x86_64: split out dumpstack code from traps_64.c

The dumpstack code is logically quite independent from the
hardware traps. Split it out into its own file.

Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 565 insertions, 0 deletions

diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
new file mode 100644
index 000000000000..6f1505074db0
--- /dev/null
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -0,0 +1,565 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/utsname.h>
+#include <linux/hardirq.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/kexec.h>
+#include <linux/bug.h>
+#include <linux/nmi.h>
+
+#include <asm/stacktrace.h>
+
+int panic_on_unrecovered_nmi;
+int kstack_depth_to_print = 12;
+static unsigned int code_bytes = 64;
+static int die_counter;
+
+void printk_address(unsigned long address, int reliable)
+{
+	printk(" [<%016lx>] %s%pS\n",
+			address, reliable ?	"" : "? ", (void *) address);
+}
+
+static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
+					unsigned *usedp, char **idp)
+{
+	static char ids[][8] = {
+		[DEBUG_STACK - 1] = "#DB",
+		[NMI_STACK - 1] = "NMI",
+		[DOUBLEFAULT_STACK - 1] = "#DF",
+		[STACKFAULT_STACK - 1] = "#SS",
+		[MCE_STACK - 1] = "#MC",
+#if DEBUG_STKSZ > EXCEPTION_STKSZ
+		[N_EXCEPTION_STACKS ...
+			N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
+#endif
+	};
+	unsigned k;
+
+	/*
+	 * Iterate over all exception stacks, and figure out whether
+	 * 'stack' is in one of them:
+	 */
+	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
+		unsigned long end = per_cpu(orig_ist, cpu).ist[k];
+		/*
+		 * Is 'stack' above this exception frame's end?
+		 * If yes then skip to the next frame.
+		 */
+		if (stack >= end)
+			continue;
+		/*
+		 * Is 'stack' above this exception frame's start address?
+		 * If yes then we found the right frame.
+		 */
+		if (stack >= end - EXCEPTION_STKSZ) {
+			/*
+			 * Make sure we only iterate through an exception
+			 * stack once. If it comes up for the second time
+			 * then there's something wrong going on - just
+			 * break out and return NULL:
+			 */
+			if (*usedp & (1U << k))
+				break;
+			*usedp |= 1U << k;
+			*idp = ids[k];
+			return (unsigned long *)end;
+		}
+		/*
+		 * If this is a debug stack, and if it has a larger size than
+		 * the usual exception stacks, then 'stack' might still
+		 * be within the lower portion of the debug stack:
+		 */
+#if DEBUG_STKSZ > EXCEPTION_STKSZ
+		if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) {
+			unsigned j = N_EXCEPTION_STACKS - 1;
+
+			/*
+			 * Black magic. A large debug stack is composed of
+			 * multiple exception stack entries, which we
+			 * iterate through now. Dont look:
+			 */
+			do {
+				++j;
+				end -= EXCEPTION_STKSZ;
+				ids[j][4] = '1' + (j - N_EXCEPTION_STACKS);
+			} while (stack < end - EXCEPTION_STKSZ);
+			if (*usedp & (1U << j))
+				break;
+			*usedp |= 1U << j;
+			*idp = ids[j];
+			return (unsigned long *)end;
+		}
+#endif
+	}
+	return NULL;
+}
+
+/*
+ * x86-64 can have up to three kernel stacks:
+ * process stack
+ * interrupt stack
+ * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
+ */
+
+static inline int valid_stack_ptr(struct thread_info *tinfo,
+			void *p, unsigned int size, void *end)
+{
+	void *t = tinfo;
+	if (end) {
+		if (p < end && p >= (end-THREAD_SIZE))
+			return 1;
+		else
+			return 0;
+	}
+	return p > t && p < t + THREAD_SIZE - size;
+}
+
+/* The form of the top of the frame on the stack */
+struct stack_frame {
+	struct stack_frame *next_frame;
+	unsigned long return_address;
+};
+
+static inline unsigned long
+print_context_stack(struct thread_info *tinfo,
+		unsigned long *stack, unsigned long bp,
+		const struct stacktrace_ops *ops, void *data,
+		unsigned long *end)
+{
+	struct stack_frame *frame = (struct stack_frame *)bp;
+
+	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
+		unsigned long addr;
+
+		addr = *stack;
+		if (__kernel_text_address(addr)) {
+			if ((unsigned long) stack == bp + 8) {
+				ops->address(data, addr, 1);
+				frame = frame->next_frame;
+				bp = (unsigned long) frame;
+			} else {
+				ops->address(data, addr, bp == 0);
+			}
+		}
+		stack++;
+	}
+	return bp;
+}
+
+void dump_trace(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp,
+		const struct stacktrace_ops *ops, void *data)
+{
+	const unsigned cpu = get_cpu();
+	unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
+	unsigned used = 0;
+	struct thread_info *tinfo;
+
+	if (!task)
+		task = current;
+
+	if (!stack) {
+		unsigned long dummy;
+		stack = &dummy;
+		if (task && task != current)
+			stack = (unsigned long *)task->thread.sp;
+	}
+
+#ifdef CONFIG_FRAME_POINTER
+	if (!bp) {
+		if (task == current) {
+			/* Grab bp right from our regs */
+			asm("movq %%rbp, %0" : "=r" (bp) : );
+		} else {
+			/* bp is the last reg pushed by switch_to */
+			bp = *(unsigned long *) task->thread.sp;
+		}
+	}
+#endif
+
+	/*
+	 * Print function call entries in all stacks, starting at the
+	 * current stack address. If the stacks consist of nested
+	 * exceptions
+	 */
+	tinfo = task_thread_info(task);
+	for (;;) {
+		char *id;
+		unsigned long *estack_end;
+		estack_end = in_exception_stack(cpu, (unsigned long)stack,
+						&used, &id);
+
+		if (estack_end) {
+			if (ops->stack(data, id) < 0)
+				break;
+
+			bp = print_context_stack(tinfo, stack, bp, ops,
+							data, estack_end);
+			ops->stack(data, "<EOE>");
+			/*
+			 * We link to the next stack via the
+			 * second-to-last pointer (index -2 to end) in the
+			 * exception stack:
+			 */
+			stack = (unsigned long *) estack_end[-2];
+			continue;
+		}
+		if (irqstack_end) {
+			unsigned long *irqstack;
+			irqstack = irqstack_end -
+				(IRQSTACKSIZE - 64) / sizeof(*irqstack);
+
+			if (stack >= irqstack && stack < irqstack_end) {
+				if (ops->stack(data, "IRQ") < 0)
+					break;
+				bp = print_context_stack(tinfo, stack, bp,
+						ops, data, irqstack_end);
+				/*
+				 * 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 *) (irqstack_end[-1]);
+				irqstack_end = NULL;
+				ops->stack(data, "EOI");
+				continue;
+			}
+		}
+		break;
+	}
+
+	/*
+	 * This handles the process stack:
+	 */
+	bp = print_context_stack(tinfo, stack, bp, ops, data, NULL);
+	put_cpu();
+}
+EXPORT_SYMBOL(dump_trace);
+
+static void
+print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
+{
+	print_symbol(msg, symbol);
+	printk("\n");
+}
+
+static void print_trace_warning(void *data, char *msg)
+{
+	printk("%s\n", msg);
+}
+
+static int print_trace_stack(void *data, char *name)
+{
+	printk(" <%s> ", name);
+	return 0;
+}
+
+static void print_trace_address(void *data, unsigned long addr, int reliable)
+{
+	touch_nmi_watchdog();
+	printk_address(addr, reliable);
+}
+
+static const struct stacktrace_ops print_trace_ops = {
+	.warning = print_trace_warning,
+	.warning_symbol = print_trace_warning_symbol,
+	.stack = print_trace_stack,
+	.address = print_trace_address,
+};
+
+static void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp, char *log_lvl)
+{
+	printk("Call Trace:\n");
+	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
+}
+
+void show_trace(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp)
+{
+	show_trace_log_lvl(task, regs, stack, bp, "");
+}
+
+static void
+show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *sp, unsigned long bp, char *log_lvl)
+{
+	unsigned long *stack;
+	int i;
+	const int cpu = smp_processor_id();
+	unsigned long *irqstack_end =
+		(unsigned long *) (cpu_pda(cpu)->irqstackptr);
+	unsigned long *irqstack =
+		(unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
+
+	/*
+	 * debugging aid: "show_stack(NULL, NULL);" prints the
+	 * back trace for this cpu.
+	 */
+
+	if (sp == NULL) {
+		if (task)
+			sp = (unsigned long *)task->thread.sp;
+		else
+			sp = (unsigned long *)&sp;
+	}
+
+	stack = sp;
+	for (i = 0; i < kstack_depth_to_print; i++) {
+		if (stack >= irqstack && stack <= irqstack_end) {
+			if (stack == irqstack_end) {
+				stack = (unsigned long *) (irqstack_end[-1]);
+				printk(" <EOI> ");
+			}
+		} else {
+		if (((long) stack & (THREAD_SIZE-1)) == 0)
+			break;
+		}
+		if (i && ((i % 4) == 0))
+			printk("\n");
+		printk(" %016lx", *stack++);
+		touch_nmi_watchdog();
+	}
+	printk("\n");
+	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+	show_stack_log_lvl(task, NULL, sp, 0, "");
+}
+
+/*
+ * The architecture-independent dump_stack generator
+ */
+void dump_stack(void)
+{
+	unsigned long bp = 0;
+	unsigned long stack;
+
+#ifdef CONFIG_FRAME_POINTER
+	if (!bp)
+		asm("movq %%rbp, %0" : "=r" (bp) : );
+#endif
+
+	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
+		current->pid, current->comm, print_tainted(),
+		init_utsname()->release,
+		(int)strcspn(init_utsname()->version, " "),
+		init_utsname()->version);
+	show_trace(NULL, NULL, &stack, bp);
+}
+EXPORT_SYMBOL(dump_stack);
+
+void show_registers(struct pt_regs *regs)
+{
+	int i;
+	unsigned long sp;
+	const int cpu = smp_processor_id();
+	struct task_struct *cur = cpu_pda(cpu)->pcurrent;
+
+	sp = regs->sp;
+	printk("CPU %d ", cpu);
+	__show_regs(regs, 1);
+	printk("Process %s (pid: %d, threadinfo %p, task %p)\n",
+		cur->comm, cur->pid, task_thread_info(cur), cur);
+
+	/*
+	 * When in-kernel, we also print out the stack and code at the
+	 * time of the fault..
+	 */
+	if (!user_mode(regs)) {
+		unsigned int code_prologue = code_bytes * 43 / 64;
+		unsigned int code_len = code_bytes;
+		unsigned char c;
+		u8 *ip;
+
+		printk("Stack: ");
+		show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
+				regs->bp, "");
+
+		printk(KERN_EMERG "Code: ");
+
+		ip = (u8 *)regs->ip - code_prologue;
+		if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
+			/* try starting at RIP */
+			ip = (u8 *)regs->ip;
+			code_len = code_len - code_prologue + 1;
+		}
+		for (i = 0; i < code_len; i++, ip++) {
+			if (ip < (u8 *)PAGE_OFFSET ||
+					probe_kernel_address(ip, c)) {
+				printk(" Bad RIP value.");
+				break;
+			}
+			if (ip == (u8 *)regs->ip)
+				printk("<%02x> ", c);
+			else
+				printk("%02x ", c);
+		}
+	}
+	printk("\n");
+}
+
+int is_valid_bugaddr(unsigned long ip)
+{
+	unsigned short ud2;
+
+	if (__copy_from_user(&ud2, (const void __user *) ip, sizeof(ud2)))
+		return 0;
+
+	return ud2 == 0x0b0f;
+}
+
+static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
+static int die_owner = -1;
+static unsigned int die_nest_count;
+
+unsigned __kprobes long oops_begin(void)
+{
+	int cpu;
+	unsigned long flags;
+
+	oops_enter();
+
+	/* racy, but better than risking deadlock. */
+	raw_local_irq_save(flags);
+	cpu = smp_processor_id();
+	if (!__raw_spin_trylock(&die_lock)) {
+		if (cpu == die_owner)
+			/* nested oops. should stop eventually */;
+		else
+			__raw_spin_lock(&die_lock);
+	}
+	die_nest_count++;
+	die_owner = cpu;
+	console_verbose();
+	bust_spinlocks(1);
+	return flags;
+}
+
+void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
+{
+	die_owner = -1;
+	bust_spinlocks(0);
+	die_nest_count--;
+	if (!die_nest_count)
+		/* Nest count reaches zero, release the lock. */
+		__raw_spin_unlock(&die_lock);
+	raw_local_irq_restore(flags);
+	if (!regs) {
+		oops_exit();
+		return;
+	}
+	if (in_interrupt())
+		panic("Fatal exception in interrupt");
+	if (panic_on_oops)
+		panic("Fatal exception");
+	oops_exit();
+	do_exit(signr);
+}
+
+int __kprobes __die(const char *str, struct pt_regs *regs, long err)
+{
+	printk(KERN_EMERG "%s: %04lx [%u] ", str, err & 0xffff, ++die_counter);
+#ifdef CONFIG_PREEMPT
+	printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+	printk("SMP ");
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	printk("DEBUG_PAGEALLOC");
+#endif
+	printk("\n");
+	if (notify_die(DIE_OOPS, str, regs, err,
+			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+		return 1;
+
+	show_registers(regs);
+	add_taint(TAINT_DIE);
+	/* Executive summary in case the oops scrolled away */
+	printk(KERN_ALERT "RIP ");
+	printk_address(regs->ip, 1);
+	printk(" RSP <%016lx>\n", regs->sp);
+	if (kexec_should_crash(current))
+		crash_kexec(regs);
+	return 0;
+}
+
+void die(const char *str, struct pt_regs *regs, long err)
+{
+	unsigned long flags = oops_begin();
+
+	if (!user_mode(regs))
+		report_bug(regs->ip, regs);
+
+	if (__die(str, regs, err))
+		regs = NULL;
+	oops_end(flags, regs, SIGSEGV);
+}
+
+notrace __kprobes void
+die_nmi(char *str, struct pt_regs *regs, int do_panic)
+{
+	unsigned long flags;
+
+	if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
+		return;
+
+	flags = oops_begin();
+	/*
+	 * We are in trouble anyway, lets at least try
+	 * to get a message out.
+	 */
+	printk(KERN_EMERG "%s", str);
+	printk(" on CPU%d, ip %08lx, registers:\n",
+		smp_processor_id(), regs->ip);
+	show_registers(regs);
+	if (kexec_should_crash(current))
+		crash_kexec(regs);
+	if (do_panic || panic_on_oops)
+		panic("Non maskable interrupt");
+	oops_end(flags, NULL, SIGBUS);
+	nmi_exit();
+	local_irq_enable();
+	do_exit(SIGBUS);
+}
+
+static int __init oops_setup(char *s)
+{
+	if (!s)
+		return -EINVAL;
+	if (!strcmp(s, "panic"))
+		panic_on_oops = 1;
+	return 0;
+}
+early_param("oops", oops_setup);
+
+static int __init kstack_setup(char *s)
+{
+	if (!s)
+		return -EINVAL;
+	kstack_depth_to_print = simple_strtoul(s, NULL, 0);
+	return 0;
+}
+early_param("kstack", kstack_setup);
+
+static int __init code_bytes_setup(char *s)
+{
+	code_bytes = simple_strtoul(s, NULL, 0);
+	if (code_bytes > 8192)
+		code_bytes = 8192;
+
+	return 1;
+}
+__setup("code_bytes=", code_bytes_setup);