From 7ff49300931015923a5a66ee98f9ea2a51ee5610 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 20 Jan 2022 20:31:17 -0800
Subject: drm/i915/guc: Add work queue to trigger a GT reset
Git-commit: 1f73a367420c954f5cae2f899ebb9515be093645
Patch-mainline: v5.18-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

The G2H handler needs to be flushed during a GT reset but a G2H
indicating engine reset failure can trigger a GT reset. Add a worker to
trigger the GT rest when an engine reset failure is received to break
this circular dependency.

v2:
 (John Harrison)
  - Store engine reset mask
  - Fix typo in commit message
v3:
 (John Harrison)
  - Fix another typo in commit message
  - s/reset_*/reset_fail_*/

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220121043118.24886-3-matthew.brost@intel.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  9 +++++
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 37 +++++++++++++++++--
 2 files changed, 42 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 3bdbfe6a4a9e..697d9d66acef 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -119,6 +119,15 @@ struct intel_guc {
 		 * function as it might be in an atomic context (no sleeping)
 		 */
 		struct work_struct destroyed_worker;
+		/**
+		 * @reset_fail_worker: worker to trigger a GT reset after an
+		 * engine reset fails
+		 */
+		struct work_struct reset_fail_worker;
+		/**
+		 * @reset_fail_mask: mask of engines that failed to reset
+		 */
+		intel_engine_mask_t reset_fail_mask;
 	} submission_state;
 
 	/**
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 9cb700984e2a..4a0cf42c90b6 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1811,6 +1811,7 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc)
 }
 
 static void destroyed_worker_func(struct work_struct *w);
+static void reset_fail_worker_func(struct work_struct *w);
 
 /*
  * Set up the memory resources to be shared with the GuC (via the GGTT)
@@ -1841,6 +1842,8 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	INIT_LIST_HEAD(&guc->submission_state.destroyed_contexts);
 	INIT_WORK(&guc->submission_state.destroyed_worker,
 		  destroyed_worker_func);
+	INIT_WORK(&guc->submission_state.reset_fail_worker,
+		  reset_fail_worker_func);
 
 	guc->submission_state.guc_ids_bitmap =
 		bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID(guc), GFP_KERNEL);
@@ -4107,6 +4110,26 @@ guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
 	return gt->engine_class[engine_class][instance];
 }
 
+static void reset_fail_worker_func(struct work_struct *w)
+{
+	struct intel_guc *guc = container_of(w, struct intel_guc,
+					     submission_state.reset_fail_worker);
+	struct intel_gt *gt = guc_to_gt(guc);
+	intel_engine_mask_t reset_fail_mask;
+	unsigned long flags;
+
+	spin_lock_irqsave(&guc->submission_state.lock, flags);
+	reset_fail_mask = guc->submission_state.reset_fail_mask;
+	guc->submission_state.reset_fail_mask = 0;
+	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
+
+	if (likely(reset_fail_mask))
+		intel_gt_handle_error(gt, reset_fail_mask,
+				      I915_ERROR_CAPTURE,
+				      "GuC failed to reset engine mask=0x%x\n",
+				      reset_fail_mask);
+}
+
 int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 					 const u32 *msg, u32 len)
 {
@@ -4114,6 +4137,7 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 	struct intel_gt *gt = guc_to_gt(guc);
 	u8 guc_class, instance;
 	u32 reason;
+	unsigned long flags;
 
 	if (unlikely(len != 3)) {
 		drm_err(&gt->i915->drm, "Invalid length %u", len);
@@ -4138,10 +4162,15 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 	drm_err(&gt->i915->drm, "GuC engine reset request failed on %d:%d (%s) because 0x%08X",
 		guc_class, instance, engine->name, reason);
 
-	intel_gt_handle_error(gt, engine->mask,
-			      I915_ERROR_CAPTURE,
-			      "GuC failed to reset %s (reason=0x%08x)\n",
-			      engine->name, reason);
+	spin_lock_irqsave(&guc->submission_state.lock, flags);
+	guc->submission_state.reset_fail_mask |= engine->mask;
+	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
+
+	/*
+	 * A GT reset flushes this worker queue (G2H handler) so we must use
+	 * another worker to trigger a GT reset.
+	 */
+	queue_work(system_unbound_wq, &guc->submission_state.reset_fail_worker);
 
 	return 0;
 }
-- 
2.38.1