md: Move alloc/free acct bioset in to personality

bioset acct is only needed for raid0 and raid5. Therefore, md_run only
allocates it for raid0 and raid5. However, this does not cover
personality takeover, which may cause uninitialized bioset. For example,
the following repro steps:

  mdadm -CR /dev/md0 -l1 -n2 /dev/loop0 /dev/loop1
  mdadm --wait /dev/md0
  mkfs.xfs /dev/md0
  mdadm /dev/md0 --grow -l5
  mount /dev/md0 /mnt

causes panic like:

[  225.933939] BUG: kernel NULL pointer dereference, address: 0000000000000000
[  225.934903] #PF: supervisor instruction fetch in kernel mode
[  225.935639] #PF: error_code(0x0010) - not-present page
[  225.936361] PGD 0 P4D 0
[  225.936677] Oops: 0010 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN PTI
[  225.937525] CPU: 27 PID: 1133 Comm: mount Not tainted 5.16.0-rc3+ #706
[  225.938416] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.module_el8.4.0+547+a85d02ba 04/01/2014
[  225.939922] RIP: 0010:0x0
[  225.940289] Code: Unable to access opcode bytes at RIP 0xffffffffffffffd6.
[  225.941196] RSP: 0018:ffff88815897eff0 EFLAGS: 00010246
[  225.941897] RAX: 0000000000000000 RBX: 0000000000092800 RCX: ffffffff81370a39
[  225.942813] RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000092800
[  225.943772] RBP: 1ffff1102b12fe04 R08: fffffbfff0b43c01 R09: fffffbfff0b43c01
[  225.944807] R10: ffffffff85a1e007 R11: fffffbfff0b43c00 R12: ffff88810eaaaf58
[  225.945757] R13: 0000000000000000 R14: ffff88810eaaafb8 R15: ffff88815897f040
[  225.946709] FS:  00007ff3f2505080(0000) GS:ffff888fb5e00000(0000) knlGS:0000000000000000
[  225.947814] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  225.948556] CR2: ffffffffffffffd6 CR3: 000000015aa5a006 CR4: 0000000000370ee0
[  225.949537] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  225.950455] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  225.951414] Call Trace:
[  225.951787]  <TASK>
[  225.952120]  mempool_alloc+0xe5/0x250
[  225.952625]  ? mempool_resize+0x370/0x370
[  225.953187]  ? rcu_read_lock_sched_held+0xa1/0xd0
[  225.953862]  ? rcu_read_lock_bh_held+0xb0/0xb0
[  225.954464]  ? sched_clock_cpu+0x15/0x120
[  225.955019]  ? find_held_lock+0xac/0xd0
[  225.955564]  bio_alloc_bioset+0x1ed/0x2a0
[  225.956080]  ? lock_downgrade+0x3a0/0x3a0
[  225.956644]  ? bvec_alloc+0xc0/0xc0
[  225.957135]  bio_clone_fast+0x19/0x80
[  225.957651]  raid5_make_request+0x1370/0x1b70
[  225.958286]  ? sched_clock_cpu+0x15/0x120
[  225.958797]  ? __lock_acquire+0x8b2/0x3510
[  225.959339]  ? raid5_get_active_stripe+0xce0/0xce0
[  225.959986]  ? lock_is_held_type+0xd8/0x130
[  225.960528]  ? rcu_read_lock_sched_held+0xa1/0xd0
[  225.961135]  ? rcu_read_lock_bh_held+0xb0/0xb0
[  225.961703]  ? sched_clock_cpu+0x15/0x120
[  225.962232]  ? lock_release+0x27a/0x6c0
[  225.962746]  ? do_wait_intr_irq+0x130/0x130
[  225.963302]  ? lock_downgrade+0x3a0/0x3a0
[  225.963815]  ? lock_release+0x6c0/0x6c0
[  225.964348]  md_handle_request+0x342/0x530
[  225.964888]  ? set_in_sync+0x170/0x170
[  225.965397]  ? blk_queue_split+0x133/0x150
[  225.965988]  ? __blk_queue_split+0x8b0/0x8b0
[  225.966524]  ? submit_bio_checks+0x3b2/0x9d0
[  225.967069]  md_submit_bio+0x127/0x1c0
[...]

Fix this by moving alloc/free of acct bioset to pers->run and pers->free.

While we are on this, properly handle md_integrity_register() error in
raid0_run().

Fixes: daee2024715d (md: check level before create and exit io_acct_set)
Cc: stable@vger.kernel.org
Acked-by: Guoqing Jiang <guoqing.jiang@linux.dev>
Signed-off-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Song Liu <song@kernel.org>

1 files changed, 17 insertions, 10 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3f75c5896b92..3f57843918ec 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5881,13 +5881,6 @@ int md_run(struct mddev *mddev)
 		if (err)
 			goto exit_bio_set;
 	}
-	if (mddev->level != 1 && mddev->level != 10 &&
-	    !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);
@@ -6064,9 +6057,6 @@ bitmap_abort:
 	module_put(pers->owner);
 	md_bitmap_destroy(mddev);
 abort:
-	if (mddev->level != 1 && mddev->level != 10)
-		bioset_exit(&mddev->io_acct_set);
-exit_sync_set:
 	bioset_exit(&mddev->sync_set);
 exit_bio_set:
 	bioset_exit(&mddev->bio_set);
@@ -8608,6 +8598,23 @@ 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;