[PATCH 3/5] drm/i915: No TLB invalidation on wedged or suspended GT

[Nirmoy Das]

From: Fei Yang <fei.yang at intel.com>

In case of GT is suspended or wedged, don't allow submission of new TLB
invalidation request and cancel all pending requests. The TLB entries
will be invalidated either during GuC reload or on system resume.

Signed-off-by: Fei Yang <fei.yang at intel.com>
Signed-off-by: Nirmoy Das <nirmoy.das at intel.com>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc.c        |  5 +++++
 drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  1 +
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 21 +++++++++++++++----
 drivers/gpu/drm/i915/i915_driver.c            | 12 +++++++++++
 4 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index e3e3cd072d30..94d55e9b0b2f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -897,6 +897,11 @@ static int guc_send_invalidate_tlb(struct intel_guc *guc, u32 type)
 	};
 	u32 size = ARRAY_SIZE(action);
 
+	/* Check if GT is wedged or suspended */
+	if (intel_gt_is_wedged(guc_to_gt(guc)) ||
+	    !intel_irqs_enabled(guc_to_gt(guc)->i915))
+		return -EINVAL;
+
 	if (!(intel_guc_ct_enabled(&guc->ct) &&
 	      intel_guc_submission_is_used(guc))) {
 		GT_TRACE(guc_to_gt(guc), "GuC is not ready for TLB invalidation\n");
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index b5a1ab4145c9..ced97c27d1d7 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -536,4 +536,5 @@ void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
 
 int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc);
 
+void wake_up_all_tlb_invalidate(struct intel_guc *guc);
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 906ee7ca5f60..d1d1bb2f76a9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -32,6 +32,7 @@
 
 #include "i915_drv.h"
 #include "i915_reg.h"
+#include "i915_irq.h"
 #include "i915_trace.h"
 
 /**
@@ -1771,13 +1772,20 @@ static void wake_up_tlb_invalidate(struct intel_guc_tlb_wait *wait)
 	wake_up(&wait->wq);
 }
 
-void intel_guc_submission_reset(struct intel_guc *guc, intel_engine_mask_t stalled)
+void wake_up_all_tlb_invalidate(struct intel_guc *guc)
 {
 	struct intel_guc_tlb_wait *wait;
+	unsigned long i;
+
+	xa_for_each(&guc->tlb_lookup, i, wait)
+		wake_up_tlb_invalidate(wait);
+}
+
+void intel_guc_submission_reset(struct intel_guc *guc, intel_engine_mask_t stalled)
+{
 	struct intel_context *ce;
 	unsigned long index;
 	unsigned long flags;
-	unsigned long i;
 
 	if (unlikely(!guc_submission_initialized(guc))) {
 		/* Reset called during driver load? GuC not yet initialised! */
@@ -1808,8 +1816,7 @@ void intel_guc_submission_reset(struct intel_guc *guc, intel_engine_mask_t stall
 	 * The full GT reset will have cleared the TLB caches and flushed the
 	 * G2H message queue; we can release all the blocked waiters.
 	 */
-	xa_for_each(&guc->tlb_lookup, i, wait)
-		wake_up_tlb_invalidate(wait);
+	wake_up_all_tlb_invalidate(guc);
 }
 
 static void guc_cancel_context_requests(struct intel_context *ce)
@@ -1905,6 +1912,12 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
 
 	/* GuC is blown away, drop all references to contexts */
 	xa_destroy(&guc->context_lookup);
+
+	/*
+	 * Wedged GT won't respond to any TLB invalidation request. Simply
+	 * release all the blocked waiters.
+	 */
+	wake_up_all_tlb_invalidate(guc);
 }
 
 void intel_guc_submission_reset_finish(struct intel_guc *guc)
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index d50347e5773a..66d7906542c8 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -72,6 +72,7 @@
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_rc6.h"
+#include "gt/uc/intel_guc.h"
 
 #include "pxp/intel_pxp.h"
 #include "pxp/intel_pxp_debugfs.h"
@@ -1076,6 +1077,8 @@ static int i915_drm_suspend(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev);
 	pci_power_t opregion_target_state;
+	struct intel_gt *gt;
+	int i;
 
 	disable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
@@ -1092,6 +1095,10 @@ static int i915_drm_suspend(struct drm_device *dev)
 	intel_dp_mst_suspend(dev_priv);
 
 	intel_runtime_pm_disable_interrupts(dev_priv);
+
+	for_each_gt(gt, dev_priv, i)
+		wake_up_all_tlb_invalidate(&gt->uc.guc);
+
 	intel_hpd_cancel_work(dev_priv);
 
 	intel_suspend_encoders(dev_priv);
@@ -1263,6 +1270,11 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	intel_gvt_resume(dev_priv);
 
+	for_each_gt(gt, dev_priv, i) {
+		intel_guc_invalidate_tlb_full(&gt->uc.guc);
+		intel_guc_invalidate_tlb_guc(&gt->uc.guc);
+	}
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return 0;
-- 
2.41.0