On Sat, Sep 24, 2022 at 09:00:39PM -0400, Joel Fernandes wrote:
>
>
> > On Sep 24, 2022, at 7:28 PM, Joel Fernandes <joel@xxxxxxxxxxxxxxxxx> wrote:
> >
> > Hi Frederic, thanks for the response, replies
> > below courtesy fruit company’s device:
> >
> >>> On Sep 24, 2022, at 6:46 PM, Frederic Weisbecker <frederic@xxxxxxxxxx> wrote:
> >>>
> >>> On Thu, Sep 22, 2022 at 10:01:01PM +0000, Joel Fernandes (Google) wrote:
> >>> @@ -3902,7 +3939,11 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
> >>> rdp->barrier_head.func = rcu_barrier_callback;
> >>> debug_rcu_head_queue(&rdp->barrier_head);
> >>> rcu_nocb_lock(rdp);
> >>> - WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
> >>> + /*
> >>> + * Flush the bypass list, but also wake up the GP thread as otherwise
> >>> + * bypass/lazy CBs maynot be noticed, and can cause real long delays!
> >>> + */
> >>> + WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, FLUSH_BP_WAKE));
> >>
> >> This fixes an issue that goes beyond lazy implementation. It should be done
> >> in a separate patch, handling rcu_segcblist_entrain() as well, with "Fixes: " tag.
> >
> > I wanted to do that, however on discussion with
> > Paul I thought of making this optimization only for
> > all lazy bypass CBs. That makes it directly related
> > this patch since the laziness notion is first
> > introduced here. On the other hand I could make
> > this change in a later patch since we are not
> > super bisectable anyway courtesy of the last
> > patch (which is not really an issue if the CONFIG
> > is kept off during someone’s bisection.
>
> Or are we saying it’s worth doing the wake up for rcu barrier even for regular bypass CB? That’d save 2 jiffies on rcu barrier. If we agree it’s needed, then yes splitting the patch makes sense.
>
> Please let me know your opinions, thanks,
>
> - Joel
Sure, I mean since we are fixing the buggy rcu_barrier_entrain() anyway, let's
just fix bypass as well. Such as in the following (untested):
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b39e97175a9e..a0df964abb0e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3834,6 +3834,8 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
{
unsigned long gseq = READ_ONCE(rcu_state.barrier_sequence);
unsigned long lseq = READ_ONCE(rdp->barrier_seq_snap);
+ bool wake_nocb = false;
+ bool was_alldone = false;
lockdep_assert_held(&rcu_state.barrier_lock);
if (rcu_seq_state(lseq) || !rcu_seq_state(gseq) || rcu_seq_ctr(lseq) != rcu_seq_ctr(gseq))
@@ -3842,6 +3844,8 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
rdp->barrier_head.func = rcu_barrier_callback;
debug_rcu_head_queue(&rdp->barrier_head);
rcu_nocb_lock(rdp);
+ if (rcu_rdp_is_offloaded(rdp) && !rcu_segcblist_pend_cbs(&rdp->cblist))
+ was_alldone = true;
WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
atomic_inc(&rcu_state.barrier_cpu_count);
@@ -3849,7 +3853,12 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
debug_rcu_head_unqueue(&rdp->barrier_head);
rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence);
}
+ if (was_alldone && rcu_segcblist_pend_cbs(&rdp->cblist))
+ wake_nocb = true;
rcu_nocb_unlock(rdp);
+ if (wake_nocb)
+ wake_nocb_gp(rdp, false);
+
smp_store_release(&rdp->barrier_seq_snap, gseq);
}
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index d4a97e40ea9c..925dd98f8b23 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -439,6 +439,7 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
static void rcu_init_one_nocb(struct rcu_node *rnp);
+static bool wake_nocb_gp(struct rcu_data *rdp, bool force);
static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
unsigned long j);
static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 538a0ed93946..e1701aa9c82c 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1600,6 +1600,10 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
{
}
+static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
+{
+}
+
static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
unsigned long j)
{
