drm/i915/gt: Register the migrate contexts with their engines

[ Upstream commit 3e42cc61275f95fd7f022b6380b95428efe134d3 ]

Pinned contexts, like the migrate contexts need reset after resume
since their context image may have been lost. Also the GuC needs to
register pinned contexts.

Add a list to struct intel_engine_cs where we add all pinned contexts on
creation, and traverse that list at resume time to reset the pinned
contexts.

This fixes the kms_pipe_crc_basic@suspend-read-crc-pipe-a selftest for now,
but proper LMEM backup / restore is needed for full suspend functionality.
However, note that even with full LMEM backup / restore it may be
desirable to keep the reset since backing up the migrate context images
must happen using memcpy() after the migrate context has become inactive,
and for performance- and other reasons we want to avoid memcpy() from
LMEM.

Also traverse the list at guc_init_lrc_mapping() calling
guc_kernel_context_pin() for the pinned contexts, like is already done
for the kernel context.

v2:
- Don't reset the contexts on each __engine_unpark() but rather at
  resume time (Chris Wilson).
v3:
- Reset contexts in the engine sanitize callback. (Chris Wilson)

Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Brost Matthew <matthew.brost@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210922062527.865433-6-thomas.hellstrom@linux.intel.com
Signed-off-by: Sasha Levin <sashal@kernel.org>

drivers/gpu/drm/i915/gt/intel_context_types.h

@@ -152,6 +152,14 @@ struct intel_context {
 	/** sseu: Control eu/slice partitioning */
 	struct intel_sseu sseu;
 
+	/**
+	 * pinned_contexts_link: List link for the engine's pinned contexts.
+	 * This is only used if this is a perma-pinned kernel context and
+	 * the list is assumed to only be manipulated during driver load
+	 * or unload time so no mutex protection currently.
+	 */
+	struct list_head pinned_contexts_link;
+
 	u8 wa_bb_page; /* if set, page num reserved for context workarounds */
 
 	struct {

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -320,6 +320,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 
 	BUILD_BUG_ON(BITS_PER_TYPE(engine->mask) < I915_NUM_ENGINES);
 
+	INIT_LIST_HEAD(&engine->pinned_contexts_list);
 	engine->id = id;
 	engine->legacy_idx = INVALID_ENGINE;
 	engine->mask = BIT(id);
@@ -875,6 +876,8 @@ intel_engine_create_pinned_context(struct intel_engine_cs *engine,
 		return ERR_PTR(err);
 	}
 
+	list_add_tail(&ce->pinned_contexts_link, &engine->pinned_contexts_list);
+
 	/*
 	 * Give our perma-pinned kernel timelines a separate lockdep class,
 	 * so that we can use them from within the normal user timelines
@@ -897,6 +900,7 @@ void intel_engine_destroy_pinned_context(struct intel_context *ce)
 	list_del(&ce->timeline->engine_link);
 	mutex_unlock(&hwsp->vm->mutex);
 
+	list_del(&ce->pinned_contexts_link);
 	intel_context_unpin(ce);
 	intel_context_put(ce);
 }

drivers/gpu/drm/i915/gt/intel_engine_pm.c

@@ -298,6 +298,29 @@ void intel_engine_init__pm(struct intel_engine_cs *engine)
 	intel_engine_init_heartbeat(engine);
 }
 
+/**
+ * intel_engine_reset_pinned_contexts - Reset the pinned contexts of
+ * an engine.
+ * @engine: The engine whose pinned contexts we want to reset.
+ *
+ * Typically the pinned context LMEM images lose or get their content
+ * corrupted on suspend. This function resets their images.
+ */
+void intel_engine_reset_pinned_contexts(struct intel_engine_cs *engine)
+{
+	struct intel_context *ce;
+
+	list_for_each_entry(ce, &engine->pinned_contexts_list,
+			    pinned_contexts_link) {
+		/* kernel context gets reset at __engine_unpark() */
+		if (ce == engine->kernel_context)
+			continue;
+
+		dbg_poison_ce(ce);
+		ce->ops->reset(ce);
+	}
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_engine_pm.c"
 #endif

drivers/gpu/drm/i915/gt/intel_engine_pm.h

@@ -69,4 +69,6 @@ intel_engine_create_kernel_request(struct intel_engine_cs *engine)
 
 void intel_engine_init__pm(struct intel_engine_cs *engine);
 
+void intel_engine_reset_pinned_contexts(struct intel_engine_cs *engine);
+
 #endif /* INTEL_ENGINE_PM_H */

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -304,6 +304,13 @@ struct intel_engine_cs {
 
 	struct intel_context *kernel_context; /* pinned */
 
+	/**
+	 * pinned_contexts_list: List of pinned contexts. This list is only
+	 * assumed to be manipulated during driver load- or unload time and
+	 * does therefore not have any additional protection.
+	 */
+	struct list_head pinned_contexts_list;
+
 	intel_engine_mask_t saturated; /* submitting semaphores too late? */
 
 	struct {

drivers/gpu/drm/i915/gt/intel_execlists_submission.c

@@ -2787,6 +2787,8 @@ static void execlists_sanitize(struct intel_engine_cs *engine)
 
 	/* And scrub the dirty cachelines for the HWSP */
 	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+
+	intel_engine_reset_pinned_contexts(engine);
 }
 
 static void enable_error_interrupt(struct intel_engine_cs *engine)

drivers/gpu/drm/i915/gt/intel_ring_submission.c

@@ -17,6 +17,7 @@
 #include "intel_ring.h"
 #include "shmem_utils.h"
 #include "intel_engine_heartbeat.h"
+#include "intel_engine_pm.h"
 
 /* Rough estimate of the typical request size, performing a flush,
  * set-context and then emitting the batch.
@@ -292,6 +293,8 @@ static void xcs_sanitize(struct intel_engine_cs *engine)
 
 	/* And scrub the dirty cachelines for the HWSP */
 	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+
+	intel_engine_reset_pinned_contexts(engine);
 }
 
 static void reset_prepare(struct intel_engine_cs *engine)

drivers/gpu/drm/i915/gt/mock_engine.c

@@ -376,6 +376,8 @@ int mock_engine_init(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 
+	INIT_LIST_HEAD(&engine->pinned_contexts_list);
+
 	engine->sched_engine = i915_sched_engine_create(ENGINE_MOCK);
 	if (!engine->sched_engine)
 		return -ENOMEM;

drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c

@@ -2347,6 +2347,8 @@ static void guc_sanitize(struct intel_engine_cs *engine)
 
 	/* And scrub the dirty cachelines for the HWSP */
 	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+
+	intel_engine_reset_pinned_contexts(engine);
 }
 
 static void setup_hwsp(struct intel_engine_cs *engine)
@@ -2422,9 +2424,13 @@ static inline void guc_init_lrc_mapping(struct intel_guc *guc)
 	 * and even it did this code would be run again.
 	 */
 
-	for_each_engine(engine, gt, id)
+	for_each_engine(engine, gt, id) {
-		if (engine->kernel_context)
+		struct intel_context *ce;
-			guc_kernel_context_pin(guc, engine->kernel_context);
+
+		list_for_each_entry(ce, &engine->pinned_contexts_list,
+				    pinned_contexts_link)
+			guc_kernel_context_pin(guc, ce);
+	}
 }
 
 static void guc_release(struct intel_engine_cs *engine)