cxl/events: Update General Media Event Record to CXL spec rev 3.1

CXL spec rev 3.1 section 8.2.9.2.1.1 Table 8-45, General Media Event
Record has updated with following new fields and new types for Memory
Event Type and Transaction Type fields.
1. Advanced Programmable Corrected Memory Error Threshold Event Flags
2. Corrected Memory Error Count at Event
3. Memory Event Sub-Type

The format of component identifier has changed (CXL spec 3.1 section
8.2.9.2.1 Table 8-44).

Update the general media event record and general media trace event for
the above spec changes. The new fields are inserted in logical places.

Example trace log of cxl_general_media trace event,

cxl_general_media: memdev=mem0 host=0000:0f:00.0 serial=3 log=Fatal : \
time=156831237413 uuid=fbcd0a77-c260-417f-85a9-088b1621eba6 len=128 \
flags='0x1' handle=1 related_handle=0 maint_op_class=2 \
maint_op_sub_class=4 : dpa=30d40 dpa_flags='' \
descriptor='UNCORRECTABLE_EVENT|THRESHOLD_EVENT|POISON_LIST_OVERFLOW' \
type='TE State Violation' sub_type='Media Link Command Training Error' \
transaction_type='Host Inject Poison' channel=3 rank=33 device=5 \
validity_flags='CHANNEL|RANK|DEVICE|COMPONENT|COMPONENT PLDM FORMAT' \
comp_id=03 74 c5 08 9a 1a 0b fc d2 7e 2f 31 9b 3c 81 4d \
comp_id_pldm_valid_flags='PLDM Entity ID | Resource ID' \
pldm_entity_id=74 c5 08 9a 1a 0b pldm_resource_id=fc d2 7e 2f \
hpa=ffffffffffffffff region= \
region_uuid=00000000-0000-0000-0000-000000000000 \
cme_threshold_ev_flags='Corrected Memory Errors in Multiple Media \
Components|Exceeded Programmable Threshold' cme_count=120

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Link: https://patch.msgid.link/20250111091756.1682-4-shiju.jose@huawei.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index b508873ce4260b572795c7bd1163e02a404cbe42..39e83b8543f39a4aa3a0eb76f1731a27424100e5 100644 (file)
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -292,7 +292,7 @@ TRACE_EVENT(cxl_generic_event,
 
 /*
  * General Media Event Record - GMER
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45
  */
 #define CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT           BIT(0)
 #define CXL_GMER_EVT_DESC_THRESHOLD_EVENT              BIT(1)
@@ -306,10 +306,18 @@ TRACE_EVENT(cxl_generic_event,
 #define CXL_GMER_MEM_EVT_TYPE_ECC_ERROR                        0x00
 #define CXL_GMER_MEM_EVT_TYPE_INV_ADDR                 0x01
 #define CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR          0x02
-#define show_gmer_mem_event_type(type) __print_symbolic(type,                  \
-       { CXL_GMER_MEM_EVT_TYPE_ECC_ERROR,              "ECC Error" },          \
-       { CXL_GMER_MEM_EVT_TYPE_INV_ADDR,               "Invalid Address" },    \
-       { CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,        "Data Path Error" }     \
+#define CXL_GMER_MEM_EVT_TYPE_TE_STATE_VIOLATION       0x03
+#define CXL_GMER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR    0x04
+#define CXL_GMER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE    0x05
+#define CXL_GMER_MEM_EVT_TYPE_CKID_VIOLATION           0x06
+#define show_gmer_mem_event_type(type) __print_symbolic(type,                          \
+       { CXL_GMER_MEM_EVT_TYPE_ECC_ERROR,              "ECC Error" },                  \
+       { CXL_GMER_MEM_EVT_TYPE_INV_ADDR,               "Invalid Address" },            \
+       { CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,        "Data Path Error" },            \
+       { CXL_GMER_MEM_EVT_TYPE_TE_STATE_VIOLATION,     "TE State Violation" },         \
+       { CXL_GMER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR,  "Scrub Media ECC Error" },      \
+       { CXL_GMER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE,  "Adv Prog CME Counter Expiration" },    \
+       { CXL_GMER_MEM_EVT_TYPE_CKID_VIOLATION,         "CKID Violation" }              \
 )
 
 #define CXL_GMER_TRANS_UNKNOWN                         0x00
@@ -319,6 +327,8 @@ TRACE_EVENT(cxl_generic_event,
 #define CXL_GMER_TRANS_HOST_INJECT_POISON              0x04
 #define CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB            0x05
 #define CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT       0x06
+#define CXL_GMER_TRANS_INTERNAL_MEDIA_ECS              0x07
+#define CXL_GMER_TRANS_MEDIA_INITIALIZATION            0x08
 #define show_trans_type(type)  __print_symbolic(type,                                  \
        { CXL_GMER_TRANS_UNKNOWN,                       "Unknown" },                    \
        { CXL_GMER_TRANS_HOST_READ,                     "Host Read" },                  \
@@ -326,18 +336,57 @@ TRACE_EVENT(cxl_generic_event,
        { CXL_GMER_TRANS_HOST_SCAN_MEDIA,               "Host Scan Media" },            \
        { CXL_GMER_TRANS_HOST_INJECT_POISON,            "Host Inject Poison" },         \
        { CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,          "Internal Media Scrub" },       \
-       { CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT,     "Internal Media Management" }   \
+       { CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT,     "Internal Media Management" },  \
+       { CXL_GMER_TRANS_INTERNAL_MEDIA_ECS,            "Internal Media Error Check Scrub" },   \
+       { CXL_GMER_TRANS_MEDIA_INITIALIZATION,          "Media Initialization" }        \
 )
 
 #define CXL_GMER_VALID_CHANNEL                         BIT(0)
 #define CXL_GMER_VALID_RANK                            BIT(1)
 #define CXL_GMER_VALID_DEVICE                          BIT(2)
 #define CXL_GMER_VALID_COMPONENT                       BIT(3)
+#define CXL_GMER_VALID_COMPONENT_ID_FORMAT             BIT(4)
 #define show_valid_flags(flags)        __print_flags(flags, "|",                  \
        { CXL_GMER_VALID_CHANNEL,                       "CHANNEL"       }, \
        { CXL_GMER_VALID_RANK,                          "RANK"          }, \
        { CXL_GMER_VALID_DEVICE,                        "DEVICE"        }, \
-       { CXL_GMER_VALID_COMPONENT,                     "COMPONENT"     }  \
+       { CXL_GMER_VALID_COMPONENT,                     "COMPONENT"     }, \
+       { CXL_GMER_VALID_COMPONENT_ID_FORMAT,           "COMPONENT PLDM FORMAT" } \
+)
+
+#define CXL_GMER_CME_EV_FLAG_CME_MULTIPLE_MEDIA                BIT(0)
+#define CXL_GMER_CME_EV_FLAG_THRESHOLD_EXCEEDED                BIT(1)
+#define show_cme_threshold_ev_flags(flags)     __print_flags(flags, "|",       \
+       {                                                                       \
+               CXL_GMER_CME_EV_FLAG_CME_MULTIPLE_MEDIA,                        \
+               "Corrected Memory Errors in Multiple Media Components"          \
+       }, {                                                                    \
+               CXL_GMER_CME_EV_FLAG_THRESHOLD_EXCEEDED,                        \
+               "Exceeded Programmable Threshold"                               \
+       }                                                                       \
+)
+
+#define CXL_GMER_MEM_EVT_SUB_TYPE_NOT_REPORTED                         0x00
+#define CXL_GMER_MEM_EVT_SUB_TYPE_INTERNAL_DATAPATH_ERROR              0x01
+#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_COMMAND_TRAINING_ERROR    0x02
+#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CONTROL_TRAINING_ERROR    0x03
+#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_DATA_TRAINING_ERROR       0x04
+#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CRC_ERROR                 0x05
+#define show_mem_event_sub_type(sub_type)      __print_symbolic(sub_type,                      \
+       { CXL_GMER_MEM_EVT_SUB_TYPE_NOT_REPORTED, "Not Reported" },                             \
+       { CXL_GMER_MEM_EVT_SUB_TYPE_INTERNAL_DATAPATH_ERROR, "Internal Datapath Error" },       \
+       {                                                                                       \
+               CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_COMMAND_TRAINING_ERROR,                    \
+               "Media Link Command Training Error"                                             \
+       }, {                                                                                    \
+               CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CONTROL_TRAINING_ERROR,                    \
+               "Media Link Control Training Error"                                             \
+       }, {                                                                                    \
+               CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_DATA_TRAINING_ERROR,                       \
+               "Media Link Data Training Error"                                                \
+       }, {                                                                                    \
+               CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CRC_ERROR, "Media Link CRC Error"          \
+       }                                                                                       \
 )
 
 TRACE_EVENT(cxl_general_media,
@@ -363,6 +412,9 @@ TRACE_EVENT(cxl_general_media,
                __field(u16, validity_flags)
                __field(u8, rank)
                __field(u8, dpa_flags)
+               __field(u32, cme_count)
+               __field(u8, sub_type)
+               __field(u8, cme_threshold_ev_flags)
                __string(region_name, cxlr ? dev_name(&cxlr->dev) : "")
        ),
 
@@ -377,6 +429,7 @@ TRACE_EVENT(cxl_general_media,
                __entry->dpa &= CXL_DPA_MASK;
                __entry->descriptor = rec->media_hdr.descriptor;
                __entry->type = rec->media_hdr.type;
+               __entry->sub_type = rec->sub_type;
                __entry->transaction_type = rec->media_hdr.transaction_type;
                __entry->channel = rec->media_hdr.channel;
                __entry->rank = rec->media_hdr.rank;
@@ -392,20 +445,33 @@ TRACE_EVENT(cxl_general_media,
                        __assign_str(region_name);
                        uuid_copy(&__entry->region_uuid, &uuid_null);
                }
+               __entry->cme_threshold_ev_flags = rec->cme_threshold_ev_flags;
+               __entry->cme_count = get_unaligned_le24(rec->cme_count);
        ),
 
        CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' " \
-               "descriptor='%s' type='%s' transaction_type='%s' channel=%u rank=%u " \
-               "device=%x comp_id=%s validity_flags='%s' " \
-               "hpa=%llx region=%s region_uuid=%pUb",
+               "descriptor='%s' type='%s' sub_type='%s' " \
+               "transaction_type='%s' channel=%u rank=%u " \
+               "device=%x validity_flags='%s' " \
+               "comp_id=%s comp_id_pldm_valid_flags='%s' " \
+               "pldm_entity_id=%s pldm_resource_id=%s " \
+               "hpa=%llx region=%s region_uuid=%pUb " \
+               "cme_threshold_ev_flags='%s' cme_count=%u",
                __entry->dpa, show_dpa_flags(__entry->dpa_flags),
                show_event_desc_flags(__entry->descriptor),
                show_gmer_mem_event_type(__entry->type),
+               show_mem_event_sub_type(__entry->sub_type),
                show_trans_type(__entry->transaction_type),
                __entry->channel, __entry->rank, __entry->device,
-               __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE),
                show_valid_flags(__entry->validity_flags),
-               __entry->hpa, __get_str(region_name), &__entry->region_uuid
+               __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE),
+               show_comp_id_pldm_flags(__entry->comp_id[0]),
+               show_pldm_entity_id(__entry->validity_flags, CXL_GMER_VALID_COMPONENT,
+                                   CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+               show_pldm_resource_id(__entry->validity_flags, CXL_GMER_VALID_COMPONENT,
+                                     CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+               __entry->hpa, __get_str(region_name), &__entry->region_uuid,
+               show_cme_threshold_ev_flags(__entry->cme_threshold_ev_flags), __entry->cme_count
        )
 );
 

diff --git a/include/cxl/event.h b/include/cxl/event.h
index e1d485ad376b4a1bca536382dda4ac7836e98e35..2b07adf390102ad70af95e54dae3c5b5606c43aa 100644 (file)
--- a/include/cxl/event.h
+++ b/include/cxl/event.h
@@ -45,14 +45,17 @@ struct cxl_event_generic {
 
 /*
  * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45
  */
 #define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10
 struct cxl_event_gen_media {
        struct cxl_event_media_hdr media_hdr;
        u8 device[3];
        u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
-       u8 reserved[46];
+       u8 cme_threshold_ev_flags;
+       u8 cme_count[3];
+       u8 sub_type;
+       u8 reserved[41];
 } __packed;
 
 /*