diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 0b25228..a2e3af0 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2100,7 +2100,6 @@
 	for_each_engine(engine, dev_priv) {
 		struct drm_i915_gem_request *head_req = NULL;
 		int count = 0;
-		unsigned long flags;
 
 		seq_printf(m, "%s\n", engine->name);
 
@@ -2127,13 +2126,13 @@
 				   i, status, ctx_id);
 		}
 
-		spin_lock_irqsave(&engine->execlist_lock, flags);
+		spin_lock_bh(&engine->execlist_lock);
 		list_for_each(cursor, &engine->execlist_queue)
 			count++;
 		head_req = list_first_entry_or_null(&engine->execlist_queue,
 						    struct drm_i915_gem_request,
 						    execlist_link);
-		spin_unlock_irqrestore(&engine->execlist_lock, flags);
+		spin_unlock_bh(&engine->execlist_lock);
 
 		seq_printf(m, "\t%d requests in queue\n", count);
 		if (head_req) {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ca96fc1..40f90c7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2842,13 +2842,15 @@
 	 */
 
 	if (i915.enable_execlists) {
-		spin_lock_irq(&engine->execlist_lock);
+		/* Ensure irq handler finishes or is cancelled. */
+		tasklet_kill(&engine->irq_tasklet);
 
+		spin_lock_bh(&engine->execlist_lock);
 		/* list_splice_tail_init checks for empty lists */
 		list_splice_tail_init(&engine->execlist_queue,
 				      &engine->execlist_retired_req_list);
+		spin_unlock_bh(&engine->execlist_lock);
 
-		spin_unlock_irq(&engine->execlist_lock);
 		intel_execlists_retire_requests(engine);
 	}
 
@@ -2968,9 +2970,9 @@
 		i915_gem_retire_requests_ring(engine);
 		idle &= list_empty(&engine->request_list);
 		if (i915.enable_execlists) {
-			spin_lock_irq(&engine->execlist_lock);
+			spin_lock_bh(&engine->execlist_lock);
 			idle &= list_empty(&engine->execlist_queue);
-			spin_unlock_irq(&engine->execlist_lock);
+			spin_unlock_bh(&engine->execlist_lock);
 
 			intel_execlists_retire_requests(engine);
 		}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index a9c1813..c85eb8d 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1323,7 +1323,7 @@
 	if (iir & (GT_RENDER_USER_INTERRUPT << test_shift))
 		notify_ring(engine);
 	if (iir & (GT_CONTEXT_SWITCH_INTERRUPT << test_shift))
-		intel_lrc_irq_handler(engine);
+		tasklet_schedule(&engine->irq_tasklet);
 }
 
 static irqreturn_t gen8_gt_irq_handler(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 5d4ca3b..a1db6a0 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -131,6 +131,7 @@
  * preemption, but just sampling the new tail pointer).
  *
  */
+#include <linux/interrupt.h>
 
 #include <drm/drmP.h>
 #include <drm/i915_drm.h>
@@ -418,20 +419,18 @@
 {
 	struct drm_i915_private *dev_priv = rq0->i915;
 
-	/* BUG_ON(!irqs_disabled());  */
-
 	execlists_update_context(rq0);
 
 	if (rq1)
 		execlists_update_context(rq1);
 
-	spin_lock(&dev_priv->uncore.lock);
+	spin_lock_irq(&dev_priv->uncore.lock);
 	intel_uncore_forcewake_get__locked(dev_priv, FORCEWAKE_ALL);
 
 	execlists_elsp_write(rq0, rq1);
 
 	intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
-	spin_unlock(&dev_priv->uncore.lock);
+	spin_unlock_irq(&dev_priv->uncore.lock);
 }
 
 static void execlists_context_unqueue(struct intel_engine_cs *engine)
@@ -538,13 +537,14 @@
 
 /**
  * intel_lrc_irq_handler() - handle Context Switch interrupts
- * @ring: Engine Command Streamer to handle.
+ * @engine: Engine Command Streamer to handle.
  *
  * Check the unread Context Status Buffers and manage the submission of new
  * contexts to the ELSP accordingly.
  */
-void intel_lrc_irq_handler(struct intel_engine_cs *engine)
+static void intel_lrc_irq_handler(unsigned long data)
 {
+	struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
 	struct drm_i915_private *dev_priv = engine->dev->dev_private;
 	u32 status_pointer;
 	unsigned int read_pointer, write_pointer;
@@ -552,8 +552,7 @@
 	unsigned int csb_read = 0, i;
 	unsigned int submit_contexts = 0;
 
-	spin_lock(&dev_priv->uncore.lock);
-	intel_uncore_forcewake_get__locked(dev_priv, FORCEWAKE_ALL);
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
 	status_pointer = I915_READ_FW(RING_CONTEXT_STATUS_PTR(engine));
 
@@ -578,8 +577,7 @@
 		      _MASKED_FIELD(GEN8_CSB_READ_PTR_MASK,
 				    engine->next_context_status_buffer << 8));
 
-	intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
-	spin_unlock(&dev_priv->uncore.lock);
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
 	spin_lock(&engine->execlist_lock);
 
@@ -621,7 +619,7 @@
 
 	i915_gem_request_reference(request);
 
-	spin_lock_irq(&engine->execlist_lock);
+	spin_lock_bh(&engine->execlist_lock);
 
 	list_for_each_entry(cursor, &engine->execlist_queue, execlist_link)
 		if (++num_elements > 2)
@@ -646,7 +644,7 @@
 	if (num_elements == 0)
 		execlists_context_unqueue(engine);
 
-	spin_unlock_irq(&engine->execlist_lock);
+	spin_unlock_bh(&engine->execlist_lock);
 }
 
 static int logical_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
@@ -1033,9 +1031,9 @@
 		return;
 
 	INIT_LIST_HEAD(&retired_list);
-	spin_lock_irq(&engine->execlist_lock);
+	spin_lock_bh(&engine->execlist_lock);
 	list_replace_init(&engine->execlist_retired_req_list, &retired_list);
-	spin_unlock_irq(&engine->execlist_lock);
+	spin_unlock_bh(&engine->execlist_lock);
 
 	list_for_each_entry_safe(req, tmp, &retired_list, execlist_link) {
 		struct intel_context *ctx = req->ctx;
@@ -2016,6 +2014,13 @@
 	if (!intel_engine_initialized(engine))
 		return;
 
+	/*
+	 * Tasklet cannot be active at this point due intel_mark_active/idle
+	 * so this is just for documentation.
+	 */
+	if (WARN_ON(test_bit(TASKLET_STATE_SCHED, &engine->irq_tasklet.state)))
+		tasklet_kill(&engine->irq_tasklet);
+
 	dev_priv = engine->dev->dev_private;
 
 	if (engine->buffer) {
@@ -2089,6 +2094,9 @@
 	INIT_LIST_HEAD(&engine->execlist_retired_req_list);
 	spin_lock_init(&engine->execlist_lock);
 
+	tasklet_init(&engine->irq_tasklet,
+		     intel_lrc_irq_handler, (unsigned long)engine);
+
 	logical_ring_init_platform_invariants(engine);
 
 	ret = i915_cmd_parser_init_ring(engine);
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index a17cb12..0b0853e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -118,7 +118,6 @@
 			       struct drm_i915_gem_execbuffer2 *args,
 			       struct list_head *vmas);
 
-void intel_lrc_irq_handler(struct intel_engine_cs *engine);
 void intel_execlists_retire_requests(struct intel_engine_cs *engine);
 
 #endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 221a9462..18074ab 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -266,7 +266,8 @@
 	} semaphore;
 
 	/* Execlists */
-	spinlock_t execlist_lock;
+	struct tasklet_struct irq_tasklet;
+	spinlock_t execlist_lock; /* used inside tasklet, use spin_lock_bh */
 	struct list_head execlist_queue;
 	struct list_head execlist_retired_req_list;
 	unsigned int next_context_status_buffer;