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 23DAAC433E2 for ; Wed, 27 May 2020 22:34:32 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id B83AA20707 for ; Wed, 27 May 2020 22:34:31 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=fb.com header.i=@fb.com header.b="MYVLkCRK" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org B83AA20707 Authentication-Results: mail.kernel.org; dmarc=fail (p=reject 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 DC4C2800BE; Wed, 27 May 2020 18:34:18 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id C812E800C1; Wed, 27 May 2020 18:34:18 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 9C306800BE; Wed, 27 May 2020 18:34:18 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0072.hostedemail.com [216.40.44.72]) by kanga.kvack.org (Postfix) with ESMTP id 61432800BF for ; Wed, 27 May 2020 18:34:18 -0400 (EDT) Received: from smtpin30.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay03.hostedemail.com (Postfix) with ESMTP id 255768248076 for ; Wed, 27 May 2020 22:34:18 +0000 (UTC) X-FDA: 76863953796.30.low84_7cc6519790942 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin30.hostedemail.com (Postfix) with ESMTP id 0CB65180B3C83 for ; Wed, 27 May 2020 22:34:18 +0000 (UTC) X-HE-Tag: low84_7cc6519790942 X-Filterd-Recvd-Size: 13338 Received: from mx0a-00082601.pphosted.com (mx0a-00082601.pphosted.com [67.231.145.42]) by imf29.hostedemail.com (Postfix) with ESMTP for ; Wed, 27 May 2020 22:34:17 +0000 (UTC) Received: from pps.filterd (m0044012.ppops.net [127.0.0.1]) by mx0a-00082601.pphosted.com (8.16.0.42/8.16.0.42) with SMTP id 04RMF6nO017589 for ; Wed, 27 May 2020 15:34:16 -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=faF+7FLM4zfgJ684Xrz0yZYkzdADq7S20IJiu1ZZp1w=; b=MYVLkCRK1fFp4tpqZf//87cDY4/SaX1ENxzcwmmHlhVFRS1NqaRyf/1SJVYcLWxHpqx5 RI5IOkn1uZby6oxGKf6QXQv5LXBcqF50MgurRjCNAWDAgznvWUosAQUhVbTy3bNNmv+N V4T0UeJdqBKOvpqSnISVA43wxHvU5RP1UPo= Received: from mail.thefacebook.com ([163.114.132.120]) by mx0a-00082601.pphosted.com with ESMTP id 31999r4xhd-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NOT) for ; Wed, 27 May 2020 15:34:16 -0700 Received: from intmgw002.41.prn1.facebook.com (2620:10d:c085:208::f) by mail.thefacebook.com (2620:10d:c085:11d::5) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1979.3; Wed, 27 May 2020 15:34:15 -0700 Received: by devvm1291.vll0.facebook.com (Postfix, from userid 111017) id B25E31669026; Wed, 27 May 2020 15:34:07 -0700 (PDT) Smtp-Origin-Hostprefix: devvm From: Roman Gushchin Smtp-Origin-Hostname: devvm1291.vll0.facebook.com To: Andrew Morton , Christoph Lameter CC: Johannes Weiner , Michal Hocko , Shakeel Butt , , Vlastimil Babka , , , Roman Gushchin Smtp-Origin-Cluster: vll0c01 Subject: [PATCH v5 08/19] mm: memcg/slab: save obj_cgroup for non-root slab objects Date: Wed, 27 May 2020 15:33:53 -0700 Message-ID: <20200527223404.1008856-9-guro@fb.com> X-Mailer: git-send-email 2.24.1 In-Reply-To: <20200527223404.1008856-1-guro@fb.com> References: <20200527223404.1008856-1-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=2.50.10434:6.0.216,18.0.687 definitions=2020-05-27_03:2020-05-27,2020-05-27 signatures=0 X-Proofpoint-Spam-Details: rule=fb_default_notspam policy=fb_default score=0 impostorscore=0 spamscore=0 malwarescore=0 mlxlogscore=999 suspectscore=2 cotscore=-2147483648 bulkscore=0 phishscore=0 priorityscore=1501 adultscore=0 clxscore=1015 lowpriorityscore=0 mlxscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2004280000 definitions=main-2005270170 X-FB-Internal: deliver X-Rspamd-Queue-Id: 0CB65180B3C83 X-Spamd-Result: default: False [0.00 / 100.00] X-Rspamd-Server: rspam05 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: Store the obj_cgroup pointer in the corresponding place of page->obj_cgroups for each allocated non-root slab object. Make sure that each allocated object holds a reference to obj_cgroup. Objcg pointer is obtained from the memcg->objcg dereferencing in memcg_kmem_get_cache() and passed from pre_alloc_hook to post_alloc_hook. Then in case of successful allocation(s) it's getting stored in the page->obj_cgroups vector. The objcg obtaining part look a bit bulky now, but it will be simplified by next commits in the series. Signed-off-by: Roman Gushchin Reviewed-by: Vlastimil Babka --- include/linux/memcontrol.h | 3 +- mm/memcontrol.c | 14 +++++++-- mm/slab.c | 18 +++++++----- mm/slab.h | 60 ++++++++++++++++++++++++++++++++++---- mm/slub.c | 14 +++++---- 5 files changed, 88 insertions(+), 21 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ca2e71975581..98239fdf9fee 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1406,7 +1406,8 @@ static inline void memcg_set_shrinker_bit(struct me= m_cgroup *memcg, } #endif =20 -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); +struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep, + struct obj_cgroup **objcgp); void memcg_kmem_put_cache(struct kmem_cache *cachep); =20 #ifdef CONFIG_MEMCG_KMEM diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1c4d2462e867..a25bfc071416 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2916,7 +2916,8 @@ static inline bool memcg_kmem_bypass(void) * done with it, memcg_kmem_put_cache() must be called to release the * reference. */ -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) +struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep, + struct obj_cgroup **objcgp) { struct mem_cgroup *memcg; struct kmem_cache *memcg_cachep; @@ -2972,8 +2973,17 @@ struct kmem_cache *memcg_kmem_get_cache(struct kme= m_cache *cachep) */ if (unlikely(!memcg_cachep)) memcg_schedule_kmem_cache_create(memcg, cachep); - else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt)) + else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt)) { + struct obj_cgroup *objcg =3D rcu_dereference(memcg->objcg); + + if (!objcg || !obj_cgroup_tryget(objcg)) { + percpu_ref_put(&memcg_cachep->memcg_params.refcnt); + goto out_unlock; + } + + *objcgp =3D objcg; cachep =3D memcg_cachep; + } out_unlock: rcu_read_unlock(); return cachep; diff --git a/mm/slab.c b/mm/slab.c index 9350062ffc1a..02b4363930c1 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3222,9 +3222,10 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t f= lags, int nodeid, unsigned long save_flags; void *ptr; int slab_node =3D numa_mem_id(); + struct obj_cgroup *objcg =3D NULL; =20 flags &=3D gfp_allowed_mask; - cachep =3D slab_pre_alloc_hook(cachep, flags); + cachep =3D slab_pre_alloc_hook(cachep, &objcg, 1, flags); if (unlikely(!cachep)) return NULL; =20 @@ -3260,7 +3261,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t fl= ags, int nodeid, if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr) memset(ptr, 0, cachep->object_size); =20 - slab_post_alloc_hook(cachep, flags, 1, &ptr); + slab_post_alloc_hook(cachep, objcg, flags, 1, &ptr); return ptr; } =20 @@ -3301,9 +3302,10 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags,= unsigned long caller) { unsigned long save_flags; void *objp; + struct obj_cgroup *objcg =3D NULL; =20 flags &=3D gfp_allowed_mask; - cachep =3D slab_pre_alloc_hook(cachep, flags); + cachep =3D slab_pre_alloc_hook(cachep, &objcg, 1, flags); if (unlikely(!cachep)) return NULL; =20 @@ -3317,7 +3319,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, = unsigned long caller) if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp) memset(objp, 0, cachep->object_size); =20 - slab_post_alloc_hook(cachep, flags, 1, &objp); + slab_post_alloc_hook(cachep, objcg, flags, 1, &objp); return objp; } =20 @@ -3439,6 +3441,7 @@ void ___cache_free(struct kmem_cache *cachep, void = *objp, memset(objp, 0, cachep->object_size); kmemleak_free_recursive(objp, cachep->flags); objp =3D cache_free_debugcheck(cachep, objp, caller); + memcg_slab_free_hook(cachep, virt_to_head_page(objp), objp); =20 /* * Skip calling cache_free_alien() when the platform is not numa. @@ -3504,8 +3507,9 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp= _t flags, size_t size, void **p) { size_t i; + struct obj_cgroup *objcg =3D NULL; =20 - s =3D slab_pre_alloc_hook(s, flags); + s =3D slab_pre_alloc_hook(s, &objcg, size, flags); if (!s) return 0; =20 @@ -3528,13 +3532,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, g= fp_t flags, size_t size, for (i =3D 0; i < size; i++) memset(p[i], 0, s->object_size); =20 - slab_post_alloc_hook(s, flags, size, p); + slab_post_alloc_hook(s, objcg, flags, size, p); /* FIXME: Trace call missing. Christoph would like a bulk variant */ return size; error: local_irq_enable(); cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_); - slab_post_alloc_hook(s, flags, i, p); + slab_post_alloc_hook(s, objcg, flags, i, p); __kmem_cache_free_bulk(s, i, p); return 0; } diff --git a/mm/slab.h b/mm/slab.h index a1633ea15fbf..8bca0cb4b928 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -438,6 +438,41 @@ static inline void memcg_free_page_obj_cgroups(struc= t page *page) page->obj_cgroups =3D NULL; } =20 +static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, + struct obj_cgroup *objcg, + size_t size, void **p) +{ + struct page *page; + unsigned long off; + size_t i; + + for (i =3D 0; i < size; i++) { + if (likely(p[i])) { + page =3D virt_to_head_page(p[i]); + off =3D obj_to_index(s, page, p[i]); + obj_cgroup_get(objcg); + page_obj_cgroups(page)[off] =3D objcg; + } + } + obj_cgroup_put(objcg); + memcg_kmem_put_cache(s); +} + +static inline void memcg_slab_free_hook(struct kmem_cache *s, struct pag= e *page, + void *p) +{ + struct obj_cgroup *objcg; + unsigned int off; + + if (!memcg_kmem_enabled() || is_root_cache(s)) + return; + + off =3D obj_to_index(s, page, p); + objcg =3D page_obj_cgroups(page)[off]; + page_obj_cgroups(page)[off] =3D NULL; + obj_cgroup_put(objcg); +} + extern void slab_init_memcg_params(struct kmem_cache *); extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *me= mcg); =20 @@ -497,6 +532,17 @@ static inline void memcg_free_page_obj_cgroups(struc= t page *page) { } =20 +static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, + struct obj_cgroup *objcg, + size_t size, void **p) +{ +} + +static inline void memcg_slab_free_hook(struct kmem_cache *s, struct pag= e *page, + void *p) +{ +} + static inline void slab_init_memcg_params(struct kmem_cache *s) { } @@ -605,7 +651,8 @@ static inline size_t slab_ksize(const struct kmem_cac= he *s) } =20 static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *= s, - gfp_t flags) + struct obj_cgroup **objcgp, + size_t size, gfp_t flags) { flags &=3D gfp_allowed_mask; =20 @@ -619,13 +666,14 @@ static inline struct kmem_cache *slab_pre_alloc_hoo= k(struct kmem_cache *s, =20 if (memcg_kmem_enabled() && ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT))) - return memcg_kmem_get_cache(s); + return memcg_kmem_get_cache(s, objcgp); =20 return s; } =20 -static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flag= s, - size_t size, void **p) +static inline void slab_post_alloc_hook(struct kmem_cache *s, + struct obj_cgroup *objcg, + gfp_t flags, size_t size, void **p) { size_t i; =20 @@ -637,8 +685,8 @@ static inline void slab_post_alloc_hook(struct kmem_c= ache *s, gfp_t flags, s->flags, flags); } =20 - if (memcg_kmem_enabled()) - memcg_kmem_put_cache(s); + if (memcg_kmem_enabled() && !is_root_cache(s)) + memcg_slab_post_alloc_hook(s, objcg, size, p); } =20 #ifndef CONFIG_SLOB diff --git a/mm/slub.c b/mm/slub.c index 601c0fc3c83a..82c87444409f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2738,8 +2738,9 @@ static __always_inline void *slab_alloc_node(struct= kmem_cache *s, struct kmem_cache_cpu *c; struct page *page; unsigned long tid; + struct obj_cgroup *objcg =3D NULL; =20 - s =3D slab_pre_alloc_hook(s, gfpflags); + s =3D slab_pre_alloc_hook(s, &objcg, 1, gfpflags); if (!s) return NULL; redo: @@ -2815,7 +2816,7 @@ static __always_inline void *slab_alloc_node(struct= kmem_cache *s, if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(object, 0, s->object_size); =20 - slab_post_alloc_hook(s, gfpflags, 1, &object); + slab_post_alloc_hook(s, objcg, gfpflags, 1, &object); =20 return object; } @@ -3020,6 +3021,8 @@ static __always_inline void do_slab_free(struct kme= m_cache *s, void *tail_obj =3D tail ? : head; struct kmem_cache_cpu *c; unsigned long tid; + + memcg_slab_free_hook(s, page, head); redo: /* * Determine the currently cpus per cpu slab. @@ -3199,9 +3202,10 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gf= p_t flags, size_t size, { struct kmem_cache_cpu *c; int i; + struct obj_cgroup *objcg =3D NULL; =20 /* memcg and kmem_cache debug support */ - s =3D slab_pre_alloc_hook(s, flags); + s =3D slab_pre_alloc_hook(s, &objcg, size, flags); if (unlikely(!s)) return false; /* @@ -3255,11 +3259,11 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, g= fp_t flags, size_t size, } =20 /* memcg and kmem_cache debug support */ - slab_post_alloc_hook(s, flags, size, p); + slab_post_alloc_hook(s, objcg, flags, size, p); return i; error: local_irq_enable(); - slab_post_alloc_hook(s, flags, i, p); + slab_post_alloc_hook(s, objcg, flags, i, p); __kmem_cache_free_bulk(s, i, p); return 0; } --=20 2.25.4