i5 1240p使用perf避坑指南

新入手了一台小米迷你主机，CPU是英特尔的十二代i5 1240p，intel i5 1240p微架构属于alder lake，有4个大核，8个小核，每个大核有两个线程，因此，该CPU多线程能力为12核16线程。最近在研究性能剖析相关的知识，没想到遇到了不少坑，记于此。

Perf on WSL（cycles:u not supported）

首先尝试了在windows wsl中使用perf

$ sudo apt install linux-tools-generic

安装的可执行程序位于/usr/lib/linux-tools/\<kernel version>/perf

$ perf stat ls
Performance counter stats for 'ls':

              0.76 msec task-clock:u              #    0.706 CPUs utilized
                 0      context-switches:u        #    0.000 /sec
                 0      cpu-migrations:u          #    0.000 /sec
               113      page-faults:u             #  149.431 K/sec
   <not supported>      cycles:u
   <not supported>      instructions:u
   <not supported>      branches:u
   <not supported>      branch-misses:u

       0.001070439 seconds time elapsed

       0.001058000 seconds user
       0.000000000 seconds sys

查看pmu驱动，结果是这样的

$ dmesg | grep PMU

$ dmesg | grep PMU
[    0.094674] Performance Events: unsupported p6 CPU model 154 no PMU driver, software events only.
$ lscpu
Architecture:                    x86_64
CPU op-mode(s):                  32-bit, 64-bit
Byte Order:                      Little Endian
Address sizes:                   39 bits physical, 48 bits virtual
CPU(s):                          16
On-line CPU(s) list:             0-15
Thread(s) per core:              2
Core(s) per socket:              8
Socket(s):                       1
Vendor ID:                       GenuineIntel
CPU family:                      6
Model:                           154
Model name:                      12th Gen Intel(R) Core(TM) i5-1240P
Stepping:                        3
CPU MHz:                         2112.007
BogoMIPS:                        4224.01
Virtualization:                  VT-x
Hypervisor vendor:               Microsoft
Virtualization type:             full
L1d cache:                       384 KiB
L1i cache:                       256 KiB
L2 cache:                        10 MiB
L3 cache:                        12 MiB
Vulnerability Itlb multihit:     Not affected
Vulnerability L1tf:              Not affected
Vulnerability Mds:               Not affected
Vulnerability Meltdown:          Not affected
Vulnerability Mmio stale data:   Not affected
Vulnerability Retbleed:          Mitigation; Enhanced IBRS
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:        Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Not affected
Flags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxs
                                 r sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology tsc_
                                 reliable nonstop_tsc cpuid pni pclmulqdq vmx ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic m
                                 ovbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowpr
                                 efetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi ept vpid ept_a
                                 d fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb
                                 sha_ni xsaveopt xsavec xgetbv1 xsaves avx_vnni umip waitpkg gfni vaes vpclmulqdq rdpid
                                 movdiri movdir64b fsrm serialize flush_l1d arch_capabilities

Flags中没有看到arch_perfmon，也就是说Hardware Performance Monitor没有使能

Perf On Hyper-V

再试一下通过Hyper-V行不行，我已经使能了Hyper-V，然后通过微软这篇官方[1]文档使能pmu

$ # Enable IPT
Set-VMProcessor MyVMName -Perfmon @("ipt", "pmu")

再启动Hyper-V虚拟机，直接报错找不到系统监视器，启动失败

小米迷你主机安装Ubuntu

一开始安装的20.04，发现wifi驱动没有适配，为了省事，直接安装22.04。装完之后，pmu能正常使用了。

 Performance counter stats for 'ls':

              0.78 msec task-clock                #    0.548 CPUs utilized          
                 0      context-switches          #    0.000 /sec                   
                 0      cpu-migrations            #    0.000 /sec                   
                91      page-faults               #  116.387 K/sec                  
         1,448,050      cpu_core/cycles/          #    1.852 G/sec                  
     <not counted>      cpu_atom/cycles/                                              (0.00%)
         1,749,783      cpu_core/instructions/    #    2.238 G/sec                  
     <not counted>      cpu_atom/instructions/                                        (0.00%)
           325,300      cpu_core/branches/        #  416.052 M/sec                  
     <not counted>      cpu_atom/branches/                                            (0.00%)
             9,590      cpu_core/branch-misses/   #   12.265 M/sec                  
     <not counted>      cpu_atom/branch-misses/                                       (0.00%)

       0.001426852 seconds time elapsed

       0.001447000 seconds user
       0.000000000 seconds sys

推荐一个烧录镜像工具，Rufus，功能简单清晰

参考文献

[1]: https://learn.microsoft.com/zh-cn/windows-server/virtualization/hyper-v/manage/performance-monitoring-hardware