Merge 7.2-rc5 into usb-next

We need the USB fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

18 files changed, 343 insertions, 110 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 64572f85edc8..c4673a54c4ba 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -9114,6 +9114,35 @@ u32 *btf_kfunc_flags(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_p
 	return btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id);
 }
 
+/*
+ * Check a single KF_* @flag on a kfunc across all of its hook sets.
+ * Returns:
+ *   * 1 if @flag is set
+ *   * 0 if @flag is not set
+ *   * -EINVAL if @flag is set inconsistently across the sets
+ *   * -ENOENT if kfunc_btf_id is not a registered kfunc
+ */
+int btf_kfunc_check_flag(const struct btf *btf, u32 kfunc_btf_id, u32 flag)
+{
+	enum btf_kfunc_hook hook;
+	int res = -ENOENT;
+	bool is_set;
+	u32 *flags;
+
+	for (hook = 0; hook < BTF_KFUNC_HOOK_MAX; hook++) {
+		flags = btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id);
+		if (!flags)
+			continue;
+		is_set = *flags & flag;
+		if (res < 0)
+			res = is_set;
+		else if (res != is_set)
+			return -EINVAL;
+	}
+
+	return res;
+}
+
 u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id,
 				const struct bpf_prog *prog)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6515d4d3c003..7aa47342dc65 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2584,24 +2584,25 @@ static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset)
 
 #define KF_IMPL_SUFFIX "_impl"
 
-static const struct btf_type *find_kfunc_impl_proto(struct bpf_verifier_env *env,
+static const struct btf_type *find_kfunc_impl_proto(struct bpf_verifier_log *log,
 						    struct btf *btf,
 						    const char *func_name)
 {
-	char *buf = env->tmp_str_buf;
 	const struct btf_type *func;
+	char buf[KSYM_NAME_LEN];
 	s32 impl_id;
 	int len;
 
-	len = snprintf(buf, TMP_STR_BUF_LEN, "%s%s", func_name, KF_IMPL_SUFFIX);
-	if (len < 0 || len >= TMP_STR_BUF_LEN) {
-		verbose(env, "function name %s%s is too long\n", func_name, KF_IMPL_SUFFIX);
+	len = snprintf(buf, sizeof(buf), "%s%s", func_name, KF_IMPL_SUFFIX);
+	if (len < 0 || len >= sizeof(buf)) {
+		bpf_log(log, "function name %s%s is too long\n",
+			func_name, KF_IMPL_SUFFIX);
 		return NULL;
 	}
 
 	impl_id = btf_find_by_name_kind(btf, buf, BTF_KIND_FUNC);
 	if (impl_id <= 0) {
-		verbose(env, "cannot find function %s in BTF\n", buf);
+		bpf_log(log, "cannot find function %s in BTF\n", buf);
 		return NULL;
 	}
 
@@ -2653,7 +2654,7 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env,
 	 * can be found through the counterpart _impl kfunc.
 	 */
 	if (kfunc_flags && (*kfunc_flags & KF_IMPLICIT_ARGS))
-		func_proto = find_kfunc_impl_proto(env, btf, func_name);
+		func_proto = find_kfunc_impl_proto(&env->log, btf, func_name);
 	else
 		func_proto = btf_type_by_id(btf, func->type);
 
@@ -5326,14 +5327,11 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
 static int __check_buffer_access(struct bpf_verifier_env *env,
 				 const char *buf_info,
 				 const struct bpf_reg_state *reg,
-				 argno_t argno, int off, int size)
+				 argno_t argno, int off, int size,
+				 u32 *access_end)
 {
-	if (off < 0) {
-		verbose(env,
-			"%s invalid %s buffer access: off=%d, size=%d\n",
-			reg_arg_name(env, argno), buf_info, off, size);
-		return -EACCES;
-	}
+	s64 start;
+
 	if (!tnum_is_const(reg->var_off)) {
 		char tn_buf[48];
 
@@ -5344,6 +5342,15 @@ static int __check_buffer_access(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
+	start = (s64)reg->var_off.value + off;
+	if (start < 0) {
+		verbose(env,
+			"%s invalid negative %s buffer offset: off=%d, var_off=%lld\n",
+			reg_arg_name(env, argno), buf_info, off, (s64)reg->var_off.value);
+		return -EACCES;
+	}
+
+	*access_end = start + size;
 	return 0;
 }
 
@@ -5351,14 +5358,14 @@ static int check_tp_buffer_access(struct bpf_verifier_env *env,
 				  const struct bpf_reg_state *reg,
 				  argno_t argno, int off, int size)
 {
+	u32 access_end;
 	int err;
 
-	err = __check_buffer_access(env, "tracepoint", reg, argno, off, size);
+	err = __check_buffer_access(env, "tracepoint", reg, argno, off, size, &access_end);
 	if (err)
 		return err;
 
-	env->prog->aux->max_tp_access = max(reg->var_off.value + off + size,
-					    env->prog->aux->max_tp_access);
+	env->prog->aux->max_tp_access = max(access_end, env->prog->aux->max_tp_access);
 
 	return 0;
 }
@@ -5370,13 +5377,14 @@ static int check_buffer_access(struct bpf_verifier_env *env,
 			       u32 *max_access)
 {
 	const char *buf_info = type_is_rdonly_mem(reg->type) ? "rdonly" : "rdwr";
+	u32 access_end;
 	int err;
 
-	err = __check_buffer_access(env, buf_info, reg, argno, off, size);
+	err = __check_buffer_access(env, buf_info, reg, argno, off, size, &access_end);
 	if (err)
 		return err;
 
-	*max_access = max(reg->var_off.value + off + size, *max_access);
+	*max_access = max(access_end, *max_access);
 
 	return 0;
 }
@@ -9181,7 +9189,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 				return ret;
 			if (check_mem_reg(env, reg, argno, arg->mem_size))
 				return -EINVAL;
-			if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) {
+			if (!(arg->arg_type & PTR_MAYBE_NULL) &&
+			    (type_may_be_null(reg->type) || bpf_register_is_null(reg))) {
 				bpf_log(log, "%s is expected to be non-NULL\n",
 					reg_arg_name(env, argno));
 				return -EINVAL;
@@ -18873,6 +18882,47 @@ static int btf_id_allow_sleepable(u32 btf_id, unsigned long addr, const struct b
 	return -EINVAL;
 }
 
+/*
+ * Resolve the prototype describing a trace target's real ABI. A
+ * KF_IMPLICIT_ARGS kfunc has its injected args stripped from the public
+ * prototype, so use the _impl prototype; other targets use their own.
+ */
+static const struct btf_type *
+btf_attach_func_proto(struct bpf_verifier_log *log, struct btf *btf, u32 func_id)
+{
+	const struct btf_type *func;
+	struct module *mod = NULL;
+	const char *name;
+	int implicit;
+
+	func = btf_type_by_id(btf, func_id);
+	if (!func || !btf_type_is_func(func))
+		return NULL;
+	name = btf_name_by_offset(btf, func->name_off);
+
+	/*
+	 * btf_kfunc_check_flag() reads kfunc_set_tab, which for a module is
+	 * stable only once it is live; hold a module ref across the read to
+	 * exclude a concurrent module load.
+	 */
+	if (btf_is_module(btf)) {
+		mod = btf_try_get_module(btf);
+		if (!mod)
+			return NULL;
+	}
+	implicit = btf_kfunc_check_flag(btf, func_id, KF_IMPLICIT_ARGS);
+	module_put(mod);
+
+	if (implicit == -EINVAL) {
+		bpf_log(log, "kfunc %s has inconsistent KF_IMPLICIT_ARGS\n", name);
+		return NULL;
+	}
+	if (implicit > 0)
+		return find_kfunc_impl_proto(log, btf, name);
+
+	return btf_type_by_id(btf, func->type);
+}
+
 int bpf_check_attach_target(struct bpf_verifier_log *log,
 			    const struct bpf_prog *prog,
 			    const struct bpf_prog *tgt_prog,
@@ -19121,8 +19171,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 		if (prog_extension &&
 		    btf_check_type_match(log, prog, btf, t))
 			return -EINVAL;
-		t = btf_type_by_id(btf, t->type);
-		if (!btf_type_is_func_proto(t))
+		t = btf_attach_func_proto(log, btf, btf_id);
+		if (!t || !btf_type_is_func_proto(t))
 			return -EINVAL;
 
 		if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) &&
@@ -19405,10 +19455,8 @@ int bpf_check_attach_btf_id_multi(struct btf *btf, struct bpf_prog *prog, u32 bt
 	tname = btf_name_by_offset(btf, t->name_off);
 	if (!tname)
 		return -EINVAL;
-	if (!btf_type_is_func(t))
-		return -EINVAL;
-	t = btf_type_by_id(btf, t->type);
-	if (!btf_type_is_func_proto(t))
+	t = btf_attach_func_proto(NULL, btf, btf_id);
+	if (!t || !btf_type_is_func_proto(t))
 		return -EINVAL;
 	err = btf_distill_func_proto(NULL, btf, t, tname, &tgt_info->fmodel);
 	if (err < 0)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 591e3aa487fc..45944b3e31ca 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2653,7 +2653,12 @@ void cpuset_update_tasks_nodemask(struct cpuset *cs)
 
 		migrate = is_memory_migrate(cs);
 
-		mpol_rebind_mm(mm, &cs->mems_allowed);
+		/*
+		 * For v1 we can have empty effective_mems, but we cannot
+		 * attach any tasks (see cpuset_can_attach_check()). For v2,
+		 * effective_mems is guaranteed to not be empty.
+		 */
+		mpol_rebind_mm(mm, &cs->effective_mems);
 		if (migrate)
 			cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
 		else
diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c
index b79b2a488974..f38b5b18f3f8 100644
--- a/kernel/liveupdate/luo_session.c
+++ b/kernel/liveupdate/luo_session.c
@@ -378,7 +378,7 @@ static const struct luo_ioctl_op luo_session_ioctl_ops[] = {
 	IOCTL_OP(LIVEUPDATE_SESSION_RETRIEVE_FD, luo_session_retrieve_fd,
 		 struct liveupdate_session_retrieve_fd, token, LUO_IOCTL_INCOMING),
 	IOCTL_OP(LIVEUPDATE_SESSION_GET_NAME, luo_session_get_name,
-		 struct liveupdate_session_retrieve_fd, token, LUO_IOCTL_ALL),
+		 struct liveupdate_session_get_name, name, LUO_IOCTL_ALL),
 };
 
 static bool luo_ioctl_type_valid(struct luo_session *session,
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 691d53fe0f64..e3fa7b2fac9d 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -479,6 +479,18 @@ static bool rq_is_open(struct rq *rq, u64 enq_flags)
  */
 DEFINE_PER_CPU(struct rq *, scx_locked_rq_state);
 
+static void switch_rq_lock(struct rq *from, struct rq *to)
+{
+	bool tracked = scx_locked_rq() == from;
+
+	if (tracked)
+		update_locked_rq(NULL);
+	raw_spin_rq_unlock(from);
+	raw_spin_rq_lock(to);
+	if (tracked)
+		update_locked_rq(to);
+}
+
 /*
  * Flipped on enable per sch->is_cid_type. Declared in internal.h so
  * subsystem inlines can read it.
@@ -2274,8 +2286,7 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
 	deactivate_task(src_rq, p, 0);
 	set_task_cpu(p, cpu_of(dst_rq));
 
-	raw_spin_rq_unlock(src_rq);
-	raw_spin_rq_lock(dst_rq);
+	switch_rq_lock(src_rq, dst_rq);
 
 	/*
 	 * We want to pass scx-specific enq_flags but activate_task() will
@@ -2307,6 +2318,7 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
  *   no to the BPF scheduler initiated migrations while offline.
  *
  * The caller must ensure that @p and @rq are on different CPUs.
+ * If enforce == true, caller must hold @p's rq lock.
  */
 static bool task_can_run_on_remote_rq(struct scx_sched *sch,
 				      struct task_struct *p, struct rq *rq,
@@ -2314,6 +2326,14 @@ static bool task_can_run_on_remote_rq(struct scx_sched *sch,
 {
 	s32 cpu = cpu_of(rq);
 
+	/*
+	 * To prevent races with @p still running on its old CPU while switching
+	 * out, make sure we're holding @p's rq lock so as not to risk
+	 * erroneously killing the BPF scheduler.
+	 */
+	if (enforce)
+		lockdep_assert_rq_held(task_rq(p));
+
 	WARN_ON_ONCE(task_cpu(p) == cpu);
 
 	/*
@@ -2581,13 +2601,6 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 		return;
 	}
 
-	if (src_rq != dst_rq &&
-	    unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
-		dispatch_enqueue(sch, rq, find_global_dsq(sch, task_cpu(p)), p,
-				 enq_flags | SCX_ENQ_CLEAR_OPSS | SCX_ENQ_GDSQ_FALLBACK);
-		return;
-	}
-
 	/*
 	 * @p is on a possibly remote @src_rq which we need to lock to move the
 	 * task. If dequeue is in progress, it'd be locking @src_rq and waiting
@@ -2606,14 +2619,14 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 
 	/* switch to @src_rq lock */
 	if (locked_rq != src_rq) {
-		raw_spin_rq_unlock(locked_rq);
+		switch_rq_lock(locked_rq, src_rq);
 		locked_rq = src_rq;
-		raw_spin_rq_lock(src_rq);
 	}
 
 	/* task_rq couldn't have changed if we're still the holding cpu */
 	if (likely(p->scx.holding_cpu == raw_smp_processor_id()) &&
 	    !WARN_ON_ONCE(src_rq != task_rq(p))) {
+		bool fallback = false;
 		/*
 		 * If @p is staying on the same rq, there's no need to go
 		 * through the full deactivate/activate cycle. Optimize by
@@ -2623,6 +2636,11 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 			p->scx.holding_cpu = -1;
 			dispatch_enqueue(sch, dst_rq, &dst_rq->scx.local_dsq, p,
 					 enq_flags);
+		} else if (unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
+			p->scx.holding_cpu = -1;
+			fallback = true;
+			dispatch_enqueue(sch, src_rq, find_global_dsq(sch, task_cpu(p)),
+					 p, enq_flags | SCX_ENQ_GDSQ_FALLBACK);
 		} else {
 			move_remote_task_to_local_dsq(p, enq_flags,
 						      src_rq, dst_rq);
@@ -2631,15 +2649,13 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 		}
 
 		/* if the destination CPU is idle, wake it up */
-		if (sched_class_above(p->sched_class, dst_rq->curr->sched_class))
+		if (!fallback && sched_class_above(p->sched_class, dst_rq->curr->sched_class))
 			resched_curr(dst_rq);
 	}
 
 	/* switch back to @rq lock */
-	if (locked_rq != rq) {
-		raw_spin_rq_unlock(locked_rq);
-		raw_spin_rq_lock(rq);
-	}
+	if (locked_rq != rq)
+		switch_rq_lock(locked_rq, rq);
 }
 
 /**
@@ -2970,24 +2986,38 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 
 	/*
 	 * @p is getting newly scheduled or got kicked after someone updated its
-	 * slice. Refresh whether tick can be stopped. See scx_can_stop_tick().
+	 * slice. Update SCX_RQ_CAN_STOP_TICK to reflect whether the tick can be
+	 * stopped. See scx_can_stop_tick().
+	 *
+	 * Moreover, refresh the load_avgs just when transitioning in and out of
+	 * nohz. In the future, we might want to add a mechanism to update
+	 * load_avgs periodically on tick-stopped CPUs.
 	 */
-	if ((p->scx.slice == SCX_SLICE_INF) !=
-	    (bool)(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) {
-		if (p->scx.slice == SCX_SLICE_INF)
+	if (p->scx.slice == SCX_SLICE_INF) {
+		if (!(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) {
+			/*
+			 * Bypass mode always assigns finite slices, so @p
+			 * can't have an infinite slice while bypassing.
+			 * Therefore, sched_update_tick_dependency() can safely
+			 * evaluate the outgoing task.
+			 */
 			rq->scx.flags |= SCX_RQ_CAN_STOP_TICK;
-		else
-			rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK;
+			sched_update_tick_dependency(rq);
 
-		sched_update_tick_dependency(rq);
+			update_other_load_avgs(rq);
+		}
+	} else {
+		if (rq->scx.flags & SCX_RQ_CAN_STOP_TICK) {
+			rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK;
+			update_other_load_avgs(rq);
+		}
 
 		/*
-		 * For now, let's refresh the load_avgs just when transitioning
-		 * in and out of nohz. In the future, we might want to add a
-		 * mechanism which calls the following periodically on
-		 * tick-stopped CPUs.
+		 * @rq still references the outgoing scheduling context. A finite
+		 * slice is sufficient by itself to require the tick.
 		 */
-		update_other_load_avgs(rq);
+		if (tick_nohz_full_cpu(cpu_of(rq)))
+			tick_nohz_dep_set_cpu(cpu_of(rq), TICK_DEP_BIT_SCHED);
 	}
 }
 
@@ -3082,9 +3112,14 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		 * sched_class, %SCX_OPS_ENQ_LAST must be set. Tell
 		 * ops.enqueue() that @p is the only one available for this cpu,
 		 * which should trigger an explicit follow-up scheduling event.
+		 *
+		 * Core scheduling can force this CPU idle while @p stays
+		 * runnable. @p's cookie then won't match the core's, so skip
+		 * the warning in that case.
 		 */
 		if (next && sched_class_above(&ext_sched_class, next->sched_class)) {
-			WARN_ON_ONCE(!(sch->ops.flags & SCX_OPS_ENQ_LAST));
+			WARN_ON_ONCE(sched_cpu_cookie_match(rq, p) &&
+				     !(sch->ops.flags & SCX_OPS_ENQ_LAST));
 			do_enqueue_task(rq, p, SCX_ENQ_LAST, -1);
 		} else {
 			do_enqueue_task(rq, p, 0, -1);
@@ -3648,6 +3683,13 @@ static void scx_disable_task(struct scx_sched *sch, struct task_struct *p)
 	scx_set_task_state(p, SCX_TASK_READY);
 
 	/*
+	 * Reset the SCX-managed fields when @p leaves the BPF scheduler's
+	 * control, after ops.disable() has observed their final values.
+	 */
+	p->scx.dsq_vtime = 0;
+	p->scx.slice = 0;
+
+	/*
 	 * Verify the task is not in BPF scheduler's custody. If flag
 	 * transitions are consistent, the flag should always be clear
 	 * here.
@@ -3925,6 +3967,17 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p,
 	if (task_dead_and_done(p))
 		return;
 
+	/*
+	 * When switching sched_class away from SCX, reweight_task_scx()
+	 * is called _after_ scx_disable_task(). Skip calling ops.set_weight()
+	 * since the BPF scheduler may have already forgotten the task in
+	 * ops.disable().
+	 * p->scx.weight will be recalculated in scx_enable_task() if the task
+	 * ever returns to SCX class.
+	 */
+	if (scx_get_task_state(p) != SCX_TASK_ENABLED)
+		return;
+
 	p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight));
 	if (SCX_HAS_OP(sch, set_weight))
 		SCX_CALL_OP_TASK(sch, set_weight, rq, p, p->scx.weight);
@@ -4301,6 +4354,15 @@ bool scx_can_stop_tick(struct rq *rq)
 	if (p->sched_class != &ext_sched_class)
 		return true;
 
+	/*
+	 * @rq->curr may still reference an outgoing EXT task after it has been
+	 * dequeued. If no EXT tasks are accounted on @rq, ignore its stale
+	 * slice state. If another task is dispatched from a DSQ,
+	 * set_next_task_scx() will update the dependency for the incoming task.
+	 */
+	if (!rq->scx.nr_running)
+		return true;
+
 	if (scx_bypassing(sch, cpu_of(rq)))
 		return false;
 
@@ -4901,6 +4963,8 @@ static void scx_sched_free_rcu_work(struct work_struct *work)
 		cgroup_put(sch_cgroup(sch));
 	if (sch->sub_kset)
 		kobject_put(&sch->sub_kset->kobj);
+	if (scx_parent(sch))
+		kobject_put(&scx_parent(sch)->kobj);
 #endif	/* CONFIG_EXT_SUB_SCHED */
 
 	for_each_possible_cpu(cpu) {
@@ -5672,7 +5736,7 @@ static void free_kick_syncs(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		struct scx_kick_syncs **ksyncs = per_cpu_ptr(&scx_kick_syncs, cpu);
+		struct scx_kick_syncs __rcu **ksyncs = per_cpu_ptr(&scx_kick_syncs, cpu);
 		struct scx_kick_syncs *to_free;
 
 		to_free = rcu_replace_pointer(*ksyncs, NULL, true);
@@ -6653,7 +6717,7 @@ static int alloc_kick_syncs(void)
 	 * can exceed percpu allocator limits on large machines.
 	 */
 	for_each_possible_cpu(cpu) {
-		struct scx_kick_syncs **ksyncs = per_cpu_ptr(&scx_kick_syncs, cpu);
+		struct scx_kick_syncs __rcu **ksyncs = per_cpu_ptr(&scx_kick_syncs, cpu);
 		struct scx_kick_syncs *new_ksyncs;
 
 		WARN_ON_ONCE(rcu_access_pointer(*ksyncs));
@@ -6825,11 +6889,6 @@ static struct scx_sched *scx_alloc_and_add_sched(struct scx_enable_cmd *cmd,
 		sch->ops = *cmd->ops;
 	}
 
-	rcu_assign_pointer(ops->priv, sch);
-
-	sch->kobj.kset = scx_kset;
-	INIT_LIST_HEAD(&sch->all);
-
 #ifdef CONFIG_EXT_SUB_SCHED
 	char *buf = kzalloc(PATH_MAX, GFP_KERNEL);
 	if (!buf) {
@@ -6847,13 +6906,32 @@ static struct scx_sched *scx_alloc_and_add_sched(struct scx_enable_cmd *cmd,
 	sch->cgrp = cgrp;
 	INIT_LIST_HEAD(&sch->children);
 	INIT_LIST_HEAD(&sch->sibling);
+#endif	/* CONFIG_EXT_SUB_SCHED */
 
-	if (parent)
+	/*
+	 * Publishing makes @sch visible to scx_prog_sched() readers. Failure
+	 * paths after this point must free @sch through kobject_put() whose
+	 * release path defers the actual freeing by an RCU grace period.
+	 */
+	rcu_assign_pointer(ops->priv, sch);
+
+	sch->kobj.kset = scx_kset;
+	INIT_LIST_HEAD(&sch->all);
+
+#ifdef CONFIG_EXT_SUB_SCHED
+	if (parent) {
+		/*
+		 * Pin @parent for @sch's lifetime. The kobject hierarchy pins
+		 * it only via @parent->sub_kset, which is dropped during
+		 * disable. Released in scx_sched_free_rcu_work().
+		 */
+		kobject_get(&parent->kobj);
 		ret = kobject_init_and_add(&sch->kobj, &scx_ktype,
 					   &parent->sub_kset->kobj,
 					   "sub-%llu", cgroup_id(cgrp));
-	else
+	} else {
 		ret = kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root");
+	}
 
 	if (ret < 0) {
 		RCU_INIT_POINTER(ops->priv, NULL);
@@ -6895,7 +6973,6 @@ static struct scx_sched *scx_alloc_and_add_sched(struct scx_enable_cmd *cmd,
 
 #ifdef CONFIG_EXT_SUB_SCHED
 err_free_lb_resched:
-	RCU_INIT_POINTER(ops->priv, NULL);
 	free_cpumask_var(sch->bypass_lb_resched_cpumask);
 #endif
 err_free_lb_cpumask:
@@ -6988,7 +7065,7 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 	 * run past the BPF allocation. Skip for cid-form.
 	 */
 	if (!sch->is_cid_type && (ops->cpu_acquire || ops->cpu_release))
-		pr_warn("ops->cpu_acquire/release() are deprecated, use sched_switch TP instead\n");
+		pr_warn_ratelimited("ops->cpu_acquire/release() are deprecated, use sched_switch TP instead\n");
 
 	/*
 	 * Sub-scheduler support is tied to the cid-form struct_ops. A sub-sched
@@ -7686,6 +7763,12 @@ err_unlock_and_disable:
 	percpu_up_write(&scx_fork_rwsem);
 err_disable:
 	mutex_unlock(&scx_enable_mutex);
+	/*
+	 * Some enable failures only return an errno (e.g. -ENOMEM from an
+	 * allocation) without calling scx_error(). Record it so
+	 * scx_flush_disable_work() runs the disable and ops.exit() fires.
+	 */
+	scx_error(sch, "scx_sub_enable() failed (%d)", ret);
 	scx_flush_disable_work(sch);
 	cmd->ret = 0;
 }
@@ -7806,7 +7889,7 @@ static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log,
 		     off + size <= offsetofend(struct task_struct, scx.slice)) ||
 		    (off >= offsetof(struct task_struct, scx.dsq_vtime) &&
 		     off + size <= offsetofend(struct task_struct, scx.dsq_vtime))) {
-			pr_warn("sched_ext: Writing directly to p->scx.slice/dsq_vtime is deprecated, use scx_bpf_task_set_slice/dsq_vtime()");
+			pr_warn_ratelimited("sched_ext: Writing directly to p->scx.slice/dsq_vtime is deprecated, use scx_bpf_task_set_slice/dsq_vtime()\n");
 			return SCALAR_VALUE;
 		}
 
@@ -8796,10 +8879,8 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	in_balance = this_rq->scx.flags & SCX_RQ_IN_BALANCE;
 
 	if (in_balance) {
-		if (this_rq != src_rq) {
-			raw_spin_rq_unlock(this_rq);
-			raw_spin_rq_lock(src_rq);
-		}
+		if (this_rq != src_rq)
+			switch_rq_lock(this_rq, src_rq);
 	} else {
 		raw_spin_rq_lock(src_rq);
 	}
@@ -8831,10 +8912,8 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	dispatched = true;
 out:
 	if (in_balance) {
-		if (this_rq != locked_rq) {
-			raw_spin_rq_unlock(locked_rq);
-			raw_spin_rq_lock(this_rq);
-		}
+		if (this_rq != locked_rq)
+			switch_rq_lock(locked_rq, this_rq);
 	} else {
 		raw_spin_rq_unlock_irqrestore(locked_rq, flags);
 	}
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index 145272cb4d8a..673059fa9d72 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -1469,21 +1469,24 @@ static const char *scx_enable_state_str[] = {
  * The sched_ext core uses a "lock dancing" protocol coordinated by
  * p->scx.holding_cpu. When moving a task to a different rq:
  *
- *   1. Verify task can be moved (CPU affinity, migration_disabled, etc.)
- *   2. Set p->scx.holding_cpu to the current CPU
- *   3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING
+ *   1. Set p->scx.holding_cpu to the current CPU
+ *   2. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING
  *      is set, so clearing DISPATCHING first prevents the circular wait
  *      (safe to lock the rq we need)
- *   4. Unlock the current CPU's rq
- *   5. Lock src_rq (where the task currently lives)
- *   6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the
+ *   3. Unlock the current CPU's rq
+ *   4. Lock src_rq (where the task currently lives)
+ *   5. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the
  *      race (dequeue clears holding_cpu to -1 when it takes the task), in
  *      this case migration is aborted
- *   7. If src_rq == dst_rq: clear holding_cpu and enqueue directly
+ *   6. If src_rq == dst_rq: clear holding_cpu and enqueue directly
  *      into dst_rq's local DSQ (no lock swap needed)
- *   8. Otherwise: call move_remote_task_to_local_dsq(), which releases
- *      src_rq, locks dst_rq, and performs the deactivate/activate
- *      migration cycle (dst_rq is held on return)
+ *   7. Otherwise, verify under src_rq lock that the task can be moved to dst_rq
+ *      (CPU affinity, migration_disabled, etc.). If not, clear holding_cpu,
+ *      leave the task on src_rq, and enqueue it on the fallback DSQ.
+ *   8. Otherwise (i.e. if the task can be moved to dst_rq), call
+ *      move_remote_task_to_local_dsq(), which releases src_rq, locks dst_rq,
+ *      and performs the deactivate/activate migration cycle
+ *      (dst_rq is held on return)
  *   9. Unlock dst_rq and re-lock the current CPU's rq to restore
  *      the lock state expected by the caller
  *
diff --git a/kernel/smp.c b/kernel/smp.c
index a0bb56bd8dda..52dffc86555c 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -137,10 +137,10 @@ csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd)
 	trace_csd_function_exit(func, csd);
 }
 
-#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
-
 static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled);
 
+#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
+
 /*
  * Parse the csdlock_debug= kernel boot parameter.
  *
@@ -342,6 +342,10 @@ static __always_inline void csd_lock_wait(call_single_data_t *csd)
 	smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
 }
 #else
+static __always_inline void __csd_lock_wait(call_single_data_t *csd)
+{
+}
+
 static void csd_lock_record(call_single_data_t *csd)
 {
 }
@@ -354,8 +358,23 @@ static __always_inline void csd_lock_wait(call_single_data_t *csd)
 
 static __always_inline void csd_lock(call_single_data_t *csd)
 {
-	csd_lock_wait(csd);
-	csd->node.u_flags |= CSD_FLAG_LOCK;
+	if (IS_ENABLED(CONFIG_CSD_LOCK_WAIT_DEBUG) &&
+	    static_branch_unlikely(&csdlock_debug_enabled)) {
+
+		for (;;) {
+			unsigned int flags;
+
+			__csd_lock_wait(csd);
+			flags = READ_ONCE(csd->node.u_flags);
+
+			if (!(flags & CSD_FLAG_LOCK) &&
+			    try_cmpxchg_acquire(&csd->node.u_flags, &flags, flags | CSD_FLAG_LOCK))
+				break;
+		}
+	} else {
+		csd_lock_wait(csd);
+		csd->node.u_flags |= CSD_FLAG_LOCK;
+	}
 
 	/*
 	 * prevent CPU from reordering the above assignment
@@ -380,7 +399,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data);
 #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
 static call_single_data_t *get_single_csd_data(int cpu)
 {
-	if (static_branch_unlikely(&csdlock_debug_enabled))
+	if (static_branch_unlikely(&csdlock_debug_enabled) &&
+	    (unsigned int)cpu < nr_cpu_ids)
 		return per_cpu_ptr(&csd_data, cpu);
 	return this_cpu_ptr(&csd_data);
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f93e34dd2328..6c47a94f5924 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1098,6 +1098,12 @@ struct ftrace_ops global_ops = {
 };
 
 /*
+ * parser_lock - Protects trace_parser state against concurrent operations.
+ * Held across trace_get_user() and subsequent buffer parsing to prevent races.
+ */
+static DEFINE_MUTEX(parser_lock);
+
+/*
  * Used by the stack unwinder to know about dynamic ftrace trampolines.
  */
 struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr)
@@ -5842,6 +5848,8 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 	/* iter->hash is a local copy, so we don't need regex_lock */
 
 	parser = &iter->parser;
+
+	guard(mutex)(&parser_lock);
 	read = trace_get_user(parser, ubuf, cnt, ppos);
 
 	if (read >= 0 && trace_parser_loaded(parser) &&
@@ -6984,12 +6992,14 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 		iter = file->private_data;
 
 	parser = &iter->parser;
+	mutex_lock(&parser_lock);
 	if (trace_parser_loaded(parser)) {
 		int enable = !(iter->flags & FTRACE_ITER_NOTRACE);
 
 		ftrace_process_regex(iter, parser->buffer,
 				     parser->idx, enable);
 	}
+	mutex_unlock(&parser_lock);
 
 	trace_parser_put(parser);
 
@@ -7321,10 +7331,12 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 
 		parser = &fgd->parser;
 
+		mutex_lock(&parser_lock);
 		if (trace_parser_loaded((parser))) {
 			ret = ftrace_graph_set_hash(fgd->new_hash,
 						    parser->buffer);
 		}
+		mutex_unlock(&parser_lock);
 
 		trace_parser_put(parser);
 
@@ -7437,6 +7449,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
 
 	parser = &fgd->parser;
 
+	guard(mutex)(&parser_lock);
 	read = trace_get_user(parser, ubuf, cnt, ppos);
 
 	if (read >= 0 && trace_parser_loaded(parser) &&
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 18710c190c92..01a5e87af299 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6187,7 +6187,7 @@ char *trace_user_fault_read(struct trace_user_buf_info *tinfo,
 {
 	int cpu = smp_processor_id();
 	char *buffer = per_cpu_ptr(tinfo->tbuf, cpu)->buf;
-	unsigned int cnt;
+	unsigned long long cnt;
 	int trys = 0;
 	int ret;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 80fe152af1dd..bf77331f56a4 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1941,6 +1941,7 @@ struct event_trigger_data {
 	struct list_head		named_list;
 	struct event_trigger_data	*named_data;
 	struct llist_node		llist;
+	void				(*private_data_free)(struct event_trigger_data *data);
 };
 
 /* Avoid typos */
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 50518b071414..bcd97cb24ac9 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -172,7 +172,8 @@ static bool eprobe_dyn_event_match(const char *system, const char *event,
 	if (!slash)
 		return false;
 
-	if (strncmp(ep->event_system, argv[0], slash - argv[0]))
+	if (strncmp(ep->event_system, argv[0], slash - argv[0]) ||
+	    ep->event_system[slash - argv[0]] != '\0')
 		return false;
 	if (strcmp(ep->event_name, slash + 1))
 		return false;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c46e623e7e0d..956692856fa8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1350,7 +1350,9 @@ __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match,
 		call = file->event_call;
 
 		/* If a module is specified, skip events that are not that module */
-		if (module && (!call->module || strcmp(module_name(call->module), module)))
+		if (module &&
+		    ((call->flags & TRACE_EVENT_FL_DYNAMIC) ||
+		     !call->module || strcmp(module_name(call->module), module)))
 			continue;
 
 		name = trace_event_name(call);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 82ce492ab268..58d28cd1afa3 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6349,6 +6349,7 @@ static void event_hist_trigger_free(struct event_trigger_data *data)
 
 		trigger_data_free(data);
 
+		tracepoint_synchronize_unregister();
 		remove_hist_vars(hist_data);
 
 		unregister_field_var_hists(hist_data);
@@ -6388,6 +6389,7 @@ static void event_hist_trigger_named_free(struct event_trigger_data *data)
 
 		del_named_trigger(data);
 		trigger_data_free(data);
+		tracepoint_synchronize_unregister();
 		kfree(cmd_ops);
 	}
 }
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 655db2e82513..ad83419cb420 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -38,6 +38,13 @@ static void trigger_create_kthread_locked(void)
 	}
 }
 
+static void trigger_data_free_one(struct event_trigger_data *data)
+{
+	if (data->private_data_free)
+		data->private_data_free(data);
+	kfree(data);
+}
+
 static void trigger_data_free_queued_locked(void)
 {
 	struct event_trigger_data *data, *tmp;
@@ -52,7 +59,7 @@ static void trigger_data_free_queued_locked(void)
 	tracepoint_synchronize_unregister();
 
 	llist_for_each_entry_safe(data, tmp, llnodes, llist)
-		kfree(data);
+		trigger_data_free_one(data);
 }
 
 /* Bulk garbage collection of event_trigger_data elements */
@@ -75,7 +82,7 @@ static int trigger_kthread_fn(void *ignore)
 		tracepoint_synchronize_unregister();
 
 		llist_for_each_entry_safe(data, tmp, llnodes, llist)
-			kfree(data);
+			trigger_data_free_one(data);
 	}
 
 	return 0;
@@ -1717,6 +1724,14 @@ int event_enable_trigger_print(struct seq_file *m,
 	return 0;
 }
 
+static void enable_trigger_private_data_free(struct event_trigger_data *data)
+{
+	struct enable_trigger_data *enable_data = data->private_data;
+
+	trace_event_put_ref(enable_data->file->event_call);
+	kfree(enable_data);
+}
+
 void event_enable_trigger_free(struct event_trigger_data *data)
 {
 	struct enable_trigger_data *enable_data = data->private_data;
@@ -1728,9 +1743,8 @@ void event_enable_trigger_free(struct event_trigger_data *data)
 	if (!data->ref) {
 		/* Remove the SOFT_MODE flag */
 		trace_event_enable_disable(enable_data->file, 0, 1);
-		trace_event_put_ref(enable_data->file->event_call);
+		data->private_data_free = enable_trigger_private_data_free;
 		trigger_data_free(data);
-		kfree(enable_data);
 	}
 }
 
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 226cf66e0d68..b88b8d9923ad 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -109,7 +109,6 @@ static void mmio_pipe_open(struct trace_iterator *iter)
 	iter->private = hiter;
 }
 
-/* XXX: This is not called when the pipe is closed! */
 static void mmio_close(struct trace_iterator *iter)
 {
 	struct header_iter *hiter = iter->private;
@@ -146,7 +145,7 @@ static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp,
 		goto print_out;
 	}
 
-	if (!hiter)
+	if (!hiter || !hiter->dev)
 		return 0;
 
 	mmio_print_pcidev(s, hiter->dev);
@@ -279,6 +278,7 @@ static struct tracer mmio_tracer __read_mostly =
 	.start		= mmio_trace_start,
 	.pipe_open	= mmio_pipe_open,
 	.close		= mmio_close,
+	.pipe_close	= mmio_close,
 	.read		= mmio_read,
 	.print_line	= mmio_print_line,
 	.noboot		= true,
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index d17cfee77d9c..506e6037e163 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -188,7 +188,7 @@ void __trace_probe_log_err(int offset, int err_type)
 
 	lockdep_assert_held(&dyn_event_ops_mutex);
 
-	if (!trace_probe_log.argv)
+	if (!trace_probe_log.argv || !trace_probe_log.argc)
 		return;
 
 	/* Recalculate the length and allocate buffer */
@@ -2013,7 +2013,7 @@ int traceprobe_update_arg(struct probe_arg *arg)
 }
 
 /* When len=0, we just calculate the needed length */
-#define LEN_OR_ZERO (len ? len - pos : 0)
+#define LEN_OR_ZERO (len > pos ? len - pos : 0)
 static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
 			   enum probe_print_type ptype)
 {
@@ -2338,16 +2338,17 @@ int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b)
 bool trace_probe_match_command_args(struct trace_probe *tp,
 				    int argc, const char **argv)
 {
-	char buf[MAX_ARGSTR_LEN + 1];
 	int i;
 
 	if (tp->nr_args < argc)
 		return false;
 
 	for (i = 0; i < argc; i++) {
-		snprintf(buf, sizeof(buf), "%s=%s",
-			 tp->args[i].name, tp->args[i].comm);
-		if (strcmp(buf, argv[i]))
+		int len = strlen(tp->args[i].name);
+
+		if (strncmp(argv[i], tp->args[i].name, len) ||
+		    argv[i][len] != '=' ||
+		    strcmp(argv[i] + len + 1, tp->args[i].comm))
 			return false;
 	}
 	return true;
diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c
index 0f6ef5c36d84..e6724f947170 100644
--- a/kernel/trace/trace_remote.c
+++ b/kernel/trace/trace_remote.c
@@ -1004,11 +1004,10 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size,
 		desc->nr_cpus++;
 
 		for (id = 0; id < nr_pages; id++) {
+			rb_desc->nr_page_va++;
 			rb_desc->page_va[id] = (unsigned long)__get_free_page(GFP_KERNEL);
 			if (!rb_desc->page_va[id])
 				goto err;
-
-			rb_desc->nr_page_va++;
 		}
 		rb_desc = __next_ring_buffer_desc(rb_desc);
 	}
@@ -1150,10 +1149,21 @@ static ssize_t remote_events_dir_enable_write(struct file *filp, const char __us
 
 	for (i = 0; i < remote->nr_events; i++) {
 		struct remote_event *evt = &remote->events[i];
+		int eret;
 
-		trace_remote_enable_event(remote, evt, enable);
+		eret = trace_remote_enable_event(remote, evt, enable);
+		/*
+		 * Save the first error and return that. Some events
+		 * may still have been enabled, but let the user
+		 * know that something went wrong.
+		 */
+		if (!ret && eret)
+			ret = eret;
 	}
 
+	if (ret)
+		return ret;
+
 	return count;
 }
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index e98ee7e1e66f..8a4f3c75e39f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1451,6 +1451,11 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 		if (syscall_get_data(sys_data, args, &user_ptr,
 				     &size, user_sizes, &uargs, buf_size) < 0)
 			return;
+
+		/* The above may have caused a migration */
+		head = this_cpu_ptr(sys_data->enter_event->perf_events);
+		if (hlist_empty(head))
+			return;
 	}
 
 	/* get the size after alignment with the u32 buffer size field */