re: mostly working SMP again

[matthew green <mrg%eterna.com.au@localhost>]

   >     CPU1: data fault: pc=0xf000ab3c addr=0x80
   
   0xf000ab20 <savefpstate+0>:     rd  %psr, %o1
   0xf000ab24 <savefpstate+4>:     sethi  %hi(0x1000), %o2
   0xf000ab28 <savefpstate+8>:     or  %o1, %o2, %o1
   0xf000ab2c <savefpstate+12>:    mov  %o1, %psr
   0xf000ab30 <savefpstate+16>:    sethi  %hi(0x2000), %o5
   0xf000ab34 <savefpstate+20>:    mov  %g0, %o3
   0xf000ab38 <savefpstate+24>:    nop
   0xf000ab3c <special_fp_store+0>:        st  %fsr, [ %o0 + 0x80 ]


this is interesting;  i'd posit that this problem occured when the fpstore
trap was taken and it corrupted %o0, except that when i instrumented this
by putting an explicit test for %o0 being 0 at the start of savefpstate
it would trigger some times...

thanks for the details.  i wish i had a nicely reproduceable way for
my own system, but it takes hours or days sometimes...


.mrg.