/* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. * * Copyright (C) 1995 - 2000 by Ralf Baechle
*/ #include <linux/context_tracking.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/types.h> #include <linux/ptrace.h> #include <linux/ratelimit.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/kprobes.h> #include <linux/perf_event.h> #include <linux/uaccess.h>
/* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate * routines.
*/ staticvoid __do_page_fault(struct pt_regs *regs, unsignedlong write, unsignedlong address)
{ struct vm_area_struct * vma = NULL; struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; constint field = sizeof(unsignedlong) * 2; int si_code;
vm_fault_t fault; unsignedint flags = FAULT_FLAG_DEFAULT;
#ifdef CONFIG_KPROBES /* * This is to notify the fault handler of the kprobes.
*/ if (notify_die(DIE_PAGE_FAULT, "page fault", regs, -1,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) return; #endif
si_code = SEGV_MAPERR;
/* * 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.
*/ #ifdef CONFIG_64BIT # define VMALLOC_FAULT_TARGET no_context #else # define VMALLOC_FAULT_TARGET vmalloc_fault #endif
/* * If we're in an interrupt or have no user * context, we must not take the fault..
*/ if (faulthandler_disabled() || !mm) goto bad_area_nosemaphore;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
retry:
vma = lock_mm_and_find_vma(mm, address, regs); if (!vma) goto bad_area_nosemaphore; /* * Ok, we have a good vm_area for this memory access, so * we can handle it..
*/
si_code = SEGV_ACCERR;
if (write) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area;
flags |= FAULT_FLAG_WRITE;
} else { if (cpu_has_rixi) { if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) { #if 0
pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] XI violation\n",
raw_smp_processor_id(),
current->comm, current->pid,
field, address, write,
field, regs->cp0_epc); #endif goto bad_area;
} if (!(vma->vm_flags & VM_READ) &&
exception_epc(regs) != address) { #if 0
pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n",
raw_smp_processor_id(),
current->comm, current->pid,
field, address, write,
field, regs->cp0_epc); #endif goto bad_area;
}
} else { if (unlikely(!vma_is_accessible(vma))) 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, regs);
if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return;
}
/* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return;
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
/* * No need to mmap_read_unlock(mm) as we would * have already released it in __lock_page_or_retry * in mm/filemap.c.
*/
goto retry;
}
mmap_read_unlock(mm); 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:
mmap_read_unlock(mm);
no_context: /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) {
current->thread.cp0_baduaddr = address; return;
}
/* * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice.
*/
bust_spinlocks(1);
printk(KERN_ALERT "CPU %d Unable to handle kernel paging request at " "virtual address %0*lx, epc == %0*lx, ra == %0*lx\n",
raw_smp_processor_id(), field, address, field, regs->cp0_epc,
field, regs->regs[31]);
die("Oops", regs);
out_of_memory: /* * We ran out of memory, call the OOM killer, and return the userspace * (which will retry the fault, or kill us if we got oom-killed).
*/
mmap_read_unlock(mm); if (!user_mode(regs)) goto no_context;
pagefault_out_of_memory(); return;
do_sigbus:
mmap_read_unlock(mm);
/* Kernel mode? Handle exceptions or die */ if (!user_mode(regs)) goto no_context;
/* * Send a sigbus, regardless of whether we were in kernel * or user mode.
*/ #if 0
printk("do_page_fault() #3: sending SIGBUS to %s for " "invalid %s\n%0*lx (epc == %0*lx, ra == %0*lx)\n",
tsk->comm,
write ? "write access to" : "read access from",
field, address,
field, (unsignedlong) regs->cp0_epc,
field, (unsignedlong) regs->regs[31]); #endif
current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
tsk->thread.cp0_badvaddr = address;
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
return; #ifndef CONFIG_64BIT
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;
p4d_t *p4d, *p4d_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.