[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250110115556.1654-5-shiju.jose@huawei.com>
Date: Fri, 10 Jan 2025 11:55:54 +0000
From: <shiju.jose@...wei.com>
To: <dave.jiang@...el.com>, <dan.j.williams@...el.com>,
<jonathan.cameron@...wei.com>, <alison.schofield@...el.com>,
<nifan.cxl@...il.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 v5 4/6] cxl/events: Update DRAM Event Record to CXL spec rev 3.1
From: Shiju Jose <shiju.jose@...wei.com>
CXL spec 3.1 section 8.2.9.2.1.2 Table 8-46, DRAM Event Record has updated
with following new fields and new types for Memory Event Type, Transaction
Type and Validity Flags fields.
1. Component Identifier
2. Sub-channel
3. Advanced Programmable Corrected Memory Error Threshold Event Flags
4. Corrected Memory Error Count at Event
5. Memory Event Sub-Type
Update DRAM events record and DRAM trace event for the above spec
changes. The new fields are inserted in logical places.
Includes trivial consistency of white space improvements.
Example trace print of cxl_dram trace event,
cxl_dram: memdev=mem0 host=0000:0f:00.0 serial=3 log=Informational : \
time=54799339519 uuid=601dcbb3-9c06-4eab-b8af-4e9bfb5c9624 len=128 \
flags='0x1' handle=1 related_handle=0 maint_op_class=1 \
maint_op_sub_class=3 : dpa=18680 dpa_flags='' \
descriptor='UNCORRECTABLE_EVENT|THRESHOLD_EVENT' type='Data Path Error' \
sub_type='Media Link CRC Error' transaction_type='Internal Media Scrub' \
channel=3 rank=17 nibble_mask=3b00b2 bank_group=7 bank=11 row=2 \
column=77 cor_mask=21 00 00 00 00 00 00 00 2c 00 00 00 00 00 00 00 37 00 \
00 00 00 00 00 00 42 00 00 00 00 00 00 00 validity_flags='CHANNEL|RANK|NIBBLE|\
BANK GROUP|BANK|ROW|COLUMN|CORRECTION MASK|COMPONENT|COMPONENT PLDM FORMAT' \
comp_id=01 74 c5 08 9a 1a 0b fc d2 7e 2f 31 9b 3c 81 4d \
comp_id_pldm_valid_flags='PLDM Entity ID' pldm_entity_id=74 c5 08 9a 1a 0b \
pldm_resource_id=0x00 hpa=ffffffffffffffff region= \
region_uuid=00000000-0000-0000-0000-000000000000 sub_channel=5 \
cme_threshold_ev_flags='Corrected Memory Errors in Multiple Media Components|\
Exceeded Programmable Threshold' cvme_count=148
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@...wei.com>
Reviewed-by: Davidlohr Bueso <dave@...olabs.net>
Signed-off-by: Shiju Jose <shiju.jose@...wei.com>
---
drivers/cxl/core/trace.h | 71 ++++++++++++++++++++++++++++++----------
include/cxl/event.h | 9 +++--
2 files changed, 60 insertions(+), 20 deletions(-)
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 241c10596f4d..cbaf6244d77f 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -478,7 +478,7 @@ TRACE_EVENT(cxl_general_media,
/*
* DRAM Event Record - DER
*
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46
*/
/*
* DRAM Event Record defines many fields the same as the General Media Event
@@ -488,11 +488,17 @@ TRACE_EVENT(cxl_general_media,
#define CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR 0x01
#define CXL_DER_MEM_EVT_TYPE_INV_ADDR 0x02
#define CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR 0x03
-#define show_dram_mem_event_type(type) __print_symbolic(type, \
- { CXL_DER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \
- { CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \
- { CXL_DER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \
- { CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" } \
+#define CXL_DER_MEM_EVT_TYPE_TE_STATE_VIOLATION 0x04
+#define CXL_DER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE 0x05
+#define CXL_DER_MEM_EVT_TYPE_CKID_VIOLATION 0x06
+#define show_dram_mem_event_type(type) __print_symbolic(type, \
+ { CXL_DER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \
+ { CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \
+ { CXL_DER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \
+ { CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" }, \
+ { CXL_DER_MEM_EVT_TYPE_TE_STATE_VIOLATION, "TE State Violation" }, \
+ { CXL_DER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE, "Adv Prog CME Counter Expiration" }, \
+ { CXL_DER_MEM_EVT_TYPE_CKID_VIOLATION, "CKID Violation" } \
)
#define CXL_DER_VALID_CHANNEL BIT(0)
@@ -503,15 +509,21 @@ TRACE_EVENT(cxl_general_media,
#define CXL_DER_VALID_ROW BIT(5)
#define CXL_DER_VALID_COLUMN BIT(6)
#define CXL_DER_VALID_CORRECTION_MASK BIT(7)
-#define show_dram_valid_flags(flags) __print_flags(flags, "|", \
- { CXL_DER_VALID_CHANNEL, "CHANNEL" }, \
- { CXL_DER_VALID_RANK, "RANK" }, \
- { CXL_DER_VALID_NIBBLE, "NIBBLE" }, \
- { CXL_DER_VALID_BANK_GROUP, "BANK GROUP" }, \
- { CXL_DER_VALID_BANK, "BANK" }, \
- { CXL_DER_VALID_ROW, "ROW" }, \
- { CXL_DER_VALID_COLUMN, "COLUMN" }, \
- { CXL_DER_VALID_CORRECTION_MASK, "CORRECTION MASK" } \
+#define CXL_DER_VALID_COMPONENT BIT(8)
+#define CXL_DER_VALID_COMPONENT_ID_FORMAT BIT(9)
+#define CXL_DER_VALID_SUB_CHANNEL BIT(10)
+#define show_dram_valid_flags(flags) __print_flags(flags, "|", \
+ { CXL_DER_VALID_CHANNEL, "CHANNEL" }, \
+ { CXL_DER_VALID_RANK, "RANK" }, \
+ { CXL_DER_VALID_NIBBLE, "NIBBLE" }, \
+ { CXL_DER_VALID_BANK_GROUP, "BANK GROUP" }, \
+ { CXL_DER_VALID_BANK, "BANK" }, \
+ { CXL_DER_VALID_ROW, "ROW" }, \
+ { CXL_DER_VALID_COLUMN, "COLUMN" }, \
+ { CXL_DER_VALID_CORRECTION_MASK, "CORRECTION MASK" }, \
+ { CXL_DER_VALID_COMPONENT, "COMPONENT" }, \
+ { CXL_DER_VALID_COMPONENT_ID_FORMAT, "COMPONENT PLDM FORMAT" }, \
+ { CXL_DER_VALID_SUB_CHANNEL, "SUB CHANNEL" } \
)
TRACE_EVENT(cxl_dram,
@@ -527,6 +539,7 @@ TRACE_EVENT(cxl_dram,
__field(u64, dpa)
__field(u8, descriptor)
__field(u8, type)
+ __field(u8, sub_type)
__field(u8, transaction_type)
__field(u8, channel)
__field(u16, validity_flags)
@@ -541,6 +554,10 @@ TRACE_EVENT(cxl_dram,
__field(u8, bank) /* Out of order to pack trace record */
__field(u8, dpa_flags) /* Out of order to pack trace record */
__string(region_name, cxlr ? dev_name(&cxlr->dev) : "")
+ __array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE)
+ __field(u8, sub_channel)
+ __field(u8, cme_threshold_ev_flags)
+ __field(u32, cvme_count)
),
TP_fast_assign(
@@ -553,6 +570,7 @@ TRACE_EVENT(cxl_dram,
__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->validity_flags = get_unaligned_le16(rec->media_hdr.validity_flags);
__entry->channel = rec->media_hdr.channel;
@@ -572,23 +590,40 @@ TRACE_EVENT(cxl_dram,
__assign_str(region_name);
uuid_copy(&__entry->region_uuid, &uuid_null);
}
+ memcpy(__entry->comp_id, &rec->component_id,
+ CXL_EVENT_GEN_MED_COMP_ID_SIZE);
+ __entry->sub_channel = rec->sub_channel;
+ __entry->cme_threshold_ev_flags = rec->cme_threshold_ev_flags;
+ __entry->cvme_count = get_unaligned_le24(rec->cvme_count);
),
- CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' " \
+ CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' sub_type='%s' " \
"transaction_type='%s' channel=%u rank=%u nibble_mask=%x " \
"bank_group=%u bank=%u row=%u column=%u cor_mask=%s " \
"validity_flags='%s' " \
- "hpa=%llx region=%s region_uuid=%pUb",
+ "comp_id=%s comp_id_pldm_valid_flags='%s' " \
+ "pldm_entity_id=%s pldm_resource_id=%s " \
+ "hpa=%llx region=%s region_uuid=%pUb " \
+ "sub_channel=%u cme_threshold_ev_flags='%s' cvme_count=%u",
__entry->dpa, show_dpa_flags(__entry->dpa_flags),
show_event_desc_flags(__entry->descriptor),
show_dram_mem_event_type(__entry->type),
+ show_mem_event_sub_type(__entry->sub_type),
show_trans_type(__entry->transaction_type),
__entry->channel, __entry->rank, __entry->nibble_mask,
__entry->bank_group, __entry->bank,
__entry->row, __entry->column,
__print_hex(__entry->cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE),
show_dram_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_DER_VALID_COMPONENT,
+ CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+ show_pldm_resource_id(__entry->validity_flags, CXL_DER_VALID_COMPONENT,
+ CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+ __entry->hpa, __get_str(region_name), &__entry->region_uuid,
+ __entry->sub_channel, show_cme_threshold_ev_flags(__entry->cme_threshold_ev_flags),
+ __entry->cvme_count
)
);
diff --git a/include/cxl/event.h b/include/cxl/event.h
index 2b07adf39010..10815414f376 100644
--- a/include/cxl/event.h
+++ b/include/cxl/event.h
@@ -60,7 +60,7 @@ struct cxl_event_gen_media {
/*
* DRAM Event Record - DER
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
+ * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46
*/
#define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20
struct cxl_event_dram {
@@ -71,7 +71,12 @@ struct cxl_event_dram {
u8 row[3];
u8 column[2];
u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
- u8 reserved[0x17];
+ u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+ u8 sub_channel;
+ u8 cme_threshold_ev_flags;
+ u8 cvme_count[3];
+ u8 sub_type;
+ u8 reserved;
} __packed;
/*
--
2.43.0
Powered by blists - more mailing lists