netdev - [PATCH net v5 2/2] mlx5: fix possible ptp queue fifo use-after-free

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 2 Feb 2023 09:13:55 -0800
From:   Vadim Fedorenko <vadfed@...a.com>
To:     Jakub Kicinski <kuba@...nel.org>,
        Vadim Fedorenko <vadim.fedorenko@...ux.dev>,
        Rahul Rameshbabu <rrameshbabu@...dia.com>,
        "Tariq Toukan" <ttoukan.linux@...il.com>,
        Gal Pressman <gal@...dia.com>,
        "Saeed Mahameed" <saeed@...nel.org>
CC:     Vadim Fedorenko <vadfed@...a.com>, <netdev@...r.kernel.org>
Subject: [PATCH net v5 2/2] 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: 58a518948f60 ("net/mlx5e: Add resiliency for PTP TX port timestamp")
Signed-off-by: Vadim Fedorenko <vadfed@...a.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/ptp.c  | 19 ++++++++++++++++++-
 .../net/ethernet/mellanox/mlx5/core/en/txrx.h |  2 ++
 .../ethernet/mellanox/mlx5/core/en_stats.c    |  1 +
 .../ethernet/mellanox/mlx5/core/en_stats.h    |  1 +
 4 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index b72de2b520ec..ae75e230170b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/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));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index d5afad368a69..5646f0687f65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/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)++);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 6687b8136e44..4478223c1720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/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[] = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 375752d6546d..b77100b60b50 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/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 {
-- 
2.30.2