On Sun, May 17, 2026 at 11:30:14AM -0700, Paul E. McKenney wrote: > On Sun, May 17, 2026 at 02:40:42PM +0200, Uladzislau Rezki wrote: > > On Thu, May 14, 2026 at 09:33:10PM +0800, Z qiang wrote: > > > > > > > > From: "Paul E. McKenney" <[email protected]> > > > > > > > > Currently, rcutorture bypasses lazy RCU by using call_rcu_hurry(). > > > > This works, avoiding the dreaded rtort_pipe_count WARN(), but fails to > > > > fully test lazy RCU. The rtort_pipe_count WARN() splats because lazy > > > > RCU > > > > could delay the start of an RCU grace period for a full stutter period, > > > > which defaults to only three seconds. > > > > > > > > This commit therefore reverts the call_rcu_hurry() instances > > > > back to call_rcu(), but, in kernels built with CONFIG_RCU_LAZY=y, > > > > queues a workqueue handler just before the call to stutter_wait() in > > > > rcu_torture_writer(). This workqueue handler invokes rcu_barrier(), > > > > which motivates any lingering lazy callbacks, thus avoiding the splat. > > > > > > > > Questions for review: > > > > > > > > 1. Should we avoid queueing work for RCU implementations not > > > > supporting lazy callbacks? > > > > > > Hello, Paul > > > > > > maybe we can do this: > > > > > > rcu_ops = { > > > ... > > > .support_lazy = IS_ENABLED(CONFIG_RCU_LAZY), > > > }; > > > > > > and > > > > > > if (cur_ops->support_lazy ) > > > queue_work(..., &lazy_work); > > > > > > > > > > > 2. Should we avoid queueing work in kernels built with > > > > CONFIG_RCU_LAZY=y, but that were not booted with the > > > > rcutree.enable_rcu_lazy kernel boot parameter set? (Note that > > > > this requires some ugliness to access this parameter, and must > > > > also handle Tiny RCU.) > > > > > > > > 3. Does the rcu_torture_ops structure need a ->call_hurry() field, > > > > and if so, why? If not, why not? > > > > > > > > 4. Your additional questions here! > > > > > > > > Reported-by: Saravana Kannan <[email protected]> > > > > Signed-off-by: Paul E. McKenney <[email protected]> > > > > Signed-off-by: Uladzislau Rezki (Sony) <[email protected]> > > > > --- > > > > kernel/rcu/rcutorture.c | 21 ++++++++++++++++++--- > > > > 1 file changed, 18 insertions(+), 3 deletions(-) > > > > > > > > diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c > > > > index 5f2848b828dc..91ba3160ba6a 100644 > > > > --- a/kernel/rcu/rcutorture.c > > > > +++ b/kernel/rcu/rcutorture.c > > > > @@ -572,7 +572,7 @@ static unsigned long rcu_no_completed(void) > > > > > > > > static void rcu_torture_deferred_free(struct rcu_torture *p) > > > > { > > > > - call_rcu_hurry(&p->rtort_rcu, rcu_torture_cb); > > > > + call_rcu(&p->rtort_rcu, rcu_torture_cb); > > > > } > > > > > > > > static void rcu_sync_torture_init(void) > > > > @@ -619,7 +619,7 @@ static struct rcu_torture_ops rcu_ops = { > > > > .poll_gp_state_exp = poll_state_synchronize_rcu, > > > > .cond_sync_exp = cond_synchronize_rcu_expedited, > > > > .cond_sync_exp_full = cond_synchronize_rcu_expedited_full, > > > > - .call = call_rcu_hurry, > > > > + .call = call_rcu, > > > > .cb_barrier = rcu_barrier, > > > > .fqs = rcu_force_quiescent_state, > > > > .gp_kthread_dbg = show_rcu_gp_kthreads, > > > > @@ -1145,7 +1145,7 @@ static void > > > > rcu_tasks_torture_deferred_free(struct rcu_torture *p) > > > > > > > > static void synchronize_rcu_mult_test(void) > > > > { > > > > - synchronize_rcu_mult(call_rcu_tasks, call_rcu_hurry); > > > > + synchronize_rcu_mult(call_rcu_tasks, call_rcu); > > > > } > > > > > > > > static struct rcu_torture_ops tasks_ops = { > > > > @@ -1631,6 +1631,17 @@ static void do_rtws_sync(struct > > > > torture_random_state *trsp, void (*sync)(void)) > > > > cpus_read_unlock(); > > > > } > > > > > > > > +/* > > > > + * Do an rcu_barrier() to motivate lazy callbacks during a stutter > > > > + * pause. Without this, we can get false-positives rtort_pipe_count > > > > + * splats. > > > > + */ > > > > +static void rcu_torture_writer_work(struct work_struct *work) > > > > +{ > > > > + if (cur_ops->cb_barrier) > > > > + cur_ops->cb_barrier(); > > > > +} > > > > + > > > > /* > > > > * RCU torture writer kthread. Repeatedly substitutes a new structure > > > > * for that pointed to by rcu_torture_current, freeing the old > > > > structure > > > > @@ -1651,6 +1662,7 @@ rcu_torture_writer(void *arg) > > > > int i; > > > > int idx; > > > > unsigned long j; > > > > + struct work_struct lazy_work; > > > > int oldnice = task_nice(current); > > > > struct rcu_gp_oldstate *rgo = NULL; > > > > int rgo_size = 0; > > > > @@ -1667,6 +1679,7 @@ rcu_torture_writer(void *arg) > > > > stallsdone += (stall_cpu_holdoff + stall_gp_kthread + > > > > stall_cpu + 60) * > > > > HZ * (stall_cpu_repeat + 1); > > > > VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); > > > > + INIT_WORK_ONSTACK(&lazy_work, rcu_torture_writer_work); > > > > if (!can_expedite) > > > > pr_alert("%s" TORTURE_FLAG > > > > " GP expediting controlled from boot/sysfs for > > > > %s.\n", > > > > @@ -1895,6 +1908,8 @@ rcu_torture_writer(void *arg) > > > > !rcu_gp_is_normal(); > > > > } > > > > rcu_torture_writer_state = RTWS_STUTTER; > > > > + if (IS_ENABLED(CONFIG_RCU_LAZY)) > > > > + queue_work(system_percpu_wq, &lazy_work); > > > > > > > > > When the task ends, the lazy_work should be cancel and destroy: > > > > > > diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c > > > index f593f8b794dd..5adf537ab410 100644 > > > --- a/kernel/rcu/rcutorture.c > > > +++ b/kernel/rcu/rcutorture.c > > > @@ -1682,7 +1682,6 @@ rcu_torture_writer(void *arg) > > > stallsdone += (stall_cpu_holdoff + stall_gp_kthread + stall_cpu + 60) * > > > HZ * (stall_cpu_repeat + 1); > > > VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); > > > - INIT_WORK_ONSTACK(&lazy_work, rcu_torture_writer_work); > > > if (!can_expedite) > > > pr_alert("%s" TORTURE_FLAG > > > " GP expediting controlled from boot/sysfs for %s.\n", > > > @@ -1719,6 +1718,8 @@ rcu_torture_writer(void *arg) > > > pr_alert("%s" TORTURE_FLAG " Waited %lu jiffies for boot to complete.\n", > > > torture_type, jiffies - j); > > > > > > + INIT_WORK_ONSTACK(&lazy_work, rcu_torture_writer_work); > > > + > > > do { > > > rcu_torture_writer_state = RTWS_FIXED_DELAY; > > > torture_hrtimeout_us(500, 1000, &rand); > > > @@ -1943,6 +1944,9 @@ rcu_torture_writer(void *arg) > > > pr_alert("%s" TORTURE_FLAG > > > " Dynamic grace-period expediting was disabled.\n", > > > torture_type); > > > + if (IS_ENABLED(CONFIG_RCU_LAZY)) > > > + cancel_work_sync(&lazy_work); > > > + destroy_work_on_stack(&lazy_work); > > > kfree(ulo); > > > kfree(rgo); > > > rcu_torture_writer_state = RTWS_STOPPING; > > > > > I agree, we seem miss destroying the work via destroy_work_on_stack() > > and "sync" the lazy_work work via cancel_work_sync(). > > > > Paul, any thoughts? > > Good eyes!!! I will take a closer look tomorrow. > > In the meantime, one question... Do we want to test for your new > ->support_lazy instead of IS_ENABLED(CONFIG_RCU_LAZY) for that > cancel_work_sync() and destroy_work_on_stack()? If we really need > IS_ENABLED(CONFIG_RCU_LAZY), could you please suggest a comment giving > the reasoning? > To me IS_ENABLED(CONFIG_RCU_LAZY) is enough :) I am not sure we really need ->support_lazy flag.
-- Uladzislau Rezki
