From: Saurabh Sengar <ssengar@xxxxxxxxxxxxxxxxxxx> Sent: Wednesday, July 24, 2024 10:26 PM
>
> Currently on a very large system with 1780 CPUs, hv_acpi_init takes
> around 3 seconds to complete for all the CPUs. This is because of
> sequential synic initialization for each CPU.
>
> Defer these tasks so that each CPU executes hv_acpi_init in parallel
> to take full advantage of multiple CPUs.
>
> This solution saves around 2 seconds of boot time on a 1780 CPU system,
> that around 66% improvement in the existing logic.
>
> Signed-off-by: Saurabh Sengar <ssengar@xxxxxxxxxxxxxxxxxxx>
> ---
> drivers/hv/vmbus_drv.c | 33 ++++++++++++++++++++++++++++++---
> 1 file changed, 30 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index c857dc3975be..3395526ad0d0 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -1306,6 +1306,13 @@ static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id)
> return IRQ_HANDLED;
> }
>
> +static void vmbus_percpu_work(struct work_struct *work)
> +{
> + unsigned int cpu = smp_processor_id();
> +
> + hv_synic_init(cpu);
> +}
> +
> /*
> * vmbus_bus_init -Main vmbus driver initialization routine.
> *
> @@ -1316,7 +1323,8 @@ static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id)
> */
> static int vmbus_bus_init(void)
> {
> - int ret;
> + int ret, cpu;
> + struct work_struct __percpu *works;
>
> ret = hv_init();
> if (ret != 0) {
> @@ -1355,12 +1363,31 @@ static int vmbus_bus_init(void)
> if (ret)
> goto err_alloc;
>
> + works = alloc_percpu(struct work_struct);
> + if (!works) {
> + ret = -ENOMEM;
> + goto err_alloc;
> + }
> +
> /*
> * Initialize the per-cpu interrupt state and stimer state.
> * Then connect to the host.
> */
> - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online",
> - hv_synic_init, hv_synic_cleanup);
> + cpus_read_lock();
> + for_each_online_cpu(cpu) {
> + struct work_struct *work = per_cpu_ptr(works, cpu);
> +
> + INIT_WORK(work, vmbus_percpu_work);
> + schedule_work_on(cpu, work);
> + }
> +
> + for_each_online_cpu(cpu)
> + flush_work(per_cpu_ptr(works, cpu));
> +
> + ret = __cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online", false,
> + hv_synic_init, hv_synic_cleanup, false);
I'd suggest using cpuhp_setup_state_nocalls_cpuslocked(). It appears to be
the interface intended for users outside the cpuhotplug code, whereas
__cpuhp_setup_state_cpuslocked() should be private to the cpuhotplug code.
Michael
> + cpus_read_unlock();
> + free_percpu(works);
> if (ret < 0)
> goto err_alloc;
> hyperv_cpuhp_online = ret;
> --
> 2.43.0
>
