From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-19.4 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS, URIBL_BLOCKED,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 10F01C11F69 for ; Mon, 12 Jul 2021 08:25:27 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id ED0106121E for ; Mon, 12 Jul 2021 08:25:26 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1347957AbhGLI1q (ORCPT ); Mon, 12 Jul 2021 04:27:46 -0400 Received: from mail.kernel.org ([198.145.29.99]:46796 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1347970AbhGLHk3 (ORCPT ); Mon, 12 Jul 2021 03:40:29 -0400 Received: by mail.kernel.org (Postfix) with ESMTPSA id A368F60724; Mon, 12 Jul 2021 07:37:19 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1626075440; bh=98EcQETqPwe1ACPUn42K4UojE0FiMjoZHJbXehKdTQo=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=J1FjQJukpXNq10xaFbKyk1mXtkWBuE9z5Hyri1wTmWI8m8U9n3jHeoMC6rNGnVsp/ iPlrcsWnyhwyiAzetScJ0R/X32IekWMr6THOlSk5LQvUsoRM0GxliTRXMwqcWv/L7r kpD91mKkyhxZfFadvIxZOx4O1jQbsJfiTW4em1vw= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, John Garry , David Jeffery , Bart Van Assche , Ming Lei , Jens Axboe , Sasha Levin Subject: [PATCH 5.13 221/800] blk-mq: clear stale request in tags->rq[] before freeing one request pool Date: Mon, 12 Jul 2021 08:04:04 +0200 Message-Id: <20210712060944.966643305@linuxfoundation.org> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210712060912.995381202@linuxfoundation.org> References: <20210712060912.995381202@linuxfoundation.org> User-Agent: quilt/0.66 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Ming Lei [ Upstream commit bd63141d585bef14f4caf111f6d0e27fe2300ec6 ] refcount_inc_not_zero() in bt_tags_iter() still may read one freed request. Fix the issue by the following approach: 1) hold a per-tags spinlock when reading ->rqs[tag] and calling refcount_inc_not_zero in bt_tags_iter() 2) clearing stale request referred via ->rqs[tag] before freeing request pool, the per-tags spinlock is held for clearing stale ->rq[tag] So after we cleared stale requests, bt_tags_iter() won't observe freed request any more, also the clearing will wait for pending request reference. The idea of clearing ->rqs[] is borrowed from John Garry's previous patch and one recent David's patch. Tested-by: John Garry Reviewed-by: David Jeffery Reviewed-by: Bart Van Assche Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20210511152236.763464-4-ming.lei@redhat.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-mq-tag.c | 9 +++++++-- block/blk-mq-tag.h | 6 ++++++ block/blk-mq.c | 46 +++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 54 insertions(+), 7 deletions(-) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 544edf2c56a5..1671dae43030 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -202,10 +202,14 @@ struct bt_iter_data { static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, unsigned int bitnr) { - struct request *rq = tags->rqs[bitnr]; + struct request *rq; + unsigned long flags; + spin_lock_irqsave(&tags->lock, flags); + rq = tags->rqs[bitnr]; if (!rq || !refcount_inc_not_zero(&rq->ref)) - return NULL; + rq = NULL; + spin_unlock_irqrestore(&tags->lock, flags); return rq; } @@ -538,6 +542,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; + spin_lock_init(&tags->lock); if (blk_mq_is_sbitmap_shared(flags)) return tags; diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 7d3e6b333a4a..f887988e5ef6 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -20,6 +20,12 @@ struct blk_mq_tags { struct request **rqs; struct request **static_rqs; struct list_head page_list; + + /* + * used to clear request reference in rqs[] before freeing one + * request pool + */ + spinlock_t lock; }; extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, diff --git a/block/blk-mq.c b/block/blk-mq.c index debfa5cd8025..dd371f321d35 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2307,6 +2307,45 @@ queue_exit: return BLK_QC_T_NONE; } +static size_t order_to_size(unsigned int order) +{ + return (size_t)PAGE_SIZE << order; +} + +/* called before freeing request pool in @tags */ +static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set, + struct blk_mq_tags *tags, unsigned int hctx_idx) +{ + struct blk_mq_tags *drv_tags = set->tags[hctx_idx]; + struct page *page; + unsigned long flags; + + list_for_each_entry(page, &tags->page_list, lru) { + unsigned long start = (unsigned long)page_address(page); + unsigned long end = start + order_to_size(page->private); + int i; + + for (i = 0; i < set->queue_depth; i++) { + struct request *rq = drv_tags->rqs[i]; + unsigned long rq_addr = (unsigned long)rq; + + if (rq_addr >= start && rq_addr < end) { + WARN_ON_ONCE(refcount_read(&rq->ref) != 0); + cmpxchg(&drv_tags->rqs[i], rq, NULL); + } + } + } + + /* + * Wait until all pending iteration is done. + * + * Request reference is cleared and it is guaranteed to be observed + * after the ->lock is released. + */ + spin_lock_irqsave(&drv_tags->lock, flags); + spin_unlock_irqrestore(&drv_tags->lock, flags); +} + void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { @@ -2325,6 +2364,8 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, } } + blk_mq_clear_rq_mapping(set, tags, hctx_idx); + while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); @@ -2384,11 +2425,6 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, return tags; } -static size_t order_to_size(unsigned int order) -{ - return (size_t)PAGE_SIZE << order; -} - static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, int node) { -- 2.30.2