[PATCH v4] tracing: Allow for max buffer data size trace_marker writes

[Steven Rostedt]

From: "Steven Rostedt (Google)" <rostedt@xxxxxxxxxxx>

Allow a trace write to be as big as the ring buffer tracing data will
allow. Currently, it only allows writes of 1KB in size, but there's no
reason that it cannot allow what the ring buffer can hold.

Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
---
Changes since v3: https://lore.kernel.org/linux-trace-kernel/20231212110332.6fca52c4@xxxxxxxxxxxxxxxxxx

- No greated cheese. (Mathieu Desnoyers)

 include/linux/ring_buffer.h |  1 +
 kernel/trace/ring_buffer.c  | 15 +++++++++++++++
 kernel/trace/trace.c        | 31 ++++++++++++++++++++++++-------
 3 files changed, 40 insertions(+), 7 deletions(-)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 782e14f62201..b1b03b2c0f08 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -141,6 +141,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
 bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter);
 
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu);
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer);
 
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu);
 void ring_buffer_reset_online_cpus(struct trace_buffer *buffer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6b82c3398938..087f0f6b3409 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5255,6 +5255,21 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
+/**
+ * ring_buffer_max_event_size - return the max data size of an event
+ * @buffer: The ring buffer.
+ *
+ * Returns the maximum size an event can be.
+ */
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer)
+{
+	/* If abs timestamp is requested, events have a timestamp too */
+	if (ring_buffer_time_stamp_abs(buffer))
+		return BUF_MAX_DATA_SIZE - RB_LEN_TIME_EXTEND;
+	return BUF_MAX_DATA_SIZE;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_max_event_size);
+
 static void rb_clear_buffer_page(struct buffer_page *page)
 {
 	local_set(&page->write, 0);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ef86379555e4..a359783fede8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7272,8 +7272,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	enum event_trigger_type tt = ETT_NONE;
 	struct trace_buffer *buffer;
 	struct print_entry *entry;
+	int meta_size;
 	ssize_t written;
-	int size;
+	size_t size;
 	int len;
 
 /* Used in tracing_mark_raw_write() as well */
@@ -7286,12 +7287,12 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
 		return -EINVAL;
 
-	if (cnt > TRACE_BUF_SIZE)
-		cnt = TRACE_BUF_SIZE;
-
-	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
+	if ((ssize_t)cnt < 0)
+		return -EINVAL;
 
-	size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */
+	meta_size = sizeof(*entry) + 2;  /* add '\0' and possible '\n' */
+ again:
+	size = cnt + meta_size;
 
 	/* If less than "<faulted>", then make sure we can still add that */
 	if (cnt < FAULTED_SIZE)
@@ -7300,9 +7301,25 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	buffer = tr->array_buffer.buffer;
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					    tracing_gen_ctx());
-	if (unlikely(!event))
+	if (unlikely(!event)) {
+		/*
+		 * If the size was greater than what was allowed, then
+		 * make it smaller and try again.
+		 */
+		if (size > ring_buffer_max_event_size(buffer)) {
+			/* cnt < FAULTED size should never be bigger than max */
+			if (WARN_ON_ONCE(cnt < FAULTED_SIZE))
+				return -EBADF;
+			cnt = ring_buffer_max_event_size(buffer) - meta_size;
+			/* The above should only happen once */
+			if (WARN_ON_ONCE(cnt + meta_size == size))
+				return -EBADF;
+			goto again;
+		}
+
 		/* Ring buffer disabled, return as if not open for write */
 		return -EBADF;
+	}
 
 	entry = ring_buffer_event_data(event);
 	entry->ip = _THIS_IP_;
-- 
2.42.0