/* 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.
*/ if (addr < PAGE_SIZE)
msg = "NULL pointer dereference"; else { if (kfence_handle_page_fault(addr, regs->cause == EXC_STORE_PAGE_FAULT, regs)) return;
if (fault & VM_FAULT_OOM) { /* * 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).
*/
pagefault_out_of_memory(); return;
} elseif (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) { /* Kernel mode? Handle exceptions or die */
do_trap(regs, SIGBUS, BUS_ADRERR, addr); return;
} elseif (fault & VM_FAULT_SIGSEGV) {
do_trap(regs, SIGSEGV, SEGV_MAPERR, addr); return;
}
BUG();
}
staticinlinevoid
bad_area_nosemaphore(struct pt_regs *regs, int code, unsignedlong addr)
{ /* * Something tried to access memory that isn't in our memory map. * Fix it, but check if it's kernel or user first.
*/ /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) {
do_trap(regs, SIGSEGV, code, addr); return;
}
/* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) return do_trap(regs, SIGSEGV, code, addr);
/* * Synchronize this task's top level page-table * with the 'reference' page table. * * Do _not_ use "tsk->active_mm->pgd" here. * We might be inside an interrupt in the middle * of a task switch.
*/
index = pgd_index(addr);
pfn = csr_read(CSR_SATP) & SATP_PPN;
pgd = (pgd_t *)pfn_to_virt(pfn) + index;
pgd_k = init_mm.pgd + index;
if (!pgd_present(pgdp_get(pgd_k))) {
no_context(regs, addr); return;
}
set_pgd(pgd, pgdp_get(pgd_k));
pud_k = pud_offset(p4d_k, addr); if (!pud_present(pudp_get(pud_k))) {
no_context(regs, addr); return;
} if (pud_leaf(pudp_get(pud_k))) goto flush_tlb;
/* * Since the vmalloc area is global, it is unnecessary * to copy individual PTEs
*/
pmd_k = pmd_offset(pud_k, addr); if (!pmd_present(pmdp_get(pmd_k))) {
no_context(regs, addr); return;
} if (pmd_leaf(pmdp_get(pmd_k))) goto flush_tlb;
/* * Make sure the actual PTE exists as well to * catch kernel vmalloc-area accesses to non-mapped * addresses. If we don't do this, this will just * silently loop forever.
*/
pte_k = pte_offset_kernel(pmd_k, addr); if (!pte_present(ptep_get(pte_k))) {
no_context(regs, addr); return;
}
/* * The kernel assumes that TLBs don't cache invalid * entries, but in RISC-V, SFENCE.VMA specifies an * ordering constraint, not a cache flush; it is * necessary even after writing invalid entries.
*/
flush_tlb:
local_flush_tlb_page(addr);
}
staticinlinebool access_error(unsignedlong cause, struct vm_area_struct *vma)
{ switch (cause) { case EXC_INST_PAGE_FAULT: if (!(vma->vm_flags & VM_EXEC)) { returntrue;
} break; case EXC_LOAD_PAGE_FAULT: /* Write implies read */ if (!(vma->vm_flags & (VM_READ | VM_WRITE))) { returntrue;
} break; case EXC_STORE_PAGE_FAULT: if (!(vma->vm_flags & VM_WRITE)) { returntrue;
} break; default:
panic("%s: unhandled cause %lu", __func__, cause);
} returnfalse;
}
/* * This routine handles page faults. It determines the address and the * problem, and then passes it off to one of the appropriate routines.
*/ void handle_page_fault(struct pt_regs *regs)
{ struct task_struct *tsk; struct vm_area_struct *vma; struct mm_struct *mm; unsignedlong addr, cause; unsignedint flags = FAULT_FLAG_DEFAULT; int code = SEGV_MAPERR;
vm_fault_t fault;
cause = regs->cause;
addr = regs->badaddr;
tsk = current;
mm = tsk->mm;
if (kprobe_page_fault(regs, cause)) return;
if (user_mode(regs))
trace_page_fault_user(addr, regs, cause); else
trace_page_fault_kernel(addr, regs, cause);
/* * 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 ((!IS_ENABLED(CONFIG_MMU) || !IS_ENABLED(CONFIG_64BIT)) &&
unlikely(addr >= VMALLOC_START && addr < VMALLOC_END)) {
vmalloc_fault(regs, code, addr); return;
}
/* Enable interrupts if they were enabled in the parent context. */ if (!regs_irqs_disabled(regs))
local_irq_enable();
/* * If we're in an interrupt, have no user context, or are running * in an atomic region, then we must not take the fault.
*/ if (unlikely(faulthandler_disabled() || !mm)) {
tsk->thread.bad_cause = cause;
no_context(regs, addr); return;
}
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
if (!user_mode(regs) && addr < TASK_SIZE && unlikely(!(regs->status & SR_SUM))) { if (fixup_exception(regs)) return;
die_kernel_fault("access to user memory without uaccess routines", addr, regs);
}
/* * Ok, we have a good vm_area for this memory access, so * we can handle it.
*/
code = SEGV_ACCERR;
if (unlikely(access_error(cause, vma))) {
tsk->thread.bad_cause = cause;
bad_area(regs, mm, code, addr); return;
}
/* * If for any reason at all we could not handle the fault, * make sure we exit gracefully rather than endlessly redo * the fault.
*/
fault = handle_mm_fault(vma, addr, flags, regs);
/* * If we need to retry but a fatal signal is pending, handle the * signal first. We do not need to release the mmap_lock because it * would already be released in __lock_page_or_retry in mm/filemap.c.
*/ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs))
no_context(regs, addr); return;
}
/* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return;
if (unlikely(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;
}
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.