> I run into the below ucma related warnings from the kernel with 3.3-rc5 > when I stepped over crash of process as of wrong libs/etc (not the point > here...). Do you see here a real bug? basically the process was exiting > and the cleanup code in the kernel was running rdma_destroy_id when a > callback on that id was arriving from the IB CM. I saw that you lately > touched that/similar area in commit 9ced69ca5296567033804950d8d2161f454c5012 > "RDMA/ucma: Discard all events for new connections until accepted"
This is a real issue, but unrelated to the above commit. The problem has likely existed in the code for quite a while. I'll work on a fix. - Sean -- FYI The issue is that under certain conditions, we hold file->mut when calling rdma_destroy_id(). rdma_destroy_id() blocks until all outstanding callbacks complete, but in this case the callback also wants to acquire file->mut, resulting in the deadlock. -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
