diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 963f6d4481f76ec54b5aeab138b0cca3f4ff90e5..2c453a4e97d5ba28ca3a21da372f73eed0131268 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2991,6 +2991,16 @@ static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv)
 	return false;
 }
 
+static inline bool
+intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+	if (IS_BROXTON(dev_priv) && intel_iommu_gfx_mapped)
+		return true;
+#endif
+	return false;
+}
+
 int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 				int enable_ppgtt);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 50b8f1139ff99d6dc8d3ec225abf251d6af4465d..db89843bdd46cbddfc53477542fab47f8b578260 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2191,6 +2191,101 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 		gen8_set_pte(&gtt_base[i], scratch_pte);
 }
 
+static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
+{
+	struct drm_i915_private *dev_priv = vm->i915;
+
+	/*
+	 * Make sure the internal GAM fifo has been cleared of all GTT
+	 * writes before exiting stop_machine(). This guarantees that
+	 * any aperture accesses waiting to start in another process
+	 * cannot back up behind the GTT writes causing a hang.
+	 * The register can be any arbitrary GAM register.
+	 */
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+}
+
+struct insert_page {
+	struct i915_address_space *vm;
+	dma_addr_t addr;
+	u64 offset;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
+{
+	struct insert_page *arg = _arg;
+
+	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
+					  dma_addr_t addr,
+					  u64 offset,
+					  enum i915_cache_level level,
+					  u32 unused)
+{
+	struct insert_page arg = { vm, addr, offset, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
+}
+
+struct insert_entries {
+	struct i915_address_space *vm;
+	struct sg_table *st;
+	u64 start;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
+{
+	struct insert_entries *arg = _arg;
+
+	gen8_ggtt_insert_entries(arg->vm, arg->st, arg->start, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+					     struct sg_table *st,
+					     u64 start,
+					     enum i915_cache_level level,
+					     u32 unused)
+{
+	struct insert_entries arg = { vm, st, start, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
+}
+
+struct clear_range {
+	struct i915_address_space *vm;
+	u64 start;
+	u64 length;
+};
+
+static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
+{
+	struct clear_range *arg = _arg;
+
+	gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
+					  u64 start,
+					  u64 length)
+{
+	struct clear_range arg = { vm, start, length };
+
+	stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
+}
+
 static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 				  u64 start, u64 length)
 {
@@ -2785,6 +2880,14 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
 
+	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
+	if (intel_ggtt_update_needs_vtd_wa(dev_priv)) {
+		ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+		ggtt->base.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
+		if (ggtt->base.clear_range != nop_clear_range)
+			ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+	}
+
 	ggtt->invalidate = gen6_ggtt_invalidate;
 
 	return ggtt_probe_common(ggtt, size);