Date: Fri, 26 Jan 2018 21:07:29 -0500 From: Ed Maste <emaste@freebsd.org> To: Ian FREISLICH <ian.freislich@capeaugusta.com> Cc: Konstantin Belousov <kostikbel@gmail.com>, current <current@freebsd.org> Subject: Re: Insta-reset-bootloop with r328166 and vm.pmap.pcid_enabled=1 Message-ID: <CAPyFy2Cd%2Bq1BjF6P_Tm%2Bedm-TAUG=_P4CsX4-%2BBL-SjPvaiDcg@mail.gmail.com> In-Reply-To: <f64e380b-344b-c02f-004a-2c67525134b1@capeaugusta.com> References: <9e533d36-f2ee-58fc-d629-eed7d70645b4@capeaugusta.com> <20180125221312.GU55707@kib.kiev.ua> <f64e380b-344b-c02f-004a-2c67525134b1@capeaugusta.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 25 January 2018 at 17:21, Ian FREISLICH <ian.freislich@capeaugusta.com> wrote: >> Yes, this is how it is currently behaves. >> PCID can be used to optimize PTI, see https://reviews.freebsd.org/D13985. >> It is used for very differrent algorithm when PTI=1, comparing with PTI=0. > > Maybe there should be an "interlock" on these knobs, although judging > from the number of reports I'm the only that shot my foot. Sorry for the trouble. Once D13985 is committed these knobs can both be set to 1 (and in fact that will be the default configuration on Intel systems). I suspect the commit will happen soon and until then it's just a temporary bump inherent in running -current.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAPyFy2Cd%2Bq1BjF6P_Tm%2Bedm-TAUG=_P4CsX4-%2BBL-SjPvaiDcg>