linux-kernel - [PATCH v2] sched: debug: use task_pid_nr

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20170806044141.5093-1-asarai@suse.com>
Date:   Sun,  6 Aug 2017 14:41:41 +1000
From:   Aleksa Sarai <asarai@...e.com>
To:     Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        "Eric W. Biederman" <ebiederm@...ssion.com>
Cc:     cyphar@...har.com, linux-kernel@...r.kernel.org,
        Aleksa Sarai <asarai@...e.com>, stable@...r.kernel.org,
        Jess Frazelle <acidburn@...gle.com>
Subject: [PATCH v2] sched: debug: use task_pid_nr_ns in /proc/$pid/sched

It appears as though the addition of the PID namespace did not update
the output code for /proc/*/sched, which resulted in it providing PIDs
that were not self-consistent with the /proc mount. This additionally
made it trivial to detect whether a process was inside &init_pid_ns from
userspace (making container detection trivial[1]). This lead to
situations such as:

  % unshare -pmf
  % mount -t proc proc /proc
  % head -n1 /proc/1/sched
  head (10047, #threads: 1)

Fix this by just using task_pid_nr_ns for the output of /proc/*/sched.
All of the other uses of task_pid_nr in kernel/sched/debug.c are from a
sysctl context and thus don't need to be namespaced.

[1]: https://github.com/jessfraz/amicontained

Cc: <stable@...r.kernel.org>
Cc: Jess Frazelle <acidburn@...gle.com>
Signed-off-by: Aleksa Sarai <asarai@...e.com>
---
 fs/proc/base.c              | 3 ++-
 include/linux/sched/debug.h | 4 +++-
 kernel/sched/debug.c        | 5 +++--
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 719c2e943ea1..98fd8f6df851 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1408,12 +1408,13 @@ static const struct file_operations proc_fail_nth_operations = {
 static int sched_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = m->private;
+	struct pid_namespace *ns = inode->i_sb->s_fs_info;
 	struct task_struct *p;
 
 	p = get_proc_task(inode);
 	if (!p)
 		return -ESRCH;
-	proc_sched_show_task(p, m);
+	proc_sched_show_task(p, ns, m);
 
 	put_task_struct(p);
 
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index e0eaee54c5a4..5d58d49e9f87 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -6,6 +6,7 @@
  */
 
 struct task_struct;
+struct pid_namespace;
 
 extern void dump_cpu_task(int cpu);
 
@@ -34,7 +35,8 @@ extern void sched_show_task(struct task_struct *p);
 
 #ifdef CONFIG_SCHED_DEBUG
 struct seq_file;
-extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
+extern void proc_sched_show_task(struct task_struct *p,
+				 struct pid_namespace *ns, struct seq_file *m);
 extern void proc_sched_set_task(struct task_struct *p);
 #endif
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4fa66de52bd6..ac345115877b 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -872,11 +872,12 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 #endif
 }
 
-void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
+void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
+						  struct seq_file *m)
 {
 	unsigned long nr_switches;
 
-	SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p),
+	SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr_ns(p, ns),
 						get_nr_threads(p));
 	SEQ_printf(m,
 		"---------------------------------------------------------"
-- 
2.13.3