gve: Fix stats report corruption on queue count change

The driver and the NIC share a region in memory for stats reporting.
The NIC calculates its offset into this region based on the total size
of the stats region and the size of the NIC's stats.

When the number of queues is changed, the driver's stats region is
resized. If the queue count is increased, the NIC can write past
the end of the allocated stats region, causing memory corruption.
If the queue count is decreased, there is a gap between the driver
and NIC stats, leading to incorrect stats reporting.

This change fixes the issue by allocating stats region with maximum
size, and the offset calculation for NIC stats is changed to match
with the calculation of the NIC.

Cc: stable@vger.kernel.org
Fixes: 24aeb56f2d38 ("gve: Add Gvnic stats AQ command and ethtool show/set-priv-flags.")
Signed-off-by: Debarghya Kundu <debarghyak@google.com>
Reviewed-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20260202193925.3106272-2-hramamurthy@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index 311b106160b20aa0e3eba81aada79c35cb6369df..137dd7285bdad2ce0d5ca8d8be1d41cf84a4533e 100644 (file)
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -156,7 +156,8 @@ gve_get_ethtool_stats(struct net_device *netdev,
        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;
+       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;
@@ -265,20 +266,38 @@ 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);
@@ -354,14 +373,9 @@ 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 52c5e4942cd48940d6e29c04a5327bc739dd4daa..dbc84de39b7078bdeaebffb56f4c9a067086f0f1 100644 (file)
--- 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 =