netdev - Re: [PATCH net-next] tls: Add opt-in zerocopy mode of sendfile()

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 for Android: free password hash cracker in your pocket

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

Message-ID: <e837a0a7-dff5-9c56-d84c-f2c050656c0b@nvidia.com>
Date:   Fri, 6 May 2022 19:34:21 +0300
From:   Maxim Mikityanskiy <maximmi@...dia.com>
To:     David Laight <David.Laight@...LAB.COM>
Cc:     Jakub Kicinski <kuba@...nel.org>,
        "David S. Miller" <davem@...emloft.net>,
        Daniel Borkmann <daniel@...earbox.net>,
        Paolo Abeni <pabeni@...hat.com>,
        Boris Pismenny <borisp@...dia.com>,
        Tariq Toukan <tariqt@...dia.com>,
        Saeed Mahameed <saeedm@...dia.com>,
        Gal Pressman <gal@...dia.com>,
        "netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [PATCH net-next] tls: Add opt-in zerocopy mode of sendfile()

On 2022-05-06 11:09, David Laight wrote:
> From: Maxim Mikityanskiy
>> Sent: 05 May 2022 19:28
>>
>> On 2022-05-05 16:48, David Laight wrote:
>>> From: Maxim Mikityanskiy
>>>> Sent: 05 May 2022 13:40
>>>>
>>>> On 2022-05-04 12:49, David Laight wrote:
>>>>>>> If you declare the union on the stack in the callers, and pass by value
>>>>>>> - is the compiler not going to be clever enough to still DDRT?
>>>>>>
>>>>>> Ah, OK, it should do the thing. I thought you wanted me to ditch the
>>>>>> union altogether.
>>>>>
>>>>> Some architectures always pass struct/union by address.
>>>>> Which is probably not what you had in mind.
>>>>
>>>> Do you have any specific architecture in mind? I couldn't find any
>>>> information that it happens anywhere, x86_64 ABI [1] (pages 20-21)
>>>> aligns with my expectations, and my common sense can't explain why would
>>>> some architectures do what you say.
>>>>
>>>> In C, when the caller passes a struct as a parameter, the callee can
>>>> freely modify it. If the compiler silently replaced it with a pointer,
>>>> the callee would corrupt the caller's local variable, so such approach
>>>> requires the caller to make an extra copy.
>>>
>>> Yes, that is what happens.
>>
>> I did a quick experiment with gcc 9 on m68k and i386, and it doesn't
>> confirm what you claim.
>>
>> #include <stdint.h>
>> #include <stdio.h>
>>
>> union test {
>>           uint32_t x;
>>           uint32_t *y;
>> };
>>
>> void func1(void *ptr, union test t)
>> {
>>           if (ptr) {
>>                   printf("%p %u\n", ptr, t.x);
>>           } else {
>>                   printf("%u\n", *t.y);
>>           }
>> }
>>
>> void func2(void *ptr, uint32_t *y)
>> {
>>           if (ptr) {
>>                   printf("%p %u\n", ptr, (uint32_t)y);
>>           } else {
>>                   printf("%u\n", *y);
>>           }
>> }
>>
>> gcc -S test.c -fno-strict-aliasing -o -
>>
>> I believe this minimal example reflects well enough what happens in my
>> code. The assembly generated for func1 and func2 are identical. In both
>> cases the second parameter is passed on the stack by value, not by pointer.
> 
> Hmmm, perhaps it is/was only sparc32 that passed all structures by reference.

Looks like sparc32 really does this crazy thing (and if the callee wants 
to modify the union, it has to make a copy). Well, it's always great to 
learn something new - thanks for the information!

I'll consider it, but I'll likely keep the union anyway, since other 
options are uglier or less performant on common 64-bit architectures, 
and sparc32 is a legacy architecture that is unlikely to be used with 
the new performance feature of TLS zerocopy sendfile.

> godbolt doesn't seem to have a sparc compiler and I don't have a
> working sparc system any more.

I just installed a cross-compiler from the repository and inspected the 
assembly.

> It is also possible that the calling conventions are slightly
> different than the ones I remember using years ago.
> 
> Certainly on i386 even 4 byte structures are returned by reference.

Right, return values are a different thing, there is this pseudo 
parameter that points to the buffer for the struct being returned, but 
I'm not going to return my union, I only pass it as a parameter, so it 
doesn't concern me.

> 	David
> 
> -
> Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
> Registration No: 1397386 (Wales)