tracing: identify which executable object the userspace address belongs to
Impact: modify+improve the userstacktrace tracing visualization feature
Store thread group leader id, and use it to lookup the address in the
process's map. We could have looked up the address on thread's map,
but the thread might not exist by the time we are called. The process
might not exist either, but if you are reading trace_pipe, that is
unlikely.
Example usage:
mount -t debugfs nodev /sys/kernel/debug
cd /sys/kernel/debug/tracing
echo userstacktrace >iter_ctrl
echo sym-userobj >iter_ctrl
echo sched_switch >current_tracer
echo 1 >tracing_enabled
cat trace_pipe >/tmp/trace&
.... run application ...
echo 0 >tracing_enabled
cat /tmp/trace
You'll see stack entries like:
/lib/libpthread-2.7.so[+0xd370]
You can convert them to function/line using:
addr2line -fie /lib/libpthread-2.7.so 0xd370
Or:
addr2line -fie /usr/lib/debug/libpthread-2.7.so 0xd370
For non-PIC/PIE executables this won't work:
a.out[+0x73b]
You need to run the following: addr2line -fie a.out 0x40073b
(where 0x400000 is the default load address of a.out)
Signed-off-by: Török Edwin <edwintorok@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
index 79a80f7..35a78bc 100644
--- a/Documentation/ftrace.txt
+++ b/Documentation/ftrace.txt
@@ -324,7 +324,7 @@
cat /debug/tracing/trace_options
print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
- noblock nostacktrace nosched-tree nouserstacktrace
+ noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj
To disable one of the options, echo in the option prepended with "no".
@@ -381,6 +381,17 @@
userstacktrace - This option changes the trace.
It records a stacktrace of the current userspace thread.
+ sym-userobj - when user stacktrace are enabled, look up which object the
+ address belongs to, and print a relative address
+ This is especially useful when ASLR is on, otherwise you don't
+ get a chance to resolve the address to object/file/line after the app is no
+ longer running
+
+ The lookup is performed when you read trace,trace_pipe,latency_trace. Example:
+
+ a.out-1623 [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0
+x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
+
sched-tree - TBD (any users??)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ced8b4f..62776b7 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -30,6 +30,7 @@
#include <linux/gfp.h>
#include <linux/fs.h>
#include <linux/kprobes.h>
+#include <linux/seq_file.h>
#include <linux/writeback.h>
#include <linux/stacktrace.h>
@@ -276,6 +277,7 @@
"branch",
"annotate",
"userstacktrace",
+ "sym-userobj",
NULL
};
@@ -422,6 +424,28 @@
return trace_seq_putmem(s, hex, j);
}
+static int
+trace_seq_path(struct trace_seq *s, struct path *path)
+{
+ unsigned char *p;
+
+ if (s->len >= (PAGE_SIZE - 1))
+ return 0;
+ p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
+ if (!IS_ERR(p)) {
+ p = mangle_path(s->buffer + s->len, p, "\n");
+ if (p) {
+ s->len = p - s->buffer;
+ return 1;
+ }
+ } else {
+ s->buffer[s->len++] = '?';
+ return 1;
+ }
+
+ return 0;
+}
+
static void
trace_seq_reset(struct trace_seq *s)
{
@@ -802,6 +826,7 @@
entry->preempt_count = pc & 0xff;
entry->pid = (tsk) ? tsk->pid : 0;
+ entry->tgid = (tsk) ? tsk->tgid : 0;
entry->flags =
#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1429,28 +1454,73 @@
return ret;
}
+static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+ unsigned long ip, unsigned long sym_flags)
+{
+ struct file *file = NULL;
+ unsigned long vmstart = 0;
+ int ret = 1;
+
+ if (mm) {
+ const struct vm_area_struct *vma = find_vma(mm, ip);
+ if (vma) {
+ file = vma->vm_file;
+ vmstart = vma->vm_start;
+ }
+ }
+ if (file) {
+ ret = trace_seq_path(s, &file->f_path);
+ if (ret)
+ ret = trace_seq_printf(s, "[+0x%lx]",
+ ip - vmstart);
+ }
+ if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
+ ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+ return ret;
+}
+
static int
seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
- unsigned long sym_flags)
+ unsigned long sym_flags)
{
+ struct mm_struct *mm = NULL;
int ret = 1;
unsigned i;
+ if (trace_flags & TRACE_ITER_SYM_USEROBJ) {
+ struct task_struct *task;
+ /*
+ * we do the lookup on the thread group leader,
+ * since individual threads might have already quit!
+ */
+ rcu_read_lock();
+ task = find_task_by_vpid(entry->ent.tgid);
+ rcu_read_unlock();
+
+ if (task)
+ mm = get_task_mm(task);
+ }
+
for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
unsigned long ip = entry->caller[i];
if (ip == ULONG_MAX || !ret)
break;
- if (i)
+ if (i && ret)
ret = trace_seq_puts(s, " <- ");
if (!ip) {
- ret = trace_seq_puts(s, "??");
+ if (ret)
+ ret = trace_seq_puts(s, "??");
continue;
}
- if (ret /*&& (sym_flags & TRACE_ITER_SYM_ADDR)*/)
- ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+ if (!ret)
+ break;
+ if (ret)
+ ret = seq_print_user_ip(s, mm, ip, sym_flags);
}
+ if (mm)
+ mmput(mm);
return ret;
}
@@ -1775,8 +1845,7 @@
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);
+ trace_seq_putc(s, '\n');
break;
}
default:
@@ -3581,6 +3650,9 @@
atomic_inc(&global_trace.data[cpu]->disabled);
}
+ /* don't look at user memory in panic mode */
+ trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+
printk(KERN_TRACE "Dumping ftrace buffer:\n");
iter.tr = &global_trace;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 17bb4c8..28c15c2 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -508,7 +508,8 @@
TRACE_ITER_PREEMPTONLY = 0x800,
TRACE_ITER_BRANCH = 0x1000,
TRACE_ITER_ANNOTATE = 0x2000,
- TRACE_ITER_USERSTACKTRACE = 0x4000
+ TRACE_ITER_USERSTACKTRACE = 0x4000,
+ TRACE_ITER_SYM_USEROBJ = 0x8000
};
/*