[GIT PULL] RCU fix

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-urgent-for-linus

 Thanks,

	Ingo

------------------>
Peter Zijlstra (1):
      rcu: Cure load woes


 kernel/rcutree.c        |   54 ++++++++++++++++++++++++++++++++++++++++-------
 kernel/rcutree_plugin.h |   11 ++++++++-
 2 files changed, 56 insertions(+), 9 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 77a7671..89419ff 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1648,7 +1648,6 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	kthread_bind(t, cpu);
-	set_task_state(t, TASK_INTERRUPTIBLE);
 	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
 	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
 	per_cpu(rcu_cpu_kthread_task, cpu) = t;
@@ -1756,7 +1755,6 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
 		if (IS_ERR(t))
 			return PTR_ERR(t);
 		raw_spin_lock_irqsave(&rnp->lock, flags);
-		set_task_state(t, TASK_INTERRUPTIBLE);
 		rnp->node_kthread_task = t;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		sp.sched_priority = 99;
@@ -1765,6 +1763,8 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
 	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
 }
 
+static void rcu_wake_one_boost_kthread(struct rcu_node *rnp);
+
 /*
  * Spawn all kthreads -- called as soon as the scheduler is running.
  */
@@ -1772,18 +1772,30 @@ static int __init rcu_spawn_kthreads(void)
 {
 	int cpu;
 	struct rcu_node *rnp;
+	struct task_struct *t;
 
 	rcu_kthreads_spawnable = 1;
 	for_each_possible_cpu(cpu) {
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
-		if (cpu_online(cpu))
+		if (cpu_online(cpu)) {
 			(void)rcu_spawn_one_cpu_kthread(cpu);
+			t = per_cpu(rcu_cpu_kthread_task, cpu);
+			if (t)
+				wake_up_process(t);
+		}
 	}
 	rnp = rcu_get_root(rcu_state);
 	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+	if (rnp->node_kthread_task)
+		wake_up_process(rnp->node_kthread_task);
 	if (NUM_RCU_NODES > 1) {
-		rcu_for_each_leaf_node(rcu_state, rnp)
+		rcu_for_each_leaf_node(rcu_state, rnp) {
 			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+			t = rnp->node_kthread_task;
+			if (t)
+				wake_up_process(t);
+			rcu_wake_one_boost_kthread(rnp);
+		}
 	}
 	return 0;
 }
@@ -2188,14 +2200,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
-static void __cpuinit rcu_online_cpu(int cpu)
+static void __cpuinit rcu_prepare_cpu(int cpu)
 {
 	rcu_init_percpu_data(cpu, &rcu_sched_state, 0);
 	rcu_init_percpu_data(cpu, &rcu_bh_state, 0);
 	rcu_preempt_init_percpu_data(cpu);
 }
 
-static void __cpuinit rcu_online_kthreads(int cpu)
+static void __cpuinit rcu_prepare_kthreads(int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
@@ -2209,6 +2221,31 @@ static void __cpuinit rcu_online_kthreads(int cpu)
 }
 
 /*
+ * kthread_create() creates threads in TASK_UNINTERRUPTIBLE state,
+ * but the RCU threads are woken on demand, and if demand is low this
+ * could be a while triggering the hung task watchdog.
+ *
+ * In order to avoid this, poke all tasks once the CPU is fully
+ * up and running.
+ */
+static void __cpuinit rcu_online_kthreads(int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;
+	struct task_struct *t;
+
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t)
+		wake_up_process(t);
+
+	t = rnp->node_kthread_task;
+	if (t)
+		wake_up_process(t);
+
+	rcu_wake_one_boost_kthread(rnp);
+}
+
+/*
  * Handle CPU online/offline notification events.
  */
 static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
@@ -2221,10 +2258,11 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		rcu_online_cpu(cpu);
-		rcu_online_kthreads(cpu);
+		rcu_prepare_cpu(cpu);
+		rcu_prepare_kthreads(cpu);
 		break;
 	case CPU_ONLINE:
+		rcu_online_kthreads(cpu);
 	case CPU_DOWN_FAILED:
 		rcu_node_kthread_setaffinity(rnp, -1);
 		rcu_cpu_kthread_setrt(cpu, 1);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index a767b7d..c8bff30 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1295,7 +1295,6 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	set_task_state(t, TASK_INTERRUPTIBLE);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
@@ -1303,6 +1302,12 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	return 0;
 }
 
+static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+{
+	if (rnp->boost_kthread_task)
+		wake_up_process(rnp->boost_kthread_task);
+}
+
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
@@ -1326,6 +1331,10 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	return 0;
 }
 
+static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+{
+}
+
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 #ifndef CONFIG_SMP

Re: [GIT PULL] RCU fix

[Linus Torvalds]

On Wed, Jun 1, 2011 at 1:27 AM, Ingo Molnar <mingo@elte.hu> wrote:
>
> Please pull the latest core-urgent-for-linus git tree from:
>
>   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-urgent-for-linus

So remind me again why RCU switched to the stupid threads? It caused
problems for rcutiny, it now causes silly problems for rcutree. Why do
it? It's just extra complexity and no real advantage afaik.

                 Linus

Re: [GIT PULL] RCU fix

[Paul E. McKenney]

On Wed, Jun 01, 2011 at 02:05:21AM +0900, Linus Torvalds wrote:
> On Wed, Jun 1, 2011 at 1:27 AM, Ingo Molnar <mingo@elte.hu> wrote:
> >
> > Please pull the latest core-urgent-for-linus git tree from:
> >
> >   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-urgent-for-linus
> 
> So remind me again why RCU switched to the stupid threads? It caused
> problems for rcutiny, it now causes silly problems for rcutree. Why do
> it? It's just extra complexity and no real advantage afaik.

The reason for the switch is to allow threads blocked in TREE_PREEMPT_RCU
and TINY_PREEMPT_RCU RCU read-side critical sections to have their
priority boosted in order to avoid OOM.  People have made these OOMs
happen, so this is not longer just a theoretical concern.

							Thanx, Paul

Re: [GIT PULL] RCU fix

[Linus Torvalds]

On Wed, Jun 1, 2011 at 2:44 AM, Paul E. McKenney
<paulmck@linux.vnet.ibm.com> wrote:
>
> The reason for the switch is to allow threads blocked in TREE_PREEMPT_RCU
> and TINY_PREEMPT_RCU RCU read-side critical sections to have their
> priority boosted in order to avoid OOM.  People have made these OOMs
> happen, so this is not longer just a theoretical concern.

Quite frankly, that doesn't make much sense.

First off, the default for priority boosting is off (and you cannot
even select it unless you have RT_MUTEX and PREEMPT_RCU), so why the
heck do we still use the threads even when we don't support the
boosting at all?

Secondly, if a process is in danger of exhausting the RCU resources,
and it is preemptable, why doesn't the rcu_read_unlock() logic just
try to force a reschedule and thus an rcu idle period? Using processes
and process priorities for this seems to be just stupid.

I dunno. After RCU_TINY showed how fragile it was to use kernel
threads for this, and after this subtle issue just re-inforced that
conclusion, I just cannot begin to believe that using a thread was the
right thing to do. It just seems stupid.

                         Linus

Re: [GIT PULL] RCU fix

[Paul E. McKenney]

On Wed, Jun 01, 2011 at 02:52:59AM +0900, Linus Torvalds wrote:
> On Wed, Jun 1, 2011 at 2:44 AM, Paul E. McKenney
> <paulmck@linux.vnet.ibm.com> wrote:
> >
> > The reason for the switch is to allow threads blocked in TREE_PREEMPT_RCU
> > and TINY_PREEMPT_RCU RCU read-side critical sections to have their
> > priority boosted in order to avoid OOM.  People have made these OOMs
> > happen, so this is not longer just a theoretical concern.
> 
> Quite frankly, that doesn't make much sense.
> 
> First off, the default for priority boosting is off (and you cannot
> even select it unless you have RT_MUTEX and PREEMPT_RCU), so why the
> heck do we still use the threads even when we don't support the
> boosting at all?

I considered using softirq in the !RCU_BOOST case, but that makes the
code larger and just makes the failure cases we saw less likely.  And
some of the failure cases could be made to happen from userspace with
real-time threads, not just from RCU priority boosting.

But I could of course switch to the dual softirq/kthread approach
if needed.

> Secondly, if a process is in danger of exhausting the RCU resources,
> and it is preemptable, why doesn't the rcu_read_unlock() logic just
> try to force a reschedule and thus an rcu idle period? Using processes
> and process priorities for this seems to be just stupid.

This approach does work (and is used) for TINY_RCU and TREE_RCU,
but it unfortunately simply does not work for TINY_PREEMPT_RCU and
TREE_PREEMPT_RCU.  The reason for this is that for the preemptible
variants of RCU, a reschedule in not guaranteed to be an RCU quiescent
state.  Which is why RCU_BOOST depends on PREEMPT_RCU (which is either
TINY_PREEMPT_RCU or TREE_PREEMPT_RCU.

> I dunno. After RCU_TINY showed how fragile it was to use kernel
> threads for this, and after this subtle issue just re-inforced that
> conclusion, I just cannot begin to believe that using a thread was the
> right thing to do. It just seems stupid.

Again, at least some of these were things that could be made to happen
from userspace with the standard APIs, so those at least did need to
be fixed.

							Thanx, Paul

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

   # HEAD: 31409c97640ff5f1a49e34ac7f3c82097bf57bec Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent

Fix a false positive warning.

 Thanks,

	Ingo

------------------>
Paul E. McKenney (1):
      security/device_cgroup: Fix RCU_LOCKDEP_WARN() condition


 security/device_cgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 73455089feef..03c1652c9a1f 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -401,7 +401,7 @@ static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
 	bool match = false;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&
-			 lockdep_is_held(&devcgroup_mutex),
+			 !lockdep_is_held(&devcgroup_mutex),
 			 "device_cgroup:verify_new_ex called without proper synchronization");
 
 	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

   # HEAD: cb0f3f320d64831afb39940863c5927d6af25514 Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent

An RCU Kconfig fix that eliminates an annoying interactive kconfig 
question for CONFIG_RCU_TORTURE_TEST_SLOW_INIT.

 Thanks,

	Ingo

------------------>
Paul E. McKenney (1):
      rcu: Control grace-period delays directly from value


 kernel/rcu/tree.c | 16 +++++++++-------
 lib/Kconfig.debug |  1 +
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 233165da782f..8cf7304b2867 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -162,11 +162,14 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
 module_param(kthread_prio, int, 0644);
 
-/* Delay in jiffies for grace-period initialization delays. */
-static int gp_init_delay = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT)
-				? CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY
-				: 0;
+/* Delay in jiffies for grace-period initialization delays, debug only. */
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
 module_param(gp_init_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
+static const int gp_init_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
+#define PER_RCU_NODE_PERIOD 10	/* Number of grace periods between delays. */
 
 /*
  * Track the rcutorture test sequence number and the update version
@@ -1843,9 +1846,8 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
 		ACCESS_ONCE(rsp->gp_activity) = jiffies;
-		if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) &&
-		    gp_init_delay > 0 &&
-		    !(rsp->gpnum % (rcu_num_nodes * 10)))
+		if (gp_init_delay > 0 &&
+		    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD)))
 			schedule_timeout_uninterruptible(gp_init_delay);
 	}
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 93967e634a1e..7815ddd5ae56 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1281,6 +1281,7 @@ config RCU_TORTURE_TEST_SLOW_INIT_DELAY
 	int "How much to slow down RCU grace-period initialization"
 	range 0 5
 	default 3
+	depends on RCU_TORTURE_TEST_SLOW_INIT
 	help
 	  This option specifies the number of jiffies to wait between
 	  each rcu_node structure initialization.

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

   # HEAD: 3b3336d4fed58ea5a019a8a1d00fa741be492716 Merge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent

Fix a bug that caused an RCU warning splat.

 Thanks,

	Ingo

------------------>
Paul E. McKenney (1):
      rcu: Clear need_qs flag to prevent splat


 kernel/rcu/tree_plugin.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 2e850a51bb8f..bca28b00f7e6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -327,6 +327,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	special = t->rcu_read_unlock_special;
 	if (special.b.need_qs) {
 		rcu_preempt_qs();
+		t->rcu_read_unlock_special.b.need_qs = false;
 		if (!t->rcu_read_unlock_special.s) {
 			local_irq_restore(flags);
 			return;

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

   # HEAD: 651bc1a474ad5f3a94587117cf509d7fa9247f69 Merge branch 'rcu/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent

A boot hang fix for the offloaded callback RCU model 
(RCU_NOCB_CPU=y && (TREE_CPU=y || TREE_PREEMPT_RC))
in certain bootup scenarios.

 Thanks,

	Ingo

------------------>
Pranith Kumar (1):
      rcu: Make nocb leader kthreads process pending callbacks after spawning


 kernel/rcu/tree.h        |  2 +-
 kernel/rcu/tree_plugin.h | 22 +++++++++++-----------
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 71e64c718f75..6a86eb7bac45 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -358,7 +358,7 @@ struct rcu_data {
 	struct rcu_head **nocb_gp_tail;
 	long nocb_gp_count;
 	long nocb_gp_count_lazy;
-	bool nocb_leader_wake;		/* Is the nocb leader thread awake? */
+	bool nocb_leader_sleep;		/* Is the nocb leader thread asleep? */
 	struct rcu_data *nocb_next_follower;
 					/* Next follower in wakeup chain. */
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 00dc411e9676..a7997e272564 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2074,9 +2074,9 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 
 	if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
 		return;
-	if (!ACCESS_ONCE(rdp_leader->nocb_leader_wake) || force) {
+	if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
 		/* Prior xchg orders against prior callback enqueue. */
-		ACCESS_ONCE(rdp_leader->nocb_leader_wake) = true;
+		ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
 		wake_up(&rdp_leader->nocb_wq);
 	}
 }
@@ -2253,7 +2253,7 @@ static void nocb_leader_wait(struct rcu_data *my_rdp)
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
 		wait_event_interruptible(my_rdp->nocb_wq,
-					 ACCESS_ONCE(my_rdp->nocb_leader_wake));
+				!ACCESS_ONCE(my_rdp->nocb_leader_sleep));
 		/* Memory barrier handled by smp_mb() calls below and repoll. */
 	} else if (firsttime) {
 		firsttime = false; /* Don't drown trace log with "Poll"! */
@@ -2292,12 +2292,12 @@ static void nocb_leader_wait(struct rcu_data *my_rdp)
 		schedule_timeout_interruptible(1);
 
 		/* Rescan in case we were a victim of memory ordering. */
-		my_rdp->nocb_leader_wake = false;
-		smp_mb();  /* Ensure _wake false before scan. */
+		my_rdp->nocb_leader_sleep = true;
+		smp_mb();  /* Ensure _sleep true before scan. */
 		for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
 			if (ACCESS_ONCE(rdp->nocb_head)) {
 				/* Found CB, so short-circuit next wait. */
-				my_rdp->nocb_leader_wake = true;
+				my_rdp->nocb_leader_sleep = false;
 				break;
 			}
 		goto wait_again;
@@ -2307,17 +2307,17 @@ static void nocb_leader_wait(struct rcu_data *my_rdp)
 	rcu_nocb_wait_gp(my_rdp);
 
 	/*
-	 * We left ->nocb_leader_wake set to reduce cache thrashing.
-	 * We clear it now, but recheck for new callbacks while
+	 * We left ->nocb_leader_sleep unset to reduce cache thrashing.
+	 * We set it now, but recheck for new callbacks while
 	 * traversing our follower list.
 	 */
-	my_rdp->nocb_leader_wake = false;
-	smp_mb(); /* Ensure _wake false before scan of ->nocb_head. */
+	my_rdp->nocb_leader_sleep = true;
+	smp_mb(); /* Ensure _sleep true before scan of ->nocb_head. */
 
 	/* Each pass through the following loop wakes a follower, if needed. */
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
 		if (ACCESS_ONCE(rdp->nocb_head))
-			my_rdp->nocb_leader_wake = true; /* No need to wait. */
+			my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/
 		if (!rdp->nocb_gp_head)
 			continue; /* No CBs, so no need to wake follower. */
 

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

   HEAD: 745040347d7e8e7b47e3790de76423d9eab474eb Merge branch 'rcu/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent

Fix leaking RCU extended quiescent state, which might trigger 
warnings and mess up the extended quiescent state tracking logic 
into thinking that we are in "RCU user mode" while we aren't.

 Thanks,

	Ingo

------------------>
Frederic Weisbecker (1):
      rcu: Fix unrecovered RCU user mode in syscall_trace_leave()


 arch/x86/kernel/ptrace.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index b00b33a..eff5b8c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1511,6 +1511,13 @@ void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
 
+	/*
+	 * We may come here right after calling schedule_user()
+	 * or do_notify_resume(), in which case we can be in RCU
+	 * user mode.
+	 */
+	rcu_user_exit();
+
 	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

   HEAD: 40b3c43f042c2ba8915aff5c63708207ed7639cb Merge branch 'rcu/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent

 Thanks,

	Ingo

------------------>
Paul E. McKenney (1):
      Revert "rcu: Move PREEMPT_RCU preemption to switch_to() invocation"


 arch/um/drivers/mconsole_kern.c |    1 -
 include/linux/rcupdate.h        |    1 -
 include/linux/rcutiny.h         |    6 ++++++
 include/linux/sched.h           |   10 ----------
 kernel/rcutree.c                |    1 +
 kernel/rcutree.h                |    1 +
 kernel/rcutree_plugin.h         |   14 +++++++++++---
 kernel/sched/core.c             |    1 -
 8 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 88e466b..43b39d6 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -705,7 +705,6 @@ static void stack_proc(void *arg)
 	struct task_struct *from = current, *to = arg;
 
 	to->thread.saved_task = from;
-	rcu_switch_from(from);
 	switch_to(from, to, from);
 }
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 26d1a47..9cac722 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -184,7 +184,6 @@ static inline int rcu_preempt_depth(void)
 /* Internal to kernel */
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
-extern void rcu_preempt_note_context_switch(void);
 extern void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
 extern void rcu_idle_enter(void);
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 854dc4c..4e56a9c 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -87,6 +87,10 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 
 #ifdef CONFIG_TINY_RCU
 
+static inline void rcu_preempt_note_context_switch(void)
+{
+}
+
 static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 {
 	*delta_jiffies = ULONG_MAX;
@@ -95,6 +99,7 @@ static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 
 #else /* #ifdef CONFIG_TINY_RCU */
 
+void rcu_preempt_note_context_switch(void);
 int rcu_preempt_needs_cpu(void);
 
 static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
@@ -108,6 +113,7 @@ static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 static inline void rcu_note_context_switch(int cpu)
 {
 	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch();
 }
 
 /*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4059c0f..06a4c5f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1871,22 +1871,12 @@ static inline void rcu_copy_process(struct task_struct *p)
 	INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
-static inline void rcu_switch_from(struct task_struct *prev)
-{
-	if (prev->rcu_read_lock_nesting != 0)
-		rcu_preempt_note_context_switch();
-}
-
 #else
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
 }
 
-static inline void rcu_switch_from(struct task_struct *prev)
-{
-}
-
 #endif
 
 #ifdef CONFIG_SMP
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 38ecdda..4b97bba 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -201,6 +201,7 @@ void rcu_note_context_switch(int cpu)
 {
 	trace_rcu_utilization("Start context switch");
 	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch(cpu);
 	trace_rcu_utilization("End context switch");
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index ea05649..19b61ac 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -444,6 +444,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
+static void rcu_preempt_note_context_switch(int cpu);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 5271a02..3e48994 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -153,7 +153,7 @@ static void rcu_preempt_qs(int cpu)
  *
  * Caller must disable preemption.
  */
-void rcu_preempt_note_context_switch(void)
+static void rcu_preempt_note_context_switch(int cpu)
 {
 	struct task_struct *t = current;
 	unsigned long flags;
@@ -164,7 +164,7 @@ void rcu_preempt_note_context_switch(void)
 	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = __this_cpu_ptr(rcu_preempt_state.rda);
+		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -228,7 +228,7 @@ void rcu_preempt_note_context_switch(void)
 	 * means that we continue to block the current grace period.
 	 */
 	local_irq_save(flags);
-	rcu_preempt_qs(smp_processor_id());
+	rcu_preempt_qs(cpu);
 	local_irq_restore(flags);
 }
 
@@ -1002,6 +1002,14 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
+ * Because preemptible RCU does not exist, we never have to check for
+ * CPUs being in quiescent states.
+ */
+static void rcu_preempt_note_context_switch(int cpu)
+{
+}
+
+/*
  * Because preemptible RCU does not exist, there are never any preempted
  * RCU readers.
  */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d5594a4..eaead2d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2081,7 +2081,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
 #endif
 
 	/* Here we just switch the register state and the stack. */
-	rcu_switch_from(prev);
 	switch_to(prev, next, prev);
 
 	barrier();

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

   HEAD: b41772abebc27c61dd578b76da99aa5240b4c99a rcu: Stop rcu_do_batch() from multiplexing the "count" variable

 Thanks,

	Ingo

------------------>
Paul E. McKenney (1):
      rcu: Stop rcu_do_batch() from multiplexing the "count" variable


 kernel/rcutree.c |   14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 3b0f133..38ecdda 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1530,7 +1530,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 	struct rcu_head *next, *list, **tail;
-	int bl, count, count_lazy;
+	int bl, count, count_lazy, i;
 
 	/* If no callbacks are ready, just return.*/
 	if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
@@ -1553,9 +1553,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
 	*rdp->nxttail[RCU_DONE_TAIL] = NULL;
 	tail = rdp->nxttail[RCU_DONE_TAIL];
-	for (count = RCU_NEXT_SIZE - 1; count >= 0; count--)
-		if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL])
-			rdp->nxttail[count] = &rdp->nxtlist;
+	for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
+		if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
+			rdp->nxttail[i] = &rdp->nxtlist;
 	local_irq_restore(flags);
 
 	/* Invoke callbacks. */
@@ -1583,9 +1583,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	if (list != NULL) {
 		*tail = rdp->nxtlist;
 		rdp->nxtlist = list;
-		for (count = 0; count < RCU_NEXT_SIZE; count++)
-			if (&rdp->nxtlist == rdp->nxttail[count])
-				rdp->nxttail[count] = tail;
+		for (i = 0; i < RCU_NEXT_SIZE; i++)
+			if (&rdp->nxtlist == rdp->nxttail[i])
+				rdp->nxttail[i] = tail;
 			else
 				break;
 	}

[GIT PULL] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

   HEAD: 4d8cd7e780aab781e40ea3178bdbae089f5125a0 Merge branch 'rcu/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent

 Thanks,

	Ingo

------------------>
Paul E. McKenney (1):
      rcu: Permit call_rcu() from CPU_DYING notifiers


 kernel/rcutree.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1050d6d..d0c5baf 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1820,7 +1820,6 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	 * a quiescent state betweentimes.
 	 */
 	local_irq_save(flags);
-	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
 	rdp = this_cpu_ptr(rsp->rda);
 
 	/* Add the callback to our list. */

[git pull] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

 Thanks,

	Ingo

------------------>
Eric Dumazet (1):
      rcu: increment quiescent state counter in ksoftirqd()


 kernel/softirq.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de..9041ea7 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -626,6 +626,7 @@ static int ksoftirqd(void * __bind_cpu)
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
+			rcu_qsctr_inc((long)__bind_cpu);
 		}
 		preempt_enable();
 		set_current_state(TASK_INTERRUPTIBLE);

[git pull] RCU fix

[Ingo Molnar]

Linus,

Please pull the latest core-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

This fixes a long-existent RCU / scheduler interaction bug 
resulting in long bootup delays (sometimes hangs) that has 
become more prominent in .29 and which has been tracked down 
recently.

I didnt like the fix of adding yet another boot state flag but 
neither of the alternatives looked too appealing either:

    http://lkml.org/lkml/2009/2/25/321

So i went with this one.

But we can clean up this code if anyone has a good idea how to 
do it better. The main source of the fragility is the fact that 
we run the 'idle' thread as the init task for quite some time. 
But we cannot really create a real init task until we have a 
number of core kernel facilities up and running.

 Thanks,

	Ingo

------------------>
Paul E. McKenney (1):
      rcu: Teach RCU that idle task is not quiscent state at boot


 include/linux/rcuclassic.h |    6 ++++++
 include/linux/rcupdate.h   |    4 ++++
 include/linux/rcupreempt.h |   15 +++++++++++++++
 include/linux/rcutree.h    |    6 ++++++
 init/main.c                |    3 ++-
 kernel/rcuclassic.c        |    4 ++--
 kernel/rcupdate.c          |   12 ++++++++++++
 kernel/rcupreempt.c        |    3 +++
 kernel/rcutree.c           |    4 ++--
 9 files changed, 52 insertions(+), 5 deletions(-)

diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index f3f697d..80044a4 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -181,4 +181,10 @@ extern long rcu_batches_completed_bh(void);
 #define rcu_enter_nohz()	do { } while (0)
 #define rcu_exit_nohz()		do { } while (0)
 
+/* A context switch is a grace period for rcuclassic. */
+static inline int rcu_blocking_is_gp(void)
+{
+	return num_online_cpus() == 1;
+}
+
 #endif /* __LINUX_RCUCLASSIC_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 921340a..528343e 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -52,6 +52,9 @@ struct rcu_head {
 	void (*func)(struct rcu_head *head);
 };
 
+/* Internal to kernel, but needed by rcupreempt.h. */
+extern int rcu_scheduler_active;
+
 #if defined(CONFIG_CLASSIC_RCU)
 #include <linux/rcuclassic.h>
 #elif defined(CONFIG_TREE_RCU)
@@ -265,6 +268,7 @@ extern void rcu_barrier_sched(void);
 
 /* Internal to kernel */
 extern void rcu_init(void);
+extern void rcu_scheduler_starting(void);
 extern int rcu_needs_cpu(int cpu);
 
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
index 3e05c09..74304b4 100644
--- a/include/linux/rcupreempt.h
+++ b/include/linux/rcupreempt.h
@@ -142,4 +142,19 @@ static inline void rcu_exit_nohz(void)
 #define rcu_exit_nohz()		do { } while (0)
 #endif /* CONFIG_NO_HZ */
 
+/*
+ * A context switch is a grace period for rcupreempt synchronize_rcu()
+ * only during early boot, before the scheduler has been initialized.
+ * So, how the heck do we get a context switch?  Well, if the caller
+ * invokes synchronize_rcu(), they are willing to accept a context
+ * switch, so we simply pretend that one happened.
+ *
+ * After boot, there might be a blocked or preempted task in an RCU
+ * read-side critical section, so we cannot then take the fastpath.
+ */
+static inline int rcu_blocking_is_gp(void)
+{
+	return num_online_cpus() == 1 && !rcu_scheduler_active;
+}
+
 #endif /* __LINUX_RCUPREEMPT_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index d4368b7..a722fb6 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -326,4 +326,10 @@ static inline void rcu_exit_nohz(void)
 }
 #endif /* CONFIG_NO_HZ */
 
+/* A context switch is a grace period for rcutree. */
+static inline int rcu_blocking_is_gp(void)
+{
+	return num_online_cpus() == 1;
+}
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/init/main.c b/init/main.c
index 8442094..83697e1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -97,7 +97,7 @@ static inline void mark_rodata_ro(void) { }
 extern void tc_init(void);
 #endif
 
-enum system_states system_state;
+enum system_states system_state __read_mostly;
 EXPORT_SYMBOL(system_state);
 
 /*
@@ -463,6 +463,7 @@ static noinline void __init_refok rest_init(void)
 	 * at least once to get things moving:
 	 */
 	init_idle_bootup_task(current);
+	rcu_scheduler_starting();
 	preempt_enable_no_resched();
 	schedule();
 	preempt_disable();
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index bd5a900..654c640 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu)
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	    (idle_cpu(cpu) && rcu_scheduler_active &&
+	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index d92a76a..cae8a05 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,6 +44,7 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/kernel_stat.h>
 
 enum rcu_barrier {
 	RCU_BARRIER_STD,
@@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
 static struct completion rcu_barrier_completion;
+int rcu_scheduler_active __read_mostly;
 
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
@@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head  *head)
 void synchronize_rcu(void)
 {
 	struct rcu_synchronize rcu;
+
+	if (rcu_blocking_is_gp())
+		return;
+
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
@@ -175,3 +181,9 @@ void __init rcu_init(void)
 	__rcu_init();
 }
 
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 33cfc50..5d59e85 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1181,6 +1181,9 @@ void __synchronize_sched(void)
 {
 	struct rcu_synchronize rcu;
 
+	if (num_online_cpus() == 1)
+		return;  /* blocking is gp if only one CPU! */
+
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index b2fd602..97ce315 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	    (idle_cpu(cpu) && rcu_scheduler_active &&
+	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user

[git pull] rcu fix

[Ingo Molnar]

Linus,

Please pull the latest RCU fixes git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

Thanks,

	Ingo

------------------>
Gautham R Shenoy (1):
      rcu: fix hotplug vs rcu race

 kernel/rcuclassic.c |   16 +++++++++++++++-
 1 files changed, 15 insertions(+), 1 deletions(-)

diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index f4ffbd0..a38895a 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -89,8 +89,22 @@ static void force_quiescent_state(struct rcu_data *rdp,
 		/*
 		 * Don't send IPI to itself. With irqs disabled,
 		 * rdp->cpu is the current cpu.
+		 *
+		 * cpu_online_map is updated by the _cpu_down()
+		 * using stop_machine_run(). Since we're in irqs disabled
+		 * section, stop_machine_run() is not exectuting, hence
+		 * the cpu_online_map is stable.
+		 *
+		 * However,  a cpu might have been offlined _just_ before
+		 * we disabled irqs while entering here.
+		 * And rcu subsystem might not yet have handled the CPU_DEAD
+		 * notification, leading to the offlined cpu's bit
+		 * being set in the rcp->cpumask.
+		 *
+		 * Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent
+		 * sending smp_reschedule() to an offlined CPU.
 		 */
-		cpumask = rcp->cpumask;
+		cpus_and(cpumask, rcp->cpumask, cpu_online_map);
 		cpu_clear(rdp->cpu, cpumask);
 		for_each_cpu_mask(cpu, cpumask)
 			smp_send_reschedule(cpu);