s390/pci: Fix stale function handles in error handling

The error event information for PCI error events contains a function
handle for the respective function. This handle is generally captured at
the time the error event was recorded. Due to delays in processing or
cascading issues, it may happen that during firmware recovery multiple
events are generated. When processing these events in order Linux may
already have recovered an affected function making the event information
stale. Fix this by doing an unconditional CLP List PCI function
retrieving the current function handle with the zdev->state_lock held
and ignoring the event if its function handle is stale.

Cc: [email protected]
Fixes: 4cdf2f4 ("s390/pci: implement minimal PCI error recovery")
Reviewed-by: Julian Ruess <[email protected]>
Reviewed-by: Gerd Bayer <[email protected]>
Reviewed-by: Farhan Ali <[email protected]>
Signed-off-by: Niklas Schnelle <[email protected]>
Signed-off-by: Alexander Gordeev <[email protected]>

Author: niklas88

arch/s390/pci/pci_event.c

@@ -273,6 +273,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
 	struct pci_dev *pdev = NULL;
 	pci_ers_result_t ers_res;
+	u32 fh = 0;
+	int rc;
 
 	zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n",
 		 ccdf->fid, ccdf->fh, ccdf->pec);
@@ -281,6 +283,15 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 
 	if (zdev) {
 		mutex_lock(&zdev->state_lock);
+		rc = clp_refresh_fh(zdev->fid, &fh);
+		if (rc)
+			goto no_pdev;
+		if (!fh || ccdf->fh != fh) {
+			/* Ignore events with stale handles */
+			zpci_dbg(3, "err fid:%x, fh:%x (stale %x)\n",
+				 ccdf->fid, fh, ccdf->fh);
+			goto no_pdev;
+		}
 		zpci_update_fh(zdev, ccdf->fh);
 		if (zdev->zbus->bus)
 			pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);