drm/i915/guc: Implement banned contexts for GuC submission

When using GuC submission, if a context gets banned disable scheduling
and mark all inflight requests as complete.

Cc: John Harrison <John.C.Harrison@Intel.com>
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/20210727002348.97202-25-matthew.brost@intel.com

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -1084,7 +1084,7 @@ static void kill_engines(struct i915_gem_engines *engines, bool ban)
 	for_each_gem_engine(ce, engines, it) {
 		struct intel_engine_cs *engine;
 
-		if (ban && intel_context_set_banned(ce))
+		if (ban && intel_context_ban(ce, NULL))
 			continue;
 
 		/*

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

@@ -16,6 +16,7 @@
 #include "intel_engine_types.h"
 #include "intel_ring_types.h"
 #include "intel_timeline_types.h"
+#include "i915_trace.h"
 
 #define CE_TRACE(ce, fmt, ...) do {					\
 	const struct intel_context *ce__ = (ce);			\
@@ -243,6 +244,18 @@ static inline bool intel_context_set_banned(struct intel_context *ce)
 	return test_and_set_bit(CONTEXT_BANNED, &ce->flags);
 }
 
+static inline bool intel_context_ban(struct intel_context *ce,
+				     struct i915_request *rq)
+{
+	bool ret = intel_context_set_banned(ce);
+
+	trace_intel_context_ban(ce);
+	if (ce->ops->ban)
+		ce->ops->ban(ce, rq);
+
+	return ret;
+}
+
 static inline bool
 intel_context_force_single_submission(const struct intel_context *ce)
 {

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

@@ -35,6 +35,8 @@ struct intel_context_ops {
 
 	int (*alloc)(struct intel_context *ce);
 
+	void (*ban)(struct intel_context *ce, struct i915_request *rq);
+
 	int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr);
 	int (*pin)(struct intel_context *ce, void *vaddr);
 	void (*unpin)(struct intel_context *ce);

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

@@ -22,7 +22,6 @@
 #include "intel_reset.h"
 
 #include "uc/intel_guc.h"
-#include "uc/intel_guc_submission.h"
 
 #define RESET_MAX_RETRIES 3
 
@@ -39,21 +38,6 @@ static void rmw_clear_fw(struct intel_uncore *uncore, i915_reg_t reg, u32 clr)
 	intel_uncore_rmw_fw(uncore, reg, clr, 0);
 }
 
-static void skip_context(struct i915_request *rq)
-{
-	struct intel_context *hung_ctx = rq->context;
-
-	list_for_each_entry_from_rcu(rq, &hung_ctx->timeline->requests, link) {
-		if (!i915_request_is_active(rq))
-			return;
-
-		if (rq->context == hung_ctx) {
-			i915_request_set_error_once(rq, -EIO);
-			__i915_request_skip(rq);
-		}
-	}
-}
-
 static void client_mark_guilty(struct i915_gem_context *ctx, bool banned)
 {
 	struct drm_i915_file_private *file_priv = ctx->file_priv;
@@ -88,10 +72,8 @@ static bool mark_guilty(struct i915_request *rq)
 	bool banned;
 	int i;
 
-	if (intel_context_is_closed(rq->context)) {
-		intel_context_set_banned(rq->context);
+	if (intel_context_is_closed(rq->context))
 		return true;
-	}
 
 	rcu_read_lock();
 	ctx = rcu_dereference(rq->context->gem_context);
@@ -123,11 +105,9 @@ static bool mark_guilty(struct i915_request *rq)
 	banned = !i915_gem_context_is_recoverable(ctx);
 	if (time_before(jiffies, prev_hang + CONTEXT_FAST_HANG_JIFFIES))
 		banned = true;
-	if (banned) {
+	if (banned)
 		drm_dbg(&ctx->i915->drm, "context %s: guilty %d, banned\n",
 			ctx->name, atomic_read(&ctx->guilty_count));
-		intel_context_set_banned(rq->context);
-	}
 
 	client_mark_guilty(ctx, banned);
 
@@ -149,6 +129,8 @@ static void mark_innocent(struct i915_request *rq)
 
 void __i915_request_reset(struct i915_request *rq, bool guilty)
 {
+	bool banned = false;
+
 	RQ_TRACE(rq, "guilty? %s\n", yesno(guilty));
 	GEM_BUG_ON(__i915_request_is_complete(rq));
 
@@ -156,13 +138,15 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 	if (guilty) {
 		i915_request_set_error_once(rq, -EIO);
 		__i915_request_skip(rq);
-		if (mark_guilty(rq) && !intel_engine_uses_guc(rq->engine))
-			skip_context(rq);
+		banned = mark_guilty(rq);
 	} else {
 		i915_request_set_error_once(rq, -EAGAIN);
 		mark_innocent(rq);
 	}
 	rcu_read_unlock();
+
+	if (banned)
+		intel_context_ban(rq->context, rq);
 }
 
 static bool i915_in_reset(struct pci_dev *pdev)

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

@@ -586,9 +586,29 @@ static void ring_context_reset(struct intel_context *ce)
 	clear_bit(CONTEXT_VALID_BIT, &ce->flags);
 }
 
+static void ring_context_ban(struct intel_context *ce,
+			     struct i915_request *rq)
+{
+	struct intel_engine_cs *engine;
+
+	if (!rq || !i915_request_is_active(rq))
+		return;
+
+	engine = rq->engine;
+	lockdep_assert_held(&engine->sched_engine->lock);
+	list_for_each_entry_continue(rq, &engine->sched_engine->requests,
+				     sched.link)
+		if (rq->context == ce) {
+			i915_request_set_error_once(rq, -EIO);
+			__i915_request_skip(rq);
+		}
+}
+
 static const struct intel_context_ops ring_context_ops = {
 	.alloc = ring_context_alloc,
 
+	.ban = ring_context_ban,
+
 	.pre_pin = ring_context_pre_pin,
 	.pin = ring_context_pin,
 	.unpin = ring_context_unpin,

drivers/gpu/drm/i915/gt/uc/intel_guc.h

@@ -281,6 +281,8 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine);
 
 int intel_guc_global_policies_update(struct intel_guc *guc);
 
+void intel_guc_context_ban(struct intel_context *ce, struct i915_request *rq);
+
 void intel_guc_submission_reset_prepare(struct intel_guc *guc);
 void intel_guc_submission_reset(struct intel_guc *guc, bool stalled);
 void intel_guc_submission_reset_finish(struct intel_guc *guc);

drivers/gpu/drm/i915/i915_trace.h

@@ -925,6 +925,11 @@ DEFINE_EVENT(intel_context, intel_context_reset,
 	     TP_ARGS(ce)
 );
 
+DEFINE_EVENT(intel_context, intel_context_ban,
+	     TP_PROTO(struct intel_context *ce),
+	     TP_ARGS(ce)
+);
+
 DEFINE_EVENT(intel_context, intel_context_register,
 	     TP_PROTO(struct intel_context *ce),
 	     TP_ARGS(ce)
@@ -1017,6 +1022,11 @@ trace_intel_context_reset(struct intel_context *ce)
 {
 }
 
+static inline void
+trace_intel_context_ban(struct intel_context *ce)
+{
+}
+
 static inline void
 trace_intel_context_register(struct intel_context *ce)
 {