Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts and no adjacent changes.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>

29 files changed, 269 insertions, 148 deletions

diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 6292ac5f9bd1..3bc61628ab25 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -339,10 +339,6 @@ BTF_ID(func, bpf_lsm_path_chmod)
 BTF_ID(func, bpf_lsm_path_chown)
 #endif /* CONFIG_SECURITY_PATH */
 
-#ifdef CONFIG_KEYS
-BTF_ID(func, bpf_lsm_key_free)
-#endif /* CONFIG_KEYS */
-
 BTF_ID(func, bpf_lsm_mmap_file)
 BTF_ID(func, bpf_lsm_netlink_send)
 BTF_ID(func, bpf_lsm_path_notify)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 75e4fe83c509..5cd1c7a23848 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3523,7 +3523,7 @@ end:
  *   (i + 1) * elem_size
  * where i is the repeat index and elem_size is the size of an element.
  */
-static int btf_repeat_fields(struct btf_field_info *info,
+static int btf_repeat_fields(struct btf_field_info *info, int info_cnt,
 			     u32 field_cnt, u32 repeat_cnt, u32 elem_size)
 {
 	u32 i, j;
@@ -3543,6 +3543,12 @@ static int btf_repeat_fields(struct btf_field_info *info,
 		}
 	}
 
+	/* The type of struct size or variable size is u32,
+	 * so the multiplication will not overflow.
+	 */
+	if (field_cnt * (repeat_cnt + 1) > info_cnt)
+		return -E2BIG;
+
 	cur = field_cnt;
 	for (i = 0; i < repeat_cnt; i++) {
 		memcpy(&info[cur], &info[0], field_cnt * sizeof(info[0]));
@@ -3587,7 +3593,7 @@ static int btf_find_nested_struct(const struct btf *btf, const struct btf_type *
 		info[i].off += off;
 
 	if (nelems > 1) {
-		err = btf_repeat_fields(info, ret, nelems - 1, t->size);
+		err = btf_repeat_fields(info, info_cnt, ret, nelems - 1, t->size);
 		if (err == 0)
 			ret *= nelems;
 		else
@@ -3681,10 +3687,10 @@ static int btf_find_field_one(const struct btf *btf,
 
 	if (ret == BTF_FIELD_IGNORE)
 		return 0;
-	if (nelems > info_cnt)
+	if (!info_cnt)
 		return -E2BIG;
 	if (nelems > 1) {
-		ret = btf_repeat_fields(info, 1, nelems - 1, sz);
+		ret = btf_repeat_fields(info, info_cnt, 1, nelems - 1, sz);
 		if (ret < 0)
 			return ret;
 	}
@@ -8961,6 +8967,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
 	if (!type) {
 		bpf_log(ctx->log, "relo #%u: bad type id %u\n",
 			relo_idx, relo->type_id);
+		kfree(specs);
 		return -EINVAL;
 	}
 
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 9e0e3b0a18e4..7878be18e9d2 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -333,9 +333,11 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
 
 static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
 				struct xdp_frame **frames, int n,
-				struct net_device *dev)
+				struct net_device *tx_dev,
+				struct net_device *rx_dev)
 {
-	struct xdp_txq_info txq = { .dev = dev };
+	struct xdp_txq_info txq = { .dev = tx_dev };
+	struct xdp_rxq_info rxq = { .dev = rx_dev };
 	struct xdp_buff xdp;
 	int i, nframes = 0;
 
@@ -346,6 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
 
 		xdp_convert_frame_to_buff(xdpf, &xdp);
 		xdp.txq = &txq;
+		xdp.rxq = &rxq;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 		switch (act) {
@@ -360,7 +363,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
 			bpf_warn_invalid_xdp_action(NULL, xdp_prog, act);
 			fallthrough;
 		case XDP_ABORTED:
-			trace_xdp_exception(dev, xdp_prog, act);
+			trace_xdp_exception(tx_dev, xdp_prog, act);
 			fallthrough;
 		case XDP_DROP:
 			xdp_return_frame_rx_napi(xdpf);
@@ -388,7 +391,7 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 	}
 
 	if (bq->xdp_prog) {
-		to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev);
+		to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx);
 		if (!to_send)
 			goto out;
 	}
diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index 5aebfc3051e3..4a858fdb6476 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -688,8 +688,7 @@ static void print_reg_state(struct bpf_verifier_env *env,
 	if (t == SCALAR_VALUE && reg->precise)
 		verbose(env, "P");
 	if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) {
-		/* reg->off should be 0 for SCALAR_VALUE */
-		verbose_snum(env, reg->var_off.value + reg->off);
+		verbose_snum(env, reg->var_off.value);
 		return;
 	}
 
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index e20b90c36131..de3b681d1d13 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -29,7 +29,7 @@ struct bpf_ringbuf {
 	u64 mask;
 	struct page **pages;
 	int nr_pages;
-	spinlock_t spinlock ____cacheline_aligned_in_smp;
+	raw_spinlock_t spinlock ____cacheline_aligned_in_smp;
 	/* For user-space producer ring buffers, an atomic_t busy bit is used
 	 * to synchronize access to the ring buffers in the kernel, rather than
 	 * the spinlock that is used for kernel-producer ring buffers. This is
@@ -173,7 +173,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 	if (!rb)
 		return NULL;
 
-	spin_lock_init(&rb->spinlock);
+	raw_spin_lock_init(&rb->spinlock);
 	atomic_set(&rb->busy, 0);
 	init_waitqueue_head(&rb->waitq);
 	init_irq_work(&rb->work, bpf_ringbuf_notify);
@@ -421,10 +421,10 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 	cons_pos = smp_load_acquire(&rb->consumer_pos);
 
 	if (in_nmi()) {
-		if (!spin_trylock_irqsave(&rb->spinlock, flags))
+		if (!raw_spin_trylock_irqsave(&rb->spinlock, flags))
 			return NULL;
 	} else {
-		spin_lock_irqsave(&rb->spinlock, flags);
+		raw_spin_lock_irqsave(&rb->spinlock, flags);
 	}
 
 	pend_pos = rb->pending_pos;
@@ -450,7 +450,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 	 */
 	if (new_prod_pos - cons_pos > rb->mask ||
 	    new_prod_pos - pend_pos > rb->mask) {
-		spin_unlock_irqrestore(&rb->spinlock, flags);
+		raw_spin_unlock_irqrestore(&rb->spinlock, flags);
 		return NULL;
 	}
 
@@ -462,7 +462,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 	/* pairs with consumer's smp_load_acquire() */
 	smp_store_release(&rb->producer_pos, new_prod_pos);
 
-	spin_unlock_irqrestore(&rb->spinlock, flags);
+	raw_spin_unlock_irqrestore(&rb->spinlock, flags);
 
 	return (void *)hdr + BPF_RINGBUF_HDR_SZ;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a8f1808a1ca5..8cfa7183d2ef 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3565,15 +3565,16 @@ static void bpf_perf_link_dealloc(struct bpf_link *link)
 }
 
 static int bpf_perf_link_fill_common(const struct perf_event *event,
-				     char __user *uname, u32 ulen,
+				     char __user *uname, u32 *ulenp,
 				     u64 *probe_offset, u64 *probe_addr,
 				     u32 *fd_type, unsigned long *missed)
 {
 	const char *buf;
-	u32 prog_id;
+	u32 prog_id, ulen;
 	size_t len;
 	int err;
 
+	ulen = *ulenp;
 	if (!ulen ^ !uname)
 		return -EINVAL;
 
@@ -3581,10 +3582,17 @@ static int bpf_perf_link_fill_common(const struct perf_event *event,
 				      probe_offset, probe_addr, missed);
 	if (err)
 		return err;
+
+	if (buf) {
+		len = strlen(buf);
+		*ulenp = len + 1;
+	} else {
+		*ulenp = 1;
+	}
 	if (!uname)
 		return 0;
+
 	if (buf) {
-		len = strlen(buf);
 		err = bpf_copy_to_user(uname, buf, ulen, len);
 		if (err)
 			return err;
@@ -3609,7 +3617,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
 
 	uname = u64_to_user_ptr(info->perf_event.kprobe.func_name);
 	ulen = info->perf_event.kprobe.name_len;
-	err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+	err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr,
 					&type, &missed);
 	if (err)
 		return err;
@@ -3617,7 +3625,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
 		info->perf_event.type = BPF_PERF_EVENT_KRETPROBE;
 	else
 		info->perf_event.type = BPF_PERF_EVENT_KPROBE;
-
+	info->perf_event.kprobe.name_len = ulen;
 	info->perf_event.kprobe.offset = offset;
 	info->perf_event.kprobe.missed = missed;
 	if (!kallsyms_show_value(current_cred()))
@@ -3639,7 +3647,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
 
 	uname = u64_to_user_ptr(info->perf_event.uprobe.file_name);
 	ulen = info->perf_event.uprobe.name_len;
-	err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+	err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr,
 					&type, NULL);
 	if (err)
 		return err;
@@ -3648,6 +3656,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
 		info->perf_event.type = BPF_PERF_EVENT_URETPROBE;
 	else
 		info->perf_event.type = BPF_PERF_EVENT_UPROBE;
+	info->perf_event.uprobe.name_len = ulen;
 	info->perf_event.uprobe.offset = offset;
 	info->perf_event.uprobe.cookie = event->bpf_cookie;
 	return 0;
@@ -3673,12 +3682,18 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event,
 {
 	char __user *uname;
 	u32 ulen;
+	int err;
 
 	uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name);
 	ulen = info->perf_event.tracepoint.name_len;
+	err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL);
+	if (err)
+		return err;
+
 	info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT;
+	info->perf_event.tracepoint.name_len = ulen;
 	info->perf_event.tracepoint.cookie = event->bpf_cookie;
-	return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL);
+	return 0;
 }
 
 static int bpf_perf_link_fill_perf_event(const struct perf_event *event,
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 02aa9db8d796..5af9e130e500 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -99,7 +99,7 @@ static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *co
 		rcu_read_lock();
 		pid = find_pid_ns(common->pid, common->ns);
 		if (pid) {
-			task = get_pid_task(pid, PIDTYPE_TGID);
+			task = get_pid_task(pid, PIDTYPE_PID);
 			*tid = common->pid;
 		}
 		rcu_read_unlock();
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9a7ed527e47e..411ab1b57af4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2750,10 +2750,16 @@ static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env,
 		b->module = mod;
 		b->offset = offset;
 
+		/* sort() reorders entries by value, so b may no longer point
+		 * to the right entry after this
+		 */
 		sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
 		     kfunc_btf_cmp_by_off, NULL);
+	} else {
+		btf = b->btf;
 	}
-	return b->btf;
+
+	return btf;
 }
 
 void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab)
@@ -6333,10 +6339,10 @@ static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size)
 
 	/* both of s64_max/s64_min positive or negative */
 	if ((s64_max >= 0) == (s64_min >= 0)) {
-		reg->smin_value = reg->s32_min_value = s64_min;
-		reg->smax_value = reg->s32_max_value = s64_max;
-		reg->umin_value = reg->u32_min_value = s64_min;
-		reg->umax_value = reg->u32_max_value = s64_max;
+		reg->s32_min_value = reg->smin_value = s64_min;
+		reg->s32_max_value = reg->smax_value = s64_max;
+		reg->u32_min_value = reg->umin_value = s64_min;
+		reg->u32_max_value = reg->umax_value = s64_max;
 		reg->var_off = tnum_range(s64_min, s64_max);
 		return;
 	}
@@ -14264,12 +14270,13 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	 * r1 += 0x1
 	 * if r2 < 1000 goto ...
 	 * use r1 in memory access
-	 * So remember constant delta between r2 and r1 and update r1 after
-	 * 'if' condition.
+	 * So for 64-bit alu remember constant delta between r2 and r1 and
+	 * update r1 after 'if' condition.
 	 */
-	if (env->bpf_capable && BPF_OP(insn->code) == BPF_ADD &&
-	    dst_reg->id && is_reg_const(src_reg, alu32)) {
-		u64 val = reg_const_value(src_reg, alu32);
+	if (env->bpf_capable &&
+	    BPF_OP(insn->code) == BPF_ADD && !alu32 &&
+	    dst_reg->id && is_reg_const(src_reg, false)) {
+		u64 val = reg_const_value(src_reg, false);
 
 		if ((dst_reg->id & BPF_ADD_CONST) ||
 		    /* prevent overflow in sync_linked_regs() later */
@@ -15326,8 +15333,12 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s
 			continue;
 		if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) ||
 		    reg->off == known_reg->off) {
+			s32 saved_subreg_def = reg->subreg_def;
+
 			copy_register_state(reg, known_reg);
+			reg->subreg_def = saved_subreg_def;
 		} else {
+			s32 saved_subreg_def = reg->subreg_def;
 			s32 saved_off = reg->off;
 
 			fake_reg.type = SCALAR_VALUE;
@@ -15340,6 +15351,7 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s
 			 * otherwise another sync_linked_regs() will be incorrect.
 			 */
 			reg->off = saved_off;
+			reg->subreg_def = saved_subreg_def;
 
 			scalar32_min_max_add(reg, &fake_reg);
 			scalar_min_max_add(reg, &fake_reg);
@@ -22310,7 +22322,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	/* 'struct bpf_verifier_env' can be global, but since it's not small,
 	 * allocate/free it every time bpf_check() is called
 	 */
-	env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
+	env = kvzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
 	if (!env)
 		return -ENOMEM;
 
@@ -22546,6 +22558,6 @@ err_unlock:
 		mutex_unlock(&bpf_verifier_lock);
 	vfree(env->insn_aux_data);
 err_free_env:
-	kfree(env);
+	kvfree(env);
 	return ret;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e3589c4287cb..cdd09769e6c5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9251,7 +9251,7 @@ static void perf_event_switch(struct task_struct *task,
 		},
 	};
 
-	if (!sched_in && task->on_rq) {
+	if (!sched_in && task_is_runnable(task)) {
 		switch_event.event_id.header.misc |=
 				PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
 	}
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 44bbd7dbd2c8..8d530d0949ff 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -109,7 +109,12 @@ static int __set_task_frozen(struct task_struct *p, void *arg)
 {
 	unsigned int state = READ_ONCE(p->__state);
 
-	if (p->on_rq)
+	/*
+	 * Allow freezing the sched_delayed tasks; they will not execute until
+	 * ttwu() fixes them up, so it is safe to swap their state now, instead
+	 * of waiting for them to get fully dequeued.
+	 */
+	if (task_is_runnable(p))
 		return 0;
 
 	if (p != current && task_curr(p))
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 6333f4ccf024..4d7ee95df06e 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -986,6 +986,15 @@ static bool rcu_tasks_is_holdout(struct task_struct *t)
 		return false;
 
 	/*
+	 * t->on_rq && !t->se.sched_delayed *could* be considered sleeping but
+	 * since it is a spurious state (it will transition into the
+	 * traditional blocked state or get woken up without outside
+	 * dependencies), not considering it such should only affect timing.
+	 *
+	 * Be conservative for now and not include it.
+	 */
+
+	/*
 	 * Idle tasks (or idle injection) within the idle loop are RCU-tasks
 	 * quiescent states. But CPU boot code performed by the idle task
 	 * isn't a quiescent state.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index aeb595514461..dbfb5717d6af 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -548,6 +548,11 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
  *   ON_RQ_MIGRATING state is used for migration without holding both
  *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
  *
+ *   Additionally it is possible to be ->on_rq but still be considered not
+ *   runnable when p->se.sched_delayed is true. These tasks are on the runqueue
+ *   but will be dequeued as soon as they get picked again. See the
+ *   task_is_runnable() helper.
+ *
  * p->on_cpu <- { 0, 1 }:
  *
  *   is set by prepare_task() and cleared by finish_task() such that it will be
@@ -2012,11 +2017,6 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	if (!(flags & ENQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
-	if (!(flags & ENQUEUE_RESTORE)) {
-		sched_info_enqueue(rq, p);
-		psi_enqueue(p, (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED));
-	}
-
 	p->sched_class->enqueue_task(rq, p, flags);
 	/*
 	 * Must be after ->enqueue_task() because ENQUEUE_DELAYED can clear
@@ -2024,6 +2024,11 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	 */
 	uclamp_rq_inc(rq, p);
 
+	if (!(flags & ENQUEUE_RESTORE)) {
+		sched_info_enqueue(rq, p);
+		psi_enqueue(p, flags & ENQUEUE_MIGRATED);
+	}
+
 	if (sched_core_enabled(rq))
 		sched_core_enqueue(rq, p);
 }
@@ -2041,7 +2046,7 @@ inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!(flags & DEQUEUE_SAVE)) {
 		sched_info_dequeue(rq, p);
-		psi_dequeue(p, flags & DEQUEUE_SLEEP);
+		psi_dequeue(p, !(flags & DEQUEUE_SLEEP));
 	}
 
 	/*
@@ -4323,9 +4328,10 @@ static bool __task_needs_rq_lock(struct task_struct *p)
  * @arg: Argument to function.
  *
  * Fix the task in it's current state by avoiding wakeups and or rq operations
- * and call @func(@arg) on it.  This function can use ->on_rq and task_curr()
- * to work out what the state is, if required.  Given that @func can be invoked
- * with a runqueue lock held, it had better be quite lightweight.
+ * and call @func(@arg) on it.  This function can use task_is_runnable() and
+ * task_curr() to work out what the state is, if required.  Given that @func
+ * can be invoked with a runqueue lock held, it had better be quite
+ * lightweight.
  *
  * Returns:
  *   Whatever @func returns
@@ -6544,6 +6550,7 @@ static void __sched notrace __schedule(int sched_mode)
 	 * as a preemption by schedule_debug() and RCU.
 	 */
 	bool preempt = sched_mode > SM_NONE;
+	bool block = false;
 	unsigned long *switch_count;
 	unsigned long prev_state;
 	struct rq_flags rf;
@@ -6629,6 +6636,7 @@ static void __sched notrace __schedule(int sched_mode)
 			 * After this, schedule() must not care about p->state any more.
 			 */
 			block_task(rq, prev, flags);
+			block = true;
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -6674,7 +6682,7 @@ picked:
 
 		migrate_disable_switch(rq, prev);
 		psi_account_irqtime(rq, prev, next);
-		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
+		psi_sched_switch(prev, next, block);
 
 		trace_sched_switch(preempt, prev, next, prev_state);
 
@@ -7017,20 +7025,20 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag
 }
 EXPORT_SYMBOL(default_wake_function);
 
-void __setscheduler_prio(struct task_struct *p, int prio)
+const struct sched_class *__setscheduler_class(struct task_struct *p, int prio)
 {
 	if (dl_prio(prio))
-		p->sched_class = &dl_sched_class;
-	else if (rt_prio(prio))
-		p->sched_class = &rt_sched_class;
+		return &dl_sched_class;
+
+	if (rt_prio(prio))
+		return &rt_sched_class;
+
 #ifdef CONFIG_SCHED_CLASS_EXT
-	else if (task_should_scx(p))
-		p->sched_class = &ext_sched_class;
+	if (task_should_scx(p))
+		return &ext_sched_class;
 #endif
-	else
-		p->sched_class = &fair_sched_class;
 
-	p->prio = prio;
+	return &fair_sched_class;
 }
 
 #ifdef CONFIG_RT_MUTEXES
@@ -7076,7 +7084,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 {
 	int prio, oldprio, queued, running, queue_flag =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
-	const struct sched_class *prev_class;
+	const struct sched_class *prev_class, *next_class;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -7134,6 +7142,11 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 		queue_flag &= ~DEQUEUE_MOVE;
 
 	prev_class = p->sched_class;
+	next_class = __setscheduler_class(p, prio);
+
+	if (prev_class != next_class && p->se.sched_delayed)
+		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
+
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
@@ -7171,7 +7184,9 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 			p->rt.timeout = 0;
 	}
 
-	__setscheduler_prio(p, prio);
+	p->sched_class = next_class;
+	p->prio = prio;
+
 	check_class_changing(rq, p, prev_class);
 
 	if (queued)
@@ -10465,7 +10480,9 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
 		return;
 	if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan)))
 		return;
-	task_work_add(curr, work, TWA_RESUME);
+
+	/* No page allocation under rq lock */
+	task_work_add(curr, work, TWA_RESUME | TWAF_NO_ALLOC);
 }
 
 void sched_mm_cid_exit_signals(struct task_struct *t)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9ce93d0bf452..be1b917dc8ce 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2385,7 +2385,7 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 
 	deadline_queue_push_tasks(rq);
 
-	if (hrtick_enabled(rq))
+	if (hrtick_enabled_dl(rq))
 		start_hrtick_dl(rq, &p->dl);
 }
 
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 6eae3b69bf6e..5900b06fd036 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4493,7 +4493,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 
 		sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
 
-		__setscheduler_prio(p, p->prio);
+		p->sched_class = __setscheduler_class(p, p->prio);
 		check_class_changing(task_rq(p), p, old_class);
 
 		sched_enq_and_set_task(&ctx);
@@ -5204,7 +5204,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
 
 		p->scx.slice = SCX_SLICE_DFL;
-		__setscheduler_prio(p, p->prio);
+		p->sched_class = __setscheduler_class(p, p->prio);
 		check_class_changing(task_rq(p), p, old_class);
 
 		sched_enq_and_set_task(&ctx);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 225b31aaee55..c157d4860a3b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1247,7 +1247,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 
 	account_cfs_rq_runtime(cfs_rq, delta_exec);
 
-	if (rq->nr_running == 1)
+	if (cfs_rq->nr_running == 1)
 		return;
 
 	if (resched || did_preempt_short(cfs_rq, curr)) {
@@ -6058,10 +6058,13 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 
-		if (se->on_rq) {
-			SCHED_WARN_ON(se->sched_delayed);
+		/* Handle any unfinished DELAY_DEQUEUE business first. */
+		if (se->sched_delayed) {
+			int flags = DEQUEUE_SLEEP | DEQUEUE_DELAYED;
+
+			dequeue_entity(qcfs_rq, se, flags);
+		} else if (se->on_rq)
 			break;
-		}
 		enqueue_entity(qcfs_rq, se, ENQUEUE_WAKEUP);
 
 		if (cfs_rq_is_idle(group_cfs_rq(se)))
@@ -13174,22 +13177,6 @@ static void attach_task_cfs_rq(struct task_struct *p)
 static void switched_from_fair(struct rq *rq, struct task_struct *p)
 {
 	detach_task_cfs_rq(p);
-	/*
-	 * Since this is called after changing class, this is a little weird
-	 * and we cannot use DEQUEUE_DELAYED.
-	 */
-	if (p->se.sched_delayed) {
-		/* First, dequeue it from its new class' structures */
-		dequeue_task(rq, p, DEQUEUE_NOCLOCK | DEQUEUE_SLEEP);
-		/*
-		 * Now, clean up the fair_sched_class side of things
-		 * related to sched_delayed being true and that wasn't done
-		 * due to the generic dequeue not using DEQUEUE_DELAYED.
-		 */
-		finish_delayed_dequeue_entity(&p->se);
-		p->se.rel_deadline = 0;
-		__block_task(rq, p);
-	}
 }
 
 static void switched_to_fair(struct rq *rq, struct task_struct *p)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6085ef50febf..081519ffab46 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3800,7 +3800,7 @@ static inline int rt_effective_prio(struct task_struct *p, int prio)
 
 extern int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi);
 extern int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
-extern void __setscheduler_prio(struct task_struct *p, int prio);
+extern const struct sched_class *__setscheduler_class(struct task_struct *p, int prio);
 extern void set_load_weight(struct task_struct *p, bool update_load);
 extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags);
 extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags);
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 237780aa3c53..767e098a3bd1 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -119,45 +119,63 @@ static inline void psi_account_irqtime(struct rq *rq, struct task_struct *curr,
 /*
  * PSI tracks state that persists across sleeps, such as iowaits and
  * memory stalls. As a result, it has to distinguish between sleeps,
- * where a task's runnable state changes, and requeues, where a task
- * and its state are being moved between CPUs and runqueues.
+ * where a task's runnable state changes, and migrations, where a task
+ * and its runnable state are being moved between CPUs and runqueues.
+ *
+ * A notable case is a task whose dequeue is delayed. PSI considers
+ * those sleeping, but because they are still on the runqueue they can
+ * go through migration requeues. In this case, *sleeping* states need
+ * to be transferred.
  */
-static inline void psi_enqueue(struct task_struct *p, bool wakeup)
+static inline void psi_enqueue(struct task_struct *p, bool migrate)
 {
-	int clear = 0, set = TSK_RUNNING;
+	int clear = 0, set = 0;
 
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	if (p->in_memstall)
-		set |= TSK_MEMSTALL_RUNNING;
-
-	if (!wakeup) {
+	if (p->se.sched_delayed) {
+		/* CPU migration of "sleeping" task */
+		SCHED_WARN_ON(!migrate);
 		if (p->in_memstall)
 			set |= TSK_MEMSTALL;
+		if (p->in_iowait)
+			set |= TSK_IOWAIT;
+	} else if (migrate) {
+		/* CPU migration of runnable task */
+		set = TSK_RUNNING;
+		if (p->in_memstall)
+			set |= TSK_MEMSTALL | TSK_MEMSTALL_RUNNING;
 	} else {
+		/* Wakeup of new or sleeping task */
 		if (p->in_iowait)
 			clear |= TSK_IOWAIT;
+		set = TSK_RUNNING;
+		if (p->in_memstall)
+			set |= TSK_MEMSTALL_RUNNING;
 	}
 
 	psi_task_change(p, clear, set);
 }
 
-static inline void psi_dequeue(struct task_struct *p, bool sleep)
+static inline void psi_dequeue(struct task_struct *p, bool migrate)
 {
 	if (static_branch_likely(&psi_disabled))
 		return;
 
 	/*
+	 * When migrating a task to another CPU, clear all psi
+	 * state. The enqueue callback above will work it out.
+	 */
+	if (migrate)
+		psi_task_change(p, p->psi_flags, 0);
+
+	/*
 	 * A voluntary sleep is a dequeue followed by a task switch. To
 	 * avoid walking all ancestors twice, psi_task_switch() handles
 	 * TSK_RUNNING and TSK_IOWAIT for us when it moves TSK_ONCPU.
 	 * Do nothing here.
 	 */
-	if (sleep)
-		return;
-
-	psi_task_change(p, p->psi_flags, 0);
 }
 
 static inline void psi_ttwu_dequeue(struct task_struct *p)
@@ -190,8 +208,8 @@ static inline void psi_sched_switch(struct task_struct *prev,
 }
 
 #else /* CONFIG_PSI */
-static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
-static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
+static inline void psi_enqueue(struct task_struct *p, bool migrate) {}
+static inline void psi_dequeue(struct task_struct *p, bool migrate) {}
 static inline void psi_ttwu_dequeue(struct task_struct *p) {}
 static inline void psi_sched_switch(struct task_struct *prev,
 				    struct task_struct *next,
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index aa70beee9895..0470bcc3d204 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -529,7 +529,7 @@ int __sched_setscheduler(struct task_struct *p,
 {
 	int oldpolicy = -1, policy = attr->sched_policy;
 	int retval, oldprio, newprio, queued, running;
-	const struct sched_class *prev_class;
+	const struct sched_class *prev_class, *next_class;
 	struct balance_callback *head;
 	struct rq_flags rf;
 	int reset_on_fork;
@@ -706,6 +706,12 @@ change:
 			queue_flags &= ~DEQUEUE_MOVE;
 	}
 
+	prev_class = p->sched_class;
+	next_class = __setscheduler_class(p, newprio);
+
+	if (prev_class != next_class && p->se.sched_delayed)
+		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
+
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
@@ -713,11 +719,10 @@ change:
 	if (running)
 		put_prev_task(rq, p);
 
-	prev_class = p->sched_class;
-
 	if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
 		__setscheduler_params(p, attr);
-		__setscheduler_prio(p, newprio);
+		p->sched_class = next_class;
+		p->prio = newprio;
 	}
 	__setscheduler_uclamp(p, attr);
 	check_class_changing(rq, p, prev_class);
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 5d14d639ac71..c969f1f26be5 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -55,15 +55,26 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 		  enum task_work_notify_mode notify)
 {
 	struct callback_head *head;
+	int flags = notify & TWA_FLAGS;
 
+	notify &= ~TWA_FLAGS;
 	if (notify == TWA_NMI_CURRENT) {
 		if (WARN_ON_ONCE(task != current))
 			return -EINVAL;
 		if (!IS_ENABLED(CONFIG_IRQ_WORK))
 			return -EINVAL;
 	} else {
-		/* record the work call stack in order to print it in KASAN reports */
-		kasan_record_aux_stack(work);
+		/*
+		 * Record the work call stack in order to print it in KASAN
+		 * reports.
+		 *
+		 * Note that stack allocation can fail if TWAF_NO_ALLOC flag
+		 * is set and new page is needed to expand the stack buffer.
+		 */
+		if (flags & TWAF_NO_ALLOC)
+			kasan_record_aux_stack_noalloc(work);
+		else
+			kasan_record_aux_stack(work);
 	}
 
 	head = READ_ONCE(task->task_works);
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 316a4e8c97d3..1af0bb2cc45c 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -309,6 +309,9 @@ static int pc_clock_settime(clockid_t id, const struct timespec64 *ts)
 	struct posix_clock_desc cd;
 	int err;
 
+	if (!timespec64_valid_strict(ts))
+		return -EINVAL;
+
 	err = get_clock_desc(id, &cd);
 	if (err)
 		return err;
@@ -318,9 +321,6 @@ static int pc_clock_settime(clockid_t id, const struct timespec64 *ts)
 		goto out;
 	}
 
-	if (!timespec64_valid_strict(ts))
-		return -EINVAL;
-
 	if (cd.clk->ops.clock_settime)
 		err = cd.clk->ops.clock_settime(cd.clk, ts);
 	else
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 753a184c7090..f203f000da1a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -434,6 +434,12 @@ static void tick_nohz_kick_task(struct task_struct *tsk)
 	 *   smp_mb__after_spin_lock()
 	 *   tick_nohz_task_switch()
 	 *     LOAD p->tick_dep_mask
+	 *
+	 * XXX given a task picks up the dependency on schedule(), should we
+	 * only care about tasks that are currently on the CPU instead of all
+	 * that are on the runqueue?
+	 *
+	 * That is, does this want to be: task_on_cpu() / task_curr()?
 	 */
 	if (!sched_task_on_rq(tsk))
 		return;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a582cd25ca87..3bd402fa62a4 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3133,7 +3133,8 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
 	struct bpf_uprobe_multi_link *umulti_link;
 	u32 ucount = info->uprobe_multi.count;
 	int err = 0, i;
-	long left;
+	char *p, *buf;
+	long left = 0;
 
 	if (!upath ^ !upath_size)
 		return -EINVAL;
@@ -3147,26 +3148,23 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
 	info->uprobe_multi.pid = umulti_link->task ?
 				 task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0;
 
-	if (upath) {
-		char *p, *buf;
-
-		upath_size = min_t(u32, upath_size, PATH_MAX);
-
-		buf = kmalloc(upath_size, GFP_KERNEL);
-		if (!buf)
-			return -ENOMEM;
-		p = d_path(&umulti_link->path, buf, upath_size);
-		if (IS_ERR(p)) {
-			kfree(buf);
-			return PTR_ERR(p);
-		}
-		upath_size = buf + upath_size - p;
-		left = copy_to_user(upath, p, upath_size);
+	upath_size = upath_size ? min_t(u32, upath_size, PATH_MAX) : PATH_MAX;
+	buf = kmalloc(upath_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	p = d_path(&umulti_link->path, buf, upath_size);
+	if (IS_ERR(p)) {
 		kfree(buf);
-		if (left)
-			return -EFAULT;
-		info->uprobe_multi.path_size = upath_size;
+		return PTR_ERR(p);
 	}
+	upath_size = buf + upath_size - p;
+
+	if (upath)
+		left = copy_to_user(upath, p, upath_size);
+	kfree(buf);
+	if (left)
+		return -EFAULT;
+	info->uprobe_multi.path_size = upath_size;
 
 	if (!uoffsets && !ucookies && !uref_ctr_offsets)
 		return 0;
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index d7d4fb403f6f..41e7a15dcb50 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1160,19 +1160,14 @@ void fgraph_update_pid_func(void)
 static int start_graph_tracing(void)
 {
 	unsigned long **ret_stack_list;
-	int ret, cpu;
+	int ret;
 
-	ret_stack_list = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
+	ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE,
+				 sizeof(*ret_stack_list), GFP_KERNEL);
 
 	if (!ret_stack_list)
 		return -ENOMEM;
 
-	/* The cpu_boot init_task->ret_stack will never be freed */
-	for_each_online_cpu(cpu) {
-		if (!idle_task(cpu)->ret_stack)
-			ftrace_graph_init_idle_task(idle_task(cpu), cpu);
-	}
-
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
@@ -1242,14 +1237,34 @@ static void ftrace_graph_disable_direct(bool disable_branch)
 	fgraph_direct_gops = &fgraph_stub;
 }
 
+/* The cpu_boot init_task->ret_stack will never be freed */
+static int fgraph_cpu_init(unsigned int cpu)
+{
+	if (!idle_task(cpu)->ret_stack)
+		ftrace_graph_init_idle_task(idle_task(cpu), cpu);
+	return 0;
+}
+
 int register_ftrace_graph(struct fgraph_ops *gops)
 {
+	static bool fgraph_initialized;
 	int command = 0;
 	int ret = 0;
 	int i = -1;
 
 	mutex_lock(&ftrace_lock);
 
+	if (!fgraph_initialized) {
+		ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph_idle_init",
+					fgraph_cpu_init, NULL);
+		if (ret < 0) {
+			pr_warn("fgraph: Error to init cpu hotplug support\n");
+			return ret;
+		}
+		fgraph_initialized = true;
+		ret = 0;
+	}
+
 	if (!fgraph_array[0]) {
 		/* The array must always have real data on it */
 		for (i = 0; i < FGRAPH_ARRAY_SIZE; i++)
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index b0e0ec85912e..ebda68ee9abf 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -912,6 +912,11 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 		}
 	}
 
+	if (argc - 2 > MAX_TRACE_ARGS) {
+		ret = -E2BIG;
+		goto error;
+	}
+
 	mutex_lock(&event_mutex);
 	event_call = find_and_get_event(sys_name, sys_event);
 	ep = alloc_event_probe(group, event, event_call, argc - 2);
@@ -937,7 +942,7 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 
 	argc -= 2; argv += 2;
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		trace_probe_log_set_index(i + 2);
 		ret = trace_eprobe_tp_update_arg(ep, argv, i);
 		if (ret)
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index a079abd8955b..c62d1629cffe 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1187,6 +1187,10 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		argc = new_argc;
 		argv = new_argv;
 	}
+	if (argc > MAX_TRACE_ARGS) {
+		ret = -E2BIG;
+		goto out;
+	}
 
 	ret = traceprobe_expand_dentry_args(argc, argv, &dbuf);
 	if (ret)
@@ -1203,7 +1207,7 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	}
 
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		trace_probe_log_set_index(i + 2);
 		ctx.offset = 0;
 		ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 61a6da808203..263fac44d3ca 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1013,6 +1013,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 		argc = new_argc;
 		argv = new_argv;
 	}
+	if (argc > MAX_TRACE_ARGS) {
+		ret = -E2BIG;
+		goto out;
+	}
 
 	ret = traceprobe_expand_dentry_args(argc, argv, &dbuf);
 	if (ret)
@@ -1029,7 +1033,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 	}
 
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		trace_probe_log_set_index(i + 2);
 		ctx.offset = 0;
 		ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 39877c80d6cb..16a5e368e7b7 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -276,7 +276,7 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
 		}
 		trace_probe_log_err(offset, NO_EVENT_NAME);
 		return -EINVAL;
-	} else if (len > MAX_EVENT_NAME_LEN) {
+	} else if (len >= MAX_EVENT_NAME_LEN) {
 		trace_probe_log_err(offset, EVENT_TOO_LONG);
 		return -EINVAL;
 	}
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index c4ad7cd7e778..1469dd8075fa 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1485,7 +1485,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	/* reset the max latency */
 	tr->max_latency = 0;
 
-	while (p->on_rq) {
+	while (task_is_runnable(p)) {
 		/*
 		 * Sleep to make sure the -deadline thread is asleep too.
 		 * On virtual machines we can't rely on timings,
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c40531d2cbad..b30fc8fcd095 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -565,6 +565,8 @@ static int __trace_uprobe_create(int argc, const char **argv)
 
 	if (argc < 2)
 		return -ECANCELED;
+	if (argc - 2 > MAX_TRACE_ARGS)
+		return -E2BIG;
 
 	if (argv[0][1] == ':')
 		event = &argv[0][2];
@@ -690,7 +692,7 @@ static int __trace_uprobe_create(int argc, const char **argv)
 	tu->filename = filename;
 
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		struct traceprobe_parse_context ctx = {
 			.flags = (is_return ? TPARG_FL_RETURN : 0) | TPARG_FL_USER,
 		};
@@ -875,6 +877,7 @@ struct uprobe_cpu_buffer {
 };
 static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer;
 static int uprobe_buffer_refcnt;
+#define MAX_UCB_BUFFER_SIZE PAGE_SIZE
 
 static int uprobe_buffer_init(void)
 {
@@ -979,6 +982,11 @@ static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu,
 	ucb = uprobe_buffer_get();
 	ucb->dsize = tu->tp.size + dsize;
 
+	if (WARN_ON_ONCE(ucb->dsize > MAX_UCB_BUFFER_SIZE)) {
+		ucb->dsize = MAX_UCB_BUFFER_SIZE;
+		dsize = MAX_UCB_BUFFER_SIZE - tu->tp.size;
+	}
+
 	store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize);
 
 	*ucbp = ucb;
@@ -998,9 +1006,6 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
 
 	WARN_ON(call != trace_file->event_call);
 
-	if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE))
-		return;
-
 	if (trace_trigger_soft_disabled(trace_file))
 		return;