Use new pixman_glyph_cache_t API that will be in pixman 0.28.0glyph2

This new API allows glyphs to be cached in a data structure in pixman,
and entire glyph strings to be composited in one go.

Also bump pixman dependency to 0.27.2.

Results from the cairo peformance test suite running against Xvfb with
a screen size of 1680x1050@32bpp:

Speedups
========
 xlib          firefox-talos-gfx  12416.63 -> 3603.93   3.45x speedup
██▌
 xlib          xfce4-terminal-a1   1727.57 -> 1048.85:  1.65x speedup
▋
 xlib                  evolution   1370.49 -> 869.34:   1.58x speedup
▋
 xlib         gnome-terminal-vim   1832.83 -> 1251.94:  1.46x speedup
▌
 xlib                    poppler   1519.70 -> 1204.05:  1.26x speedup
▎
 xlib       firefox-planet-gnome   6982.55 -> 5598.16:  1.25x speedup
▎
 xlib                  ocitysmap   1142.77 -> 1071.53:  1.07x speedup
▏

No slowdowns were reported.

Results of x11perf -aa10text:

Before:

      8000000 reps @   0.0007 msec (1450000.0/sec)
      8000000 reps @   0.0007 msec (1460000.0/sec)
      8000000 reps @   0.0007 msec (1460000.0/sec)
      8000000 reps @   0.0007 msec (1470000.0/sec)
      8000000 reps @   0.0007 msec (1480000.0/sec)
     40000000 trep @   0.0007 msec (1460000.0/sec)

After:

     32000000 reps @   0.0002 msec (4910000.0/sec)
     32000000 reps @   0.0002 msec (4830000.0/sec)
     32000000 reps @   0.0002 msec (4890000.0/sec)
     32000000 reps @   0.0002 msec (4830000.0/sec)
     32000000 reps @   0.0002 msec (4900000.0/sec)
    160000000 trep @   0.0002 msec (4870000.0/sec)

Acked-by: Aaron Plattner <aplattner@nvidia.com>
Signed-off-by: Soren Sandmann <ssp@redhat.com>

2 files changed, 143 insertions, 2 deletions

diff --git a/configure.ac b/configure.ac
index ac3bf26f1..ca1b43862 100644
--- a/configure.ac
+++ b/configure.ac
@@ -812,7 +812,7 @@ LIBPCIACCESS="pciaccess >= 0.12.901"
 LIBUDEV="libudev >= 143"
 LIBSELINUX="libselinux >= 2.0.86"
 LIBDBUS="dbus-1 >= 1.0"
-LIBPIXMAN="pixman-1 >= 0.21.8"
+LIBPIXMAN="pixman-1 >= 0.27.2"
 
 dnl Pixman is always required, but we separate it out so we can link
 dnl specific modules against it
diff --git a/fb/fbpict.c b/fb/fbpict.c
index 097a1a6bd..a70fa1888 100644
--- a/fb/fbpict.c
+++ b/fb/fbpict.c
@@ -70,6 +70,146 @@ fbComposite(CARD8 op,
     free_pixman_pict(pDst, dest);
 }
 
+static pixman_glyph_cache_t *glyphCache;
+
+static void
+fbUnrealizeGlyph(ScreenPtr pScreen,
+		 GlyphPtr pGlyph)
+{
+    if (glyphCache)
+	pixman_glyph_cache_remove (glyphCache, pGlyph, NULL);
+}
+
+static void
+fbGlyphs(CARD8 op,
+	 PicturePtr pSrc,
+	 PicturePtr pDst,
+	 PictFormatPtr maskFormat,
+	 INT16 xSrc,
+	 INT16 ySrc, int nlist,
+	 GlyphListPtr list,
+	 GlyphPtr *glyphs)
+{
+#define N_STACK_GLYPHS 512
+    ScreenPtr pScreen = pDst->pDrawable->pScreen;
+    pixman_glyph_t stack_glyphs[N_STACK_GLYPHS];
+    pixman_glyph_t *pglyphs = stack_glyphs;
+    pixman_image_t *srcImage, *dstImage;
+    int srcXoff, srcYoff, dstXoff, dstYoff;
+    GlyphPtr glyph;
+    int n_glyphs;
+    int x, y;
+    int i, n;
+    int xDst = list->xOff, yDst = list->yOff;
+
+    miCompositeSourceValidate(pSrc);
+    
+    n_glyphs = 0;
+    for (i = 0; i < nlist; ++i)
+	n_glyphs += list[i].len;
+
+    if (!glyphCache)
+	glyphCache = pixman_glyph_cache_create();
+
+    pixman_glyph_cache_freeze (glyphCache);
+    
+    if (n_glyphs > N_STACK_GLYPHS) {
+	if (!(pglyphs = malloc (n_glyphs * sizeof (pixman_glyph_t))))
+	    goto out;
+    }
+    
+    i = 0;
+    x = y = 0;
+    while (nlist--) {
+        x += list->xOff;
+        y += list->yOff;
+        n = list->len;
+        while (n--) {
+	    const void *g;
+
+            glyph = *glyphs++;
+
+	    if (!(g = pixman_glyph_cache_lookup (glyphCache, glyph, NULL))) {
+		pixman_image_t *glyphImage;
+		PicturePtr pPicture;
+		int xoff, yoff;
+
+		pPicture = GetGlyphPicture(glyph, pScreen);
+		if (!pPicture) {
+		    n_glyphs--;
+		    goto next;
+		}
+
+		if (!(glyphImage = image_from_pict(pPicture, FALSE, &xoff, &yoff)))
+		    goto out;
+
+		g = pixman_glyph_cache_insert(glyphCache, glyph, NULL,
+					      glyph->info.x,
+					      glyph->info.y,
+					      glyphImage);
+
+		free_pixman_pict(pPicture, glyphImage);
+
+		if (!g)
+		    goto out;
+	    }
+
+	    pglyphs[i].x = x;
+	    pglyphs[i].y = y;
+	    pglyphs[i].glyph = g;
+	    i++;
+
+	next:
+            x += glyph->info.xOff;
+            y += glyph->info.yOff;
+	}
+	list++;
+    }
+
+    if (!(srcImage = image_from_pict(pSrc, FALSE, &srcXoff, &srcYoff)))
+	goto out;
+
+    if (!(dstImage = image_from_pict(pDst, TRUE, &dstXoff, &dstYoff)))
+	goto out_free_src;
+
+    if (maskFormat) {
+	pixman_format_code_t format;
+	pixman_box32_t extents;
+	int x, y;
+
+	format = maskFormat->format | (maskFormat->depth << 24);
+
+	pixman_glyph_get_extents(glyphCache, n_glyphs, pglyphs, &extents);
+
+	x = extents.x1;
+	y = extents.y1;
+
+	pixman_composite_glyphs(op, srcImage, dstImage, format,
+				xSrc + srcXoff + xDst, ySrc + srcYoff + yDst,
+				x, y,
+				x + dstXoff, y + dstYoff,
+				extents.x2 - extents.x1,
+				extents.y2 - extents.y1,
+				glyphCache, n_glyphs, pglyphs);
+    }
+    else {
+	pixman_composite_glyphs_no_mask(op, srcImage, dstImage,
+					xSrc + srcXoff - xDst, ySrc + srcYoff - yDst,
+					dstXoff, dstYoff,
+					glyphCache, n_glyphs, pglyphs);
+    }
+
+    free_pixman_pict(pDst, dstImage);
+
+out_free_src:
+    free_pixman_pict(pSrc, srcImage);
+
+out:
+    pixman_glyph_cache_thaw(glyphCache);
+    if (pglyphs != stack_glyphs)
+	free(pglyphs);
+}
+
 static pixman_image_t *
 create_solid_fill_image(PicturePtr pict)
 {
@@ -357,7 +497,8 @@ fbPictureInit(ScreenPtr pScreen, PictFormatPtr formats, int nformats)
         return FALSE;
     ps = GetPictureScreen(pScreen);
     ps->Composite = fbComposite;
-    ps->Glyphs = miGlyphs;
+    ps->Glyphs = fbGlyphs;
+    ps->UnrealizeGlyph = fbUnrealizeGlyph;
     ps->CompositeRects = miCompositeRects;
     ps->RasterizeTrapezoid = fbRasterizeTrapezoid;
     ps->Trapezoids = fbTrapezoids;