linux/arch/x86/kernel/process_32.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

345 lines
9.3 KiB
C

/*
* Copyright (C) 1995 Linus Torvalds
*
* Pentium III FXSR, SSE support
* Gareth Hughes <gareth@valinux.com>, May 2000
*/
/*
* This file handles the architecture-dependent parts of process handling..
*/
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/reboot.h>
#include <linux/init.h>
#include <linux/mc146818rtc.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
#include <linux/personality.h>
#include <linux/percpu.h>
#include <linux/prctl.h>
#include <linux/ftrace.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/kdebug.h>
#include <asm/pgtable.h>
#include <asm/ldt.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/desc.h>
#ifdef CONFIG_MATH_EMULATION
#include <asm/math_emu.h>
#endif
#include <linux/err.h>
#include <asm/tlbflush.h>
#include <asm/cpu.h>
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/debugreg.h>
#include <asm/switch_to.h>
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
/*
* Return saved PC of a blocked thread.
*/
unsigned long thread_saved_pc(struct task_struct *tsk)
{
return ((unsigned long *)tsk->thread.sp)[3];
}
void __show_regs(struct pt_regs *regs, int all)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
unsigned long d0, d1, d2, d3, d6, d7;
unsigned long sp;
unsigned short ss, gs;
if (user_mode_vm(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
gs = get_user_gs(regs);
} else {
sp = kernel_stack_pointer(regs);
savesegment(ss, ss);
savesegment(gs, gs);
}
printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
(u16)regs->cs, regs->ip, regs->flags,
smp_processor_id());
print_symbol("EIP is at %s\n", regs->ip);
printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
regs->ax, regs->bx, regs->cx, regs->dx);
printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
regs->si, regs->di, regs->bp, sp);
printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
(u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss);
if (!all)
return;
cr0 = read_cr0();
cr2 = read_cr2();
cr3 = read_cr3();
cr4 = read_cr4_safe();
printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
cr0, cr2, cr3, cr4);
get_debugreg(d0, 0);
get_debugreg(d1, 1);
get_debugreg(d2, 2);
get_debugreg(d3, 3);
printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
d0, d1, d2, d3);
get_debugreg(d6, 6);
get_debugreg(d7, 7);
printk(KERN_DEFAULT "DR6: %08lx DR7: %08lx\n",
d6, d7);
}
void release_thread(struct task_struct *dead_task)
{
BUG_ON(dead_task->mm);
release_vm86_irqs(dead_task);
}
int copy_thread(unsigned long clone_flags, unsigned long sp,
unsigned long arg, struct task_struct *p)
{
struct pt_regs *childregs = task_pt_regs(p);
struct task_struct *tsk;
int err;
p->thread.sp = (unsigned long) childregs;
p->thread.sp0 = (unsigned long) (childregs+1);
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
p->thread.ip = (unsigned long) ret_from_kernel_thread;
task_user_gs(p) = __KERNEL_STACK_CANARY;
childregs->ds = __USER_DS;
childregs->es = __USER_DS;
childregs->fs = __KERNEL_PERCPU;
childregs->bx = sp; /* function */
childregs->bp = arg;
childregs->orig_ax = -1;
childregs->cs = __KERNEL_CS | get_kernel_rpl();
childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
p->fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
return 0;
}
*childregs = *current_pt_regs();
childregs->ax = 0;
if (sp)
childregs->sp = sp;
p->thread.ip = (unsigned long) ret_from_fork;
task_user_gs(p) = get_user_gs(current_pt_regs());
p->fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
tsk = current;
err = -ENOMEM;
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
IO_BITMAP_BYTES, GFP_KERNEL);
if (!p->thread.io_bitmap_ptr) {
p->thread.io_bitmap_max = 0;
return -ENOMEM;
}
set_tsk_thread_flag(p, TIF_IO_BITMAP);
}
err = 0;
/*
* Set a new TLS for the child thread?
*/
if (clone_flags & CLONE_SETTLS)
err = do_set_thread_area(p, -1,
(struct user_desc __user *)childregs->si, 0);
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
return err;
}
void
start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
set_user_gs(regs, 0);
regs->fs = 0;
regs->ds = __USER_DS;
regs->es = __USER_DS;
regs->ss = __USER_DS;
regs->cs = __USER_CS;
regs->ip = new_ip;
regs->sp = new_sp;
regs->flags = X86_EFLAGS_IF;
/*
* force it to the iret return path by making it look as if there was
* some work pending.
*/
set_thread_flag(TIF_NOTIFY_RESUME);
}
EXPORT_SYMBOL_GPL(start_thread);
/*
* switch_to(x,y) should switch tasks from x to y.
*
* We fsave/fwait so that an exception goes off at the right time
* (as a call from the fsave or fwait in effect) rather than to
* the wrong process. Lazy FP saving no longer makes any sense
* with modern CPU's, and this simplifies a lot of things (SMP
* and UP become the same).
*
* NOTE! We used to use the x86 hardware context switching. The
* reason for not using it any more becomes apparent when you
* try to recover gracefully from saved state that is no longer
* valid (stale segment register values in particular). With the
* hardware task-switch, there is no way to fix up bad state in
* a reasonable manner.
*
* The fact that Intel documents the hardware task-switching to
* be slow is a fairly red herring - this code is not noticeably
* faster. However, there _is_ some room for improvement here,
* so the performance issues may eventually be a valid point.
* More important, however, is the fact that this allows us much
* more flexibility.
*
* The return value (in %ax) will be the "prev" task after
* the task-switch, and shows up in ret_from_fork in entry.S,
* for example.
*/
__notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread,
*next = &next_p->thread;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
fpu_switch_t fpu;
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
fpu = switch_fpu_prepare(prev_p, next_p, cpu);
/*
* Reload esp0.
*/
load_sp0(tss, next);
/*
* Save away %gs. No need to save %fs, as it was saved on the
* stack on entry. No need to save %es and %ds, as those are
* always kernel segments while inside the kernel. Doing this
* before setting the new TLS descriptors avoids the situation
* where we temporarily have non-reloadable segments in %fs
* and %gs. This could be an issue if the NMI handler ever
* used %fs or %gs (it does not today), or if the kernel is
* running inside of a hypervisor layer.
*/
lazy_save_gs(prev->gs);
/*
* Load the per-thread Thread-Local Storage descriptor.
*/
load_TLS(next, cpu);
/*
* Restore IOPL if needed. In normal use, the flags restore
* in the switch assembly will handle this. But if the kernel
* is running virtualized at a non-zero CPL, the popf will
* not restore flags, so it must be done in a separate step.
*/
if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
set_iopl_mask(next->iopl);
/*
* Now maybe handle debug registers and/or IO bitmaps
*/
if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||
task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
__switch_to_xtra(prev_p, next_p, tss);
/*
* Leave lazy mode, flushing any hypercalls made here.
* This must be done before restoring TLS segments so
* the GDT and LDT are properly updated, and must be
* done before math_state_restore, so the TS bit is up
* to date.
*/
arch_end_context_switch(next_p);
/*
* Restore %gs if needed (which is common)
*/
if (prev->gs | next->gs)
lazy_load_gs(next->gs);
switch_fpu_finish(next_p, fpu);
this_cpu_write(current_task, next_p);
return prev_p;
}
#define top_esp (THREAD_SIZE - sizeof(unsigned long))
#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long))
unsigned long get_wchan(struct task_struct *p)
{
unsigned long bp, sp, ip;
unsigned long stack_page;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
stack_page = (unsigned long)task_stack_page(p);
sp = p->thread.sp;
if (!stack_page || sp < stack_page || sp > top_esp+stack_page)
return 0;
/* include/asm-i386/system.h:switch_to() pushes bp last. */
bp = *(unsigned long *) sp;
do {
if (bp < stack_page || bp > top_ebp+stack_page)
return 0;
ip = *(unsigned long *) (bp+4);
if (!in_sched_functions(ip))
return ip;
bp = *(unsigned long *) bp;
} while (count++ < 16);
return 0;
}