Date: Fri, 20 Aug 2004 17:28:02 GMT From: John Baldwin <jhb@FreeBSD.org> To: Perforce Change Reviews <perforce@freebsd.org> Subject: PERFORCE change 60155 for review Message-ID: <200408201728.i7KHS2rq031687@repoman.freebsd.org>
next in thread | raw e-mail | index | archive | help
http://perforce.freebsd.org/chv.cgi?CH=60155 Change 60155 by jhb@jhb_slimer on 2004/08/20 17:28:00 Update todo. Affected files ... .. //depot/projects/smpng/sys/notes#17 edit Differences ... ==== //depot/projects/smpng/sys/notes#17 (text+ko) ==== @@ -3,9 +3,6 @@ - Consolidate linux module version and dependencies into MI location. - Untested -- Enable a pmap_emulate_reference check for Alpha under INVARIANTS instead - of DEBUG. ?? -- Lock Giant at beginning of pcic(4) driver's kthread ?? - Use an explicit IDT handler for the PPro errata 5AP. - CVS already has a different work around where we disable the local APIC on these processors. However, the apic(4) code tries to re-enable the @@ -52,5 +49,10 @@ buys is being able to swi_sched() from a fast handler, but that doesn't make sense because you can't actually enqueue a task onto its queue from a fast interrupt context +- Make ABI wrappers use kern_fcntl() and make them MP safe. +- "Optimize" atomic_store_rel() on i386 (it actually seems to be slower, + go figure) +- Optimize spin locks on UP such that they don't do atomic operations + - Untested Space reserved for child branches:
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200408201728.i7KHS2rq031687>