void
MachineCheckException(struct pt_regs *regs)
{
#ifdef CONFIG_ALL_PPC
unsigned long fixup;
#endif /* CONFIG_ALL_PPC */
if (user_mode(regs)) {
_exception(SIGSEGV, regs);
return;
}
#if defined(CONFIG_8xx) && defined(CONFIG_PCI)
/* the qspan pci read routines can cause machine checks -- Cort */
bad_page_fault(regs, regs->dar);
return;
#endif
#if defined(CONFIG_XMON) || defined(CONFIG_KGDB)
if (debugger_fault_handler) {
debugger_fault_handler(regs);
return;
}
#endif
#ifdef CONFIG_ALL_PPC
/*
* I/O accesses can cause machine checks on powermacs.
* Check if the NIP corresponds to the address of a sync
* instruction for which there is an entry in the exception
* table.
*/
if (regs->msr & (0x80000 | 0x40000)
&& (fixup = search_exception_table(regs->nip)) != 0) {
/*
* Check that it's a sync instruction.
* As the address is in the exception table
* we should be able to read the instr there.
*/
if (*(unsigned int *)regs->nip == 0x7c0004ac) {
unsigned int lsi = ((unsigned int *)regs->nip)[-1];
int rb = (lsi >> 11) & 0x1f;
printk(KERN_DEBUG "%s bad port %lx at %lx\n",
(lsi & 0x100)? "OUT to": "IN from",
regs->gpr[rb] - _IO_BASE, regs->nip);
regs->nip = fixup;
return;
}
}
void
MachineCheckException(struct pt_regs *regs)
{
if ( !user_mode(regs) )
{
#ifdef CONFIG_MBX
/* the mbx pci read routines can cause machine checks -- Cort */
bad_page_fault(regs,regs->dar);
return;
#endif /* CONFIG_MBX */
#if defined(CONFIG_XMON) || defined(CONFIG_KGDB)
if (debugger_fault_handler) {
debugger_fault_handler(regs);
return;
}
#endif
printk("Machine check in kernel mode.\n");
printk("Caused by (from msr): ");
printk("regs %p ",regs);
switch( regs->msr & 0x0000F000)
{
case (1<<12) :
printk("Machine check signal - probably due to mm fault\n"
"with mmu off\n");
break;
case (1<<13) :
printk("Transfer error ack signal\n");
break;
case (1<<14) :
printk("Data parity signal\n");
break;
case (1<<15) :
printk("Address parity signal\n");
break;
default:
printk("Unknown values in msr\n");
}
show_regs(regs);
#if defined(CONFIG_XMON) || defined(CONFIG_KGDB)
debugger(regs);
#endif
print_backtrace((unsigned long *)regs->gpr[1]);
instruction_dump((unsigned long *)regs->nip);
panic("machine check");
}
_exception(SIGSEGV, regs);
}
void
AlignmentException(struct pt_regs *regs)
{
int fixed;
#ifdef __SMP__
if (regs->msr & MSR_FP )
smp_giveup_fpu(current);
#else
if (last_task_used_math == current)
giveup_fpu();
#endif
fixed = fix_alignment(regs);
if (fixed == 1) {
regs->nip += 4; /* skip over emulated instruction */
return;
}
if (fixed == -EFAULT) {
/* fixed == -EFAULT means the operand address was bad */
bad_page_fault(regs, regs->dar);
return;
}
_exception(SIGBUS, regs);
}
void
AlignmentException(struct pt_regs *regs)
{
int fixed;
siginfo_t info;
fixed = fix_alignment(regs);
if (fixed == 1) {
regs->nip += 4; /* skip over emulated instruction */
emulate_single_step(regs);
return;
}
/* Operand address was bad */
if (fixed == -EFAULT) {
if (user_mode(regs)) {
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = SEGV_MAPERR;
info.si_addr = (void *)regs->dar;
force_sig_info(SIGSEGV, &info, current);
} else {
/* Search exception table */
bad_page_fault(regs, regs->dar, SIGSEGV);
}
return;
}
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRALN;
info.si_addr = (void *)regs->nip;
_exception(SIGBUS, &info, regs);
}
void do_page_fault(struct pt_regs *regs)
{
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
unsigned int exccause = regs->exccause;
unsigned int address = regs->excvaddr;
siginfo_t info;
int is_write, is_exec;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
info.si_code = SEGV_MAPERR;
/* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*/
if (address >= TASK_SIZE && !user_mode(regs))
goto vmalloc_fault;
/* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (faulthandler_disabled() || !mm) {
bad_page_fault(regs, address, SIGSEGV);
return;
}
is_write = (exccause == EXCCAUSE_STORE_CACHE_ATTRIBUTE) ? 1 : 0;
is_exec = (exccause == EXCCAUSE_ITLB_PRIVILEGE ||
exccause == EXCCAUSE_ITLB_MISS ||
exccause == EXCCAUSE_FETCH_CACHE_ATTRIBUTE) ? 1 : 0;
#ifdef DEBUG_PAGE_FAULT
printk("[%s:%d:%08x:%d:%08x:%s%s]\n", current->comm, current->pid,
address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
#endif
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
/* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
info.si_code = SEGV_ACCERR;
if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
flags |= FAULT_FLAG_WRITE;
} else if (is_exec) {
if (!(vma->vm_flags & VM_EXEC))
goto bad_area;
} else /* Allow read even from write-only pages. */
if (!(vma->vm_flags & (VM_READ | VM_WRITE)))
goto bad_area;
/* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
}
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR)
current->maj_flt++;
else
current->min_flt++;
if (fault & VM_FAULT_RETRY) {
flags &= ~FAULT_FLAG_ALLOW_RETRY;
flags |= FAULT_FLAG_TRIED;
/* No need to up_read(&mm->mmap_sem) as we would
* have already released it in __lock_page_or_retry
* in mm/filemap.c.
*/
goto retry;
}
}
up_read(&mm->mmap_sem);
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
if (flags & VM_FAULT_MAJOR)
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
else
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
return;
/* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
bad_area:
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
current->thread.bad_vaddr = address;
current->thread.error_code = is_write;
info.si_signo = SIGSEGV;
info.si_errno = 0;
/* info.si_code has been set above */
info.si_addr = (void *) address;
force_sig_info(SIGSEGV, &info, current);
return;
}
bad_page_fault(regs, address, SIGSEGV);
return;
/* We ran out of memory, or some other thing happened to us that made
* us unable to handle the page fault gracefully.
*/
out_of_memory:
up_read(&mm->mmap_sem);
if (!user_mode(regs))
bad_page_fault(regs, address, SIGKILL);
else
pagefault_out_of_memory();
return;
do_sigbus:
up_read(&mm->mmap_sem);
/* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
current->thread.bad_vaddr = address;
info.si_code = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void *) address;
force_sig_info(SIGBUS, &info, current);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
bad_page_fault(regs, address, SIGBUS);
return;
vmalloc_fault:
{
/* Synchronize this task's top level page-table
* with the 'reference' page table.
*/
struct mm_struct *act_mm = current->active_mm;
int index = pgd_index(address);
pgd_t *pgd, *pgd_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
if (act_mm == NULL)
goto bad_page_fault;
pgd = act_mm->pgd + index;
pgd_k = init_mm.pgd + index;
if (!pgd_present(*pgd_k))
goto bad_page_fault;
pgd_val(*pgd) = pgd_val(*pgd_k);
pmd = pmd_offset(pgd, address);
pmd_k = pmd_offset(pgd_k, address);
if (!pmd_present(*pmd) || !pmd_present(*pmd_k))
goto bad_page_fault;
pmd_val(*pmd) = pmd_val(*pmd_k);
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
goto bad_page_fault;
return;
}
bad_page_fault:
bad_page_fault(regs, address, SIGKILL);
return;
}
void do_page_fault(struct pt_regs *regs)
{
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
unsigned int exccause = regs->exccause;
unsigned int address = regs->excvaddr;
siginfo_t info;
int is_write, is_exec;
int fault;
info.si_code = SEGV_MAPERR;
if (address >= TASK_SIZE && !user_mode(regs))
goto vmalloc_fault;
if (in_atomic() || !mm) {
bad_page_fault(regs, address, SIGSEGV);
return;
}
is_write = (exccause == EXCCAUSE_STORE_CACHE_ATTRIBUTE) ? 1 : 0;
is_exec = (exccause == EXCCAUSE_ITLB_PRIVILEGE ||
exccause == EXCCAUSE_ITLB_MISS ||
exccause == EXCCAUSE_FETCH_CACHE_ATTRIBUTE) ? 1 : 0;
#ifdef DEBUG_PAGE_FAULT
printk("[%s:%d:%08x:%d:%08x:%s%s]\n", current->comm, current->pid,
address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
#endif
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
good_area:
info.si_code = SEGV_ACCERR;
if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
} else if (is_exec) {
if (!(vma->vm_flags & VM_EXEC))
goto bad_area;
} else
if (!(vma->vm_flags & (VM_READ | VM_WRITE)))
goto bad_area;
fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
}
if (fault & VM_FAULT_MAJOR)
current->maj_flt++;
else
current->min_flt++;
up_read(&mm->mmap_sem);
return;
bad_area:
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
current->thread.bad_vaddr = address;
current->thread.error_code = is_write;
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_addr = (void *) address;
force_sig_info(SIGSEGV, &info, current);
return;
}
bad_page_fault(regs, address, SIGSEGV);
return;
out_of_memory:
up_read(&mm->mmap_sem);
if (!user_mode(regs))
bad_page_fault(regs, address, SIGKILL);
else
pagefault_out_of_memory();
return;
do_sigbus:
up_read(&mm->mmap_sem);
current->thread.bad_vaddr = address;
info.si_code = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void *) address;
force_sig_info(SIGBUS, &info, current);
if (!user_mode(regs))
bad_page_fault(regs, address, SIGBUS);
vmalloc_fault:
{
struct mm_struct *act_mm = current->active_mm;
int index = pgd_index(address);
pgd_t *pgd, *pgd_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
if (act_mm == NULL)
goto bad_page_fault;
pgd = act_mm->pgd + index;
pgd_k = init_mm.pgd + index;
if (!pgd_present(*pgd_k))
goto bad_page_fault;
pgd_val(*pgd) = pgd_val(*pgd_k);
pmd = pmd_offset(pgd, address);
pmd_k = pmd_offset(pgd_k, address);
if (!pmd_present(*pmd) || !pmd_present(*pmd_k))
goto bad_page_fault;
pmd_val(*pmd) = pmd_val(*pmd_k);
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
goto bad_page_fault;
return;
}
bad_page_fault:
bad_page_fault(regs, address, SIGKILL);
return;
}
/*
* For 600- and 800-family processors, the error_code parameter is DSISR
* for a data fault, SRR1 for an instruction fault. For 400-family processors
* the error_code parameter is ESR for a data fault, 0 for an instruction
* fault.
*/
void do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
siginfo_t info;
int code = SEGV_MAPERR;
#if defined(CONFIG_4xx)
int is_write = error_code & ESR_DST;
#else
int is_write = 0;
/*
* Fortunately the bit assignments in SRR1 for an instruction
* fault and DSISR for a data fault are mostly the same for the
* bits we are interested in. But there are some bits which
* indicate errors in DSISR but can validly be set in SRR1.
*/
if (regs->trap == 0x400)
error_code &= 0x48200000;
else
is_write = error_code & 0x02000000;
#endif /* CONFIG_4xx */
#if defined(CONFIG_XMON) || defined(CONFIG_KGDB)
if (debugger_fault_handler && regs->trap == 0x300) {
debugger_fault_handler(regs);
return;
}
#if !defined(CONFIG_4xx)
if (error_code & 0x00400000) {
/* DABR match */
if (debugger_dabr_match(regs))
return;
}
#endif /* !CONFIG_4xx */
#endif /* CONFIG_XMON || CONFIG_KGDB */
if (in_interrupt() || mm == NULL) {
bad_page_fault(regs, address);
return;
}
down(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
good_area:
code = SEGV_ACCERR;
#if defined(CONFIG_6xx)
if (error_code & 0x95700000)
/* an error such as lwarx to I/O controller space,
address matching DABR, eciwx, etc. */
goto bad_area;
#endif /* CONFIG_6xx */
#if defined(CONFIG_8xx)
/* The MPC8xx seems to always set 0x80000000, which is
* "undefined". Of those that can be set, this is the only
* one which seems bad.
*/
if (error_code & 0x10000000)
/* Guarded storage error. */
goto bad_area;
#endif /* CONFIG_8xx */
/* a write */
if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
/* a read */
} else {
/* protection fault */
if (error_code & 0x08000000)
goto bad_area;
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
switch (handle_mm_fault(mm, vma, address, is_write)) {
case 1:
current->min_flt++;
break;
case 2:
current->maj_flt++;
break;
case 0:
goto do_sigbus;
default:
goto out_of_memory;
}
up(&mm->mmap_sem);
/*
* keep track of tlb+htab misses that are good addrs but
* just need pte's created via handle_mm_fault()
* -- Cort
*/
pte_misses++;
return;
bad_area:
up(&mm->mmap_sem);
pte_errors++;
/* User mode accesses cause a SIGSEGV */
if (user_mode(regs)) {
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = code;
info.si_addr = (void *) address;
force_sig_info(SIGSEGV, &info, current);
return;
}
bad_page_fault(regs, address);
return;
/*
* We ran out of memory, or some other thing happened to us that made
* us unable to handle the page fault gracefully.
*/
out_of_memory:
up(&mm->mmap_sem);
printk("VM: killing process %s\n", current->comm);
if (user_mode(regs))
do_exit(SIGKILL);
bad_page_fault(regs, address);
return;
do_sigbus:
up(&mm->mmap_sem);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void *)address;
force_sig_info (SIGBUS, &info, current);
if (!user_mode(regs))
bad_page_fault(regs, address);
}
void do_page_fault(struct pt_regs *regs)
{
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
unsigned int exccause = regs->exccause;
unsigned int address = regs->excvaddr;
siginfo_t info;
int is_write, is_exec;
is_write = (exccause == EXCCAUSE_STORE_CACHE_ATTRIBUTE) ? 1 : 0;
is_exec = (exccause == EXCCAUSE_ITLB_PRIVILEGE ||
exccause == EXCCAUSE_ITLB_MISS ||
exccause == EXCCAUSE_FETCH_CACHE_ATTRIBUTE) ? 1 : 0;
#if DEBUG_PAGE_FAULT
printk("[%s:%d:%08x:%d:%08lx:%s%s]\n", current->comm, current->pid,
address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
#endif
info.si_code = SEGV_MAPERR;
/* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*/
if (address >= TASK_SIZE && !user_mode(regs))
goto vmalloc_fault;
/* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (in_atomic() || !mm) {
bad_page_fault(regs, address, SIGSEGV);
return;
}
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
/* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
info.si_code = SEGV_ACCERR;
if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
} else if (is_exec) {
if (!(vma->vm_flags & VM_EXEC))
goto bad_area;
} else /* Allow read even from write-only pages. */
if (!(vma->vm_flags & (VM_READ | VM_WRITE)))
goto bad_area;
/* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
survive:
switch (handle_mm_fault(mm, vma, address, is_write)) {
case VM_FAULT_MINOR:
current->min_flt++;
break;
case VM_FAULT_MAJOR:
current->maj_flt++;
break;
case VM_FAULT_SIGBUS:
goto do_sigbus;
case VM_FAULT_OOM:
goto out_of_memory;
default:
BUG();
}
up_read(&mm->mmap_sem);
return;
/* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
bad_area:
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
current->thread.bad_vaddr = address;
current->thread.error_code = is_write;
info.si_signo = SIGSEGV;
info.si_errno = 0;
/* info.si_code has been set above */
info.si_addr = (void *) address;
force_sig_info(SIGSEGV, &info, current);
return;
}
bad_page_fault(regs, address, SIGSEGV);
return;
/* We ran out of memory, or some other thing happened to us that made
* us unable to handle the page fault gracefully.
*/
out_of_memory:
up_read(&mm->mmap_sem);
if (current->pid == 1) {
yield();
down_read(&mm->mmap_sem);
goto survive;
}
printk("VM: killing process %s\n", current->comm);
if (user_mode(regs))
do_exit(SIGKILL);
bad_page_fault(regs, address, SIGKILL);
return;
do_sigbus:
up_read(&mm->mmap_sem);
/* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
current->thread.bad_vaddr = address;
info.si_code = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void *) address;
force_sig_info(SIGBUS, &info, current);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
bad_page_fault(regs, address, SIGBUS);
vmalloc_fault:
{
/* Synchronize this task's top level page-table
* with the 'reference' page table.
*/
struct mm_struct *act_mm = current->active_mm;
int index = pgd_index(address);
pgd_t *pgd, *pgd_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
if (act_mm == NULL)
goto bad_page_fault;
pgd = act_mm->pgd + index;
pgd_k = init_mm.pgd + index;
if (!pgd_present(*pgd_k))
goto bad_page_fault;
pgd_val(*pgd) = pgd_val(*pgd_k);
pmd = pmd_offset(pgd, address);
pmd_k = pmd_offset(pgd_k, address);
if (!pmd_present(*pmd) || !pmd_present(*pmd_k))
goto bad_page_fault;
pmd_val(*pmd) = pmd_val(*pmd_k);
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
goto bad_page_fault;
return;
}
bad_page_fault:
bad_page_fault(regs, address, SIGKILL);
return;
}