Merge branch 'linus' into sched/urgent, to resolve conflict

 Conflicts:
	kernel/sched/ext.c

There's a context conflict between this upstream commit:

  3fdb9ebcec10 sched_ext: Start schedulers with consistent p->scx.slice values

... and this fix in sched/urgent:

  98442f0ccd82 sched: Fix delayed_dequeue vs switched_from_fair()

Resolve it.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 63 insertions, 35 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 77dc0b25140e..3ea4f7bb1837 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2337,9 +2337,12 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 	if (!buffer->buffers[cpu])
 		goto fail_free_buffers;
 
-	ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
-	if (ret < 0)
-		goto fail_free_buffers;
+	/* If already mapped, do not hook to CPU hotplug */
+	if (!start) {
+		ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
+		if (ret < 0)
+			goto fail_free_buffers;
+	}
 
 	mutex_init(&buffer->mutex);
 
@@ -6725,39 +6728,38 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	}
 
 	for_each_buffer_cpu(buffer, cpu) {
+		struct buffer_data_page *old_free_data_page;
+		struct list_head old_pages;
+		unsigned long flags;
 
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			continue;
 
 		cpu_buffer = buffer->buffers[cpu];
 
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
 		/* Clear the head bit to make the link list normal to read */
 		rb_head_page_deactivate(cpu_buffer);
 
-		/* Now walk the list and free all the old sub buffers */
-		list_for_each_entry_safe(bpage, tmp, cpu_buffer->pages, list) {
-			list_del_init(&bpage->list);
-			free_buffer_page(bpage);
-		}
-		/* The above loop stopped an the last page needing to be freed */
-		bpage = list_entry(cpu_buffer->pages, struct buffer_page, list);
-		free_buffer_page(bpage);
-
-		/* Free the current reader page */
-		free_buffer_page(cpu_buffer->reader_page);
+		/*
+		 * Collect buffers from the cpu_buffer pages list and the
+		 * reader_page on old_pages, so they can be freed later when not
+		 * under a spinlock. The pages list is a linked list with no
+		 * head, adding old_pages turns it into a regular list with
+		 * old_pages being the head.
+		 */
+		list_add(&old_pages, cpu_buffer->pages);
+		list_add(&cpu_buffer->reader_page->list, &old_pages);
 
 		/* One page was allocated for the reader page */
 		cpu_buffer->reader_page = list_entry(cpu_buffer->new_pages.next,
 						     struct buffer_page, list);
 		list_del_init(&cpu_buffer->reader_page->list);
 
-		/* The cpu_buffer pages are a link list with no head */
+		/* Install the new pages, remove the head from the list */
 		cpu_buffer->pages = cpu_buffer->new_pages.next;
-		cpu_buffer->new_pages.next->prev = cpu_buffer->new_pages.prev;
-		cpu_buffer->new_pages.prev->next = cpu_buffer->new_pages.next;
-
-		/* Clear the new_pages list */
-		INIT_LIST_HEAD(&cpu_buffer->new_pages);
+		list_del_init(&cpu_buffer->new_pages);
 
 		cpu_buffer->head_page
 			= list_entry(cpu_buffer->pages, struct buffer_page, list);
@@ -6766,11 +6768,20 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 		cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update;
 		cpu_buffer->nr_pages_to_update = 0;
 
-		free_pages((unsigned long)cpu_buffer->free_page, old_order);
+		old_free_data_page = cpu_buffer->free_page;
 		cpu_buffer->free_page = NULL;
 
 		rb_head_page_activate(cpu_buffer);
 
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+		/* Free old sub buffers */
+		list_for_each_entry_safe(bpage, tmp, &old_pages, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+		free_pages((unsigned long)old_free_data_page, old_order);
+
 		rb_check_pages(cpu_buffer);
 	}
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c01375adc471..a8f52b6527ca 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3697,8 +3697,8 @@ static void test_can_verify(void)
 void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 			 va_list ap)
 {
-	long text_delta = iter->tr->text_delta;
-	long data_delta = iter->tr->data_delta;
+	long text_delta = 0;
+	long data_delta = 0;
 	const char *p = fmt;
 	const char *str;
 	bool good;
@@ -3710,6 +3710,17 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 	if (static_branch_unlikely(&trace_no_verify))
 		goto print;
 
+	/*
+	 * When the kernel is booted with the tp_printk command line
+	 * parameter, trace events go directly through to printk().
+	 * It also is checked by this function, but it does not
+	 * have an associated trace_array (tr) for it.
+	 */
+	if (iter->tr) {
+		text_delta = iter->tr->text_delta;
+		data_delta = iter->tr->data_delta;
+	}
+
 	/* Don't bother checking when doing a ftrace_dump() */
 	if (iter->fmt == static_fmt_buf)
 		goto print;
@@ -10610,10 +10621,10 @@ __init static void enable_instances(void)
 		 * cannot be deleted by user space, so keep the reference
 		 * to it.
 		 */
-		if (start)
+		if (start) {
 			tr->flags |= TRACE_ARRAY_FL_BOOT;
-		else
-			trace_array_put(tr);
+			tr->ref++;
+		}
 
 		while ((tok = strsep(&curr_str, ","))) {
 			early_enable_events(tr, tok, true);
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index b791524a6536..3bd6071441ad 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -520,6 +520,8 @@ static void hwlat_hotplug_workfn(struct work_struct *dummy)
 	if (!hwlat_busy || hwlat_data.thread_mode != MODE_PER_CPU)
 		goto out_unlock;
 
+	if (!cpu_online(cpu))
+		goto out_unlock;
 	if (!cpumask_test_cpu(cpu, tr->tracing_cpumask))
 		goto out_unlock;
 
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 1439064f65d6..a50ed23bee77 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1953,12 +1953,8 @@ static void stop_kthread(unsigned int cpu)
 {
 	struct task_struct *kthread;
 
-	mutex_lock(&interface_lock);
-	kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
+	kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL);
 	if (kthread) {
-		per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
-		mutex_unlock(&interface_lock);
-
 		if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask) &&
 		    !WARN_ON(!test_bit(OSN_WORKLOAD, &osnoise_options))) {
 			kthread_stop(kthread);
@@ -1972,7 +1968,6 @@ static void stop_kthread(unsigned int cpu)
 			put_task_struct(kthread);
 		}
 	} else {
-		mutex_unlock(&interface_lock);
 		/* if no workload, just return */
 		if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
 			/*
@@ -1994,8 +1989,12 @@ static void stop_per_cpu_kthreads(void)
 {
 	int cpu;
 
-	for_each_possible_cpu(cpu)
+	cpus_read_lock();
+
+	for_each_online_cpu(cpu)
 		stop_kthread(cpu);
+
+	cpus_read_unlock();
 }
 
 /*
@@ -2007,6 +2006,10 @@ static int start_kthread(unsigned int cpu)
 	void *main = osnoise_main;
 	char comm[24];
 
+	/* Do not start a new thread if it is already running */
+	if (per_cpu(per_cpu_osnoise_var, cpu).kthread)
+		return 0;
+
 	if (timerlat_enabled()) {
 		snprintf(comm, 24, "timerlat/%d", cpu);
 		main = timerlat_main;
@@ -2061,11 +2064,10 @@ static int start_per_cpu_kthreads(void)
 		if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask)) {
 			struct task_struct *kthread;
 
-			kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
+			kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL);
 			if (!WARN_ON(!kthread))
 				kthread_stop(kthread);
 		}
-		per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
 	}
 
 	for_each_cpu(cpu, current_mask) {
@@ -2095,6 +2097,8 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
 	mutex_lock(&interface_lock);
 	cpus_read_lock();
 
+	if (!cpu_online(cpu))
+		goto out_unlock;
 	if (!cpumask_test_cpu(cpu, &osnoise_cpumask))
 		goto out_unlock;