Merge branch 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  tracing/documentation: Cover new frame pointer semantics
  tracing/documentation: Fix a typo in ftrace.txt
  ring-buffer: Check for end of page in iterator
  ring-buffer: Check if ring buffer iterator has stale data
  tracing: Prevent kernel oops with corrupted buffer

5 files changed, 51 insertions, 10 deletions

diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt
index 239f14b2b55a..6a5a579126b0 100644
--- a/Documentation/trace/ftrace-design.txt
+++ b/Documentation/trace/ftrace-design.txt
@@ -1,5 +1,6 @@
                 function tracer guts
                 ====================
+                By Mike Frysinger
 
 Introduction
 ------------
@@ -173,14 +174,16 @@ void ftrace_graph_caller(void)
 
         unsigned long *frompc = &...;
         unsigned long selfpc = <return address> - MCOUNT_INSN_SIZE;
-        prepare_ftrace_return(frompc, selfpc);
+        /* passing frame pointer up is optional -- see below */
+        prepare_ftrace_return(frompc, selfpc, frame_pointer);
 
         /* restore all state needed by the ABI */
 }
 #endif
 
-For information on how to implement prepare_ftrace_return(), simply look at
-the x86 version.  The only architecture-specific piece in it is the setup of
+For information on how to implement prepare_ftrace_return(), simply look at the
+x86 version (the frame pointer passing is optional; see the next section for
+more information).  The only architecture-specific piece in it is the setup of
 the fault recovery table (the asm(...) code).  The rest should be the same
 across architectures.
 
@@ -205,6 +208,23 @@ void return_to_handler(void)
 #endif
 
 
+HAVE_FUNCTION_GRAPH_FP_TEST
+---------------------------
+
+An arch may pass in a unique value (frame pointer) to both the entering and
+exiting of a function.  On exit, the value is compared and if it does not
+match, then it will panic the kernel.  This is largely a sanity check for bad
+code generation with gcc.  If gcc for your port sanely updates the frame
+pointer under different opitmization levels, then ignore this option.
+
+However, adding support for it isn't terribly difficult.  In your assembly code
+that calls prepare_ftrace_return(), pass the frame pointer as the 3rd argument.
+Then in the C version of that function, do what the x86 port does and pass it
+along to ftrace_push_return_trace() instead of a stub value of 0.
+
+Similarly, when you call ftrace_return_to_handler(), pass it the frame pointer.
+
+
 HAVE_FTRACE_NMI_ENTER
 ---------------------
 
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 8179692fbb90..bab3040da548 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -1625,7 +1625,7 @@ If I am only interested in sys_nanosleep and hrtimer_interrupt:
 
  # echo sys_nanosleep hrtimer_interrupt \
                 > set_ftrace_filter
- # echo ftrace > current_tracer
+ # echo function > current_tracer
  # echo 1 > tracing_enabled
  # usleep 1
  # echo 0 > tracing_enabled
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 6c22d8a2f289..60e2ce0181ee 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -27,9 +27,7 @@ config HAVE_FUNCTION_GRAPH_TRACER
 config HAVE_FUNCTION_GRAPH_FP_TEST
         bool
         help
-         An arch may pass in a unique value (frame pointer) to both the
-         entering and exiting of a function. On exit, the value is compared
-         and if it does not match, then it will panic the kernel.
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
         bool
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index edefe3b2801b..8c1b2d290718 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -464,6 +464,8 @@ struct ring_buffer_iter {
         struct ring_buffer_per_cpu      *cpu_buffer;
         unsigned long                   head;
         struct buffer_page              *head_page;
+        struct buffer_page              *cache_reader_page;
+        unsigned long                   cache_read;
         u64                             read_stamp;
 };
 
@@ -2716,6 +2718,8 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
                 iter->read_stamp = cpu_buffer->read_stamp;
         else
                 iter->read_stamp = iter->head_page->page->time_stamp;
+        iter->cache_reader_page = cpu_buffer->reader_page;
+        iter->cache_read = cpu_buffer->read;
 }
 
 /**
@@ -3060,13 +3064,22 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         struct ring_buffer_event *event;
         int nr_loops = 0;
 
-        if (ring_buffer_iter_empty(iter))
-                return NULL;
-
         cpu_buffer = iter->cpu_buffer;
         buffer = cpu_buffer->buffer;
 
+        /*
+         * Check if someone performed a consuming read to
+         * the buffer. A consuming read invalidates the iterator
+         * and we need to reset the iterator in this case.
+         */
+        if (unlikely(iter->cache_read != cpu_buffer->read ||
+                     iter->cache_reader_page != cpu_buffer->reader_page))
+                rb_iter_reset(iter);
+
  again:
+        if (ring_buffer_iter_empty(iter))
+                return NULL;
+
         /*
          * We repeat when a timestamp is encountered.
          * We can get multiple timestamps by nested interrupts or also
@@ -3081,6 +3094,11 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         if (rb_per_cpu_empty(cpu_buffer))
                 return NULL;
 
+        if (iter->head >= local_read(&iter->head_page->page->commit)) {
+                rb_inc_iter(iter);
+                goto again;
+        }
+
         event = rb_iter_head_event(iter);
 
         switch (event->type_len) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0df1b0f2cb9e..eac6875cb990 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -951,6 +951,11 @@ void trace_find_cmdline(int pid, char comm[])
                 return;
         }
 
+        if (WARN_ON_ONCE(pid < 0)) {
+                strcpy(comm, "<XXX>");
+                return;
+        }
+
         if (pid > PID_MAX_DEFAULT) {
                 strcpy(comm, "<...>");
                 return;