summaryrefslogtreecommitdiff
path: root/drivers/misc
diff options
context:
space:
mode:
authorVaibhav Jain <vaibhav@linux.vnet.ibm.com>2017-04-27 10:58:22 +0530
committerMichael Ellerman <mpe@ellerman.id.au>2017-05-02 22:41:42 +1000
commit4f58f0bf155e87dda31a3088b1e107fa9dd79f0e (patch)
tree2862a990503edd8c443742c6665d35caafa90ee7 /drivers/misc
parentea9a26d117cf0637c71d3e0076f4a124bf5859df (diff)
cxl: Route eeh events to all drivers in cxl_pci_error_detected()
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") Cc: stable@vger.kernel.org # v4.3+ 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>
Diffstat (limited to 'drivers/misc')
-rw-r--r--drivers/misc/cxl/pci.c15
1 files changed, 9 insertions, 6 deletions
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 556ef910a651..c8e9e43c75a7 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -2057,7 +2057,7 @@ 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.
@@ -2162,15 +2162,18 @@ 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 */