* Copyright (C) 2001,2002 Andi Kleen, SuSE Labs.
*/
-#include <linux/config.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/kprobes.h>
+#include <linux/uaccess.h>
#include <asm/system.h>
-#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/smp.h>
#include <asm/tlbflush.h>
#define PF_RSVD (1<<3)
#define PF_INSTR (1<<4)
-void bust_spinlocks(int yes)
+static ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain);
+
+/* Hook to register for page fault notifications */
+int register_page_fault_notifier(struct notifier_block *nb)
{
- int loglevel_save = console_loglevel;
- if (yes) {
- oops_in_progress = 1;
- } else {
-#ifdef CONFIG_VT
- unblank_screen();
-#endif
- oops_in_progress = 0;
- /*
- * OK, the message is on the console. Now we call printk()
- * without oops_in_progress set so that printk will give klogd
- * a poke. Hold onto your hats...
- */
- console_loglevel = 15; /* NMI oopser may have shut the console up */
- printk(" ");
- console_loglevel = loglevel_save;
- }
+ vmalloc_sync_all();
+ return atomic_notifier_chain_register(¬ify_page_fault_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_page_fault_notifier);
+
+int unregister_page_fault_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_unregister(¬ify_page_fault_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_page_fault_notifier);
+
+static inline int notify_page_fault(struct pt_regs *regs, long err)
+{
+ struct die_args args = {
+ .regs = regs,
+ .str = "page fault",
+ .err = err,
+ .trapnr = 14,
+ .signr = SIGSEGV
+ };
+ return atomic_notifier_call_chain(¬ify_page_fault_chain,
+ DIE_PAGE_FAULT, &args);
}
/* Sometimes the CPU reports invalid exceptions on prefetch.
if (error_code & PF_INSTR)
return 0;
- instr = (unsigned char *)convert_rip_to_linear(current, regs);
+ instr = (unsigned char __user *)convert_rip_to_linear(current, regs);
max_instr = instr + 15;
if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE)
unsigned char instr_hi;
unsigned char instr_lo;
- if (__get_user(opcode, instr))
+ if (probe_kernel_address(instr, opcode))
break;
instr_hi = opcode & 0xf0;
case 0x00:
/* Prefetch instruction is 0x0F0D or 0x0F18 */
scan_more = 0;
- if (__get_user(opcode, instr))
+ if (probe_kernel_address(instr, opcode))
break;
prefetch = (instr_lo == 0xF) &&
(opcode == 0x0D || opcode == 0x18);
static int bad_address(void *p)
{
unsigned long dummy;
- return __get_user(dummy, (unsigned long *)p);
+ return probe_kernel_address((unsigned long *)p, dummy);
}
void dump_pagetable(unsigned long address)
printk("PGD %lx ", pgd_val(*pgd));
if (!pgd_present(*pgd)) goto ret;
- pud = __pud_offset_k((pud_t *)pgd_page(*pgd), address);
+ pud = pud_offset(pgd, address);
if (bad_address(pud)) goto bad;
printk("PUD %lx ", pud_val(*pud));
if (!pud_present(*pud)) goto ret;
int unhandled_signal(struct task_struct *tsk, int sig)
{
- if (tsk->pid == 1)
+ if (is_init(tsk))
return 1;
if (tsk->ptrace & PT_PTRACED)
return 0;
if (pgd_none(*pgd))
set_pgd(pgd, *pgd_ref);
else
- BUG_ON(pgd_page(*pgd) != pgd_page(*pgd_ref));
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
/* Below here mismatches are bugs because these lower tables
are shared */
pud_ref = pud_offset(pgd_ref, address);
if (pud_none(*pud_ref))
return -1;
- if (pud_none(*pud) || pud_page(*pud) != pud_page(*pud_ref))
+ if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
BUG();
pmd = pmd_offset(pud, address);
pmd_ref = pmd_offset(pud_ref, address);
unsigned long flags;
siginfo_t info;
+ tsk = current;
+ mm = tsk->mm;
+ prefetchw(&mm->mmap_sem);
+
/* get the address */
__asm__("movq %%cr2,%0":"=r" (address));
- tsk = current;
- mm = tsk->mm;
info.si_code = SEGV_MAPERR;
if (vmalloc_fault(address) >= 0)
return;
}
- if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
- SIGSEGV) == NOTIFY_STOP)
+ if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
return;
/*
* Don't take the mm semaphore here. If we fixup a prefetch
goto bad_area_nosemaphore;
}
- if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
- SIGSEGV) == NOTIFY_STOP)
+ if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
return;
if (likely(regs->eflags & X86_EFLAGS_IF))
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunatly, in the case of an
- * erroneous fault occuring in a code path which already holds mmap_sem
+ * erroneous fault occurring in a code path which already holds mmap_sem
* we will deadlock attempting to validate the fault against the
* address space. Luckily the kernel only validly references user
* space from well defined areas of code, which are listed in the
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (error_code & 4) {
- // XXX: align red zone size with ABI
- if (address + 128 < regs->rsp)
+ /* Allow userspace just enough access below the stack pointer
+ * to let the 'enter' instruction work.
+ */
+ if (address + 65536 + 32 * sizeof(unsigned long) < regs->rsp)
goto bad_area;
}
if (expand_stack(vma, address))
case PF_PROT: /* read, present */
goto bad_area;
case 0: /* read, not present */
- if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
goto bad_area;
}
printk(KERN_ALERT "Unable to handle kernel paging request");
printk(" at %016lx RIP: \n" KERN_ALERT,address);
printk_address(regs->rip);
- printk("\n");
dump_pagetable(address);
tsk->thread.cr2 = address;
tsk->thread.trap_no = 14;
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (current->pid == 1) {
+ if (is_init(current)) {
yield();
goto again;
}
if (pgd_none(*pgd))
set_pgd(pgd, *pgd_ref);
else
- BUG_ON(pgd_page(*pgd) != pgd_page(*pgd_ref));
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
}
spin_unlock(&pgd_lock);
set_bit(pgd_index(address), insync);
static int __init enable_pagefaulttrace(char *str)
{
page_fault_trace = 1;
- return 0;
+ return 1;
}
__setup("pagefaulttrace", enable_pagefaulttrace);