RCU_USER_QS traces.

[Dave Jones]

 > We have CONFIG_RCU_USER_QS that is a specific case. It's an intermediate state
 > before we implement a true CONFIG_NO_HZ_FULL. But the option is useless on its
 > own for users. Worse, it introduces a real overhead. OTOH we want it to be upstream
 > to make the development of full tickless feature more incremental.

I couldn't resist trying it.. Did these get reported yet ?


WARNING: at kernel/rcutree.c:377 rcu_eqs_enter+0x93/0xa0()
Pid: 0, comm: swapper/1 Not tainted 3.6.0+ #24
Call Trace:
 [<ffffffff810678af>] warn_slowpath_common+0x7f/0xc0
 [<ffffffff8106790a>] warn_slowpath_null+0x1a/0x20
 [<ffffffff8111a383>] rcu_eqs_enter+0x93/0xa0
 [<ffffffff8111af0b>] rcu_idle_enter+0x2b/0x70
 [<ffffffff8102460f>] cpu_idle+0xbf/0x140
 [<ffffffff816ad18d>] start_secondary+0x252/0x254

WARNING: at kernel/rcutree.c:352 rcu_eqs_enter_common.isra.37+0x1c6/0x1e0()
Pid: 0, comm: swapper/1 Tainted: G        W    3.6.0+ #24
Call Trace:
 [<ffffffff810678af>] warn_slowpath_common+0x7f/0xc0
 [<ffffffff8106790a>] warn_slowpath_null+0x1a/0x20
 [<ffffffff8111a2d6>] rcu_eqs_enter_common.isra.37+0x1c6/0x1e0
 [<ffffffff8111a355>] rcu_eqs_enter+0x65/0xa0
 [<ffffffff8111af0b>] rcu_idle_enter+0x2b/0x70
 [<ffffffff8102460f>] cpu_idle+0xbf/0x140
 [<ffffffff816ad18d>] start_secondary+0x252/0x254

WARNING: at kernel/rcutree.c:539 rcu_eqs_exit+0x99/0xb0()
Pid: 0, comm: swapper/1 Tainted: G        W    3.6.0+ #24
Call Trace:
 [<ffffffff810678af>] warn_slowpath_common+0x7f/0xc0
 [<ffffffff8106790a>] warn_slowpath_null+0x1a/0x20
 [<ffffffff8111a0f9>] rcu_eqs_exit+0x99/0xb0
 [<ffffffff8111ae9b>] rcu_idle_exit+0x2b/0x70
 [<ffffffff8102461e>] cpu_idle+0xce/0x140
 [<ffffffff816ad18d>] start_secondary+0x252/0x254

WARNING: at kernel/rcutree.c:513 rcu_eqs_exit_common.isra.35+0xd4/0xe0()
Pid: 0, comm: swapper/1 Tainted: G        W    3.6.0+ #24
Call Trace:
 [<ffffffff810678af>] warn_slowpath_common+0x7f/0xc0
 [<ffffffff8106790a>] warn_slowpath_null+0x1a/0x20
 [<ffffffff8111a054>] rcu_eqs_exit_common.isra.35+0xd4/0xe0
 [<ffffffff8111a0bc>] rcu_eqs_exit+0x5c/0xb0
 [<ffffffff8111ae9b>] rcu_idle_exit+0x2b/0x70
 [<ffffffff8102461e>] cpu_idle+0xce/0x140
 [<ffffffff816ad18d>] start_secondary+0x252/0x254

	Dave

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/