| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20090416085814.8b6d077f.kamezawa.hiroyu@jp.fujitsu.com>
Date: Thu, 16 Apr 2009 08:58:14 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: Andrea Righi <righi.andrea@...il.com>
Cc: Ryo Tsuruta <ryov@...inux.co.jp>, menage@...gle.com,
balbir@...ux.vnet.ibm.com, guijianfeng@...fujitsu.com,
agk@...rceware.org, akpm@...ux-foundation.org, axboe@...nel.dk,
baramsori72@...il.com, chlunde@...g.uio.no,
dave@...ux.vnet.ibm.com, dpshah@...gle.com, eric.rannaud@...il.com,
fernando@....ntt.co.jp, taka@...inux.co.jp, lizf@...fujitsu.com,
matt@...ehost.com, dradford@...ehost.com, ngupta@...gle.com,
randy.dunlap@...cle.com, roberto@...it.it, s-uchida@...jp.nec.com,
subrata@...ux.vnet.ibm.com, yoshikawa.takuya@....ntt.co.jp,
containers@...ts.linux-foundation.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 3/9] bio-cgroup controller
On Wed, 15 Apr 2009 15:23:57 +0200
Andrea Righi <righi.andrea@...il.com> wrote:
> On Wed, Apr 15, 2009 at 09:38:50PM +0900, Ryo Tsuruta wrote:
> > Hi Andrea and Kamezawa-san,
> >
> > > Ryo, it would be great if you can look at this and fix/integrate into
> > > the mainstream bio-cgroup. Otherwise I can try to to schedule this in my
> > > work.
> >
> > O.K. I'll apply those fixes and post patches as soon as I can.
> >
>
> Very good! I've just tested the bio_cgroup_id inclusion in
> page_cgroup->flags. I'm posting the patch on-top-of my patchset.
>
> If you're interested, it should apply cleanly to the original
> bio-cgroup, except for the get/put_cgroup_from_page() part.
>
> Thanks,
> -Andrea
> ---
> bio-cgroup: encode bio_cgroup_id in page_cgroup->flags
>
> Encode the bio_cgroup_id into the flags argument of page_cgroup as
> suggested by Kamezawa.
>
> Lower 16-bits of the flags attribute are used for the actual page_cgroup
> flags. The rest is reserved to store the bio-cgroup id.
>
> This allows to save 4 bytes (in 32-bit architectures) or 8 bytes (in
> 64-bit) for each page_cgroup element.
>
> Signed-off-by: Andrea Righi <righi.andrea@...il.com>
> ---
> include/linux/biotrack.h | 2 +-
> include/linux/page_cgroup.h | 24 +++++++++++++++++++++---
> mm/biotrack.c | 26 ++++++++++++--------------
> 3 files changed, 34 insertions(+), 18 deletions(-)
>
> diff --git a/include/linux/biotrack.h b/include/linux/biotrack.h
> index 25b8810..4bd0242 100644
> --- a/include/linux/biotrack.h
> +++ b/include/linux/biotrack.h
> @@ -28,7 +28,7 @@ struct bio_cgroup {
>
> static inline void __init_bio_page_cgroup(struct page_cgroup *pc)
> {
> - pc->bio_cgroup_id = 0;
> + page_cgroup_set_bio_id(pc, 0);
> }
>
> extern struct cgroup *get_cgroup_from_page(struct page *page);
> diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
> index 00a49c5..af780a4 100644
> --- a/include/linux/page_cgroup.h
> +++ b/include/linux/page_cgroup.h
> @@ -16,12 +16,30 @@ struct page_cgroup {
> #ifdef CONFIG_CGROUP_MEM_RES_CTLR
> struct mem_cgroup *mem_cgroup;
> #endif
> -#ifdef CONFIG_CGROUP_BIO
> - int bio_cgroup_id;
> -#endif
> struct list_head lru; /* per cgroup LRU list */
> };
>
> +#ifdef CONFIG_CGROUP_BIO
> +/*
> + * use lower 16 bits for flags and reserve the rest for the bio-cgroup id
> + */
> +#define BIO_CGROUP_ID_SHIFT (16)
> +#define BIO_CGROUP_ID_BITS (8 * sizeof(unsigned long) - BIO_CGROUP_ID_SHIFT)
> +
> +static inline unsigned long page_cgroup_get_bio_id(struct page_cgroup *pc)
> +{
> + return pc->flags >> BIO_CGROUP_ID_SHIFT;
> +}
> +
> +static inline void page_cgroup_set_bio_id(struct page_cgroup *pc,
> + unsigned long id)
> +{
> + WARN_ON(id >= (1UL << BIO_CGROUP_ID_BITS));
> + pc->flags &= (1UL << BIO_CGROUP_ID_SHIFT) - 1;
> + pc->flags |= (unsigned long)(id << BIO_CGROUP_ID_SHIFT);
> +}
> +#endif
> +
Ah, there is "Lock" bit in pc->flags and above "set" code does read-modify-write
without lock_page_cgroup().
Could you use lock_page_cgroup() or cmpxchg ? (or using something magical technique ?)
Thanks,
-Kame
> void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat);
> void __init page_cgroup_init(void);
> struct page_cgroup *lookup_page_cgroup(struct page *page);
> diff --git a/mm/biotrack.c b/mm/biotrack.c
> index 431056c..4cca3bf 100644
> --- a/mm/biotrack.c
> +++ b/mm/biotrack.c
> @@ -74,7 +74,7 @@ void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm)
> struct bio_cgroup *biog;
> struct page_cgroup *pc;
>
> - WARN_ON_ONCE(test_bit(PG_locked, &page->flags));
> + WARN_ON_ONCE(!test_bit(PG_locked, &page->flags));
>
> if (bio_cgroup_disabled())
> return;
> @@ -82,7 +82,7 @@ void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm)
> if (unlikely(!pc))
> return;
>
> - pc->bio_cgroup_id = 0; /* 0: default bio_cgroup id */
> + __init_bio_page_cgroup(pc);
> if (!mm)
> return;
> /*
> @@ -95,11 +95,11 @@ void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm)
> goto out;
> /*
> * css_get(&bio->css) isn't called to increment the reference
> - * count of this bio_cgroup "biog" so pc->bio_cgroup_id might turn
> - * invalid even if this page is still active.
> - * This approach is chosen to minimize the overhead.
> + * count of this bio_cgroup "biog" so the bio-cgroup id might turn
> + * invalid even if this page is still active. This approach is chosen
> + * to minimize the overhead.
> */
> - pc->bio_cgroup_id = biog->id;
> + page_cgroup_set_bio_id(pc, biog->id);
> out:
> rcu_read_unlock();
> }
> @@ -112,7 +112,7 @@ void bio_cgroup_reset_owner(struct page *page, struct mm_struct *mm)
> /*
> * A little trick:
> * Just call bio_cgroup_set_owner() for pages which are already
> - * active since the bio_cgroup_id member of page_cgroup can be
> + * active since the bio-cgroup id member of page_cgroup can be
> * updated without any locks. This is because an integer type of
> * variable can be set a new value at once on modern cpus.
> */
> @@ -148,12 +148,10 @@ void bio_cgroup_copy_owner(struct page *npage, struct page *opage)
> opc = lookup_page_cgroup(opage);
> if (unlikely(!opc))
> return;
> -
> /*
> - * Do this without any locks. The reason is the same as
> - * bio_cgroup_reset_owner().
> + * XXX: is it safe to do this without locking?
> */
> - npc->bio_cgroup_id = opc->bio_cgroup_id;
> + page_cgroup_set_bio_id(npc, page_cgroup_get_bio_id(opc));
> }
>
> /* Create a new bio-cgroup. */
> @@ -250,7 +248,7 @@ struct cgroup *get_cgroup_from_page(struct page *page)
> if (!pc)
> return NULL;
> lock_page_cgroup(pc);
> - biog = find_bio_cgroup(pc->bio_cgroup_id);
> + biog = find_bio_cgroup(page_cgroup_get_bio_id(pc));
> if (biog) {
> css_get(&biog->css);
> cgrp = biog->css.cgroup;
> @@ -268,7 +266,7 @@ void put_cgroup_from_page(struct page *page)
> if (!pc)
> return;
> lock_page_cgroup(pc);
> - biog = find_bio_cgroup(pc->bio_cgroup_id);
> + biog = find_bio_cgroup(page_cgroup_get_bio_id(pc));
> if (biog)
> css_put(&biog->css);
> unlock_page_cgroup(pc);
> @@ -283,7 +281,7 @@ int get_bio_cgroup_id(struct bio *bio)
>
> pc = lookup_page_cgroup(page);
> if (pc)
> - id = pc->bio_cgroup_id;
> + id = page_cgroup_get_bio_id(pc);
> return id;
> }
> EXPORT_SYMBOL(get_bio_cgroup_id);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists