uvesafb,vesafb: create WC or WB PAT-entries

with an PAT-enabled kernel, when using uvesafb or vesafb, these drivers will
create uncached-minus PAT entries for the framebuffer memory because they use
ioremap() (not the *_cache or *_wc variants). When the framebuffer memory
intersects with the video RAM used by Xorg, the complete video RAM will be
mapped uncached-minus what results in a serve performance penalty.

Here are the correct MTRR entries created by uvesafb:
schlicht@netbook:~$ cat /proc/mtrr
reg00: base=0x000000000 ( 0MB), size= 2048MB, count=1: write-back
reg01: base=0x06ff00000 ( 1791MB), size= 1MB, count=1: uncachable
reg02: base=0x070000000 ( 1792MB), size= 256MB, count=1: uncachable
reg03: base=0x0d0000000 ( 3328MB), size= 16MB, count=1: write-combining

And here are the problematic PAT entries:
schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list
PAT memtype list:
write-back @ 0x0-0x1000
uncached-minus @ 0x6fedd000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee3000-0x6fee4000
uncached-minus @ 0x6fee3000-0x6fee4000
uncached-minus @ 0x6fee3000-0x6fee4000
uncached-minus @ 0xd0000000-0xe0000000 <-- created by xserver-xorg
uncached-minus @ 0xd0000000-0xd1194000 <-- created by uvesafb
uncached-minus @ 0xf4000000-0xf4009000
uncached-minus @ 0xf4200000-0xf4400000
uncached-minus @ 0xf5000000-0xf5010000
uncached-minus @ 0xf5100000-0xf5104000
uncached-minus @ 0xf5400000-0xf5404000
uncached-minus @ 0xf5404000-0xf5405000
uncached-minus @ 0xf5404000-0xf5405000
uncached-minus @ 0xfed00000-0xfed01000

Therefore I created the attached patch for uvesafb which uses ioremap_wc() to
create the correct PAT entries, as shown below:
schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list
PAT memtype list:
write-back @ 0x0-0x1000
uncached-minus @ 0x6fedd000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee2000-0x6fee3000
uncached-minus @ 0x6fee3000-0x6fee4000
uncached-minus @ 0x6fee3000-0x6fee4000
uncached-minus @ 0x6fee3000-0x6fee4000
write-combining @ 0xd0000000-0xe0000000
write-combining @ 0xd0000000-0xd1194000
uncached-minus @ 0xf4000000-0xf4009000
uncached-minus @ 0xf4200000-0xf4400000
uncached-minus @ 0xf5000000-0xf5010000
uncached-minus @ 0xf5100000-0xf5104000
uncached-minus @ 0xf5400000-0xf5404000
uncached-minus @ 0xf5404000-0xf5405000
uncached-minus @ 0xf5404000-0xf5405000
uncached-minus @ 0xfed00000-0xfed01000

This results in a performance gain, objectively measurable with e.g.
x11perf -comppixwin10 -comppixwin100 -comppixwin500:
1: x11perf_xaa.log
2: x11perf_xaa_patched.log

1 2 Operation
-------- ---------------- -----------------
124000.0 202000.0 ( 1.63) Composite 10x10 from pixmap to window
3340.0 24400.0 ( 7.31) Composite 100x100 from pixmap to window
131.0 1150.0 ( 8.78) Composite 500x500 from pixmap to window

You can see the serve performance gain when composing larger pixmaps to window.

The patches replace the ioremap() function with the variant matching the mtrr-
parameter. To create "write-back" PAT entries, the ioremap_cache() function
must be called after creating the MTRR entries, and the ioremap_cache() region
must completely fit into the MTRR region, this is why the MTRR region size is
now rounded up to the next power-of-two.

Signed-off-by: Thomas Schlichter <[e-mail]>
Signed-off-by: Paul Mundt <[e-mail]>

drivers/video/uvesafb.c

···
 			int rc;
 
 			/* Find the largest power-of-two */
-			while (temp_size & (temp_size - 1))
-				temp_size &= (temp_size - 1);
+			temp_size = roundup_pow_of_two(temp_size);
 
 			/* Try and find a power of two to add */
 			do {
···
 #endif /* CONFIG_MTRR */
 }
 
+static void __devinit uvesafb_ioremap(struct fb_info *info)
+{
+#ifdef CONFIG_X86
+	switch (mtrr) {
+	case 1: /* uncachable */
+		info->screen_base = ioremap_nocache(info->fix.smem_start, info->fix.smem_len);
+		break;
+	case 2: /* write-back */
+		info->screen_base = ioremap_cache(info->fix.smem_start, info->fix.smem_len);
+		break;
+	case 3: /* write-combining */
+		info->screen_base = ioremap_wc(info->fix.smem_start, info->fix.smem_len);
+		break;
+	case 4: /* write-through */
+	default:
+		info->screen_base = ioremap(info->fix.smem_start, info->fix.smem_len);
+		break;
+	}
+#else
+	info->screen_base = ioremap(info->fix.smem_start, info->fix.smem_len);
+#endif /* CONFIG_X86 */
+}
 
 static ssize_t uvesafb_show_vbe_ver(struct device *dev,
 		struct device_attribute *attr, char *buf)
···
 
 	uvesafb_init_info(info, mode);
 
+	if (!request_region(0x3c0, 32, "uvesafb")) {
+		printk(KERN_ERR "uvesafb: request region 0x3c0-0x3e0 failed\n");
+		err = -EIO;
+		goto out_mode;
+	}
+
 	if (!request_mem_region(info->fix.smem_start, info->fix.smem_len,
 				"uvesafb")) {
 		printk(KERN_ERR "uvesafb: cannot reserve video memory at "
 				"0x%lx\n", info->fix.smem_start);
 		err = -EIO;
-		goto out_mode;
+		goto out_reg;
 	}
 
-	info->screen_base = ioremap(info->fix.smem_start, info->fix.smem_len);
+	uvesafb_init_mtrr(info);
+	uvesafb_ioremap(info);
 
 	if (!info->screen_base) {
 		printk(KERN_ERR
···
 		goto out_mem;
 	}
 
-	if (!request_region(0x3c0, 32, "uvesafb")) {
-		printk(KERN_ERR "uvesafb: request region 0x3c0-0x3e0 failed\n");
-		err = -EIO;
-		goto out_unmap;
-	}
-
-	uvesafb_init_mtrr(info);
 	platform_set_drvdata(dev, info);
 
 	if (register_framebuffer(info) < 0) {
 		printk(KERN_ERR
 			"uvesafb: failed to register framebuffer device\n");
 		err = -EINVAL;
-		goto out_reg;
+		goto out_unmap;
 	}
 
 	printk(KERN_INFO "uvesafb: framebuffer at 0x%lx, mapped to 0x%p, "
···
 
 	return 0;
 
-out_reg:
-	release_region(0x3c0, 32);
 out_unmap:
 	iounmap(info->screen_base);
 out_mem:
 	release_mem_region(info->fix.smem_start, info->fix.smem_len);
+out_reg:
+	release_region(0x3c0, 32);
 out_mode:
 	if (!list_empty(&info->modelist))
 		fb_destroy_modelist(&info->modelist);

drivers/video/vesafb.c

···
 	info->apertures->ranges[0].base = screen_info.lfb_base;
 	info->apertures->ranges[0].size = size_total;
 
-	info->screen_base = ioremap(vesafb_fix.smem_start, vesafb_fix.smem_len);
-	if (!info->screen_base) {
-		printk(KERN_ERR
-		       "vesafb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n",
-			vesafb_fix.smem_len, vesafb_fix.smem_start);
-		err = -EIO;
-		goto err;
-	}
-
-	printk(KERN_INFO "vesafb: framebuffer at 0x%lx, mapped to 0x%p, "
-	       "using %dk, total %dk\n",
-	       vesafb_fix.smem_start, info->screen_base,
-	       size_remap/1024, size_total/1024);
 	printk(KERN_INFO "vesafb: mode is %dx%dx%d, linelength=%d, pages=%d\n",
 	       vesafb_defined.xres, vesafb_defined.yres, vesafb_defined.bits_per_pixel, vesafb_fix.line_length, screen_info.pages);
 
···
 			int rc;
 
 			/* Find the largest power-of-two */
-			while (temp_size & (temp_size - 1))
-				temp_size &= (temp_size - 1);
+			temp_size = roundup_pow_of_two(temp_size);
 
 			/* Try and find a power of two to add */
 			do {
···
 	}
 #endif
 	
+	switch (mtrr) {
+	case 1: /* uncachable */
+		info->screen_base = ioremap_nocache(vesafb_fix.smem_start, vesafb_fix.smem_len);
+		break;
+	case 2: /* write-back */
+		info->screen_base = ioremap_cache(vesafb_fix.smem_start, vesafb_fix.smem_len);
+		break;
+	case 3: /* write-combining */
+		info->screen_base = ioremap_wc(vesafb_fix.smem_start, vesafb_fix.smem_len);
+		break;
+	case 4: /* write-through */
+	default:
+		info->screen_base = ioremap(vesafb_fix.smem_start, vesafb_fix.smem_len);
+		break;
+	}
+	if (!info->screen_base) {
+		printk(KERN_ERR
+		       "vesafb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n",
+			vesafb_fix.smem_len, vesafb_fix.smem_start);
+		err = -EIO;
+		goto err;
+	}
+
+	printk(KERN_INFO "vesafb: framebuffer at 0x%lx, mapped to 0x%p, "
+	       "using %dk, total %dk\n",
+	       vesafb_fix.smem_start, info->screen_base,
+	       size_remap/1024, size_total/1024);
+
 	info->fbops = &vesafb_ops;
 	info->var = vesafb_defined;
 	info->fix = vesafb_fix;