pid_nr_ns(task_pid(c), ns));
-+	read_unlock(&tasklist_lock);
-+	seq_putc(m, '\n');
-+
-+	return 0;
-+}
-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
-@@ -3204,6 +3204,7 @@ static const struct pid_entry tgid_base_
- 	INF("cmdline",    S_IRUGO, proc_pid_cmdline),
- 	ONE("stat",       S_IRUGO, proc_tgid_stat),
- 	ONE("statm",      S_IRUGO, proc_pid_statm),
-+	ONE("children",   S_IRUGO, proc_pid_children),
- 	REG("maps",       S_IRUGO, proc_maps_operations),
- #ifdef CONFIG_NUMA
- 	REG("numa_maps",  S_IRUGO, proc_numa_maps_operations),
-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
-@@ -51,6 +51,9 @@ extern int proc_pid_status(struct seq_fi
- 				struct pid *pid, struct task_struct *task);
- extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
- 				struct pid *pid, struct task_struct *task);
-+extern int proc_pid_children(struct seq_file *m, struct pid_namespace *ns,
-+			     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_maps_operations;

kernel/fs-proc-add-children-entry-11

+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: [PATCH] fs, proc: Introduce the /proc/<pid>/children entry v4
+
+There is no easy way to make a reverse parent->children chain
+from arbitrary <pid> (while parent pid is provided in "PPid"
+field of /proc/<pid>/status).
+
+So instead of walking over all pids in the system to figure out which
+children a task have -- we add explicit /proc/<pid>/children entry,
+because kernel already has this kind of information but it is not
+yet exported. This is a first level children, not the whole process
+tree, neither the process threads are identified with this interface.
+
+v2:
+ - Kame suggested to use a separated /proc/<pid>/children entry
+   instead of poking /proc/<pid>/status
+ - Andew suggested to use rcu facility instead of locking
+   tasklist_lock
+ - Tejun pointed that non-seekable seq file might not be
+   enough for tasks with large number of children
+
+v3:
+ - To be on a safe side use %lu format for pid_t printing
+
+v4:
+ - New line get printed when sequence ends not at seq->stop,
+   a nit pointed by Tejun
+ - Documentation update
+ - tasklist_lock is back, Oleg pointed that ->children list
+   is actually not rcu-safe
+
+Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.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>
+Cc: Pavel Emelyanov <xemul@parallels.com>
+---
+ Documentation/filesystems/proc.txt |   20 ++++
+ fs/proc/array.c                    |  163 +++++++++++++++++++++++++++++++++++++
+ fs/proc/base.c                     |    1 
+ fs/proc/internal.h                 |    6 +
+ 4 files changed, 190 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>/children - Information about task children
+ 
+ 
+ ------------------------------------------------------------------------------
+@@ -1545,3 +1546,22 @@ a task to set its own or one of its thre
+ is limited in size compared to the cmdline value, so writing anything longer
+ then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
+ comm value.
++
++3.7	/proc/<pid>/children - Information about task children
++--------------------------------------------------------------
++This file provides a fast way to retrieve first level children pids
++of a task pointed by <pid>. The format is a stream of pids separated
++by space with a new line at the end. If a task has no children at
++all -- only a new line returned.
++
++Note the "first level" here -- if a child has own children they will
++not be printed there, one need to read /proc/<children-pid>/children
++to obtain descendants. The same applies to threads -- they are not
++counted here.
++
++Because this interface is intended to be fast and cheap it doesn't
++guarantee to provide the precise results, which means if a child is
++exiting it might or might not be counted. The same applies to freshly
++created children -- they might or might not be counted. If one needs
++precise pids -- the task and children should be either stopped or
++frozen.
+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
+@@ -547,3 +547,166 @@ int proc_pid_statm(struct seq_file *m, s
+ 
+ 	return 0;
+ }
++
++static struct list_head *
++children_get_at(struct proc_pid_children_iter *iter, loff_t pos)
++{
++	struct task_struct *t = iter->group_leader;
++	struct task_struct *task;
++
++	rcu_read_lock();
++	do {
++		list_for_each_entry(task, &t->children, sibling) {
++			if (list_empty(&task->sibling))
++				break;
++			if (pos-- == 0) {
++				put_task_struct(iter->last_group);
++				iter->last_group = t;
++				get_task_struct(iter->last_group);
++				get_task_struct(task);
++				rcu_read_unlock();
++				return &task->sibling;
++			}
++		}
++	} while_each_thread(iter->group_leader, t);
++	rcu_read_unlock();
++
++	return NULL;
++}
++
++static int children_seq_show(struct seq_file *seq, void *v)
++{
++	struct task_struct *task = container_of(v, struct task_struct, sibling);
++	unsigned long pid;
++	int ret = -1;
++
++	rcu_read_lock();
++	if (pid_alive(task)) {
++		pid = (unsigned long)pid_vnr(task_pid(task));
++		ret = 0;
++	}
++	rcu_read_unlock();
++
++	if (!ret)
++		ret = seq_printf(seq, " %lu", pid);
++	return ret;
++}
++
++static void *children_seq_start(struct seq_file *seq, loff_t *pos)
++{
++	return children_get_at(seq->private, *pos);
++}
++
++static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
++{
++	struct proc_pid_children_iter *iter = seq->private;
++	struct task_struct *task = container_of(v, struct task_struct, sibling);
++	struct list_head *next = NULL;
++
++	if (!iter->last_group)
++		goto out;
++
++	rcu_read_lock();
++
++	if (list_empty(&task->sibling) ||
++	    list_is_last(v, &iter->last_group->children)) {
++		struct task_struct *t = iter->last_group;
++
++		while_each_thread(iter->group_leader, t) {
++			if (!list_empty(&t->children)) {
++				put_task_struct(task);
++				next = t->children.next;
++				task = container_of(next, struct task_struct, sibling);
++				get_task_struct(task);
++				put_task_struct(iter->last_group);
++				iter->last_group = t;
++				get_task_struct(iter->last_group);
++				goto out_unlock;
++			}
++		}
++
++		put_task_struct(task);
++		put_task_struct(iter->last_group);
++		iter->last_group = NULL;
++	} else {
++		next = ((struct list_head *)v)->next;
++		put_task_struct(task);
++		task = container_of(next, struct task_struct, sibling);
++		get_task_struct(task);
++	}
++out_unlock:
++	rcu_read_unlock();
++out:
++	++*pos;
++	if (!next)
++		seq_printf(seq, "\n");
++	return next;
++}
++
++static void children_seq_stop(struct seq_file *seq, void *v)
++{
++	struct proc_pid_children_iter *iter = seq->private;
++	if (iter->last_group)
++		put_task_struct(iter->last_group);
++	iter->last_group = NULL;
++}
++
++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 proc_pid_children_iter *iter = NULL;
++	struct task_struct *task = NULL;
++	int ret;
++
++	ret = -ENOMEM;
++	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
++	if (!iter)
++		goto err;
++
++	ret = -ENOENT;
++	task = get_proc_task(inode);
++	if (!task)
++		goto err;
++
++	ret = seq_open(file, &children_seq_ops);
++	if (!ret) {
++		struct seq_file *m = file->private_data;
++		m->private = iter;
++		iter->group_leader = task;
++		iter->last_group = task;
++		get_task_struct(iter->last_group);
++	}
++
++err:
++	if (ret) {
++		if (task)
++			put_task_struct(task);
++		kfree(iter);
++	}
++
++	return ret;
++}
++
++int children_seq_release(struct inode *inode, struct file *file)
++{
++	struct seq_file *m = file->private_data;
++	struct proc_pid_children_iter *iter = m->private;
++
++	put_task_struct(iter->group_leader);
++	kfree(iter);
++	seq_release(inode, file);
++	return 0;
++}
++
++const struct file_operations proc_pid_children_operations = {
++	.open    = children_seq_open,
++	.read    = seq_read,
++	.llseek  = seq_lseek,
++	.release = children_seq_release,
++};
+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
+@@ -3204,6 +3204,7 @@ static const struct pid_entry tgid_base_
+ 	INF("cmdline",    S_IRUGO, proc_pid_cmdline),
+ 	ONE("stat",       S_IRUGO, proc_tgid_stat),
+ 	ONE("statm",      S_IRUGO, proc_pid_statm),
++	REG("children",   S_IRUGO, proc_pid_children_operations),
+ 	REG("maps",       S_IRUGO, proc_maps_operations),
+ #ifdef CONFIG_NUMA
+ 	REG("numa_maps",  S_IRUGO, proc_numa_maps_operations),
+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 +53,12 @@ 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);
+ 
++struct proc_pid_children_iter {
++	struct task_struct *group_leader;
++	struct task_struct *last_group;
++};
++
++extern const struct file_operations proc_pid_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;

kernel/mincore-Add-named-constant-for-reported-present-bit

-mincore: Add named constant for reported present bit
+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: [PATCH] mincore: Add named constant for reported present bit
 
 From: Pavel Emelyanov <xemul@parallels.com>
 

kernel/mincore-Report-whether-page-is-anon-or-not

-mincore: Report whether page is anon or not
+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: [PATCH] mincore: Report whether page is anon or not
 
 From: Pavel Emelyanov <xemul@parallels.com>
 

kernel/procfs-introduce-the-proc-pid-map_files-directory-checkpatch

-procfs-introduce-the-proc-pid-map_files-directory-checkpatch-fixes
+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: [PATCH] procfs-introduce-the-proc-pid-map_files-directory-checkpatch-fixes
 
 From: Andrew Morton <akpm@linux-foundation.org>
 

kernel/series

 fs-proc-Make-proc_get_link-to-use-dentry
 fs-proc-Introduce-the-proc-pid-map_files-directory
 procfs-introduce-the-proc-pid-map_files-directory-checkpatch
-fs-proc-Add-start_data-end_data-start_brk-members
-fs-proc-add-children-entry
-prctl-tune-up-mm_struct-members-2
+sysfs-add-kernel.ns_last_pid
+c-r-introduce-checkpoint_restore-symbol.patch
+c-r-procfs-add-start_data-end_data-start_brk-members-to-proc-pid-stat-v4.patch
+c-r-procfs-add-start_data-end_data-start_brk-members-to-proc-pid-stat-v4-fix.patch
+c-r-prctl-add-pr_set_mm-codes-to-set-up-mm_struct-entries.patch
+c-r-prctl-add-pr_set_mm-codes-to-set-up-mm_struct-entries-fix.patch
 mincore-Add-named-constant-for-reported-present-bit
 mincore-Report-whether-page-is-anon-or-not
-sysfs-add-kernel.ns_last_pid
+fs-proc-add-children-entry-11

kernel/sysfs-add-kernel.ns_last_pid

-sysctl: Add the kernel.ns_last_pid control
+From: Cyrill Gorcunov <gorcunov@openvz.org>
+Subject: [PATCH] sysctl: Add the kernel.ns_last_pid control
 
 From: Pavel Emelyanov <xemul@parallels.com>