Date: Wed, 11 Aug 2010 13:21:46 +0200 From: Attilio Rao <attilio@freebsd.org> To: Kostik Belousov <kostikbel@gmail.com> Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org Subject: Re: svn commit: r211176 - in head/sys: amd64/amd64 i386/i386 Message-ID: <AANLkTikk3m-=5W7TVV5C-XM4AnwS1LuAi7GGEeP0B9dV@mail.gmail.com> In-Reply-To: <20100811105739.GJ2396@deviant.kiev.zoral.com.ua> References: <201008111051.o7BApRp4028538@svn.freebsd.org> <20100811105739.GJ2396@deviant.kiev.zoral.com.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
2010/8/11 Kostik Belousov <kostikbel@gmail.com>: > On Wed, Aug 11, 2010 at 10:51:27AM +0000, Attilio Rao wrote: >> Author: attilio >> Date: Wed Aug 11 10:51:27 2010 >> New Revision: 211176 >> URL: http://svn.freebsd.org/changeset/base/211176 >> >> Log: >> =C2=A0 IPI handlers may run generally with interrupts disabled because t= hey >> =C2=A0 are served via an interrupt gate. >> >> =C2=A0 However, that doesn't explicitly prevent preemption and thread >> =C2=A0 migration thus scheduler pinning may be necessary in some handler= s. >> =C2=A0 Fix that. > > How the preemption is supposed to happen ? Aside from the explicit > calls to mi_switch() from e.g. critical_exit(). IIRC it should be hardclock() willing to schedule the softclock(). It is the critical_exit() in the thread_unlock() that may trigger it (sorry for not digging more, it was a while back that I hacked this part, but I guess you can verify on your own). We already have other points within the kernel that take care of dealing with preemption/migration like lapic_handle_timer(), for example. Thanks, Attilio --=20 Peace can only be achieved by understanding - A. Einstein
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTikk3m-=5W7TVV5C-XM4AnwS1LuAi7GGEeP0B9dV>