lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20181122003333.592319701@goodmis.org>
Date:   Wed, 21 Nov 2018 19:28:16 -0500
From:   Steven Rostedt <rostedt@...dmis.org>
To:     linux-kernel@...r.kernel.org
Cc:     Linus Torvalds <torvalds@...ux-foundation.org>,
        Ingo Molnar <mingo@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Peter Zijlstra <peterz@...radead.org>,
        linux-arch@...r.kernel.org,
        Joel Fernandes <joel@...lfernandes.org>,
        Masami Hiramatsu <mhiramat@...nel.org>,
        Josh Poimboeuf <jpoimboe@...hat.com>,
        Andy Lutomirski <luto@...nel.org>,
        Frederic Weisbecker <frederic@...nel.org>, stable@...nel.org
Subject: [for-next][PATCH 15/18] function_graph: Use new curr_ret_depth to manage depth instead of
 curr_ret_stack

From: "Steven Rostedt (VMware)" <rostedt@...dmis.org>

Currently, the depth of the ret_stack is determined by curr_ret_stack index.
The issue is that there's a race between setting of the curr_ret_stack and
calling of the callback attached to the return of the function.

Commit 03274a3ffb44 ("tracing/fgraph: Adjust fgraph depth before calling
trace return callback") moved the calling of the callback to after the
setting of the curr_ret_stack, even stating that it was safe to do so, when
in fact, it was the reason there was a barrier() there (yes, I should have
commented that barrier()).

Not only does the curr_ret_stack keep track of the current call graph depth,
it also keeps the ret_stack content from being overwritten by new data.

The function profiler, uses the "subtime" variable of ret_stack structure
and by moving the curr_ret_stack, it allows for interrupts to use the same
structure it was using, corrupting the data, and breaking the profiler.

To fix this, there needs to be two variables to handle the call stack depth
and the pointer to where the ret_stack is being used, as they need to change
at two different locations.

Cc: stable@...nel.org
Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback")
Signed-off-by: Steven Rostedt (VMware) <rostedt@...dmis.org>
---
 include/linux/sched.h                |  1 +
 kernel/trace/ftrace.c                |  3 +++
 kernel/trace/trace_functions_graph.c | 21 +++++++++++++--------
 3 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a51c13c2b1a0..d6183a55e8eb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1116,6 +1116,7 @@ struct task_struct {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	/* Index of current stored address in ret_stack: */
 	int				curr_ret_stack;
+	int				curr_ret_depth;
 
 	/* Stack of return addresses for return function tracing: */
 	struct ftrace_ret_stack		*ret_stack;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f536f601bd46..48513954713c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6814,6 +6814,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 			atomic_set(&t->tracing_graph_pause, 0);
 			atomic_set(&t->trace_overrun, 0);
 			t->curr_ret_stack = -1;
+			t->curr_ret_depth = -1;
 			/* Make sure the tasks see the -1 first: */
 			smp_wmb();
 			t->ret_stack = ret_stack_list[start++];
@@ -7038,6 +7039,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
 void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
 {
 	t->curr_ret_stack = -1;
+	t->curr_ret_depth = -1;
 	/*
 	 * The idle task has no parent, it either has its own
 	 * stack or no stack at all.
@@ -7068,6 +7070,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 	/* Make sure we do not use the parent ret_stack */
 	t->ret_stack = NULL;
 	t->curr_ret_stack = -1;
+	t->curr_ret_depth = -1;
 
 	if (ftrace_graph_active) {
 		struct ftrace_ret_stack *ret_stack;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 88ca787a1cdc..02d4081a7f5a 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/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.*/
 static int
-ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
+ftrace_push_return_trace(unsigned long ret, unsigned long func,
 			 unsigned long frame_pointer, unsigned long *retp)
 {
 	unsigned long long calltime;
@@ -177,8 +177,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
 #ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 	current->ret_stack[index].retp = retp;
 #endif
-	*depth = current->curr_ret_stack;
-
 	return 0;
 }
 
@@ -188,14 +186,20 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	struct ftrace_graph_ent trace;
 
 	trace.func = func;
-	trace.depth = current->curr_ret_stack + 1;
+	trace.depth = ++current->curr_ret_depth;
 
 	/* Only trace if the calling function expects to */
 	if (!ftrace_graph_entry(&trace))
-		return -EBUSY;
+		goto out;
 
-	return ftrace_push_return_trace(ret, func, &trace.depth,
-					frame_pointer, retp);
+	if (ftrace_push_return_trace(ret, func,
+				     frame_pointer, retp))
+		goto out;
+
+	return 0;
+ out:
+	current->curr_ret_depth--;
+	return -EBUSY;
 }
 
 /* Retrieve a function return address to the trace stack on thread info.*/
@@ -257,7 +261,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 	trace->func = current->ret_stack[index].func;
 	trace->calltime = current->ret_stack[index].calltime;
 	trace->overrun = atomic_read(&current->trace_overrun);
-	trace->depth = index;
+	trace->depth = current->curr_ret_depth;
 }
 
 /*
@@ -273,6 +277,7 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 	trace.rettime = trace_clock_local();
 	barrier();
 	current->curr_ret_stack--;
+	current->curr_ret_depth--;
 	/*
 	 * The curr_ret_stack can be less than -1 only if it was
 	 * filtered out and it's about to return from the function.
-- 
2.19.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ