cvs commit: src/sys/i386/i386 pmap.c

[Alan Cox]

On Fri, Oct 29, 2004 at 03:49:17PM -0400, John Baldwin wrote:
> On Friday 29 October 2004 03:10 pm, Alan Cox wrote:
> > alc         2004-10-29 19:10:47 UTC
> >
> >   FreeBSD src repository
> >
> >   Modified files:
> >     sys/i386/i386        pmap.c
> >   Log:
> >   Implement per-CPU SYSMAPs, i.e., CADDR* and CMAP*, to reduce lock
> >   contention within pmap_zero_page() and pmap_copy_page().
> 
> Cool.  One note: I think you have to move the sched_pin before the lookup in 
> the sysmaps_pcpu[] table so you don't migrate to another CPU if you get an 
> interrupt after you've locked the sysmap.  I'm curious if can get rid of the 
> sysmaps lock altogether actually.  It might require a critical section to do 
> so though, and zero'ing page(s) is probably too long to defer interrupts.
> 

If an interrupt and migration occurs, it could result in contention
for the lock but not a correctness problem.  However, what you suggest
does have the virtue of making the code more obviously correctness.

As far as using a critical section, how long is too long for deferring
interrupts?  I measured the cost of pmap_zero_page() at ~5400 cycles
on a 400MHz FSB Xeon.  The cost of pmap_copy_page() is much higher,
but I don't recall what it is.

Alan