summaryrefslogtreecommitdiff
path: root/net/devlink/health.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/devlink/health.c')
-rw-r--r--net/devlink/health.c228
1 files changed, 169 insertions, 59 deletions
diff --git a/net/devlink/health.c b/net/devlink/health.c
index b8d3084e6fe0..136a67c36a20 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -60,6 +60,7 @@ struct devlink_health_reporter {
struct devlink_port *devlink_port;
struct devlink_fmsg *dump_fmsg;
u64 graceful_period;
+ u64 burst_period;
bool auto_recover;
bool auto_dump;
u8 health_state;
@@ -108,11 +109,14 @@ devlink_port_health_reporter_find_by_name(struct devlink_port *devlink_port,
static struct devlink_health_reporter *
__devlink_health_reporter_create(struct devlink *devlink,
const struct devlink_health_reporter_ops *ops,
- u64 graceful_period, void *priv)
+ void *priv)
{
struct devlink_health_reporter *reporter;
- if (WARN_ON(graceful_period && !ops->recover))
+ if (WARN_ON(ops->default_graceful_period && !ops->recover))
+ return ERR_PTR(-EINVAL);
+
+ if (WARN_ON(ops->default_burst_period && !ops->default_graceful_period))
return ERR_PTR(-EINVAL);
reporter = kzalloc(sizeof(*reporter), GFP_KERNEL);
@@ -122,7 +126,8 @@ __devlink_health_reporter_create(struct devlink *devlink,
reporter->priv = priv;
reporter->ops = ops;
reporter->devlink = devlink;
- reporter->graceful_period = graceful_period;
+ reporter->graceful_period = ops->default_graceful_period;
+ reporter->burst_period = ops->default_burst_period;
reporter->auto_recover = !!ops->recover;
reporter->auto_dump = !!ops->dump;
return reporter;
@@ -134,13 +139,12 @@ __devlink_health_reporter_create(struct devlink *devlink,
*
* @port: devlink_port to which health reports will relate
* @ops: devlink health reporter ops
- * @graceful_period: min time (in msec) between recovery attempts
* @priv: driver priv pointer
*/
struct devlink_health_reporter *
devl_port_health_reporter_create(struct devlink_port *port,
const struct devlink_health_reporter_ops *ops,
- u64 graceful_period, void *priv)
+ void *priv)
{
struct devlink_health_reporter *reporter;
@@ -150,8 +154,7 @@ devl_port_health_reporter_create(struct devlink_port *port,
ops->name))
return ERR_PTR(-EEXIST);
- reporter = __devlink_health_reporter_create(port->devlink, ops,
- graceful_period, priv);
+ reporter = __devlink_health_reporter_create(port->devlink, ops, priv);
if (IS_ERR(reporter))
return reporter;
@@ -164,14 +167,13 @@ EXPORT_SYMBOL_GPL(devl_port_health_reporter_create);
struct devlink_health_reporter *
devlink_port_health_reporter_create(struct devlink_port *port,
const struct devlink_health_reporter_ops *ops,
- u64 graceful_period, void *priv)
+ void *priv)
{
struct devlink_health_reporter *reporter;
struct devlink *devlink = port->devlink;
devl_lock(devlink);
- reporter = devl_port_health_reporter_create(port, ops,
- graceful_period, priv);
+ reporter = devl_port_health_reporter_create(port, ops, priv);
devl_unlock(devlink);
return reporter;
}
@@ -182,13 +184,12 @@ EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create);
*
* @devlink: devlink instance which the health reports will relate
* @ops: devlink health reporter ops
- * @graceful_period: min time (in msec) between recovery attempts
* @priv: driver priv pointer
*/
struct devlink_health_reporter *
devl_health_reporter_create(struct devlink *devlink,
const struct devlink_health_reporter_ops *ops,
- u64 graceful_period, void *priv)
+ void *priv)
{
struct devlink_health_reporter *reporter;
@@ -197,8 +198,7 @@ devl_health_reporter_create(struct devlink *devlink,
if (devlink_health_reporter_find_by_name(devlink, ops->name))
return ERR_PTR(-EEXIST);
- reporter = __devlink_health_reporter_create(devlink, ops,
- graceful_period, priv);
+ reporter = __devlink_health_reporter_create(devlink, ops, priv);
if (IS_ERR(reporter))
return reporter;
@@ -210,13 +210,12 @@ EXPORT_SYMBOL_GPL(devl_health_reporter_create);
struct devlink_health_reporter *
devlink_health_reporter_create(struct devlink *devlink,
const struct devlink_health_reporter_ops *ops,
- u64 graceful_period, void *priv)
+ void *priv)
{
struct devlink_health_reporter *reporter;
devl_lock(devlink);
- reporter = devl_health_reporter_create(devlink, ops,
- graceful_period, priv);
+ reporter = devl_health_reporter_create(devlink, ops, priv);
devl_unlock(devlink);
return reporter;
}
@@ -298,6 +297,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg,
reporter->graceful_period))
goto reporter_nest_cancel;
if (reporter->ops->recover &&
+ devlink_nl_put_u64(msg, DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD,
+ reporter->burst_period))
+ goto reporter_nest_cancel;
+ if (reporter->ops->recover &&
nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,
reporter->auto_recover))
goto reporter_nest_cancel;
@@ -462,16 +465,33 @@ int devlink_nl_health_reporter_set_doit(struct sk_buff *skb,
if (!reporter->ops->recover &&
(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] ||
- info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]))
+ info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] ||
+ info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD]))
return -EOPNOTSUPP;
if (!reporter->ops->dump &&
info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP])
return -EOPNOTSUPP;
- if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD])
+ if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) {
reporter->graceful_period =
nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]);
+ if (!reporter->graceful_period)
+ reporter->burst_period = 0;
+ }
+
+ if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD]) {
+ u64 burst_period =
+ nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD]);
+
+ if (!reporter->graceful_period && burst_period) {
+ NL_SET_ERR_MSG_MOD(info->extack,
+ "Cannot set burst period without a grace period.");
+ return -EINVAL;
+ }
+
+ reporter->burst_period = burst_period;
+ }
if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])
reporter->auto_recover =
@@ -514,11 +534,25 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
devlink_nl_notify_send_desc(devlink, msg, &desc);
}
+static bool
+devlink_health_reporter_in_burst(struct devlink_health_reporter *reporter)
+{
+ unsigned long burst_threshold = reporter->last_recovery_ts +
+ msecs_to_jiffies(reporter->burst_period);
+
+ return time_is_after_jiffies(burst_threshold);
+}
+
void
devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter)
{
reporter->recovery_count++;
- reporter->last_recovery_ts = jiffies;
+ if (!devlink_health_reporter_in_burst(reporter))
+ /* When burst period is set, last_recovery_ts marks the first
+ * recovery within the burst period, not necessarily the last
+ * one.
+ */
+ reporter->last_recovery_ts = jiffies;
}
EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done);
@@ -592,12 +626,37 @@ dump_err:
return err;
}
+static bool
+devlink_health_recover_abort(struct devlink_health_reporter *reporter,
+ enum devlink_health_reporter_state prev_state)
+{
+ unsigned long recover_ts_threshold;
+
+ if (!reporter->auto_recover)
+ return false;
+
+ /* abort if the previous error wasn't recovered */
+ if (prev_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY)
+ return true;
+
+ if (devlink_health_reporter_in_burst(reporter))
+ return false;
+
+ recover_ts_threshold = reporter->last_recovery_ts +
+ msecs_to_jiffies(reporter->burst_period) +
+ msecs_to_jiffies(reporter->graceful_period);
+ if (reporter->last_recovery_ts && reporter->recovery_count &&
+ time_is_after_jiffies(recover_ts_threshold))
+ return true;
+
+ return false;
+}
+
int devlink_health_report(struct devlink_health_reporter *reporter,
const char *msg, void *priv_ctx)
{
enum devlink_health_reporter_state prev_health_state;
struct devlink *devlink = reporter->devlink;
- unsigned long recover_ts_threshold;
int ret;
/* write a log message of the current error */
@@ -608,13 +667,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR;
devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
- /* abort if the previous error wasn't recovered */
- recover_ts_threshold = reporter->last_recovery_ts +
- msecs_to_jiffies(reporter->graceful_period);
- if (reporter->auto_recover &&
- (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY ||
- (reporter->last_recovery_ts && reporter->recovery_count &&
- time_is_after_jiffies(recover_ts_threshold)))) {
+ if (devlink_health_recover_abort(reporter, prev_health_state)) {
trace_devlink_health_recover_aborted(devlink,
reporter->ops->name,
reporter->health_state,
@@ -735,7 +788,7 @@ static void devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name)
return;
}
- item->nla_type = NLA_NUL_STRING;
+ item->nla_type = DEVLINK_VAR_ATTR_TYPE_NUL_STRING;
item->len = strlen(name) + 1;
item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME;
memcpy(&item->value, name, item->len);
@@ -822,32 +875,37 @@ static void devlink_fmsg_put_value(struct devlink_fmsg *fmsg,
static void devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value)
{
devlink_fmsg_err_if_binary(fmsg);
- devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG);
+ devlink_fmsg_put_value(fmsg, &value, sizeof(value),
+ DEVLINK_VAR_ATTR_TYPE_FLAG);
}
static void devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value)
{
devlink_fmsg_err_if_binary(fmsg);
- devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8);
+ devlink_fmsg_put_value(fmsg, &value, sizeof(value),
+ DEVLINK_VAR_ATTR_TYPE_U8);
}
void devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value)
{
devlink_fmsg_err_if_binary(fmsg);
- devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32);
+ devlink_fmsg_put_value(fmsg, &value, sizeof(value),
+ DEVLINK_VAR_ATTR_TYPE_U32);
}
EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put);
static void devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value)
{
devlink_fmsg_err_if_binary(fmsg);
- devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64);
+ devlink_fmsg_put_value(fmsg, &value, sizeof(value),
+ DEVLINK_VAR_ATTR_TYPE_U64);
}
void devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value)
{
devlink_fmsg_err_if_binary(fmsg);
- devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, NLA_NUL_STRING);
+ devlink_fmsg_put_value(fmsg, value, strlen(value) + 1,
+ DEVLINK_VAR_ATTR_TYPE_NUL_STRING);
}
EXPORT_SYMBOL_GPL(devlink_fmsg_string_put);
@@ -857,7 +915,8 @@ void devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value,
if (!fmsg->err && !fmsg->putting_binary)
fmsg->err = -EINVAL;
- devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY);
+ devlink_fmsg_put_value(fmsg, value, value_len,
+ DEVLINK_VAR_ATTR_TYPE_BINARY);
}
EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put);
@@ -928,43 +987,26 @@ void devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name,
EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put);
static int
-devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb)
-{
- switch (msg->nla_type) {
- case NLA_FLAG:
- case NLA_U8:
- case NLA_U32:
- case NLA_U64:
- case NLA_NUL_STRING:
- case NLA_BINARY:
- return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE,
- msg->nla_type);
- default:
- return -EINVAL;
- }
-}
-
-static int
devlink_fmsg_item_fill_data(struct devlink_fmsg_item *msg, struct sk_buff *skb)
{
int attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA;
u8 tmp;
switch (msg->nla_type) {
- case NLA_FLAG:
+ case DEVLINK_VAR_ATTR_TYPE_FLAG:
/* Always provide flag data, regardless of its value */
tmp = *(bool *)msg->value;
return nla_put_u8(skb, attrtype, tmp);
- case NLA_U8:
+ case DEVLINK_VAR_ATTR_TYPE_U8:
return nla_put_u8(skb, attrtype, *(u8 *)msg->value);
- case NLA_U32:
+ case DEVLINK_VAR_ATTR_TYPE_U32:
return nla_put_u32(skb, attrtype, *(u32 *)msg->value);
- case NLA_U64:
+ case DEVLINK_VAR_ATTR_TYPE_U64:
return devlink_nl_put_u64(skb, attrtype, *(u64 *)msg->value);
- case NLA_NUL_STRING:
+ case DEVLINK_VAR_ATTR_TYPE_NUL_STRING:
return nla_put_string(skb, attrtype, (char *)&msg->value);
- case NLA_BINARY:
+ case DEVLINK_VAR_ATTR_TYPE_BINARY:
return nla_put(skb, attrtype, msg->len, (void *)&msg->value);
default:
return -EINVAL;
@@ -998,7 +1040,8 @@ devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb,
err = nla_put_flag(skb, item->attrtype);
break;
case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA:
- err = devlink_fmsg_item_fill_type(item, skb);
+ err = nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE,
+ item->nla_type);
if (err)
break;
err = devlink_fmsg_item_fill_data(item, skb);
@@ -1238,3 +1281,70 @@ int devlink_nl_health_reporter_test_doit(struct sk_buff *skb,
return reporter->ops->test(reporter, info->extack);
}
+
+/**
+ * devlink_fmsg_dump_skb - Dump sk_buffer structure
+ * @fmsg: devlink formatted message pointer
+ * @skb: pointer to skb
+ *
+ * Dump diagnostic information about sk_buff structure, like headroom, length,
+ * tailroom, MAC, etc.
+ */
+void devlink_fmsg_dump_skb(struct devlink_fmsg *fmsg, const struct sk_buff *skb)
+{
+ struct skb_shared_info *sh = skb_shinfo(skb);
+ struct sock *sk = skb->sk;
+ bool has_mac, has_trans;
+
+ has_mac = skb_mac_header_was_set(skb);
+ has_trans = skb_transport_header_was_set(skb);
+
+ devlink_fmsg_pair_nest_start(fmsg, "skb");
+ devlink_fmsg_obj_nest_start(fmsg);
+ devlink_fmsg_put(fmsg, "actual len", skb->len);
+ devlink_fmsg_put(fmsg, "head len", skb_headlen(skb));
+ devlink_fmsg_put(fmsg, "data len", skb->data_len);
+ devlink_fmsg_put(fmsg, "tail len", skb_tailroom(skb));
+ devlink_fmsg_put(fmsg, "MAC", has_mac ? skb->mac_header : -1);
+ devlink_fmsg_put(fmsg, "MAC len",
+ has_mac ? skb_mac_header_len(skb) : -1);
+ devlink_fmsg_put(fmsg, "network hdr", skb->network_header);
+ devlink_fmsg_put(fmsg, "network hdr len",
+ has_trans ? skb_network_header_len(skb) : -1);
+ devlink_fmsg_put(fmsg, "transport hdr",
+ has_trans ? skb->transport_header : -1);
+ devlink_fmsg_put(fmsg, "csum", (__force u32)skb->csum);
+ devlink_fmsg_put(fmsg, "csum_ip_summed", (u8)skb->ip_summed);
+ devlink_fmsg_put(fmsg, "csum_complete_sw", !!skb->csum_complete_sw);
+ devlink_fmsg_put(fmsg, "csum_valid", !!skb->csum_valid);
+ devlink_fmsg_put(fmsg, "csum_level", (u8)skb->csum_level);
+ devlink_fmsg_put(fmsg, "sw_hash", !!skb->sw_hash);
+ devlink_fmsg_put(fmsg, "l4_hash", !!skb->l4_hash);
+ devlink_fmsg_put(fmsg, "proto", ntohs(skb->protocol));
+ devlink_fmsg_put(fmsg, "pkt_type", (u8)skb->pkt_type);
+ devlink_fmsg_put(fmsg, "iif", skb->skb_iif);
+
+ if (sk) {
+ devlink_fmsg_pair_nest_start(fmsg, "sk");
+ devlink_fmsg_obj_nest_start(fmsg);
+ devlink_fmsg_put(fmsg, "family", sk->sk_type);
+ devlink_fmsg_put(fmsg, "type", sk->sk_type);
+ devlink_fmsg_put(fmsg, "proto", sk->sk_protocol);
+ devlink_fmsg_obj_nest_end(fmsg);
+ devlink_fmsg_pair_nest_end(fmsg);
+ }
+
+ devlink_fmsg_obj_nest_end(fmsg);
+ devlink_fmsg_pair_nest_end(fmsg);
+
+ devlink_fmsg_pair_nest_start(fmsg, "shinfo");
+ devlink_fmsg_obj_nest_start(fmsg);
+ devlink_fmsg_put(fmsg, "tx_flags", sh->tx_flags);
+ devlink_fmsg_put(fmsg, "nr_frags", sh->nr_frags);
+ devlink_fmsg_put(fmsg, "gso_size", sh->gso_size);
+ devlink_fmsg_put(fmsg, "gso_type", sh->gso_type);
+ devlink_fmsg_put(fmsg, "gso_segs", sh->gso_segs);
+ devlink_fmsg_obj_nest_end(fmsg);
+ devlink_fmsg_pair_nest_end(fmsg);
+}
+EXPORT_SYMBOL_GPL(devlink_fmsg_dump_skb);