eeh_handle_special_event() is called when an EEH event is detected but
can't be narrowed down to a specific PE. This function looks through
every PE to find one in an erroneous state, then calls the regular event
handler eeh_handle_normal_event() once it knows which PE has an error.
However, if eeh_handle_normal_event() found that the PE cannot possibly
be recovered, it will free it, rendering the passed PE stale.
This leads to a use after free in eeh_handle_special_event() as it attempts to
clear the "recovering" state on the PE after eeh_handle_normal_event() returns.
Thus, make sure the PE is valid when attempting to clear state in
eeh_handle_special_event().
Fixes: 8a6b1bc70dbb ("powerpc/eeh: EEH core to handle special event")
Cc: stable@xxxxxxxxxxxxxxx # v3.11+
Reported-by: Alexey Kardashevskiy <aik@xxxxxxxxx>
Signed-off-by: Russell Currey <ruscur@xxxxxxxxxx>
Reviewed-by: Gavin Shan <gwshan@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
---
This is a backport for upstream patch daeba2956f32f91f3493788ff6ee02fb1b2f02fa
that applies to 3.18 and 4.4.
---
arch/powerpc/kernel/eeh_driver.c | 19 +++++++++++++++----
1 file changed, 15 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 247a0dc012f1..483c11aa1597 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -653,7 +653,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
*/
#define MAX_WAIT_FOR_RECOVERY 300
-static void eeh_handle_normal_event(struct eeh_pe *pe)
+static bool eeh_handle_normal_event(struct eeh_pe *pe)
{
struct pci_bus *frozen_bus;
int rc = 0;
@@ -663,7 +663,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
if (!frozen_bus) {
pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
__func__, pe->phb->global_number, pe->addr);
- return;
+ return false;
}
eeh_pe_update_time_stamp(pe);
@@ -788,7 +788,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
pr_info("EEH: Notify device driver to resume\n");
eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
- return;
+ return false;
excess_failures:
/*
@@ -829,7 +829,11 @@ perm_error:
pci_lock_rescan_remove();
pcibios_remove_pci_devices(frozen_bus);
pci_unlock_rescan_remove();
+
+ /* The passed PE should no longer be used */
+ return true;
}
+ return false;
}
static void eeh_handle_special_event(void)
@@ -895,7 +899,14 @@ static void eeh_handle_special_event(void)
*/
if (rc == EEH_NEXT_ERR_FROZEN_PE ||
rc == EEH_NEXT_ERR_FENCED_PHB) {
- eeh_handle_normal_event(pe);
+ /*
+ * eeh_handle_normal_event() can make the PE stale if it
+ * determines that the PE cannot possibly be recovered.
+ * Don't modify the PE state if that's the case.
+ */
+ if (eeh_handle_normal_event(pe))
+ continue;
+
eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
} else {
pci_lock_rescan_remove();
--
2.13.0