| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <2025050716-lunar-grimy-9783@gregkh>
Date: Wed, 7 May 2025 10:38:24 +0200
From: Greg KH <gregkh@...uxfoundation.org>
To: Salvatore Bonaccorso <carnil@...ian.org>
Cc: Yu Kuai <yukuai1@...weicloud.com>, stable@...r.kernel.org,
song@...nel.org, linux-raid@...r.kernel.org,
linux-kernel@...r.kernel.org, yukuai3@...wei.com,
yi.zhang@...wei.com, yangerkun@...wei.com, johnny.chenyi@...wei.com
Subject: Re: [PATCH v6.1] md: move initialization and destruction of
'io_acct_set' to md.c
On Tue, May 06, 2025 at 09:16:54PM +0200, Salvatore Bonaccorso wrote:
> Hi,
>
> On Tue, May 06, 2025 at 09:24:17AM +0800, Yu Kuai wrote:
> > From: Yu Kuai <yukuai3@...wei.com>
> >
> > commit c567c86b90d4715081adfe5eb812141a5b6b4883 upstream.
> >
> > 'io_acct_set' is only used for raid0 and raid456, prepare to use it for
> > raid1 and raid10, so that io accounting from different levels can be
> > consistent.
> >
> > By the way, follow up patches will also use this io clone mechanism to
> > make sure 'active_io' represents in flight io, not io that is dispatching,
> > so that mddev_suspend will wait for io to be done as designed.
> >
> > Signed-off-by: Yu Kuai <yukuai3@...wei.com>
> > Reviewed-by: Xiao Ni <xni@...hat.com>
> > Signed-off-by: Song Liu <song@...nel.org>
> > Link: https://lore.kernel.org/r/20230621165110.1498313-2-yukuai1@huaweicloud.com
> > [Yu Kuai: This is the relied patch for commit 4a05f7ae3371 ("md/raid10:
> > fix missing discard IO accounting"), kernel will panic while issuing
> > discard to raid10 without this patch]
> > Signed-off-by: Yu Kuai <yukuai3@...wei.com>
> > ---
> > drivers/md/md.c | 27 ++++++++++-----------------
> > drivers/md/md.h | 2 --
> > drivers/md/raid0.c | 16 ++--------------
> > drivers/md/raid5.c | 41 +++++++++++------------------------------
> > 4 files changed, 23 insertions(+), 63 deletions(-)
> >
> > diff --git a/drivers/md/md.c b/drivers/md/md.c
> > index d5fbccc72810..a9fcfcbc2d11 100644
> > --- a/drivers/md/md.c
> > +++ b/drivers/md/md.c
> > @@ -5965,6 +5965,13 @@ int md_run(struct mddev *mddev)
> > goto exit_bio_set;
> > }
> >
> > + if (!bioset_initialized(&mddev->io_acct_set)) {
> > + err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE,
> > + offsetof(struct md_io_acct, bio_clone), 0);
> > + if (err)
> > + goto exit_sync_set;
> > + }
> > +
> > spin_lock(&pers_lock);
> > pers = find_pers(mddev->level, mddev->clevel);
> > if (!pers || !try_module_get(pers->owner)) {
> > @@ -6142,6 +6149,8 @@ int md_run(struct mddev *mddev)
> > module_put(pers->owner);
> > md_bitmap_destroy(mddev);
> > abort:
> > + bioset_exit(&mddev->io_acct_set);
> > +exit_sync_set:
> > bioset_exit(&mddev->sync_set);
> > exit_bio_set:
> > bioset_exit(&mddev->bio_set);
> > @@ -6374,6 +6383,7 @@ static void __md_stop(struct mddev *mddev)
> > percpu_ref_exit(&mddev->active_io);
> > bioset_exit(&mddev->bio_set);
> > bioset_exit(&mddev->sync_set);
> > + bioset_exit(&mddev->io_acct_set);
> > }
> >
> > void md_stop(struct mddev *mddev)
> > @@ -8744,23 +8754,6 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
> > }
> > EXPORT_SYMBOL_GPL(md_submit_discard_bio);
> >
> > -int acct_bioset_init(struct mddev *mddev)
> > -{
> > - int err = 0;
> > -
> > - if (!bioset_initialized(&mddev->io_acct_set))
> > - err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE,
> > - offsetof(struct md_io_acct, bio_clone), 0);
> > - return err;
> > -}
> > -EXPORT_SYMBOL_GPL(acct_bioset_init);
> > -
> > -void acct_bioset_exit(struct mddev *mddev)
> > -{
> > - bioset_exit(&mddev->io_acct_set);
> > -}
> > -EXPORT_SYMBOL_GPL(acct_bioset_exit);
> > -
> > static void md_end_io_acct(struct bio *bio)
> > {
> > struct md_io_acct *md_io_acct = bio->bi_private;
> > diff --git a/drivers/md/md.h b/drivers/md/md.h
> > index 4f0b48097455..1fda5e139beb 100644
> > --- a/drivers/md/md.h
> > +++ b/drivers/md/md.h
> > @@ -746,8 +746,6 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
> > extern void md_finish_reshape(struct mddev *mddev);
> > void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
> > struct bio *bio, sector_t start, sector_t size);
> > -int acct_bioset_init(struct mddev *mddev);
> > -void acct_bioset_exit(struct mddev *mddev);
> > void md_account_bio(struct mddev *mddev, struct bio **bio);
> >
> > extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
> > diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
> > index 7c6a0b4437d8..c50a7abda744 100644
> > --- a/drivers/md/raid0.c
> > +++ b/drivers/md/raid0.c
> > @@ -377,7 +377,6 @@ static void raid0_free(struct mddev *mddev, void *priv)
> > struct r0conf *conf = priv;
> >
> > free_conf(mddev, conf);
> > - acct_bioset_exit(mddev);
> > }
> >
> > static int raid0_run(struct mddev *mddev)
> > @@ -392,16 +391,11 @@ static int raid0_run(struct mddev *mddev)
> > if (md_check_no_bitmap(mddev))
> > return -EINVAL;
> >
> > - if (acct_bioset_init(mddev)) {
> > - pr_err("md/raid0:%s: alloc acct bioset failed.\n", mdname(mddev));
> > - return -ENOMEM;
> > - }
> > -
> > /* if private is not null, we are here after takeover */
> > if (mddev->private == NULL) {
> > ret = create_strip_zones(mddev, &conf);
> > if (ret < 0)
> > - goto exit_acct_set;
> > + return ret;
> > mddev->private = conf;
> > }
> > conf = mddev->private;
> > @@ -432,15 +426,9 @@ static int raid0_run(struct mddev *mddev)
> >
> > ret = md_integrity_register(mddev);
> > if (ret)
> > - goto free;
> > + free_conf(mddev, conf);
> >
> > return ret;
> > -
> > -free:
> > - free_conf(mddev, conf);
> > -exit_acct_set:
> > - acct_bioset_exit(mddev);
> > - return ret;
> > }
> >
> > /*
> > diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
> > index 4315dabd3202..6e80a439ec45 100644
> > --- a/drivers/md/raid5.c
> > +++ b/drivers/md/raid5.c
> > @@ -7770,19 +7770,12 @@ static int raid5_run(struct mddev *mddev)
> > struct md_rdev *rdev;
> > struct md_rdev *journal_dev = NULL;
> > sector_t reshape_offset = 0;
> > - int i, ret = 0;
> > + int i;
> > long long min_offset_diff = 0;
> > int first = 1;
> >
> > - if (acct_bioset_init(mddev)) {
> > - pr_err("md/raid456:%s: alloc acct bioset failed.\n", mdname(mddev));
> > + if (mddev_init_writes_pending(mddev) < 0)
> > return -ENOMEM;
> > - }
> > -
> > - if (mddev_init_writes_pending(mddev) < 0) {
> > - ret = -ENOMEM;
> > - goto exit_acct_set;
> > - }
> >
> > if (mddev->recovery_cp != MaxSector)
> > pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
> > @@ -7813,8 +7806,7 @@ static int raid5_run(struct mddev *mddev)
> > (mddev->bitmap_info.offset || mddev->bitmap_info.file)) {
> > pr_notice("md/raid:%s: array cannot have both journal and bitmap\n",
> > mdname(mddev));
> > - ret = -EINVAL;
> > - goto exit_acct_set;
> > + return -EINVAL;
> > }
> >
> > if (mddev->reshape_position != MaxSector) {
> > @@ -7839,15 +7831,13 @@ static int raid5_run(struct mddev *mddev)
> > if (journal_dev) {
> > pr_warn("md/raid:%s: don't support reshape with journal - aborting.\n",
> > mdname(mddev));
> > - ret = -EINVAL;
> > - goto exit_acct_set;
> > + return -EINVAL;
> > }
> >
> > if (mddev->new_level != mddev->level) {
> > pr_warn("md/raid:%s: unsupported reshape required - aborting.\n",
> > mdname(mddev));
> > - ret = -EINVAL;
> > - goto exit_acct_set;
> > + return -EINVAL;
> > }
> > old_disks = mddev->raid_disks - mddev->delta_disks;
> > /* reshape_position must be on a new-stripe boundary, and one
> > @@ -7863,8 +7853,7 @@ static int raid5_run(struct mddev *mddev)
> > if (sector_div(here_new, chunk_sectors * new_data_disks)) {
> > pr_warn("md/raid:%s: reshape_position not on a stripe boundary\n",
> > mdname(mddev));
> > - ret = -EINVAL;
> > - goto exit_acct_set;
> > + return -EINVAL;
> > }
> > reshape_offset = here_new * chunk_sectors;
> > /* here_new is the stripe we will write to */
> > @@ -7886,8 +7875,7 @@ static int raid5_run(struct mddev *mddev)
> > else if (mddev->ro == 0) {
> > pr_warn("md/raid:%s: in-place reshape must be started in read-only mode - aborting\n",
> > mdname(mddev));
> > - ret = -EINVAL;
> > - goto exit_acct_set;
> > + return -EINVAL;
> > }
> > } else if (mddev->reshape_backwards
> > ? (here_new * chunk_sectors + min_offset_diff <=
> > @@ -7897,8 +7885,7 @@ static int raid5_run(struct mddev *mddev)
> > /* Reading from the same stripe as writing to - bad */
> > pr_warn("md/raid:%s: reshape_position too early for auto-recovery - aborting.\n",
> > mdname(mddev));
> > - ret = -EINVAL;
> > - goto exit_acct_set;
> > + return -EINVAL;
> > }
> > pr_debug("md/raid:%s: reshape will continue\n", mdname(mddev));
> > /* OK, we should be able to continue; */
> > @@ -7922,10 +7909,8 @@ static int raid5_run(struct mddev *mddev)
> > else
> > conf = mddev->private;
> >
> > - if (IS_ERR(conf)) {
> > - ret = PTR_ERR(conf);
> > - goto exit_acct_set;
> > - }
> > + if (IS_ERR(conf))
> > + return PTR_ERR(conf);
> >
> > if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
> > if (!journal_dev) {
> > @@ -8125,10 +8110,7 @@ static int raid5_run(struct mddev *mddev)
> > free_conf(conf);
> > mddev->private = NULL;
> > pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
> > - ret = -EIO;
> > -exit_acct_set:
> > - acct_bioset_exit(mddev);
> > - return ret;
> > + return -EIO;
> > }
> >
> > static void raid5_free(struct mddev *mddev, void *priv)
> > @@ -8136,7 +8118,6 @@ static void raid5_free(struct mddev *mddev, void *priv)
> > struct r5conf *conf = priv;
> >
> > free_conf(conf);
> > - acct_bioset_exit(mddev);
> > mddev->to_remove = &raid5_attrs_group;
> > }
> >
> > --
> > 2.39.2
>
> FWIW, this was tested for people in Debian affected by
> https://bugs.debian.org/1104460 .
Thanks for the debugging, now queued up!
Powered by blists - more mailing lists