Hi! On 27/01/2021 23:43, Peter Zijlstra wrote: > On Wed, Jan 27, 2021 at 09:01:08PM +0100, Alexander A Sverdlin wrote: >> From: Alexander Sverdlin <alexander.sverd...@nokia.com> >> >> Ensure writes are pushed out of core write buffer to prevent waiting code >> on another cores from spinning longer than necessary. > Our smp_wmb() as defined does not have that property. You're relying on > some arch specific details which do not belong in common code.
Yes, my intention was SYNCW on Octeon, which by accident is smp_wmb(). Do you think that the core write buffer is only Octeon feature and there will be no others? Should I re-implement arch_mcs_spin_lock_contended() for Octeon only, as it has been done for ARM? >> diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h >> index 5e10153..10e497a 100644 >> --- a/kernel/locking/mcs_spinlock.h >> +++ b/kernel/locking/mcs_spinlock.h >> @@ -89,6 +89,11 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct >> mcs_spinlock *node) >> return; >> } >> WRITE_ONCE(prev->next, node); >> + /* >> + * This is necessary to make sure that the corresponding "while" in the >> + * mcs_spin_unlock() doesn't loop forever >> + */ > This comment is utterly inadequate, since it does not describe an > explicit ordering between two (or more) stores. > >> + smp_wmb(); >> >> /* Wait until the lock holder passes the lock down. */ >> arch_mcs_spin_lock_contended(&node->locked); >> diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c >> index cbff6ba..577fe01 100644 >> --- a/kernel/locking/qspinlock.c >> +++ b/kernel/locking/qspinlock.c >> @@ -469,6 +469,12 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, >> u32 val) >> >> /* Link @node into the waitqueue. */ >> WRITE_ONCE(prev->next, node); >> + /* >> + * This is necessary to make sure that the corresponding >> + * smp_cond_load_relaxed() below (running on another core) >> + * doesn't spin forever. >> + */ >> + smp_wmb(); > That's insane, cache coherency should not allow that to happen in the > first place. Our smp_wmb() cannot help with that. > -- Best regards, Alexander Sverdlin.