From 024914477e15ef8b17f271ec47f1bb8a589f0806 Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Wed, 10 Mar 2010 15:22:17 -0800 Subject: memcg: move charges of anonymous swap This patch is another core part of this move-charge-at-task-migration feature. It enables moving charges of anonymous swaps. To move the charge of swap, we need to exchange swap_cgroup's record. In current implementation, swap_cgroup's record is protected by: - page lock: if the entry is on swap cache. - swap_lock: if the entry is not on swap cache. This works well in usual swap-in/out activity. But this behavior make the feature of moving swap charge check many conditions to exchange swap_cgroup's record safely. So I changed modification of swap_cgroup's recored(swap_cgroup_record()) to use xchg, and define a new function to cmpxchg swap_cgroup's record. This patch also enables moving charge of non pte_present but not uncharged swap caches, which can be exist on swap-out path, by getting the target pages via find_get_page() as do_mincore() does. [kosaki.motohiro@jp.fujitsu.com: fix ia64 build] [akpm@linux-foundation.org: fix typos] Signed-off-by: Daisuke Nishimura Cc: Balbir Singh Acked-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Paul Menage Cc: Daisuke Nishimura Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_cgroup.c | 34 ++++++++++++++++++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) (limited to 'mm/page_cgroup.c') diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 3d535d594826..3dd88539a0e6 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -334,6 +334,37 @@ not_enough_page: return -ENOMEM; } +/** + * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry. + * @end: swap entry to be cmpxchged + * @old: old id + * @new: new id + * + * Returns old id at success, 0 at failure. + * (There is no mem_cgroup useing 0 as its id) + */ +unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, + unsigned short old, unsigned short new) +{ + int type = swp_type(ent); + unsigned long offset = swp_offset(ent); + unsigned long idx = offset / SC_PER_PAGE; + unsigned long pos = offset & SC_POS_MASK; + struct swap_cgroup_ctrl *ctrl; + struct page *mappage; + struct swap_cgroup *sc; + + ctrl = &swap_cgroup_ctrl[type]; + + mappage = ctrl->map[idx]; + sc = page_address(mappage); + sc += pos; + if (cmpxchg(&sc->id, old, new) == old) + return old; + else + return 0; +} + /** * swap_cgroup_record - record mem_cgroup for this swp_entry. * @ent: swap entry to be recorded into @@ -358,8 +389,7 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) mappage = ctrl->map[idx]; sc = page_address(mappage); sc += pos; - old = sc->id; - sc->id = id; + old = xchg(&sc->id, id); return old; } -- cgit v1.2.3 From e9e58a4ec3b1086d1ed8c915311aef1ae55454fd Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 15 Mar 2010 00:34:57 -0400 Subject: memcg: avoid use cmpxchg in swap cgroup maintainance swap_cgroup uses 2bytes data and uses cmpxchg in a new operation. 2byte cmpxchg/xchg is not available on some archs. This patch replaces cmpxchg/xchg with operations under lock. Signed-off-by: KAMEZAWA Hiroyuki Reported-by: Sachin Sant wrote: Acked-by: Balbir Singh Acked-by: Daisuke Nishimura Cc: Li Zefan Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_cgroup.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'mm/page_cgroup.c') diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 3dd88539a0e6..6c0081441a32 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -284,6 +284,7 @@ static DEFINE_MUTEX(swap_cgroup_mutex); struct swap_cgroup_ctrl { struct page **map; unsigned long length; + spinlock_t lock; }; struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES]; @@ -353,16 +354,22 @@ unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, struct swap_cgroup_ctrl *ctrl; struct page *mappage; struct swap_cgroup *sc; + unsigned long flags; + unsigned short retval; ctrl = &swap_cgroup_ctrl[type]; mappage = ctrl->map[idx]; sc = page_address(mappage); sc += pos; - if (cmpxchg(&sc->id, old, new) == old) - return old; + spin_lock_irqsave(&ctrl->lock, flags); + retval = sc->id; + if (retval == old) + sc->id = new; else - return 0; + retval = 0; + spin_unlock_irqrestore(&ctrl->lock, flags); + return retval; } /** @@ -383,13 +390,17 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) struct page *mappage; struct swap_cgroup *sc; unsigned short old; + unsigned long flags; ctrl = &swap_cgroup_ctrl[type]; mappage = ctrl->map[idx]; sc = page_address(mappage); sc += pos; - old = xchg(&sc->id, id); + spin_lock_irqsave(&ctrl->lock, flags); + old = sc->id; + sc->id = id; + spin_unlock_irqrestore(&ctrl->lock, flags); return old; } @@ -441,6 +452,7 @@ int swap_cgroup_swapon(int type, unsigned long max_pages) mutex_lock(&swap_cgroup_mutex); ctrl->length = length; ctrl->map = array; + spin_lock_init(&ctrl->lock); if (swap_cgroup_prepare(type)) { /* memory shortage */ ctrl->map = NULL; -- cgit v1.2.3