[RFC PATCH 3/9] PCI/portdrv: Update portdrv with an atomic notifier for reporting AER internal errors

[Terry Bowman <terry.bowman@amd.com>]

PCIe port devices are bound to portdrv, the PCIe port bus driver. portdrv
does not implement an AER correctable handler (CE) but does implement the
AER uncorrectable error (UCE). The UCE handler is fairly straightforward
in that it only checks for frozen error state and returns the next step
for recovery accordingly.

As a result, port devices relying on AER correctable internal errors (CIE)
and AER uncorrectable internal errors (UIE) will not be handled. Note,
the PCIe spec indicates AER CIE/UIE can be used to report implementation
specific errors.[1]

CXL root ports, CXL downstream switch ports, and CXL upstream switch ports
are examples of devices using the AER CIE/UIE for implementation specific
purposes. These CXL ports use the AER interrupt and AER CIE/UIE status to
report CXL RAS errors.[2]

Add an atomic notifier to portdrv's CE/UCE handlers. Use the atomic
notifier to report CIE/UIE errors to the registered functions. This will
require adding a CE handler and updating the existing UCE handler.

For the UCE handler, the CXL spec states UIE errors should return need
reset: "The only method of recovering from an Uncorrectable Internal Error
is reset or hardware replacement."[1]

[1] PCI6.0 - 6.2.10 Internal Errors
[2] CXL3.1 - 12.2.2 CXL Root Ports, Downstream Switch Ports, and
             Upstream Switch Ports

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: linux-pci@vger.kernel.org
---
 drivers/pci/pcie/portdrv.c | 32 ++++++++++++++++++++++++++++++++
 drivers/pci/pcie/portdrv.h |  2 ++
 2 files changed, 34 insertions(+)

diff --git a/drivers/pci/pcie/portdrv.c b/drivers/pci/pcie/portdrv.c
index 14a4b89a3b83..86d80e0e9606 100644
--- a/drivers/pci/pcie/portdrv.c
+++ b/drivers/pci/pcie/portdrv.c
@@ -37,6 +37,9 @@ struct portdrv_service_data {
 	u32 service;
 };
 
+ATOMIC_NOTIFIER_HEAD(portdrv_aer_internal_err_chain);
+EXPORT_SYMBOL_GPL(portdrv_aer_internal_err_chain);
+
 /**
  * release_pcie_device - free PCI Express port service device structure
  * @dev: Port service device to release
@@ -745,11 +748,39 @@ static void pcie_portdrv_shutdown(struct pci_dev *dev)
 static pci_ers_result_t pcie_portdrv_error_detected(struct pci_dev *dev,
 					pci_channel_state_t error)
 {
+	if (dev->aer_cap) {
+		u32 status;
+
+		pci_read_config_dword(dev, dev->aer_cap + PCI_ERR_UNCOR_STATUS,
+				      &status);
+
+		if (status & PCI_ERR_UNC_INTN) {
+			atomic_notifier_call_chain(&portdrv_aer_internal_err_chain,
+						   AER_FATAL, (void *)dev);
+			return PCI_ERS_RESULT_NEED_RESET;
+		}
+	}
+
 	if (error == pci_channel_io_frozen)
 		return PCI_ERS_RESULT_NEED_RESET;
 	return PCI_ERS_RESULT_CAN_RECOVER;
 }
 
+static void pcie_portdrv_cor_error_detected(struct pci_dev *dev)
+{
+	u32 status;
+
+	if (!dev->aer_cap)
+		return;
+
+	pci_read_config_dword(dev, dev->aer_cap + PCI_ERR_COR_STATUS,
+			      &status);
+
+	if (status & PCI_ERR_COR_INTERNAL)
+		atomic_notifier_call_chain(&portdrv_aer_internal_err_chain,
+					   AER_CORRECTABLE, (void *)dev);
+}
+
 static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev)
 {
 	size_t off = offsetof(struct pcie_port_service_driver, slot_reset);
@@ -780,6 +811,7 @@ static const struct pci_device_id port_pci_ids[] = {
 
 static const struct pci_error_handlers pcie_portdrv_err_handler = {
 	.error_detected = pcie_portdrv_error_detected,
+	.cor_error_detected = pcie_portdrv_cor_error_detected,
 	.slot_reset = pcie_portdrv_slot_reset,
 	.mmio_enabled = pcie_portdrv_mmio_enabled,
 };
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 12c89ea0313b..8a39197f0203 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -121,4 +121,6 @@ static inline void pcie_pme_interrupt_enable(struct pci_dev *dev, bool en) {}
 #endif /* !CONFIG_PCIE_PME */
 
 struct device *pcie_port_find_device(struct pci_dev *dev, u32 service);
+
+extern struct atomic_notifier_head portdrv_aer_internal_err_chain;
 #endif /* _PORTDRV_H_ */
-- 
2.34.1