From ae9b15fbe63447bc1d3bba3769f409d17ca6fdf6 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 17 May 2023 14:30:10 +0000 Subject: [PATCH] net: fix stack overflow when LRO is disabled for virtual interfaces When the virtual interface's feature is updated, it synchronizes the updated feature for its own lower interface. This propagation logic should be worked as the iteration, not recursively. But it works recursively due to the netdev notification unexpectedly. This problem occurs when it disables LRO only for the team and bonding interface type. team0 | +------+------+-----+-----+ | | | | | team1 team2 team3 ... team200 If team0's LRO feature is updated, it generates the NETDEV_FEAT_CHANGE event to its own lower interfaces(team1 ~ team200). It is worked by netdev_sync_lower_features(). So, the NETDEV_FEAT_CHANGE notification logic of each lower interface work iteratively. But generated NETDEV_FEAT_CHANGE event is also sent to the upper interface too. upper interface(team0) generates the NETDEV_FEAT_CHANGE event for its own lower interfaces again. lower and upper interfaces receive this event and generate this event again and again. So, the stack overflow occurs. But it is not the infinite loop issue. Because the netdev_sync_lower_features() updates features before generating the NETDEV_FEAT_CHANGE event. Already synchronized lower interfaces skip notification logic. So, it is just the problem that iteration logic is changed to the recursive unexpectedly due to the notification mechanism. Reproducer: ip link add team0 type team ethtool -K team0 lro on for i in {1..200} do ip link add team$i master team0 type team ethtool -K team$i lro on done ethtool -K team0 lro off In order to fix it, the notifier_ctx member of bonding/team is introduced. Reported-by: syzbot+60748c96cf5c6df8e581@syzkaller.appspotmail.com Fixes: fd867d51f889 ("net/core: generic support for disabling netdev features down stack") Signed-off-by: Taehee Yoo Reviewed-by: Eric Dumazet Reviewed-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230517143010.3596250-1-ap420073@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 8 +++++++- drivers/net/team/team.c | 7 ++++++- include/linux/if_team.h | 1 + include/net/bonding.h | 1 + 4 files changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 3fed888..edbaa14 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3947,7 +3947,11 @@ static int bond_slave_netdev_event(unsigned long event, unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: - bond_compute_features(bond); + if (!bond->notifier_ctx) { + bond->notifier_ctx = true; + bond_compute_features(bond); + bond->notifier_ctx = false; + } break; case NETDEV_RESEND_IGMP: /* Propagate to master device */ @@ -6342,6 +6346,8 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; + bond->notifier_ctx = false; + spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index d10606f..555b0b1 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1629,6 +1629,7 @@ static int team_init(struct net_device *dev) team->dev = dev; team_set_no_mode(team); + team->notifier_ctx = false; team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); if (!team->pcpu_stats) @@ -3022,7 +3023,11 @@ static int team_device_event(struct notifier_block *unused, team_del_slave(port->team->dev, dev); break; case NETDEV_FEAT_CHANGE: - team_compute_features(port->team); + if (!port->team->notifier_ctx) { + port->team->notifier_ctx = true; + team_compute_features(port->team); + port->team->notifier_ctx = false; + } break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ diff --git a/include/linux/if_team.h b/include/linux/if_team.h index fc985e5..8de6b6e 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -208,6 +208,7 @@ struct team { bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ bool port_mtu_change_allowed; + bool notifier_ctx; struct { unsigned int count; unsigned int interval; /* in ms */ diff --git a/include/net/bonding.h b/include/net/bonding.h index 0efef2a..59955ac 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -221,6 +221,7 @@ struct bonding { struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; + bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); -- 2.7.4