[PATCH tip/core/rcu 0/9] CPU-hotplug updates for 4.2

[PATCH tip/core/rcu 0/9] CPU-hotplug updates for 4.2

[Paul E. McKenney]

Hello!

The following series improves RCU's handling of CPU hotplug.  It also
contains a couple of ARM placeholder patches in case someone gets caught
out by tighter diagnostics.

1.	Eliminate a HOTPLUG_CPU #ifdef in favor of IS_ENABLED()

2.	Adjust rcu_read_unlock_special()'s acquisition of the
	task's lock to start allowing for the fact that blocked
	tasks are no longer migrated to the root rcu_node structure.
	If the warning does not trigger, a later patch will eliminate
	the loop.

3.	Rmove dead code from force_qs_rnp().

4.	Remove redundant offline check.

5.	Correctly initialize ->rcu_qs_ctr_snap at online time to get the
	code out of its current "working by accident" state.

6.	Move smpboot_unpark_threads() handling into a notifier for
	uniformity.

7.	[Placeholder for ARM64]  Use common code for ARM64 CPU-offline
	notification.

8.	[Placeholder for ARM]  Use common code for ARM CPU-offline
	notification.

9.	Remove extraneous __cpuinit, courtesy of Paul Gortmaker.

							Thanx, Paul

------------------------------------------------------------------------

 b/arch/arm/kernel/smp.c    |    6 +----
 b/arch/arm64/kernel/smp.c  |    6 +----
 b/kernel/cpu.c             |    4 +--
 b/kernel/rcu/tree.c        |   47 ++++++++++++++-------------------------------
 b/kernel/rcu/tree_plugin.h |    9 +++++---
 5 files changed, 27 insertions(+), 45 deletions(-)

[PATCH tip/core/rcu 1/9] rcu: Eliminate HOTPLUG_CPU #ifdef in favor of IS_ENABLED()

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

This commit removes a HOTPLUG_CPU #ifdef, replacing it with
IS_ENABLED()-protected return statements.  This relies on the
optimizer to remove any resulting dead code.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 39 ++++++++++++++-------------------------
 1 file changed, 14 insertions(+), 25 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4d3299577d7b..7c323e320075 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2333,8 +2333,6 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
 /*
  * Send the specified CPU's RCU callbacks to the orphanage.  The
  * specified CPU must be offline, and the caller must hold the
@@ -2345,7 +2343,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 			  struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	/* No-CBs CPUs do not have orphanable callbacks. */
-	if (rcu_is_nocb_cpu(rdp->cpu))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
 		return;
 
 	/*
@@ -2404,7 +2402,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
-	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
 		return;
 
 	/* Do the accounting first. */
@@ -2451,6 +2450,9 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
 	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
 	RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	RCU_TRACE(mask = rdp->grpmask);
 	trace_rcu_grace_period(rsp->name,
 			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
@@ -2479,7 +2481,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
 		return;
 	for (;;) {
 		mask = rnp->grpmask;
@@ -2510,6 +2513,9 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -2531,6 +2537,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
 
@@ -2545,26 +2554,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 		  cpu, rdp->qlen, rdp->nxtlist);
 }
 
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
-{
-}
-
-static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
-{
-}
-
-static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Invoke any RCU callbacks that have made it to the end of their grace
  * period.  Thottle as specified by rdp->blimit.
-- 
1.8.1.5

[PATCH tip/core/rcu 2/9] rcu: Adjust ->lock acquisition for tasks no longer migrating

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

Tasks are no longer migrated away from a given rcu_node structure
when all CPUs corresponding to that rcu_node structure have gone offline.
This means that rcu_read_unlock_special() no longer needs to loop
retrying rcu_node ->lock acquisition because the current task is
guaranteed to stay put.

This commit takes a small and paranoid step towards relying on this
guarantee by placing a WARN_ON_ONCE() just after the early exit from
the lock-acquisition loop.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 58b1ebdc4387..c8340e929eb4 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -307,9 +307,11 @@ void rcu_read_unlock_special(struct task_struct *t)
 		t->rcu_read_unlock_special.b.blocked = false;
 
 		/*
-		 * Remove this task from the list it blocked on.  The
-		 * task can migrate while we acquire the lock, but at
-		 * most one time.  So at most two passes through loop.
+		 * Remove this task from the list it blocked on.  The task
+		 * now remains queued on the rcu_node corresponding to
+		 * the CPU it first blocked on, so the first attempt to
+		 * acquire the task's rcu_node's ->lock will succeed.
+		 * Keep the loop and add a WARN_ON() out of sheer paranoia.
 		 */
 		for (;;) {
 			rnp = t->rcu_blocked_node;
@@ -317,6 +319,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
+			WARN_ON_ONCE(1);
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
-- 
1.8.1.5

[PATCH tip/core/rcu 3/9] rcu: Remove dead code from force_qs_rnp()

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

Because force_qs_rnp() is invoked only from the force-quiescent-state
code which runs only in the context of the grace-period kthread, a grace
period must always be in progress throughout force_qs_rnp()'s execution.
This commit therefore removes the rcu_gp_in_progress() check and the
associated dead code.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7c323e320075..20aeb6f9fe38 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2718,10 +2718,6 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
-		if (!rcu_gp_in_progress(rsp)) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			return;
-		}
 		if (rnp->qsmask == 0) {
 			if (rcu_state_p == &rcu_sched_state ||
 			    rsp != rcu_state_p ||
-- 
1.8.1.5

[PATCH tip/core/rcu 4/9] rcu: Remove redundant offline check

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

Because offline CPUs are propagated up the rcu_node tree's ->qsmaskinit
bits just before each grace period starts, the ->qsmaskinit bit cannot
be clear when the corresponding ->qsmask bit is set.  Furthermore, this
condition used to correspond to a CPU that was on its way offline, and
making RCU's notion of an offline CPU more precise has eliminated this
situation.  This commit therefore removes the now-redundant offline
check from force_qs_rnp().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 20aeb6f9fe38..1eb1029a5464 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2747,8 +2747,6 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
 			if ((rnp->qsmask & bit) != 0) {
-				if ((rnp->qsmaskinit & bit) == 0)
-					*isidle = false; /* Pending hotplug. */
 				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
 					mask |= bit;
 			}
-- 
1.8.1.5

[PATCH tip/core/rcu 5/9] rcu: Correctly initialize ->rcu_qs_ctr_snap at online time

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

The rcu_data structure's ->rcu_qs_ctr_snap field is initialized at
CPU-online time from the current CPU's element of the per-CPU rcu_qs_ctr
variable.  Unfortunately, this is at CPU_UP_PREPARE time, so has nothing
to do with the CPU being onlined.  This commit therefore initializes
this variable from the incoming CPU's element of rcu_qs_ctr.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1eb1029a5464..48d002d4faac 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3761,7 +3761,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
 	rdp->passed_quiesce = false;
-	rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+	rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
 	rdp->qs_pending = false;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-- 
1.8.1.5

[PATCH tip/core/rcu 6/9] cpu: Handle smpboot_unpark_threads() uniformly

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

Commit 00df35f99191 (cpu: Defer smpboot kthread unparking until CPU known
to scheduler) put the online path's call to smpboot_unpark_threads()
into a CPU-hotplug notifier.  This commit places the offline-failure
paths call into the same notifier for the sake of uniformity.

Note that it is not currently possible to place the offline path's call to
smpboot_park_threads() into an existing notifier because the CPU_DYING
notifiers run in a restricted environment, and the CPU_UP_PREPARE
notifiers run too soon.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 94bbe4695232..260eb7db281e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -398,7 +398,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
-		smpboot_unpark_threads(cpu);
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
 		goto out_release;
 	}
@@ -463,6 +462,7 @@ static int smpboot_thread_call(struct notifier_block *nfb,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 
+	case CPU_DOWN_FAILED:
 	case CPU_ONLINE:
 		smpboot_unpark_threads(cpu);
 		break;
-- 
1.8.1.5

[PATCH tip/core/rcu 7/9] arm64: Use common outgoing-CPU-notification code

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

This commit removes the open-coded CPU-offline notification with new
common code.  In particular, this change avoids calling scheduler code
using RCU from an offline CPU that RCU is ignoring.  This is a minimal
change.  A more intrusive change might invoke the cpu_check_up_prepare()
and cpu_set_state_online() functions at CPU-online time, which would
allow onlining throw an error if the CPU did not go offline properly.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/smp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2cb008177252..a899c1beff54 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -253,15 +253,13 @@ static int op_cpu_kill(unsigned int cpu)
 	return cpu_ops[cpu]->cpu_kill(cpu);
 }
 
-static DECLARE_COMPLETION(cpu_died);
-
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+	if (!cpu_wait_death(cpu, 5)) {
 		pr_crit("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
@@ -294,7 +292,7 @@ void cpu_die(void)
 	local_irq_disable();
 
 	/* Tell __cpu_die() that this CPU is now safe to dispose of */
-	complete(&cpu_died);
+	(void)cpu_report_death();
 
 	/*
 	 * Actually shutdown the CPU. This must never fail. The specific hotplug
-- 
1.8.1.5

Re: [PATCH tip/core/rcu 7/9] arm64: Use common outgoing-CPU-notification code

[Will Deacon]

Hi Paul,

Sorry for being late on this one.

On Tue, May 12, 2015 at 10:50:05PM +0100, Paul E. McKenney wrote:
> From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
> 
> This commit removes the open-coded CPU-offline notification with new
> common code.  In particular, this change avoids calling scheduler code
> using RCU from an offline CPU that RCU is ignoring.  This is a minimal
> change.  A more intrusive change might invoke the cpu_check_up_prepare()
> and cpu_set_state_online() functions at CPU-online time, which would
> allow onlining throw an error if the CPU did not go offline properly.
> 
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> Cc: linux-arm-kernel@lists.infradead.org
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> ---
>  arch/arm64/kernel/smp.c | 6 ++----
>  1 file changed, 2 insertions(+), 4 deletions(-)

I don't have a better idea, so:

  Acked-by: Will Deacon <will.deacon@arm.com>

Is this queued via -tip already, or can we pick it into the arm64 tree
for 4.2?

Cheers,

Will

> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
> index 2cb008177252..a899c1beff54 100644
> --- a/arch/arm64/kernel/smp.c
> +++ b/arch/arm64/kernel/smp.c
> @@ -253,15 +253,13 @@ static int op_cpu_kill(unsigned int cpu)
>  	return cpu_ops[cpu]->cpu_kill(cpu);
>  }
>  
> -static DECLARE_COMPLETION(cpu_died);
> -
>  /*
>   * called on the thread which is asking for a CPU to be shutdown -
>   * waits until shutdown has completed, or it is timed out.
>   */
>  void __cpu_die(unsigned int cpu)
>  {
> -	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
> +	if (!cpu_wait_death(cpu, 5)) {
>  		pr_crit("CPU%u: cpu didn't die\n", cpu);
>  		return;
>  	}
> @@ -294,7 +292,7 @@ void cpu_die(void)
>  	local_irq_disable();
>  
>  	/* Tell __cpu_die() that this CPU is now safe to dispose of */
> -	complete(&cpu_died);
> +	(void)cpu_report_death();
>  
>  	/*
>  	 * Actually shutdown the CPU. This must never fail. The specific hotplug
> -- 
> 1.8.1.5
> 

Re: [PATCH tip/core/rcu 7/9] arm64: Use common outgoing-CPU-notification code

[Paul E. McKenney]

On Thu, May 21, 2015 at 09:58:06AM +0100, Will Deacon wrote:
> Hi Paul,
> 
> Sorry for being late on this one.

No problem!  In fact, just in time -- I was going to bug you about
this later today.  ;-)

> On Tue, May 12, 2015 at 10:50:05PM +0100, Paul E. McKenney wrote:
> > From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
> > 
> > This commit removes the open-coded CPU-offline notification with new
> > common code.  In particular, this change avoids calling scheduler code
> > using RCU from an offline CPU that RCU is ignoring.  This is a minimal
> > change.  A more intrusive change might invoke the cpu_check_up_prepare()
> > and cpu_set_state_online() functions at CPU-online time, which would
> > allow onlining throw an error if the CPU did not go offline properly.
> > 
> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> > Cc: linux-arm-kernel@lists.infradead.org
> > Cc: Catalin Marinas <catalin.marinas@arm.com>
> > Cc: Will Deacon <will.deacon@arm.com>
> > ---
> >  arch/arm64/kernel/smp.c | 6 ++----
> >  1 file changed, 2 insertions(+), 4 deletions(-)
> 
> I don't have a better idea, so:
> 
>   Acked-by: Will Deacon <will.deacon@arm.com>
> 
> Is this queued via -tip already, or can we pick it into the arm64 tree
> for 4.2?

Feel free to take it into the arm64 tree.  Just let me know, and I
will drop it from my tree.

Now I only need to bug the arm32 guys.  ;-)

							Thanx, Paul

> Cheers,
> 
> Will
> 
> > diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
> > index 2cb008177252..a899c1beff54 100644
> > --- a/arch/arm64/kernel/smp.c
> > +++ b/arch/arm64/kernel/smp.c
> > @@ -253,15 +253,13 @@ static int op_cpu_kill(unsigned int cpu)
> >  	return cpu_ops[cpu]->cpu_kill(cpu);
> >  }
> >  
> > -static DECLARE_COMPLETION(cpu_died);
> > -
> >  /*
> >   * called on the thread which is asking for a CPU to be shutdown -
> >   * waits until shutdown has completed, or it is timed out.
> >   */
> >  void __cpu_die(unsigned int cpu)
> >  {
> > -	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
> > +	if (!cpu_wait_death(cpu, 5)) {
> >  		pr_crit("CPU%u: cpu didn't die\n", cpu);
> >  		return;
> >  	}
> > @@ -294,7 +292,7 @@ void cpu_die(void)
> >  	local_irq_disable();
> >  
> >  	/* Tell __cpu_die() that this CPU is now safe to dispose of */
> > -	complete(&cpu_died);
> > +	(void)cpu_report_death();
> >  
> >  	/*
> >  	 * Actually shutdown the CPU. This must never fail. The specific hotplug
> > -- 
> > 1.8.1.5
> > 
> 

Re: [PATCH tip/core/rcu 7/9] arm64: Use common outgoing-CPU-notification code

[Catalin Marinas]

On Thu, May 21, 2015 at 05:48:33AM -0700, Paul E. McKenney wrote:
> On Thu, May 21, 2015 at 09:58:06AM +0100, Will Deacon wrote:
> > On Tue, May 12, 2015 at 10:50:05PM +0100, Paul E. McKenney wrote:
> > > From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
> > > 
> > > This commit removes the open-coded CPU-offline notification with new
> > > common code.  In particular, this change avoids calling scheduler code
> > > using RCU from an offline CPU that RCU is ignoring.  This is a minimal
> > > change.  A more intrusive change might invoke the cpu_check_up_prepare()
> > > and cpu_set_state_online() functions at CPU-online time, which would
> > > allow onlining throw an error if the CPU did not go offline properly.
> > > 
> > > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> > > Cc: linux-arm-kernel@lists.infradead.org
> > > Cc: Catalin Marinas <catalin.marinas@arm.com>
> > > Cc: Will Deacon <will.deacon@arm.com>
> > > ---
> > >  arch/arm64/kernel/smp.c | 6 ++----
> > >  1 file changed, 2 insertions(+), 4 deletions(-)
> > 
> > I don't have a better idea, so:
> > 
> >   Acked-by: Will Deacon <will.deacon@arm.com>
> > 
> > Is this queued via -tip already, or can we pick it into the arm64 tree
> > for 4.2?
> 
> Feel free to take it into the arm64 tree.  Just let me know, and I
> will drop it from my tree.

Queued for 4.2. Thanks.

-- 
Catalin

Re: [PATCH tip/core/rcu 7/9] arm64: Use common outgoing-CPU-notification code

[Paul E. McKenney]

On Thu, May 21, 2015 at 02:25:57PM +0100, Catalin Marinas wrote:
> On Thu, May 21, 2015 at 05:48:33AM -0700, Paul E. McKenney wrote:
> > On Thu, May 21, 2015 at 09:58:06AM +0100, Will Deacon wrote:
> > > On Tue, May 12, 2015 at 10:50:05PM +0100, Paul E. McKenney wrote:
> > > > From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
> > > > 
> > > > This commit removes the open-coded CPU-offline notification with new
> > > > common code.  In particular, this change avoids calling scheduler code
> > > > using RCU from an offline CPU that RCU is ignoring.  This is a minimal
> > > > change.  A more intrusive change might invoke the cpu_check_up_prepare()
> > > > and cpu_set_state_online() functions at CPU-online time, which would
> > > > allow onlining throw an error if the CPU did not go offline properly.
> > > > 
> > > > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> > > > Cc: linux-arm-kernel@lists.infradead.org
> > > > Cc: Catalin Marinas <catalin.marinas@arm.com>
> > > > Cc: Will Deacon <will.deacon@arm.com>
> > > > ---
> > > >  arch/arm64/kernel/smp.c | 6 ++----
> > > >  1 file changed, 2 insertions(+), 4 deletions(-)
> > > 
> > > I don't have a better idea, so:
> > > 
> > >   Acked-by: Will Deacon <will.deacon@arm.com>
> > > 
> > > Is this queued via -tip already, or can we pick it into the arm64 tree
> > > for 4.2?
> > 
> > Feel free to take it into the arm64 tree.  Just let me know, and I
> > will drop it from my tree.
> 
> Queued for 4.2. Thanks.

Very good, dropped from my tree.

							Thanx, Paul

[PATCH tip/core/rcu 8/9] arm: Use common outgoing-CPU-notification code

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

This commit removes the open-coded CPU-offline notification with new
common code.  In particular, this change avoids calling scheduler code
using RCU from an offline CPU that RCU is ignoring.  This is a minimal
change.  A more intrusive change might invoke the cpu_check_up_prepare()
and cpu_set_state_online() functions at CPU-online time, which would
allow onlining throw an error if the CPU did not go offline properly.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Russell King <linux@arm.linux.org.uk>
---
 arch/arm/kernel/smp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index cca5b8758185..8ef0ef0287ee 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -218,15 +218,13 @@ int __cpu_disable(void)
 	return 0;
 }
 
-static DECLARE_COMPLETION(cpu_died);
-
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+	if (!cpu_wait_death(cpu, 5)) {
 		pr_err("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
@@ -272,7 +270,7 @@ void __ref cpu_die(void)
 	 * this returns, power and/or clocks can be removed at any point
 	 * from this CPU and its cache by platform_cpu_kill().
 	 */
-	complete(&cpu_died);
+	(void)cpu_report_death();
 
 	/*
 	 * Ensure that the cache lines associated with that completion are
-- 
1.8.1.5

Re: [PATCH tip/core/rcu 8/9] arm: Use common outgoing-CPU-notification code

[Geert Uytterhoeven]

Hi Paul,

On Tue, May 12, 2015 at 11:50 PM, Paul E. McKenney
<paulmck@linux.vnet.ibm.com> wrote:
> From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
>
> This commit removes the open-coded CPU-offline notification with new
> common code.  In particular, this change avoids calling scheduler code
> using RCU from an offline CPU that RCU is ignoring.  This is a minimal
> change.  A more intrusive change might invoke the cpu_check_up_prepare()
> and cpu_set_state_online() functions at CPU-online time, which would
> allow onlining throw an error if the CPU did not go offline properly.
>
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> Cc: linux-arm-kernel@lists.infradead.org
> Cc: Russell King <linux@arm.linux.org.uk>

Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>

Thanks, this seems to fix the intermittent "suspicious RCU usage" warnings I've
been seeing during suspend to RAM on r8a7791/koelsch, which has a dual-core
Cortex A15:

    Disabling non-boot CPUs ...

    ===============================
    [ INFO: suspicious RCU usage. ]
    4.4.0-rc4-koelsch #2123 Tainted: G        W
    -------------------------------
    kernel/sched/fair.c:4938 suspicious rcu_dereference_check() usage!

    other info that might help us debug this:

    RCU used illegally from offline CPU!
    rcu_scheduler_active = 1, debug_locks = 0
    3 locks held by swapper/1/0:
     #0:  ((cpu_died).wait.lock){......}, at: [<c006077c>] complete+0x14/0x44
     #1:  (&p->pi_lock){-.-.-.}, at: [<c004b8a8>] try_to_wake_up+0x24/0x340
     #2:  (rcu_read_lock){......}, at: [<c0052740>]
select_task_rq_fair+0xb4/0x820

    stack backtrace:
    CPU: 1 PID: 0 Comm: swapper/1 Tainted: G        W
4.4.0-rc4-koelsch #2123
    Hardware name: Generic R8A7791 (Flattened Device Tree)
    [<c0017390>] (unwind_backtrace) from [<c0013094>] (show_stack+0x10/0x14)
    [<c0013094>] (show_stack) from [<c01ee718>] (dump_stack+0x70/0x8c)
    [<c01ee718>] (dump_stack) from [<c0052810>]
(select_task_rq_fair+0x184/0x820)
    [<c0052810>] (select_task_rq_fair) from [<c004ba54>]
(try_to_wake_up+0x1d0/0x340)
    [<c004ba54>] (try_to_wake_up) from [<c0060070>] (__wake_up_common+0x4c/0x78)
    [<c0060070>] (__wake_up_common) from [<c00600ac>]
(__wake_up_locked+0x10/0x18)
    [<c00600ac>] (__wake_up_locked) from [<c006079c>] (complete+0x34/0x44)
    [<c006079c>] (complete) from [<c00159f8>] (arch_cpu_idle_dead+0x2c/0x8c)
    [<c00159f8>] (arch_cpu_idle_dead) from [<c0060a24>]
(cpu_startup_entry+0x84/0x228)
    [<c0060a24>] (cpu_startup_entry) from [<4000a4ac>] (0x4000a4ac)
    CPU1: shutdown

But I understand from the various other threads about this issue that this
patch is not going upstream, as it papers over the real issue?

Gr{oetje,eeting}s,

                        Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds

[PATCH tip/core/rcu 9/9] cpu: Remove new instance of __cpuinit that crept back in

[Paul E. McKenney]

From: Paul Gortmaker <paul.gortmaker@windriver.com>

We removed __cpuinit support (leaving no-op stubs) quite some time ago.
However a new instance was added in commit 00df35f991914db6b8bde8cf0980
("cpu: Defer smpboot kthread unparking until CPU known to scheduler")

Since we want to clobber the stubs soon, get this removed now.

Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 260eb7db281e..9c9c9fab16cc 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -479,7 +479,7 @@ static struct notifier_block smpboot_thread_notifier = {
 	.priority = CPU_PRI_SMPBOOT,
 };
 
-void __cpuinit smpboot_thread_init(void)
+void smpboot_thread_init(void)
 {
 	register_cpu_notifier(&smpboot_thread_notifier);
 }
-- 
1.8.1.5