Messages in this thread | | | Date | Sun, 22 Nov 1998 02:51:36 -0800 | From | "David S. Miller" <> | Subject | Re: Intel microcode fixes [OFF-TOPIC] |
| |
Date: Sat, 21 Nov 1998 22:50:58 -0500 (EST) From: "Richard B. Johnson" <root@chaos.analogic.com>
The rest of the story says that, upon power-up, in real mode, it is possible to update the new Pentium's WCS by writing the microcode word-by-word to a register (don't know which), while manipulating a bit in CR0. The bit (don't know which) acts like a transfer pump and has to be set/reset for each word transferred.
This is well documented in some of the web pages which describe the scheme as much as the public has been able to figure out. Also disassembling certain SCO patches and BIOSs reveal how the download is performed exactly.
Heck, some of us have even us have even successfully uploaded bogus microcode to Pentiums while trying to reverse engineer to format...
ummm... who said that...
Later, David S. Miller davem@dm.cobaltmicro.com
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |