Merge branch 'for-6.8/cxl-cper' into for-6.8/cxl

Pick up the CPER to CXL driver integration work for v6.8. Some
additional cleanup of cper_estatus_print() messages is needed, but that
is to be handled incrementally.

5 files changed, 213 insertions, 138 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 63ad0541db38..56a5d2ef9e0a 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
+#include <linux/cxl-event.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -657,6 +658,78 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/*
+ * Only a single callback can be registered for CXL CPER events.
+ */
+static DECLARE_RWSEM(cxl_cper_rw_sem);
+static cxl_cper_callback cper_callback;
+
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
+	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID						\
+	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID					\
+	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
+
+static void cxl_cper_post_event(enum cxl_event_type event_type,
+				struct cxl_cper_event_rec *rec)
+{
+	if (rec->hdr.length <= sizeof(rec->hdr) ||
+	    rec->hdr.length > sizeof(*rec)) {
+		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
+		       rec->hdr.length);
+		return;
+	}
+
+	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
+		pr_err(FW_WARN "CXL CPER invalid event\n");
+		return;
+	}
+
+	guard(rwsem_read)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		cper_callback(event_type, rec);
+}
+
+int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		return -EINVAL;
+	cper_callback = callback;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_callback, CXL);
+
+int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (callback != cper_callback)
+		return -EINVAL;
+	cper_callback = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_callback, CXL);
+
 static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -690,6 +763,22 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
+		} else if (guid_equal(sec_type,
+				      &CPER_SEC_CXL_MEM_MODULE_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index d51a1f250c8c..27166a411705 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -837,54 +837,37 @@ out:
 }
 EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL);
 
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-static const uuid_t gen_media_event_uuid =
-	UUID_INIT(0xfbcd0a77, 0xc260, 0x417f,
-		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6);
-
-/*
- * DRAM Event Record
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
- */
-static const uuid_t dram_event_uuid =
-	UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,
-		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24);
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-static const uuid_t mem_mod_event_uuid =
-	UUID_INIT(0xfe927475, 0xdd59, 0x4339,
-		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74);
-
-static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
-				   enum cxl_event_log_type type,
-				   struct cxl_event_record_raw *record)
+void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt)
 {
-	uuid_t *id = &record->hdr.id;
-
-	if (uuid_equal(id, &gen_media_event_uuid)) {
-		struct cxl_event_gen_media *rec =
-				(struct cxl_event_gen_media *)record;
+	if (event_type == CXL_CPER_EVENT_GEN_MEDIA)
+		trace_cxl_general_media(cxlmd, type, &evt->gen_media);
+	else if (event_type == CXL_CPER_EVENT_DRAM)
+		trace_cxl_dram(cxlmd, type, &evt->dram);
+	else if (event_type == CXL_CPER_EVENT_MEM_MODULE)
+		trace_cxl_memory_module(cxlmd, type, &evt->mem_module);
+	else
+		trace_cxl_generic_event(cxlmd, type, uuid, &evt->generic);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, CXL);
 
-		trace_cxl_general_media(cxlmd, type, rec);
-	} else if (uuid_equal(id, &dram_event_uuid)) {
-		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
+static void __cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+				     enum cxl_event_log_type type,
+				     struct cxl_event_record_raw *record)
+{
+	enum cxl_event_type ev_type = CXL_CPER_EVENT_GENERIC;
+	const uuid_t *uuid = &record->id;
 
-		trace_cxl_dram(cxlmd, type, rec);
-	} else if (uuid_equal(id, &mem_mod_event_uuid)) {
-		struct cxl_event_mem_module *rec =
-				(struct cxl_event_mem_module *)record;
+	if (uuid_equal(uuid, &CXL_EVENT_GEN_MEDIA_UUID))
+		ev_type = CXL_CPER_EVENT_GEN_MEDIA;
+	else if (uuid_equal(uuid, &CXL_EVENT_DRAM_UUID))
+		ev_type = CXL_CPER_EVENT_DRAM;
+	else if (uuid_equal(uuid, &CXL_EVENT_MEM_MODULE_UUID))
+		ev_type = CXL_CPER_EVENT_MEM_MODULE;
 
-		trace_cxl_memory_module(cxlmd, type, rec);
-	} else {
-		/* For unknown record types print just the header */
-		trace_cxl_generic_event(cxlmd, type, record);
-	}
+	cxl_event_trace_record(cxlmd, type, ev_type, uuid, &record->event);
 }
 
 static int cxl_clear_event_record(struct cxl_memdev_state *mds,
@@ -927,7 +910,10 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds,
 	 */
 	i = 0;
 	for (cnt = 0; cnt < total; cnt++) {
-		payload->handles[i++] = get_pl->records[cnt].hdr.handle;
+		struct cxl_event_record_raw *raw = &get_pl->records[cnt];
+		struct cxl_event_generic *gen = &raw->event.generic;
+
+		payload->handles[i++] = gen->hdr.handle;
 		dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log,
 			le16_to_cpu(payload->handles[i]));
 
@@ -992,8 +978,8 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds,
 			break;
 
 		for (i = 0; i < nr_rec; i++)
-			cxl_event_trace_record(cxlmd, type,
-					       &payload->records[i]);
+			__cxl_event_trace_record(cxlmd, type,
+						 &payload->records[i]);
 
 		if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW)
 			trace_cxl_overflow(cxlmd, type, payload);
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index a0b5819bc70b..89445435303a 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -181,6 +181,7 @@ TRACE_EVENT(cxl_overflow,
  *	1) Add CXL_EVT_TP_entry to TP_STRUCT__entry
  *	2) Use CXL_EVT_TP_fast_assign within TP_fast_assign;
  *	   pass the dev, log, and CXL event header
+ *	   NOTE: The uuid must be assigned by the specific trace event
  *	3) Use CXL_EVT_TP_printk() instead of TP_printk()
  *
  * See the generic_event tracepoint as an example.
@@ -203,7 +204,6 @@ TRACE_EVENT(cxl_overflow,
 	__assign_str(host, dev_name((cxlmd)->dev.parent));			\
 	__entry->log = (l);							\
 	__entry->serial = (cxlmd)->cxlds->serial;				\
-	memcpy(&__entry->hdr_uuid, &(hdr).id, sizeof(uuid_t));			\
 	__entry->hdr_length = (hdr).length;					\
 	__entry->hdr_flags = get_unaligned_le24((hdr).flags);			\
 	__entry->hdr_handle = le16_to_cpu((hdr).handle);			\
@@ -225,9 +225,9 @@ TRACE_EVENT(cxl_overflow,
 TRACE_EVENT(cxl_generic_event,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 struct cxl_event_record_raw *rec),
+		 const uuid_t *uuid, struct cxl_event_generic *gen_rec),
 
-	TP_ARGS(cxlmd, log, rec),
+	TP_ARGS(cxlmd, log, uuid, gen_rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -235,8 +235,9 @@ TRACE_EVENT(cxl_generic_event,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
+		CXL_EVT_TP_fast_assign(cxlmd, log, gen_rec->hdr);
+		memcpy(&__entry->hdr_uuid, uuid, sizeof(uuid_t));
+		memcpy(__entry->data, gen_rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
 	),
 
 	CXL_EVT_TP_printk("%s",
@@ -337,6 +338,7 @@ TRACE_EVENT(cxl_general_media,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		memcpy(&__entry->hdr_uuid, &CXL_EVENT_GEN_MEDIA_UUID, sizeof(uuid_t));
 
 		/* General Media */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -423,6 +425,7 @@ TRACE_EVENT(cxl_dram,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		memcpy(&__entry->hdr_uuid, &CXL_EVENT_DRAM_UUID, sizeof(uuid_t));
 
 		/* DRAM */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -570,6 +573,7 @@ TRACE_EVENT(cxl_memory_module,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		memcpy(&__entry->hdr_uuid, &CXL_EVENT_MEM_MODULE_UUID, sizeof(uuid_t));
 
 		/* Memory Module Event */
 		__entry->event_type = rec->event_type;
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 1125d4f988e1..5303d6942b88 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -6,6 +6,7 @@
 #include <linux/cdev.h>
 #include <linux/uuid.h>
 #include <linux/rcuwait.h>
+#include <linux/cxl-event.h>
 #include <linux/node.h>
 #include "cxl.h"
 
@@ -602,25 +603,28 @@ struct cxl_mbox_identify {
 } __packed;
 
 /*
- * Common Event Record Format
- * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ * General Media Event Record UUID
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
  */
-struct cxl_event_record_hdr {
-	uuid_t id;
-	u8 length;
-	u8 flags[3];
-	__le16 handle;
-	__le16 related_handle;
-	__le64 timestamp;
-	u8 maint_op_class;
-	u8 reserved[15];
-} __packed;
+#define CXL_EVENT_GEN_MEDIA_UUID                                            \
+	UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, 0x85, 0xa9, 0x08, 0x8b, 0x16, \
+		  0x21, 0xeb, 0xa6)
 
-#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
-struct cxl_event_record_raw {
-	struct cxl_event_record_hdr hdr;
-	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
-} __packed;
+/*
+ * DRAM Event Record UUID
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CXL_EVENT_DRAM_UUID                                                 \
+	UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, \
+		  0x5c, 0x96, 0x24)
+
+/*
+ * Memory Module Event Record UUID
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CXL_EVENT_MEM_MODULE_UUID                                           \
+	UUID_INIT(0xfe927475, 0xdd59, 0x4339, 0xa5, 0x86, 0x79, 0xba, 0xb1, \
+		  0x13, 0xb7, 0x74)
 
 /*
  * Get Event Records output payload
@@ -663,74 +667,6 @@ struct cxl_mbox_clear_event_payload {
 } __packed;
 #define CXL_CLEAR_EVENT_MAX_HANDLES U8_MAX
 
-/*
- * 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;
-
 struct cxl_mbox_get_partition_info {
 	__le64 active_volatile_cap;
 	__le64 active_persistent_cap;
@@ -888,6 +824,10 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 				  unsigned long *cmds);
 void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status);
+void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt);
 int cxl_set_timestamp(struct cxl_memdev_state *mds);
 int cxl_poison_state_init(struct cxl_memdev_state *mds);
 int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 0155fb66b580..4fd1f207c84e 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2020 Intel Corporation. All rights reserved. */
+#include <asm-generic/unaligned.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/moduleparam.h>
 #include <linux/module.h>
@@ -969,6 +970,61 @@ static struct pci_driver cxl_pci_driver = {
 	},
 };
 
+#define CXL_EVENT_HDR_FLAGS_REC_SEVERITY GENMASK(1, 0)
+static void cxl_cper_event_call(enum cxl_event_type ev_type,
+				struct cxl_cper_event_rec *rec)
+{
+	struct cper_cxl_event_devid *device_id = &rec->hdr.device_id;
+	struct pci_dev *pdev __free(pci_dev_put) = NULL;
+	enum cxl_event_log_type log_type;
+	struct cxl_dev_state *cxlds;
+	unsigned int devfn;
+	u32 hdr_flags;
+
+	devfn = PCI_DEVFN(device_id->device_num, device_id->func_num);
+	pdev = pci_get_domain_bus_and_slot(device_id->segment_num,
+					   device_id->bus_num, devfn);
+	if (!pdev)
+		return;
+
+	guard(pci_dev)(pdev);
+	if (pdev->driver != &cxl_pci_driver)
+		return;
+
+	cxlds = pci_get_drvdata(pdev);
+	if (!cxlds)
+		return;
+
+	/* Fabricate a log type */
+	hdr_flags = get_unaligned_le24(rec->event.generic.hdr.flags);
+	log_type = FIELD_GET(CXL_EVENT_HDR_FLAGS_REC_SEVERITY, hdr_flags);
+
+	cxl_event_trace_record(cxlds->cxlmd, log_type, ev_type,
+			       &uuid_null, &rec->event);
+}
+
+static int __init cxl_pci_driver_init(void)
+{
+	int rc;
+
+	rc = cxl_cper_register_callback(cxl_cper_event_call);
+	if (rc)
+		return rc;
+
+	rc = pci_register_driver(&cxl_pci_driver);
+	if (rc)
+		cxl_cper_unregister_callback(cxl_cper_event_call);
+
+	return rc;
+}
+
+static void __exit cxl_pci_driver_exit(void)
+{
+	pci_unregister_driver(&cxl_pci_driver);
+	cxl_cper_unregister_callback(cxl_cper_event_call);
+}
+
+module_init(cxl_pci_driver_init);
+module_exit(cxl_pci_driver_exit);
 MODULE_LICENSE("GPL v2");
-module_pci_driver(cxl_pci_driver);
 MODULE_IMPORT_NS(CXL);