From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755286AbbLIJqX (ORCPT ); Wed, 9 Dec 2015 04:46:23 -0500 Received: from youngberry.canonical.com ([91.189.89.112]:45566 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753889AbbLIJmA (ORCPT ); Wed, 9 Dec 2015 04:42:00 -0500 From: Luis Henriques To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: NeilBrown , Luis Henriques Subject: [PATCH 3.16.y-ckt 117/126] md/raid0: update queue parameter in a safer location. Date: Wed, 9 Dec 2015 09:38:07 +0000 Message-Id: <1449653896-5236-118-git-send-email-luis.henriques@canonical.com> In-Reply-To: <1449653896-5236-1-git-send-email-luis.henriques@canonical.com> References: <1449653896-5236-1-git-send-email-luis.henriques@canonical.com> X-Extended-Stable: 3.16 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.16.7-ckt21 -stable review patch. If anyone has any objections, please let me know. ------------------ From: NeilBrown commit 199dc6ed5179251fa6158a461499c24bdd99c836 upstream. When a (e.g.) RAID5 array is reshaped to RAID0, the updating of queue parameters (e.g. max number of sectors per bio) is done in the wrong place. It should be part of ->run, but it is actually part of ->takeover. This means it happens before level_store() calls: blk_set_stacking_limits(&mddev->queue->limits); and so it ineffective. This can lead to errors from underlying devices. So move all the relevant settings out of create_stripe_zones() and into raid0_run(). As this can lead to a bug-on it is suitable for any -stable kernel which supports reshape to RAID0. So 2.6.35 or later. As the bug has been present for five years there is no urgency, so no need to rush into -stable. Fixes: 9af204cf720c ("md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover") Reported-by: Yi Zhang Signed-off-by: NeilBrown [ luis: backported to 3.16: - raid0 isn't accessed from dm-raid so no conditional mddev->queue accesses (done with commit 753f2856cda2 "md raid0: access mddev->queue (request queue member) conditionally because it is not set when accessed from dm-raid") - adjusted context ] Signed-off-by: Luis Henriques --- drivers/md/raid0.c | 66 +++++++++++++++++++++++++++++------------------------- 1 file changed, 36 insertions(+), 30 deletions(-) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 9afd00b45f83..3d6b97b6dc6f 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -88,7 +88,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) char b[BDEVNAME_SIZE]; char b2[BDEVNAME_SIZE]; struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); - bool discard_supported = false; + unsigned short blksize = 512; if (!conf) return -ENOMEM; @@ -103,6 +103,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) sector_div(sectors, mddev->chunk_sectors); rdev1->sectors = sectors * mddev->chunk_sectors; + blksize = max(blksize, queue_logical_block_size( + rdev1->bdev->bd_disk->queue)); + rdev_for_each(rdev2, mddev) { pr_debug("md/raid0:%s: comparing %s(%llu)" " with %s(%llu)\n", @@ -139,6 +142,18 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) } pr_debug("md/raid0:%s: FINAL %d zones\n", mdname(mddev), conf->nr_strip_zones); + /* + * now since we have the hard sector sizes, we can make sure + * chunk size is a multiple of that sector size + */ + if ((mddev->chunk_sectors << 9) % blksize) { + printk(KERN_ERR "md/raid0:%s: chunk_size of %d not multiple of block size %d\n", + mdname(mddev), + mddev->chunk_sectors << 9, blksize); + err = -EINVAL; + goto abort; + } + err = -ENOMEM; conf->strip_zone = kzalloc(sizeof(struct strip_zone)* conf->nr_strip_zones, GFP_KERNEL); @@ -193,18 +208,12 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) } dev[j] = rdev1; - disk_stack_limits(mddev->gendisk, rdev1->bdev, - rdev1->data_offset << 9); - if (rdev1->bdev->bd_disk->queue->merge_bvec_fn) conf->has_merge_bvec = 1; if (!smallest || (rdev1->sectors < smallest->sectors)) smallest = rdev1; cnt++; - - if (blk_queue_discard(bdev_get_queue(rdev1->bdev))) - discard_supported = true; } if (cnt != mddev->raid_disks) { printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - " @@ -267,26 +276,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) mddev->queue->backing_dev_info.congested_fn = raid0_congested; mddev->queue->backing_dev_info.congested_data = mddev; - /* - * now since we have the hard sector sizes, we can make sure - * chunk size is a multiple of that sector size - */ - if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) { - printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n", - mdname(mddev), - mddev->chunk_sectors << 9); - goto abort; - } - - blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); - blk_queue_io_opt(mddev->queue, - (mddev->chunk_sectors << 9) * mddev->raid_disks); - - if (!discard_supported) - queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); - else - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); - pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; @@ -429,6 +418,8 @@ static int raid0_run(struct mddev *mddev) { struct r0conf *conf; int ret; + struct md_rdev *rdev; + bool discard_supported = false; if (mddev->chunk_sectors == 0) { printk(KERN_ERR "md/raid0:%s: chunk size must be set.\n", @@ -437,9 +428,6 @@ static int raid0_run(struct mddev *mddev) } if (md_check_no_bitmap(mddev)) return -EINVAL; - blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { @@ -449,6 +437,24 @@ static int raid0_run(struct mddev *mddev) mddev->private = conf; } conf = mddev->private; + rdev_for_each(rdev, mddev) { + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + if (blk_queue_discard(bdev_get_queue(rdev->bdev))) + discard_supported = true; + } + blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + + blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); + blk_queue_io_opt(mddev->queue, + (mddev->chunk_sectors << 9) * mddev->raid_disks); + + if (!discard_supported) + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + else + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); /* calculate array device size */ md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));