On 09.07.20 17:22, Jan Leupold via Xenomai wrote:
Hi Greg,
Am 02.07.20 um 14:07 schrieb Greg Gallagher:
On Thu., Jul. 2, 2020, 6:16 a.m. Jan Leupold via Xenomai
<[email protected] <mailto:[email protected]>> wrote:
Hi,
I have a problem with switchtest, executed on sama5d2,
ipipe-4.19.128-cip28, xenomai-3.1.
When started without arguments:
== Testing FPU check routines...
d0: 1 != 2
... snip ...
d15: 1 != 2
== FPU check routines: OK.
== Threads: sleeper_ufps-0 rtk-1 rtk-2 rtk_fp-3 rtk_fp-4 rtk_fp_ufpp-5
rtk_fp_ufpp-6 rtup-7 rtup-8 rtup_ufpp-9 rtup_ufpp-10 rtus-11 rtus-12
rtus_ufps-13 rtus_ufps-14 rtuo-15 rtuo-16 rtuo_ufpp-17 rtuo_ufpp-18
rtuo_ufps-19 rtuo_ufps-20 rtuo_ufpp_ufps-21 rtuo_ufpp_ufps-22
RTT| 00:00:00
RTH|ctx switches|-------total
RTD| 25| 25
no more output, exit status = 1
When started as "switchtest -n":
== Threads: sleeper-0 rtk-1 rtk-2 rtup-3 rtup-4 rtus-5 rtus-6 rtuo-7 rtuo-8
RTT| 00:00:01
RTH|ctx switches|-------total
RTD| 4295| 4295
RTD| 4316| 8611
RTD| 4279| 12890
RTD| 4316| 17206
RTD| 4313| 21519
^C
RTD| 1215| 22734
deliberately terminated by CTRL-C, exit status = 0
Any threadspec of rtus_ufps, rtup_ufpp or rtuo_ufpp will cause the effect.
When looking at the source code I would suspect "fp_regs_set()" to
cause it.
The kernel log reports messages like this one:
[Xenomai] rtup_ufpp-1[1599] called regular ioctl() on /dev/rtdm/switchtest
While I have no reason to think that floating point operations are not
OK on this target I would like to at least know why switchtest fails
when using floating point:
* VFP initialization with respect to register access?
* Number of floating point registers? (although NEON should have more than
the tested 16)
* Any ideas?
Regards,
Jan
Some more details:
CONFIG_VFP, CONFIG_VFPv3 and CONFIG_NEON are set.
trace-cmd record -e cobalt* -e sched* -e signal*
switchtest
trace-cmd report
---> output (at least the portion that seems to me relevant):
... switchtest threads are doing their work, and then comes rtup-ufpp-9 ...
rtup-8-1538 [000] 135.112086: cobalt_switch_context:
prev_name=rtup-8 prev_pid=1538 prev_prio=1 prev_state=0x48042 ==>
next_name=rtup_ufpp-9 next_pid=1539 next_prio=1
rtup_ufpp-9-1539 [000] 135.112129: cobalt_head_sysexit: result=0
rtup_ufpp-9-1539 [000] 135.112154: cobalt_head_sysentry:
syscall=ioctl
rtup_ufpp-9-1539 [000] 135.112170: cobalt_fd_ioctl:
device=0xc0b7a988 fd=3 arg=0x9 pid=1539 comm=rtup_ufpp-9
rtup_ufpp-9-1539 [000] 135.112192: cobalt_fd_ioctl_status:
device=0xc0b7a988 fd=3 pid=1539 comm=rtup_ufpp-9
rtup_ufpp-9-1539 [000] 135.112207: cobalt_shadow_gorelax:
reason=syscall
rtup_ufpp-9-1539 [000] 135.112221: cobalt_lostage_request:
request=c090b004 pid=1539 comm=rtup_ufpp-9
rtup_ufpp-9-1539 [000] 135.112240: cobalt_thread_suspend: pid=1539
mask=0x80 timeout=0 timeout_mode=0 wchan=(nil)
rtup_ufpp-9-1539 [000] 135.112254: cobalt_schedule:
status=0x10000000
rtup_ufpp-9-1539 [000] 135.112262: cobalt_switch_context:
prev_name=rtup_ufpp-9 prev_pid=1539 prev_prio=1 prev_state=0x480c0 ==>
next_name=ROOT next_pid=0 next_prio=-1
switchtest-1530 [000] 135.112308: cobalt_lostage_wakeup: pid=1539
comm=rtup_ufpp-9
switchtest-1530 [000] 135.112329: sched_waking:
comm=rtup_ufpp-9 pid=1539 prio=98 target_cpu=000
switchtest-1530 [000] 135.112380: sched_wakeup:
rtup_ufpp-9:1539 [98] success=1 CPU:000
switchtest-1530 [000] 135.112450: sched_stat_runtime:
comm=switchtest pid=1530 runtime=3009028 [ns] vruntime=22563904956 [ns]
switchtest-1530 [000] 135.112489: sched_switch:
switchtest:1530 [120] R ==> rtup_ufpp-9:1539 [98]
rtup_ufpp-9-1539 [000] 135.112561: cobalt_shadow_relaxed:
state=0x480c0 info=0x0
rtup_ufpp-9-1539 [000] 135.112581: cobalt_fd_ioctl:
device=0xc0b7a988 fd=3 arg=0x9 pid=1539 comm=rtup_ufpp-9
rtup_ufpp-9-1539 [000] 135.112602: cobalt_fd_ioctl_status:
device=0xc0b7a988 fd=3 pid=1539 comm=rtup_ufpp-9
rtup_ufpp-9-1539 [000] 135.112614: cobalt_head_sysexit: result=-38
rtup_ufpp-9-1539 [000] 135.112997: sched_waking:
comm=switchtest pid=1527 prio=120 target_cpu=000
rtup_ufpp-9-1539 [000] 135.113036: sched_wakeup:
switchtest:1527 [120] success=1 CPU:000
rtup_ufpp-9-1539 [000] 135.113055: signal_generate: sig=15
errno=0 code=-6 comm=switchtest pid=1527 grp=0 res=0
rtup_ufpp-9-1539 [000] 135.113204: sched_switch:
rtup_ufpp-9:1539 [98] S ==> switchtest:1527 [120]
switchtest-1527 [000] 135.113621: sched_waking:
comm=switchtest pid=1530 prio=120 target_cpu=000
switchtest-1527 [000] 135.113656: sched_stat_runtime:
comm=switchtest pid=1527 runtime=492337 [ns] vruntime=22561734482 [ns]
switchtest-1527 [000] 135.113684: sched_wakeup:
switchtest:1530 [120] success=1 CPU:000
switchtest-1527 [000] 135.113697: signal_generate: sig=32
errno=0 code=-6 comm=switchtest pid=1530 grp=0 res=0
switchtest-1527 [000] 135.113805: cobalt_thread_unblock: pid=1537
state=0x48042 info=0x0
switchtest-1527 [000] 135.113820: cobalt_thread_resume:
name=rtup-7 pid=1537 mask=0x2
switchtest-1527 [000] 135.113837: cobalt_synch_forget:
synch=0xd92e00e0
switchtest-1527 [000] 135.113872: cobalt_schedule_remote:
status=0x10000000
switchtest-1527 [000] 135.113880: cobalt_schedule:
status=0x10000000
switchtest-1527 [000] 135.113893: cobalt_switch_context:
prev_name=ROOT prev_pid=0 prev_prio=-1 prev_state=0x18008 ==>
next_name=rtup-7 next_pid=1537 next_prio=1
rtup-7-1537 [000] 135.113948: cobalt_fd_ioctl_status:
device=0xc0b7a988 fd=3 pid=1537 comm=rtup-7
rtup-7-1537 [000] 135.113972: cobalt_shadow_gorelax:
reason=signal
rtup-7-1537 [000] 135.113985: cobalt_lostage_request:
request=c090b004 pid=1537 comm=rtup-7
rtup-7-1537 [000] 135.113999: cobalt_thread_suspend: pid=1537
mask=0x80 timeout=0 timeout_mode=0 wchan=(nil)
rtup-7-1537 [000] 135.114013: cobalt_schedule:
status=0x10000000
rtup-7-1537 [000] 135.114021: cobalt_switch_context:
prev_name=rtup-7 prev_pid=1537 prev_prio=1 prev_state=0x480c0 ==>
next_name=ROOT next_pid=0 next_prio=-1
Mit freundlichen Grüßen
*Jan Leupold*
Entwicklung
Development
--
I can take a look and see if I can reproduce on another arm platform. I'm
not too familiar with this test but I'll run it and see if there's anything
unusual on the ipipe side of things.
-Greg
Thanks for trying it out on other platforms! I think I found a way now
to get switchtest working:
When I use DEFAULTTUNE="cortexa5thf-neon-vfpv4" (in yocto) instead of
"cortexa5thf", it executes without any problems on my target.
I'm not an expert in the semantics of these tuning - do they make sense
as well, or are we still facing a not fully understood issue here?
Jan
--
Siemens AG, Corporate Technology, CT RDA IOT SES-DE
Corporate Competence Center Embedded Linux
