cxl/pci: Add RCH downstream port AER register discovery

Restricted CXL host (RCH) downstream port AER information is not currently
logged while in the error state. One problem preventing the error logging
is the AER and RAS registers are not accessible. The CXL driver requires
changes to find RCH downstream port AER and RAS registers for purpose of
error logging.

RCH downstream ports are not enumerated during a PCI bus scan and are
instead discovered using system firmware, ACPI in this case.[1] The
downstream port is implemented as a Root Complex Register Block (RCRB).
The RCRB is a 4k memory block containing PCIe registers based on the PCIe
root port.[2] The RCRB includes AER extended capability registers used for
reporting errors. Note, the RCH's AER Capability is located in the RCRB
memory space instead of PCI configuration space, thus its register access
is different. Existing kernel PCIe AER functions can not be used to manage
the downstream port AER capabilities and RAS registers because the port was
not enumerated during PCI scan and the registers are not PCI config
accessible.

Discover RCH downstream port AER extended capability registers. Use MMIO
accesses to search for extended AER capability in RCRB register space.

[1] CXL 3.0 Spec, 9.11.2 - System Firmware View of CXL 1.1 Hierarchy
[2] CXL 3.0 Spec, 8.2.1.1 - RCH Downstream Port RCRB

Co-developed-by: Robert Richter <rrichter@amd.com>
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Signed-off-by: Robert Richter <rrichter@amd.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/20231018171713.1883517-12-rrichter@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

5 files changed, 61 insertions, 0 deletions

diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 45e7e044cf4a..f470ef5c0a6a 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -73,6 +73,7 @@ struct cxl_rcrb_info;
 resource_size_t __rcrb_to_component(struct device *dev,
 				    struct cxl_rcrb_info *ri,
 				    enum cxl_rcrb which);
+u16 cxl_rcrb_to_aer(struct device *dev, resource_size_t rcrb);
 
 extern struct rw_semaphore cxl_dpa_rwsem;
 
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index c7a7887ebdcf..cbccc222bb91 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -718,6 +718,21 @@ static bool cxl_report_and_clear(struct cxl_dev_state *cxlds)
 	return true;
 }
 
+#ifdef CONFIG_PCIEAER_CXL
+
+void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport)
+{
+	struct device *dport_dev = dport->dport_dev;
+	struct pci_host_bridge *host_bridge;
+
+	host_bridge = to_pci_host_bridge(dport_dev);
+	if (host_bridge->native_cxl_error)
+		dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_setup_parent_dport, CXL);
+
+#endif
+
 pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 				    pci_channel_state_t state)
 {
diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
index e0fbe964f6f0..9111ceef1127 100644
--- a/drivers/cxl/core/regs.c
+++ b/drivers/cxl/core/regs.c
@@ -470,6 +470,42 @@ int cxl_setup_regs(struct cxl_register_map *map)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_setup_regs, CXL);
 
+u16 cxl_rcrb_to_aer(struct device *dev, resource_size_t rcrb)
+{
+	void __iomem *addr;
+	u16 offset = 0;
+	u32 cap_hdr;
+
+	if (WARN_ON_ONCE(rcrb == CXL_RESOURCE_NONE))
+		return 0;
+
+	if (!request_mem_region(rcrb, SZ_4K, dev_name(dev)))
+		return 0;
+
+	addr = ioremap(rcrb, SZ_4K);
+	if (!addr)
+		goto out;
+
+	cap_hdr = readl(addr + offset);
+	while (PCI_EXT_CAP_ID(cap_hdr) != PCI_EXT_CAP_ID_ERR) {
+		offset = PCI_EXT_CAP_NEXT(cap_hdr);
+
+		/* Offset 0 terminates capability list. */
+		if (!offset)
+			break;
+		cap_hdr = readl(addr + offset);
+	}
+
+	if (offset)
+		dev_dbg(dev, "found AER extended capability (0x%x)\n", offset);
+
+	iounmap(addr);
+out:
+	release_mem_region(rcrb, SZ_4K);
+
+	return offset;
+}
+
 resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri,
 				    enum cxl_rcrb which)
 {
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index c07064e0c136..cdb2ade6ba29 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -704,6 +704,13 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
 					 struct device *dport_dev, int port_id,
 					 resource_size_t rcrb);
 
+#ifdef CONFIG_PCIEAER_CXL
+void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport);
+#else
+static inline void cxl_setup_parent_dport(struct device *host,
+					  struct cxl_dport *dport) { }
+#endif
+
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
 struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev);
 struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 04107058739b..e087febf9af0 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -157,6 +157,8 @@ static int cxl_mem_probe(struct device *dev)
 	else
 		endpoint_parent = &parent_port->dev;
 
+	cxl_setup_parent_dport(dev, dport);
+
 	device_lock(endpoint_parent);
 	if (!endpoint_parent->driver) {
 		dev_err(dev, "CXL port topology %s not enabled\n",