Contributors: 11
Author Tokens Token Proportion Commits Commit Proportion
Ley Foon Tan 785 90.44% 2 14.29%
Mike Rapoport 39 4.49% 1 7.14%
Chung-Ling Tang 15 1.73% 1 7.14%
Linus Torvalds 10 1.15% 1 7.14%
Michel Lespinasse 7 0.81% 2 14.29%
Peter Xu 5 0.58% 2 14.29%
Ingo Molnar 3 0.35% 1 7.14%
David Hildenbrand 1 0.12% 1 7.14%
Paul Gortmaker 1 0.12% 1 7.14%
Nicholas Piggin 1 0.12% 1 7.14%
Souptick Joarder 1 0.12% 1 7.14%
Total 868 14 


/*
 * Copyright (C) 2009 Wind River Systems Inc
 *   Implemented by fredrik.markstrom@gmail.com and ivarholmqvist@gmail.com
 *
 * based on arch/mips/mm/fault.c which is:
 *
 * Copyright (C) 1995-2000 Ralf Baechle
 *
 * 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.
 */

#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/sched/debug.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/extable.h>
#include <linux/uaccess.h>

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

#define EXC_SUPERV_INSN_ACCESS	9  /* Supervisor only instruction address */
#define EXC_SUPERV_DATA_ACCESS	11 /* Supervisor only data address */
#define EXC_X_PROTECTION_FAULT	13 /* TLB permission violation (x) */
#define EXC_R_PROTECTION_FAULT	14 /* TLB permission violation (r) */
#define EXC_W_PROTECTION_FAULT	15 /* TLB permission violation (w) */

/*
 * 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;
	vm_fault_t fault;
	unsigned int flags = FAULT_FLAG_DEFAULT;

	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 (faulthandler_disabled() || !mm)
		goto bad_area_nosemaphore;

	if (user_mode(regs))
		flags |= FAULT_FLAG_USER;

	if (!mmap_read_trylock(mm)) {
		if (!user_mode(regs) && !search_exception_tables(regs->ea))
			goto bad_area_nosemaphore;
retry:
		mmap_read_lock(mm);
	}

	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;
	}

	/*
	 * 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);

	if (fault_signal_pending(fault, regs))
		return;

	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();
	}

	/*
	 * Major/minor page fault accounting is only done on the
	 * initial attempt. If we go through a retry, it is extremely
	 * likely that the page will be found in page cache at that point.
	 */
	if (flags & FAULT_FLAG_ALLOW_RETRY) {
		if (fault & VM_FAULT_MAJOR)
			current->maj_flt++;
		else
			current->min_flt++;
		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);

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:
	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;

	_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;
		p4d_t *p4d, *p4d_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);

		p4d = p4d_offset(pgd, address);
		p4d_k = p4d_offset(pgd_k, address);
		if (!p4d_present(*p4d_k))
			goto no_context;
		pud = pud_offset(p4d, address);
		pud_k = pud_offset(p4d_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_kernel_page(address);
		return;
	}
}