diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 0541d7b5c841..bc8756d06b3e 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -832,10 +832,14 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm,
 	return &plane->base;
 }
 
-static const u32 tegra_cursor_plane_formats[] = {
+static const u32 tegra_legacy_cursor_plane_formats[] = {
 	DRM_FORMAT_RGBA8888,
 };
 
+static const u32 tegra_cursor_plane_formats[] = {
+	DRM_FORMAT_ARGB8888,
+};
+
 static int tegra_cursor_atomic_check(struct drm_plane *plane,
 				     struct drm_atomic_state *state)
 {
@@ -875,12 +879,24 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane,
 									   plane);
 	struct tegra_plane_state *tegra_plane_state = to_tegra_plane_state(new_state);
 	struct tegra_dc *dc = to_tegra_dc(new_state->crtc);
-	u32 value = CURSOR_CLIP_DISPLAY;
+	struct tegra_drm *tegra = plane->dev->dev_private;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	u64 dma_mask = *dc->dev->dma_mask;
+#endif
+	unsigned int x, y;
+	u32 value = 0;
 
 	/* rien ne va plus */
 	if (!new_state->crtc || !new_state->fb)
 		return;
 
+	/*
+	 * Legacy display supports hardware clipping of the cursor, but
+	 * nvdisplay relies on software to clip the cursor to the screen.
+	 */
+	if (!dc->soc->has_nvdisplay)
+		value |= CURSOR_CLIP_DISPLAY;
+
 	switch (new_state->crtc_w) {
 	case 32:
 		value |= CURSOR_SIZE_32x32;
@@ -908,7 +924,7 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane,
 	tegra_dc_writel(dc, value, DC_DISP_CURSOR_START_ADDR);
 
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	value = (tegra_plane_state->iova[0] >> 32) & 0x3;
+	value = (tegra_plane_state->iova[0] >> 32) & (dma_mask >> 32);
 	tegra_dc_writel(dc, value, DC_DISP_CURSOR_START_ADDR_HI);
 #endif
 
@@ -920,15 +936,39 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane,
 	value = tegra_dc_readl(dc, DC_DISP_BLEND_CURSOR_CONTROL);
 	value &= ~CURSOR_DST_BLEND_MASK;
 	value &= ~CURSOR_SRC_BLEND_MASK;
-	value |= CURSOR_MODE_NORMAL;
+
+	if (dc->soc->has_nvdisplay)
+		value &= ~CURSOR_COMPOSITION_MODE_XOR;
+	else
+		value |= CURSOR_MODE_NORMAL;
+
 	value |= CURSOR_DST_BLEND_NEG_K1_TIMES_SRC;
 	value |= CURSOR_SRC_BLEND_K1_TIMES_SRC;
 	value |= CURSOR_ALPHA;
 	tegra_dc_writel(dc, value, DC_DISP_BLEND_CURSOR_CONTROL);
 
+	/* nvdisplay relies on software for clipping */
+	if (dc->soc->has_nvdisplay) {
+		struct drm_rect src;
+
+		x = new_state->dst.x1;
+		y = new_state->dst.y1;
+
+		drm_rect_fp_to_int(&src, &new_state->src);
+
+		value = (src.y1 & tegra->vmask) << 16 | (src.x1 & tegra->hmask);
+		tegra_dc_writel(dc, value, DC_DISP_PCALC_HEAD_SET_CROPPED_POINT_IN_CURSOR);
+
+		value = (drm_rect_height(&src) & tegra->vmask) << 16 |
+			(drm_rect_width(&src) & tegra->hmask);
+		tegra_dc_writel(dc, value, DC_DISP_PCALC_HEAD_SET_CROPPED_SIZE_IN_CURSOR);
+	} else {
+		x = new_state->crtc_x;
+		y = new_state->crtc_y;
+	}
+
 	/* position the cursor */
-	value = (new_state->crtc_y & 0x3fff) << 16 |
-		(new_state->crtc_x & 0x3fff);
+	value = ((y & tegra->vmask) << 16) | (x & tegra->hmask);
 	tegra_dc_writel(dc, value, DC_DISP_CURSOR_POSITION);
 }
 
@@ -982,8 +1022,13 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm,
 	plane->index = 6;
 	plane->dc = dc;
 
-	num_formats = ARRAY_SIZE(tegra_cursor_plane_formats);
-	formats = tegra_cursor_plane_formats;
+	if (!dc->soc->has_nvdisplay) {
+		num_formats = ARRAY_SIZE(tegra_legacy_cursor_plane_formats);
+		formats = tegra_legacy_cursor_plane_formats;
+	} else {
+		num_formats = ARRAY_SIZE(tegra_cursor_plane_formats);
+		formats = tegra_cursor_plane_formats;
+	}
 
 	err = drm_universal_plane_init(drm, &plane->base, possible_crtcs,
 				       &tegra_plane_funcs, formats,
diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h
index 051d03dcb9b0..21074cd2ce5e 100644
--- a/drivers/gpu/drm/tegra/dc.h
+++ b/drivers/gpu/drm/tegra/dc.h
@@ -511,6 +511,8 @@ int tegra_dc_rgb_exit(struct tegra_dc *dc);
 
 #define DC_DISP_CURSOR_START_ADDR_HI		0x4ec
 #define DC_DISP_BLEND_CURSOR_CONTROL		0x4f1
+#define CURSOR_COMPOSITION_MODE_BLEND		(0 << 25)
+#define CURSOR_COMPOSITION_MODE_XOR		(1 << 25)
 #define CURSOR_MODE_LEGACY			(0 << 24)
 #define CURSOR_MODE_NORMAL			(1 << 24)
 #define CURSOR_DST_BLEND_ZERO			(0 << 16)
@@ -705,6 +707,9 @@ int tegra_dc_rgb_exit(struct tegra_dc *dc);
 #define PROTOCOL_MASK (0xf << 8)
 #define PROTOCOL_SINGLE_TMDS_A (0x1 << 8)
 
+#define DC_DISP_PCALC_HEAD_SET_CROPPED_POINT_IN_CURSOR	0x442
+#define DC_DISP_PCALC_HEAD_SET_CROPPED_SIZE_IN_CURSOR	0x446
+
 #define DC_WIN_CORE_WINDOWGROUP_SET_CONTROL	0x702
 #define OWNER_MASK (0xf << 0)
 #define OWNER(x) (((x) & 0xf) << 0)