aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/eeh_pe.c
diff options
context:
space:
mode:
authorOliver O'Halloran <oohall@gmail.com>2019-09-03 20:15:52 +1000
committerMichael Ellerman <mpe@ellerman.id.au>2019-09-05 14:22:37 +1000
commit799abe283e5103d48e079149579b4f167c95ea0e (patch)
tree5eb535683b2ccfbbe99afb2bd87a666f10759fb9 /arch/powerpc/kernel/eeh_pe.c
parentpowerpc/64s/exception: reduce page fault unnecessary loads (diff)
downloadlinux-dev-799abe283e5103d48e079149579b4f167c95ea0e.tar.xz
linux-dev-799abe283e5103d48e079149579b4f167c95ea0e.zip
powerpc/eeh: Clean up EEH PEs after recovery finishes
When the last device in an eeh_pe is removed the eeh_pe structure itself (and any empty parents) are freed since they are no longer needed. This results in a crash when a hotplug driver is involved since the following may occur: 1. Device is suprise removed. 2. Driver performs an MMIO, which fails and queues and eeh_event. 3. Hotplug driver receives a hotplug interrupt and removes any pci_devs that were under the slot. 4. pci_dev is torn down and the eeh_pe is freed. 5. The EEH event handler thread processes the eeh_event and crashes since the eeh_pe pointer in the eeh_event structure is no longer valid. Crashing is generally considered poor form. Instead of doing that use the fact PEs are marked as EEH_PE_INVALID to keep them around until the end of the recovery cycle, at which point we can safely prune any empty PEs. Signed-off-by: Oliver O'Halloran <oohall@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20190903101605.2890-2-oohall@gmail.com
Diffstat (limited to 'arch/powerpc/kernel/eeh_pe.c')
-rw-r--r--arch/powerpc/kernel/eeh_pe.c23
1 files changed, 22 insertions, 1 deletions
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 1a6254bcf056..177852e39a25 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -470,6 +470,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
{
struct eeh_pe *pe, *parent, *child;
+ bool keep, recover;
int cnt;
pe = eeh_dev_to_pe(edev);
@@ -490,10 +491,21 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
*/
while (1) {
parent = pe->parent;
+
+ /* PHB PEs should never be removed */
if (pe->type & EEH_PE_PHB)
break;
- if (!(pe->state & EEH_PE_KEEP)) {
+ /*
+ * XXX: KEEP is set while resetting a PE. I don't think it's
+ * ever set without RECOVERING also being set. I could
+ * be wrong though so catch that with a WARN.
+ */
+ keep = !!(pe->state & EEH_PE_KEEP);
+ recover = !!(pe->state & EEH_PE_RECOVERING);
+ WARN_ON(keep && !recover);
+
+ if (!keep && !recover) {
if (list_empty(&pe->edevs) &&
list_empty(&pe->child_list)) {
list_del(&pe->child);
@@ -502,6 +514,15 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
break;
}
} else {
+ /*
+ * Mark the PE as invalid. At the end of the recovery
+ * process any invalid PEs will be garbage collected.
+ *
+ * We need to delay the free()ing of them since we can
+ * remove edev's while traversing the PE tree which
+ * might trigger the removal of a PE and we can't
+ * deal with that (yet).
+ */
if (list_empty(&pe->edevs)) {
cnt = 0;
list_for_each_entry(child, &pe->child_list, child) {