[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241022105849.1272-6-shiju.jose@huawei.com>
Date: Tue, 22 Oct 2024 11:58:48 +0100
From: <shiju.jose@...wei.com>
To: <dave.jiang@...el.com>, <dan.j.williams@...el.com>,
<jonathan.cameron@...wei.com>, <alison.schofield@...el.com>,
<vishal.l.verma@...el.com>, <ira.weiny@...el.com>, <dave@...olabs.net>,
<linux-cxl@...r.kernel.org>
CC: <linux-kernel@...r.kernel.org>, <linuxarm@...wei.com>,
<tanxiaofei@...wei.com>, <prime.zeng@...ilicon.com>, <shiju.jose@...wei.com>
Subject: [PATCH v2 5/6] cxl/events: Update Memory Module Event Record to CXL spec rev 3.1
From: Shiju Jose <shiju.jose@...wei.com>
CXL spec 3.1 section 8.2.9.2.1.3 Table 8-47, Memory Module Event Record
has updated with following new fields and new info for Device Event Type
and Device Health Information fields.
1. Validity Flags
2. Component Identifier
3. Device Event Sub-Type
Update the Memory Module event record and Memory Module trace event for
the above spec changes. The new fields are inserted in logical places.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@...wei.com>
Signed-off-by: Shiju Jose <shiju.jose@...wei.com>
---
drivers/cxl/core/trace.h | 56 ++++++++++++++++++++++++++++++++++------
include/cxl/event.h | 5 +++-
2 files changed, 52 insertions(+), 9 deletions(-)
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index f6142c01d306..4e11819b8589 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -616,7 +616,7 @@ TRACE_EVENT(cxl_dram,
/*
* Memory Module Event Record - MMER
*
- * CXL res 3.0 section 8.2.9.2.1.3; Table 8-45
+ * CXL res 3.1 section 8.2.9.2.1.3; Table 8-47
*/
#define CXL_MMER_HEALTH_STATUS_CHANGE 0x00
#define CXL_MMER_MEDIA_STATUS_CHANGE 0x01
@@ -624,27 +624,35 @@ TRACE_EVENT(cxl_dram,
#define CXL_MMER_TEMP_CHANGE 0x03
#define CXL_MMER_DATA_PATH_ERROR 0x04
#define CXL_MMER_LSA_ERROR 0x05
+#define CXL_MMER_UNRECOV_SIDEBAND_BUS_ERROR 0x06
+#define CXL_MMER_MEMORY_MEDIA_FRU_ERROR 0x07
+#define CXL_MMER_POWER_MANAGEMENT_FAULT 0x08
#define show_dev_evt_type(type) __print_symbolic(type, \
{ CXL_MMER_HEALTH_STATUS_CHANGE, "Health Status Change" }, \
{ CXL_MMER_MEDIA_STATUS_CHANGE, "Media Status Change" }, \
{ CXL_MMER_LIFE_USED_CHANGE, "Life Used Change" }, \
{ CXL_MMER_TEMP_CHANGE, "Temperature Change" }, \
{ CXL_MMER_DATA_PATH_ERROR, "Data Path Error" }, \
- { CXL_MMER_LSA_ERROR, "LSA Error" } \
+ { CXL_MMER_LSA_ERROR, "LSA Error" }, \
+ { CXL_MMER_UNRECOV_SIDEBAND_BUS_ERROR, "Unrecoverable Internal Sideband Bus Error" }, \
+ { CXL_MMER_MEMORY_MEDIA_FRU_ERROR, "Memory Media FRU Error" }, \
+ { CXL_MMER_POWER_MANAGEMENT_FAULT, "Power Management Fault" } \
)
/*
* Device Health Information - DHI
*
- * CXL res 3.0 section 8.2.9.8.3.1; Table 8-100
+ * CXL res 3.1 section 8.2.9.9.3.1; Table 8-133
*/
#define CXL_DHI_HS_MAINTENANCE_NEEDED BIT(0)
#define CXL_DHI_HS_PERFORMANCE_DEGRADED BIT(1)
#define CXL_DHI_HS_HW_REPLACEMENT_NEEDED BIT(2)
+#define CXL_DHI_HS_MEM_CAPACITY_DEGRADED BIT(3)
#define show_health_status_flags(flags) __print_flags(flags, "|", \
{ CXL_DHI_HS_MAINTENANCE_NEEDED, "MAINTENANCE_NEEDED" }, \
{ CXL_DHI_HS_PERFORMANCE_DEGRADED, "PERFORMANCE_DEGRADED" }, \
- { CXL_DHI_HS_HW_REPLACEMENT_NEEDED, "REPLACEMENT_NEEDED" } \
+ { CXL_DHI_HS_HW_REPLACEMENT_NEEDED, "REPLACEMENT_NEEDED" }, \
+ { CXL_DHI_HS_MEM_CAPACITY_DEGRADED, "MEM_CAPACITY_DEGRADED" } \
)
#define CXL_DHI_MS_NORMAL 0x00
@@ -698,6 +706,25 @@ TRACE_EVENT(cxl_dram,
#define CXL_DHI_AS_COR_VOL_ERR_CNT(as) ((as & 0x10) >> 4)
#define CXL_DHI_AS_COR_PER_ERR_CNT(as) ((as & 0x20) >> 5)
+#define CXL_MMER_VALID_COMPONENT BIT(0)
+#define CXL_MMER_VALID_COMPONENT_ID_FORMAT BIT(1)
+#define show_mem_module_valid_flags(flags) __print_flags(flags, "|", \
+ { CXL_MMER_VALID_COMPONENT, "COMPONENT" } \
+)
+#define CXL_MMER_DEV_EVT_SUB_TYPE_NOT_REPORTED 0x00
+#define CXL_MMER_DEV_EVT_SUB_TYPE_INVALID_CONFIG_DATA 0x01
+#define CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_CONFIG_DATA 0x02
+#define CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_MEM_MEDIA_FRU 0x03
+#define show_dev_event_sub_type(sub_type) __print_symbolic(sub_type, \
+ { CXL_MMER_DEV_EVT_SUB_TYPE_NOT_REPORTED, "Not Reported" }, \
+ { CXL_MMER_DEV_EVT_SUB_TYPE_INVALID_CONFIG_DATA, "Invalid Config Data" }, \
+ { CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_CONFIG_DATA, "Unsupported Config Data" }, \
+ { \
+ CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_MEM_MEDIA_FRU, \
+ "Unsupported Memory Media FRU" \
+ } \
+)
+
TRACE_EVENT(cxl_memory_module,
TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
@@ -710,6 +737,7 @@ TRACE_EVENT(cxl_memory_module,
/* Memory Module Event */
__field(u8, event_type)
+ __field(u8, event_sub_type)
/* Device Health Info */
__field(u8, health_status)
@@ -720,6 +748,8 @@ TRACE_EVENT(cxl_memory_module,
__field(u32, cor_per_err_cnt)
__field(s16, device_temp)
__field(u8, add_status)
+ __field(u16, validity_flags)
+ __array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE)
),
TP_fast_assign(
@@ -728,6 +758,7 @@ TRACE_EVENT(cxl_memory_module,
/* Memory Module Event */
__entry->event_type = rec->event_type;
+ __entry->event_sub_type = rec->event_sub_type;
/* Device Health Info */
__entry->health_status = rec->info.health_status;
@@ -738,13 +769,18 @@ TRACE_EVENT(cxl_memory_module,
__entry->cor_per_err_cnt = get_unaligned_le32(rec->info.cor_per_err_cnt);
__entry->device_temp = get_unaligned_le16(rec->info.device_temp);
__entry->add_status = rec->info.add_status;
+ __entry->validity_flags = get_unaligned_le16(rec->validity_flags);
+ memcpy(__entry->comp_id, &rec->component_id,
+ CXL_EVENT_GEN_MED_COMP_ID_SIZE);
),
- CXL_EVT_TP_printk("event_type='%s' health_status='%s' media_status='%s' " \
- "as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \
+ CXL_EVT_TP_printk("event_type='%s' event_sub_type='%s' health_status='%s' " \
+ "media_status='%s' as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \
"as_cor_per_err_cnt=%s life_used=%u device_temp=%d " \
- "dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u",
+ "dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u " \
+ "validity_flags='%s' comp_id=%s%s",
show_dev_evt_type(__entry->event_type),
+ show_dev_event_sub_type(__entry->event_sub_type),
show_health_status_flags(__entry->health_status),
show_media_status(__entry->media_status),
show_two_bit_status(CXL_DHI_AS_LIFE_USED(__entry->add_status)),
@@ -753,7 +789,11 @@ TRACE_EVENT(cxl_memory_module,
show_one_bit_status(CXL_DHI_AS_COR_PER_ERR_CNT(__entry->add_status)),
__entry->life_used, __entry->device_temp,
__entry->dirty_shutdown_cnt, __entry->cor_vol_err_cnt,
- __entry->cor_per_err_cnt
+ __entry->cor_per_err_cnt,
+ show_mem_module_valid_flags(__entry->validity_flags),
+ comp_id_pldm_flags(__entry->comp_id[0]),
+ cxl_print_component_id(__entry->validity_flags, CXL_MMER_VALID_COMPONENT,
+ CXL_MMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id)
)
);
diff --git a/include/cxl/event.h b/include/cxl/event.h
index 7e98492c85df..8ee93e146b5b 100644
--- a/include/cxl/event.h
+++ b/include/cxl/event.h
@@ -102,7 +102,10 @@ struct cxl_event_mem_module {
struct cxl_event_record_hdr hdr;
u8 event_type;
struct cxl_get_health_info info;
- u8 reserved[0x3d];
+ u8 validity_flags[2];
+ u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+ u8 event_sub_type;
+ u8 reserved[0x2a];
} __packed;
union cxl_event {
--
2.34.1
Powered by blists - more mailing lists