net/smc: fix kernel panic caused by race of smc_sock

A crash occurs when smc_cdc_tx_handler() tries to access smc_sock
but smc_release() has already freed it.

[ 4570.695099] BUG: unable to handle page fault for address: 000000002eae9e88
[ 4570.696048] #PF: supervisor write access in kernel mode
[ 4570.696728] #PF: error_code(0x0002) - not-present page
[ 4570.697401] PGD 0 P4D 0
[ 4570.697716] Oops: 0002 [#1] PREEMPT SMP NOPTI
[ 4570.698228] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.16.0-rc4+ #111
[ 4570.699013] Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 8c24b4c 04/0
[ 4570.699933] RIP: 0010:_raw_spin_lock+0x1a/0x30
<...>
[ 4570.711446] Call Trace:
[ 4570.711746]  <IRQ>
[ 4570.711992]  smc_cdc_tx_handler+0x41/0xc0
[ 4570.712470]  smc_wr_tx_tasklet_fn+0x213/0x560
[ 4570.712981]  ? smc_cdc_tx_dismisser+0x10/0x10
[ 4570.713489]  tasklet_action_common.isra.17+0x66/0x140
[ 4570.714083]  __do_softirq+0x123/0x2f4
[ 4570.714521]  irq_exit_rcu+0xc4/0xf0
[ 4570.714934]  common_interrupt+0xba/0xe0

Though smc_cdc_tx_handler() checked the existence of smc connection,
smc_release() may have already dismissed and released the smc socket
before smc_cdc_tx_handler() further visits it.

smc_cdc_tx_handler()           |smc_release()
if (!conn)                     |
                               |
                               |smc_cdc_tx_dismiss_slots()
                               |      smc_cdc_tx_dismisser()
                               |
                               |sock_put(&smc->sk) <- last sock_put,
                               |                      smc_sock freed
bh_lock_sock(&smc->sk) (panic) |

To make sure we won't receive any CDC messages after we free the
smc_sock, add a refcount on the smc_connection for inflight CDC
message(posted to the QP but haven't received related CQE), and
don't release the smc_connection until all the inflight CDC messages
haven been done, for both success or failed ones.

Using refcount on CDC messages brings another problem: when the link
is going to be destroyed, smcr_link_clear() will reset the QP, which
then remove all the pending CQEs related to the QP in the CQ. To make
sure all the CQEs will always come back so the refcount on the
smc_connection can always reach 0, smc_ib_modify_qp_reset() was replaced
by smc_ib_modify_qp_error().
And remove the timeout in smc_wr_tx_wait_no_pending_sends() since we
need to wait for all pending WQEs done, or we may encounter use-after-
free when handling CQEs.

For IB device removal routine, we need to wait for all the QPs on that
device been destroyed before we can destroy CQs on the device, or
the refcount on smc_connection won't reach 0 and smc_sock cannot be
released.

Fixes: 5f08318f617b ("smc: connection data control (CDC)")
Reported-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 20 insertions, 5 deletions

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 55ca175e8d57..a6849362f4dd 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1127,7 +1127,7 @@ void smc_conn_free(struct smc_connection *conn)
 			smc_ism_unset_conn(conn);
 		tasklet_kill(&conn->rx_tsklet);
 	} else {
-		smc_cdc_tx_dismiss_slots(conn);
+		smc_cdc_wait_pend_tx_wr(conn);
 		if (current_work() != &conn->abort_work)
 			cancel_work_sync(&conn->abort_work);
 	}
@@ -1204,7 +1204,7 @@ void smcr_link_clear(struct smc_link *lnk, bool log)
 	smc_llc_link_clear(lnk, log);
 	smcr_buf_unmap_lgr(lnk);
 	smcr_rtoken_clear_link(lnk);
-	smc_ib_modify_qp_reset(lnk);
+	smc_ib_modify_qp_error(lnk);
 	smc_wr_free_link(lnk);
 	smc_ib_destroy_queue_pair(lnk);
 	smc_ib_dealloc_protection_domain(lnk);
@@ -1336,7 +1336,7 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft)
 		else
 			tasklet_unlock_wait(&conn->rx_tsklet);
 	} else {
-		smc_cdc_tx_dismiss_slots(conn);
+		smc_cdc_wait_pend_tx_wr(conn);
 	}
 	smc_lgr_unregister_conn(conn);
 	smc_close_active_abort(smc);
@@ -1459,11 +1459,16 @@ void smc_smcd_terminate_all(struct smcd_dev *smcd)
 /* Called when an SMCR device is removed or the smc module is unloaded.
  * If smcibdev is given, all SMCR link groups using this device are terminated.
  * If smcibdev is NULL, all SMCR link groups are terminated.
+ *
+ * We must wait here for QPs been destroyed before we destroy the CQs,
+ * or we won't received any CQEs and cdc_pend_tx_wr cannot reach 0 thus
+ * smc_sock cannot be released.
  */
 void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 {
 	struct smc_link_group *lgr, *lg;
 	LIST_HEAD(lgr_free_list);
+	LIST_HEAD(lgr_linkdown_list);
 	int i;
 
 	spin_lock_bh(&smc_lgr_list.lock);
@@ -1475,7 +1480,7 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 		list_for_each_entry_safe(lgr, lg, &smc_lgr_list.list, list) {
 			for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 				if (lgr->lnk[i].smcibdev == smcibdev)
-					smcr_link_down_cond_sched(&lgr->lnk[i]);
+					list_move_tail(&lgr->list, &lgr_linkdown_list);
 			}
 		}
 	}
@@ -1487,6 +1492,16 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 		__smc_lgr_terminate(lgr, false);
 	}
 
+	list_for_each_entry_safe(lgr, lg, &lgr_linkdown_list, list) {
+		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+			if (lgr->lnk[i].smcibdev == smcibdev) {
+				mutex_lock(&lgr->llc_conf_mutex);
+				smcr_link_down_cond(&lgr->lnk[i]);
+				mutex_unlock(&lgr->llc_conf_mutex);
+			}
+		}
+	}
+
 	if (smcibdev) {
 		if (atomic_read(&smcibdev->lnk_cnt))
 			wait_event(smcibdev->lnks_deleted,
@@ -1586,7 +1601,6 @@ static void smcr_link_down(struct smc_link *lnk)
 	if (!lgr || lnk->state == SMC_LNK_UNUSED || list_empty(&lgr->list))
 		return;
 
-	smc_ib_modify_qp_reset(lnk);
 	to_lnk = smc_switch_conns(lgr, lnk, true);
 	if (!to_lnk) { /* no backup link available */
 		smcr_link_clear(lnk, true);
@@ -1824,6 +1838,7 @@ create:
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
 	conn->urg_state = SMC_URG_READ;
+	init_waitqueue_head(&conn->cdc_pend_tx_wq);
 	INIT_WORK(&smc->conn.abort_work, smc_conn_abort_work);
 	if (ini->is_smcd) {
 		conn->rx_off = sizeof(struct smcd_cdc_msg);