PM runtime can be done simultaneously with AER error handling.
Avoid that by using pm_runtime_get_sync() just after pci_dev_get()
and pm_runtime_put() just before pci_dev_put() in AER recovery
procedures.
I'm not sure about DPC case since I do not see get/put there. It
just call pci_do_recovery() from threaded irq dcd_handler().
I think pm_runtime* should be added to this handler as well.
pm_runtime_get_sync() will increase dev->power.usage_count counter to
prevent any rpm actives. When there is suspending pending, it will wait
for it and do the rpm resume. Not sure if that problem, on my testing
I did not encounter issues with that.
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:
[ 853.253938] igc 0000:02:00.0: not ready 65535ms after bus reset; giving up
[ 853.253973] pcieport 0000:00:1c.2: AER: Root Port link has been reset (-25)
[ 853.253996] pcieport 0000:00:1c.2: AER: subordinate device reset failed
[ 853.254099] pcieport 0000:00:1c.2: AER: device recovery failed
[ 853.254178] 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@xxxxxxxxxxxxxxx>
---
drivers/pci/pcie/aer.c | 8 ++++++++
drivers/pci/pcie/edr.c | 3 +++
2 files changed, 11 insertions(+)
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 42a3bd35a3e1..9b56460edc76 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -23,6 +23,7 @@
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/pm.h>
+#include <linux/pm_runtime.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
@@ -813,6 +814,7 @@ static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
{
if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
e_info->dev[e_info->error_dev_num] = pci_dev_get(dev);
+ pm_runtime_get_sync(&dev->dev);
e_info->error_dev_num++;
return 0;
}
@@ -1111,6 +1113,8 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
{
cxl_rch_handle_error(dev, info);
pci_aer_handle_error(dev, info);
+
+ pm_runtime_put(&dev->dev);
pci_dev_put(dev);
}
@@ -1143,6 +1147,8 @@ static void aer_recover_work_func(struct work_struct *work)
PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn));
continue;
}
+ pm_runtime_get_sync(&pdev->dev);
+
pci_print_aer(pdev, entry.severity, entry.regs);
/*
* Memory for aer_capability_regs(entry.regs) is being allocated from the
@@ -1159,6 +1165,8 @@ static void aer_recover_work_func(struct work_struct *work)
else if (entry.severity == AER_FATAL)
pcie_do_recovery(pdev, pci_channel_io_frozen,
aer_root_reset);
+
+ pm_runtime_put(&pdev->dev);
pci_dev_put(pdev);
}
}
diff --git a/drivers/pci/pcie/edr.c b/drivers/pci/pcie/edr.c
index 5f4914d313a1..bd96babd7249 100644
--- a/drivers/pci/pcie/edr.c
+++ b/drivers/pci/pcie/edr.c
@@ -10,6 +10,7 @@
#include <linux/pci.h>
#include <linux/pci-acpi.h>
+#include <linux/pm_runtime.h>
#include "portdrv.h"
#include "../pci.h"
@@ -169,6 +170,7 @@ static void edr_handle_event(acpi_handle handle, u32 event, void *data)
return;
}
+ pm_runtime_get_sync(&edev->dev);
pci_dbg(pdev, "Reported EDR dev: %s\n", pci_name(edev));
/* If port does not support DPC, just send the OST */
@@ -209,6 +211,7 @@ static void edr_handle_event(acpi_handle handle, u32 event, void *data)
acpi_send_edr_status(pdev, edev, EDR_OST_FAILED);
}
+ pm_runtime_put(&edev->dev);
pci_dev_put(edev);
}
--
2.34.1
