lkml.org 
[lkml]   [2020]   [Sep]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v7 10/13] PCI/RCEC: Add RCiEP's linked RCEC to AER/ERR
Date
From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>

When attempting error recovery for an RCiEP associated with an RCEC device,
there needs to be a way to update the Root Error Status, the Uncorrectable
Error Status and the Uncorrectable Error Severity of the parent RCEC.
In some non-native cases in which there is no OS visible device
associated with the RCiEP, there is nothing to act upon as the firmware
is acting before the OS. So add handling for the linked 'rcec' in AER/ERR
while taking into account non-native cases.

Co-developed-by: Sean V Kelley <sean.v.kelley@intel.com>
Signed-off-by: Sean V Kelley <sean.v.kelley@intel.com>
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/pci/pcie/aer.c | 9 +++++----
drivers/pci/pcie/err.c | 39 ++++++++++++++++++++++++++++-----------
2 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 65dff5f3457a..dccdba60b5d9 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1358,17 +1358,18 @@ static int aer_probe(struct pcie_device *dev)
static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
{
int aer = dev->aer_cap;
+ int rc = 0;
u32 reg32;
- int rc;
-

/* Disable Root's interrupt in response to error messages */
pci_read_config_dword(dev, aer + PCI_ERR_ROOT_COMMAND, &reg32);
reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
pci_write_config_dword(dev, aer + PCI_ERR_ROOT_COMMAND, reg32);

- rc = pci_bus_error_reset(dev);
- pci_info(dev, "Root Port link has been reset\n");
+ if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_EC) {
+ rc = pci_bus_error_reset(dev);
+ pci_info(dev, "Root Port link has been reset\n");
+ }

/* Clear Root Error Status */
pci_read_config_dword(dev, aer + PCI_ERR_ROOT_STATUS, &reg32);
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 38abd7984996..956ad4c86d53 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -149,7 +149,8 @@ static int report_resume(struct pci_dev *dev, void *data)
/**
* pci_walk_bridge - walk bridges potentially AER affected
* @bridge bridge which may be an RCEC with associated RCiEPs,
- * an RCiEP associated with an RCEC, or a Port.
+ * or a Port.
+ * @dev an RCiEP lacking an associated RCEC.
* @cb callback to be called for each device found
* @userdata arbitrary pointer to be passed to callback.
*
@@ -160,13 +161,20 @@ static int report_resume(struct pci_dev *dev, void *data)
* If the device provided has no subordinate bus, call the provided
* callback on the device itself.
*/
-static void pci_walk_bridge(struct pci_dev *bridge, int (*cb)(struct pci_dev *, void *),
+static void pci_walk_bridge(struct pci_dev *bridge, struct pci_dev *dev,
+ int (*cb)(struct pci_dev *, void *),
void *userdata)
{
- if (bridge->subordinate)
+ /*
+ * In a non-native case where there is no OS-visible reporting
+ * device the bridge will be NULL, i.e., no RCEC, no PORT.
+ */
+ if (bridge && bridge->subordinate)
pci_walk_bus(bridge->subordinate, cb, userdata);
- else
+ else if (bridge)
cb(bridge, userdata);
+ else
+ cb(dev, userdata);
}

static pci_ers_result_t flr_on_rciep(struct pci_dev *dev)
@@ -196,16 +204,25 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
type = pci_pcie_type(dev);
if (type == PCI_EXP_TYPE_ROOT_PORT ||
type == PCI_EXP_TYPE_DOWNSTREAM ||
- type == PCI_EXP_TYPE_RC_EC ||
- type == PCI_EXP_TYPE_RC_END)
+ type == PCI_EXP_TYPE_RC_EC)
bridge = dev;
+ else if (type == PCI_EXP_TYPE_RC_END)
+ bridge = dev->rcec;
else
bridge = pci_upstream_bridge(dev);

pci_dbg(dev, "broadcast error_detected message\n");
if (state == pci_channel_io_frozen) {
- pci_walk_bridge(bridge, report_frozen_detected, &status);
+ pci_walk_bridge(bridge, dev, report_frozen_detected, &status);
if (type == PCI_EXP_TYPE_RC_END) {
+ /*
+ * The callback only clears the Root Error Status
+ * of the RCEC (see aer.c). Only perform this for the
+ * native case, i.e., an RCEC is present.
+ */
+ if (bridge)
+ reset_subordinate_devices(bridge);
+
status = flr_on_rciep(dev);
if (status != PCI_ERS_RESULT_RECOVERED) {
pci_warn(dev, "function level reset failed\n");
@@ -219,13 +236,13 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
}
}
} else {
- pci_walk_bridge(bridge, report_normal_detected, &status);
+ pci_walk_bridge(bridge, dev, report_normal_detected, &status);
}

if (status == PCI_ERS_RESULT_CAN_RECOVER) {
status = PCI_ERS_RESULT_RECOVERED;
pci_dbg(dev, "broadcast mmio_enabled message\n");
- pci_walk_bridge(bridge, report_mmio_enabled, &status);
+ pci_walk_bridge(bridge, dev, report_mmio_enabled, &status);
}

if (status == PCI_ERS_RESULT_NEED_RESET) {
@@ -236,14 +253,14 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
*/
status = PCI_ERS_RESULT_RECOVERED;
pci_dbg(dev, "broadcast slot_reset message\n");
- pci_walk_bridge(bridge, report_slot_reset, &status);
+ pci_walk_bridge(bridge, dev, report_slot_reset, &status);
}

if (status != PCI_ERS_RESULT_RECOVERED)
goto failed;

pci_dbg(dev, "broadcast resume message\n");
- pci_walk_bridge(bridge, report_resume, &status);
+ pci_walk_bridge(bridge, dev, report_resume, &status);

if (type == PCI_EXP_TYPE_ROOT_PORT ||
type == PCI_EXP_TYPE_DOWNSTREAM ||
--
2.28.0
\
 
 \ /
  Last update: 2020-10-01 00:00    [W:0.219 / U:9.952 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site