Fix calculation of rdb_shift by using original number of QPs, not
their slot in profile[] (which will be rearranged when we sort it).
Signed-off-by: Roland Dreier <[EMAIL PROTECTED]>
--- linux-export.orig/drivers/infiniband/hw/mthca/mthca_profile.c
2005-03-31 19:07:14.000000000 -0800
+++ linux-export/drivers/infiniband/hw/mthca/mthca_profile.c 2005-04-01
12:38:21.237350633 -0800
@@ -208,8 +208,7 @@
break;
case MTHCA_RES_RDB:
for (dev->qp_table.rdb_shift = 0;
- profile[MTHCA_RES_QP].num <<
dev->qp_table.rdb_shift <
- profile[i].num;
+ request->num_qp << dev->qp_table.rdb_shift <
profile[i].num;
++dev->qp_table.rdb_shift)
; /* nothing */
dev->qp_table.rdb_base = (u32) profile[i].start;
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general