INFO: suspicious RCU usage
===============================
[ INFO: suspicious RCU usage. ]
-------------------------------
/build/linux/kernel/sched/fair.c:5091 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 1
1 lock held by swapper/0/1:
#0: (&sb->s_type->i_mutex_key#2){+.+.+.}, at: [<ffffffff812a0e0c>] debugfs_create_file+0x8c/0x270
stack backtrace: Pid: 1, comm: swapper/0 Not tainted 3.2.0-rc1-00339-gcd490c5 #14 Call Trace: <IRQ> [<ffffffff815f9968>] ? _raw_spin_unlock_irqrestore+0x38/0x80 [<ffffffff8109407f>] lockdep_rcu_suspicious+0xbf/0xe0 [<ffffffff8107dd48>] trigger_load_balance+0x5b8/0x5c0 [<ffffffff81070544>] scheduler_tick+0x104/0x160 [<ffffffff8104a1ce>] update_process_times+0x6e/0x90 [<ffffffff8108e32c>] tick_periodic+0x2c/0x70 [<ffffffff8108e394>] tick_handle_periodic+0x24/0x80 [<ffffffff812a07a7>] ? T.562+0xf7/0x170 [<ffffffff815fce56>] smp_apic_timer_interrupt+0x66/0x98 [<ffffffff815fb2f0>] apic_timer_interrupt+0x70/0x80 <EOI> [<ffffffff810984a4>] ? lock_release+0xe4/0x2b0 [<ffffffff815f98f3>] _raw_spin_unlock+0x23/0x60 [<ffffffff812a07a7>] T.562+0xf7/0x170 [<ffffffff812a0e71>] debugfs_create_file+0xf1/0x270 [<ffffffff810e96c9>] trace_create_file+0x19/0x50 [<ffffffff81af7b3c>] tracer_init_debugfs+0x2bd/0x3c0 [<ffffffff810e96c9>] ? trace_create_file+0x19/0x50 [<ffffffff81af787f>] ? clear_boot_tracer+0x2d/0x2d [<ffffffff810001d3>] do_one_initcall+0x43/0x180 [<ffffffff81adf637>] kernel_init+0xd0/0x156 [<ffffffff815fc574>] kernel_thread_helper+0x4/0x10 [<ffffffff8106fdb8>] ? finish_task_switch+0x88/0xf0 [<ffffffff815f99eb>] ? _raw_spin_unlock_irq+0x3b/0x70 [<ffffffff815f9f61>] ? retint_restore_args+0xe/0xe [<ffffffff81adf567>] ? parse_early_options+0x20/0x20 [<ffffffff815fc570>] ? gs_change+0xb/0xb
Seems due to commit [0b005cf5: sched, nohz: Implement sched group, domain aware nohz idle load balancing]
Thanks,
Yong
Quoted 42 lines · Yong Zhang
===============================
[ INFO: suspicious RCU usage. ]
-------------------------------
/build/linux/kernel/sched/fair.c:5091 suspiciousrcu_dereference_check()usage!other info that might help us debug this:
rcu_scheduler_active= 1,debug_locks= 1
1 lock held by swapper/0/1:
#0: (&sb->s_type->i_mutex_key#2){+.+.+.}, at: [<ffffffff812a0e0c>]debugfs_create_file+0x8c/0x270stack backtrace: Pid: 1, comm: swapper/0 Not tainted 3.2.0-rc1-00339-gcd490c5 #14 Call Trace: <IRQ> [<ffffffff815f9968>] ? _raw_spin_unlock_irqrestore+0x38/0x80 [<ffffffff8109407f>] lockdep_rcu_suspicious+0xbf/0xe0 [<ffffffff8107dd48>] trigger_load_balance+0x5b8/0x5c0 [<ffffffff81070544>] scheduler_tick+0x104/0x160 [<ffffffff8104a1ce>] update_process_times+0x6e/0x90 [<ffffffff8108e32c>] tick_periodic+0x2c/0x70 [<ffffffff8108e394>] tick_handle_periodic+0x24/0x80 [<ffffffff812a07a7>] ? T.562+0xf7/0x170 [<ffffffff815fce56>] smp_apic_timer_interrupt+0x66/0x98 [<ffffffff815fb2f0>] apic_timer_interrupt+0x70/0x80 <EOI> [<ffffffff810984a4>] ? lock_release+0xe4/0x2b0 [<ffffffff815f98f3>] _raw_spin_unlock+0x23/0x60 [<ffffffff812a07a7>] T.562+0xf7/0x170 [<ffffffff812a0e71>] debugfs_create_file+0xf1/0x270 [<ffffffff810e96c9>] trace_create_file+0x19/0x50 [<ffffffff81af7b3c>] tracer_init_debugfs+0x2bd/0x3c0 [<ffffffff810e96c9>] ? trace_create_file+0x19/0x50 [<ffffffff81af787f>] ? clear_boot_tracer+0x2d/0x2d [<ffffffff810001d3>] do_one_initcall+0x43/0x180 [<ffffffff81adf637>] kernel_init+0xd0/0x156 [<ffffffff815fc574>] kernel_thread_helper+0x4/0x10 [<ffffffff8106fdb8>] ? finish_task_switch+0x88/0xf0 [<ffffffff815f99eb>] ? _raw_spin_unlock_irq+0x3b/0x70 [<ffffffff815f9f61>] ? retint_restore_args+0xe/0xe [<ffffffff81adf567>] ? parse_early_options+0x20/0x20 [<ffffffff815fc570>] ? gs_change+0xb/0xb
Quoted 2 lines
Seems due to commit [
0b005cf5: sched, nohz: Implement sched group, domain aware nohz idle load balancing]
I think something like the below should suffice, the sd argument only lives inside the for_each_domain() so wrapping the whole block should suffice.
--- kernel/sched/fair.c | 9 +++++++-- 1 files changed, 7 insertions(+), 2 deletions(-)
kernel/sched/fair.c +7 -2
@@ -5088,23 +5088,28 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)if (rq->nr_running >=2 ) goto need_kick; +rcu_read_lock ();for_each_domain (cpu, sd) {struct sched_group *sg = sd->groups;struct sched_group_power *sgp = sg->sgp;int nr_busy =atomic_read (&sgp->nr_busy_cpus);if (sd->flags &SD_SHARE_PKG_RESOURCES && nr_busy >1 ) - goto need_kick; + goto need_kick_unlock;if (sd->flags &SD_ASYM_PACKING && nr_busy != sg->group_weight && (cpumask_first_and (nohz.idle_cpus_mask,sched_domain_span (sd)) < cpu)) - goto need_kick; + goto need_kick_unlock;if (!(sd->flags & (SD_SHARE_PKG_RESOURCES |SD_ASYM_PACKING )))break ; } +rcu_read_unlock ();return 0 ; + +need_kick_unlock: +rcu_read_unlock (); need_kick:return 1 ; }
Peter Zijlstra
maintainerI made that
---
Subject: sched, nohz: Fix missing RCU read lock
From: Peter Zijlstra <[email protected]>
Date: Wed Dec 07 14:28:44 CET 2011
Yong Zhang reported:
Quoted 2 lines
[ INFO: suspicious RCU usage. ]
kernel/sched/fair.c:5091suspiciousrcu_dereference_check()usage!
This is due to the sched_domain stuff being RCU protected and commit 0b005cf5 ("sched, nohz: Implement sched group, domain aware nohz idle load balancing") overlooking this fact.
The sd variable only lives inside the for_each_domain() block, so we only need to wrap that.
---
kernel/sched/fair.c +7 -2
@@ -5088,23 +5088,28 @@ static inline int nohz_kick_needed(strucif (rq->nr_running >=2 ) goto need_kick; +rcu_read_lock ();for_each_domain (cpu, sd) {struct sched_group *sg = sd->groups;struct sched_group_power *sgp = sg->sgp;int nr_busy =atomic_read (&sgp->nr_busy_cpus);if (sd->flags &SD_SHARE_PKG_RESOURCES && nr_busy >1 ) - goto need_kick; + goto need_kick_unlock;if (sd->flags &SD_ASYM_PACKING && nr_busy != sg->group_weight && (cpumask_first_and (nohz.idle_cpus_mask,sched_domain_span (sd)) < cpu)) - goto need_kick; + goto need_kick_unlock;if (!(sd->flags & (SD_SHARE_PKG_RESOURCES |SD_ASYM_PACKING )))break ; } +rcu_read_unlock ();return 0 ; + +need_kick_unlock: +rcu_read_unlock (); need_kick:return 1 ; }
Yong Zhang
Tested-byQuoted 12 lines · Peter Zijlstra
I made that
---
Subject: sched, nohz: Fix missing RCU read lock
From: Peter Zijlstra <[email protected]>
Date: Wed Dec 07 14:28:44 CET 2011Yong Zhang reported:
Quoted 2 lines
[ INFO: suspicious RCU usage. ]
kernel/sched/fair.c:5091suspiciousrcu_dereference_check()usage!
Quoted 7 lines
This is due to the
sched_domainstuff being RCU protected and commit0b005cf5("sched, nohz: Implement sched group, domain aware nohz idle load balancing") overlooking this fact.The sd variable only lives inside the
for_each_domain()block, so we only need to wrap that.
Works for me.
Thanks,
Yong
Quoted 46 lines
Cc Suresh Siddha <[email protected]>Reported-by Yong Zhang <[email protected]>Signed-off-by Peter Zijlstra <[email protected]>---
Index:linux-2.6/kernel/sched/fair.c
===================================================================kernel/sched/fair.c +7
-3@@ -5088,23 +5088,28 @@ static inline int nohz_kick_needed(strucif (rq->nr_running >=2 ) goto need_kick; +rcu_read_lock ();for_each_domain (cpu, sd) {struct sched_group *sg = sd->groups;struct sched_group_power *sgp = sg->sgp;int nr_busy =atomic_read (&sgp->nr_busy_cpus);if (sd->flags &SD_SHARE_PKG_RESOURCES && nr_busy >1 ) - goto need_kick; + goto need_kick_unlock;if (sd->flags &SD_ASYM_PACKING && nr_busy != sg->group_weight && (cpumask_first_and (nohz.idle_cpus_mask,sched_domain_span (sd)) < cpu)) - goto need_kick; + goto need_kick_unlock;if (!(sd->flags & (SD_SHARE_PKG_RESOURCES |SD_ASYM_PACKING )))break ; } +rcu_read_unlock ();return 0 ; + +need_kick_unlock: +rcu_read_unlock (); need_kick:return 1 ; } --To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Signature · 1 line
Only stand for myself
tip-bot for Peter Zijlstra
maintainer[tip:sched/core] sched, nohz: Fix missing RCU read lock
In reply to Peter ZijlstraCommit-ID: 067491b7313c41f49607fce782d29344d1472587 Gitweb: http://git.kernel.org/tip/067491b7313c41f49607fce782d29344d1472587 Author: Peter Zijlstra <[email protected]> AuthorDate: Wed, 7 Dec 2011 14:32:08 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Thu, 8 Dec 2011 05:45:48 +0100
sched, nohz: Fix missing RCU read lock
Yong Zhang reported:
Quoted 2 lines
[ INFO: suspicious RCU usage. ]
kernel/sched/fair.c:5091suspiciousrcu_dereference_check()usage!
This is due to the sched_domain stuff being RCU protected and commit 0b005cf5 ("sched, nohz: Implement sched group, domain aware nohz idle load balancing") overlooking this fact.
The sd variable only lives inside the for_each_domain() block, so we only need to wrap that.
--- kernel/sched/fair.c | 9 +++++++-- 1 files changed, 7 insertions(+), 2 deletions(-)
kernel/sched/fair.c +7 -2
@@ -5088,23 +5088,28 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)if (rq->nr_running >=2 ) goto need_kick; +rcu_read_lock ();for_each_domain (cpu, sd) {struct sched_group *sg = sd->groups;struct sched_group_power *sgp = sg->sgp;int nr_busy =atomic_read (&sgp->nr_busy_cpus);if (sd->flags &SD_SHARE_PKG_RESOURCES && nr_busy >1 ) - goto need_kick; + goto need_kick_unlock;if (sd->flags &SD_ASYM_PACKING && nr_busy != sg->group_weight && (cpumask_first_and (nohz.idle_cpus_mask,sched_domain_span (sd)) < cpu)) - goto need_kick; + goto need_kick_unlock;if (!(sd->flags & (SD_SHARE_PKG_RESOURCES |SD_ASYM_PACKING )))break ; } +rcu_read_unlock ();return 0 ; + +need_kick_unlock: +rcu_read_unlock (); need_kick:return 1 ; }