[Intel-gfx] [PATCH] drm/i915: Fill unused GGTT with scratch pages for VT-d

[Chris Wilson]

One of the numerous VT-d workarounds we require is that the display
hardware reads past the end of the buffer triggering VT-d faults. This
is acknowledged in the code as being safe "since we fill the unused
portions of the GGTT with the scratch page". Alas, that is no longer
always true and so we trigger DMAR read faults.

Skylake also requires another workaround to avoid mixing VT-d and
unpopulated PTE, and so there we also need to ensure we fill unused
entries with the scratch page.

Reported-by: Mike Lothian <mike at fireburn.co.uk>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=96584
Fixes: f7770bfd9fd2 ("drm/i915: Skip clearing the GGTT on full-ppgtt systems")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: David Weinehall <david.weinehall at intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h      |  9 +++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.c  |  2 +-
 drivers/gpu/drm/i915/intel_display.c | 11 +----------
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 442386abd516..217ca3c9b1c6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2857,6 +2857,15 @@ struct drm_i915_cmd_table {
 
 #include "i915_trace.h"
 
+static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+	if (INTEL_GEN(dev_priv) >= 6 && intel_iommu_gfx_mapped)
+		return true;
+#endif
+	return false;
+}
+
 extern int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state);
 extern int i915_resume_switcheroo(struct drm_device *dev);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index a8be1c2a8b9e..033fe10768e0 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2608,7 +2608,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->base.unbind_vma = ggtt_unbind_vma;
 	ggtt->base.insert_page = gen8_ggtt_insert_page;
 	ggtt->base.clear_range = nop_clear_range;
-	if (!USES_FULL_PPGTT(dev_priv))
+	if (!USES_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv))
 		ggtt->base.clear_range = gen8_ggtt_clear_range;
 
 	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index a8b0ec13dfe9..8145b65c4262 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2071,15 +2071,6 @@ static void intel_disable_pipe(struct intel_crtc *crtc)
 		intel_wait_for_pipe_off(crtc);
 }
 
-static bool need_vtd_wa(struct drm_device *dev)
-{
-#ifdef CONFIG_INTEL_IOMMU
-	if (INTEL_INFO(dev)->gen >= 6 && intel_iommu_gfx_mapped)
-		return true;
-#endif
-	return false;
-}
-
 static unsigned int intel_tile_size(const struct drm_i915_private *dev_priv)
 {
 	return IS_GEN2(dev_priv) ? 2048 : 4096;
@@ -2262,7 +2253,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
 	 * we should always have valid PTE following the scanout preventing
 	 * the VT-d warning.
 	 */
-	if (need_vtd_wa(dev) && alignment < 256 * 1024)
+	if (intel_scanout_needs_vtd_wa(dev_priv) && alignment < 256 * 1024)
 		alignment = 256 * 1024;
 
 	/*
-- 
2.8.1