When sending an IPI to a single CPU there is no need to deal with cpumasks.
With 2 CPU guest on WS2019 I'm seeing a minor (like 3%, 8043 -> 7761 CPU
cycles) improvement with smp_call_function_single() loop benchmark. The
optimization, however, is tiny and straitforward. Also, send_ipi_one() is
important for PV spinlock kick.
I was also wondering if it would make sense to switch to using regular
APIC IPI send for CPU > 64 case but no, 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@xxxxxxxxxx>
---
arch/x86/hyperv/hv_apic.c | 22 +++++++++++++++++++---
arch/x86/include/asm/trace/hyperv.h | 15 +++++++++++++++
2 files changed, 34 insertions(+), 3 deletions(-)
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index e01078e93dd3..847f9d0328fe 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -194,10 +194,26 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
static bool __send_ipi_one(int cpu, int vector)
{
- struct cpumask mask = CPU_MASK_NONE;
+ int ret;
- cpumask_set_cpu(cpu, &mask);
- return __send_ipi_mask(&mask, vector);
+ trace_hyperv_send_ipi_one(cpu, vector);
+
+ if (unlikely(!hv_hypercall_pg))
+ return false;
+
+ if (unlikely((vector < HV_IPI_LOW_VECTOR) ||
+ (vector > HV_IPI_HIGH_VECTOR)))
+ return false;
+
+ if (cpu >= 64)
+ goto do_ex_hypercall;
+
+ ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector,
+ BIT_ULL(hv_cpu_number_to_vp_number(cpu)));
+ return ((ret == 0) ? true : false);
+
+do_ex_hypercall:
+ return __send_ipi_mask_ex(cpumask_of(cpu), vector);
}
static void hv_send_ipi(int cpu, int vector)
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
--
2.20.1
