diff mbox series

[v3] PCI/AER: Block runtime suspend when handling errors

Message ID 20240212120135.146068-1-stanislaw.gruszka@linux.intel.com (mailing list archive)
State Accepted
Delegated to: Bjorn Helgaas
Headers show
Series [v3] PCI/AER: Block runtime suspend when handling errors | expand

Commit Message

Stanislaw Gruszka Feb. 12, 2024, 12:01 p.m. UTC
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.
It will also resume a device, if it was previously 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.

Cc: stable@vger.kernel.org
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
 drivers/pci/pcie/err.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

RFC -> v1:
 add runtime callbacks to pcie_do_recovery(), this covers DPC case
 as well as case of recovering multiple devices under same port.

v1 -> v2:
 - add R-b, A-b, cc-stable tags
 - tweak commit message

v2 -> v3:
 - fix mangled commit message

Comments

Bjorn Helgaas March 8, 2024, midnight UTC | #1
On Mon, Feb 12, 2024 at 01:01:35PM +0100, Stanislaw Gruszka wrote:
> 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.
> It will also resume a device, if it was previously 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.
> 
> Cc: stable@vger.kernel.org
> Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
> Acked-by: Rafael J. Wysocki <rafael@kernel.org>
> Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>

Applied to pci/aer for v6.9, thanks!

> ---
>  drivers/pci/pcie/err.c | 20 ++++++++++++++++++++
>  1 file changed, 20 insertions(+)
> 
> RFC -> v1:
>  add runtime callbacks to pcie_do_recovery(), this covers DPC case
>  as well as case of recovering multiple devices under same port.
> 
> v1 -> v2:
>  - add R-b, A-b, cc-stable tags
>  - tweak commit message
> 
> v2 -> v3:
>  - fix mangled commit message
> 
> diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
> index 59c90d04a609..705893b5f7b0 100644
> --- a/drivers/pci/pcie/err.c
> +++ b/drivers/pci/pcie/err.c
> @@ -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? */
> -- 
> 2.34.1
>
diff mbox series

Patch

diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 59c90d04a609..705893b5f7b0 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -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? */