ftrace: Add return address pointer to ftrace_ret_stack

Storing this value will help prevent unwinders from getting out of sync
with the function graph tracer ret_stack.  Now instead of needing a
stateful iterator, they can compare the return address pointer to find
the right ret_stack entry.

Note that an array of 50 ftrace_ret_stack structs is allocated for every
task.  So when an arch implements this, it will add either 200 or 400
bytes of memory usage per task (depending on whether it's a 32-bit or
64-bit platform).

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nilay Vaish <nilayvaish@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a95cfcc39e8f26b89a430c56926af0bb217bc0a1.1471607358.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/trace/ftrace-design.txt

@@ -203,6 +203,17 @@ 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_FUNCTION_GRAPH_RET_ADDR_PTR
+--------------------------------
+
+An arch may pass in a pointer to the return address on the stack.  This
+prevents potential stack unwinding issues where the unwinder gets out of
+sync with ret_stack and the wrong addresses are reported by
+ftrace_graph_ret_addr().
+
+Adding support for it is easy: just define the macro in asm/ftrace.h and
+pass the return address pointer as the 'retp' argument to
+ftrace_push_return_trace().
 
 HAVE_FTRACE_NMI_ENTER
 ---------------------

arch/arm/kernel/ftrace.c

@@ -218,7 +218,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	}
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
-				       frame_pointer);
+				       frame_pointer, NULL);
 	if (err == -EBUSY) {
 		*parent = old;
 		return;

arch/arm64/kernel/ftrace.c

@@ -138,7 +138,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 		return;
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
-				       frame_pointer);
+				       frame_pointer, NULL);
 	if (err == -EBUSY)
 		return;
 	else

arch/blackfin/kernel/ftrace.c

@@ -107,7 +107,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 		return;
 
 	if (ftrace_push_return_trace(*parent, self_addr, &trace.depth,
-	                             frame_pointer) == -EBUSY)
+				     frame_pointer, NULL) == -EBUSY)
 		return;
 
 	trace.func = self_addr;

arch/microblaze/kernel/ftrace.c

@@ -63,7 +63,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0);
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL);
 	if (err == -EBUSY) {
 		*parent = old;
 		return;

arch/mips/kernel/ftrace.c

@@ -382,8 +382,8 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra,
 	if (unlikely(faulted))
 		goto out;
 
-	if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp)
+	if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp,
-	    == -EBUSY) {
+				     NULL) == -EBUSY) {
 		*parent_ra_addr = old_parent_ra;
 		return;
 	}

arch/parisc/kernel/ftrace.c

@@ -48,7 +48,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent,
 		return;
 
         if (ftrace_push_return_trace(old, self_addr, &trace.depth,
-			0 ) == -EBUSY)
+				     0, NULL) == -EBUSY)
                 return;
 
 	/* activate parisc_return_to_handler() as return point */

arch/powerpc/kernel/ftrace.c

@@ -593,7 +593,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 	if (!ftrace_graph_entry(&trace))
 		goto out;
 
-	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0,
+				     NULL) == -EBUSY)
 		goto out;
 
 	parent = return_hooker;

arch/s390/kernel/ftrace.c

@@ -209,7 +209,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 	/* Only trace if the calling function expects to. */
 	if (!ftrace_graph_entry(&trace))
 		goto out;
-	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0,
+				     NULL) == -EBUSY)
 		goto out;
 	parent = (unsigned long) return_to_handler;
 out:

arch/sh/kernel/ftrace.c

@@ -382,7 +382,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0);
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL);
 	if (err == -EBUSY) {
 		__raw_writel(old, parent);
 		return;

arch/sparc/kernel/ftrace.c

@@ -131,7 +131,7 @@ unsigned long prepare_ftrace_return(unsigned long parent,
 		return parent + 8UL;
 
 	if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
-				     frame_pointer) == -EBUSY)
+				     frame_pointer, NULL) == -EBUSY)
 		return parent + 8UL;
 
 	trace.func = self_addr;

arch/tile/kernel/ftrace.c

@@ -184,7 +184,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	*parent = return_hooker;
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
-				       frame_pointer);
+				       frame_pointer, NULL);
 	if (err == -EBUSY) {
 		*parent = old;
 		return;

arch/x86/kernel/ftrace.c

@@ -1029,7 +1029,7 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	}
 
 	if (ftrace_push_return_trace(old, self_addr, &trace.depth,
-		    frame_pointer) == -EBUSY) {
+				     frame_pointer, NULL) == -EBUSY) {
 		*parent = old;
 		return;
 	}

include/linux/ftrace.h

@@ -798,6 +798,9 @@ struct ftrace_ret_stack {
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	unsigned long fp;
 #endif
+#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+	unsigned long *retp;
+#endif
 };
 
 /*
@@ -809,7 +812,7 @@ extern void return_to_handler(void);
 
 extern int
 ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
-			 unsigned long frame_pointer);
+			 unsigned long frame_pointer, unsigned long *retp);
 
 /*
  * Sometimes we don't want to trace a function with the function

kernel/trace/trace_functions_graph.c

@@ -119,7 +119,7 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration,
 /* Add a function return address to the trace stack on thread info.*/
 int
 ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
-			 unsigned long frame_pointer)
+			 unsigned long frame_pointer, unsigned long *retp)
 {
 	unsigned long long calltime;
 	int index;
@@ -173,6 +173,9 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
 	current->ret_stack[index].subtime = 0;
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	current->ret_stack[index].fp = frame_pointer;
+#endif
+#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+	current->ret_stack[index].retp = retp;
 #endif
 	*depth = current->curr_ret_stack;