[PATCH v8 16/16] CXL/PCI: Disable CXL protocol errors during CXL Port cleanup

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

During CXL device cleanup the CXL PCIe Port device interrupts may remain
enabled. This can potentialy allow unnecessary interrupt processing on
behalf of the CXL errors while the device is destroyed.

Disable CXL protocol errors by setting the CXL devices' AER mask register.

Introduce pci_aer_mask_internal_errors() similar to pci_aer_unmask_internal_errors().

Next, introduce cxl_disable_prot_errors() to call pci_aer_mask_internal_errors().
Register cxl_disable_prot_errors() to run at CXL device cleanup.
Register for CXL Root Ports, CXL Downstream Ports, CXL Upstream Ports, and
CXL Endpoints.

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
---
 drivers/cxl/port.c     | 18 +++++++++++++++++-
 drivers/pci/pcie/aer.c | 25 +++++++++++++++++++++++++
 include/linux/aer.h    |  1 +
 3 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index bb7a0526e609..7e3efd8be8eb 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -101,6 +101,19 @@ void cxl_enable_prot_errors(struct device *dev)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_enable_prot_errors, "CXL");
 
+void cxl_disable_prot_errors(void *_dev)
+{
+	struct device *dev = _dev;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct device *pci_dev __free(put_device) = get_device(&pdev->dev);
+
+	if (!pci_dev || !pdev->aer_cap)
+		return;
+
+	pci_aer_mask_internal_errors(pdev);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_disable_prot_errors, "CXL");
+
 static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
 {
 	resource_size_t aer_phys;
@@ -166,6 +179,7 @@ static void cxl_uport_init_ras_reporting(struct cxl_port *port,
 
 	cxl_assign_error_handlers(&port->dev, &cxl_port_error_handlers);
 	cxl_enable_prot_errors(port->uport_dev);
+	devm_add_action_or_reset(host, cxl_disable_prot_errors, port->uport_dev);
 }
 
 /**
@@ -197,6 +211,7 @@ void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
 
 	cxl_assign_error_handlers(dport->dport_dev, &cxl_port_error_handlers);
 	cxl_enable_prot_errors(dport->dport_dev);
+	devm_add_action_or_reset(host, cxl_disable_prot_errors, dport->dport_dev);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
 
@@ -223,7 +238,7 @@ static void cxl_endpoint_port_init_ras(struct cxl_port *port)
 	struct device *cxlmd_dev __free(put_device) = &cxlmd->dev;
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 
-	if (!dport || !dev_is_pci(dport->dport_dev)) {
+	if (!dport || !dev_is_pci(dport->dport_dev) || !dev_is_pci(cxlds->dev)) {
 		dev_err(&port->dev, "CXL port topology not found\n");
 		return;
 	}
@@ -232,6 +247,7 @@ static void cxl_endpoint_port_init_ras(struct cxl_port *port)
 
 	cxl_assign_error_handlers(cxlmd_dev, &cxl_ep_error_handlers);
 	cxl_enable_prot_errors(cxlds->dev);
+	devm_add_action_or_reset(cxlds->dev, cxl_disable_prot_errors, cxlds->dev);
 }
 
 #else
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index d3068f5cc767..d1ef0c676ff8 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -977,6 +977,31 @@ void pci_aer_unmask_internal_errors(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_NS_GPL(pci_aer_unmask_internal_errors, "CXL");
 
+/**
+ * pci_aer_mask_internal_errors - mask internal errors
+ * @dev: pointer to the pcie_dev data structure
+ *
+ * Masks internal errors in the Uncorrectable and Correctable Error
+ * Mask registers.
+ *
+ * Note: AER must be enabled and supported by the device which must be
+ * checked in advance, e.g. with pcie_aer_is_native().
+ */
+void pci_aer_mask_internal_errors(struct pci_dev *dev)
+{
+	int aer = dev->aer_cap;
+	u32 mask;
+
+	pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, &mask);
+	mask |= PCI_ERR_UNC_INTN;
+	pci_write_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, mask);
+
+	pci_read_config_dword(dev, aer + PCI_ERR_COR_MASK, &mask);
+	mask |= PCI_ERR_COR_INTERNAL;
+	pci_write_config_dword(dev, aer + PCI_ERR_COR_MASK, mask);
+}
+EXPORT_SYMBOL_NS_GPL(pci_aer_mask_internal_errors, "CXL");
+
 static bool is_cxl_mem_dev(struct pci_dev *dev)
 {
 	/*
diff --git a/include/linux/aer.h b/include/linux/aer.h
index a65fe324fad2..f0c84db466e5 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -101,5 +101,6 @@ int cper_severity_to_aer(int cper_severity);
 void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 		       int severity, struct aer_capability_regs *aer_regs);
 void pci_aer_unmask_internal_errors(struct pci_dev *dev);
+void pci_aer_mask_internal_errors(struct pci_dev *dev);
 #endif //_AER_H_
 
-- 
2.34.1