fs/proc: apply the time namespace offset to /proc/stat btime

'/proc/stat' provides the field 'btime' which states the time stamp of
system boot in seconds. In case of time namespaces, the offset to the
boot time stamp was not applied earlier.
This confuses tasks which are in another time universe, e.g., in a
container of a container runtime which utilize time namespaces to
virtualize boottime.

Therefore, we make procfs to virtualize also the btime field by
subtracting the offset of the timens boottime from 'btime' before
printing the stats.

Since start_boottime of processes are seconds since boottime and the
boottime stamp is now shifted according to the timens offset, the
offset of the time namespace also needs to be applied before the
process stats are given to userspace.

This avoids that processes shown, e.g., by 'ps' appear as time
travelers in the corresponding time namespace.

Signed-off-by: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
Reviewed-by: Andrei Vagin <avagin@gmail.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20201027204258.7869-3-michael.weiss@aisec.fraunhofer.de

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 65ec2029fa80202801ea10d561bdc2d00f4cd3c5..277f654f289eeb7fa9edcf45bb2a7be0cf8ffda0 100644 (file)
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -56,6 +56,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/time.h>
+#include <linux/time_namespace.h>
 #include <linux/kernel.h>
 #include <linux/kernel_stat.h>
 #include <linux/tty.h>
@@ -533,8 +534,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
        priority = task_prio(task);
        nice = task_nice(task);
 
-       /* convert nsec -> ticks */
-       start_time = nsec_to_clock_t(task->start_boottime);
+       /* apply timens offset for boottime and convert nsec -> ticks */
+       start_time =
+               nsec_to_clock_t(timens_add_boottime_ns(task->start_boottime));
 
        seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns));
        seq_puts(m, " (");

diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 46b3293015fe61f78dd14781aaabc4b9491da1a2..9df128ea941782aeadfc3da7006cda295ffef8a1 100644 (file)
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -10,6 +10,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/time.h>
+#include <linux/time_namespace.h>
 #include <linux/irqnr.h>
 #include <linux/sched/cputime.h>
 #include <linux/tick.h>
@@ -118,6 +119,8 @@ static int show_stat(struct seq_file *p, void *v)
                irq = softirq = steal = 0;
        guest = guest_nice = 0;
        getboottime64(&boottime);
+       /* shift boot timestamp according to the timens offset */
+       timens_sub_boottime(&boottime);
 
        for_each_possible_cpu(i) {
                struct kernel_cpustat kcpustat;