Received: by 2002:a05:6a10:2726:0:0:0:0 with SMTP id ib38csp1018861pxb; Wed, 6 Apr 2022 06:52:30 -0700 (PDT) X-Google-Smtp-Source: ABdhPJyp+TiLy/uE9/jYY9L+ZFQZgZV5gOoJeod0v9V2f4h5nbGKvZxXaqjU7pgoVhru/34194G/ X-Received: by 2002:a63:eb51:0:b0:382:53c4:bb66 with SMTP id b17-20020a63eb51000000b0038253c4bb66mr7297176pgk.540.1649253149854; Wed, 06 Apr 2022 06:52:29 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1649253149; cv=none; d=google.com; s=arc-20160816; b=dr75ifdP5hS7lkeaos3zQbx6PIfi9qGPp1wwOrDwQO4M9p0ykBMgoyTxkCi5teSsln DaQbwPnGfQgHqvlm0oTm4DM3VhSFLK8knWX9+IhzCejBN69jCTzjxXu2Kt/e+q0HnFtI SoTrO7aZGomt9l2FJ2YbwEFAXUIHLSJkZB+4r5bariS4f4HD5sIDGMeccsUu5+AVaPYz lIkg/V4N8qL71oUZpYezgRKstRgLT/W3+vc4TwD8cwTZLSsNhnsfesUe4RQn8/Zqf1J8 6Ykdua4uqzqxyZxm5YDaJ8/39egMxSrF6MUOoakrU7c9QxkzRxT9qvc6o/6LA08jL63C NN7g== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :user-agent:references:in-reply-to:message-id:date:subject:cc:to :from:dkim-signature; bh=Q74UNCmT5rnT3kAyWlI+hljbWdli6UvYlflft7SSoqM=; b=yxFrMi+g8QpOmxHgEvH5REtu6LG/BD24C/KU0W3NdZinpezMzLw+jNv36OLLta3N38 6oY3oFupiwJPmtAtDgwbOs/kqn7j8figBEkZaAQlVewFizlSnwJgV7GNlt5Ok7Nb02Sx pSVyPDwFhEQOQWBS22ul/1sijDXf7uSrf994pGZbw5nWs7a5nEKYjh9ni196ZhREN4hz +om3B8XWfhjEsb6pmQNNvIJx+e09FxoNEYJiioOYZnKlZrukde6p1YGUnWi9f5HBvsmP swIdqXDSC77nsjJdjVEnvVsNZZL/NukhyoWvFzTMdbtHJ6e6UitebpmNrVPzy7Z4c5mZ eT1g== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linuxfoundation.org header.s=korg header.b=n+AqkrU6; spf=softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linuxfoundation.org Return-Path: Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net. [23.128.96.19]) by mx.google.com with ESMTPS id z6-20020aa79586000000b004fa95dfe8f7si14524724pfj.174.2022.04.06.06.52.29 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 06 Apr 2022 06:52:29 -0700 (PDT) Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19; Authentication-Results: mx.google.com; dkim=pass header.i=@linuxfoundation.org header.s=korg header.b=n+AqkrU6; spf=softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linuxfoundation.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 075144B1970; Wed, 6 Apr 2022 04:46:57 -0700 (PDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1449293AbiDEUKU (ORCPT + 99 others); Tue, 5 Apr 2022 16:10:20 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:56640 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S243474AbiDEKgs (ORCPT ); Tue, 5 Apr 2022 06:36:48 -0400 Received: from dfw.source.kernel.org (dfw.source.kernel.org [139.178.84.217]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 46ACD546A8; Tue, 5 Apr 2022 03:22:16 -0700 (PDT) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id C8527617CC; Tue, 5 Apr 2022 10:22:15 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id D7F58C385A0; Tue, 5 Apr 2022 10:22:14 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1649154135; bh=v4fuHg+FggY81ONTe7Fsg3hACzko1YCMxZhRCvjLkfM=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=n+AqkrU6/pXCz0t/SH1UdR1ztbjr/Kqkx86y8+6+Cc50PQy/7oitUtSWj6No8kdH/ XTQoqhhdU2lnGX2V3tTCNqaQLzlosetZf7/oK8Bi0kFYi0j0a6CCbS68geoZOyYi2a MRtkUAnmTB1/3/3NChkVivPyP7fm63gtA682wXY0= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Waiman Long , "Peter Zijlstra (Intel)" , Sasha Levin Subject: [PATCH 5.10 470/599] locking/lockdep: Iterate lock_classes directly when reading lockdep files Date: Tue, 5 Apr 2022 09:32:44 +0200 Message-Id: <20220405070312.813087664@linuxfoundation.org> X-Mailer: git-send-email 2.35.1 In-Reply-To: <20220405070258.802373272@linuxfoundation.org> References: <20220405070258.802373272@linuxfoundation.org> User-Agent: quilt/0.66 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=-2.0 required=5.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,RDNS_NONE,SPF_HELO_NONE,T_SCC_BODY_TEXT_LINE autolearn=no autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Waiman Long [ Upstream commit fb7275acd6fb988313dddd8d3d19efa70d9015ad ] When dumping lock_classes information via /proc/lockdep, we can't take the lockdep lock as the lock hold time is indeterminate. Iterating over all_lock_classes without holding lock can be dangerous as there is a slight chance that it may branch off to other lists leading to infinite loop or even access invalid memory if changes are made to all_lock_classes list in parallel. To avoid this problem, iteration of lock classes is now done directly on the lock_classes array itself. The lock_classes_in_use bitmap is checked to see if the lock class is being used. To avoid iterating the full array all the times, a new max_lock_class_idx value is added to track the maximum lock_class index that is currently being used. We can theoretically take the lockdep lock for iterating all_lock_classes when other lockdep files (lockdep_stats and lock_stat) are accessed as the lock hold time will be shorter for them. For consistency, they are also modified to iterate the lock_classes array directly. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220211035526.1329503-2-longman@redhat.com Signed-off-by: Sasha Levin --- kernel/locking/lockdep.c | 14 +++++--- kernel/locking/lockdep_internals.h | 6 ++-- kernel/locking/lockdep_proc.c | 51 +++++++++++++++++++++++++----- 3 files changed, 56 insertions(+), 15 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index aa758236ff6a..b6683cefe19a 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -182,11 +182,9 @@ static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES); static struct hlist_head lock_keys_hash[KEYHASH_SIZE]; unsigned long nr_lock_classes; unsigned long nr_zapped_classes; -#ifndef CONFIG_DEBUG_LOCKDEP -static -#endif +unsigned long max_lock_class_idx; struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; -static DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS); +DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS); static inline struct lock_class *hlock_class(struct held_lock *hlock) { @@ -337,7 +335,7 @@ static inline void lock_release_holdtime(struct held_lock *hlock) * elements. These elements are linked together by the lock_entry member in * struct lock_class. */ -LIST_HEAD(all_lock_classes); +static LIST_HEAD(all_lock_classes); static LIST_HEAD(free_lock_classes); /** @@ -1239,6 +1237,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) struct lockdep_subclass_key *key; struct hlist_head *hash_head; struct lock_class *class; + int idx; DEBUG_LOCKS_WARN_ON(!irqs_disabled()); @@ -1304,6 +1303,9 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) * of classes. */ list_move_tail(&class->lock_entry, &all_lock_classes); + idx = class - lock_classes; + if (idx > max_lock_class_idx) + max_lock_class_idx = idx; if (verbose(class)) { graph_unlock(); @@ -5919,6 +5921,8 @@ static void zap_class(struct pending_free *pf, struct lock_class *class) WRITE_ONCE(class->name, NULL); nr_lock_classes--; __clear_bit(class - lock_classes, lock_classes_in_use); + if (class - lock_classes == max_lock_class_idx) + max_lock_class_idx--; } else { WARN_ONCE(true, "%s() failed for class %s\n", __func__, class->name); diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index de49f9e1c11b..a19b01635347 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -121,7 +121,6 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) -extern struct list_head all_lock_classes; extern struct lock_chain lock_chains[]; #define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1) @@ -151,6 +150,10 @@ extern unsigned int nr_large_chain_blocks; extern unsigned int max_lockdep_depth; extern unsigned int max_bfs_queue_depth; +extern unsigned long max_lock_class_idx; + +extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; +extern unsigned long lock_classes_in_use[]; #ifdef CONFIG_PROVE_LOCKING extern unsigned long lockdep_count_forward_deps(struct lock_class *); @@ -205,7 +208,6 @@ struct lockdep_stats { }; DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats); -extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; #define __debug_atomic_inc(ptr) \ this_cpu_inc(lockdep_stats.ptr); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 02ef87f50df2..ccb5292d1e19 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -24,14 +24,33 @@ #include "lockdep_internals.h" +/* + * Since iteration of lock_classes is done without holding the lockdep lock, + * it is not safe to iterate all_lock_classes list directly as the iteration + * may branch off to free_lock_classes or the zapped list. Iteration is done + * directly on the lock_classes array by checking the lock_classes_in_use + * bitmap and max_lock_class_idx. + */ +#define iterate_lock_classes(idx, class) \ + for (idx = 0, class = lock_classes; idx <= max_lock_class_idx; \ + idx++, class++) + static void *l_next(struct seq_file *m, void *v, loff_t *pos) { - return seq_list_next(v, &all_lock_classes, pos); + struct lock_class *class = v; + + ++class; + *pos = class - lock_classes; + return (*pos > max_lock_class_idx) ? NULL : class; } static void *l_start(struct seq_file *m, loff_t *pos) { - return seq_list_start_head(&all_lock_classes, *pos); + unsigned long idx = *pos; + + if (idx > max_lock_class_idx) + return NULL; + return lock_classes + idx; } static void l_stop(struct seq_file *m, void *v) @@ -57,14 +76,16 @@ static void print_name(struct seq_file *m, struct lock_class *class) static int l_show(struct seq_file *m, void *v) { - struct lock_class *class = list_entry(v, struct lock_class, lock_entry); + struct lock_class *class = v; struct lock_list *entry; char usage[LOCK_USAGE_CHARS]; + int idx = class - lock_classes; - if (v == &all_lock_classes) { + if (v == lock_classes) seq_printf(m, "all lock classes:\n"); + + if (!test_bit(idx, lock_classes_in_use)) return 0; - } seq_printf(m, "%p", class->key); #ifdef CONFIG_DEBUG_LOCKDEP @@ -218,8 +239,11 @@ static int lockdep_stats_show(struct seq_file *m, void *v) #ifdef CONFIG_PROVE_LOCKING struct lock_class *class; + unsigned long idx; - list_for_each_entry(class, &all_lock_classes, lock_entry) { + iterate_lock_classes(idx, class) { + if (!test_bit(idx, lock_classes_in_use)) + continue; if (class->usage_mask == 0) nr_unused++; @@ -252,6 +276,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v) sum_forward_deps += lockdep_count_forward_deps(class); } + #ifdef CONFIG_DEBUG_LOCKDEP DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused); #endif @@ -343,6 +368,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v) seq_printf(m, " max bfs queue depth: %11u\n", max_bfs_queue_depth); #endif + seq_printf(m, " max lock class index: %11lu\n", + max_lock_class_idx); lockdep_stats_debug_show(m); seq_printf(m, " debug_locks: %11u\n", debug_locks); @@ -620,12 +647,16 @@ static int lock_stat_open(struct inode *inode, struct file *file) if (!res) { struct lock_stat_data *iter = data->stats; struct seq_file *m = file->private_data; + unsigned long idx; - list_for_each_entry(class, &all_lock_classes, lock_entry) { + iterate_lock_classes(idx, class) { + if (!test_bit(idx, lock_classes_in_use)) + continue; iter->class = class; iter->stats = lock_stats(class); iter++; } + data->iter_end = iter; sort(data->stats, data->iter_end - data->stats, @@ -643,6 +674,7 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct lock_class *class; + unsigned long idx; char c; if (count) { @@ -652,8 +684,11 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf, if (c != '0') return count; - list_for_each_entry(class, &all_lock_classes, lock_entry) + iterate_lock_classes(idx, class) { + if (!test_bit(idx, lock_classes_in_use)) + continue; clear_lock_stats(class); + } } return count; } -- 2.34.1