From 25fe708bbc59289d3d1ea4b126fbc1b460a072a5 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Thu, 21 May 2026 01:12:01 -0700 Subject: [PATCH] net: team: fix NULL pointer dereference in team_xmit during mode change __team_change_mode() clears team->ops with memset() before restoring safe dummy handlers via team_adjust_ops(). A concurrent team_xmit() running under RCU on another CPU can read team->ops.transmit during this window and call a NULL function pointer, crashing the kernel. The race requires a mode change (CAP_NET_ADMIN) concurrent with transmit on the team device. BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: 0010 [#1] SMP KASAN NOPTI RIP: 0010:0x0 Call Trace: team_xmit (drivers/net/team/team_core.c:1853) dev_hard_start_xmit (net/core/dev.c:3904) __dev_queue_xmit (net/core/dev.c:4871) packet_sendmsg (net/packet/af_packet.c:3109) __sys_sendto (net/socket.c:2265) The original code assumed that no ports means no traffic, so mode changes could freely memset()/memcpy() the ops. AF_PACKET with forced carrier breaks that assumption. Prevent the race instead of making it safe: replace memset()/memcpy() with per-field updates that never touch transmit or receive. Those two handlers are managed solely by team_adjust_ops(), which already installs dummies when tx_en_port_count == 0 (always true during mode change since no ports are present). WRITE_ONCE/READ_ONCE prevent store/load tearing on the handler pointers. synchronize_net() before exit_op() drains in-flight readers that may still reference old mode state from before port removal switched the handlers to dummies. Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Reviewed-by: Jiayuan Chen Link: https://patch.msgid.link/20260521081159.1491563-3-bestswngs@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/team/team_core.c | 45 +++++++++++++++++++++++++----------- 1 file changed, 32 insertions(+), 13 deletions(-) diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 0c87f9972457..f51388d50307 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -534,21 +534,23 @@ static void team_adjust_ops(struct team *team) if (!team->tx_en_port_count || !team_is_mode_set(team) || !team->mode->ops->transmit) - team->ops.transmit = team_dummy_transmit; + WRITE_ONCE(team->ops.transmit, team_dummy_transmit); else - team->ops.transmit = team->mode->ops->transmit; + WRITE_ONCE(team->ops.transmit, team->mode->ops->transmit); if (!team->rx_en_port_count || !team_is_mode_set(team) || !team->mode->ops->receive) - team->ops.receive = team_dummy_receive; + WRITE_ONCE(team->ops.receive, team_dummy_receive); else - team->ops.receive = team->mode->ops->receive; + WRITE_ONCE(team->ops.receive, team->mode->ops->receive); } /* - * We can benefit from the fact that it's ensured no port is present - * at the time of mode change. Therefore no packets are in fly so there's no - * need to set mode operations in any special way. + * team_change_mode() ensures no ports are present during mode change, + * but lockless readers can still reach team_xmit(). Avoid touching + * transmit/receive -- they are already set to dummies by + * team_adjust_ops() since no ports are enabled. synchronize_net() + * drains in-flight readers before destroying old mode state. */ static int __team_change_mode(struct team *team, const struct team_mode *new_mode) @@ -557,9 +559,21 @@ static int __team_change_mode(struct team *team, if (team_is_mode_set(team)) { void (*exit_op)(struct team *team) = team->ops.exit; - /* Clear ops area so no callback is called any longer */ - memset(&team->ops, 0, sizeof(struct team_mode_ops)); - team_adjust_ops(team); + /* Clear cold-path ops used only under RTNL. transmit and + * receive are already dummies (no ports) so leave them + * alone -- overwriting them is the source of the race. + */ + team->ops.init = NULL; + team->ops.exit = NULL; + team->ops.port_enter = NULL; + team->ops.port_leave = NULL; + team->ops.port_change_dev_addr = NULL; + team->ops.port_tx_disabled = NULL; + + /* Wait for in-flight readers before tearing down mode + * state they may reference. + */ + synchronize_net(); if (exit_op) exit_op(team); @@ -582,7 +596,12 @@ static int __team_change_mode(struct team *team, } team->mode = new_mode; - memcpy(&team->ops, new_mode->ops, sizeof(struct team_mode_ops)); + team->ops.init = new_mode->ops->init; + team->ops.exit = new_mode->ops->exit; + team->ops.port_enter = new_mode->ops->port_enter; + team->ops.port_leave = new_mode->ops->port_leave; + team->ops.port_change_dev_addr = new_mode->ops->port_change_dev_addr; + team->ops.port_tx_disabled = new_mode->ops->port_tx_disabled; team_adjust_ops(team); return 0; @@ -743,7 +762,7 @@ static rx_handler_result_t team_handle_frame(struct sk_buff **pskb) /* allow exact match delivery for disabled ports */ res = RX_HANDLER_EXACT; } else { - res = team->ops.receive(team, port, skb); + res = READ_ONCE(team->ops.receive)(team, port, skb); } if (res == RX_HANDLER_ANOTHER) { struct team_pcpu_stats *pcpu_stats; @@ -1845,7 +1864,7 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) tx_success = team_queue_override_transmit(team, skb); if (!tx_success) - tx_success = team->ops.transmit(team, skb); + tx_success = READ_ONCE(team->ops.transmit)(team, skb); if (tx_success) { struct team_pcpu_stats *pcpu_stats;