diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index ada095023dad..80bed69fe5b7 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -145,6 +145,13 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (%s)", obj->ring->name);
 }
 
+static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx)
+{
+	seq_putc(m, ctx->is_initialized ? 'I' : 'i');
+	seq_putc(m, ctx->remap_slice ? 'R' : 'r');
+	seq_putc(m, ' ');
+}
+
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -1463,6 +1470,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		seq_puts(m, "HW context ");
+		describe_ctx(m, ctx);
 		for_each_ring(ring, dev_priv, i)
 			if (ring->default_context == ctx)
 				seq_printf(m, "(default context %s) ", ring->name);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 179592762537..015df5264dcc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -601,6 +601,7 @@ struct i915_hw_context {
 	struct kref ref;
 	int id;
 	bool is_initialized;
+	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
 	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_object *obj;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 2bbdce821ac3..9af3fe7e42b0 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -181,6 +181,10 @@ create_hw_context(struct drm_device *dev,
 
 	ctx->file_priv = file_priv;
 	ctx->id = ret;
+	/* NB: Mark all slices as needing a remap so that when the context first
+	 * loads it will restore whatever remap state already exists. If there
+	 * is no remap info, it will be a NOP. */
+	ctx->remap_slice = (1 << NUM_L3_SLICES(dev)) - 1;
 
 	return ctx;
 
@@ -396,11 +400,11 @@ static int do_switch(struct i915_hw_context *to)
 	struct intel_ring_buffer *ring = to->ring;
 	struct i915_hw_context *from = ring->last_context;
 	u32 hw_flags = 0;
-	int ret;
+	int ret, i;
 
 	BUG_ON(from != NULL && from->obj != NULL && from->obj->pin_count == 0);
 
-	if (from == to)
+	if (from == to && !to->remap_slice)
 		return 0;
 
 	ret = i915_gem_obj_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false);
@@ -423,8 +427,6 @@ static int do_switch(struct i915_hw_context *to)
 
 	if (!to->is_initialized || is_default_context(to))
 		hw_flags |= MI_RESTORE_INHIBIT;
-	else if (WARN_ON_ONCE(from == to)) /* not yet expected */
-		hw_flags |= MI_FORCE_RESTORE;
 
 	ret = mi_set_context(ring, to, hw_flags);
 	if (ret) {
@@ -432,6 +434,18 @@ static int do_switch(struct i915_hw_context *to)
 		return ret;
 	}
 
+	for (i = 0; i < MAX_L3_SLICES; i++) {
+		if (!(to->remap_slice & (1<<i)))
+			continue;
+
+		ret = i915_gem_l3_remap(ring, i);
+		/* If it failed, try again next round */
+		if (ret)
+			DRM_DEBUG_DRIVER("L3 remapping failed\n");
+		else
+			to->remap_slice &= ~(1<<i);
+	}
+
 	/* The backing object for the context is done after switching to the
 	 * *next* context. Therefore we cannot retire the previous context until
 	 * the next context has already started running. In fact, the below code
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index b07bdfb8892d..deb8787308d6 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -118,9 +118,8 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
-	uint32_t misccpctl;
 	int slice = (int)(uintptr_t)attr->private;
-	int i, ret;
+	int ret;
 
 	count = round_down(count, 4);
 
@@ -134,26 +133,13 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info[slice])
-			memcpy(buf,
-			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
-			       count);
-		else
-			memset(buf, 0, count);
+	if (dev_priv->l3_parity.remap_info[slice])
+		memcpy(buf,
+		       dev_priv->l3_parity.remap_info[slice] + (offset/4),
+		       count);
+	else
+		memset(buf, 0, count);
 
-		goto out;
-	}
-
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-
-	for (i = 0; i < count; i += 4)
-		*((uint32_t *)(&buf[i])) = I915_READ(GEN7_L3LOG_BASE + offset + i);
-
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
-
-out:
 	mutex_unlock(&drm_dev->struct_mutex);
 
 	return count;
@@ -168,6 +154,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	struct i915_hw_context *ctx;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
@@ -176,6 +163,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
+	if (dev_priv->hw_contexts_disabled)
+		return -ENXIO;
+
 	ret = i915_mutex_lock_interruptible(drm_dev);
 	if (ret)
 		return ret;
@@ -204,8 +194,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 
 	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	if (i915_gem_l3_remap(&dev_priv->ring[RCS], slice))
-		count = 0;
+	/* NB: We defer the remapping until we switch to the context */
+	list_for_each_entry(ctx, &dev_priv->context_list, link)
+		ctx->remap_slice |= (1<<slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);