3 files changed, 51 insertions, 9 deletions

diff --git a/drivers/gpu/drm/mgag200/Kconfig b/drivers/gpu/drm/mgag200/Kconfig
index b28c5e4828..5e4d48df48 100644
--- a/drivers/gpu/drm/mgag200/Kconfig
+++ b/drivers/gpu/drm/mgag200/Kconfig
@@ -11,3 +11,15 @@ config DRM_MGAG200
 	 MGA G200 desktop chips and the server variants. It requires 0.3.0
 	 of the modesetting userspace driver, and a version of mga driver
 	 that will fail on KMS enabled devices.
+
+config DRM_MGAG200_IOBURST_WORKAROUND
+	bool "Disable buffer caching"
+	depends on DRM_MGAG200 && PREEMPT_RT && X86
+	help
+	  Enable a workaround to avoid I/O bursts within the mgag200 driver at
+	  the expense of overall display performance.
+	  It restores the <v5.10 behavior, by mapping the framebuffer in system
+	  RAM as Write-Combining, and flushing the cache after each write.
+	  This is only useful on x86_64 if you want to run processes with
+	  deterministic latency.
+	  If unsure, say N.
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index 2fb18b782b..573dbe256a 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -84,6 +84,20 @@ resource_size_t mgag200_probe_vram(void __iomem *mem, resource_size_t size)
 	return offset - 65536;
 }
 
+#if defined(CONFIG_DRM_MGAG200_IOBURST_WORKAROUND)
+static struct drm_gem_object *mgag200_create_object(struct drm_device *dev, size_t size)
+{
+	struct drm_gem_shmem_object *shmem;
+
+	shmem = kzalloc(sizeof(*shmem), GFP_KERNEL);
+	if (!shmem)
+		return NULL;
+
+	shmem->map_wc = true;
+	return &shmem->base;
+}
+#endif
+
 /*
  * DRM driver
  */
@@ -99,6 +113,9 @@ static const struct drm_driver mgag200_driver = {
 	.major = DRIVER_MAJOR,
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
+#if defined(CONFIG_DRM_MGAG200_IOBURST_WORKAROUND)
+	.gem_create_object = mgag200_create_object,
+#endif
 	DRM_GEM_SHMEM_DRIVER_OPS,
 };
 
@@ -146,14 +163,13 @@ int mgag200_device_preinit(struct mga_device *mdev)
 	}
 	mdev->vram_res = res;
 
-	/* Don't fail on errors, but performance might be reduced. */
-	devm_arch_io_reserve_memtype_wc(dev->dev, res->start, resource_size(res));
-	devm_arch_phys_wc_add(dev->dev, res->start, resource_size(res));
-
-	mdev->vram = devm_ioremap(dev->dev, res->start, resource_size(res));
+	mdev->vram = devm_ioremap_wc(dev->dev, res->start, resource_size(res));
 	if (!mdev->vram)
 		return -ENOMEM;
 
+	/* Don't fail on errors, but performance might be reduced. */
+	devm_arch_phys_wc_add(dev->dev, res->start, resource_size(res));
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 0f0d59938c..e17cb4c5f7 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -13,14 +13,15 @@
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_cache.h>
 #include <drm/drm_damage_helper.h>
+#include <drm/drm_edid.h>
 #include <drm/drm_format_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_print.h>
-#include <drm/drm_probe_helper.h>
 
 #include "mgag200_drv.h"
 
@@ -436,6 +437,13 @@ static void mgag200_handle_damage(struct mga_device *mdev, const struct iosys_ma
 
 	iosys_map_incr(&dst, drm_fb_clip_offset(fb->pitches[0], fb->format, clip));
 	drm_fb_memcpy(&dst, fb->pitches, vmap, fb, clip);
+
+	/* Flushing the cache greatly improves latency on x86_64 */
+#if defined(CONFIG_DRM_MGAG200_IOBURST_WORKAROUND)
+	if (!vmap->is_iomem)
+		drm_clflush_virt_range(vmap->vaddr + clip->y1 * fb->pitches[0],
+				       drm_rect_height(clip) * fb->pitches[0]);
+#endif
 }
 
 /*
@@ -717,17 +725,23 @@ void mgag200_crtc_atomic_destroy_state(struct drm_crtc *crtc, struct drm_crtc_st
 int mgag200_vga_connector_helper_get_modes(struct drm_connector *connector)
 {
 	struct mga_device *mdev = to_mga_device(connector->dev);
-	int ret;
+	const struct drm_edid *drm_edid;
+	int count;
 
 	/*
 	 * Protect access to I/O registers from concurrent modesetting
 	 * by acquiring the I/O-register lock.
 	 */
 	mutex_lock(&mdev->rmmio_lock);
-	ret = drm_connector_helper_get_modes_from_ddc(connector);
+
+	drm_edid = drm_edid_read(connector);
+	drm_edid_connector_update(connector, drm_edid);
+	count = drm_edid_connector_add_modes(connector);
+	drm_edid_free(drm_edid);
+
 	mutex_unlock(&mdev->rmmio_lock);
 
-	return ret;
+	return count;
 }
 
 /*