1 files changed, 80 insertions, 35 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9712083832f4..c366a0a9ddba 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -519,6 +519,7 @@ struct ring_buffer_per_cpu {
 	local_t				committing;
 	local_t				commits;
 	local_t				pages_touched;
+	local_t				pages_lost;
 	local_t				pages_read;
 	long				last_pages_touch;
 	size_t				shortest_full;
@@ -894,10 +895,18 @@ size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu)
 size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu)
 {
 	size_t read;
+	size_t lost;
 	size_t cnt;
 
 	read = local_read(&buffer->buffers[cpu]->pages_read);
+	lost = local_read(&buffer->buffers[cpu]->pages_lost);
 	cnt = local_read(&buffer->buffers[cpu]->pages_touched);
+
+	if (WARN_ON_ONCE(cnt < lost))
+		return 0;
+
+	cnt -= lost;
+
 	/* The reader can read an empty page, but not more than that */
 	if (cnt < read) {
 		WARN_ON_ONCE(read > cnt + 1);
@@ -907,6 +916,21 @@ size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu)
 	return cnt - read;
 }
 
+static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int full)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	size_t nr_pages;
+	size_t dirty;
+
+	nr_pages = cpu_buffer->nr_pages;
+	if (!nr_pages || !full)
+		return true;
+
+	dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+
+	return (dirty * 100) > (full * nr_pages);
+}
+
 /*
  * rb_wake_up_waiters - wake up tasks waiting for ring buffer input
  *
@@ -1046,22 +1070,20 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		    !ring_buffer_empty_cpu(buffer, cpu)) {
 			unsigned long flags;
 			bool pagebusy;
-			size_t nr_pages;
-			size_t dirty;
+			bool done;
 
 			if (!full)
 				break;
 
 			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
-			nr_pages = cpu_buffer->nr_pages;
-			dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+			done = !pagebusy && full_hit(buffer, cpu, full);
+
 			if (!cpu_buffer->shortest_full ||
 			    cpu_buffer->shortest_full > full)
 				cpu_buffer->shortest_full = full;
 			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-			if (!pagebusy &&
-			    (!nr_pages || (dirty * 100) > full * nr_pages))
+			if (done)
 				break;
 		}
 
@@ -1087,6 +1109,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
  * @cpu: the cpu buffer to wait on
  * @filp: the file descriptor
  * @poll_table: The poll descriptor
+ * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS
  *
  * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
  * as data is added to any of the @buffer's cpu buffers. Otherwise
@@ -1096,14 +1119,15 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
  * zero otherwise.
  */
 __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
-			  struct file *filp, poll_table *poll_table)
+			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct rb_irq_work *work;
 
-	if (cpu == RING_BUFFER_ALL_CPUS)
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		work = &buffer->irq_work;
-	else {
+		full = 0;
+	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return -EINVAL;
 
@@ -1111,8 +1135,14 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 		work = &cpu_buffer->irq_work;
 	}
 
-	poll_wait(filp, &work->waiters, poll_table);
-	work->waiters_pending = true;
+	if (full) {
+		poll_wait(filp, &work->full_waiters, poll_table);
+		work->full_waiters_pending = true;
+	} else {
+		poll_wait(filp, &work->waiters, poll_table);
+		work->waiters_pending = true;
+	}
+
 	/*
 	 * There's a tight race between setting the waiters_pending and
 	 * checking if the ring buffer is empty.  Once the waiters_pending bit
@@ -1128,6 +1158,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 	 */
 	smp_mb();
 
+	if (full)
+		return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0;
+
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
 		return EPOLLIN | EPOLLRDNORM;
@@ -1769,9 +1802,9 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 
 	free_buffer_page(cpu_buffer->reader_page);
 
-	rb_head_page_deactivate(cpu_buffer);
-
 	if (head) {
+		rb_head_page_deactivate(cpu_buffer);
+
 		list_for_each_entry_safe(bpage, tmp, head, list) {
 			list_del_init(&bpage->list);
 			free_buffer_page(bpage);
@@ -2007,6 +2040,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 			 */
 			local_add(page_entries, &cpu_buffer->overrun);
 			local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+			local_inc(&cpu_buffer->pages_lost);
 		}
 
 		/*
@@ -2028,8 +2062,10 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct list_head *pages = &cpu_buffer->new_pages;
 	int retries, success;
+	unsigned long flags;
 
-	raw_spin_lock_irq(&cpu_buffer->reader_lock);
+	/* Can be called at early boot up, where interrupts must not been enabled */
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	/*
 	 * We are holding the reader lock, so the reader page won't be swapped
 	 * in the ring buffer. Now we are racing with the writer trying to
@@ -2086,7 +2122,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	 * tracing
 	 */
 	RB_WARN_ON(cpu_buffer, !success);
-	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	/* free pages if they weren't inserted */
 	if (!success) {
@@ -2214,8 +2250,16 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 				rb_update_pages(cpu_buffer);
 				cpu_buffer->nr_pages_to_update = 0;
 			} else {
-				schedule_work_on(cpu,
-						&cpu_buffer->update_pages_work);
+				/* Run directly if possible. */
+				migrate_disable();
+				if (cpu != smp_processor_id()) {
+					migrate_enable();
+					schedule_work_on(cpu,
+							 &cpu_buffer->update_pages_work);
+				} else {
+					update_pages_handler(&cpu_buffer->update_pages_work);
+					migrate_enable();
+				}
 			}
 		}
 
@@ -2264,9 +2308,17 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		if (!cpu_online(cpu_id))
 			rb_update_pages(cpu_buffer);
 		else {
-			schedule_work_on(cpu_id,
-					 &cpu_buffer->update_pages_work);
-			wait_for_completion(&cpu_buffer->update_done);
+			/* Run directly if possible. */
+			migrate_disable();
+			if (cpu_id == smp_processor_id()) {
+				rb_update_pages(cpu_buffer);
+				migrate_enable();
+			} else {
+				migrate_enable();
+				schedule_work_on(cpu_id,
+						 &cpu_buffer->update_pages_work);
+				wait_for_completion(&cpu_buffer->update_done);
+			}
 		}
 
 		cpu_buffer->nr_pages_to_update = 0;
@@ -2491,6 +2543,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		local_add(entries, &cpu_buffer->overrun);
 		local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+		local_inc(&cpu_buffer->pages_lost);
 
 		/*
 		 * The entries will be zeroed out when we move the
@@ -3145,8 +3198,7 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
 		event->time_delta = 1;
 }
 
-static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
-		      struct ring_buffer_event *event)
+static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	local_inc(&cpu_buffer->entries);
 	rb_end_commit(cpu_buffer);
@@ -3155,10 +3207,6 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 static __always_inline void
 rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 {
-	size_t nr_pages;
-	size_t dirty;
-	size_t full;
-
 	if (buffer->irq_work.waiters_pending) {
 		buffer->irq_work.waiters_pending = false;
 		/* irq_work_queue() supplies it's own memory barriers */
@@ -3182,10 +3230,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 
 	cpu_buffer->last_pages_touch = local_read(&cpu_buffer->pages_touched);
 
-	full = cpu_buffer->shortest_full;
-	nr_pages = cpu_buffer->nr_pages;
-	dirty = ring_buffer_nr_dirty_pages(buffer, cpu_buffer->cpu);
-	if (full && nr_pages && (dirty * 100) <= full * nr_pages)
+	if (!full_hit(buffer, cpu_buffer->cpu, cpu_buffer->shortest_full))
 		return;
 
 	cpu_buffer->irq_work.wakeup_full = true;
@@ -3355,15 +3400,14 @@ void ring_buffer_nest_end(struct trace_buffer *buffer)
  *
  * Must be paired with ring_buffer_lock_reserve.
  */
-int ring_buffer_unlock_commit(struct trace_buffer *buffer,
-			      struct ring_buffer_event *event)
+int ring_buffer_unlock_commit(struct trace_buffer *buffer)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	int cpu = raw_smp_processor_id();
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	rb_commit(cpu_buffer, event);
+	rb_commit(cpu_buffer);
 
 	rb_wakeups(buffer, cpu_buffer);
 
@@ -3949,7 +3993,7 @@ int ring_buffer_write(struct trace_buffer *buffer,
 
 	memcpy(body, data, length);
 
-	rb_commit(cpu_buffer, event);
+	rb_commit(cpu_buffer);
 
 	rb_wakeups(buffer, cpu_buffer);
 
@@ -5248,6 +5292,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->committing, 0);
 	local_set(&cpu_buffer->commits, 0);
 	local_set(&cpu_buffer->pages_touched, 0);
+	local_set(&cpu_buffer->pages_lost, 0);
 	local_set(&cpu_buffer->pages_read, 0);
 	cpu_buffer->last_pages_touch = 0;
 	cpu_buffer->shortest_full = 0;
@@ -5969,7 +6014,7 @@ static __init int rb_write_something(struct rb_test_data *data, bool nested)
 	}
 
  out:
-	ring_buffer_unlock_commit(data->buffer, event);
+	ring_buffer_unlock_commit(data->buffer);
 
 	return 0;
 }