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

include/linux/net.h
  a5ef058dc4d9 ("net: introduce and use custom sockopt socket flag")
  e993ffe3da4b ("net: flag sockets supporting msghdr originated zerocopy")

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

15 files changed, 241 insertions, 119 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index eba603cec2c5..35c07afac924 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4436,6 +4436,11 @@ static int btf_func_proto_check(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
+		if (btf_type_is_resolve_source_only(ret_type)) {
+			btf_verifier_log_type(env, t, "Invalid return type");
+			return -EINVAL;
+		}
+
 		if (btf_type_needs_resolve(ret_type) &&
 		    !env_type_is_resolved(env, ret_type_id)) {
 			err = btf_resolve(env, ret_type, ret_type_id);
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index fa64b80b8bca..04f0a045dcaa 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -4,6 +4,7 @@
 #include <linux/hash.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/init.h>
 
 /* The BPF dispatcher is a multiway branch code generator. The
  * dispatcher is a mechanism to avoid the performance penalty of an
@@ -90,6 +91,11 @@ int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int n
 	return -ENOTSUPP;
 }
 
+int __weak __init bpf_arch_init_dispatcher_early(void *ip)
+{
+	return -ENOTSUPP;
+}
+
 static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf)
 {
 	s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0];
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 2433be58bb85..8f0d65f2474a 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -423,14 +423,17 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	/* No progs are using this bpf_mem_cache, but htab_map_free() called
 	 * bpf_mem_cache_free() for all remaining elements and they can be in
 	 * free_by_rcu or in waiting_for_gp lists, so drain those lists now.
+	 *
+	 * Except for waiting_for_gp list, there are no concurrent operations
+	 * on these lists, so it is safe to use __llist_del_all().
 	 */
 	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
 		free_one(c, llnode);
 	llist_for_each_safe(llnode, t, llist_del_all(&c->waiting_for_gp))
 		free_one(c, llnode);
-	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist))
+	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_llist))
 		free_one(c, llnode);
-	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
+	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_llist_extra))
 		free_one(c, llnode);
 }
 
@@ -498,6 +501,16 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 		rcu_in_progress = 0;
 		for_each_possible_cpu(cpu) {
 			c = per_cpu_ptr(ma->cache, cpu);
+			/*
+			 * refill_work may be unfinished for PREEMPT_RT kernel
+			 * in which irq work is invoked in a per-CPU RT thread.
+			 * It is also possible for kernel with
+			 * arch_irq_work_has_interrupt() being false and irq
+			 * work is invoked in timer interrupt. So waiting for
+			 * the completion of irq work to ease the handling of
+			 * concurrency.
+			 */
+			irq_work_sync(&c->refill_work);
 			drain_mem_cache(c);
 			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 		}
@@ -512,6 +525,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			cc = per_cpu_ptr(ma->caches, cpu);
 			for (i = 0; i < NUM_CACHES; i++) {
 				c = &cc->cache[i];
+				irq_work_sync(&c->refill_work);
 				drain_mem_cache(c);
 				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 			}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 014ee0953dbd..7f0a9f6cb889 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6946,6 +6946,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 
 	callee->in_callback_fn = true;
+	callee->callback_ret_range = tnum_range(0, 1);
 	return 0;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index aefc1e08e015..01933db7629c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -54,6 +54,7 @@
 #include <linux/highmem.h>
 #include <linux/pgtable.h>
 #include <linux/buildid.h>
+#include <linux/task_work.h>
 
 #include "internal.h"
 
@@ -2276,11 +2277,26 @@ event_sched_out(struct perf_event *event,
 	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
-	if (READ_ONCE(event->pending_disable) >= 0) {
-		WRITE_ONCE(event->pending_disable, -1);
+	if (event->pending_disable) {
+		event->pending_disable = 0;
 		perf_cgroup_event_disable(event, ctx);
 		state = PERF_EVENT_STATE_OFF;
 	}
+
+	if (event->pending_sigtrap) {
+		bool dec = true;
+
+		event->pending_sigtrap = 0;
+		if (state != PERF_EVENT_STATE_OFF &&
+		    !event->pending_work) {
+			event->pending_work = 1;
+			dec = false;
+			task_work_add(current, &event->pending_task, TWA_RESUME);
+		}
+		if (dec)
+			local_dec(&event->ctx->nr_pending);
+	}
+
 	perf_event_set_state(event, state);
 
 	if (!is_software_event(event))
@@ -2432,7 +2448,7 @@ static void __perf_event_disable(struct perf_event *event,
  * hold the top-level event's child_mutex, so any descendant that
  * goes to exit will block in perf_event_exit_event().
  *
- * When called from perf_pending_event it's OK because event->ctx
+ * When called from perf_pending_irq it's OK because event->ctx
  * is the current context on this CPU and preemption is disabled,
  * hence we can't get into perf_event_task_sched_out for this context.
  */
@@ -2471,9 +2487,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable);
 
 void perf_event_disable_inatomic(struct perf_event *event)
 {
-	WRITE_ONCE(event->pending_disable, smp_processor_id());
-	/* can fail, see perf_pending_event_disable() */
-	irq_work_queue(&event->pending);
+	event->pending_disable = 1;
+	irq_work_queue(&event->pending_irq);
 }
 
 #define MAX_INTERRUPTS (~0ULL)
@@ -3428,11 +3443,23 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 		raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
 		if (context_equiv(ctx, next_ctx)) {
 
+			perf_pmu_disable(pmu);
+
+			/* PMIs are disabled; ctx->nr_pending is stable. */
+			if (local_read(&ctx->nr_pending) ||
+			    local_read(&next_ctx->nr_pending)) {
+				/*
+				 * Must not swap out ctx when there's pending
+				 * events that rely on the ctx->task relation.
+				 */
+				raw_spin_unlock(&next_ctx->lock);
+				rcu_read_unlock();
+				goto inside_switch;
+			}
+
 			WRITE_ONCE(ctx->task, next);
 			WRITE_ONCE(next_ctx->task, task);
 
-			perf_pmu_disable(pmu);
-
 			if (cpuctx->sched_cb_usage && pmu->sched_task)
 				pmu->sched_task(ctx, false);
 
@@ -3473,6 +3500,7 @@ unlock:
 		raw_spin_lock(&ctx->lock);
 		perf_pmu_disable(pmu);
 
+inside_switch:
 		if (cpuctx->sched_cb_usage && pmu->sched_task)
 			pmu->sched_task(ctx, false);
 		task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
@@ -4939,7 +4967,7 @@ static void perf_addr_filters_splice(struct perf_event *event,
 
 static void _free_event(struct perf_event *event)
 {
-	irq_work_sync(&event->pending);
+	irq_work_sync(&event->pending_irq);
 
 	unaccount_event(event);
 
@@ -6439,7 +6467,8 @@ static void perf_sigtrap(struct perf_event *event)
 		return;
 
 	/*
-	 * perf_pending_event() can race with the task exiting.
+	 * Both perf_pending_task() and perf_pending_irq() can race with the
+	 * task exiting.
 	 */
 	if (current->flags & PF_EXITING)
 		return;
@@ -6448,23 +6477,33 @@ static void perf_sigtrap(struct perf_event *event)
 		      event->attr.type, event->attr.sig_data);
 }
 
-static void perf_pending_event_disable(struct perf_event *event)
+/*
+ * Deliver the pending work in-event-context or follow the context.
+ */
+static void __perf_pending_irq(struct perf_event *event)
 {
-	int cpu = READ_ONCE(event->pending_disable);
+	int cpu = READ_ONCE(event->oncpu);
 
+	/*
+	 * If the event isn't running; we done. event_sched_out() will have
+	 * taken care of things.
+	 */
 	if (cpu < 0)
 		return;
 
+	/*
+	 * Yay, we hit home and are in the context of the event.
+	 */
 	if (cpu == smp_processor_id()) {
-		WRITE_ONCE(event->pending_disable, -1);
-
-		if (event->attr.sigtrap) {
+		if (event->pending_sigtrap) {
+			event->pending_sigtrap = 0;
 			perf_sigtrap(event);
-			atomic_set_release(&event->event_limit, 1); /* rearm event */
-			return;
+			local_dec(&event->ctx->nr_pending);
+		}
+		if (event->pending_disable) {
+			event->pending_disable = 0;
+			perf_event_disable_local(event);
 		}
-
-		perf_event_disable_local(event);
 		return;
 	}
 
@@ -6484,35 +6523,62 @@ static void perf_pending_event_disable(struct perf_event *event)
 	 *				  irq_work_queue(); // FAILS
 	 *
 	 *  irq_work_run()
-	 *    perf_pending_event()
+	 *    perf_pending_irq()
 	 *
 	 * But the event runs on CPU-B and wants disabling there.
 	 */
-	irq_work_queue_on(&event->pending, cpu);
+	irq_work_queue_on(&event->pending_irq, cpu);
 }
 
-static void perf_pending_event(struct irq_work *entry)
+static void perf_pending_irq(struct irq_work *entry)
 {
-	struct perf_event *event = container_of(entry, struct perf_event, pending);
+	struct perf_event *event = container_of(entry, struct perf_event, pending_irq);
 	int rctx;
 
-	rctx = perf_swevent_get_recursion_context();
 	/*
 	 * If we 'fail' here, that's OK, it means recursion is already disabled
 	 * and we won't recurse 'further'.
 	 */
+	rctx = perf_swevent_get_recursion_context();
 
-	perf_pending_event_disable(event);
-
+	/*
+	 * The wakeup isn't bound to the context of the event -- it can happen
+	 * irrespective of where the event is.
+	 */
 	if (event->pending_wakeup) {
 		event->pending_wakeup = 0;
 		perf_event_wakeup(event);
 	}
 
+	__perf_pending_irq(event);
+
 	if (rctx >= 0)
 		perf_swevent_put_recursion_context(rctx);
 }
 
+static void perf_pending_task(struct callback_head *head)
+{
+	struct perf_event *event = container_of(head, struct perf_event, pending_task);
+	int rctx;
+
+	/*
+	 * If we 'fail' here, that's OK, it means recursion is already disabled
+	 * and we won't recurse 'further'.
+	 */
+	preempt_disable_notrace();
+	rctx = perf_swevent_get_recursion_context();
+
+	if (event->pending_work) {
+		event->pending_work = 0;
+		perf_sigtrap(event);
+		local_dec(&event->ctx->nr_pending);
+	}
+
+	if (rctx >= 0)
+		perf_swevent_put_recursion_context(rctx);
+	preempt_enable_notrace();
+}
+
 #ifdef CONFIG_GUEST_PERF_EVENTS
 struct perf_guest_info_callbacks __rcu *perf_guest_cbs;
 
@@ -9212,8 +9278,8 @@ int perf_event_account_interrupt(struct perf_event *event)
  */
 
 static int __perf_event_overflow(struct perf_event *event,
-				   int throttle, struct perf_sample_data *data,
-				   struct pt_regs *regs)
+				 int throttle, struct perf_sample_data *data,
+				 struct pt_regs *regs)
 {
 	int events = atomic_read(&event->event_limit);
 	int ret = 0;
@@ -9236,24 +9302,36 @@ static int __perf_event_overflow(struct perf_event *event,
 	if (events && atomic_dec_and_test(&event->event_limit)) {
 		ret = 1;
 		event->pending_kill = POLL_HUP;
-		event->pending_addr = data->addr;
-
 		perf_event_disable_inatomic(event);
 	}
 
+	if (event->attr.sigtrap) {
+		/*
+		 * Should not be able to return to user space without processing
+		 * pending_sigtrap (kernel events can overflow multiple times).
+		 */
+		WARN_ON_ONCE(event->pending_sigtrap && event->attr.exclude_kernel);
+		if (!event->pending_sigtrap) {
+			event->pending_sigtrap = 1;
+			local_inc(&event->ctx->nr_pending);
+		}
+		event->pending_addr = data->addr;
+		irq_work_queue(&event->pending_irq);
+	}
+
 	READ_ONCE(event->overflow_handler)(event, data, regs);
 
 	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
-		irq_work_queue(&event->pending);
+		irq_work_queue(&event->pending_irq);
 	}
 
 	return ret;
 }
 
 int perf_event_overflow(struct perf_event *event,
-			  struct perf_sample_data *data,
-			  struct pt_regs *regs)
+			struct perf_sample_data *data,
+			struct pt_regs *regs)
 {
 	return __perf_event_overflow(event, 1, data, regs);
 }
@@ -11570,8 +11648,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 
 	init_waitqueue_head(&event->waitq);
-	event->pending_disable = -1;
-	init_irq_work(&event->pending, perf_pending_event);
+	init_irq_work(&event->pending_irq, perf_pending_irq);
+	init_task_work(&event->pending_task, perf_pending_task);
 
 	mutex_init(&event->mmap_mutex);
 	raw_spin_lock_init(&event->addr_filters.lock);
@@ -11593,9 +11671,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (parent_event)
 		event->event_caps = parent_event->event_caps;
 
-	if (event->attr.sigtrap)
-		atomic_set(&event->event_limit, 1);
-
 	if (task) {
 		event->attach_state = PERF_ATTACH_TASK;
 		/*
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 726132039c38..273a0fe7910a 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -22,7 +22,7 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
 	atomic_set(&handle->rb->poll, EPOLLIN);
 
 	handle->event->pending_wakeup = 1;
-	irq_work_queue(&handle->event->pending);
+	irq_work_queue(&handle->event->pending_irq);
 }
 
 /*
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 460c12b7dfea..7971e989e425 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -30,6 +30,13 @@
 
 #define GCOV_TAG_FUNCTION_LENGTH	3
 
+/* Since GCC 12.1 sizes are in BYTES and not in WORDS (4B). */
+#if (__GNUC__ >= 12)
+#define GCOV_UNIT_SIZE				4
+#else
+#define GCOV_UNIT_SIZE				1
+#endif
+
 static struct gcov_info *gcov_info_head;
 
 /**
@@ -383,12 +390,18 @@ size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 	pos += store_gcov_u32(buffer, pos, info->version);
 	pos += store_gcov_u32(buffer, pos, info->stamp);
 
+#if (__GNUC__ >= 12)
+	/* Use zero as checksum of the compilation unit. */
+	pos += store_gcov_u32(buffer, pos, 0);
+#endif
+
 	for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
 		fi_ptr = info->functions[fi_idx];
 
 		/* Function record. */
 		pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION);
-		pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH);
+		pos += store_gcov_u32(buffer, pos,
+			GCOV_TAG_FUNCTION_LENGTH * GCOV_UNIT_SIZE);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->ident);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
@@ -402,7 +415,8 @@ size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 			/* Counter record. */
 			pos += store_gcov_u32(buffer, pos,
 					      GCOV_TAG_FOR_COUNTER(ct_idx));
-			pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2);
+			pos += store_gcov_u32(buffer, pos,
+				ci_ptr->num * 2 * GCOV_UNIT_SIZE);
 
 			for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) {
 				pos += store_gcov_u64(buffer, pos,
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6bb8e72bc815..93416afebd59 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1403,30 +1403,32 @@ static void rcu_poll_gp_seq_end(unsigned long *snap)
 // where caller does not hold the root rcu_node structure's lock.
 static void rcu_poll_gp_seq_start_unlocked(unsigned long *snap)
 {
+	unsigned long flags;
 	struct rcu_node *rnp = rcu_get_root();
 
 	if (rcu_init_invoked()) {
 		lockdep_assert_irqs_enabled();
-		raw_spin_lock_irq_rcu_node(rnp);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	}
 	rcu_poll_gp_seq_start(snap);
 	if (rcu_init_invoked())
-		raw_spin_unlock_irq_rcu_node(rnp);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
 // Make the polled API aware of the end of a grace period, but where
 // caller does not hold the root rcu_node structure's lock.
 static void rcu_poll_gp_seq_end_unlocked(unsigned long *snap)
 {
+	unsigned long flags;
 	struct rcu_node *rnp = rcu_get_root();
 
 	if (rcu_init_invoked()) {
 		lockdep_assert_irqs_enabled();
-		raw_spin_lock_irq_rcu_node(rnp);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	}
 	rcu_poll_gp_seq_end(snap);
 	if (rcu_init_invoked())
-		raw_spin_unlock_irq_rcu_node(rnp);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5800b0623ff3..cb2aa2b54c7a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4823,10 +4823,10 @@ static inline void finish_task(struct task_struct *prev)
 
 #ifdef CONFIG_SMP
 
-static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
+static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
 {
 	void (*func)(struct rq *rq);
-	struct callback_head *next;
+	struct balance_callback *next;
 
 	lockdep_assert_rq_held(rq);
 
@@ -4853,15 +4853,15 @@ static void balance_push(struct rq *rq);
  * This abuse is tolerated because it places all the unlikely/odd cases behind
  * a single test, namely: rq->balance_callback == NULL.
  */
-struct callback_head balance_push_callback = {
+struct balance_callback balance_push_callback = {
 	.next = NULL,
-	.func = (void (*)(struct callback_head *))balance_push,
+	.func = balance_push,
 };
 
-static inline struct callback_head *
+static inline struct balance_callback *
 __splice_balance_callbacks(struct rq *rq, bool split)
 {
-	struct callback_head *head = rq->balance_callback;
+	struct balance_callback *head = rq->balance_callback;
 
 	if (likely(!head))
 		return NULL;
@@ -4883,7 +4883,7 @@ __splice_balance_callbacks(struct rq *rq, bool split)
 	return head;
 }
 
-static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
 {
 	return __splice_balance_callbacks(rq, true);
 }
@@ -4893,7 +4893,7 @@ static void __balance_callbacks(struct rq *rq)
 	do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
 }
 
-static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
+static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
 {
 	unsigned long flags;
 
@@ -4910,12 +4910,12 @@ static inline void __balance_callbacks(struct rq *rq)
 {
 }
 
-static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
 {
 	return NULL;
 }
 
-static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
+static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
 {
 }
 
@@ -6188,7 +6188,7 @@ static void sched_core_balance(struct rq *rq)
 	preempt_enable();
 }
 
-static DEFINE_PER_CPU(struct callback_head, core_balance_head);
+static DEFINE_PER_CPU(struct balance_callback, core_balance_head);
 
 static void queue_core_balance(struct rq *rq)
 {
@@ -7419,7 +7419,7 @@ static 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;
-	struct callback_head *head;
+	struct balance_callback *head;
 	struct rq_flags rf;
 	int reset_on_fork;
 	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 86dea6a05267..9ae8f41e3372 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -644,8 +644,8 @@ static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
 	return rq->online && dl_task(prev);
 }
 
-static DEFINE_PER_CPU(struct callback_head, dl_push_head);
-static DEFINE_PER_CPU(struct callback_head, dl_pull_head);
+static DEFINE_PER_CPU(struct balance_callback, dl_push_head);
+static DEFINE_PER_CPU(struct balance_callback, dl_pull_head);
 
 static void push_dl_tasks(struct rq *);
 static void pull_dl_task(struct rq *);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d869bcf898cc..ed2a47e4ddae 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -410,8 +410,8 @@ static inline int has_pushable_tasks(struct rq *rq)
 	return !plist_head_empty(&rq->rt.pushable_tasks);
 }
 
-static DEFINE_PER_CPU(struct callback_head, rt_push_head);
-static DEFINE_PER_CPU(struct callback_head, rt_pull_head);
+static DEFINE_PER_CPU(struct balance_callback, rt_push_head);
+static DEFINE_PER_CPU(struct balance_callback, rt_pull_head);
 
 static void push_rt_tasks(struct rq *);
 static void pull_rt_task(struct rq *);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1644242ecd11..a4a20046e586 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -938,6 +938,12 @@ struct uclamp_rq {
 DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
 #endif /* CONFIG_UCLAMP_TASK */
 
+struct rq;
+struct balance_callback {
+	struct balance_callback *next;
+	void (*func)(struct rq *rq);
+};
+
 /*
  * This is the main, per-CPU runqueue data structure.
  *
@@ -1036,7 +1042,7 @@ struct rq {
 	unsigned long		cpu_capacity;
 	unsigned long		cpu_capacity_orig;
 
-	struct callback_head	*balance_callback;
+	struct balance_callback *balance_callback;
 
 	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;
@@ -1182,6 +1188,14 @@ static inline bool is_migration_disabled(struct task_struct *p)
 #endif
 }
 
+DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+
+#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
+#define this_rq()		this_cpu_ptr(&runqueues)
+#define task_rq(p)		cpu_rq(task_cpu(p))
+#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
+#define raw_rq()		raw_cpu_ptr(&runqueues)
+
 struct sched_group;
 #ifdef CONFIG_SCHED_CORE
 static inline struct cpumask *sched_group_span(struct sched_group *sg);
@@ -1269,7 +1283,7 @@ static inline bool sched_group_cookie_match(struct rq *rq,
 		return true;
 
 	for_each_cpu_and(cpu, sched_group_span(group), p->cpus_ptr) {
-		if (sched_core_cookie_match(rq, p))
+		if (sched_core_cookie_match(cpu_rq(cpu), p))
 			return true;
 	}
 	return false;
@@ -1384,14 +1398,6 @@ static inline void update_idle_core(struct rq *rq)
 static inline void update_idle_core(struct rq *rq) { }
 #endif
 
-DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-
-#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
-#define this_rq()		this_cpu_ptr(&runqueues)
-#define task_rq(p)		cpu_rq(task_cpu(p))
-#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
-#define raw_rq()		raw_cpu_ptr(&runqueues)
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static inline struct task_struct *task_of(struct sched_entity *se)
 {
@@ -1544,7 +1550,7 @@ struct rq_flags {
 #endif
 };
 
-extern struct callback_head balance_push_callback;
+extern struct balance_callback balance_push_callback;
 
 /*
  * Lockdep annotation that avoids accidental unlocks; it's like a
@@ -1724,7 +1730,7 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 
 static inline void
 queue_balance_callback(struct rq *rq,
-		       struct callback_head *head,
+		       struct balance_callback *head,
 		       void (*func)(struct rq *rq))
 {
 	lockdep_assert_rq_held(rq);
@@ -1737,7 +1743,7 @@ queue_balance_callback(struct rq *rq,
 	if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
 		return;
 
-	head->func = (void (*)(struct callback_head *))func;
+	head->func = func;
 	head->next = rq->balance_callback;
 	rq->balance_callback = head;
 }
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7f5eb295fe19..a995ea1ef849 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -346,8 +346,40 @@ static void put_probe_ref(void)
 	mutex_unlock(&blk_probe_mutex);
 }
 
+static int blk_trace_start(struct blk_trace *bt)
+{
+	if (bt->trace_state != Blktrace_setup &&
+	    bt->trace_state != Blktrace_stopped)
+		return -EINVAL;
+
+	blktrace_seq++;
+	smp_mb();
+	bt->trace_state = Blktrace_running;
+	raw_spin_lock_irq(&running_trace_lock);
+	list_add(&bt->running_list, &running_trace_list);
+	raw_spin_unlock_irq(&running_trace_lock);
+	trace_note_time(bt);
+
+	return 0;
+}
+
+static int blk_trace_stop(struct blk_trace *bt)
+{
+	if (bt->trace_state != Blktrace_running)
+		return -EINVAL;
+
+	bt->trace_state = Blktrace_stopped;
+	raw_spin_lock_irq(&running_trace_lock);
+	list_del_init(&bt->running_list);
+	raw_spin_unlock_irq(&running_trace_lock);
+	relay_flush(bt->rchan);
+
+	return 0;
+}
+
 static void blk_trace_cleanup(struct request_queue *q, struct blk_trace *bt)
 {
+	blk_trace_stop(bt);
 	synchronize_rcu();
 	blk_trace_free(q, bt);
 	put_probe_ref();
@@ -362,8 +394,7 @@ static int __blk_trace_remove(struct request_queue *q)
 	if (!bt)
 		return -EINVAL;
 
-	if (bt->trace_state != Blktrace_running)
-		blk_trace_cleanup(q, bt);
+	blk_trace_cleanup(q, bt);
 
 	return 0;
 }
@@ -658,7 +689,6 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 
 static int __blk_trace_startstop(struct request_queue *q, int start)
 {
-	int ret;
 	struct blk_trace *bt;
 
 	bt = rcu_dereference_protected(q->blk_trace,
@@ -666,36 +696,10 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 	if (bt == NULL)
 		return -EINVAL;
 
-	/*
-	 * For starting a trace, we can transition from a setup or stopped
-	 * trace. For stopping a trace, the state must be running
-	 */
-	ret = -EINVAL;
-	if (start) {
-		if (bt->trace_state == Blktrace_setup ||
-		    bt->trace_state == Blktrace_stopped) {
-			blktrace_seq++;
-			smp_mb();
-			bt->trace_state = Blktrace_running;
-			raw_spin_lock_irq(&running_trace_lock);
-			list_add(&bt->running_list, &running_trace_list);
-			raw_spin_unlock_irq(&running_trace_lock);
-
-			trace_note_time(bt);
-			ret = 0;
-		}
-	} else {
-		if (bt->trace_state == Blktrace_running) {
-			bt->trace_state = Blktrace_stopped;
-			raw_spin_lock_irq(&running_trace_lock);
-			list_del_init(&bt->running_list);
-			raw_spin_unlock_irq(&running_trace_lock);
-			relay_flush(bt->rchan);
-			ret = 0;
-		}
-	}
-
-	return ret;
+	if (start)
+		return blk_trace_start(bt);
+	else
+		return blk_trace_stop(bt);
 }
 
 int blk_trace_startstop(struct request_queue *q, int start)
@@ -772,10 +776,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 void blk_trace_shutdown(struct request_queue *q)
 {
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->debugfs_mutex))) {
-		__blk_trace_startstop(q, 0);
+				      lockdep_is_held(&q->debugfs_mutex)))
 		__blk_trace_remove(q);
-	}
 }
 
 #ifdef CONFIG_BLK_CGROUP
@@ -1614,13 +1616,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
-	if (bt->trace_state == Blktrace_running) {
-		bt->trace_state = Blktrace_stopped;
-		raw_spin_lock_irq(&running_trace_lock);
-		list_del_init(&bt->running_list);
-		raw_spin_unlock_irq(&running_trace_lock);
-		relay_flush(bt->rchan);
-	}
+	blk_trace_stop(bt);
 
 	put_probe_ref();
 	synchronize_rcu();
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 49fb9ec8366d..1ed08967fb97 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -687,6 +687,7 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
+	sd->sample_flags |= PERF_SAMPLE_RAW;
 
 	err = __bpf_perf_event_output(regs, map, flags, sd);
 
@@ -745,6 +746,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 	perf_fetch_caller_regs(regs);
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
+	sd->sample_flags |= PERF_SAMPLE_RAW;
 
 	ret = __bpf_perf_event_output(regs, map, flags, sd);
 out:
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 064072c16e3d..f50398cb790d 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -74,6 +74,7 @@ static int proc_do_uts_string(struct ctl_table *table, int write,
 static DEFINE_CTL_TABLE_POLL(hostname_poll);
 static DEFINE_CTL_TABLE_POLL(domainname_poll);
 
+// Note: update 'enum uts_proc' to match any changes to this table
 static struct ctl_table uts_kern_table[] = {
 	{
 		.procname	= "arch",