x86/dumpstack: Add get_stack_info() interface

valid_stack_ptr() is buggy: it assumes that all stacks are of size
THREAD_SIZE, which is not true for exception stacks.  So the
walk_stack() callbacks will need to know the location of the beginning
of the stack as well as the end.

Another issue is that in general the various features of a stack (type,
size, next stack pointer, description string) are scattered around in
various places throughout the stack dump code.

Encapsulate all that information in a single place with a new stack_info
struct and a get_stack_info() interface.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
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: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/8164dd0db96b7e6a279fa17ae5e6dc375eecb4a9.1473905218.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/events/core.c

@@ -2251,7 +2251,7 @@ void arch_perf_update_userpage(struct perf_event *event,
  * callchain support
  */
 
-static int backtrace_stack(void *data, char *name)
+static int backtrace_stack(void *data, const char *name)
 {
 	return 0;
 }

arch/x86/include/asm/stacktrace.h

@@ -10,6 +10,39 @@
 #include <linux/ptrace.h>
 #include <asm/switch_to.h>
 
+enum stack_type {
+	STACK_TYPE_UNKNOWN,
+	STACK_TYPE_TASK,
+	STACK_TYPE_IRQ,
+	STACK_TYPE_SOFTIRQ,
+	STACK_TYPE_EXCEPTION,
+	STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
+};
+
+struct stack_info {
+	enum stack_type type;
+	unsigned long *begin, *end, *next_sp;
+};
+
+bool in_task_stack(unsigned long *stack, struct task_struct *task,
+		   struct stack_info *info);
+
+int get_stack_info(unsigned long *stack, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask);
+
+void stack_type_str(enum stack_type type, const char **begin,
+		    const char **end);
+
+static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
+{
+	void *begin = info->begin;
+	void *end   = info->end;
+
+	return (info->type != STACK_TYPE_UNKNOWN &&
+		addr >= begin && addr < end &&
+		addr + len > begin && addr + len <= end);
+}
+
 extern int kstack_depth_to_print;
 
 struct thread_info;
@@ -20,27 +53,27 @@ typedef unsigned long (*walk_stack_t)(struct task_struct *task,
 				      unsigned long bp,
 				      const struct stacktrace_ops *ops,
 				      void *data,
-				      unsigned long *end,
+				      struct stack_info *info,
 				      int *graph);
 
 extern unsigned long
 print_context_stack(struct task_struct *task,
 		    unsigned long *stack, unsigned long bp,
 		    const struct stacktrace_ops *ops, void *data,
-		    unsigned long *end, int *graph);
+		    struct stack_info *info, int *graph);
 
 extern unsigned long
 print_context_stack_bp(struct task_struct *task,
 		       unsigned long *stack, unsigned long bp,
 		       const struct stacktrace_ops *ops, void *data,
-		       unsigned long *end, int *graph);
+		       struct stack_info *info, int *graph);
 
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {
 	int (*address)(void *data, unsigned long address, int reliable);
 	/* On negative return stop dumping */
-	int (*stack)(void *data, char *name);
+	int (*stack)(void *data, const char *name);
 	walk_stack_t	walk_stack;
 };
 

arch/x86/kernel/dumpstack.c

@@ -25,6 +25,23 @@ unsigned int code_bytes = 64;
 int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
 static int die_counter;
 
+bool in_task_stack(unsigned long *stack, struct task_struct *task,
+		   struct stack_info *info)
+{
+	unsigned long *begin = task_stack_page(task);
+	unsigned long *end   = task_stack_page(task) + THREAD_SIZE;
+
+	if (stack < begin || stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_TASK;
+	info->begin	= begin;
+	info->end	= end;
+	info->next_sp	= NULL;
+
+	return true;
+}
+
 static void printk_stack_address(unsigned long address, int reliable,
 				 char *log_lvl)
 {
@@ -46,24 +63,11 @@ void printk_address(unsigned long address)
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-static inline int valid_stack_ptr(struct task_struct *task,
-			void *p, unsigned int size, void *end)
-{
-	void *t = task_stack_page(task);
-	if (end) {
-		if (p < end && p >= (end-THREAD_SIZE))
-			return 1;
-		else
-			return 0;
-	}
-	return p >= t && p < t + THREAD_SIZE - size;
-}
-
 unsigned long
 print_context_stack(struct task_struct *task,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data,
-		unsigned long *end, int *graph)
+		struct stack_info *info, int *graph)
 {
 	struct stack_frame *frame = (struct stack_frame *)bp;
 
@@ -75,7 +79,7 @@ print_context_stack(struct task_struct *task,
 	    PAGE_SIZE)
 		stack = (unsigned long *)task_stack_page(task);
 
-	while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
+	while (on_stack(info, stack, sizeof(*stack))) {
 		unsigned long addr = *stack;
 
 		if (__kernel_text_address(addr)) {
@@ -114,12 +118,12 @@ unsigned long
 print_context_stack_bp(struct task_struct *task,
 		       unsigned long *stack, unsigned long bp,
 		       const struct stacktrace_ops *ops, void *data,
-		       unsigned long *end, int *graph)
+		       struct stack_info *info, int *graph)
 {
 	struct stack_frame *frame = (struct stack_frame *)bp;
 	unsigned long *retp = &frame->return_address;
 
-	while (valid_stack_ptr(task, retp, sizeof(*retp), end)) {
+	while (on_stack(info, stack, sizeof(*stack) * 2)) {
 		unsigned long addr = *retp;
 		unsigned long real_addr;
 
@@ -138,7 +142,7 @@ print_context_stack_bp(struct task_struct *task,
 }
 EXPORT_SYMBOL_GPL(print_context_stack_bp);
 
-static int print_trace_stack(void *data, char *name)
+static int print_trace_stack(void *data, const char *name)
 {
 	printk("%s <%s> ", (char *)data, name);
 	return 0;

arch/x86/kernel/dumpstack_32.c

@@ -16,61 +16,117 @@
 
 #include <asm/stacktrace.h>
 
-static void *is_irq_stack(void *p, void *irq)
+void stack_type_str(enum stack_type type, const char **begin, const char **end)
 {
-	if (p < irq || p >= (irq + THREAD_SIZE))
+	switch (type) {
-		return NULL;
+	case STACK_TYPE_IRQ:
-	return irq + THREAD_SIZE;
+	case STACK_TYPE_SOFTIRQ:
+		*begin = "IRQ";
+		*end   = "EOI";
+		break;
+	default:
+		*begin = NULL;
+		*end   = NULL;
+	}
 }
 
-
+static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
-static void *is_hardirq_stack(unsigned long *stack)
 {
-	void *irq = this_cpu_read(hardirq_stack);
+	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack);
+	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
-	return is_irq_stack(stack, irq);
+	if (stack < begin || stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_IRQ;
+	info->begin	= begin;
+	info->end	= end;
+
+	/*
+	 * See irq_32.c -- the next stack pointer is stored at the beginning of
+	 * the stack.
+	 */
+	info->next_sp	= (unsigned long *)*begin;
+
+	return true;
 }
 
-static void *is_softirq_stack(unsigned long *stack)
+static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	void *irq = this_cpu_read(softirq_stack);
+	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack);
+	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
-	return is_irq_stack(stack, irq);
+	if (stack < begin || stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_SOFTIRQ;
+	info->begin	= begin;
+	info->end	= end;
+
+	/*
+	 * The next stack pointer is stored at the beginning of the stack.
+	 * See irq_32.c.
+	 */
+	info->next_sp	= (unsigned long *)*begin;
+
+	return true;
+}
+
+int get_stack_info(unsigned long *stack, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask)
+{
+	if (!stack)
+		goto unknown;
+
+	task = task ? : current;
+
+	if (in_task_stack(stack, task, info))
+		return 0;
+
+	if (task != current)
+		goto unknown;
+
+	if (in_hardirq_stack(stack, info))
+		return 0;
+
+	if (in_softirq_stack(stack, info))
+		return 0;
+
+unknown:
+	info->type = STACK_TYPE_UNKNOWN;
+	return -EINVAL;
 }
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
 {
+	unsigned long visit_mask = 0;
 	int graph = 0;
-	u32 *prev_esp;
 
 	task = task ? : current;
 	stack = stack ? : get_stack_pointer(task, regs);
 	bp = bp ? : (unsigned long)get_frame_pointer(task, regs);
 
 	for (;;) {
-		void *end_stack;
+		const char *begin_str, *end_str;
+		struct stack_info info;
 
-		end_stack = is_hardirq_stack(stack);
+		if (get_stack_info(stack, task, &info, &visit_mask))
-		if (!end_stack)
-			end_stack = is_softirq_stack(stack);
-
-		bp = ops->walk_stack(task, stack, bp, ops, data,
-				     end_stack, &graph);
-
-		/* Stop if not on irq stack */
-		if (!end_stack)
 			break;
 
-		/* The previous esp is saved on the bottom of the stack */
+		stack_type_str(info.type, &begin_str, &end_str);
-		prev_esp = (u32 *)(end_stack - THREAD_SIZE);
+
-		stack = (unsigned long *)*prev_esp;
+		if (begin_str && ops->stack(data, begin_str) < 0)
-		if (!stack)
 			break;
 
-		if (ops->stack(data, "IRQ") < 0)
+		bp = ops->walk_stack(task, stack, bp, ops, data, &info, &graph);
+
+		if (end_str && ops->stack(data, end_str) < 0)
 			break;
+
+		stack = info.next_sp;
+
 		touch_nmi_watchdog();
 	}
 }

arch/x86/kernel/dumpstack_64.c

@@ -28,76 +28,109 @@ static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
 	[DEBUG_STACK - 1]			= DEBUG_STKSZ
 };
 
-static unsigned long *in_exception_stack(unsigned long stack, unsigned *usedp,
+void stack_type_str(enum stack_type type, const char **begin, const char **end)
-					 char **idp)
 {
-	unsigned long begin, end;
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+
+	switch (type) {
+	case STACK_TYPE_IRQ:
+		*begin = "IRQ";
+		*end   = "EOI";
+		break;
+	case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST:
+		*begin = exception_stack_names[type - STACK_TYPE_EXCEPTION];
+		*end   = "EOE";
+		break;
+	default:
+		*begin = NULL;
+		*end   = NULL;
+	}
+}
+
+static bool in_exception_stack(unsigned long *stack, struct stack_info *info,
+			       unsigned long *visit_mask)
+{
+	unsigned long *begin, *end;
+	struct pt_regs *regs;
 	unsigned k;
 
 	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
 
 	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
-		end   = raw_cpu_ptr(&orig_ist)->ist[k];
+		end   = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k];
-		begin = end - exception_stack_sizes[k];
+		begin = end - (exception_stack_sizes[k] / sizeof(long));
+		regs  = (struct pt_regs *)end - 1;
 
 		if (stack < begin || stack >= end)
 			continue;
 
 		/*
-		 * Make sure we only iterate through an exception stack once.
+		 * Make sure we don't iterate through an exception stack more
-		 * If it comes up for the second time then there's something
+		 * than once.  If it comes up a second time then there's
-		 * wrong going on - just break and return NULL:
+		 * something wrong going on - just break out and report an
+		 * unknown stack type.
 		 */
-		if (*usedp & (1U << k))
+		if (*visit_mask & (1U << k))
 			break;
-		*usedp |= 1U << k;
+		*visit_mask |= 1U << k;
 
-		*idp = exception_stack_names[k];
+		info->type	= STACK_TYPE_EXCEPTION + k;
-		return (unsigned long *)end;
+		info->begin	= begin;
+		info->end	= end;
+		info->next_sp	= (unsigned long *)regs->sp;
+
+		return true;
 	}
 
-	return NULL;
+	return false;
 }
 
-static inline int
+static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
-in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
-	     unsigned long *irq_stack_end)
 {
-	return (stack >= irq_stack && stack < irq_stack_end);
+	unsigned long *end   = (unsigned long *)this_cpu_read(irq_stack_ptr);
+	unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
+
+	if (stack < begin || stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_IRQ;
+	info->begin	= begin;
+	info->end	= end;
+
+	/*
+	 * The next stack pointer is the first thing pushed by the entry code
+	 * after switching to the irq stack.
+	 */
+	info->next_sp = (unsigned long *)*(end - 1);
+
+	return true;
 }
 
-enum stack_type {
+int get_stack_info(unsigned long *stack, struct task_struct *task,
-	STACK_IS_UNKNOWN,
+		   struct stack_info *info, unsigned long *visit_mask)
-	STACK_IS_NORMAL,
-	STACK_IS_EXCEPTION,
-	STACK_IS_IRQ,
-};
-
-static enum stack_type
-analyze_stack(struct task_struct *task, unsigned long *stack,
-	      unsigned long **stack_end, unsigned long *irq_stack,
-	      unsigned *used, char **id)
 {
-	unsigned long addr;
+	if (!stack)
+		goto unknown;
 
-	addr = ((unsigned long)stack & (~(THREAD_SIZE - 1)));
+	task = task ? : current;
-	if ((unsigned long)task_stack_page(task) == addr)
-		return STACK_IS_NORMAL;
 
-	*stack_end = in_exception_stack((unsigned long)stack, used, id);
+	if (in_task_stack(stack, task, info))
-	if (*stack_end)
+		return 0;
-		return STACK_IS_EXCEPTION;
 
-	if (!irq_stack)
+	if (task != current)
-		return STACK_IS_NORMAL;
+		goto unknown;
 
-	*stack_end = irq_stack;
+	if (in_exception_stack(stack, info, visit_mask))
-	irq_stack -= (IRQ_STACK_SIZE / sizeof(long));
+		return 0;
 
-	if (in_irq_stack(stack, irq_stack, *stack_end))
+	if (in_irq_stack(stack, info))
-		return STACK_IS_IRQ;
+		return 0;
 
-	return STACK_IS_UNKNOWN;
+	return 0;
+
+unknown:
+	info->type = STACK_TYPE_UNKNOWN;
+	return -EINVAL;
 }
 
 /*
@@ -111,8 +144,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
 {
-	unsigned long *irq_stack = (unsigned long *)this_cpu_read(irq_stack_ptr);
+	unsigned long visit_mask = 0;
-	unsigned used = 0;
+	struct stack_info info;
 	int graph = 0;
 	int done = 0;
 
@@ -126,57 +159,37 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	 * exceptions
 	 */
 	while (!done) {
-		unsigned long *stack_end;
+		const char *begin_str, *end_str;
-		enum stack_type stype;
-		char *id;
 
-		stype = analyze_stack(task, stack, &stack_end, irq_stack, &used,
+		get_stack_info(stack, task, &info, &visit_mask);
-				      &id);
 
 		/* Default finish unless specified to continue */
 		done = 1;
 
-		switch (stype) {
+		switch (info.type) {
 
 		/* Break out early if we are on the thread stack */
-		case STACK_IS_NORMAL:
+		case STACK_TYPE_TASK:
 			break;
 
-		case STACK_IS_EXCEPTION:
+		case STACK_TYPE_IRQ:
+		case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST:
 
-			if (ops->stack(data, id) < 0)
+			stack_type_str(info.type, &begin_str, &end_str);
+
+			if (ops->stack(data, begin_str) < 0)
 				break;
 
 			bp = ops->walk_stack(task, stack, bp, ops,
-					     data, stack_end, &graph);
+					     data, &info, &graph);
-			ops->stack(data, "EOE");
+
-			/*
+			ops->stack(data, end_str);
-			 * We link to the next stack via the
+
-			 * second-to-last pointer (index -2 to end) in the
+			stack = info.next_sp;
-			 * exception stack:
-			 */
-			stack = (unsigned long *) stack_end[-2];
 			done = 0;
 			break;
 
-		case STACK_IS_IRQ:
+		default:
-
-			if (ops->stack(data, "IRQ") < 0)
-				break;
-			bp = ops->walk_stack(task, stack, bp,
-				     ops, data, stack_end, &graph);
-			/*
-			 * We link to the next stack (which would be
-			 * the process stack normally) the last
-			 * pointer (index -1 to end) in the IRQ stack:
-			 */
-			stack = (unsigned long *) (stack_end[-1]);
-			irq_stack = NULL;
-			ops->stack(data, "EOI");
-			done = 0;
-			break;
-
-		case STACK_IS_UNKNOWN:
 			ops->stack(data, "UNK");
 			break;
 		}
@@ -185,7 +198,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	/*
 	 * This handles the process stack:
 	 */
-	bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph);
+	bp = ops->walk_stack(task, stack, bp, ops, data, &info, &graph);
 }
 EXPORT_SYMBOL(dump_trace);
 

arch/x86/kernel/stacktrace.c

@@ -9,7 +9,7 @@
 #include <linux/uaccess.h>
 #include <asm/stacktrace.h>
 
-static int save_stack_stack(void *data, char *name)
+static int save_stack_stack(void *data, const char *name)
 {
 	return 0;
 }

arch/x86/oprofile/backtrace.c

@@ -17,7 +17,7 @@
 #include <asm/ptrace.h>
 #include <asm/stacktrace.h>
 
-static int backtrace_stack(void *data, char *name)
+static int backtrace_stack(void *data, const char *name)
 {
 	/* Yes, we want all stacks */
 	return 0;