android_kernel_xiaomi_sm8350/arch/x86/kernel/traps_32.c

1229 lines
31 KiB
C
Raw Normal View History

/*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Pentium III FXSR, SSE support
* Gareth Hughes <gareth@valinux.com>, May 2000
*/
/*
* 'Traps.c' handles hardware traps and faults after we have saved some
* state in 'asm.s'.
*/
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/highmem.h>
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
#include <linux/utsname.h>
#include <linux/kprobes.h>
#include <linux/kexec.h>
#include <linux/unwind.h>
#include <linux/uaccess.h>
#include <linux/nmi.h>
#include <linux/bug.h>
#ifdef CONFIG_EISA
#include <linux/ioport.h>
#include <linux/eisa.h>
#endif
#ifdef CONFIG_MCA
#include <linux/mca.h>
#endif
#if defined(CONFIG_EDAC)
#include <linux/edac.h>
#endif
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/atomic.h>
#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/i387.h>
#include <asm/nmi.h>
#include <asm/unwind.h>
#include <asm/smp.h>
#include <asm/arch_hooks.h>
#include <linux/kdebug.h>
#include <asm/stacktrace.h>
#include <linux/module.h>
#include "mach_traps.h"
int panic_on_unrecovered_nmi;
DECLARE_BITMAP(used_vectors, NR_VECTORS);
EXPORT_SYMBOL_GPL(used_vectors);
asmlinkage int system_call(void);
/* Do we ignore FPU interrupts ? */
char ignore_fpu_irq = 0;
/*
* The IDT has to be page-aligned to simplify the Pentium
* F0 0F bug workaround.. We have a special link segment
* for this.
*/
gate_desc idt_table[256]
__attribute__((__section__(".data.idt"))) = { { { { 0, 0 } } }, };
asmlinkage void divide_error(void);
asmlinkage void debug(void);
asmlinkage void nmi(void);
asmlinkage void int3(void);
asmlinkage void overflow(void);
asmlinkage void bounds(void);
asmlinkage void invalid_op(void);
asmlinkage void device_not_available(void);
asmlinkage void coprocessor_segment_overrun(void);
asmlinkage void invalid_TSS(void);
asmlinkage void segment_not_present(void);
asmlinkage void stack_segment(void);
asmlinkage void general_protection(void);
asmlinkage void page_fault(void);
asmlinkage void coprocessor_error(void);
asmlinkage void simd_coprocessor_error(void);
asmlinkage void alignment_check(void);
asmlinkage void spurious_interrupt_bug(void);
asmlinkage void machine_check(void);
int kstack_depth_to_print = 24;
static unsigned int code_bytes = 64;
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 04:16:30 -05:00
void printk_address(unsigned long address, int reliable)
{
#ifdef CONFIG_KALLSYMS
unsigned long offset = 0, symsize;
const char *symname;
char *modname;
char *delim = ":";
char namebuf[128];
char reliab[4] = "";
symname = kallsyms_lookup(address, &symsize, &offset,
&modname, namebuf);
if (!symname) {
printk(" [<%08lx>]\n", address);
return;
}
if (!reliable)
strcpy(reliab, "? ");
if (!modname)
modname = delim = "";
printk(" [<%08lx>] %s%s%s%s%s+0x%lx/0x%lx\n",
address, reliab, delim, modname, delim, symname, offset, symsize);
#else
printk(" [<%08lx>]\n", address);
#endif
}
static inline int valid_stack_ptr(struct thread_info *tinfo, void *p, unsigned size)
{
return p > (void *)tinfo &&
p <= (void *)tinfo + THREAD_SIZE - size;
}
/* The form of the top of the frame on the stack */
struct stack_frame {
struct stack_frame *next_frame;
unsigned long return_address;
};
static inline unsigned long print_context_stack(struct thread_info *tinfo,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data)
{
struct stack_frame *frame = (struct stack_frame *)bp;
while (valid_stack_ptr(tinfo, stack, sizeof(*stack))) {
unsigned long addr;
addr = *stack;
if (__kernel_text_address(addr)) {
if ((unsigned long) stack == bp + 4) {
ops->address(data, addr, 1);
frame = frame->next_frame;
bp = (unsigned long) frame;
} else {
ops->address(data, addr, bp == 0);
}
}
stack++;
}
return bp;
}
#define MSG(msg) ops->warning(data, msg)
void dump_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data)
{
if (!task)
task = current;
if (!stack) {
unsigned long dummy;
stack = &dummy;
if (task != current)
stack = (unsigned long *)task->thread.sp;
}
#ifdef CONFIG_FRAME_POINTER
if (!bp) {
if (task == current) {
/* Grab bp right from our regs */
asm ("movl %%ebp, %0" : "=r" (bp) : );
} else {
/* bp is the last reg pushed by switch_to */
bp = *(unsigned long *) task->thread.sp;
}
}
#endif
while (1) {
struct thread_info *context;
context = (struct thread_info *)
((unsigned long)stack & (~(THREAD_SIZE - 1)));
bp = print_context_stack(context, stack, bp, ops, data);
/* Should be after the line below, but somewhere
in early boot context comes out corrupted and we
can't reference it -AK */
if (ops->stack(data, "IRQ") < 0)
break;
stack = (unsigned long*)context->previous_esp;
if (!stack)
break;
touch_nmi_watchdog();
}
}
EXPORT_SYMBOL(dump_trace);
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)
{
return 0;
}
/*
* Print one address/symbol entries per line.
*/
static void print_trace_address(void *data, unsigned long addr, int reliable)
{
printk("%s [<%08lx>] ", (char *)data, addr);
if (!reliable)
printk("? ");
print_symbol("%s\n", addr);
touch_nmi_watchdog();
}
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,
};
static void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp, char *log_lvl)
{
dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
printk("%s =======================\n", 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, "");
}
static void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *sp, unsigned long bp, char *log_lvl)
{
unsigned long *stack;
int i;
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 (kstack_end(stack))
break;
if (i && ((i % 8) == 0))
printk("\n%s ", log_lvl);
printk("%08lx ", *stack++);
}
printk("\n%sCall Trace:\n", log_lvl);
show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
void show_stack(struct task_struct *task, unsigned long *sp)
{
printk(" ");
show_stack_log_lvl(task, NULL, sp, 0, "");
}
/*
* The architecture-independent dump_stack generator
*/
void dump_stack(void)
{
unsigned long stack;
unsigned long bp = 0;
#ifdef CONFIG_FRAME_POINTER
if (!bp)
asm("movl %%ebp, %0" : "=r" (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(current, NULL, &stack, bp);
}
EXPORT_SYMBOL(dump_stack);
void show_registers(struct pt_regs *regs)
{
int i;
print_modules();
__show_registers(regs, 0);
printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)",
TASK_COMM_LEN, current->comm, task_pid_nr(current),
current_thread_info(), current, task_thread_info(current));
/*
* When in-kernel, we also print out the stack and code at the
* time of the fault..
*/
if (!user_mode_vm(regs)) {
u8 *ip;
unsigned int code_prologue = code_bytes * 43 / 64;
unsigned int code_len = code_bytes;
unsigned char c;
printk("\n" KERN_EMERG "Stack: ");
show_stack_log_lvl(NULL, regs, &regs->sp, 0, KERN_EMERG);
printk(KERN_EMERG "Code: ");
ip = (u8 *)regs->ip - code_prologue;
if (ip < (u8 *)PAGE_OFFSET ||
probe_kernel_address(ip, c)) {
/* try starting at EIP */
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)) {
printk(" Bad EIP value.");
break;
}
if (ip == (u8 *)regs->ip)
printk("<%02x> ", c);
else
printk("%02x ", c);
}
}
printk("\n");
}
int is_valid_bugaddr(unsigned long ip)
{
unsigned short ud2;
if (ip < PAGE_OFFSET)
return 0;
if (probe_kernel_address((unsigned short *)ip, ud2))
return 0;
return ud2 == 0x0b0f;
}
static int die_counter;
int __kprobes __die(const char * str, struct pt_regs * regs, long err)
{
unsigned long sp;
unsigned short ss;
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");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_no, SIGSEGV) !=
NOTIFY_STOP) {
show_registers(regs);
/* Executive summary in case the oops scrolled away */
sp = (unsigned long) (&regs->sp);
savesegment(ss, ss);
if (user_mode(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
}
printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
print_symbol("%s", regs->ip);
printk(" SS:ESP %04x:%08lx\n", ss, sp);
return 0;
} else {
return 1;
}
}
/*
* 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)
{
static struct {
raw_spinlock_t lock;
u32 lock_owner;
int lock_owner_depth;
} die = {
.lock = __RAW_SPIN_LOCK_UNLOCKED,
.lock_owner = -1,
.lock_owner_depth = 0
};
unsigned long flags;
oops_enter();
if (die.lock_owner != raw_smp_processor_id()) {
console_verbose();
raw_local_irq_save(flags);
__raw_spin_lock(&die.lock);
die.lock_owner = smp_processor_id();
die.lock_owner_depth = 0;
bust_spinlocks(1);
} else
raw_local_irq_save(flags);
if (++die.lock_owner_depth < 3) {
report_bug(regs->ip, regs);
if (__die(str, regs, err))
regs = NULL;
} else {
printk(KERN_EMERG "Recursive die() failure, output suppressed\n");
}
bust_spinlocks(0);
die.lock_owner = -1;
add_taint(TAINT_DIE);
__raw_spin_unlock(&die.lock);
raw_local_irq_restore(flags);
if (!regs)
return;
if (kexec_should_crash(current))
crash_kexec(regs);
if (in_interrupt())
panic("Fatal exception in interrupt");
if (panic_on_oops)
panic("Fatal exception");
oops_exit();
do_exit(SIGSEGV);
}
static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err)
{
if (!user_mode_vm(regs))
die(str, regs, err);
}
static void __kprobes do_trap(int trapnr, int signr, char *str, int vm86,
struct pt_regs * regs, long error_code,
siginfo_t *info)
{
struct task_struct *tsk = current;
if (regs->flags & VM_MASK) {
if (vm86)
goto vm86_trap;
goto trap_signal;
}
if (!user_mode(regs))
goto kernel_trap;
trap_signal: {
/*
* We want error_code and trap_no set for userspace faults and
* kernelspace faults which result in die(), but not
* kernelspace faults which are fixed up. die() gives the
* process no chance to handle the signal and notice the
* kernel fault information, so that won't result in polluting
* the information about previously queued, but not yet
* delivered, faults. See also do_general_protection below.
*/
tsk->thread.error_code = error_code;
tsk->thread.trap_no = trapnr;
if (info)
force_sig_info(signr, info, tsk);
else
force_sig(signr, tsk);
return;
}
kernel_trap: {
if (!fixup_exception(regs)) {
tsk->thread.error_code = error_code;
tsk->thread.trap_no = trapnr;
die(str, regs, error_code);
}
return;
}
vm86_trap: {
int ret = handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, trapnr);
if (ret) goto trap_signal;
return;
}
}
#define DO_ERROR(trapnr, signr, str, name) \
void do_##name(struct pt_regs * regs, long error_code) \
{ \
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
== NOTIFY_STOP) \
return; \
do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \
}
#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr, irq) \
void do_##name(struct pt_regs * regs, long error_code) \
{ \
siginfo_t info; \
if (irq) \
local_irq_enable(); \
info.si_signo = signr; \
info.si_errno = 0; \
info.si_code = sicode; \
info.si_addr = (void __user *)siaddr; \
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
== NOTIFY_STOP) \
return; \
do_trap(trapnr, signr, str, 0, regs, error_code, &info); \
}
#define DO_VM86_ERROR(trapnr, signr, str, name) \
void do_##name(struct pt_regs * regs, long error_code) \
{ \
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
== NOTIFY_STOP) \
return; \
do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \
}
#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
void do_##name(struct pt_regs * regs, long error_code) \
{ \
siginfo_t info; \
info.si_signo = signr; \
info.si_errno = 0; \
info.si_code = sicode; \
info.si_addr = (void __user *)siaddr; \
trace_hardirqs_fixup(); \
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
== NOTIFY_STOP) \
return; \
do_trap(trapnr, signr, str, 1, regs, error_code, &info); \
}
DO_VM86_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip)
#ifndef CONFIG_KPROBES
DO_VM86_ERROR( 3, SIGTRAP, "int3", int3)
#endif
DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow)
DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds)
DO_ERROR_INFO( 6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip, 0)
DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0, 0)
DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0, 1)
void __kprobes do_general_protection(struct pt_regs * regs,
long error_code)
{
int cpu = get_cpu();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
struct thread_struct *thread = &current->thread;
/*
* Perform the lazy TSS's I/O bitmap copy. If the TSS has an
* invalid offset set (the LAZY one) and the faulting thread has
* a valid I/O bitmap pointer, we copy the I/O bitmap in the TSS
* and we set the offset field correctly. Then we let the CPU to
* restart the faulting instruction.
*/
if (tss->x86_tss.io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY &&
thread->io_bitmap_ptr) {
memcpy(tss->io_bitmap, thread->io_bitmap_ptr,
thread->io_bitmap_max);
/*
* If the previously set map was extending to higher ports
* than the current one, pad extra space with 0xff (no access).
*/
if (thread->io_bitmap_max < tss->io_bitmap_max)
memset((char *) tss->io_bitmap +
thread->io_bitmap_max, 0xff,
tss->io_bitmap_max - thread->io_bitmap_max);
tss->io_bitmap_max = thread->io_bitmap_max;
tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
tss->io_bitmap_owner = thread;
put_cpu();
return;
}
put_cpu();
if (regs->flags & VM_MASK)
goto gp_in_vm86;
if (!user_mode(regs))
goto gp_in_kernel;
current->thread.error_code = error_code;
current->thread.trap_no = 13;
if (show_unhandled_signals && unhandled_signal(current, SIGSEGV) &&
printk_ratelimit()) {
printk(KERN_INFO
"%s[%d] general protection ip:%lx sp:%lx error:%lx",
current->comm, task_pid_nr(current),
regs->ip, regs->sp, error_code);
print_vma_addr(" in ", regs->ip);
printk("\n");
}
force_sig(SIGSEGV, current);
return;
gp_in_vm86:
local_irq_enable();
handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
return;
gp_in_kernel:
if (!fixup_exception(regs)) {
current->thread.error_code = error_code;
current->thread.trap_no = 13;
if (notify_die(DIE_GPF, "general protection fault", regs,
error_code, 13, SIGSEGV) == NOTIFY_STOP)
return;
die("general protection fault", regs, error_code);
}
}
static __kprobes void
mem_parity_error(unsigned char reason, struct pt_regs * regs)
{
printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on "
"CPU %d.\n", reason, smp_processor_id());
printk(KERN_EMERG "You have some hardware problem, likely on the PCI bus.\n");
#if defined(CONFIG_EDAC)
if(edac_handler_set()) {
edac_atomic_assert_error();
return;
}
#endif
if (panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
/* Clear and disable the memory parity error line. */
clear_mem_error(reason);
}
static __kprobes void
io_check_error(unsigned char reason, struct pt_regs * regs)
{
unsigned long i;
printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
show_registers(regs);
/* Re-enable the IOCK line, wait for a few seconds */
reason = (reason & 0xf) | 8;
outb(reason, 0x61);
i = 2000;
while (--i) udelay(1000);
reason &= ~8;
outb(reason, 0x61);
}
static __kprobes void
unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
{
if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
return;
#ifdef CONFIG_MCA
/* Might actually be able to figure out what the guilty party
* is. */
if( MCA_bus ) {
mca_handle_nmi();
return;
}
#endif
printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on "
"CPU %d.\n", reason, smp_processor_id());
printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
if (panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
}
static DEFINE_SPINLOCK(nmi_print_lock);
void __kprobes die_nmi(struct pt_regs *regs, const char *msg)
{
if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 2, SIGINT) ==
NOTIFY_STOP)
return;
spin_lock(&nmi_print_lock);
/*
* We are in trouble anyway, lets at least try
* to get a message out.
*/
bust_spinlocks(1);
printk(KERN_EMERG "%s", msg);
printk(" on CPU%d, ip %08lx, registers:\n",
smp_processor_id(), regs->ip);
show_registers(regs);
console_silent();
spin_unlock(&nmi_print_lock);
bust_spinlocks(0);
/* If we are in kernel we are probably nested up pretty bad
* and might aswell get out now while we still can.
*/
if (!user_mode_vm(regs)) {
current->thread.trap_no = 2;
crash_kexec(regs);
}
do_exit(SIGSEGV);
}
static __kprobes void default_do_nmi(struct pt_regs * regs)
{
unsigned char reason = 0;
/* Only the BSP gets external NMIs from the system. */
if (!smp_processor_id())
reason = get_nmi_reason();
if (!(reason & 0xc0)) {
if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
== NOTIFY_STOP)
return;
#ifdef CONFIG_X86_LOCAL_APIC
/*
* Ok, so this is none of the documented NMI sources,
* so it must be the NMI watchdog.
*/
if (nmi_watchdog_tick(regs, reason))
return;
if (!do_nmi_callback(regs, smp_processor_id()))
#endif
unknown_nmi_error(reason, regs);
return;
}
if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
return;
if (reason & 0x80)
mem_parity_error(reason, regs);
if (reason & 0x40)
io_check_error(reason, regs);
/*
* Reassert NMI in case it became active meanwhile
* as it's edge-triggered.
*/
reassert_nmi();
}
static int ignore_nmis;
__kprobes void do_nmi(struct pt_regs * regs, long error_code)
{
int cpu;
nmi_enter();
cpu = smp_processor_id();
[PATCH] i386 CPU hotplug (The i386 CPU hotplug patch provides infrastructure for some work which Pavel is doing as well as for ACPI S3 (suspend-to-RAM) work which Li Shaohua <shaohua.li@intel.com> is doing) The following provides i386 architecture support for safely unregistering and registering processors during runtime, updated for the current -mm tree. In order to avoid dumping cpu hotplug code into kernel/irq/* i dropped the cpu_online check in do_IRQ() by modifying fixup_irqs(). The difference being that on cpu offline, fixup_irqs() is called before we clear the cpu from cpu_online_map and a long delay in order to ensure that we never have any queued external interrupts on the APICs. There are additional changes to s390 and ppc64 to account for this change. 1) Add CONFIG_HOTPLUG_CPU 2) disable local APIC timer on dead cpus. 3) Disable preempt around irq balancing to prevent CPUs going down. 4) Print irq stats for all possible cpus. 5) Debugging check for interrupts on offline cpus. 6) Hacky fixup_irqs() to redirect irqs when cpus go off/online. 7) play_dead() for offline cpus to spin inside. 8) Handle offline cpus set in flush_tlb_others(). 9) Grab lock earlier in smp_call_function() to prevent CPUs going down. 10) Implement __cpu_disable() and __cpu_die(). 11) Enable local interrupts in cpu_enable() after fixup_irqs() 12) Don't fiddle with NMI on dead cpu, but leave intact on other cpus. 13) Program IRQ affinity whilst cpu is still in cpu_online_map on offline. Signed-off-by: Zwane Mwaikambo <zwane@linuxpower.ca> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-25 17:54:50 -04:00
++nmi_count(cpu);
if (!ignore_nmis)
default_do_nmi(regs);
nmi_exit();
}
void stop_nmi(void)
{
acpi_nmi_disable();
ignore_nmis++;
}
void restart_nmi(void)
{
ignore_nmis--;
acpi_nmi_enable();
}
#ifdef CONFIG_KPROBES
void __kprobes do_int3(struct pt_regs *regs, long error_code)
{
trace_hardirqs_fixup();
if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
== NOTIFY_STOP)
return;
/* This is an interrupt gate, because kprobes wants interrupts
disabled. Normal trap handlers don't. */
restore_interrupts(regs);
do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL);
}
#endif
/*
* Our handling of the processor debug registers is non-trivial.
* We do not clear them on entry and exit from the kernel. Therefore
* it is possible to get a watchpoint trap here from inside the kernel.
* However, the code in ./ptrace.c has ensured that the user can
* only set watchpoints on userspace addresses. Therefore the in-kernel
* watchpoint trap can only occur in code which is reading/writing
* from user space. Such code must not hold kernel locks (since it
* can equally take a page fault), therefore it is safe to call
* force_sig_info even though that claims and releases locks.
*
* Code in ./signal.c ensures that the debug control register
* is restored before we deliver any signal, and therefore that
* user code runs with the correct debug control register even though
* we clear it here.
*
* Being careful here means that we don't have to be as careful in a
* lot of more complicated places (task switching can be a bit lazy
* about restoring all the debug state, and ptrace doesn't have to
* find every occurrence of the TF bit that could be saved away even
* by user code)
*/
void __kprobes do_debug(struct pt_regs * regs, long error_code)
{
unsigned int condition;
struct task_struct *tsk = current;
lockdep: annotate do_debug() trap handler Ensure the hardirq state is consistent before using locks. Use the rare trace_hardirqs_fixup() because the trap can happen in any context. resolves this rare lockdep warning: WARNING: at kernel/lockdep.c:2658 check_flags() [<c013571e>] check_flags+0x90/0x140 [<c0138a69>] lock_release+0x4b/0x1d0 [<c0507fea>] notifier_call_chain+0x2a/0x47 [<c050806b>] __atomic_notifier_call_chain+0x64/0x6d [<c0508007>] __atomic_notifier_call_chain+0x0/0x6d [<c050808b>] atomic_notifier_call_chain+0x17/0x1a [<c0131802>] notify_die+0x30/0x34 [<c0506b09>] do_debug+0x3e/0xd4 [<c050658f>] debug_stack_correct+0x27/0x2c [<c04be389>] tcp_rcv_established+0x1/0x620 [<c04c38c2>] tcp_v4_do_rcv+0x2b/0x313 [<c04c56b6>] tcp_v4_rcv+0x467/0x85d [<c0505ff2>] _spin_lock_nested+0x27/0x32 [<c04c5a4d>] tcp_v4_rcv+0x7fe/0x85d [<c04c560e>] tcp_v4_rcv+0x3bf/0x85d [<c04adbb5>] ip_local_deliver_finish+0x11b/0x1b0 [<c04adac8>] ip_local_deliver_finish+0x2e/0x1b0 [<c04ada7b>] ip_rcv_finish+0x27b/0x29a [<c04961e5>] netif_receive_skb+0xfb/0x2a6 [<c04add0f>] ip_rcv+0x0/0x1fb [<c0496354>] netif_receive_skb+0x26a/0x2a6 [<c04961e5>] netif_receive_skb+0xfb/0x2a6 [<c049872e>] process_backlog+0x7f/0xc6 [<c04983ba>] net_rx_action+0xb9/0x1ac [<c0498348>] net_rx_action+0x47/0x1ac [<c01376cb>] trace_hardirqs_on+0x118/0x16b [<c01225e2>] __do_softirq+0x49/0xa2 [<c010595f>] do_softirq+0x60/0xdd [<c0506300>] _spin_unlock_irq+0x20/0x2c [<c0103e4f>] restore_nocheck+0x12/0x15 [<c01440e1>] handle_fasteoi_irq+0x0/0x9b [<c0105a70>] do_IRQ+0x94/0xaa [<c0506300>] _spin_unlock_irq+0x20/0x2c [<c0104832>] common_interrupt+0x2e/0x34 [<c0114703>] native_safe_halt+0x2/0x3 [<c0102c01>] default_idle+0x44/0x65 [<c010257f>] cpu_idle+0x42/0x50 [<c076ea09>] start_kernel+0x26b/0x270 [<c076e317>] unknown_bootoption+0x0/0x196 ======================= irq event stamp: 559190 hardirqs last enabled at (559190): [<c0507316>] kprobe_exceptions_notify+0x299/0x305 hardirqs last disabled at (559189): [<c05067bf>] do_int3+0x1d/0x95 softirqs last enabled at (559172): [<c010595f>] do_softirq+0x60/0xdd softirqs last disabled at (559181): [<c010595f>] do_softirq+0x60/0xdd Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2007-11-26 14:42:19 -05:00
trace_hardirqs_fixup();
get_debugreg(condition, 6);
/*
* The processor cleared BTF, so don't mark that we need it set.
*/
clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR);
tsk->thread.debugctlmsr = 0;
if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
SIGTRAP) == NOTIFY_STOP)
return;
/* It's safe to allow irq's after DR6 has been saved */
if (regs->flags & X86_EFLAGS_IF)
local_irq_enable();
/* Mask out spurious debug traps due to lazy DR7 setting */
if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
if (!tsk->thread.debugreg7)
goto clear_dr7;
}
if (regs->flags & VM_MASK)
goto debug_vm86;
/* Save debug status register where ptrace can see it */
tsk->thread.debugreg6 = condition;
/*
* Single-stepping through TF: make sure we ignore any events in
* kernel space (but re-enable TF when returning to user mode).
*/
if (condition & DR_STEP) {
/*
* We already checked v86 mode above, so we can
* check for kernel mode by just checking the CPL
* of CS.
*/
if (!user_mode(regs))
goto clear_TF_reenable;
}
/* Ok, finally something we can handle */
send_sigtrap(tsk, regs, error_code);
/* Disable additional traps. They'll be re-enabled when
* the signal is delivered.
*/
clear_dr7:
set_debugreg(0, 7);
return;
debug_vm86:
handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
return;
clear_TF_reenable:
set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
regs->flags &= ~TF_MASK;
return;
}
/*
* Note that we play around with the 'TS' bit in an attempt to get
* the correct behaviour even in the presence of the asynchronous
* IRQ13 behaviour
*/
void math_error(void __user *ip)
{
struct task_struct * task;
siginfo_t info;
unsigned short cwd, swd;
/*
* Save the info for the exception handler and clear the error.
*/
task = current;
save_init_fpu(task);
task->thread.trap_no = 16;
task->thread.error_code = 0;
info.si_signo = SIGFPE;
info.si_errno = 0;
info.si_code = __SI_FAULT;
info.si_addr = ip;
/*
* (~cwd & swd) will mask out exceptions that are not set to unmasked
* status. 0x3f is the exception bits in these regs, 0x200 is the
* C1 reg you need in case of a stack fault, 0x040 is the stack
* fault bit. We should only be taking one exception at a time,
* so if this combination doesn't produce any single exception,
* then we have a bad program that isn't syncronizing its FPU usage
* and it will suffer the consequences since we won't be able to
* fully reproduce the context of the exception
*/
cwd = get_fpu_cwd(task);
swd = get_fpu_swd(task);
switch (swd & ~cwd & 0x3f) {
case 0x000: /* No unmasked exception */
return;
default: /* Multiple exceptions */
break;
case 0x001: /* Invalid Op */
/*
* swd & 0x240 == 0x040: Stack Underflow
* swd & 0x240 == 0x240: Stack Overflow
* User must clear the SF bit (0x40) if set
*/
info.si_code = FPE_FLTINV;
break;
case 0x002: /* Denormalize */
case 0x010: /* Underflow */
info.si_code = FPE_FLTUND;
break;
case 0x004: /* Zero Divide */
info.si_code = FPE_FLTDIV;
break;
case 0x008: /* Overflow */
info.si_code = FPE_FLTOVF;
break;
case 0x020: /* Precision */
info.si_code = FPE_FLTRES;
break;
}
force_sig_info(SIGFPE, &info, task);
}
void do_coprocessor_error(struct pt_regs * regs, long error_code)
{
ignore_fpu_irq = 1;
math_error((void __user *)regs->ip);
}
static void simd_math_error(void __user *ip)
{
struct task_struct * task;
siginfo_t info;
unsigned short mxcsr;
/*
* Save the info for the exception handler and clear the error.
*/
task = current;
save_init_fpu(task);
task->thread.trap_no = 19;
task->thread.error_code = 0;
info.si_signo = SIGFPE;
info.si_errno = 0;
info.si_code = __SI_FAULT;
info.si_addr = ip;
/*
* The SIMD FPU exceptions are handled a little differently, as there
* is only a single status/control register. Thus, to determine which
* unmasked exception was caught we must mask the exception mask bits
* at 0x1f80, and then use these to mask the exception bits at 0x3f.
*/
mxcsr = get_fpu_mxcsr(task);
switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
case 0x000:
default:
break;
case 0x001: /* Invalid Op */
info.si_code = FPE_FLTINV;
break;
case 0x002: /* Denormalize */
case 0x010: /* Underflow */
info.si_code = FPE_FLTUND;
break;
case 0x004: /* Zero Divide */
info.si_code = FPE_FLTDIV;
break;
case 0x008: /* Overflow */
info.si_code = FPE_FLTOVF;
break;
case 0x020: /* Precision */
info.si_code = FPE_FLTRES;
break;
}
force_sig_info(SIGFPE, &info, task);
}
void do_simd_coprocessor_error(struct pt_regs * regs,
long error_code)
{
if (cpu_has_xmm) {
/* Handle SIMD FPU exceptions on PIII+ processors. */
ignore_fpu_irq = 1;
simd_math_error((void __user *)regs->ip);
} else {
/*
* Handle strange cache flush from user space exception
* in all other cases. This is undocumented behaviour.
*/
if (regs->flags & VM_MASK) {
handle_vm86_fault((struct kernel_vm86_regs *)regs,
error_code);
return;
}
current->thread.trap_no = 19;
current->thread.error_code = error_code;
die_if_kernel("cache flush denied", regs, error_code);
force_sig(SIGSEGV, current);
}
}
void do_spurious_interrupt_bug(struct pt_regs * regs,
long error_code)
{
#if 0
/* No need to warn about this any longer. */
printk("Ignoring P6 Local APIC Spurious Interrupt Bug...\n");
#endif
}
unsigned long patch_espfix_desc(unsigned long uesp,
unsigned long kesp)
{
struct desc_struct *gdt = __get_cpu_var(gdt_page).gdt;
unsigned long base = (kesp - uesp) & -THREAD_SIZE;
unsigned long new_kesp = kesp - base;
unsigned long lim_pages = (new_kesp | (THREAD_SIZE - 1)) >> PAGE_SHIFT;
__u64 desc = *(__u64 *)&gdt[GDT_ENTRY_ESPFIX_SS];
/* Set up base for espfix segment */
desc &= 0x00f0ff0000000000ULL;
desc |= ((((__u64)base) << 16) & 0x000000ffffff0000ULL) |
((((__u64)base) << 32) & 0xff00000000000000ULL) |
((((__u64)lim_pages) << 32) & 0x000f000000000000ULL) |
(lim_pages & 0xffff);
*(__u64 *)&gdt[GDT_ENTRY_ESPFIX_SS] = desc;
return new_kesp;
}
/*
* 'math_state_restore()' saves the current math information in the
* old math state array, and gets the new ones from the current task
*
* Careful.. There are problems with IBM-designed IRQ13 behaviour.
* Don't touch unless you *really* know how it works.
*
* Must be called with kernel preemption disabled (in this case,
* local interrupts are disabled at the call-site in entry.S).
*/
asmlinkage void math_state_restore(void)
{
struct thread_info *thread = current_thread_info();
struct task_struct *tsk = thread->task;
clts(); /* Allow maths ops (or we recurse) */
if (!tsk_used_math(tsk))
init_fpu(tsk);
restore_fpu(tsk);
thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */
tsk->fpu_counter++;
}
EXPORT_SYMBOL_GPL(math_state_restore);
#ifndef CONFIG_MATH_EMULATION
asmlinkage void math_emulate(long arg)
{
printk(KERN_EMERG "math-emulation not enabled and no coprocessor found.\n");
printk(KERN_EMERG "killing %s.\n",current->comm);
force_sig(SIGFPE,current);
schedule();
}
#endif /* CONFIG_MATH_EMULATION */
void __init trap_init(void)
{
int i;
#ifdef CONFIG_EISA
void __iomem *p = early_ioremap(0x0FFFD9, 4);
if (readl(p) == 'E'+('I'<<8)+('S'<<16)+('A'<<24)) {
EISA_bus = 1;
}
early_iounmap(p, 4);
#endif
#ifdef CONFIG_X86_LOCAL_APIC
init_apic_mappings();
#endif
set_trap_gate(0,&divide_error);
set_intr_gate(1,&debug);
set_intr_gate(2,&nmi);
set_system_intr_gate(3, &int3); /* int3/4 can be called from all */
set_system_gate(4,&overflow);
set_trap_gate(5,&bounds);
set_trap_gate(6,&invalid_op);
set_trap_gate(7,&device_not_available);
set_task_gate(8,GDT_ENTRY_DOUBLEFAULT_TSS);
set_trap_gate(9,&coprocessor_segment_overrun);
set_trap_gate(10,&invalid_TSS);
set_trap_gate(11,&segment_not_present);
set_trap_gate(12,&stack_segment);
set_trap_gate(13,&general_protection);
set_intr_gate(14,&page_fault);
set_trap_gate(15,&spurious_interrupt_bug);
set_trap_gate(16,&coprocessor_error);
set_trap_gate(17,&alignment_check);
#ifdef CONFIG_X86_MCE
set_trap_gate(18,&machine_check);
#endif
set_trap_gate(19,&simd_coprocessor_error);
/*
* Verify that the FXSAVE/FXRSTOR data will be 16-byte aligned.
* Generate a build-time error if the alignment is wrong.
*/
BUILD_BUG_ON(offsetof(struct task_struct, thread.i387.fxsave) & 15);
if (cpu_has_fxsr) {
printk(KERN_INFO "Enabling fast FPU save and restore... ");
set_in_cr4(X86_CR4_OSFXSR);
printk("done.\n");
}
if (cpu_has_xmm) {
printk(KERN_INFO "Enabling unmasked SIMD FPU exception "
"support... ");
set_in_cr4(X86_CR4_OSXMMEXCPT);
printk("done.\n");
}
set_system_gate(SYSCALL_VECTOR,&system_call);
/* Reserve all the builtin and the syscall vector. */
for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
set_bit(i, used_vectors);
set_bit(SYSCALL_VECTOR, used_vectors);
/*
* Should be a barrier for any external CPU state.
*/
cpu_init();
trap_init_hook();
}
static int __init kstack_setup(char *s)
{
kstack_depth_to_print = simple_strtoul(s, NULL, 0);
return 1;
}
__setup("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);