gve: Fix race condition on tx->dropped_pkt update

The tx->dropped_pkt counter is a 64-bit integer that is incremented
directly. On 32-bit architectures, this operation is not atomic and
can lead to read/write tearing if a reader accesses the counter during
the update. This can result in incorrect values being reported for
dropped packets.

To prevent this potential data corruption, wrap the increment
operation with u64_stats_update_begin() and u64_stats_update_end().
This ensures that updates to the 64-bit counter are atomic, even on
32-bit systems, by using a sequence lock.

The u64_stats_sync API requires the writer to have exclusive access,
which is already provided in this context by the network stack's
serialization of the transmit path (net_device_ops::ndo_start_xmit
[1]) for a given queue.

[1]: https://www.kernel.org/doc/Documentation/networking/netdevices.txt

Signed-off-by: Max Yuan <maxyuan@google.com>
Reviewed-by: Jordan Rhee <jordanrhee@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index c6ff0968929d61521f0b17fdaae56c053dd2763c..97efc8d27e6f74182af9dadb4a36a9068edfb44e 100644 (file)
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -730,7 +730,9 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx,
                gve_tx_unmap_buf(tx->dev, &tx->info[idx & tx->mask]);
        }
 drop:
+       u64_stats_update_begin(&tx->statss);
        tx->dropped_pkt++;
+       u64_stats_update_end(&tx->statss);
        return 0;
 }
 

diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 6f1d515673d25a31bfa9e29afee5c5a7e0872ec9..40b89b3e5a318a69c4488eabb9477a6ac28ed66e 100644 (file)
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -1002,7 +1002,9 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx,
        return 0;
 
 drop:
+       u64_stats_update_begin(&tx->statss);
        tx->dropped_pkt++;
+       u64_stats_update_end(&tx->statss);
        dev_kfree_skb_any(skb);
        return 0;
 }
@@ -1324,7 +1326,11 @@ static void remove_miss_completions(struct gve_priv *priv,
                /* This indicates the packet was dropped. */
                dev_kfree_skb_any(pending_packet->skb);
                pending_packet->skb = NULL;
+
+               u64_stats_update_begin(&tx->statss);
                tx->dropped_pkt++;
+               u64_stats_update_end(&tx->statss);
+
                net_err_ratelimited("%s: No reinjection completion was received for: %d.\n",
                                    priv->dev->name,
                                    (int)(pending_packet - tx->dqo.pending_packets));