Re: [PATCH 3/3] kernel/smp: add more data to CSD lock debugging
From: Paul E. McKenney
Date: Fri Feb 26 2021 - 13:13:05 EST
On Fri, Feb 26, 2021 at 05:38:44PM +0100, Peter Zijlstra wrote:
>
>
I hate all of this, but if this will finally catch the actual problem,
>
we can then revert all this, so sure.
OK, I will bite... What exactly do you hate about it?
Thanx, Paul
>
Also, I think this will conflict with the patches from Nadav that I have
>
queued:
>
>
https://lkml.kernel.org/r/20210220231712.2475218-1-namit@xxxxxxxxxx
>
>
which I'll be pushing to tip/x86/mm once -rc1 happens.
>
>
On Fri, Feb 26, 2021 at 12:25:21PM +0100, Juergen Gross wrote:
>
>
> +static void __smp_call_single_queue_debug(int cpu, struct llist_node *node)
>
> +{
>
> + unsigned int this_cpu = smp_processor_id();
>
> + struct cfd_seq_local *seq = this_cpu_ptr(&cfd_seq_local);
>
> + struct call_function_data *cfd = this_cpu_ptr(&cfd_data);
>
> + struct cfd_percpu *pcpu = per_cpu_ptr(cfd->pcpu, cpu);
>
> +
>
> + cfd_seq_store(pcpu->seq_queue, this_cpu, cpu, CFD_SEQ_QUEUE);
>
> + if (llist_add(node, &per_cpu(call_single_queue, cpu))) {
>
> + cfd_seq_store(pcpu->seq_ipi, this_cpu, cpu, CFD_SEQ_IPI);
>
> + cfd_seq_store(seq->ping, this_cpu, cpu, CFD_SEQ_PING);
>
> + send_call_function_single_ipi(cpu);
>
> + cfd_seq_store(seq->pinged, this_cpu, cpu, CFD_SEQ_PINGED);
>
> + } else {
>
> + cfd_seq_store(pcpu->seq_noipi, this_cpu, cpu, CFD_SEQ_NOIPI);
>
> + }
>
> +}
>
> #else
>
> +#define cfd_seq_store(var, src, dst, type)
>
> +
>
> static void csd_lock_record(call_single_data_t *csd)
>
> {
>
> }
>
> @@ -290,6 +396,19 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data);
>
>
>
> void __smp_call_single_queue(int cpu, struct llist_node *node)
>
> {
>
> +#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
>
> + if (static_branch_unlikely(&csdlock_debug_extended)) {
>
> + unsigned int type;
>
> +
>
> + type = CSD_TYPE(container_of(node, call_single_data_t,
>
> + node.llist));
>
> + if (type == CSD_TYPE_SYNC || type == CSD_TYPE_ASYNC) {
>
> + __smp_call_single_queue_debug(cpu, node);
>
> + return;
>
> + }
>
> + }
>
> +#endif
>
>
This is a bit weird, might as well put it in generic_exec_single()
>
because there you still know the type matches.
>
>
>
> @@ -712,12 +840,21 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
>
> csd->node.src = smp_processor_id();
>
> csd->node.dst = cpu;
>
> #endif
>
> - if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu)))
>
> + cfd_seq_store(pcpu->seq_queue, this_cpu, cpu, CFD_SEQ_QUEUE);
>
> + if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) {
>
> __cpumask_set_cpu(cpu, cfd->cpumask_ipi);
>
> + cfd_seq_store(pcpu->seq_ipi, this_cpu, cpu, CFD_SEQ_IPI);
>
> + } else {
>
> + cfd_seq_store(pcpu->seq_noipi, this_cpu, cpu, CFD_SEQ_NOIPI);
>
> + }
>
> }
>
>
>
> /* Send a message to all CPUs in the map */
>
> + cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->ping, this_cpu,
>
> + CFD_SEQ_NOCPU, CFD_SEQ_PING);
>
> arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
>
> + cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->pinged, this_cpu,
>
> + CFD_SEQ_NOCPU, CFD_SEQ_PINGED);
>
>
Too bad we can't share with the single case, a well.