Re: atomic ops on i386

On 2014-04-13, Alex Rousskov <rousskov_at_measurement-factory.com> wrote:
> On 04/13/2014 06:36 AM, Stuart Henderson wrote:
>
>> I'm just trying to build 3.5-HEAD on OpenBSD/i386 (i.e. 32-bit mode) for
>> the first time. It fails due to use of 64-bit atomic ops:
>>
>> MemStore.o(.text+0xc90): In function `MemStore::anchorEntry(StoreEntry&, int, Ipc::StoreMapAnchor const&)':
>> : undefined reference to `__sync_fetch_and_add_8'
>> MemStore.o(.text+0x3aa3): In function `MemStore::copyFromShm(StoreEntry&, int, Ipc::StoreMapAnchor const&)':
>> : undefined reference to `__sync_fetch_and_add_8'
>> MemStore.o(.text+0x3cce): In function `MemStore::copyFromShm(StoreEntry&, int, Ipc::StoreMapAnchor const&)':
>> : undefined reference to `__sync_fetch_and_add_8'
>> MemStore.o(.text+0x4040): In function `MemStore::copyFromShm(StoreEntry&, int, Ipc::StoreMapAnchor const&)':
>> : undefined reference to `__sync_fetch_and_add_8'
>> MemStore.o(.text+0x435f): In function `MemStore::copyFromShm(StoreEntry&, int, Ipc::StoreMapAnchor const&)':
>> : undefined reference to `__sync_fetch_and_add_8'
>> MemStore.o(.text+0x473d): more undefined references to `__sync_fetch_and_add_8' follow
>> collect2: error: ld returned 1 exit status
>
> I am not an expert on this, but googling suggests building with
> -march=i586 or a similar GCC option may solve your problem. More
> possibly relevant details at

That does fix the problem building, but I need this for package builds
which are supposed to still work on 486, so I can't rely on users having
586 (cmpxchg8b).

> http://www.squid-cache.org/mail-archive/squid-dev/201308/0103.html

specifically "because swap_file_sz that they need to keep in sync
across Squid kids is 64 bits" - so I think fixing the autoconf check is
probably what's needed then.

>> Should the autoconf test be changed to check for working 64-bit ops, or
>> is something more involved wanted?
>
> Filing a bug report may be a good idea, especially if you cannot make
> this work.

I suppose the simplest fix would be something like this,

--- configure.ac.orig Fri Apr 4 21:31:38 2014
+++ configure.ac Sun Apr 13 15:12:37 2014
@@ -416,7 +416,7 @@ dnl Check for atomic operations support in the compile
 dnl
 AC_MSG_CHECKING([for GNU atomic operations support])
 AC_RUN_IFELSE([AC_LANG_PROGRAM([[
- int n = 0;
+ long long n = 0;
 ]],[[
     __sync_add_and_fetch(&n, 10); // n becomes 10
     __sync_fetch_and_add(&n, 20); // n becomes 30

Happy to open a bug report if that's preferred, I thought I'd ask here
first to work out the best direction.
Received on Sun Apr 13 2014 - 21:19:20 MDT