From: Michal Hocko <mhocko@kernel.org>
To: Waiman Long <longman@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Johannes Weiner <hannes@cmpxchg.org>,
Roman Gushchin <guro@fb.com>, Vlastimil Babka <vbabka@suse.cz>,
Konstantin Khlebnikov <khlebnikov@yandex-team.ru>,
Jann Horn <jannh@google.com>, Song Liu <songliubraving@fb.com>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Rafael Aquini <aquini@redhat.com>, Mel Gorman <mgorman@suse.de>
Subject: Re: [PATCH] mm/vmstat: Reduce zone lock hold time when reading /proc/pagetypeinfo
Date: Tue, 22 Oct 2019 18:57:45 +0200 [thread overview]
Message-ID: <20191022165745.GT9379@dhcp22.suse.cz> (raw)
In-Reply-To: <20191022162156.17316-1-longman@redhat.com>
[Cc Mel]
On Tue 22-10-19 12:21:56, Waiman Long wrote:
> The pagetypeinfo_showfree_print() function prints out the number of
> free blocks for each of the page orders and migrate types. The current
> code just iterates the each of the free lists to get counts. There are
> bug reports about hard lockup panics when reading the /proc/pagetyeinfo
> file just because it look too long to iterate all the free lists within
> a zone while holing the zone lock with irq disabled.
>
> Given the fact that /proc/pagetypeinfo is readable by all, the possiblity
> of crashing a system by the simple act of reading /proc/pagetypeinfo
> by any user is a security problem that needs to be addressed.
Should we make the file 0400? It is a useful thing when debugging but
not something regular users would really need for life.
> There is a free_area structure associated with each page order. There
> is also a nr_free count within the free_area for all the different
> migration types combined. Tracking the number of free list entries
> for each migration type will probably add some overhead to the fast
> paths like moving pages from one migration type to another which may
> not be desirable.
Have you tried to measure that overhead?
> we can actually skip iterating the list of one of the migration types
> and used nr_free to compute the missing count. Since MIGRATE_MOVABLE
> is usually the largest one on large memory systems, this is the one
> to be skipped. Since the printing order is migration-type => order, we
> will have to store the counts in an internal 2D array before printing
> them out.
>
> Even by skipping the MIGRATE_MOVABLE pages, we may still be holding the
> zone lock for too long blocking out other zone lock waiters from being
> run. This can be problematic for systems with large amount of memory.
> So a check is added to temporarily release the lock and reschedule if
> more than 64k of list entries have been iterated for each order. With
> a MAX_ORDER of 11, the worst case will be iterating about 700k of list
> entries before releasing the lock.
But you are still iterating through the whole free_list at once so if it
gets really large then this is still possible. I think it would be
preferable to use per migratetype nr_free if it doesn't cause any
regressions.
> Signed-off-by: Waiman Long <longman@redhat.com>
> ---
> mm/vmstat.c | 51 +++++++++++++++++++++++++++++++++++++++++----------
> 1 file changed, 41 insertions(+), 10 deletions(-)
>
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 6afc892a148a..40c9a1494709 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1373,23 +1373,54 @@ static void pagetypeinfo_showfree_print(struct seq_file *m,
> pg_data_t *pgdat, struct zone *zone)
> {
> int order, mtype;
> + unsigned long nfree[MAX_ORDER][MIGRATE_TYPES];
>
> - for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) {
> - seq_printf(m, "Node %4d, zone %8s, type %12s ",
> - pgdat->node_id,
> - zone->name,
> - migratetype_names[mtype]);
> - for (order = 0; order < MAX_ORDER; ++order) {
> + lockdep_assert_held(&zone->lock);
> + lockdep_assert_irqs_disabled();
> +
> + /*
> + * MIGRATE_MOVABLE is usually the largest one in large memory
> + * systems. We skip iterating that list. Instead, we compute it by
> + * subtracting the total of the rests from free_area->nr_free.
> + */
> + for (order = 0; order < MAX_ORDER; ++order) {
> + unsigned long nr_total = 0;
> + struct free_area *area = &(zone->free_area[order]);
> +
> + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) {
> unsigned long freecount = 0;
> - struct free_area *area;
> struct list_head *curr;
>
> - area = &(zone->free_area[order]);
> -
> + if (mtype == MIGRATE_MOVABLE)
> + continue;
> list_for_each(curr, &area->free_list[mtype])
> freecount++;
> - seq_printf(m, "%6lu ", freecount);
> + nfree[order][mtype] = freecount;
> + nr_total += freecount;
> }
> + nfree[order][MIGRATE_MOVABLE] = area->nr_free - nr_total;
> +
> + /*
> + * If we have already iterated more than 64k of list
> + * entries, we might have hold the zone lock for too long.
> + * Temporarily release the lock and reschedule before
> + * continuing so that other lock waiters have a chance
> + * to run.
> + */
> + if (nr_total > (1 << 16)) {
> + spin_unlock_irq(&zone->lock);
> + cond_resched();
> + spin_lock_irq(&zone->lock);
> + }
> + }
> +
> + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) {
> + seq_printf(m, "Node %4d, zone %8s, type %12s ",
> + pgdat->node_id,
> + zone->name,
> + migratetype_names[mtype]);
> + for (order = 0; order < MAX_ORDER; ++order)
> + seq_printf(m, "%6lu ", nfree[order][mtype]);
> seq_putc(m, '\n');
> }
> }
> --
> 2.18.1
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2019-10-22 16:57 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-22 16:21 [PATCH] mm/vmstat: Reduce zone lock hold time when reading /proc/pagetypeinfo Waiman Long
2019-10-22 16:57 ` Michal Hocko [this message]
2019-10-22 18:00 ` Waiman Long
2019-10-22 18:40 ` Waiman Long
2019-10-23 0:52 ` David Rientjes
2019-10-23 8:31 ` Mel Gorman
2019-10-23 9:04 ` Michal Hocko
2019-10-23 9:56 ` Mel Gorman
2019-10-23 10:27 ` [RFC PATCH 0/2] " Michal Hocko
2019-10-23 10:27 ` [RFC PATCH 1/2] mm, vmstat: hide /proc/pagetypeinfo from normal users Michal Hocko
2019-10-23 13:13 ` Mel Gorman
2019-10-23 13:27 ` Vlastimil Babka
2019-10-23 14:52 ` Waiman Long
2019-10-23 15:10 ` Rafael Aquini
2019-10-23 16:15 ` Vlastimil Babka
2019-10-24 19:01 ` David Rientjes
2019-10-23 10:27 ` [RFC PATCH 2/2] mm, vmstat: reduce zone->lock holding time by /proc/pagetypeinfo Michal Hocko
2019-10-23 13:15 ` Mel Gorman
2019-10-23 13:32 ` Vlastimil Babka
2019-10-23 13:37 ` Michal Hocko
2019-10-23 13:48 ` Vlastimil Babka
2019-10-23 14:31 ` Michal Hocko
2019-10-23 16:20 ` Vlastimil Babka
2019-10-23 13:46 ` Rafael Aquini
2019-10-23 14:56 ` Waiman Long
2019-10-23 15:21 ` Waiman Long
2019-10-23 16:10 ` Michal Hocko
2019-10-23 16:17 ` Waiman Long
2019-10-23 16:21 ` Waiman Long
2019-10-23 16:15 ` Vlastimil Babka
2019-10-23 16:41 ` Michal Hocko
2019-10-23 16:47 ` Waiman Long
2019-10-23 17:34 ` [PATCH 1/2] mm, vmstat: Release zone lock more frequently when reading /proc/pagetypeinfo Waiman Long
2019-10-23 18:01 ` Michal Hocko
2019-10-23 18:14 ` Waiman Long
2019-10-23 20:02 ` Michal Hocko
2019-10-23 17:34 ` [PATCH 2/2] mm, vmstat: List total free blocks for each order in /proc/pagetypeinfo Waiman Long
2019-10-23 18:02 ` Michal Hocko
2019-10-23 18:07 ` Waiman Long
2019-10-24 8:20 ` [RFC PATCH 0/2] mm/vmstat: Reduce zone lock hold time when reading /proc/pagetypeinfo Michal Hocko
2019-10-24 16:16 ` Waiman Long
2019-10-23 12:42 ` [PATCH] " Qian Cai
2019-10-23 13:25 ` Vlastimil Babka
2019-10-22 21:59 ` Andrew Morton
2019-10-23 6:15 ` Michal Hocko
2019-10-23 14:30 ` Waiman Long
2019-10-23 14:48 ` Qian Cai
2019-10-23 15:01 ` Waiman Long
2019-10-23 15:05 ` Qian Cai
2019-10-23 22:30 ` Andrew Morton
2019-10-24 5:33 ` Qian Cai
2019-10-24 7:42 ` Michal Hocko
2019-10-24 11:11 ` Qian Cai
2019-10-24 13:38 ` Michal Hocko
2019-10-24 14:55 ` Qian Cai
2019-10-24 3:33 ` Feng Tang
2019-10-24 4:34 ` Qian Cai
2019-10-24 5:34 ` Feng Tang
2019-10-24 10:51 ` Qian Cai
2019-10-25 1:38 ` Feng Tang
2019-10-23 15:03 ` Rafael Aquini
2019-10-23 15:51 ` Qian Cai
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191022165745.GT9379@dhcp22.suse.cz \
--to=mhocko@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=aquini@redhat.com \
--cc=gregkh@linuxfoundation.org \
--cc=guro@fb.com \
--cc=hannes@cmpxchg.org \
--cc=jannh@google.com \
--cc=khlebnikov@yandex-team.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=longman@redhat.com \
--cc=mgorman@suse.de \
--cc=songliubraving@fb.com \
--cc=vbabka@suse.cz \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).