cvs commit: src/sys/conf files

[M. Warner Losh]

In message: <20061018100033.pz0u24u2gw8owc8s at webmail.leidinger.net>
            Alexander Leidinger <Alexander at Leidinger.net> writes:
: Quoting Warner Losh <imp at FreeBSD.org> (from Tue, 17 Oct 2006 18:08:04  
: +0000 (UTC)):
: 
: > imp         2006-10-17 18:08:04 UTC
: >
: >   FreeBSD src repository
: >
: >   Modified files:
: >     sys/conf             files
: >   Log:
: >   Collapse the two identical emu10k1-alsa%diked.h creation rules for
: >   snd_emu10k1 and snd_emu10kx into one line.  The 'pci' dependency here
: >   adds no value, so I eliminted it (we don't have a snd.all file that
: >   might make it mildly useful, and even then it wouldn't be that
: >   useful).  With the pci optional component eliminated, I could use the
: >   '|' operator.  I could have also include pci on both sides of the |
: >   operator, but since it isn't a value add at all, it was better to
: >   eliminate it.
: 
: Nice. Is this stuff documented somewhere?

No.  A lot of this is black magic voodoo :-(.  Would make a good
project to document config.  However, I fear that once documented, the
mythical replacement would actually arrive...

: How do I determine if 'pci'  
: adds a value or not? Is it of no value because the header lists  
: emu10k[1x] as a depedency and the emu10k[1x].c lists the 'pci'  
: dependency?

It is of no value because it is only a pci device.  If you have
snd_emu10k1 in the kernel config file w/o pci, then nothing is
included.  It should, instead, give an error at config or compile time
since this violates pola.

It wouldn't be useless in, say, the ep case.  In that case we only
compile the bus front ends that are in the kernel.  This means you
don't get EISA frontend if there's no 'device eisa' in your kernel.

Warner