Merge tag 'trace-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing update from Steven Rostedt:
 "This batch of changes is mostly clean ups and small bug fixes.  The
  only real feature that was added this release is from Namhyung Kim,
  who introduced "set_graph_notrace" filter that lets you run the
  function graph tracer and not trace particular functions and their
  call chain.

  Tom Zanussi added some updates to the ftrace multibuffer tracing that
  made it more consistent with the top level tracing.

  One of the fixes for perf function tracing required an API change in
  RCU; the addition of "rcu_is_watching()".  As Paul McKenney is pushing
  that change in this release too, he gave me a branch that included all
  the changes to get that working, and I pulled that into my tree in
  order to complete the perf function tracing fix"

* tag 'trace-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  tracing: Add rcu annotation for syscall trace descriptors
  tracing: Do not use signed enums with unsigned long long in fgragh output
  tracing: Remove unused function ftrace_off_permanent()
  tracing: Do not assign filp->private_data to freed memory
  tracing: Add helper function tracing_is_disabled()
  tracing: Open tracer when ftrace_dump_on_oops is used
  tracing: Add support for SOFT_DISABLE to syscall events
  tracing: Make register/unregister_ftrace_command __init
  tracing: Update event filters for multibuffer
  recordmcount.pl: Add support for __fentry__
  ftrace: Have control op function callback only trace when RCU is watching
  rcu: Do not trace rcu_is_watching() functions
  ftrace/x86: skip over the breakpoint for ftrace caller
  trace/trace_stat: use rbtree postorder iteration helper instead of opencoding
  ftrace: Add set_graph_notrace filter
  ftrace: Narrow down the protected area of graph_lock
  ftrace: Introduce struct ftrace_graph_data
  ftrace: Get rid of ftrace_graph_filter_enabled
  tracing: Fix potential out-of-bounds in trace_get_user()
  tracing: Show more exact help information about snapshot

1 files changed, 66 insertions, 16 deletions

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index b5c09242683d..0b99120d395c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -82,9 +82,9 @@ static struct trace_array *graph_array;
  * to fill in space into DURATION column.
  */
 enum {
-        DURATION_FILL_FULL  = -1,
-        DURATION_FILL_START = -2,
-        DURATION_FILL_END   = -3,
+        FLAGS_FILL_FULL  = 1 << TRACE_GRAPH_PRINT_FILL_SHIFT,
+        FLAGS_FILL_START = 2 << TRACE_GRAPH_PRINT_FILL_SHIFT,
+        FLAGS_FILL_END   = 3 << TRACE_GRAPH_PRINT_FILL_SHIFT,
 };
 
 static enum print_line_t
@@ -114,16 +114,37 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
                 return -EBUSY;
         }
 
+        /*
+         * The curr_ret_stack is an index to ftrace return stack of
+         * current task.  Its value should be in [0, FTRACE_RETFUNC_
+         * DEPTH) when the function graph tracer is used.  To support
+         * filtering out specific functions, it makes the index
+         * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH)
+         * so when it sees a negative index the ftrace will ignore
+         * the record.  And the index gets recovered when returning
+         * from the filtered function by adding the FTRACE_NOTRACE_
+         * DEPTH and then it'll continue to record functions normally.
+         *
+         * The curr_ret_stack is initialized to -1 and get increased
+         * in this function.  So it can be less than -1 only if it was
+         * filtered out via ftrace_graph_notrace_addr() which can be
+         * set from set_graph_notrace file in debugfs by user.
+         */
+        if (current->curr_ret_stack < -1)
+                return -EBUSY;
+
         calltime = trace_clock_local();
 
         index = ++current->curr_ret_stack;
+        if (ftrace_graph_notrace_addr(func))
+                current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH;
         barrier();
         current->ret_stack[index].ret = ret;
         current->ret_stack[index].func = func;
         current->ret_stack[index].calltime = calltime;
         current->ret_stack[index].subtime = 0;
         current->ret_stack[index].fp = frame_pointer;
-        *depth = index;
+        *depth = current->curr_ret_stack;
 
         return 0;
 }
@@ -137,7 +158,17 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 
         index = current->curr_ret_stack;
 
-        if (unlikely(index < 0)) {
+        /*
+         * A negative index here means that it's just returned from a
+         * notrace'd function.  Recover index to get an original
+         * return address.  See ftrace_push_return_trace().
+         *
+         * TODO: Need to check whether the stack gets corrupted.
+         */
+        if (index < 0)
+                index += FTRACE_NOTRACE_DEPTH;
+
+        if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) {
                 ftrace_graph_stop();
                 WARN_ON(1);
                 /* Might as well panic, otherwise we have no where to go */
@@ -193,6 +224,15 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
         trace.rettime = trace_clock_local();
         barrier();
         current->curr_ret_stack--;
+        /*
+         * The curr_ret_stack can be less than -1 only if it was
+         * filtered out and it's about to return from the function.
+         * Recover the index and continue to trace normal functions.
+         */
+        if (current->curr_ret_stack < -1) {
+                current->curr_ret_stack += FTRACE_NOTRACE_DEPTH;
+                return ret;
+        }
 
         /*
          * The trace should run after decrementing the ret counter
@@ -230,7 +270,7 @@ int __trace_graph_entry(struct trace_array *tr,
                 return 0;
         entry   = ring_buffer_event_data(event);
         entry->graph_ent                        = *trace;
-        if (!filter_current_check_discard(buffer, call, entry, event))
+        if (!call_filter_check_discard(call, entry, buffer, event))
                 __buffer_unlock_commit(buffer, event);
 
         return 1;
@@ -259,10 +299,20 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 
         /* trace it when it is-nested-in or is a function enabled. */
         if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
-             ftrace_graph_ignore_irqs()) ||
+             ftrace_graph_ignore_irqs()) || (trace->depth < 0) ||
             (max_depth && trace->depth >= max_depth))
                 return 0;
 
+        /*
+         * Do not trace a function if it's filtered by set_graph_notrace.
+         * Make the index of ret stack negative to indicate that it should
+         * ignore further functions.  But it needs its own ret stack entry
+         * to recover the original index in order to continue tracing after
+         * returning from the function.
+         */
+        if (ftrace_graph_notrace_addr(trace->func))
+                return 1;
+
         local_irq_save(flags);
         cpu = raw_smp_processor_id();
         data = per_cpu_ptr(tr->trace_buffer.data, cpu);
@@ -335,7 +385,7 @@ void __trace_graph_return(struct trace_array *tr,
                 return;
         entry   = ring_buffer_event_data(event);
         entry->ret                              = *trace;
-        if (!filter_current_check_discard(buffer, call, entry, event))
+        if (!call_filter_check_discard(call, entry, buffer, event))
                 __buffer_unlock_commit(buffer, event);
 }
 
@@ -652,7 +702,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
         }
 
         /* No overhead */
-        ret = print_graph_duration(DURATION_FILL_START, s, flags);
+        ret = print_graph_duration(0, s, flags | FLAGS_FILL_START);
         if (ret != TRACE_TYPE_HANDLED)
                 return ret;
 
@@ -664,7 +714,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
-        ret = print_graph_duration(DURATION_FILL_END, s, flags);
+        ret = print_graph_duration(0, s, flags | FLAGS_FILL_END);
         if (ret != TRACE_TYPE_HANDLED)
                 return ret;
 
@@ -729,14 +779,14 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s,
                         return TRACE_TYPE_HANDLED;
 
         /* No real adata, just filling the column with spaces */
-        switch (duration) {
-        case DURATION_FILL_FULL:
+        switch (flags & TRACE_GRAPH_PRINT_FILL_MASK) {
+        case FLAGS_FILL_FULL:
                 ret = trace_seq_puts(s, "              |  ");
                 return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
-        case DURATION_FILL_START:
+        case FLAGS_FILL_START:
                 ret = trace_seq_puts(s, "  ");
                 return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
-        case DURATION_FILL_END:
+        case FLAGS_FILL_END:
                 ret = trace_seq_puts(s, " |");
                 return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
         }
@@ -852,7 +902,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
         }
 
         /* No time */
-        ret = print_graph_duration(DURATION_FILL_FULL, s, flags);
+        ret = print_graph_duration(0, s, flags | FLAGS_FILL_FULL);
         if (ret != TRACE_TYPE_HANDLED)
                 return ret;
 
@@ -1172,7 +1222,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* No time */
-        ret = print_graph_duration(DURATION_FILL_FULL, s, flags);
+        ret = print_graph_duration(0, s, flags | FLAGS_FILL_FULL);
         if (ret != TRACE_TYPE_HANDLED)
                 return ret;