From f5df2990c364d1ac596d24b3118dbc56503f7cd4 Mon Sep 17 00:00:00 2001 From: Luka Gejak Date: Wed, 1 Apr 2026 11:22:42 +0200 Subject: net: hsr: serialize seq_blocks merge across nodes During node merging, hsr_handle_sup_frame() walks node_curr->seq_blocks to update node_real without holding node_curr->seq_out_lock. This allows concurrent mutations from duplicate registration paths, risking inconsistent state or XArray/bitmap corruption. Fix this by locking both nodes' seq_out_lock during the merge. To prevent ABBA deadlocks, locks are acquired in order of memory address. Reviewed-by: Felix Maurer Fixes: 415e6367512b ("hsr: Implement more robust duplicate discard for PRP") Signed-off-by: Luka Gejak Link: https://patch.msgid.link/20260401092243.52121-2-luka.gejak@linux.dev Signed-off-by: Jakub Kicinski --- net/hsr/hsr_framereg.c | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 50996f4de7f9..d41863593674 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -123,6 +123,40 @@ static void hsr_free_node_rcu(struct rcu_head *rn) hsr_free_node(node); } +static void hsr_lock_seq_out_pair(struct hsr_node *node_a, + struct hsr_node *node_b) +{ + if (node_a == node_b) { + spin_lock_bh(&node_a->seq_out_lock); + return; + } + + if (node_a < node_b) { + spin_lock_bh(&node_a->seq_out_lock); + spin_lock_nested(&node_b->seq_out_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock_bh(&node_b->seq_out_lock); + spin_lock_nested(&node_a->seq_out_lock, SINGLE_DEPTH_NESTING); + } +} + +static void hsr_unlock_seq_out_pair(struct hsr_node *node_a, + struct hsr_node *node_b) +{ + if (node_a == node_b) { + spin_unlock_bh(&node_a->seq_out_lock); + return; + } + + if (node_a < node_b) { + spin_unlock(&node_b->seq_out_lock); + spin_unlock_bh(&node_a->seq_out_lock); + } else { + spin_unlock(&node_a->seq_out_lock); + spin_unlock_bh(&node_b->seq_out_lock); + } +} + void hsr_del_nodes(struct list_head *node_db) { struct hsr_node *node; @@ -432,7 +466,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) } ether_addr_copy(node_real->macaddress_B, ethhdr->h_source); - spin_lock_bh(&node_real->seq_out_lock); + hsr_lock_seq_out_pair(node_real, node_curr); for (i = 0; i < HSR_PT_PORTS; i++) { if (!node_curr->time_in_stale[i] && time_after(node_curr->time_in[i], node_real->time_in[i])) { @@ -455,7 +489,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) src_blk->seq_nrs[i], HSR_SEQ_BLOCK_SIZE); } } - spin_unlock_bh(&node_real->seq_out_lock); + hsr_unlock_seq_out_pair(node_real, node_curr); node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); -- cgit v1.2.3 From 2e3514e63bfb0e972b1f19668547a455d0129e88 Mon Sep 17 00:00:00 2001 From: Luka Gejak Date: Wed, 1 Apr 2026 11:22:43 +0200 Subject: net: hsr: fix VLAN add unwind on slave errors When vlan_vid_add() fails for a secondary slave, the error path calls vlan_vid_del() on the failing port instead of the peer slave that had already succeeded. This results in asymmetric VLAN state across the HSR pair. Fix this by switching to a centralized unwind path that removes the VID from any slave device that was already programmed. Fixes: 1a8a63a5305e ("net: hsr: Add VLAN CTAG filter support") Signed-off-by: Luka Gejak Link: https://patch.msgid.link/20260401092243.52121-3-luka.gejak@linux.dev Signed-off-by: Jakub Kicinski --- net/hsr/hsr_device.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index d1bfc49b5f01..fd2fea25eff0 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -532,8 +532,8 @@ static void hsr_change_rx_flags(struct net_device *dev, int change) static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { - bool is_slave_a_added = false; - bool is_slave_b_added = false; + struct net_device *slave_a_dev = NULL; + struct net_device *slave_b_dev = NULL; struct hsr_port *port; struct hsr_priv *hsr; int ret = 0; @@ -549,33 +549,35 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, switch (port->type) { case HSR_PT_SLAVE_A: if (ret) { - /* clean up Slave-B */ netdev_err(dev, "add vid failed for Slave-A\n"); - if (is_slave_b_added) - vlan_vid_del(port->dev, proto, vid); - return ret; + goto unwind; } - - is_slave_a_added = true; + slave_a_dev = port->dev; break; - case HSR_PT_SLAVE_B: if (ret) { - /* clean up Slave-A */ netdev_err(dev, "add vid failed for Slave-B\n"); - if (is_slave_a_added) - vlan_vid_del(port->dev, proto, vid); - return ret; + goto unwind; } - - is_slave_b_added = true; + slave_b_dev = port->dev; break; default: + if (ret) + goto unwind; break; } } return 0; + +unwind: + if (slave_a_dev) + vlan_vid_del(slave_a_dev, proto, vid); + + if (slave_b_dev) + vlan_vid_del(slave_b_dev, proto, vid); + + return ret; } static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, -- cgit v1.2.3