svn commit: r221499 - in projects/largeSMP: gnu/usr.bin/gdb/kgdb lib/libmemstat sys/amd64/acpica sys/amd64/amd64 sys/amd64/include sys/arm/arm sys/arm/include sys/cddl/dev/cyclic/i386 sys/cddl/dev/...

[Warner Losh]

This is really exciting news.  My time and focus lately has been elsewhere.  Rather than sit on it, I'm forwarding this on to the mips@ list so that whoever has the time can work on supporting this.

Warner

On May 5, 2011, at 8:50 AM, Attilio Rao wrote:

> 2011/5/5 Attilio Rao <attilio at freebsd.org>:
>> Author: attilio
>> Date: Thu May  5 14:39:14 2011
>> New Revision: 221499
>> URL: http://svn.freebsd.org/changeset/base/221499
>> 
>> Log:
>>  Commit the support for removing cpumask_t and replacing it directly with
>>  cpuset_t objects.
>>  That is going to offer the underlying support for a simple bump of
>>  MAXCPU and then support for number of cpus > 32 (as it is today).
>> 
>>  Right now, cpumask_t is an int, 32 bits on all our supported architecture.
>>  cpumask_t on the other side is implemented as an array of longs, and
>>  easilly extendible by definition.
>> 
>>  The architectures touched by this commit are the following:
>>  - amd64
>>  - i386
>>  - pc98
>>  - arm
>>  - ia64
>>  - XEN
>> 
>>  while the others are still missing.
>>  Userland is believed to be fully converted with the changes contained
>>  here.
>> 
>>  Some technical notes:
>>  - This commit may be considered an ABI nop for all the architectures
>>    different from amd64 and ia64 (and sparc64 in the future)
>>  - per-cpu members, which are now converted to cpuset_t, needs to be
>>    accessed avoiding migration, because the size of cpuset_t should be
>>    considered unknown
>>  - size of cpuset_t objects is different from kernel and userland (this is
>>    primirally done in order to leave some more space in userland to cope
>>    with KBI extensions). If you need to access kernel cpuset_t from the
>>    userland please refer to example in this patch on how to do that
>>    correctly (kgdb may be a good source, for example).
>>  - Support for other architectures is going to be added soon
>>  - Only MAXCPU for amd64 is bumped now
>> 
>>  The patch has been tested by sbruno and Nicholas Esborn on opteron
>>  4 x 12 pack CPUs. More testing on big SMP is expected to came soon.
>>  pluknet tested the patch with his 8-ways on both amd64 and i386.
>> 
>>  Tested by:    pluknet, sbruno, gianni, Nicholas Esborn
>>  Reviewed by:  jeff, jhb, sbruno
> 
> 
> Hi,
> sorry for writing to you directly, but I'm contacting you as arch maintainer.
> 
> I really want to push this project in ASAP and I may need some help
> from you about testing patches, architecture specific.
> 
> So far the missing bits involve:
> - mips
> - powerpc
> - sparc64
> - sun4v
> 
> What I'm looking for is specifically testing/reviewing assitance, as I
> add the supports to a specific architecture.
> I don't plan to bump the MAXCPU on arches !amd64, but if you want to,
> feel free to do that after the patch makes the tree.
> 
> Thanks,
> Attilio
> 
> 
> -- 
> Peace can only be achieved by understanding - A. Einstein
> 
>