From 0541db8ee32c09463a72d0987382b3a3336b0043 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Wed, 27 Nov 2024 21:30:13 +0800 Subject: [PATCH 1/2] net/smc: initialize close_work early to avoid warning We encountered a warning that close_work was canceled before initialization. WARNING: CPU: 7 PID: 111103 at kernel/workqueue.c:3047 __flush_work+0x19e/0x1b0 Workqueue: events smc_lgr_terminate_work [smc] RIP: 0010:__flush_work+0x19e/0x1b0 Call Trace: ? __wake_up_common+0x7a/0x190 ? work_busy+0x80/0x80 __cancel_work_timer+0xe3/0x160 smc_close_cancel_work+0x1a/0x70 [smc] smc_close_active_abort+0x207/0x360 [smc] __smc_lgr_terminate.part.38+0xc8/0x180 [smc] process_one_work+0x19e/0x340 worker_thread+0x30/0x370 ? process_one_work+0x340/0x340 kthread+0x117/0x130 ? __kthread_cancel_work+0x50/0x50 ret_from_fork+0x22/0x30 This is because when smc_close_cancel_work is triggered, e.g. the RDMA driver is rmmod and the LGR is terminated, the conn->close_work is flushed before initialization, resulting in WARN_ON(!work->func). __smc_lgr_terminate | smc_connect_{rdma|ism} ------------------------------------------------------------- | smc_conn_create | \- smc_lgr_register_conn for conn in lgr->conns_all | \- smc_conn_kill | \- smc_close_active_abort | \- smc_close_cancel_work | \- cancel_work_sync | \- __flush_work | (close_work) | | smc_close_init | \- INIT_WORK(&close_work) So fix this by initializing close_work before establishing the connection. Fixes: 46c28dbd4c23 ("net/smc: no socket state changes in tasklet context") Fixes: 413498440e30 ("net/smc: add SMC-D support in af_smc") Signed-off-by: Wen Gu Reviewed-by: Wenjia Zhang Reviewed-by: Alexandra Winter Signed-off-by: Paolo Abeni --- net/smc/af_smc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9d76e902fd77..ed6d4d520bc7 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -383,6 +383,7 @@ void smc_sk_init(struct net *net, struct sock *sk, int protocol) smc->limit_smc_hs = net->smc.limit_smc_hs; smc->use_fallback = false; /* assume rdma capability first */ smc->fallback_rsn = 0; + smc_close_init(smc); } static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, @@ -1299,7 +1300,6 @@ static int smc_connect_rdma(struct smc_sock *smc, goto connect_abort; } - smc_close_init(smc); smc_rx_init(smc); if (ini->first_contact_local) { @@ -1435,7 +1435,6 @@ static int smc_connect_ism(struct smc_sock *smc, goto connect_abort; } } - smc_close_init(smc); smc_rx_init(smc); smc_tx_init(smc); @@ -2479,7 +2478,6 @@ static void smc_listen_work(struct work_struct *work) goto out_decl; mutex_lock(&smc_server_lgr_pending); - smc_close_init(new_smc); smc_rx_init(new_smc); smc_tx_init(new_smc); From 2c7f14ed9c19ec0f149479d1c2842ec1f9bf76d7 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Wed, 27 Nov 2024 21:30:14 +0800 Subject: [PATCH 2/2] net/smc: fix LGR and link use-after-free issue We encountered a LGR/link use-after-free issue, which manifested as the LGR/link refcnt reaching 0 early and entering the clear process, making resource access unsafe. refcount_t: addition on 0; use-after-free. WARNING: CPU: 14 PID: 107447 at lib/refcount.c:25 refcount_warn_saturate+0x9c/0x140 Workqueue: events smc_lgr_terminate_work [smc] Call trace: refcount_warn_saturate+0x9c/0x140 __smc_lgr_terminate.part.45+0x2a8/0x370 [smc] smc_lgr_terminate_work+0x28/0x30 [smc] process_one_work+0x1b8/0x420 worker_thread+0x158/0x510 kthread+0x114/0x118 or refcount_t: underflow; use-after-free. WARNING: CPU: 6 PID: 93140 at lib/refcount.c:28 refcount_warn_saturate+0xf0/0x140 Workqueue: smc_hs_wq smc_listen_work [smc] Call trace: refcount_warn_saturate+0xf0/0x140 smcr_link_put+0x1cc/0x1d8 [smc] smc_conn_free+0x110/0x1b0 [smc] smc_conn_abort+0x50/0x60 [smc] smc_listen_find_device+0x75c/0x790 [smc] smc_listen_work+0x368/0x8a0 [smc] process_one_work+0x1b8/0x420 worker_thread+0x158/0x510 kthread+0x114/0x118 It is caused by repeated release of LGR/link refcnt. One suspect is that smc_conn_free() is called repeatedly because some smc_conn_free() from server listening path are not protected by sock lock. e.g. Calls under socklock | smc_listen_work ------------------------------------------------------- lock_sock(sk) | smc_conn_abort smc_conn_free | \- smc_conn_free \- smcr_link_put | \- smcr_link_put (duplicated) release_sock(sk) So here add sock lock protection in smc_listen_work() path, making it exclusive with other connection operations. Fixes: 3b2dec2603d5 ("net/smc: restructure client and server code in af_smc") Co-developed-by: Guangguan Wang Signed-off-by: Guangguan Wang Co-developed-by: Kai Signed-off-by: Kai Signed-off-by: Wen Gu Reviewed-by: Wenjia Zhang Signed-off-by: Paolo Abeni --- net/smc/af_smc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index ed6d4d520bc7..9e6c69d18581 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1900,6 +1900,7 @@ static void smc_listen_out(struct smc_sock *new_smc) if (tcp_sk(new_smc->clcsock->sk)->syn_smc) atomic_dec(&lsmc->queued_smc_hs); + release_sock(newsmcsk); /* lock in smc_listen_work() */ if (lsmc->sk.sk_state == SMC_LISTEN) { lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); @@ -2421,6 +2422,7 @@ static void smc_listen_work(struct work_struct *work) u8 accept_version; int rc = 0; + lock_sock(&new_smc->sk); /* release in smc_listen_out() */ if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) return smc_listen_out_err(new_smc);