Merge tag 'cxl-for-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull CXL (Compute Express Link) updates from Dan Williams:
 "The bulk of this update is support for enumerating the performance
  capabilities of CXL memory targets and connecting that to a platform
  CXL memory QoS class. Some follow-on work remains to hook up this data
  into core-mm policy, but that is saved for v6.9.

  The next significant update is unifying how CXL event records (things
  like background scrub errors) are processed between so called
  "firmware first" and native error record retrieval. The CXL driver
  handler that processes the record retrieved from the device mailbox is
  now the handler for that same record format coming from an EFI/ACPI
  notification source.

  This also contains miscellaneous feature updates, like Get Timestamp,
  and other fixups.

  Summary:

   - Add support for parsing the Coherent Device Attribute Table (CDAT)

   - Add support for calculating a platform CXL QoS class from CDAT data

   - Unify the tracing of EFI CXL Events with native CXL Events.

   - Add Get Timestamp support

   - Miscellaneous cleanups and fixups"

* tag 'cxl-for-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (41 commits)
  cxl/core: use sysfs_emit() for attr's _show()
  cxl/pci: Register for and process CPER events
  PCI: Introduce cleanup helpers for device reference counts and locks
  acpi/ghes: Process CXL Component Events
  cxl/events: Create a CXL event union
  cxl/events: Separate UUID from event structures
  cxl/events: Remove passing a UUID to known event traces
  cxl/events: Create common event UUID defines
  cxl/events: Promote CXL event structures to a core header
  cxl: Refactor to use __free() for cxl_root allocation in cxl_endpoint_port_probe()
  cxl: Refactor to use __free() for cxl_root allocation in cxl_find_nvdimm_bridge()
  cxl: Fix device reference leak in cxl_port_perf_data_calculate()
  cxl: Convert find_cxl_root() to return a 'struct cxl_root *'
  cxl: Introduce put_cxl_root() helper
  cxl/port: Fix missing target list lock
  cxl/port: Fix decoder initialization when nr_targets > interleave_ways
  cxl/region: fix x9 interleave typo
  cxl/trace: Pass UUID explicitly to event traces
  cxl/region: use %pap format to print resource_size_t
  cxl/region: Add dev_dbg() detail on failure to allocate HPA space
  ...

7 files changed, 205 insertions, 10 deletions

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 118a18b7ff84..b7165e52b3c6 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,6 +15,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
+#include <linux/node.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -431,6 +432,16 @@ int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
 int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
 #endif
 
+#ifdef CONFIG_ACPI_HMAT
+int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord);
+#else
+static inline int acpi_get_genport_coordinates(u32 uid,
+					       struct access_coordinate *coord)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 #ifdef CONFIG_ACPI_NUMA
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
new file mode 100644
index 000000000000..91125eca4c8a
--- /dev/null
+++ b/include/linux/cxl-event.h
@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Intel Corporation. */
+#ifndef _LINUX_CXL_EVENT_H
+#define _LINUX_CXL_EVENT_H
+
+/*
+ * Common Event Record Format
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_hdr {
+	u8 length;
+	u8 flags[3];
+	__le16 handle;
+	__le16 related_handle;
+	__le64 timestamp;
+	u8 maint_op_class;
+	u8 reserved[15];
+} __packed;
+
+#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
+struct cxl_event_generic {
+	struct cxl_event_record_hdr hdr;
+	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
+} __packed;
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
+struct cxl_event_gen_media {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 device[3];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 reserved[46];
+} __packed;
+
+/*
+ * DRAM Event Record - DER
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
+ */
+#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
+struct cxl_event_dram {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 nibble_mask[3];
+	u8 bank_group;
+	u8 bank;
+	u8 row[3];
+	u8 column[2];
+	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
+	u8 reserved[0x17];
+} __packed;
+
+/*
+ * Get Health Info Record
+ * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
+ */
+struct cxl_get_health_info {
+	u8 health_status;
+	u8 media_status;
+	u8 add_status;
+	u8 life_used;
+	u8 device_temp[2];
+	u8 dirty_shutdown_cnt[4];
+	u8 cor_vol_err_cnt[4];
+	u8 cor_per_err_cnt[4];
+} __packed;
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+struct cxl_event_mem_module {
+	struct cxl_event_record_hdr hdr;
+	u8 event_type;
+	struct cxl_get_health_info info;
+	u8 reserved[0x3d];
+} __packed;
+
+union cxl_event {
+	struct cxl_event_generic generic;
+	struct cxl_event_gen_media gen_media;
+	struct cxl_event_dram dram;
+	struct cxl_event_mem_module mem_module;
+} __packed;
+
+/*
+ * Common Event Record Format; in event logs
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_raw {
+	uuid_t id;
+	union cxl_event event;
+} __packed;
+
+enum cxl_event_type {
+	CXL_CPER_EVENT_GENERIC,
+	CXL_CPER_EVENT_GEN_MEDIA,
+	CXL_CPER_EVENT_DRAM,
+	CXL_CPER_EVENT_MEM_MODULE,
+};
+
+#define CPER_CXL_DEVICE_ID_VALID		BIT(0)
+#define CPER_CXL_DEVICE_SN_VALID		BIT(1)
+#define CPER_CXL_COMP_EVENT_LOG_VALID		BIT(2)
+struct cxl_cper_event_rec {
+	struct {
+		u32 length;
+		u64 validation_bits;
+		struct cper_cxl_event_devid {
+			u16 vendor_id;
+			u16 device_id;
+			u8 func_num;
+			u8 device_num;
+			u8 bus_num;
+			u16 segment_num;
+			u16 slot_num; /* bits 2:0 reserved */
+			u8 reserved;
+		} __packed device_id;
+		struct cper_cxl_event_sn {
+			u32 lower_dw;
+			u32 upper_dw;
+		} __packed dev_serial_num;
+	} __packed hdr;
+
+	union cxl_event event;
+} __packed;
+
+typedef void (*cxl_cper_callback)(enum cxl_event_type type,
+				  struct cxl_cper_event_rec *rec);
+
+#ifdef CONFIG_ACPI_APEI_GHES
+int cxl_cper_register_callback(cxl_cper_callback callback);
+int cxl_cper_unregister_callback(cxl_cper_callback callback);
+#else
+static inline int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	return 0;
+}
+
+static inline int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	return 0;
+}
+#endif
+
+#endif /* _LINUX_CXL_EVENT_H */
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index ca49947f0a77..95421860397a 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -25,16 +25,35 @@ struct acpi_subtable_proc {
 	int count;
 };
 
+union fw_table_header {
+	struct acpi_table_header acpi;
+	struct acpi_table_cdat cdat;
+};
+
 union acpi_subtable_headers {
 	struct acpi_subtable_header common;
 	struct acpi_hmat_structure hmat;
 	struct acpi_prmt_module_header prmt;
 	struct acpi_cedt_header cedt;
+	struct acpi_cdat_header cdat;
 };
 
 int acpi_parse_entries_array(char *id, unsigned long table_size,
-			     struct acpi_table_header *table_header,
+			     union fw_table_header *table_header,
 			     struct acpi_subtable_proc *proc,
 			     int proc_num, unsigned int max_entries);
 
+int cdat_table_parse(enum acpi_cdat_type type,
+		     acpi_tbl_entry_handler_arg handler_arg, void *arg,
+		     struct acpi_table_cdat *table_header);
+
+/* CXL is the only non-ACPI consumer of the FIRMWARE_TABLE library */
+#if IS_ENABLED(CONFIG_ACPI) && !IS_ENABLED(CONFIG_CXL_BUS)
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_fwtbl_lib __init_or_acpilib
+#else
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, CXL)
+#define __init_or_fwtbl_lib
+#endif
+
 #endif
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 1e39d27bee41..69e781900082 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -33,7 +33,7 @@ struct memory_dev_type {
 	struct kref kref;
 };
 
-struct node_hmem_attrs;
+struct access_coordinate;
 
 #ifdef CONFIG_NUMA
 extern bool numa_demotion_enabled;
@@ -45,9 +45,9 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype);
 int register_mt_adistance_algorithm(struct notifier_block *nb);
 int unregister_mt_adistance_algorithm(struct notifier_block *nb);
 int mt_calc_adistance(int node, int *adist);
-int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source);
-int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist);
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -126,13 +126,13 @@ static inline int mt_calc_adistance(int node, int *adist)
 	return NOTIFY_DONE;
 }
 
-static inline int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+static inline int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 					   const char *source)
 {
 	return -EIO;
 }
 
-static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 {
 	return -EIO;
 }
diff --git a/include/linux/node.h b/include/linux/node.h
index 427a5975cf40..25b66d705ee2 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -20,14 +20,14 @@
 #include <linux/list.h>
 
 /**
- * struct node_hmem_attrs - heterogeneous memory performance attributes
+ * struct access_coordinate - generic performance coordinates container
  *
  * @read_bandwidth:	Read bandwidth in MB/s
  * @write_bandwidth:	Write bandwidth in MB/s
  * @read_latency:	Read latency in nanoseconds
  * @write_latency:	Write latency in nanoseconds
  */
-struct node_hmem_attrs {
+struct access_coordinate {
 	unsigned int read_bandwidth;
 	unsigned int write_bandwidth;
 	unsigned int read_latency;
@@ -65,7 +65,7 @@ struct node_cache_attrs {
 
 #ifdef CONFIG_HMEM_REPORTING
 void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs);
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 			 unsigned access);
 #else
 static inline void node_add_cache(unsigned int nid,
@@ -74,7 +74,7 @@ static inline void node_add_cache(unsigned int nid,
 }
 
 static inline void node_set_perf_attrs(unsigned int nid,
-				       struct node_hmem_attrs *hmem_attrs,
+				       struct access_coordinate *coord,
 				       unsigned access)
 {
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 99a66bc69a39..add9368e6314 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1171,6 +1171,7 @@ int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge);
 u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp);
 struct pci_dev *pci_dev_get(struct pci_dev *dev);
 void pci_dev_put(struct pci_dev *dev);
+DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T))
 void pci_remove_bus(struct pci_bus *b);
 void pci_stop_and_remove_bus_device(struct pci_dev *dev);
 void pci_stop_and_remove_bus_device_locked(struct pci_dev *dev);
@@ -1367,6 +1368,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps);
 u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 			     enum pci_bus_speed *speed,
 			     enum pcie_link_width *width);
+int pcie_link_speed_mbps(struct pci_dev *pdev);
 void pcie_print_link_status(struct pci_dev *dev);
 int pcie_reset_flr(struct pci_dev *dev, bool probe);
 int pcie_flr(struct pci_dev *dev);
@@ -1877,6 +1879,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev);
 void pci_dev_lock(struct pci_dev *dev);
 int pci_dev_trylock(struct pci_dev *dev);
 void pci_dev_unlock(struct pci_dev *dev);
+DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T))
 
 /*
  * PCI domain support.  Sometimes called PCI segment (eg by ACPI),
diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h
index 14bc6e742148..42066f4eb890 100644
--- a/include/uapi/linux/cxl_mem.h
+++ b/include/uapi/linux/cxl_mem.h
@@ -46,6 +46,7 @@
 	___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"),         \
 	___DEPRECATED(SCAN_MEDIA, "Scan Media"),                          \
 	___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"),          \
+	___C(GET_TIMESTAMP, "Get Timestamp"),                             \
 	___C(MAX, "invalid / last command")
 
 #define ___C(a, b) CXL_MEM_COMMAND_ID_##a