Merge branch 'gve-stats-reporting-fixes'

Max Yuan says:

====================
gve: Stats reporting fixes

This series addresses two issues related to statistics in the gve driver.

The first patch fixes a memory corruption issue that occurs when resizing
the stats region during queue count changes. By allocating the maximum
possible size upfront and aligning offset calculations with the NIC,
we ensure stability and accuracy across reconfigurations.

The second patch fixes the 'rx_dropped' counter by removing allocation
failures and incorporating XDP transmit and redirect errors to provide
a more accurate representation of dropped packets.
====================

Link: https://patch.msgid.link/20260202193925.3106272-1-hramamurthy@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 53 insertions, 28 deletions

diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index 311b106160b2..66ddc4413f8d 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -152,11 +152,13 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	u64 tmp_rx_pkts, tmp_rx_hsplit_pkt, tmp_rx_bytes, tmp_rx_hsplit_bytes,
 		tmp_rx_skb_alloc_fail, tmp_rx_buf_alloc_fail,
 		tmp_rx_desc_err_dropped_pkt, tmp_rx_hsplit_unsplit_pkt,
-		tmp_tx_pkts, tmp_tx_bytes;
+		tmp_tx_pkts, tmp_tx_bytes,
+		tmp_xdp_tx_errors, tmp_xdp_redirect_errors;
 	u64 rx_buf_alloc_fail, rx_desc_err_dropped_pkt, rx_hsplit_unsplit_pkt,
 		rx_pkts, rx_hsplit_pkt, rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes,
-		tx_dropped;
-	int stats_idx, base_stats_idx, max_stats_idx;
+		tx_dropped, xdp_tx_errors, xdp_redirect_errors;
+	int rx_base_stats_idx, max_rx_stats_idx, max_tx_stats_idx;
+	int stats_idx, stats_region_len, nic_stats_len;
 	struct stats *report_stats;
 	int *rx_qid_to_stats_idx;
 	int *tx_qid_to_stats_idx;
@@ -198,6 +200,7 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	for (rx_pkts = 0, rx_bytes = 0, rx_hsplit_pkt = 0,
 	     rx_skb_alloc_fail = 0, rx_buf_alloc_fail = 0,
 	     rx_desc_err_dropped_pkt = 0, rx_hsplit_unsplit_pkt = 0,
+	     xdp_tx_errors = 0, xdp_redirect_errors = 0,
 	     ring = 0;
 	     ring < priv->rx_cfg.num_queues; ring++) {
 		if (priv->rx) {
@@ -215,6 +218,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 					rx->rx_desc_err_dropped_pkt;
 				tmp_rx_hsplit_unsplit_pkt =
 					rx->rx_hsplit_unsplit_pkt;
+				tmp_xdp_tx_errors = rx->xdp_tx_errors;
+				tmp_xdp_redirect_errors =
+					rx->xdp_redirect_errors;
 			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
 						       start));
 			rx_pkts += tmp_rx_pkts;
@@ -224,6 +230,8 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			rx_buf_alloc_fail += tmp_rx_buf_alloc_fail;
 			rx_desc_err_dropped_pkt += tmp_rx_desc_err_dropped_pkt;
 			rx_hsplit_unsplit_pkt += tmp_rx_hsplit_unsplit_pkt;
+			xdp_tx_errors += tmp_xdp_tx_errors;
+			xdp_redirect_errors += tmp_xdp_redirect_errors;
 		}
 	}
 	for (tx_pkts = 0, tx_bytes = 0, tx_dropped = 0, ring = 0;
@@ -249,8 +257,8 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = rx_bytes;
 	data[i++] = tx_bytes;
 	/* total rx dropped packets */
-	data[i++] = rx_skb_alloc_fail + rx_buf_alloc_fail +
-		    rx_desc_err_dropped_pkt;
+	data[i++] = rx_skb_alloc_fail + rx_desc_err_dropped_pkt +
+		    xdp_tx_errors + xdp_redirect_errors;
 	data[i++] = tx_dropped;
 	data[i++] = priv->tx_timeo_cnt;
 	data[i++] = rx_skb_alloc_fail;
@@ -265,20 +273,38 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = priv->stats_report_trigger_cnt;
 	i = GVE_MAIN_STATS_LEN;
 
-	/* For rx cross-reporting stats, start from nic rx stats in report */
-	base_stats_idx = GVE_TX_STATS_REPORT_NUM * num_tx_queues +
-		GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues;
-	/* The boundary between driver stats and NIC stats shifts if there are
-	 * stopped queues.
-	 */
-	base_stats_idx += NIC_RX_STATS_REPORT_NUM * num_stopped_rxqs +
-		NIC_TX_STATS_REPORT_NUM * num_stopped_txqs;
-	max_stats_idx = NIC_RX_STATS_REPORT_NUM *
-		(priv->rx_cfg.num_queues - num_stopped_rxqs) +
-		base_stats_idx;
+	rx_base_stats_idx = 0;
+	max_rx_stats_idx = 0;
+	max_tx_stats_idx = 0;
+	stats_region_len = priv->stats_report_len -
+				sizeof(struct gve_stats_report);
+	nic_stats_len = (NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues +
+		NIC_TX_STATS_REPORT_NUM * num_tx_queues) * sizeof(struct stats);
+	if (unlikely((stats_region_len -
+				nic_stats_len) % sizeof(struct stats))) {
+		net_err_ratelimited("Starting index of NIC stats should be multiple of stats size");
+	} else {
+		/* For rx cross-reporting stats,
+		 * start from nic rx stats in report
+		 */
+		rx_base_stats_idx = (stats_region_len - nic_stats_len) /
+							sizeof(struct stats);
+		/* The boundary between driver stats and NIC stats
+		 * shifts if there are stopped queues
+		 */
+		rx_base_stats_idx += NIC_RX_STATS_REPORT_NUM *
+			num_stopped_rxqs + NIC_TX_STATS_REPORT_NUM *
+			num_stopped_txqs;
+		max_rx_stats_idx = NIC_RX_STATS_REPORT_NUM *
+			(priv->rx_cfg.num_queues - num_stopped_rxqs) +
+			rx_base_stats_idx;
+		max_tx_stats_idx = NIC_TX_STATS_REPORT_NUM *
+			(num_tx_queues - num_stopped_txqs) +
+			max_rx_stats_idx;
+	}
 	/* Preprocess the stats report for rx, map queue id to start index */
 	skip_nic_stats = false;
-	for (stats_idx = base_stats_idx; stats_idx < max_stats_idx;
+	for (stats_idx = rx_base_stats_idx; stats_idx < max_rx_stats_idx;
 		stats_idx += NIC_RX_STATS_REPORT_NUM) {
 		u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name);
 		u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id);
@@ -311,6 +337,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 				tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail;
 				tmp_rx_desc_err_dropped_pkt =
 					rx->rx_desc_err_dropped_pkt;
+				tmp_xdp_tx_errors = rx->xdp_tx_errors;
+				tmp_xdp_redirect_errors =
+					rx->xdp_redirect_errors;
 			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
 						       start));
 			data[i++] = tmp_rx_bytes;
@@ -321,8 +350,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			data[i++] = rx->rx_frag_alloc_cnt;
 			/* rx dropped packets */
 			data[i++] = tmp_rx_skb_alloc_fail +
-				tmp_rx_buf_alloc_fail +
-				tmp_rx_desc_err_dropped_pkt;
+				    tmp_rx_desc_err_dropped_pkt +
+				    tmp_xdp_tx_errors +
+				    tmp_xdp_redirect_errors;
 			data[i++] = rx->rx_copybreak_pkt;
 			data[i++] = rx->rx_copied_pkt;
 			/* stats from NIC */
@@ -354,14 +384,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 		i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS;
 	}
 
-	/* For tx cross-reporting stats, start from nic tx stats in report */
-	base_stats_idx = max_stats_idx;
-	max_stats_idx = NIC_TX_STATS_REPORT_NUM *
-		(num_tx_queues - num_stopped_txqs) +
-		max_stats_idx;
-	/* Preprocess the stats report for tx, map queue id to start index */
 	skip_nic_stats = false;
-	for (stats_idx = base_stats_idx; stats_idx < max_stats_idx;
+	/* NIC TX stats start right after NIC RX stats */
+	for (stats_idx = max_rx_stats_idx; stats_idx < max_tx_stats_idx;
 		stats_idx += NIC_TX_STATS_REPORT_NUM) {
 		u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name);
 		u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id);
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 52c5e4942cd4..dbc84de39b70 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -283,9 +283,9 @@ static int gve_alloc_stats_report(struct gve_priv *priv)
 	int tx_stats_num, rx_stats_num;
 
 	tx_stats_num = (GVE_TX_STATS_REPORT_NUM + NIC_TX_STATS_REPORT_NUM) *
-		       gve_num_tx_queues(priv);
+				priv->tx_cfg.max_queues;
 	rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) *
-		       priv->rx_cfg.num_queues;
+				priv->rx_cfg.max_queues;
 	priv->stats_report_len = struct_size(priv->stats_report, stats,
 					     size_add(tx_stats_num, rx_stats_num));
 	priv->stats_report =