Date: Tue, 03 Dec 1996 21:53:29 -0800 From: Erich Boleyn <erich@uruk.org> To: smp@freebsd.org Subject: Crashing on activating other CPUs Message-ID: <E0vVAGv-0000q5-00@uruk.org>
next in thread | raw e-mail | index | archive | help
I synced up my tree here, and tried it out with and without APIC_IO (and with/without SMP_INVLTLB). The syscons problems are fixed (yayy!), and it runs well as long as I don't try to start any other CPUs (via "sysctl -w kern.smp_active=2"). If I do the above command, a big flurry of: Fatal trap 12: page fault while in kernel mode ...and full dump messages run by before it freezes solid (and a reset is necessary). No variation on SMP_INVLTLB or APIC_IO seems to change the above behavior. The last messages say: cpunumber = 2 fault virtual address = 0xa0 fault code = supervisor read, page not present instruction pointer = 0x8:0xf01150d9 stack pointer = 0x10:0xf0223c12 frame pointer = 0x10:0xf0223c22 ... current precess = Idle interrupt mask = tty panic (cpu#2): page fault boot() called on cpu#2 I'll sniff around to see if I can find where it is in the code tomorrow (my wife is saying I must come to bed or I won't live to see the morning ;-). I suspect it might be a greater than 2 CPUs problem (question: should I be saying "kern.smp_active=4" on my 4 CPU test box??). -- Erich Stefan Boleyn \_ E-mail (preferred): <erich@uruk.org> Mad Genius wanna-be, CyberMuffin \__ (finger me for other stats) Web: http://www.uruk.org/~erich/ Motto: "I'll live forever or die trying"
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E0vVAGv-0000q5-00>