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 Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0EC79C433F5 for ; Thu, 7 Apr 2022 03:16:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S240138AbiDGDSx (ORCPT ); Wed, 6 Apr 2022 23:18:53 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:44560 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S240044AbiDGDSa (ORCPT ); Wed, 6 Apr 2022 23:18:30 -0400 Received: from mail-yb1-xb49.google.com (mail-yb1-xb49.google.com [IPv6:2607:f8b0:4864:20::b49]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 22DBB6E350 for ; Wed, 6 Apr 2022 20:16:15 -0700 (PDT) Received: by mail-yb1-xb49.google.com with SMTP id k206-20020a2524d7000000b0063db1bacae1so3281743ybk.4 for ; Wed, 06 Apr 2022 20:16:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=date:in-reply-to:message-id:mime-version:references:subject:from:to :cc:content-transfer-encoding; bh=wodybzRV+5o7d6sjMRBtXZOqyy0KFnN+jq7iHOTZKSo=; b=I+FvVWIwIJ1xLjbzQMrWOxDhxTfBCxOeP19oZyPhOj7DfkEwWfZDea57PAzCRcPz12 hCpkTLlaZtZE7rndERADHaKJMvitgbtMSFGOZDn/drZiCmq6meH/Cqb9jez7Gq8m4iHk AJIJU+W9TVoIFyma/22Uggv/2al7B3BskLaMxHLP0GHx7+w61XQ9fgnLvQ3dDKFlbxah hV5OkyI7MhvFP9nKw+dhEzw9PBLQWRnPXLeI0CMNPJ9s0S/RqTBSYYp6K/ylR69cHjFY m6ZdLVvCnlvLgM2fJwprz6Lwq5xB+m5V1CSMeVLvjRpP11M8xjpfvBcl1dei25PSNgwU 9y0Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:date:in-reply-to:message-id:mime-version :references:subject:from:to:cc:content-transfer-encoding; bh=wodybzRV+5o7d6sjMRBtXZOqyy0KFnN+jq7iHOTZKSo=; b=LSR+TIgwtvE9oiPvnKS+hewIGYkezEY6FER4v8AaW647/IFNBwNHMNq0ir6xXQ/Lt5 WB9DP0c8BMrhWdSPTgU+exh7CI7RLmmDiE6KYIDsMbze1NxwyFes1ZZgRYJ21au5wWbD aucV6j3ioTRt1lzEZtnK9uVOpiI98dMAVcfPypmS5KZYrRE/VtEmy0WwKTfQkT8lWa88 XRPUHDyjJ9w1UblpWLtrvCBGz2K3w1y78OV3A2oL7EitCYpw6Cohb/a+KRdKVjDb0lCW isIRtlbIA8n7jNtzCnmdVGY9mSsV+MWaIrpTbrqtWTNt5eym8w/yul9nUlI1PIv4boe3 tkFg== X-Gm-Message-State: AOAM530Wi+RYlPxbN5jmzHjOrYZsErgK0gTKdcTg7SBvnNz35pyh2UJU vIvY2gv8X1c1qbIndOQfAluAZVVU+Ws= X-Google-Smtp-Source: ABdhPJyZHoyZpJTQTeThbSU1jtN41oBFWFGS0AmMt0Uz95SlsQ25lNlbGTYLXXbGXrhA3mluIDwF4h/APco= X-Received: from yuzhao.bld.corp.google.com ([2620:15c:183:200:9ea2:c755:ae22:6862]) (user=yuzhao job=sendgmr) by 2002:a5b:6cf:0:b0:61e:1371:3cda with SMTP id r15-20020a5b06cf000000b0061e13713cdamr8627177ybq.235.1649301374788; Wed, 06 Apr 2022 20:16:14 -0700 (PDT) Date: Wed, 6 Apr 2022 21:15:24 -0600 In-Reply-To: <20220407031525.2368067-1-yuzhao@google.com> Message-Id: <20220407031525.2368067-13-yuzhao@google.com> Mime-Version: 1.0 References: <20220407031525.2368067-1-yuzhao@google.com> X-Mailer: git-send-email 2.35.1.1094.g7c7d902a7c-goog Subject: [PATCH v10 12/14] mm: multi-gen LRU: debugfs interface From: Yu Zhao To: Stephen Rothwell , linux-mm@kvack.org Cc: Andi Kleen , Andrew Morton , Aneesh Kumar , Barry Song <21cnbao@gmail.com>, Catalin Marinas , Dave Hansen , Hillf Danton , Jens Axboe , Jesse Barnes , Johannes Weiner , Jonathan Corbet , Linus Torvalds , Matthew Wilcox , Mel Gorman , Michael Larabel , Michal Hocko , Mike Rapoport , Rik van Riel , Vlastimil Babka , Will Deacon , Ying Huang , linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, page-reclaim@google.com, x86@kernel.org, Yu Zhao , Brian Geffon , Jan Alexander Steffens , Oleksandr Natalenko , Steven Barrett , Suleiman Souhlal , Daniel Byrne , Donald Carr , "=?UTF-8?q?Holger=20Hoffst=C3=A4tte?=" , Konstantin Kharlamov , Shuang Zhai , Sofia Trinh , Vaibhav Jain Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-doc@vger.kernel.org Add /sys/kernel/debug/lru_gen for working set estimation and proactive reclaim. These features are required to optimize job scheduling (bin packing) in data centers [1][2]. Compared with the page table-based approach and the PFN-based approach, e.g., mm/damon/[vp]addr.c, this lruvec-based approach has the following advantages: 1. It offers better choices because it is aware of memcgs, NUMA nodes, shared mappings and unmapped page cache. 2. It is more scalable because it is O(nr_hot_pages), whereas the PFN-based approach is O(nr_total_pages). Add /sys/kernel/debug/lru_gen_full for debugging. [1] https://dl.acm.org/doi/10.1145/3297858.3304053 [2] https://dl.acm.org/doi/10.1145/3503222.3507731 Signed-off-by: Yu Zhao Acked-by: Brian Geffon Acked-by: Jan Alexander Steffens (heftig) Acked-by: Oleksandr Natalenko Acked-by: Steven Barrett Acked-by: Suleiman Souhlal Tested-by: Daniel Byrne Tested-by: Donald Carr Tested-by: Holger Hoffst=C3=A4tte Tested-by: Konstantin Kharlamov Tested-by: Shuang Zhai Tested-by: Sofia Trinh Tested-by: Vaibhav Jain --- include/linux/nodemask.h | 1 + mm/vmscan.c | 346 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 347 insertions(+) diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 567c3ddba2c4..90840c459abc 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -486,6 +486,7 @@ static inline int num_node_state(enum node_states state= ) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) +#define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U =20 diff --git a/mm/vmscan.c b/mm/vmscan.c index 4b7da68b8750..913c28805236 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -53,6 +53,7 @@ #include #include #include +#include =20 #include #include @@ -5191,6 +5192,348 @@ static struct attribute_group lru_gen_attr_group = =3D { .attrs =3D lru_gen_attrs, }; =20 +/*************************************************************************= ***** + * debugfs interface + *************************************************************************= *****/ + +static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) +{ + struct mem_cgroup *memcg; + loff_t nr_to_skip =3D *pos; + + m->private =3D kvmalloc(PATH_MAX, GFP_KERNEL); + if (!m->private) + return ERR_PTR(-ENOMEM); + + memcg =3D mem_cgroup_iter(NULL, NULL, NULL); + do { + int nid; + + for_each_node_state(nid, N_MEMORY) { + if (!nr_to_skip--) + return get_lruvec(memcg, nid); + } + } while ((memcg =3D mem_cgroup_iter(NULL, memcg, NULL))); + + return NULL; +} + +static void lru_gen_seq_stop(struct seq_file *m, void *v) +{ + if (!IS_ERR_OR_NULL(v)) + mem_cgroup_iter_break(NULL, lruvec_memcg(v)); + + kvfree(m->private); + m->private =3D NULL; +} + +static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + int nid =3D lruvec_pgdat(v)->node_id; + struct mem_cgroup *memcg =3D lruvec_memcg(v); + + ++*pos; + + nid =3D next_memory_node(nid); + if (nid =3D=3D MAX_NUMNODES) { + memcg =3D mem_cgroup_iter(NULL, memcg, NULL); + if (!memcg) + return NULL; + + nid =3D first_memory_node; + } + + return get_lruvec(memcg, nid); +} + +static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruve= c, + unsigned long max_seq, unsigned long *min_seq, + unsigned long seq) +{ + int i; + int type, tier; + int hist =3D lru_hist_from_seq(seq); + struct lru_gen_struct *lrugen =3D &lruvec->lrugen; + + for (tier =3D 0; tier < MAX_NR_TIERS; tier++) { + seq_printf(m, " %10d", tier); + for (type =3D 0; type < ANON_AND_FILE; type++) { + unsigned long n[3] =3D {}; + + if (seq =3D=3D max_seq) { + n[0] =3D READ_ONCE(lrugen->avg_refaulted[type][tier]); + n[1] =3D READ_ONCE(lrugen->avg_total[type][tier]); + + seq_printf(m, " %10luR %10luT %10lu ", n[0], n[1], n[2]); + } else if (seq =3D=3D min_seq[type] || NR_HIST_GENS > 1) { + n[0] =3D atomic_long_read(&lrugen->refaulted[hist][type][tier]); + n[1] =3D atomic_long_read(&lrugen->evicted[hist][type][tier]); + if (tier) + n[2] =3D READ_ONCE(lrugen->protected[hist][type][tier - 1]); + + seq_printf(m, " %10lur %10lue %10lup", n[0], n[1], n[2]); + } else + seq_puts(m, " 0 0 0 "); + } + seq_putc(m, '\n'); + } + + seq_puts(m, " "); + for (i =3D 0; i < NR_MM_STATS; i++) { + if (seq =3D=3D max_seq && NR_HIST_GENS =3D=3D 1) + seq_printf(m, " %10lu%c", READ_ONCE(lruvec->mm_state.stats[hist][i]), + toupper(MM_STAT_CODES[i])); + else if (seq !=3D max_seq && NR_HIST_GENS > 1) + seq_printf(m, " %10lu%c", READ_ONCE(lruvec->mm_state.stats[hist][i]), + MM_STAT_CODES[i]); + else + seq_puts(m, " 0 "); + } + seq_putc(m, '\n'); +} + +static int lru_gen_seq_show(struct seq_file *m, void *v) +{ + unsigned long seq; + bool full =3D !debugfs_real_fops(m->file)->write; + struct lruvec *lruvec =3D v; + struct lru_gen_struct *lrugen =3D &lruvec->lrugen; + int nid =3D lruvec_pgdat(lruvec)->node_id; + struct mem_cgroup *memcg =3D lruvec_memcg(lruvec); + DEFINE_MAX_SEQ(lruvec); + DEFINE_MIN_SEQ(lruvec); + + if (nid =3D=3D first_memory_node) { + const char *path =3D memcg ? m->private : ""; + +#ifdef CONFIG_MEMCG + if (memcg) + cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); +#endif + seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); + } + + seq_printf(m, " node %5d\n", nid); + + if (!full) + seq =3D min_seq[LRU_GEN_ANON]; + else if (max_seq >=3D MAX_NR_GENS) + seq =3D max_seq - MAX_NR_GENS + 1; + else + seq =3D 0; + + for (; seq <=3D max_seq; seq++) { + int type, zone; + int gen =3D lru_gen_from_seq(seq); + unsigned long birth =3D READ_ONCE(lruvec->lrugen.timestamps[gen]); + + seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); + + for (type =3D 0; type < ANON_AND_FILE; type++) { + long size =3D 0; + char mark =3D full && seq < min_seq[type] ? 'x' : ' '; + + for (zone =3D 0; zone < MAX_NR_ZONES; zone++) + size +=3D READ_ONCE(lrugen->nr_pages[gen][type][zone]); + + seq_printf(m, " %10lu%c", max(size, 0L), mark); + } + + seq_putc(m, '\n'); + + if (full) + lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); + } + + return 0; +} + +static const struct seq_operations lru_gen_seq_ops =3D { + .start =3D lru_gen_seq_start, + .stop =3D lru_gen_seq_stop, + .next =3D lru_gen_seq_next, + .show =3D lru_gen_seq_show, +}; + +static int run_aging(struct lruvec *lruvec, unsigned long seq, struct scan= _control *sc, + bool can_swap, bool full_scan) +{ + DEFINE_MAX_SEQ(lruvec); + + if (seq =3D=3D max_seq) + try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, full_scan); + + return seq > max_seq ? -EINVAL : 0; +} + +static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct s= can_control *sc, + int swappiness, unsigned long nr_to_reclaim) +{ + struct blk_plug plug; + int err =3D -EINTR; + DEFINE_MAX_SEQ(lruvec); + + if (seq + MIN_NR_GENS > max_seq) + return -EINVAL; + + sc->nr_reclaimed =3D 0; + + blk_start_plug(&plug); + + while (!signal_pending(current)) { + DEFINE_MIN_SEQ(lruvec); + + if (seq < min_seq[!swappiness] || sc->nr_reclaimed >=3D nr_to_reclaim || + !evict_folios(lruvec, sc, swappiness, NULL)) { + err =3D 0; + break; + } + + cond_resched(); + } + + blk_finish_plug(&plug); + + return err; +} + +static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, + struct scan_control *sc, int swappiness, unsigned long opt) +{ + struct lruvec *lruvec; + int err =3D -EINVAL; + struct mem_cgroup *memcg =3D NULL; + + if (!mem_cgroup_disabled()) { + rcu_read_lock(); + memcg =3D mem_cgroup_from_id(memcg_id); +#ifdef CONFIG_MEMCG + if (memcg && !css_tryget(&memcg->css)) + memcg =3D NULL; +#endif + rcu_read_unlock(); + + if (!memcg) + goto done; + } + if (memcg_id !=3D mem_cgroup_id(memcg)) + goto done; + + if (nid < 0 || nid >=3D MAX_NUMNODES || !node_state(nid, N_MEMORY)) + goto done; + + lruvec =3D get_lruvec(memcg, nid); + + if (swappiness < 0) + swappiness =3D get_swappiness(lruvec, sc); + else if (swappiness > 200) + goto done; + + switch (cmd) { + case '+': + err =3D run_aging(lruvec, seq, sc, swappiness, opt); + break; + case '-': + err =3D run_eviction(lruvec, seq, sc, swappiness, opt); + break; + } +done: + mem_cgroup_put(memcg); + + return err; +} + +static ssize_t lru_gen_seq_write(struct file *file, const char __user *src= , + size_t len, loff_t *pos) +{ + void *buf; + char *cur, *next; + unsigned int flags; + int err =3D 0; + struct scan_control sc =3D { + .may_writepage =3D true, + .may_unmap =3D true, + .may_swap =3D true, + .reclaim_idx =3D MAX_NR_ZONES - 1, + .gfp_mask =3D GFP_KERNEL, + }; + + buf =3D kvmalloc(len + 1, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, src, len)) { + kvfree(buf); + return -EFAULT; + } + + next =3D buf; + next[len] =3D '\0'; + + sc.reclaim_state.mm_walk =3D alloc_mm_walk(); + if (!sc.reclaim_state.mm_walk) { + kvfree(buf); + return -ENOMEM; + } + + set_task_reclaim_state(current, &sc.reclaim_state); + flags =3D memalloc_noreclaim_save(); + + while ((cur =3D strsep(&next, ",;\n"))) { + int n; + int end; + char cmd; + unsigned int memcg_id; + unsigned int nid; + unsigned long seq; + unsigned int swappiness =3D -1; + unsigned long opt =3D -1; + + cur =3D skip_spaces(cur); + if (!*cur) + continue; + + n =3D sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid, + &seq, &end, &swappiness, &end, &opt, &end); + if (n < 4 || cur[end]) { + err =3D -EINVAL; + break; + } + + err =3D run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); + if (err) + break; + } + + memalloc_noreclaim_restore(flags); + set_task_reclaim_state(current, NULL); + + free_mm_walk(sc.reclaim_state.mm_walk); + kvfree(buf); + + return err ? : len; +} + +static int lru_gen_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &lru_gen_seq_ops); +} + +static const struct file_operations lru_gen_rw_fops =3D { + .open =3D lru_gen_seq_open, + .read =3D seq_read, + .write =3D lru_gen_seq_write, + .llseek =3D seq_lseek, + .release =3D seq_release, +}; + +static const struct file_operations lru_gen_ro_fops =3D { + .open =3D lru_gen_seq_open, + .read =3D seq_read, + .llseek =3D seq_lseek, + .release =3D seq_release, +}; + /*************************************************************************= ***** * initialization *************************************************************************= *****/ @@ -5249,6 +5592,9 @@ static int __init init_lru_gen(void) if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); =20 + debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops); + debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops); + return 0; }; late_initcall(init_lru_gen); --=20 2.35.1.1094.g7c7d902a7c-goog