Re: [PATCH bpf-next v2 02/18] x86,bpf: add bpf_global_caller for global trampoline

[Menglong Dong <menglong.dong@linux.dev>]

On 7/15/25 16:36, Menglong Dong wrote:
>
> On 7/15/25 10:25, Alexei Starovoitov wrote:
>> Pls share top 10 from "perf report" while running the bench.
>> I'm curious about what's hot.
>> Last time I benchmarked fentry/fexit migrate_disable/enable were
>> one the hottest functions. I suspect it's the case here as well.
>
>
> You are right, the migrate_disable/enable are the hottest functions in
> both bpf trampoline and global trampoline. Following is the perf top
> for fentry-multi:
> 36.36% bpf_prog_2dcccf652aac1793_bench_trigger_fentry_multi [k] 
> bpf_prog_2dcccf652aac1793_bench_trigger_fentry_multi 20.54% [kernel] 
> [k] migrate_enable 19.35% [kernel] [k] bpf_global_caller_5_run 6.52% 
> [kernel] [k] bpf_global_caller_5 3.58% libc.so.6 [.] syscall 2.88% 
> [kernel] [k] entry_SYSCALL_64 1.50% [kernel] [k] memchr_inv 1.39% 
> [kernel] [k] fput 1.04% [kernel] [k] migrate_disable 0.91% [kernel] 
> [k] _copy_to_user
>
> And I also did the testing for fentry:
>
> 54.63% bpf_prog_2dcccf652aac1793_bench_trigger_fentry [k] 
> bpf_prog_2dcccf652aac1793_bench_trigger_fentry
> 10.43% [kernel] [k] migrate_enable
> 10.07% bpf_trampoline_6442517037 [k] bpf_trampoline_6442517037
> 8.06% [kernel] [k] __bpf_prog_exit_recur 4.11% libc.so.6 [.] syscall 
> 2.15% [kernel] [k] entry_SYSCALL_64 1.48% [kernel] [k] memchr_inv 
> 1.32% [kernel] [k] fput 1.16% [kernel] [k] _copy_to_user 0.73% 
> [kernel] [k] bpf_prog_test_run_raw_tp
> The migrate_enable/disable are used to do the recursive checking,
> and I even wanted to perform recursive checks in the same way as
> ftrace to eliminate this overhead :/
>

Sorry that I'm not familiar with Thunderbird yet, and the perf top
messed up. Following are the test results for fentry-multi:
   36.36% bpf_prog_2dcccf652aac1793_bench_trigger_fentry_multi [k] 
bpf_prog_2dcccf652aac1793_bench_trigger_fentry_multi
   20.54% [kernel] [k] migrate_enable
   19.35% [kernel] [k] bpf_global_caller_5_run
   6.52% [kernel] [k] bpf_global_caller_5
   3.58% libc.so.6 [.] syscall
   2.88% [kernel] [k] entry_SYSCALL_64
   1.50% [kernel] [k] memchr_inv
   1.39% [kernel] [k] fput
   1.04% [kernel] [k] migrate_disable
   0.91% [kernel] [k] _copy_to_user

And I also did the testing for fentry:
   54.63% bpf_prog_2dcccf652aac1793_bench_trigger_fentry [k] 
bpf_prog_2dcccf652aac1793_bench_trigger_fentry
   10.43% [kernel] [k] migrate_enable
   10.07% bpf_trampoline_6442517037 [k] bpf_trampoline_6442517037
   8.06% [kernel] [k] __bpf_prog_exit_recur
   4.11% libc.so.6 [.] syscall
   2.15% [kernel] [k] entry_SYSCALL_64
   1.48% [kernel] [k] memchr_inv
   1.32% [kernel] [k] fput
   1.16% [kernel] [k] _copy_to_user
   0.73% [kernel] [k] bpf_prog_test_run_raw_tp

The migrate_enable/disable are used to do the recursive checking,
and I even wanted to perform recursive checks in the same way as
ftrace to eliminate this overhead :/

Thanks!
Menglong Dong