[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [xen staging] x86/hpet: use an atomic add instead of a cmpxchg loop
commit f49fb70d3d4c1729fce825f0fda6863ac3ec00e0 Author: Jan Beulich <jbeulich@xxxxxxxx> AuthorDate: Mon Feb 26 10:16:56 2024 +0100 Commit: Jan Beulich <jbeulich@xxxxxxxx> CommitDate: Mon Feb 26 10:16:56 2024 +0100 x86/hpet: use an atomic add instead of a cmpxchg loop The usage of a cmpxchg loop in hpet_get_channel() is unnecessary, as the same can be achieved with an atomic increment, which is both simpler to read, and avoid any need for a loop. Note there can be a small divergence in the channel returned if next_channel overflows, but returned channel will always be in the [0, num_hpets_used) range, and that's fine for the purpose of balancing HPET channels across CPUs. Signed-of-by: Roger Pau Monné <roger.pau@xxxxxxxxxx> Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx> Reviewed-by: Julien Grall <jgrall@xxxxxxxxxx> --- xen/arch/x86/hpet.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/xen/arch/x86/hpet.c b/xen/arch/x86/hpet.c index d9e9c8ffa3..0759eae055 100644 --- a/xen/arch/x86/hpet.c +++ b/xen/arch/x86/hpet.c @@ -457,11 +457,7 @@ static struct hpet_event_channel *hpet_get_channel(unsigned int cpu) if ( num_hpets_used >= nr_cpu_ids ) return &hpet_events[cpu]; - do { - next = next_channel; - if ( (i = next + 1) == num_hpets_used ) - i = 0; - } while ( cmpxchg(&next_channel, next, i) != next ); + next = arch_fetch_and_add(&next_channel, 1) % num_hpets_used; /* try unused channel first */ for ( i = next; i < next + num_hpets_used; i++ ) -- generated by git-patchbot for /home/xen/git/xen.git#staging
|
![]() |
Lists.xenproject.org is hosted with RackSpace, monitoring our |