[CI 09/14] drm/xe: Flush GGTT writes after populating DPT

[Tvrtko Ursulin <tvrtko.ursulin@igalia.com>]

When DPT is placed in stolen it is populated using ioremap_wc() via GGTT.

I915 has established that on modern platforms a small flush and delay is
required for those writes to reliably land so lets add the same logic
(simplified by removing impossible platforms) to xe as well.

v2:
 * Do it only for system memory buffers.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/xe/display/xe_fb_pin.c | 45 ++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index b18d15cc3c53..eb21eeae9d17 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -12,9 +12,11 @@
 #include "intel_fb.h"
 #include "intel_fb_pin.h"
 #include "intel_fbdev.h"
+#include "regs/xe_engine_regs.h"
 #include "xe_bo.h"
 #include "xe_device.h"
 #include "xe_ggtt.h"
+#include "xe_mmio.h"
 #include "xe_pm.h"
 #include "xe_vram_types.h"
 
@@ -79,6 +81,46 @@ write_dpt_remapped(struct xe_bo *bo, struct iosys_map *map, u32 *dpt_ofs,
 	*dpt_ofs = ALIGN(*dpt_ofs, 4096);
 }
 
+static void gt_flush_ggtt_writes(struct xe_gt *gt)
+{
+	if (!gt)
+		return;
+
+	xe_mmio_read32(&gt->mmio, RING_TAIL(RENDER_RING_BASE));
+}
+
+static void ggtt_flush_writes(struct xe_ggtt *ggtt)
+{
+	struct xe_device *xe = tile_to_xe(ggtt->tile);
+
+	/*
+	 * No actual flushing is required for the GTT write domain for reads
+	 * from the GTT domain. Writes to it "immediately" go to main memory
+	 * as far as we know, so there's no chipset flush. It also doesn't
+	 * land in the GPU render cache.
+	 *
+	 * However, we do have to enforce the order so that all writes through
+	 * the GTT land before any writes to the device, such as updates to
+	 * the GATT itself.
+	 *
+	 * We also have to wait a bit for the writes to land from the GTT.
+	 * An uncached read (i.e. mmio) seems to be ideal for the round-trip
+	 * timing. This issue has only been observed when switching quickly
+	 * between GTT writes and CPU reads from inside the kernel on recent hw,
+	 * and it appears to only affect discrete GTT blocks (i.e. on LLC
+	 * system agents we cannot reproduce this behaviour, until Cannonlake
+	 * that was!).
+	 */
+
+	wmb();
+
+	if (xe_pm_runtime_get_if_active(xe)) {
+		gt_flush_ggtt_writes(ggtt->tile->primary_gt);
+		gt_flush_ggtt_writes(ggtt->tile->media_gt);
+		xe_pm_runtime_put(xe);
+	}
+}
+
 static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb,
 			       const struct i915_gtt_view *view,
 			       struct i915_vma *vma,
@@ -162,6 +204,9 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb,
 					  rot_info->plane[i].dst_stride);
 	}
 
+	if (dpt->vmap.is_iomem && !xe_bo_is_vram(dpt))
+		ggtt_flush_writes(tile0->mem.ggtt);
+
 	vma->dpt = dpt;
 	vma->node = dpt->ggtt_node[tile0->id];
 
-- 
2.48.0