Comments
Patch
@@ -1296,6 +1296,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
switch (action) {
case OF_RECONFIG_DETACH_NODE:
+ remove_ddw(np);
if (pci && pci->iommu_table)
iommu_free_table(pci->iommu_table, np->full_name);
@@ -1308,16 +1309,6 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
}
}
spin_unlock(&direct_window_list_lock);
-
- /*
- * Because the notifier runs after isolation of the
- * slot, we are guaranteed any DMA window has already
- * been revoked and the TCEs have been marked invalid,
- * so we don't need a call to remove_ddw(np). However,
- * if an additional notifier action is added before the
- * isolate call, we should update this code for
- * completeness with such a call.
- */
break;
default:
err = NOTIFY_DONE;
There are now two kinds of DMA windows that might be presented by PowerVM DDW support -- huge windows (that can map all of system memory regardless of the LPAR configuration) and non-huge windows (which can't). They are implemented slightly differently in PowerVM, and thus have different characteristics. The most obvious is that slot isolate doesn't clear the TCEs/window for us with non-huge windows. Thus, when a DLPAR operation occurs on a slot using a non-huge window, TCEs are still present (the notifier chain doesn't currently remove them explicitly) and the DLPAR fails. Fix this by calling remove_ddw() first, which will unmap the DDW TCEs. Note: a corresponding change to drmgr is needed to actually successfully DLPAR, such that the device-tree update (which causes the notifier chain to fire) occurs before slot isolate. Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>