diff options
| author | Felix Kuehling <Felix.Kuehling@amd.com> | 2018-05-01 17:56:08 -0400 |
|---|---|---|
| committer | Oded Gabbay <oded.gabbay@gmail.com> | 2018-05-01 17:56:08 -0400 |
| commit | eeb27b7eb3826c23cc5688c47845e7309f20fc32 (patch) | |
| tree | e2bb326aa927e3d5f45622c5e373af2dfa180a36 /drivers/gpu/drm/amd/amdkfd/kfd_events.c | |
| parent | f8ea72d097965617bba0d6773fd29d44070c5e1a (diff) | |
drm/amdkfd: Fix signal handling performance again
It turns out that idr_for_each_entry is really slow compared to just
iterating over the slots. Based on measurements the difference is
estimated to be about a factor 64. That means using idr_for_each_entry
is only worth it with very few allocated events.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_events.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_events.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index bccf2f761177..5562e94e786a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -496,7 +496,7 @@ void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id, pr_debug_ratelimited("Partial ID invalid: %u (%u valid bits)\n", partial_id, valid_id_bits); - if (p->signal_event_count < KFD_SIGNAL_EVENT_LIMIT/2) { + if (p->signal_event_count < KFD_SIGNAL_EVENT_LIMIT / 64) { /* With relatively few events, it's faster to * iterate over the event IDR */ |