net: mana: Add standard counter rx_missed_errors

Report standard counter stats->rx_missed_errors
using hc_rx_discards_no_wqe from the hardware.

Add a global workqueue to periodically run
mana_query_gf_stats every 2 seconds to get the latest
info in eth_stats and define a driver capability flag
to notify hardware of the periodic queries.

To avoid repeated failures and log flooding, the workqueue
is not rescheduled if mana_query_gf_stats fails on HWC timeout
error and the stats are reset to 0. Other errors are transient
which will not need a VF reset for recovery.

Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/1763120599-6331-3-git-send-email-ernis@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 33 insertions, 3 deletions

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index d8ce4402c696..13f47be7aca6 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -534,6 +534,11 @@ static void mana_get_stats64(struct net_device *ndev,
 
 	netdev_stats_to_stats64(st, &ndev->stats);
 
+	if (apc->ac->hwc_timeout_occurred)
+		netdev_warn_once(ndev, "HWC timeout occurred\n");
+
+	st->rx_missed_errors = apc->ac->hc_stats.hc_rx_discards_no_wqe;
+
 	for (q = 0; q < num_queues; q++) {
 		rx_stats = &apc->rxqs[q]->stats;
 
@@ -2809,7 +2814,7 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx,
 	return 0;
 }
 
-void mana_query_gf_stats(struct mana_context *ac)
+int mana_query_gf_stats(struct mana_context *ac)
 {
 	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 	struct mana_query_gf_stat_resp resp = {};
@@ -2852,14 +2857,14 @@ void mana_query_gf_stats(struct mana_context *ac)
 				sizeof(resp));
 	if (err) {
 		dev_err(dev, "Failed to query GF stats: %d\n", err);
-		return;
+		return err;
 	}
 	err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT,
 				   sizeof(resp));
 	if (err || resp.hdr.status) {
 		dev_err(dev, "Failed to query GF stats: %d, 0x%x\n", err,
 			resp.hdr.status);
-		return;
+		return err;
 	}
 
 	ac->hc_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe;
@@ -2894,6 +2899,8 @@ void mana_query_gf_stats(struct mana_context *ac)
 	ac->hc_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts;
 	ac->hc_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes;
 	ac->hc_stats.hc_tx_err_gdma = resp.tx_err_gdma;
+
+	return 0;
 }
 
 void mana_query_phy_stats(struct mana_port_context *apc)
@@ -3428,6 +3435,24 @@ int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type even
 	return 0;
 }
 
+#define MANA_GF_STATS_PERIOD (2 * HZ)
+
+static void mana_gf_stats_work_handler(struct work_struct *work)
+{
+	struct mana_context *ac =
+		container_of(to_delayed_work(work), struct mana_context, gf_stats_work);
+	int err;
+
+	err = mana_query_gf_stats(ac);
+	if (err == -ETIMEDOUT) {
+		/* HWC timeout detected - reset stats and stop rescheduling */
+		ac->hwc_timeout_occurred = true;
+		memset(&ac->hc_stats, 0, sizeof(ac->hc_stats));
+		return;
+	}
+	schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD);
+}
+
 int mana_probe(struct gdma_dev *gd, bool resuming)
 {
 	struct gdma_context *gc = gd->gdma_context;
@@ -3520,6 +3545,10 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 	}
 
 	err = add_adev(gd, "eth");
+
+	INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler);
+	schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD);
+
 out:
 	if (err) {
 		mana_remove(gd, false);
@@ -3544,6 +3573,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 	int i;
 
 	disable_work_sync(&ac->link_change_work);
+	cancel_delayed_work_sync(&ac->gf_stats_work);
 
 	/* adev currently doesn't support suspending, always remove it */
 	if (gd->adev)