From: ira.weiny@intel.com
To: Dan Williams <dan.j.williams@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>,
Steven Rostedt <rostedt@goodmis.org>,
Alison Schofield <alison.schofield@intel.com>,
Vishal Verma <vishal.l.verma@intel.com>,
Ben Widawsky <bwidawsk@kernel.org>,
Jonathan Cameron <Jonathan.Cameron@huawei.com>,
Davidlohr Bueso <dave@stgolabs.net>,
Dave Jiang <dave.jiang@intel.com>,
linux-kernel@vger.kernel.org, linux-cxl@vger.kernel.org
Subject: [PATCH V2 07/11] cxl/mem: Trace Memory Module Event Record
Date: Wed, 30 Nov 2022 16:27:15 -0800 [thread overview]
Message-ID: <20221201002719.2596558-8-ira.weiny@intel.com> (raw)
In-Reply-To: <20221201002719.2596558-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
CXL rev 3.0 section 8.2.9.2.1.3 defines the Memory Module Event Record.
Determine if the event read is memory module record and if so trace the
record.
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
Changes from V1:
Use all caps for flag fields
Changes from RFC v2:
Ensure field names match TP_print output
Steven
prefix TRACE_EVENT with 'cxl_'
Jonathan
Remove reserved field
Define a 1bit and 2 bit status decoder
Fix paren alignment
Changes from RFC:
Clean up spec reference
Add reserved data
Use new CXL header macros
Jonathan
Use else if
Use get_unaligned_le*() for unaligned fields
Dave Jiang
s/cxl_mem_mod_event/memory_module
s/cxl_evt_mem_mod_rec/cxl_event_mem_module
---
drivers/cxl/core/mbox.c | 17 ++++-
drivers/cxl/cxlmem.h | 26 +++++++
include/trace/events/cxl.h | 144 +++++++++++++++++++++++++++++++++++++
3 files changed, 186 insertions(+), 1 deletion(-)
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 66fc50d89bf4..30840b711381 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -725,11 +725,20 @@ 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 bool cxl_event_tracing_enabled(void)
{
return trace_cxl_generic_event_enabled() ||
trace_cxl_general_media_enabled() ||
- trace_cxl_dram_enabled();
+ trace_cxl_dram_enabled() ||
+ trace_cxl_memory_module_enabled();
}
static void cxl_trace_event_record(const char *dev_name,
@@ -749,6 +758,12 @@ static void cxl_trace_event_record(const char *dev_name,
trace_cxl_dram(dev_name, type, rec);
return;
+ } else if (uuid_equal(id, &mem_mod_event_uuid)) {
+ struct cxl_event_mem_module *rec =
+ (struct cxl_event_mem_module *)record;
+
+ trace_cxl_memory_module(dev_name, type, rec);
+ return;
}
/* For unknown record types print just the header */
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index f5f63a475478..450b410f29f6 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -452,6 +452,32 @@ struct cxl_event_dram {
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;
diff --git a/include/trace/events/cxl.h b/include/trace/events/cxl.h
index 474390f895d9..48786d6c9615 100644
--- a/include/trace/events/cxl.h
+++ b/include/trace/events/cxl.h
@@ -334,6 +334,150 @@ TRACE_EVENT(cxl_dram,
)
);
+/*
+ * Memory Module Event Record - MMER
+ *
+ * CXL res 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CXL_MMER_HEALTH_STATUS_CHANGE 0x00
+#define CXL_MMER_MEDIA_STATUS_CHANGE 0x01
+#define CXL_MMER_LIFE_USED_CHANGE 0x02
+#define CXL_MMER_TEMP_CHANGE 0x03
+#define CXL_MMER_DATA_PATH_ERROR 0x04
+#define CXL_MMER_LAS_ERROR 0x05
+#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_LAS_ERROR, "LSA Error" } \
+)
+
+/*
+ * Device Health Information - DHI
+ *
+ * CXL res 3.0 section 8.2.9.8.3.1; Table 8-100
+ */
+#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 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" } \
+)
+
+#define CXL_DHI_MS_NORMAL 0x00
+#define CXL_DHI_MS_NOT_READY 0x01
+#define CXL_DHI_MS_WRITE_PERSISTENCY_LOST 0x02
+#define CXL_DHI_MS_ALL_DATA_LOST 0x03
+#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_POWER_LOSS 0x04
+#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_SHUTDOWN 0x05
+#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_IMMINENT 0x06
+#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_POWER_LOSS 0x07
+#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_SHUTDOWN 0x08
+#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_IMMINENT 0x09
+#define show_media_status(ms) __print_symbolic(ms, \
+ { CXL_DHI_MS_NORMAL, \
+ "Normal" }, \
+ { CXL_DHI_MS_NOT_READY, \
+ "Not Ready" }, \
+ { CXL_DHI_MS_WRITE_PERSISTENCY_LOST, \
+ "Write Persistency Lost" }, \
+ { CXL_DHI_MS_ALL_DATA_LOST, \
+ "All Data Lost" }, \
+ { CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_POWER_LOSS, \
+ "Write Persistency Loss in the Event of Power Loss" }, \
+ { CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_SHUTDOWN, \
+ "Write Persistency Loss in Event of Shutdown" }, \
+ { CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_IMMINENT, \
+ "Write Persistency Loss Imminent" }, \
+ { CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_POWER_LOSS, \
+ "All Data Loss in Event of Power Loss" }, \
+ { CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_SHUTDOWN, \
+ "All Data loss in the Event of Shutdown" }, \
+ { CXL_DHI_MS_WRITE_ALL_DATA_LOSS_IMMINENT, \
+ "All Data Loss Imminent" } \
+)
+
+#define CXL_DHI_AS_NORMAL 0x0
+#define CXL_DHI_AS_WARNING 0x1
+#define CXL_DHI_AS_CRITICAL 0x2
+#define show_two_bit_status(as) __print_symbolic(as, \
+ { CXL_DHI_AS_NORMAL, "Normal" }, \
+ { CXL_DHI_AS_WARNING, "Warning" }, \
+ { CXL_DHI_AS_CRITICAL, "Critical" } \
+)
+#define show_one_bit_status(as) __print_symbolic(as, \
+ { CXL_DHI_AS_NORMAL, "Normal" }, \
+ { CXL_DHI_AS_WARNING, "Warning" } \
+)
+
+#define CXL_DHI_AS_LIFE_USED(as) (as & 0x3)
+#define CXL_DHI_AS_DEV_TEMP(as) ((as & 0xC) >> 2)
+#define CXL_DHI_AS_COR_VOL_ERR_CNT(as) ((as & 0x10) >> 4)
+#define CXL_DHI_AS_COR_PER_ERR_CNT(as) ((as & 0x20) >> 5)
+
+TRACE_EVENT(cxl_memory_module,
+
+ TP_PROTO(const char *dev_name, enum cxl_event_log_type log,
+ struct cxl_event_mem_module *rec),
+
+ TP_ARGS(dev_name, log, rec),
+
+ TP_STRUCT__entry(
+ CXL_EVT_TP_entry
+
+ /* Memory Module Event */
+ __field(u8, event_type)
+
+ /* Device Health Info */
+ __field(u8, health_status)
+ __field(u8, media_status)
+ __field(u8, life_used)
+ __field(u32, dirty_shutdown_cnt)
+ __field(u32, cor_vol_err_cnt)
+ __field(u32, cor_per_err_cnt)
+ __field(s16, device_temp)
+ __field(u8, add_status)
+ ),
+
+ TP_fast_assign(
+ CXL_EVT_TP_fast_assign(dev_name, log, rec->hdr);
+
+ /* Memory Module Event */
+ __entry->event_type = rec->event_type;
+
+ /* Device Health Info */
+ __entry->health_status = rec->info.health_status;
+ __entry->media_status = rec->info.media_status;
+ __entry->life_used = rec->info.life_used;
+ __entry->dirty_shutdown_cnt = get_unaligned_le32(rec->info.dirty_shutdown_cnt);
+ __entry->cor_vol_err_cnt = get_unaligned_le32(rec->info.cor_vol_err_cnt);
+ __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;
+ ),
+
+ 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 " \
+ "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",
+ show_dev_evt_type(__entry->event_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)),
+ show_two_bit_status(CXL_DHI_AS_DEV_TEMP(__entry->add_status)),
+ show_one_bit_status(CXL_DHI_AS_COR_VOL_ERR_CNT(__entry->add_status)),
+ 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
+ )
+);
+
+
#endif /* _CXL_TRACE_EVENTS_H */
/* This part must be outside protection */
--
2.37.2
next prev parent reply other threads:[~2022-12-01 0:27 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-01 0:27 [PATCH V2 00/11] CXL: Process event logs ira.weiny
2022-12-01 0:27 ` [PATCH V2 01/11] cxl/pci: Add generic MSI-X/MSI irq support ira.weiny
2022-12-01 10:18 ` Jonathan Cameron
2022-12-01 18:37 ` Dave Jiang
2022-12-02 0:23 ` Dan Williams
2022-12-02 0:34 ` Ira Weiny
2022-12-02 2:00 ` Dan Williams
2022-12-02 13:04 ` Jonathan Cameron
2022-12-01 0:27 ` [PATCH V2 02/11] cxl/mem: Implement Get Event Records command ira.weiny
2022-12-01 13:06 ` Jonathan Cameron
2022-12-01 15:10 ` Ira Weiny
2022-12-01 17:38 ` Steven Rostedt
2022-12-02 0:09 ` Ira Weiny
2022-12-02 4:40 ` Steven Rostedt
2022-12-02 5:00 ` Steven Rostedt
2022-12-02 21:31 ` Ira Weiny
2022-12-02 1:39 ` Dan Williams
2022-12-02 21:47 ` Ira Weiny
2022-12-03 21:33 ` Dan Williams
2022-12-01 0:27 ` [PATCH V2 03/11] cxl/mem: Implement Clear " ira.weiny
2022-12-01 13:26 ` Jonathan Cameron
2022-12-01 15:30 ` Ira Weiny
2022-12-02 2:29 ` Dan Williams
2022-12-02 13:18 ` Jonathan Cameron
2022-12-02 13:34 ` Steven Rostedt
2022-12-02 19:27 ` Dan Williams
2022-12-02 21:28 ` Ira Weiny
2022-12-02 23:49 ` Ira Weiny
2022-12-03 1:14 ` Dan Williams
2022-12-06 7:35 ` Ira Weiny
2022-12-01 0:27 ` [PATCH V2 04/11] cxl/mem: Clear events on driver load ira.weiny
2022-12-01 13:30 ` Jonathan Cameron
2022-12-01 17:02 ` Ira Weiny
2022-12-02 2:48 ` Dan Williams
2022-12-02 16:34 ` Ira Weiny
2022-12-02 23:34 ` Dan Williams
2022-12-03 21:00 ` Ira Weiny
2022-12-01 0:27 ` [PATCH V2 05/11] cxl/mem: Trace General Media Event Record ira.weiny
2022-12-01 18:54 ` Dave Jiang
2022-12-02 6:18 ` Dan Williams
2022-12-01 0:27 ` [PATCH V2 06/11] cxl/mem: Trace DRAM " ira.weiny
2022-12-01 18:55 ` Dave Jiang
2022-12-01 0:27 ` ira.weiny [this message]
2022-12-01 13:31 ` [PATCH V2 07/11] cxl/mem: Trace Memory Module " Jonathan Cameron
2022-12-01 18:57 ` Dave Jiang
2022-12-02 6:25 ` Dan Williams
2022-12-01 0:27 ` [PATCH V2 08/11] cxl/mem: Wire up event interrupts ira.weiny
2022-12-01 14:21 ` Jonathan Cameron
2022-12-01 17:23 ` Ira Weiny
2022-12-01 18:35 ` Davidlohr Bueso
2022-12-02 7:37 ` Dan Williams
2022-12-02 14:19 ` Jonathan Cameron
2022-12-02 19:43 ` Dan Williams
2022-12-05 13:01 ` Jonathan Cameron
2022-12-05 16:35 ` Dan Williams
2022-12-06 9:38 ` Jonathan Cameron
2022-12-01 0:27 ` [PATCH V2 09/11] cxl/test: Add generic mock events ira.weiny
2022-12-01 14:37 ` Jonathan Cameron
2022-12-01 17:49 ` Ira Weiny
2022-12-02 8:07 ` Dan Williams
2022-12-01 0:27 ` [PATCH V2 10/11] cxl/test: Add specific events ira.weiny
2022-12-01 21:00 ` Dave Jiang
2022-12-01 0:27 ` [PATCH V2 11/11] cxl/test: Simulate event log overflow ira.weiny
2022-12-01 21:28 ` Dave Jiang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20221201002719.2596558-8-ira.weiny@intel.com \
--to=ira.weiny@intel.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=alison.schofield@intel.com \
--cc=bwidawsk@kernel.org \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=dave@stgolabs.net \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=vishal.l.verma@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.