ethtool: linkstate: add a statistic for PHY down events

The previous attempt to augment carrier_down (see Link)
was not met with much enthusiasm so let's do the simple
thing of exposing what some devices already maintain.
Add a common ethtool statistic for link going down.
Currently users have to maintain per-driver mapping
to extract the right stat from the vendor-specific ethtool -S
stats. carrier_down does not fit the bill because it counts
a lot of software related false positives.

Add the statistic to the extended link state API to steer
vendors towards implementing all of it.

Implement for bnxt and all Linux-controlled PHYs. mlx5 and (possibly)
enic also have a counter for this but I leave the implementation
to their maintainers.

Link: https://lore.kernel.org/r/[email protected]
Reviewed-by: Florian Fainelli <[email protected]>
Reviewed-by: Michael Chan <[email protected]>
Reviewed-by: Andrew Lunn <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>

Documentation/networking/ethtool-netlink.rst

@@ -491,6 +491,7 @@ Kernel response contents:
   ``ETHTOOL_A_LINKSTATE_SQI_MAX``       u32     Max support SQI value
   ``ETHTOOL_A_LINKSTATE_EXT_STATE``     u8      link extended state
   ``ETHTOOL_A_LINKSTATE_EXT_SUBSTATE``  u8      link extended substate
+  ``ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT``  u32     count of link down events
   ====================================  ======  ============================
 
 For most NIC drivers, the value of ``ETHTOOL_A_LINKSTATE_LINK`` returns

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c

@@ -4112,6 +4112,20 @@ static void bnxt_get_rmon_stats(struct net_device *dev,
 	*ranges = bnxt_rmon_ranges;
 }
 
+static void bnxt_get_link_ext_stats(struct net_device *dev,
+				    struct ethtool_link_ext_stats *stats)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	u64 *rx;
+
+	if (BNXT_VF(bp) || !(bp->flags & BNXT_FLAG_PORT_STATS_EXT))
+		return;
+
+	rx = bp->rx_port_stats_ext.sw_stats;
+	stats->link_down_events =
+		*(rx + BNXT_RX_STATS_EXT_OFFSET(link_down_events));
+}
+
 void bnxt_ethtool_free(struct bnxt *bp)
 {
 	kfree(bp->test_info);
@@ -4161,6 +4175,7 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_eeprom             = bnxt_get_eeprom,
 	.set_eeprom		= bnxt_set_eeprom,
 	.get_link		= bnxt_get_link,
+	.get_link_ext_stats	= bnxt_get_link_ext_stats,
 	.get_eee		= bnxt_get_eee,
 	.set_eee		= bnxt_set_eee,
 	.get_module_info	= bnxt_get_module_info,

drivers/net/phy/phy.c

@@ -67,6 +67,7 @@ static void phy_link_down(struct phy_device *phydev)
 {
 	phydev->phy_link_change(phydev, false);
 	phy_led_trigger_change_speed(phydev);
+	WRITE_ONCE(phydev->link_down_events, phydev->link_down_events + 1);
 }
 
 static const char *phy_pause_str(struct phy_device *phydev)

include/linux/ethtool.h

@@ -125,6 +125,20 @@ struct ethtool_link_ext_state_info {
 	};
 };
 
+struct ethtool_link_ext_stats {
+	/* Custom Linux statistic for PHY level link down events.
+	 * In a simpler world it should be equal to netdev->carrier_down_count
+	 * unfortunately netdev also counts local reconfigurations which don't
+	 * actually take the physical link down, not to mention NC-SI which,
+	 * if present, keeps the link up regardless of host state.
+	 * This statistic counts when PHY _actually_ went down, or lost link.
+	 *
+	 * Note that we need u64 for ethtool_stats_init() and comparisons
+	 * to ETHTOOL_STAT_NOT_SET, but only u32 is exposed to the user.
+	 */
+	u64 link_down_events;
+};
+
 /**
  * ethtool_rxfh_indir_default - get default value for RX flow hash indirection
  * @index: Index in RX flow hash indirection table
@@ -481,6 +495,7 @@ struct ethtool_module_power_mode_params {
  *	do not attach ext_substate attribute to netlink message). If link_ext_state
  *	and link_ext_substate are unknown, return -ENODATA. If not implemented,
  *	link_ext_state and link_ext_substate will not be sent to userspace.
+ * @get_link_ext_stats: Read extra link-related counters.
  * @get_eeprom_len: Read range of EEPROM addresses for validation of
  *	@get_eeprom and @set_eeprom requests.
  *	Returns 0 if device does not support EEPROM access.
@@ -652,6 +667,8 @@ struct ethtool_ops {
 	u32	(*get_link)(struct net_device *);
 	int	(*get_link_ext_state)(struct net_device *,
 				      struct ethtool_link_ext_state_info *);
+	void	(*get_link_ext_stats)(struct net_device *dev,
+				      struct ethtool_link_ext_stats *stats);
 	int	(*get_eeprom_len)(struct net_device *);
 	int	(*get_eeprom)(struct net_device *,
 			      struct ethtool_eeprom *, u8 *);

include/linux/phy.h

@@ -600,6 +600,7 @@ struct macsec_ops;
  * @psec: Pointer to Power Sourcing Equipment control struct
  * @lock:  Mutex for serialization access to PHY
  * @state_queue: Work queue for state machine
+ * @link_down_events: Number of times link was lost
  * @shared: Pointer to private data shared by phys in one package
  * @priv: Pointer to driver private data
  *
@@ -723,6 +724,8 @@ struct phy_device {
 
 	int pma_extable;
 
+	unsigned int link_down_events;
+
 	void (*phy_link_change)(struct phy_device *phydev, bool up);
 	void (*adjust_link)(struct net_device *dev);
 

include/uapi/linux/ethtool_netlink.h

@@ -262,6 +262,7 @@ enum {
 	ETHTOOL_A_LINKSTATE_SQI_MAX,		/* u32 */
 	ETHTOOL_A_LINKSTATE_EXT_STATE,		/* u8 */
 	ETHTOOL_A_LINKSTATE_EXT_SUBSTATE,	/* u8 */
+	ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT,	/* u32 */
 
 	/* add new constants above here */
 	__ETHTOOL_A_LINKSTATE_CNT,

net/ethtool/linkstate.c

@@ -13,6 +13,7 @@ struct linkstate_reply_data {
 	int					link;
 	int					sqi;
 	int					sqi_max;
+	struct ethtool_link_ext_stats		link_stats;
 	bool					link_ext_state_provided;
 	struct ethtool_link_ext_state_info	ethtool_link_ext_state_info;
 };
@@ -22,7 +23,7 @@ struct linkstate_reply_data {
 
 const struct nla_policy ethnl_linkstate_get_policy[] = {
 	[ETHTOOL_A_LINKSTATE_HEADER]		=
-		NLA_POLICY_NESTED(ethnl_header_policy),
+		NLA_POLICY_NESTED(ethnl_header_policy_stats),
 };
 
 static int linkstate_get_sqi(struct net_device *dev)
@@ -107,6 +108,19 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base,
 			goto out;
 	}
 
+	ethtool_stats_init((u64 *)&data->link_stats,
+			   sizeof(data->link_stats) / 8);
+
+	if (req_base->flags & ETHTOOL_FLAG_STATS) {
+		if (dev->phydev)
+			data->link_stats.link_down_events =
+				READ_ONCE(dev->phydev->link_down_events);
+
+		if (dev->ethtool_ops->get_link_ext_stats)
+			dev->ethtool_ops->get_link_ext_stats(dev,
+							     &data->link_stats);
+	}
+
 	ret = 0;
 out:
 	ethnl_ops_complete(dev);
@@ -134,6 +148,9 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base,
 	if (data->ethtool_link_ext_state_info.__link_ext_substate)
 		len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_SUBSTATE */
 
+	if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET)
+		len += nla_total_size(sizeof(u32));
+
 	return len;
 }
 
@@ -166,6 +183,11 @@ static int linkstate_fill_reply(struct sk_buff *skb,
 			return -EMSGSIZE;
 	}
 
+	if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET)
+		if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT,
+				data->link_stats.link_down_events))
+			return -EMSGSIZE;
+
 	return 0;
 }