[PATCH 1/2] x86/dumpstack: Fix partial register dumps

[Josh Poimboeuf]

The show_regs_safe() logic is wrong.  When there's an iret stack frame,
it prints the entire pt_regs -- most of which is random stack data --
instead of just the five registers at the end.

show_regs_safe() is also poorly named: the on_stack() checks aren't for
safety.  Rename the function to show_regs_if_on_stack() and add a
comment to explain why the checks are needed.

These issues were introduced with the "partial register dump" feature of
the following commit:

  b02fcf9ba121 ("x86/unwinder: Handle stack overflows more gracefully")

That patch had gone through a few iterations of development, and the
above issues were artifacts from a previous iteration of the patch where
'regs' pointed directly to the iret frame rather than to the (partially
empty) pt_regs.

Tested-by: Alexander Tsoy <alexander@xxxxxxx>
Fixes: b02fcf9ba121 ("x86/unwinder: Handle stack overflows more gracefully")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
---
 arch/x86/include/asm/unwind.h | 17 +++++++++++++----
 arch/x86/kernel/dumpstack.c   | 28 ++++++++++++++++++++--------
 arch/x86/kernel/stacktrace.c  |  2 +-
 3 files changed, 34 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index c1688c2d0a12..1f86e1b0a5cd 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -56,18 +56,27 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
 
 #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
 /*
- * WARNING: The entire pt_regs may not be safe to dereference.  In some cases,
- * only the iret frame registers are accessible.  Use with caution!
+ * If 'partial' returns true, only the iret frame registers are valid.
  */
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state,
+						    bool *partial)
 {
 	if (unwind_done(state))
 		return NULL;
 
+	if (partial) {
+#ifdef CONFIG_UNWINDER_ORC
+		*partial = !state->full_regs;
+#else
+		*partial = false;
+#endif
+	}
+
 	return state->regs;
 }
 #else
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state,
+						    bool *partial)
 {
 	return NULL;
 }
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 36b17e0febe8..e4c2c73bd99e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -76,12 +76,23 @@ void show_iret_regs(struct pt_regs *regs)
 		regs->sp, regs->flags);
 }
 
-static void show_regs_safe(struct stack_info *info, struct pt_regs *regs)
+static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
+				  bool partial)
 {
-	if (on_stack(info, regs, sizeof(*regs)))
+	/*
+	 * These on_stack() checks aren't strictly necessary: the unwind code
+	 * has already validated the 'regs' pointer.  The checks are done for
+	 * ordering reasons: if the registers are on the next stack, we don't
+	 * want to print them out yet.  Otherwise they'll be shown as part of
+	 * the wrong stack.  Later, when show_trace_log_lvl() switches to the
+	 * next stack, this function will be called again with the same regs so
+	 * they can be printed in the right context.
+	 */
+	if (!partial && on_stack(info, regs, sizeof(*regs))) {
 		__show_regs(regs, 0);
-	else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
-			  IRET_FRAME_SIZE)) {
+
+	} else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
+				       IRET_FRAME_SIZE)) {
 		/*
 		 * When an interrupt or exception occurs in entry code, the
 		 * full pt_regs might not have been saved yet.  In that case
@@ -98,6 +109,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	struct stack_info stack_info = {0};
 	unsigned long visit_mask = 0;
 	int graph_idx = 0;
+	bool partial;
 
 	printk("%sCall Trace:\n", log_lvl);
 
@@ -140,7 +152,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			printk("%s <%s>\n", log_lvl, stack_name);
 
 		if (regs)
-			show_regs_safe(&stack_info, regs);
+			show_regs_if_on_stack(&stack_info, regs, partial);
 
 		/*
 		 * Scan the stack, printing any text addresses we find.  At the
@@ -164,7 +176,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 
 			/*
 			 * Don't print regs->ip again if it was already printed
-			 * by show_regs_safe() below.
+			 * by show_regs_if_on_stack().
 			 */
 			if (regs && stack == &regs->ip)
 				goto next;
@@ -199,9 +211,9 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unwind_next_frame(&state);
 
 			/* if the frame has entry regs, print them */
-			regs = unwind_get_entry_regs(&state);
+			regs = unwind_get_entry_regs(&state, &partial);
 			if (regs)
-				show_regs_safe(&stack_info, regs);
+				show_regs_if_on_stack(&stack_info, regs, partial);
 		}
 
 		if (stack_name)
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 77835bc021c7..7dd0d2a0d142 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -102,7 +102,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
 	     unwind_next_frame(&state)) {
 
-		regs = unwind_get_entry_regs(&state);
+		regs = unwind_get_entry_regs(&state, NULL);
 		if (regs) {
 			/*
 			 * Kernel mode registers on the stack indicate an
-- 
2.13.6