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 <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Mathieu Desnoyers <[e-mail]>
Cc: Andrew Morton <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Takaya Saeki <[e-mail]>
Cc: Tom Zanussi <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: Ian Rogers <[e-mail]>
Cc: Douglas Raillard <[e-mail]>
Cc: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Link: https://lore.kernel.org/[e-mail]
Signed-off-by: Steven Rostedt (Google) <[e-mail]>

Documentation/trace/ftrace.rst

···
 	for each function. The displayed address is the patch-site address
 	and can differ from /proc/kallsyms address.
 
+  syscall_user_buf_size:
+
+	Some system call trace events will record the data from a user
+	space address that one of the parameters point to. The amount of
+	data per event is limited. This file holds the max number of bytes
+	that will be recorded into the ring buffer to hold this data.
+	The max value is currently 165.
+
   dyn_ftrace_total_info:
 
 	This file is for debugging purposes. The number of functions that

kernel/trace/Kconfig

···
 	help
 	  Basic tracer to catch the syscall entry and exit events.
 
+config TRACE_SYSCALL_BUF_SIZE_DEFAULT
+	int "System call user read max size"
+	range 0 165
+	default 63
+	depends on FTRACE_SYSCALLS
+	help
+	 Some system call trace events will record the data from a user
+	 space address that one of the parameters point to. The amount of
+	 data per event is limited. That limit is set by this config and
+	 this config also affects how much user space data perf can read.
+
+	 For a tracing instance, this size may be changed by writing into
+	 its syscall_user_buf_size file.
+
 config TRACER_SNAPSHOT
 	bool "Create a snapshot trace buffer"
 	select TRACER_MAX_TRACE

kernel/trace/trace.c

···
 }
 
 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)
 {
···
 	.open		= tracing_open_generic_tr,
 	.read		= tracing_entries_read,
 	.write		= tracing_entries_write,
+	.llseek		= generic_file_llseek,
+	.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,
 };
···
 
 	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);
···
 
 	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);
 
···
 	register_die_notifier(&trace_die_notifier);
 
 	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);

kernel/trace/trace.h

···
 #define HIST_STACKTRACE_SIZE	(HIST_STACKTRACE_DEPTH * sizeof(unsigned long))
 #define HIST_STACKTRACE_SKIP	5
 
+#define SYSCALL_FAULT_USER_MAX 165
+
 /*
  * syscalls are special, and need special handling, this is why
  * they are not included in trace_entries.h
···
 	int			function_enabled;
 #endif
 	int			no_filter_buffering_ref;
+	unsigned int		syscall_buf_sz;
 	struct list_head	hist_vars;
 #ifdef CONFIG_TRACER_SNAPSHOT
 	struct cond_snapshot	*cond_snapshot;

kernel/trace/trace_syscalls.c

···
 /*
  * Create a per CPU temporary buffer to copy user space pointers into.
  *
+ * SYSCALL_FAULT_USER_MAX is the amount to copy from user space.
+ *  (defined in kernel/trace/trace.h)
+
+ * SYSCALL_FAULT_ARG_SZ is the amount to copy from user space plus the
+ *   nul terminating byte and possibly appended EXTRA (4 bytes).
+ *
  * SYSCALL_FAULT_BUF_SZ holds the size of the per CPU buffer to use
- * to copy memory from user space addresses into.
- *
- * SYSCALL_FAULT_ARG_SZ is the amount to copy from user space.
- *
- * SYSCALL_FAULT_USER_MAX is the amount to copy into the ring buffer.
- *  It's slightly smaller than SYSCALL_FAULT_ARG_SZ to know if it
- *  needs to append the EXTRA or not.
- *
- * This only allows up to 3 args from system calls.
+ * to copy memory from user space addresses into that will hold
+ * 3 args as only 3 args are allowed to be copied from system calls.
  */
-#define SYSCALL_FAULT_BUF_SZ 512
-#define SYSCALL_FAULT_ARG_SZ 168
-#define SYSCALL_FAULT_USER_MAX 128
+#define SYSCALL_FAULT_ARG_SZ (SYSCALL_FAULT_USER_MAX + 1 + 4)
 #define SYSCALL_FAULT_MAX_CNT 3
+#define SYSCALL_FAULT_BUF_SZ (SYSCALL_FAULT_ARG_SZ * SYSCALL_FAULT_MAX_CNT)
 
 /* Use the tracing per CPU buffer infrastructure to copy from user space */
 struct syscall_user_buffer {
···
 	return 0;
 }
 
-static char *sys_fault_user(struct syscall_metadata *sys_data,
+static char *sys_fault_user(unsigned int buf_size,
+			    struct syscall_metadata *sys_data,
 			    struct syscall_user_buffer *sbuf,
 			    unsigned long *args,
 			    unsigned int data_size[SYSCALL_FAULT_MAX_CNT])
···
 		data_size[i] = -1; /* Denotes no pointer */
 	}
 
+	/* A zero size means do not even try */
+	if (!buf_size)
+		return NULL;
+
 	buffer = trace_user_fault_read(&sbuf->buf, NULL, size,
 				       syscall_copy, &sargs);
 	if (!buffer)
···
 					buf[x] = '.';
 			}
 
+			size = min(buf_size, SYSCALL_FAULT_USER_MAX);
+
 			/*
 			 * If the text was truncated due to our max limit,
 			 * add "..." to the string.
 			 */
-			if (ret > SYSCALL_FAULT_USER_MAX) {
-				strscpy(buf + SYSCALL_FAULT_USER_MAX, EXTRA,
-					sizeof(EXTRA));
-				ret = SYSCALL_FAULT_USER_MAX + sizeof(EXTRA);
+			if (ret > size) {
+				strscpy(buf + size, EXTRA, sizeof(EXTRA));
+				ret = size + sizeof(EXTRA);
 			} else {
 				buf[ret++] = '\0';
 			}
 		} else {
-			ret = min(ret, SYSCALL_FAULT_USER_MAX);
+			ret = min((unsigned int)ret, buf_size);
 		}
 		data_size[i] = ret;
 	}
···
 
 static int
 syscall_get_data(struct syscall_metadata *sys_data, unsigned long *args,
-		 char **buffer, int *size, int *user_sizes, int *uargs)
+		 char **buffer, int *size, int *user_sizes, int *uargs,
+		 int buf_size)
 {
 	struct syscall_user_buffer *sbuf;
 	int i;
···
 	if (!sbuf)
 		return -1;
 
-	*buffer = sys_fault_user(sys_data, sbuf, args, user_sizes);
+	*buffer = sys_fault_user(buf_size, sys_data, sbuf, args, user_sizes);
 	/*
 	 * user_size is the amount of data to append.
 	 * Need to add 4 for the meta field that points to
···
 
 	if (mayfault) {
 		if (syscall_get_data(sys_data, args, &user_ptr,
-				     &size, user_sizes, &uargs) < 0)
+				     &size, user_sizes, &uargs, tr->syscall_buf_sz) < 0)
 			return;
 	}
 
···
 	bool mayfault;
 	char *user_ptr;
 	int user_sizes[SYSCALL_FAULT_MAX_CNT] = {};
+	int buf_size = CONFIG_TRACE_SYSCALL_BUF_SIZE_DEFAULT;
 	int syscall_nr;
 	int rctx;
 	int size = 0;
···
 
 	if (mayfault) {
 		if (syscall_get_data(sys_data, args, &user_ptr,
-				     &size, user_sizes, &uargs) < 0)
+				     &size, user_sizes, &uargs, buf_size) < 0)
 			return;
 	}