[PATCH v16 10/10] cxl: Enable CXL protocol error reporting

From: Terry Bowman

Date: Mon Mar 02 2026 - 16:46:54 EST


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@xxxxxxx>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@xxxxxxxxxxxxxxx>
Reviewed-by: Dave Jiang <dave.jiang@xxxxxxxxx>
Reviewed-by: Ben Cheatham <benjamin.cheatham@xxxxxxx>

---

Change in v15 -> v16:
- None

Change in v14 -> v15:
- None

Changes in v13->v14:
- Update commit title's prefix (Bjorn)

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
---
drivers/cxl/core/port.c | 2 ++
drivers/cxl/core/ras.c | 22 ++++++++++++++++++++++
drivers/cxl/cxlpci.h | 4 ++++
3 files changed, 28 insertions(+)

diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 27271402915f..c33d58fb7264 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1852,6 +1852,8 @@ 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 d6112b812c82..bfe6cb35154e 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -119,6 +119,24 @@ static void cxl_cper_prot_err_work_fn(struct work_struct *work)
}
static DECLARE_WORK(cxl_cper_prot_err_work, cxl_cper_prot_err_work_fn);

+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);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_unmask_proto_interrupts, "CXL");
+
static void cxl_dport_map_ras(struct cxl_dport *dport)
{
struct cxl_register_map *map = &dport->reg_map;
@@ -129,6 +147,8 @@ static void cxl_dport_map_ras(struct cxl_dport *dport)
else if (cxl_map_component_regs(map, &dport->regs.component,
BIT(CXL_CM_CAP_CAP_ID_RAS)))
dev_dbg(dev, "Failed to map RAS capability.\n");
+
+ cxl_unmask_proto_interrupts(dev);
}

/**
@@ -172,6 +192,8 @@ void devm_cxl_port_ras_setup(struct cxl_port *port)
if (cxl_map_component_regs(map, &port->regs,
BIT(CXL_CM_CAP_CAP_ID_RAS)))
dev_dbg(&port->dev, "Failed to map RAS capability\n");
+
+ cxl_unmask_proto_interrupts(port->uport_dev);
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_port_ras_setup, "CXL");

diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
index 184a95e96ea9..b7cf9d6137b3 100644
--- a/drivers/cxl/cxlpci.h
+++ b/drivers/cxl/cxlpci.h
@@ -82,6 +82,7 @@ void devm_cxl_dport_rch_ras_setup(struct cxl_dport *dport);
pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
pci_channel_state_t error);
void devm_cxl_port_ras_setup(struct cxl_port *port);
+void cxl_unmask_proto_interrupts(struct device *dev);
#else
static inline pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
pci_channel_state_t state)
@@ -96,6 +97,9 @@ static inline void devm_cxl_dport_rch_ras_setup(struct cxl_dport *dport)
static inline void devm_cxl_port_ras_setup(struct cxl_port *port)
{
}
+static inline void cxl_unmask_proto_interrupts(struct device *dev)
+{
+}
#endif

#endif /* __CXL_PCI_H__ */
--
2.34.1