linux-rt-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* RCU splat on boot from an idle CPU
@ 2015-09-01  0:46 Philipp Schrader
  2015-09-01 15:35 ` Thomas Gleixner
  0 siblings, 1 reply; 13+ messages in thread
From: Philipp Schrader @ 2015-09-01  0:46 UTC (permalink / raw)
  To: linux-rt-users

Hi all,

I've got a real-time kernel on a DRA7 evaluation module (EVM).
Very early in the boot process I get the following splat.

[    0.055073]
[    0.055076] ===============================
[    0.055079] [ INFO: suspicious RCU usage. ]
[    0.055084] 4.1.6+ #2 Not tainted
[    0.055086] -------------------------------
[    0.055090] include/trace/events/hist.h:31 suspicious
rcu_dereference_check() usage!
[    0.055093]
[    0.055093] other info that might help us debug this:
[    0.055093]
[    0.055097]
[    0.055097] RCU used illegally from idle CPU!
[    0.055097] rcu_scheduler_active = 1, debug_locks = 1
[    0.055100] RCU used illegally from extended quiescent state!
[    0.055104] no locks held by swapper/0/0.
[    0.055106]
[    0.055106] stack backtrace:
[    0.055112] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.1.6+ #2
[    0.055116] Hardware name: Generic DRA74X (Flattened Device Tree)
[    0.055130] [<c00196b8>] (unwind_backtrace) from [<c001515c>]
(show_stack+0x20/0x24)
[    0.055146] [<c001515c>] (show_stack) from [<c07bc408>]
(dump_stack+0x84/0xa0)
[    0.055160] [<c07bc408>] (dump_stack) from [<c009bc38>]
(lockdep_rcu_suspicious+0xb0/0x110)
[    0.055172] [<c009bc38>] (lockdep_rcu_suspicious) from [<c01246c4>]
(time_hardirqs_off+0x2b8/0x3c8)
[    0.055184] [<c01246c4>] (time_hardirqs_off) from [<c009a218>]
(trace_hardirqs_off_caller+0x2c/0xf4)
[    0.055194] [<c009a218>] (trace_hardirqs_off_caller) from
[<c009a2f4>] (trace_hardirqs_off+0x14/0x18)
[    0.055204] [<c009a2f4>] (trace_hardirqs_off) from [<c00c7ecc>]
(rcu_idle_enter+0x78/0xcc)
[    0.055213] [<c00c7ecc>] (rcu_idle_enter) from [<c0093eb0>]
(cpu_startup_entry+0x190/0x518)
[    0.055222] [<c0093eb0>] (cpu_startup_entry) from [<c07b95b4>]
(rest_init+0x13c/0x17c)
[    0.055231] [<c07b95b4>] (rest_init) from [<c0b32c74>]
(start_kernel+0x320/0x380)
[    0.055238] [<c0b32c74>] (start_kernel) from [<8000807c>] (0x8000807c)

I'm not sure how to debug this; I'm still reading up on RCUs. Pretty
nifty ideas.

Looking at include/trace/events/hist.h it appears line 31 is the end
of a TRACE_EVENT macro usage.
Does that mean the macro is using RCU improperly somehow?

Thanks,
Philipp

^ permalink raw reply	[flat|nested] 13+ messages in thread

end of thread, other threads:[~2015-12-11 16:59 UTC | newest]

Thread overview: 13+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-09-01  0:46 RCU splat on boot from an idle CPU Philipp Schrader
2015-09-01 15:35 ` Thomas Gleixner
2015-09-02 19:38   ` Steven Rostedt
2015-09-02 22:10     ` Philipp Schrader
2015-09-02 23:07       ` Paul E. McKenney
2015-09-03 16:53         ` Steven Rostedt
2015-09-03 21:39           ` Paul E. McKenney
2015-09-03 16:55         ` Philipp Schrader
2015-09-03 17:12           ` Steven Rostedt
2015-12-11 16:32           ` Sebastian Andrzej Siewior
2015-12-11 16:46             ` Philipp Schrader
2015-12-11 16:53               ` Paul E. McKenney
2015-12-11 16:59                 ` Philipp Schrader

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).