Re: [PATCH] eulerfs: add the /proc/idle file.

Hi,

Thanks for your patch.

邮件标题，前缀总写上对应的分支名。

On 2021/9/29 15:42, Hongyu Li wrote:

From: Hongyu Li <“543306408@qq.com”>

邮箱不用加双引号。

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler-competition/summer-2021/issues/I3EBT6

请在 https://gitee.com/openeuler/kernel/issues/ 下面建一条需求，并把链接放到这里。 不用直接贴 openeuler-competition 的 issue 链接，可以在 openeuler/kernel 的issue 描述中 附上这个链接。

CVE: NA

---

The /proc/idle can give higher precision in accounting the CPU idle time compared with the traditional /proc/stat ways.

Commit message ，建议描述下存在的问题，和解决方法，以及怎么使用这个新的接口。

Signed-off-by: Hongyu Li <“543306408@qq.com”>

fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/proc_idle.c | 82 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 16 +++++++++ kernel/sched/idle.c | 21 +++++++++++ 5 files changed, 127 insertions(+) create mode 100644 fs/proc/proc_idle.c

diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..46620afe9cac 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS

+config PROC_IDLE

• bool "include /proc/idle file"
• depends on PROC_FS
• default y
• help

•  Provide the CPU idle time in the /proc/idle file.
  

diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..69dd2da3a080 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += proc_idle.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/proc_idle.c b/fs/proc/proc_idle.c new file mode 100644 index 000000000000..bbb52e247448 --- /dev/null +++ b/fs/proc/proc_idle.c

我建议叫 fs/proc/stat2.c 比较好，方便将来扩展其他属性。 叫 idle 的话，名字限制比较大。

另外，新增文件的文件头要有 licence （GPL v2)，参考下其他文档。

@@ -0,0 +1,82 @@ +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.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/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h>

+#ifdef CONFIG_PROC_IDLE

+#define PROC_NAME "idle"

+extern u64 cpu_rq_get(int cpu);

+static u64 get_idle_sum_exec_runtime(int cpu) +{

• u64 idle = cpu_rq_get(cpu);
• return idle;

+}

+static int show_idle(struct seq_file *p, void *v) +{

• int i;
• u64 idle;
• idle = 0;
• for_each_possible_cpu(i) {

• idle += get_idle_sum_exec_runtime(i);
  

• }
• seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle));
• seq_putc(p, '\n');
• for_each_online_cpu(i) {

• idle = get_idle_sum_exec_runtime(i);
  

这个直接返回统计的时间，会有一个窗口存在不准确的情况。 比如，当前是 idle 状态，持续了一段时间，这里返回的还是上次更新的值， 并没有把这段持续时间算上。

• seq_printf(p, "cpu%d", i);
  

• seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
  

• seq_putc(p, '\n');
  

• }
• return 0;

+}

+static int idle_open(struct inode *inode, struct file *file) +{

• unsigned int size = 1024 + 128 * num_online_cpus();

1024 和 128 是什么含义？

• return single_open_size(file, show_idle, NULL, size);

+}

+static struct proc_ops idle_procs_ops = {

• .proc_open = idle_open,
• .proc_read_iter = seq_read_iter,
• .proc_lseek = seq_lseek,
• .proc_release = single_release,

+};

+static int __init kernel_module_init(void) +{

• proc_create(PROC_NAME, 0, NULL, &idle_procs_ops);
• return 0;

+}

+fs_initcall(kernel_module_init);

+#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..bb280852bb06 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -1078,3 +1078,19 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch);

#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */

+#ifdef CONFIG_PROC_IDLE

+u64 cpu_rq_get(int cpu) +{

• struct rq *rq = cpu_rq(cpu);
• struct sched_entity *idle_se = &rq->idle->se;
• u64 idle = idle_se->sum_exec_runtime;
• return idle;

+} +EXPORT_SYMBOL_GPL(cpu_rq_get);

这个是不是不导出也可以？ 另外，这个名字没表示出含义。

+#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..e3fb940a61e8 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -424,6 +424,20 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl

static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE

• struct sched_entity *idle_se = &rq->idle->se;
• u64 now = sched_clock();
• u64 delta_exec;
• delta_exec = now - idle_se->exec_start;
• if (unlikely((s64)delta_exec <= 0))

• return;
  

• schedstat_set(idle_se->statistics.exec_max,

• max(delta_exec, idle_se->statistics.exec_max));
  

• idle_se->sum_exec_runtime += delta_exec;

+#endif }

static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +450,13 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle;

+#ifdef CONFIG_PROC_IDLE

• struct sched_entity *idle_se = &rq->idle->se;
• u64 now = sched_clock();
• idle_se->exec_start = now;

+#endif

建议增加一个动态开关，static_key，如果不使能这个特性的话，就不必引入这些开销。

set_next_task_idle(rq, next, true);

return next;