drm/i915/guc: Update intel_gt_wait_for_idle to work with GuC

When running the GuC the GPU can't be considered idle if the GuC still
has contexts pinned. As such, a call has been added in
intel_gt_wait_for_idle to idle the UC and in turn the GuC by waiting for
the number of unpinned contexts to go to zero.

v2: rtimeout -> remaining_timeout
v3: Drop unnecessary includes, guc_submission_busy_loop ->
guc_submission_send_busy_loop, drop negatie timeout trick, move a
refactor of guc_context_unpin to earlier path (John H)
v4: Add stddef.h back into intel_gt_requests.h, sort circuit idle
function if not in GuC submission mode

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/20210721215101.139794-16-matthew.brost@intel.com

drivers/gpu/drm/i915/gem/i915_gem_mman.c

@@ -645,7 +645,8 @@ mmap_offset_attach(struct drm_i915_gem_object *obj,
 		goto insert;
 
 	/* Attempt to reap some mmap space from dead objects */
-	err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT);
+	err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT,
+					       NULL);
 	if (err)
 		goto err;
 

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

@@ -585,6 +585,25 @@ static void __intel_gt_disable(struct intel_gt *gt)
 	GEM_BUG_ON(intel_gt_pm_is_awake(gt));
 }
 
+int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout)
+{
+	long remaining_timeout;
+
+	/* If the device is asleep, we have no requests outstanding */
+	if (!intel_gt_pm_is_awake(gt))
+		return 0;
+
+	while ((timeout = intel_gt_retire_requests_timeout(gt, timeout,
+							   &remaining_timeout)) > 0) {
+		cond_resched();
+		if (signal_pending(current))
+			return -EINTR;
+	}
+
+	return timeout ? timeout : intel_uc_wait_for_idle(&gt->uc,
+							  remaining_timeout);
+}
+
 int intel_gt_init(struct intel_gt *gt)
 {
 	int err;

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

@@ -48,6 +48,8 @@ void intel_gt_driver_release(struct intel_gt *gt);
 
 void intel_gt_driver_late_release(struct intel_gt *gt);
 
+int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
+
 void intel_gt_check_and_clear_faults(struct intel_gt *gt);
 void intel_gt_clear_error_registers(struct intel_gt *gt,
 				    intel_engine_mask_t engine_mask);

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

@@ -130,7 +130,8 @@ void intel_engine_fini_retire(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->retire);
 }
 
-long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
+long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout,
+				      long *remaining_timeout)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl, *tn;
@@ -195,22 +196,10 @@ out_active:	spin_lock(&timelines->lock);
 	if (flush_submission(gt, timeout)) /* Wait, there's more! */
 		active_count++;
 
-	return active_count ? timeout : 0;
-}
-
-int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout)
-{
-	/* If the device is asleep, we have no requests outstanding */
-	if (!intel_gt_pm_is_awake(gt))
-		return 0;
-
-	while ((timeout = intel_gt_retire_requests_timeout(gt, timeout)) > 0) {
-		cond_resched();
-		if (signal_pending(current))
-			return -EINTR;
-	}
+	if (remaining_timeout)
+		*remaining_timeout = timeout;
 
-	return timeout;
+	return active_count ? timeout : 0;
 }
 
 static void retire_work_handler(struct work_struct *work)

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

@@ -6,14 +6,17 @@
 #ifndef INTEL_GT_REQUESTS_H
 #define INTEL_GT_REQUESTS_H
 
+#include <stddef.h>
+
 struct intel_engine_cs;
 struct intel_gt;
 struct intel_timeline;
 
-long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout);
+long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout,
+				      long *remaining_timeout);
 static inline void intel_gt_retire_requests(struct intel_gt *gt)
 {
-	intel_gt_retire_requests_timeout(gt, 0);
+	intel_gt_retire_requests_timeout(gt, 0, NULL);
 }
 
 void intel_engine_init_retire(struct intel_engine_cs *engine);
@@ -21,8 +24,6 @@ void intel_engine_add_retire(struct intel_engine_cs *engine,
 			     struct intel_timeline *tl);
 void intel_engine_fini_retire(struct intel_engine_cs *engine);
 
-int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
-
 void intel_gt_init_requests(struct intel_gt *gt);
 void intel_gt_park_requests(struct intel_gt *gt);
 void intel_gt_unpark_requests(struct intel_gt *gt);

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

@@ -39,6 +39,8 @@ struct intel_guc {
 	spinlock_t irq_lock;
 	unsigned int msg_enabled_mask;
 
+	atomic_t outstanding_submission_g2h;
+
 	struct {
 		void (*reset)(struct intel_guc *guc);
 		void (*enable)(struct intel_guc *guc);
@@ -245,6 +247,8 @@ static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask)
 	spin_unlock_irq(&guc->irq_lock);
 }
 
+int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout);
+
 int intel_guc_reset_engine(struct intel_guc *guc,
 			   struct intel_engine_cs *engine);
 

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

@@ -109,6 +109,7 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 	INIT_LIST_HEAD(&ct->requests.incoming);
 	INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
 	tasklet_setup(&ct->receive_tasklet, ct_receive_tasklet_func);
+	init_waitqueue_head(&ct->wq);
 }
 
 static inline const char *guc_ct_buffer_type_to_str(u32 type)

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

@@ -10,6 +10,7 @@
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/ktime.h>
+#include <linux/wait.h>
 
 #include "intel_guc_fwif.h"
 
@@ -68,6 +69,9 @@ struct intel_guc_ct {
 
 	struct tasklet_struct receive_tasklet;
 
+	/** @wq: wait queue for g2h chanenl */
+	wait_queue_head_t wq;
+
 	struct {
 		u16 last_fence; /* last fence used to send request */
 

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

@@ -252,6 +252,72 @@ static inline void set_lrc_desc_registered(struct intel_guc *guc, u32 id,
 	xa_store_irq(&guc->context_lookup, id, ce, GFP_ATOMIC);
 }
 
+static int guc_submission_send_busy_loop(struct intel_guc *guc,
+					 const u32 *action,
+					 u32 len,
+					 u32 g2h_len_dw,
+					 bool loop)
+{
+	int err;
+
+	err = intel_guc_send_busy_loop(guc, action, len, g2h_len_dw, loop);
+
+	if (!err && g2h_len_dw)
+		atomic_inc(&guc->outstanding_submission_g2h);
+
+	return err;
+}
+
+static int guc_wait_for_pending_msg(struct intel_guc *guc,
+				    atomic_t *wait_var,
+				    bool interruptible,
+				    long timeout)
+{
+	const int state = interruptible ?
+		TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
+	DEFINE_WAIT(wait);
+
+	might_sleep();
+	GEM_BUG_ON(timeout < 0);
+
+	if (!atomic_read(wait_var))
+		return 0;
+
+	if (!timeout)
+		return -ETIME;
+
+	for (;;) {
+		prepare_to_wait(&guc->ct.wq, &wait, state);
+
+		if (!atomic_read(wait_var))
+			break;
+
+		if (signal_pending_state(state, current)) {
+			timeout = -EINTR;
+			break;
+		}
+
+		if (!timeout) {
+			timeout = -ETIME;
+			break;
+		}
+
+		timeout = io_schedule_timeout(timeout);
+	}
+	finish_wait(&guc->ct.wq, &wait);
+
+	return (timeout < 0) ? timeout : 0;
+}
+
+int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout)
+{
+	if (!intel_uc_uses_guc_submission(&guc_to_gt(guc)->uc))
+		return 0;
+
+	return guc_wait_for_pending_msg(guc, &guc->outstanding_submission_g2h,
+					true, timeout);
+}
+
 static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
 	int err;
@@ -278,6 +344,7 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 
 	err = intel_guc_send_nb(guc, action, len, g2h_len_dw);
 	if (!enabled && !err) {
+		atomic_inc(&guc->outstanding_submission_g2h);
 		set_context_enabled(ce);
 	} else if (!enabled) {
 		clr_context_pending_enable(ce);
@@ -735,7 +802,8 @@ static int __guc_action_register_context(struct intel_guc *guc,
 		offset,
 	};
 
-	return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true);
+	return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
+					     0, true);
 }
 
 static int register_context(struct intel_context *ce)
@@ -755,8 +823,9 @@ static int __guc_action_deregister_context(struct intel_guc *guc,
 		guc_id,
 	};
 
-	return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action),
-					G2H_LEN_DW_DEREGISTER_CONTEXT, true);
+	return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
+					     G2H_LEN_DW_DEREGISTER_CONTEXT,
+					     true);
 }
 
 static int deregister_context(struct intel_context *ce, u32 guc_id)
@@ -901,8 +970,8 @@ static void __guc_context_sched_disable(struct intel_guc *guc,
 
 	intel_context_get(ce);
 
-	intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action),
-				 G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, true);
+	guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
+				      G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, true);
 }
 
 static u16 prep_context_pending_disable(struct intel_context *ce)
@@ -1444,6 +1513,12 @@ g2h_context_lookup(struct intel_guc *guc, u32 desc_idx)
 	return ce;
 }
 
+static void decr_outstanding_submission_g2h(struct intel_guc *guc)
+{
+	if (atomic_dec_and_test(&guc->outstanding_submission_g2h))
+		wake_up_all(&guc->ct.wq);
+}
+
 int intel_guc_deregister_done_process_msg(struct intel_guc *guc,
 					  const u32 *msg,
 					  u32 len)
@@ -1479,6 +1554,8 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc,
 		lrc_destroy(&ce->ref);
 	}
 
+	decr_outstanding_submission_g2h(guc);
+
 	return 0;
 }
 
@@ -1527,6 +1604,7 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc,
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 	}
 
+	decr_outstanding_submission_g2h(guc);
 	intel_context_put(ce);
 
 	return 0;

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

@@ -81,6 +81,11 @@ uc_state_checkers(guc, guc_submission);
 #undef uc_state_checkers
 #undef __uc_state_checker
 
+static inline int intel_uc_wait_for_idle(struct intel_uc *uc, long timeout)
+{
+	return intel_guc_wait_for_idle(&uc->guc, timeout);
+}
+
 #define intel_uc_ops_function(_NAME, _OPS, _TYPE, _RET) \
 static inline _TYPE intel_uc_##_NAME(struct intel_uc *uc) \
 { \

drivers/gpu/drm/i915/i915_gem_evict.c

@@ -27,6 +27,7 @@
  */
 
 #include "gem/i915_gem_context.h"
+#include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"

drivers/gpu/drm/i915/selftests/igt_live_test.c

@@ -5,7 +5,7 @@
  */
 
 #include "i915_drv.h"
-#include "gt/intel_gt_requests.h"
+#include "gt/intel_gt.h"
 
 #include "../i915_selftest.h"
 #include "igt_flush_test.h"

drivers/gpu/drm/i915/selftests/mock_gem_device.c

@@ -52,7 +52,8 @@ void mock_device_flush(struct drm_i915_private *i915)
 	do {
 		for_each_engine(engine, gt, id)
 			mock_engine_flush(engine);
-	} while (intel_gt_retire_requests_timeout(gt, MAX_SCHEDULE_TIMEOUT));
+	} while (intel_gt_retire_requests_timeout(gt, MAX_SCHEDULE_TIMEOUT,
+						  NULL));
 }
 
 static void mock_device_release(struct drm_device *dev)