[Intel-gfx] [PATCH v2] drm/i915: fix SFC reset flow

[Daniele Ceraolo Spurio]

Our assumption that the we can ask the HW to lock the SFC even if not
currently in use does not match the HW commitment. The expectation from
the HW is that SW will not try to lock the SFC if the engine is not
using it and if we do that the behavior is undefined; on ICL the HW
ends up to returning the ack and ignoring our lock request, but this is
not guaranteed and we shouldn't expect it going forward.

Also, failing to get the ack while the SFC is in use means that we can't
cleanly reset it, so fail the engine reset in that scenario.

v2: drop rmw change, keep the log as debug and handle failure (Chris),
    improve comments (Tvrtko).

Reported-by: Owen Zhang <owen.zhang at intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin at linux.intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_reset.c | 51 +++++++++++++++++----------
 1 file changed, 33 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 8327220ac558..797cf50625cb 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -309,7 +309,7 @@ static int gen6_reset_engines(struct intel_gt *gt,
 	return gen6_hw_domain_reset(gt, hw_mask);
 }
 
-static u32 gen11_lock_sfc(struct intel_engine_cs *engine)
+static int gen11_lock_sfc(struct intel_engine_cs *engine, u32 *hw_mask)
 {
 	struct intel_uncore *uncore = engine->uncore;
 	u8 vdbox_sfc_access = RUNTIME_INFO(engine->i915)->vdbox_sfc_access;
@@ -318,6 +318,7 @@ static u32 gen11_lock_sfc(struct intel_engine_cs *engine)
 	i915_reg_t sfc_usage;
 	u32 sfc_usage_bit;
 	u32 sfc_reset_bit;
+	int ret;
 
 	switch (engine->class) {
 	case VIDEO_DECODE_CLASS:
@@ -352,28 +353,33 @@ static u32 gen11_lock_sfc(struct intel_engine_cs *engine)
 	}
 
 	/*
-	 * Tell the engine that a software reset is going to happen. The engine
-	 * will then try to force lock the SFC (if currently locked, it will
-	 * remain so until we tell the engine it is safe to unlock; if currently
-	 * unlocked, it will ignore this and all new lock requests). If SFC
-	 * ends up being locked to the engine we want to reset, we have to reset
-	 * it as well (we will unlock it once the reset sequence is completed).
+	 * If the engine is using a SFC, tell the engine that a software reset
+	 * is going to happen. The engine will then try to force lock the SFC.
+	 * If SFC ends up being locked to the engine we want to reset, we have
+	 * to reset it as well (we will unlock it once the reset sequence is
+	 * completed).
 	 */
+	if (!(intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit))
+		return 0;
+
 	rmw_set_fw(uncore, sfc_forced_lock, sfc_forced_lock_bit);
 
-	if (__intel_wait_for_register_fw(uncore,
-					 sfc_forced_lock_ack,
-					 sfc_forced_lock_ack_bit,
-					 sfc_forced_lock_ack_bit,
-					 1000, 0, NULL)) {
-		DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
+	ret = __intel_wait_for_register_fw(uncore,
+					   sfc_forced_lock_ack,
+					   sfc_forced_lock_ack_bit,
+					   sfc_forced_lock_ack_bit,
+					   1000, 0, NULL);
+
+	/* was the SFC released while we were trying to lock it? */
+	if (!(intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit))
 		return 0;
-	}
 
-	if (intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit)
-		return sfc_reset_bit;
+	if (ret)
+		DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
+	else
+		*hw_mask |= sfc_reset_bit;
 
-	return 0;
+	return ret;
 }
 
 static void gen11_unlock_sfc(struct intel_engine_cs *engine)
@@ -430,12 +436,21 @@ static int gen11_reset_engines(struct intel_gt *gt,
 		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
 			hw_mask |= hw_engine_mask[engine->id];
-			hw_mask |= gen11_lock_sfc(engine);
+			ret = gen11_lock_sfc(engine, &hw_mask);
+			if (ret)
+				goto sfc_unlock;
 		}
 	}
 
 	ret = gen6_hw_domain_reset(gt, hw_mask);
 
+sfc_unlock:
+	/*
+	 * we unlock the SFC based on the lock status and not the result of
+	 * gen11_lock_sfc to make sure that we clean properly if something
+	 * wrong happened during the lock (e.g. lock acquired after timeout
+	 * expiration).
+	 */
 	if (engine_mask != ALL_ENGINES)
 		for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
 			gen11_unlock_sfc(engine);
-- 
2.23.0