diff mbox series

[05/10] rcu: Assume IRQS disabled from rcu_report_dead()

Message ID 20230908203603.5865-6-frederic@kernel.org
State New
Headers
Series rcu cleanups |

Commit Message

Frederic Weisbecker Sept. 8, 2023, 8:35 p.m. UTC 
  rcu_report_dead() is the last RCU word from the CPU down through the
hotplug path. It is called in the idle loop right before the CPU shuts
down for good. Because it removes the CPU from the grace period state
machine and reports an ultimate quiescent state if necessary, no further
use of RCU is allowed. Therefore it is expected that IRQs are disabled
upon calling this function and are not to be re-enabled again until the
CPU shuts down.

Remove the IRQs disablement from that function and verify instead that
it is actually called with IRQs disabled as it is expected at that
special point in the idle path.

Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 kernel/rcu/tree.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

Comments

Paul E. McKenney Oct. 2, 2023, 3:41 p.m. UTC | #1 
On Fri, Sep 08, 2023 at 10:35:58PM +0200, Frederic Weisbecker wrote:
> rcu_report_dead() is the last RCU word from the CPU down through the
> hotplug path. It is called in the idle loop right before the CPU shuts
> down for good. Because it removes the CPU from the grace period state
> machine and reports an ultimate quiescent state if necessary, no further
> use of RCU is allowed. Therefore it is expected that IRQs are disabled
> upon calling this function and are not to be re-enabled again until the
> CPU shuts down.
> 
> Remove the IRQs disablement from that function and verify instead that
> it is actually called with IRQs disabled as it is expected at that
> special point in the idle path.
> 
> Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> Signed-off-by: Frederic Weisbecker <frederic@kernel.org>

Reviewed-by: Paul E. McKenney <paulmck@kernel.org>

> ---
>  kernel/rcu/tree.c | 10 ++++++----
>  1 file changed, 6 insertions(+), 4 deletions(-)
> 
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index a83ecab77917..8b5ebef32e17 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -4553,11 +4553,16 @@ void rcu_cpu_starting(unsigned int cpu)
>   */
>  void rcu_report_dead(unsigned int cpu)
>  {
> -	unsigned long flags, seq_flags;
> +	unsigned long flags;
>  	unsigned long mask;
>  	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
>  	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
>  
> +	/*
> +	 * IRQS must be disabled from now on and until the CPU dies, or an interrupt
> +	 * may introduce a new READ-side while it is actually off the QS masks.
> +	 */
> +	lockdep_assert_irqs_disabled();
>  	// Do any dangling deferred wakeups.
>  	do_nocb_deferred_wakeup(rdp);
>  
> @@ -4565,7 +4570,6 @@ void rcu_report_dead(unsigned int cpu)
>  
>  	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
>  	mask = rdp->grpmask;
> -	local_irq_save(seq_flags);
>  	arch_spin_lock(&rcu_state.ofl_lock);
>  	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
>  	rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
> @@ -4579,8 +4583,6 @@ void rcu_report_dead(unsigned int cpu)
>  	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
>  	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
>  	arch_spin_unlock(&rcu_state.ofl_lock);
> -	local_irq_restore(seq_flags);
> -
>  	rdp->cpu_started = false;
>  }
>  
> -- 
> 2.41.0
>
diff mbox series

Patch

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a83ecab77917..8b5ebef32e17 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -4553,11 +4553,16 @@  void rcu_cpu_starting(unsigned int cpu)
  */
 void rcu_report_dead(unsigned int cpu)
 {
-	unsigned long flags, seq_flags;
+	unsigned long flags;
 	unsigned long mask;
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	/*
+	 * IRQS must be disabled from now on and until the CPU dies, or an interrupt
+	 * may introduce a new READ-side while it is actually off the QS masks.
+	 */
+	lockdep_assert_irqs_disabled();
 	// Do any dangling deferred wakeups.
 	do_nocb_deferred_wakeup(rdp);
 
@@ -4565,7 +4570,6 @@  void rcu_report_dead(unsigned int cpu)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
-	local_irq_save(seq_flags);
 	arch_spin_lock(&rcu_state.ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
 	rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
@@ -4579,8 +4583,6 @@  void rcu_report_dead(unsigned int cpu)
 	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	arch_spin_unlock(&rcu_state.ofl_lock);
-	local_irq_restore(seq_flags);
-
 	rdp->cpu_started = false;
 }