From accdbd23676d812d2345f86d8e3ee62f108841ff Mon Sep 17 00:00:00 2001
From: Carl Worth <cworth@cworth.org>
Date: Fri, 29 May 2009 15:34:20 -0700
Subject: [PATCH] UXA: Rasterize trapezoids to system memory, not a pixmap

Since we're only doing software rasterization right now, anyway, it
makes more sense to just rasterize to system memory and then upload
to a pixmap once complete. This avoids expensive read-modify-write
cycles.

This results in a 2.4x speedup for a real-world test case that's
heavy on trapezoids, which is swfdec running on the following file:

http://michalevy.com/wp-content/uploads/Giant%20Steps%202007.swf

Many thanks to Chris Wilson for his cairo-traces repository and
cairo-perf-trace tool which makes it so easy to measure things
like this.
---
 uxa/uxa-render.c | 53 +++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 46 insertions(+), 7 deletions(-)

diff --git a/uxa/uxa-render.c b/uxa/uxa-render.c
index b377bf53..2d81ac44 100644
--- a/uxa/uxa-render.c
+++ b/uxa/uxa-render.c
@@ -897,23 +897,62 @@ 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,