Alan Cox 77cb6e6f8d Correctly maintain the per-cpu field "curpmap" on amd64 just like we ... do on i386. The consequences of not doing so on amd64 became apparent with the introduction of the COUNT_IPIS and COUNT_XINVLTLB_HITS options. Specifically, single-threaded applications were generating unnecessary IPIs to shoot-down the TLB on other processors. However, this is clearly nonsensical because a single-threaded application is only running on the current processor. The reason that this happens is that pmap_activate() is unable to properly update the old pmap's field "pm_active" without the correct "curpmap". So, in effect, stale bits in "pm_active" were leading pmap_protect(), pmap_remove(), pmap_remove_pages(), etc. to flush the TLB contents on some arbitrary processor that wasn't even running the same application. Reviewed by: kib MFC after: 3 weeks		2010-07-08 03:35:00 +00:00
..
acpica	Restore the machine check register banks on resume. For banks being	2010-06-15 18:51:41 +00:00
amd64	Correctly maintain the per-cpu field "curpmap" on amd64 just like we	2010-07-08 03:35:00 +00:00
compile
conf	Add the u3g(4) driver. I can't find any reason why it's not here.	2010-07-07 09:23:46 +00:00
ia32	Move prototypes for kern_sigtimedwait() and kern_sigprocmask() to	2010-06-30 18:03:42 +00:00
include	Fix style issues with the previous commit, namely	2010-07-07 12:08:58 +00:00
linux32	Regenerate	2010-06-28 18:17:21 +00:00
pci	number of cleanups in i386 and amd64 pci md code	2009-09-24 07:11:23 +00:00
Makefile	Adjustments to make a tags file a bit more suitable to amd64.	2008-12-01 14:15:10 +00:00