net/mlx5e: TC, Check if flow is PEER before acquiring devcom lock

In case __mlx5e_add_fdb_flow() fails in lower levels, the flow is
deleted via mlx5e_tc_del_flow(), and mlx5e_tc_del_flow() is acquiring
ESW devcom lock without condition. In addition, in case of peer_flow,
__mlx5e_add_fdb_flow() is called while holding ESW devcom comp lock.
This results in an AA deadlock.

To fix this, introduce a new PEER flag that is set on flows created as
peer flows (the duplicate flows on peer devices), and check it in
mlx5e_tc_del_flow() before acquiring ESW devcom lock.

Lockdep splat:
============================================
WARNING: possible recursive locking detected
============================================
 Possible unsafe locking scenario:
       CPU0
       ----
  lock(&comp->lock_key#2);
  lock(&comp->lock_key#2);
 *** DEADLOCK ***
Call Trace:
 <TASK>
 dump_stack_lvl+0x69/0xa0
 print_deadlock_bug.cold+0xbd/0xca
 __lock_acquire+0x1671/0x2ec0
 lock_acquire+0x10e/0x2e0
 down_read+0x95/0x430
 mlx5_devcom_for_each_peer_begin+0x4e/0xe0 [mlx5_core]
 mlx5e_tc_del_flow+0x11d/0xa70 [mlx5_core]
 mlx5e_flow_put+0x99/0x100 [mlx5_core]
 __mlx5e_add_fdb_flow+0x409/0xf00 [mlx5_core]
 mlx5e_configure_flower+0x2a86/0x4100 [mlx5_core]
 mlx5e_rep_setup_tc_cls_flower+0x12f/0x1b0 [mlx5_core]
 mlx5e_rep_setup_tc_cb+0x153/0x750 [mlx5_core]
 tc_setup_cb_add+0x1dc/0x470
 fl_change+0x2f4d/0x626d [cls_flower]
 tc_new_tfilter+0x79b/0x2310
 rtnetlink_rcv_msg+0x778/0xad0
 do_syscall_64+0x70/0x960
 entry_SYSCALL_64_after_hwframe+0x4b/0x53
 </TASK>

Fixes: 04de7dda7394 ("net/mlx5e: Infrastructure for duplicated offloading of TC flows")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260728044338.2271143-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index 28cab4bf525ccfacb4cbb91957981c8ce9ee221a..7bfe7cdc5770819ced36a72c3605685412431550 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -30,6 +30,7 @@ enum {
        MLX5E_TC_FLOW_FLAG_FAILED                = MLX5E_TC_FLOW_BASE + 9,
        MLX5E_TC_FLOW_FLAG_SAMPLE                = MLX5E_TC_FLOW_BASE + 10,
        MLX5E_TC_FLOW_FLAG_USE_ACT_STATS         = MLX5E_TC_FLOW_BASE + 11,
+       MLX5E_TC_FLOW_FLAG_PEER                  = MLX5E_TC_FLOW_BASE + 12,
 };
 
 struct mlx5e_tc_flow_parse_attr {

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 1bc7b9019124a449ee68041fa29733287de94569..b290beb4369ad565fefb99d6c98f661d69642cc5 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2161,7 +2161,8 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
        if (mlx5e_is_eswitch_flow(flow)) {
                struct mlx5_devcom_comp_dev *devcom = flow->priv->mdev->priv.eswitch->devcom;
 
-               if (!mlx5_devcom_for_each_peer_begin(devcom)) {
+               if (flow_flag_test(flow, PEER) ||
+                   !mlx5_devcom_for_each_peer_begin(devcom)) {
                        mlx5e_tc_del_fdb_flow(priv, flow);
                        return;
                }
@@ -4628,6 +4629,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f,
        else
                in_mdev = priv->mdev;
 
+       flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_PEER);
        parse_attr = flow->attr->parse_attr;
        peer_flow = __mlx5e_add_fdb_flow(peer_priv, f, flow_flags,
                                         parse_attr->filter_dev,