From cc9cb0a71725aa8dd8d8f534a9b562bbf7981f75 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:53 +0000 Subject: sched, smp: Trace IPIs sent via send_call_function_single_ipi() send_call_function_single_ipi() is the thing that sends IPIs at the bottom of smp_call_function*() via either generic_exec_single() or smp_call_function_many_cond(). Give it an IPI-related tracepoint. Note that this ends up tracing any IPI sent via __smp_call_single_queue(), which covers __ttwu_queue_wakelist() and irq_work_queue_on() "for free". Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Acked-by: Ingo Molnar Link: https://lore.kernel.org/r/20230307143558.294354-3-vschneid@redhat.com --- kernel/sched/core.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 488655f2319f..c26a2cd99ec7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -80,6 +80,7 @@ #define CREATE_TRACE_POINTS #include #include +#include #undef CREATE_TRACE_POINTS #include "sched.h" @@ -95,6 +96,8 @@ #include "../../io_uring/io-wq.h" #include "../smpboot.h" +EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask); + /* * Export tracepoints that act as a bare tracehook (ie: have no trace event * associated with them) to allow external modules to probe them. @@ -3830,10 +3833,12 @@ void send_call_function_single_ipi(int cpu) { struct rq *rq = cpu_rq(cpu); - if (!set_nr_if_polling(rq->idle)) + if (!set_nr_if_polling(rq->idle)) { + trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL); arch_send_call_function_single_ipi(cpu); - else + } else { trace_sched_wake_idle_without_ipi(cpu); + } } /* -- cgit v1.2.3 From 68f4ff04dbada18dad79659c266a8e5e29e458cd Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:58 +0000 Subject: sched, smp: Trace smp callback causing an IPI Context ======= The newly-introduced ipi_send_cpumask tracepoint has a "callback" parameter which so far has only been fed with NULL. While CSD_TYPE_SYNC/ASYNC and CSD_TYPE_IRQ_WORK share a similar backing struct layout (meaning their callback func can be accessed without caring about the actual CSD type), CSD_TYPE_TTWU doesn't even have a function attached to its struct. This means we need to check the type of a CSD before eventually dereferencing its associated callback. This isn't as trivial as it sounds: the CSD type is stored in __call_single_node.u_flags, which get cleared right before the callback is executed via csd_unlock(). This implies checking the CSD type before it is enqueued on the call_single_queue, as the target CPU's queue can be flushed before we get to sending an IPI. Furthermore, send_call_function_single_ipi() only has a CPU parameter, and would need to have an additional argument to trickle down the invoked function. This is somewhat silly, as the extra argument will always be pushed down to the function even when nothing is being traced, which is unnecessary overhead. Changes ======= send_call_function_single_ipi() is only used by smp.c, and is defined in sched/core.c as it contains scheduler-specific ops (set_nr_if_polling() of a CPU's idle task). Split it into two parts: the scheduler bits remain in sched/core.c, and the actual IPI emission is moved into smp.c. This lets us define an __always_inline helper function that can take the related callback as parameter without creating useless register pressure in the non-traced path which only gains a (disabled) static branch. Do the same thing for the multi IPI case. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230307143558.294354-8-vschneid@redhat.com --- kernel/sched/core.c | 18 +++++++++++------- kernel/sched/smp.h | 2 +- kernel/smp.c | 49 +++++++++++++++++++++++++++++++++++++++++-------- 3 files changed, 53 insertions(+), 16 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c26a2cd99ec7..b0a48cfc0a22 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3829,16 +3829,20 @@ void sched_ttwu_pending(void *arg) rq_unlock_irqrestore(rq, &rf); } -void send_call_function_single_ipi(int cpu) +/* + * Prepare the scene for sending an IPI for a remote smp_call + * + * Returns true if the caller can proceed with sending the IPI. + * Returns false otherwise. + */ +bool call_function_single_prep_ipi(int cpu) { - struct rq *rq = cpu_rq(cpu); - - if (!set_nr_if_polling(rq->idle)) { - trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL); - arch_send_call_function_single_ipi(cpu); - } else { + if (set_nr_if_polling(cpu_rq(cpu)->idle)) { trace_sched_wake_idle_without_ipi(cpu); + return false; } + + return true; } /* diff --git a/kernel/sched/smp.h b/kernel/sched/smp.h index 2eb23dd0f285..21ac44428bb0 100644 --- a/kernel/sched/smp.h +++ b/kernel/sched/smp.h @@ -6,7 +6,7 @@ extern void sched_ttwu_pending(void *arg); -extern void send_call_function_single_ipi(int cpu); +extern bool call_function_single_prep_ipi(int cpu); #ifdef CONFIG_SMP extern void flush_smp_call_function_queue(void); diff --git a/kernel/smp.c b/kernel/smp.c index 6bbfabbe62fc..37e9613a0889 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -104,9 +104,18 @@ void __init call_function_init(void) } static __always_inline void -send_call_function_ipi_mask(struct cpumask *mask) +send_call_function_single_ipi(int cpu, smp_call_func_t func) { - trace_ipi_send_cpumask(mask, _RET_IP_, NULL); + if (call_function_single_prep_ipi(cpu)) { + trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, func); + arch_send_call_function_single_ipi(cpu); + } +} + +static __always_inline void +send_call_function_ipi_mask(struct cpumask *mask, smp_call_func_t func) +{ + trace_ipi_send_cpumask(mask, _RET_IP_, func); arch_send_call_function_ipi_mask(mask); } @@ -307,9 +316,8 @@ static __always_inline void csd_unlock(struct __call_single_data *csd) smp_store_release(&csd->node.u_flags, 0); } -static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); - -void __smp_call_single_queue(int cpu, struct llist_node *node) +static __always_inline void +raw_smp_call_single_queue(int cpu, struct llist_node *node, smp_call_func_t func) { /* * The list addition should be visible to the target CPU when it pops @@ -324,7 +332,32 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) - send_call_function_single_ipi(cpu); + send_call_function_single_ipi(cpu, func); +} + +static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); + +void __smp_call_single_queue(int cpu, struct llist_node *node) +{ + /* + * We have to check the type of the CSD before queueing it, because + * once queued it can have its flags cleared by + * flush_smp_call_function_queue() + * 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()) { + call_single_data_t *csd; + smp_call_func_t func; + + csd = container_of(node, call_single_data_t, node.llist); + func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? + sched_ttwu_pending : csd->func; + + raw_smp_call_single_queue(cpu, node, func); + } else { + raw_smp_call_single_queue(cpu, node, NULL); + } } /* @@ -768,9 +801,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask, * provided mask. */ if (nr_cpus == 1) - send_call_function_single_ipi(last_cpu); + send_call_function_single_ipi(last_cpu, func); else if (likely(nr_cpus > 1)) - send_call_function_ipi_mask(cfd->cpumask_ipi); + send_call_function_ipi_mask(cfd->cpumask_ipi, func); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { -- cgit v1.2.3 From 68e2d17c9eb311ab59aeb6d0c38aad8985fa2596 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 22 Mar 2023 11:28:36 +0100 Subject: trace: Add trace_ipi_send_cpu() Because copying cpumasks around when targeting a single CPU is a bit daft... Tested-and-reviewed-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230322103004.GA571242%40hirez.programming.kicks-ass.net --- include/linux/smp.h | 6 +++--- include/trace/events/ipi.h | 22 ++++++++++++++++++++++ kernel/irq_work.c | 6 ++---- kernel/sched/core.c | 1 + kernel/smp.c | 4 ++-- 5 files changed, 30 insertions(+), 9 deletions(-) (limited to 'kernel/sched') diff --git a/include/linux/smp.h b/include/linux/smp.h index c036a2228d8d..ed8f344ba627 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -130,9 +130,9 @@ extern void arch_smp_send_reschedule(int cpu); * 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); \ }) /* diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h index b1125dc27682..3de9bfc982ce 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_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=%u 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), diff --git a/kernel/irq_work.c b/kernel/irq_work.c index c33e88e32a67..2f4fb336dda1 100644 --- 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(); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b0a48cfc0a22..ad40755ddc11 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -96,6 +96,7 @@ #include "../../io_uring/io-wq.h" #include "../smpboot.h" +EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu); EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask); /* diff --git a/kernel/smp.c b/kernel/smp.c index 37e9613a0889..43f0796ecdb2 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -107,7 +107,7 @@ 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); } } @@ -346,7 +346,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) * 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; -- cgit v1.2.3