netdev - Re: [PATCH net-next 1/2] net/tcp: optimise locking for blocking splice

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: <14ce6ee2-922a-93c2-0d6e-5778822ca5d6@gmail.com>
Date: Fri, 23 Jun 2023 14:42:21 +0100
From: Pavel Begunkov <asml.silence@...il.com>
To: Eric Dumazet <edumazet@...gle.com>
Cc: Paolo Abeni <pabeni@...hat.com>, netdev@...r.kernel.org,
 davem@...emloft.net, dsahern@...nel.org, kuba@...nel.org
Subject: Re: [PATCH net-next 1/2] net/tcp: optimise locking for blocking
 splice

On 6/19/23 11:59, Eric Dumazet wrote:
> On Mon, Jun 19, 2023 at 11:27 AM Pavel Begunkov <asml.silence@...il.com> wrote:
>>
>> On 5/24/23 13:51, Pavel Begunkov wrote:
>>> On 5/23/23 14:52, Paolo Abeni wrote:
>>>> On Fri, 2023-05-19 at 14:33 +0100, Pavel Begunkov wrote:
>>>>> Even when tcp_splice_read() reads all it was asked for, for blocking
>>>>> sockets it'll release and immediately regrab the socket lock, loop
>>>>> around and break on the while check.
>>>>>
>>>>> Check tss.len right after we adjust it, and return if we're done.
>>>>> That saves us one release_sock(); lock_sock(); pair per successful
>>>>> blocking splice read.
>>>>>
>>>>> Signed-off-by: Pavel Begunkov <asml.silence@...il.com>
>>>>> ---
>>>>>    net/ipv4/tcp.c | 8 +++++---
>>>>>    1 file changed, 5 insertions(+), 3 deletions(-)
>>>>>
>>>>> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
>>>>> index 4d6392c16b7a..bf7627f37e69 100644
>>>>> --- a/net/ipv4/tcp.c
>>>>> +++ b/net/ipv4/tcp.c
>>>>> @@ -789,13 +789,15 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
>>>>>         */
>>>>>        if (unlikely(*ppos))
>>>>>            return -ESPIPE;
>>>>> +    if (unlikely(!tss.len))
>>>>> +        return 0;
>>>>>        ret = spliced = 0;
>>>>>        lock_sock(sk);
>>>>>        timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK);
>>>>> -    while (tss.len) {
>>>>> +    while (true) {
>>>>>            ret = __tcp_splice_read(sk, &tss);
>>>>>            if (ret < 0)
>>>>>                break;
>>>>> @@ -835,10 +837,10 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
>>>>>                }
>>>>>                continue;
>>>>>            }
>>>>> -        tss.len -= ret;
>>>>>            spliced += ret;
>>>>> +        tss.len -= ret;
>>>>
>>>> The patch LGTM. The only minor thing that I note is that the above
>>>> chunk is not needed. Perhaps avoiding unneeded delta could be worthy.
>>>
>>> It keeps it closer to the tss.len test, so I'd leave it for that reason,
>>> but on the other hand the compiler should be perfectly able to optimise it
>>> regardless (i.e. sub;cmp;jcc; vs sub;jcc;). I don't have a hard feeling
>>> on that, can change if you want.
>>
>> Is there anything I can do to help here? I think the patch is
>> fine, but can amend the change per Paolo's suggestion if required.
>>
> 
> We prefer seeing patches focusing on the change, instead of also doing
> arbitrary changes
> making future backports more likely to conflict.

Thank you for taking a look! I cut it down and resent.

I don't agree it's arbitrary, it's a clean up related to the
change. I'm just trying to not make the death by a thousand cuts
problem worse for networking, but I guess I'm worried for nothing.

-- 
Pavel Begunkov