From: Valentin Schneider Date: Sat, 12 Jul 2025 03:33:48 +0000 (+0000) Subject: sched: Fix proxy/current (push,pull)ability X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=be39617e38e0b1939a6014d77ee6f14707d59b1b;p=thirdparty%2Flinux.git sched: Fix proxy/current (push,pull)ability Proxy execution forms atomic pairs of tasks: The waiting donor task (scheduling context) and a proxy (execution context). The donor task, along with the rest of the blocked chain, follows the proxy wrt CPU placement. They can be the same task, in which case push/pull doesn't need any modification. When they are different, however, FIFO1 & FIFO42: ,-> RT42 | | blocked-on | v blocked_donor | mutex | | owner | v `-- RT1 RT1 RT42 CPU0 CPU1 ^ ^ | | overloaded !overloaded rq prio = 42 rq prio = 0 RT1 is eligible to be pushed to CPU1, but should that happen it will "carry" RT42 along. Clearly here neither RT1 nor RT42 must be seen as push/pullable. Unfortunately, only the donor task is usually dequeued from the rq, and the proxy'ed execution context (rq->curr) remains on the rq. This can cause RT1 to be selected for migration from logic like the rt pushable_list. Thus, adda a dequeue/enqueue cycle on the proxy task before __schedule returns, which allows the sched class logic to avoid adding the now current task to the pushable_list. Furthermore, tasks becoming blocked on a mutex don't need an explicit dequeue/enqueue cycle to be made (push/pull)able: they have to be running to block on a mutex, thus they will eventually hit put_prev_task(). Signed-off-by: Valentin Schneider Signed-off-by: Connor O'Brien Signed-off-by: John Stultz Signed-off-by: Peter Zijlstra (Intel) Tested-by: K Prateek Nayak Link: https://lkml.kernel.org/r/20250712033407.2383110-8-jstultz@google.com --- diff --git a/kernel/sched/core.c b/kernel/sched/core.c index cb55d4247e65e..a0b11201a7b4e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6654,6 +6654,23 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf) } #endif /* SCHED_PROXY_EXEC */ +static inline void proxy_tag_curr(struct rq *rq, struct task_struct *owner) +{ + if (!sched_proxy_exec()) + return; + /* + * pick_next_task() calls set_next_task() on the chosen task + * at some point, which ensures it is not push/pullable. + * However, the chosen/donor task *and* the mutex owner form an + * atomic pair wrt push/pull. + * + * Make sure owner we run is not pushable. Unfortunately we can + * only deal with that by means of a dequeue/enqueue cycle. :-/ + */ + dequeue_task(rq, owner, DEQUEUE_NOCLOCK | DEQUEUE_SAVE); + enqueue_task(rq, owner, ENQUEUE_NOCLOCK | ENQUEUE_RESTORE); +} + /* * __schedule() is the main scheduler function. * @@ -6798,6 +6815,10 @@ picked: * changes to task_struct made by pick_next_task(). */ RCU_INIT_POINTER(rq->curr, next); + + if (!task_current_donor(rq, next)) + proxy_tag_curr(rq, next); + /* * The membarrier system call requires each architecture * to have a full memory barrier after updating @@ -6832,6 +6853,10 @@ picked: /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); } else { + /* In case next was already curr but just got blocked_donor */ + if (!task_current_donor(rq, next)) + proxy_tag_curr(rq, next); + rq_unpin_lock(rq, &rf); __balance_callbacks(rq); raw_spin_rq_unlock_irq(rq); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 1af06e48227dd..e2d51f4306b31 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2121,6 +2121,9 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) if (dl_server(&p->dl)) return; + if (task_is_blocked(p)) + return; + if (!task_current(rq, p) && !p->dl.dl_throttled && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -2415,6 +2418,10 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct task_s update_curr_dl(rq); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); + + if (task_is_blocked(p)) + return; + if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index be6e9bcbe82b6..7936d43337313 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1440,6 +1440,9 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) enqueue_rt_entity(rt_se, flags); + if (task_is_blocked(p)) + return; + if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } @@ -1716,6 +1719,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_s update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1); + if (task_is_blocked(p)) + return; /* * The previous task needs to be made eligible for pushing * if it is still active