[RESEND v13 24/25] CXL/PCI: Enable CXL protocol errors during CXL Port probe

Terry Bowman posted 25 patches 1 month, 1 week ago
[RESEND v13 24/25] CXL/PCI: Enable CXL protocol errors during CXL Port probe
Posted by Terry Bowman 1 month, 1 week ago
CXL protocol errors are not enabled for all CXL devices after boot. These
must be enabled inorder to process CXL protocol errors.

Introduce cxl_unmask_proto_interrupts() to call pci_aer_unmask_internal_errors().
pci_aer_unmask_internal_errors() expects the pdev->aer_cap is initialized.
But, dev->aer_cap is not initialized for CXL Upstream Switch Ports and CXL
Downstream Switch Ports. Initialize the dev->aer_cap if necessary. Enable AER
correctable internal errors and uncorrectable internal errors for all CXL
devices.

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com>

---

Changes in v12->v13:
- Add dev and dev_is_pci() NULL checks in cxl_unmask_proto_interrupts() (Terry)
- Add Dave Jiang's and Ben's review-by

Changes in v11->v12:
- None

Changes in v10->v11:
- Added check for valid PCI devices in is_cxl_error() (Terry)
- Removed check for RCiEP in cxl_handle_proto_err() and
  cxl_report_error_detected() (Terry)
---
 drivers/cxl/core/core.h |  4 ++++
 drivers/cxl/core/port.c |  4 ++++
 drivers/cxl/core/ras.c  | 26 +++++++++++++++++++++++++-
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 046ec65ed147..a7a0838c8f23 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -159,6 +159,8 @@ pci_ers_result_t pci_error_detected(struct pci_dev *pdev,
 void pci_cor_error_detected(struct pci_dev *pdev);
 pci_ers_result_t cxl_port_error_detected(struct device *dev);
 void cxl_port_cor_error_detected(struct device *dev);
+void cxl_mask_proto_interrupts(struct device *dev);
+void cxl_unmask_proto_interrupts(struct device *dev);
 #else
 static inline int cxl_ras_init(void)
 {
@@ -183,6 +185,8 @@ static inline pci_ers_result_t cxl_port_error_detected(struct device *dev)
 {
 	return PCI_ERS_RESULT_NONE;
 }
+static inline void cxl_unmask_proto_interrupts(struct device *dev) { }
+static inline void cxl_mask_proto_interrupts(struct device *dev) { }
 #endif /* CONFIG_CXL_RAS */
 
 /* Restricted CXL Host specific RAS functions */
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index d060f864cf2e..a23c742eb670 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1747,6 +1747,8 @@ static int add_port_attach_ep(struct cxl_memdev *cxlmd,
 		rc = -ENXIO;
 	}
 
+	cxl_unmask_proto_interrupts(cxlmd->cxlds->dev);
+
 	return rc;
 }
 
@@ -1833,6 +1835,8 @@ int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd)
 
 			rc = cxl_add_ep(dport, &cxlmd->dev);
 
+			cxl_unmask_proto_interrupts(cxlmd->cxlds->dev);
+
 			/*
 			 * If the endpoint already exists in the port's list,
 			 * that's ok, it was added on a previous pass.
diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index 52c6f19564b6..101e55723785 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -122,6 +122,23 @@ static bool is_pcie_endpoint(struct pci_dev *pdev)
 	return pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT;
 }
 
+void cxl_unmask_proto_interrupts(struct device *dev)
+{
+	if (!dev || !dev_is_pci(dev))
+		return;
+
+	struct pci_dev *pdev __free(pci_dev_put) = pci_dev_get(to_pci_dev(dev));
+
+	if (!pdev->aer_cap) {
+		pdev->aer_cap = pci_find_ext_capability(pdev,
+							PCI_EXT_CAP_ID_ERR);
+		if (!pdev->aer_cap)
+			return;
+	}
+
+	pci_aer_unmask_internal_errors(pdev);
+}
+
 static void cxl_dport_map_ras(struct cxl_dport *dport)
 {
 	struct cxl_register_map *map = &dport->reg_map;
@@ -230,7 +247,10 @@ void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
 
 		cxl_dport_map_rch_aer(dport);
 		cxl_disable_rch_root_ints(dport);
+		return;
 	}
+
+	cxl_unmask_proto_interrupts(dport->dport_dev);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
 
@@ -241,8 +261,12 @@ void cxl_uport_init_ras_reporting(struct cxl_port *port,
 
 	map->host = host;
 	if (cxl_map_component_regs(map, &port->uport_regs,
-				   BIT(CXL_CM_CAP_CAP_ID_RAS)))
+				   BIT(CXL_CM_CAP_CAP_ID_RAS))) {
 		dev_dbg(&port->dev, "Failed to map RAS capability\n");
+		return;
+	}
+
+	cxl_unmask_proto_interrupts(port->uport_dev);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_uport_init_ras_reporting, "CXL");
 
-- 
2.34.1