mirror of
https://github.com/torvalds/linux.git
synced 2024-12-04 01:51:34 +00:00
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
This commit is contained in:
parent
83527ef7ab
commit
b264f57fde
@ -194,10 +194,20 @@ do_ex_hypercall:
|
||||
|
||||
static bool __send_ipi_one(int cpu, int vector)
|
||||
{
|
||||
struct cpumask mask = CPU_MASK_NONE;
|
||||
int vp = hv_cpu_number_to_vp_number(cpu);
|
||||
|
||||
cpumask_set_cpu(cpu, &mask);
|
||||
return __send_ipi_mask(&mask, vector);
|
||||
trace_hyperv_send_ipi_one(cpu, vector);
|
||||
|
||||
if (!hv_hypercall_pg || (vp == VP_INVAL))
|
||||
return false;
|
||||
|
||||
if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
|
||||
return false;
|
||||
|
||||
if (vp >= 64)
|
||||
return __send_ipi_mask_ex(cpumask_of(cpu), vector);
|
||||
|
||||
return !hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
|
||||
}
|
||||
|
||||
static void hv_send_ipi(int cpu, int vector)
|
||||
|
@ -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
|
||||
|
Loading…
Reference in New Issue
Block a user