Re: [PATCH 2/2] s390x/pci: fix set_ind_atomic

2020-07-01 Thread Christian Borntraeger
On 16.06.20 06:50, Halil Pasic wrote: > The atomic_cmpxchg() loop is broken because we occasionally end up with > old and _old having different values (a legit compiler can generate code > that accessed *ind_addr again to pick up a value for _old instead of > using the value of old that was

[PATCH 2/2] s390x/pci: fix set_ind_atomic

2020-06-15 Thread Halil Pasic
The atomic_cmpxchg() loop is broken because we occasionally end up with old and _old having different values (a legit compiler can generate code that accessed *ind_addr again to pick up a value for _old instead of using the value of old that was already fetched according to the rules of the