d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Make ofwfb not be painfully slow. This reduces the time for a verbose boot

Browse Source 
on my G4 iBook by more than half. Still 10% slower than syscons, but that's
much better than a factor of 2.

The slowness had to do with pathological write performance on 8-bit
framebuffers, which are almost universally used on Open Firmware systems.
Writing 1 byte at a time, potentially nonconsecutively, resulted in many
extra PCI write cycles. This patch, in the common case where it's writing
one or several characters in an 8x8 font, gangs the writes together into
a set of 32-bit writes. This is a port of r143830 to vt(4).

The EFI framebuffer is also extremely slow, probably for the same reason,
and the same patch will likely help there.
This commit is contained in:
Nathan Whitehorn 2014-05-11 01:58:56 +00:00
parent 8be8ad916f
commit 015ac42e4b
Notes: svn2git 2020-12-20 02:59:44 +00:00 
svn path=/head/; revision=265864
1 changed files with 65 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

92
sys/dev/vt/hw/ofwfb/ofwfb.c
View File

@ -136,6 +136,10 @@ ofwfb_bitbltchr(struct vt_device *vd, const uint8_t *src, const uint8_t *mask,
uint32_t fgc, bgc;
int c;
uint8_t b, m;
union {
uint32_t l;
uint8_t c[4];
} ch1, ch2;
fgc = sc->sc_colormap[fg];
bgc = sc->sc_colormap[bg];
@ -147,36 +151,70 @@ ofwfb_bitbltchr(struct vt_device *vd, const uint8_t *src, const uint8_t *mask,
return;
line = (sc->sc_stride * top) + left * sc->sc_depth/8;
for (; height > 0; height--) {
for (c = 0; c < width; c++) {
if (c % 8 == 0)
if (mask == NULL && sc->sc_depth == 8 && (width % 8 == 0)) {
for (; height > 0; height--) {
for (c = 0; c < width; c += 8) {
b = *src++;
else
b <<= 1;
if (mask != NULL) {
if (c % 8 == 0)
m = *mask++;
else
m <<= 1;
/* Skip pixel write, if mask has no bit set. */
if ((m & 0x80) == 0)
continue;
}
switch(sc->sc_depth) {
case 8:
*(uint8_t *)(sc->sc_addr + line + c) =
b & 0x80 ? fg : bg;
break;
case 32:
*(uint32_t *)(sc->sc_addr + line + 4*c) =
(b & 0x80) ? fgc : bgc;
break;
default:
/* panic? */
break;
/*
* Assume that there is more background than
* foreground in characters and init accordingly
*/
ch1.l = ch2.l = (bg << 24) | (bg << 16) |
(bg << 8) | bg;
/*
* Calculate 2 x 4-chars at a time, and then
* write these out.
*/
if (b & 0x80) ch1.c[0] = fg;
if (b & 0x40) ch1.c[1] = fg;
if (b & 0x20) ch1.c[2] = fg;
if (b & 0x10) ch1.c[3] = fg;
if (b & 0x08) ch2.c[0] = fg;
if (b & 0x04) ch2.c[1] = fg;
if (b & 0x02) ch2.c[2] = fg;
if (b & 0x01) ch2.c[3] = fg;
*(uint32_t *)(sc->sc_addr + line + c) = ch1.l;
*(uint32_t *)(sc->sc_addr + line + c + 4) =
ch2.l;
}
line += sc->sc_stride;
}
} else {
for (; height > 0; height--) {
for (c = 0; c < width; c++) {
if (c % 8 == 0)
b = *src++;
else
b <<= 1;
if (mask != NULL) {
if (c % 8 == 0)
m = *mask++;
else
m <<= 1;
/* Skip pixel write, if mask not set. */
if ((m & 0x80) == 0)
continue;
}
switch(sc->sc_depth) {
case 8:
*(uint8_t *)(sc->sc_addr + line + c) =
b & 0x80 ? fg : bg;
break;
case 32:
*(uint32_t *)(sc->sc_addr + line + 4*c)
= (b & 0x80) ? fgc : bgc;
break;
default:
/* panic? */
break;
}
}
line += sc->sc_stride;
}
line += sc->sc_stride;
}
}