From: Yu Kuai yukuai3@huawei.com

mainline inclusion from mainline-v6.3-rc1 commit e5cfefa97bccf956ea0bb6464c1f6c84fd7a8d9f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6MQLP CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

As explained in commit 36369f46e917 ("block: Do not reread partition table on exclusively open device"), reread partition on the device that is exclusively opened by someone else is problematic.

This patch will make sure partition scan will only be proceed if current thread open the device exclusively, or the device is not opened exclusively, and in the later case, other scanners and exclusive openers will be blocked temporarily until partition scan is done.

Fixes: 10c70d95c0f2 ("block: remove the bd_openers checks in blk_drop_partitions") Cc: stable@vger.kernel.org Suggested-by: Jan Kara jack@suse.cz Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20230217022200.3092987-3-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe axboe@kernel.dk

Conflicts: block/genhd.c block/ioctl.c Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Hou Tao houtao1@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- block/genhd.c | 38 ++++++++++++++++++++++++++++++++++---- block/ioctl.c | 2 +- 2 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c index f224381ed46f..b6ad3554876f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -739,16 +739,42 @@ static void register_disk(struct device *parent, struct gendisk *disk, int disk_scan_partitions(struct gendisk *disk, fmode_t mode) { struct block_device *bdev; + struct block_device *claim; + int ret = 0;

if (!disk_part_scan_enabled(disk)) return -EINVAL;

+ /* + * If the device is opened exclusively by current thread already, it's + * safe to scan partitons, otherwise, use bd_prepare_to_claim() to + * synchronize with other exclusive openers and other partition + * scanners. + */ + if (!(mode & FMODE_EXCL)) { + claim = bdget_part(&disk->part0); + if (!claim) + return -ENOMEM; + + ret = bd_prepare_to_claim(claim, claim, disk_scan_partitions); + if (ret) { + bdput(claim); + return ret; + } + } + set_bit(GD_NEED_PART_SCAN, &disk->state); - bdev = blkdev_get_by_dev(disk_devt(disk), mode, NULL); + bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL); if (IS_ERR(bdev)) - return PTR_ERR(bdev); - blkdev_put(bdev, mode); - return 0; + ret = PTR_ERR(bdev); + else + blkdev_put(bdev, mode); + + if (!(mode & FMODE_EXCL)) { + bd_abort_claiming(claim, claim, disk_scan_partitions); + bdput(claim); + } + return ret; }

static void disk_init_partition(struct gendisk *disk) @@ -850,6 +876,10 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, disk_add_events(disk); blk_integrity_add(disk);

+ /* Make sure the first partition scan will be proceed */ + if (get_capacity(disk) && disk_part_scan_enabled(disk)) + set_bit(GD_NEED_PART_SCAN, &disk->state); + /* * Set the flag at last, so that block devcie can't be opened * before it's registration is done. diff --git a/block/ioctl.c b/block/ioctl.c index 565d43c9addd..e3c5a27c23b1 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -543,7 +543,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, return -EINVAL; if (bdev->bd_part_count) return -EBUSY; - return disk_scan_partitions(bdev->bd_disk, mode & ~FMODE_EXCL); + return disk_scan_partitions(bdev->bd_disk, mode); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACETEARDOWN:

From: Guoqing Jiang guoqing.jiang@linux.dev

mainline inclusion from mainline-v6.0-rc1 commit 9dfbdafda3b34e262e43e786077bab8e476a89d1 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6OMCC CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?h...

--------------------------------

Since the bug which commit 8b48ec23cc51a ("md: don't unregister sync_thread with reconfig_mutex held") fixed is related with action_store path, other callers which reap sync_thread didn't need to be changed.

Let's pull md_unregister_thread from md_reap_sync_thread, then fix previous bug with belows.

1. unlock mddev before md_reap_sync_thread in action_store. 2. save reshape_position before unlock, then restore it to ensure position not changed accidentally by others.

Signed-off-by: Guoqing Jiang guoqing.jiang@linux.dev Signed-off-by: Song Liu song@kernel.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Hou Tao houtao1@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- drivers/md/dm-raid.c | 1 + drivers/md/md.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index a2d09c9c6e9f..134c51027dce 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3693,6 +3693,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv, if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) { if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); } } else if (decipher_sync_action(mddev, mddev->recovery) != st_idle) diff --git a/drivers/md/md.c b/drivers/md/md.c index e072ccb08735..cf7ca756b216 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4872,6 +4872,19 @@ action_store(struct mddev *mddev, const char *page, size_t len) if (work_pending(&mddev->del_work)) flush_workqueue(md_misc_wq); if (mddev->sync_thread) { + sector_t save_rp = mddev->reshape_position; + + mddev_unlock(mddev); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); + mddev_lock_nointr(mddev); + /* + * set RECOVERY_INTR again and restore reshape + * position in case others changed them after + * got lock, eg, reshape_position_store and + * md_check_recovery. + */ + mddev->reshape_position = save_rp; set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_reap_sync_thread(mddev); } @@ -6251,6 +6264,7 @@ static void __md_stop_writes(struct mddev *mddev) flush_workqueue(md_misc_wq); if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); }

@@ -9321,6 +9335,7 @@ void md_check_recovery(struct mddev *mddev) * ->spare_active and clear saved_raid_disk */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); @@ -9356,6 +9371,7 @@ void md_check_recovery(struct mddev *mddev) goto unlock; } if (mddev->sync_thread) { + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); goto unlock; } @@ -9435,8 +9451,7 @@ void md_reap_sync_thread(struct mddev *mddev) sector_t old_dev_sectors = mddev->dev_sectors; bool is_reshaped = false;

- /* resync has finished, collect result */ - md_unregister_thread(&mddev->sync_thread); + /* sync_thread should be unregistered, collect result */ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && mddev->degraded != mddev->raid_disks) {

From: Yu Kuai yukuai3@huawei.com

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6OMCC CVE: NA

--------------------------------

Prepare to handle 'idle' and 'frozen' differently to fix a deadlock, there are no functional changes except that MD_RECOVERY_RUNNING is checked again after 'reconfig_mutex' is held.

Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Hou Tao houtao1@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- drivers/md/md.c | 61 ++++++++++++++++++++++++++++++++++++------------- 1 file changed, 45 insertions(+), 16 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c index e072ccb08735..e02b18205d86 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4855,6 +4855,46 @@ action_show(struct mddev *mddev, char *page) return sprintf(page, "%s\n", type); }

+static void stop_sync_thread(struct mddev *mddev) +{ + if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + return; + + if (mddev_lock(mddev)) + return; + + /* + * Check again in case MD_RECOVERY_RUNNING is cleared before lock is + * held. + */ + if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { + mddev_unlock(mddev); + return; + } + + if (work_pending(&mddev->del_work)) + flush_workqueue(md_misc_wq); + + if (mddev->sync_thread) { + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_reap_sync_thread(mddev); + } + + mddev_unlock(mddev); +} + +static void idle_sync_thread(struct mddev *mddev) +{ + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + stop_sync_thread(mddev); +} + +static void frozen_sync_thread(struct mddev *mddev) +{ + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + stop_sync_thread(mddev); +} + static ssize_t action_store(struct mddev *mddev, const char *page, size_t len) { @@ -4862,22 +4902,11 @@ action_store(struct mddev *mddev, const char *page, size_t len) return -EINVAL;

- if (cmd_match(page, "idle") || cmd_match(page, "frozen")) { - if (cmd_match(page, "frozen")) - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - else - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && - mddev_lock(mddev) == 0) { - if (work_pending(&mddev->del_work)) - flush_workqueue(md_misc_wq); - if (mddev->sync_thread) { - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_reap_sync_thread(mddev); - } - mddev_unlock(mddev); - } - } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + if (cmd_match(page, "idle")) + idle_sync_thread(mddev); + else if (cmd_match(page, "frozen")) + frozen_sync_thread(mddev); + else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; else if (cmd_match(page, "resync")) clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);

From: Yu Kuai yukuai3@huawei.com

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6OMCC CVE: NA

--------------------------------

Our test found a following deadlock in raid10:

1) Issue a normal write, and such write failed:

raid10_end_write_request set_bit(R10BIO_WriteError, &r10_bio->state) one_write_done reschedule_retry

// later from md thread raid10d handle_write_completed list_add(&r10_bio->retry_list, &conf->bio_end_io_list)

// later from md thread raid10d if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) list_move(conf->bio_end_io_list.prev, &tmp) r10_bio = list_first_entry(&tmp, struct r10bio, retry_list) raid_end_bio_io(r10_bio)

Dependency chain 1: normal io is waiting for updating superblock

2) Trigger a recovery:

raid10_sync_request raise_barrier

Dependency chain 2: sync thread is waiting for normal io

3) echo idle/frozen to sync_action:

action_store mddev_lock md_unregister_thread kthread_stop

Dependency chain 3: drop 'reconfig_mutex' is waiting for sync thread

4) md thread can't update superblock:

raid10d md_check_recovery if (mddev_trylock(mddev)) md_update_sb

Dependency chain 4: update superblock is waiting for 'reconfig_mutex'

Hence cyclic dependency exist, in order to fix the problem, we must break one of them. Dependency 1 and 2 can't be broken because they are foundation design. Dependency 4 may be possible if it can be guaranteed that no io can be inflight, however, this requires a new mechanism which seems complex. Dependency 3 is a good choice, because idle/frozen only requires sync thread to finish, which can be done asynchronously that is already implemented, and 'reconfig_mutex' is not needed anymore.

This patch switch 'idle' and 'frozen' to wait sync thread to be done asynchronously, and this patch also add a sequence counter to record how many times sync thread is done, so that 'idle' won't keep waiting on new started sync thread.

Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Hou Tao houtao1@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- drivers/md/md.c | 24 ++++++++++++++++++++---- drivers/md/md.h | 2 ++ 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c index a04485cdae29..abf58ef633a3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -697,6 +697,7 @@ void mddev_init(struct mddev *mddev) atomic_set(&mddev->active, 1); atomic_set(&mddev->openers, 0); atomic_set(&mddev->active_io, 0); + atomic_set(&mddev->sync_seq, 0); spin_lock_init(&mddev->lock); atomic_set(&mddev->flush_pending, 0); init_waitqueue_head(&mddev->sb_wait); @@ -4876,19 +4877,28 @@ static void stop_sync_thread(struct mddev *mddev) if (work_pending(&mddev->del_work)) flush_workqueue(md_misc_wq);

- if (mddev->sync_thread) { - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_reap_sync_thread(mddev); - } + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + /* + * Thread might be blocked waiting for metadata update which will now + * never happen. + */ + if (mddev->sync_thread) + wake_up_process(mddev->sync_thread->tsk);

mddev_unlock(mddev); }

static void idle_sync_thread(struct mddev *mddev) { + int sync_seq = atomic_read(&mddev->sync_seq); + mutex_lock(&mddev->sync_mutex); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); stop_sync_thread(mddev); + + wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) || + !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); + mutex_unlock(&mddev->sync_mutex); }

@@ -4897,6 +4907,10 @@ static void frozen_sync_thread(struct mddev *mddev) mutex_lock(&mddev->sync_mutex); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); stop_sync_thread(mddev); + + wait_event(resync_wait, mddev->sync_thread == NULL && + !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); + mutex_unlock(&mddev->sync_mutex); }

@@ -9471,6 +9485,8 @@ void md_reap_sync_thread(struct mddev *mddev)

/* resync has finished, collect result */ md_unregister_thread(&mddev->sync_thread); + atomic_inc(&mddev->sync_seq); + if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && mddev->degraded != mddev->raid_disks) { diff --git a/drivers/md/md.h b/drivers/md/md.h index 50c7d3e4f2d7..4565f17fc048 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -531,6 +531,8 @@ struct mddev {

/* Used to synchronize idle and frozen for action_store() */ struct mutex sync_mutex; + /* The sequence number for sync thread */ + atomic_t sync_seq; };

enum recovery_flags {

From: Yu Kuai yukuai3@huawei.com

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6OMCC CVE: NA

--------------------------------

Before refactoring idle and frozen from action_store, interruptible apis is used so that hungtask warning won't be triggered if it takes too long to finish indle/frozen sync_thread. This patch do the same.

Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Hou Tao houtao1@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- drivers/md/md.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c index cd86a3a1f771..61f68689ddfd 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4892,11 +4892,14 @@ static void idle_sync_thread(struct mddev *mddev) { int sync_seq = atomic_read(&mddev->sync_seq);

- mutex_lock(&mddev->sync_mutex); + if (mutex_lock_interruptible(&mddev->sync_mutex)) + return; + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); stop_sync_thread(mddev);

- wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) || + wait_event_interruptible(resync_wait, + sync_seq != atomic_read(&mddev->sync_seq) || !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));

mutex_unlock(&mddev->sync_mutex); @@ -4904,11 +4907,13 @@ static void idle_sync_thread(struct mddev *mddev)

static void frozen_sync_thread(struct mddev *mddev) { - mutex_lock(&mddev->sync_mutex); + if (mutex_lock_interruptible(&mddev->sync_mutex)) + return; + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); stop_sync_thread(mddev);

- wait_event(resync_wait, mddev->sync_thread == NULL && + wait_event_interruptible(resync_wait, mddev->sync_thread == NULL && !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));

mutex_unlock(&mddev->sync_mutex);

From: Andreas Gruenbacher agruenba@redhat.com

mainline inclusion from mainline-v5.14-rc2 commit 8e1bcef8e18d0fec4afe527c074bb1fd6c2b140c category: bugfix bugzilla: 188764, https://gitee.com/openeuler/kernel/issues/I736LW

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Create an iop in the writeback path if one doesn't exist. This allows us to avoid creating the iop in some cases. We'll initially do that for pages with inline data, but it can be extended to pages which are entirely within an extent. It also allows for an iop to be removed from pages in the future (eg page split).

Co-developed-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Baokun Li libaokun1@huawei.com Reviewed-by: Yang Erkun yangerkun@huawei.com Reviewed-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- fs/iomap/buffered-io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 33ddce5c5bbc..342331115ca5 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1382,14 +1382,13 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct inode *inode, struct page *page, u64 end_offset) { - struct iomap_page *iop = to_iomap_page(page); + struct iomap_page *iop = iomap_page_create(inode, page); struct iomap_ioend *ioend, *next; unsigned len = i_blocksize(inode); u64 file_offset; /* file offset of page */ int error = 0, count = 0, i; LIST_HEAD(submit_list);

- WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop); WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0);

/*

From: Andreas Gruenbacher agruenba@redhat.com

mainline inclusion from mainline-v5.14-rc2 commit 229adf3c64dbeae4e2f45fb561907ada9fcc0d0c category: bugfix bugzilla: 188764, https://gitee.com/openeuler/kernel/issues/I736LW

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Now that we create those objects in iomap_writepage_map when needed, there's no need to pre-create them in iomap_page_mkwrite_actor anymore.

Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Baokun Li libaokun1@huawei.com Reviewed-by: Yang Erkun yangerkun@huawei.com Reviewed-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- fs/iomap/buffered-io.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 67871d0a7e4f..e625c1920458 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1002,7 +1002,6 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, block_commit_write(page, 0, length); } else { WARN_ON_ONCE(!PageUptodate(page)); - iomap_page_create(inode, page); set_page_dirty(page); }

From: Tudor Ambarus tudor.ambarus@linaro.org

stable inclusion from stable-v5.10.180 commit 0dde3141c527b09b96bef1e7eeb18b8127810ce9 category: bugfix bugzilla: 188791,https://gitee.com/openeuler/kernel/issues/I76XUJ

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 4f04351888a83e595571de672e0a4a8b74f4fb31 upstream.

When modifying the block device while it is mounted by the filesystem, syzbot reported the following:

BUG: KASAN: slab-out-of-bounds in crc16+0x206/0x280 lib/crc16.c:58 Read of size 1 at addr ffff888075f5c0a8 by task syz-executor.2/15586

CPU: 1 PID: 15586 Comm: syz-executor.2 Not tainted 6.2.0-rc5-syzkaller-00205-gc96618275234 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 crc16+0x206/0x280 lib/crc16.c:58 ext4_group_desc_csum+0x81b/0xb20 fs/ext4/super.c:3187 ext4_group_desc_csum_set+0x195/0x230 fs/ext4/super.c:3210 ext4_mb_clear_bb fs/ext4/mballoc.c:6027 [inline] ext4_free_blocks+0x191a/0x2810 fs/ext4/mballoc.c:6173 ext4_remove_blocks fs/ext4/extents.c:2527 [inline] ext4_ext_rm_leaf fs/ext4/extents.c:2710 [inline] ext4_ext_remove_space+0x24ef/0x46a0 fs/ext4/extents.c:2958 ext4_ext_truncate+0x177/0x220 fs/ext4/extents.c:4416 ext4_truncate+0xa6a/0xea0 fs/ext4/inode.c:4342 ext4_setattr+0x10c8/0x1930 fs/ext4/inode.c:5622 notify_change+0xe50/0x1100 fs/attr.c:482 do_truncate+0x200/0x2f0 fs/open.c:65 handle_truncate fs/namei.c:3216 [inline] do_open fs/namei.c:3561 [inline] path_openat+0x272b/0x2dd0 fs/namei.c:3714 do_filp_open+0x264/0x4f0 fs/namei.c:3741 do_sys_openat2+0x124/0x4e0 fs/open.c:1310 do_sys_open fs/open.c:1326 [inline] __do_sys_creat fs/open.c:1402 [inline] __se_sys_creat fs/open.c:1396 [inline] __x64_sys_creat+0x11f/0x160 fs/open.c:1396 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f72f8a8c0c9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f72f97e3168 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 00007f72f8bac050 RCX: 00007f72f8a8c0c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000020000280 RBP: 00007f72f8ae7ae9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffd165348bf R14: 00007f72f97e3300 R15: 0000000000022000

Replace le16_to_cpu(sbi->s_es->s_desc_size) with sbi->s_desc_size

It reduces ext4's compiled text size, and makes the code more efficient (we remove an extra indirect reference and a potential byte swap on big endian systems), and there is no downside. It also avoids the potential KASAN / syzkaller failure, as a bonus.

Reported-by: syzbot+fc51227e7100c9294894@syzkaller.appspotmail.com Reported-by: syzbot+8785e41224a3afd04321@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=70d28d11ab14bd7938f3e088365252aa923cff4... Link: https://syzkaller.appspot.com/bug?id=b85721b38583ecc6b5e72ff524c67302abbc30f... Link: https://lore.kernel.org/all/000000000000ece18705f3b20934@google.com/ Fixes: 717d50e4971b ("Ext4: Uninitialized Block Groups") Cc: stable@vger.kernel.org Signed-off-by: Tudor Ambarus tudor.ambarus@linaro.org Link: https://lore.kernel.org/r/20230504121525.3275886-1-tudor.ambarus@linaro.org Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Baokun Li libaokun1@huawei.com Reviewed-by: Yang Erkun yangerkun@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- fs/ext4/super.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 3be882d07616..5e776f27976c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2878,11 +2878,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ - if (ext4_has_feature_64bit(sb) && - offset < le16_to_cpu(sbi->s_es->s_desc_size)) + if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, - le16_to_cpu(sbi->s_es->s_desc_size) - - offset); + sbi->s_desc_size - offset);

out: return cpu_to_le16(crc);

From: Xia Fukun xiafukun@huawei.com

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6YJJQ CVE: NA

----------------------------------------

The function sd_llc_free_all() will be called to release allocated resources when space allocation for the scheduling domain structure fails. However, this function did not check if sd is a null pointer when releasing sdd resources, resulting in an error: "Unable to handle kernel paging request at virtual address".

Fix this issue by adding null pointer discrimination.

Fixes: 79bec4c643fb ("sched/topology: Provide hooks to allocate data shared per LLC") Signed-off-by: Xia Fukun xiafukun@huawei.com Reviewed-by: Zhang Qiao zhangqiao22@huawei.com Reviewed-by: songping yu yusongping@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- kernel/sched/topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 9b4e3b25ddff..d8827c0535a8 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2035,7 +2035,7 @@ static void sd_llc_free_all(const struct cpumask *cpu_map)

for_each_sd_topology(tl) { sdd = &tl->data; - if (!sdd) + if (!sdd || !sdd->sd) continue; for_each_cpu(j, cpu_map) { sd = *per_cpu_ptr(sdd->sd, j);

From: Dmitry Osipenko dmitry.osipenko@collabora.com

stable inclusion from stable-v5.10.171 commit 87c647def389354c95263d6635c62ca0de7d12ca category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6IKWF CVE: CVE-2023-22998

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 64b88afbd92fbf434759d1896a7cf705e1c00e79 upstream.

Previous commit fixed checking of the ERR_PTR value returned by drm_gem_shmem_get_sg_table(), but it missed to zero out the shmem->pages, which will crash virtio_gpu_cleanup_object(). Add the missing zeroing of the shmem->pages.

Fixes: c24968734abf ("drm/virtio: Fix NULL vs IS_ERR checking in virtio_gpu_object_shmem_init") Reviewed-by: Emil Velikov emil.l.velikov@gmail.com Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Link: http://patchwork.freedesktop.org/patch/msgid/20220630200726.1884320-2-dmitry... Signed-off-by: Gerd Hoffmann kraxel@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ovidiu Panait ovidiu.panait@windriver.com Signed-off-by: Guo Mengqi guomengqi3@huawei.com Reviewed-by: Weilong Chen chenweilong@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- drivers/gpu/drm/virtio/virtgpu_object.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index d4fab3361d2c..168148686001 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -159,6 +159,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base); if (IS_ERR(shmem->pages)) { drm_gem_shmem_unpin(&bo->base.base); + shmem->pages = NULL; return PTR_ERR(shmem->pages); }

From: Xiu Jianfeng xiujianfeng@huaweicloud.com

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I798WQ CVE: NA

----------------------------------------------------------------------

We found a refcount UAF bug as follows:

refcount_t: addition on 0; use-after-free. WARNING: CPU: 1 PID: 342 at lib/refcount.c:25 refcount_warn_saturate+0xa0/0x148 Workqueue: events cpuset_hotplug_workfn Call trace: refcount_warn_saturate+0xa0/0x148 __refcount_add.constprop.0+0x5c/0x80 css_task_iter_advance_css_set+0xd8/0x210 css_task_iter_advance+0xa8/0x120 css_task_iter_next+0x94/0x158 update_tasks_root_domain+0x58/0x98 rebuild_root_domains+0xa0/0x1b0 rebuild_sched_domains_locked+0x144/0x188 cpuset_hotplug_workfn+0x138/0x5a0 process_one_work+0x1e8/0x448 worker_thread+0x228/0x3e0 kthread+0xe0/0xf0 ret_from_fork+0x10/0x20

then a kernel panic will be triggered as below:

Unable to handle kernel paging request at virtual address 00000000c0000010 Call trace: cgroup_apply_control_disable+0xa4/0x16c rebind_subsystems+0x224/0x590 cgroup_destroy_root+0x64/0x2e0 css_free_rwork_fn+0x198/0x2a0 process_one_work+0x1d4/0x4bc worker_thread+0x158/0x410 kthread+0x108/0x13c ret_from_fork+0x10/0x18

The race that cause this bug can be shown as below:

(hotplug cpu) | (umount cpuset) mutex_lock(&cpuset_mutex) | mutex_lock(&cgroup_mutex) cpuset_hotplug_workfn | rebuild_root_domains | rebind_subsystems update_tasks_root_domain | spin_lock_irq(&css_set_lock) css_task_iter_start | list_move_tail(&cset->e_cset_node[ss->id] while(css_task_iter_next) | &dcgrp->e_csets[ss->id]); css_task_iter_end | spin_unlock_irq(&css_set_lock) mutex_unlock(&cpuset_mutex) | mutex_unlock(&cgroup_mutex)

Inside css_task_iter_start/next/end, css_set_lock is hold and then released, so when iterating task(left side), the css_set may be moved to another list(right side), then it->cset_head points to the old list head and it->cset_pos->next points to the head node of new list, which can't be used as struct css_set.

To fix this issue, introduce CSS_TASK_ITER_STOPPED flag for css_task_iter. when moving css_set to dcgrp->e_csets[ss->id] in rebind_subsystems(), stop the task iteration.

Reported-by: Gaosheng Cui cuigaosheng1@huawei.com Link: https://www.spinics.net/lists/cgroups/msg37935.html Fixes: f9a25f776d78 ("cpusets: Rebuild root domain deadline accounting information") Signed-off-by: Xiu Jianfeng xiujianfeng@huaweicloud.com Signed-off-by: Gaosheng Cui cuigaosheng1@huawei.com Reviewed-by: Wang Weiyang wangweiyang2@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com --- include/linux/cgroup.h | 1 + kernel/cgroup/cgroup.c | 34 +++++++++++++++++++++++++++++++++- 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9226ec130ba3..9d50e3e01648 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -47,6 +47,7 @@ struct kernel_clone_args;

/* internal flags */ #define CSS_TASK_ITER_SKIPPED (1U << 16) +#define CSS_TASK_ITER_STOPPED (1U << 17)

/* a css_task_iter should be treated as an opaque object */ struct css_task_iter { diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 46d5c120c626..f9c5375ad8fd 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -214,6 +214,8 @@ static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); +static void css_task_iter_stop(struct css_task_iter *it, + struct cgroup_subsys *ss); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); @@ -854,6 +856,19 @@ static void css_set_skip_task_iters(struct css_set *cset, css_task_iter_skip(it, task); }

+/* + * @cset is moving to other list, it's not safe to continue the iteration, + * because the cset_head of css_task_iter which is from the old list can + * not be used as the stop condition of iteration. + */ +static void css_set_stop_iters(struct css_set *cset, struct cgroup_subsys *ss) +{ + struct css_task_iter *it, *pos; + + list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) + css_task_iter_stop(it, ss); +} + /** * css_set_move_task - move a task from one css_set to another * @task: task being moved @@ -1774,9 +1789,11 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) css->cgroup = dcgrp;

spin_lock_irq(&css_set_lock); - hash_for_each(css_set_table, i, cset, hlist) + hash_for_each(css_set_table, i, cset, hlist) { + css_set_stop_iters(cset, ss); list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); + } spin_unlock_irq(&css_set_lock);

if (ss->css_rstat_flush) { @@ -4664,6 +4681,16 @@ static void css_task_iter_skip(struct css_task_iter *it, } }

+static void css_task_iter_stop(struct css_task_iter *it, + struct cgroup_subsys *ss) +{ + lockdep_assert_held(&css_set_lock); + + if (it->ss == ss) { + it->flags |= CSS_TASK_ITER_STOPPED; + } +} + static void css_task_iter_advance(struct css_task_iter *it) { struct task_struct *task; @@ -4767,6 +4794,11 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)

spin_lock_irq(&css_set_lock);

+ if (it->flags & CSS_TASK_ITER_STOPPED) { + spin_unlock_irq(&css_set_lock); + return NULL; + } + /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it);