linux_dsm_epyc7002/fs/proc/stat.c

205 lines
5.6 KiB
C
Raw Normal View History

#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/seq_file.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/irqnr.h>
#include <linux/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 cputime64_t get_idle_time(int cpu)
{
cputime64_t idle;
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
idle += arch_idle_time(cpu);
return idle;
}
static cputime64_t get_iowait_time(int cpu)
{
cputime64_t iowait;
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
if (cpu_online(cpu) && nr_iowait_cpu(cpu))
iowait += arch_idle_time(cpu);
return iowait;
}
#else
static u64 get_idle_time(int cpu)
{
u64 idle, idle_time = -1ULL;
if (cpu_online(cpu))
idle_time = get_cpu_idle_time_us(cpu, NULL);
if (idle_time == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
else
idle = usecs_to_cputime64(idle_time);
return idle;
}
static u64 get_iowait_time(int cpu)
{
u64 iowait, iowait_time = -1ULL;
if (cpu_online(cpu))
iowait_time = get_cpu_iowait_time_us(cpu, NULL);
if (iowait_time == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
else
iowait = usecs_to_cputime64(iowait_time);
return iowait;
}
#endif
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);
for_each_possible_cpu(i) {
user += kcpustat_cpu(i).cpustat[CPUTIME_USER];
nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE];
system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
idle += get_idle_time(i);
iowait += get_iowait_time(i);
irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice += kcpustat_cpu(i).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();
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:54 +07:00
seq_puts(p, "cpu ");
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
seq_putc(p, '\n');
for_each_online_cpu(i) {
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE];
system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
idle = get_idle_time(i);
iowait = get_iowait_time(i);
irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:54 +07:00
seq_printf(p, "cpu%d", i);
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
seq_putc(p, '\n');
}
seq_printf(p, "intr %llu", (unsigned long long)sum);
/* sum again ? it could be updated? */
for_each_irq_nr(j)
genirq: Prevent proc race against freeing of irq descriptors Since the rework of the sparse interrupt code to actually free the unused interrupt descriptors there exists a race between the /proc interfaces to the irq subsystem and the code which frees the interrupt descriptor. CPU0 CPU1 show_interrupts() desc = irq_to_desc(X); free_desc(desc) remove_from_radix_tree(); kfree(desc); raw_spinlock_irq(&desc->lock); /proc/interrupts is the only interface which can actively corrupt kernel memory via the lock access. /proc/stat can only read from freed memory. Extremly hard to trigger, but possible. The interfaces in /proc/irq/N/ are not affected by this because the removal of the proc file is serialized in procfs against concurrent readers/writers. The removal happens before the descriptor is freed. For architectures which have CONFIG_SPARSE_IRQ=n this is a non issue as the descriptor is never freed. It's merely cleared out with the irq descriptor lock held. So any concurrent proc access will either see the old correct value or the cleared out ones. Protect the lookup and access to the irq descriptor in show_interrupts() with the sparse_irq_lock. Provide kstat_irqs_usr() which is protecting the lookup and access with sparse_irq_lock and switch /proc/stat to use it. Document the existing kstat_irqs interfaces so it's clear that the caller needs to take care about protection. The users of these interfaces are either not affected due to SPARSE_IRQ=n or already protected against removal. Fixes: 1f5a5b87f78f "genirq: Implement a sane sparse_irq allocator" Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2014-12-12 05:01:41 +07:00
seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j));
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_printf(p, "softirq %llu", (unsigned long long)sum_softirq);
for (i = 0; i < NR_SOFTIRQS; i++)
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:54 +07:00
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)
{
size_t 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 file_operations proc_stat_operations = {
.open = stat_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int __init proc_stat_init(void)
{
proc_create("stat", 0, NULL, &proc_stat_operations);
return 0;
}
fs_initcall(proc_stat_init);