linux/fs/proc/stat.c
Linus Torvalds 6d93a1971a time-namespace-v5.11
-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCX9cwgAAKCRCRxhvAZXjc
 onViAP9CDMQct0RfdpdKOrh4NkxWiheBp7CzVSP1Xfy8KHBslgD/X7kilcthT8PC
 JTJmngrVWoehX+s49kl2PSuuLsGElAo=
 =llnx
 -----END PGP SIGNATURE-----

Merge tag 'time-namespace-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull time namespace updates from Christian Brauner:
 "When time namespaces were introduced we missed to virtualize the
  'btime' field in /proc/stat. This confuses tasks which are in another
  time namespace with a virtualized boottime which is common in some
  container workloads. This contains Michael's series to fix 'btime'
  which Thomas asked me to take through my tree.

  To fix 'btime' virtualization we simply subtract the offset of the
  time namespace's boottime from btime before printing the stats. Note
  that since start_boottime of processes are seconds since boottime and
  the boottime stamp is now shifted according to the time namespace's
  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 by tools such as 'ps' appear as time travelers in the
  corresponding time namespace.

  Selftests are included to verify that btime virtualization in
  /proc/stat works as expected"

* tag 'time-namespace-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  namespace: make timens_on_fork() return nothing
  selftests/timens: added selftest for /proc/stat btime
  fs/proc: apply the time namespace offset to /proc/stat btime
  timens: additional helper functions for boottime offset handling
2020-12-14 16:35:39 -08:00

243 lines
6.2 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/cpumask.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/proc_fs.h>
#include <linux/sched.h>
#include <linux/sched/stat.h>
#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>
#ifndef arch_irq_stat_cpu
#define arch_irq_stat_cpu(cpu) 0
#endif
#ifndef arch_irq_stat
#define arch_irq_stat() 0
#endif
#ifdef arch_idle_time
static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
{
u64 idle;
idle = kcs->cpustat[CPUTIME_IDLE];
if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
idle += arch_idle_time(cpu);
return idle;
}
static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
{
u64 iowait;
iowait = kcs->cpustat[CPUTIME_IOWAIT];
if (cpu_online(cpu) && nr_iowait_cpu(cpu))
iowait += arch_idle_time(cpu);
return iowait;
}
#else
static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
{
u64 idle, idle_usecs = -1ULL;
if (cpu_online(cpu))
idle_usecs = get_cpu_idle_time_us(cpu, NULL);
if (idle_usecs == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
idle = kcs->cpustat[CPUTIME_IDLE];
else
idle = idle_usecs * NSEC_PER_USEC;
return idle;
}
static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
{
u64 iowait, iowait_usecs = -1ULL;
if (cpu_online(cpu))
iowait_usecs = get_cpu_iowait_time_us(cpu, NULL);
if (iowait_usecs == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
iowait = kcs->cpustat[CPUTIME_IOWAIT];
else
iowait = iowait_usecs * NSEC_PER_USEC;
return iowait;
}
#endif
static void show_irq_gap(struct seq_file *p, unsigned int gap)
{
static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0";
while (gap > 0) {
unsigned int inc;
inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2);
seq_write(p, zeros, 2 * inc);
gap -= inc;
}
}
static void show_all_irqs(struct seq_file *p)
{
unsigned int i, next = 0;
for_each_active_irq(i) {
show_irq_gap(p, i - next);
seq_put_decimal_ull(p, " ", kstat_irqs_usr(i));
next = i + 1;
}
show_irq_gap(p, nr_irqs - next);
}
static int show_stat(struct seq_file *p, void *v)
{
int i, j;
u64 user, nice, system, idle, iowait, irq, softirq, steal;
u64 guest, guest_nice;
u64 sum = 0;
u64 sum_softirq = 0;
unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
struct timespec64 boottime;
user = nice = system = idle = iowait =
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;
u64 *cpustat = kcpustat.cpustat;
kcpustat_cpu_fetch(&kcpustat, i);
user += cpustat[CPUTIME_USER];
nice += cpustat[CPUTIME_NICE];
system += cpustat[CPUTIME_SYSTEM];
idle += get_idle_time(&kcpustat, i);
iowait += get_iowait_time(&kcpustat, i);
irq += cpustat[CPUTIME_IRQ];
softirq += cpustat[CPUTIME_SOFTIRQ];
steal += cpustat[CPUTIME_STEAL];
guest += cpustat[CPUTIME_GUEST];
guest_nice += cpustat[CPUTIME_GUEST_NICE];
sum += kstat_cpu_irqs_sum(i);
sum += arch_irq_stat_cpu(i);
for (j = 0; j < NR_SOFTIRQS; j++) {
unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
per_softirq_sums[j] += softirq_stat;
sum_softirq += softirq_stat;
}
}
sum += arch_irq_stat();
seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(user));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
seq_putc(p, '\n');
for_each_online_cpu(i) {
struct kernel_cpustat kcpustat;
u64 *cpustat = kcpustat.cpustat;
kcpustat_cpu_fetch(&kcpustat, i);
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = cpustat[CPUTIME_USER];
nice = cpustat[CPUTIME_NICE];
system = cpustat[CPUTIME_SYSTEM];
idle = get_idle_time(&kcpustat, i);
iowait = get_iowait_time(&kcpustat, i);
irq = cpustat[CPUTIME_IRQ];
softirq = cpustat[CPUTIME_SOFTIRQ];
steal = cpustat[CPUTIME_STEAL];
guest = cpustat[CPUTIME_GUEST];
guest_nice = cpustat[CPUTIME_GUEST_NICE];
seq_printf(p, "cpu%d", i);
seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
seq_putc(p, '\n');
}
seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
show_all_irqs(p);
seq_printf(p,
"\nctxt %llu\n"
"btime %llu\n"
"processes %lu\n"
"procs_running %lu\n"
"procs_blocked %lu\n",
nr_context_switches(),
(unsigned long long)boottime.tv_sec,
total_forks,
nr_running(),
nr_iowait());
seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq);
for (i = 0; i < NR_SOFTIRQS; i++)
seq_put_decimal_ull(p, " ", per_softirq_sums[i]);
seq_putc(p, '\n');
return 0;
}
static int stat_open(struct inode *inode, struct file *file)
{
unsigned int size = 1024 + 128 * num_online_cpus();
/* minimum size to display an interrupt count : 2 bytes */
size += 2 * nr_irqs;
return single_open_size(file, show_stat, NULL, size);
}
static const struct proc_ops stat_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_open = stat_open,
.proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = single_release,
};
static int __init proc_stat_init(void)
{
proc_create("stat", 0, NULL, &stat_proc_ops);
return 0;
}
fs_initcall(proc_stat_init);