summaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_stack.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-04-29 13:55:38 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-04-29 13:55:38 -0700
commit9e8529afc4518f4e5d610001545ebc97e1333c79 (patch)
tree26e1aa2cbb50f3f511cfa7d8e39e6b7bd9221b68 /kernel/trace/trace_stack.c
parentec25e246b94a3233ab064994ef05a170bdba0e7c (diff)
parent4c69e6ea415a35eb7f0fc8ee9390c8f7436492a2 (diff)
downloadop-kernel-dev-9e8529afc4518f4e5d610001545ebc97e1333c79.zip
op-kernel-dev-9e8529afc4518f4e5d610001545ebc97e1333c79.tar.gz
Merge tag 'trace-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing updates from Steven Rostedt: "Along with the usual minor fixes and clean ups there are a few major changes with this pull request. 1) Multiple buffers for the ftrace facility This feature has been requested by many people over the last few years. I even heard that Google was about to implement it themselves. I finally had time and cleaned up the code such that you can now create multiple instances of the ftrace buffer and have different events go to different buffers. This way, a low frequency event will not be lost in the noise of a high frequency event. Note, currently only events can go to different buffers, the tracers (ie function, function_graph and the latency tracers) still can only be written to the main buffer. 2) The function tracer triggers have now been extended. The function tracer had two triggers. One to enable tracing when a function is hit, and one to disable tracing. Now you can record a stack trace on a single (or many) function(s), take a snapshot of the buffer (copy it to the snapshot buffer), and you can enable or disable an event to be traced when a function is hit. 3) A perf clock has been added. A "perf" clock can be chosen to be used when tracing. This will cause ftrace to use the same clock as perf uses, and hopefully this will make it easier to interleave the perf and ftrace data for analysis." * tag 'trace-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (82 commits) tracepoints: Prevent null probe from being added tracing: Compare to 1 instead of zero for is_signed_type() tracing: Remove obsolete macro guard _TRACE_PROFILE_INIT ftrace: Get rid of ftrace_profile_bits tracing: Check return value of tracing_init_dentry() tracing: Get rid of unneeded key calculation in ftrace_hash_move() tracing: Reset ftrace_graph_filter_enabled if count is zero tracing: Fix off-by-one on allocating stat->pages kernel: tracing: Use strlcpy instead of strncpy tracing: Update debugfs README file tracing: Fix ftrace_dump() tracing: Rename trace_event_mutex to trace_event_sem tracing: Fix comment about prefix in arch_syscall_match_sym_name() tracing: Convert trace_destroy_fields() to static tracing: Move find_event_field() into trace_events.c tracing: Use TRACE_MAX_PRINT instead of constant tracing: Use pr_warn_once instead of open coded implementation ring-buffer: Add ring buffer startup selftest tracing: Bring Documentation/trace/ftrace.txt up to date tracing: Add "perf" trace_clock ... Conflicts: kernel/trace/ftrace.c kernel/trace/trace.c
Diffstat (limited to 'kernel/trace/trace_stack.c')
-rw-r--r--kernel/trace/trace_stack.c76
1 files changed, 69 insertions, 7 deletions
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 83a8b5b..b20428c 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -20,13 +20,24 @@
#define STACK_TRACE_ENTRIES 500
+#ifdef CC_USING_FENTRY
+# define fentry 1
+#else
+# define fentry 0
+#endif
+
static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
{ [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
+/*
+ * Reserve one entry for the passed in ip. This will allow
+ * us to remove most or all of the stack size overhead
+ * added by the stack tracer itself.
+ */
static struct stack_trace max_stack_trace = {
- .max_entries = STACK_TRACE_ENTRIES,
- .entries = stack_dump_trace,
+ .max_entries = STACK_TRACE_ENTRIES - 1,
+ .entries = &stack_dump_trace[1],
};
static unsigned long max_stack_size;
@@ -39,25 +50,34 @@ static DEFINE_MUTEX(stack_sysctl_mutex);
int stack_tracer_enabled;
static int last_stack_tracer_enabled;
-static inline void check_stack(void)
+static inline void
+check_stack(unsigned long ip, unsigned long *stack)
{
unsigned long this_size, flags;
unsigned long *p, *top, *start;
+ static int tracer_frame;
+ int frame_size = ACCESS_ONCE(tracer_frame);
int i;
- this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+ this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
this_size = THREAD_SIZE - this_size;
+ /* Remove the frame of the tracer */
+ this_size -= frame_size;
if (this_size <= max_stack_size)
return;
/* we do not handle interrupt stacks yet */
- if (!object_is_on_stack(&this_size))
+ if (!object_is_on_stack(stack))
return;
local_irq_save(flags);
arch_spin_lock(&max_stack_lock);
+ /* In case another CPU set the tracer_frame on us */
+ if (unlikely(!frame_size))
+ this_size -= tracer_frame;
+
/* a race could have already updated it */
if (this_size <= max_stack_size)
goto out;
@@ -70,10 +90,18 @@ static inline void check_stack(void)
save_stack_trace(&max_stack_trace);
/*
+ * Add the passed in ip from the function tracer.
+ * Searching for this on the stack will skip over
+ * most of the overhead from the stack tracer itself.
+ */
+ stack_dump_trace[0] = ip;
+ max_stack_trace.nr_entries++;
+
+ /*
* Now find where in the stack these are.
*/
i = 0;
- start = &this_size;
+ start = stack;
top = (unsigned long *)
(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
@@ -97,6 +125,18 @@ static inline void check_stack(void)
found = 1;
/* Start the search from here */
start = p + 1;
+ /*
+ * We do not want to show the overhead
+ * of the stack tracer stack in the
+ * max stack. If we haven't figured
+ * out what that is, then figure it out
+ * now.
+ */
+ if (unlikely(!tracer_frame) && i == 1) {
+ tracer_frame = (p - stack) *
+ sizeof(unsigned long);
+ max_stack_size -= tracer_frame;
+ }
}
}
@@ -113,6 +153,7 @@ static void
stack_trace_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
{
+ unsigned long stack;
int cpu;
preempt_disable_notrace();
@@ -122,7 +163,26 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
if (per_cpu(trace_active, cpu)++ != 0)
goto out;
- check_stack();
+ /*
+ * When fentry is used, the traced function does not get
+ * its stack frame set up, and we lose the parent.
+ * The ip is pretty useless because the function tracer
+ * was called before that function set up its stack frame.
+ * In this case, we use the parent ip.
+ *
+ * By adding the return address of either the parent ip
+ * or the current ip we can disregard most of the stack usage
+ * caused by the stack tracer itself.
+ *
+ * The function tracer always reports the address of where the
+ * mcount call was, but the stack will hold the return address.
+ */
+ if (fentry)
+ ip = parent_ip;
+ else
+ ip += MCOUNT_INSN_SIZE;
+
+ check_stack(ip, &stack);
out:
per_cpu(trace_active, cpu)--;
@@ -371,6 +431,8 @@ static __init int stack_trace_init(void)
struct dentry *d_tracer;
d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
trace_create_file("stack_max_size", 0644, d_tracer,
&max_stack_size, &stack_max_size_fops);
OpenPOWER on IntegriCloud