diff mbox series

[v5,1/7] trace: Add trace_ipi_send_cpumask()

Message ID 20230307143558.294354-2-vschneid@redhat.com
State New
Headers show
Series Generic IPI sending tracepoint | expand

Commit Message

Valentin Schneider March 7, 2023, 2:35 p.m. UTC 
trace_ipi_raise() is unsuitable for generically tracing IPI sources due to
its "reason" argument being an uninformative string (on arm64 all you get
is "Function call interrupts" for SMP calls).

Add a variant of it that exports a target cpumask, a callsite and a callback.

Signed-off-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/trace/events/ipi.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

Comments

Peter Zijlstra March 22, 2023, 9:39 a.m. UTC | #1 
On Tue, Mar 07, 2023 at 02:35:52PM +0000, Valentin Schneider wrote:
> trace_ipi_raise() is unsuitable for generically tracing IPI sources due to
> its "reason" argument being an uninformative string (on arm64 all you get
> is "Function call interrupts" for SMP calls).
> 
> Add a variant of it that exports a target cpumask, a callsite and a callback.
> 
> Signed-off-by: Valentin Schneider <vschneid@redhat.com>
> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
> ---
>  include/trace/events/ipi.h | 22 ++++++++++++++++++++++
>  1 file changed, 22 insertions(+)
> 
> diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h
> index 0be71dad6ec03..b1125dc27682c 100644
> --- a/include/trace/events/ipi.h
> +++ b/include/trace/events/ipi.h
> @@ -35,6 +35,28 @@ TRACE_EVENT(ipi_raise,
>  	TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason)
>  );
>  
> +TRACE_EVENT(ipi_send_cpumask,
> +
> +	TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback),
> +
> +	TP_ARGS(cpumask, callsite, callback),
> +
> +	TP_STRUCT__entry(
> +		__cpumask(cpumask)
> +		__field(void *, callsite)
> +		__field(void *, callback)
> +	),
> +
> +	TP_fast_assign(
> +		__assign_cpumask(cpumask, cpumask_bits(cpumask));
> +		__entry->callsite = (void *)callsite;
> +		__entry->callback = callback;
> +	),
> +
> +	TP_printk("cpumask=%s callsite=%pS callback=%pS",
> +		  __get_cpumask(cpumask), __entry->callsite, __entry->callback)
> +);

Would it make sense to add a variant like: ipi_send_cpu() that records a
single cpu instead of a cpumask. A lot of sites seems to do:
cpumask_of(cpu) for that first argument, and it seems to me it is quite
daft to have to memcpy a full multi-word cpumask in those cases.

Remember, nr_possible_cpus > 64 is quite common these days.
Peter Zijlstra March 22, 2023, 10:30 a.m. UTC | #2 
On Wed, Mar 22, 2023 at 10:39:55AM +0100, Peter Zijlstra wrote:
> On Tue, Mar 07, 2023 at 02:35:52PM +0000, Valentin Schneider wrote:
> > trace_ipi_raise() is unsuitable for generically tracing IPI sources due to
> > its "reason" argument being an uninformative string (on arm64 all you get
> > is "Function call interrupts" for SMP calls).
> > 
> > Add a variant of it that exports a target cpumask, a callsite and a callback.
> > 
> > Signed-off-by: Valentin Schneider <vschneid@redhat.com>
> > Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
> > ---
> >  include/trace/events/ipi.h | 22 ++++++++++++++++++++++
> >  1 file changed, 22 insertions(+)
> > 
> > diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h
> > index 0be71dad6ec03..b1125dc27682c 100644
> > --- a/include/trace/events/ipi.h
> > +++ b/include/trace/events/ipi.h
> > @@ -35,6 +35,28 @@ TRACE_EVENT(ipi_raise,
> >  	TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason)
> >  );
> >  
> > +TRACE_EVENT(ipi_send_cpumask,
> > +
> > +	TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback),
> > +
> > +	TP_ARGS(cpumask, callsite, callback),
> > +
> > +	TP_STRUCT__entry(
> > +		__cpumask(cpumask)
> > +		__field(void *, callsite)
> > +		__field(void *, callback)
> > +	),
> > +
> > +	TP_fast_assign(
> > +		__assign_cpumask(cpumask, cpumask_bits(cpumask));
> > +		__entry->callsite = (void *)callsite;
> > +		__entry->callback = callback;
> > +	),
> > +
> > +	TP_printk("cpumask=%s callsite=%pS callback=%pS",
> > +		  __get_cpumask(cpumask), __entry->callsite, __entry->callback)
> > +);
> 
> Would it make sense to add a variant like: ipi_send_cpu() that records a
> single cpu instead of a cpumask. A lot of sites seems to do:
> cpumask_of(cpu) for that first argument, and it seems to me it is quite
> daft to have to memcpy a full multi-word cpumask in those cases.
> 
> Remember, nr_possible_cpus > 64 is quite common these days.

Something we litte bit like so...

---
Subject: trace: Add trace_ipi_send_cpu()
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed Mar 22 11:28:36 CET 2023

Because copying cpumasks around when targeting a single CPU is a bit
daft...

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/smp.h        |    6 +++---
 include/trace/events/ipi.h |   22 ++++++++++++++++++++++
 kernel/irq_work.c          |    6 ++----
 kernel/smp.c               |    4 ++--
 4 files changed, 29 insertions(+), 9 deletions(-)

--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -130,9 +130,9 @@ extern void arch_smp_send_reschedule(int
  * scheduler_ipi() is inline so can't be passed as callback reason, but the
  * callsite IP should be sufficient for root-causing IPIs sent from here.
  */
-#define smp_send_reschedule(cpu) ({				  \
-	trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL);  \
-	arch_smp_send_reschedule(cpu);				  \
+#define smp_send_reschedule(cpu) ({		  \
+	trace_ipi_send_cpu(cpu, _RET_IP_, NULL);  \
+	arch_smp_send_reschedule(cpu);		  \
 })
 
 /*
--- a/include/trace/events/ipi.h
+++ b/include/trace/events/ipi.h
@@ -35,6 +35,28 @@ TRACE_EVENT(ipi_raise,
 	TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason)
 );
 
+TRACE_EVENT(ipi_send_cpu,
+
+	TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback),
+
+	TP_ARGS(cpu, callsite, callback),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, cpu)
+		__field(void *, callsite)
+		__field(void *, callback)
+	),
+
+	TP_fast_assign(
+		__entry->cpu = cpu;
+		__entry->callsite = (void *)callsite;
+		__entry->callback = callback;
+	),
+
+	TP_printk("cpu=%s callsite=%pS callback=%pS",
+		  __entry->cpu, __entry->callsite, __entry->callback)
+);
+
 TRACE_EVENT(ipi_send_cpumask,
 
 	TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback),
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -78,10 +78,8 @@ void __weak arch_irq_work_raise(void)
 
 static __always_inline void irq_work_raise(struct irq_work *work)
 {
-	if (trace_ipi_send_cpumask_enabled() && arch_irq_work_has_interrupt())
-		trace_ipi_send_cpumask(cpumask_of(smp_processor_id()),
-				       _RET_IP_,
-				       work->func);
+	if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt())
+		trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func);
 
 	arch_irq_work_raise();
 }
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -109,7 +109,7 @@ static __always_inline void
 send_call_function_single_ipi(int cpu, smp_call_func_t func)
 {
 	if (call_function_single_prep_ipi(cpu)) {
-		trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, func);
+		trace_ipi_send_cpu(cpu, _RET_IP_, func);
 		arch_send_call_function_single_ipi(cpu);
 	}
 }
@@ -348,7 +348,7 @@ void __smp_call_single_queue(int cpu, st
 	 * even if we haven't sent the smp_call IPI yet (e.g. the stopper
 	 * executes migration_cpu_stop() on the remote CPU).
 	 */
-	if (trace_ipi_send_cpumask_enabled()) {
+	if (trace_ipi_send_cpu_enabled()) {
 		call_single_data_t *csd;
 		smp_call_func_t func;
Valentin Schneider March 22, 2023, 11:24 a.m. UTC | #3 
On 22/03/23 11:30, Peter Zijlstra wrote:
> On Wed, Mar 22, 2023 at 10:39:55AM +0100, Peter Zijlstra wrote:
>> On Tue, Mar 07, 2023 at 02:35:52PM +0000, Valentin Schneider wrote:
>> > +TRACE_EVENT(ipi_send_cpumask,
>> > +
>> > +	TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback),
>> > +
>> > +	TP_ARGS(cpumask, callsite, callback),
>> > +
>> > +	TP_STRUCT__entry(
>> > +		__cpumask(cpumask)
>> > +		__field(void *, callsite)
>> > +		__field(void *, callback)
>> > +	),
>> > +
>> > +	TP_fast_assign(
>> > +		__assign_cpumask(cpumask, cpumask_bits(cpumask));
>> > +		__entry->callsite = (void *)callsite;
>> > +		__entry->callback = callback;
>> > +	),
>> > +
>> > +	TP_printk("cpumask=%s callsite=%pS callback=%pS",
>> > +		  __get_cpumask(cpumask), __entry->callsite, __entry->callback)
>> > +);
>>
>> Would it make sense to add a variant like: ipi_send_cpu() that records a
>> single cpu instead of a cpumask. A lot of sites seems to do:
>> cpumask_of(cpu) for that first argument, and it seems to me it is quite
>> daft to have to memcpy a full multi-word cpumask in those cases.
>>
>> Remember, nr_possible_cpus > 64 is quite common these days.
>
> Something we litte bit like so...
>

I was wondering whether we could stick with a single trace event, but let
ftrace be aware of weight=1 vs weight>1 cpumasks.

For weight>1, it would memcpy() as usual, for weight=1, it could write a
pointer to a cpu_bit_bitmap[] equivalent embedded in the trace itself.

Unfortunately, Ftrace bitmasks are represented as a u32 made of two 16 bit
values: [offset in event record, size], so there isn't a straightforward
way to point to a "reusable" cpumask. AFAICT the only alternative would be
to do that via a different trace event, but then we should just go with a
plain old uint - i.e. do what you're doing here, so:

Tested-and-reviewed-by: Valentin Schneider <vschneid@redhat.com>

(with the tiny typo fix below)

> @@ -35,6 +35,28 @@ TRACE_EVENT(ipi_raise,
>       TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason)
>  );
>
> +TRACE_EVENT(ipi_send_cpu,
> +
> +	TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback),
> +
> +	TP_ARGS(cpu, callsite, callback),
> +
> +	TP_STRUCT__entry(
> +		__field(unsigned int, cpu)
> +		__field(void *, callsite)
> +		__field(void *, callback)
> +	),
> +
> +	TP_fast_assign(
> +		__entry->cpu = cpu;
> +		__entry->callsite = (void *)callsite;
> +		__entry->callback = callback;
> +	),
> +
> +	TP_printk("cpu=%s callsite=%pS callback=%pS",
                        ^
                      s/s/u/

> +		  __entry->cpu, __entry->callsite, __entry->callback)
> +);
> +
diff mbox series

Patch

diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h
index 0be71dad6ec03..b1125dc27682c 100644
--- a/include/trace/events/ipi.h
+++ b/include/trace/events/ipi.h
@@ -35,6 +35,28 @@  TRACE_EVENT(ipi_raise,
 	TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason)
 );
 
+TRACE_EVENT(ipi_send_cpumask,
+
+	TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback),
+
+	TP_ARGS(cpumask, callsite, callback),
+
+	TP_STRUCT__entry(
+		__cpumask(cpumask)
+		__field(void *, callsite)
+		__field(void *, callback)
+	),
+
+	TP_fast_assign(
+		__assign_cpumask(cpumask, cpumask_bits(cpumask));
+		__entry->callsite = (void *)callsite;
+		__entry->callback = callback;
+	),
+
+	TP_printk("cpumask=%s callsite=%pS callback=%pS",
+		  __get_cpumask(cpumask), __entry->callsite, __entry->callback)
+);
+
 DECLARE_EVENT_CLASS(ipi_handler,
 
 	TP_PROTO(const char *reason),