From nobody Sun Dec 14 08:03:36 2025 Received: from mail-yb1-f174.google.com (mail-yb1-f174.google.com [209.85.219.174]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 98D051BDE3; Wed, 3 Jan 2024 16:49:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="kqBfK335" Received: by mail-yb1-f174.google.com with SMTP id 3f1490d57ef6-dbe87cbc052so1500964276.2; Wed, 03 Jan 2024 08:49:16 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1704300555; x=1704905355; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=lwZZYWh+e0yk/cuTVxoiseyhi+aiBF9zz0tdKJ/4vMs=; b=kqBfK335h0wkxsSw38j2vQvPlktEv1Gwb5XiT31bJjqgMFS1/CQFoVOn4Q4PrqBoBt hfx1ntKGVABM1TPc5ZytAv5lMuHE3U46OfpHlW0uCM2JI5whZoMLGu4KQoRN+m6DB2X0 urw9plMiz9AaoUYFlegISzmVJ3aIDansCn3g+T56g405Kw6EQxmeNMkedwL0uaunbm9R yayCKzCiqW+AEkTeOPqUaRX/wSaHVKQF904+5pX9ImQzyGXwMjPCUuAH4H2XDN+MR3ul lBdNNwrOggTQt7NK/SSbYabhCBSD+MYhpgETJqtFsEk8ncBMuzYNUCzVTiPGHG/mPofe Gxog== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1704300555; x=1704905355; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=lwZZYWh+e0yk/cuTVxoiseyhi+aiBF9zz0tdKJ/4vMs=; b=NqBgC2vm4DkgGJTSjk/ChPzKsbftIGsYg5sV2QnvTFkcQF+qG348xEjgTCPjwrpeY7 HmAhhSppo2QaolVal+5POCp8lXhB2TiHPLmxiYcd0vNgSmDFMCY2lXT5kCb3/ZHqNMWD QTE+4Lj+ofX1plOdS206ROpw37xWm090o/R+/Tx8fRUrjK+M2TI2j0EslORTOMD4sDKX kZda8deF3ZlToCUHAg5CH8lpMDsya97XAE+rQP10KxdB0Yz99c6kIvg/upX2jJYN2yiW 8ZpY21Kw7rZruHU+FsGST+ypaiQ1v1/BuT8Sxl1zlIeT8HHogFYDRIQAXKwrfDh5B0li xlqg== X-Gm-Message-State: AOJu0YwqcM7QNoHODPPjrrqiQV8Gjl2+so9+oz03g52tithIqdEaZQ5i 31+JjOms3sDsIcIbOGF83sE= X-Google-Smtp-Source: AGHT+IGe4cxlLsn+e6P2JdgSr5WbR+2RuPxygGamlYxVp3FhQSYsh7zg529zAFbjlkOVWnvfCaAsxw== X-Received: by 2002:a25:ef52:0:b0:dbe:a003:a24a with SMTP id w18-20020a25ef52000000b00dbea003a24amr971520ybm.56.1704300555318; Wed, 03 Jan 2024 08:49:15 -0800 (PST) Received: from localhost ([2620:10d:c091:400::5:fcab]) by smtp.gmail.com with ESMTPSA id ci10-20020a05622a260a00b00427f1eeddccsm7362030qtb.38.2024.01.03.08.49.14 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 03 Jan 2024 08:49:15 -0800 (PST) From: Dan Schatzberg To: Andrew Morton Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, linux-mm@kvack.org, David Rientjes , Chris Li , Nhat Pham , Tejun Heo , Zefan Li , Johannes Weiner , Jonathan Corbet , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , David Hildenbrand , Matthew Wilcox , Kefeng Wang , Dan Schatzberg , Yue Zhao , Yosry Ahmed , Hugh Dickins Subject: [PATCH v6 1/2] mm: add defines for min/max swappiness Date: Wed, 3 Jan 2024 08:48:36 -0800 Message-Id: <20240103164841.2800183-2-schatzberg.dan@gmail.com> X-Mailer: git-send-email 2.39.3 In-Reply-To: <20240103164841.2800183-1-schatzberg.dan@gmail.com> References: <20240103164841.2800183-1-schatzberg.dan@gmail.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" We use the constants 0 and 200 in a few places in the mm code when referring to the min and max swappiness. This patch adds MIN_SWAPPINESS and MAX_SWAPPINESS #defines to improve clarity. There are no functional changes. Signed-off-by: Dan Schatzberg Acked-by: David Rientjes Acked-by: Chris Li Reviewed-by: Nhat Pham --- include/linux/swap.h | 2 ++ mm/memcontrol.c | 2 +- mm/vmscan.c | 14 +++++++------- 3 files changed, 10 insertions(+), 8 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index f6dd6575b905..e2ab76c25b4a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -407,6 +407,8 @@ extern unsigned long try_to_free_pages(struct zonelist = *zonelist, int order, =20 #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) +#define MIN_SWAPPINESS 0 +#define MAX_SWAPPINESS 200 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b226090fd906..fbe9f02dd206 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4337,7 +4337,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_= subsys_state *css, { struct mem_cgroup *memcg =3D mem_cgroup_from_css(css); =20 - if (val > 200) + if (val > MAX_SWAPPINESS) return -EINVAL; =20 if (!mem_cgroup_is_root(memcg)) diff --git a/mm/vmscan.c b/mm/vmscan.c index 9dd8977de5a2..d91963e2d47f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -183,7 +183,7 @@ struct scan_control { #endif =20 /* - * From 0 .. 200. Higher means more swappy. + * From 0 .. MAX_SWAPPINESS. Higher means more swappy. */ int vm_swappiness =3D 60; =20 @@ -2403,7 +2403,7 @@ static void get_scan_count(struct lruvec *lruvec, str= uct scan_control *sc, ap =3D swappiness * (total_cost + 1); ap /=3D anon_cost + 1; =20 - fp =3D (200 - swappiness) * (total_cost + 1); + fp =3D (MAX_SWAPPINESS - swappiness) * (total_cost + 1); fp /=3D file_cost + 1; =20 fraction[0] =3D ap; @@ -4400,7 +4400,7 @@ static int get_type_to_scan(struct lruvec *lruvec, in= t swappiness, int *tier_idx { int type, tier; struct ctrl_pos sp, pv; - int gain[ANON_AND_FILE] =3D { swappiness, 200 - swappiness }; + int gain[ANON_AND_FILE] =3D { swappiness, MAX_SWAPPINESS - swappiness }; =20 /* * Compare the first tier of anon with that of file to determine which @@ -4436,7 +4436,7 @@ static int isolate_folios(struct lruvec *lruvec, stru= ct scan_control *sc, int sw /* * Try to make the obvious choice first. When anon and file are both * available from the same generation, interpret swappiness 1 as file - * first and 200 as anon first. + * first and MAX_SWAPPINESS as anon first. */ if (!swappiness) type =3D LRU_GEN_FILE; @@ -4444,7 +4444,7 @@ static int isolate_folios(struct lruvec *lruvec, stru= ct scan_control *sc, int sw type =3D LRU_GEN_ANON; else if (swappiness =3D=3D 1) type =3D LRU_GEN_FILE; - else if (swappiness =3D=3D 200) + else if (swappiness =3D=3D MAX_SWAPPINESS) type =3D LRU_GEN_ANON; else type =3D get_type_to_scan(lruvec, swappiness, &tier); @@ -5398,9 +5398,9 @@ static int run_cmd(char cmd, int memcg_id, int nid, u= nsigned long seq, =20 lruvec =3D get_lruvec(memcg, nid); =20 - if (swappiness < 0) + if (swappiness < MIN_SWAPPINESS) swappiness =3D get_swappiness(lruvec, sc); - else if (swappiness > 200) + else if (swappiness > MAX_SWAPPINESS) goto done; =20 switch (cmd) { --=20 2.39.3 From nobody Sun Dec 14 08:03:36 2025 Received: from mail-oa1-f46.google.com (mail-oa1-f46.google.com [209.85.160.46]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 564F81C6B6; Wed, 3 Jan 2024 16:49:21 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="PAK4DpB/" Received: by mail-oa1-f46.google.com with SMTP id 586e51a60fabf-2041c292da8so5611787fac.3; Wed, 03 Jan 2024 08:49:21 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1704300560; x=1704905360; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=D3Trd70tjvozyYFyAqV83nWEjrGIqqcGlRP9h5UvVDg=; b=PAK4DpB/rykOxGRvha5MOOJ6NcjBGXrZwE8v5pWRrTS8xOoRECwUZ9CwdKIqhx8rAo aRFxd8JO3FsZsZd8GXpCneb3fbDKJ/h+6lth5HwhDlnHE2vjQz51CcuN4JRxYKtnyzFf ESXB/tsyj3Q3NCww3leAs7HAjz7nStV9OVc+xdJ1I97HGrobARwgETaSvnqYj8t626Z3 LRXBDIR9r/J8jwPEJS3uJrAeHQQGVIOUTEDUYZjg57hpN/0cQVXRd5gSa0xSmrXYDPee QlrpEgQTI/G/wgHFaGgSzx5a/IWESjAJ+LkzpprEid0xKAAuRx0DRTj3+/NxgKpJMePZ J6kg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1704300560; x=1704905360; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=D3Trd70tjvozyYFyAqV83nWEjrGIqqcGlRP9h5UvVDg=; b=roDRAGh0NKZOIB57xSZzmezCjrl2za+LZ04catF8dvup76dmYuiPuus55GS0z8grYh ZFuFUd0mkG7czF27b9JqcsY393On94RjSxB1ulb+D/DPWW/RiROBYbjXiQhHRPqtIerj 6jEmNKozriOhuJcboPgJLVrL5MzpPpcyaVRlwQu9rjp8c1WmRduQQrsBVSpvObgFc/Js VkQoO63WdjljcUH2u3ZODNjbtR3tnVMY8qbNwBg3RDYj/XSNGQRLFExkVvunTy7aU8rV s+hJU8xO9cjukOpF8ii3tpa3uNHafNPGPZiQo2aXHSdqh+4ROWWIMSA49toaXjdMNJxh 6qYg== X-Gm-Message-State: AOJu0YxnTgmFyZjux+mxE0DfppJii004e1QwqzDrJrhF4RlKY5j4ZTAR hTsUss45m1GIi1pj2oJjo6QmaH2mI+bv8w== X-Google-Smtp-Source: AGHT+IGWRB8L2IIvPf9EnZ4lUQJp6LGFWjdNsZAx9VXs2gk8qcsXnGn53Hz5bzHQNB+7UwxdKCkwhQ== X-Received: by 2002:a05:6870:63a0:b0:204:4926:1824 with SMTP id t32-20020a05687063a000b0020449261824mr16093129oap.80.1704300560221; Wed, 03 Jan 2024 08:49:20 -0800 (PST) Received: from localhost ([2620:10d:c091:400::5:fcab]) by smtp.gmail.com with ESMTPSA id l19-20020a05620a28d300b0077d84f46d65sm10296915qkp.37.2024.01.03.08.49.19 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 03 Jan 2024 08:49:19 -0800 (PST) From: Dan Schatzberg To: Andrew Morton Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, linux-mm@kvack.org, Yosry Ahmed , Michal Hocko , David Rientjes , Chris Li , Tejun Heo , Zefan Li , Johannes Weiner , Jonathan Corbet , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , David Hildenbrand , Matthew Wilcox , Kefeng Wang , Dan Schatzberg , Yue Zhao , Hugh Dickins Subject: [PATCH v6 2/2] mm: add swapiness= arg to memory.reclaim Date: Wed, 3 Jan 2024 08:48:37 -0800 Message-Id: <20240103164841.2800183-3-schatzberg.dan@gmail.com> X-Mailer: git-send-email 2.39.3 In-Reply-To: <20240103164841.2800183-1-schatzberg.dan@gmail.com> References: <20240103164841.2800183-1-schatzberg.dan@gmail.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Allow proactive reclaimers to submit an additional swappiness=3D argument to memory.reclaim. This overrides the global or per-memcg swappiness setting for that reclaim attempt. For example: echo "2M swappiness=3D0" > /sys/fs/cgroup/memory.reclaim will perform reclaim on the rootcg with a swappiness setting of 0 (no swap) regardless of the vm.swappiness sysctl setting. Userspace proactive reclaimers use the memory.reclaim interface to trigger reclaim. The memory.reclaim interface does not allow for any way to effect the balance of file vs anon during proactive reclaim. The only approach is to adjust the vm.swappiness setting. However, there are a few reasons we look to control the balance of file vs anon during proactive reclaim, separately from reactive reclaim: * Swapout should be limited to manage SSD write endurance. In near-OOM situations we are fine with lots of swap-out to avoid OOMs. As these are typically rare events, they have relatively little impact on write endurance. However, proactive reclaim runs continuously and so its impact on SSD write endurance is more significant. Therefore it is desireable to control swap-out for proactive reclaim separately from reactive reclaim * Some userspace OOM killers like systemd-oomd[1] support OOM killing on swap exhaustion. This makes sense if the swap exhaustion is triggered due to reactive reclaim but less so if it is triggered due to proactive reclaim (e.g. one could see OOMs when free memory is ample but anon is just particularly cold). Therefore, it's desireable to have proactive reclaim reduce or stop swap-out before the threshold at which OOM killing occurs. In the case of Meta's Senpai proactive reclaimer, we adjust vm.swappiness before writes to memory.reclaim[2]. This has been in production for nearly two years and has addressed our needs to control proactive vs reactive reclaim behavior but is still not ideal for a number of reasons: * vm.swappiness is a global setting, adjusting it can race/interfere with other system administration that wishes to control vm.swappiness. In our case, we need to disable Senpai before adjusting vm.swappiness. * vm.swappiness is stateful - so a crash or restart of Senpai can leave a misconfigured setting. This requires some additional management to record the "desired" setting and ensure Senpai always adjusts to it. With this patch, we avoid these downsides of adjusting vm.swappiness globally. [1]https://www.freedesktop.org/software/systemd/man/latest/systemd-oomd.ser= vice.html [2]https://github.com/facebookincubator/oomd/blob/main/src/oomd/plugins/Sen= pai.cpp#L585-L598 Signed-off-by: Dan Schatzberg Suggested-by: Yosry Ahmed Acked-by: Michal Hocko Acked-by: David Rientjes Acked-by: Chris Li --- Documentation/admin-guide/cgroup-v2.rst | 18 ++++---- include/linux/swap.h | 3 +- mm/memcontrol.c | 56 ++++++++++++++++++++----- mm/vmscan.c | 25 +++++++++-- 4 files changed, 80 insertions(+), 22 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-= guide/cgroup-v2.rst index 3f85254f3cef..ee42f74e0765 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1282,17 +1282,10 @@ PAGE_SIZE multiple when read back. This is a simple interface to trigger memory reclaim in the target cgroup. =20 - This file accepts a single key, the number of bytes to reclaim. - No nested keys are currently supported. - Example:: =20 echo "1G" > memory.reclaim =20 - The interface can be later extended with nested keys to - configure the reclaim behavior. For example, specify the - type of memory to reclaim from (anon, file, ..). - Please note that the kernel can over or under reclaim from the target cgroup. If less bytes are reclaimed than the specified amount, -EAGAIN is returned. @@ -1304,6 +1297,17 @@ PAGE_SIZE multiple when read back. This means that the networking layer will not adapt based on reclaim induced by memory.reclaim. =20 +The following nested keys are defined. + + =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D + swappiness Swappiness value to reclaim with + =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D + + Specifying a swappiness value instructs the kernel to perform + the reclaim with that swappiness value. Note that this has the + same semantics as vm.swappiness applied to memcg reclaim with + all the existing limitations and potential future extensions. + memory.peak A read-only single value file which exists on non-root cgroups. diff --git a/include/linux/swap.h b/include/linux/swap.h index e2ab76c25b4a..8afdec40efe3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -412,7 +412,8 @@ extern unsigned long try_to_free_pages(struct zonelist = *zonelist, int order, extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options); + unsigned int reclaim_options, + int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fbe9f02dd206..6d627a754851 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include #include @@ -2449,7 +2450,8 @@ static unsigned long reclaim_high(struct mem_cgroup *= memcg, psi_memstall_enter(&pflags); nr_reclaimed +=3D try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, - MEMCG_RECLAIM_MAY_SWAP); + MEMCG_RECLAIM_MAY_SWAP, + NULL); psi_memstall_leave(&pflags); } while ((memcg =3D parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); @@ -2740,7 +2742,7 @@ static int try_charge_memcg(struct mem_cgroup *memcg,= gfp_t gfp_mask, =20 psi_memstall_enter(&pflags); nr_reclaimed =3D try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, - gfp_mask, reclaim_options); + gfp_mask, reclaim_options, NULL); psi_memstall_leave(&pflags); =20 if (mem_cgroup_margin(mem_over_limit) >=3D nr_pages) @@ -3660,7 +3662,7 @@ static int mem_cgroup_resize_max(struct mem_cgroup *m= emcg, } =20 if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) { + memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, NULL)) { ret =3D -EBUSY; break; } @@ -3774,7 +3776,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *= memcg) return -EINTR; =20 if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - MEMCG_RECLAIM_MAY_SWAP)) + MEMCG_RECLAIM_MAY_SWAP, NULL)) nr_retries--; } =20 @@ -6720,7 +6722,7 @@ static ssize_t memory_high_write(struct kernfs_open_f= ile *of, } =20 reclaimed =3D try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP); + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL); =20 if (!reclaimed && !nr_retries--) break; @@ -6769,7 +6771,7 @@ static ssize_t memory_max_write(struct kernfs_open_fi= le *of, =20 if (nr_reclaims) { if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP)) + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL)) nr_reclaims--; continue; } @@ -6895,19 +6897,50 @@ static ssize_t memory_oom_group_write(struct kernfs= _open_file *of, return nbytes; } =20 +enum { + MEMORY_RECLAIM_SWAPPINESS =3D 0, + MEMORY_RECLAIM_NULL, +}; + +static const match_table_t tokens =3D { + { MEMORY_RECLAIM_SWAPPINESS, "swappiness=3D%d"}, + { MEMORY_RECLAIM_NULL, NULL }, +}; + static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg =3D mem_cgroup_from_css(of_css(of)); unsigned int nr_retries =3D MAX_RECLAIM_RETRIES; unsigned long nr_to_reclaim, nr_reclaimed =3D 0; + int swappiness =3D -1; unsigned int reclaim_options; - int err; + char *old_buf, *start; + substring_t args[MAX_OPT_ARGS]; =20 buf =3D strstrip(buf); - err =3D page_counter_memparse(buf, "", &nr_to_reclaim); - if (err) - return err; + + old_buf =3D buf; + nr_to_reclaim =3D memparse(buf, &buf) / PAGE_SIZE; + if (buf =3D=3D old_buf) + return -EINVAL; + + buf =3D strstrip(buf); + + while ((start =3D strsep(&buf, " ")) !=3D NULL) { + if (!strlen(start)) + continue; + switch (match_token(start, tokens, args)) { + case MEMORY_RECLAIM_SWAPPINESS: + if (match_int(&args[0], &swappiness)) + return -EINVAL; + if (swappiness < MIN_SWAPPINESS || swappiness > MAX_SWAPPINESS) + return -EINVAL; + break; + default: + return -EINVAL; + } + } =20 reclaim_options =3D MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE; while (nr_reclaimed < nr_to_reclaim) { @@ -6926,7 +6959,8 @@ static ssize_t memory_reclaim(struct kernfs_open_file= *of, char *buf, =20 reclaimed =3D try_to_free_mem_cgroup_pages(memcg, min(nr_to_reclaim - nr_reclaimed, SWAP_CLUSTER_MAX), - GFP_KERNEL, reclaim_options); + GFP_KERNEL, reclaim_options, + swappiness =3D=3D -1 ? NULL : &swappiness); =20 if (!reclaimed && !nr_retries--) return -EAGAIN; diff --git a/mm/vmscan.c b/mm/vmscan.c index d91963e2d47f..394e0dd46b2e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -92,6 +92,11 @@ struct scan_control { unsigned long anon_cost; unsigned long file_cost; =20 +#ifdef CONFIG_MEMCG + /* Swappiness value for proactive reclaim. Always use sc_swappiness()! */ + int *proactive_swappiness; +#endif + /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 @@ -227,6 +232,13 @@ static bool writeback_throttling_sane(struct scan_cont= rol *sc) #endif return false; } + +static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) +{ + if (sc->proactive && sc->proactive_swappiness) + return *sc->proactive_swappiness; + return mem_cgroup_swappiness(memcg); +} #else static bool cgroup_reclaim(struct scan_control *sc) { @@ -242,6 +254,11 @@ static bool writeback_throttling_sane(struct scan_cont= rol *sc) { return true; } + +static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) +{ + return READ_ONCE(vm_swappiness); +} #endif =20 static void set_task_reclaim_state(struct task_struct *task, @@ -2327,7 +2344,7 @@ static void get_scan_count(struct lruvec *lruvec, str= uct scan_control *sc, struct pglist_data *pgdat =3D lruvec_pgdat(lruvec); struct mem_cgroup *memcg =3D lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; - int swappiness =3D mem_cgroup_swappiness(memcg); + int swappiness =3D sc_swappiness(sc, memcg); u64 fraction[ANON_AND_FILE]; u64 denominator =3D 0; /* gcc */ enum scan_balance scan_balance; @@ -2608,7 +2625,7 @@ static int get_swappiness(struct lruvec *lruvec, stru= ct scan_control *sc) mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; =20 - return mem_cgroup_swappiness(memcg); + return sc_swappiness(sc, memcg); } =20 static int get_nr_gens(struct lruvec *lruvec, int type) @@ -6463,12 +6480,14 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgr= oup *memcg, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options) + unsigned int reclaim_options, + int *swappiness) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc =3D { .nr_to_reclaim =3D max(nr_pages, SWAP_CLUSTER_MAX), + .proactive_swappiness =3D swappiness, .gfp_mask =3D (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx =3D MAX_NR_ZONES - 1, --=20 2.39.3