From 2ae16aaa78b5edc6e6d0904c84fd9cdfb762bcda Mon Sep 17 00:00:00 2001 From: Quanye Yang Date: Sun, 30 Aug 2026 15:09:55 +0800 Subject: [PATCH] RDMA/rtrs-clt: Fix CQ pool leak when connect is interrupted The client borrows shared CQ credits in the ADDR_RESOLVED handler via ib_cq_pool_get(), before the peer is connected. create_cm() can return -ERESTARTSYS from wait_event_interruptible_timeout() without destroying the CM ID. The init_conns() and stop-and-destroy paths then call destroy_con_cq_qp() while cq is still NULL (no PUT) and only afterwards rdma_destroy_id(). CMA serializes the handler against rdma_destroy_id() with handler_mutex, but that does not order the GET against destroy_con_cq_qp(). If ADDR_RESOLVED has already passed the DESTROYING check, it can take con_mutex, GET credits, and then lose the con to kfree. Device unregister later hits WARN_ON(cq->cqe_used) in ib_cq_pool_cleanup(). Set a per-connection flag under con_mutex before CQ/QP teardown so a racing ADDR_RESOLVED cannot borrow credits after teardown has begun. Reported-by: syzbot+d396918a29afb8543e1c@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d396918a29afb8543e1c Fixes: 3b89e92c2a95 ("RDMA/rtrs: Use new shared CQ mechanism") Signed-off-by: Quanye Yang Link: https://patch.msgid.link/20260830-rdma-rtrs-clt-cq-pool-leak-v1-1-b169434fd3df@proton.me Reviewed-by: Jack Wang Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 8 ++++++++ drivers/infiniband/ulp/rtrs/rtrs-clt.h | 2 ++ 2 files changed, 10 insertions(+) diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 7b2c51ae614f..eac38b57b00d 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -1732,6 +1732,8 @@ static void destroy_con_cq_qp(struct rtrs_clt_con *con) /* * Be careful here: destroy_con_cq_qp() can be called even * create_con_cq_qp() failed, see comments there. + * Caller must set con->destroyed under this lock first so a + * racing ADDR_RESOLVED cannot ib_cq_pool_get() after we PUT/SKIP. */ lockdep_assert_held(&con->con_mutex); rtrs_cq_qp_destroy(&con->c); @@ -1766,6 +1768,10 @@ static int rtrs_rdma_addr_resolved(struct rtrs_clt_con *con) int err; mutex_lock(&con->con_mutex); + if (con->destroyed) { + mutex_unlock(&con->con_mutex); + return -ECONNABORTED; + } err = create_con_cq_qp(con); mutex_unlock(&con->con_mutex); if (err) { @@ -2221,6 +2227,7 @@ static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_path *clt_path) break; con = to_clt_con(clt_path->s.con[cid]); mutex_lock(&con->con_mutex); + con->destroyed = true; destroy_con_cq_qp(con); mutex_unlock(&con->con_mutex); destroy_cm(con); @@ -2387,6 +2394,7 @@ static int init_conns(struct rtrs_clt_path *clt_path) if (con->c.cm_id) { stop_cm(con); mutex_lock(&con->con_mutex); + con->destroyed = true; destroy_con_cq_qp(con); mutex_unlock(&con->con_mutex); destroy_cm(con); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h index 1305601a6251..ad64f4517c4b 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h @@ -75,6 +75,8 @@ struct rtrs_clt_con { unsigned int cpu; struct mutex con_mutex; int cm_err; + /* Set under con_mutex before CQ/QP teardown. */ + bool destroyed; }; /**