Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760070Ab0HEKCz (ORCPT ); Thu, 5 Aug 2010 06:02:55 -0400 Received: from fgwmail5.fujitsu.co.jp ([192.51.44.35]:33162 "EHLO fgwmail5.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755601Ab0HEKCx (ORCPT ); Thu, 5 Aug 2010 06:02:53 -0400 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 Date: Thu, 5 Aug 2010 18:57:58 +0900 From: KAMEZAWA Hiroyuki To: KAMEZAWA Hiroyuki Cc: linux-mm@kvack.org, "balbir@linux.vnet.ibm.com" , "nishimura@mxp.nes.nec.co.jp" , vgoyal@redhat.com, m-ikeda@ds.jp.nec.com, gthelen@google.com, "akpm@linux-foundation.org" , "linux-kernel@vger.kernel.org" Subject: [PATCH 2/4 -mm][memcg] use id in page cgroup Message-Id: <20100805185758.fccad69f.kamezawa.hiroyu@jp.fujitsu.com> In-Reply-To: <20100805184434.3a29c0f9.kamezawa.hiroyu@jp.fujitsu.com> References: <20100805184434.3a29c0f9.kamezawa.hiroyu@jp.fujitsu.com> Organization: FUJITSU Co. LTD. X-Mailer: Sylpheed 3.0.3 (GTK+ 2.10.14; i686-pc-mingw32) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6727 Lines: 195 From: KAMEZAWA Hiroyuki Now, addresses of memory cgroup can be calculated by their ID without complex. This patch relplaces pc->mem_cgroup from a pointer to a unsigned short. On 64bit architecture, this offers us more 6bytes room per page_cgroup. Use 2bytes for blkio-cgroup's page tracking. More 4bytes will be used for some light-weight concurrent access. We may able to move this id onto flags field but ...go step by step. Changelog: 20100804 - added comments to page_cgroup.h Changelog: 20100730 - fixed some garbage added by debug code in early stage Signed-off-by: KAMEZAWA Hiroyuki --- include/linux/page_cgroup.h | 6 +++++- mm/memcontrol.c | 32 +++++++++++++++++++------------- mm/page_cgroup.c | 2 +- 3 files changed, 25 insertions(+), 15 deletions(-) Index: mmotm-0727/include/linux/page_cgroup.h =================================================================== --- mmotm-0727.orig/include/linux/page_cgroup.h +++ mmotm-0727/include/linux/page_cgroup.h @@ -9,10 +9,14 @@ * page_cgroup helps us identify information about the cgroup * All page cgroups are allocated at boot or memory hotplug event, * then the page cgroup for pfn always exists. + * + * TODO: It seems ID for cgroup can be packed into "flags". But there will + * be race between assigning ID <-> set/clear flags. Please be careful. */ struct page_cgroup { unsigned long flags; - struct mem_cgroup *mem_cgroup; + unsigned short mem_cgroup; /* ID of assigned memory cgroup */ + unsigned short blk_cgroup; /* Not Used..but will be. */ struct page *page; struct list_head lru; /* per cgroup LRU list */ }; Index: mmotm-0727/mm/page_cgroup.c =================================================================== --- mmotm-0727.orig/mm/page_cgroup.c +++ mmotm-0727/mm/page_cgroup.c @@ -15,7 +15,7 @@ static void __meminit __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn) { pc->flags = 0; - pc->mem_cgroup = NULL; + pc->mem_cgroup = 0; pc->page = pfn_to_page(pfn); INIT_LIST_HEAD(&pc->lru); } Index: mmotm-0727/mm/memcontrol.c =================================================================== --- mmotm-0727.orig/mm/memcontrol.c +++ mmotm-0727/mm/memcontrol.c @@ -379,7 +379,7 @@ struct cgroup_subsys_state *mem_cgroup_c static struct mem_cgroup_per_zone * page_cgroup_zoneinfo(struct page_cgroup *pc) { - struct mem_cgroup *mem = pc->mem_cgroup; + struct mem_cgroup *mem = id_to_memcg(pc->mem_cgroup); int nid = page_cgroup_nid(pc); int zid = page_cgroup_zid(pc); @@ -721,6 +721,11 @@ static inline bool mem_cgroup_is_root(st return (mem == root_mem_cgroup); } +static inline bool mem_cgroup_is_rootid(unsigned short id) +{ + return (id == 1); +} + /* * Following LRU functions are allowed to be used without PCG_LOCK. * Operations are called by routine of global LRU independently from memcg. @@ -753,7 +758,7 @@ void mem_cgroup_del_lru_list(struct page */ mz = page_cgroup_zoneinfo(pc); MEM_CGROUP_ZSTAT(mz, lru) -= 1; - if (mem_cgroup_is_root(pc->mem_cgroup)) + if (mem_cgroup_is_rootid(pc->mem_cgroup)) return; VM_BUG_ON(list_empty(&pc->lru)); list_del_init(&pc->lru); @@ -780,7 +785,7 @@ void mem_cgroup_rotate_lru_list(struct p */ smp_rmb(); /* unused or root page is not rotated. */ - if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup)) + if (!PageCgroupUsed(pc) || mem_cgroup_is_rootid(pc->mem_cgroup)) return; mz = page_cgroup_zoneinfo(pc); list_move(&pc->lru, &mz->lists[lru]); @@ -806,7 +811,7 @@ void mem_cgroup_add_lru_list(struct page mz = page_cgroup_zoneinfo(pc); MEM_CGROUP_ZSTAT(mz, lru) += 1; SetPageCgroupAcctLRU(pc); - if (mem_cgroup_is_root(pc->mem_cgroup)) + if (mem_cgroup_is_rootid(pc->mem_cgroup)) return; list_add(&pc->lru, &mz->lists[lru]); } @@ -1474,7 +1479,7 @@ void mem_cgroup_update_file_mapped(struc return; lock_page_cgroup(pc); - mem = pc->mem_cgroup; + mem = id_to_memcg(pc->mem_cgroup); if (!mem || !PageCgroupUsed(pc)) goto done; @@ -1862,7 +1867,7 @@ struct mem_cgroup *try_get_mem_cgroup_fr pc = lookup_page_cgroup(page); lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { - mem = pc->mem_cgroup; + mem = id_to_memcg(pc->mem_cgroup); if (mem && !css_tryget(&mem->css)) mem = NULL; } else if (PageSwapCache(page)) { @@ -1898,7 +1903,7 @@ static void __mem_cgroup_commit_charge(s return; } - pc->mem_cgroup = mem; + pc->mem_cgroup = css_id(&mem->css); /* * We access a page_cgroup asynchronously without lock_page_cgroup(). * Especially when a page_cgroup is taken from a page, pc->mem_cgroup @@ -1956,7 +1961,7 @@ static void __mem_cgroup_move_account(st VM_BUG_ON(PageLRU(pc->page)); VM_BUG_ON(!PageCgroupLocked(pc)); VM_BUG_ON(!PageCgroupUsed(pc)); - VM_BUG_ON(pc->mem_cgroup != from); + VM_BUG_ON(id_to_memcg(pc->mem_cgroup) != from); if (PageCgroupFileMapped(pc)) { /* Update mapped_file data for mem_cgroup */ @@ -1971,7 +1976,7 @@ static void __mem_cgroup_move_account(st mem_cgroup_cancel_charge(from); /* caller should have done css_get */ - pc->mem_cgroup = to; + pc->mem_cgroup = css_id(&to->css); mem_cgroup_charge_statistics(to, pc, true); /* * We charges against "to" which may not have any tasks. Then, "to" @@ -1991,7 +1996,7 @@ static int mem_cgroup_move_account(struc { int ret = -EINVAL; lock_page_cgroup(pc); - if (PageCgroupUsed(pc) && pc->mem_cgroup == from) { + if (PageCgroupUsed(pc) && id_to_memcg(pc->mem_cgroup) == from) { __mem_cgroup_move_account(pc, from, to, uncharge); ret = 0; } @@ -2330,7 +2335,7 @@ __mem_cgroup_uncharge_common(struct page lock_page_cgroup(pc); - mem = pc->mem_cgroup; + mem = id_to_memcg(pc->mem_cgroup); if (!PageCgroupUsed(pc)) goto unlock_out; @@ -2575,7 +2580,7 @@ int mem_cgroup_prepare_migration(struct pc = lookup_page_cgroup(page); lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { - mem = pc->mem_cgroup; + mem = id_to_memcg(pc->mem_cgroup); css_get(&mem->css); /* * At migrating an anonymous page, its mapcount goes down @@ -4398,7 +4403,8 @@ static int is_target_pte_for_mc(struct v * mem_cgroup_move_account() checks the pc is valid or not under * the lock. */ - if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) { + if (PageCgroupUsed(pc) && + id_to_memcg(pc->mem_cgroup) == mc.from) { ret = MC_TARGET_PAGE; if (target) target->page = page; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/