From: Cosmin Ratiu mlx5_eswitch_block_encap() takes mode_lock but ignores eswitch_operation_in_progress. mlx5_devlink_eswitch_encap_mode_set() claims the operation and drops mode_lock while rebuilding the FDB and updating offloads.encap, so a reservation can read a stale or rolled-back encap value. In diagram form: T1: first IPsec SA (NIC table) T2: encap none -> basic mlx5_devlink_eswitch_encap_mode_set() down_write(&esw->mode_lock) sees num_block_encap == 0 eswitch_operation_in_progress = true up_write(&esw->mode_lock) esw_destroy_offloads_fdb_tables() mlx5e_xfrm_add_state() mlx5e_ipsec_fs_tunnel_allowed() mlx5_eswitch_block_encap() down_write(&esw->mode_lock) reads encap == NONE num_block_encap++ up_write(&esw->mode_lock) esw->offloads.encap = BASIC esw_create_offloads_fdb_tables() The race happens therefore because offloads.encap is not consistently accessed under mode_lock. There are other variations of the above race (e.g. in rollback, or in tx_create()). Use mlx5_esw_lock() to reject a reservation while an operation is in progress. This implies changing mlx5e_ipsec_fs_tunnel_allowed() to propagate the error. Note that these are not new failure modes as it seems on first glance, because if the eswitch_operation_in_progress flag is set, rx_get()/tx_get()->mlx5_eswitch_block_mode() already fails with -EBUSY. The new code simply protects against an operation initiated in the short window after mlx5_eswitch_block_mode(). This race was found by Sashiko during inspection of another patch of this series. No attempt has been made to trigger it, as it requires very precise timing. Fixes: baac8351f74c ("net/mlx5e: Reduce eswitch mode_lock protection context") Signed-off-by: Cosmin Ratiu Reviewed-by: Jianbo Liu Signed-off-by: Tariq Toukan --- .../mellanox/mlx5/core/en_accel/ipsec.c | 5 ++++- .../mellanox/mlx5/core/en_accel/ipsec.h | 2 +- .../mellanox/mlx5/core/en_accel/ipsec_fs.c | 21 ++++++++++++------- .../net/ethernet/mellanox/mlx5/core/eswitch.h | 6 +++--- .../mellanox/mlx5/core/eswitch_offloads.c | 20 +++++++++++------- 5 files changed, 35 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 7e991a09b3ff..7bc5d07b4321 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -812,7 +812,10 @@ static int mlx5e_xfrm_add_state(struct net_device *dev, if (x->props.mode == XFRM_MODE_TUNNEL && x->xso.type == XFRM_DEV_OFFLOAD_PACKET) { - allow_tunnel_mode = mlx5e_ipsec_fs_tunnel_allowed(sa_entry); + err = mlx5e_ipsec_fs_tunnel_allowed(sa_entry); + if (err < 0) + goto unblock_mode; + allow_tunnel_mode = err; if (!allow_tunnel_mode) { NL_SET_ERR_MSG_MOD(extack, "Packet offload tunnel mode is disabled due to encap settings"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index abcbd38db9db..f4b2d7b950c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -320,7 +320,7 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry); int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry); void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry); void mlx5e_accel_ipsec_fs_modify(struct mlx5e_ipsec_sa_entry *sa_entry); -bool mlx5e_ipsec_fs_tunnel_allowed(struct mlx5e_ipsec_sa_entry *sa_entry); +int mlx5e_ipsec_fs_tunnel_allowed(struct mlx5e_ipsec_sa_entry *sa_entry); int mlx5_ipsec_create_sa_ctx(struct mlx5e_ipsec_sa_entry *sa_entry); void mlx5_ipsec_free_sa_ctx(struct mlx5e_ipsec_sa_entry *sa_entry); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index fd9fbf359333..1529d4730323 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -1072,9 +1072,12 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, goto err_fs_ft_sa_sel; /* Create FT */ - if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL) - rx->allow_tunnel_mode = - mlx5_eswitch_block_encap(mdev, rx == ipsec->rx_esw); + if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL) { + err = mlx5_eswitch_block_encap(mdev, rx == ipsec->rx_esw); + if (err < 0) + goto err_fs_ft; + rx->allow_tunnel_mode = err; + } if (rx->allow_tunnel_mode) flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; @@ -1315,9 +1318,12 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx, if (err) goto err_status_rule; - if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL) - tx->allow_tunnel_mode = - mlx5_eswitch_block_encap(mdev, tx == ipsec->tx_esw); + if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL) { + err = mlx5_eswitch_block_encap(mdev, tx == ipsec->tx_esw); + if (err < 0) + goto err_encap; + tx->allow_tunnel_mode = err; + } if (tx->allow_tunnel_mode) flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; @@ -1387,6 +1393,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx, err_sa_ft: if (tx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); +err_encap: mlx5_del_flow_rules(tx->status.rule); err_status_rule: mlx5_destroy_flow_table(tx->ft.status); @@ -2854,7 +2861,7 @@ void mlx5e_accel_ipsec_fs_modify(struct mlx5e_ipsec_sa_entry *sa_entry) memcpy(sa_entry, &sa_entry_shadow, sizeof(*sa_entry)); } -bool mlx5e_ipsec_fs_tunnel_allowed(struct mlx5e_ipsec_sa_entry *sa_entry) +int mlx5e_ipsec_fs_tunnel_allowed(struct mlx5e_ipsec_sa_entry *sa_entry) { struct mlx5e_ipsec *ipsec = sa_entry->ipsec; struct xfrm_state *x = sa_entry->x; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index e9cbcd73b23f..928b20e73d37 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -967,7 +967,7 @@ void mlx5_eswitch_unload_reps(struct mlx5_eswitch *esw); bool mlx5_eswitch_is_peer(struct mlx5_eswitch *esw, struct mlx5_eswitch *peer_esw); -bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb); +int mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb); void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev); int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev); @@ -1071,10 +1071,10 @@ mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw) static inline void mlx5_eswitch_unload_reps(struct mlx5_eswitch *esw) {} -static inline bool +static inline int mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb) { - return true; + return 1; } static inline void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index c712848b202d..7a0131e26ff0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -4712,25 +4712,31 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); } -bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb) +/* Return 1 if allowed, 0 if disallowed by the configuration, or -EBUSY + * if an eswitch operation is in progress. + */ +int mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb) { struct mlx5_eswitch *esw = dev->priv.eswitch; enum devlink_eswitch_encap_mode encap; - bool allow_tunnel = false; + int ret; if (!mlx5_esw_allowed(esw)) - return true; + return 1; + + ret = mlx5_esw_lock(esw); + if (ret) + return ret; - down_write(&esw->mode_lock); encap = esw->offloads.encap; if (esw->mode == MLX5_ESWITCH_LEGACY || (encap == DEVLINK_ESWITCH_ENCAP_MODE_NONE && !from_fdb)) { - allow_tunnel = true; + ret = 1; esw->offloads.num_block_encap++; } - up_write(&esw->mode_lock); + mlx5_esw_unlock(esw); - return allow_tunnel; + return ret; } void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev) -- 2.44.0