tracing: add support for userspace stacktraces in tracing/iter_ctrl

Impact: add new (default-off) tracing visualization feature

Usage example:

 mount -t debugfs nodev /sys/kernel/debug
 cd /sys/kernel/debug/tracing
 echo userstacktrace >iter_ctrl
 echo sched_switch >current_tracer
 echo 1 >tracing_enabled
 .... run application ...
 echo 0 >tracing_enabled

Then read one of 'trace','latency_trace','trace_pipe'.

To get the best output you can compile your userspace programs with
frame pointers (at least glibc + the app you are tracing).
Signed-off-by: NTörök Edwin <edwintorok@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Documentation/ftrace.txt

@@ -324,7 +324,7 @@ output. To see what is available, simply cat the file:
 
   cat /debug/tracing/trace_options
   print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
- noblock nostacktrace nosched-tree
+ noblock nostacktrace nosched-tree nouserstacktrace
 
 To disable one of the options, echo in the option prepended with "no".
 
@@ -378,6 +378,9 @@ Here are the available options:
 		When a trace is recorded, so is the stack of functions.
 		This allows for back traces of trace sites.
 
+  userstacktrace - This option changes the trace.
+		   It records a stacktrace of the current userspace thread.
+
   sched-tree - TBD (any users??)
 
 

arch/x86/kernel/stacktrace.c

@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <asm/stacktrace.h>
 
 static void save_stack_warning(void *data, char *msg)
@@ -83,3 +84,59 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
+
+struct stack_frame {
+	const void __user	*next_fp;
+	unsigned long		return_address;
+};
+
+static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+{
+	int ret;
+
+	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
+		return 0;
+
+	ret = 1;
+	pagefault_disable();
+	if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
+		ret = 0;
+	pagefault_enable();
+
+	return ret;
+}
+
+void save_stack_trace_user(struct stack_trace *trace)
+{
+	/*
+	 * Trace user stack if we are not a kernel thread
+	 */
+	if (current->mm) {
+		const struct pt_regs *regs = task_pt_regs(current);
+		const void __user *fp = (const void __user *)regs->bp;
+
+		if (trace->nr_entries < trace->max_entries)
+			trace->entries[trace->nr_entries++] = regs->ip;
+
+		while (trace->nr_entries < trace->max_entries) {
+			struct stack_frame frame;
+			frame.next_fp = NULL;
+			frame.return_address = 0;
+			if (!copy_stack_frame(fp, &frame))
+				break;
+			if ((unsigned long)fp < regs->sp)
+				break;
+			if (frame.return_address)
+				trace->entries[trace->nr_entries++] =
+					frame.return_address;
+			if (fp == frame.next_fp)
+				break;
+			fp = frame.next_fp;
+		}
+	}
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+

include/linux/stacktrace.h

@@ -15,9 +15,17 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
+
+#ifdef CONFIG_X86
+extern void save_stack_trace_user(struct stack_trace *trace);
+#else
+# define save_stack_trace_user(trace)              do { } while (0)
+#endif
+
 #else
 # define save_stack_trace(trace)			do { } while (0)
 # define save_stack_trace_tsk(tsk, trace)		do { } while (0)
+# define save_stack_trace_user(trace)              do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
 #endif
 

kernel/trace/trace.c

@@ -275,6 +275,7 @@ static const char *trace_options[] = {
 	"ftrace_preempt",
 	"branch",
 	"annotate",
+	"userstacktrace",
 	NULL
 };
 
@@ -918,6 +919,44 @@ void __trace_stack(struct trace_array *tr,
 	ftrace_trace_stack(tr, data, flags, skip, preempt_count());
 }
 
+static void ftrace_trace_userstack(struct trace_array *tr,
+		   struct trace_array_cpu *data,
+		   unsigned long flags, int pc)
+{
+	struct userstack_entry *entry;
+	struct stack_trace trace;
+	struct ring_buffer_event *event;
+	unsigned long irq_flags;
+
+	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
+		return;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, flags, pc);
+	entry->ent.type		= TRACE_USER_STACK;
+
+	memset(&entry->caller, 0, sizeof(entry->caller));
+
+	trace.nr_entries	= 0;
+	trace.max_entries	= FTRACE_STACK_ENTRIES;
+	trace.skip		= 0;
+	trace.entries		= entry->caller;
+
+	save_stack_trace_user(&trace);
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+}
+
+void __trace_userstack(struct trace_array *tr,
+		   struct trace_array_cpu *data,
+		   unsigned long flags)
+{
+	ftrace_trace_userstack(tr, data, flags, preempt_count());
+}
+
 static void
 ftrace_trace_special(void *__tr, void *__data,
 		     unsigned long arg1, unsigned long arg2, unsigned long arg3,
@@ -941,6 +980,7 @@ ftrace_trace_special(void *__tr, void *__data,
 	entry->arg3			= arg3;
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, irq_flags, 4, pc);
+	ftrace_trace_userstack(tr, data, irq_flags, pc);
 
 	trace_wake_up();
 }
@@ -979,6 +1019,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_cpu	= task_cpu(next);
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, flags, 5, pc);
+	ftrace_trace_userstack(tr, data, flags, pc);
 }
 
 void
@@ -1008,6 +1049,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_cpu			= task_cpu(wakee);
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, flags, 6, pc);
+	ftrace_trace_userstack(tr, data, flags, pc);
 
 	trace_wake_up();
 }
@@ -1387,6 +1429,31 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 	return ret;
 }
 
+static int
+seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
+		unsigned long sym_flags)
+{
+	int ret = 1;
+	unsigned i;
+
+	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+		unsigned long ip = entry->caller[i];
+
+		if (ip == ULONG_MAX || !ret)
+			break;
+		if (i)
+			ret = trace_seq_puts(s, " <- ");
+		if (!ip) {
+			ret = trace_seq_puts(s, "??");
+			continue;
+		}
+		if (ret /*&& (sym_flags & TRACE_ITER_SYM_ADDR)*/)
+			ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+	}
+
+	return ret;
+}
+
 static void print_lat_help_header(struct seq_file *m)
 {
 	seq_puts(m, "#                  _------=> CPU#            \n");
@@ -1702,6 +1769,16 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 				 field->line);
 		break;
 	}
+	case TRACE_USER_STACK: {
+		struct userstack_entry *field;
+
+		trace_assign_type(field, entry);
+
+		seq_print_userip_objs(field, s, sym_flags);
+		if (entry->flags & TRACE_FLAG_CONT)
+			trace_seq_print_cont(s, iter);
+		break;
+	}
 	default:
 		trace_seq_printf(s, "Unknown type %d\n", entry->type);
 	}
@@ -1853,6 +1930,19 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 				 field->line);
 		break;
 	}
+	case TRACE_USER_STACK: {
+		struct userstack_entry *field;
+
+		trace_assign_type(field, entry);
+
+		ret = seq_print_userip_objs(field, s, sym_flags);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		ret = trace_seq_putc(s, '\n');
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		break;
+	}
 	}
 	return TRACE_TYPE_HANDLED;
 }
@@ -1912,6 +2002,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 
@@ -2000,6 +2091,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 
@@ -2054,6 +2146,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 

kernel/trace/trace.h

@@ -26,6 +26,7 @@ enum trace_type {
 	TRACE_BOOT_CALL,
 	TRACE_BOOT_RET,
 	TRACE_FN_RET,
+	TRACE_USER_STACK,
 
 	__TRACE_LAST_TYPE
 };
@@ -42,6 +43,7 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
+	int			tgid;
 };
 
 /*
@@ -99,6 +101,11 @@ struct stack_entry {
 	unsigned long		caller[FTRACE_STACK_ENTRIES];
 };
 
+struct userstack_entry {
+	struct trace_entry	ent;
+	unsigned long		caller[FTRACE_STACK_ENTRIES];
+};
+
 /*
  * ftrace_printk entry:
  */
@@ -240,6 +247,7 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct ctx_switch_entry, 0);	\
 		IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
 		IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK);	\
+		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
 		IF_ASSIGN(var, ent, struct special_entry, 0);		\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
@@ -500,6 +508,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_PREEMPTONLY		= 0x800,
 	TRACE_ITER_BRANCH		= 0x1000,
 	TRACE_ITER_ANNOTATE		= 0x2000,
+	TRACE_ITER_USERSTACKTRACE       = 0x4000
 };
 
 /*