[Intel-gfx] [PATCH v3 1/2] drm/i915/gt: Serialize GRDOM access between multiple engine resets

[Mauro Carvalho Chehab]

From: Chris Wilson <chris.p.wilson at intel.com>

Don't allow two engines to be reset in parallel, as they would both
try to select a reset bit (and send requests to common registers)
and wait on that register, at the same time. Serialize control of
the reset requests/acks using the uncore->lock, which will also ensure
that no other GT state changes at the same time as the actual reset.

Cc: stable at vger.kernel.org # Up to 4.4
Reported-by: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti at intel.com>
Acked-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab at kernel.org>
---

To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
See [PATCH v3 0/2] at: https://lore.kernel.org/all/cover.1656921701.git.mchehab@kernel.org/

 drivers/gpu/drm/i915/gt/intel_reset.c | 37 ++++++++++++++++++++-------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index a5338c3fde7a..c68d36fb5bbd 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -300,9 +300,9 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
 	return err;
 }
 
-static int gen6_reset_engines(struct intel_gt *gt,
-			      intel_engine_mask_t engine_mask,
-			      unsigned int retry)
+static int __gen6_reset_engines(struct intel_gt *gt,
+				intel_engine_mask_t engine_mask,
+				unsigned int retry)
 {
 	struct intel_engine_cs *engine;
 	u32 hw_mask;
@@ -321,6 +321,20 @@ static int gen6_reset_engines(struct intel_gt *gt,
 	return gen6_hw_domain_reset(gt, hw_mask);
 }
 
+static int gen6_reset_engines(struct intel_gt *gt,
+			      intel_engine_mask_t engine_mask,
+			      unsigned int retry)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&gt->uncore->lock, flags);
+	ret = __gen6_reset_engines(gt, engine_mask, retry);
+	spin_unlock_irqrestore(&gt->uncore->lock, flags);
+
+	return ret;
+}
+
 static struct intel_engine_cs *find_sfc_paired_vecs_engine(struct intel_engine_cs *engine)
 {
 	int vecs_id;
@@ -487,9 +501,9 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine)
 	rmw_clear_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit);
 }
 
-static int gen11_reset_engines(struct intel_gt *gt,
-			       intel_engine_mask_t engine_mask,
-			       unsigned int retry)
+static int __gen11_reset_engines(struct intel_gt *gt,
+				 intel_engine_mask_t engine_mask,
+				 unsigned int retry)
 {
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
@@ -583,8 +597,11 @@ static int gen8_reset_engines(struct intel_gt *gt,
 	struct intel_engine_cs *engine;
 	const bool reset_non_ready = retry >= 1;
 	intel_engine_mask_t tmp;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&gt->uncore->lock, flags);
+
 	for_each_engine_masked(engine, gt, engine_mask, tmp) {
 		ret = gen8_engine_reset_prepare(engine);
 		if (ret && !reset_non_ready)
@@ -612,17 +629,19 @@ static int gen8_reset_engines(struct intel_gt *gt,
 	 * This is best effort, so ignore any error from the initial reset.
 	 */
 	if (IS_DG2(gt->i915) && engine_mask == ALL_ENGINES)
-		gen11_reset_engines(gt, gt->info.engine_mask, 0);
+		__gen11_reset_engines(gt, gt->info.engine_mask, 0);
 
 	if (GRAPHICS_VER(gt->i915) >= 11)
-		ret = gen11_reset_engines(gt, engine_mask, retry);
+		ret = __gen11_reset_engines(gt, engine_mask, retry);
 	else
-		ret = gen6_reset_engines(gt, engine_mask, retry);
+		ret = __gen6_reset_engines(gt, engine_mask, retry);
 
 skip_reset:
 	for_each_engine_masked(engine, gt, engine_mask, tmp)
 		gen8_engine_reset_cancel(engine);
 
+	spin_unlock_irqrestore(&gt->uncore->lock, flags);
+
 	return ret;
 }
 
-- 
2.36.1