From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.8 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH, MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED, USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1B1ABC5518E for ; Wed, 22 Apr 2020 20:47:42 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id B512A20882 for ; Wed, 22 Apr 2020 20:47:41 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=fb.com header.i=@fb.com header.b="oobsa7DW" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org B512A20882 Authentication-Results: mail.kernel.org; dmarc=fail (p=quarantine dis=none) header.from=fb.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 067568E000D; Wed, 22 Apr 2020 16:47:26 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 01A028E0005; Wed, 22 Apr 2020 16:47:25 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id D64D78E000E; Wed, 22 Apr 2020 16:47:25 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0014.hostedemail.com [216.40.44.14]) by kanga.kvack.org (Postfix) with ESMTP id ACD078E0005 for ; Wed, 22 Apr 2020 16:47:25 -0400 (EDT) Received: from smtpin24.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay03.hostedemail.com (Postfix) with ESMTP id 66FD48248047 for ; Wed, 22 Apr 2020 20:47:25 +0000 (UTC) X-FDA: 76736676450.24.bun35_40c4bd59dbc5f X-HE-Tag: bun35_40c4bd59dbc5f X-Filterd-Recvd-Size: 10874 Received: from mx0a-00082601.pphosted.com (mx0b-00082601.pphosted.com [67.231.153.30]) by imf28.hostedemail.com (Postfix) with ESMTP for ; Wed, 22 Apr 2020 20:47:24 +0000 (UTC) Received: from pps.filterd (m0001303.ppops.net [127.0.0.1]) by m0001303.ppops.net (8.16.0.42/8.16.0.42) with SMTP id 03MKlDYW016498 for ; Wed, 22 Apr 2020 13:47:24 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fb.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding : content-type; s=facebook; bh=k31UF3lc/V330emquUpnrEBWF2oe4QDGcEd9mx3bsmM=; b=oobsa7DWPyL0ow7edwuRj3HklT0Y+yef3oLKc/udyGPDhnVaf76E3HQBiAMcj/ih/vYh lzPsZLPGume8cYWnTN+eTTRkKYN07lCVKLI17/SVNF5yUQ9Wk1kuSiasNitxTvVW0dEz jgh6hDulUWjvSVOv23C7mtwpSHc8SJiduFo= Received: from mail.thefacebook.com ([163.114.132.120]) by m0001303.ppops.net with ESMTP id 30jatknts5-9 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NOT) for ; Wed, 22 Apr 2020 13:47:24 -0700 Received: from intmgw004.06.prn3.facebook.com (2620:10d:c085:108::4) by mail.thefacebook.com (2620:10d:c085:21d::7) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Wed, 22 Apr 2020 13:47:23 -0700 Received: by devvm4439.prn2.facebook.com (Postfix, from userid 111017) id CF42022935801; Wed, 22 Apr 2020 13:47:16 -0700 (PDT) Smtp-Origin-Hostprefix: devvm From: Roman Gushchin Smtp-Origin-Hostname: devvm4439.prn2.facebook.com To: Andrew Morton CC: Johannes Weiner , Michal Hocko , , , , Roman Gushchin Smtp-Origin-Cluster: prn2c23 Subject: [PATCH v3 05/19] mm: memcontrol: decouple reference counting from page accounting Date: Wed, 22 Apr 2020 13:46:54 -0700 Message-ID: <20200422204708.2176080-6-guro@fb.com> X-Mailer: git-send-email 2.24.1 In-Reply-To: <20200422204708.2176080-1-guro@fb.com> References: <20200422204708.2176080-1-guro@fb.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-FB-Internal: Safe Content-Type: text/plain X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.138,18.0.676 definitions=2020-04-22_07:2020-04-22,2020-04-22 signatures=0 X-Proofpoint-Spam-Details: rule=fb_default_notspam policy=fb_default score=0 spamscore=0 clxscore=1015 malwarescore=0 impostorscore=0 adultscore=0 suspectscore=0 lowpriorityscore=0 priorityscore=1501 phishscore=0 mlxlogscore=999 mlxscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2003020000 definitions=main-2004220159 X-FB-Internal: deliver X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: From: Johannes Weiner The reference counting of a memcg is currently coupled directly to how many 4k pages are charged to it. This doesn't work well with Roman's new slab controller, which maintains pools of objects and doesn't want to keep an extra balance sheet for the pages backing those objects. This unusual refcounting design (reference counts usually track pointers to an object) is only for historical reasons: memcg used to not take any css references and simply stalled offlining until all charges had been reparented and the page counters had dropped to zero. When we got rid of the reparenting requirement, the simple mechanical translation was to take a reference for every charge. More historical context can be found in commit e8ea14cc6ead ("mm: memcontrol: take a css reference for each charged page"), commit 64f219938941 ("mm: memcontrol: remove obsolete kmemcg pinning tricks") and commit b2052564e66d ("mm: memcontrol: continue cache reclaim from offlined groups"). The new slab controller exposes the limitations in this scheme, so let's switch it to a more idiomatic reference counting model based on actual kernel pointers to the memcg: - The per-cpu stock holds a reference to the memcg its caching - User pages hold a reference for their page->mem_cgroup. Transparent huge pages will no longer acquire tail references in advance, we'll get them if needed during the split. - Kernel pages hold a reference for their page->mem_cgroup - mem_cgroup_try_charge(), if successful, will return one reference to be consumed by page->mem_cgroup during commit, or put during cancel - Pages allocated in the root cgroup will acquire and release css references for simplicity. css_get() and css_put() optimize that. - The current memcg_charge_slab() already hacked around the per-charge references; this change gets rid of that as well. Roman: I've reformatted commit references in the commit log to make checkpatch.pl happy. Signed-off-by: Johannes Weiner Signed-off-by: Roman Gushchin Acked-by: Roman Gushchin --- mm/memcontrol.c | 45 ++++++++++++++++++++++++++------------------- mm/slab.h | 2 -- 2 files changed, 26 insertions(+), 21 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6cbc1f4829fc..83805b48817d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2111,13 +2111,17 @@ static void drain_stock(struct memcg_stock_pcp *s= tock) { struct mem_cgroup *old =3D stock->cached; =20 + if (!old) + return; + if (stock->nr_pages) { page_counter_uncharge(&old->memory, stock->nr_pages); if (do_memsw_account()) page_counter_uncharge(&old->memsw, stock->nr_pages); - css_put_many(&old->css, stock->nr_pages); stock->nr_pages =3D 0; } + + css_put(&old->css); stock->cached =3D NULL; } =20 @@ -2153,6 +2157,7 @@ static void refill_stock(struct mem_cgroup *memcg, = unsigned int nr_pages) stock =3D this_cpu_ptr(&memcg_stock); if (stock->cached !=3D memcg) { /* reset if necessary */ drain_stock(stock); + css_get(&memcg->css); stock->cached =3D memcg; } stock->nr_pages +=3D nr_pages; @@ -2583,12 +2588,10 @@ static int try_charge(struct mem_cgroup *memcg, g= fp_t gfp_mask, page_counter_charge(&memcg->memory, nr_pages); if (do_memsw_account()) page_counter_charge(&memcg->memsw, nr_pages); - css_get_many(&memcg->css, nr_pages); =20 return 0; =20 done_restock: - css_get_many(&memcg->css, batch); if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); =20 @@ -2625,8 +2628,6 @@ static void cancel_charge(struct mem_cgroup *memcg,= unsigned int nr_pages) page_counter_uncharge(&memcg->memory, nr_pages); if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, nr_pages); - - css_put_many(&memcg->css, nr_pages); } =20 static void lock_page_lru(struct page *page, int *isolated) @@ -2977,6 +2978,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp= _t gfp, int order) if (!ret) { page->mem_cgroup =3D memcg; __SetPageKmemcg(page); + return 0; } } css_put(&memcg->css); @@ -2999,12 +3001,11 @@ void __memcg_kmem_uncharge_page(struct page *page= , int order) VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); __memcg_kmem_uncharge(memcg, nr_pages); page->mem_cgroup =3D NULL; + css_put(&memcg->css); =20 /* slab pages do not have PageKmemcg flag set */ if (PageKmemcg(page)) __ClearPageKmemcg(page); - - css_put_many(&memcg->css, nr_pages); } #endif /* CONFIG_MEMCG_KMEM */ =20 @@ -3016,15 +3017,18 @@ void __memcg_kmem_uncharge_page(struct page *page= , int order) */ void mem_cgroup_split_huge_fixup(struct page *head) { + struct mem_cgroup *memcg =3D head->mem_cgroup; int i; =20 if (mem_cgroup_disabled()) return; =20 - for (i =3D 1; i < HPAGE_PMD_NR; i++) - head[i].mem_cgroup =3D head->mem_cgroup; + for (i =3D 1; i < HPAGE_PMD_NR; i++) { + css_get(&memcg->css); + head[i].mem_cgroup =3D memcg; + } =20 - __mod_memcg_state(head->mem_cgroup, MEMCG_RSS_HUGE, -HPAGE_PMD_NR); + __mod_memcg_state(memcg, MEMCG_RSS_HUGE, -HPAGE_PMD_NR); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ =20 @@ -5443,7 +5447,9 @@ static int mem_cgroup_move_account(struct page *pag= e, * uncharging, charging, migration, or LRU putback. */ =20 - /* caller should have done css_get */ + css_get(&to->css); + css_put(&from->css); + page->mem_cgroup =3D to; =20 spin_unlock_irqrestore(&from->move_lock, flags); @@ -6537,8 +6543,10 @@ int mem_cgroup_try_charge(struct page *page, struc= t mm_struct *mm, memcg =3D get_mem_cgroup_from_mm(mm); =20 ret =3D try_charge(memcg, gfp_mask, nr_pages); - - css_put(&memcg->css); + if (ret) { + css_put(&memcg->css); + memcg =3D NULL; + } out: *memcgp =3D memcg; return ret; @@ -6634,6 +6642,8 @@ void mem_cgroup_cancel_charge(struct page *page, st= ruct mem_cgroup *memcg, return; =20 cancel_charge(memcg, nr_pages); + + css_put(&memcg->css); } =20 struct uncharge_gather { @@ -6675,9 +6685,6 @@ static void uncharge_batch(const struct uncharge_ga= ther *ug) __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, nr_pages); memcg_check_events(ug->memcg, ug->dummy_page); local_irq_restore(flags); - - if (!mem_cgroup_is_root(ug->memcg)) - css_put_many(&ug->memcg->css, nr_pages); } =20 static void uncharge_page(struct page *page, struct uncharge_gather *ug) @@ -6725,6 +6732,7 @@ static void uncharge_page(struct page *page, struct= uncharge_gather *ug) =20 ug->dummy_page =3D page; page->mem_cgroup =3D NULL; + css_put(&ug->memcg->css); } =20 static void uncharge_list(struct list_head *page_list) @@ -6831,8 +6839,8 @@ void mem_cgroup_migrate(struct page *oldpage, struc= t page *newpage) page_counter_charge(&memcg->memory, nr_pages); if (do_memsw_account()) page_counter_charge(&memcg->memsw, nr_pages); - css_get_many(&memcg->css, nr_pages); =20 + css_get(&memcg->css); commit_charge(newpage, memcg, false); =20 local_irq_save(flags); @@ -7071,8 +7079,7 @@ void mem_cgroup_swapout(struct page *page, swp_entr= y_t entry) -nr_entries); memcg_check_events(memcg, page); =20 - if (!mem_cgroup_is_root(memcg)) - css_put_many(&memcg->css, nr_entries); + css_put(&memcg->css); } =20 /** diff --git a/mm/slab.h b/mm/slab.h index 633eedb6bad1..8a574d9361c1 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -373,9 +373,7 @@ static __always_inline int memcg_charge_slab(struct p= age *page, lruvec =3D mem_cgroup_lruvec(memcg, page_pgdat(page)); mod_lruvec_state(lruvec, cache_vmstat_idx(s), nr_pages << PAGE_SHIFT); =20 - /* transer try_charge() page references to kmem_cache */ percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages); - css_put_many(&memcg->css, nr_pages); out: css_put(&memcg->css); return ret; --=20 2.25.3