proc: rewrite do_task_stat to correctly handle pid namespaces.

Currently (as pointed out by Oleg) do_task_stat has a race when calling
task_pid_nr_ns with the task exiting.  In addition do_task_stat is not
currently displaying information in the context of the pid namespace that
mounted the /proc filesystem.  So "cut -d' ' -f 1 /proc/<pid>/stat" may not
equal <pid>.

This patch fixes the problem by converting to a single_open seq_file show
method.  Getting the pid namespace from the filesystem superblock instead of
current, and simply using the the struct pid from the inode instead of
attempting to get that same pid from the task.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 20 insertions, 17 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 6ba2746e4517..7e9f3b65f25b 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -77,6 +77,7 @@
 #include <linux/cpuset.h>
 #include <linux/rcupdate.h>
 #include <linux/delayacct.h>
+#include <linux/seq_file.h>
 #include <linux/pid_namespace.h>
 
 #include <asm/pgtable.h>
@@ -390,14 +391,14 @@ static cputime_t task_gtime(struct task_struct *p)
 	return p->gtime;
 }
 
-static int do_task_stat(struct task_struct *task, char *buffer, int whole)
+static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task, int whole)
 {
 	unsigned long vsize, eip, esp, wchan = ~0UL;
 	long priority, nice;
 	int tty_pgrp = -1, tty_nr = 0;
 	sigset_t sigign, sigcatch;
 	char state;
-	int res;
 	pid_t ppid = 0, pgid = -1, sid = -1;
 	int num_threads = 0;
 	struct mm_struct *mm;
@@ -409,9 +410,6 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 	unsigned long rsslim = 0;
 	char tcomm[sizeof(task->comm)];
 	unsigned long flags;
-	struct pid_namespace *ns;
-
-	ns = current->nsproxy->pid_ns;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -498,10 +496,10 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 	/* convert nsec -> ticks */
 	start_time = nsec_to_clock_t(start_time);
 
-	res = sprintf(buffer, "%d (%s) %c %d %d %d %d %d %u %lu \
+	seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
 %lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
 %lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
-		task_pid_nr_ns(task, ns),
+		pid_nr_ns(pid, ns),
 		tcomm,
 		state,
 		ppid,
@@ -550,17 +548,19 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 		cputime_to_clock_t(cgtime));
 	if (mm)
 		mmput(mm);
-	return res;
+	return 0;
 }
 
-int proc_tid_stat(struct task_struct *task, char *buffer)
+int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
 {
-	return do_task_stat(task, buffer, 0);
+	return do_task_stat(m, ns, pid, task, 0);
 }
 
-int proc_tgid_stat(struct task_struct *task, char *buffer)
+int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
 {
-	return do_task_stat(task, buffer, 1);
+	return do_task_stat(m, ns, pid, task, 1);
 }
 
 int proc_pid_statm(struct task_struct *task, char *buffer)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index f4b1e14bd95b..f77818ecaa8a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2280,7 +2280,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("sched",      S_IRUGO|S_IWUSR, pid_sched),
 #endif
 	INF("cmdline",    S_IRUGO, pid_cmdline),
-	INF("stat",       S_IRUGO, tgid_stat),
+	ONE("stat",       S_IRUGO, tgid_stat),
 	INF("statm",      S_IRUGO, pid_statm),
 	REG("maps",       S_IRUGO, maps),
 #ifdef CONFIG_NUMA
@@ -2611,7 +2611,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("sched",     S_IRUGO|S_IWUSR, pid_sched),
 #endif
 	INF("cmdline",   S_IRUGO, pid_cmdline),
-	INF("stat",      S_IRUGO, tid_stat),
+	ONE("stat",      S_IRUGO, tid_stat),
 	INF("statm",     S_IRUGO, pid_statm),
 	REG("maps",      S_IRUGO, maps),
 #ifdef CONFIG_NUMA
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 7d57e8069924..f1cc6f1f4e34 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -46,10 +46,13 @@ extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
 
 extern int maps_protect;
 
-extern void create_seq_entry(char *name, mode_t mode, const struct file_operations *f);
+extern void create_seq_entry(char *name, mode_t mode,
+				const struct file_operations *f);
 extern int proc_exe_link(struct inode *, struct dentry **, struct vfsmount **);
-extern int proc_tid_stat(struct task_struct *,  char *);
-extern int proc_tgid_stat(struct task_struct *, char *);
+extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task);
+extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task);
 extern int proc_pid_status(struct task_struct *, char *);
 extern int proc_pid_statm(struct task_struct *, char *);
 extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);