/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
unsigned long address)
{
struct vm_area_struct *vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
int code = SEGV_MAPERR;
int fault;
unsigned int flags = 0;
cause >>= 2;
/* Restart the instruction */
regs->ea -= 4;
/*
* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*
* NOTE! We MUST NOT take any locks for this case. We may
* be in an interrupt or a critical region, and should
* only copy the information from the master page table,
* nothing more.
*/
if (unlikely(address >= VMALLOC_START && address <= VMALLOC_END)) {
if (user_mode(regs))
goto bad_area_nosemaphore;
else
goto vmalloc_fault;
}
if (unlikely(address >= TASK_SIZE))
goto bad_area_nosemaphore;
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
if (!down_read_trylock(&mm->mmap_sem)) {
if (!user_mode(regs) && !search_exception_tables(regs->ea))
goto bad_area_nosemaphore;
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:
code = SEGV_ACCERR;
switch (cause) {
case EXC_SUPERV_INSN_ACCESS:
goto bad_area;
case EXC_SUPERV_DATA_ACCESS:
goto bad_area;
case EXC_X_PROTECTION_FAULT:
if (!(vma->vm_flags & VM_EXEC))
goto bad_area;
break;
case EXC_R_PROTECTION_FAULT:
if (!(vma->vm_flags & VM_READ))
goto bad_area;
break;
case EXC_W_PROTECTION_FAULT:
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
flags = FAULT_FLAG_WRITE;
break;
}
survive:
/*
* 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(mm, vma, address, flags);
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 (fault & VM_FAULT_MAJOR)
tsk->maj_flt++;
else
tsk->min_flt++;
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);
bad_area_nosemaphore:
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs)) {
if (unhandled_signal(current, SIGSEGV) && printk_ratelimit()) {
pr_info("%s: unhandled page fault (%d) at 0x%08lx, "
"cause %ld\n", current->comm, SIGSEGV, address, cause);
show_regs(regs);
}
_exception(SIGSEGV, regs, code, address);
return;
}
no_context:
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs))
return;
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
bust_spinlocks(1);
pr_alert("Unable to handle kernel %s at virtual address %08lx",
address < PAGE_SIZE ? "NULL pointer dereference" :
"paging request", address);
pr_alert("ea = %08lx, ra = %08lx, cause = %ld\n", regs->ea, regs->ra,
cause);
panic("Oops");
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 (is_global_init(tsk)) {
yield();
down_read(&mm->mmap_sem);
goto survive;
}
if (!user_mode(regs))
goto no_context;
pagefault_out_of_memory();
return;
do_sigbus:
up_read(&mm->mmap_sem);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
goto no_context;
_exception(SIGBUS, regs, BUS_ADRERR, address);
return;
vmalloc_fault:
{
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
*
* Do _not_ use "tsk" here. We might be inside
* an interrupt in the middle of a task switch..
*/
int offset = pgd_index(address);
pgd_t *pgd, *pgd_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
pgd = pgd_current + offset;
pgd_k = init_mm.pgd + offset;
if (!pgd_present(*pgd_k))
goto no_context;
set_pgd(pgd, *pgd_k);
pud = pud_offset(pgd, address);
pud_k = pud_offset(pgd_k, address);
if (!pud_present(*pud_k))
goto no_context;
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd_k))
goto no_context;
set_pmd(pmd, *pmd_k);
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
goto no_context;
flush_tlb_one(address);
return;
}
}
asmlinkage struct pt_regs *do_debug(struct pt_regs *regs)
{
struct thread_info *ti;
unsigned long trampoline_addr;
u32 status;
u32 ctrl;
int code;
status = ocd_read(DS);
ti = current_thread_info();
code = TRAP_BRKPT;
pr_debug("do_debug: status=0x%08x PC=0x%08lx SR=0x%08lx tif=0x%08lx\n",
status, regs->pc, regs->sr, ti->flags);
if (!user_mode(regs)) {
unsigned long die_val = DIE_BREAKPOINT;
if (status & (1 << OCD_DS_SSS_BIT))
die_val = DIE_SSTEP;
if (notify_die(die_val, "ptrace", regs, 0, 0, SIGTRAP)
== NOTIFY_STOP)
return regs;
if ((status & (1 << OCD_DS_SWB_BIT))
&& test_and_clear_ti_thread_flag(
ti, TIF_BREAKPOINT)) {
/*
* Explicit breakpoint from trampoline or
* exception/syscall/interrupt handler.
*
* The real saved regs are on the stack right
* after the ones we saved on entry.
*/
regs++;
pr_debug(" -> TIF_BREAKPOINT done, adjusted regs:"
"PC=0x%08lx SR=0x%08lx\n",
regs->pc, regs->sr);
BUG_ON(!user_mode(regs));
if (test_thread_flag(TIF_SINGLE_STEP)) {
pr_debug("Going to do single step...\n");
return regs;
}
/*
* No TIF_SINGLE_STEP means we're done
* stepping over a syscall. Do the trap now.
*/
code = TRAP_TRACE;
} else if ((status & (1 << OCD_DS_SSS_BIT))
&& test_ti_thread_flag(ti, TIF_SINGLE_STEP)) {
pr_debug("Stepped into something, "
"setting TIF_BREAKPOINT...\n");
set_ti_thread_flag(ti, TIF_BREAKPOINT);
/*
* We stepped into an exception, interrupt or
* syscall handler. Some exception handlers
* don't check for pending work, so we need to
* set up a trampoline just in case.
*
* The exception entry code will undo the
* trampoline stuff if it does a full context
* save (which also means that it'll check for
* pending work later.)
*/
if ((regs->sr & MODE_MASK) == MODE_EXCEPTION) {
trampoline_addr
= (unsigned long)&debug_trampoline;
pr_debug("Setting up trampoline...\n");
ti->rar_saved = sysreg_read(RAR_EX);
ti->rsr_saved = sysreg_read(RSR_EX);
sysreg_write(RAR_EX, trampoline_addr);
sysreg_write(RSR_EX, (MODE_EXCEPTION
| SR_EM | SR_GM));
BUG_ON(ti->rsr_saved & MODE_MASK);
}
/*
* If we stepped into a system call, we
* shouldn't do a single step after we return
* since the return address is right after the
* "scall" instruction we were told to step
* over.
*/
if ((regs->sr & MODE_MASK) == MODE_SUPERVISOR) {
pr_debug("Supervisor; no single step\n");
clear_ti_thread_flag(ti, TIF_SINGLE_STEP);
}
ctrl = ocd_read(DC);
ctrl &= ~(1 << OCD_DC_SS_BIT);
ocd_write(DC, ctrl);
return regs;
} else {
printk(KERN_ERR "Unexpected OCD_DS value: 0x%08x\n",
status);
printk(KERN_ERR "Thread flags: 0x%08lx\n", ti->flags);
die("Unhandled debug trap in kernel mode",
regs, SIGTRAP);
}
} else if (status & (1 << OCD_DS_SSS_BIT)) {
/* Single step in user mode */
code = TRAP_TRACE;
ctrl = ocd_read(DC);
ctrl &= ~(1 << OCD_DC_SS_BIT);
ocd_write(DC, ctrl);
}
pr_debug("Sending SIGTRAP: code=%d PC=0x%08lx SR=0x%08lx\n",
code, regs->pc, regs->sr);
clear_thread_flag(TIF_SINGLE_STEP);
_exception(SIGTRAP, regs, code, instruction_pointer(regs));
return regs;
}
