Re: [RFC PATCH 1/3] cgroup: list all subsystem states in debugfs files

[Dmitry Yakunin <zeil@nebius.com>]

Sure, if you can share you work it would be nice. Thank you.

On 12.09.2023 00:16, Yosry Ahmed wrote:
> On Mon, Sep 11, 2023 at 12:55 AM Yakunin, Dmitry (Nebius)
> <zeil@nebius.com> wrote:
>> After removing cgroup subsystem state could leak or live in background
>> forever because it is pinned by some reference. For example memory cgroup
>> could be pinned by pages in cache or tmpfs.
>>
>> This patch adds common debugfs interface for listing basic state for each
>> controller. Controller could define callback for dumping own attributes.
>>
>> In file /sys/kernel/debug/cgroup/<controller> each line shows state in
>> format: <common_attr>=<value>... [-- <controller_attr>=<value>... ]
>>
>> Common attributes:
>>
>> css - css pointer
>> cgroup - cgroup pointer
>> id - css id
>> ino - cgroup inode
>> flags - css flags
>> refcnt - css atomic refcount, for online shows huge bias
>> path - cgroup path
>>
>> This patch adds memcg attributes:
>>
>> mem_id - 16-bit memory cgroup id
>> memory - charged pages
>> memsw - charged memory+swap for v1 and swap for v2
>> kmem - charged kernel pages
>> tcpmem - charged tcp pages
>> shmem - shmem/tmpfs pages
>>
>> Link: https://lore.kernel.org/lkml/153414348591.737150.14229960913953276515.stgit@buzz
>> Suggested-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
>> Reviewed-by: Andrey Ryabinin <arbn@yandex-team.com>
>> Signed-off-by: Dmitry Yakunin <zeil@nebius.com>
> FWIW, I was just recently working on a debugfs directly that exposes a
> list of all zombie memcgs as well as the "memory.stat" output for all
> of them.
>
> This entails a file at /sys/kernel/debug/zombie_memcgs/all that
> contains a list of zombie memcgs (with indentation to reflect the
> hierarchy) and an id for each of them.
>
> This id can be used to index per-memcg directories at
> /sys/kernel/debug/zombie_memcgs/<id>/, which include debug files. The
> only one we have so far is
> /sys/kernel/debug/zombie_memcgs/<id>/memory.stat.
>
> If there is interest in this, I can share more information.
>
>> ---
>>   include/linux/cgroup-defs.h |   1 +
>>   kernel/cgroup/cgroup.c      | 101 ++++++++++++++++++++++++++++++++++++
>>   mm/memcontrol.c             |  14 +++++
>>   3 files changed, 116 insertions(+)
>>
>> diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
>> index 8a0d5466c7be..810bd300cbee 100644
>> --- a/include/linux/cgroup-defs.h
>> +++ b/include/linux/cgroup-defs.h
>> @@ -673,6 +673,7 @@ struct cgroup_subsys {
>>          void (*exit)(struct task_struct *task);
>>          void (*release)(struct task_struct *task);
>>          void (*bind)(struct cgroup_subsys_state *root_css);
>> +       void (*css_dump)(struct cgroup_subsys_state *css, struct seq_file *m);
>>
>>          bool early_init:1;
>>
>> diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
>> index 625d7483951c..fb9931ff7570 100644
>> --- a/kernel/cgroup/cgroup.c
>> +++ b/kernel/cgroup/cgroup.c
>> @@ -40,6 +40,7 @@
>>   #include <linux/mount.h>
>>   #include <linux/pagemap.h>
>>   #include <linux/proc_fs.h>
>> +#include <linux/debugfs.h>
>>   #include <linux/rcupdate.h>
>>   #include <linux/sched.h>
>>   #include <linux/sched/task.h>
>> @@ -7068,3 +7069,103 @@ static int __init cgroup_sysfs_init(void)
>>   subsys_initcall(cgroup_sysfs_init);
>>
>>   #endif /* CONFIG_SYSFS */
>> +
>> +#ifdef CONFIG_DEBUG_FS
>> +void *css_debugfs_seqfile_start(struct seq_file *m, loff_t *pos)
>> +{
>> +       struct cgroup_subsys *ss = m->private;
>> +       struct cgroup_subsys_state *css;
>> +       int id = *pos;
>> +
>> +       rcu_read_lock();
>> +       css = idr_get_next(&ss->css_idr, &id);
>> +       *pos = id;
>> +       return css;
>> +}
>> +
>> +void *css_debugfs_seqfile_next(struct seq_file *m, void *v, loff_t *pos)
>> +{
>> +       struct cgroup_subsys *ss = m->private;
>> +       struct cgroup_subsys_state *css;
>> +       int id = *pos + 1;
>> +
>> +       css = idr_get_next(&ss->css_idr, &id);
>> +       *pos = id;
>> +       return css;
>> +}
>> +
>> +void css_debugfs_seqfile_stop(struct seq_file *m, void *v)
>> +{
>> +       rcu_read_unlock();
>> +}
>> +
>> +int css_debugfs_seqfile_show(struct seq_file *m, void *v)
>> +{
>> +       struct cgroup_subsys *ss = m->private;
>> +       struct cgroup_subsys_state *css = v;
>> +       /* data is NULL for root cgroup_subsys_state */
>> +       struct percpu_ref_data *data = css->refcnt.data;
>> +       size_t buflen;
>> +       char *buf;
>> +       int len;
>> +
>> +       seq_printf(m, "css=%pK cgroup=%pK id=%d ino=%lu flags=%#x refcnt=%lu path=",
>> +                  css, css->cgroup, css->id, cgroup_ino(css->cgroup),
>> +                  css->flags, data ? atomic_long_read(&data->count) : 0);
>> +
>> +       buflen = seq_get_buf(m, &buf);
>> +       if (buf) {
>> +               len = cgroup_path(css->cgroup, buf, buflen);
>> +               seq_commit(m, len < buflen ? len : -1);
>> +       }
>> +
>> +       if (ss->css_dump) {
>> +               seq_puts(m, " -- ");
>> +               ss->css_dump(css, m);
>> +       }
>> +
>> +       seq_putc(m, '\n');
>> +       return 0;
>> +}
>> +
>> +static const struct seq_operations css_debug_seq_ops = {
>> +       .start = css_debugfs_seqfile_start,
>> +       .next = css_debugfs_seqfile_next,
>> +       .stop = css_debugfs_seqfile_stop,
>> +       .show = css_debugfs_seqfile_show,
>> +};
>> +
>> +static int css_debugfs_open(struct inode *inode, struct file *file)
>> +{
>> +       int ret = seq_open(file, &css_debug_seq_ops);
>> +       struct seq_file *m = file->private_data;
>> +
>> +       if (!ret)
>> +               m->private = inode->i_private;
>> +       return ret;
>> +}
>> +
>> +static const struct file_operations css_debugfs_fops = {
>> +       .open = css_debugfs_open,
>> +       .read = seq_read,
>> +       .llseek = seq_lseek,
>> +       .release = seq_release,
>> +};
>> +
>> +static int __init css_debugfs_init(void)
>> +{
>> +       struct cgroup_subsys *ss;
>> +       struct dentry *dir;
>> +       int ssid;
>> +
>> +       dir = debugfs_create_dir("cgroup", NULL);
>> +       if (dir) {
>> +               for_each_subsys(ss, ssid)
>> +                       debugfs_create_file(ss->name, 0644, dir, ss,
>> +                                           &css_debugfs_fops);
>> +       }
>> +
>> +       return 0;
>> +}
>> +late_initcall(css_debugfs_init);
>> +#endif /* CONFIG_DEBUG_FS */
>> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
>> index 4b27e245a055..7b3d4a10ac63 100644
>> --- a/mm/memcontrol.c
>> +++ b/mm/memcontrol.c
>> @@ -5654,6 +5654,20 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
>>          }
>>   }
>>
>> +static void mem_cgroup_css_dump(struct cgroup_subsys_state *css,
>> +                               struct seq_file *m)
>> +{
>> +       struct mem_cgroup *memcg = mem_cgroup_from_css(css);
>> +
>> +       seq_printf(m, "mem_id=%u memory=%lu memsw=%lu kmem=%lu tcpmem=%lu shmem=%lu",
>> +                  mem_cgroup_id(memcg),
>> +                  page_counter_read(&memcg->memory),
>> +                  page_counter_read(&memcg->memsw),
>> +                  page_counter_read(&memcg->kmem),
>> +                  page_counter_read(&memcg->tcpmem),
>> +                  memcg_page_state(memcg, NR_SHMEM));
>> +}
>> +
>>   #ifdef CONFIG_MMU
>>   /* Handlers for move charge at task migration. */
>>   static int mem_cgroup_do_precharge(unsigned long count)
>> --
>> 2.25.1
>>
>>