lkml.org 
[lkml]   [2021]   [Feb]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 3/3] kernel/smp: add more data to CSD lock debugging
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@vmware.com
>
> 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.

\
 
 \ /
  Last update: 2021-02-26 19:14    [W:0.551 / U:0.256 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site