tmp_suning_uos_patched/arch/arm/kernel/traps.c
Hugh Dickins 69b0475456 [PATCH] mm: arm ready for split ptlock
Prepare arm for the split page_table_lock: three issues.

Signal handling's preserve and restore of iwmmxt context currently involves
reading and writing that context to and from user space, while holding
page_table_lock to secure the user page(s) against kswapd.  If we split the
lock, then the structure might span two pages, secured by to read into and
write from a kernel stack buffer, copying that out and in without locking (the
structure is 160 bytes in size, and here we're near the top of the kernel
stack).  Or would the overhead be noticeable?

arm_syscall's cmpxchg emulation use pte_offset_map_lock, instead of
pte_offset_map and mm-wide page_table_lock; and strictly, it should now also
take mmap_sem before descending to pmd, to guard against another thread
munmapping, and the page table pulled out beneath this thread.

Updated two comments in fault-armv.c.  adjust_pte is interesting, since its
modification of a pte in one part of the mm depends on the lock held when
calling update_mmu_cache for a pte in some other part of that mm.  This can't
be done with a split page_table_lock (and we've already taken the lowest lock
in the hierarchy here): so we'll have to disable split on arm, unless
CONFIG_CPU_CACHE_VIPT to ensures adjust_pte never used.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-29 21:40:42 -07:00

703 lines
17 KiB
C

/*
* linux/arch/arm/kernel/traps.c
*
* Copyright (C) 1995-2002 Russell King
* Fragments that appear the same as linux/arch/i386/kernel/traps.c (C) Linus Torvalds
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* 'traps.c' handles hardware exceptions after we have saved some state in
* 'linux/arch/arm/lib/traps.S'. Mostly a debugging aid, but will probably
* kill the offending process.
*/
#include <linux/config.h>
#include <linux/module.h>
#include <linux/signal.h>
#include <linux/spinlock.h>
#include <linux/personality.h>
#include <linux/ptrace.h>
#include <linux/kallsyms.h>
#include <linux/init.h>
#include <asm/atomic.h>
#include <asm/cacheflush.h>
#include <asm/io.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/traps.h>
#include "ptrace.h"
#include "signal.h"
const char *processor_modes[]=
{ "USER_26", "FIQ_26" , "IRQ_26" , "SVC_26" , "UK4_26" , "UK5_26" , "UK6_26" , "UK7_26" ,
"UK8_26" , "UK9_26" , "UK10_26", "UK11_26", "UK12_26", "UK13_26", "UK14_26", "UK15_26",
"USER_32", "FIQ_32" , "IRQ_32" , "SVC_32" , "UK4_32" , "UK5_32" , "UK6_32" , "ABT_32" ,
"UK8_32" , "UK9_32" , "UK10_32", "UND_32" , "UK12_32", "UK13_32", "UK14_32", "SYS_32"
};
static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
#ifdef CONFIG_DEBUG_USER
unsigned int user_debug;
static int __init user_debug_setup(char *str)
{
get_option(&str, &user_debug);
return 1;
}
__setup("user_debug=", user_debug_setup);
#endif
void dump_backtrace_entry(unsigned long where, unsigned long from)
{
#ifdef CONFIG_KALLSYMS
printk("[<%08lx>] ", where);
print_symbol("(%s) ", where);
printk("from [<%08lx>] ", from);
print_symbol("(%s)\n", from);
#else
printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
#endif
}
/*
* Stack pointers should always be within the kernels view of
* physical memory. If it is not there, then we can't dump
* out any information relating to the stack.
*/
static int verify_stack(unsigned long sp)
{
if (sp < PAGE_OFFSET || (sp > (unsigned long)high_memory && high_memory != 0))
return -EFAULT;
return 0;
}
/*
* Dump out the contents of some memory nicely...
*/
static void dump_mem(const char *str, unsigned long bottom, unsigned long top)
{
unsigned long p = bottom & ~31;
mm_segment_t fs;
int i;
/*
* We need to switch to kernel mode so that we can use __get_user
* to safely read from kernel space. Note that we now dump the
* code first, just in case the backtrace kills us.
*/
fs = get_fs();
set_fs(KERNEL_DS);
printk("%s(0x%08lx to 0x%08lx)\n", str, bottom, top);
for (p = bottom & ~31; p < top;) {
printk("%04lx: ", p & 0xffff);
for (i = 0; i < 8; i++, p += 4) {
unsigned int val;
if (p < bottom || p >= top)
printk(" ");
else {
__get_user(val, (unsigned long *)p);
printk("%08x ", val);
}
}
printk ("\n");
}
set_fs(fs);
}
static void dump_instr(struct pt_regs *regs)
{
unsigned long addr = instruction_pointer(regs);
const int thumb = thumb_mode(regs);
const int width = thumb ? 4 : 8;
mm_segment_t fs;
int i;
/*
* We need to switch to kernel mode so that we can use __get_user
* to safely read from kernel space. Note that we now dump the
* code first, just in case the backtrace kills us.
*/
fs = get_fs();
set_fs(KERNEL_DS);
printk("Code: ");
for (i = -4; i < 1; i++) {
unsigned int val, bad;
if (thumb)
bad = __get_user(val, &((u16 *)addr)[i]);
else
bad = __get_user(val, &((u32 *)addr)[i]);
if (!bad)
printk(i == 0 ? "(%0*x) " : "%0*x ", width, val);
else {
printk("bad PC value.");
break;
}
}
printk("\n");
set_fs(fs);
}
static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
{
unsigned int fp;
int ok = 1;
printk("Backtrace: ");
fp = regs->ARM_fp;
if (!fp) {
printk("no frame pointer");
ok = 0;
} else if (verify_stack(fp)) {
printk("invalid frame pointer 0x%08x", fp);
ok = 0;
} else if (fp < (unsigned long)(tsk->thread_info + 1))
printk("frame pointer underflow");
printk("\n");
if (ok)
c_backtrace(fp, processor_mode(regs));
}
void dump_stack(void)
{
#ifdef CONFIG_DEBUG_ERRORS
__backtrace();
#endif
}
EXPORT_SYMBOL(dump_stack);
void show_stack(struct task_struct *tsk, unsigned long *sp)
{
unsigned long fp;
if (!tsk)
tsk = current;
if (tsk != current)
fp = thread_saved_fp(tsk);
else
asm("mov%? %0, fp" : "=r" (fp));
c_backtrace(fp, 0x10);
barrier();
}
DEFINE_SPINLOCK(die_lock);
/*
* This function is protected against re-entrancy.
*/
NORET_TYPE void die(const char *str, struct pt_regs *regs, int err)
{
struct task_struct *tsk = current;
static int die_counter;
console_verbose();
spin_lock_irq(&die_lock);
bust_spinlocks(1);
printk("Internal error: %s: %x [#%d]\n", str, err, ++die_counter);
print_modules();
__show_regs(regs);
printk("Process %s (pid: %d, stack limit = 0x%p)\n",
tsk->comm, tsk->pid, tsk->thread_info + 1);
if (!user_mode(regs) || in_interrupt()) {
dump_mem("Stack: ", regs->ARM_sp,
THREAD_SIZE + (unsigned long)tsk->thread_info);
dump_backtrace(regs, tsk);
dump_instr(regs);
}
bust_spinlocks(0);
spin_unlock_irq(&die_lock);
do_exit(SIGSEGV);
}
void notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
unsigned long err, unsigned long trap)
{
if (user_mode(regs)) {
current->thread.error_code = err;
current->thread.trap_no = trap;
force_sig_info(info->si_signo, info, current);
} else {
die(str, regs, err);
}
}
static LIST_HEAD(undef_hook);
static DEFINE_SPINLOCK(undef_lock);
void register_undef_hook(struct undef_hook *hook)
{
unsigned long flags;
spin_lock_irqsave(&undef_lock, flags);
list_add(&hook->node, &undef_hook);
spin_unlock_irqrestore(&undef_lock, flags);
}
void unregister_undef_hook(struct undef_hook *hook)
{
unsigned long flags;
spin_lock_irqsave(&undef_lock, flags);
list_del(&hook->node);
spin_unlock_irqrestore(&undef_lock, flags);
}
asmlinkage void do_undefinstr(struct pt_regs *regs)
{
unsigned int correction = thumb_mode(regs) ? 2 : 4;
unsigned int instr;
struct undef_hook *hook;
siginfo_t info;
void __user *pc;
/*
* According to the ARM ARM, PC is 2 or 4 bytes ahead,
* depending whether we're in Thumb mode or not.
* Correct this offset.
*/
regs->ARM_pc -= correction;
pc = (void __user *)instruction_pointer(regs);
if (thumb_mode(regs)) {
get_user(instr, (u16 __user *)pc);
} else {
get_user(instr, (u32 __user *)pc);
}
spin_lock_irq(&undef_lock);
list_for_each_entry(hook, &undef_hook, node) {
if ((instr & hook->instr_mask) == hook->instr_val &&
(regs->ARM_cpsr & hook->cpsr_mask) == hook->cpsr_val) {
if (hook->fn(regs, instr) == 0) {
spin_unlock_irq(&undef_lock);
return;
}
}
}
spin_unlock_irq(&undef_lock);
#ifdef CONFIG_DEBUG_USER
if (user_debug & UDBG_UNDEFINED) {
printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n",
current->comm, current->pid, pc);
dump_instr(regs);
}
#endif
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_ILLOPC;
info.si_addr = pc;
notify_die("Oops - undefined instruction", regs, &info, 0, 6);
}
asmlinkage void do_unexp_fiq (struct pt_regs *regs)
{
#ifndef CONFIG_IGNORE_FIQ
printk("Hmm. Unexpected FIQ received, but trying to continue\n");
printk("You may have a hardware problem...\n");
#endif
}
/*
* bad_mode handles the impossible case in the vectors. If you see one of
* these, then it's extremely serious, and could mean you have buggy hardware.
* It never returns, and never tries to sync. We hope that we can at least
* dump out some state information...
*/
asmlinkage void bad_mode(struct pt_regs *regs, int reason, int proc_mode)
{
console_verbose();
printk(KERN_CRIT "Bad mode in %s handler detected: mode %s\n",
handler[reason], processor_modes[proc_mode]);
die("Oops - bad mode", regs, 0);
local_irq_disable();
panic("bad mode");
}
static int bad_syscall(int n, struct pt_regs *regs)
{
struct thread_info *thread = current_thread_info();
siginfo_t info;
if (current->personality != PER_LINUX &&
current->personality != PER_LINUX_32BIT &&
thread->exec_domain->handler) {
thread->exec_domain->handler(n, regs);
return regs->ARM_r0;
}
#ifdef CONFIG_DEBUG_USER
if (user_debug & UDBG_SYSCALL) {
printk(KERN_ERR "[%d] %s: obsolete system call %08x.\n",
current->pid, current->comm, n);
dump_instr(regs);
}
#endif
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_ILLTRP;
info.si_addr = (void __user *)instruction_pointer(regs) -
(thumb_mode(regs) ? 2 : 4);
notify_die("Oops - bad syscall", regs, &info, n, 0);
return regs->ARM_r0;
}
static inline void
do_cache_op(unsigned long start, unsigned long end, int flags)
{
struct vm_area_struct *vma;
if (end < start || flags)
return;
vma = find_vma(current->active_mm, start);
if (vma && vma->vm_start < end) {
if (start < vma->vm_start)
start = vma->vm_start;
if (end > vma->vm_end)
end = vma->vm_end;
flush_cache_user_range(vma, start, end);
}
}
/*
* Handle all unrecognised system calls.
* 0x9f0000 - 0x9fffff are some more esoteric system calls
*/
#define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE)
asmlinkage int arm_syscall(int no, struct pt_regs *regs)
{
struct thread_info *thread = current_thread_info();
siginfo_t info;
if ((no >> 16) != 0x9f)
return bad_syscall(no, regs);
switch (no & 0xffff) {
case 0: /* branch through 0 */
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = SEGV_MAPERR;
info.si_addr = NULL;
notify_die("branch through zero", regs, &info, 0, 0);
return 0;
case NR(breakpoint): /* SWI BREAK_POINT */
regs->ARM_pc -= thumb_mode(regs) ? 2 : 4;
ptrace_break(current, regs);
return regs->ARM_r0;
/*
* Flush a region from virtual address 'r0' to virtual address 'r1'
* _exclusive_. There is no alignment requirement on either address;
* user space does not need to know the hardware cache layout.
*
* r2 contains flags. It should ALWAYS be passed as ZERO until it
* is defined to be something else. For now we ignore it, but may
* the fires of hell burn in your belly if you break this rule. ;)
*
* (at a later date, we may want to allow this call to not flush
* various aspects of the cache. Passing '0' will guarantee that
* everything necessary gets flushed to maintain consistency in
* the specified region).
*/
case NR(cacheflush):
do_cache_op(regs->ARM_r0, regs->ARM_r1, regs->ARM_r2);
return 0;
case NR(usr26):
if (!(elf_hwcap & HWCAP_26BIT))
break;
regs->ARM_cpsr &= ~MODE32_BIT;
return regs->ARM_r0;
case NR(usr32):
if (!(elf_hwcap & HWCAP_26BIT))
break;
regs->ARM_cpsr |= MODE32_BIT;
return regs->ARM_r0;
case NR(set_tls):
thread->tp_value = regs->ARM_r0;
#if defined(CONFIG_HAS_TLS_REG)
asm ("mcr p15, 0, %0, c13, c0, 3" : : "r" (regs->ARM_r0) );
#elif !defined(CONFIG_TLS_REG_EMUL)
/*
* User space must never try to access this directly.
* Expect your app to break eventually if you do so.
* The user helper at 0xffff0fe0 must be used instead.
* (see entry-armv.S for details)
*/
*((unsigned int *)0xffff0ff0) = regs->ARM_r0;
#endif
return 0;
#ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG
/*
* Atomically store r1 in *r2 if *r2 is equal to r0 for user space.
* Return zero in r0 if *MEM was changed or non-zero if no exchange
* happened. Also set the user C flag accordingly.
* If access permissions have to be fixed up then non-zero is
* returned and the operation has to be re-attempted.
*
* *NOTE*: This is a ghost syscall private to the kernel. Only the
* __kuser_cmpxchg code in entry-armv.S should be aware of its
* existence. Don't ever use this from user code.
*/
case 0xfff0:
{
extern void do_DataAbort(unsigned long addr, unsigned int fsr,
struct pt_regs *regs);
unsigned long val;
unsigned long addr = regs->ARM_r2;
struct mm_struct *mm = current->mm;
pgd_t *pgd; pmd_t *pmd; pte_t *pte;
spinlock_t *ptl;
regs->ARM_cpsr &= ~PSR_C_BIT;
down_read(&mm->mmap_sem);
pgd = pgd_offset(mm, addr);
if (!pgd_present(*pgd))
goto bad_access;
pmd = pmd_offset(pgd, addr);
if (!pmd_present(*pmd))
goto bad_access;
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!pte_present(*pte) || !pte_write(*pte)) {
pte_unmap_unlock(pte, ptl);
goto bad_access;
}
val = *(unsigned long *)addr;
val -= regs->ARM_r0;
if (val == 0) {
*(unsigned long *)addr = regs->ARM_r1;
regs->ARM_cpsr |= PSR_C_BIT;
}
pte_unmap_unlock(pte, ptl);
up_read(&mm->mmap_sem);
return val;
bad_access:
up_read(&mm->mmap_sem);
/* simulate a write access fault */
do_DataAbort(addr, 15 + (1 << 11), regs);
return -1;
}
#endif
default:
/* Calls 9f00xx..9f07ff are defined to return -ENOSYS
if not implemented, rather than raising SIGILL. This
way the calling program can gracefully determine whether
a feature is supported. */
if (no <= 0x7ff)
return -ENOSYS;
break;
}
#ifdef CONFIG_DEBUG_USER
/*
* experience shows that these seem to indicate that
* something catastrophic has happened
*/
if (user_debug & UDBG_SYSCALL) {
printk("[%d] %s: arm syscall %d\n",
current->pid, current->comm, no);
dump_instr(regs);
if (user_mode(regs)) {
__show_regs(regs);
c_backtrace(regs->ARM_fp, processor_mode(regs));
}
}
#endif
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_ILLTRP;
info.si_addr = (void __user *)instruction_pointer(regs) -
(thumb_mode(regs) ? 2 : 4);
notify_die("Oops - bad syscall(2)", regs, &info, no, 0);
return 0;
}
#ifdef CONFIG_TLS_REG_EMUL
/*
* We might be running on an ARMv6+ processor which should have the TLS
* register but for some reason we can't use it, or maybe an SMP system
* using a pre-ARMv6 processor (there are apparently a few prototypes like
* that in existence) and therefore access to that register must be
* emulated.
*/
static int get_tp_trap(struct pt_regs *regs, unsigned int instr)
{
int reg = (instr >> 12) & 15;
if (reg == 15)
return 1;
regs->uregs[reg] = current_thread_info()->tp_value;
regs->ARM_pc += 4;
return 0;
}
static struct undef_hook arm_mrc_hook = {
.instr_mask = 0x0fff0fff,
.instr_val = 0x0e1d0f70,
.cpsr_mask = PSR_T_BIT,
.cpsr_val = 0,
.fn = get_tp_trap,
};
static int __init arm_mrc_hook_init(void)
{
register_undef_hook(&arm_mrc_hook);
return 0;
}
late_initcall(arm_mrc_hook_init);
#endif
void __bad_xchg(volatile void *ptr, int size)
{
printk("xchg: bad data size: pc 0x%p, ptr 0x%p, size %d\n",
__builtin_return_address(0), ptr, size);
BUG();
}
EXPORT_SYMBOL(__bad_xchg);
/*
* A data abort trap was taken, but we did not handle the instruction.
* Try to abort the user program, or panic if it was the kernel.
*/
asmlinkage void
baddataabort(int code, unsigned long instr, struct pt_regs *regs)
{
unsigned long addr = instruction_pointer(regs);
siginfo_t info;
#ifdef CONFIG_DEBUG_USER
if (user_debug & UDBG_BADABORT) {
printk(KERN_ERR "[%d] %s: bad data abort: code %d instr 0x%08lx\n",
current->pid, current->comm, code, instr);
dump_instr(regs);
show_pte(current->mm, addr);
}
#endif
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_ILLOPC;
info.si_addr = (void __user *)addr;
notify_die("unknown data abort code", regs, &info, instr, 0);
}
void __attribute__((noreturn)) __bug(const char *file, int line, void *data)
{
printk(KERN_CRIT"kernel BUG at %s:%d!", file, line);
if (data)
printk(" - extra data = %p", data);
printk("\n");
*(int *)0 = 0;
/* Avoid "noreturn function does return" */
for (;;);
}
EXPORT_SYMBOL(__bug);
void __readwrite_bug(const char *fn)
{
printk("%s called, but not implemented\n", fn);
BUG();
}
EXPORT_SYMBOL(__readwrite_bug);
void __pte_error(const char *file, int line, unsigned long val)
{
printk("%s:%d: bad pte %08lx.\n", file, line, val);
}
void __pmd_error(const char *file, int line, unsigned long val)
{
printk("%s:%d: bad pmd %08lx.\n", file, line, val);
}
void __pgd_error(const char *file, int line, unsigned long val)
{
printk("%s:%d: bad pgd %08lx.\n", file, line, val);
}
asmlinkage void __div0(void)
{
printk("Division by zero in kernel.\n");
dump_stack();
}
EXPORT_SYMBOL(__div0);
void abort(void)
{
BUG();
/* if that doesn't kill us, halt */
panic("Oops failed to kill thread");
}
EXPORT_SYMBOL(abort);
void __init trap_init(void)
{
extern char __stubs_start[], __stubs_end[];
extern char __vectors_start[], __vectors_end[];
extern char __kuser_helper_start[], __kuser_helper_end[];
int kuser_sz = __kuser_helper_end - __kuser_helper_start;
/*
* Copy the vectors, stubs and kuser helpers (in entry-armv.S)
* into the vector page, mapped at 0xffff0000, and ensure these
* are visible to the instruction stream.
*/
memcpy((void *)0xffff0000, __vectors_start, __vectors_end - __vectors_start);
memcpy((void *)0xffff0200, __stubs_start, __stubs_end - __stubs_start);
memcpy((void *)0xffff1000 - kuser_sz, __kuser_helper_start, kuser_sz);
/*
* Copy signal return handlers into the vector page, and
* set sigreturn to be a pointer to these.
*/
memcpy((void *)KERN_SIGRETURN_CODE, sigreturn_codes,
sizeof(sigreturn_codes));
flush_icache_range(0xffff0000, 0xffff0000 + PAGE_SIZE);
modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
}