On Mon, 2011-09-12 at 16:53 +0200, Mike Galbraith wrote: > On Mon, 2011-09-12 at 15:52 +0200, Mike Galbraith wrote: > > > 36717 <...>-6266 [002] 242.543129: sys_semop <-system_call_fastpath > > 36718 <...>-6266 [002] 242.543129: sys_semtimedop <-sys_semop > > 36719 <...>-6266 [002] 242.543131: ipc_lock_check <-sys_semtimedop > > 36720 <...>-6266 [002] 242.543131: ipc_lock <-ipc_lock_check > > 36721 <...>-6266 [002] 242.543132: __rcu_read_lock <-ipc_lock > > 36722 <...>-6266 [002] 242.543133: migrate_disable <-ipc_lock > > 36723 <...>-6266 [002] 242.543134: migrate_disable: migrate_disable: in_atomic:0 p->migrate_disable_atomic:0 p->migrate_disable:0 > > 36724 <...>-6266 [002] 242.543134: pin_current_cpu <-migrate_disable > > 36725 <...>-6266 [002] 242.543134: _raw_spin_lock_irqsave <-migrate_disable > > 36726 <...>-6266 [002] 242.543135: _raw_spin_unlock_irqrestore <-migrate_disable > > 36727 <...>-6266 [002] 242.543135: rt_spin_lock <-ipc_lock > > 36728 <...>-6266 [002] 242.543136: ipcperms <-sys_semtimedop > > 36729 <...>-6266 [002] 242.543137: ns_capable <-ipcperms > > 36730 <...>-6266 [002] 242.543138: cap_capable <-ns_capable > > 36731 <...>-6266 [002] 242.543138: pid_vnr <-sys_semtimedop > > 36732 <...>-6266 [002] 242.543139: try_atomic_semop <-sys_semtimedop > > 36733 <...>-6266 [002] 242.543140: do_smart_update <-sys_semtimedop > > 36734 <...>-6266 [002] 242.543140: update_queue <-do_smart_update > > 36735 <...>-6266 [002] 242.543141: try_atomic_semop <-update_queue > > 36736 <...>-6266 [002] 242.543142: update_queue <-do_smart_update > > 36737 <...>-6266 [002] 242.543142: try_atomic_semop <-update_queue > > 36738 <...>-6266 [002] 242.543143: update_queue <-do_smart_update > > 36739 <...>-6266 [002] 242.543143: try_atomic_semop <-update_queue > > 36740 <...>-6266 [002] 242.543144: get_seconds <-do_smart_update > > 36741 <...>-6266 [002] 242.543144: rt_spin_unlock <-sys_semtimedop > > 36742 <...>-6266 [002] 242.543144: migrate_enable <-sys_semtimedop > > 36743 <...>-6266 [002] 242.543145: migrate_enable: migrate_enable: in_atomic:1 p->migrate_disable_atomic:0 p->migrate_disable:1 > > Hm. Seems this is home grown a non-preemptive wakeup in the making. Does the below cure things? It breaks !rt builds, but we can cure that if it works.. --- include/linux/sem.h | 2 ++ ipc/sem.c | 20 ++++---------------- 2 files changed, 6 insertions(+), 16 deletions(-) Index: linux-rt/include/linux/sem.h =================================================================== --- linux-rt.orig/include/linux/sem.h +++ linux-rt/include/linux/sem.h @@ -80,6 +80,7 @@ struct seminfo { #include <asm/atomic.h> #include <linux/rcupdate.h> #include <linux/cache.h> +#include <linux/wait.h> struct task_struct; @@ -114,6 +115,7 @@ struct sem_queue { struct sembuf *sops; /* array of pending operations */ int nsops; /* number of operations */ int alter; /* does the operation alter the array? */ + wait_queue_head_t wait; }; /* Each task has a list of undo requests. They are executed automatically Index: linux-rt/ipc/sem.c =================================================================== --- linux-rt.orig/ipc/sem.c +++ linux-rt/ipc/sem.c @@ -415,13 +415,6 @@ static int try_atomic_semop (struct sem_ static void wake_up_sem_queue_prepare(struct list_head *pt, struct sem_queue *q, int error) { - if (list_empty(pt)) { - /* - * Hold preempt off so that we don't get preempted and have the - * wakee busy-wait until we're scheduled back on. - */ - preempt_disable(); - } q->status = IN_WAKEUP; q->pid = error; @@ -450,7 +443,7 @@ static void wake_up_sem_queue_do(struct q->status = q->pid; } if (did_something) - preempt_enable(); + wake_up_all(&q->wait); } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) @@ -1275,15 +1268,9 @@ static struct sem_undo *find_alloc_undo( */ static int get_queue_result(struct sem_queue *q) { - int error; - - error = q->status; - while (unlikely(error == IN_WAKEUP)) { - cpu_relax(); - error = q->status; - } + wait_event(q->wait, ACCESS_ONCE(q->status) != IN_WAKEUP); - return error; + return q->status; } @@ -1432,6 +1419,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, queue.status = -EINTR; queue.sleeper = current; + init_waitqueue_head(&queue.wait); current->state = TASK_INTERRUPTIBLE; sem_unlock(sma); -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html