[RFC PATCH 3/6] PCI/AER: Enable RCEC to report internal error for CXL root port

From: Li Ming
Date: Wed Mar 13 2024 - 05:05:49 EST


Per CXl r3.1 section 12.2.2, CXL.cachemem protocol erros detected by CXL
root port could be logged in RCEC AER Extended Capability as
PCI_ERR_UNC_INTN or PCI_ERR_COR_INTERNAL. Unmask these errors for that
case.

Signed-off-by: Li Ming <ming4.li@xxxxxxxxx>
---
drivers/pci/pcie/aer.c | 24 +++++++++++++++++-------
1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 42a3bd35a3e1..364c74e47273 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -985,7 +985,7 @@ static bool cxl_error_is_native(struct pci_dev *dev)
{
struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);

- return (pcie_ports_native || host->native_aer);
+ return (pcie_ports_native || host->native_aer) && host->is_cxl;
}

static bool is_internal_error(struct aer_err_info *info)
@@ -1041,8 +1041,13 @@ static int handles_cxl_error_iter(struct pci_dev *dev, void *data)
{
bool *handles_cxl = data;

- if (!*handles_cxl)
- *handles_cxl = is_cxl_mem_dev(dev) && cxl_error_is_native(dev);
+ if (!*handles_cxl && cxl_error_is_native(dev)) {
+ if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END &&
+ dev->rcec && is_cxl_mem_dev(dev))
+ *handles_cxl = true;
+ if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+ *handles_cxl = true;
+ }

/* Non-zero terminates iteration */
return *handles_cxl;
@@ -1054,13 +1059,18 @@ static bool handles_cxl_errors(struct pci_dev *rcec)

if (pci_pcie_type(rcec) == PCI_EXP_TYPE_RC_EC &&
pcie_aer_is_native(rcec))
- pcie_walk_rcec(rcec, handles_cxl_error_iter, &handles_cxl);
+ pcie_walk_rcec_all(rcec, handles_cxl_error_iter, &handles_cxl);

return handles_cxl;
}

-static void cxl_rch_enable_rcec(struct pci_dev *rcec)
+static void cxl_enable_rcec(struct pci_dev *rcec)
{
+ /*
+ * Enable RCEC's internal error report for two cases:
+ * 1. RCiEP detected CXL.cachemem protocol errors
+ * 2. CXL root port detected CXL.cachemem protocol errors.
+ */
if (!handles_cxl_errors(rcec))
return;

@@ -1069,7 +1079,7 @@ static void cxl_rch_enable_rcec(struct pci_dev *rcec)
}

#else
-static inline void cxl_rch_enable_rcec(struct pci_dev *dev) { }
+static inline void cxl_enable_rcec(struct pci_dev *dev) { }
static inline void cxl_rch_handle_error(struct pci_dev *dev,
struct aer_err_info *info) { }
#endif
@@ -1494,7 +1504,7 @@ static int aer_probe(struct pcie_device *dev)
return status;
}

- cxl_rch_enable_rcec(port);
+ cxl_enable_rcec(port);
aer_enable_rootport(rpc);
pci_info(port, "enabled with IRQ %d\n", dev->irq);
return 0;
--
2.40.1