From patchwork Thu Mar 30 19:17:54 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yosry Ahmed X-Patchwork-Id: 13194760 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id A5203C6FD1D for ; Thu, 30 Mar 2023 19:18:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232038AbjC3TSI (ORCPT ); Thu, 30 Mar 2023 15:18:08 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47680 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232014AbjC3TSH (ORCPT ); Thu, 30 Mar 2023 15:18:07 -0400 Received: from mail-yb1-xb4a.google.com (mail-yb1-xb4a.google.com [IPv6:2607:f8b0:4864:20::b4a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 59D80E38D for ; Thu, 30 Mar 2023 12:18:06 -0700 (PDT) Received: by mail-yb1-xb4a.google.com with SMTP id 204-20020a250fd5000000b00b6d6655dc35so19626569ybp.6 for ; Thu, 30 Mar 2023 12:18:06 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1680203885; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=ECd9n7cK9XN/T+IJ39MyPXAm65DzgHuyZCFnDGQgZIE=; b=tY0E3oybgVZIuKKOOKBykm8/TKbf2scexLJVT3DkzJcaMo8pgAVQKd31VkYqY1QVPJ mHo+yh2Z2e/UWhIAS6NyKjgzsMFfM3Q7bRmRT9xetX5hDAZEg0lz49jvXxYxOEOA0GHz 2iOR7gvTKjdYv9QT9UofKbbkFs9vSWVQ0TKS3904q473sNNcjSfvya1m1B2ab+CL/f+M 4qtYTT2pypw3Co5Bobg3nKNc5an7wdNYyXFt6rny9eUWrmoVflUhZJQGBV9r+u9oNXbf thlMA7X4kUIdycQp/zBF4S4OoaK6pqFmZjXA4rakf85jUKtTz9rXXIDv36itoKwLwzmv vt/Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1680203885; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=ECd9n7cK9XN/T+IJ39MyPXAm65DzgHuyZCFnDGQgZIE=; b=BsKAasW/HkjCAJ93cQ/1FYmBi8Iolsr+mkh04kT9sQXPz+SsiCKljpn+uLpnkf6u4B QFl4a6L4F+m/EksMeHX5vIeAfQnL7+LJycrlaICizumbZYvMhnFtKAV43Ttyfhq3FOP/ 6EzYX/fF+N/4wFWbjXCVzbzLWcfqg1LzcvWlDMLl9olIesPeAHi9BCt7kqmiFJpkIU9s RtSYBVYLwQS1POhB5ydlP+o35SeLc5GAggBoHJLfkPH7lgknSzimiO4/DCyWi6sAJaWC yzryG9nfG16z+yYTnx8jy4iG/y78qqs2mMRCeVmjC1ItFnjEiMh0cBu9GBOFaL/yqcbT 8ihg== X-Gm-Message-State: AAQBX9fuAOnBomuex18BehJA34AqYGI8Qc3qBI2JVp2qLaPY8HLadSdO aAzgjGgWzS73s+W7NPdhPHaDy8o8mBtPj95t X-Google-Smtp-Source: AKy350aEWgmUGoq47vtgVPSLObUE1OHXFIc1JYGvZjZHSdRsfuGe4z8jTEoHLVbNJzm7tfhcDcAxLa1st977h/QM X-Received: from yosry.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:2327]) (user=yosryahmed job=sendgmr) by 2002:a25:d1d8:0:b0:b6d:fc53:c5c0 with SMTP id i207-20020a25d1d8000000b00b6dfc53c5c0mr4650822ybg.1.1680203885608; Thu, 30 Mar 2023 12:18:05 -0700 (PDT) Date: Thu, 30 Mar 2023 19:17:54 +0000 In-Reply-To: <20230330191801.1967435-1-yosryahmed@google.com> Mime-Version: 1.0 References: <20230330191801.1967435-1-yosryahmed@google.com> X-Mailer: git-send-email 2.40.0.348.gf938b09366-goog Message-ID: <20230330191801.1967435-2-yosryahmed@google.com> Subject: [PATCH v3 1/8] cgroup: rename cgroup_rstat_flush_"irqsafe" to "atomic" From: Yosry Ahmed To: Tejun Heo , Josef Bacik , Jens Axboe , Zefan Li , Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Andrew Morton , " =?utf-8?q?Michal_Koutn=C3=BD?= " Cc: Vasily Averin , cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, Yosry Ahmed Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org cgroup_rstat_flush_irqsafe() can be a confusing name. It may read as "irqs are disabled throughout", which is what the current implementation does (currently under discussion [1]), but is not the intention. The intention is that this function is safe to call from atomic contexts. Name it as such. Suggested-by: Johannes Weiner Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner --- include/linux/cgroup.h | 2 +- kernel/cgroup/rstat.c | 4 ++-- mm/memcontrol.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3410aecffdb4..885f5395fcd0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -692,7 +692,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); -void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); +void cgroup_rstat_flush_atomic(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 831f1f472bb8..d3252b0416b6 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -241,12 +241,12 @@ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) } /** - * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush() + * cgroup_rstat_flush_atomic- atomic version of cgroup_rstat_flush() * @cgrp: target cgroup * * This function can be called from any context. */ -void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp) +void cgroup_rstat_flush_atomic(struct cgroup *cgrp) { unsigned long flags; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5abffe6f8389..0205e58ea430 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -642,7 +642,7 @@ static void __mem_cgroup_flush_stats(void) return; flush_next_time = jiffies_64 + 2*FLUSH_TIME; - cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); + cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); spin_unlock_irqrestore(&stats_flush_lock, flag); } From patchwork Thu Mar 30 19:17:55 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yosry Ahmed X-Patchwork-Id: 13194761 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2E63CC77B70 for ; Thu, 30 Mar 2023 19:18:12 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232022AbjC3TSK (ORCPT ); Thu, 30 Mar 2023 15:18:10 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47756 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232046AbjC3TSJ (ORCPT ); Thu, 30 Mar 2023 15:18:09 -0400 Received: from mail-pl1-x649.google.com (mail-pl1-x649.google.com [IPv6:2607:f8b0:4864:20::649]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id E3B00EB5A for ; Thu, 30 Mar 2023 12:18:07 -0700 (PDT) Received: by mail-pl1-x649.google.com with SMTP id a9-20020a170902b58900b0019e2eafafddso11569404pls.7 for ; Thu, 30 Mar 2023 12:18:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1680203887; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=LXlZsArwPDY7OuU2BxzeoXG1UXSoglEAfUQ5EzzMXG4=; b=QmYQM+j13cdbjBiZy3Y+dzkJUgGOVHTdr9lvDbSE859fYaJtq+8zmH02RDaKbdpvap CqejHKuoW/4IBz5mIHOf6Y8AHa6GMb/hCZ7zMABh1AePaLkgpcjAyzU7xGg8rQCDHyuT xd/GhSCAHuv9H/zwirCUR2wyGX+B6mkWwB9WVRwD19bK9qyHzg7+GCXy42vkNiRXXZdr kN4hOyhVE2VLeXDBEBRHB8fSA0RE0BkgU+jq32E4Jq+3xIhGwrpX/kGZ92PdxYBPFxyB 8OgXFYA1yB1rgGnRYxUqB9CL2/ZWFsevIT5f1UxupCOTzAHu4BNZEW/BqlkhNKD16qxi CoQQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1680203887; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=LXlZsArwPDY7OuU2BxzeoXG1UXSoglEAfUQ5EzzMXG4=; b=IZDmQ4N/IhD4XYIAQSXOSMg9zwj9E9G3P3PEF8FZWwUevzREoG7KeGcYyXFyJk7k7y RcsNQRtTHftsumb5XkouT/UZVlrpyZE3RTooW6mxLxUOgrFx7o1Lc+PONc1iRXgiAdb3 8mP+J2qZapEAV4LQlr5q2msDxtyIZZqWuohHVwav1H3+3SHX+TIazr6gC/cWyHOvxMtA 4BU+voEgEUdBss7OlbQjlvmVAyPD/3AVOQ2iaEskfe+SvoQ2NxjykvX047x1IKIHbWNk nSkltJm5IyPYUGU3e2f6G/EqFziGYkPau7JYcTMumR6mtUtCbS3xBIyZs5Ek0DTwFARU ooCg== X-Gm-Message-State: AAQBX9chbyFoS189M1GHGXf6PvcOCyE5t/OJpF2AOQb1yh52zUWCc4v6 yFQOZvXHpXBL0cWfOwwHjySwihZ57RkBhXcM X-Google-Smtp-Source: AKy350acDpkb2oKWRJtDPrvhJr6G7w3aWGLRFehCl/mgbnA6nqxhni7pGTt+2Eb5S7HVMulqi96jSmdvt00VgGJt X-Received: from yosry.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:2327]) (user=yosryahmed job=sendgmr) by 2002:a17:90a:ec11:b0:237:9cbe:22ad with SMTP id l17-20020a17090aec1100b002379cbe22admr7641616pjy.5.1680203887352; Thu, 30 Mar 2023 12:18:07 -0700 (PDT) Date: Thu, 30 Mar 2023 19:17:55 +0000 In-Reply-To: <20230330191801.1967435-1-yosryahmed@google.com> Mime-Version: 1.0 References: <20230330191801.1967435-1-yosryahmed@google.com> X-Mailer: git-send-email 2.40.0.348.gf938b09366-goog Message-ID: <20230330191801.1967435-3-yosryahmed@google.com> Subject: [PATCH v3 2/8] memcg: rename mem_cgroup_flush_stats_"delayed" to "ratelimited" From: Yosry Ahmed To: Tejun Heo , Josef Bacik , Jens Axboe , Zefan Li , Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Andrew Morton , " =?utf-8?q?Michal_Koutn=C3=BD?= " Cc: Vasily Averin , cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, Yosry Ahmed , Michal Hocko Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org mem_cgroup_flush_stats_delayed() suggests his is using a delayed_work, but this is actually sometimes flushing directly from the callsite. What it's doing is ratelimited calls. A better name would be mem_cgroup_flush_stats_ratelimited(). Suggested-by: Johannes Weiner Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko --- include/linux/memcontrol.h | 4 ++-- mm/memcontrol.c | 2 +- mm/workingset.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b6eda2ab205d..ac3f3b3a45e2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1037,7 +1037,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_delayed(void); +void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1535,7 +1535,7 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_delayed(void) +static inline void mem_cgroup_flush_stats_ratelimited(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0205e58ea430..c3b6aae78901 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -653,7 +653,7 @@ void mem_cgroup_flush_stats(void) __mem_cgroup_flush_stats(); } -void mem_cgroup_flush_stats_delayed(void) +void mem_cgroup_flush_stats_ratelimited(void) { if (time_after64(jiffies_64, flush_next_time)) mem_cgroup_flush_stats(); diff --git a/mm/workingset.c b/mm/workingset.c index 00c6f4d9d9be..af862c6738c3 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -462,7 +462,7 @@ void workingset_refault(struct folio *folio, void *shadow) mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - mem_cgroup_flush_stats_delayed(); + mem_cgroup_flush_stats_ratelimited(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if From patchwork Thu Mar 30 19:17:56 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yosry Ahmed X-Patchwork-Id: 13194762 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7CC22C6FD1D for ; Thu, 30 Mar 2023 19:18:24 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232101AbjC3TSU (ORCPT ); Thu, 30 Mar 2023 15:18:20 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47990 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232064AbjC3TSN (ORCPT ); Thu, 30 Mar 2023 15:18:13 -0400 Received: from mail-yw1-x114a.google.com (mail-yw1-x114a.google.com [IPv6:2607:f8b0:4864:20::114a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 1529EF77D for ; Thu, 30 Mar 2023 12:18:10 -0700 (PDT) Received: by mail-yw1-x114a.google.com with SMTP id 00721157ae682-54196bfcd5fso194620127b3.4 for ; Thu, 30 Mar 2023 12:18:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1680203889; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=aVus0GFA9nzxOZ5lNIH1Nx8kHcLEa/aLkX98gl9HKOI=; b=Rb2fsB8aWLuAh/6UfhLacuvSldBOfVahXww4db+vgAZH6d8hHK5iS/Pb3yBuHu8zXu 8OHs3K+JgNd5BWKL8HmUqSNmeBMWOUfM93BgScQIJGiFyUTuS/OhqqsgB8B/zESgECWW id0La031n/vRfUHiqMH5ptV4ZUHLtuC1awDopegwUjfP8gYPSzkD9GboR6Sv+BT5F0il 4cP0p/kpaTUv9ECKBi7X6nDyHboM9b8Z+lLZ6iyDmkLsMIt+cWstg1DQo4e/ZnrIN56I iRBi8QgWvfbGxJTMXxv2zZuY7CwzGwzqEOEYe4XvyV9MRzo4MibTgBPKLkzWKa272DY9 IgGw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1680203889; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=aVus0GFA9nzxOZ5lNIH1Nx8kHcLEa/aLkX98gl9HKOI=; b=XJ6UzuSXHuxpSmr0+tCe7KDFe0ib5If8t8nO0APJ6VCepO+EmVIrEPWusCRzCnOKqF sI32XXCkHbnf+LOwtTudpPo/SaZLC4dSn+UXWww3PJ6eKX2YzsSnYVuqgmcisZ4c1lLp aY80inbe2i8/IZ+Tf7+tcqluPIp56+rHBzKmYMjUpP0SYi7WHT6mIC1Lx8Uavyw1iYq1 F0I8LPmzSj7iMUVw9jrXu/dFppffAtNys5XZOspdhBg6iG7NxQTV/wC3mk94a29rYmRA nFVUYUY+FKK/4ib+E8VD3kNkz0MKifeHXaWcFS6C1M6YhOmL7Mnvr7c+IoU+83f+ZWYA k9ZQ== X-Gm-Message-State: AAQBX9dvttPOJTMbS+CXK3aKblqEPeV6Ky7pC2fgw/NHyR+MeP+62x5I VlM+0txO08uPpJS6aocjLR+OYzrMt2E4fbA/ X-Google-Smtp-Source: AKy350az4CClmAfjDaxG6/AcT2u/aalMEwRTuNYj9qh25Mudi/3feszrufxHB4k9is1ESXC81UQXzGZVI+EC5ExV X-Received: from yosry.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:2327]) (user=yosryahmed job=sendgmr) by 2002:a05:6902:10c3:b0:b79:4826:e8e3 with SMTP id w3-20020a05690210c300b00b794826e8e3mr10930499ybu.1.1680203889210; Thu, 30 Mar 2023 12:18:09 -0700 (PDT) Date: Thu, 30 Mar 2023 19:17:56 +0000 In-Reply-To: <20230330191801.1967435-1-yosryahmed@google.com> Mime-Version: 1.0 References: <20230330191801.1967435-1-yosryahmed@google.com> X-Mailer: git-send-email 2.40.0.348.gf938b09366-goog Message-ID: <20230330191801.1967435-4-yosryahmed@google.com> Subject: [PATCH v3 3/8] memcg: do not flush stats in irq context From: Yosry Ahmed To: Tejun Heo , Josef Bacik , Jens Axboe , Zefan Li , Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Andrew Morton , " =?utf-8?q?Michal_Koutn=C3=BD?= " Cc: Vasily Averin , cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, Yosry Ahmed , Michal Hocko Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Currently, the only context in which we can invoke an rstat flush from irq context is through mem_cgroup_usage() on the root memcg when called from memcg_check_events(). An rstat flush is an expensive operation that should not be done in irq context, so do not flush stats and use the stale stats in this case. Arguably, usage threshold events are not reliable on the root memcg anyway since its usage is ill-defined. Suggested-by: Johannes Weiner Suggested-by: Shakeel Butt Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko --- mm/memcontrol.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c3b6aae78901..ff39f78f962e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3669,7 +3669,21 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) unsigned long val; if (mem_cgroup_is_root(memcg)) { - mem_cgroup_flush_stats(); + /* + * We can reach here from irq context through: + * uncharge_batch() + * |--memcg_check_events() + * |--mem_cgroup_threshold() + * |--__mem_cgroup_threshold() + * |--mem_cgroup_usage + * + * rstat flushing is an expensive operation that should not be + * done from irq context; use stale stats in this case. + * Arguably, usage threshold events are not reliable on the root + * memcg anyway since its usage is ill-defined. + */ + if (in_task()) + mem_cgroup_flush_stats(); val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) From patchwork Thu Mar 30 19:17:57 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yosry Ahmed X-Patchwork-Id: 13194763 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 62172C77B6F for ; Thu, 30 Mar 2023 19:18:25 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232134AbjC3TSW (ORCPT ); Thu, 30 Mar 2023 15:18:22 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47984 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231628AbjC3TST (ORCPT ); Thu, 30 Mar 2023 15:18:19 -0400 Received: from mail-pl1-x649.google.com (mail-pl1-x649.google.com [IPv6:2607:f8b0:4864:20::649]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 77B95FF39 for ; Thu, 30 Mar 2023 12:18:11 -0700 (PDT) Received: by mail-pl1-x649.google.com with SMTP id x4-20020a170902ec8400b001a1a5f6f272so11621307plg.1 for ; Thu, 30 Mar 2023 12:18:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1680203891; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=4nnUf1Bi8zb8HMhH9DtFsVEWdtAjMz82Sf34ZimV0fg=; b=X2RFp1pZWOYnRsIh7IWjsVsM+KEFc9WJSHxF/6WWA0h+C4aKaj5fmmxIF9JIbSgACd wSFJlPVZHSShfit9sIv2gEMkHiLDYI1aj0ZjNxN+KDFEUuJ5hrS0dAiMoZtgG8tE01Qw Z6IuI1YwDe0K3jJKl09PQ+88WTXCXmLj3mXjZyc3NpqNvz62t2kYidmfKl22OQzA3sQQ EAjXhE1Jh+vHizPfZUZ3LQ+IzSkqjVL6en02vxZp22lS6vBDlsf8gGPBHsHSCXP5Ac15 JluiS/D70cGu14FmTesFiFf/4cN9gJ7flhGTivB535PauxJnWfGkMyHN0wJ36oB1Mtk7 YlVQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1680203891; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=4nnUf1Bi8zb8HMhH9DtFsVEWdtAjMz82Sf34ZimV0fg=; b=kZ/fanNMMQ5JOy8ZF6diIt6UOi9bHa8k3aGaGkASrwTUDQvfnjtb7YKo8fLPgdDTLB j1U0JgnJhVw/p+/M0bviELTkJ6IkG68RBD5Sjkqpx9G63JO6QE8kS0lF6FmNWuJ63Euc v6OuqQA5Ul5yNiVnU/Ab7TMl8anCbmOHsf5CK/uZ/NFFzrCG1ak6Ex+6hG+incm38P7v AZYRDJgS1fcUZWNWGoVLJImDEh84M8Hr0aoWLJLnUiwZSPM9fcr5nb6dye8tiJI15vnM szFKFNgTPSZLLPsJpEHP6Ny9UfOWrOZLaTwRgaybq+b2Mg9nP9ROjnBzHfBtQEyFW/WH IHJQ== X-Gm-Message-State: AAQBX9dHtm0L6N+OwhdhDQVQepg4gW+BSR6kuZuNWCZ+EzOIRut5ZZ8w 1jfVRjnSgdv85LcCcooBc546W+/wQxqGsrVF X-Google-Smtp-Source: AKy350ZmAXD9xXrcG5sJYCYyMiAcFBYVD5KvS63XKanxHd2/adSILGt8yBb9ajmjtAKFUTblNAGcd8BbimVIOaMZ X-Received: from yosry.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:2327]) (user=yosryahmed job=sendgmr) by 2002:a05:6a00:2286:b0:627:e6d5:ba2d with SMTP id f6-20020a056a00228600b00627e6d5ba2dmr13290706pfe.6.1680203890966; Thu, 30 Mar 2023 12:18:10 -0700 (PDT) Date: Thu, 30 Mar 2023 19:17:57 +0000 In-Reply-To: <20230330191801.1967435-1-yosryahmed@google.com> Mime-Version: 1.0 References: <20230330191801.1967435-1-yosryahmed@google.com> X-Mailer: git-send-email 2.40.0.348.gf938b09366-goog Message-ID: <20230330191801.1967435-5-yosryahmed@google.com> Subject: [PATCH v3 4/8] memcg: replace stats_flush_lock with an atomic From: Yosry Ahmed To: Tejun Heo , Josef Bacik , Jens Axboe , Zefan Li , Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Andrew Morton , " =?utf-8?q?Michal_Koutn=C3=BD?= " Cc: Vasily Averin , cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, Yosry Ahmed , Michal Hocko Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org As Johannes notes in [1], stats_flush_lock is currently used to: (a) Protect updated to stats_flush_threshold. (b) Protect updates to flush_next_time. (c) Serializes calls to cgroup_rstat_flush() based on those ratelimits. However: 1. stats_flush_threshold is already an atomic 2. flush_next_time is not atomic. The writer is locked, but the reader is lockless. If the reader races with a flush, you could see this: if (time_after(jiffies, flush_next_time)) spin_trylock() flush_next_time = now + delay flush() spin_unlock() spin_trylock() flush_next_time = now + delay flush() spin_unlock() which means we already can get flushes at a higher frequency than FLUSH_TIME during races. But it isn't really a problem. The reader could also see garbled partial updates if the compiler decides to split the write, so it needs at least READ_ONCE and WRITE_ONCE protection. 3. Serializing cgroup_rstat_flush() calls against the ratelimit factors is currently broken because of the race in 2. But the race is actually harmless, all we might get is the occasional earlier flush. If there is no delta, the flush won't do much. And if there is, the flush is justified. So the lock can be removed all together. However, the lock also served the purpose of preventing a thundering herd problem for concurrent flushers, see [2]. Use an atomic instead to serve the purpose of unifying concurrent flushers. [1]https://lore.kernel.org/lkml/20230323172732.GE739026@cmpxchg.org/ [2]https://lore.kernel.org/lkml/20210716212137.1391164-2-shakeelb@google.com/ Signed-off-by: Yosry Ahmed Acked-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Michal Hocko --- mm/memcontrol.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ff39f78f962e..65750f8b8259 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -585,8 +585,8 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) */ static void flush_memcg_stats_dwork(struct work_struct *w); static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); -static DEFINE_SPINLOCK(stats_flush_lock); static DEFINE_PER_CPU(unsigned int, stats_updates); +static atomic_t stats_flush_ongoing = ATOMIC_INIT(0); static atomic_t stats_flush_threshold = ATOMIC_INIT(0); static u64 flush_next_time; @@ -636,15 +636,19 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) static void __mem_cgroup_flush_stats(void) { - unsigned long flag; - - if (!spin_trylock_irqsave(&stats_flush_lock, flag)) + /* + * We always flush the entire tree, so concurrent flushers can just + * skip. This avoids a thundering herd problem on the rstat global lock + * from memcg flushers (e.g. reclaim, refault, etc). + */ + if (atomic_read(&stats_flush_ongoing) || + atomic_xchg(&stats_flush_ongoing, 1)) return; - flush_next_time = jiffies_64 + 2*FLUSH_TIME; + WRITE_ONCE(flush_next_time, jiffies_64 + 2*FLUSH_TIME); cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); - spin_unlock_irqrestore(&stats_flush_lock, flag); + atomic_set(&stats_flush_ongoing, 0); } void mem_cgroup_flush_stats(void) @@ -655,7 +659,7 @@ void mem_cgroup_flush_stats(void) void mem_cgroup_flush_stats_ratelimited(void) { - if (time_after64(jiffies_64, flush_next_time)) + if (time_after64(jiffies_64, READ_ONCE(flush_next_time))) mem_cgroup_flush_stats(); } From patchwork Thu Mar 30 19:17:58 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yosry Ahmed X-Patchwork-Id: 13194764 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5DE72C6FD1D for ; Thu, 30 Mar 2023 19:18:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232176AbjC3TS0 (ORCPT ); Thu, 30 Mar 2023 15:18:26 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:48616 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232108AbjC3TSU (ORCPT ); Thu, 30 Mar 2023 15:18:20 -0400 Received: from mail-pl1-x649.google.com (mail-pl1-x649.google.com [IPv6:2607:f8b0:4864:20::649]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 218F1EC58 for ; Thu, 30 Mar 2023 12:18:13 -0700 (PDT) Received: by mail-pl1-x649.google.com with SMTP id e5-20020a17090301c500b001a1aa687e4bso11699704plh.17 for ; Thu, 30 Mar 2023 12:18:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1680203893; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=4K13XuzFhLt0ZIgNSFirN/NTpinGGuhSsjDOtu88ZFQ=; b=nHw0e79hZFaw3nf4LyIXmmhTYfA1FbBbf2dimkl5At5Psg3CjvNgu6oG6xad78uoN/ S2j2UYV8EipalJrwt2zNvbI6g73PyAp4x9X0MELejGCTtg493QkbzRVplqF8mo+gd+ZT v2g6y/Uq/dc/IcDqjVuG6qTAXC3lltOSedgQENPqcdYx34VNoyr/anJbPmkUtw6k7KGZ kbHnvz3Vd5/Dm/bxM/NXhZiy/XES3eJpoxargQYJd3pDWMStv8K0/vXl6hkWv2MnHLzC WyPbqSXfAwOToFWCyu1C3jP4ndGUE9RCrti/toBLaYuvsaopTHlhvDYChxTi2n0kxppd O1Nw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1680203893; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=4K13XuzFhLt0ZIgNSFirN/NTpinGGuhSsjDOtu88ZFQ=; b=Rey3PJaIr11amC22AuTfNR3cRzNecw4tOR3WaSGU2gi/ldL+ZMiJpafWzTCwz31TbC NeuBIkwLNzFh9obxVHdVRjt1gyrXkJ2PbsJJws7CZpc+aq2S17ATV9L+P/Ak2rKefRdx A2UAQwgTFUp+PQfoTn/sbM2R2bKA0Q2lBHuFv1Gpdj5lcfLdqSvn4IRmiHgKu+BGdkn0 rLSY/Cv2vBO4K5TtWGjhmcaqyJWHMEuxf0IwIWVKvkrUVJqKuc0etJNAYe+cVvQANp06 VYGO0aprFDFBuAEja/oF3enjtH8RPpn6Iy2RWbh4KRBL2YMl04iJQAGNXStw4E/PAejX qztw== X-Gm-Message-State: AAQBX9d05Asyvgs8H7LU0xKun4mBULTYurT2OKqueHTHfMDorVUYnBPV pT4uGpRN9tqtJWfDWqbMkrW/smAg2roGJp4G X-Google-Smtp-Source: AKy350YSzgQBtWYiTKsbkJ1oQdlD62/Xn6W7mjRdu2TN+RxVPyaHwSjuEqzrgKulPryFVMSvh1+rAuiwX+ctKyIl X-Received: from yosry.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:2327]) (user=yosryahmed job=sendgmr) by 2002:a63:1914:0:b0:50b:de95:af77 with SMTP id z20-20020a631914000000b0050bde95af77mr2125406pgl.1.1680203892860; Thu, 30 Mar 2023 12:18:12 -0700 (PDT) Date: Thu, 30 Mar 2023 19:17:58 +0000 In-Reply-To: <20230330191801.1967435-1-yosryahmed@google.com> Mime-Version: 1.0 References: <20230330191801.1967435-1-yosryahmed@google.com> X-Mailer: git-send-email 2.40.0.348.gf938b09366-goog Message-ID: <20230330191801.1967435-6-yosryahmed@google.com> Subject: [PATCH v3 5/8] memcg: sleep during flushing stats in safe contexts From: Yosry Ahmed To: Tejun Heo , Josef Bacik , Jens Axboe , Zefan Li , Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Andrew Morton , " =?utf-8?q?Michal_Koutn=C3=BD?= " Cc: Vasily Averin , cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, Yosry Ahmed , Michal Hocko Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Currently, all contexts that flush memcg stats do so with sleeping not allowed. Some of these contexts are perfectly safe to sleep in, such as reading cgroup files from userspace or the background periodic flusher. Flushing is an expensive operation that scales with the number of cpus and the number of cgroups in the system, so avoid doing it atomically where possible. Refactor the code to make mem_cgroup_flush_stats() non-atomic (aka sleepable), and provide a separate atomic version. The atomic version is used in reclaim, refault, writeback, and in mem_cgroup_usage(). All other code paths are left to use the non-atomic version. This includes callbacks for userspace reads and the periodic flusher. Since refault is the only caller of mem_cgroup_flush_stats_ratelimited(), change it to mem_cgroup_flush_stats_atomic_ratelimited(). Reclaim and refault code paths are modified to do non-atomic flushing in separate later patches -- so it will eventually be changed back to mem_cgroup_flush_stats_ratelimited(). Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Michal Hocko Acked-by: Johannes Weiner Acked-by: Johannes Weiner --- include/linux/memcontrol.h | 9 ++++++-- mm/memcontrol.c | 45 ++++++++++++++++++++++++++++++-------- mm/vmscan.c | 2 +- mm/workingset.c | 2 +- 4 files changed, 45 insertions(+), 13 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ac3f3b3a45e2..b424ba3ebd09 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1037,7 +1037,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_ratelimited(void); +void mem_cgroup_flush_stats_atomic(void); +void mem_cgroup_flush_stats_atomic_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1535,7 +1536,11 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_ratelimited(void) +static inline void mem_cgroup_flush_stats_atomic(void) +{ +} + +static inline void mem_cgroup_flush_stats_atomic_ratelimited(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 65750f8b8259..a2ce3aa10d94 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -634,7 +634,7 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) } } -static void __mem_cgroup_flush_stats(void) +static void do_flush_stats(bool atomic) { /* * We always flush the entire tree, so concurrent flushers can just @@ -646,26 +646,46 @@ static void __mem_cgroup_flush_stats(void) return; WRITE_ONCE(flush_next_time, jiffies_64 + 2*FLUSH_TIME); - cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup); + + if (atomic) + cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup); + else + cgroup_rstat_flush(root_mem_cgroup->css.cgroup); + atomic_set(&stats_flush_threshold, 0); atomic_set(&stats_flush_ongoing, 0); } +static bool should_flush_stats(void) +{ + return atomic_read(&stats_flush_threshold) > num_online_cpus(); +} + void mem_cgroup_flush_stats(void) { - if (atomic_read(&stats_flush_threshold) > num_online_cpus()) - __mem_cgroup_flush_stats(); + if (should_flush_stats()) + do_flush_stats(false); } -void mem_cgroup_flush_stats_ratelimited(void) +void mem_cgroup_flush_stats_atomic(void) +{ + if (should_flush_stats()) + do_flush_stats(true); +} + +void mem_cgroup_flush_stats_atomic_ratelimited(void) { if (time_after64(jiffies_64, READ_ONCE(flush_next_time))) - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_atomic(); } static void flush_memcg_stats_dwork(struct work_struct *w) { - __mem_cgroup_flush_stats(); + /* + * Always flush here so that flushing in latency-sensitive paths is + * as cheap as possible. + */ + do_flush_stats(false); queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME); } @@ -3685,9 +3705,12 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) * done from irq context; use stale stats in this case. * Arguably, usage threshold events are not reliable on the root * memcg anyway since its usage is ill-defined. + * + * Additionally, other call paths through memcg_check_events() + * disable irqs, so make sure we are flushing stats atomically. */ if (in_task()) - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_atomic(); val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) @@ -4610,7 +4633,11 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - mem_cgroup_flush_stats(); + /* + * wb_writeback() takes a spinlock and calls + * wb_over_bg_thresh()->mem_cgroup_wb_stats(). Do not sleep. + */ + mem_cgroup_flush_stats_atomic(); *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); diff --git a/mm/vmscan.c b/mm/vmscan.c index 9c1c5e8b24b8..a9511ccb936f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2845,7 +2845,7 @@ static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) * Flush the memory cgroup stats, so that we read accurate per-memcg * lruvec stats for heuristics. */ - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_atomic(); /* * Determine the scan balance between anon and file LRUs. diff --git a/mm/workingset.c b/mm/workingset.c index af862c6738c3..dab0c362b9e3 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -462,7 +462,7 @@ void workingset_refault(struct folio *folio, void *shadow) mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - mem_cgroup_flush_stats_ratelimited(); + mem_cgroup_flush_stats_atomic_ratelimited(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if From patchwork Thu Mar 30 19:17:59 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yosry Ahmed X-Patchwork-Id: 13194765 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8CA94C77B62 for ; Thu, 30 Mar 2023 19:18:29 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232191AbjC3TS1 (ORCPT ); Thu, 30 Mar 2023 15:18:27 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47998 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231626AbjC3TSV (ORCPT ); Thu, 30 Mar 2023 15:18:21 -0400 Received: from mail-pf1-x44a.google.com (mail-pf1-x44a.google.com [IPv6:2607:f8b0:4864:20::44a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 5745D10245 for ; Thu, 30 Mar 2023 12:18:15 -0700 (PDT) Received: by mail-pf1-x44a.google.com with SMTP id o14-20020a62f90e000000b0062d87d997eeso6042469pfh.18 for ; Thu, 30 Mar 2023 12:18:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1680203895; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=zjUVlGzaNGh8M5BDppplh7Z2E1z5drNgoNePIuD8ZZo=; b=EVT1tk0hlY3K/RTYvcQHMKPpwQPVXOnpdSgQM68BKQtZmfmON2APgqvMOvMMFyRoss Dmd2H4VUZwWGIfs6kzYLS/yY0LBdZ4oH1VkvSRWDGcSOJqUREz+4yAA6vO0jGdRbUllx xh0AWez/MaDxogJM7rwIORKSy2FNGdepATzkqraYhiO3RCB8HnWcqe3zSlq35IxkzxtC FV1PJ6neoxu760xZAlTGk8nkupYvKz5UcVjEtp57Ggrbl9Lds+WScYdzag5BG/1gW5Yv DUw8gcccaLuVJ49JXssrnmfFrYddyvv++tF0t2hffuUaTqszDGsJ7ZLQoChqmjJGkrqP YfTQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1680203895; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=zjUVlGzaNGh8M5BDppplh7Z2E1z5drNgoNePIuD8ZZo=; b=q+7n8PWMghCnn/AHPCSJmLZDpHepquPm7hpzGDwAlYUYAZKP2rN1efa9ZzugQ3TCoi Zu05q/n7ri2yQT8bYrdP+dJcCQof/mGXg1lkd53f5Qk27mKhZ3dM8U/Cu2C7ReEU1CEA AZI8ftliKk2jSAcKwXzY0A4WAgviqJuKMucEOlKC16VxnGT5RP+wzUDji9JwPsfgqH+z z0oNaWl2LKXnkJLHgecbIQFBfRv05x5InR3SRBgkvl2cvlgGk/x4GOxjmTsvgsEenowV o+a2PPQlNNT8lrV6h9ffMU/2xQbCZfnQRCCzmSAE7/3M/eUEsoUpegbTkVfaDzJ8i+x2 TUrg== X-Gm-Message-State: AAQBX9e8idJ0HxmRu7egGOBVNPsLAkNsWq0o0A1BGtPAV9UvriJ2EJ5j B3ih1oMtKX8AtuVSRu8LF7MCNOSsqwzixU2i X-Google-Smtp-Source: AKy350YjU2Y2MgqNkqgZoIOPOW0+HOYv1MqQ0pV2FUPZVEGY798zCaQjIBhDtJyF0YZxiEsyw9QKlZMU8q/qm34J X-Received: from yosry.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:2327]) (user=yosryahmed job=sendgmr) by 2002:a17:902:6b44:b0:1a2:6e4d:7832 with SMTP id g4-20020a1709026b4400b001a26e4d7832mr2680127plt.1.1680203894775; Thu, 30 Mar 2023 12:18:14 -0700 (PDT) Date: Thu, 30 Mar 2023 19:17:59 +0000 In-Reply-To: <20230330191801.1967435-1-yosryahmed@google.com> Mime-Version: 1.0 References: <20230330191801.1967435-1-yosryahmed@google.com> X-Mailer: git-send-email 2.40.0.348.gf938b09366-goog Message-ID: <20230330191801.1967435-7-yosryahmed@google.com> Subject: [PATCH v3 6/8] workingset: memcg: sleep when flushing stats in workingset_refault() From: Yosry Ahmed To: Tejun Heo , Josef Bacik , Jens Axboe , Zefan Li , Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Andrew Morton , " =?utf-8?q?Michal_Koutn=C3=BD?= " Cc: Vasily Averin , cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, Yosry Ahmed , Michal Hocko Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org In workingset_refault(), we call mem_cgroup_flush_stats_atomic_ratelimited() to read accurate stats within an RCU read section and with sleeping disallowed. Move the call above the RCU read section to make it non-atomic. Flushing is an expensive operation that scales with the number of cpus and the number of cgroups in the system, so avoid doing it atomically where possible. Since workingset_refault() is the only caller of mem_cgroup_flush_stats_atomic_ratelimited(), just make it non-atomic, and rename it to mem_cgroup_flush_stats_ratelimited(). Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko --- include/linux/memcontrol.h | 4 ++-- mm/memcontrol.c | 4 ++-- mm/workingset.c | 5 +++-- 3 files changed, 7 insertions(+), 6 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b424ba3ebd09..a4bc3910a2eb 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1038,7 +1038,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void mem_cgroup_flush_stats(void); void mem_cgroup_flush_stats_atomic(void); -void mem_cgroup_flush_stats_atomic_ratelimited(void); +void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1540,7 +1540,7 @@ static inline void mem_cgroup_flush_stats_atomic(void) { } -static inline void mem_cgroup_flush_stats_atomic_ratelimited(void) +static inline void mem_cgroup_flush_stats_ratelimited(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a2ce3aa10d94..361c0bbf7283 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -673,10 +673,10 @@ void mem_cgroup_flush_stats_atomic(void) do_flush_stats(true); } -void mem_cgroup_flush_stats_atomic_ratelimited(void) +void mem_cgroup_flush_stats_ratelimited(void) { if (time_after64(jiffies_64, READ_ONCE(flush_next_time))) - mem_cgroup_flush_stats_atomic(); + mem_cgroup_flush_stats(); } static void flush_memcg_stats_dwork(struct work_struct *w) diff --git a/mm/workingset.c b/mm/workingset.c index dab0c362b9e3..3025beee9b34 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -406,6 +406,9 @@ void workingset_refault(struct folio *folio, void *shadow) unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); eviction <<= bucket_order; + /* Flush stats (and potentially sleep) before holding RCU read lock */ + mem_cgroup_flush_stats_ratelimited(); + rcu_read_lock(); /* * Look up the memcg associated with the stored ID. It might @@ -461,8 +464,6 @@ void workingset_refault(struct folio *folio, void *shadow) lruvec = mem_cgroup_lruvec(memcg, pgdat); mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - - mem_cgroup_flush_stats_atomic_ratelimited(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if From patchwork Thu Mar 30 19:18:00 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yosry Ahmed X-Patchwork-Id: 13194766 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 44DA8C761A6 for ; Thu, 30 Mar 2023 19:19:08 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229521AbjC3TTG (ORCPT ); Thu, 30 Mar 2023 15:19:06 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:48522 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232184AbjC3TS0 (ORCPT ); Thu, 30 Mar 2023 15:18:26 -0400 Received: from mail-pl1-x649.google.com (mail-pl1-x649.google.com [IPv6:2607:f8b0:4864:20::649]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 6C4A010429 for ; Thu, 30 Mar 2023 12:18:17 -0700 (PDT) Received: by mail-pl1-x649.google.com with SMTP id kp6-20020a170903280600b001a2945a7fdeso775661plb.18 for ; Thu, 30 Mar 2023 12:18:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1680203896; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=xcUaqJ6BFfuwa7nRJSvBlAwhhxeRf5mk+29EPOCHz/Q=; b=ltNePRXuZIePvYweAMHUj9ZiAeC5qavTrptvs7HWUZy4ZQjHtls0D9eRHEg0pqkaqA 2rj8RSL+AK/a3iTAV1slsfA/XO8i87DoFdpL6M03j+wstTxD0gNLM1Eo1e2c6UpyLkfA 02M3+F6NXEWgNHJDDpxLzGC2sGDBHCNs+LO2yZgTc79ihpz2oe9Gkrj2oQSZRb8nP/pk DTjpgFJ4LNEzmr5tCkDpR0cOQrENPev1JFpwtylRIUOchlXAi5bgsrxJgKXBgxobydtr bGBrN9gUtdaDKVSRv2j9cJxRBN0C3BLXf8CobNS0sZxfbCzcE+BakwfvTig0jcnVMYxC dA2A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1680203896; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=xcUaqJ6BFfuwa7nRJSvBlAwhhxeRf5mk+29EPOCHz/Q=; b=7Zw256l7Ij15lRxObxRe1nTjISkSv28rBqjPzBy+ij0L9wNQdaWgVYgdYEIG7W1SEo 3UEFoHvTMYNNKhfKuBOc6IGAXIT1XIuagjyzon6ns6VWRx5r+ZbC3k4V6eAgfdFW1uq3 0IZ+ByHyWTFW9smM6bE138hD/HuEr63nA8hYwIwqklXAt0pPobLPOwXX27tIvpz6pcQT 507suc9iymhDbB2V4aE3BFuUSRN41r/M9bBOnTYszfdD+UkCitA49oaLnejHFnr/rWw0 VfTVy7MhHui4ZqYrdPtsfI6R3/2LU6+PpcLE6Guq3/gvCejiAbIXs58Cm2jL+jbQYZxP Z0cw== X-Gm-Message-State: AAQBX9dDMUiT4jRDEDSvhJnPW+r6EE3Cxy7KiEmcoEuXU2bH/1Hu/O7O 16YIyA5sMiF0DZ2Y1ZXw8clawwYHUD/vnPeK X-Google-Smtp-Source: AKy350bGhjPkePduCVIwuMcmgqQ6a76256SvlUw7LUz9ChuwvjB5lA7RHnWs+sTxxUB3GpOtDLTlb1QCGdSZixrZ X-Received: from yosry.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:2327]) (user=yosryahmed job=sendgmr) by 2002:a63:40c1:0:b0:4fd:5105:eb93 with SMTP id n184-20020a6340c1000000b004fd5105eb93mr6667473pga.3.1680203896567; Thu, 30 Mar 2023 12:18:16 -0700 (PDT) Date: Thu, 30 Mar 2023 19:18:00 +0000 In-Reply-To: <20230330191801.1967435-1-yosryahmed@google.com> Mime-Version: 1.0 References: <20230330191801.1967435-1-yosryahmed@google.com> X-Mailer: git-send-email 2.40.0.348.gf938b09366-goog Message-ID: <20230330191801.1967435-8-yosryahmed@google.com> Subject: [PATCH v3 7/8] vmscan: memcg: sleep when flushing stats during reclaim From: Yosry Ahmed To: Tejun Heo , Josef Bacik , Jens Axboe , Zefan Li , Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Andrew Morton , " =?utf-8?q?Michal_Koutn=C3=BD?= " Cc: Vasily Averin , cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, Yosry Ahmed , Michal Hocko Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Memory reclaim is a sleepable context. Flushing is an expensive operaiton that scales with the number of cpus and the number of cgroups in the system, so avoid doing it atomically unnecessarily. This can slow down reclaim code if flushing stats is taking too long, but there is already multiple cond_resched()'s in reclaim code. Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko --- mm/vmscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index a9511ccb936f..9c1c5e8b24b8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2845,7 +2845,7 @@ static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) * Flush the memory cgroup stats, so that we read accurate per-memcg * lruvec stats for heuristics. */ - mem_cgroup_flush_stats_atomic(); + mem_cgroup_flush_stats(); /* * Determine the scan balance between anon and file LRUs. From patchwork Thu Mar 30 19:18:01 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Yosry Ahmed X-Patchwork-Id: 13194767 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9437EC77B6E for ; Thu, 30 Mar 2023 19:19:09 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230392AbjC3TTH (ORCPT ); Thu, 30 Mar 2023 15:19:07 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:48674 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232213AbjC3TSj (ORCPT ); Thu, 30 Mar 2023 15:18:39 -0400 Received: from mail-yw1-x1149.google.com (mail-yw1-x1149.google.com [IPv6:2607:f8b0:4864:20::1149]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 0FD4510A97 for ; Thu, 30 Mar 2023 12:18:18 -0700 (PDT) Received: by mail-yw1-x1149.google.com with SMTP id 00721157ae682-54574d6204aso197368167b3.15 for ; Thu, 30 Mar 2023 12:18:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1680203898; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=WbNC07VGnJucfMQdaVru/HWxeCTMcNM6hFkgQ/MCeFU=; b=PUv9MA0n+Z8fm7ErrGvHySjECm+JmVMmb7yIewlfjR/61XxilLPkk2HWdbFMTfUOaL VEd5S3Db2lj6fZaM1EVkiIBt/SsoMNdbAydQDGkFf9C+290T1e1uwhZ4tZ9DFf8Phq0h P4OVDvENTCX+3IndK3Cvs6OkRD4foG1c4Yew7PAGOLNrfjOHkmrszhM9+d8Istzt+wK/ krUK3yorRZOqS1BM/g9ye1FRB5jRNaXtQwUxDYcXcRNeFj0C93RhkVtRFak+8MvkC/U9 MW/LMGQgSZbJ8G2s7XbIxfyCgArJtDyQ9vNCBWNE1utNTCLeMAHTcanEcYFbU2EbD5hm feog== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1680203898; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=WbNC07VGnJucfMQdaVru/HWxeCTMcNM6hFkgQ/MCeFU=; b=r2FZY38tQchfcZbu1Zto7vGCPjKLZ79bXYzPv6r6JLMpMa83CHWU+K1rIUG+UMhG8R okB8/vRCOhGNfra4HTpKNBhzBjA5FdZWtmuX1ZGkYrRaqaLTIdxGCqvFC3uw5YN8VvcG gSla5WJD2o0/tLFMW4CTR2ziRUNGST92V1rWenmBagvAJzn3Gw5TOHrWJuwNM3/8Xs75 osIi0WrD11mAabsrDaTnGNPJzrU9+fAnQM/u8vAVAnlTJITe3BXntvW4QcTz29oVmLGo NqF3PClvpL1ot8NAdGEzCvhLzHDaxebtqZDIF2/EHwb8xeBVDZsXJMfBvkgT9Rggv/k/ eCEw== X-Gm-Message-State: AAQBX9e5hbLSzgBsr5fgJ2zaXqYWqnJ0ZYA7tUuaz8HXXho0YKYm0IAj FFgiAAwCf/bJ7bfAxum8PvIuRpu0R8xAArH1 X-Google-Smtp-Source: AKy350Z/bGsj2O9Q2OanxyiTVpU0KIn4cOhMHnfEJjh1llR4Xo1YrB6Sk31TDPAteoghtoX9TuixuaLotnLFVi3d X-Received: from yosry.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:2327]) (user=yosryahmed job=sendgmr) by 2002:a25:12d4:0:b0:b6e:d788:eba4 with SMTP id 203-20020a2512d4000000b00b6ed788eba4mr12664999ybs.6.1680203898630; Thu, 30 Mar 2023 12:18:18 -0700 (PDT) Date: Thu, 30 Mar 2023 19:18:01 +0000 In-Reply-To: <20230330191801.1967435-1-yosryahmed@google.com> Mime-Version: 1.0 References: <20230330191801.1967435-1-yosryahmed@google.com> X-Mailer: git-send-email 2.40.0.348.gf938b09366-goog Message-ID: <20230330191801.1967435-9-yosryahmed@google.com> Subject: [PATCH v3 8/8] memcg: do not modify rstat tree for zero updates From: Yosry Ahmed To: Tejun Heo , Josef Bacik , Jens Axboe , Zefan Li , Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Andrew Morton , " =?utf-8?q?Michal_Koutn=C3=BD?= " Cc: Vasily Averin , cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org, Yosry Ahmed , Michal Hocko Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org In some situations, we may end up calling memcg_rstat_updated() with a value of 0, which means the stat was not actually updated. An example is if we fail to reclaim any pages in shrink_folio_list(). Do not add the cgroup to the rstat updated tree in this case, to avoid unnecessarily flushing it. Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Michal Koutný --- mm/memcontrol.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 361c0bbf7283..a63ee2efa780 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -618,6 +618,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) { unsigned int x; + if (!val) + return; + cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id()); x = __this_cpu_add_return(stats_updates, abs(val));