From: Gabriele Paoloni <gabriele.paoloni@xxxxxxxxxx>
Currently if an uncorrectable error is reported by an EP the AER
driver walks over all the devices connected to the upstream port
bus and in turns call the report_error_detected() callback.
If any of the devices connected to the bus does not implement
dev->driver->err_handler->error_detected() do_recovery() will fail.
However for non fatal errors the PCIe link should not be considered
compromised, therefore it makes sense to report the error only to
all the functions of a multifunction device.
This patch implements this new behaviour for non fatal errors.
Signed-off-by: Gabriele Paoloni <gabriele.paoloni@xxxxxxxxxx>
Signed-off-by: Dongdong Liu <liudongdong3@xxxxxxxxxx>
---
drivers/pci/bus.c | 38 ++++++++++++++++++++++++++++++++++++++
drivers/pci/pcie/aer/aerdrv_core.c | 13 ++++++++++++-
include/linux/pci.h | 3 ++-
3 files changed, 52 insertions(+), 2 deletions(-)
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index bc56cf1..bc8f8b2 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -364,6 +364,44 @@ void pci_bus_add_devices(const struct pci_bus *bus)
}
EXPORT_SYMBOL(pci_bus_add_devices);
+/** pci_walk_mf_dev - walk all functions of a multi-function
+ * device calling callback.
+ * @dev a function in a multi-function device
+ * @cb callback to be called for each device found
+ * @userdata arbitrary pointer to be passed to callback.
+ *
+ * Walk, on a given bus, only the adjacent functions of a
+ * multi-function device. Call the provided callback on each
+ * device found.
+ *
+ * We check the return of @cb each time. If it returns anything
+ * other than 0, we break out.
+ *
+ */
+void pci_walk_mf_dev(struct pci_dev *dev, int (*cb)(struct pci_dev *, void *),
+ void *userdata)
+{
+ int retval;
+ struct pci_bus *bus;
+ struct pci_dev *pdev;
+ int ndev;
+
+ bus = dev->bus;
+ ndev = PCI_SLOT(dev->devfn);
+
+ down_read(&pci_bus_sem);
+ /* call cb for all the functions of the mf device */
+ list_for_each_entry(pdev, &bus->devices, bus_list) {
+ if (PCI_SLOT(pdev->devfn) == ndev) {
+ retval = cb(pdev, userdata);
+ if (retval)
+ break;
+ }
+ }
+ up_read(&pci_bus_sem);
+}
+EXPORT_SYMBOL_GPL(pci_walk_mf_dev);
+
/** pci_walk_bus - walk devices on/under bus, calling callback.
* @top bus whose devices should be walked
* @cb callback to be called for each device found
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index b1303b3..67c3dc0 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -390,7 +390,18 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
* If the error is reported by an end point, we think this
* error is related to the upstream link of the end point.
*/
- pci_walk_bus(dev->bus, cb, &result_data);
+ if ((state == pci_channel_io_normal) &&
+ (!pci_ari_enabled(dev->bus)))
+ /*
+ * the error is non fatal so the bus is ok, just walk
+ * through all the functions in a multifunction device.
+ * if ARI is enabled on the bus then there can be only
+ * one device under that bus (so walk all the functions
+ * under the bus).
+ */
+ pci_walk_mf_dev(dev, cb, &result_data);
+ else
+ pci_walk_bus(dev->bus, cb, &result_data);
}
return result_data.result;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 4869e66..69e77bb 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1269,7 +1269,8 @@ const struct pci_device_id *pci_match_id(const struct pci_device_id *ids,
struct pci_dev *dev);
int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
int pass);
-
+void pci_walk_mf_dev(struct pci_dev *dev, int (*cb)(struct pci_dev *, void *),
+ void *userdata);
void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
void *userdata);
int pci_cfg_space_size(struct pci_dev *dev);
--
1.9.1
