Date: Sun, 11 Nov 2007 17:10:43 -0800 From: Marcel Moolenaar <xcllnt@mac.com> To: Alexander Motin <mav@FreeBSD.org> Cc: Kostik Belousov <kostikbel@gmail.com>, Julian Elischer <julian@elischer.org>, freebsd-arch@FreeBSD.org Subject: Re: Kernel thread stack usage Message-ID: <06618562-A789-4B5E-94BF-0ED8AB51A1FF@mac.com> In-Reply-To: <4737696A.7050605@FreeBSD.org> References: <1191187393.00807485.1191175801@10.7.7.3> <1191189248.00807488.1191177603@10.7.7.3> <4736D8AF.7010209@FreeBSD.org> <20071111163815.GJ37471@deviant.kiev.zoral.com.ua> <47373C5E.2080800@elischer.org> <0414590D-0C2A-4EBD-9617-7AC193ABD1E8@mac.com> <4737696A.7050605@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Nov 11, 2007, at 12:43 PM, Alexander Motin wrote: > Marcel Moolenaar wrote: >> This is not theoretical at all: On ia64 there are 2 stacks. One >> growing down and one growing up. The downward stack is used for >> stack-based variables and the pward growing stack is used by >> the processor for stacked registers. > > Hmm, interesting. And which one is pointed by td_kstack there? Or > they are using same segment but from opposite sides? The latter. The td_kstack variable points to the bottom, which is where the register stack starts. The memory stack start from td_kstack + td_kstack_size. >> The code suggested will not be meaningful on ia64. > > Why? If variable stack growing down and it's segment is pointed by > td_kstack then where is the problem? Or you mean that system will > die earlier when those two stacks in same segment will reach each > other? It's the register stack that grows faster in general and yes, they grow towards each other so they can eventually run into each other. -- Marcel Moolenaar xcllnt@mac.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?06618562-A789-4B5E-94BF-0ED8AB51A1FF>