mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
b264f57fde
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
99 lines
2.4 KiB
C
99 lines
2.4 KiB
C
#undef TRACE_SYSTEM
|
|
#define TRACE_SYSTEM hyperv
|
|
|
|
#if !defined(_TRACE_HYPERV_H) || defined(TRACE_HEADER_MULTI_READ)
|
|
#define _TRACE_HYPERV_H
|
|
|
|
#include <linux/tracepoint.h>
|
|
|
|
#if IS_ENABLED(CONFIG_HYPERV)
|
|
|
|
TRACE_EVENT(hyperv_mmu_flush_tlb_others,
|
|
TP_PROTO(const struct cpumask *cpus,
|
|
const struct flush_tlb_info *info),
|
|
TP_ARGS(cpus, info),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned int, ncpus)
|
|
__field(struct mm_struct *, mm)
|
|
__field(unsigned long, addr)
|
|
__field(unsigned long, end)
|
|
),
|
|
TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
|
|
__entry->mm = info->mm;
|
|
__entry->addr = info->start;
|
|
__entry->end = info->end;
|
|
),
|
|
TP_printk("ncpus %d mm %p addr %lx, end %lx",
|
|
__entry->ncpus, __entry->mm,
|
|
__entry->addr, __entry->end)
|
|
);
|
|
|
|
TRACE_EVENT(hyperv_nested_flush_guest_mapping,
|
|
TP_PROTO(u64 as, int ret),
|
|
TP_ARGS(as, ret),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(u64, as)
|
|
__field(int, ret)
|
|
),
|
|
TP_fast_assign(__entry->as = as;
|
|
__entry->ret = ret;
|
|
),
|
|
TP_printk("address space %llx ret %d", __entry->as, __entry->ret)
|
|
);
|
|
|
|
TRACE_EVENT(hyperv_nested_flush_guest_mapping_range,
|
|
TP_PROTO(u64 as, int ret),
|
|
TP_ARGS(as, ret),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(u64, as)
|
|
__field(int, ret)
|
|
),
|
|
TP_fast_assign(__entry->as = as;
|
|
__entry->ret = ret;
|
|
),
|
|
TP_printk("address space %llx ret %d", __entry->as, __entry->ret)
|
|
);
|
|
|
|
TRACE_EVENT(hyperv_send_ipi_mask,
|
|
TP_PROTO(const struct cpumask *cpus,
|
|
int vector),
|
|
TP_ARGS(cpus, vector),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned int, ncpus)
|
|
__field(int, vector)
|
|
),
|
|
TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
|
|
__entry->vector = vector;
|
|
),
|
|
TP_printk("ncpus %d vector %x",
|
|
__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
|
|
#define TRACE_INCLUDE_PATH asm/trace/
|
|
#undef TRACE_INCLUDE_FILE
|
|
#define TRACE_INCLUDE_FILE hyperv
|
|
#endif /* _TRACE_HYPERV_H */
|
|
|
|
/* This part must be outside protection */
|
|
#include <trace/define_trace.h>
|