[Intel-gfx] [PATCH v3] drm/i915/slpc: Optmize waitboost for SLPC

[Vinay Belgaumkar]

Waitboost (when SLPC is enabled) results in a H2G message. This can result
in thousands of messages during a stress test and fill up an already full
CTB. There is no need to request for RP0 if GuC is already requesting the
same.

v2: Add the tracing back, and check requested freq
in the worker thread (Tvrtko)
v3: Check requested freq in dec_waiters as well

Signed-off-by: Vinay Belgaumkar <vinay.belgaum...@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_rps.c         |  3 +++
 drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c | 14 +++++++++++---
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c 
b/drivers/gpu/drm/i915/gt/intel_rps.c
index fc23c562d9b2..18b75cf08d1b 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1016,6 +1016,9 @@ void intel_rps_boost(struct i915_request *rq)
                if (rps_uses_slpc(rps)) {
                        slpc = rps_to_slpc(rps);
 
+                       GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n",
+                                rq->fence.context, rq->fence.seqno);
+
                        /* Return if old value is non zero */
                        if (!atomic_fetch_inc(&slpc->num_waiters))
                                schedule_work(&slpc->boost_work);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c 
b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
index b7cdeec44bd3..9dbdbab1515a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
@@ -227,14 +227,19 @@ static int slpc_force_min_freq(struct intel_guc_slpc 
*slpc, u32 freq)
 static void slpc_boost_work(struct work_struct *work)
 {
        struct intel_guc_slpc *slpc = container_of(work, typeof(*slpc), 
boost_work);
+       struct intel_rps *rps = &slpc_to_gt(slpc)->rps;
        int err;
 
        /*
         * Raise min freq to boost. It's possible that
         * this is greater than current max. But it will
         * certainly be limited by RP0. An error setting
-        * the min param is not fatal.
+        * the min param is not fatal. No need to boost
+        * if we are already requesting it.
         */
+       if (intel_rps_get_requested_frequency(rps) == slpc->boost_freq)
+               return;
+
        mutex_lock(&slpc->lock);
        if (atomic_read(&slpc->num_waiters)) {
                err = slpc_force_min_freq(slpc, slpc->boost_freq);
@@ -728,6 +733,7 @@ int intel_guc_slpc_set_boost_freq(struct intel_guc_slpc 
*slpc, u32 val)
 
 void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc)
 {
+       struct intel_rps *rps = &slpc_to_gt(slpc)->rps;
        /*
         * Return min back to the softlimit.
         * This is called during request retire,
@@ -735,8 +741,10 @@ void intel_guc_slpc_dec_waiters(struct intel_guc_slpc 
*slpc)
         * set_param fails.
         */
        mutex_lock(&slpc->lock);
-       if (atomic_dec_and_test(&slpc->num_waiters))
-               slpc_force_min_freq(slpc, slpc->min_freq_softlimit);
+       if (atomic_dec_and_test(&slpc->num_waiters)) {
+               if (intel_rps_get_requested_frequency(rps) != 
slpc->min_freq_softlimit)
+                       slpc_force_min_freq(slpc, slpc->min_freq_softlimit);
+       }
        mutex_unlock(&slpc->lock);
 }
 
-- 
2.35.1