path: root/mm/madvise.c

// SPDX-License-Identifier: GPL-2.0
/*
 *	linux/mm/madvise.c
 *
 * Copyright (C) 1999  Linus Torvalds
 * Copyright (C) 2002  Christoph Hellwig
 */

#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/mempolicy.h>
#include <linux/page-isolation.h>
#include <linux/page_idle.h>
#include <linux/userfaultfd_k.h>
#include <linux/hugetlb.h>
#include <linux/falloc.h>
#include <linux/fadvise.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/uio.h>
#include <linux/ksm.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/pagewalk.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/mmu_notifier.h>

#include <asm/tlb.h>

#include "internal.h"

struct madvise_walk_private {
	struct mmu_gather *tlb;
	bool pageout;
};

/*
 * Any behaviour which results in changes to the vma->vm_flags needs to
 * take mmap_lock for writing. Others, which simply traverse vmas, need
 * to only take it for reading.
 */
static int madvise_need_mmap_write(int behavior)
{
	switch (behavior) {
	case MADV_REMOVE:
	case MADV_WILLNEED:
	case MADV_DONTNEED:
	case MADV_COLD:
	case MADV_PAGEOUT:
	case MADV_FREE:
		return 0;
	default:
		/* be safe, default to 1. list exceptions explicitly */
		return 1;
	}
}

/*
 * We can potentially split a vm area into separate
 * areas, each area with its own behavior.
 */
static long madvise_behavior(struct vm_area_struct *vma,
		     struct vm_area_struct **prev,
		     unsigned long start, unsigned long end, int behavior)
{
	struct mm_struct *mm = vma->vm_mm;
	int error = 0;
	pgoff_t pgoff;
	unsigned long new_flags = vma->vm_flags;

	switch (behavior) {
	case MADV_NORMAL:
		new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
		break;
	case MADV_SEQUENTIAL:
		new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ;
		break;
	case MADV_RANDOM:
		new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ;
		break;
	case MADV_DONTFORK:
		new_flags |= VM_DONTCOPY;
		break;
	case MADV_DOFORK:
		if (vma->vm_flags & VM_IO) {
			error = -EINVAL;
			goto out;
		}
		new_flags &= ~VM_DONTCOPY;
		break;
	case MADV_WIPEONFORK:
		/* MADV_WIPEONFORK is only supported on anonymous memory. */
		if (vma->vm_file || vma->vm_flags & VM_SHARED) {
			error = -EINVAL;
			goto out;
		}
		new_flags |= VM_WIPEONFORK;
		break;
	case MADV_KEEPONFORK:
		new_flags &= ~VM_WIPEONFORK;
		break;
	case MADV_DONTDUMP:
		new_flags |= VM_DONTDUMP;
		break;
	case MADV_DODUMP:
		if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) {
			error = -EINVAL;
			goto out;
		}
		new_flags &= ~VM_DONTDUMP;
		break;
	case MADV_MERGEABLE:
	case MADV_UNMERGEABLE:
		error = ksm_madvise(vma, start, end, behavior, &new_flags);
		if (error)
			goto out_convert_errno;
		break;
	case MADV_HUGEPAGE:
	case MADV_NOHUGEPAGE:
		error = hugepage_madvise(vma, &new_flags, behavior);
		if (error)
			goto out_convert_errno;
		break;
	}

	if (new_flags == vma->vm_flags) {
		*prev = vma;
		goto out;
	}

	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >>