Merge tag 'drm-intel-fixes-2022-09-29' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixesdrm-fixes-2022-09-30-1drm-fixes-2022-09-30

- Restrict forced preemption to the active context (Chris)
- Restrict perf_limit_reasons to the supported platforms - gen11+ (Ashutosh)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YzXAkH1a32pYJD33@intel.com

3 files changed, 46 insertions, 5 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 633a7e5dba3b..6b5d4ea22b67 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -166,6 +166,21 @@ struct intel_engine_execlists {
 	struct timer_list preempt;
 
 	/**
+	 * @preempt_target: active request at the time of the preemption request
+	 *
+	 * We force a preemption to occur if the pending contexts have not
+	 * been promoted to active upon receipt of the CS ack event within
+	 * the timeout. This timeout maybe chosen based on the target,
+	 * using a very short timeout if the context is no longer schedulable.
+	 * That short timeout may not be applicable to other contexts, so
+	 * if a context switch should happen within before the preemption
+	 * timeout, we may shoot early at an innocent context. To prevent this,
+	 * we record which context was active at the time of the preemption
+	 * request and only reset that context upon the timeout.
+	 */
+	const struct i915_request *preempt_target;
+
+	/**
 	 * @ccid: identifier for contexts submitted to this engine
 	 */
 	u32 ccid;
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 4b909cb88cdf..c718e6dc40b5 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -1241,6 +1241,9 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine,
 	if (!rq)
 		return 0;
 
+	/* Only allow ourselves to force reset the currently active context */
+	engine->execlists.preempt_target = rq;
+
 	/* Force a fast reset for terminated contexts (ignoring sysfs!) */
 	if (unlikely(intel_context_is_banned(rq->context) || bad_request(rq)))
 		return INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS;
@@ -2427,8 +2430,24 @@ static void execlists_submission_tasklet(struct tasklet_struct *t)
 	GEM_BUG_ON(inactive - post > ARRAY_SIZE(post));
 
 	if (unlikely(preempt_timeout(engine))) {
+		const struct i915_request *rq = *engine->execlists.active;
+
+		/*
+		 * If after the preempt-timeout expired, we are still on the
+		 * same active request/context as before we initiated the
+		 * preemption, reset the engine.
+		 *
+		 * However, if we have processed a CS event to switch contexts,
+		 * but not yet processed the CS event for the pending
+		 * preemption, reset the timer allowing the new context to
+		 * gracefully exit.
+		 */
 		cancel_timer(&engine->execlists.preempt);
-		engine->execlists.error_interrupt |= ERROR_PREEMPT;
+		if (rq == engine->execlists.preempt_target)
+			engine->execlists.error_interrupt |= ERROR_PREEMPT;
+		else
+			set_timer_ms(&engine->execlists.preempt,
+				     active_preempt_timeout(engine, rq));
 	}
 
 	if (unlikely(READ_ONCE(engine->execlists.error_interrupt))) {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
index 73a8b46e0234..d09a0e845d09 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
@@ -545,8 +545,7 @@ static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_ratl, RATL_MASK);
 static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_thermalert, VR_THERMALERT_MASK);
 static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_tdc, VR_TDC_MASK);
 
-static const struct attribute *freq_attrs[] = {
-	&dev_attr_punit_req_freq_mhz.attr,
+static const struct attribute *throttle_reason_attrs[] = {
 	&attr_throttle_reason_status.attr,
 	&attr_throttle_reason_pl1.attr,
 	&attr_throttle_reason_pl2.attr,
@@ -763,12 +762,20 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
 	if (!is_object_gt(kobj))
 		return;
 
-	ret = sysfs_create_files(kobj, freq_attrs);
+	ret = sysfs_create_file(kobj, &dev_attr_punit_req_freq_mhz.attr);
 	if (ret)
 		drm_warn(&gt->i915->drm,
-			 "failed to create gt%u throttle sysfs files (%pe)",
+			 "failed to create gt%u punit_req_freq_mhz sysfs (%pe)",
 			 gt->info.id, ERR_PTR(ret));
 
+	if (GRAPHICS_VER(gt->i915) >= 11) {
+		ret = sysfs_create_files(kobj, throttle_reason_attrs);
+		if (ret)
+			drm_warn(&gt->i915->drm,
+				 "failed to create gt%u throttle sysfs files (%pe)",
+				 gt->info.id, ERR_PTR(ret));
+	}
+
 	if (HAS_MEDIA_RATIO_MODE(gt->i915) && intel_uc_uses_guc_slpc(&gt->uc)) {
 		ret = sysfs_create_files(kobj, media_perf_power_attrs);
 		if (ret)