Message-Id: <1549823329-10377-5-git-send-email-ayal@mellanox.com>
Date:   Sun, 10 Feb 2019 20:28:49 +0200
From:   Aya Levin <ayal@...lanox.com>
To:     David Ahern <dsahern@...il.com>, netdev@...r.kernel.org,
        "David S. Miller" <davem@...emloft.net>,
        Jiri Pirko <jiri@...lanox.com>
Cc:     Moshe Shemesh <moshe@...lanox.com>, Aya Levin <ayal@...lanox.com>,
        Eran Ben Elisha <eranbe@...lanox.com>,
        Tal Alon <talal@...lanox.com>,
        Ariel Almog <ariela@...lanox.com>
Subject: [PATCH for-next 4/4] devlink: add health command support

This patch adds support for the following commands:
devlink health show      [DEV reporter REPORTE_NAME]
devlink health recover    DEV reporter REPORTER_NAME
devlink health diagnose   DEV reporter REPORTER_NAME
devlink health dump show  DEV reporter REPORTER_NAME
devlink health dump clear DEV reporter REPORTER_NAME
devlink health set        DEV reporter REPORTER_NAME NAME VALUE

 * show: Devlink health show command displays status and configuration info on
   specific reporter on a device or dump the info on all reporters on all
   devices.
 * recover: Devlink health recover enables the user to initiate a
   recovery on a reporter. This operation will increment the recoveries
   counter displayed in the show command.
 * diagnose: Devlink health diagnose enables the user to retrieve diagnostics data
   on a reporter on a device. The command's output is a free text defined
   by the reporter.
 * dump show: Devlink health dump show displays the last saved dump. Devlink
   health saves a single dump. If a dump is not already stored by
   the Devlink for this reporter, Devlink generates a new dump. The
   dump can be generated automatically when a reporter reports on an
   error or manually by user's request.
   dump output is defined by the reporter.
 * dump clear: Devlink health dump clear, deletes the last saved dump file.
 * set: Devlink health set, enables the user to configure:
	1) grace_period [msec] time interval between auto recoveries.
	2) auto_recover [true/false] whether the devlink should execute
	automatic recover on error.

Examples:
$devlink health show pci/0000:00:09.0 reporter tx
pci/0000:00:09.0:
name tx
  state healthy #err 0 #recover 1 last_dump_ts N/A
    parameters:
      grace period 600 auto_recover true
$devlink health diagnose pci/0000:00:09.0 reporter tx
SQs:
  sqn: 4283 HW state: 1 stopped: false
  sqn: 4288 HW state: 1 stopped: false
  sqn: 4293 HW state: 1 stopped: false
  sqn: 4298 HW state: 1 stopped: false
  sqn: 4303 HW state: 1 stopped: false
$devlink health dump show pci/0000:00:09.0 reporter tx
TX dump data
$devlink health dump clear pci/0000:00:09.0 reporter tx
$devlink health set pci/0000:00:09.0 reporter tx grace_period 3500
$devlink health set pci/0000:00:09.0 reporter tx auto_recover false

Signed-off-by: Aya Levin <ayal@...lanox.com>
Reviewed-by: Moshe Shemesh <moshe@...lanox.com>
---
 devlink/devlink.c            | 551 ++++++++++++++++++++++++++++++++++++++++++-
 include/uapi/linux/devlink.h |  23 ++
 man/man8/devlink-health.8    | 176 ++++++++++++++
 man/man8/devlink.8           |   7 +-
 4 files changed, 755 insertions(+), 2 deletions(-)
 create mode 100644 man/man8/devlink-health.8

diff --git a/devlink/devlink.c b/devlink/devlink.c
index a433883f1b2b..2ddbf389a3ea 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -22,6 +22,8 @@
 #include <linux/devlink.h>
 #include <libmnl/libmnl.h>
 #include <netinet/ether.h>
+#include <sys/sysinfo.h>
+#include <sys/queue.h>
 
 #include "SNAPSHOT.h"
 #include "list.h"
@@ -41,6 +43,10 @@
 #define PARAM_CMODE_PERMANENT_STR "permanent"
 #define DL_ARGS_REQUIRED_MAX_ERR_LEN 80
 
+#define HEALTH_REPORTER_STATE_HEALTHY_STR "healthy"
+#define HEALTH_REPORTER_STATE_ERROR_STR "error"
+#define HEALTH_REPORTER_TIMESTAMP_FORMAT_LEN 80
+
 static int g_new_line_count;
 
 #define pr_err(args...) fprintf(stderr, ##args)
@@ -200,6 +206,9 @@ static void ifname_map_free(struct ifname_map *ifname_map)
 #define DL_OPT_REGION_SNAPSHOT_ID	BIT(22)
 #define DL_OPT_REGION_ADDRESS		BIT(23)
 #define DL_OPT_REGION_LENGTH		BIT(24)
+#define DL_OPT_HEALTH_REPORTER_NAME	BIT(25)
+#define DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD	BIT(26)
+#define DL_OPT_HEALTH_REPORTER_AUTO_RECOVER	BIT(27)
 
 struct dl_opts {
 	uint32_t present; /* flags of present items */
@@ -231,6 +240,9 @@ struct dl_opts {
 	uint32_t region_snapshot_id;
 	uint64_t region_address;
 	uint64_t region_length;
+	const char *reporter_name;
+	uint64_t reporter_graceful_period;
+	bool reporter_auto_recover;
 };
 
 struct dl {
@@ -391,6 +403,17 @@ static const enum mnl_attr_data_type devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_INFO_VERSION_STORED] = MNL_TYPE_NESTED,
 	[DEVLINK_ATTR_INFO_VERSION_NAME] = MNL_TYPE_STRING,
 	[DEVLINK_ATTR_INFO_VERSION_VALUE] = MNL_TYPE_STRING,
+	[DEVLINK_ATTR_FMSG] = MNL_TYPE_NESTED,
+	[DEVLINK_ATTR_FMSG_OBJ_NAME] = MNL_TYPE_STRING,
+	[DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE] = MNL_TYPE_U8,
+	[DEVLINK_ATTR_HEALTH_REPORTER] = MNL_TYPE_NESTED,
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = MNL_TYPE_STRING,
+	[DEVLINK_ATTR_HEALTH_REPORTER_STATE] = MNL_TYPE_U8,
+	[DEVLINK_ATTR_HEALTH_REPORTER_ERR] = MNL_TYPE_U64,
+	[DEVLINK_ATTR_HEALTH_REPORTER_RECOVER] = MNL_TYPE_U64,
+	[DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS] = MNL_TYPE_U64,
+	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = MNL_TYPE_U64,
+	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = MNL_TYPE_U8,
 };
 
 static int attr_cb(const struct nlattr *attr, void *data)
@@ -822,6 +845,24 @@ static int dl_argv_uint16_t(struct dl *dl, uint16_t *p_val)
 	return 0;
 }
 
+static int dl_argv_bool(struct dl *dl, bool *p_val)
+{
+	char *str = dl_argv_next(dl);
+	int err;
+
+	if (!str) {
+		pr_err("Boolean argument expected\n");
+		return -EINVAL;
+	}
+
+	err = strtobool(str, p_val);
+	if (err) {
+		pr_err("\"%s\" is not a valid boolean value\n", str);
+		return err;
+	}
+	return 0;
+}
+
 static int dl_argv_str(struct dl *dl, const char **p_str)
 {
 	const char *str = dl_argv_next(dl);
@@ -976,6 +1017,7 @@ static const struct dl_args_metadata dl_args_required[] = {
 	{DL_OPT_REGION_SNAPSHOT_ID,   "Region snapshot id expected.\n"},
 	{DL_OPT_REGION_ADDRESS,	      "Region address value expected.\n"},
 	{DL_OPT_REGION_LENGTH,	      "Region length value expected.\n"},
+	{DL_OPT_HEALTH_REPORTER_NAME, "Reporter's name is expected.\n"},
 };
 
 static int validate_finding_required_dl_args(uint32_t o_required,
@@ -1231,6 +1273,28 @@ static int dl_argv_parse(struct dl *dl, uint32_t o_required,
 			if (err)
 				return err;
 			o_found |= DL_OPT_REGION_LENGTH;
+		} else if (dl_argv_match(dl, "reporter") &&
+			   (o_all & DL_OPT_HEALTH_REPORTER_NAME)) {
+			dl_arg_inc(dl);
+			err = dl_argv_str(dl, &opts->reporter_name);
+			if (err)
+				return err;
+			o_found |= DL_OPT_HEALTH_REPORTER_NAME;
+		} else if (dl_argv_match(dl, "grace_period") &&
+			   (o_all & DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD)) {
+			dl_arg_inc(dl);
+			err = dl_argv_uint64_t(dl,
+					       &opts->reporter_graceful_period);
+			if (err)
+				return err;
+			o_found |= DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD;
+		} else if (dl_argv_match(dl, "auto_recover") &&
+			(o_all & DL_OPT_HEALTH_REPORTER_AUTO_RECOVER)) {
+			dl_arg_inc(dl);
+			err = dl_argv_bool(dl, &opts->reporter_auto_recover);
+			if (err)
+				return err;
+			o_found |= DL_OPT_HEALTH_REPORTER_AUTO_RECOVER;
 		} else {
 			pr_err("Unknown option \"%s\"\n", dl_argv(dl));
 			return -EINVAL;
@@ -1328,6 +1392,16 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
 	if (opts->present & DL_OPT_REGION_LENGTH)
 		mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_LEN,
 				 opts->region_length);
+	if (opts->present & DL_OPT_HEALTH_REPORTER_NAME)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+				  opts->reporter_name);
+	if (opts->present & DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD)
+		mnl_attr_put_u64(nlh,
+				 DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,
+				 opts->reporter_graceful_period);
+	if (opts->present & DL_OPT_HEALTH_REPORTER_AUTO_RECOVER)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,
+				opts->reporter_auto_recover);
 }
 
 static int dl_argv_parse_put(struct nlmsghdr *nlh, struct dl *dl,
@@ -5677,11 +5751,482 @@ static int cmd_region(struct dl *dl)
 	return -ENOENT;
 }
 
+static int cmd_health_set_params(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_HEALTH_REPORTER_SET,
+			       NLM_F_REQUEST | NLM_F_ACK);
+	err = dl_argv_parse(dl, DL_OPT_HANDLE | DL_OPT_HEALTH_REPORTER_NAME,
+			    DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD |
+			    DL_OPT_HEALTH_REPORTER_AUTO_RECOVER);
+	if (err)
+		return err;
+
+	dl_opts_put(nlh, dl);
+	return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
+static int cmd_health_dump_clear(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = mnlg_msg_prepare(dl->nlg,
+			       DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+			       NLM_F_REQUEST | NLM_F_ACK);
+
+	err = dl_argv_parse_put(nlh, dl,
+				DL_OPT_HANDLE | DL_OPT_HEALTH_REPORTER_NAME, 0);
+	if (err)
+		return err;
+
+	dl_opts_put(nlh, dl);
+	return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
+static int health_value_show(struct dl *dl, int type, struct nlattr *nl_data)
+{
+	const char *str;
+	uint8_t *data;
+	uint32_t len;
+	uint64_t val_u64;
+	uint32_t val_u32;
+	uint16_t val_u16;
+	uint8_t val_u8;
+	bool val_bool;
+	int i;
+
+	switch (type) {
+	case MNL_TYPE_FLAG:
+		val_bool = mnl_attr_get_u8(nl_data);
+		if (dl->json_output)
+			jsonw_bool(dl->jw, !!val_bool);
+		else
+			pr_out("%s ", val_bool ? "true" : "false");
+		break;
+	case MNL_TYPE_U8:
+		val_u8 = mnl_attr_get_u8(nl_data);
+		if (dl->json_output)
+			jsonw_uint(dl->jw, val_u8);
+		else
+			pr_out("%u ", val_u8);
+		break;
+	case MNL_TYPE_U16:
+		val_u16 = mnl_attr_get_u16(nl_data);
+		if (dl->json_output)
+			jsonw_uint(dl->jw, val_u16);
+		else
+			pr_out("%u ", val_u16);
+		break;
+	case MNL_TYPE_U32:
+		val_u32 = mnl_attr_get_u32(nl_data);
+		if (dl->json_output)
+			jsonw_uint(dl->jw, val_u32);
+		else
+			pr_out("%u ", val_u32);
+		break;
+	case MNL_TYPE_U64:
+		val_u64 = mnl_attr_get_u64(nl_data);
+		if (dl->json_output)
+			jsonw_u64(dl->jw, val_u64);
+		else
+			pr_out("%lu ", val_u64);
+		break;
+	case MNL_TYPE_NUL_STRING:
+		str = mnl_attr_get_str(nl_data);
+		if (dl->json_output)
+			jsonw_string(dl->jw, str);
+		else
+			pr_out("%s ", str);
+		break;
+	case MNL_TYPE_BINARY:
+		len = mnl_attr_get_payload_len(nl_data);
+		data = mnl_attr_get_payload(nl_data);
+		i = 0;
+		while (i < len) {
+			if (dl->json_output) {
+				jsonw_printf(dl->jw, "%d", data[i]);
+			} else {
+				pr_out("%02x ", data[i]);
+				if (!(i % 15))
+					pr_out("\n");
+			}
+			i++;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	return MNL_CB_OK;
+}
+
+struct nest_qentry {
+	int attr_type;
+
+	TAILQ_ENTRY(nest_qentry) nest_entries;
+};
+
+struct health_cb_data {
+	struct dl *dl;
+	uint8_t value_type;
+
+	TAILQ_HEAD(, nest_qentry) qhead;
+};
+
+static int cmd_health_nest_queue(struct health_cb_data *health_data,
+				 uint8_t *attr_value, bool insert)
+{
+	struct nest_qentry *entry = NULL;
+
+	if (insert) {
+		entry = malloc(sizeof(struct nest_qentry));
+		if (!entry)
+			return -ENOMEM;
+
+		entry->attr_type = *attr_value;
+		TAILQ_INSERT_HEAD(&health_data->qhead, entry, nest_entries);
+	} else {
+		if (TAILQ_EMPTY(&health_data->qhead))
+			return MNL_CB_ERROR;
+		entry = TAILQ_FIRST(&health_data->qhead);
+		*attr_value = entry->attr_type;
+		TAILQ_REMOVE(&health_data->qhead, entry, nest_entries);
+		free(entry);
+	}
+	return MNL_CB_OK;
+}
+
+static int cmd_health_nest(struct health_cb_data *health_data,
+			   uint8_t nest_value, bool start)
+{
+	struct dl *dl = health_data->dl;
+	uint8_t value = nest_value;
+	int err;
+
+	err = cmd_health_nest_queue(health_data, &value, start);
+	if (err != MNL_CB_OK)
+		return err;
+
+	switch (value) {
+	case DEVLINK_ATTR_FMSG_OBJ_NEST_START:
+		if (start)
+			pr_out_entry_start(dl);
+		else
+			pr_out_entry_end(dl);
+		break;
+	case DEVLINK_ATTR_FMSG_PAIR_NEST_START:
+		break;
+	case DEVLINK_ATTR_FMSG_ARR_NEST_START:
+		if (dl->json_output) {
+			if (start)
+				jsonw_start_array(dl->jw);
+			else
+				jsonw_end_array(dl->jw);
+		} else {
+			if (start) {
+				__pr_out_newline();
+				__pr_out_indent_inc();
+			} else {
+				__pr_out_indent_dec();
+			}
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	return MNL_CB_OK;
+}
+
+static int cmd_health_object_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+	struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+	struct health_cb_data *health_data = data;
+	struct dl *dl = health_data->dl;
+	struct nlattr *nla_object;
+	const char *name;
+	int attr_type;
+	int err;
+
+	mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+	if (!tb[DEVLINK_ATTR_FMSG])
+		return MNL_CB_ERROR;
+
+	mnl_attr_for_each_nested(nla_object, tb[DEVLINK_ATTR_FMSG]) {
+		attr_type = mnl_attr_get_type(nla_object);
+		switch (attr_type) {
+		case DEVLINK_ATTR_FMSG_OBJ_NEST_START:
+		case DEVLINK_ATTR_FMSG_PAIR_NEST_START:
+		case DEVLINK_ATTR_FMSG_ARR_NEST_START:
+			err = cmd_health_nest(health_data, attr_type, true);
+			if (err != MNL_CB_OK)
+				return err;
+			break;
+		case DEVLINK_ATTR_FMSG_NEST_END:
+			err = cmd_health_nest(health_data, attr_type, false);
+			if (err != MNL_CB_OK)
+				return err;
+			break;
+		case DEVLINK_ATTR_FMSG_OBJ_NAME:
+			name = mnl_attr_get_str(nla_object);
+			if (dl->json_output)
+				jsonw_name(dl->jw, name);
+			else
+				pr_out("%s: ", name);
+			break;
+		case DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE:
+			health_data->value_type = mnl_attr_get_u8(nla_object);
+			break;
+		case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA:
+			err = health_value_show(dl, health_data->value_type,
+						nla_object);
+			if (err != MNL_CB_OK)
+				return err;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	return MNL_CB_OK;
+}
+
+static int cmd_health_object_common(struct dl *dl, uint8_t cmd)
+{
+	struct nlmsghdr *nlh;
+	struct health_cb_data data;
+	int err;
+
+	nlh = mnlg_msg_prepare(dl->nlg, cmd,
+			       NLM_F_REQUEST | NLM_F_ACK);
+
+	err = dl_argv_parse_put(nlh, dl,
+				DL_OPT_HANDLE | DL_OPT_HEALTH_REPORTER_NAME, 0);
+	if (err)
+		return err;
+
+	data.dl = dl;
+	TAILQ_INIT(&data.qhead);
+	err = _mnlg_socket_sndrcv(dl->nlg, nlh, cmd_health_object_cb, &data);
+	return err;
+}
+
+static int cmd_health_diagnose(struct dl *dl)
+{
+	return cmd_health_object_common(dl, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE);
+}
+
+static int cmd_health_dump_show(struct dl *dl)
+{
+	return cmd_health_object_common(dl, DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET);
+}
+
+static int cmd_health_recover(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+			       NLM_F_REQUEST | NLM_F_ACK);
+
+	err = dl_argv_parse_put(nlh, dl,
+				DL_OPT_HANDLE | DL_OPT_HEALTH_REPORTER_NAME, 0);
+	if (err)
+		return err;
+
+	dl_opts_put(nlh, dl);
+	return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
+enum devlink_health_reporter_state {
+	DEVLINK_HEALTH_REPORTER_STATE_HEALTHY,
+	DEVLINK_HEALTH_REPORTER_STATE_ERROR,
+};
+
+static const char *health_state_name(uint8_t state)
+{
+	switch (state) {
+	case DEVLINK_HEALTH_REPORTER_STATE_HEALTHY:
+		return HEALTH_REPORTER_STATE_HEALTHY_STR;
+	case DEVLINK_HEALTH_REPORTER_STATE_ERROR:
+		return HEALTH_REPORTER_STATE_ERROR_STR;
+	default:
+		return "<unknown state>";
+	}
+}
+
+static void format_logtime(uint64_t time_ms, char *output)
+{
+	struct sysinfo s_info;
+	struct tm *info;
+	time_t now, sec;
+	int err;
+
+	time(&now);
+	info = localtime(&now);
+	err = sysinfo(&s_info);
+	if (err)
+		goto out;
+	/* substruct uptime in sec from now
+	 * add time_ms and 5 minutes factor
+	 */
+	sec = now - (s_info.uptime - time_ms / 1000) + 300;
+	info = localtime(&sec);
+out:
+	strftime(output, HEALTH_REPORTER_TIMESTAMP_FORMAT_LEN,
+		 "%Y-%b-%d %H:%M:%S", info);
+}
+
+static void pr_out_health(struct dl *dl, struct nlattr **tb)
+{
+	char dump_time_date[HEALTH_REPORTER_TIMESTAMP_FORMAT_LEN] = "N/A";
+	struct nlattr *hlt[DEVLINK_ATTR_MAX + 1] = {};
+	enum devlink_health_reporter_state state;
+	bool auto_recover = false;
+	const struct nlattr *attr;
+	uint64_t time_ms;
+	int err;
+
+	state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY;
+
+	err = mnl_attr_parse_nested(tb[DEVLINK_ATTR_HEALTH_REPORTER], attr_cb,
+				    hlt);
+	if (err != MNL_CB_OK)
+		return;
+
+	if (!hlt[DEVLINK_ATTR_HEALTH_REPORTER_NAME]		||
+	    !hlt[DEVLINK_ATTR_HEALTH_REPORTER_ERR]		||
+	    !hlt[DEVLINK_ATTR_HEALTH_REPORTER_RECOVER]		||
+	    !hlt[DEVLINK_ATTR_HEALTH_REPORTER_STATE]		||
+	    !hlt[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]	||
+	    !hlt[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD])
+		return;
+
+	if (hlt[DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS]) {
+		attr = hlt[DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS];
+		time_ms = mnl_attr_get_u64(attr);
+		format_logtime(time_ms, dump_time_date);
+	}
+	pr_out_handle_start_arr(dl, tb);
+
+	pr_out_str(dl, "name",
+		   mnl_attr_get_str(hlt[DEVLINK_ATTR_HEALTH_REPORTER_NAME]));
+	if (!dl->json_output) {
+		__pr_out_newline();
+		__pr_out_indent_inc();
+	}
+	state = mnl_attr_get_u8(hlt[DEVLINK_ATTR_HEALTH_REPORTER_STATE]);
+	pr_out_str(dl, "state", health_state_name(state));
+	pr_out_u64(dl, "#err",
+		   mnl_attr_get_u64(hlt[DEVLINK_ATTR_HEALTH_REPORTER_ERR]));
+	pr_out_u64(dl, "#recover",
+		   mnl_attr_get_u64(hlt[DEVLINK_ATTR_HEALTH_REPORTER_RECOVER]));
+	pr_out_str(dl, "last_dump_ts", dump_time_date);
+	pr_out_array_start(dl, "parameters");
+	pr_out_entry_start(dl);
+	pr_out_u64(dl, "grace_period",
+		   mnl_attr_get_u64(hlt[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]));
+	auto_recover = mnl_attr_get_u8(hlt[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]);
+	pr_out_bool(dl, "auto_recover", auto_recover);
+	pr_out_entry_end(dl);
+	pr_out_array_end(dl);
+	__pr_out_indent_dec();
+	__pr_out_indent_dec();
+	pr_out_handle_end(dl);
+}
+
+static int cmd_health_show_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+	struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+	struct dl *dl = data;
+
+	mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+	if (!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+	    !tb[DEVLINK_ATTR_HEALTH_REPORTER])
+		return MNL_CB_ERROR;
+
+	pr_out_health(dl, tb);
+
+	return MNL_CB_OK;
+}
+
+static int cmd_health_show(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	uint16_t flags = NLM_F_REQUEST | NLM_F_ACK;
+	int err;
+
+	if (dl_argc(dl) == 0)
+		flags |= NLM_F_DUMP;
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_HEALTH_REPORTER_GET,
+			       flags);
+
+	if (dl_argc(dl) > 0) {
+		err = dl_argv_parse_put(nlh, dl,
+					DL_OPT_HANDLE |
+					DL_OPT_HEALTH_REPORTER_NAME, 0);
+		if (err)
+			return err;
+	}
+	pr_out_section_start(dl, "health");
+
+	err = _mnlg_socket_sndrcv(dl->nlg, nlh, cmd_health_show_cb, dl);
+	if (err)
+		return err;
+	pr_out_section_end(dl);
+	return err;
+}
+
+static void cmd_health_help(void)
+{
+	pr_err("Usage: devlink health show [ dev DEV reporter REPORTER_NAME ]\n");
+	pr_err("Usage: devlink health recover DEV reporter REPORTER_NAME\n");
+	pr_err("Usage: devlink health diagnose DEV reporter REPORTER_NAME\n");
+	pr_err("Usage: devlink health dump show DEV reporter REPORTER_NAME\n");
+	pr_err("Usage: devlink health dump clear DEV reporter REPORTER_NAME\n");
+	pr_err("Usage: devlink health set DEV reporter REPORTER_NAME NAME VALUE\n");
+}
+
+static int cmd_health(struct dl *dl)
+{
+	if (dl_argv_match(dl, "help")) {
+		cmd_health_help();
+		return 0;
+	} else if (dl_argv_match(dl, "show") ||
+		   dl_argv_match(dl, "list") || dl_no_arg(dl)) {
+		dl_arg_inc(dl);
+		return cmd_health_show(dl);
+	} else if (dl_argv_match(dl, "recover")) {
+		dl_arg_inc(dl);
+		return cmd_health_recover(dl);
+	} else if (dl_argv_match(dl, "diagnose")) {
+		dl_arg_inc(dl);
+		return cmd_health_diagnose(dl);
+	} else if (dl_argv_match(dl, "dump")) {
+		dl_arg_inc(dl);
+		if (dl_argv_match(dl, "show")) {
+			dl_arg_inc(dl);
+			return cmd_health_dump_show(dl);
+		} else if (dl_argv_match(dl, "clear")) {
+			dl_arg_inc(dl);
+			return cmd_health_dump_clear(dl);
+		}
+	} else if (dl_argv_match(dl, "set")) {
+		dl_arg_inc(dl);
+		return cmd_health_set_params(dl);
+	}
+
+	pr_err("Command \"%s\" not found\n", dl_argv(dl));
+	return -ENOENT;
+}
+
 static void help(void)
 {
 	pr_err("Usage: devlink [ OPTIONS ] OBJECT { COMMAND | help }\n"
 	       "       devlink [ -f[orce] ] -b[atch] filename\n"
-	       "where  OBJECT := { dev | port | sb | monitor | dpipe | resource | region }\n"
+	       "where  OBJECT := { dev | port | sb | monitor | dpipe | resource | region | health }\n"
 	       "       OPTIONS := { -V[ersion] | -n[o-nice-names] | -j[son] | -p[retty] | -v[erbose] }\n");
 }
 
@@ -5714,7 +6259,11 @@ static int dl_cmd(struct dl *dl, int argc, char **argv)
 	} else if (dl_argv_match(dl, "region")) {
 		dl_arg_inc(dl);
 		return cmd_region(dl);
+	} else if (dl_argv_match(dl, "health")) {
+		dl_arg_inc(dl);
+		return cmd_health(dl);
 	}
+
 	pr_err("Object \"%s\" not found\n", dl_argv(dl));
 	return -ENOENT;
 }
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index d51b59a7b8ee..bec76e94bc47 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -95,6 +95,12 @@ enum devlink_command {
 	DEVLINK_CMD_PORT_PARAM_DEL,
 
 	DEVLINK_CMD_INFO_GET,		/* can dump */
+	DEVLINK_CMD_HEALTH_REPORTER_GET,
+	DEVLINK_CMD_HEALTH_REPORTER_SET,
+	DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+	DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+	DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+	DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
 
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
@@ -302,6 +308,23 @@ enum devlink_attr {
 
 	DEVLINK_ATTR_SB_POOL_CELL_SIZE,		/* u32 */
 
+	DEVLINK_ATTR_FMSG,			/* nested */
+	DEVLINK_ATTR_FMSG_OBJ_NEST_START,	/* flag */
+	DEVLINK_ATTR_FMSG_PAIR_NEST_START,	/* flag */
+	DEVLINK_ATTR_FMSG_ARR_NEST_START,	/* flag */
+	DEVLINK_ATTR_FMSG_NEST_END,		/* flag */
+	DEVLINK_ATTR_FMSG_OBJ_NAME,		/* string */
+	DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE,	/* u8 */
+	DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA,	/* dynamic */
+
+	DEVLINK_ATTR_HEALTH_REPORTER,			/* nested */
+	DEVLINK_ATTR_HEALTH_REPORTER_NAME,		/* string */
+	DEVLINK_ATTR_HEALTH_REPORTER_STATE,		/* u8 */
+	DEVLINK_ATTR_HEALTH_REPORTER_ERR,		/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_RECOVER,		/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS,		/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,	/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,	/* u8 */
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/man/man8/devlink-health.8 b/man/man8/devlink-health.8
new file mode 100644
index 000000000000..2824d4d1bbf1
--- /dev/null
+++ b/man/man8/devlink-health.8
@@ -0,0 +1,176 @@
+.TH DEVLINK\-HEALTH 8 "27 Dec 2018" "iproute2" "Linux"
+.SH NAME
+devlink-health \- devlink health reporting and recovery
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B devlink
+.RI "[ " OPTIONS " ]"
+.B health
+.RI  " { " COMMAND " | "
+.BR help " }"
+.sp
+.ti -8
+.IR OPTIONS " := { "
+\fB\-V\fR[\fIersion\fR] }
+.ti -8
+.BR "devlink health show"
+.RI "[ "
+.RI "" DEV ""
+.BR " reporter "
+.RI ""REPORTER " ] "
+.ti -8
+.BR "devlink health recover"
+.RI "" DEV ""
+.BR "reporter"
+.RI "" REPORTER ""
+.ti -8
+.BR "devlink health diagnose"
+.RI "" DEV ""
+.BR "reporter"
+.RI "" REPORTER ""
+.ti -8
+.BR "devlink health dump show"
+.RI "" DEV ""
+.BR "reporter"
+.RI "" REPORTER ""
+.ti -8
+.BR "devlink health dump clear"
+.RI "" DEV ""
+.BR "reporter"
+.RI "" REPORTER ""
+.ti -8
+.BR "devlink health set"
+.RI "" DEV ""
+.BR "reporter"
+.RI "" REPORTER ""
+.RI "" NAME ""
+.RI "" VALUE ""
+.ti -8
+.B devlink health help
+.SH "DESCRIPTION"
+.SS devlink health show - Show status and configuration on all supported reporters on all devlink devices.
+.PP
+.I "DEV"
+- specifies the devlink device.
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+.SS devlink health recover - Initiate a recovery operation on a reporter.
+This action performs a recovery and increases the recoveries counter on success.
+.PP
+.I "DEV"
+- specifies the devlink device.
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+.SS devlink health diagnose - Retrieve diagnostics data on a reporter.
+.PP
+.I "DEV"
+- specifies the devlink device.
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+.SS devlink health dump show - Display the last saved dump.
+.PD 0
+.P
+Devlink health saves a single dump per reporter. If an dump is
+.P
+not already stored by the Devlink, this command will generate a new
+.P
+dump. The dump can be generated either automatically when a
+.P
+reporter reports on an error or manually at the user's request.
+.PD
+.PP
+.I "DEV"
+- specifies the devlink device.
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+.SS devlink health dump clear - Delete the saved dump.
+Deleting the saved dump enables a generation of a new dump on
+.PD 0
+.P
+the next "devlink health dump show" command.
+.PD
+.PP
+.I "DEV"
+- specifies the devlink device.
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+.SS devlink health set - Enable the user to configure:
+.PD 0
+1) grace_period [msec] - Time interval between auto recoveries.
+.P
+2) auto_recover [true/false] - Indicates whether the devlink should execute automatic recover on error.
+.PD
+.PP
+.I "DEV"
+- specifies the devlink device.
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+.SH "EXAMPLES"
+.PP
+devlink health show
+.RS 4
+pci/0000:00:09.0:
+  name tx
+  state healthy #err 1 #recover 1 last_dump_ts N/A
+  parameters:
+    grace period 600 auto_recover true
+.RE
+.PP
+devlink health recover pci/0000:00:09.0 reporter tx
+.RS 4
+Initiate recovery on tx reporter registered on pci/0000:00:09.0.
+.RE
+.PP
+devlink health diagnose pci/0000:00:09.0 reporter tx
+.RS 4
+.PD 0
+SQs:
+.P
+sqn: 4283 HW state: 1 stopped: 0
+.P
+sqn: 4288 HW state: 1 stopped: 0
+.P
+sqn: 4293 HW state: 1 stopped: 0
+.P
+sqn: 4298 HW state: 1 stopped: 0
+.PD
+.RE
+.PP
+devlink health dump show pci/0000:00:09.0 reporter tx
+.RS 4
+Display the last saved dump on tx reporter registered on pci/0000:00:09.0.
+.RE
+.PP
+devlink health dump clear pci/0000:00:09.0 reporter tx
+.RS 4
+Delete saved dump on tx reporter registered on pci/0000:00:09.0.
+.RE
+.PP
+devlink health set pci/0000:00:09.0 reporter tx grace_period 3500
+.RS 4
+Set time interval between auto recoveries to minimum of 3500 mSec on
+tx reporter registered on pci/0000:00:09.0.
+.RE
+.PP
+devlink health set pci/0000:00:09.0 reporter tx auto_recover false
+.RS 4
+Turn off auto recovery on tx reporter registered on pci/0000:00:09.0.
+.RE
+.SH SEE ALSO
+.BR devlink (8),
+.BR devlink-dev (8),
+.BR devlink-port (8),
+.BR devlink-region (8),
+.br
+
+.SH AUTHOR
+Aya Levin <ayal@...lanox.com>
diff --git a/man/man8/devlink.8 b/man/man8/devlink.8
index 8d527e7e1d60..13d4dcd908b3 100644
--- a/man/man8/devlink.8
+++ b/man/man8/devlink.8
@@ -7,7 +7,7 @@ devlink \- Devlink tool
 .in +8
 .ti -8
 .B devlink
-.RI "[ " OPTIONS " ] { " dev | port | monitor | sb | resource | region " } { " COMMAND " | "
+.RI "[ " OPTIONS " ] { " dev | port | monitor | sb | resource | region | health " } { " COMMAND " | "
 .BR help " }"
 .sp
 
@@ -78,6 +78,10 @@ Turn on verbose output.
 .B region
 - devlink address region access
 
+.TP
+.B health
+- devlink reporting and recovery
+
 .SS
 .I COMMAND
 
@@ -109,6 +113,7 @@ Exit status is 0 if command was successful or a positive integer upon failure.
 .BR devlink-sb (8),
 .BR devlink-resource (8),
 .BR devlink-region (8),
+.BR devlink-health (8),
 .br
 
 .SH REPORTING BUGS
-- 
2.14.1

Powered by blists - more mailing lists