From 4b402210486c6414fe5fbfd85934a0a22da56b04 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 16 Apr 2010 23:20:00 +0200 Subject: [PATCH 1/3] mutex: Don't spin when the owner CPU is offline or other weird cases Due to recent load-balancer changes that delay the task migration to the next wakeup, the adaptive mutex spinning ends up in a live lock when the owner's CPU gets offlined because the cpu_online() check lives before the owner running check. This patch changes mutex_spin_on_owner() to return 0 (don't spin) in any case where we aren't sure about the owner struct validity or CPU number, and if the said CPU is offline. There is no point going back & re-evaluate spinning in corner cases like that, let's just go to sleep. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Peter Zijlstra LKML-Reference: <1271212509.13059.135.camel@pasglop> Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 6af210a7de70..de0bd26e520a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3780,7 +3780,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) * the mutex owner just released it and exited. */ if (probe_kernel_address(&owner->cpu, cpu)) - goto out; + return 0; #else cpu = owner->cpu; #endif @@ -3790,14 +3790,14 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) * the cpu field may no longer be valid. */ if (cpu >= nr_cpumask_bits) - goto out; + return 0; /* * We need to validate that we can do a * get_cpu() and that we have the percpu area. */ if (!cpu_online(cpu)) - goto out; + return 0; rq = cpu_rq(cpu); @@ -3816,7 +3816,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) cpu_relax(); } -out: + return 1; } #endif From 8b08ca52f5942c21564bbb90ccfb61053f2c26a1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 21 Apr 2010 13:02:07 -0700 Subject: [PATCH 2/3] rcu: Fix RCU lockdep splat in set_task_cpu on fork path Add an RCU read-side critical section to suppress this false positive. Located-by: Eric Paris Signed-off-by: Peter Zijlstra Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: eric.dumazet@gmail.com LKML-Reference: <1271880131-3951-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/kernel/sched.c b/kernel/sched.c index de0bd26e520a..3c2a54f70ffe 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -323,6 +323,15 @@ static inline struct task_group *task_group(struct task_struct *p) /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { + /* + * Strictly speaking this rcu_read_lock() is not needed since the + * task_group is tied to the cgroup, which in turn can never go away + * as long as there are tasks attached to it. + * + * However since task_group() uses task_subsys_state() which is an + * rcu_dereference() user, this quiets CONFIG_PROVE_RCU. + */ + rcu_read_lock(); #ifdef CONFIG_FAIR_GROUP_SCHED p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; p->se.parent = task_group(p)->se[cpu]; @@ -332,6 +341,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) p->rt.rt_rq = task_group(p)->rt_rq[cpu]; p->rt.parent = task_group(p)->rt_se[cpu]; #endif + rcu_read_unlock(); } #else From 8b46f880841aac821af8efa6581bb0e46b8b9845 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 21 Apr 2010 13:02:08 -0700 Subject: [PATCH 3/3] rcu: Fix RCU lockdep splat on freezer_fork path Add an RCU read-side critical section to suppress this false positive. Located-by: Eric Paris Signed-off-by: Paul E. McKenney Acked-by: Li Zefan Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: eric.dumazet@gmail.com LKML-Reference: <1271880131-3951-2-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/cgroup_freezer.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index da5e13975531..e5c0244962b0 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -205,9 +205,12 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) * No lock is needed, since the task isn't on tasklist yet, * so it can't be moved to another cgroup, which means the * freezer won't be removed and will be valid during this - * function call. + * function call. Nevertheless, apply RCU read-side critical + * section to suppress RCU lockdep false positives. */ + rcu_read_lock(); freezer = task_freezer(task); + rcu_read_unlock(); /* * The root cgroup is non-freezable, so we can skip the