@@ -13,6 +13,7 @@
#define dev_fmt(fmt) "AER: " fmt
#include <linux/pci.h>
+#include <linux/pm_runtime.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/errno.h>
@@ -85,6 +86,18 @@ static int report_error_detected(struct pci_dev *dev,
return 0;
}
+static int pci_pm_runtime_get_sync(struct pci_dev *pdev, void *data)
+{
+ pm_runtime_get_sync(&pdev->dev);
+ return 0;
+}
+
+static int pci_pm_runtime_put(struct pci_dev *pdev, void *data)
+{
+ pm_runtime_put(&pdev->dev);
+ return 0;
+}
+
static int report_frozen_detected(struct pci_dev *dev, void *data)
{
return report_error_detected(dev, pci_channel_io_frozen, data);
@@ -207,6 +220,8 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
else
bridge = pci_upstream_bridge(dev);
+ pci_walk_bridge(bridge, pci_pm_runtime_get_sync, NULL);
+
pci_dbg(bridge, "broadcast error_detected message\n");
if (state == pci_channel_io_frozen) {
pci_walk_bridge(bridge, report_frozen_detected, &status);
@@ -251,10 +266,15 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
pcie_clear_device_status(dev);
pci_aer_clear_nonfatal_status(dev);
}
+
+ pci_walk_bridge(bridge, pci_pm_runtime_put, NULL);
+
pci_info(bridge, "device recovery successful\n");
return status;
failed:
+ pci_walk_bridge(bridge, pci_pm_runtime_put, NULL);
+
pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT);
/* TODO: Should kernel panic here? */
PM runtime can be done simultaneously with AER error handling. Avoid that by using pm_runtime_get_sync() before and pm_runtime_put() after reset in pcie_do_recovery() for all recovering devices. pm_runtime_get_sync() will increase dev->power.usage_count counter to prevent any possible future request to runtime suspend a device, as well as resume device is was in D3hot state. I tested with igc device by doing simultaneous aer_inject and rpm suspend/resume via /sys/bus/pci/devices/PCI_ID/power/control and can reproduce: igc 0000:02:00.0: not ready 65535ms after bus reset; giving up pcieport 0000:00:1c.2: AER: Root Port link has been reset (-25) pcieport 0000:00:1c.2: AER: subordinate device reset failed pcieport 0000:00:1c.2: AER: device recovery failed igc 0000:02:00.0: Unable to change power state from D3hot to D0, device inaccessible The problem disappears when applied this patch. Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com> --- RFC -> v1: add runtime callbacks to pcie_do_recovery(), this covers DPC case as well as case of recovering multiple devices under same port. drivers/pci/pcie/err.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)