From 87b940a0675e25261f022ac3e53e0dfff9cdb995 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 11 Nov 2021 02:07:30 +0000 Subject: perf/core: Use static_call to optimize perf_guest_info_callbacks Use static_call to optimize perf's guest callbacks on arm64 and x86, which are now the only architectures that define the callbacks. Use DEFINE_STATIC_CALL_RET0 as the default/NULL for all guest callbacks, as the callback semantics are that a return value '0' means "not in guest". static_call obviously avoids the overhead of CONFIG_RETPOLINE=y, but is also advantageous versus other solutions, e.g. per-cpu callbacks, in that a per-cpu memory load is not needed to detect the !guest case. Based on code from Peter and Like. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20211111020738.2512932-10-seanjc@google.com --- kernel/events/core.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'kernel/events') diff --git a/kernel/events/core.c b/kernel/events/core.c index 5a3502cd5362..3b3297a57228 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6524,12 +6524,23 @@ static void perf_pending_event(struct irq_work *entry) #ifdef CONFIG_GUEST_PERF_EVENTS struct perf_guest_info_callbacks __rcu *perf_guest_cbs; +DEFINE_STATIC_CALL_RET0(__perf_guest_state, *perf_guest_cbs->state); +DEFINE_STATIC_CALL_RET0(__perf_guest_get_ip, *perf_guest_cbs->get_ip); +DEFINE_STATIC_CALL_RET0(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); + void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) { if (WARN_ON_ONCE(rcu_access_pointer(perf_guest_cbs))) return; rcu_assign_pointer(perf_guest_cbs, cbs); + static_call_update(__perf_guest_state, cbs->state); + static_call_update(__perf_guest_get_ip, cbs->get_ip); + + /* Implementing ->handle_intel_pt_intr is optional. */ + if (cbs->handle_intel_pt_intr) + static_call_update(__perf_guest_handle_intel_pt_intr, + cbs->handle_intel_pt_intr); } EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks); @@ -6539,6 +6550,10 @@ void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) return; rcu_assign_pointer(perf_guest_cbs, NULL); + static_call_update(__perf_guest_state, (void *)&__static_call_return0); + static_call_update(__perf_guest_get_ip, (void *)&__static_call_return0); + static_call_update(__perf_guest_handle_intel_pt_intr, + (void *)&__static_call_return0); synchronize_rcu(); } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); -- cgit v1.2.3