smp: Wait only if work was enqueued

Whenever work is enqueued for a remote CPU, smp_call_function_many_cond()
may need to wait for that work to be completed. However, if no work is
enqueued for a remote CPU, because the condition func() evaluated to false
for all CPUs, there is no need to wait.

Set run_remote only if work was enqueued on remote CPUs.

Document the difference between "work enqueued", and "CPU needs to be
woken up"

Suggested-by: Jann Horn <jannh@google.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
Link: https://lore.kernel.org/all/20250703203019.11331ac3@fangorn

diff --git a/kernel/smp.c b/kernel/smp.c
index 99d1fd0e9e0e8cfcecfcb12fb49932368eef0518..c5e1da7a88dab810b7ffcb0e57e8ee548ffa75dc 100644 (file)
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -802,7 +802,6 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 
        /* Check if we need remote execution, i.e., any CPU excluding this one. */
        if (cpumask_any_and_but(mask, cpu_online_mask, this_cpu) < nr_cpu_ids) {
-               run_remote = true;
                cfd = this_cpu_ptr(&cfd_data);
                cpumask_and(cfd->cpumask, mask, cpu_online_mask);
                __cpumask_clear_cpu(this_cpu, cfd->cpumask);
@@ -816,6 +815,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
                                continue;
                        }
 
+                       /* Work is enqueued on a remote CPU. */
+                       run_remote = true;
+
                        csd_lock(csd);
                        if (wait)
                                csd->node.u_flags |= CSD_TYPE_SYNC;
@@ -827,6 +829,10 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 #endif
                        trace_csd_queue_cpu(cpu, _RET_IP_, func, csd);
 
+                       /*
+                        * Kick the remote CPU if this is the first work
+                        * item enqueued.
+                        */
                        if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) {
                                __cpumask_set_cpu(cpu, cfd->cpumask_ipi);
                                nr_cpus++;