PCI/ERR: Recover from RCiEP AER errors

Add support for handling AER errors detected by Root Complex Integrated
Endpoints (RCiEPs).  These errors are signaled to software natively via a
Root Complex Event Collector (RCEC) or non-natively via ACPI APEI if the
platform retains control of AER or uses a non-standard RCEC-like device.

When recovering from RCiEP errors, the Root Error Command and Status
registers are in the AER Capability of an associated RCEC (if any), not in
a Root Port.  In the non-native case, the platform is responsible for those
registers and we can't touch them.

[bhelgaas: commit log, etc]
Co-developed-by: Sean V Kelley <sean.v.kelley@intel.com>
Link: https://lore.kernel.org/r/20201121001036.8560-13-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>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

2 files changed, 27 insertions, 12 deletions

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 84a785fa272c..e682df536be5 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1359,8 +1359,8 @@ static int aer_probe(struct pcie_device *dev)
 }
 
 /**
- * aer_root_reset - reset Root Port hierarchy or RCEC
- * @dev: pointer to Root Port or RCEC
+ * aer_root_reset - reset Root Port hierarchy, RCEC, or RCiEP
+ * @dev: pointer to Root Port, RCEC, or RCiEP
  *
  * Invoked by Port Bus driver when performing reset.
  */
@@ -1373,8 +1373,22 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	u32 reg32;
 	int rc;
 
-	root = dev;	/* device with Root Error registers */
-	aer = root->aer_cap;
+	/*
+	 * Only Root Ports and RCECs have AER Root Command and Root Status
+	 * registers.  If "dev" is an RCiEP, the relevant registers are in
+	 * the RCEC.
+	 */
+	if (type == PCI_EXP_TYPE_RC_END)
+		root = dev->rcec;
+	else
+		root = dev;
+
+	/*
+	 * If the platform retained control of AER, an RCiEP may not have
+	 * an RCEC visible to us, so dev->rcec ("root") may be NULL.  In
+	 * that case, firmware is responsible for these registers.
+	 */
+	aer = root ? root->aer_cap : 0;
 
 	if ((host->native_aer || pcie_ports_native) && aer) {
 		/* Disable Root's interrupt in response to error messages */
@@ -1383,7 +1397,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 		pci_write_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, reg32);
 	}
 
-	if (type == PCI_EXP_TYPE_RC_EC) {
+	if (type == PCI_EXP_TYPE_RC_EC || type == PCI_EXP_TYPE_RC_END) {
 		if (pcie_has_flr(dev)) {
 			rc = pcie_flr(dev);
 			pci_info(dev, "has been reset (%d)\n", rc);
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 87a2dc8d17f8..510f31f0ef6d 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -148,7 +148,7 @@ out:
 
 /**
  * pci_walk_bridge - walk bridges potentially AER affected
- * @bridge:	bridge which may be a Port or an RCEC
+ * @bridge:	bridge which may be a Port, an RCEC, or an RCiEP
  * @cb:		callback to be called for each device found
  * @userdata:	arbitrary pointer to be passed to callback
  *
@@ -156,8 +156,8 @@ out:
  * any bridged devices on buses under this bus.  Call the provided callback
  * on each device found.
  *
- * If the device provided has no subordinate bus, e.g., an RCEC, call the
- * callback on the device itself.
+ * If the device provided has no subordinate bus, e.g., an RCEC or RCiEP,
+ * call the callback on the device itself.
  */
 static void pci_walk_bridge(struct pci_dev *bridge,
 			    int (*cb)(struct pci_dev *, void *),
@@ -179,9 +179,9 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
 	struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
 
 	/*
-	 * If the error was detected by a Root Port, Downstream Port, or
-	 * RCEC, recovery runs on the device itself.  For Ports, that also
-	 * includes any subordinate devices.
+	 * If the error was detected by a Root Port, Downstream Port, RCEC,
+	 * or RCiEP, recovery runs on the device itself.  For Ports, that
+	 * also includes any subordinate devices.
 	 *
 	 * If it was detected by another device (Endpoint, etc), recovery
 	 * runs on the device and anything else under the same Port, i.e.,
@@ -189,7 +189,8 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
 	 */
 	if (type == PCI_EXP_TYPE_ROOT_PORT ||
 	    type == PCI_EXP_TYPE_DOWNSTREAM ||
-	    type == PCI_EXP_TYPE_RC_EC)
+	    type == PCI_EXP_TYPE_RC_EC ||
+	    type == PCI_EXP_TYPE_RC_END)
 		bridge = dev;
 	else
 		bridge = pci_upstream_bridge(dev);