diff options
| author | Michael Ellerman <michael@ellerman.id.au> | 2006-03-21 20:45:51 +1100 |
|---|---|---|
| committer | Paul Mackerras <paulus@samba.org> | 2006-03-22 15:04:09 +1100 |
| commit | caf80e579b5fc0048681a47c5a55487116e56a88 (patch) | |
| tree | a5da9d218c0f98a7881cfc601f67cd619579d441 /lib/textsearch.c | |
| parent | 2b2612272c77288b2bd53d5831df737cd669cd93 (diff) | |
| download | kernel_samsung_aries-caf80e579b5fc0048681a47c5a55487116e56a88.zip kernel_samsung_aries-caf80e579b5fc0048681a47c5a55487116e56a88.tar.gz kernel_samsung_aries-caf80e579b5fc0048681a47c5a55487116e56a88.tar.bz2 | |
[PATCH] powerpc: Unconfuse htab_bolt_mapping() callers
htab_bolt_mapping() takes a vstart and pstart parameter, but all but one of
its callers actually pass it vstart and vstart. Luckily before it passes
paddr (calculated from paddr) to the hpte_insert routines it calls
virt_to_abs() (aka. __pa()) on the address, so there isn't actually a bug.
map_io_page() however does pass pstart properly, so currently it's broken
AFAICT because we're calling __pa(paddr) which will get us something very
large. Presumably no one's calling map_io_page() in the right context.
Anyway, change htab_bolt_mapping() callers to properly pass pstart, and then
use it properly in htab_bolt_mapping(), ie. don't call __pa() on it again.
Booted on p5 LPAR, iSeries and Power3.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Diffstat (limited to 'lib/textsearch.c')
0 files changed, 0 insertions, 0 deletions