Bjorn, ... [v2] with missing Doc file.
P.
----8<----
Consider the following case
[ RP ]
|
|
+---------+-----------+
| | |
[H1] [H2] [X1]
where RP is a PCIE Root Port, H1 and H2 are devices with drivers that support
PCIE AER driver error handling (ie, they have pci_error_handlers defined in
the driver), and X1 is a device with a driver that does not support PCIE
AER driver error handling.
If the Root Port takes an error what currently happens is that the
bus resets and H1 & H2 call their slot_reset functions. X1 does nothing.
In some cases a user may not wish the system to continue because X1 is
an unhardened driver. In these cases, the system should not do a bus reset,
but rather the system should panic to avoid any further possible data
corruption.
This patch implements an AER_panic sysfs entry for each root port which
a user can modify. AER_panic = 1, means the system will panic on a
PCIE error which would have normally resulted in a secondary bus reset.
The default is AER_panic = 0.
Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: Bjorn Helgaas <bhelgaas@xxxxxxxxxx>
Cc: Shyam Iyer <Shyam_Iyer@xxxxxxxx>
Cc: gregkh@xxxxxxxxxxxxxxxxxxx
Cc: ddutile@xxxxxxxxxx
[v2]: added missing Documentation/ABI/testing/sysfs-bus-pci
---
Documentation/ABI/testing/sysfs-bus-pci | 10 +++++++
drivers/pci/pci-sysfs.c | 42 ++++++++++++++++++++++++++++++-
drivers/pci/pcie/aer/aerdrv.c | 3 ++
include/linux/pci.h | 1 +
4 files changed, 55 insertions(+), 1 deletions(-)
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 34f5110..e64d434 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -210,3 +210,13 @@ Users:
firmware assigned instance number of the PCI
device that can help in understanding the firmware
intended order of the PCI device.
+
+What: /sys/bus/pci/devices/.../AER_panic
+Date: May 2012
+Contact: linux-pci@xxxxxxxxxxxxxxx, Prarit Bhargava <prarit@xxxxxxxxxx>
+Description:
+ This file is present for PCIe Root Ports only and changes the
+ behavior when an AER event targets the port.
+ This attribute can have two values. If the value is 0, this
+ PCIe bus will issue a bus reset on the secondary bus. If the
+ value is 1, the kernel will panic. The default value is 0.
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index a55e248..8c6d525 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1135,6 +1135,35 @@ static ssize_t reset_store(struct device *dev,
static struct device_attribute reset_attr = __ATTR(reset, 0200, NULL, reset_store);
+static ssize_t AER_panic_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+
+ return sprintf(buf, "%d\n", pdev->rp_AER_panic);
+}
+
+static ssize_t AER_panic_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ unsigned long val;
+
+ if (kstrtoul(buf, 0, &val) < 0)
+ return -EINVAL;
+
+ if ((val > 1) || (val < 0))
+ return -EINVAL;
+
+ pdev->rp_AER_panic = val;
+
+ return count;
+}
+
+static struct device_attribute rp_AER_panic_attr =
+ __ATTR(AER_panic, 0600, AER_panic_show, AER_panic_store);
+
static int pci_create_capabilities_sysfs(struct pci_dev *dev)
{
int retval;
@@ -1169,8 +1198,16 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev)
goto error;
dev->reset_fn = 1;
}
- return 0;
+ /* PCIE Root Port panic-on-AER allows a user to configure each root
+ * port to panic on an AER error instead of issuing a bus reset.
+ */
+ if (dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) {
+ retval = device_create_file(&dev->dev, &rp_AER_panic_attr);
+ if (retval)
+ goto error;
+ }
+ return 0;
error:
pcie_aspm_remove_sysfs_dev_files(dev);
if (dev->vpd && dev->vpd->attr) {
@@ -1279,6 +1316,9 @@ static void pci_remove_capabilities_sysfs(struct pci_dev *dev)
device_remove_file(&dev->dev, &reset_attr);
dev->reset_fn = 0;
}
+
+ if (dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT)
+ device_remove_file(&dev->dev, &rp_AER_panic_attr);
}
/**
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 58ad791..dd6b352 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -346,6 +346,9 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
u32 reg32;
int pos;
+ if (dev->rp_AER_panic)
+ panic("%s: AER detected on Root Port", pci_name(dev));
+
pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
/* Disable Root's interrupt in response to error messages */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e444f5b..a4e6a5a 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -324,6 +324,7 @@ struct pci_dev {
unsigned int is_hotplug_bridge:1;
unsigned int __aer_firmware_first_valid:1;
unsigned int __aer_firmware_first:1;
+ unsigned int rp_AER_panic:1; /* if 1, panic on AER bus reset */
pci_dev_flags_t dev_flags;
atomic_t enable_cnt; /* pci_enable_device has been called */
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
