cxl/pci: Remove CXL VH handling in CONFIG_PCIEAER_CXL conditional blocks from core/pci.c

Create new config CONFIG_CXL_RAS and put all CXL RAS items behind the
config. The config will depend on CPER and PCIE AER to build. Move the
related VH RAS code from core/pci.c to core/ras.c.

Restricted CXL host (RCH) RAS functions will be moved in a future patch.

Cc: Robert Richter <rrichter@amd.com>
Reviewed-by: Joshua Hahn <joshua.hahnjy@gmail.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Co-developed-by: Terry Bowman <terry.bowman@amd.com>
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260114182055.46029-8-terry.bowman@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

Author: davejiang

drivers/cxl/Kconfig

@@ -233,4 +233,8 @@ config CXL_MCE
 	def_bool y
 	depends on X86_MCE && MEMORY_FAILURE
 
+config CXL_RAS
+	def_bool y
+	depends on ACPI_APEI_GHES && PCIEAER && CXL_PCI
+
 endif

drivers/cxl/core/Makefile

@@ -14,9 +14,9 @@ cxl_core-y += pci.o
 cxl_core-y += hdm.o
 cxl_core-y += pmu.o
 cxl_core-y += cdat.o
-cxl_core-y += ras.o
 cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
 cxl_core-$(CONFIG_CXL_MCE) += mce.o
 cxl_core-$(CONFIG_CXL_FEATURES) += features.o
 cxl_core-$(CONFIG_CXL_EDAC_MEM_FEATURES) += edac.o
+cxl_core-$(CONFIG_CXL_RAS) += ras.o

drivers/cxl/core/core.h

@@ -144,8 +144,39 @@ int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c);
 int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
 					struct access_coordinate *c);
 
+#ifdef CONFIG_CXL_RAS
 int cxl_ras_init(void);
 void cxl_ras_exit(void);
+bool cxl_handle_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base);
+void cxl_handle_cor_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base);
+#else
+static inline int cxl_ras_init(void)
+{
+	return 0;
+}
+
+static inline void cxl_ras_exit(void)
+{
+}
+
+static inline bool cxl_handle_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base)
+{
+	return false;
+}
+static inline void cxl_handle_cor_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base) { }
+#endif /* CONFIG_CXL_RAS */
+
+/* Restricted CXL Host specific RAS functions */
+#ifdef CONFIG_CXL_RAS
+void cxl_dport_map_rch_aer(struct cxl_dport *dport);
+void cxl_disable_rch_root_ints(struct cxl_dport *dport);
+void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds);
+#else
+static inline void cxl_dport_map_rch_aer(struct cxl_dport *dport) { }
+static inline void cxl_disable_rch_root_ints(struct cxl_dport *dport) { }
+static inline void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
+#endif /* CONFIG_CXL_RAS */
+
 int cxl_gpf_port_setup(struct cxl_dport *dport);
 
 struct cxl_hdm;

drivers/cxl/core/pci.c

@@ -632,81 +632,8 @@ void read_cdat_data(struct cxl_port *port)
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, "CXL");
 
-static void cxl_handle_cor_ras(struct cxl_dev_state *cxlds,
-			       void __iomem *ras_base)
-{
-	void __iomem *addr;
-	u32 status;
-
-	if (!ras_base)
-		return;
-
-	addr = ras_base + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
-	status = readl(addr);
-	if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
-		writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
-		trace_cxl_aer_correctable_error(cxlds->cxlmd, status);
-	}
-}
-
-/* CXL spec rev3.0 8.2.4.16.1 */
-static void header_log_copy(void __iomem *ras_base, u32 *log)
-{
-	void __iomem *addr;
-	u32 *log_addr;
-	int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);
-
-	addr = ras_base + CXL_RAS_HEADER_LOG_OFFSET;
-	log_addr = log;
-
-	for (i = 0; i < log_u32_size; i++) {
-		*log_addr = readl(addr);
-		log_addr++;
-		addr += sizeof(u32);
-	}
-}
-
-/*
- * Log the state of the RAS status registers and prepare them to log the
- * next error status. Return 1 if reset needed.
- */
-static bool cxl_handle_ras(struct cxl_dev_state *cxlds,
-			   void __iomem *ras_base)
-{
-	u32 hl[CXL_HEADERLOG_SIZE_U32];
-	void __iomem *addr;
-	u32 status;
-	u32 fe;
-
-	if (!ras_base)
-		return false;
-
-	addr = ras_base + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
-	status = readl(addr);
-	if (!(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK))
-		return false;
-
-	/* If multiple errors, log header points to first error from ctrl reg */
-	if (hweight32(status) > 1) {
-		void __iomem *rcc_addr =
-			ras_base + CXL_RAS_CAP_CONTROL_OFFSET;
-
-		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
-				   readl(rcc_addr)));
-	} else {
-		fe = status;
-	}
-
-	header_log_copy(ras_base, hl);
-	trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe, hl);
-	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
-
-	return true;
-}
-
-#ifdef CONFIG_PCIEAER_CXL
-
-static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
+#ifdef CONFIG_CXL_RAS
+void cxl_dport_map_rch_aer(struct cxl_dport *dport)
 {
 	resource_size_t aer_phys;
 	struct device *host;
@@ -721,19 +648,7 @@ static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
 	}
 }
 
-static void cxl_dport_map_ras(struct cxl_dport *dport)
-{
-	struct cxl_register_map *map = &dport->reg_map;
-	struct device *dev = dport->dport_dev;
-
-	if (!map->component_map.ras.valid)
-		dev_dbg(dev, "RAS registers not found\n");
-	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");
-}
-
-static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
+void cxl_disable_rch_root_ints(struct cxl_dport *dport)
 {
 	void __iomem *aer_base = dport->regs.dport_aer;
 	u32 aer_cmd_mask, aer_cmd;
@@ -757,28 +672,6 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
 	writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND);
 }
 
-/**
- * cxl_dport_init_ras_reporting - Setup CXL RAS report on this dport
- * @dport: the cxl_dport that needs to be initialized
- * @host: host device for devm operations
- */
-void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
-{
-	dport->reg_map.host = host;
-	cxl_dport_map_ras(dport);
-
-	if (dport->rch) {
-		struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport->dport_dev);
-
-		if (!host_bridge->native_aer)
-			return;
-
-		cxl_dport_map_rch_aer(dport);
-		cxl_disable_rch_root_ints(dport);
-	}
-}
-EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
-
 /*
  * Copy the AER capability registers using 32 bit read accesses.
  * This is necessary because RCRB AER capability is MMIO mapped. Clear the
@@ -827,7 +720,7 @@ static bool cxl_rch_get_aer_severity(struct aer_capability_regs *aer_regs,
 	return false;
 }
 
-static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
+void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
 {
 	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
 	struct aer_capability_regs aer_regs;
@@ -852,82 +745,8 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
 	else
 		cxl_handle_ras(cxlds, dport->regs.ras);
 }
-
-#else
-static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
 #endif
 
-void cxl_cor_error_detected(struct pci_dev *pdev)
-{
-	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
-	struct device *dev = &cxlds->cxlmd->dev;
-
-	scoped_guard(device, dev) {
-		if (!dev->driver) {
-			dev_warn(&pdev->dev,
-				 "%s: memdev disabled, abort error handling\n",
-				 dev_name(dev));
-			return;
-		}
-
-		if (cxlds->rcd)
-			cxl_handle_rdport_errors(cxlds);
-
-		cxl_handle_cor_ras(cxlds, cxlds->regs.ras);
-	}
-}
-EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, "CXL");
-
-pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
-				    pci_channel_state_t state)
-{
-	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
-	struct cxl_memdev *cxlmd = cxlds->cxlmd;
-	struct device *dev = &cxlmd->dev;
-	bool ue;
-
-	scoped_guard(device, dev) {
-		if (!dev->driver) {
-			dev_warn(&pdev->dev,
-				 "%s: memdev disabled, abort error handling\n",
-				 dev_name(dev));
-			return PCI_ERS_RESULT_DISCONNECT;
-		}
-
-		if (cxlds->rcd)
-			cxl_handle_rdport_errors(cxlds);
-		/*
-		 * A frozen channel indicates an impending reset which is fatal to
-		 * CXL.mem operation, and will likely crash the system. On the off
-		 * chance the situation is recoverable dump the status of the RAS
-		 * capability registers and bounce the active state of the memdev.
-		 */
-		ue = cxl_handle_ras(cxlds, cxlds->regs.ras);
-	}
-
-
-	switch (state) {
-	case pci_channel_io_normal:
-		if (ue) {
-			device_release_driver(dev);
-			return PCI_ERS_RESULT_NEED_RESET;
-		}
-		return PCI_ERS_RESULT_CAN_RECOVER;
-	case pci_channel_io_frozen:
-		dev_warn(&pdev->dev,
-			 "%s: frozen state error detected, disable CXL.mem\n",
-			 dev_name(dev));
-		device_release_driver(dev);
-		return PCI_ERS_RESULT_NEED_RESET;
-	case pci_channel_io_perm_failure:
-		dev_warn(&pdev->dev,
-			 "failure state error detected, request disconnect\n");
-		return PCI_ERS_RESULT_DISCONNECT;
-	}
-	return PCI_ERS_RESULT_NEED_RESET;
-}
-EXPORT_SYMBOL_NS_GPL(cxl_error_detected, "CXL");
-
 static int cxl_flit_size(struct pci_dev *pdev)
 {
 	if (cxl_pci_flit_256(pdev))