From bfa152fa5e4d328fe3ebf15908ee8ec20a0ce6dc Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Fri, 26 Jan 2007 00:57:07 -0800 Subject: [PATCH] [PATCH] dm-multipath: fix stall on noflush suspend/resume Allow noflush suspend/resume of device-mapper device only for the case where the device size is unchanged. Otherwise, dm-multipath devices can stall when resumed if noflush was used when suspending them, all paths have failed and queue_if_no_path is set. Explanation: 1. Something is doing fsync() on the block dev, holding inode->i_sem 2. The fsync write is blocked by all-paths-down and queue_if_no_path 3. Someone requests to suspend the dm device with noflush. Pending writes are left in queue. 4. In the middle of dm_resume(), __bind() tries to get inode->i_sem to do __set_size() and waits forever. 'noflush suspend' is a new device-mapper feature introduced in early 2.6.20. So I hope the fix being included before 2.6.20 is released. Example of reproducer: 1. Create a multipath device by dmsetup 2. Fail all paths during mkfs 3. Do dmsetup suspend --noflush and load new map with healthy paths 4. Do dmsetup resume Signed-off-by: Jun'ichi Nomura Acked-by: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/dm.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index fe7c56e10435..3668b170ea68 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1116,7 +1116,8 @@ static int __bind(struct mapped_device *md, struct dm_table *t) if (size != get_capacity(md->disk)) memset(&md->geometry, 0, sizeof(md->geometry)); - __set_size(md, size); + if (md->suspended_bdev) + __set_size(md, size); if (size == 0) return 0; @@ -1264,6 +1265,11 @@ int dm_swap_table(struct mapped_device *md, struct dm_table *table) if (!dm_suspended(md)) goto out; + /* without bdev, the device size cannot be changed */ + if (!md->suspended_bdev) + if (get_capacity(md->disk) != dm_table_get_size(table)) + goto out; + __unbind(md); r = __bind(md, table); @@ -1341,11 +1347,14 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) /* This does not get reverted if there's an error later. */ dm_table_presuspend_targets(map); - md->suspended_bdev = bdget_disk(md->disk, 0); - if (!md->suspended_bdev) { - DMWARN("bdget failed in dm_suspend"); - r = -ENOMEM; - goto flush_and_out; + /* bdget() can stall if the pending I/Os are not flushed */ + if (!noflush) { + md->suspended_bdev = bdget_disk(md->disk, 0); + if (!md->suspended_bdev) { + DMWARN("bdget failed in dm_suspend"); + r = -ENOMEM; + goto flush_and_out; + } } /* @@ -1473,8 +1482,10 @@ int dm_resume(struct mapped_device *md) unlock_fs(md); - bdput(md->suspended_bdev); - md->suspended_bdev = NULL; + if (md->suspended_bdev) { + bdput(md->suspended_bdev); + md->suspended_bdev = NULL; + } clear_bit(DMF_SUSPENDED, &md->flags);