[2/2] drm/i915: No TLB invalidation on wedged or suspended GT

Commit Message

Cavitt, Jonathan Sept. 29, 2023, 3:23 p.m. UTC

From: Fei Yang <[e-mail]>

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 <[e-mail]>
Signed-off-by: Jonathan Cavitt <[e-mail]>
CC: John Harrison <[e-mail]>
---
 drivers/gpu/drm/i915/gt/intel_gt.h            |  9 +++++++
 drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  1 +
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 27 ++++++++++++++-----
 drivers/gpu/drm/i915/i915_driver.c            | 12 +++++++++
 4 files changed, 43 insertions(+), 6 deletions(-)

Patch

diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 2cac499d5aa3e..3fcc0d2cd7bf3 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -9,6 +9,7 @@ 
 #include "intel_engine_types.h"
 #include "intel_gt_types.h"
 #include "intel_reset.h"
+#include "i915_irq.h"
 
 struct drm_i915_private;
 struct drm_printer;
@@ -157,6 +158,14 @@  static inline bool intel_gt_is_wedged(const struct intel_gt *gt)
 	return unlikely(test_bit(I915_WEDGED, &gt->reset.flags));
 }
 
+static inline bool intel_gt_is_enabled(const struct intel_gt *gt)
+{
+	/* Check if GT is wedged or suspended */
+	if (intel_gt_is_wedged(gt) || !intel_irqs_enabled(gt->i915))
+		return false;
+	return true;
+}
+
 int intel_gt_probe_all(struct drm_i915_private *i915);
 int intel_gt_tiles_init(struct drm_i915_private *i915);
 void intel_gt_release_all(struct drm_i915_private *i915);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 0f74a460bfe56..5fe48f7ab7d65 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 6a2dcab63074e..fd64443806e5c 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"
 
 /**
@@ -1803,13 +1804,20 @@  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! */
@@ -1840,8 +1848,7 @@  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)
@@ -1937,6 +1944,12 @@  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)
@@ -4764,7 +4777,8 @@  static int guc_send_invalidate_tlb(struct intel_guc *guc, u32 type)
 	};
 	u32 size = ARRAY_SIZE(action);
 
-	if (!intel_guc_ct_enabled(&guc->ct))
+	if (!intel_guc_ct_enabled(&guc->ct) ||
+	    !intel_gt_is_enabled(gt))
 		return -EINVAL;
 
 	init_waitqueue_head(&_wq.wq);
@@ -4806,7 +4820,8 @@  static int guc_send_invalidate_tlb(struct intel_guc *guc, u32 type)
 	 * queued in CT buffer.
 	 */
 #define OUTSTANDING_GUC_TIMEOUT_PERIOD  (HZ * 2)
-	if (!must_wait_woken(&wait, OUTSTANDING_GUC_TIMEOUT_PERIOD)) {
+	if (!must_wait_woken(&wait, OUTSTANDING_GUC_TIMEOUT_PERIOD) &&
+	    intel_gt_is_enabled(gt)) {
 		gt_err(gt,
 		       "TLB invalidation response timed out for seqno %u\n", seqno);
 		err = -ETIME;
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index 78501a83ba109..30c2a7ced10f8 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(&gt->uc.guc);
+	}
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return 0;