mlx5: fix possible ptp queue fifo use-after-free

Fifo indexes are not checked during pop operations and it leads to
potential use-after-free when poping from empty queue. Such case was
possible during re-sync action. WARN_ON_ONCE covers future cases.

There were out-of-order cqe spotted which lead to drain of the queue and
use-after-free because of lack of fifo pointers check. Special check and
counter are added to avoid resync operation if SKB could not exist in the
fifo because of OOO cqe (skb_id must be between consumer and producer
index).

Fixes: 58a51894 ("net/mlx5e: Add resiliency for PTP TX port timestamp")
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c

@@ -86,6 +86,17 @@ static bool mlx5e_ptp_ts_cqe_drop(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, u16 skb
 	return (ptpsq->ts_cqe_ctr_mask && (skb_cc != skb_id));
 }
 
+static bool mlx5e_ptp_ts_cqe_ooo(struct mlx5e_ptpsq *ptpsq, u16 skb_id)
+{
+	u16 skb_cc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc);
+	u16 skb_pc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_pc);
+
+	if (PTP_WQE_CTR2IDX(skb_id - skb_cc) >= PTP_WQE_CTR2IDX(skb_pc - skb_cc))
+		return true;
+
+	return false;
+}
+
 static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_cc,
 					     u16 skb_id, int budget)
 {
@@ -120,8 +131,14 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 		goto out;
 	}
 
-	if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id))
+	if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id)) {
+		if (mlx5e_ptp_ts_cqe_ooo(ptpsq, skb_id)) {
+			/* already handled by a previous resync */
+			ptpsq->cq_stats->ooo_cqe_drop++;
+			return;
+		}
 		mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_cc, skb_id, budget);
+	}
 
 	skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo);
 	hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe));

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -302,6 +302,8 @@ void mlx5e_skb_fifo_push(struct mlx5e_skb_fifo *fifo, struct sk_buff *skb)
 static inline
 struct sk_buff *mlx5e_skb_fifo_pop(struct mlx5e_skb_fifo *fifo)
 {
+	WARN_ON_ONCE(*fifo->pc == *fifo->cc);
+
 	return *mlx5e_skb_fifo_get(fifo, (*fifo->cc)++);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_stats.c

@@ -2138,6 +2138,7 @@ static const struct counter_desc ptp_cq_stats_desc[] = {
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort_abs_diff_ns) },
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_cqe) },
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_event) },
+	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, ooo_cqe_drop) },
 };
 
 static const struct counter_desc ptp_rq_stats_desc[] = {

drivers/net/ethernet/mellanox/mlx5/core/en_stats.h

@@ -461,6 +461,7 @@ struct mlx5e_ptp_cq_stats {
 	u64 abort_abs_diff_ns;
 	u64 resync_cqe;
 	u64 resync_event;
+	u64 ooo_cqe_drop;
 };
 
 struct mlx5e_rep_stats {