As seen in some recent failures, SLPC num_waiters value is < 0. This happens because the inc/dec are not balanced. We should skip decrement for the same conditions as the increment. Currently, we do that for power saving profile mode. This patch also ensures that num_waiters is incremented in the case min_softlimit is at boost freq. It ensures that we don't reduce the frequency while this request is in flight.
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13598 Cc: Sk Anirban <sk.anir...@intel.com> Signed-off-by: Vinay Belgaumkar <vinay.belgaum...@intel.com> --- drivers/gpu/drm/i915/gt/intel_rps.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 8731f275fdd9..b609e3aa2122 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1003,6 +1003,10 @@ void intel_rps_dec_waiters(struct intel_rps *rps) if (rps_uses_slpc(rps)) { slpc = rps_to_slpc(rps); + /* Don't decrement num_waiters for req where increment was skipped */ + if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING) + return; + intel_guc_slpc_dec_waiters(slpc); } else { atomic_dec(&rps->num_waiters); @@ -1031,11 +1035,15 @@ void intel_rps_boost(struct i915_request *rq) if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING) return; - if (slpc->min_freq_softlimit >= slpc->boost_freq) - return; - /* Return if old value is non zero */ if (!atomic_fetch_inc(&slpc->num_waiters)) { + /* + * Skip queuing boost work if frequency is already boosted, + * but still increment num_waiters. + */ + if (slpc->min_freq_softlimit >= slpc->boost_freq) + return; + GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n", rq->fence.context, rq->fence.seqno); queue_work(rps_to_gt(rps)->i915->unordered_wq, -- 2.38.1
