From: Eric Dumazet edumazet@google.com
commit 6935c3983b246d5fbfebd3b891c825e65c118f2d upstream.
The rcu_gp_fqs_check_wake() function uses rcu_preempt_blocked_readers_cgp() to read ->gp_tasks while other cpus might overwrite this field.
We need READ_ONCE()/WRITE_ONCE() pairs to avoid compiler tricks and KCSAN splats like the following :
BUG: KCSAN: data-race in rcu_gp_fqs_check_wake / rcu_preempt_deferred_qs_irqrestore
write to 0xffffffff85a7f190 of 8 bytes by task 7317 on cpu 0: rcu_preempt_deferred_qs_irqrestore+0x43d/0x580 kernel/rcu/tree_plugin.h:507 rcu_read_unlock_special+0xec/0x370 kernel/rcu/tree_plugin.h:659 __rcu_read_unlock+0xcf/0xe0 kernel/rcu/tree_plugin.h:394 rcu_read_unlock include/linux/rcupdate.h:645 [inline] __ip_queue_xmit+0x3b0/0xa40 net/ipv4/ip_output.c:533 ip_queue_xmit+0x45/0x60 include/net/ip.h:236 __tcp_transmit_skb+0xdeb/0x1cd0 net/ipv4/tcp_output.c:1158 __tcp_send_ack+0x246/0x300 net/ipv4/tcp_output.c:3685 tcp_send_ack+0x34/0x40 net/ipv4/tcp_output.c:3691 tcp_cleanup_rbuf+0x130/0x360 net/ipv4/tcp.c:1575 tcp_recvmsg+0x633/0x1a30 net/ipv4/tcp.c:2179 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838 sock_recvmsg_nosec net/socket.c:871 [inline] sock_recvmsg net/socket.c:889 [inline] sock_recvmsg+0x92/0xb0 net/socket.c:885 sock_read_iter+0x15f/0x1e0 net/socket.c:967 call_read_iter include/linux/fs.h:1864 [inline] new_sync_read+0x389/0x4f0 fs/read_write.c:414
read to 0xffffffff85a7f190 of 8 bytes by task 10 on cpu 1: rcu_gp_fqs_check_wake kernel/rcu/tree.c:1556 [inline] rcu_gp_fqs_check_wake+0x93/0xd0 kernel/rcu/tree.c:1546 rcu_gp_fqs_loop+0x36c/0x580 kernel/rcu/tree.c:1611 rcu_gp_kthread+0x143/0x220 kernel/rcu/tree.c:1768 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352
Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 10 Comm: rcu_preempt Not tainted 5.3.0+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com [ paulmck: Added another READ_ONCE() for RCU CPU stall warnings. ] Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/rcu/tree_plugin.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index a97c20e..5f6de49 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -267,7 +267,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * blocked tasks. */ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) { - rnp->gp_tasks = &t->rcu_node_entry; + WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry); WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq); } if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) @@ -392,7 +392,7 @@ static void rcu_preempt_note_context_switch(bool preempt) */ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) { - return rnp->gp_tasks != NULL; + return READ_ONCE(rnp->gp_tasks) != NULL; }
/* @@ -557,7 +557,7 @@ static void rcu_read_unlock_special(struct task_struct *t) trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), rnp->gp_seq, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) - rnp->gp_tasks = np; + WRITE_ONCE(rnp->gp_tasks, np); if (&t->rcu_node_entry == rnp->exp_tasks) rnp->exp_tasks = np; if (IS_ENABLED(CONFIG_RCU_BOOST)) { @@ -716,7 +716,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) dump_blkd_tasks(rsp, rnp, 10); if (rcu_preempt_has_tasks(rnp) && (rnp->qsmaskinit || rnp->wait_blkd_tasks)) { - rnp->gp_tasks = rnp->blkd_tasks.next; + WRITE_ONCE(rnp->gp_tasks, rnp->blkd_tasks.next); t = container_of(rnp->gp_tasks, struct task_struct, rcu_node_entry); trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"), @@ -883,7 +883,8 @@ void exit_rcu(void) pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n", __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext); pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n", - __func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks); + __func__, READ_ONCE(rnp->gp_tasks), rnp->boost_tasks, + rnp->exp_tasks); pr_info("%s: ->blkd_tasks", __func__); i = 0; list_for_each(lhp, &rnp->blkd_tasks) {