From: alison.schofield@intel.com
To: Vishal Verma <vishal.l.verma@intel.com>
Cc: Alison Schofield <alison.schofield@intel.com>,
nvdimm@lists.linux.dev, linux-cxl@vger.kernel.org
Subject: [ndctl PATCH v7 5/7] cxl/list: collect and parse media_error records
Date: Wed, 7 Feb 2024 17:01:44 -0800 [thread overview]
Message-ID: <566a2acff6a3f32a1d6af9d81fb0da8808e5b4ff.1707351560.git.alison.schofield@intel.com> (raw)
In-Reply-To: <cover.1707351560.git.alison.schofield@intel.com>
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
next prev parent reply other threads:[~2024-02-08 1:02 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-08 1:01 [ndctl PATCH v7 0/7] Support poison list retrieval alison.schofield
2024-02-08 1:01 ` [ndctl PATCH v7 1/7] libcxl: add interfaces for GET_POISON_LIST mailbox commands alison.schofield
2024-02-08 1:01 ` [ndctl PATCH v7 2/7] cxl: add an optional pid check to event parsing alison.schofield
2024-02-08 1:01 ` [ndctl PATCH v7 3/7] cxl/event_trace: add a private context for private parsers alison.schofield
2024-02-08 1:01 ` [ndctl PATCH v7 4/7] cxl/event_trace: add helpers get_field_[string|data]() alison.schofield
2024-02-08 1:01 ` alison.schofield [this message]
2024-02-08 16:50 ` [ndctl PATCH v7 5/7] cxl/list: collect and parse media_error records Dave Jiang
2024-02-29 2:45 ` Alison Schofield
2024-02-08 1:01 ` [ndctl PATCH v7 6/7] cxl/list: add --media-errors option to cxl list alison.schofield
2024-02-08 16:51 ` Dave Jiang
2024-02-08 1:01 ` [ndctl PATCH v7 7/7] cxl/test: add cxl-poison.sh unit test alison.schofield
2024-02-08 18:18 ` Dave Jiang
2024-02-22 8:04 ` Verma, Vishal L
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=566a2acff6a3f32a1d6af9d81fb0da8808e5b4ff.1707351560.git.alison.schofield@intel.com \
--to=alison.schofield@intel.com \
--cc=linux-cxl@vger.kernel.org \
--cc=nvdimm@lists.linux.dev \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).