Matthew Dillon 4453311409 Even better then using %fs:0 in our locked synchronizing instruction, ... we instead use 0(%esp), which is per-cpu, already pretty much guarenteed to be locked into the cache, and does not stress the cache's set associativity. invlpg might also be a good choice (suggested by Ingo). Obtained from: Linus Torvalds <torvalds@transmeta.com>		1999-11-23 20:07:39 +00:00
..
apm	Use DRIVER_MODULE(), apm.c already takes care of it's devices with	1999-11-08 07:44:26 +00:00
bios	Use DRIVER_MODULE(), apm.c already takes care of it's devices with	1999-11-08 07:44:26 +00:00
boot	GC bdbtofsb()	1999-09-26 19:05:39 +00:00
conf	Update the Alpha makefile to be more in line with the x86 version. It	1999-11-22 15:39:13 +00:00
eisa	Delete unneeded #include	1999-10-11 14:42:33 +00:00
i386	Even better then using %fs:0 in our locked synchronizing instruction,	1999-11-23 20:07:39 +00:00
ibcs2	Fix case where vnode could be unlocked twice. Untested; bug found by code	1999-11-14 17:33:40 +00:00
include	Optimize two cases in the MP locking code. First, it is not necessary	1999-11-19 22:47:19 +00:00
isa	Optimize two cases in the MP locking code. First, it is not necessary	1999-11-19 16:49:30 +00:00
linux	simplify check for device.	1999-11-08 09:59:17 +00:00
pci	If we have found pci devices via pci_cfgopen(), but don't find a	1999-11-18 08:58:37 +00:00
svr4	useracc() the prequel:	1999-10-29 18:09:36 +00:00
Makefile	$Id$ -> $FreeBSD$	1999-08-28 01:08:13 +00:00