dumpstack.c 7.9 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12
/*
 *  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>
13
#include <linux/ftrace.h>
14 15 16 17 18 19 20 21 22 23
#include <linux/kexec.h>
#include <linux/bug.h>
#include <linux/nmi.h>
#include <linux/sysfs.h>

#include <asm/stacktrace.h>

#include "dumpstack.h"

int panic_on_unrecovered_nmi;
24
int panic_on_io_nmi;
25 26 27 28 29 30 31 32 33 34
unsigned int code_bytes = 64;
int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
static int die_counter;

void printk_address(unsigned long address, int reliable)
{
	printk(" [<%p>] %s%pS\n", (void *) address,
			reliable ? "" : "? ", (void *) address);
}

35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static void
print_ftrace_graph_addr(unsigned long addr, void *data,
			const struct stacktrace_ops *ops,
			struct thread_info *tinfo, int *graph)
{
	struct task_struct *task = tinfo->task;
	unsigned long ret_addr;
	int index = task->curr_ret_stack;

	if (addr != (unsigned long)return_to_handler)
		return;

	if (!task->ret_stack || index < *graph)
		return;

	index -= *graph;
	ret_addr = task->ret_stack[index].ret;

	ops->address(data, ret_addr, 1);

	(*graph)++;
}
#else
static inline void
print_ftrace_graph_addr(unsigned long addr, void *data,
			const struct stacktrace_ops *ops,
			struct thread_info *tinfo, int *graph)
{ }
#endif

66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89
/*
 * 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;
}

unsigned long
print_context_stack(struct thread_info *tinfo,
		unsigned long *stack, unsigned long bp,
		const struct stacktrace_ops *ops, void *data,
90
		unsigned long *end, int *graph)
91 92 93 94 95 96 97 98 99 100 101 102 103
{
	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 + sizeof(long)) {
				ops->address(data, addr, 1);
				frame = frame->next_frame;
				bp = (unsigned long) frame;
			} else {
104
				ops->address(data, addr, 0);
105
			}
106
			print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190
		}
		stack++;
	}
	return bp;
}


static void
print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
{
	printk(data);
	print_symbol(msg, symbol);
	printk("\n");
}

static void print_trace_warning(void *data, char *msg)
{
	printk("%s%s\n", (char *)data, msg);
}

static int print_trace_stack(void *data, char *name)
{
	printk("%s <%s> ", (char *)data, name);
	return 0;
}

/*
 * Print one address/symbol entries per line.
 */
static void print_trace_address(void *data, unsigned long addr, int reliable)
{
	touch_nmi_watchdog();
	printk(data);
	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,
};

void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
		unsigned long *stack, unsigned long bp, char *log_lvl)
{
	printk("%sCall Trace:\n", log_lvl);
	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, "");
}

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)
		get_bp(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);

191
static arch_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
192 193 194 195 196 197 198 199
static int die_owner = -1;
static unsigned int die_nest_count;

unsigned __kprobes long oops_begin(void)
{
	int cpu;
	unsigned long flags;

200 201 202 203 204
	/* notify the hw-branch tracer so it may disable tracing and
	   add the last trace to the trace buffer -
	   the earlier this happens, the more useful the trace. */
	trace_hw_branch_oops();

205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270
	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)
{
	if (regs && kexec_should_crash(current))
		crash_kexec(regs);

	bust_spinlocks(0);
	die_owner = -1;
	add_taint(TAINT_DIE);
	die_nest_count--;
	if (!die_nest_count)
		/* Nest count reaches zero, release the lock. */
		__raw_spin_unlock(&die_lock);
	raw_local_irq_restore(flags);
	oops_exit();

	if (!signr)
		return;
	if (in_interrupt())
		panic("Fatal exception in interrupt");
	if (panic_on_oops)
		panic("Fatal exception");
	do_exit(signr);
}

int __kprobes __die(const char *str, struct pt_regs *regs, long err)
{
#ifdef CONFIG_X86_32
	unsigned short ss;
	unsigned long sp;
#endif
	printk(KERN_EMERG "%s: %04lx [#%d] ", 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");
	sysfs_printk_last_file();
	if (notify_die(DIE_OOPS, str, regs, err,
			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
		return 1;

	show_registers(regs);
#ifdef CONFIG_X86_32
271
	if (user_mode_vm(regs)) {
272 273
		sp = regs->sp;
		ss = regs->ss & 0xffff;
274 275 276
	} else {
		sp = kernel_stack_pointer(regs);
		savesegment(ss, ss);
277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359
	}
	printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
	print_symbol("%s", regs->ip);
	printk(" SS:ESP %04x:%08lx\n", ss, sp);
#else
	/* Executive summary in case the oops scrolled away */
	printk(KERN_ALERT "RIP ");
	printk_address(regs->ip, 1);
	printk(" RSP <%016lx>\n", regs->sp);
#endif
	return 0;
}

/*
 * This is gone through when something in the kernel has done something bad
 * and is about to be terminated:
 */
void die(const char *str, struct pt_regs *regs, long err)
{
	unsigned long flags = oops_begin();
	int sig = SIGSEGV;

	if (!user_mode_vm(regs))
		report_bug(regs->ip, regs);

	if (__die(str, regs, err))
		sig = 0;
	oops_end(flags, regs, sig);
}

void notrace __kprobes
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;

	/*
	 * We are in trouble anyway, lets at least try
	 * to get a message out.
	 */
	flags = oops_begin();
	printk(KERN_EMERG "%s", str);
	printk(" on CPU%d, ip %08lx, registers:\n",
		smp_processor_id(), regs->ip);
	show_registers(regs);
	oops_end(flags, regs, 0);
	if (do_panic || panic_on_oops)
		panic("Non maskable interrupt");
	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);