cxl: Check if vphb exists before iterating over AFU devices

commit 12841f87b7a8ceb3d54f171660f72a86941bfcb3 upstream.

During an eeh a kernel-oops is reported if no vPHB is allocated to the
AFU. This happens as during AFU init, an error in creation of vPHB is
a non-fatal error. Hence afu->phb should always be checked for NULL
before iterating over it for the virtual AFU pci devices.

This patch fixes the kenel-oops by adding a NULL pointer check for
afu->phb before it is dereferenced.

Fixes: 9e8df8a21963 ("cxl: EEH support")
Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 3ba04f3..81093f8 100644 (file)
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -2043,6 +2043,9 @@ static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu,
        /* There should only be one entry, but go through the list
         * anyway
         */
+       if (afu->phb == NULL)
+               return result;
+
        list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
                if (!afu_dev->driver)
                        continue;
@@ -2084,8 +2087,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
                         * Tell the AFU drivers; but we don't care what they
                         * say, we're going away.
                         */
-                       if (afu->phb != NULL)
-                               cxl_vphb_error_detected(afu, state);
+                       cxl_vphb_error_detected(afu, state);
                }
                return PCI_ERS_RESULT_DISCONNECT;
        }
@@ -2225,6 +2227,9 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev)
                if (cxl_afu_select_best_mode(afu))
                        goto err;
 
+               if (afu->phb == NULL)
+                       continue;
+
                list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
                        /* Reset the device context.
                         * TODO: make this less disruptive
@@ -2287,6 +2292,9 @@ static void cxl_pci_resume(struct pci_dev *pdev)
        for (i = 0; i < adapter->slices; i++) {
                afu = adapter->afu[i];
 
+               if (afu->phb == NULL)
+                       continue;
+
                list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
                        if (afu_dev->driver && afu_dev->driver->err_handler &&
                            afu_dev->driver->err_handler->resume)