From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760836AbcDFDnn (ORCPT ); Tue, 5 Apr 2016 23:43:43 -0400 Received: from mail-pa0-f68.google.com ([209.85.220.68]:36612 "EHLO mail-pa0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753527AbcDFDnl (ORCPT ); Tue, 5 Apr 2016 23:43:41 -0400 From: Ming Lei To: Jens Axboe , linux-kernel@vger.kernel.org Cc: linux-block@vger.kernel.org, kent.overstreet@gmail.com, Christoph Hellwig , Eric Wheeler , Sebastian Roesner , Ming Lei , stable@vger.kernel.org (4.3+), Shaohua Li Subject: [PATCH v1] block: make sure big bio is splitted into at most 256 bvecs Date: Wed, 6 Apr 2016 11:43:32 +0800 Message-Id: <1459914212-9330-1-git-send-email-ming.lei@canonical.com> X-Mailer: git-send-email 1.9.1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org After arbitrary bio size is supported, the incoming bio may be very big. We have to split the bio into small bios so that each holds at most BIO_MAX_PAGES bvecs for safety reason, such as bio_clone(). This patch fixes the following kernel crash: > [ 172.660142] BUG: unable to handle kernel NULL pointer dereference at 0000000000000028 > [ 172.660229] IP: [] bio_trim+0xf/0x2a > [ 172.660289] PGD 7faf3e067 PUD 7f9279067 PMD 0 > [ 172.660399] Oops: 0000 [#1] SMP > [...] > [ 172.664780] Call Trace: > [ 172.664813] [] ? raid1_make_request+0x2e8/0xad7 [raid1] > [ 172.664846] [] ? blk_queue_split+0x377/0x3d4 > [ 172.664880] [] ? md_make_request+0xf6/0x1e9 [md_mod] > [ 172.664912] [] ? generic_make_request+0xb5/0x155 > [ 172.664947] [] ? prio_io+0x85/0x95 [bcache] > [ 172.664981] [] ? register_cache_set+0x355/0x8d0 [bcache] > [ 172.665016] [] ? register_bcache+0x1006/0x1174 [bcache] Fixes: 54efd50(block: make generic_make_request handle arbitrarily sized bios) Reported-by: Sebastian Roesner Reported-by: Eric Wheeler Cc: stable@vger.kernel.org (4.3+) Cc: Shaohua Li Cc: Kent Overstreet Signed-off-by: Ming Lei --- V1: - Kent pointed out that using max io size can't cover the case of non-full bvecs/pages The issue can be reproduced by the following approach: - create one raid1 over two virtio-blk - build bcache device over the above raid1 and another cache device and bucket size is set 2Mbytes - set cache mode as writeback - run random write over ext4 on the bcache device - then the crash can be triggered block/blk-merge.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/block/blk-merge.c b/block/blk-merge.c index 2613531..7b96471 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -94,8 +94,10 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, bool do_split = true; struct bio *new = NULL; const unsigned max_sectors = get_max_io_size(q, bio); + unsigned bvecs = 0; bio_for_each_segment(bv, bio, iter) { + bvecs++; /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. @@ -103,6 +105,23 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; + /* + * With arbitrary bio size, the incoming bio may be very + * big. We have to split the bio into small bios so that + * each holds at most BIO_MAX_PAGES bvecs because + * bio_clone() can fail to allocate big bvecs. + * + * It should have been better to apply the limit per + * request queue in which bio_clone() is involved, + * instead of globally. The biggest blocker is + * bio_clone() in bio bounce. + * + * TODO: deal with bio bounce's bio_clone() gracefully + * and convert the global limit into per-queue limit. + */ + if (bvecs >= BIO_MAX_PAGES) + goto split; + if (sectors + (bv.bv_len >> 9) > max_sectors) { /* * Consider this a new segment if we're splitting in -- 1.9.1