alistair23-linux/arch/x86/kernel/dumpstack_64.c
Tejun Heo a43cb95d54 dump_stack: unify debug information printed by show_regs()
show_regs() is inherently arch-dependent but it does make sense to print
generic debug information and some archs already do albeit in slightly
different forms.  This patch introduces a generic function to print debug
information from show_regs() so that different archs print out the same
information and it's much easier to modify what's printed.

show_regs_print_info() prints out the same debug info as dump_stack()
does plus task and thread_info pointers.

* Archs which didn't print debug info now do.

  alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r,
  metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc,
  um, xtensa

* Already prints debug info.  Replaced with show_regs_print_info().
  The printed information is superset of what used to be there.

  arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86

* s390 is special in that it used to print arch-specific information
  along with generic debug info.  Heiko and Martin think that the
  arch-specific extra isn't worth keeping s390 specfic implementation.
  Converted to use the generic version.

Note that now all archs print the debug info before actual register
dumps.

An example BUG() dump follows.

 kernel BUG at /work/os/work/kernel/workqueue.c:4841!
 invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
 Modules linked in:
 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7
 Hardware name: empty empty/S3992, BIOS 080011  10/26/2007
 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000
 RIP: 0010:[<ffffffff8234a07e>]  [<ffffffff8234a07e>] init_workqueues+0x4/0x6
 RSP: 0000:ffff88007c861ec8  EFLAGS: 00010246
 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001
 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a
 RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a
 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 FS:  0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
 CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
 Stack:
  ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650
  0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d
  ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760
 Call Trace:
  [<ffffffff81000312>] do_one_initcall+0x122/0x170
  [<ffffffff82335e5d>] kernel_init_freeable+0x9b/0x1c8
  [<ffffffff81c47760>] ? rest_init+0x140/0x140
  [<ffffffff81c4776e>] kernel_init+0xe/0xf0
  [<ffffffff81c6be9c>] ret_from_fork+0x7c/0xb0
  [<ffffffff81c47760>] ? rest_init+0x140/0x140
  ...

v2: Typo fix in x86-32.

v3: CPU number dropped from show_regs_print_info() as
    dump_stack_print_info() has been updated to print it.  s390
    specific implementation dropped as requested by s390 maintainers.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>		[tile bits]
Acked-by: Richard Kuo <rkuo@codeaurora.org>		[hexagon bits]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 17:04:02 -07:00

303 lines
7.1 KiB
C

/*
* 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/hardirq.h>
#include <linux/kdebug.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/kexec.h>
#include <linux/sysfs.h>
#include <linux/bug.h>
#include <linux/nmi.h>
#include <asm/stacktrace.h>
#define N_EXCEPTION_STACKS_END \
(N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
static char x86_stack_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_END ] = "#DB[?]"
#endif
};
static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
unsigned *usedp, char **idp)
{
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 = x86_stack_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;
x86_stack_ids[j][4] = '1' +
(j - N_EXCEPTION_STACKS);
} while (stack < end - EXCEPTION_STKSZ);
if (*usedp & (1U << j))
break;
*usedp |= 1U << j;
*idp = x86_stack_ids[j];
return (unsigned long *)end;
}
#endif
}
return NULL;
}
static inline int
in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
unsigned long *irq_stack_end)
{
return (stack >= irq_stack && stack < irq_stack_end);
}
/*
* x86-64 can have up to three kernel stacks:
* process stack
* interrupt stack
* severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
*/
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 *irq_stack_end =
(unsigned long *)per_cpu(irq_stack_ptr, cpu);
unsigned used = 0;
struct thread_info *tinfo;
int graph = 0;
unsigned long dummy;
if (!task)
task = current;
if (!stack) {
if (regs)
stack = (unsigned long *)regs->sp;
else if (task != current)
stack = (unsigned long *)task->thread.sp;
else
stack = &dummy;
}
if (!bp)
bp = stack_frame(task, regs);
/*
* 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 = ops->walk_stack(tinfo, stack, bp, ops,
data, estack_end, &graph);
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 (irq_stack_end) {
unsigned long *irq_stack;
irq_stack = irq_stack_end -
(IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
if (ops->stack(data, "IRQ") < 0)
break;
bp = ops->walk_stack(tinfo, stack, bp,
ops, data, irq_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 *) (irq_stack_end[-1]);
irq_stack_end = NULL;
ops->stack(data, "EOI");
continue;
}
}
break;
}
/*
* This handles the process stack:
*/
bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
put_cpu();
}
EXPORT_SYMBOL(dump_trace);
void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *sp, unsigned long bp, char *log_lvl)
{
unsigned long *irq_stack_end;
unsigned long *irq_stack;
unsigned long *stack;
int cpu;
int i;
preempt_disable();
cpu = smp_processor_id();
irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
irq_stack = (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
/*
* 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 >= irq_stack && stack <= irq_stack_end) {
if (stack == irq_stack_end) {
stack = (unsigned long *) (irq_stack_end[-1]);
pr_cont(" <EOI> ");
}
} else {
if (((long) stack & (THREAD_SIZE-1)) == 0)
break;
}
if (i && ((i % STACKSLOTS_PER_LINE) == 0))
pr_cont("\n");
pr_cont(" %016lx", *stack++);
touch_nmi_watchdog();
}
preempt_enable();
pr_cont("\n");
show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
void show_regs(struct pt_regs *regs)
{
int i;
unsigned long sp;
sp = regs->sp;
show_regs_print_info(KERN_DEFAULT);
__show_regs(regs, 1);
/*
* 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(KERN_DEFAULT "Stack:\n");
show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
0, KERN_DEFAULT);
printk(KERN_DEFAULT "Code: ");
ip = (u8 *)regs->ip - code_prologue;
if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
/* try starting at IP */
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)) {
pr_cont(" Bad RIP value.");
break;
}
if (ip == (u8 *)regs->ip)
pr_cont("<%02x> ", c);
else
pr_cont("%02x ", c);
}
}
pr_cont("\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;
}