| Date | Wed, 27 May 2020 01:56:34 +0200 | From | Frederic Weisbecker <> | Subject | Re: [RFC][PATCH 1/7] sched: Fix smp_call_function_single_async() usage for ILB |
| |
On Tue, May 26, 2020 at 06:10:58PM +0200, Peter Zijlstra wrote: > The recent commit: 90b5363acd47 ("sched: Clean up scheduler_ipi()") > got smp_call_function_single_async() subtly wrong. Even though it will > return -EBUSY when trying to re-use a csd, that condition is not > atomic and still requires external serialization. > > The change in kick_ilb() got this wrong. > > While on first reading kick_ilb() has an atomic test-and-set that > appears to serialize the use, the matching 'release' is not in the > right place to actually guarantee this serialization. > > Rework the nohz_idle_balance() trigger so that the release is in the > IPI callback and thus guarantees the required serialization for the > CSD. > > Fixes: 90b5363acd47 ("sched: Clean up scheduler_ipi()") > Reported-by: Qian Cai <cai@lca.pw> > Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Looks very good! Thanks!
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
|