linux-kernel - Re: Profiling execution time for __alloc_pages

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <CAOVCmzH2+iHDeyzzSvLcAKXfzcWG5fqTvAPkhqJvdKUU-gY3=A@mail.gmail.com>
Date:   Wed, 12 May 2021 23:09:57 +0530
From:   Shivank Garg <shivankgarg98@...il.com>
To:     Yang Shi <shy828301@...il.com>
Cc:     David Hildenbrand <david@...hat.com>,
        Linux MM <linux-mm@...ck.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        gregkh@...uxfoundation.org, sergey.senozhatsky@...il.com,
        pmladek@...e.com
Subject: Re: Profiling execution time for __alloc_pages_nodemask

>> Actually, I want to record the arguments for the memory allocator and
>> filter out the calls I don't need (which are creating noise).
>> For instance, I'm only interested in particular order and flags.

>BPF can do so too. You can either attach to kprobe or tracepoint, then
>filter out the calls by the function's parameters or tracepoint's
>fields.

Thanks Yang for the suggestion, I'll try the BPF. Anyway my problem
was solved by the filter in custom tracepoints (for instance,
tracing/events/kmem/filter).

Also, I used trace_*_enabled() to first check if tracepoint is enabled
and take ktime_get() only after that. This solved my initial issue.

Thanks David, Yang and the Linux community for helping me identify my
issue and solve it.

Best Regards,
Shivank