From de3bf8893c5067f2c4d7ef3c57144c134e30ad7f Mon Sep 17 00:00:00 2001 From: Steffen Dirkwinkel Date: Mon, 20 Mar 2023 09:03:47 +0100 Subject: [PATCH 318/323] kernel: fork: set wake_q_sleeper.next=NULL again in dup_task_struct Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/5.10/older/patches-5.10.204-rt100.tar.xz Without this we get system hangs within a couple of days. It's also reproducible in minutes with "stress-ng --exec 20". Example error in dmesg: INFO: task stress-ng:163916 blocked for more than 120 seconds. Not tainted 5.10.168-rt83 #2 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:stress-ng state:D stack: 0 pid:163916 ppid: 72833 flags:0x00004000 Call Trace: __schedule+0x2bd/0x940 preempt_schedule_lock+0x23/0x50 rt_spin_lock_slowlock_locked+0x117/0x2c0 rt_spin_lock_slowlock+0x51/0x80 rt_write_lock+0x1e/0x1c0 do_exit+0x3ac/0xb20 do_group_exit+0x39/0xb0 get_signal+0x145/0x960 ? wake_up_new_task+0x21f/0x3c0 arch_do_signal_or_restart+0xf1/0x830 ? __x64_sys_futex+0x146/0x1d0 exit_to_user_mode_prepare+0x116/0x1a0 syscall_exit_to_user_mode+0x28/0x190 entry_SYSCALL_64_after_hwframe+0x61/0xc6 RIP: 0033:0x7f738d9074a7 RSP: 002b:00007ffdafda3cb0 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: fffffffffffffe00 RBX: 00000000000000ca RCX: 00007f738d9074a7 RDX: 0000000000028051 RSI: 0000000000000000 RDI: 00007f738be949d0 RBP: 00007ffdafda3d88 R08: 0000000000000000 R09: 00007f738be94700 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000028051 R13: 00007f738be949d0 R14: 00007ffdafda51e0 R15: 00007f738be94700 Fixes: 1ba44dcf789d ("Merge tag 'v5.10.162' into v5.10-rt") Acked-by: Joe Korty Signed-off-by: Steffen Dirkwinkel Signed-off-by: Luis Claudio R. Goncalves --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/fork.c b/kernel/fork.c index dfefb6e7e082..5dc7abedf08f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -960,6 +960,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; + tsk->wake_q_sleeper.next = NULL; tsk->pf_io_worker = NULL; account_kernel_stack(tsk, 1); -- 2.43.0