summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/trace
diff options
context:
space:
mode:
authorVitaly Kuznetsov <vkuznets@redhat.com>2019-10-27 18:19:38 +0300
committerThomas Gleixner <tglx@linutronix.de>2019-11-12 13:44:20 +0300
commitb264f57fde0c686c5c1dfdd0c21992c49196bb87 (patch)
tree2e77028b7799efca17bca51e4fe494f3aec6087f /arch/x86/include/asm/trace
parent83527ef7abf7c02c33a90b00f0954db35415adbd (diff)
downloadlinux-b264f57fde0c686c5c1dfdd0c21992c49196bb87.tar.xz
x86/hyperv: Micro-optimize send_ipi_one()
When sending an IPI to a single CPU there is no need to deal with cpumasks. With 2 CPU guest on WS2019 a minor (like 3%, 8043 -> 7761 CPU cycles) improvement with smp_call_function_single() loop benchmark can be seeb. The optimization, however, is tiny and straitforward. Also, send_ipi_one() is important for PV spinlock kick. Switching to the regular APIC IPI send for CPU > 64 case does not make sense as it is twice as expesive (12650 CPU cycles for __send_ipi_mask_ex() call, 26000 for orig_apic.send_IPI(cpu, vector)). Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Reviewed-by: Roman Kagan <rkagan@virtuozzo.com> Link: https://lkml.kernel.org/r/20191027151938.7296-1-vkuznets@redhat.com
Diffstat (limited to 'arch/x86/include/asm/trace')
-rw-r--r--arch/x86/include/asm/trace/hyperv.h15
1 files changed, 15 insertions, 0 deletions
diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h
index ace464f09681..4d705cb4d63b 100644
--- a/arch/x86/include/asm/trace/hyperv.h
+++ b/arch/x86/include/asm/trace/hyperv.h
@@ -71,6 +71,21 @@ TRACE_EVENT(hyperv_send_ipi_mask,
__entry->ncpus, __entry->vector)
);
+TRACE_EVENT(hyperv_send_ipi_one,
+ TP_PROTO(int cpu,
+ int vector),
+ TP_ARGS(cpu, vector),
+ TP_STRUCT__entry(
+ __field(int, cpu)
+ __field(int, vector)
+ ),
+ TP_fast_assign(__entry->cpu = cpu;
+ __entry->vector = vector;
+ ),
+ TP_printk("cpu %d vector %x",
+ __entry->cpu, __entry->vector)
+ );
+
#endif /* CONFIG_HYPERV */
#undef TRACE_INCLUDE_PATH