linux_dsm_epyc7002/arch/x86/kernel/dumpstack.c
Tejun Heo 196779b9b4 dump_stack: consolidate dump_stack() implementations and unify their behaviors
Both dump_stack() and show_stack() are currently implemented by each
architecture.  show_stack(NULL, NULL) dumps the backtrace for the
current task as does dump_stack().  On some archs, dump_stack() prints
extra information - pid, utsname and so on - in addition to the
backtrace while the two are identical on other archs.

The usages in arch-independent code of the two functions indicate
show_stack(NULL, NULL) should print out bare backtrace while
dump_stack() is used for debugging purposes when something went wrong,
so it does make sense to print additional information on the task which
triggered dump_stack().

There's no reason to require archs to implement two separate but mostly
identical functions.  It leads to unnecessary subtle information.

This patch expands the dummy fallback dump_stack() implementation in
lib/dump_stack.c such that it prints out debug information (taken from
x86) and invokes show_stack(NULL, NULL) and drops arch-specific
dump_stack() implementations in all archs except blackfin.  Blackfin's
dump_stack() does something wonky that I don't understand.

Debug information can be printed separately by calling
dump_stack_print_info() so that arch-specific dump_stack()
implementation can still emit the same debug information.  This is used
in blackfin.

This patch brings the following behavior changes.

* On some archs, an extra level in backtrace for show_stack() could be
  printed.  This is because the top frame was determined in
  dump_stack() on those archs while generic dump_stack() can't do that
  reliably.  It can be compensated by inlining dump_stack() but not
  sure whether that'd be necessary.

* Most archs didn't use to print debug info on dump_stack().  They do
  now.

An example WARN dump follows.

 WARNING: at kernel/workqueue.c:4841 init_workqueues+0x35/0x505()
 Hardware name: empty
 Modules linked in:
 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #9
  0000000000000009 ffff88007c861e08 ffffffff81c614dc ffff88007c861e48
  ffffffff8108f50f ffffffff82228240 0000000000000040 ffffffff8234a03c
  0000000000000000 0000000000000000 0000000000000000 ffff88007c861e58
 Call Trace:
  [<ffffffff81c614dc>] dump_stack+0x19/0x1b
  [<ffffffff8108f50f>] warn_slowpath_common+0x7f/0xc0
  [<ffffffff8108f56a>] warn_slowpath_null+0x1a/0x20
  [<ffffffff8234a071>] init_workqueues+0x35/0x505
  ...

v2: CPU number added to the generic debug info as requested by s390
    folks and dropped the s390 specific dump_stack().  This loses %ksp
    from the debug message which the maintainers think isn't important
    enough to keep the s390-specific dump_stack() implementation.

    dump_stack_print_info() is moved to kernel/printk.c from
    lib/dump_stack.c.  Because linkage is per objecct file,
    dump_stack_print_info() living in the same lib file as generic
    dump_stack() means that archs which implement custom dump_stack()
    - at this point, only blackfin - can't use dump_stack_print_info()
    as that will bring in the generic version of dump_stack() too.  v1
    The v1 patch broke build on blackfin due to this issue.  The build
    breakage was reported by Fengguang Wu.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Vineet Gupta <vgupta@synopsys.com>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Acked-by: Vineet Gupta <vgupta@synopsys.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>	[s390 bits]
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
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

342 lines
7.4 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/utsname.h>
#include <linux/hardirq.h>
#include <linux/kdebug.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/ftrace.h>
#include <linux/kexec.h>
#include <linux/bug.h>
#include <linux/nmi.h>
#include <linux/sysfs.h>
#include <asm/stacktrace.h>
int panic_on_unrecovered_nmi;
int panic_on_io_nmi;
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)
{
pr_cont(" [<%p>] %s%pB\n",
(void *)address, reliable ? "" : "? ", (void *)address);
}
#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;
unsigned long ret_addr;
int index;
if (addr != (unsigned long)return_to_handler)
return;
task = tinfo->task;
index = task->curr_ret_stack;
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
/*
* 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,
unsigned long *end, int *graph)
{
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 {
ops->address(data, addr, 0);
}
print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
}
stack++;
}
return bp;
}
EXPORT_SYMBOL_GPL(print_context_stack);
unsigned long
print_context_stack_bp(struct thread_info *tinfo,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph)
{
struct stack_frame *frame = (struct stack_frame *)bp;
unsigned long *ret_addr = &frame->return_address;
while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
unsigned long addr = *ret_addr;
if (!__kernel_text_address(addr))
break;
ops->address(data, addr, 1);
frame = frame->next_frame;
ret_addr = &frame->return_address;
print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
}
return (unsigned long)frame;
}
EXPORT_SYMBOL_GPL(print_context_stack_bp);
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 = {
.stack = print_trace_stack,
.address = print_trace_address,
.walk_stack = print_context_stack,
};
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)
{
unsigned long bp = 0;
unsigned long stack;
/*
* Stack frames below this one aren't interesting. Don't show them
* if we're printing for %current.
*/
if (!sp && (!task || task == current)) {
sp = &stack;
bp = stack_frame(current, NULL);
}
show_stack_log_lvl(task, NULL, sp, bp, "");
}
static arch_spinlock_t die_lock = __ARCH_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 (!arch_spin_trylock(&die_lock)) {
if (cpu == die_owner)
/* nested oops. should stop eventually */;
else
arch_spin_lock(&die_lock);
}
die_nest_count++;
die_owner = cpu;
console_verbose();
bust_spinlocks(1);
return flags;
}
EXPORT_SYMBOL_GPL(oops_begin);
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, LOCKDEP_NOW_UNRELIABLE);
die_nest_count--;
if (!die_nest_count)
/* Nest count reaches zero, release the lock. */
arch_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_DEFAULT
"%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");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
return 1;
print_modules();
show_regs(regs);
#ifdef CONFIG_X86_32
if (user_mode_vm(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
} else {
sp = kernel_stack_pointer(regs);
savesegment(ss, ss);
}
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);
}
static int __init kstack_setup(char *s)
{
ssize_t ret;
unsigned long val;
if (!s)
return -EINVAL;
ret = kstrtoul(s, 0, &val);
if (ret)
return ret;
kstack_depth_to_print = val;
return 0;
}
early_param("kstack", kstack_setup);
static int __init code_bytes_setup(char *s)
{
ssize_t ret;
unsigned long val;
if (!s)
return -EINVAL;
ret = kstrtoul(s, 0, &val);
if (ret)
return ret;
code_bytes = val;
if (code_bytes > 8192)
code_bytes = 8192;
return 1;
}
__setup("code_bytes=", code_bytes_setup);