On 4/7/22 16:44, Bart Van Assche wrote: > On 4/7/22 14:06, Bob Pearson wrote: >> On 4/7/22 14:49, Bart Van Assche wrote: >>> On 4/7/22 12:15, Robert Pearson wrote: >>>> I would say it is very possible. There was a period when the >>>> pool locks were switched to _bh spinlocks but that was later >>>> reversed back to _irqsave locks which cleaned up some failures. I >>>> don't know which version Yi Zhang was using. The root cause of >>>> this bug was caused by librdmacm making verbs API calls while >>>> holding _irqsave locks which I didn't figure out until later. >>> >>> I can reproduce the issue Yi reported with kernel v5.18-rc1. Please >>> let me know if you need any additional information to reproduce >>> this issue. >> >> From your note I can't figure out what you are running. Can you give >> me more details about the failing test case? > > Hi Bob, > > In Yi's email I found the following: > > run blktests srp/001 > > That test case can be run as follows: > > git clone https://github.com/osandov/blktests && cd blktests && make && sudo ./check -q srp/001 > > Thanks, > > Bart. > OK. I know it well. I run it from time to time. I'll see if it is broken just now. Bob
