Pointer to 4.8 SMP implementation

[Venkatesh.Babu at nokia.com]

 Hi

    I have newly joined to this mailing list. Pardon me for bothering with my silly questions.
I was not able to get this information from the official website. I know this can be determined by looking at the source code, but it is going to be too much of a work. I have this option as a last resort.

    I know that FreeBSD 5.x supports fine grained locking and 4.x just supports coarse grained / giant kernel lock. I would like to know the capabilities of SMP implementation in 4.x (say 4.8). I am interested to know -
 - are the interrupts shared between the multiprocessors?
 - what algorithm is used to decide which processor services which interrupt ?
 - does it distributes the interrupts based on the processor load ?
 - does it distributes the software interrupt processing also ?
 - how the user level processes are scheduled to run on other processors ?
 - can the user process be run on a particular processor ? 
 - how the processor affinity is taken into consideration ?

Can any of you give some pointers to the SMP capability list in FreeBSD 4.x ?
It would be great if you can also point me to some design / implementation of SMP architecture  in FreeBSD 4.x. 

Thanks a lot,

  VBabu