From: Carolina Jubran cjubran@nvidia.com

mainline inclusion from mainline-v6.9-rc5 commit fef965764cf562f28afb997b626fc7c3cec99693 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9L5LB CVE: CVE-2024-27014

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

When disabling aRFS under the `priv->state_lock`, any scheduled aRFS works are canceled using the `cancel_work_sync` function, which waits for the work to end if it has already started. However, while waiting for the work handler, the handler will try to acquire the `state_lock` which is already acquired.

The worker acquires the lock to delete the rules if the state is down, which is not the worker's responsibility since disabling aRFS deletes the rules.

Add an aRFS state variable, which indicates whether the aRFS is enabled and prevent adding rules when the aRFS is disabled.

Kernel log:

====================================================== WARNING: possible circular locking dependency detected 6.7.0-rc4_net_next_mlx5_5483eb2 #1 Tainted: G I ------------------------------------------------------ ethtool/386089 is trying to acquire lock: ffff88810f21ce68 ((work_completion)(&rule->arfs_work)){+.+.}-{0:0}, at: __flush_work+0x74/0x4e0

but task is already holding lock: ffff8884a1808cc0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_ethtool_set_channels+0x53/0x200 [mlx5_core]

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&priv->state_lock){+.+.}-{3:3}: __mutex_lock+0x80/0xc90 arfs_handle_work+0x4b/0x3b0 [mlx5_core] process_one_work+0x1dc/0x4a0 worker_thread+0x1bf/0x3c0 kthread+0xd7/0x100 ret_from_fork+0x2d/0x50 ret_from_fork_asm+0x11/0x20

-> #0 ((work_completion)(&rule->arfs_work)){+.+.}-{0:0}: __lock_acquire+0x17b4/0x2c80 lock_acquire+0xd0/0x2b0 __flush_work+0x7a/0x4e0 __cancel_work_timer+0x131/0x1c0 arfs_del_rules+0x143/0x1e0 [mlx5_core] mlx5e_arfs_disable+0x1b/0x30 [mlx5_core] mlx5e_ethtool_set_channels+0xcb/0x200 [mlx5_core] ethnl_set_channels+0x28f/0x3b0 ethnl_default_set_doit+0xec/0x240 genl_family_rcv_msg_doit+0xd0/0x120 genl_rcv_msg+0x188/0x2c0 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x1a1/0x270 netlink_sendmsg+0x214/0x460 __sock_sendmsg+0x38/0x60 __sys_sendto+0x113/0x170 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x40/0xe0 entry_SYSCALL_64_after_hwframe+0x46/0x4e

other info that might help us debug this:

Possible unsafe locking scenario:

CPU0 CPU1 ---- ---- lock(&priv->state_lock); lock((work_completion)(&rule->arfs_work)); lock(&priv->state_lock); lock((work_completion)(&rule->arfs_work));

*** DEADLOCK ***

3 locks held by ethtool/386089: #0: ffffffff82ea7210 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 #1: ffffffff82e94c88 (rtnl_mutex){+.+.}-{3:3}, at: ethnl_default_set_doit+0xd3/0x240 #2: ffff8884a1808cc0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_ethtool_set_channels+0x53/0x200 [mlx5_core]

stack backtrace: CPU: 15 PID: 386089 Comm: ethtool Tainted: G I 6.7.0-rc4_net_next_mlx5_5483eb2 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x60/0xa0 check_noncircular+0x144/0x160 __lock_acquire+0x17b4/0x2c80 lock_acquire+0xd0/0x2b0 ? __flush_work+0x74/0x4e0 ? save_trace+0x3e/0x360 ? __flush_work+0x74/0x4e0 __flush_work+0x7a/0x4e0 ? __flush_work+0x74/0x4e0 ? __lock_acquire+0xa78/0x2c80 ? lock_acquire+0xd0/0x2b0 ? mark_held_locks+0x49/0x70 __cancel_work_timer+0x131/0x1c0 ? mark_held_locks+0x49/0x70 arfs_del_rules+0x143/0x1e0 [mlx5_core] mlx5e_arfs_disable+0x1b/0x30 [mlx5_core] mlx5e_ethtool_set_channels+0xcb/0x200 [mlx5_core] ethnl_set_channels+0x28f/0x3b0 ethnl_default_set_doit+0xec/0x240 genl_family_rcv_msg_doit+0xd0/0x120 genl_rcv_msg+0x188/0x2c0 ? ethnl_ops_begin+0xb0/0xb0 ? genl_family_rcv_msg_dumpit+0xf0/0xf0 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x1a1/0x270 netlink_sendmsg+0x214/0x460 __sock_sendmsg+0x38/0x60 __sys_sendto+0x113/0x170 ? do_user_addr_fault+0x53f/0x8f0 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x40/0xe0 entry_SYSCALL_64_after_hwframe+0x46/0x4e </TASK>

Fixes: 45bf454ae884 ("net/mlx5e: Enabling aRFS mechanism") Signed-off-by: Carolina Jubran cjubran@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Link: https://lore.kernel.org/r/20240411115444.374475-7-tariqt@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org

Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c drivers/net/ethernet/mellanox/mlx5/core/en/fs.h [Did not backport the commit f6755b80d693 ("net/mlx5e: Dynamic alloc arfs table for netdev when needed"), and commit f52f2faee581 ("net/mlx5e: Introduce flow steering API").] Signed-off-by: Liu Jian liujian56@huawei.com --- .../net/ethernet/mellanox/mlx5/core/en/fs.h | 1 + .../net/ethernet/mellanox/mlx5/core/en_arfs.c | 26 +++++++++++-------- 2 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 000ca294b0a0..ce2c9daae2c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -215,6 +215,7 @@ struct mlx5e_arfs_tables { struct list_head rules; int last_filter_id; struct workqueue_struct *wq; + unsigned long state; };

int mlx5e_arfs_create_tables(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 39475f6565c7..2e800d730231 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -36,6 +36,10 @@ #include <linux/ipv6.h> #include "en.h"

+enum { + MLX5E_ARFS_STATE_ENABLED, +}; + struct arfs_tuple { __be16 etype; u8 ip_proto; @@ -132,6 +136,8 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv) return err; } } + set_bit(MLX5E_ARFS_STATE_ENABLED, &priv->fs.arfs.state); + return 0; }

@@ -387,6 +393,8 @@ static void arfs_del_rules(struct mlx5e_priv *priv) int j;

HLIST_HEAD(del_list); + clear_bit(MLX5E_ARFS_STATE_ENABLED, &priv->fs.arfs.state); + spin_lock_bh(&priv->fs.arfs.arfs_lock); mlx5e_for_each_arfs_rule(rule, htmp, priv->fs.arfs.arfs_tables, i, j) { hlist_del_init(&rule->hlist); @@ -552,17 +560,8 @@ static void arfs_handle_work(struct work_struct *work) struct mlx5e_priv *priv = arfs_rule->priv; struct mlx5_flow_handle *rule;

- mutex_lock(&priv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - spin_lock_bh(&priv->fs.arfs.arfs_lock); - hlist_del(&arfs_rule->hlist); - spin_unlock_bh(&priv->fs.arfs.arfs_lock); - - mutex_unlock(&priv->state_lock); - kfree(arfs_rule); - goto out; - } - mutex_unlock(&priv->state_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &priv->fs.arfs.state)) + return;

if (!arfs_rule->rule) { rule = arfs_add_rule(priv, arfs_rule); @@ -673,6 +672,11 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, return -EPROTONOSUPPORT;

spin_lock_bh(&arfs->arfs_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) { + spin_unlock_bh(&arfs->arfs_lock); + return -EPERM; + } + arfs_rule = arfs_find_rule(arfs_t, &fk); if (arfs_rule) { if (arfs_rule->rxq == rxq_index) {