[PATCH v2 01/16] rcu/tree: Keep kfree_rcu() awake during lock contention

From: Uladzislau Rezki (Sony)
Date: Mon May 25 2020 - 17:48:20 EST


From: "Joel Fernandes (Google)" <joel@xxxxxxxxxxxxxxxxx>

On PREEMPT_RT kernels, the krcp spinlock gets converted to an rt-mutex
and causes kfree_rcu() callers to sleep. This makes it unusable for
callers in purely atomic sections such as non-threaded IRQ handlers and
raw spinlock sections. Fix it by converting the spinlock to a raw
spinlock.

Vetting all code paths, there is no reason to believe that the raw
spinlock will hurt RT latencies as it is not held for a long time.

Cc: bigeasy@xxxxxxxxxxxxx
Cc: Uladzislau Rezki <urezki@xxxxxxxxx>
Reviewed-by: Uladzislau Rezki <urezki@xxxxxxxxx>
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
---
kernel/rcu/tree.c | 30 +++++++++++++++---------------
1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6e120be29332..6e967a9d6704 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2882,7 +2882,7 @@ struct kfree_rcu_cpu {
struct kfree_rcu_bulk_data *bhead;
struct kfree_rcu_bulk_data *bcached;
struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
- spinlock_t lock;
+ raw_spinlock_t lock;
struct delayed_work monitor_work;
bool monitor_todo;
bool initialized;
@@ -2915,12 +2915,12 @@ static void kfree_rcu_work(struct work_struct *work)
krwp = container_of(to_rcu_work(work),
struct kfree_rcu_cpu_work, rcu_work);
krcp = krwp->krcp;
- spin_lock_irqsave(&krcp->lock, flags);
+ raw_spin_lock_irqsave(&krcp->lock, flags);
head = krwp->head_free;
krwp->head_free = NULL;
bhead = krwp->bhead_free;
krwp->bhead_free = NULL;
- spin_unlock_irqrestore(&krcp->lock, flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);

/* "bhead" is now private, so traverse locklessly. */
for (; bhead; bhead = bnext) {
@@ -3023,14 +3023,14 @@ static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
krcp->monitor_todo = false;
if (queue_kfree_rcu_work(krcp)) {
// Success! Our job is done here.
- spin_unlock_irqrestore(&krcp->lock, flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
return;
}

// Previous RCU batch still in progress, try again later.
krcp->monitor_todo = true;
schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
- spin_unlock_irqrestore(&krcp->lock, flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
}

/*
@@ -3043,11 +3043,11 @@ static void kfree_rcu_monitor(struct work_struct *work)
struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu,
monitor_work.work);

- spin_lock_irqsave(&krcp->lock, flags);
+ raw_spin_lock_irqsave(&krcp->lock, flags);
if (krcp->monitor_todo)
kfree_rcu_drain_unlock(krcp, flags);
else
- spin_unlock_irqrestore(&krcp->lock, flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
}

static inline bool
@@ -3118,7 +3118,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
local_irq_save(flags); // For safely calling this_cpu_ptr().
krcp = this_cpu_ptr(&krc);
if (krcp->initialized)
- spin_lock(&krcp->lock);
+ raw_spin_lock(&krcp->lock);

// Queue the object but don't yet schedule the batch.
if (debug_rcu_head_queue(head)) {
@@ -3149,7 +3149,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)

unlock_return:
if (krcp->initialized)
- spin_unlock(&krcp->lock);
+ raw_spin_unlock(&krcp->lock);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(kfree_call_rcu);
@@ -3181,11 +3181,11 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);

count = krcp->count;
- spin_lock_irqsave(&krcp->lock, flags);
+ raw_spin_lock_irqsave(&krcp->lock, flags);
if (krcp->monitor_todo)
kfree_rcu_drain_unlock(krcp, flags);
else
- spin_unlock_irqrestore(&krcp->lock, flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);

sc->nr_to_scan -= count;
freed += count;
@@ -3212,15 +3212,15 @@ void __init kfree_rcu_scheduler_running(void)
for_each_online_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);

- spin_lock_irqsave(&krcp->lock, flags);
+ raw_spin_lock_irqsave(&krcp->lock, flags);
if (!krcp->head || krcp->monitor_todo) {
- spin_unlock_irqrestore(&krcp->lock, flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
continue;
}
krcp->monitor_todo = true;
schedule_delayed_work_on(cpu, &krcp->monitor_work,
KFREE_DRAIN_JIFFIES);
- spin_unlock_irqrestore(&krcp->lock, flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
}
}

@@ -4113,7 +4113,7 @@ static void __init kfree_rcu_batch_init(void)
for_each_possible_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);

- spin_lock_init(&krcp->lock);
+ raw_spin_lock_init(&krcp->lock);
for (i = 0; i < KFREE_N_BATCHES; i++) {
INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
krcp->krw_arr[i].krcp = krcp;
--
2.20.1