Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.

#include <linux/signal.h>
#include <linux/module.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/mman.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/version.h>
#include <linux/vt_kern.h>
#include <linux/extable.h>
#include <linux/uaccess.h>
#include <linux/perf_event.h>

#include <asm/hardirq.h>
#include <asm/mmu_context.h>
#include <asm/traps.h>
#include <asm/page.h>

int fixup_exception(struct pt_regs *regs)
{
	const struct exception_table_entry *fixup;

	fixup = search_exception_tables(instruction_pointer(regs));
	if (fixup) {
		regs->pc = fixup->nextinsn;

		return 1;
	}

	return 0;
}

/*
 * 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 write,
			      unsigned long mmu_meh)
{
	struct vm_area_struct *vma = NULL;
	struct task_struct *tsk = current;
	struct mm_struct *mm = tsk->mm;
	int si_code;
	int fault;
	unsigned long address = mmu_meh & PAGE_MASK;

	si_code = SEGV_MAPERR;

#ifndef CONFIG_CPU_HAS_TLBI
	/*
	 * 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) &&
	    unlikely(address <= VMALLOC_END)) {
		/*
		 * 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_offset(address);
		pgd_t *pgd, *pgd_k;
		pud_t *pud, *pud_k;
		pmd_t *pmd, *pmd_k;
		pte_t *pte_k;

		unsigned long pgd_base;

		pgd_base = (unsigned long)__va(get_pgd());
		pgd = (pgd_t *)pgd_base + offset;
		pgd_k = init_mm.pgd + offset;

		if (!pgd_present(*pgd_k))
			goto no_context;
		set_pgd(pgd, *pgd_k);

		pud = (pud_t *)pgd;
		pud_k = (pud_t *)pgd_k;
		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;
		return;
	}
#endif

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
	/*
	 * 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;

	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:
	si_code = SEGV_ACCERR;

	if (write) {
		if (!(vma->vm_flags & VM_WRITE))
			goto bad_area;
	} else {
		if (!(vma->vm_flags & (VM_READ | VM_WRITE | 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.
	 */
	fault = handle_mm_fault(vma, address, 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;
		else if (fault & VM_FAULT_SIGSEGV)
			goto bad_area;
		BUG();
	}
	if (fault & VM_FAULT_MAJOR) {
		tsk->maj_flt++;
		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
			      address);
	} else {
		tsk->min_flt++;
		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
			      address);
	}

	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)) {
		force_sig_fault(SIGSEGV, si_code, (void __user *)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 paging request at virtual "
		 "address 0x%08lx, pc: 0x%08lx\n", address, regs->pc);
	die_if_kernel("Oops", regs, write);

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).
	 */
	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;

	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
}