[Devel] [PATCH] pid: improved namespaced iteration over processes list

[Gowrishankar M]

Below patch addresses a common solution for any place where a process
should be checked if it is associated to caller namespace. At present,
we use 'task_pid_vnr(t) > 0' to further proceed with task 't' in current
namespace.

To avoid applying this check in every code related to PID namespace,
this patch reworks on iterative macros;for_each_process and do_each_thread.

This patch can also reduce latency time on process list lookup inside the
container, as we walk along pidmap, instead of every process in system.

Signed-off-by: Gowrishankar M <gowrishankar.m at in.ibm.com>
---
 include/linux/sched.h |    8 +++++---
 kernel/pid.c          |   17 +++++++++++++++++
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2e46189..8d3b520 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1917,17 +1917,19 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
-#define next_task(p)	list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
+#include <linux/nsproxy.h>
+#define next_task(p)	pid_task(find_ge_tgid(task_pid_vnr(p) + 1, p->nsproxy->pid_ns), PIDTYPE_PID)
+#define ns_init_task	(current->nsproxy->pid_ns == &init_pid_ns ? next_task((&init_task)) : find_task_by_vpid(1))
 
 #define for_each_process(p) \
-	for (p = &init_task ; (p = next_task(p)) != &init_task ; )
+	for (p = ns_init_task ; p != NULL ; p = next_task(p))
 
 /*
  * Careful: do_each_thread/while_each_thread is a double loop so
  *          'break' will not work as expected - use goto instead.
  */
 #define do_each_thread(g, t) \
-	for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
+	for (g = t = ns_init_task ; g  != NULL ; (g = t = next_task(g))) do
 
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
diff --git a/kernel/pid.c b/kernel/pid.c
index 064e76a..3273a96 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -493,6 +493,23 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 	return pid;
 }
 
+struct pid *find_ge_tgid(int nr,  struct pid_namespace *ns)
+{
+	struct pid* pid;
+	struct task_struct* task;
+
+retry:
+	pid = find_ge_pid(nr, ns);
+	if (pid) {
+		task = pid_task(pid, PIDTYPE_PID);
+		if (!task || !has_group_leader_pid(task)) {
+			nr += 1;
+			goto retry;
+		}
+	}
+	return pid;
+}
+
 /*
  * The pid hash table is scaled according to the amount of memory in the
  * machine.  From a minimum of 16 slots up to 4096 slots at one gigabyte or
-- 
1.5.5.1

_______________________________________________
Containers mailing list
Containers at lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers