[ndctl PATCH v7 0/7] Support poison list retrieval

[ndctl PATCH v7 0/7] Support poison list retrieval

[alison.schofield]

From: Alison Schofield <alison.schofield@intel.com>

Changes since v6:
- Remove region and memdev names from json media-error record (Dan)
- Rename dpa_length to length in json media-error record (Dan)
- Add the endpoint decoder name to json media-error record (Dan)
- Document the 'Source' field in the cxl-list man page (Dan)
- Add media-errors to -vvv option
- cxl/test: Set nr_found to 0 directly, when poison list is empty
- cxl/test: Remove leftover -r in cxl list command
- Picked up a few Reviewed-by tags (DaveJ)
Link to v6: https://lore.kernel.org/linux-cxl/cover.1705534719.git.alison.schofield@intel.com/


Add the option to add a memory devices poison list to the cxl-list
json output. Offer the option by memdev and by region. Sample usage:

# cxl list -m mem1 --media-errors
[
  {
    "memdev":"mem1",
    "pmem_size":1073741824,
    "ram_size":1073741824,
    "serial":1,
    "numa_node":1,
    "host":"cxl_mem.1",
    "media_errors":[
      {
        "dpa":0,
        "length":64,
        "source":"Internal"
      },
      {
        "decoder":"decoder10.0",
        "hpa":1035355557888,
        "dpa":1073741824,
        "length":64,
        "source":"External"
      },
      {
        "decoder":"decoder10.0",
        "hpa":1035355566080,
        "dpa":1073745920,
        "length":64,
        "source":"Injected"
      }
    ]
  }
]

# cxl list -r region5 --media-errors
[
  {
    "region":"region5",
    "resource":1035355553792,
    "size":2147483648,
    "type":"pmem",
    "interleave_ways":2,
    "interleave_granularity":4096,
    "decode_state":"commit",
    "media_errors":[
      {
        "decoder":"decoder10.0",
        "hpa":1035355557888,
        "dpa":1073741824,
        "length":64,
        "source":"External"
      },
      {
        "decoder":"decoder8.1",
        "hpa":1035355566080,
        "dpa":1073745920,
        "length":64,
        "source":"Internal"
      }
    ]
  }
]

Alison Schofield (7):
  libcxl: add interfaces for GET_POISON_LIST mailbox commands
  cxl: add an optional pid check to event parsing
  cxl/event_trace: add a private context for private parsers
  cxl/event_trace: add helpers get_field_[string|data]()
  cxl/list: collect and parse media_error records
  cxl/list: add --media-errors option to cxl list
  cxl/test: add cxl-poison.sh unit test

 Documentation/cxl/cxl-list.txt |  79 +++++++++-
 cxl/event_trace.c              |  53 ++++++-
 cxl/event_trace.h              |   9 +-
 cxl/filter.h                   |   3 +
 cxl/json.c                     | 261 +++++++++++++++++++++++++++++++++
 cxl/lib/libcxl.c               |  47 ++++++
 cxl/lib/libcxl.sym             |   6 +
 cxl/libcxl.h                   |   2 +
 cxl/list.c                     |   3 +
 test/cxl-poison.sh             | 137 +++++++++++++++++
 test/meson.build               |   2 +
 11 files changed, 598 insertions(+), 4 deletions(-)
 create mode 100644 test/cxl-poison.sh


base-commit: a871e6153b11fe63780b37cdcb1eb347b296095c
-- 
2.37.3

[ndctl PATCH v7 1/7] libcxl: add interfaces for GET_POISON_LIST mailbox commands

[alison.schofield]

From: Alison Schofield <alison.schofield@intel.com>

CXL devices maintain a list of locations that are poisoned or result
in poison if the addresses are accessed by the host.

Per the spec (CXL 3.1 8.2.9.9.4.1), the device returns the Poison
List as a set of  Media Error Records that include the source of the
error, the starting device physical address and length.

Trigger the retrieval of the poison list by writing to the memory
device sysfs attribute: trigger_poison_list. The CXL driver only
offers triggering per memdev, so the trigger by region interface
offered here is a convenience API that triggers a poison list
retrieval for each memdev contributing to a region.

int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev);
int cxl_region_trigger_poison_list(struct cxl_region *region);

The resulting poison records are logged as kernel trace events
named 'cxl_poison'.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
---
 cxl/lib/libcxl.c   | 47 ++++++++++++++++++++++++++++++++++++++++++++++
 cxl/lib/libcxl.sym |  6 ++++++
 cxl/libcxl.h       |  2 ++
 3 files changed, 55 insertions(+)

diff --git a/cxl/lib/libcxl.c b/cxl/lib/libcxl.c
index af4ca44eae19..cc95c2d7c94a 100644
--- a/cxl/lib/libcxl.c
+++ b/cxl/lib/libcxl.c
@@ -1647,6 +1647,53 @@ CXL_EXPORT int cxl_memdev_disable_invalidate(struct cxl_memdev *memdev)
 	return 0;
 }
 
+CXL_EXPORT int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev)
+{
+	struct cxl_ctx *ctx = cxl_memdev_get_ctx(memdev);
+	char *path = memdev->dev_buf;
+	int len = memdev->buf_len, rc;
+
+	if (snprintf(path, len, "%s/trigger_poison_list",
+		     memdev->dev_path) >= len) {
+		err(ctx, "%s: buffer too small\n",
+		    cxl_memdev_get_devname(memdev));
+		return -ENXIO;
+	}
+	rc = sysfs_write_attr(ctx, path, "1\n");
+	if (rc < 0) {
+		fprintf(stderr,
+			"%s: Failed write sysfs attr trigger_poison_list\n",
+			cxl_memdev_get_devname(memdev));
+		return rc;
+	}
+	return 0;
+}
+
+CXL_EXPORT int cxl_region_trigger_poison_list(struct cxl_region *region)
+{
+	struct cxl_memdev_mapping *mapping;
+	int rc;
+
+	cxl_mapping_foreach(region, mapping) {
+		struct cxl_decoder *decoder;
+		struct cxl_memdev *memdev;
+
+		decoder = cxl_mapping_get_decoder(mapping);
+		if (!decoder)
+			continue;
+
+		memdev = cxl_decoder_get_memdev(decoder);
+		if (!memdev)
+			continue;
+
+		rc = cxl_memdev_trigger_poison_list(memdev);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 CXL_EXPORT int cxl_memdev_enable(struct cxl_memdev *memdev)
 {
 	struct cxl_ctx *ctx = cxl_memdev_get_ctx(memdev);
diff --git a/cxl/lib/libcxl.sym b/cxl/lib/libcxl.sym
index 8fa1cca3d0d7..277b7e21d6a6 100644
--- a/cxl/lib/libcxl.sym
+++ b/cxl/lib/libcxl.sym
@@ -264,3 +264,9 @@ global:
 	cxl_memdev_update_fw;
 	cxl_memdev_cancel_fw_update;
 } LIBCXL_5;
+
+LIBCXL_7 {
+global:
+	cxl_memdev_trigger_poison_list;
+	cxl_region_trigger_poison_list;
+} LIBCXL_6;
diff --git a/cxl/libcxl.h b/cxl/libcxl.h
index 0f4f4b2648fb..ecdffe36df2c 100644
--- a/cxl/libcxl.h
+++ b/cxl/libcxl.h
@@ -460,6 +460,8 @@ enum cxl_setpartition_mode {
 
 int cxl_cmd_partition_set_mode(struct cxl_cmd *cmd,
 		enum cxl_setpartition_mode mode);
+int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev);
+int cxl_region_trigger_poison_list(struct cxl_region *region);
 
 #ifdef __cplusplus
 } /* extern "C" */
-- 
2.37.3

[ndctl PATCH v7 2/7] cxl: add an optional pid check to event parsing

[alison.schofield]

From: Alison Schofield <alison.schofield@intel.com>

When parsing CXL events, callers may only be interested in events
that originate from the current process. Introduce an optional
argument to the event trace context: event_pid. When event_pid is
present, simply skip the parsing of events without a matching pid.
It is not a failure to see other, non matching events.

The initial use case for this is device poison listings where
only the media-error records requested by this process are wanted.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
---
 cxl/event_trace.c | 5 +++++
 cxl/event_trace.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/cxl/event_trace.c b/cxl/event_trace.c
index db8cc85f0b6f..269060898118 100644
--- a/cxl/event_trace.c
+++ b/cxl/event_trace.c
@@ -208,6 +208,11 @@ static int cxl_event_parse(struct tep_event *event, struct tep_record *record,
 			return 0;
 	}
 
+	if (event_ctx->event_pid) {
+		if (event_ctx->event_pid != tep_data_pid(event->tep, record))
+			return 0;
+	}
+
 	if (event_ctx->parse_event)
 		return event_ctx->parse_event(event, record,
 					      &event_ctx->jlist_head);
diff --git a/cxl/event_trace.h b/cxl/event_trace.h
index ec6267202c8b..7f7773b2201f 100644
--- a/cxl/event_trace.h
+++ b/cxl/event_trace.h
@@ -15,6 +15,7 @@ struct event_ctx {
 	const char *system;
 	struct list_head jlist_head;
 	const char *event_name; /* optional */
+	int event_pid; /* optional */
 	int (*parse_event)(struct tep_event *event, struct tep_record *record,
 			   struct list_head *jlist_head); /* optional */
 };
-- 
2.37.3

[ndctl PATCH v7 3/7] cxl/event_trace: add a private context for private parsers

[alison.schofield]

From: Alison Schofield <alison.schofield@intel.com>

CXL event tracing provides helpers to iterate through a trace
buffer and extract events of interest. It offers two parsing
options: a default parser that adds every field of an event to
a json object, and a private parsing option where the caller can
parse each event as it wishes.

Although the private parser can do some conditional parsing based
on field values, it has no method to receive additional information
needed to make parsing decisions in the callback.

Add a private_ctx field to the existing 'struct event_context'.
Replace the jlist_head parameter, used in the default parser,
with the private_ctx.

This is in preparation for adding a private parser requiring
additional context for cxl_poison events.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
---
 cxl/event_trace.c | 2 +-
 cxl/event_trace.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/cxl/event_trace.c b/cxl/event_trace.c
index 269060898118..fbf7a77235ff 100644
--- a/cxl/event_trace.c
+++ b/cxl/event_trace.c
@@ -215,7 +215,7 @@ static int cxl_event_parse(struct tep_event *event, struct tep_record *record,
 
 	if (event_ctx->parse_event)
 		return event_ctx->parse_event(event, record,
-					      &event_ctx->jlist_head);
+					      event_ctx->private_ctx);
 
 	return cxl_event_to_json(event, record, &event_ctx->jlist_head);
 }
diff --git a/cxl/event_trace.h b/cxl/event_trace.h
index 7f7773b2201f..ec61962abbc6 100644
--- a/cxl/event_trace.h
+++ b/cxl/event_trace.h
@@ -16,8 +16,9 @@ struct event_ctx {
 	struct list_head jlist_head;
 	const char *event_name; /* optional */
 	int event_pid; /* optional */
+	void *private_ctx; /* required with parse_event() */
 	int (*parse_event)(struct tep_event *event, struct tep_record *record,
-			   struct list_head *jlist_head); /* optional */
+			   void *private_ctx);/* optional */
 };
 
 int cxl_parse_events(struct tracefs_instance *inst, struct event_ctx *ectx);
-- 
2.37.3

[ndctl PATCH v7 4/7] cxl/event_trace: add helpers get_field_[string|data]()

[alison.schofield]

From: Alison Schofield <alison.schofield@intel.com>

Add helpers to extract the value of an event record field given the
field name. This is useful when the user knows the name and format
of the field and simply needs to get it. Add signed and unsigned
char* versions to support string and u64 data fields.

This is in preparation for adding a private parser of cxl_poison
events.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
---
 cxl/event_trace.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 cxl/event_trace.h |  5 ++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/cxl/event_trace.c b/cxl/event_trace.c
index fbf7a77235ff..8d04d8d34194 100644
--- a/cxl/event_trace.c
+++ b/cxl/event_trace.c
@@ -15,6 +15,52 @@
 #define _GNU_SOURCE
 #include <string.h>
 
+static struct tep_format_field *__find_field(struct tep_event *event,
+					     const char *name)
+{
+	struct tep_format_field **fields;
+
+	fields = tep_event_fields(event);
+	if (!fields)
+		return NULL;
+
+	for (int i = 0; fields[i]; i++) {
+		struct tep_format_field *f = fields[i];
+
+		if (strcmp(f->name, name) != 0)
+			continue;
+
+		return f;
+	}
+	return NULL;
+}
+
+unsigned char *cxl_get_field_data(struct tep_event *event,
+				  struct tep_record *record, const char *name)
+{
+	struct tep_format_field *f;
+	int len;
+
+	f = __find_field(event, name);
+	if (!f)
+		return NULL;
+
+	return tep_get_field_raw(NULL, event, f->name, record, &len, 0);
+}
+
+char *cxl_get_field_string(struct tep_event *event, struct tep_record *record,
+			   const char *name)
+{
+	struct tep_format_field *f;
+	int len;
+
+	f = __find_field(event, name);
+	if (!f)
+		return NULL;
+
+	return tep_get_field_raw(NULL, event, f->name, record, &len, 0);
+}
+
 static struct json_object *num_to_json(void *num, int elem_size, unsigned long flags)
 {
 	bool sign = flags & TEP_FIELD_IS_SIGNED;
diff --git a/cxl/event_trace.h b/cxl/event_trace.h
index ec61962abbc6..6252f583097a 100644
--- a/cxl/event_trace.h
+++ b/cxl/event_trace.h
@@ -25,5 +25,8 @@ int cxl_parse_events(struct tracefs_instance *inst, struct event_ctx *ectx);
 int cxl_event_tracing_enable(struct tracefs_instance *inst, const char *system,
 		const char *event);
 int cxl_event_tracing_disable(struct tracefs_instance *inst);
-
+char *cxl_get_field_string(struct tep_event *event, struct tep_record *record,
+		const char *name);
+unsigned char *cxl_get_field_data(struct tep_event *event,
+		struct tep_record *record, const char *name);
 #endif
-- 
2.37.3

[ndctl PATCH v7 5/7] cxl/list: collect and parse media_error records

[alison.schofield]

From: Alison Schofield <alison.schofield@intel.com>

Media_error records are logged as events in the kernel tracing
subsystem. To prepare the media_error records for cxl list, enable
tracing, trigger the poison list read, and parse the generated
cxl_poison events into a json representation.

Use the event_trace private parsing option to customize the json
representation based on cxl-list calling options and event field
settings.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
---
 cxl/json.c | 261 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 261 insertions(+)

diff --git a/cxl/json.c b/cxl/json.c
index 7678d02020b6..bc104dd877a9 100644
--- a/cxl/json.c
+++ b/cxl/json.c
@@ -1,16 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (C) 2015-2021 Intel Corporation. All rights reserved.
 #include <limits.h>
+#include <errno.h>
 #include <util/json.h>
+#include <util/bitmap.h>
 #include <uuid/uuid.h>
 #include <cxl/libcxl.h>
 #include <json-c/json.h>
 #include <json-c/printbuf.h>
 #include <ccan/short_types/short_types.h>
+#include <tracefs/tracefs.h>
 
 #include "filter.h"
 #include "json.h"
 #include "../daxctl/json.h"
+#include "event_trace.h"
 
 #define CXL_FW_VERSION_STR_LEN	16
 #define CXL_FW_MAX_SLOTS	4
@@ -571,6 +575,251 @@ err_jobj:
 	return NULL;
 }
 
+/* CXL Spec 3.1 Table 8-140 Media Error Record */
+#define CXL_POISON_SOURCE_UNKNOWN 0
+#define CXL_POISON_SOURCE_EXTERNAL 1
+#define CXL_POISON_SOURCE_INTERNAL 2
+#define CXL_POISON_SOURCE_INJECTED 3
+#define CXL_POISON_SOURCE_VENDOR 7
+
+/* CXL Spec 3.1 Table 8-139 Get Poison List Output Payload */
+#define CXL_POISON_FLAG_MORE BIT(0)
+#define CXL_POISON_FLAG_OVERFLOW BIT(1)
+#define CXL_POISON_FLAG_SCANNING BIT(2)
+
+struct poison_ctx {
+	struct json_object *jpoison;
+	struct cxl_region *region;
+	struct cxl_memdev *memdev;
+	unsigned long flags;
+};
+
+static const char *
+find_decoder_name(struct poison_ctx *ctx, const char *name, u64 addr)
+{
+	struct cxl_memdev *memdev = ctx->memdev;
+	struct cxl_memdev_mapping *mapping;
+	struct cxl_endpoint *endpoint;
+	struct cxl_decoder *decoder;
+	struct cxl_port *port;
+	u64 start, end;
+
+	if (memdev)
+		goto find_decoder;
+
+	cxl_mapping_foreach(ctx->region, mapping) {
+		decoder = cxl_mapping_get_decoder(mapping);
+		if (!decoder)
+			continue;
+
+		memdev = cxl_decoder_get_memdev(decoder);
+		if (strcmp(name, cxl_memdev_get_devname(memdev)) == 0)
+			break;
+
+		memdev = NULL;
+	}
+
+find_decoder:
+	if (!memdev)
+		return NULL;
+
+	endpoint = cxl_memdev_get_endpoint(memdev);
+	port = cxl_endpoint_get_port(endpoint);
+
+	cxl_decoder_foreach(port, decoder) {
+		start =  cxl_decoder_get_resource(decoder);
+		end = start + cxl_decoder_get_size(decoder) - 1;
+		if (start <= addr && addr <= end)
+			return cxl_decoder_get_devname(decoder);
+	}
+
+	return NULL;
+}
+
+int poison_event_to_json(struct tep_event *event, struct tep_record *record,
+			 void *ctx)
+{
+	struct poison_ctx *p_ctx = (struct poison_ctx *)ctx;
+	struct json_object *jobj, *jp, *jpoison = p_ctx->jpoison;
+	unsigned long flags = p_ctx->flags;
+	bool overflow = false;
+	unsigned char *data;
+	const char *name;
+	int pflags;
+	char *str;
+
+	jp = json_object_new_object();
+	if (!jp)
+		return -ENOMEM;
+
+	/* Skip records not in this region when listing by region */
+	name = p_ctx->region ? cxl_region_get_devname(p_ctx->region) : NULL;
+	if (name)
+		str = cxl_get_field_string(event, record, "region");
+
+	if ((name) && (strcmp(name, str) != 0)) {
+		json_object_put(jp);
+		return 0;
+	}
+
+	/* Include endpoint decoder name with hpa, when present */
+	name = cxl_get_field_string(event, record, "memdev");
+	data = cxl_get_field_data(event, record, "hpa");
+	if (*(uint64_t *)data != ULLONG_MAX)
+		name = find_decoder_name(p_ctx, name, *(uint64_t *)data);
+	else
+		name = NULL;
+
+	if (name) {
+		jobj = json_object_new_string(name);
+		if (jobj)
+			json_object_object_add(jp, "decoder", jobj);
+
+		jobj = util_json_object_hex(*(uint64_t *)data, flags);
+		if (jobj)
+			json_object_object_add(jp, "hpa", jobj);
+	}
+
+	data = cxl_get_field_data(event, record, "dpa");
+	jobj = util_json_object_hex(*(uint64_t *)data, flags);
+	if (jobj)
+		json_object_object_add(jp, "dpa", jobj);
+
+	data = cxl_get_field_data(event, record, "dpa_length");
+	jobj = util_json_object_size(*(uint32_t *)data, flags);
+	if (jobj)
+		json_object_object_add(jp, "length", jobj);
+
+	str = cxl_get_field_string(event, record, "source");
+	switch (*(uint8_t *)str) {
+	case CXL_POISON_SOURCE_UNKNOWN:
+		jobj = json_object_new_string("Unknown");
+		break;
+	case CXL_POISON_SOURCE_EXTERNAL:
+		jobj = json_object_new_string("External");
+		break;
+	case CXL_POISON_SOURCE_INTERNAL:
+		jobj = json_object_new_string("Internal");
+		break;
+	case CXL_POISON_SOURCE_INJECTED:
+		jobj = json_object_new_string("Injected");
+		break;
+	case CXL_POISON_SOURCE_VENDOR:
+		jobj = json_object_new_string("Vendor");
+		break;
+	default:
+		jobj = json_object_new_string("Reserved");
+	}
+	if (jobj)
+		json_object_object_add(jp, "source", jobj);
+
+	str = cxl_get_field_string(event, record, "flags");
+	pflags = *(uint8_t *)str;
+	if (pflags) {
+		char flag_str[32] = { '\0' };
+
+		if (pflags & CXL_POISON_FLAG_MORE)
+			strcat(flag_str, "More,");
+		if (pflags & CXL_POISON_FLAG_SCANNING)
+			strcat(flag_str, "Scanning,");
+		if (pflags & CXL_POISON_FLAG_OVERFLOW) {
+			strcat(flag_str, "Overflow,");
+			overflow = true;
+		}
+		jobj = json_object_new_string(flag_str);
+		if (jobj)
+			json_object_object_add(jp, "flags", jobj);
+	}
+	if (overflow) {
+		data = cxl_get_field_data(event, record, "overflow_ts");
+		jobj = util_json_object_hex(*(uint64_t *)data, flags);
+		if (jobj)
+			json_object_object_add(jp, "overflow_t", jobj);
+	}
+	json_object_array_add(jpoison, jp);
+
+	return 0;
+}
+
+static struct json_object *
+util_cxl_poison_events_to_json(struct tracefs_instance *inst,
+			       struct poison_ctx *p_ctx)
+{
+	struct event_ctx ectx = {
+		.event_name = "cxl_poison",
+		.event_pid = getpid(),
+		.system = "cxl",
+		.private_ctx = p_ctx,
+		.parse_event = poison_event_to_json,
+	};
+	int rc = 0;
+
+	p_ctx->jpoison = json_object_new_array();
+	if (!p_ctx->jpoison)
+		return NULL;
+
+	rc = cxl_parse_events(inst, &ectx);
+	if (rc < 0) {
+		fprintf(stderr, "Failed to parse events: %d\n", rc);
+		json_object_put(p_ctx->jpoison);
+		return NULL;
+	}
+
+	if (json_object_array_length(p_ctx->jpoison) == 0) {
+		json_object_put(p_ctx->jpoison);
+		return NULL;
+	}
+
+	return p_ctx->jpoison;
+}
+
+static struct json_object *
+util_cxl_poison_list_to_json(struct cxl_region *region,
+			     struct cxl_memdev *memdev,
+			     unsigned long flags)
+{
+	struct json_object *jpoison = NULL;
+	struct poison_ctx p_ctx;
+	struct tracefs_instance *inst;
+	int rc;
+
+	inst = tracefs_instance_create("cxl list");
+	if (!inst) {
+		fprintf(stderr, "tracefs_instance_create() failed\n");
+		return NULL;
+	}
+
+	rc = cxl_event_tracing_enable(inst, "cxl", "cxl_poison");
+	if (rc < 0) {
+		fprintf(stderr, "Failed to enable trace: %d\n", rc);
+		goto err_free;
+	}
+
+	if (region)
+		rc = cxl_region_trigger_poison_list(region);
+	else
+		rc = cxl_memdev_trigger_poison_list(memdev);
+	if (rc)
+		goto err_free;
+
+	rc = cxl_event_tracing_disable(inst);
+	if (rc < 0) {
+		fprintf(stderr, "Failed to disable trace: %d\n", rc);
+		goto err_free;
+	}
+
+	p_ctx = (struct poison_ctx) {
+		.region = region,
+		.memdev = memdev,
+		.flags = flags,
+	};
+	jpoison = util_cxl_poison_events_to_json(inst, &p_ctx);
+
+err_free:
+	tracefs_instance_free(inst);
+	return jpoison;
+}
+
 struct json_object *util_cxl_memdev_to_json(struct cxl_memdev *memdev,
 		unsigned long flags)
 {
@@ -649,6 +898,12 @@ struct json_object *util_cxl_memdev_to_json(struct cxl_memdev *memdev,
 			json_object_object_add(jdev, "firmware", jobj);
 	}
 
+	if (flags & UTIL_JSON_MEDIA_ERRORS) {
+		jobj = util_cxl_poison_list_to_json(NULL, memdev, flags);
+		if (jobj)
+			json_object_object_add(jdev, "media_errors", jobj);
+	}
+
 	json_object_set_userdata(jdev, memdev, NULL);
 	return jdev;
 }
@@ -987,6 +1242,12 @@ struct json_object *util_cxl_region_to_json(struct cxl_region *region,
 			json_object_object_add(jregion, "state", jobj);
 	}
 
+	if (flags & UTIL_JSON_MEDIA_ERRORS) {
+		jobj = util_cxl_poison_list_to_json(region, NULL, flags);
+		if (jobj)
+			json_object_object_add(jregion, "media_errors", jobj);
+	}
+
 	util_cxl_mappings_append_json(jregion, region, flags);
 
 	if (flags & UTIL_JSON_DAX) {
-- 
2.37.3

[ndctl PATCH v7 6/7] cxl/list: add --media-errors option to cxl list

[alison.schofield]

From: Alison Schofield <alison.schofield@intel.com>

The --media-errors option to 'cxl list' retrieves poison lists from
memory devices supporting the capability and displays the returned
media_error records in the cxl list json. This option can apply to
memdevs or regions.

Include media-errors in the -vvv verbose option.

Example usage in the Documentation/cxl/cxl-list.txt update.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
---
 Documentation/cxl/cxl-list.txt | 79 +++++++++++++++++++++++++++++++++-
 cxl/filter.h                   |  3 ++
 cxl/list.c                     |  3 ++
 3 files changed, 84 insertions(+), 1 deletion(-)

diff --git a/Documentation/cxl/cxl-list.txt b/Documentation/cxl/cxl-list.txt
index 838de4086678..5c20614ef579 100644
--- a/Documentation/cxl/cxl-list.txt
+++ b/Documentation/cxl/cxl-list.txt
@@ -415,6 +415,83 @@ OPTIONS
 --region::
 	Specify CXL region device name(s), or device id(s), to filter the listing.
 
+-L::
+--media-errors::
+	Include media-error information. The poison list is retrieved from the
+	device(s) and media_error records are added to the listing. Apply this
+	option to memdevs and regions where devices support the poison list
+	capability.
+
+	"decoder" and "hpa" are included when the media-error is in a mapped
+        address.
+
+	"source" will be one of: External, Internal, Injected, Vendor Specific,
+        or Unknown, as defined in CXL Specification v3.1 Table 8-140.
+
+----
+# cxl list -m mem1 --media-errors
+[
+  {
+    "memdev":"mem1",
+    "pmem_size":1073741824,
+    "ram_size":1073741824,
+    "serial":1,
+    "numa_node":1,
+    "host":"cxl_mem.1",
+    "media_errors":[
+      {
+        "dpa":0,
+        "length":64,
+        "source":"Internal"
+      },
+      {
+        "decoder":"decoder10.0",
+        "hpa":1035355557888,
+        "dpa":1073741824,
+        "length":64,
+        "source":"External"
+      },
+      {
+        "decoder":"decoder10.0",
+        "hpa":1035355566080,
+        "dpa":1073745920,
+        "length":64,
+        "source":"Injected"
+      }
+    ]
+  }
+]
+
+# cxl list -r region5 --media-errors
+[
+  {
+    "region":"region5",
+    "resource":1035355553792,
+    "size":2147483648,
+    "type":"pmem",
+    "interleave_ways":2,
+    "interleave_granularity":4096,
+    "decode_state":"commit",
+    "media_errors":[
+      {
+        "decoder":"decoder10.0",
+        "hpa":1035355557888,
+        "dpa":1073741824,
+        "length":64,
+        "source":"External"
+      },
+      {
+        "decoder":"decoder8.1",
+        "hpa":1035355553792,
+        "dpa":1073741824,
+        "length":64,
+        "source":"Internal"
+      }
+    ]
+  }
+]
+----
+
 -v::
 --verbose::
 	Increase verbosity of the output. This can be specified
@@ -431,7 +508,7 @@ OPTIONS
 	  devices with --idle.
 	- *-vvv*
 	  Everything *-vv* provides, plus enable
-	  --health and --partition.
+	  --health, --partition, --media-errors.
 
 --debug::
 	If the cxl tool was built with debug enabled, turn on debug
diff --git a/cxl/filter.h b/cxl/filter.h
index 3f65990f835a..956a46e0c7a9 100644
--- a/cxl/filter.h
+++ b/cxl/filter.h
@@ -30,6 +30,7 @@ struct cxl_filter_params {
 	bool fw;
 	bool alert_config;
 	bool dax;
+	bool media_errors;
 	int verbose;
 	struct log_ctx ctx;
 };
@@ -88,6 +89,8 @@ static inline unsigned long cxl_filter_to_flags(struct cxl_filter_params *param)
 		flags |= UTIL_JSON_ALERT_CONFIG;
 	if (param->dax)
 		flags |= UTIL_JSON_DAX | UTIL_JSON_DAX_DEVS;
+	if (param->media_errors)
+		flags |= UTIL_JSON_MEDIA_ERRORS;
 	return flags;
 }
 
diff --git a/cxl/list.c b/cxl/list.c
index 93ba51ef895c..0b25d78248d5 100644
--- a/cxl/list.c
+++ b/cxl/list.c
@@ -57,6 +57,8 @@ static const struct option options[] = {
 		    "include memory device firmware information"),
 	OPT_BOOLEAN('A', "alert-config", &param.alert_config,
 		    "include alert configuration information"),
+	OPT_BOOLEAN('L', "media-errors", &param.media_errors,
+		    "include media-error information "),
 	OPT_INCR('v', "verbose", &param.verbose, "increase output detail"),
 #ifdef ENABLE_DEBUG
 	OPT_BOOLEAN(0, "debug", &debug, "debug list walk"),
@@ -121,6 +123,7 @@ int cmd_list(int argc, const char **argv, struct cxl_ctx *ctx)
 		param.fw = true;
 		param.alert_config = true;
 		param.dax = true;
+		param.media_errors = true;
 		/* fallthrough */
 	case 2:
 		param.idle = true;
-- 
2.37.3

[ndctl PATCH v7 7/7] cxl/test: add cxl-poison.sh unit test

[alison.schofield]

From: Alison Schofield <alison.schofield@intel.com>

Exercise cxl list, libcxl, and driver pieces of the get poison list
pathway. Inject and clear poison using debugfs and use cxl-cli to
read the poison list by memdev and by region.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
---
 test/cxl-poison.sh | 137 +++++++++++++++++++++++++++++++++++++++++++++
 test/meson.build   |   2 +
 2 files changed, 139 insertions(+)
 create mode 100644 test/cxl-poison.sh

diff --git a/test/cxl-poison.sh b/test/cxl-poison.sh
new file mode 100644
index 000000000000..6fceb0f2c360
--- /dev/null
+++ b/test/cxl-poison.sh
@@ -0,0 +1,137 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2023 Intel Corporation. All rights reserved.
+
+. "$(dirname "$0")"/common
+
+rc=77
+
+set -ex
+
+trap 'err $LINENO' ERR
+
+check_prereq "jq"
+
+modprobe -r cxl_test
+modprobe cxl_test
+
+rc=1
+
+# THEORY OF OPERATION: Exercise cxl-cli and cxl driver ability to
+# inject, clear, and get the poison list. Do it by memdev and by region.
+
+find_memdev()
+{
+	readarray -t capable_mems < <("$CXL" list -b "$CXL_TEST_BUS" -M |
+		jq -r ".[] | select(.pmem_size != null) |
+		select(.ram_size != null) | .memdev")
+
+	if [ ${#capable_mems[@]} == 0 ]; then
+		echo "no memdevs found for test"
+		err "$LINENO"
+	fi
+
+	memdev=${capable_mems[0]}
+}
+
+create_x2_region()
+{
+        # Find an x2 decoder
+        decoder="$($CXL list -b "$CXL_TEST_BUS" -D -d root | jq -r ".[] |
+		select(.pmem_capable == true) |
+		select(.nr_targets == 2) |
+		.decoder")"
+
+        # Find a memdev for each host-bridge interleave position
+        port_dev0="$($CXL list -T -d "$decoder" | jq -r ".[] |
+		.targets | .[] | select(.position == 0) | .target")"
+        port_dev1="$($CXL list -T -d "$decoder" | jq -r ".[] |
+		.targets | .[] | select(.position == 1) | .target")"
+        mem0="$($CXL list -M -p "$port_dev0" | jq -r ".[0].memdev")"
+        mem1="$($CXL list -M -p "$port_dev1" | jq -r ".[0].memdev")"
+
+	region="$($CXL create-region -d "$decoder" -m "$mem0" "$mem1" |
+		 jq -r ".region")"
+	if [[ ! $region ]]; then
+		echo "create-region failed for $decoder"
+		err "$LINENO"
+	fi
+	echo "$region"
+}
+
+# When cxl-cli support for inject and clear arrives, replace
+# the writes to /sys/kernel/debug with the new cxl commands.
+
+inject_poison_sysfs()
+{
+	memdev="$1"
+	addr="$2"
+
+	echo "$addr" > /sys/kernel/debug/cxl/"$memdev"/inject_poison
+}
+
+clear_poison_sysfs()
+{
+	memdev="$1"
+	addr="$2"
+
+	echo "$addr" > /sys/kernel/debug/cxl/"$memdev"/clear_poison
+}
+
+validate_poison_found()
+{
+	list_by="$1"
+	nr_expect="$2"
+
+	poison_list="$($CXL list "$list_by" --media-errors |
+		jq -r '.[].media_errors')"
+	if [[ ! $poison_list ]]; then
+		nr_found=0
+	else
+		nr_found=$(jq "length" <<< "$poison_list")
+	fi
+	if [ "$nr_found" -ne "$nr_expect" ]; then
+		echo "$nr_expect poison records expected, $nr_found found"
+		err "$LINENO"
+	fi
+}
+
+test_poison_by_memdev()
+{
+	find_memdev
+	inject_poison_sysfs "$memdev" "0x40000000"
+	inject_poison_sysfs "$memdev" "0x40001000"
+	inject_poison_sysfs "$memdev" "0x600"
+	inject_poison_sysfs "$memdev" "0x0"
+	validate_poison_found "-m $memdev" 4
+
+	clear_poison_sysfs "$memdev" "0x40000000"
+	clear_poison_sysfs "$memdev" "0x40001000"
+	clear_poison_sysfs "$memdev" "0x600"
+	clear_poison_sysfs "$memdev" "0x0"
+	validate_poison_found "-m $memdev" 0
+}
+
+test_poison_by_region()
+{
+	create_x2_region
+	inject_poison_sysfs "$mem0" "0x40000000"
+	inject_poison_sysfs "$mem1" "0x40000000"
+	validate_poison_found "-r $region" 2
+
+	clear_poison_sysfs "$mem0" "0x40000000"
+	clear_poison_sysfs "$mem1" "0x40000000"
+	validate_poison_found "-r $region" 0
+}
+
+# Turn tracing on. Note that 'cxl list --poison' does toggle the tracing.
+# Turning it on here allows the test user to also view inject and clear
+# trace events.
+echo 1 > /sys/kernel/tracing/events/cxl/cxl_poison/enable
+
+test_poison_by_memdev
+test_poison_by_region
+
+check_dmesg "$LINENO"
+
+modprobe -r cxl-test
diff --git a/test/meson.build b/test/meson.build
index 224adaf41fcc..2706fa5d633c 100644
--- a/test/meson.build
+++ b/test/meson.build
@@ -157,6 +157,7 @@ cxl_create_region = find_program('cxl-create-region.sh')
 cxl_xor_region = find_program('cxl-xor-region.sh')
 cxl_update_firmware = find_program('cxl-update-firmware.sh')
 cxl_events = find_program('cxl-events.sh')
+cxl_poison = find_program('cxl-poison.sh')
 
 tests = [
   [ 'libndctl',               libndctl,		  'ndctl' ],
@@ -186,6 +187,7 @@ tests = [
   [ 'cxl-create-region.sh',   cxl_create_region,  'cxl'   ],
   [ 'cxl-xor-region.sh',      cxl_xor_region,     'cxl'   ],
   [ 'cxl-events.sh',          cxl_events,         'cxl'   ],
+  [ 'cxl-poison.sh',          cxl_poison,         'cxl'   ],
 ]
 
 if get_option('destructive').enabled()
-- 
2.37.3

Re: [ndctl PATCH v7 5/7] cxl/list: collect and parse media_error records

[Dave Jiang]

On 2/7/24 6:01 PM, alison.schofield@intel.com wrote:
> From: Alison Schofield <alison.schofield@intel.com>
> 
> Media_error records are logged as events in the kernel tracing
> subsystem. To prepare the media_error records for cxl list, enable
> tracing, trigger the poison list read, and parse the generated
> cxl_poison events into a json representation.
> 
> Use the event_trace private parsing option to customize the json
> representation based on cxl-list calling options and event field
> settings.
> 
> Signed-off-by: Alison Schofield <alison.schofield@intel.com>
> ---
>  cxl/json.c | 261 +++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 261 insertions(+)
> 
> diff --git a/cxl/json.c b/cxl/json.c
> index 7678d02020b6..bc104dd877a9 100644
> --- a/cxl/json.c
> +++ b/cxl/json.c
> @@ -1,16 +1,20 @@
>  // SPDX-License-Identifier: GPL-2.0
>  // Copyright (C) 2015-2021 Intel Corporation. All rights reserved.
>  #include <limits.h>
> +#include <errno.h>
>  #include <util/json.h>
> +#include <util/bitmap.h>
>  #include <uuid/uuid.h>
>  #include <cxl/libcxl.h>
>  #include <json-c/json.h>
>  #include <json-c/printbuf.h>
>  #include <ccan/short_types/short_types.h>
> +#include <tracefs/tracefs.h>
>  
>  #include "filter.h"
>  #include "json.h"
>  #include "../daxctl/json.h"
> +#include "event_trace.h"
>  
>  #define CXL_FW_VERSION_STR_LEN	16
>  #define CXL_FW_MAX_SLOTS	4
> @@ -571,6 +575,251 @@ err_jobj:
>  	return NULL;
>  }
>  
> +/* CXL Spec 3.1 Table 8-140 Media Error Record */
> +#define CXL_POISON_SOURCE_UNKNOWN 0
> +#define CXL_POISON_SOURCE_EXTERNAL 1
> +#define CXL_POISON_SOURCE_INTERNAL 2
> +#define CXL_POISON_SOURCE_INJECTED 3
> +#define CXL_POISON_SOURCE_VENDOR 7
> +
> +/* CXL Spec 3.1 Table 8-139 Get Poison List Output Payload */
> +#define CXL_POISON_FLAG_MORE BIT(0)
> +#define CXL_POISON_FLAG_OVERFLOW BIT(1)
> +#define CXL_POISON_FLAG_SCANNING BIT(2)
> +
> +struct poison_ctx {
> +	struct json_object *jpoison;
> +	struct cxl_region *region;
> +	struct cxl_memdev *memdev;
> +	unsigned long flags;
> +};
> +
> +static const char *
> +find_decoder_name(struct poison_ctx *ctx, const char *name, u64 addr)
> +{
> +	struct cxl_memdev *memdev = ctx->memdev;
> +	struct cxl_memdev_mapping *mapping;
> +	struct cxl_endpoint *endpoint;
> +	struct cxl_decoder *decoder;
> +	struct cxl_port *port;
> +	u64 start, end;
> +
> +	if (memdev)
> +		goto find_decoder;
> +
> +	cxl_mapping_foreach(ctx->region, mapping) {
> +		decoder = cxl_mapping_get_decoder(mapping);
> +		if (!decoder)
> +			continue;
> +
> +		memdev = cxl_decoder_get_memdev(decoder);
> +		if (strcmp(name, cxl_memdev_get_devname(memdev)) == 0)
> +			break;
> +
> +		memdev = NULL;
> +	}
> +
> +find_decoder:

Would it be cleaner to move this block into a helper function? Don't really care for goto blocks that are not error handling paths.

> +	if (!memdev)
> +		return NULL;
> +
> +	endpoint = cxl_memdev_get_endpoint(memdev);
> +	port = cxl_endpoint_get_port(endpoint);
> +
> +	cxl_decoder_foreach(port, decoder) {
> +		start =  cxl_decoder_get_resource(decoder);
> +		end = start + cxl_decoder_get_size(decoder) - 1;
> +		if (start <= addr && addr <= end)
> +			return cxl_decoder_get_devname(decoder);
> +	}
> +
> +	return NULL;
> +}
> +
> +int poison_event_to_json(struct tep_event *event, struct tep_record *record,
> +			 void *ctx)
> +{
> +	struct poison_ctx *p_ctx = (struct poison_ctx *)ctx;
> +	struct json_object *jobj, *jp, *jpoison = p_ctx->jpoison;
> +	unsigned long flags = p_ctx->flags;
> +	bool overflow = false;
> +	unsigned char *data;
> +	const char *name;
> +	int pflags;
> +	char *str;
> +
> +	jp = json_object_new_object();
> +	if (!jp)
> +		return -ENOMEM;
> +
> +	/* Skip records not in this region when listing by region */
> +	name = p_ctx->region ? cxl_region_get_devname(p_ctx->region) : NULL;
> +	if (name)
> +		str = cxl_get_field_string(event, record, "region");
> +
> +	if ((name) && (strcmp(name, str) != 0)) {
> +		json_object_put(jp);
> +		return 0;
> +	}
> +
> +	/* Include endpoint decoder name with hpa, when present */
> +	name = cxl_get_field_string(event, record, "memdev");
> +	data = cxl_get_field_data(event, record, "hpa");
> +	if (*(uint64_t *)data != ULLONG_MAX)
> +		name = find_decoder_name(p_ctx, name, *(uint64_t *)data);
> +	else
> +		name = NULL;
> +
> +	if (name) {
> +		jobj = json_object_new_string(name);
> +		if (jobj)
> +			json_object_object_add(jp, "decoder", jobj);
> +
> +		jobj = util_json_object_hex(*(uint64_t *)data, flags);
> +		if (jobj)
> +			json_object_object_add(jp, "hpa", jobj);
> +	}
> +
> +	data = cxl_get_field_data(event, record, "dpa");
> +	jobj = util_json_object_hex(*(uint64_t *)data, flags);
> +	if (jobj)
> +		json_object_object_add(jp, "dpa", jobj);
> +
> +	data = cxl_get_field_data(event, record, "dpa_length");
> +	jobj = util_json_object_size(*(uint32_t *)data, flags);
> +	if (jobj)
> +		json_object_object_add(jp, "length", jobj);
> +
> +	str = cxl_get_field_string(event, record, "source");
> +	switch (*(uint8_t *)str) {

This causes reading confusion when it looks like the code is retrieving a string and then compare as an integer. Should this be done through cxl_get_field_data()?

> +	case CXL_POISON_SOURCE_UNKNOWN:
> +		jobj = json_object_new_string("Unknown");
> +		break;
> +	case CXL_POISON_SOURCE_EXTERNAL:
> +		jobj = json_object_new_string("External");
> +		break;
> +	case CXL_POISON_SOURCE_INTERNAL:
> +		jobj = json_object_new_string("Internal");
> +		break;
> +	case CXL_POISON_SOURCE_INJECTED:
> +		jobj = json_object_new_string("Injected");
> +		break;
> +	case CXL_POISON_SOURCE_VENDOR:
> +		jobj = json_object_new_string("Vendor");
> +		break;
> +	default:
> +		jobj = json_object_new_string("Reserved");
> +	}
> +	if (jobj)
> +		json_object_object_add(jp, "source", jobj);
> +
> +	str = cxl_get_field_string(event, record, "flags");
> +	pflags = *(uint8_t *)str;

Same as above comment here
> +	if (pflags) {
> +		char flag_str[32] = { '\0' };
> +
> +		if (pflags & CXL_POISON_FLAG_MORE)
> +			strcat(flag_str, "More,");
> +		if (pflags & CXL_POISON_FLAG_SCANNING)
> +			strcat(flag_str, "Scanning,");
> +		if (pflags & CXL_POISON_FLAG_OVERFLOW) {
> +			strcat(flag_str, "Overflow,");
> +			overflow = true;
> +		}
> +		jobj = json_object_new_string(flag_str);
> +		if (jobj)
> +			json_object_object_add(jp, "flags", jobj);
> +	}
> +	if (overflow) {
> +		data = cxl_get_field_data(event, record, "overflow_ts");
> +		jobj = util_json_object_hex(*(uint64_t *)data, flags);
> +		if (jobj)
> +			json_object_object_add(jp, "overflow_t", jobj);
> +	}
> +	json_object_array_add(jpoison, jp);
> +
> +	return 0;
> +}
> +
> +static struct json_object *
> +util_cxl_poison_events_to_json(struct tracefs_instance *inst,
> +			       struct poison_ctx *p_ctx)
> +{
> +	struct event_ctx ectx = {
> +		.event_name = "cxl_poison",
> +		.event_pid = getpid(),
> +		.system = "cxl",
> +		.private_ctx = p_ctx,
> +		.parse_event = poison_event_to_json,
> +	};
> +	int rc = 0;
> +
> +	p_ctx->jpoison = json_object_new_array();
> +	if (!p_ctx->jpoison)
> +		return NULL;
> +
> +	rc = cxl_parse_events(inst, &ectx);
> +	if (rc < 0) {
> +		fprintf(stderr, "Failed to parse events: %d\n", rc);
> +		json_object_put(p_ctx->jpoison);
> +		return NULL;

Maybe a goto err here and the next error path may now be warranted?
> +	}
> +
> +	if (json_object_array_length(p_ctx->jpoison) == 0) {
> +		json_object_put(p_ctx->jpoison);
> +		return NULL;
> +	}
> +
> +	return p_ctx->jpoison;
> +}
> +
> +static struct json_object *
> +util_cxl_poison_list_to_json(struct cxl_region *region,
> +			     struct cxl_memdev *memdev,
> +			     unsigned long flags)
> +{
> +	struct json_object *jpoison = NULL;
> +	struct poison_ctx p_ctx;
> +	struct tracefs_instance *inst;
> +	int rc;
> +
> +	inst = tracefs_instance_create("cxl list");
> +	if (!inst) {
> +		fprintf(stderr, "tracefs_instance_create() failed\n");
> +		return NULL;
> +	}
> +
> +	rc = cxl_event_tracing_enable(inst, "cxl", "cxl_poison");
> +	if (rc < 0) {
> +		fprintf(stderr, "Failed to enable trace: %d\n", rc);
> +		goto err_free;
> +	}
> +
> +	if (region)
> +		rc = cxl_region_trigger_poison_list(region);
> +	else
> +		rc = cxl_memdev_trigger_poison_list(memdev);
> +	if (rc)
> +		goto err_free;
> +
> +	rc = cxl_event_tracing_disable(inst);
> +	if (rc < 0) {
> +		fprintf(stderr, "Failed to disable trace: %d\n", rc);
> +		goto err_free;
> +	}
> +
> +	p_ctx = (struct poison_ctx) {
> +		.region = region,
> +		.memdev = memdev,
> +		.flags = flags,
> +	};
> +	jpoison = util_cxl_poison_events_to_json(inst, &p_ctx);
> +
> +err_free:
> +	tracefs_instance_free(inst);
> +	return jpoison;
> +}
> +
>  struct json_object *util_cxl_memdev_to_json(struct cxl_memdev *memdev,
>  		unsigned long flags)
>  {
> @@ -649,6 +898,12 @@ struct json_object *util_cxl_memdev_to_json(struct cxl_memdev *memdev,
>  			json_object_object_add(jdev, "firmware", jobj);
>  	}
>  
> +	if (flags & UTIL_JSON_MEDIA_ERRORS) {
> +		jobj = util_cxl_poison_list_to_json(NULL, memdev, flags);
> +		if (jobj)
> +			json_object_object_add(jdev, "media_errors", jobj);
> +	}
> +
>  	json_object_set_userdata(jdev, memdev, NULL);
>  	return jdev;
>  }
> @@ -987,6 +1242,12 @@ struct json_object *util_cxl_region_to_json(struct cxl_region *region,
>  			json_object_object_add(jregion, "state", jobj);
>  	}
>  
> +	if (flags & UTIL_JSON_MEDIA_ERRORS) {
> +		jobj = util_cxl_poison_list_to_json(region, NULL, flags);
> +		if (jobj)
> +			json_object_object_add(jregion, "media_errors", jobj);
> +	}
> +
>  	util_cxl_mappings_append_json(jregion, region, flags);
>  
>  	if (flags & UTIL_JSON_DAX) {

Re: [ndctl PATCH v7 6/7] cxl/list: add --media-errors option to cxl list

[Dave Jiang]

On 2/7/24 6:01 PM, alison.schofield@intel.com wrote:
> From: Alison Schofield <alison.schofield@intel.com>
> 
> The --media-errors option to 'cxl list' retrieves poison lists from
> memory devices supporting the capability and displays the returned
> media_error records in the cxl list json. This option can apply to
> memdevs or regions.
> 
> Include media-errors in the -vvv verbose option.
> 
> Example usage in the Documentation/cxl/cxl-list.txt update.
> 
> Signed-off-by: Alison Schofield <alison.schofield@intel.com>

Reviewed-by: Dave Jiang <dave.jiang@intel.com>
> ---
>  Documentation/cxl/cxl-list.txt | 79 +++++++++++++++++++++++++++++++++-
>  cxl/filter.h                   |  3 ++
>  cxl/list.c                     |  3 ++
>  3 files changed, 84 insertions(+), 1 deletion(-)
> 
> diff --git a/Documentation/cxl/cxl-list.txt b/Documentation/cxl/cxl-list.txt
> index 838de4086678..5c20614ef579 100644
> --- a/Documentation/cxl/cxl-list.txt
> +++ b/Documentation/cxl/cxl-list.txt
> @@ -415,6 +415,83 @@ OPTIONS
>  --region::
>  	Specify CXL region device name(s), or device id(s), to filter the listing.
>  
> +-L::
> +--media-errors::
> +	Include media-error information. The poison list is retrieved from the
> +	device(s) and media_error records are added to the listing. Apply this
> +	option to memdevs and regions where devices support the poison list
> +	capability.
> +
> +	"decoder" and "hpa" are included when the media-error is in a mapped
> +        address.
> +
> +	"source" will be one of: External, Internal, Injected, Vendor Specific,
> +        or Unknown, as defined in CXL Specification v3.1 Table 8-140.
> +
> +----
> +# cxl list -m mem1 --media-errors
> +[
> +  {
> +    "memdev":"mem1",
> +    "pmem_size":1073741824,
> +    "ram_size":1073741824,
> +    "serial":1,
> +    "numa_node":1,
> +    "host":"cxl_mem.1",
> +    "media_errors":[
> +      {
> +        "dpa":0,
> +        "length":64,
> +        "source":"Internal"
> +      },
> +      {
> +        "decoder":"decoder10.0",
> +        "hpa":1035355557888,
> +        "dpa":1073741824,
> +        "length":64,
> +        "source":"External"
> +      },
> +      {
> +        "decoder":"decoder10.0",
> +        "hpa":1035355566080,
> +        "dpa":1073745920,
> +        "length":64,
> +        "source":"Injected"
> +      }
> +    ]
> +  }
> +]
> +
> +# cxl list -r region5 --media-errors
> +[
> +  {
> +    "region":"region5",
> +    "resource":1035355553792,
> +    "size":2147483648,
> +    "type":"pmem",
> +    "interleave_ways":2,
> +    "interleave_granularity":4096,
> +    "decode_state":"commit",
> +    "media_errors":[
> +      {
> +        "decoder":"decoder10.0",
> +        "hpa":1035355557888,
> +        "dpa":1073741824,
> +        "length":64,
> +        "source":"External"
> +      },
> +      {
> +        "decoder":"decoder8.1",
> +        "hpa":1035355553792,
> +        "dpa":1073741824,
> +        "length":64,
> +        "source":"Internal"
> +      }
> +    ]
> +  }
> +]
> +----
> +
>  -v::
>  --verbose::
>  	Increase verbosity of the output. This can be specified
> @@ -431,7 +508,7 @@ OPTIONS
>  	  devices with --idle.
>  	- *-vvv*
>  	  Everything *-vv* provides, plus enable
> -	  --health and --partition.
> +	  --health, --partition, --media-errors.
>  
>  --debug::
>  	If the cxl tool was built with debug enabled, turn on debug
> diff --git a/cxl/filter.h b/cxl/filter.h
> index 3f65990f835a..956a46e0c7a9 100644
> --- a/cxl/filter.h
> +++ b/cxl/filter.h
> @@ -30,6 +30,7 @@ struct cxl_filter_params {
>  	bool fw;
>  	bool alert_config;
>  	bool dax;
> +	bool media_errors;
>  	int verbose;
>  	struct log_ctx ctx;
>  };
> @@ -88,6 +89,8 @@ static inline unsigned long cxl_filter_to_flags(struct cxl_filter_params *param)
>  		flags |= UTIL_JSON_ALERT_CONFIG;
>  	if (param->dax)
>  		flags |= UTIL_JSON_DAX | UTIL_JSON_DAX_DEVS;
> +	if (param->media_errors)
> +		flags |= UTIL_JSON_MEDIA_ERRORS;
>  	return flags;
>  }
>  
> diff --git a/cxl/list.c b/cxl/list.c
> index 93ba51ef895c..0b25d78248d5 100644
> --- a/cxl/list.c
> +++ b/cxl/list.c
> @@ -57,6 +57,8 @@ static const struct option options[] = {
>  		    "include memory device firmware information"),
>  	OPT_BOOLEAN('A', "alert-config", &param.alert_config,
>  		    "include alert configuration information"),
> +	OPT_BOOLEAN('L', "media-errors", &param.media_errors,
> +		    "include media-error information "),
>  	OPT_INCR('v', "verbose", &param.verbose, "increase output detail"),
>  #ifdef ENABLE_DEBUG
>  	OPT_BOOLEAN(0, "debug", &debug, "debug list walk"),
> @@ -121,6 +123,7 @@ int cmd_list(int argc, const char **argv, struct cxl_ctx *ctx)
>  		param.fw = true;
>  		param.alert_config = true;
>  		param.dax = true;
> +		param.media_errors = true;
>  		/* fallthrough */
>  	case 2:
>  		param.idle = true;

Re: [ndctl PATCH v7 7/7] cxl/test: add cxl-poison.sh unit test

[Dave Jiang]

On 2/7/24 6:01 PM, alison.schofield@intel.com wrote:
> From: Alison Schofield <alison.schofield@intel.com>
> 
> Exercise cxl list, libcxl, and driver pieces of the get poison list
> pathway. Inject and clear poison using debugfs and use cxl-cli to
> read the poison list by memdev and by region.
> 
> Signed-off-by: Alison Schofield <alison.schofield@intel.com>

Reviewed-by: Dave Jiang <dave.jiang@intel.com>

Should circle back and use CXL CLI enabled poison injection/clear when that's available. 
> ---
>  test/cxl-poison.sh | 137 +++++++++++++++++++++++++++++++++++++++++++++
>  test/meson.build   |   2 +
>  2 files changed, 139 insertions(+)
>  create mode 100644 test/cxl-poison.sh
> 
> diff --git a/test/cxl-poison.sh b/test/cxl-poison.sh
> new file mode 100644
> index 000000000000..6fceb0f2c360
> --- /dev/null
> +++ b/test/cxl-poison.sh
> @@ -0,0 +1,137 @@
> +#!/bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +# Copyright (C) 2023 Intel Corporation. All rights reserved.
> +
> +. "$(dirname "$0")"/common
> +
> +rc=77
> +
> +set -ex
> +
> +trap 'err $LINENO' ERR
> +
> +check_prereq "jq"
> +
> +modprobe -r cxl_test
> +modprobe cxl_test
> +
> +rc=1
> +
> +# THEORY OF OPERATION: Exercise cxl-cli and cxl driver ability to
> +# inject, clear, and get the poison list. Do it by memdev and by region.
> +
> +find_memdev()
> +{
> +	readarray -t capable_mems < <("$CXL" list -b "$CXL_TEST_BUS" -M |
> +		jq -r ".[] | select(.pmem_size != null) |
> +		select(.ram_size != null) | .memdev")
> +
> +	if [ ${#capable_mems[@]} == 0 ]; then
> +		echo "no memdevs found for test"
> +		err "$LINENO"
> +	fi
> +
> +	memdev=${capable_mems[0]}
> +}
> +
> +create_x2_region()
> +{
> +        # Find an x2 decoder
> +        decoder="$($CXL list -b "$CXL_TEST_BUS" -D -d root | jq -r ".[] |
> +		select(.pmem_capable == true) |
> +		select(.nr_targets == 2) |
> +		.decoder")"
> +
> +        # Find a memdev for each host-bridge interleave position
> +        port_dev0="$($CXL list -T -d "$decoder" | jq -r ".[] |
> +		.targets | .[] | select(.position == 0) | .target")"
> +        port_dev1="$($CXL list -T -d "$decoder" | jq -r ".[] |
> +		.targets | .[] | select(.position == 1) | .target")"
> +        mem0="$($CXL list -M -p "$port_dev0" | jq -r ".[0].memdev")"
> +        mem1="$($CXL list -M -p "$port_dev1" | jq -r ".[0].memdev")"
> +
> +	region="$($CXL create-region -d "$decoder" -m "$mem0" "$mem1" |
> +		 jq -r ".region")"
> +	if [[ ! $region ]]; then
> +		echo "create-region failed for $decoder"
> +		err "$LINENO"
> +	fi
> +	echo "$region"
> +}
> +
> +# When cxl-cli support for inject and clear arrives, replace
> +# the writes to /sys/kernel/debug with the new cxl commands.
> +
> +inject_poison_sysfs()
> +{
> +	memdev="$1"
> +	addr="$2"
> +
> +	echo "$addr" > /sys/kernel/debug/cxl/"$memdev"/inject_poison
> +}
> +
> +clear_poison_sysfs()
> +{
> +	memdev="$1"
> +	addr="$2"
> +
> +	echo "$addr" > /sys/kernel/debug/cxl/"$memdev"/clear_poison
> +}
> +
> +validate_poison_found()
> +{
> +	list_by="$1"
> +	nr_expect="$2"
> +
> +	poison_list="$($CXL list "$list_by" --media-errors |
> +		jq -r '.[].media_errors')"
> +	if [[ ! $poison_list ]]; then
> +		nr_found=0
> +	else
> +		nr_found=$(jq "length" <<< "$poison_list")
> +	fi
> +	if [ "$nr_found" -ne "$nr_expect" ]; then
> +		echo "$nr_expect poison records expected, $nr_found found"
> +		err "$LINENO"
> +	fi
> +}
> +
> +test_poison_by_memdev()
> +{
> +	find_memdev
> +	inject_poison_sysfs "$memdev" "0x40000000"
> +	inject_poison_sysfs "$memdev" "0x40001000"
> +	inject_poison_sysfs "$memdev" "0x600"
> +	inject_poison_sysfs "$memdev" "0x0"
> +	validate_poison_found "-m $memdev" 4
> +
> +	clear_poison_sysfs "$memdev" "0x40000000"
> +	clear_poison_sysfs "$memdev" "0x40001000"
> +	clear_poison_sysfs "$memdev" "0x600"
> +	clear_poison_sysfs "$memdev" "0x0"
> +	validate_poison_found "-m $memdev" 0
> +}
> +
> +test_poison_by_region()
> +{
> +	create_x2_region
> +	inject_poison_sysfs "$mem0" "0x40000000"
> +	inject_poison_sysfs "$mem1" "0x40000000"
> +	validate_poison_found "-r $region" 2
> +
> +	clear_poison_sysfs "$mem0" "0x40000000"
> +	clear_poison_sysfs "$mem1" "0x40000000"
> +	validate_poison_found "-r $region" 0
> +}
> +
> +# Turn tracing on. Note that 'cxl list --poison' does toggle the tracing.
> +# Turning it on here allows the test user to also view inject and clear
> +# trace events.
> +echo 1 > /sys/kernel/tracing/events/cxl/cxl_poison/enable
> +
> +test_poison_by_memdev
> +test_poison_by_region
> +
> +check_dmesg "$LINENO"
> +
> +modprobe -r cxl-test
> diff --git a/test/meson.build b/test/meson.build
> index 224adaf41fcc..2706fa5d633c 100644
> --- a/test/meson.build
> +++ b/test/meson.build
> @@ -157,6 +157,7 @@ cxl_create_region = find_program('cxl-create-region.sh')
>  cxl_xor_region = find_program('cxl-xor-region.sh')
>  cxl_update_firmware = find_program('cxl-update-firmware.sh')
>  cxl_events = find_program('cxl-events.sh')
> +cxl_poison = find_program('cxl-poison.sh')
>  
>  tests = [
>    [ 'libndctl',               libndctl,		  'ndctl' ],
> @@ -186,6 +187,7 @@ tests = [
>    [ 'cxl-create-region.sh',   cxl_create_region,  'cxl'   ],
>    [ 'cxl-xor-region.sh',      cxl_xor_region,     'cxl'   ],
>    [ 'cxl-events.sh',          cxl_events,         'cxl'   ],
> +  [ 'cxl-poison.sh',          cxl_poison,         'cxl'   ],
>  ]
>  
>  if get_option('destructive').enabled()

Re: [ndctl PATCH v7 7/7] cxl/test: add cxl-poison.sh unit test

[Verma, Vishal L]

On Wed, 2024-02-07 at 17:01 -0800, alison.schofield@intel.com wrote:
> From: Alison Schofield <alison.schofield@intel.com>
> 
> Exercise cxl list, libcxl, and driver pieces of the get poison list
> pathway. Inject and clear poison using debugfs and use cxl-cli to
> read the poison list by memdev and by region.
> 
> Signed-off-by: Alison Schofield <alison.schofield@intel.com>
> ---
>  test/cxl-poison.sh | 137 +++++++++++++++++++++++++++++++++++++++++++++
>  test/meson.build   |   2 +
>  2 files changed, 139 insertions(+)
>  create mode 100644 test/cxl-poison.sh
> 
> diff --git a/test/cxl-poison.sh b/test/cxl-poison.sh
> new file mode 100644
> index 000000000000..6fceb0f2c360
> --- /dev/null
> +++ b/test/cxl-poison.sh
> @@ -0,0 +1,137 @@
> +#!/bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +# Copyright (C) 2023 Intel Corporation. All rights reserved.
> +
> +. "$(dirname "$0")"/common
> +
> +rc=77
> +
> +set -ex
> +
> +trap 'err $LINENO' ERR
> +
> +check_prereq "jq"
> +
> +modprobe -r cxl_test
> +modprobe cxl_test
> +
> +rc=1
> +
> +# THEORY OF OPERATION: Exercise cxl-cli and cxl driver ability to
> +# inject, clear, and get the poison list. Do it by memdev and by region.
> +
> +find_memdev()
> +{
> +	readarray -t capable_mems < <("$CXL" list -b "$CXL_TEST_BUS" -M |
> +		jq -r ".[] | select(.pmem_size != null) |
> +		select(.ram_size != null) | .memdev")
> +
> +	if [ ${#capable_mems[@]} == 0 ]; then
> +		echo "no memdevs found for test"
> +		err "$LINENO"
> +	fi
> +
> +	memdev=${capable_mems[0]}
> +}
> +
> +create_x2_region()
> +{
> +        # Find an x2 decoder
> +        decoder="$($CXL list -b "$CXL_TEST_BUS" -D -d root | jq -r ".[] |
> +		select(.pmem_capable == true) |
> +		select(.nr_targets == 2) |
> +		.decoder")"
> +
> +        # Find a memdev for each host-bridge interleave position
> +        port_dev0="$($CXL list -T -d "$decoder" | jq -r ".[] |
> +		.targets | .[] | select(.position == 0) | .target")"
> +        port_dev1="$($CXL list -T -d "$decoder" | jq -r ".[] |
> +		.targets | .[] | select(.position == 1) | .target")"
> +        mem0="$($CXL list -M -p "$port_dev0" | jq -r ".[0].memdev")"
> +        mem1="$($CXL list -M -p "$port_dev1" | jq -r ".[0].memdev")"

Space/tab mixing here. I wonder if one of the earlier tests where some
of this boilerplate comes from has spaces instead of tabs, and has been
creeping into new tests. Would be nice to at least clean this patch up,
and I can send a cleanup for older tests once the dust settles with the
currently in-flux patchsets.

> +
> +	region="$($CXL create-region -d "$decoder" -m "$mem0" "$mem1" |
> +		 jq -r ".region")"
> +	if [[ ! $region ]]; then
> +		echo "create-region failed for $decoder"
> +		err "$LINENO"
> +	fi
> +	echo "$region"
> +}
> +
> +# When cxl-cli support for inject and clear arrives, replace
> +# the writes to /sys/kernel/debug with the new cxl commands.
> +
> +inject_poison_sysfs()
> +{
> +	memdev="$1"
> +	addr="$2"
> +
> +	echo "$addr" > /sys/kernel/debug/cxl/"$memdev"/inject_poison
> +}
> +
> +clear_poison_sysfs()
> +{
> +	memdev="$1"
> +	addr="$2"
> +
> +	echo "$addr" > /sys/kernel/debug/cxl/"$memdev"/clear_poison
> +}
> +
> +validate_poison_found()
> +{
> +	list_by="$1"
> +	nr_expect="$2"
> +
> +	poison_list="$($CXL list "$list_by" --media-errors |
> +		jq -r '.[].media_errors')"
> +	if [[ ! $poison_list ]]; then
> +		nr_found=0
> +	else
> +		nr_found=$(jq "length" <<< "$poison_list")
> +	fi
> +	if [ "$nr_found" -ne "$nr_expect" ]; then
> +		echo "$nr_expect poison records expected, $nr_found found"
> +		err "$LINENO"
> +	fi
> +}
> +
> +test_poison_by_memdev()
> +{
> +	find_memdev
> +	inject_poison_sysfs "$memdev" "0x40000000"
> +	inject_poison_sysfs "$memdev" "0x40001000"
> +	inject_poison_sysfs "$memdev" "0x600"
> +	inject_poison_sysfs "$memdev" "0x0"
> +	validate_poison_found "-m $memdev" 4
> +
> +	clear_poison_sysfs "$memdev" "0x40000000"
> +	clear_poison_sysfs "$memdev" "0x40001000"
> +	clear_poison_sysfs "$memdev" "0x600"
> +	clear_poison_sysfs "$memdev" "0x0"
> +	validate_poison_found "-m $memdev" 0
> +}
> +
> +test_poison_by_region()
> +{
> +	create_x2_region
> +	inject_poison_sysfs "$mem0" "0x40000000"
> +	inject_poison_sysfs "$mem1" "0x40000000"
> +	validate_poison_found "-r $region" 2
> +
> +	clear_poison_sysfs "$mem0" "0x40000000"
> +	clear_poison_sysfs "$mem1" "0x40000000"
> +	validate_poison_found "-r $region" 0
> +}
> +
> +# Turn tracing on. Note that 'cxl list --poison' does toggle the tracing.
> +# Turning it on here allows the test user to also view inject and clear
> +# trace events.
> +echo 1 > /sys/kernel/tracing/events/cxl/cxl_poison/enable
> +
> +test_poison_by_memdev
> +test_poison_by_region
> +
> +check_dmesg "$LINENO"
> +
> +modprobe -r cxl-test
> diff --git a/test/meson.build b/test/meson.build
> index 224adaf41fcc..2706fa5d633c 100644
> --- a/test/meson.build
> +++ b/test/meson.build
> @@ -157,6 +157,7 @@ cxl_create_region = find_program('cxl-create-region.sh')
>  cxl_xor_region = find_program('cxl-xor-region.sh')
>  cxl_update_firmware = find_program('cxl-update-firmware.sh')
>  cxl_events = find_program('cxl-events.sh')
> +cxl_poison = find_program('cxl-poison.sh')
>  
>  tests = [
>    [ 'libndctl',               libndctl,		  'ndctl' ],
> @@ -186,6 +187,7 @@ tests = [
>    [ 'cxl-create-region.sh',   cxl_create_region,  'cxl'   ],
>    [ 'cxl-xor-region.sh',      cxl_xor_region,     'cxl'   ],
>    [ 'cxl-events.sh',          cxl_events,         'cxl'   ],
> +  [ 'cxl-poison.sh',          cxl_poison,         'cxl'   ],
>  ]
>  
>  if get_option('destructive').enabled()

Re: [ndctl PATCH v7 5/7] cxl/list: collect and parse media_error records

[Alison Schofield]

On Thu, Feb 08, 2024 at 09:50:27AM -0700, Dave Jiang wrote:
> 

Hi Dave,

Sorry I missed this in v8. Picking up for v9.  
See a question below -


snip
> 
> > +static const char *
> > +find_decoder_name(struct poison_ctx *ctx, const char *name, u64 addr)
> > +{
> > +	struct cxl_memdev *memdev = ctx->memdev;
> > +	struct cxl_memdev_mapping *mapping;
> > +	struct cxl_endpoint *endpoint;
> > +	struct cxl_decoder *decoder;
> > +	struct cxl_port *port;
> > +	u64 start, end;
> > +
> > +	if (memdev)
> > +		goto find_decoder;
> > +
> > +	cxl_mapping_foreach(ctx->region, mapping) {
> > +		decoder = cxl_mapping_get_decoder(mapping);
> > +		if (!decoder)
> > +			continue;
> > +
> > +		memdev = cxl_decoder_get_memdev(decoder);
> > +		if (strcmp(name, cxl_memdev_get_devname(memdev)) == 0)
> > +			break;
> > +
> > +		memdev = NULL;
> > +	}
> > +
> > +find_decoder:
> 
> Would it be cleaner to move this block into a helper function? Don't really care for goto blocks that are not error handling paths.

Done. Added a __find_memdev.

> 
> > +	if (!memdev)
> > +		return NULL;
> > +
> > +	endpoint = cxl_memdev_get_endpoint(memdev);
> > +	port = cxl_endpoint_get_port(endpoint);
> > +
> > +	cxl_decoder_foreach(port, decoder) {
> > +		start =  cxl_decoder_get_resource(decoder);
> > +		end = start + cxl_decoder_get_size(decoder) - 1;
> > +		if (start <= addr && addr <= end)
> > +			return cxl_decoder_get_devname(decoder);
> > +	}
> > +
> > +	return NULL;

And, with another look - cleaned up the above indented/hidden
successful return ;)


> > +}
> > +
> > +int poison_event_to_json(struct tep_event *event, struct tep_record *record,
> > +			 void *ctx)
> > +{
> > +	struct poison_ctx *p_ctx = (struct poison_ctx *)ctx;
> > +	struct json_object *jobj, *jp, *jpoison = p_ctx->jpoison;
> > +	unsigned long flags = p_ctx->flags;
> > +	bool overflow = false;
> > +	unsigned char *data;
> > +	const char *name;
> > +	int pflags;
> > +	char *str;
> > +
> > +	jp = json_object_new_object();
> > +	if (!jp)
> > +		return -ENOMEM;
> > +
> > +	/* Skip records not in this region when listing by region */
> > +	name = p_ctx->region ? cxl_region_get_devname(p_ctx->region) : NULL;
> > +	if (name)
> > +		str = cxl_get_field_string(event, record, "region");
> > +
> > +	if ((name) && (strcmp(name, str) != 0)) {
> > +		json_object_put(jp);
> > +		return 0;
> > +	}
> > +
> > +	/* Include endpoint decoder name with hpa, when present */
> > +	name = cxl_get_field_string(event, record, "memdev");
> > +	data = cxl_get_field_data(event, record, "hpa");
> > +	if (*(uint64_t *)data != ULLONG_MAX)
> > +		name = find_decoder_name(p_ctx, name, *(uint64_t *)data);
> > +	else
> > +		name = NULL;
> > +
> > +	if (name) {
> > +		jobj = json_object_new_string(name);
> > +		if (jobj)
> > +			json_object_object_add(jp, "decoder", jobj);
> > +
> > +		jobj = util_json_object_hex(*(uint64_t *)data, flags);
> > +		if (jobj)
> > +			json_object_object_add(jp, "hpa", jobj);
> > +	}
> > +
> > +	data = cxl_get_field_data(event, record, "dpa");
> > +	jobj = util_json_object_hex(*(uint64_t *)data, flags);
> > +	if (jobj)
> > +		json_object_object_add(jp, "dpa", jobj);
> > +
> > +	data = cxl_get_field_data(event, record, "dpa_length");
> > +	jobj = util_json_object_size(*(uint32_t *)data, flags);
> > +	if (jobj)
> > +		json_object_object_add(jp, "length", jobj);
> > +
> > +	str = cxl_get_field_string(event, record, "source");
> > +	switch (*(uint8_t *)str) {
> 
> This causes reading confusion when it looks like the code is retrieving a string and then compare as an integer. Should this be done through cxl_get_field_data()?
> 

Did a couple of things here -
reworked the helpers to give exactly what is needed here,
ie int, u64 or string. That gets rid of all the casting.
It also led to a bit more error checking on return value,
so bonus goodness.


> > +	case CXL_POISON_SOURCE_UNKNOWN:
> > +		jobj = json_object_new_string("Unknown");
> > +		break;
> > +	case CXL_POISON_SOURCE_EXTERNAL:
> > +		jobj = json_object_new_string("External");
> > +		break;
> > +	case CXL_POISON_SOURCE_INTERNAL:
> > +		jobj = json_object_new_string("Internal");
> > +		break;
> > +	case CXL_POISON_SOURCE_INJECTED:
> > +		jobj = json_object_new_string("Injected");
> > +		break;
> > +	case CXL_POISON_SOURCE_VENDOR:
> > +		jobj = json_object_new_string("Vendor");
> > +		break;
> > +	default:
> > +		jobj = json_object_new_string("Reserved");
> > +	}
> > +	if (jobj)
> > +		json_object_object_add(jp, "source", jobj);
> > +
> > +	str = cxl_get_field_string(event, record, "flags");
> > +	pflags = *(uint8_t *)str;
> 
> Same as above comment here

Gone. All the values that can be held in "int" are fetched
using a cxl_get_field_int().

snip
> > +static struct json_object *
> > +util_cxl_poison_events_to_json(struct tracefs_instance *inst,
> > +			       struct poison_ctx *p_ctx)
> > +{
> > +	struct event_ctx ectx = {
> > +		.event_name = "cxl_poison",
> > +		.event_pid = getpid(),
> > +		.system = "cxl",
> > +		.private_ctx = p_ctx,
> > +		.parse_event = poison_event_to_json,
> > +	};
> > +	int rc = 0;
> > +
> > +	p_ctx->jpoison = json_object_new_array();
> > +	if (!p_ctx->jpoison)
> > +		return NULL;
> > +
> > +	rc = cxl_parse_events(inst, &ectx);
> > +	if (rc < 0) {
> > +		fprintf(stderr, "Failed to parse events: %d\n", rc);
> > +		json_object_put(p_ctx->jpoison);
> > +		return NULL;
> 
> Maybe a goto err here and the next error path may now be warranted?
> > +	}
> > +
> > +	if (json_object_array_length(p_ctx->jpoison) == 0) {
> > +		json_object_put(p_ctx->jpoison);
> > +		return NULL;
> > +	}
> > +
> > +	return p_ctx->jpoison;
> > +}

Not sure what you suggest here. I can combine the err cases like
this:

if ((rc < 0) || json_object_array_length(p_ctx->jpoison) == 0) {
	fprintf(stderr, "Failed to parse events: %d\n", rc);
	json_object_put(p_ctx->jpoison);
	return NULL;
}

Or (and) something else?