Merge tag 'cxl-for-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull CXL (Compute Express Link) updates from Dan Williams:
 "The main new functionality this time is work to allow Linux to
  natively handle CXL link protocol errors signalled via PCIe AER for
  current generation CXL platforms. This required some enlightenment of
  the PCIe AER core to workaround the fact that current generation RCH
  (Restricted CXL Host) platforms physically hide topology details and
  registers via a mechanism called RCRB (Root Complex Register Block).

  The next major highlight is reworks to address bugs in parsing region
  configurations for next generation VH (Virtual Host) topologies. The
  old broken algorithm is replaced with a simpler one that significantly
  increases the number of region configurations supported by Linux. This
  is again relevant for error handling so that forward and reverse
  address translation of memory errors can be carried out by Linux for
  memory regions instantiated by platform firmware.

  As for other cross-tree work, the ACPI table parsing code has been
  refactored for reuse parsing the "CDAT" structure which is an
  ACPI-like data structure that is reported by CXL devices. That work is
  in preparation for v6.8 support for CXL QoS. Think of this as dynamic
  generation of NUMA node topology information generated by Linux rather
  than platform firmware.

  Lastly, a number of internal object lifetime issues have been resolved
  along with misc. fixes and feature updates (decoders_committed sysfs
  ABI).

  Summary:

   - Add support for RCH (Restricted CXL Host) Error recovery

   - Fix several region assembly bugs

   - Fix mem-device lifetime issues relative to the sanitize command and
     RCH topology.

   - Refactor ACPI table parsing for CDAT parsing re-use in preparation
     for CXL QOS support"

* tag 'cxl-for-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (50 commits)
  lib/fw_table: Remove acpi_parse_entries_array() export
  cxl/pci: Change CXL AER support check to use native AER
  cxl/hdm: Remove broken error path
  cxl/hdm: Fix && vs || bug
  acpi: Move common tables helper functions to common lib
  cxl: Add support for reading CXL switch CDAT table
  cxl: Add checksum verification to CDAT from CXL
  cxl: Export QTG ids from CFMWS to sysfs as qos_class attribute
  cxl: Add decoders_committed sysfs attribute to cxl_port
  cxl: Add cxl_decoders_committed() helper
  cxl/core/regs: Rework cxl_map_pmu_regs() to use map->dev for devm
  cxl/core/regs: Rename phys_addr in cxl_map_component_regs()
  PCI/AER: Unmask RCEC internal errors to enable RCH downstream port error handling
  PCI/AER: Forward RCH downstream port-detected errors to the CXL.mem dev handler
  cxl/pci: Disable root port interrupts in RCH mode
  cxl/pci: Add RCH downstream port error logging
  cxl/pci: Map RCH downstream AER registers for logging protocol errors
  cxl/pci: Update CXL error logging to use RAS register address
  PCI/AER: Refactor cper_print_aer() for use by CXL driver module
  cxl/pci: Add RCH downstream port AER register discovery
  ...

2 files changed, 162 insertions, 6 deletions

diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
index 228652a59f27..8999fcebde6a 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -49,6 +49,15 @@ config PCIEAER_INJECT
 	  gotten from:
 	     https://git.kernel.org/cgit/linux/kernel/git/gong.chen/aer-inject.git/
 
+config PCIEAER_CXL
+	bool "PCI Express CXL RAS support"
+	default y
+	depends on PCIEAER && CXL_PCI
+	help
+	  Enables CXL error handling.
+
+	  If unsure, say Y.
+
 #
 # PCI Express ECRC
 #
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index dcd35993004e..42a3bd35a3e1 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -760,9 +760,10 @@ int cper_severity_to_aer(int cper_severity)
 	}
 }
 EXPORT_SYMBOL_GPL(cper_severity_to_aer);
+#endif
 
-void cper_print_aer(struct pci_dev *dev, int aer_severity,
-		    struct aer_capability_regs *aer)
+void pci_print_aer(struct pci_dev *dev, int aer_severity,
+		   struct aer_capability_regs *aer)
 {
 	int layer, agent, tlp_header_valid = 0;
 	u32 status, mask;
@@ -801,7 +802,7 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity,
 	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
 			aer_severity, tlp_header_valid, &aer->header_log);
 }
-#endif
+EXPORT_SYMBOL_NS_GPL(pci_print_aer, CXL);
 
 /**
  * add_error_device - list device to be handled
@@ -934,14 +935,153 @@ static bool find_source_device(struct pci_dev *parent,
 	return true;
 }
 
+#ifdef CONFIG_PCIEAER_CXL
+
 /**
- * handle_error_source - handle logging error into an event log
+ * pci_aer_unmask_internal_errors - unmask internal errors
+ * @dev: pointer to the pcie_dev data structure
+ *
+ * Unmasks internal errors in the Uncorrectable and Correctable Error
+ * Mask registers.
+ *
+ * Note: AER must be enabled and supported by the device which must be
+ * checked in advance, e.g. with pcie_aer_is_native().
+ */
+static void pci_aer_unmask_internal_errors(struct pci_dev *dev)
+{
+	int aer = dev->aer_cap;
+	u32 mask;
+
+	pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, &mask);
+	mask &= ~PCI_ERR_UNC_INTN;
+	pci_write_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, mask);
+
+	pci_read_config_dword(dev, aer + PCI_ERR_COR_MASK, &mask);
+	mask &= ~PCI_ERR_COR_INTERNAL;
+	pci_write_config_dword(dev, aer + PCI_ERR_COR_MASK, mask);
+}
+
+static bool is_cxl_mem_dev(struct pci_dev *dev)
+{
+	/*
+	 * The capability, status, and control fields in Device 0,
+	 * Function 0 DVSEC control the CXL functionality of the
+	 * entire device (CXL 3.0, 8.1.3).
+	 */
+	if (dev->devfn != PCI_DEVFN(0, 0))
+		return false;
+
+	/*
+	 * CXL Memory Devices must have the 502h class code set (CXL
+	 * 3.0, 8.1.12.1).
+	 */
+	if ((dev->class >> 8) != PCI_CLASS_MEMORY_CXL)
+		return false;
+
+	return true;
+}
+
+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);
+}
+
+static bool is_internal_error(struct aer_err_info *info)
+{
+	if (info->severity == AER_CORRECTABLE)
+		return info->status & PCI_ERR_COR_INTERNAL;
+
+	return info->status & PCI_ERR_UNC_INTN;
+}
+
+static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data)
+{
+	struct aer_err_info *info = (struct aer_err_info *)data;
+	const struct pci_error_handlers *err_handler;
+
+	if (!is_cxl_mem_dev(dev) || !cxl_error_is_native(dev))
+		return 0;
+
+	/* protect dev->driver */
+	device_lock(&dev->dev);
+
+	err_handler = dev->driver ? dev->driver->err_handler : NULL;
+	if (!err_handler)
+		goto out;
+
+	if (info->severity == AER_CORRECTABLE) {
+		if (err_handler->cor_error_detected)
+			err_handler->cor_error_detected(dev);
+	} else if (err_handler->error_detected) {
+		if (info->severity == AER_NONFATAL)
+			err_handler->error_detected(dev, pci_channel_io_normal);
+		else if (info->severity == AER_FATAL)
+			err_handler->error_detected(dev, pci_channel_io_frozen);
+	}
+out:
+	device_unlock(&dev->dev);
+	return 0;
+}
+
+static void cxl_rch_handle_error(struct pci_dev *dev, struct aer_err_info *info)
+{
+	/*
+	 * Internal errors of an RCEC indicate an AER error in an
+	 * RCH's downstream port. Check and handle them in the CXL.mem
+	 * device driver.
+	 */
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC &&
+	    is_internal_error(info))
+		pcie_walk_rcec(dev, cxl_rch_handle_error_iter, info);
+}
+
+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);
+
+	/* Non-zero terminates iteration */
+	return *handles_cxl;
+}
+
+static bool handles_cxl_errors(struct pci_dev *rcec)
+{
+	bool handles_cxl = false;
+
+	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);
+
+	return handles_cxl;
+}
+
+static void cxl_rch_enable_rcec(struct pci_dev *rcec)
+{
+	if (!handles_cxl_errors(rcec))
+		return;
+
+	pci_aer_unmask_internal_errors(rcec);
+	pci_info(rcec, "CXL: Internal errors unmasked");
+}
+
+#else
+static inline void cxl_rch_enable_rcec(struct pci_dev *dev) { }
+static inline void cxl_rch_handle_error(struct pci_dev *dev,
+					struct aer_err_info *info) { }
+#endif
+
+/**
+ * pci_aer_handle_error - handle logging error into an event log
  * @dev: pointer to pci_dev data structure of error source device
  * @info: comprehensive error information
  *
  * Invoked when an error being detected by Root Port.
  */
-static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
+static void pci_aer_handle_error(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int aer = dev->aer_cap;
 
@@ -965,6 +1105,12 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
 		pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset);
 	else if (info->severity == AER_FATAL)
 		pcie_do_recovery(dev, pci_channel_io_frozen, aer_root_reset);
+}
+
+static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
+{
+	cxl_rch_handle_error(dev, info);
+	pci_aer_handle_error(dev, info);
 	pci_dev_put(dev);
 }
 
@@ -997,7 +1143,7 @@ static void aer_recover_work_func(struct work_struct *work)
 			       PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn));
 			continue;
 		}
-		cper_print_aer(pdev, entry.severity, entry.regs);
+		pci_print_aer(pdev, entry.severity, entry.regs);
 		/*
 		 * Memory for aer_capability_regs(entry.regs) is being allocated from the
 		 * ghes_estatus_pool to protect it from overwriting when multiple sections
@@ -1348,6 +1494,7 @@ static int aer_probe(struct pcie_device *dev)
 		return status;
 	}
 
+	cxl_rch_enable_rcec(port);
 	aer_enable_rootport(rpc);
 	pci_info(port, "enabled with IRQ %d\n", dev->irq);
 	return 0;