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

Cross-merge networking fixes after downstream PR.

Conflicts:

net/dsa/port.c
  9945c1fb03a3 ("net: dsa: fix older DSA drivers using phylink")
  a88dd7538461 ("net: dsa: remove legacy_pre_march2020 detection")
https://lore.kernel.org/all/20230731102254.2c9868ca@canb.auug.org.au/

net/xdp/xsk.c
  3c5b4d69c358 ("net: annotate data-races around sk->sk_mark")
  b7f72a30e9ac ("xsk: introduce wrappers and helpers for supporting multi-buffer in Tx path")
https://lore.kernel.org/all/20230731102631.39988412@canb.auug.org.au/

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  37b61cda9c16 ("bnxt: don't handle XDP in netpoll")
  2b56b3d99241 ("eth: bnxt: handle invalid Tx completions more gracefully")
https://lore.kernel.org/all/20230801101708.1dc7faac@canb.auug.org.au/

Adjacent changes:

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
  62da08331f1a ("net/mlx5e: Set proper IPsec source port in L4 selector")
  fbd517549c32 ("net/mlx5e: Add function to get IPsec offload namespace")

drivers/net/ethernet/sfc/selftest.c
  55c1528f9b97 ("sfc: fix field-spanning memcpy in selftest")
  ae9d445cd41f ("sfc: Miscellaneous comment removals")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

13 files changed, 226 insertions, 122 deletions

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 6ae02be7a48e..286ab3db0fde 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
+#include <linux/completion.h>
 #include <trace/events/xdp.h>
 #include <linux/btf_ids.h>
 
@@ -73,6 +74,7 @@ struct bpf_cpu_map_entry {
 	struct rcu_head rcu;
 
 	struct work_struct kthread_stop_wq;
+	struct completion kthread_running;
 };
 
 struct bpf_cpu_map {
@@ -129,11 +131,17 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 	 * invoked cpu_map_kthread_stop(). Catch any broken behaviour
 	 * gracefully and warn once.
 	 */
-	struct xdp_frame *xdpf;
+	void *ptr;
 
-	while ((xdpf = ptr_ring_consume(ring)))
-		if (WARN_ON_ONCE(xdpf))
-			xdp_return_frame(xdpf);
+	while ((ptr = ptr_ring_consume(ring))) {
+		WARN_ON_ONCE(1);
+		if (unlikely(__ptr_test_bit(0, &ptr))) {
+			__ptr_clear_bit(0, &ptr);
+			kfree_skb(ptr);
+			continue;
+		}
+		xdp_return_frame(ptr);
+	}
 }
 
 static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
@@ -153,7 +161,6 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 static void cpu_map_kthread_stop(struct work_struct *work)
 {
 	struct bpf_cpu_map_entry *rcpu;
-	int err;
 
 	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
 
@@ -163,14 +170,7 @@ static void cpu_map_kthread_stop(struct work_struct *work)
 	rcu_barrier();
 
 	/* kthread_stop will wake_up_process and wait for it to complete */
-	err = kthread_stop(rcpu->kthread);
-	if (err) {
-		/* kthread_stop may be called before cpu_map_kthread_run
-		 * is executed, so we need to release the memory related
-		 * to rcpu.
-		 */
-		put_cpu_map_entry(rcpu);
-	}
+	kthread_stop(rcpu->kthread);
 }
 
 static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
@@ -298,11 +298,11 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 	return nframes;
 }
 
-
 static int cpu_map_kthread_run(void *data)
 {
 	struct bpf_cpu_map_entry *rcpu = data;
 
+	complete(&rcpu->kthread_running);
 	set_current_state(TASK_INTERRUPTIBLE);
 
 	/* When kthread gives stop order, then rcpu have been disconnected
@@ -467,6 +467,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 		goto free_ptr_ring;
 
 	/* Setup kthread */
+	init_completion(&rcpu->kthread_running);
 	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
 					       "cpumap/%d/map:%d", cpu,
 					       map->id);
@@ -480,6 +481,12 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	kthread_bind(rcpu->kthread, cpu);
 	wake_up_process(rcpu->kthread);
 
+	/* Make sure kthread has been running, so kthread_stop() will not
+	 * stop the kthread prematurely and all pending frames or skbs
+	 * will be handled by the kthread before kthread_stop() returns.
+	 */
+	wait_for_completion(&rcpu->kthread_running);
+
 	return rcpu;
 
 free_prog:
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1fc6095d502d..ca385b61d546 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1545,6 +1545,17 @@ static int check_ftrace_location(struct kprobe *p)
 	return 0;
 }
 
+static bool is_cfi_preamble_symbol(unsigned long addr)
+{
+	char symbuf[KSYM_NAME_LEN];
+
+	if (lookup_symbol_name(addr, symbuf))
+		return false;
+
+	return str_has_prefix("__cfi_", symbuf) ||
+		str_has_prefix("__pfx_", symbuf);
+}
+
 static int check_kprobe_address_safe(struct kprobe *p,
 				     struct module **probed_mod)
 {
@@ -1563,7 +1574,8 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
 	    static_call_text_reserved(p->addr, p->addr) ||
-	    find_bug((unsigned long)p->addr)) {
+	    find_bug((unsigned long)p->addr) ||
+	    is_cfi_preamble_symbol((unsigned long)p->addr)) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 728f434de2bb..21db0df0eb00 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -333,21 +333,43 @@ static __always_inline int __waiter_prio(struct task_struct *task)
 	return prio;
 }
 
+/*
+ * Update the waiter->tree copy of the sort keys.
+ */
 static __always_inline void
 waiter_update_prio(struct rt_mutex_waiter *waiter, struct task_struct *task)
 {
-	waiter->prio = __waiter_prio(task);
-	waiter->deadline = task->dl.deadline;
+	lockdep_assert_held(&waiter->lock->wait_lock);
+	lockdep_assert(RB_EMPTY_NODE(&waiter->tree.entry));
+
+	waiter->tree.prio = __waiter_prio(task);
+	waiter->tree.deadline = task->dl.deadline;
+}
+
+/*
+ * Update the waiter->pi_tree copy of the sort keys (from the tree copy).
+ */
+static __always_inline void
+waiter_clone_prio(struct rt_mutex_waiter *waiter, struct task_struct *task)
+{
+	lockdep_assert_held(&waiter->lock->wait_lock);
+	lockdep_assert_held(&task->pi_lock);
+	lockdep_assert(RB_EMPTY_NODE(&waiter->pi_tree.entry));
+
+	waiter->pi_tree.prio = waiter->tree.prio;
+	waiter->pi_tree.deadline = waiter->tree.deadline;
 }
 
 /*
- * Only use with rt_mutex_waiter_{less,equal}()
+ * Only use with rt_waiter_node_{less,equal}()
  */
+#define task_to_waiter_node(p)	\
+	&(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
 #define task_to_waiter(p)	\
-	&(struct rt_mutex_waiter){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
+	&(struct rt_mutex_waiter){ .tree = *task_to_waiter_node(p) }
 
-static __always_inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left,
-						struct rt_mutex_waiter *right)
+static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left,
+					       struct rt_waiter_node *right)
 {
 	if (left->prio < right->prio)
 		return 1;
@@ -364,8 +386,8 @@ static __always_inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 	return 0;
 }
 
-static __always_inline int rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
-						 struct rt_mutex_waiter *right)
+static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left,
+						 struct rt_waiter_node *right)
 {
 	if (left->prio != right->prio)
 		return 0;
@@ -385,7 +407,7 @@ static __always_inline int rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
 static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
 				  struct rt_mutex_waiter *top_waiter)
 {
-	if (rt_mutex_waiter_less(waiter, top_waiter))
+	if (rt_waiter_node_less(&waiter->tree, &top_waiter->tree))
 		return true;
 
 #ifdef RT_MUTEX_BUILD_SPINLOCKS
@@ -393,30 +415,30 @@ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
 	 * Note that RT tasks are excluded from same priority (lateral)
 	 * steals to prevent the introduction of an unbounded latency.
 	 */
-	if (rt_prio(waiter->prio) || dl_prio(waiter->prio))
+	if (rt_prio(waiter->tree.prio) || dl_prio(waiter->tree.prio))
 		return false;
 
-	return rt_mutex_waiter_equal(waiter, top_waiter);
+	return rt_waiter_node_equal(&waiter->tree, &top_waiter->tree);
 #else
 	return false;
 #endif
 }
 
 #define __node_2_waiter(node) \
-	rb_entry((node), struct rt_mutex_waiter, tree_entry)
+	rb_entry((node), struct rt_mutex_waiter, tree.entry)
 
 static __always_inline bool __waiter_less(struct rb_node *a, const struct rb_node *b)
 {
 	struct rt_mutex_waiter *aw = __node_2_waiter(a);
 	struct rt_mutex_waiter *bw = __node_2_waiter(b);
 
-	if (rt_mutex_waiter_less(aw, bw))
+	if (rt_waiter_node_less(&aw->tree, &bw->tree))
 		return 1;
 
 	if (!build_ww_mutex())
 		return 0;
 
-	if (rt_mutex_waiter_less(bw, aw))
+	if (rt_waiter_node_less(&bw->tree, &aw->tree))
 		return 0;
 
 	/* NOTE: relies on waiter->ww_ctx being set before insertion */
@@ -434,48 +456,58 @@ static __always_inline bool __waiter_less(struct rb_node *a, const struct rb_nod
 static __always_inline void
 rt_mutex_enqueue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter)
 {
-	rb_add_cached(&waiter->tree_entry, &lock->waiters, __waiter_less);
+	lockdep_assert_held(&lock->wait_lock);
+
+	rb_add_cached(&waiter->tree.entry, &lock->waiters, __waiter_less);
 }
 
 static __always_inline void
 rt_mutex_dequeue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter)
 {
-	if (RB_EMPTY_NODE(&waiter->tree_entry))
+	lockdep_assert_held(&lock->wait_lock);
+
+	if (RB_EMPTY_NODE(&waiter->tree.entry))
 		return;
 
-	rb_erase_cached(&waiter->tree_entry, &lock->waiters);
-	RB_CLEAR_NODE(&waiter->tree_entry);
+	rb_erase_cached(&waiter->tree.entry, &lock->waiters);
+	RB_CLEAR_NODE(&waiter->tree.entry);
 }
 
-#define __node_2_pi_waiter(node) \
-	rb_entry((node), struct rt_mutex_waiter, pi_tree_entry)
+#define __node_2_rt_node(node) \
+	rb_entry((node), struct rt_waiter_node, entry)
 
-static __always_inline bool
-__pi_waiter_less(struct rb_node *a, const struct rb_node *b)
+static __always_inline bool __pi_waiter_less(struct rb_node *a, const struct rb_node *b)
 {
-	return rt_mutex_waiter_less(__node_2_pi_waiter(a), __node_2_pi_waiter(b));
+	return rt_waiter_node_less(__node_2_rt_node(a), __node_2_rt_node(b));
 }
 
 static __always_inline void
 rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
 {
-	rb_add_cached(&waiter->pi_tree_entry, &task->pi_waiters, __pi_waiter_less);
+	lockdep_assert_held(&task->pi_lock);
+
+	rb_add_cached(&waiter->pi_tree.entry, &task->pi_waiters, __pi_waiter_less);
 }
 
 static __always_inline void
 rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
 {
-	if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+	lockdep_assert_held(&task->pi_lock);
+
+	if (RB_EMPTY_NODE(&waiter->pi_tree.entry))
 		return;
 
-	rb_erase_cached(&waiter->pi_tree_entry, &task->pi_waiters);
-	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+	rb_erase_cached(&waiter->pi_tree.entry, &task->pi_waiters);
+	RB_CLEAR_NODE(&waiter->pi_tree.entry);
 }
 
-static __always_inline void rt_mutex_adjust_prio(struct task_struct *p)
+static __always_inline void rt_mutex_adjust_prio(struct rt_mutex_base *lock,
+						 struct task_struct *p)
 {
 	struct task_struct *pi_task = NULL;
 
+	lockdep_assert_held(&lock->wait_lock);
+	lockdep_assert(rt_mutex_owner(lock) == p);
 	lockdep_assert_held(&p->pi_lock);
 
 	if (task_has_pi_waiters(p))
@@ -571,9 +603,14 @@ static __always_inline struct rt_mutex_base *task_blocked_on_lock(struct task_st
  * Chain walk basics and protection scope
  *
  * [R] refcount on task
- * [P] task->pi_lock held
+ * [Pn] task->pi_lock held
  * [L] rtmutex->wait_lock held
  *
+ * Normal locking order:
+ *
+ *   rtmutex->wait_lock
+ *     task->pi_lock
+ *
  * Step	Description				Protected by
  *	function arguments:
  *	@task					[R]
@@ -588,27 +625,32 @@ static __always_inline struct rt_mutex_base *task_blocked_on_lock(struct task_st
  *	again:
  *	  loop_sanity_check();
  *	retry:
- * [1]	  lock(task->pi_lock);			[R] acquire [P]
- * [2]	  waiter = task->pi_blocked_on;		[P]
- * [3]	  check_exit_conditions_1();		[P]
- * [4]	  lock = waiter->lock;			[P]
- * [5]	  if (!try_lock(lock->wait_lock)) {	[P] try to acquire [L]
- *	    unlock(task->pi_lock);		release [P]
+ * [1]	  lock(task->pi_lock);			[R] acquire [P1]
+ * [2]	  waiter = task->pi_blocked_on;		[P1]
+ * [3]	  check_exit_conditions_1();		[P1]
+ * [4]	  lock = waiter->lock;			[P1]
+ * [5]	  if (!try_lock(lock->wait_lock)) {	[P1] try to acquire [L]
+ *	    unlock(task->pi_lock);		release [P1]
  *	    goto retry;
  *	  }
- * [6]	  check_exit_conditions_2();		[P] + [L]
- * [7]	  requeue_lock_waiter(lock, waiter);	[P] + [L]
- * [8]	  unlock(task->pi_lock);		release [P]
+ * [6]	  check_exit_conditions_2();		[P1] + [L]
+ * [7]	  requeue_lock_waiter(lock, waiter);	[P1] + [L]
+ * [8]	  unlock(task->pi_lock);		release [P1]
  *	  put_task_struct(task);		release [R]
  * [9]	  check_exit_conditions_3();		[L]
  * [10]	  task = owner(lock);			[L]
  *	  get_task_struct(task);		[L] acquire [R]
- *	  lock(task->pi_lock);			[L] acquire [P]
- * [11]	  requeue_pi_waiter(tsk, waiters(lock));[P] + [L]
- * [12]	  check_exit_conditions_4();		[P] + [L]
- * [13]	  unlock(task->pi_lock);		release [P]
+ *	  lock(task->pi_lock);			[L] acquire [P2]
+ * [11]	  requeue_pi_waiter(tsk, waiters(lock));[P2] + [L]
+ * [12]	  check_exit_conditions_4();		[P2] + [L]
+ * [13]	  unlock(task->pi_lock);		release [P2]
  *	  unlock(lock->wait_lock);		release [L]
  *	  goto again;
+ *
+ * Where P1 is the blocking task and P2 is the lock owner; going up one step
+ * the owner becomes the next blocked task etc..
+ *
+*
  */
 static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 					      enum rtmutex_chainwalk chwalk,
@@ -756,7 +798,7 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * enabled we continue, but stop the requeueing in the chain
 	 * walk.
 	 */
-	if (rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
+	if (rt_waiter_node_equal(&waiter->tree, task_to_waiter_node(task))) {
 		if (!detect_deadlock)
 			goto out_unlock_pi;
 		else
@@ -764,13 +806,18 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 	}
 
 	/*
-	 * [4] Get the next lock
+	 * [4] Get the next lock; per holding task->pi_lock we can't unblock
+	 * and guarantee @lock's existence.
 	 */
 	lock = waiter->lock;
 	/*
 	 * [5] We need to trylock here as we are holding task->pi_lock,
 	 * which is the reverse lock order versus the other rtmutex
 	 * operations.
+	 *
+	 * Per the above, holding task->pi_lock guarantees lock exists, so
+	 * inverting this lock order is infeasible from a life-time
+	 * perspective.
 	 */
 	if (!raw_spin_trylock(&lock->wait_lock)) {
 		raw_spin_unlock_irq(&task->pi_lock);
@@ -874,17 +921,18 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * or
 	 *
 	 *   DL CBS enforcement advancing the effective deadline.
-	 *
-	 * Even though pi_waiters also uses these fields, and that tree is only
-	 * updated in [11], we can do this here, since we hold [L], which
-	 * serializes all pi_waiters access and rb_erase() does not care about
-	 * the values of the node being removed.
 	 */
 	waiter_update_prio(waiter, task);
 
 	rt_mutex_enqueue(lock, waiter);
 
-	/* [8] Release the task */
+	/*
+	 * [8] Release the (blocking) task in preparation for
+	 * taking the owner task in [10].
+	 *
+	 * Since we hold lock->waiter_lock, task cannot unblock, even if we
+	 * release task->pi_lock.
+	 */
 	raw_spin_unlock(&task->pi_lock);
 	put_task_struct(task);
 
@@ -908,7 +956,12 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 		return 0;
 	}
 
-	/* [10] Grab the next task, i.e. the owner of @lock */
+	/*
+	 * [10] Grab the next task, i.e. the owner of @lock
+	 *
+	 * Per holding lock->wait_lock and checking for !owner above, there
+	 * must be an owner and it cannot go away.
+	 */
 	task = get_task_struct(rt_mutex_owner(lock));
 	raw_spin_lock(&task->pi_lock);
 
@@ -921,8 +974,9 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 * and adjust the priority of the owner.
 		 */
 		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
+		waiter_clone_prio(waiter, task);
 		rt_mutex_enqueue_pi(task, waiter);
-		rt_mutex_adjust_prio(task);
+		rt_mutex_adjust_prio(lock, task);
 
 	} else if (prerequeue_top_waiter == waiter) {
 		/*
@@ -937,8 +991,9 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 */
 		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
+		waiter_clone_prio(waiter, task);
 		rt_mutex_enqueue_pi(task, waiter);
-		rt_mutex_adjust_prio(task);
+		rt_mutex_adjust_prio(lock, task);
 	} else {
 		/*
 		 * Nothing changed. No need to do any priority
@@ -1154,6 +1209,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 	waiter->task = task;
 	waiter->lock = lock;
 	waiter_update_prio(waiter, task);
+	waiter_clone_prio(waiter, task);
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
@@ -1187,7 +1243,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 		rt_mutex_dequeue_pi(owner, top_waiter);
 		rt_mutex_enqueue_pi(owner, waiter);
 
-		rt_mutex_adjust_prio(owner);
+		rt_mutex_adjust_prio(lock, owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
 	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
@@ -1234,6 +1290,8 @@ static void __sched mark_wakeup_next_waiter(struct rt_wake_q_head *wqh,
 {
 	struct rt_mutex_waiter *waiter;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	raw_spin_lock(&current->pi_lock);
 
 	waiter = rt_mutex_top_waiter(lock);
@@ -1246,7 +1304,7 @@ static void __sched mark_wakeup_next_waiter(struct rt_wake_q_head *wqh,
 	 * task unblocks.
 	 */
 	rt_mutex_dequeue_pi(current, waiter);
-	rt_mutex_adjust_prio(current);
+	rt_mutex_adjust_prio(lock, current);
 
 	/*
 	 * As we are waking up the top waiter, and the waiter stays
@@ -1482,7 +1540,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
 	if (rt_mutex_has_waiters(lock))
 		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
 
-	rt_mutex_adjust_prio(owner);
+	rt_mutex_adjust_prio(lock, owner);
 
 	/* Store the lock on which owner is blocked or NULL */
 	next_lock = task_blocked_on_lock(owner);
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index cb9fdff76a8a..a6974d044593 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -459,7 +459,7 @@ void __sched rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
+	if (!waiter || rt_waiter_node_equal(&waiter->tree, task_to_waiter_node(task))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index c47e8361bfb5..1162e07cdaea 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -17,27 +17,44 @@
 #include <linux/rtmutex.h>
 #include <linux/sched/wake_q.h>
 
+
+/*
+ * This is a helper for the struct rt_mutex_waiter below. A waiter goes in two
+ * separate trees and they need their own copy of the sort keys because of
+ * different locking requirements.
+ *
+ * @entry:		rbtree node to enqueue into the waiters tree
+ * @prio:		Priority of the waiter
+ * @deadline:		Deadline of the waiter if applicable
+ *
+ * See rt_waiter_node_less() and waiter_*_prio().
+ */
+struct rt_waiter_node {
+	struct rb_node	entry;
+	int		prio;
+	u64		deadline;
+};
+
 /*
  * This is the control structure for tasks blocked on a rt_mutex,
  * which is allocated on the kernel stack on of the blocked task.
  *
- * @tree_entry:		pi node to enqueue into the mutex waiters tree
- * @pi_tree_entry:	pi node to enqueue into the mutex owner waiters tree
+ * @tree:		node to enqueue into the mutex waiters tree
+ * @pi_tree:		node to enqueue into the mutex owner waiters tree
  * @task:		task reference to the blocked task
  * @lock:		Pointer to the rt_mutex on which the waiter blocks
  * @wake_state:		Wakeup state to use (TASK_NORMAL or TASK_RTLOCK_WAIT)
- * @prio:		Priority of the waiter
- * @deadline:		Deadline of the waiter if applicable
  * @ww_ctx:		WW context pointer
+ *
+ * @tree is ordered by @lock->wait_lock
+ * @pi_tree is ordered by rt_mutex_owner(@lock)->pi_lock
  */
 struct rt_mutex_waiter {
-	struct rb_node		tree_entry;
-	struct rb_node		pi_tree_entry;
+	struct rt_waiter_node	tree;
+	struct rt_waiter_node	pi_tree;
 	struct task_struct	*task;
 	struct rt_mutex_base	*lock;
 	unsigned int		wake_state;
-	int			prio;
-	u64			deadline;
 	struct ww_acquire_ctx	*ww_ctx;
 };
 
@@ -105,7 +122,7 @@ static inline bool rt_mutex_waiter_is_top_waiter(struct rt_mutex_base *lock,
 {
 	struct rb_node *leftmost = rb_first_cached(&lock->waiters);
 
-	return rb_entry(leftmost, struct rt_mutex_waiter, tree_entry) == waiter;
+	return rb_entry(leftmost, struct rt_mutex_waiter, tree.entry) == waiter;
 }
 
 static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex_base *lock)
@@ -113,8 +130,10 @@ static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex_base *
 	struct rb_node *leftmost = rb_first_cached(&lock->waiters);
 	struct rt_mutex_waiter *w = NULL;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	if (leftmost) {
-		w = rb_entry(leftmost, struct rt_mutex_waiter, tree_entry);
+		w = rb_entry(leftmost, struct rt_mutex_waiter, tree.entry);
 		BUG_ON(w->lock != lock);
 	}
 	return w;
@@ -127,8 +146,10 @@ static inline int task_has_pi_waiters(struct task_struct *p)
 
 static inline struct rt_mutex_waiter *task_top_pi_waiter(struct task_struct *p)
 {
+	lockdep_assert_held(&p->pi_lock);
+
 	return rb_entry(p->pi_waiters.rb_leftmost, struct rt_mutex_waiter,
-			pi_tree_entry);
+			pi_tree.entry);
 }
 
 #define RT_MUTEX_HAS_WAITERS	1UL
@@ -190,8 +211,8 @@ static inline void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 {
 	debug_rt_mutex_init_waiter(waiter);
-	RB_CLEAR_NODE(&waiter->pi_tree_entry);
-	RB_CLEAR_NODE(&waiter->tree_entry);
+	RB_CLEAR_NODE(&waiter->pi_tree.entry);
+	RB_CLEAR_NODE(&waiter->tree.entry);
 	waiter->wake_state = TASK_NORMAL;
 	waiter->task = NULL;
 }
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 56f139201f24..3ad2cc4823e5 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -96,25 +96,25 @@ __ww_waiter_first(struct rt_mutex *lock)
 	struct rb_node *n = rb_first(&lock->rtmutex.waiters.rb_root);
 	if (!n)
 		return NULL;
-	return rb_entry(n, struct rt_mutex_waiter, tree_entry);
+	return rb_entry(n, struct rt_mutex_waiter, tree.entry);
 }
 
 static inline struct rt_mutex_waiter *
 __ww_waiter_next(struct rt_mutex *lock, struct rt_mutex_waiter *w)
 {
-	struct rb_node *n = rb_next(&w->tree_entry);
+	struct rb_node *n = rb_next(&w->tree.entry);
 	if (!n)
 		return NULL;
-	return rb_entry(n, struct rt_mutex_waiter, tree_entry);
+	return rb_entry(n, struct rt_mutex_waiter, tree.entry);
 }
 
 static inline struct rt_mutex_waiter *
 __ww_waiter_prev(struct rt_mutex *lock, struct rt_mutex_waiter *w)
 {
-	struct rb_node *n = rb_prev(&w->tree_entry);
+	struct rb_node *n = rb_prev(&w->tree.entry);
 	if (!n)
 		return NULL;
-	return rb_entry(n, struct rt_mutex_waiter, tree_entry);
+	return rb_entry(n, struct rt_mutex_waiter, tree.entry);
 }
 
 static inline struct rt_mutex_waiter *
@@ -123,7 +123,7 @@ __ww_waiter_last(struct rt_mutex *lock)
 	struct rb_node *n = rb_last(&lock->rtmutex.waiters.rb_root);
 	if (!n)
 		return NULL;
-	return rb_entry(n, struct rt_mutex_waiter, tree_entry);
+	return rb_entry(n, struct rt_mutex_waiter, tree.entry);
 }
 
 static inline void
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c92eb8c6ff08..79719979a635 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -661,8 +661,7 @@ static DEFINE_PER_CPU(int, bpf_trace_nest_level);
 BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
-	struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds);
-	int nest_level = this_cpu_inc_return(bpf_trace_nest_level);
+	struct bpf_trace_sample_data *sds;
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = size,
@@ -670,7 +669,11 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 		},
 	};
 	struct perf_sample_data *sd;
-	int err;
+	int nest_level, err;
+
+	preempt_disable();
+	sds = this_cpu_ptr(&bpf_trace_sds);
+	nest_level = this_cpu_inc_return(bpf_trace_nest_level);
 
 	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) {
 		err = -EBUSY;
@@ -688,9 +691,9 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	perf_sample_save_raw_data(sd, &raw);
 
 	err = __bpf_perf_event_output(regs, map, flags, sd);
-
 out:
 	this_cpu_dec(bpf_trace_nest_level);
+	preempt_enable();
 	return err;
 }
 
@@ -715,7 +718,6 @@ static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds);
 u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
 {
-	int nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
 	struct perf_raw_frag frag = {
 		.copy		= ctx_copy,
 		.size		= ctx_size,
@@ -732,8 +734,12 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 	};
 	struct perf_sample_data *sd;
 	struct pt_regs *regs;
+	int nest_level;
 	u64 ret;
 
+	preempt_disable();
+	nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
+
 	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) {
 		ret = -EBUSY;
 		goto out;
@@ -748,6 +754,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 	ret = __bpf_perf_event_output(regs, map, flags, sd);
 out:
 	this_cpu_dec(bpf_event_output_nest_level);
+	preempt_enable();
 	return ret;
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index de061dd47313..52dea5dd5362 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -523,6 +523,8 @@ struct ring_buffer_per_cpu {
 	rb_time_t			before_stamp;
 	u64				event_stamp[MAX_NEST];
 	u64				read_stamp;
+	/* pages removed since last reset */
+	unsigned long			pages_removed;
 	/* ring buffer pages to update, > 0 to add, < 0 to remove */
 	long				nr_pages_to_update;
 	struct list_head		new_pages; /* new pages to add */
@@ -559,6 +561,7 @@ struct ring_buffer_iter {
 	struct buffer_page		*head_page;
 	struct buffer_page		*cache_reader_page;
 	unsigned long			cache_read;
+	unsigned long			cache_pages_removed;
 	u64				read_stamp;
 	u64				page_stamp;
 	struct ring_buffer_event	*event;
@@ -947,6 +950,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
 /**
  * ring_buffer_wake_waiters - wake up any waiters on this ring buffer
  * @buffer: The ring buffer to wake waiters on
+ * @cpu: The CPU buffer to wake waiters on
  *
  * In the case of a file that represents a ring buffer is closing,
  * it is prudent to wake up any waiters that are on this.
@@ -1957,6 +1961,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 		to_remove = rb_list_head(to_remove)->next;
 		head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD;
 	}
+	/* Read iterators need to reset themselves when some pages removed */
+	cpu_buffer->pages_removed += nr_removed;
 
 	next_page = rb_list_head(to_remove)->next;
 
@@ -1978,12 +1984,6 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 		cpu_buffer->head_page = list_entry(next_page,
 						struct buffer_page, list);
 
-	/*
-	 * change read pointer to make sure any read iterators reset
-	 * themselves
-	 */
-	cpu_buffer->read = 0;
-
 	/* pages are removed, resume tracing and then free the pages */
 	atomic_dec(&cpu_buffer->record_disabled);
 	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
@@ -3376,7 +3376,6 @@ void ring_buffer_nest_end(struct trace_buffer *buffer)
 /**
  * ring_buffer_unlock_commit - commit a reserved
  * @buffer: The buffer to commit to
- * @event: The event pointer to commit.
  *
  * This commits the data to the ring buffer, and releases any locks held.
  *
@@ -4395,6 +4394,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 
 	iter->cache_reader_page = iter->head_page;
 	iter->cache_read = cpu_buffer->read;
+	iter->cache_pages_removed = cpu_buffer->pages_removed;
 
 	if (iter->head) {
 		iter->read_stamp = cpu_buffer->read_stamp;
@@ -4849,12 +4849,13 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	buffer = cpu_buffer->buffer;
 
 	/*
-	 * Check if someone performed a consuming read to
-	 * the buffer. A consuming read invalidates the iterator
-	 * and we need to reset the iterator in this case.
+	 * Check if someone performed a consuming read to the buffer
+	 * or removed some pages from the buffer. In these cases,
+	 * iterator was invalidated and we need to reset it.
 	 */
 	if (unlikely(iter->cache_read != cpu_buffer->read ||
-		     iter->cache_reader_page != cpu_buffer->reader_page))
+		     iter->cache_reader_page != cpu_buffer->reader_page ||
+		     iter->cache_pages_removed != cpu_buffer->pages_removed))
 		rb_iter_reset(iter);
 
  again:
@@ -5298,6 +5299,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->last_overrun = 0;
 
 	rb_head_page_activate(cpu_buffer);
+	cpu_buffer->pages_removed = 0;
 }
 
 /* Must have disabled the cpu buffer then done a synchronize_rcu */
@@ -5356,7 +5358,6 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 /**
  * ring_buffer_reset_online_cpus - reset a ring buffer per CPU buffer
  * @buffer: The ring buffer to reset a per cpu buffer of
- * @cpu: The CPU buffer to be reset
  */
 void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
 {
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5d6ae4eae510..578f1f7d49a6 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -611,7 +611,6 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 {
 	struct trace_event_call *call = file->event_call;
 	struct trace_array *tr = file->tr;
-	unsigned long file_flags = file->flags;
 	int ret = 0;
 	int disable;
 
@@ -635,6 +634,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 				break;
 			disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED;
 			clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+			/* Disable use of trace_buffered_event */
+			trace_buffered_event_disable();
 		} else
 			disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE);
 
@@ -673,6 +674,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 			if (atomic_inc_return(&file->sm_ref) > 1)
 				break;
 			set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+			/* Enable use of trace_buffered_event */
+			trace_buffered_event_enable();
 		}
 
 		if (!(file->flags & EVENT_FILE_FL_ENABLED)) {
@@ -712,15 +715,6 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		break;
 	}
 
-	/* Enable or disable use of trace_buffered_event */
-	if ((file_flags & EVENT_FILE_FL_SOFT_DISABLED) !=
-	    (file->flags & EVENT_FILE_FL_SOFT_DISABLED)) {
-		if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
-			trace_buffered_event_enable();
-		else
-			trace_buffered_event_disable();
-	}
-
 	return ret;
 }
 
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index d6a70aff2410..dd398afc8e25 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1230,6 +1230,7 @@ EXPORT_SYMBOL_GPL(__synth_event_gen_cmd_start);
  * synth_event_gen_cmd_array_start - Start synthetic event command from an array
  * @cmd: A pointer to the dynevent_cmd struct representing the new event
  * @name: The name of the synthetic event
+ * @mod: The module creating the event, NULL if not created from a module
  * @fields: An array of type/name field descriptions
  * @n_fields: The number of field descriptions contained in the fields array
  *
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index e535959939d3..46439e3bcec4 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -31,7 +31,9 @@ void trigger_data_free(struct event_trigger_data *data)
 /**
  * event_triggers_call - Call triggers associated with a trace event
  * @file: The trace_event_file associated with the event
+ * @buffer: The ring buffer that the event is being written to
  * @rec: The trace entry for the event, NULL for unconditional invocation
+ * @event: The event meta data in the ring buffer
  *
  * For each trigger associated with an event, invoke the trigger
  * function registered with the associated trigger command.  If rec is
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index b2b726bea1f9..c68a72707852 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -386,12 +386,12 @@ static const struct btf_type *find_btf_func_proto(const char *funcname)
 
 	/* Get BTF_KIND_FUNC type */
 	t = btf_type_by_id(btf, id);
-	if (!btf_type_is_func(t))
+	if (!t || !btf_type_is_func(t))
 		return ERR_PTR(-ENOENT);
 
 	/* The type of BTF_KIND_FUNC is BTF_KIND_FUNC_PROTO */
 	t = btf_type_by_id(btf, t->type);
-	if (!btf_type_is_func_proto(t))
+	if (!t || !btf_type_is_func_proto(t))
 		return ERR_PTR(-ENOENT);
 
 	return t;
@@ -443,7 +443,7 @@ static int parse_btf_arg(const char *varname, struct fetch_insn *code,
 	if (!ctx->params) {
 		params = find_btf_func_param(ctx->funcname, &ctx->nr_params,
 					     ctx->flags & TPARG_FL_TPOINT);
-		if (IS_ERR(params)) {
+		if (IS_ERR_OR_NULL(params)) {
 			trace_probe_log_err(ctx->offset, NO_BTF_ENTRY);
 			return PTR_ERR(params);
 		}
@@ -1273,7 +1273,7 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[],
 
 	params = find_btf_func_param(ctx->funcname, &nr_params,
 				     ctx->flags & TPARG_FL_TPOINT);
-	if (IS_ERR(params)) {
+	if (IS_ERR_OR_NULL(params)) {
 		if (args_idx != -1) {
 			/* $arg* requires BTF info */
 			trace_probe_log_err(0, NOSUP_BTFARG);
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index e5e299260d0c..bac06ee3b98b 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -131,6 +131,7 @@ EXPORT_SYMBOL_GPL(trace_seq_bitmask);
  * trace_seq_vprintf - sequence printing of trace information
  * @s: trace sequence descriptor
  * @fmt: printf format string
+ * @args: Arguments for the format string
  *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formatting of a trace