tracing: Have system call events record user array data

For system call events that have a length field, add a "user_arg_size"
parameter to the system call meta data that denotes the index of the args
array that holds the size of arg that the user_mask field has a bit set
for.

The "user_mask" has a bit set that denotes the arg that points to an array
in the user space address space and if a system call event has the
user_mask field set and the user_arg_size set, it will then record the
content of that address into the trace event, up to the size defined by
SYSCALL_FAULT_BUF_SZ - 1.

This allows the output to look like:

sys_write(fd: 0xa, buf: 0x5646978d13c0 (01:00:05:00:00:00:00:00:01:87:55:89:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00), count: 0x20)

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]>

include/trace/syscall.h

···
  * @name: name of the syscall
  * @syscall_nr: number of the syscall
  * @nb_args: number of parameters it takes
+ * @user_arg_size: holds @arg that has size of the user space to read
  * @user_mask: mask of @args that will read user space
  * @types: list of types as strings
  * @args: list of args as strings (args[i] matches types[i])
···
 struct syscall_metadata {
 	const char	*name;
 	int		syscall_nr;
-	short		nb_args;
+	u8		nb_args;
+	s8		user_arg_size;
 	short		user_mask;
 	const char	**types;
 	const char	**args;

kernel/trace/trace_syscalls.c

···
 	return entry->name;
 }
 
-/* Added to user strings when max limit is reached */
+/* Added to user strings or arrays when max limit is reached */
 #define EXTRA "..."
 
 static enum print_line_t
···
 	struct trace_entry *ent = iter->ent;
 	struct syscall_trace_enter *trace;
 	struct syscall_metadata *entry;
-	int i, syscall, val;
+	int i, syscall, val, len;
 	unsigned char *ptr;
-	int len;
 
 	trace = (typeof(trace))ent;
 	syscall = trace->nr;
···
 		ptr = (void *)ent + (val & 0xffff);
 		len = val >> 16;
 
-		trace_seq_printf(s, " \"%.*s\"", len, ptr);
+		if (entry->user_arg_size < 0) {
+			trace_seq_printf(s, " \"%.*s\"", len, ptr);
+			continue;
+		}
+
+		val = trace->args[entry->user_arg_size];
+
+		trace_seq_puts(s, " (");
+		for (int x = 0; x < len; x++, ptr++) {
+			if (x)
+				trace_seq_putc(s, ':');
+			trace_seq_printf(s, "%02x", *ptr);
+		}
+		if (len < val)
+			trace_seq_printf(s, ", %s", EXTRA);
+
+		trace_seq_putc(s, ')');
 	}
 
 	trace_seq_putc(s, ')');
···
 		if (!(BIT(i) & entry->user_mask))
 			continue;
 
-		/* Add the format for the user space string */
-		pos += snprintf(buf + pos, LEN_OR_ZERO, " \\\"%%s\\\"");
+		/* Add the format for the user space string or array */
+		if (entry->user_arg_size < 0)
+			pos += snprintf(buf + pos, LEN_OR_ZERO, " \\\"%%s\\\"");
+		else
+			pos += snprintf(buf + pos, LEN_OR_ZERO, " (%%s)");
 	}
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
 
···
 				", ((unsigned long)(REC->%s))", entry->args[i]);
 		if (!(BIT(i) & entry->user_mask))
 			continue;
-		/* The user space string for arg has name __<arg>_val */
-		pos += snprintf(buf + pos, LEN_OR_ZERO, ", __get_str(__%s_val)",
-				entry->args[i]);
+		/* The user space data for arg has name __<arg>_val */
+		if (entry->user_arg_size < 0) {
+			pos += snprintf(buf + pos, LEN_OR_ZERO, ", __get_str(__%s_val)",
+					entry->args[i]);
+		} else {
+			pos += snprintf(buf + pos, LEN_OR_ZERO, ", __print_dynamic_array(__%s_val, 1)",
+					entry->args[i]);
+		}
 	}
 
 #undef LEN_OR_ZERO
···
 	idx = ffs(mask) - 1;
 
 	/*
-	 * User space strings are faulted into a temporary buffer and then
-	 * added as a dynamic string to the end of the event.
-	 * The user space string name for the arg pointer is "__<arg>_val".
+	 * User space data is faulted into a temporary buffer and then
+	 * added as a dynamic string or array to the end of the event.
+	 * The user space data name for the arg pointer is "__<arg>_val".
 	 */
 	len = strlen(meta->args[idx]) + sizeof("___val");
 	arg = kmalloc(len, GFP_KERNEL);
···
 			    struct syscall_user_buffer *sbuf,
 			    unsigned long *args, unsigned int *data_size)
 {
+	trace_user_buf_copy syscall_copy = syscall_copy_user;
 	unsigned long size = SYSCALL_FAULT_BUF_SZ - 1;
 	unsigned long mask = sys_data->user_mask;
 	int idx = ffs(mask) - 1;
+	bool array = false;
 	char *ptr;
 	char *buf;
 
···
 	ptr = (char *)args[idx];
 	*data_size = 0;
 
+	/*
+	 * If this system call event has a size argument, use
+	 * it to define how much of user space memory to read,
+	 * and read it as an array and not a string.
+	 */
+	if (sys_data->user_arg_size >= 0) {
+		array = true;
+		size = args[sys_data->user_arg_size];
+		if (size > SYSCALL_FAULT_BUF_SZ - 1)
+			size = SYSCALL_FAULT_BUF_SZ - 1;
+		/* use normal copy_from_user() */
+		syscall_copy = NULL;
+	}
+
 	buf = trace_user_fault_read(&sbuf->buf, ptr, size,
-				    syscall_copy_user, &size);
+				    syscall_copy, &size);
 	if (!buf)
 		return NULL;
 
-	/* Replace any non-printable characters with '.' */
-	for (int i = 0; i < size; i++) {
-		if (!isprint(buf[i]))
-			buf[i] = '.';
-	}
+	/* For strings, replace any non-printable characters with '.' */
+	if (!array) {
+		for (int i = 0; i < size; i++) {
+			if (!isprint(buf[i]))
+				buf[i] = '.';
+		}
 
-	/*
-	 * If the text was truncated due to our max limit, add "..." to
-	 * the string.
-	 */
-	if (size > SYSCALL_FAULT_BUF_SZ - sizeof(EXTRA)) {
-		strscpy(buf + SYSCALL_FAULT_BUF_SZ - sizeof(EXTRA),
-			EXTRA, sizeof(EXTRA));
-		size = SYSCALL_FAULT_BUF_SZ;
-	} else {
-		buf[size++] = '\0';
+		/*
+		 * If the text was truncated due to our max limit, add "..." to
+		 * the string.
+		 */
+		if (size > SYSCALL_FAULT_BUF_SZ - sizeof(EXTRA)) {
+			strscpy(buf + SYSCALL_FAULT_BUF_SZ - sizeof(EXTRA),
+				EXTRA, sizeof(EXTRA));
+			size = SYSCALL_FAULT_BUF_SZ;
+		} else {
+			buf[size++] = '\0';
+		}
 	}
 
 	*data_size = size;
···
 
 static void syscall_put_data(struct syscall_metadata *sys_data,
 			     struct syscall_trace_enter *entry,
-			     char *buffer, int size)
+			     char *buffer, int size, int user_size)
 {
 	void *ptr;
 	int val;
···
 	val  = (ptr - (void *)entry) + 4;
 
 	/* Store the offset and the size into the meta data */
-	*(int *)ptr = val | (size << 16);
+	*(int *)ptr = val | (user_size << 16);
+
+	if (WARN_ON_ONCE((ptr - (void *)entry + user_size) > size))
+		user_size = 0;
 
 	/* Nothing to do if the user space was empty or faulted */
-	if (size) {
+	if (user_size) {
 		/* Now store the user space data into the event */
 		ptr += 4;
-		memcpy(ptr, buffer, size);
+		memcpy(ptr, buffer, user_size);
 	}
 }
 
···
 	memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	if (mayfault)
-		syscall_put_data(sys_data, entry, user_ptr, user_size);
+		syscall_put_data(sys_data, entry, user_ptr, size, user_size);
 
 	trace_event_buffer_commit(&fbuffer);
 }
···
 	if (sys_data->enter_event != call)
 		return;
 
+	sys_data->user_arg_size = -1;
+
 	switch (nr) {
+	/* user arg 1 with size arg at 2 */
+	case __NR_write:
+	case __NR_mq_timedsend:
+	case __NR_pwrite64:
+		sys_data->user_mask = BIT(1);
+		sys_data->user_arg_size = 2;
+		break;
 	/* user arg at position 0 */
 #ifdef __NR_access
 	case __NR_access:
···
 	memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	if (mayfault)
-		syscall_put_data(sys_data, rec, user_ptr, user_size);
+		syscall_put_data(sys_data, rec, user_ptr, size, user_size);
 
 	if ((valid_prog_array &&
 	     !perf_call_bpf_enter(sys_data->enter_event, fake_regs, sys_data, rec)) ||