From 18853ba782bef65fc81ef2b3370382e5b479c5eb Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Tue, 22 Apr 2025 10:26:32 +0200 Subject: sched_ext: Track currently locked rq Some kfuncs provided by sched_ext may need to operate on a struct rq, but they can be invoked from various contexts, specifically, different scx callbacks. While some of these callbacks are invoked with a particular rq already locked, others are not. This makes it impossible for a kfunc to reliably determine whether it's safe to access a given rq, triggering potential bugs or unsafe behaviors, see for example [1]. To address this, track the currently locked rq whenever a sched_ext callback is invoked via SCX_CALL_OP*(). This allows kfuncs that need to operate on an arbitrary rq to retrieve the currently locked one and apply the appropriate action as needed. [1] https://lore.kernel.org/lkml/20250325140021.73570-1-arighi@nvidia.com/ Suggested-by: Tejun Heo Signed-off-by: Andrea Righi Acked-by: Changwoo Min Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 152 ++++++++++++++++++++++++++++++------------------ kernel/sched/ext_idle.c | 2 +- 2 files changed, 95 insertions(+), 59 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index fdbf249d1c68..585bf6d8238b 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1118,8 +1118,38 @@ static void scx_kf_disallow(u32 mask) current->scx.kf_mask &= ~mask; } -#define SCX_CALL_OP(mask, op, args...) \ +/* + * Track the rq currently locked. + * + * This allows kfuncs to safely operate on rq from any scx ops callback, + * knowing which rq is already locked. + */ +static DEFINE_PER_CPU(struct rq *, locked_rq); + +static inline void update_locked_rq(struct rq *rq) +{ + /* + * Check whether @rq is actually locked. This can help expose bugs + * or incorrect assumptions about the context in which a kfunc or + * callback is executed. + */ + if (rq) + lockdep_assert_rq_held(rq); + __this_cpu_write(locked_rq, rq); +} + +/* + * Return the rq currently locked from an scx callback, or NULL if no rq is + * locked. + */ +static inline struct rq *scx_locked_rq(void) +{ + return __this_cpu_read(locked_rq); +} + +#define SCX_CALL_OP(mask, op, rq, args...) \ do { \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ scx_ops.op(args); \ @@ -1127,11 +1157,14 @@ do { \ } else { \ scx_ops.op(args); \ } \ + update_locked_rq(NULL); \ } while (0) -#define SCX_CALL_OP_RET(mask, op, args...) \ +#define SCX_CALL_OP_RET(mask, op, rq, args...) \ ({ \ __typeof__(scx_ops.op(args)) __ret; \ + \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ __ret = scx_ops.op(args); \ @@ -1139,6 +1172,7 @@ do { \ } else { \ __ret = scx_ops.op(args); \ } \ + update_locked_rq(NULL); \ __ret; \ }) @@ -1153,31 +1187,31 @@ do { \ * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on * the specific task. */ -#define SCX_CALL_OP_TASK(mask, op, task, args...) \ +#define SCX_CALL_OP_TASK(mask, op, rq, task, args...) \ do { \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task; \ - SCX_CALL_OP(mask, op, task, ##args); \ + SCX_CALL_OP(mask, op, rq, task, ##args); \ current->scx.kf_tasks[0] = NULL; \ } while (0) -#define SCX_CALL_OP_TASK_RET(mask, op, task, args...) \ +#define SCX_CALL_OP_TASK_RET(mask, op, rq, task, args...) \ ({ \ __typeof__(scx_ops.op(task, ##args)) __ret; \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task; \ - __ret = SCX_CALL_OP_RET(mask, op, task, ##args); \ + __ret = SCX_CALL_OP_RET(mask, op, rq, task, ##args); \ current->scx.kf_tasks[0] = NULL; \ __ret; \ }) -#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...) \ +#define SCX_CALL_OP_2TASKS_RET(mask, op, rq, task0, task1, args...) \ ({ \ __typeof__(scx_ops.op(task0, task1, ##args)) __ret; \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task0; \ current->scx.kf_tasks[1] = task1; \ - __ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args); \ + __ret = SCX_CALL_OP_RET(mask, op, rq, task0, task1, ##args); \ current->scx.kf_tasks[0] = NULL; \ current->scx.kf_tasks[1] = NULL; \ __ret; \ @@ -2172,7 +2206,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, WARN_ON_ONCE(*ddsp_taskp); *ddsp_taskp = p; - SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags); + SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, rq, p, enq_flags); *ddsp_taskp = NULL; if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) @@ -2269,7 +2303,7 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags add_nr_running(rq, 1); if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p)) - SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, runnable, rq, p, enq_flags); if (enq_flags & SCX_ENQ_WAKEUP) touch_core_sched(rq, p); @@ -2283,7 +2317,7 @@ out: __scx_add_event(SCX_EV_SELECT_CPU_FALLBACK, 1); } -static void ops_dequeue(struct task_struct *p, u64 deq_flags) +static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags) { unsigned long opss; @@ -2304,7 +2338,7 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags) BUG(); case SCX_OPSS_QUEUED: if (SCX_HAS_OP(dequeue)) - SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, rq, p, deq_flags); if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss, SCX_OPSS_NONE)) @@ -2337,7 +2371,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags return true; } - ops_dequeue(p, deq_flags); + ops_dequeue(rq, p, deq_flags); /* * A currently running task which is going off @rq first gets dequeued @@ -2353,11 +2387,11 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags */ if (SCX_HAS_OP(stopping) && task_current(rq, p)) { update_curr_scx(rq); - SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, false); } if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p)) - SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, rq, p, deq_flags); if (deq_flags & SCX_DEQ_SLEEP) p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP; @@ -2377,7 +2411,7 @@ static void yield_task_scx(struct rq *rq) struct task_struct *p = rq->curr; if (SCX_HAS_OP(yield)) - SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL); + SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, p, NULL); else p->scx.slice = 0; } @@ -2387,7 +2421,7 @@ static bool yield_to_task_scx(struct rq *rq, struct task_struct *to) struct task_struct *from = rq->curr; if (SCX_HAS_OP(yield)) - return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to); + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, from, to); else return false; } @@ -2945,7 +2979,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) * emitted in switch_class(). */ if (SCX_HAS_OP(cpu_acquire)) - SCX_CALL_OP(SCX_KF_REST, cpu_acquire, cpu_of(rq), NULL); + SCX_CALL_OP(SCX_KF_REST, cpu_acquire, rq, cpu_of(rq), NULL); rq->scx.cpu_released = false; } @@ -2990,7 +3024,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) do { dspc->nr_tasks = 0; - SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq), + SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, rq, cpu_of(rq), prev_on_scx ? prev : NULL); flush_dispatch_buf(rq); @@ -3104,7 +3138,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) * Core-sched might decide to execute @p before it is * dispatched. Call ops_dequeue() to notify the BPF scheduler. */ - ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC); + ops_dequeue(rq, p, SCX_DEQ_CORE_SCHED_EXEC); dispatch_dequeue(rq, p); } @@ -3112,7 +3146,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) /* see dequeue_task_scx() on why we skip when !QUEUED */ if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED)) - SCX_CALL_OP_TASK(SCX_KF_REST, running, p); + SCX_CALL_OP_TASK(SCX_KF_REST, running, rq, p); clr_task_runnable(p, true); @@ -3193,8 +3227,7 @@ static void switch_class(struct rq *rq, struct task_struct *next) .task = next, }; - SCX_CALL_OP(SCX_KF_CPU_RELEASE, - cpu_release, cpu_of(rq), &args); + SCX_CALL_OP(SCX_KF_CPU_RELEASE, cpu_release, rq, cpu_of(rq), &args); } rq->scx.cpu_released = true; } @@ -3207,7 +3240,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, /* see dequeue_task_scx() on why we skip when !QUEUED */ if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED)) - SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, true); if (p->scx.flags & SCX_TASK_QUEUED) { set_task_runnable(rq, p); @@ -3348,7 +3381,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, * verifier. */ if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a))) - return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, NULL, (struct task_struct *)a, (struct task_struct *)b); else @@ -3385,7 +3418,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag *ddsp_taskp = p; cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU, - select_cpu, p, prev_cpu, wake_flags); + select_cpu, NULL, p, prev_cpu, wake_flags); p->scx.selected_cpu = cpu; *ddsp_taskp = NULL; if (ops_cpu_valid(cpu, "from ops.select_cpu()")) @@ -3430,8 +3463,8 @@ static void set_cpus_allowed_scx(struct task_struct *p, * designation pointless. Cast it away when calling the operation. */ if (SCX_HAS_OP(set_cpumask)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p, - (struct cpumask *)p->cpus_ptr); + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, NULL, + p, (struct cpumask *)p->cpus_ptr); } static void handle_hotplug(struct rq *rq, bool online) @@ -3444,9 +3477,9 @@ static void handle_hotplug(struct rq *rq, bool online) scx_idle_update_selcpu_topology(&scx_ops); if (online && SCX_HAS_OP(cpu_online)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, rq, cpu); else if (!online && SCX_HAS_OP(cpu_offline)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, rq, cpu); else scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG, "cpu %d going %s, exiting scheduler", cpu, @@ -3550,7 +3583,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) curr->scx.slice = 0; touch_core_sched(rq, curr); } else if (SCX_HAS_OP(tick)) { - SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr); + SCX_CALL_OP_TASK(SCX_KF_REST, tick, rq, curr); } if (!curr->scx.slice) @@ -3627,7 +3660,7 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool .fork = fork, }; - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args); + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, NULL, p, &args); if (unlikely(ret)) { ret = ops_sanitize_err("init_task", ret); return ret; @@ -3668,9 +3701,10 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool static void scx_ops_enable_task(struct task_struct *p) { + struct rq *rq = task_rq(p); u32 weight; - lockdep_assert_rq_held(task_rq(p)); + lockdep_assert_rq_held(rq); /* * Set the weight before calling ops.enable() so that the scheduler @@ -3684,20 +3718,22 @@ static void scx_ops_enable_task(struct task_struct *p) p->scx.weight = sched_weight_to_cgroup(weight); if (SCX_HAS_OP(enable)) - SCX_CALL_OP_TASK(SCX_KF_REST, enable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, enable, rq, p); scx_set_task_state(p, SCX_TASK_ENABLED); if (SCX_HAS_OP(set_weight)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight); + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight); } static void scx_ops_disable_task(struct task_struct *p) { - lockdep_assert_rq_held(task_rq(p)); + struct rq *rq = task_rq(p); + + lockdep_assert_rq_held(rq); WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED); if (SCX_HAS_OP(disable)) - SCX_CALL_OP_TASK(SCX_KF_REST, disable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, disable, rq, p); scx_set_task_state(p, SCX_TASK_READY); } @@ -3726,7 +3762,7 @@ static void scx_ops_exit_task(struct task_struct *p) } if (SCX_HAS_OP(exit_task)) - SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args); + SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, task_rq(p), p, &args); scx_set_task_state(p, SCX_TASK_NONE); } @@ -3835,7 +3871,7 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p, p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight)); if (SCX_HAS_OP(set_weight)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight); + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight); } static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio) @@ -3851,8 +3887,8 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p) * different scheduler class. Keep the BPF scheduler up-to-date. */ if (SCX_HAS_OP(set_cpumask)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p, - (struct cpumask *)p->cpus_ptr); + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, rq, + p, (struct cpumask *)p->cpus_ptr); } static void switched_from_scx(struct rq *rq, struct task_struct *p) @@ -3913,7 +3949,7 @@ int scx_tg_online(struct task_group *tg) struct scx_cgroup_init_args args = { .weight = tg->scx_weight }; - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL, tg->css.cgroup, &args); if (ret) ret = ops_sanitize_err("cgroup_init", ret); @@ -3935,7 +3971,7 @@ void scx_tg_offline(struct task_group *tg) percpu_down_read(&scx_cgroup_rwsem); if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, tg->css.cgroup); tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED); percpu_up_read(&scx_cgroup_rwsem); @@ -3968,7 +4004,7 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset) continue; if (SCX_HAS_OP(cgroup_prep_move)) { - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, NULL, p, from, css->cgroup); if (ret) goto err; @@ -3982,8 +4018,8 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset) err: cgroup_taskset_for_each(p, css, tset) { if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p, - p->scx.cgrp_moving_from, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL, + p, p->scx.cgrp_moving_from, css->cgroup); p->scx.cgrp_moving_from = NULL; } @@ -4001,8 +4037,8 @@ void scx_cgroup_move_task(struct task_struct *p) * cgrp_moving_from set. */ if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from)) - SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p, - p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); + SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, NULL, + p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); p->scx.cgrp_moving_from = NULL; } @@ -4021,8 +4057,8 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) cgroup_taskset_for_each(p, css, tset) { if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p, - p->scx.cgrp_moving_from, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL, + p, p->scx.cgrp_moving_from, css->cgroup); p->scx.cgrp_moving_from = NULL; } out_unlock: @@ -4035,7 +4071,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) if (scx_cgroup_enabled && tg->scx_weight != weight) { if (SCX_HAS_OP(cgroup_set_weight)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, NULL, tg_cgrp(tg), weight); tg->scx_weight = weight; } @@ -4224,7 +4260,7 @@ static void scx_cgroup_exit(void) continue; rcu_read_unlock(); - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, css->cgroup); rcu_read_lock(); css_put(css); @@ -4261,7 +4297,7 @@ static int scx_cgroup_init(void) continue; rcu_read_unlock(); - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL, css->cgroup, &args); if (ret) { css_put(css); @@ -4758,7 +4794,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) } if (scx_ops.exit) - SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei); + SCX_CALL_OP(SCX_KF_UNLOCKED, exit, NULL, ei); cancel_delayed_work_sync(&scx_watchdog_work); @@ -4965,7 +5001,7 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, if (SCX_HAS_OP(dump_task)) { ops_dump_init(s, " "); - SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p); + SCX_CALL_OP(SCX_KF_REST, dump_task, NULL, dctx, p); ops_dump_exit(); } @@ -5012,7 +5048,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) if (SCX_HAS_OP(dump)) { ops_dump_init(&s, ""); - SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx); + SCX_CALL_OP(SCX_KF_UNLOCKED, dump, NULL, &dctx); ops_dump_exit(); } @@ -5069,7 +5105,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) used = seq_buf_used(&ns); if (SCX_HAS_OP(dump_cpu)) { ops_dump_init(&ns, " "); - SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle); + SCX_CALL_OP(SCX_KF_REST, dump_cpu, NULL, &dctx, cpu, idle); ops_dump_exit(); } @@ -5328,7 +5364,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_idle_enable(ops); if (scx_ops.init) { - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init); + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init, NULL); if (ret) { ret = ops_sanitize_err("init", ret); cpus_read_unlock(); diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index cb343ca889e0..e67a19a071c1 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -674,7 +674,7 @@ void __scx_update_idle(struct rq *rq, bool idle, bool do_notify) * managed by put_prev_task_idle()/set_next_task_idle(). */ if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq)) - SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); + SCX_CALL_OP(SCX_KF_REST, update_idle, rq, cpu_of(rq), idle); /* * Update the idle masks: -- cgit v1.2.3 From a11d6784d7316a6c77ca9f14fb1a698ebbb3c1fb Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Tue, 22 Apr 2025 10:26:33 +0200 Subject: sched_ext: Fix missing rq lock in scx_bpf_cpuperf_set() scx_bpf_cpuperf_set() can be used to set a performance target level on any CPU. However, it doesn't correctly acquire the corresponding rq lock, which may lead to unsafe behavior and trigger the following warning, due to the lockdep_assert_rq_held() check: [ 51.713737] WARNING: CPU: 3 PID: 3899 at kernel/sched/sched.h:1512 scx_bpf_cpuperf_set+0x1a0/0x1e0 ... [ 51.713836] Call trace: [ 51.713837] scx_bpf_cpuperf_set+0x1a0/0x1e0 (P) [ 51.713839] bpf_prog_62d35beb9301601f_bpfland_init+0x168/0x440 [ 51.713841] bpf__sched_ext_ops_init+0x54/0x8c [ 51.713843] scx_ops_enable.constprop.0+0x2c0/0x10f0 [ 51.713845] bpf_scx_reg+0x18/0x30 [ 51.713847] bpf_struct_ops_link_create+0x154/0x1b0 [ 51.713849] __sys_bpf+0x1934/0x22a0 Fix by properly acquiring the rq lock when possible or raising an error if we try to operate on a CPU that is not the one currently locked. Fixes: d86adb4fc0655 ("sched_ext: Add cpuperf support") Signed-off-by: Andrea Righi Acked-by: Changwoo Min Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 585bf6d8238b..ac79067dc87e 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -7113,13 +7113,32 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf) } if (ops_cpu_valid(cpu, NULL)) { - struct rq *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq(); + struct rq_flags rf; + + /* + * When called with an rq lock held, restrict the operation + * to the corresponding CPU to prevent ABBA deadlocks. + */ + if (locked_rq && rq != locked_rq) { + scx_ops_error("Invalid target CPU %d", cpu); + return; + } + + /* + * If no rq lock is held, allow to operate on any CPU by + * acquiring the corresponding rq lock. + */ + if (!locked_rq) { + rq_lock_irqsave(rq, &rf); + update_rq_clock(rq); + } rq->scx.cpuperf_target = perf; + cpufreq_update_util(rq, 0); - rcu_read_lock_sched_notrace(); - cpufreq_update_util(cpu_rq(cpu), 0); - rcu_read_unlock_sched_notrace(); + if (!locked_rq) + rq_unlock_irqrestore(rq, &rf); } } -- cgit v1.2.3 From e7dcd1304b9ac08c428c84fdb96ce6a04ff2114f Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Fri, 25 Apr 2025 19:57:02 +0200 Subject: sched_ext: Remove duplicate BTF_ID_FLAGS definitions Some kfuncs specific to the idle CPU selection policy are registered in both the scx_kfunc_ids_any and scx_kfunc_ids_idle blocks, even though they should only be defined in the latter. Remove the duplicates from scx_kfunc_ids_any. Fixes: 337d1b354a297 ("sched_ext: Move built-in idle CPU selection policy to a separate file") Signed-off-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index ac79067dc87e..dddb0af36f8d 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -7369,12 +7369,6 @@ BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids) BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE) -BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE) -BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE) -BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE) -BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle) -BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU) -BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_cpu_rq) -- cgit v1.2.3 From e38be1c7647c8c78304ce6d931b3b654e27948b3 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Mon, 28 Apr 2025 23:43:20 +0200 Subject: sched_ext: Fix rq lock state in hotplug ops The ops.cpu_online() and ops.cpu_offline() callbacks incorrectly assume that the rq involved in the operation is locked, which is not the case during hotplug, triggering the following warning: WARNING: CPU: 1 PID: 20 at kernel/sched/sched.h:1504 handle_hotplug+0x280/0x340 Fix by not tracking the target rq as locked in the context of ops.cpu_online() and ops.cpu_offline(). Fixes: 18853ba782bef ("sched_ext: Track currently locked rq") Reported-by: Tejun Heo Signed-off-by: Andrea Righi Tested-by: Changwoo Min Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index dddb0af36f8d..4e37b40ce280 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3477,9 +3477,9 @@ static void handle_hotplug(struct rq *rq, bool online) scx_idle_update_selcpu_topology(&scx_ops); if (online && SCX_HAS_OP(cpu_online)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, rq, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, NULL, cpu); else if (!online && SCX_HAS_OP(cpu_offline)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, rq, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, NULL, cpu); else scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG, "cpu %d going %s, exiting scheduler", cpu, -- cgit v1.2.3 From 428dc9fc0873989d73918d4a9cc22745b7bbc799 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 May 2025 11:30:39 -1000 Subject: sched_ext: bpf_iter_scx_dsq_new() should always initialize iterator BPF programs may call next() and destroy() on BPF iterators even after new() returns an error value (e.g. bpf_for_each() macro ignores error returns from new()). bpf_iter_scx_dsq_new() could leave the iterator in an uninitialized state after an error return causing bpf_iter_scx_dsq_next() to dereference garbage data. Make bpf_iter_scx_dsq_new() always clear $kit->dsq so that next() and destroy() become noops. Signed-off-by: Tejun Heo Fixes: 650ba21b131e ("sched_ext: Implement DSQ iterator") Cc: stable@vger.kernel.org # v6.12+ Acked-by: Andrea Righi --- kernel/sched/ext.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 4e37b40ce280..f5133249fd4d 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -6827,6 +6827,12 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) != __alignof__(struct bpf_iter_scx_dsq)); + /* + * next() and destroy() will be called regardless of the return value. + * Always clear $kit->dsq. + */ + kit->dsq = NULL; + if (flags & ~__SCX_DSQ_ITER_USER_FLAGS) return -EINVAL; -- cgit v1.2.3 From 39b5ef791d109dd54c7c2e6e87933edfcc0ad1ac Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 8 May 2025 15:24:13 -0400 Subject: cgroup/cpuset: Extend kthread_is_per_cpu() check to all PF_NO_SETAFFINITY tasks Commit ec5fbdfb99d1 ("cgroup/cpuset: Enable update_tasks_cpumask() on top_cpuset") enabled us to pull CPUs dedicated to child partitions from tasks in top_cpuset by ignoring per cpu kthreads. However, there can be other kthreads that are not per cpu but have PF_NO_SETAFFINITY flag set to indicate that we shouldn't mess with their CPU affinity. For other kthreads, their affinity will be changed to skip CPUs dedicated to child partitions whether it is an isolating or a scheduling one. As all the per cpu kthreads have PF_NO_SETAFFINITY set, the PF_NO_SETAFFINITY tasks are essentially a superset of per cpu kthreads. Fix this issue by dropping the kthread_is_per_cpu() check and checking the PF_NO_SETAFFINITY flag instead. Fixes: ec5fbdfb99d1 ("cgroup/cpuset: Enable update_tasks_cpumask() on top_cpuset") Signed-off-by: Waiman Long Acked-by: Frederic Weisbecker Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 306b60430091..24b70ea3e6ce 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1116,9 +1116,11 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) if (top_cs) { /* - * Percpu kthreads in top_cpuset are ignored + * PF_NO_SETAFFINITY tasks are ignored. + * All per cpu kthreads should have PF_NO_SETAFFINITY + * flag set, see kthread_set_per_cpu(). */ - if (kthread_is_per_cpu(task)) + if (task->flags & PF_NO_SETAFFINITY) continue; cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus); } else { -- cgit v1.2.3 From 9dda18a32b4a6693fccd3f7c0738af646147b1cf Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 10 Apr 2025 05:22:21 -0700 Subject: tracing: fprobe: Fix RCU warning message in list traversal When CONFIG_PROVE_RCU_LIST is enabled, fprobe triggers the following warning: WARNING: suspicious RCU usage kernel/trace/fprobe.c:457 RCU-list traversed in non-reader section!! other info that might help us debug this: #1: ffffffff863c4e08 (fprobe_mutex){+.+.}-{4:4}, at: fprobe_module_callback+0x7b/0x8c0 Call Trace: fprobe_module_callback notifier_call_chain blocking_notifier_call_chain This warning occurs because fprobe_remove_node_in_module() traverses an RCU list using RCU primitives without holding an RCU read lock. However, the function is only called from fprobe_module_callback(), which holds the fprobe_mutex lock that provides sufficient protection for safely traversing the list. Fix the warning by specifying the locking design to the CONFIG_PROVE_RCU_LIST mechanism. Add the lockdep_is_held() argument to hlist_for_each_entry_rcu() to inform the RCU checker that fprobe_mutex provides the required protection. Link: https://lore.kernel.org/all/20250410-fprobe-v1-1-068ef5f41436@debian.org/ Fixes: a3dc2983ca7b90 ("tracing: fprobe: Cleanup fprobe hash when module unloading") Signed-off-by: Breno Leitao Tested-by: Antonio Quartulli Tested-by: Matthieu Baerts (NGI0) Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 95c6e3473a76..ba7ff14f5339 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -454,7 +454,8 @@ static void fprobe_remove_node_in_module(struct module *mod, struct hlist_head * struct fprobe_hlist_node *node; int ret = 0; - hlist_for_each_entry_rcu(node, head, hlist) { + hlist_for_each_entry_rcu(node, head, hlist, + lockdep_is_held(&fprobe_mutex)) { if (!within_module(node->addr, mod)) continue; if (delete_fprobe_node(node)) -- cgit v1.2.3 From e41b5af4519f90f9a751805ede2102ae36caf5d0 Mon Sep 17 00:00:00 2001 From: Paul Cacheux Date: Sun, 4 May 2025 20:27:52 +0200 Subject: tracing: add missing trace_probe_log_clear for eprobes Make sure trace_probe_log_clear is called in the tracing eprobe code path, matching the trace_probe_log_init call. Link: https://lore.kernel.org/all/20250504-fix-trace-probe-log-race-v3-1-9e99fec7eddc@gmail.com/ Signed-off-by: Paul Cacheux Acked-by: Steven Rostedt (Google) Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_eprobe.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index c08355c3ef32..916555f0de81 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -969,10 +969,13 @@ static int __trace_eprobe_create(int argc, const char *argv[]) goto error; } } + trace_probe_log_clear(); return ret; + parse_error: ret = -EINVAL; error: + trace_probe_log_clear(); trace_event_probe_cleanup(ep); return ret; } -- cgit v1.2.3 From e9f180d7cfde23b9f8eebd60272465176373ab2c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 22 Apr 2025 16:49:42 +0200 Subject: kernel/fork: only call untrack_pfn_clear() on VMAs duplicated for fork() Not intuitive, but vm_area_dup() located in kernel/fork.c is not only used for duplicating VMAs during fork(), but also for duplicating VMAs when splitting VMAs or when mremap()'ing them. VM_PFNMAP mappings can at least get ordinarily mremap()'ed (no change in size) and apparently also shrunk during mremap(), which implies duplicating the VMA in __split_vma() first. In case of ordinary mremap() (no change in size), we first duplicate the VMA in copy_vma_and_data()->copy_vma() to then call untrack_pfn_clear() on the old VMA: we effectively move the VM_PAT reservation. So the untrack_pfn_clear() call on the new VMA duplicating is wrong in that context. Splitting of VMAs seems problematic, because we don't duplicate/adjust the reservation when splitting the VMA. Instead, in memtype_erase() -- called during zapping/munmap -- we shrink a reservation in case only the end address matches: Assume we split a VMA into A and B, both would share a reservation until B is unmapped. So when unmapping B, the reservation would be updated to cover only A. When unmapping A, we would properly remove the now-shrunk reservation. That scenario describes the mremap() shrinking (old_size > new_size), where we split + unmap B, and the untrack_pfn_clear() on the new VMA when is wrong. What if we manage to split a VM_PFNMAP VMA into A and B and unmap A first? It would be broken because we would never free the reservation. Likely, there are ways to trigger such a VMA split outside of mremap(). Affecting other VMA duplication was not intended, vm_area_dup() being used outside of kernel/fork.c was an oversight. So let's fix that for; how to handle VMA splits better should be investigated separately. With a simple reproducer that uses mprotect() to split such a VMA I can trigger x86/PAT: pat_mremap:26448 freeing invalid memtype [mem 0x00000000-0x00000fff] Link: https://lkml.kernel.org/r/20250422144942.2871395-1-david@redhat.com Fixes: dc84bc2aba85 ("x86/mm/pat: Fix VM_PAT handling when fork() fails in copy_page_range()") Signed-off-by: David Hildenbrand Reviewed-by: Lorenzo Stoakes Cc: Ingo Molnar Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Borislav Petkov Cc: Rik van Riel Cc: "H. Peter Anvin" Cc: Linus Torvalds Signed-off-by: Andrew Morton --- kernel/fork.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index c4b26cd8998b..168681fc4b25 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -498,10 +498,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) vma_numab_state_init(new); dup_anon_vma_name(orig, new); - /* track_pfn_copy() will later take care of copying internal state. */ - if (unlikely(new->vm_flags & VM_PFNMAP)) - untrack_pfn_clear(new); - return new; } @@ -672,6 +668,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; + + /* track_pfn_copy() will later take care of copying internal state. */ + if (unlikely(tmp->vm_flags & VM_PFNMAP)) + untrack_pfn_clear(tmp); + retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; -- cgit v1.2.3 From 9520a2b3f0b5e182f73410e45b9b92ea51d9b828 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 7 Apr 2025 23:08:44 +0000 Subject: kbuild: Require pahole v1.29 with GENDWARFKSYMS on X86 With CONFIG_GENDWARFKSYMS, __gendwarfksyms_ptr variables are added to the kernel in EXPORT_SYMBOL() to ensure DWARF type information is available for exported symbols in the TUs where they're actually exported. These symbols are dropped when linking vmlinux, but dangling references to them remain in DWARF. With CONFIG_DEBUG_INFO_BTF enabled on X86, pahole versions after commit 47dcb534e253 ("btf_encoder: Stop indexing symbols for VARs") and before commit 9810758003ce ("btf_encoder: Verify 0 address DWARF variables are in ELF section") place these symbols in the .data..percpu section, which results in an "Invalid offset" error in btf_datasec_check_meta() during boot, as all the variables are at zero offset and have non-zero size. If CONFIG_DEBUG_INFO_BTF_MODULES is enabled, this also results in a failure to load modules with: failed to validate module [$module] BTF: -22 As the issue occurs in pahole v1.28 and the fix was merged after v1.29 was released, require pahole v1.29 when GENDWARFKSYMS is enabled with DEBUG_INFO_BTF on X86. Reported-by: Paolo Pisati Signed-off-by: Sami Tolvanen Signed-off-by: Masahiro Yamada --- kernel/module/Kconfig | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index d7762ef5949a..39278737bb68 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -192,6 +192,11 @@ config GENDWARFKSYMS depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT # Requires ELF object files. depends on !LTO + # To avoid conflicts with the discarded __gendwarfksyms_ptr symbols on + # X86, requires pahole before commit 47dcb534e253 ("btf_encoder: Stop + # indexing symbols for VARs") or after commit 9810758003ce ("btf_encoder: + # Verify 0 address DWARF variables are in ELF section"). + depends on !X86 || !DEBUG_INFO_BTF || PAHOLE_VERSION < 128 || PAHOLE_VERSION > 129 help Calculate symbol versions from DWARF debugging information using gendwarfksyms. Requires DEBUG_INFO to be enabled. -- cgit v1.2.3 From fd837de3c9cb1a162c69bc1fb1f438467fe7f2f5 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sat, 10 May 2025 12:44:41 +0900 Subject: tracing: probes: Fix a possible race in trace_probe_log APIs Since the shared trace_probe_log variable can be accessed and modified via probe event create operation of kprobe_events, uprobe_events, and dynamic_events, it should be protected. In the dynamic_events, all operations are serialized by `dyn_event_ops_mutex`. But kprobe_events and uprobe_events interfaces are not serialized. To solve this issue, introduces dyn_event_create(), which runs create() operation under the mutex, for kprobe_events and uprobe_events. This also uses lockdep to check the mutex is held when using trace_probe_log* APIs. Link: https://lore.kernel.org/all/174684868120.551552.3068655787654268804.stgit@devnote2/ Reported-by: Paul Cacheux Closes: https://lore.kernel.org/all/20250510074456.805a16872b591e2971a4d221@kernel.org/ Fixes: ab105a4fb894 ("tracing: Use tracing error_log with probe events") Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_dynevent.c | 16 +++++++++++++++- kernel/trace/trace_dynevent.h | 1 + kernel/trace/trace_kprobe.c | 2 +- kernel/trace/trace_probe.c | 9 +++++++++ kernel/trace/trace_uprobe.c | 2 +- 5 files changed, 27 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index a322e4f249a5..5d64a18cacac 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -16,7 +16,7 @@ #include "trace_output.h" /* for trace_event_sem */ #include "trace_dynevent.h" -static DEFINE_MUTEX(dyn_event_ops_mutex); +DEFINE_MUTEX(dyn_event_ops_mutex); static LIST_HEAD(dyn_event_ops_list); bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call) @@ -116,6 +116,20 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type return ret; } +/* + * Locked version of event creation. The event creation must be protected by + * dyn_event_ops_mutex because of protecting trace_probe_log. + */ +int dyn_event_create(const char *raw_command, struct dyn_event_operations *type) +{ + int ret; + + mutex_lock(&dyn_event_ops_mutex); + ret = type->create(raw_command); + mutex_unlock(&dyn_event_ops_mutex); + return ret; +} + static int create_dyn_event(const char *raw_command) { struct dyn_event_operations *ops; diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h index 936477a111d3..beee3f8d7544 100644 --- a/kernel/trace/trace_dynevent.h +++ b/kernel/trace/trace_dynevent.h @@ -100,6 +100,7 @@ void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos); void dyn_event_seq_stop(struct seq_file *m, void *v); int dyn_events_release_all(struct dyn_event_operations *type); int dyn_event_release(const char *raw_command, struct dyn_event_operations *type); +int dyn_event_create(const char *raw_command, struct dyn_event_operations *type); /* * for_each_dyn_event - iterate over the dyn_event list diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 2703b96d8990..3e5c47b6d7b2 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1089,7 +1089,7 @@ static int create_or_delete_trace_kprobe(const char *raw_command) if (raw_command[0] == '-') return dyn_event_release(raw_command, &trace_kprobe_ops); - ret = trace_kprobe_create(raw_command); + ret = dyn_event_create(raw_command, &trace_kprobe_ops); return ret == -ECANCELED ? -EINVAL : ret; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 2eeecb6c95ee..424751cdf31f 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -154,9 +154,12 @@ fail: } static struct trace_probe_log trace_probe_log; +extern struct mutex dyn_event_ops_mutex; void trace_probe_log_init(const char *subsystem, int argc, const char **argv) { + lockdep_assert_held(&dyn_event_ops_mutex); + trace_probe_log.subsystem = subsystem; trace_probe_log.argc = argc; trace_probe_log.argv = argv; @@ -165,11 +168,15 @@ void trace_probe_log_init(const char *subsystem, int argc, const char **argv) void trace_probe_log_clear(void) { + lockdep_assert_held(&dyn_event_ops_mutex); + memset(&trace_probe_log, 0, sizeof(trace_probe_log)); } void trace_probe_log_set_index(int index) { + lockdep_assert_held(&dyn_event_ops_mutex); + trace_probe_log.index = index; } @@ -178,6 +185,8 @@ void __trace_probe_log_err(int offset, int err_type) char *command, *p; int i, len = 0, pos = 0; + lockdep_assert_held(&dyn_event_ops_mutex); + if (!trace_probe_log.argv) return; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 3386439ec9f6..35cf76c75dd7 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -741,7 +741,7 @@ static int create_or_delete_trace_uprobe(const char *raw_command) if (raw_command[0] == '-') return dyn_event_release(raw_command, &trace_uprobe_ops); - ret = trace_uprobe_create(raw_command); + ret = dyn_event_create(raw_command, &trace_uprobe_ops); return ret == -ECANCELED ? -EINVAL : ret; } -- cgit v1.2.3 From e333332657f615ac2b55aa35565c4a882018bbe9 Mon Sep 17 00:00:00 2001 From: pengdonglin Date: Mon, 12 May 2025 17:42:45 +0800 Subject: ftrace: Fix preemption accounting for stacktrace trigger command When using the stacktrace trigger command to trace syscalls, the preemption count was consistently reported as 1 when the system call event itself had 0 ("."). For example: root@ubuntu22-vm:/sys/kernel/tracing/events/syscalls/sys_enter_read $ echo stacktrace > trigger $ echo 1 > enable sshd-416 [002] ..... 232.864910: sys_read(fd: a, buf: 556b1f3221d0, count: 8000) sshd-416 [002] ...1. 232.864913: => ftrace_syscall_enter => syscall_trace_enter => do_syscall_64 => entry_SYSCALL_64_after_hwframe The root cause is that the trace framework disables preemption in __DO_TRACE before invoking the trigger callback. Use the tracing_gen_ctx_dec() that will accommodate for the increase of the preemption count in __DO_TRACE when calling the callback. The result is the accurate reporting of: sshd-410 [004] ..... 210.117660: sys_read(fd: 4, buf: 559b725ba130, count: 40000) sshd-410 [004] ..... 210.117662: => ftrace_syscall_enter => syscall_trace_enter => do_syscall_64 => entry_SYSCALL_64_after_hwframe Cc: stable@vger.kernel.org Fixes: ce33c845b030c ("tracing: Dump stacktrace trigger to the corresponding instance") Link: https://lore.kernel.org/20250512094246.1167956-1-dolinux.peng@gmail.com Signed-off-by: pengdonglin Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_trigger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index b66b6d235d91..6e87ae2a1a66 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1560,7 +1560,7 @@ stacktrace_trigger(struct event_trigger_data *data, struct trace_event_file *file = data->private_data; if (file) - __trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP); + __trace_stack(file->tr, tracing_gen_ctx_dec(), STACK_SKIP); else trace_dump_stack(STACK_SKIP); } -- cgit v1.2.3 From 11aff32439df6ca5b3b891b43032faf88f4a6a29 Mon Sep 17 00:00:00 2001 From: pengdonglin Date: Mon, 12 May 2025 17:42:46 +0800 Subject: ftrace: Fix preemption accounting for stacktrace filter command The preemption count of the stacktrace filter command to trace ksys_read is consistently incorrect: $ echo ksys_read:stacktrace > set_ftrace_filter <...>-453 [004] ...1. 38.308956: => ksys_read => do_syscall_64 => entry_SYSCALL_64_after_hwframe The root cause is that the trace framework disables preemption when invoking the filter command callback in function_trace_probe_call: preempt_disable_notrace(); probe_ops->func(ip, parent_ip, probe_opsbe->tr, probe_ops, probe->data); preempt_enable_notrace(); Use tracing_gen_ctx_dec() to account for the preempt_disable_notrace(), which will output the correct preemption count: $ echo ksys_read:stacktrace > set_ftrace_filter <...>-410 [006] ..... 31.420396: => ksys_read => do_syscall_64 => entry_SYSCALL_64_after_hwframe Cc: stable@vger.kernel.org Fixes: 36590c50b2d07 ("tracing: Merge irqflags + preempt counter.") Link: https://lore.kernel.org/20250512094246.1167956-2-dolinux.peng@gmail.com Signed-off-by: pengdonglin Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 98ccf3f00c51..4e37a0f6aaa3 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -633,11 +633,7 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip, static __always_inline void trace_stack(struct trace_array *tr) { - unsigned int trace_ctx; - - trace_ctx = tracing_gen_ctx(); - - __trace_stack(tr, trace_ctx, FTRACE_STACK_SKIP); + __trace_stack(tr, tracing_gen_ctx_dec(), FTRACE_STACK_SKIP); } static void -- cgit v1.2.3 From 1d6c39c89f617c9fec6bbae166e25b16a014f7c8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 13 May 2025 11:50:32 -0400 Subject: ring-buffer: Fix persistent buffer when commit page is the reader page The ring buffer is made up of sub buffers (sometimes called pages as they are by default PAGE_SIZE). It has the following "pages": "tail page" - this is the page that the next write will write to "head page" - this is the page that the reader will swap the reader page with. "reader page" - This belongs to the reader, where it will swap the head page from the ring buffer so that the reader does not race with the writer. The writer may end up on the "reader page" if the ring buffer hasn't written more than one page, where the "tail page" and the "head page" are the same. The persistent ring buffer has meta data that points to where these pages exist so on reboot it can re-create the pointers to the cpu_buffer descriptor. But when the commit page is on the reader page, the logic is incorrect. The check to see if the commit page is on the reader page checked if the head page was the reader page, which would never happen, as the head page is always in the ring buffer. The correct check would be to test if the commit page is on the reader page. If that's the case, then it can exit out early as the commit page is only on the reader page when there's only one page of data in the buffer. There's no reason to iterate the ring buffer pages to find the "commit page" as it is already found. To trigger this bug: # echo 1 > /sys/kernel/tracing/instances/boot_mapped/events/syscalls/sys_enter_fchownat/enable # touch /tmp/x # chown sshd /tmp/x # reboot On boot up, the dmesg will have: Ring buffer meta [0] is from previous boot! Ring buffer meta [1] is from previous boot! Ring buffer meta [2] is from previous boot! Ring buffer meta [3] is from previous boot! Ring buffer meta [4] commit page not found Ring buffer meta [5] is from previous boot! Ring buffer meta [6] is from previous boot! Ring buffer meta [7] is from previous boot! Where the buffer on CPU 4 had a "commit page not found" error and that buffer is cleared and reset causing the output to be empty and the data lost. When it works correctly, it has: # cat /sys/kernel/tracing/instances/boot_mapped/trace_pipe <...>-1137 [004] ..... 998.205323: sys_enter_fchownat: __syscall_nr=0x104 (260) dfd=0xffffff9c (4294967196) filename=(0xffffc90000a0002c) user=0x3e8 (1000) group=0xffffffff (4294967295) flag=0x0 (0 Cc: stable@vger.kernel.org Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250513115032.3e0b97f7@gandalf.local.home Fixes: 5f3b6e839f3ce ("ring-buffer: Validate boot range memory events") Reported-by: Tasos Sahanidis Tested-by: Tasos Sahanidis Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c0f877d39a24..3f9bf562beea 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1887,10 +1887,12 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) head_page = cpu_buffer->head_page; - /* If both the head and commit are on the reader_page then we are done. */ - if (head_page == cpu_buffer->reader_page && - head_page == cpu_buffer->commit_page) + /* If the commit_buffer is the reader page, update the commit page */ + if (meta->commit_buffer == (unsigned long)cpu_buffer->reader_page->page) { + cpu_buffer->commit_page = cpu_buffer->reader_page; + /* Nothing more to do, the only page is the reader page */ goto done; + } /* Iterate until finding the commit page */ for (i = 0; i < meta->nr_subbufs + 1; i++, rb_inc_page(&head_page)) { -- cgit v1.2.3