cxl: Route eeh events to all drivers in cxl_pci_error_detected()

commit 4f58f0bf155e87dda31a3088b1e107fa9dd79f0e upstream.

Fix a boundary condition where in some cases an eeh event that results
in card reset isn't passed on to a driver attached to the virtual PCI
device associated with a slice. This will happen in case when a slice
attached device driver returns a value other than
PCI_ERS_RESULT_NEED_RESET from the eeh error_detected() callback. This
would result in an early return from cxl_pci_error_detected() and
other drivers attached to other AFUs on the card wont be notified.

The patch fixes this by making sure that all slice attached
device-drivers are notified and the return values from
error_detected() callback are aggregated in a scheme where request for
'disconnect' trumps all and 'none' trumps 'need_reset'.

Fixes: 9e8df8a21963 ("cxl: EEH support")
Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com>
Reviewed-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 80b1a7e..fa4fe02 100644 (file)
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1779,7 +1779,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
 {
        struct cxl *adapter = pci_get_drvdata(pdev);
        struct cxl_afu *afu;
-       pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET;
+       pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET, afu_result;
        int i;
 
        /* At this point, we could still have an interrupt pending.
@@ -1884,15 +1884,18 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
        for (i = 0; i < adapter->slices; i++) {
                afu = adapter->afu[i];
 
-               result = cxl_vphb_error_detected(afu, state);
-
-               /* Only continue if everyone agrees on NEED_RESET */
-               if (result != PCI_ERS_RESULT_NEED_RESET)
-                       return result;
+               afu_result = cxl_vphb_error_detected(afu, state);
 
                cxl_context_detach_all(afu);
                cxl_ops->afu_deactivate_mode(afu, afu->current_mode);
                pci_deconfigure_afu(afu);
+
+               /* Disconnect trumps all, NONE trumps NEED_RESET */
+               if (afu_result == PCI_ERS_RESULT_DISCONNECT)
+                       result = PCI_ERS_RESULT_DISCONNECT;
+               else if ((afu_result == PCI_ERS_RESULT_NONE) &&
+                        (result == PCI_ERS_RESULT_NEED_RESET))
+                       result = PCI_ERS_RESULT_NONE;
        }
 
        /* should take the context lock here */