From 9a5da84da59e67816e154b95f2b5f2f6a07e8973 Mon Sep 17 00:00:00 2001
From: oga <oga@openbsd.org>
Date: Sat, 18 Jul 2009 15:02:51 +0000
Subject: [PATCH] Since we don't accelerate trapesoid rendering under uxa yet
 anyway software rasterise them THEN put them into buffer objects.
 read-modify-write of graphics memory is expensive.

2.5x speed increase under heavy trap rendering measured.

Another upstream backport. ok matthieu@
---
 driver/xf86-video-intel/uxa/uxa-render.c | 53 ++++++++++++++++++++----
 1 file changed, 46 insertions(+), 7 deletions(-)

diff --git a/driver/xf86-video-intel/uxa/uxa-render.c b/driver/xf86-video-intel/uxa/uxa-render.c
index edbf0d8c4..057369d22 100644
--- a/driver/xf86-video-intel/uxa/uxa-render.c
+++ b/driver/xf86-video-intel/uxa/uxa-render.c
@@ -902,23 +902,62 @@ uxa_trapezoids (CARD8 op, PicturePtr pSrc, PicturePtr pDst,
 	PicturePtr	pPicture;
 	INT16		xDst, yDst;
 	INT16		xRel, yRel;
+	int		width, height, stride;
+	PixmapPtr	pPixmap;
+	GCPtr		pGC;
+	pixman_image_t	*image;
 
 	xDst = traps[0].left.p1.x >> 16;
 	yDst = traps[0].left.p1.y >> 16;
 
+	width = bounds.x2 - bounds.x1;
+	height = bounds.y2 - bounds.y1;
+	stride = (width * BitsPerPixel (maskFormat->depth) + 7) / 8;
+
 	pPicture = uxa_create_alpha_picture (pScreen, pDst, maskFormat,
-	                                  bounds.x2 - bounds.x1,
-	                                  bounds.y2 - bounds.y1);
+					     width, height);
 	if (!pPicture)
 	    return;
 
-	if (uxa_prepare_access(pPicture->pDrawable, UXA_ACCESS_RW)) {
-	    for (; ntrap; ntrap--, traps++)
-		(*ps->RasterizeTrapezoid) (pPicture, traps,
-					   -bounds.x1, -bounds.y1);
-	    uxa_finish_access(pPicture->pDrawable);
+	image = pixman_image_create_bits (pPicture->format,
+					  width, height,
+					  NULL, stride);
+	if (!image) {
+	    FreePicture (pPicture, 0);
+	    return;
 	}
 
+	for (; ntrap; ntrap--, traps++)
+	    pixman_rasterize_trapezoid (image, (pixman_trapezoid_t *) traps,
+					-bounds.x1, -bounds.y1);
+
+	pPixmap = GetScratchPixmapHeader(pScreen, width, height,
+					 maskFormat->depth,
+					 BitsPerPixel (maskFormat->depth),
+					 PixmapBytePad (width, maskFormat->depth),
+					 pixman_image_get_data (image));
+	if (!pPixmap) {
+	    FreePicture (pPicture, 0);
+	    pixman_image_unref (image);
+	    return;
+	}
+
+	pGC = GetScratchGC (pPicture->pDrawable->depth, pScreen);
+	if (!pGC)
+	{
+	    FreeScratchPixmapHeader (pPixmap);
+	    pixman_image_unref (image);
+	    FreePicture (pPicture, 0);
+	    return;
+	}
+
+	(*pGC->ops->CopyArea) (&pPixmap->drawable, pPicture->pDrawable,
+			       pGC, 0, 0, width, height, 0, 0);
+
+	FreeScratchGC (pGC);
+	FreeScratchPixmapHeader (pPixmap);
+	pixman_image_unref (image);
+
 	xRel = bounds.x1 + xSrc - xDst;
 	yRel = bounds.y1 + ySrc - yDst;
 	CompositePicture (op, pSrc, pPicture, pDst,