diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 1f1761fc6597d09ab6446c277fded7aceae96215..5b31e1e05ddd6423d708390adc338583ae1e82a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -116,6 +116,7 @@ intel_context_init(struct intel_context *ce,
 	ce->engine = engine;
 	ce->ops = engine->cops;
 	ce->sseu = engine->sseu;
+	ce->saturated = 0;
 
 	INIT_LIST_HEAD(&ce->signal_link);
 	INIT_LIST_HEAD(&ce->signals);
@@ -158,6 +159,7 @@ void intel_context_enter_engine(struct intel_context *ce)
 
 void intel_context_exit_engine(struct intel_context *ce)
 {
+	ce->saturated = 0;
 	intel_engine_pm_put(ce->engine);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index d5a7dbd0daeeff553b2cfaeab2c0541c4c796964..963a312430e6d37a8a3a627afab750d77df8c550 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -13,6 +13,7 @@
 #include <linux/types.h>
 
 #include "i915_active_types.h"
+#include "intel_engine_types.h"
 #include "intel_sseu.h"
 
 struct i915_gem_context;
@@ -52,6 +53,8 @@ struct intel_context {
 	atomic_t pin_count;
 	struct mutex pin_mutex; /* guards pinning and associated on-gpuing */
 
+	intel_engine_mask_t saturated; /* submitting semaphores too late? */
+
 	/**
 	 * active_tracker: Active tracker for the external rq activity
 	 * on this intel_context object.
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index d06c45305b03d9af0b7f9ea11e338ed087e6f073..ae9ce46e1b15055e886a4cfce0b661b8332032b5 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -410,6 +410,26 @@ void __i915_request_submit(struct i915_request *request)
 	if (i915_gem_context_is_banned(request->gem_context))
 		i915_request_skip(request, -EIO);
 
+	/*
+	 * Are we using semaphores when the gpu is already saturated?
+	 *
+	 * Using semaphores incurs a cost in having the GPU poll a
+	 * memory location, busywaiting for it to change. The continual
+	 * memory reads can have a noticeable impact on the rest of the
+	 * system with the extra bus traffic, stalling the cpu as it too
+	 * tries to access memory across the bus (perf stat -e bus-cycles).
+	 *
+	 * If we installed a semaphore on this request and we only submit
+	 * the request after the signaler completed, that indicates the
+	 * system is overloaded and using semaphores at this time only
+	 * increases the amount of work we are doing. If so, we disable
+	 * further use of semaphores until we are idle again, whence we
+	 * optimistically try again.
+	 */
+	if (request->sched.semaphores &&
+	    i915_sw_fence_signaled(&request->semaphore))
+		request->hw_context->saturated |= request->sched.semaphores;
+
 	/* We may be recursing from the signal callback of another i915 fence */
 	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
@@ -785,6 +805,24 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 					     I915_FENCE_GFP);
 }
 
+static intel_engine_mask_t
+already_busywaiting(struct i915_request *rq)
+{
+	/*
+	 * Polling a semaphore causes bus traffic, delaying other users of
+	 * both the GPU and CPU. We want to limit the impact on others,
+	 * while taking advantage of early submission to reduce GPU
+	 * latency. Therefore we restrict ourselves to not using more
+	 * than one semaphore from each source, and not using a semaphore
+	 * if we have detected the engine is saturated (i.e. would not be
+	 * submitted early and cause bus traffic reading an already passed
+	 * semaphore).
+	 *
+	 * See the are-we-too-late? check in __i915_request_submit().
+	 */
+	return rq->sched.semaphores | rq->hw_context->saturated;
+}
+
 static int
 emit_semaphore_wait(struct i915_request *to,
 		    struct i915_request *from,
@@ -798,7 +836,7 @@ emit_semaphore_wait(struct i915_request *to,
 	GEM_BUG_ON(INTEL_GEN(to->i915) < 8);
 
 	/* Just emit the first semaphore we see as request space is limited. */
-	if (to->sched.semaphores & from->engine->mask)
+	if (already_busywaiting(to) & from->engine->mask)
 		return i915_sw_fence_await_dma_fence(&to->submit,
 						     &from->fence, 0,
 						     I915_FENCE_GFP);