Merge branch 'for-6.3/cxl-events' into cxl/next

Add the CXL event and interrupt support for the v6.3 update.

2 files changed, 353 insertions, 1 deletions

diff --git a/tools/testing/cxl/test/Kbuild b/tools/testing/cxl/test/Kbuild
index 4e59e2c911f6..61d5f7bcddf9 100644
--- a/tools/testing/cxl/test/Kbuild
+++ b/tools/testing/cxl/test/Kbuild
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-ccflags-y := -I$(srctree)/drivers/cxl/
+ccflags-y := -I$(srctree)/drivers/cxl/ -I$(srctree)/drivers/cxl/core
 
 obj-m += cxl_test.o
 obj-m += cxl_mock.o
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 5e4ecd93f1d2..9263b04d35f7 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -9,6 +9,8 @@
 #include <linux/bits.h>
 #include <cxlmem.h>
 
+#include "trace.h"
+
 #define LSA_SIZE SZ_128K
 #define DEV_SIZE SZ_2G
 #define EFFECT(x) (1U << x)
@@ -67,6 +69,26 @@ static struct {
 
 #define PASS_TRY_LIMIT 3
 
+#define CXL_TEST_EVENT_CNT_MAX 15
+
+/* Set a number of events to return at a time for simulation.  */
+#define CXL_TEST_EVENT_CNT 3
+
+struct mock_event_log {
+	u16 clear_idx;
+	u16 cur_idx;
+	u16 nr_events;
+	u16 nr_overflow;
+	u16 overflow_reset;
+	struct cxl_event_record_raw *events[CXL_TEST_EVENT_CNT_MAX];
+};
+
+struct mock_event_store {
+	struct cxl_dev_state *cxlds;
+	struct mock_event_log mock_logs[CXL_EVENT_TYPE_MAX];
+	u32 ev_status;
+};
+
 struct cxl_mockmem_data {
 	void *lsa;
 	u32 security_state;
@@ -74,9 +96,317 @@ struct cxl_mockmem_data {
 	u8 master_pass[NVDIMM_PASSPHRASE_LEN];
 	int user_limit;
 	int master_limit;
+	struct mock_event_store mes;
+	u8 event_buf[SZ_4K];
+};
+
+static struct mock_event_log *event_find_log(struct device *dev, int log_type)
+{
+	struct cxl_mockmem_data *mdata = dev_get_drvdata(dev);
+
+	if (log_type >= CXL_EVENT_TYPE_MAX)
+		return NULL;
+	return &mdata->mes.mock_logs[log_type];
+}
 
+static struct cxl_event_record_raw *event_get_current(struct mock_event_log *log)
+{
+	return log->events[log->cur_idx];
+}
+
+static void event_reset_log(struct mock_event_log *log)
+{
+	log->cur_idx = 0;
+	log->clear_idx = 0;
+	log->nr_overflow = log->overflow_reset;
+}
+
+/* Handle can never be 0 use 1 based indexing for handle */
+static u16 event_get_clear_handle(struct mock_event_log *log)
+{
+	return log->clear_idx + 1;
+}
+
+/* Handle can never be 0 use 1 based indexing for handle */
+static __le16 event_get_cur_event_handle(struct mock_event_log *log)
+{
+	u16 cur_handle = log->cur_idx + 1;
+
+	return cpu_to_le16(cur_handle);
+}
+
+static bool event_log_empty(struct mock_event_log *log)
+{
+	return log->cur_idx == log->nr_events;
+}
+
+static void mes_add_event(struct mock_event_store *mes,
+			  enum cxl_event_log_type log_type,
+			  struct cxl_event_record_raw *event)
+{
+	struct mock_event_log *log;
+
+	if (WARN_ON(log_type >= CXL_EVENT_TYPE_MAX))
+		return;
+
+	log = &mes->mock_logs[log_type];
+
+	if ((log->nr_events + 1) > CXL_TEST_EVENT_CNT_MAX) {
+		log->nr_overflow++;
+		log->overflow_reset = log->nr_overflow;
+		return;
+	}
+
+	log->events[log->nr_events] = event;
+	log->nr_events++;
+}
+
+static int mock_get_event(struct cxl_dev_state *cxlds,
+			  struct cxl_mbox_cmd *cmd)
+{
+	struct cxl_get_event_payload *pl;
+	struct mock_event_log *log;
+	u16 nr_overflow;
+	u8 log_type;
+	int i;
+
+	if (cmd->size_in != sizeof(log_type))
+		return -EINVAL;
+
+	if (cmd->size_out < struct_size(pl, records, CXL_TEST_EVENT_CNT))
+		return -EINVAL;
+
+	log_type = *((u8 *)cmd->payload_in);
+	if (log_type >= CXL_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	memset(cmd->payload_out, 0, cmd->size_out);
+
+	log = event_find_log(cxlds->dev, log_type);
+	if (!log || event_log_empty(log))
+		return 0;
+
+	pl = cmd->payload_out;
+
+	for (i = 0; i < CXL_TEST_EVENT_CNT && !event_log_empty(log); i++) {
+		memcpy(&pl->records[i], event_get_current(log),
+		       sizeof(pl->records[i]));
+		pl->records[i].hdr.handle = event_get_cur_event_handle(log);
+		log->cur_idx++;
+	}
+
+	pl->record_count = cpu_to_le16(i);
+	if (!event_log_empty(log))
+		pl->flags |= CXL_GET_EVENT_FLAG_MORE_RECORDS;
+
+	if (log->nr_overflow) {
+		u64 ns;
+
+		pl->flags |= CXL_GET_EVENT_FLAG_OVERFLOW;
+		pl->overflow_err_count = cpu_to_le16(nr_overflow);
+		ns = ktime_get_real_ns();
+		ns -= 5000000000; /* 5s ago */
+		pl->first_overflow_timestamp = cpu_to_le64(ns);
+		ns = ktime_get_real_ns();
+		ns -= 1000000000; /* 1s ago */
+		pl->last_overflow_timestamp = cpu_to_le64(ns);
+	}
+
+	return 0;
+}
+
+static int mock_clear_event(struct cxl_dev_state *cxlds,
+			    struct cxl_mbox_cmd *cmd)
+{
+	struct cxl_mbox_clear_event_payload *pl = cmd->payload_in;
+	struct mock_event_log *log;
+	u8 log_type = pl->event_log;
+	u16 handle;
+	int nr;
+
+	if (log_type >= CXL_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	log = event_find_log(cxlds->dev, log_type);
+	if (!log)
+		return 0; /* No mock data in this log */
+
+	/*
+	 * This check is technically not invalid per the specification AFAICS.
+	 * (The host could 'guess' handles and clear them in order).
+	 * However, this is not good behavior for the host so test it.
+	 */
+	if (log->clear_idx + pl->nr_recs > log->cur_idx) {
+		dev_err(cxlds->dev,
+			"Attempting to clear more events than returned!\n");
+		return -EINVAL;
+	}
+
+	/* Check handle order prior to clearing events */
+	for (nr = 0, handle = event_get_clear_handle(log);
+	     nr < pl->nr_recs;
+	     nr++, handle++) {
+		if (handle != le16_to_cpu(pl->handles[nr])) {
+			dev_err(cxlds->dev, "Clearing events out of order\n");
+			return -EINVAL;
+		}
+	}
+
+	if (log->nr_overflow)
+		log->nr_overflow = 0;
+
+	/* Clear events */
+	log->clear_idx += pl->nr_recs;
+	return 0;
+}
+
+static void cxl_mock_event_trigger(struct device *dev)
+{
+	struct cxl_mockmem_data *mdata = dev_get_drvdata(dev);
+	struct mock_event_store *mes = &mdata->mes;
+	int i;
+
+	for (i = CXL_EVENT_TYPE_INFO; i < CXL_EVENT_TYPE_MAX; i++) {
+		struct mock_event_log *log;
+
+		log = event_find_log(dev, i);
+		if (log)
+			event_reset_log(log);
+	}
+
+	cxl_mem_get_event_records(mes->cxlds, mes->ev_status);
+}
+
+struct cxl_event_record_raw maint_needed = {
+	.hdr = {
+		.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
+				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
+		.length = sizeof(struct cxl_event_record_raw),
+		.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0xa5b6),
+	},
+	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
+};
+
+struct cxl_event_record_raw hardware_replace = {
+	.hdr = {
+		.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
+				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
+		.length = sizeof(struct cxl_event_record_raw),
+		.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0xb6a5),
+	},
+	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
+};
+
+struct cxl_event_gen_media gen_media = {
+	.hdr = {
+		.id = UUID_INIT(0xfbcd0a77, 0xc260, 0x417f,
+				0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6),
+		.length = sizeof(struct cxl_event_gen_media),
+		.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0),
+	},
+	.phys_addr = cpu_to_le64(0x2000),
+	.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
+	.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
+	.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
+	/* .validity_flags = <set below> */
+	.channel = 1,
+	.rank = 30
+};
+
+struct cxl_event_dram dram = {
+	.hdr = {
+		.id = UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,
+				0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24),
+		.length = sizeof(struct cxl_event_dram),
+		.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0),
+	},
+	.phys_addr = cpu_to_le64(0x8000),
+	.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
+	.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
+	.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
+	/* .validity_flags = <set below> */
+	.channel = 1,
+	.bank_group = 5,
+	.bank = 2,
+	.column = {0xDE, 0xAD},
 };
 
+struct cxl_event_mem_module mem_module = {
+	.hdr = {
+		.id = UUID_INIT(0xfe927475, 0xdd59, 0x4339,
+				0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74),
+		.length = sizeof(struct cxl_event_mem_module),
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0),
+	},
+	.event_type = CXL_MMER_TEMP_CHANGE,
+	.info = {
+		.health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED,
+		.media_status = CXL_DHI_MS_ALL_DATA_LOST,
+		.add_status = (CXL_DHI_AS_CRITICAL << 2) |
+			      (CXL_DHI_AS_WARNING << 4) |
+			      (CXL_DHI_AS_WARNING << 5),
+		.device_temp = { 0xDE, 0xAD},
+		.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
+		.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+		.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+	}
+};
+
+static void cxl_mock_add_event_logs(struct mock_event_store *mes)
+{
+	put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK,
+			   &gen_media.validity_flags);
+
+	put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP |
+			   CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN,
+			   &dram.validity_flags);
+
+	mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed);
+	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
+		      (struct cxl_event_record_raw *)&gen_media);
+	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
+		      (struct cxl_event_record_raw *)&mem_module);
+	mes->ev_status |= CXLDEV_EVENT_STATUS_INFO;
+
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &maint_needed);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL,
+		      (struct cxl_event_record_raw *)&dram);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL,
+		      (struct cxl_event_record_raw *)&gen_media);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL,
+		      (struct cxl_event_record_raw *)&mem_module);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL,
+		      (struct cxl_event_record_raw *)&dram);
+	/* Overflow this log */
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes->ev_status |= CXLDEV_EVENT_STATUS_FAIL;
+
+	mes_add_event(mes, CXL_EVENT_TYPE_FATAL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FATAL,
+		      (struct cxl_event_record_raw *)&dram);
+	mes->ev_status |= CXLDEV_EVENT_STATUS_FATAL;
+}
+
 static int mock_gsl(struct cxl_mbox_cmd *cmd)
 {
 	if (cmd->size_out < sizeof(mock_gsl_payload))
@@ -582,6 +912,12 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *
 	case CXL_MBOX_OP_GET_PARTITION_INFO:
 		rc = mock_partition_info(cxlds, cmd);
 		break;
+	case CXL_MBOX_OP_GET_EVENT_RECORD:
+		rc = mock_get_event(cxlds, cmd);
+		break;
+	case CXL_MBOX_OP_CLEAR_EVENT_RECORD:
+		rc = mock_clear_event(cxlds, cmd);
+		break;
 	case CXL_MBOX_OP_SET_LSA:
 		rc = mock_set_lsa(cxlds, cmd);
 		break;
@@ -628,6 +964,15 @@ static bool is_rcd(struct platform_device *pdev)
 	return !!id->driver_data;
 }
 
+static ssize_t event_trigger_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	cxl_mock_event_trigger(dev);
+	return count;
+}
+static DEVICE_ATTR_WO(event_trigger);
+
 static int cxl_mock_mem_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -655,6 +1000,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
 	cxlds->serial = pdev->id;
 	cxlds->mbox_send = cxl_mock_mbox_send;
 	cxlds->payload_size = SZ_4K;
+	cxlds->event.buf = (struct cxl_get_event_payload *) mdata->event_buf;
 	if (is_rcd(pdev)) {
 		cxlds->rcd = true;
 		cxlds->component_reg_phys = CXL_RESOURCE_NONE;
@@ -672,10 +1018,15 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
 	if (rc)
 		return rc;
 
+	mdata->mes.cxlds = cxlds;
+	cxl_mock_add_event_logs(&mdata->mes);
+
 	cxlmd = devm_cxl_add_memdev(cxlds);
 	if (IS_ERR(cxlmd))
 		return PTR_ERR(cxlmd);
 
+	cxl_mem_get_event_records(cxlds, CXLDEV_EVENT_STATUS_ALL);
+
 	return 0;
 }
 
@@ -714,6 +1065,7 @@ static DEVICE_ATTR_RW(security_lock);
 
 static struct attribute *cxl_mock_mem_attrs[] = {
 	&dev_attr_security_lock.attr,
+	&dev_attr_event_trigger.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(cxl_mock_mem);