1 files changed, 161 insertions, 103 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 13aaf5e85b81..25476ead681b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -384,7 +384,7 @@ struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
-	long				wait_index;
+	atomic_t			seq;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;
@@ -754,10 +754,24 @@ static void rb_wake_up_waiters(struct irq_work *work)
 {
 	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
 
+	/* For waiters waiting for the first wake up */
+	(void)atomic_fetch_inc_release(&rbwork->seq);
+
 	wake_up_all(&rbwork->waiters);
 	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
+		/* Only cpu_buffer sets the above flags */
+		struct ring_buffer_per_cpu *cpu_buffer =
+			container_of(rbwork, struct ring_buffer_per_cpu, irq_work);
+
+		/* Called from interrupt context */
+		raw_spin_lock(&cpu_buffer->reader_lock);
 		rbwork->wakeup_full = false;
 		rbwork->full_waiters_pending = false;
+
+		/* Waking up all waiters, they will reset the shortest full */
+		cpu_buffer->shortest_full = 0;
+		raw_spin_unlock(&cpu_buffer->reader_lock);
+
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
@@ -798,30 +812,115 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
 		rbwork = &cpu_buffer->irq_work;
 	}
 
-	rbwork->wait_index++;
-	/* make sure the waiters see the new index */
-	smp_wmb();
-
 	/* This can be called in any context */
 	irq_work_queue(&rbwork->work);
 }
 
+static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	bool ret = false;
+
+	/* Reads of all CPUs always waits for any data */
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		return !ring_buffer_empty(buffer);
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	if (!ring_buffer_empty_cpu(buffer, cpu)) {
+		unsigned long flags;
+		bool pagebusy;
+
+		if (!full)
+			return true;
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+		ret = !pagebusy && full_hit(buffer, cpu, full);
+
+		if (!ret && (!cpu_buffer->shortest_full ||
+			     cpu_buffer->shortest_full > full)) {
+		    cpu_buffer->shortest_full = full;
+		}
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	}
+	return ret;
+}
+
+static inline bool
+rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer,
+	     int cpu, int full, ring_buffer_cond_fn cond, void *data)
+{
+	if (rb_watermark_hit(buffer, cpu, full))
+		return true;
+
+	if (cond(data))
+		return true;
+
+	/*
+	 * The events can happen in critical sections where
+	 * checking a work queue can cause deadlocks.
+	 * After adding a task to the queue, this flag is set
+	 * only to notify events to try to wake up the queue
+	 * using irq_work.
+	 *
+	 * We don't clear it even if the buffer is no longer
+	 * empty. The flag only causes the next event to run
+	 * irq_work to do the work queue wake up. The worse
+	 * that can happen if we race with !trace_empty() is that
+	 * an event will cause an irq_work to try to wake up
+	 * an empty queue.
+	 *
+	 * There's no reason to protect this flag either, as
+	 * the work queue and irq_work logic will do the necessary
+	 * synchronization for the wake ups. The only thing
+	 * that is necessary is that the wake up happens after
+	 * a task has been queued. It's OK for spurious wake ups.
+	 */
+	if (full)
+		rbwork->full_waiters_pending = true;
+	else
+		rbwork->waiters_pending = true;
+
+	return false;
+}
+
+struct rb_wait_data {
+	struct rb_irq_work		*irq_work;
+	int				seq;
+};
+
+/*
+ * The default wait condition for ring_buffer_wait() is to just to exit the
+ * wait loop the first time it is woken up.
+ */
+static bool rb_wait_once(void *data)
+{
+	struct rb_wait_data *rdata = data;
+	struct rb_irq_work *rbwork = rdata->irq_work;
+
+	return atomic_read_acquire(&rbwork->seq) != rdata->seq;
+}
+
 /**
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
  * @cpu: the cpu buffer to wait on
  * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS
+ * @cond: condition function to break out of wait (NULL to run once)
+ * @data: the data to pass to @cond.
  *
  * 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
  * it will wait for data to be added to a specific cpu buffer.
  */
-int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
+int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full,
+		     ring_buffer_cond_fn cond, void *data)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	DEFINE_WAIT(wait);
-	struct rb_irq_work *work;
-	long wait_index;
+	struct wait_queue_head *waitq;
+	struct rb_irq_work *rbwork;
+	struct rb_wait_data rdata;
 	int ret = 0;
 
 	/*
@@ -830,90 +929,31 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 	 * caller on the appropriate wait queue.
 	 */
 	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
+		rbwork = &buffer->irq_work;
 		/* Full only makes sense on per cpu reads */
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return -ENODEV;
 		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
-	}
-
-	wait_index = READ_ONCE(work->wait_index);
-
-	while (true) {
-		if (full)
-			prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
-		else
-			prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
-
-		/*
-		 * The events can happen in critical sections where
-		 * checking a work queue can cause deadlocks.
-		 * After adding a task to the queue, this flag is set
-		 * only to notify events to try to wake up the queue
-		 * using irq_work.
-		 *
-		 * We don't clear it even if the buffer is no longer
-		 * empty. The flag only causes the next event to run
-		 * irq_work to do the work queue wake up. The worse
-		 * that can happen if we race with !trace_empty() is that
-		 * an event will cause an irq_work to try to wake up
-		 * an empty queue.
-		 *
-		 * There's no reason to protect this flag either, as
-		 * the work queue and irq_work logic will do the necessary
-		 * synchronization for the wake ups. The only thing
-		 * that is necessary is that the wake up happens after
-		 * a task has been queued. It's OK for spurious wake ups.
-		 */
-		if (full)
-			work->full_waiters_pending = true;
-		else
-			work->waiters_pending = true;
-
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-
-		if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer))
-			break;
-
-		if (cpu != RING_BUFFER_ALL_CPUS &&
-		    !ring_buffer_empty_cpu(buffer, cpu)) {
-			unsigned long flags;
-			bool pagebusy;
-			bool done;
-
-			if (!full)
-				break;
-
-			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
-			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 (done)
-				break;
-		}
-
-		schedule();
-
-		/* Make sure to see the new wait index */
-		smp_rmb();
-		if (wait_index != work->wait_index)
-			break;
+		rbwork = &cpu_buffer->irq_work;
 	}
 
 	if (full)
-		finish_wait(&work->full_waiters, &wait);
+		waitq = &rbwork->full_waiters;
 	else
-		finish_wait(&work->waiters, &wait);
+		waitq = &rbwork->waiters;
+
+	/* Set up to exit loop as soon as it is woken */
+	if (!cond) {
+		cond = rb_wait_once;
+		rdata.irq_work = rbwork;
+		rdata.seq = atomic_read_acquire(&rbwork->seq);
+		data = &rdata;
+	}
+
+	ret = wait_event_interruptible((*waitq),
+				rb_wait_cond(rbwork, buffer, cpu, full, cond, data));
 
 	return ret;
 }
@@ -937,30 +977,44 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct rb_irq_work *work;
+	struct rb_irq_work *rbwork;
 
 	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
+		rbwork = &buffer->irq_work;
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
-			return -EINVAL;
+			return EPOLLERR;
 
 		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
+		rbwork = &cpu_buffer->irq_work;
 	}
 
 	if (full) {
-		poll_wait(filp, &work->full_waiters, poll_table);
-		work->full_waiters_pending = true;
-		if (!cpu_buffer->shortest_full ||
-		    cpu_buffer->shortest_full > full)
-			cpu_buffer->shortest_full = full;
-	} else {
-		poll_wait(filp, &work->waiters, poll_table);
-		work->waiters_pending = true;
+		poll_wait(filp, &rbwork->full_waiters, poll_table);
+
+		if (rb_watermark_hit(buffer, cpu, full))
+			return EPOLLIN | EPOLLRDNORM;
+		/*
+		 * Only allow full_waiters_pending update to be seen after
+		 * the shortest_full is set (in rb_watermark_hit). If the
+		 * writer sees the full_waiters_pending flag set, it will
+		 * compare the amount in the ring buffer to shortest_full.
+		 * If the amount in the ring buffer is greater than the
+		 * shortest_full percent, it will call the irq_work handler
+		 * to wake up this list. The irq_handler will reset shortest_full
+		 * back to zero. That's done under the reader_lock, but
+		 * the below smp_mb() makes sure that the update to
+		 * full_waiters_pending doesn't leak up into the above.
+		 */
+		smp_mb();
+		rbwork->full_waiters_pending = true;
+		return 0;
 	}
 
+	poll_wait(filp, &rbwork->waiters, poll_table);
+	rbwork->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
@@ -976,9 +1030,6 @@ __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;
@@ -1009,7 +1060,7 @@ static inline u64 rb_time_stamp(struct trace_buffer *buffer)
 	u64 ts;
 
 	/* Skip retpolines :-( */
-	if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local))
+	if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && likely(buffer->clock == trace_clock_local))
 		ts = trace_clock_local();
 	else
 		ts = buffer->clock();
@@ -1472,7 +1523,8 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 		list_add(&bpage->list, pages);
 
-		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags,
+		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
+					mflags | __GFP_ZERO,
 					cpu_buffer->buffer->subbuf_order);
 		if (!page)
 			goto free_pages;
@@ -1557,7 +1609,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 
 	cpu_buffer->reader_page = bpage;
 
-	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order);
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_ZERO,
+				cpu_buffer->buffer->subbuf_order);
 	if (!page)
 		goto fail_free_reader;
 	bpage->page = page_address(page);
@@ -4337,7 +4390,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
 	cpu_buffer = iter->cpu_buffer;
 	reader = cpu_buffer->reader_page;
 	head_page = cpu_buffer->head_page;
-	commit_page = cpu_buffer->commit_page;
+	commit_page = READ_ONCE(cpu_buffer->commit_page);
 	commit_ts = commit_page->page->time_stamp;
 
 	/*
@@ -5525,7 +5578,8 @@ ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
 	if (bpage->data)
 		goto out;
 
-	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY,
+	page = alloc_pages_node(cpu_to_node(cpu),
+				GFP_KERNEL | __GFP_NORETRY | __GFP_ZERO,
 				cpu_buffer->buffer->subbuf_order);
 	if (!page) {
 		kfree(bpage);
@@ -5877,6 +5931,10 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	if (psize <= BUF_PAGE_HDR_SIZE)
 		return -EINVAL;
 
+	/* Size of a subbuf cannot be greater than the write counter */
+	if (psize > RB_WRITE_MASK + 1)
+		return -EINVAL;
+
 	old_order = buffer->subbuf_order;
 	old_size = buffer->subbuf_size;