Thomas, On Tuesday, 25 September 2007 22:46, Thomas Gleixner wrote: > Rafael, > > On Tue, 2007-09-25 at 22:07 +0200, Rafael J. Wysocki wrote: > > On Tuesday, 25 September 2007 15:17, Thomas Gleixner wrote: > > > On Tue, 2007-09-25 at 15:16 +0200, Rafael J. Wysocki wrote: > > [--snip--] > > > > > > I start to get desperate. Below is a patch, which moves the apic timer > > > disable check after the calibration routine. Can you please apply on top > > > of -hrt and add "noapictimer" to the command line ? Does it boot ? > > > > 2.6.23-rc7 with patch-2.6.23-rc7-hrt1.patch and the patch below applied > > boots > > with noapictimer and doesn't boot without it. > > That was expected. I explicitly asked to add "noapictimer" to the kernel > command line. > > Ok, so we ruled out the apic timer calibration routine. I did not expect > that this would be the culprit, but with "dark screen" as the only debug > info, I need to resort to small steps. > > Can you please send me the output of /proc/timer_list of 2.6.23-rc7-hrt1 > after booting with "noapictimer" ?
Sure, attached. [Note: the kernel has been compiled with both NO_HZ and HIGH_RES_TIMERS unset.] > I'm a bit confused by your earlier confirmation, that mainline w/o the > -hrt patches boots fine, when you add "apicmaintimer" to the kernel > command line. "apicmaintimer" stops the PIT like we do in -hrt and we > just use the local APIC timer for everything. Can you please retest and > confirm that this is correct ? No, it's not. The mainline _usually_ doesn't boot with "apicmaintimer". It seems to me that _sometimes_ the CPU just doesn't enter this C1E state and then everything goes fine ... > Is the 32 bit kernel working on that box ? Can't tell, I have only 64-bit userland here. > Thanks for your patience. Well, I'm only making sure that future kernels will run on my box. ;-) > tglx > > PS: I just sent out the "disable APIC timer for AMD C1E boxen" patch. Yes, I've already tested it and sent a reply. It works. :-) > We debugged this half a year ago on a nx6325, but I completely forgot about > that. The explanation from AMD was sensible, but your "apicmaintimer" > works statement is contradictory. Well, it was wrong. I have some problems with resuming from suspend to RAM using 2.6.23-rc8-mm1 with this patch applied, but I think they are related to something else. I'll wait for the next -mm with debugging that. For now, I'm going to build 2.6.23-rc8 with my collection of suspend patches plus patch-2.6.23-rc7-hrt1.patch and the "disable APIC timer for AMD C1E boxes" patch applied. I'll play with that a bit and let you know how it's behaving. Greetings, Rafael
Timer List Version: v0.3 HRTIMER_MAX_CLOCK_BASES: 2 now at 279792107058 nsecs cpu: 0 clock 0: .index: 0 .resolution: 4000250 nsecs .get_time: ktime_get_real active timers: clock 1: .index: 1 .resolution: 4000250 nsecs .get_time: ktime_get active timers: #0: <ffff81004f98bda8>, hrtimer_wakeup, S:01, do_nanosleep, kwrapper/4664 # expires at 280207419178 nsecs [in 415312120 nsecs] #1: <ffff81004f98bda8>, hrtimer_wakeup, S:01, futex_wait, nscd/4080 # expires at 282678021548 nsecs [in 2885914490 nsecs] #2: <ffff81004f98bda8>, hrtimer_wakeup, S:01, futex_wait, nscd/4082 # expires at 282678129670 nsecs [in 2886022612 nsecs] #3: <ffff81004f98bda8>, it_real_fn, S:01, do_setitimer, qmgr/4239 # expires at 378654389676 nsecs [in 98862282618 nsecs] #4: <ffff81004f98bda8>, it_real_fn, S:01, do_setitimer, pickup/4238 # expires at 557809025993 nsecs [in 278016918935 nsecs] #5: <ffff81004f98bda8>, it_real_fn, S:01, do_setitimer, master/4216 # expires at 557809137746 nsecs [in 278017030688 nsecs] cpu: 1 clock 0: .index: 0 .resolution: 4000250 nsecs .get_time: ktime_get_real active timers: clock 1: .index: 1 .resolution: 4000250 nsecs .get_time: ktime_get active timers: #0: <ffff81004f98bda8>, it_real_fn, S:01, do_setitimer, Xorg/4355 # expires at 279804542721 nsecs [in 12435663 nsecs] #1: <ffff81004f98bda8>, it_real_fn, S:01, do_setitimer, ssh-agent/4611 # expires at 279962268496 nsecs [in 170161438 nsecs] #2: <ffff81004f98bda8>, hrtimer_wakeup, S:01, do_nanosleep, hald-addon-stor/4148 # expires at 280071774352 nsecs [in 279667294 nsecs] #3: <ffff81004f98bda8>, hrtimer_wakeup, S:01, futex_wait, nscd/4081 # expires at 282678034680 nsecs [in 2885927622 nsecs] #4: <ffff81004f98bda8>, hrtimer_wakeup, S:01, do_nanosleep, cron/4241 # expires at 335311096287 nsecs [in 55518989229 nsecs] #5: <ffff81004f98bda8>, it_real_fn, S:01, do_setitimer, dhcpcd/5128 # expires at 604918992928181 nsecs [in 604639200821123 nsecs] #6: <ffff81004f98bda8>, hrtimer_wakeup, S:01, do_nanosleep, dhcpcd/5128 # expires at 604918992950531 nsecs [in 604639200843473 nsecs] Tick Device: mode: 0 Clock Event Device: pit max_delta_ns: 27461866 min_delta_ns: 12571 mult: 5124677 shift: 32 mode: 2 next_event: 9223372036854775807 nsecs set_next_event: pit_next_event set_mode: init_pit_timer event_handler: tick_handle_periodic_broadcast tick_broadcast_mask: 00000003 Tick Device: mode: 0 Clock Event Device: lapic max_delta_ns: 0 min_delta_ns: 0 mult: 0 shift: 32 mode: 1 next_event: 0 nsecs set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: tick_handle_periodic Tick Device: mode: 0 Clock Event Device: lapic max_delta_ns: 0 min_delta_ns: 0 mult: 0 shift: 32 mode: 1 next_event: 0 nsecs set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: tick_handle_periodic
