From db3d0e0e5d4bc5ab4fe445b9f413d1b486508ca5 Mon Sep 17 00:00:00 2001 From: Xiang Mei Date: Sun, 12 Jul 2026 16:42:01 -0700 Subject: netfilter: nf_conntrack_sip: widen NAT rewrite delta to s32 in sip_help_tcp() sip_help_tcp() stores the size change of each NAT-rewritten SIP message in s16 diff and accumulates it in s16 tdiff, but a single message can grow by more than S16_MAX while the packet stays under the 65535 enlarge_skb() limit: nf_nat_sip() rewrites every matching URI, and a long Contact list expands the message by tens of kilobytes. diff then wraps, and "datalen = datalen + diff - msglen" yields a huge unsigned datalen, so the next iteration's ct_sip_get_header() reads past the linearized skb tail. Widen diff, tdiff and the seq_adjust hook to s32. Both are bounded by the 65535 byte packet limit, and the seqadj core is already s32 (nf_ct_seqadj_set() takes s32), so no previously accepted input is rejected. BUG: KASAN: use-after-free in ct_sip_get_header (net/netfilter/nf_conntrack_sip.c:464) Read of size 1 at addr ffff888010800000 by task ksoftirqd/1/25 ct_sip_get_header (net/netfilter/nf_conntrack_sip.c:464) sip_help_tcp (net/netfilter/nf_conntrack_sip.c:1694) nf_confirm (net/netfilter/nf_conntrack_proto.c:183) nf_hook_slow (net/netfilter/core.c:619) ip6_output (net/ipv6/ip6_output.c:246) ip6_forward (net/ipv6/ip6_output.c:690) ipv6_rcv (net/ipv6/ip6_input.c:351) __netif_receive_skb_one_core (net/core/dev.c:6212) process_backlog (net/core/dev.c:6676) __napi_poll (net/core/dev.c:7735) net_rx_action (net/core/dev.c:7955) handle_softirqs (kernel/softirq.c:622) run_ksoftirqd (kernel/softirq.c:1076) ... Fixes: f5b321bd37fb ("netfilter: nf_conntrack_sip: add TCP support") Reported-by: Weiming Shi Link: https://patch.msgid.link/netfilter-devel/20260712234201.3213635-1-xmei5@asu.edu Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Xiang Mei Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_sip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index dbc614dfe0d5..aafa0c04f917 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -115,7 +115,7 @@ struct nf_nat_sip_hooks { unsigned int *datalen); void (*seq_adjust)(struct sk_buff *skb, - unsigned int protoff, s16 off); + unsigned int protoff, s32 off); unsigned int (*expect)(struct sk_buff *skb, unsigned int protoff, -- cgit v1.2.3 From 97ac08560d236ca17f6606d9e671118e5eae5721 Mon Sep 17 00:00:00 2001 From: Eric Joyner Date: Wed, 22 Jul 2026 21:13:42 -0700 Subject: ethtool: Embed FEC hist ranges as buffer in struct When a driver's .get_fec_stats() handler is called and the driver supports FEC histogram stats, the driver supplies the histogram bin ranges via a pointer. This pointer is assigned while under the netdev ops lock in fec_prepare_data(), but the actual data is only read after the lock is released; so this allows the driver to change the ranges (e.g. from another .get_fec_stats() call) while the current call chain is reading them in fec_fill_reply(). Fix this by adding an ethtool core-owned buffer, ranges_buf, to struct ethtool_fec_hist. Drivers whose ranges are built dynamically (currently just mlx5) fill ranges_buf and then point the existing ranges pointer at it, giving ethtool a consistent copy that stays valid after the netdev ops lock is dropped and later in fec_fill_reply(). Drivers whose ranges are compile-time constants (bnxt, netdevsim) are unaffected by the potential race and keep setting the existing ranges pointer to their constant array, without making copies. Fixes: cc2f08129925 ("ethtool: add FEC bins histogram report") Signed-off-by: Eric Joyner Reviewed-by: Vadim Fedorenko Link: https://patch.msgid.link/20260723041342.39238-1-eric.joyner@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 - drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 7 ------- drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 19 +++++++++---------- include/linux/ethtool.h | 1 + 4 files changed, 10 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index d507289096c2..6867a5aed42c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -984,7 +984,6 @@ struct mlx5e_priv { struct mlx5e_mqprio_rl *mqprio_rl; struct dentry *dfs_root; struct mlx5_devcom_comp_dev *devcom; - struct ethtool_fec_hist_range *fec_ranges; }; static inline u16 mlx5e_stats_nch_read(const struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c1acb9012d3f..7d47a1da8b6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6415,14 +6415,8 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, if (!priv->channel_stats) goto err_free_tx_rates; - priv->fec_ranges = kzalloc_objs(*priv->fec_ranges, ETHTOOL_FEC_HIST_MAX); - if (!priv->fec_ranges) - goto err_free_channel_stats; - return 0; -err_free_channel_stats: - kfree(priv->channel_stats); err_free_tx_rates: kfree(priv->tx_rates); err_free_txq2sq_stats: @@ -6447,7 +6441,6 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) if (!priv->mdev) return; - kfree(priv->fec_ranges); for (i = 0; i < priv->stats_nch; i++) kvfree(priv->channel_stats[i]); kfree(priv->channel_stats); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index de38b60806c2..e7e6db7f6bf1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1550,7 +1550,7 @@ static bool fec_rs_validate_hist_type(int mode, int hist_type) static u8 fec_rs_histogram_fill_ranges(struct mlx5e_priv *priv, int mode, - const struct ethtool_fec_hist_range **ranges) + struct ethtool_fec_hist_range *ranges) { struct mlx5_core_dev *mdev = priv->mdev; u32 out[MLX5_ST_SZ_DW(pphcr_reg)] = {0}; @@ -1558,8 +1558,6 @@ fec_rs_histogram_fill_ranges(struct mlx5e_priv *priv, int mode, int sz = MLX5_ST_SZ_BYTES(pphcr_reg); u8 hist_type, num_of_bins; - memset(priv->fec_ranges, 0, - ETHTOOL_FEC_HIST_MAX * sizeof(*priv->fec_ranges)); MLX5_SET(pphcr_reg, in, local_port, 1); if (mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPHCR, 0, 0)) return 0; @@ -1575,12 +1573,11 @@ fec_rs_histogram_fill_ranges(struct mlx5e_priv *priv, int mode, for (int i = 0; i < num_of_bins; i++) { void *bin_range = MLX5_ADDR_OF(pphcr_reg, out, bin_range[i]); - priv->fec_ranges[i].high = MLX5_GET(bin_range_layout, bin_range, - high_val); - priv->fec_ranges[i].low = MLX5_GET(bin_range_layout, bin_range, - low_val); + ranges[i].high = MLX5_GET(bin_range_layout, bin_range, + high_val); + ranges[i].low = MLX5_GET(bin_range_layout, bin_range, + low_val); } - *ranges = priv->fec_ranges; return num_of_bins; } @@ -1622,10 +1619,12 @@ static void fec_set_histograms_stats(struct mlx5e_priv *priv, int mode, case MLX5E_FEC_LLRS_272_257_1: case MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD: num_of_bins = - fec_rs_histogram_fill_ranges(priv, mode, &hist->ranges); - if (num_of_bins) + fec_rs_histogram_fill_ranges(priv, mode, hist->ranges_buf); + if (num_of_bins) { + hist->ranges = hist->ranges_buf; return fec_rs_histogram_fill_stats(priv, num_of_bins, hist); + } break; default: return; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 5d491a98265e..12683b5d125e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -562,6 +562,7 @@ struct ethtool_fec_hist { u64 per_lane[ETHTOOL_MAX_LANES]; } values[ETHTOOL_FEC_HIST_MAX]; const struct ethtool_fec_hist_range *ranges; + struct ethtool_fec_hist_range ranges_buf[ETHTOOL_FEC_HIST_MAX]; }; /** * struct ethtool_fec_stats - statistics for IEEE 802.3 FEC -- cgit v1.2.3 From 6bc85579c3bbb2f088cbac849c5dc2a134dda736 Mon Sep 17 00:00:00 2001 From: Simon Schippers Date: Tue, 28 Jul 2026 11:22:38 +0200 Subject: Revert "ptr_ring: move free-space check into separate helper" This reverts commit fba362c17d9d9211fc51f272156bb84fc23bdf98. __ptr_ring_check_produce() has no users left after reverting commit 1d6e569b7d0c ("tun/tap & vhost-net: avoid ptr_ring tail-drop when a qdisc is present"). Signed-off-by: Simon Schippers Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20260728092240.250257-3-simon.schippers@tu-dortmund.de Signed-off-by: Jakub Kicinski --- include/linux/ptr_ring.h | 20 ++------------------ 1 file changed, 2 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index c95e891903f0..d2c3629bbe45 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -96,20 +96,6 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) return ret; } -/* Note: callers invoking this in a loop must use a compiler barrier, - * for example cpu_relax(). Callers must hold producer_lock. - */ -static inline int __ptr_ring_check_produce(struct ptr_ring *r) -{ - if (unlikely(!r->size)) - return -EINVAL; - - if (data_race(r->queue[r->producer])) - return -ENOSPC; - - return 0; -} - /* Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). Callers must hold producer_lock. * Callers are responsible for making sure pointer that is being queued @@ -117,10 +103,8 @@ static inline int __ptr_ring_check_produce(struct ptr_ring *r) */ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) { - int p = __ptr_ring_check_produce(r); - - if (p) - return p; + if (unlikely(!r->size) || data_race(r->queue[r->producer])) + return -ENOSPC; /* Make sure the pointer we are storing points to a valid data. */ /* Pairs with the dependency ordering in __ptr_ring_consume. */ -- cgit v1.2.3 From 8f83be72d9f5ef16c4a908450d0d993e8ec99d34 Mon Sep 17 00:00:00 2001 From: Simon Schippers Date: Tue, 28 Jul 2026 11:22:39 +0200 Subject: Revert "vhost-net: wake queue of tun/tap after ptr_ring consume" This reverts commit baf808fe4fcd35767ab732b4ab2ea80dabfd97a6. There is no netdev queue left to wake after reverting commit 1d6e569b7d0c ("tun/tap & vhost-net: avoid ptr_ring tail-drop when a qdisc is present"). Signed-off-by: Simon Schippers Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20260728092240.250257-4-simon.schippers@tu-dortmund.de Signed-off-by: Jakub Kicinski --- drivers/net/tun.c | 23 ----------------------- drivers/vhost/net.c | 21 ++++++--------------- include/linux/if_tun.h | 3 --- 3 files changed, 6 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index ec5573f545af..39abc3078097 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3787,29 +3787,6 @@ struct ptr_ring *tun_get_tx_ring(struct file *file) } EXPORT_SYMBOL_GPL(tun_get_tx_ring); -/* Callers must hold ring.consumer_lock */ -void tun_wake_queue(struct file *file, int consumed) -{ - struct tun_file *tfile; - struct tun_struct *tun; - - if (file->f_op != &tun_fops) - return; - - tfile = file->private_data; - if (!tfile) - return; - - rcu_read_lock(); - - tun = rcu_dereference(tfile->tun); - if (tun) - __tun_wake_queue(tun, tfile, consumed); - - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(tun_wake_queue); - module_init(tun_init); module_exit(tun_cleanup); MODULE_DESCRIPTION(DRV_DESCRIPTION); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 3e72b9c6af0c..6949b704166d 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -176,21 +176,13 @@ static void *vhost_net_buf_consume(struct vhost_net_buf *rxq) return ret; } -static int vhost_net_buf_produce(struct sock *sk, - struct vhost_net_virtqueue *nvq) +static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq) { - struct file *file = sk->sk_socket->file; struct vhost_net_buf *rxq = &nvq->rxq; rxq->head = 0; - spin_lock(&nvq->rx_ring->consumer_lock); - rxq->tail = __ptr_ring_consume_batched(nvq->rx_ring, rxq->queue, - VHOST_NET_BATCH); - - if (rxq->tail) - tun_wake_queue(file, rxq->tail); - - spin_unlock(&nvq->rx_ring->consumer_lock); + rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue, + VHOST_NET_BATCH); return rxq->tail; } @@ -217,15 +209,14 @@ static int vhost_net_buf_peek_len(void *ptr) return __skb_array_len_with_tag(ptr); } -static int vhost_net_buf_peek(struct sock *sk, - struct vhost_net_virtqueue *nvq) +static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq) { struct vhost_net_buf *rxq = &nvq->rxq; if (!vhost_net_buf_is_empty(rxq)) goto out; - if (!vhost_net_buf_produce(sk, nvq)) + if (!vhost_net_buf_produce(nvq)) return 0; out: @@ -1013,7 +1004,7 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk) unsigned long flags; if (rvq->rx_ring) - return vhost_net_buf_peek(sk, rvq); + return vhost_net_buf_peek(rvq); spin_lock_irqsave(&sk->sk_receive_queue.lock, flags); head = skb_peek(&sk->sk_receive_queue); diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 5f3e206c7a73..80166eb62f41 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -22,7 +22,6 @@ struct tun_msg_ctl { #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -void tun_wake_queue(struct file *file, int consumed); static inline bool tun_is_xdp_frame(void *ptr) { @@ -56,8 +55,6 @@ static inline struct ptr_ring *tun_get_tx_ring(struct file *f) return ERR_PTR(-EINVAL); } -static inline void tun_wake_queue(struct file *f, int consumed) {} - static inline bool tun_is_xdp_frame(void *ptr) { return false; -- cgit v1.2.3