Commit 6aaa58c9 authored Oct 19, 2018 by Jack Wang Committed by Shaohua Li Oct 22, 2018

md: fix memleak for mempool



I noticed kmemleak report memory leak when run create/stop
md in a loop, backtrace:
[<000000001ca975e7>] mempool_create_node+0x86/0xd0
[<0000000095576bcd>] md_run+0x1057/0x1410 [md_mod]
[<000000007b45c5fc>] do_md_run+0x15/0x130 [md_mod]
[<000000001ede9ec0>] md_ioctl+0x1f49/0x25d0 [md_mod]
[<000000004142cacf>] blkdev_ioctl+0x680/0xd00

The root cause is we alloc mddev->flush_pool and
mddev->flush_bio_pool in md_run, but from do_md_stop
will not call into md_stop but __md_stop, move the
mempool_destroy to __md_stop fixes the problem for me.

The bug was introduced in 5a409b4f, the fixes should go to
4.18+

Fixes: 5a409b4f ("MD: fix lock contention for flush bios")
Signed-off-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Shaohua Li <shli@fb.com>

parent ea89238c

drivers/md/md.c

+8 −8

Original line number	Diff line number	Diff line
		@@ -5904,14 +5904,6 @@ static void __md_stop(struct mddev *mddev)
		mddev->to_remove = &md_redundancy_group;
		module_put(pers->owner);
		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
		}

		void md_stop(struct mddev *mddev)
		{
		/* stop the array and free an attached data structures.
		* This is called from dm-raid
		*/
		__md_stop(mddev);
		if (mddev->flush_bio_pool) {
		mempool_destroy(mddev->flush_bio_pool);
		mddev->flush_bio_pool = NULL;
		@@ -5920,6 +5912,14 @@ void md_stop(struct mddev *mddev)
		mempool_destroy(mddev->flush_pool);
		mddev->flush_pool = NULL;
		}
		}

		void md_stop(struct mddev *mddev)
		{
		/* stop the array and free an attached data structures.
		* This is called from dm-raid
		*/
		__md_stop(mddev);
		bioset_exit(&mddev->bio_set);
		bioset_exit(&mddev->sync_set);
		}

Admin message