netdev - Re: [PATCH net-next 4/7] net: implement per-cpu reserves for memory

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

Message-ID: <CANn89iK3nsoWOxE5X0afcyCEuab57v5jrKn-b5ZwNO3njO_7pQ@mail.gmail.com>
Date:   Thu, 9 Jun 2022 08:43:46 -0700
From:   Eric Dumazet <edumazet@...gle.com>
To:     Neal Cardwell <ncardwell@...gle.com>
Cc:     Shakeel Butt <shakeelb@...gle.com>,
        Eric Dumazet <eric.dumazet@...il.com>,
        "David S . Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>,
        netdev <netdev@...r.kernel.org>,
        Soheil Hassas Yeganeh <soheil@...gle.com>,
        Wei Wang <weiwan@...gle.com>
Subject: Re: [PATCH net-next 4/7] net: implement per-cpu reserves for memory_allocated

On Thu, Jun 9, 2022 at 8:09 AM Neal Cardwell <ncardwell@...gle.com> wrote:

> Yes, sorry about that. In parallel Soheil just pointed out to me OOB
> that the code is correct because at that point in the code we know
> that local_reserve is negative...
>
> Sorry for the noise!

No worries Neal, I made the same mistake when writing the function :)

Once we determined the new pcpu reserve X is out-of-range (-1MB ..
+1MB) we have to transfer it to shared memory_allocated

Regardless of the value X, the transfert is the same regardless of
initial raise/decrease intent :

pcpu_reserve -= X;  // using this_cpu op which is IRQ safe
memory_reserve += X;  // using atomic op, IRQ and SMP safe