Message-ID: <20200323120044.GA29433@dhcp-128-65.nay.redhat.com>
Date:   Mon, 23 Mar 2020 20:00:44 +0800
From:   Dave Young <dyoung@...hat.com>
To:     Jaewon Kim <jaewon31.kim@...sung.com>
Cc:     gregkh@...uxfoundation.org, leon@...nel.org, vbabka@...e.cz,
        adobriyan@...il.com, akpm@...ux-foundation.org, labbott@...hat.com,
        sumit.semwal@...aro.org, minchan@...nel.org, ngupta@...are.org,
        sergey.senozhatsky.work@...il.com, kasong@...hat.com,
        bhe@...hat.com, linux-api@...r.kernel.org,
        kexec@...ts.infradead.org, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, jaewon31.kim@...il.com
Subject: Re: [RFC PATCH v2 1/3] meminfo_extra: introduce meminfo extra

Hi Jaewon,

On 03/23/20 at 05:05pm, Jaewon Kim wrote:
> Provide APIs to drivers so that they can show its memory usage on
> /proc/meminfo_extra.
> 
> int register_meminfo_extra(atomic_long_t *val, int shift,
> 			   const char *name);
> int unregister_meminfo_extra(atomic_long_t *val);
> 
> Signed-off-by: Jaewon Kim <jaewon31.kim@...sung.com>
> ---
> v2: move to /proc/meminfo_extra as a new file, meminfo_extra.c
>     use rcu to reduce lock overhead
> v1: print info at /proc/meminfo
> ---
>  fs/proc/Makefile        |   1 +
>  fs/proc/meminfo_extra.c | 123 ++++++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/mm.h      |   4 ++
>  mm/page_alloc.c         |   1 +
>  4 files changed, 129 insertions(+)
>  create mode 100644 fs/proc/meminfo_extra.c
> 
> diff --git a/fs/proc/Makefile b/fs/proc/Makefile
> index bd08616ed8ba..83d2f55591c6 100644
> --- a/fs/proc/Makefile
> +++ b/fs/proc/Makefile
> @@ -19,6 +19,7 @@ proc-y	+= devices.o
>  proc-y	+= interrupts.o
>  proc-y	+= loadavg.o
>  proc-y	+= meminfo.o
> +proc-y	+= meminfo_extra.o
>  proc-y	+= stat.o
>  proc-y	+= uptime.o
>  proc-y	+= util.o
> diff --git a/fs/proc/meminfo_extra.c b/fs/proc/meminfo_extra.c
> new file mode 100644
> index 000000000000..bd3f0d2b7fb7
> --- /dev/null
> +++ b/fs/proc/meminfo_extra.c
> @@ -0,0 +1,123 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <linux/mm.h>
> +#include <linux/proc_fs.h>
> +#include <linux/seq_file.h>
> +#include <linux/slab.h>
> +
> +static void show_val_kb(struct seq_file *m, const char *s, unsigned long num)
> +{
> +	seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8);
> +	seq_write(m, " kB\n", 4);
> +}
> +
> +static LIST_HEAD(meminfo_head);
> +static DEFINE_SPINLOCK(meminfo_lock);
> +
> +#define NAME_SIZE      15
> +#define NAME_BUF_SIZE  (NAME_SIZE + 2) /* ':' and '\0' */
> +
> +struct meminfo_extra {
> +	struct list_head list;
> +	atomic_long_t *val;
> +	int shift_for_page;

Can this be simplified to use a bytes value without an extra shift?

> +	char name[NAME_BUF_SIZE];
> +	char name_pad[NAME_BUF_SIZE];
> +};
> +
There should be document about below function here.

> +int register_meminfo_extra(atomic_long_t *val, int shift, const char *name)
> +{
> +	struct meminfo_extra *meminfo, *memtemp;
> +	int len;
> +	int error = 0;
> +
> +	meminfo = kzalloc(sizeof(*meminfo), GFP_KERNEL);
> +	if (!meminfo) {
> +		error = -ENOMEM;
> +		goto out;
> +	}
> +
> +	meminfo->val = val;
> +	meminfo->shift_for_page = shift;
> +	strncpy(meminfo->name, name, NAME_SIZE);
> +	len = strlen(meminfo->name);
> +	meminfo->name[len] = ':';
> +	strncpy(meminfo->name_pad, meminfo->name, NAME_BUF_SIZE);
> +	while (++len < NAME_BUF_SIZE - 1)
> +		meminfo->name_pad[len] = ' ';
> +
> +	spin_lock(&meminfo_lock);
> +	list_for_each_entry_rcu(memtemp, &meminfo_head, list) {
> +		if (memtemp->val == val) {
> +			error = -EINVAL;
> +			break;
> +		}
> +	}
> +	if (!error)
> +		list_add_tail_rcu(&meminfo->list, &meminfo_head);
> +	spin_unlock(&meminfo_lock);
> +	if (error)
> +		kfree(meminfo);
> +out:
> +
> +	return error;
> +}
> +EXPORT_SYMBOL(register_meminfo_extra);
> +
> +int unregister_meminfo_extra(atomic_long_t *val)
> +{
> +	struct meminfo_extra *memtemp;
> +	int error = -EINVAL;
> +
> +	spin_lock(&meminfo_lock);
> +	list_for_each_entry_rcu(memtemp, &meminfo_head, list) {
> +		if (memtemp->val == val) {
> +			list_del_rcu(&memtemp->list);
> +			error = 0;
> +			break;
> +		}
> +	}
> +	spin_unlock(&meminfo_lock);
> +	if (!error) {
> +		synchronize_rcu();
> +		kfree(memtemp);
> +	}
> +
> +	return error;
> +}
> +EXPORT_SYMBOL(unregister_meminfo_extra);
> +
> +static void __meminfo_extra(struct seq_file *m)
> +{
> +	struct meminfo_extra *memtemp;
> +	unsigned long nr_page;
> +
> +	rcu_read_lock();
> +	list_for_each_entry_rcu(memtemp, &meminfo_head, list) {
> +		nr_page = (unsigned long)atomic_long_read(memtemp->val);
> +		nr_page = nr_page >> memtemp->shift_for_page;
> +		if (m)
> +			show_val_kb(m, memtemp->name_pad, nr_page);
> +		else
> +			pr_cont("%s%lukB ", memtemp->name, nr_page);

nr_page != nr_kb?

> +	}
> +	rcu_read_unlock();
> +}
> +
> +void show_meminfo_extra(void)
> +{
> +	__meminfo_extra(NULL);
> +}
> +
> +static int meminfo_extra_proc_show(struct seq_file *m, void *v)
> +{
> +	__meminfo_extra(m);
> +
> +	return 0;
> +}
> +
> +static int __init proc_meminfo_extra_init(void)
> +{
> +	proc_create_single("meminfo_extra", 0, NULL, meminfo_extra_proc_show);
> +	return 0;
> +}
> +fs_initcall(proc_meminfo_extra_init);
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 52269e56c514..55317161ab57 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2898,6 +2898,10 @@ void __init setup_nr_node_ids(void);
>  static inline void setup_nr_node_ids(void) {}
>  #endif
>  
> +void show_meminfo_extra(void);
> +int register_meminfo_extra(atomic_long_t *val, int shift, const char *name);
> +int unregister_meminfo_extra(atomic_long_t *val);
> +
>  extern int memcmp_pages(struct page *page1, struct page *page2);
>  
>  static inline int pages_identical(struct page *page1, struct page *page2)
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 3c4eb750a199..db1be9a39783 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5229,6 +5229,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
>  	struct zone *zone;
>  	pg_data_t *pgdat;
>  
> +	show_meminfo_extra();
>  	for_each_populated_zone(zone) {
>  		if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
>  			continue;
> -- 
> 2.13.7
> 
> 
> _______________________________________________
> kexec mailing list
> kexec@...ts.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec
> 

Thanks
Dave

Powered by blists - more mailing lists