From 265ad47a40da581be77172b4a8e1fb72b2bd914a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 10 Aug 2022 11:20:12 -0700 Subject: md/raid10: Fix the data type of an r10_sync_page_io() argument Fix the following sparse warning: drivers/md/raid10.c:2647:60: sparse: sparse: incorrect type in argument 5 (different base types) @@ expected restricted blk_opf_t [usertype] opf @@ got int rw @@ This patch does not change any functionality since REQ_OP_READ = READ = 0 and since REQ_OP_WRITE = WRITE = 1. Cc: Rong A Chen Cc: Jens Axboe Cc: Paul Menzel Fixes: 4ce4c73f662b ("md/core: Combine two sync_page_io() arguments") Reported-by: kernel test robot Signed-off-by: Bart Van Assche Signed-off-by: Song Liu --- drivers/md/raid10.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 9117fcdee1be..64d6e4cd8a3a 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2639,18 +2639,18 @@ static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev) } static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector, - int sectors, struct page *page, int rw) + int sectors, struct page *page, enum req_op op) { sector_t first_bad; int bad_sectors; if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors) - && (rw == READ || test_bit(WriteErrorSeen, &rdev->flags))) + && (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags))) return -1; - if (sync_page_io(rdev, sector, sectors << 9, page, rw, false)) + if (sync_page_io(rdev, sector, sectors << 9, page, op, false)) /* success */ return 1; - if (rw == WRITE) { + if (op == REQ_OP_WRITE) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, @@ -2780,7 +2780,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 if (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s, conf->tmppage, WRITE) + s, conf->tmppage, REQ_OP_WRITE) == 0) { /* Well, this device is dead */ pr_notice("md/raid10:%s: read correction write failed (%d sectors at %llu on %pg)\n", @@ -2814,8 +2814,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 switch (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s, conf->tmppage, - READ)) { + s, conf->tmppage, REQ_OP_READ)) { case 0: /* Well, this device is dead */ pr_notice("md/raid10:%s: unable to read back corrected sectors (%d sectors at %llu on %pg)\n", -- cgit v1.2.3 From 5e8daf906f890560df430d30617c692a794acb73 Mon Sep 17 00:00:00 2001 From: David Sloan Date: Thu, 11 Aug 2022 11:14:13 -0600 Subject: md: Flush workqueue md_rdev_misc_wq in md_alloc() A race condition still exists when removing and re-creating md devices in test cases. However, it is only seen on some setups. The race condition was tracked down to a reference still being held to the kobject by the rdev in the md_rdev_misc_wq which will be released in rdev_delayed_delete(). md_alloc() waits for previous deletions by waiting on the md_misc_wq, but the md_rdev_misc_wq may still be holding a reference to a recently removed device. To fix this, also flush the md_rdev_misc_wq in md_alloc(). Signed-off-by: David Sloan [logang@deltatee.com: rewrote commit message] Signed-off-by: Logan Gunthorpe Signed-off-by: Song Liu --- drivers/md/md.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index afaf36b2f6ab..71d221601bf8 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5620,6 +5620,7 @@ struct mddev *md_alloc(dev_t dev, char *name) * removed (mddev_delayed_delete). */ flush_workqueue(md_misc_wq); + flush_workqueue(md_rdev_misc_wq); mutex_lock(&disks_mutex); mddev = mddev_alloc(dev); -- cgit v1.2.3 From 1d258758cf06a0734482989911d184dd5837ed4e Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Wed, 17 Aug 2022 20:05:13 +0800 Subject: Revert "md-raid: destroy the bitmap after destroying the thread" This reverts commit e151db8ecfb019b7da31d076130a794574c89f6f. Because it obviously breaks clustered raid as noticed by Neil though it fixed KASAN issue for dm-raid, let's revert it and fix KASAN issue in next commit. [1]. https://lore.kernel.org/linux-raid/a6657e08-b6a7-358b-2d2a-0ac37d49d23a@linux.dev/T/#m95ac225cab7409f66c295772483d091084a6d470 Fixes: e151db8ecfb0 ("md-raid: destroy the bitmap after destroying the thread") Signed-off-by: Guoqing Jiang Signed-off-by: Song Liu --- drivers/md/md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 71d221601bf8..107c4c953c35 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6239,11 +6239,11 @@ static void mddev_detach(struct mddev *mddev) static void __md_stop(struct mddev *mddev) { struct md_personality *pers = mddev->pers; + md_bitmap_destroy(mddev); mddev_detach(mddev); /* Ensure ->event_work is done */ if (mddev->event_work.func) flush_workqueue(md_misc_wq); - md_bitmap_destroy(mddev); spin_lock(&mddev->lock); mddev->pers = NULL; spin_unlock(&mddev->lock); -- cgit v1.2.3 From 0dd84b319352bb8ba64752d4e45396d8b13e6018 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Wed, 17 Aug 2022 20:05:14 +0800 Subject: md: call __md_stop_writes in md_stop From the link [1], we can see raid1d was running even after the path raid_dtr -> md_stop -> __md_stop. Let's stop write first in destructor to align with normal md-raid to fix the KASAN issue. [1]. https://lore.kernel.org/linux-raid/CAPhsuW5gc4AakdGNdF8ubpezAuDLFOYUO_sfMZcec6hQFm8nhg@mail.gmail.com/T/#m7f12bf90481c02c6d2da68c64aeed4779b7df74a Fixes: 48df498daf62 ("md: move bitmap_destroy to the beginning of __md_stop") Reported-by: Mikulas Patocka Signed-off-by: Guoqing Jiang Signed-off-by: Song Liu --- drivers/md/md.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index 107c4c953c35..729be2c5296c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6261,6 +6261,7 @@ void md_stop(struct mddev *mddev) /* stop the array and free an attached data structures. * This is called from dm-raid */ + __md_stop_writes(mddev); __md_stop(mddev); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); -- cgit v1.2.3