tracing: Add a config and syscall_user_buf_size file to limit amount written

When a system call that can copy user space addresses into the ring
buffer, it can copy up to 511 bytes of data. This can waste precious ring
buffer space if the user isn't interested in the output. Add a new file
"syscall_user_buf_size" that gets initialized to a new config
CONFIG_SYSCALL_BUF_SIZE_DEFAULT that defaults to 63.

The config also is used to limit how much perf can read from user space.

Also lower the max down to 165, as this isn't to record everything that a
system call may be passing through to the kernel. 165 is more than enough.

The reason for 165 is because adding one for the nul terminating byte, as
well as possibly needing to append the "..." string turns it into 170
bytes. As this needs to save up to 3 arguments and 3 * 170 is 510 which
fits nicely in 512 bytes (a power of 2).

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Takaya Saeki <takayas@google.com>
Cc: Tom Zanussi <zanussi@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Douglas Raillard <douglas.raillard@arm.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Link: https://lore.kernel.org/20251028231148.260068913@kernel.org
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 52 insertions, 0 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 50832411c5c0..2aee9a3088f4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6912,6 +6912,43 @@ out_err:
 }
 
 static ssize_t
+tracing_syscall_buf_read(struct file *filp, char __user *ubuf,
+			 size_t cnt, loff_t *ppos)
+{
+	struct inode *inode = file_inode(filp);
+	struct trace_array *tr = inode->i_private;
+	char buf[64];
+	int r;
+
+	r = snprintf(buf, 64, "%d\n", tr->syscall_buf_sz);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+tracing_syscall_buf_write(struct file *filp, const char __user *ubuf,
+			  size_t cnt, loff_t *ppos)
+{
+	struct inode *inode = file_inode(filp);
+	struct trace_array *tr = inode->i_private;
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val > SYSCALL_FAULT_USER_MAX)
+		val = SYSCALL_FAULT_USER_MAX;
+
+	tr->syscall_buf_sz = val;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
 tracing_entries_read(struct file *filp, char __user *ubuf,
 		     size_t cnt, loff_t *ppos)
 {
@@ -8043,6 +8080,14 @@ static const struct file_operations tracing_entries_fops = {
 	.release	= tracing_release_generic_tr,
 };
 
+static const struct file_operations tracing_syscall_buf_fops = {
+	.open		= tracing_open_generic_tr,
+	.read		= tracing_syscall_buf_read,
+	.write		= tracing_syscall_buf_write,
+	.llseek		= generic_file_llseek,
+	.release	= tracing_release_generic_tr,
+};
+
 static const struct file_operations tracing_buffer_meta_fops = {
 	.open		= tracing_buffer_meta_open,
 	.read		= seq_read,
@@ -10145,6 +10190,8 @@ trace_array_create_systems(const char *name, const char *systems,
 
 	raw_spin_lock_init(&tr->start_lock);
 
+	tr->syscall_buf_sz = global_trace.syscall_buf_sz;
+
 	tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 #ifdef CONFIG_TRACER_MAX_TRACE
 	spin_lock_init(&tr->snapshot_trigger_lock);
@@ -10461,6 +10508,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("buffer_subbuf_size_kb", TRACE_MODE_WRITE, d_tracer,
 			  tr, &buffer_subbuf_size_fops);
 
+	trace_create_file("syscall_user_buf_size", TRACE_MODE_WRITE, d_tracer,
+			 tr, &tracing_syscall_buf_fops);
+
 	create_trace_options_dir(tr);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -11386,6 +11436,8 @@ __init static int tracer_alloc_buffers(void)
 
 	global_trace.flags = TRACE_ARRAY_FL_GLOBAL;
 
+	global_trace.syscall_buf_sz = CONFIG_TRACE_SYSCALL_BUF_SIZE_DEFAULT;
+
 	INIT_LIST_HEAD(&global_trace.systems);
 	INIT_LIST_HEAD(&global_trace.events);
 	INIT_LIST_HEAD(&global_trace.hist_vars);