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=-9.8 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham 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 83948C432C3 for ; Wed, 27 Nov 2019 20:38:38 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 5342921780 for ; Wed, 27 Nov 2019 20:38:38 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1574887118; bh=zk/yj7nZce/1x8CxeZiDLu8VFD6lylu5eiLPJJaQATA=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=O8e3TRL2Fo1PUGXG70bh3RpE0ZgSX3FBMmoV+l9G9bFRjaiZnlyu5sxnwTiemwiTl duNVDRBlKVZxukj0M1rstLLBuolxqPJMnJhOToK3SCaBjQeMwc8EU9pN0vB0QiL5a3 uVS+WE/Jh9laQ1Be9XRArYbFCvOFWiCDaCpMahig= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727073AbfK0Uih (ORCPT ); Wed, 27 Nov 2019 15:38:37 -0500 Received: from mail.kernel.org ([198.145.29.99]:42382 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728768AbfK0Uig (ORCPT ); Wed, 27 Nov 2019 15:38:36 -0500 Received: from localhost (83-86-89-107.cable.dynamic.v4.ziggo.nl [83.86.89.107]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 15713215B2; Wed, 27 Nov 2019 20:38:35 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1574887115; bh=zk/yj7nZce/1x8CxeZiDLu8VFD6lylu5eiLPJJaQATA=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=X/0WhqRKSujptXrjDH+2b0Ua9POLWJJTnH8GhrU0t5372eSmYurWzjtiwX1xJb235 NYaqFajZBvpnjmCFlX1mwa+neSM40dS4lXaaSzpCOF6Lx3sIGHzsKrjooYlpUJqKqQ LBRqvSse6LXU21wSDilHvqLGI5CPEg/uxcXfNFGc= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Changwei Ge , Guozhonghua , Mark Fasheh , Joel Becker , Junxiao Bi , Joseph Qi , Andrew Morton , Linus Torvalds , Sasha Levin Subject: [PATCH 4.4 076/132] ocfs2: dont put and assigning null to bh allocated outside Date: Wed, 27 Nov 2019 21:31:07 +0100 Message-Id: <20191127203009.238856040@linuxfoundation.org> X-Mailer: git-send-email 2.24.0 In-Reply-To: <20191127202857.270233486@linuxfoundation.org> References: <20191127202857.270233486@linuxfoundation.org> User-Agent: quilt/0.66 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: stable-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: stable@vger.kernel.org From: Changwei Ge [ Upstream commit cf76c78595ca87548ca5e45c862ac9e0949c4687 ] ocfs2_read_blocks() and ocfs2_read_blocks_sync() are both used to read several blocks from disk. Currently, the input argument *bhs* can be NULL or NOT. It depends on the caller's behavior. If the function fails in reading blocks from disk, the corresponding bh will be assigned to NULL and put. Obviously, above process for non-NULL input bh is not appropriate. Because the caller doesn't even know its bhs are put and re-assigned. If buffer head is managed by caller, ocfs2_read_blocks and ocfs2_read_blocks_sync() should not evaluate it to NULL. It will cause caller accessing illegal memory, thus crash. Link: http://lkml.kernel.org/r/HK2PR06MB045285E0F4FBB561F9F2F9B3D5680@HK2PR06MB0452.apcprd06.prod.outlook.com Signed-off-by: Changwei Ge Reviewed-by: Guozhonghua Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Changwei Ge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/ocfs2/buffer_head_io.c | 77 ++++++++++++++++++++++++++++++--------- 1 file changed, 59 insertions(+), 18 deletions(-) diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 9ee8bcfbf00f3..92593179f7e2b 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -98,25 +98,34 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, return ret; } +/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it + * will be easier to handle read failure. + */ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, unsigned int nr, struct buffer_head *bhs[]) { int status = 0; unsigned int i; struct buffer_head *bh; + int new_bh = 0; trace_ocfs2_read_blocks_sync((unsigned long long)block, nr); if (!nr) goto bail; + /* Don't put buffer head and re-assign it to NULL if it is allocated + * outside since the caller can't be aware of this alternation! + */ + new_bh = (bhs[0] == NULL); + for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { bhs[i] = sb_getblk(osb->sb, block++); if (bhs[i] == NULL) { status = -ENOMEM; mlog_errno(status); - goto bail; + break; } } bh = bhs[i]; @@ -151,9 +160,26 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, submit_bh(READ, bh); } +read_failure: for (i = nr; i > 0; i--) { bh = bhs[i - 1]; + if (unlikely(status)) { + if (new_bh && bh) { + /* If middle bh fails, let previous bh + * finish its read and then put it to + * aovoid bh leak + */ + if (!buffer_jbd(bh)) + wait_on_buffer(bh); + put_bh(bh); + bhs[i - 1] = NULL; + } else if (bh && buffer_uptodate(bh)) { + clear_buffer_uptodate(bh); + } + continue; + } + /* No need to wait on the buffer if it's managed by JBD. */ if (!buffer_jbd(bh)) wait_on_buffer(bh); @@ -163,8 +189,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, * so we can safely record this and loop back * to cleanup the other buffers. */ status = -EIO; - put_bh(bh); - bhs[i - 1] = NULL; + goto read_failure; } } @@ -172,6 +197,9 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, return status; } +/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it + * will be easier to handle read failure. + */ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, struct buffer_head *bhs[], int flags, int (*validate)(struct super_block *sb, @@ -181,6 +209,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, int i, ignore_cache = 0; struct buffer_head *bh; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); + int new_bh = 0; trace_ocfs2_read_blocks_begin(ci, (unsigned long long)block, nr, flags); @@ -206,6 +235,11 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, goto bail; } + /* Don't put buffer head and re-assign it to NULL if it is allocated + * outside since the caller can't be aware of this alternation! + */ + new_bh = (bhs[0] == NULL); + ocfs2_metadata_cache_io_lock(ci); for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { @@ -214,7 +248,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, ocfs2_metadata_cache_io_unlock(ci); status = -ENOMEM; mlog_errno(status); - goto bail; + /* Don't forget to put previous bh! */ + break; } } bh = bhs[i]; @@ -308,16 +343,27 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, } } - status = 0; - +read_failure: for (i = (nr - 1); i >= 0; i--) { bh = bhs[i]; if (!(flags & OCFS2_BH_READAHEAD)) { - if (status) { - /* Clear the rest of the buffers on error */ - put_bh(bh); - bhs[i] = NULL; + if (unlikely(status)) { + /* Clear the buffers on error including those + * ever succeeded in reading + */ + if (new_bh && bh) { + /* If middle bh fails, let previous bh + * finish its read and then put it to + * aovoid bh leak + */ + if (!buffer_jbd(bh)) + wait_on_buffer(bh); + put_bh(bh); + bhs[i] = NULL; + } else if (bh && buffer_uptodate(bh)) { + clear_buffer_uptodate(bh); + } continue; } /* We know this can't have changed as we hold the @@ -335,9 +381,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, * uptodate. */ status = -EIO; clear_buffer_needs_validate(bh); - put_bh(bh); - bhs[i] = NULL; - continue; + goto read_failure; } if (buffer_needs_validate(bh)) { @@ -347,11 +391,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, BUG_ON(buffer_jbd(bh)); clear_buffer_needs_validate(bh); status = validate(sb, bh); - if (status) { - put_bh(bh); - bhs[i] = NULL; - continue; - } + if (status) + goto read_failure; } } -- 2.20.1