mmap.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm/mmap.c
 *
 * Written by obz.
 *
 * Address space accounting code	<alan@lxorguk.ukuu.org.uk>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/mm.h>
#include <linux/vmacache.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/capability.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
#include <linux/profile.h>
#include <linux/export.h>
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
#include <linux/mmdebug.h>
#include <linux/perf_event.h>
#include <linux/audit.h>
#include <linux/khugepaged.h>
#include <linux/uprobes.h>
#include <linux/rbtree_augmented.h>
#include <linux/notifier.h>
#include <linux/memory.h>
#include <linux/printk.h>
#include <linux/userfaultfd_k.h>
#include <linux/moduleparam.h>
#include <linux/pkeys.h>
#include <linux/oom.h>
#include <linux/sched/mm.h>

#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>

#define CREATE_TRACE_POINTS
#include <trace/events/mmap.h>

#include "internal.h"

#ifndef arch_mmap_check
#define arch_mmap_check(addr, len, flags)	(0)
#endif

#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN;
const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX;
int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS;
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN;
const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
#endif

static bool ignore_rlimit_data;
core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);

static void unmap_region(struct mm_struct *mm,
		struct vm_area_struct *vma, struct vm_area_struct *prev,
		unsigned long start, unsigned long end);

/* description of effects of mapping type and prot in current implementation.
 * this is due to the limited x86 page protection hardware.  The expected
 * behavior is in parens:
 *
 * map_type	prot
 *		PROT_NONE	PROT_READ	PROT_WRITE	PROT_EXEC
 * MAP_SHARED	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (yes) yes	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *
 * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 */
pgprot_t protection_map[16] __ro_after_init = {
	__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
	__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
};

#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT
static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
{
	return prot;
}
#endif

pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
	pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags &
				(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
			pgprot_val(arch_vm_get_page_prot(vm_flags)));

	return arch_filter_pgprot(ret);
}
EXPORT_SYMBOL(vm_get_page_prot);

static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
{
	return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
}

/* Update vma->vm_page_prot to reflect vma->vm_flags. */
void vma_set_page_prot(struct vm_area_struct *vma)
{
	unsigned long vm_flags = vma->vm_flags;
	pgprot_t vm_page_prot;

	vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
	if (vma_wants_writenotify(vma, vm_page_prot)) {
		vm_flags &= ~VM_SHARED;
		vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags);
	}
	/* remove_protection_ptes reads vma->vm_page_prot without mmap_sem */
	WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
}

/*
 * Requires inode->i_mapping->i_mmap_rwsem
 */
static void __remove_shared_vm_struct(struct vm_area_struct *vma,
		struct file *file, struct address_space *mapping)
{
	if (vma->vm_flags & VM_DENYWRITE)
		atomic_inc(&file_inode(file)->i_writecount);
	if (vma->vm_flags & VM_SHARED)
		mapping_unmap_writable(mapping);

	flush_dcache_mmap_lock(mapping);
	vma_interval_tree_remove(vma, &mapping->i_mmap);
	flush_dcache_mmap_unlock(mapping);
}

/*
 * Unlink a file-based vm structure from its interval tree, to hide
 * vma from rmap and vmtruncate before freeing its page tables.
 */
void unlink_file_vma(struct vm_area_struct *vma)
{
	struct file *file = vma->vm_file;

	if (file) {
		struct address_space *mapping = file->f_mapping;
		i_mmap_lock_write(mapping);
		__remove_shared_vm_struct(vma, file, mapping);
		i_mmap_unlock_write(mapping);
	}
}

/*
 * Close a vm structure and free it, returning the next.
 */
static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
{
	struct vm_area_struct *next = vma->vm_next;

	might_sleep();
	if (vma->vm_ops && vma->vm_ops->close)
		vma->vm_ops->close(vma);
	if (vma->vm_file)
		fput(vma->vm_file);
	mpol_put(vma_policy(vma));
	vm_area_free(vma);
	return next;
}

static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags,
		struct list_head *uf);
SYSCALL_DEFINE1(brk, unsigned long, brk)
{
	unsigned long retval;
	unsigned long newbrk, oldbrk, origbrk;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *next;
	unsigned long min_brk;
	bool populate;
	bool downgraded = false;
	LIST_HEAD(uf);

	if (down_write_killable(&mm->mmap_sem))
		return -EINTR;

	origbrk = mm->brk;

#ifdef CONFIG_COMPAT_BRK
	/*
	 * CONFIG_COMPAT_BRK can still be overridden by setting
	 * randomize_va_space to 2, which will still cause mm->start_brk
	 * to be arbitrarily shifted
	 */
	if (current->brk_randomized)
		min_brk = mm->start_brk;
	else
		min_brk = mm->end_data;
#else
	min_brk = mm->start_brk;
#endif
	if (brk < min_brk)
		goto out;

	/*
	 * Check against rlimit here. If this check is done later after the test
	 * of oldbrk with newbrk then it can escape the test and let the data
	 * segment grow beyond its set limit the in case where the limit is
	 * not page aligned -Ram Gupta
	 */
	if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk,
			      mm->end_data, mm->start_data))
		goto out;

	newbrk = PAGE_ALIGN(brk);
	oldbrk = PAGE_ALIGN(mm->brk);
	if (oldbrk == newbrk) {
		mm->brk = brk;
		goto success;
	}

	/*
	 * Always allow shrinking brk.
	 * __do_munmap() may downgrade mmap_sem to read.
	 */
	if (brk <= mm->brk) {
		int ret;

		/*
		 * mm->brk must to be protected by write mmap_sem so update it
		 * before downgrading mmap_sem. When __do_munmap() fails,
		 * mm->brk will be restored from origbrk.
		 */
		mm->brk = brk;
		ret = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true);
		if (ret < 0) {
			mm->brk = origbrk;
			goto out;
		} else if (ret == 1) {
			downgraded = true;
		}
		goto success;
	}

	/* Check against existing mmap mappings. */
	next = find_vma(mm, oldbrk);
	if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
		goto out;

	/* Ok, looks good - let it rip. */
	if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
		goto out;
	mm->brk = brk;

success:
	populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
	if (downgraded)
		up_read(&mm->mmap_sem);
	else
		up_write(&mm->mmap_sem);
	userfaultfd_unmap_complete(mm, &uf);
	if (populate)
		mm_populate(oldbrk, newbrk - oldbrk);
	return brk;

out:
	retval = origbrk;
	up_write(&mm->mmap_sem);
	return retval;
}

static inline unsigned long vma_compute_gap(struct vm_area_struct *vma)
{
	unsigned long gap, prev_end;

	/*
	 * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we
	 * allow two stack_guard_gaps between them here, and when choosing
	 * an unmapped area; whereas when expanding we only require one.
	 * That's a little inconsistent, but keeps the code here simpler.
	 */
	gap = vm_start_gap(vma);
	if (vma->vm_prev) {
		prev_end = vm_end_gap(vma->vm_prev);
		if (gap > prev_end)
			gap -= prev_end;
		else
			gap = 0;
	}
	return gap;
}

#ifdef CONFIG_DEBUG_VM_RB
static unsigned long vma_compute_subtree_gap(struct vm_area_struct *vma)
{
	unsigned long max = vma_compute_gap(vma), subtree_gap;
	if (vma->vm_rb.rb_left) {
		subtree_gap = rb_entry(vma->vm_rb.rb_left,
				struct vm_area_struct, vm_rb)->rb_subtree_gap;
		if (subtree_gap > max)
			max = subtree_gap;
	}
	if (vma->vm_rb.rb_right) {
		subtree_gap = rb_entry(vma->vm_rb.rb_right,
				struct vm_area_struct, vm_rb)->rb_subtree_gap;
		if (subtree_gap > max)
			max = subtree_gap;
	}
	return max;
}

static int browse_rb(struct mm_struct *mm)
{
	struct rb_root *root = &mm->mm_rb;
	int i = 0, j, bug = 0;
	struct rb_node *nd, *pn = NULL;
	unsigned long prev = 0, pend = 0;

	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
		struct vm_area_struct *vma;
		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
		if (vma->vm_start < prev) {
			pr_emerg("vm_start %lx < prev %lx\n",
				  vma->vm_start, prev);
			bug = 1;
		}
		if (vma->vm_start < pend) {
			pr_emerg("vm_start %lx < pend %lx\n",
				  vma->vm_start, pend);
			bug = 1;
		}
		if (vma->vm_start > vma->vm_end) {
			pr_emerg("vm_start %lx > vm_end %lx\n",
				  vma->vm_start, vma->vm_end);
			bug = 1;
		}
		spin_lock(&mm->page_table_lock);
		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
			pr_emerg("free gap %lx, correct %lx\n",
			       vma->rb_subtree_gap,
			       vma_compute_subtree_gap(vma));
			bug = 1;
		}
		spin_unlock(&mm->page_table_lock);
		i++;
		pn = nd;
		prev = vma->vm_start;
		pend = vma->vm_end;
	}
	j = 0;
	for (nd = pn; nd; nd = rb_prev(nd))
		j++;
	if (i != j) {
		pr_emerg("backwards %d, forwards %d\n", j, i);
		bug = 1;
	}
	return bug ? -1 : i;
}

static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
{
	struct rb_node *nd;

	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
		struct vm_area_struct *vma;
		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
		VM_BUG_ON_VMA(vma != ignore &&
			vma->rb_subtree_gap != vma_compute_subtree_gap(vma),
			vma);
	}
}

static void validate_mm(struct mm_struct *mm)
{
	int bug = 0;
	int i = 0;
	unsigned long highest_address = 0;
	struct vm_area_struct *vma = mm->mmap;

	while (vma) {
		struct anon_vma *anon_vma = vma->anon_vma;
		struct anon_vma_chain *avc;

		if (anon_vma) {
			anon_vma_lock_read(anon_vma);
			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
				anon_vma_interval_tree_verify(avc);
			anon_vma_unlock_read(anon_vma);
		}

		highest_address = vm_end_gap(vma);
		vma = vma->vm_next;
		i++;
	}
	if (i != mm->map_count) {
		pr_emerg("map_count %d vm_next %d\n", mm->map_count, i);
		bug = 1;
	}
	if (highest_address != mm->highest_vm_end) {
		pr_emerg("mm->highest_vm_end %lx, found %lx\n",
			  mm->highest_vm_end, highest_address);
		bug = 1;
	}
	i = browse_rb(mm);
	if (i != mm->map_count) {
		if (i != -1)
			pr_emerg("map_count %d rb %d\n", mm->map_count, i);
		bug = 1;
	}
	VM_BUG_ON_MM(bug, mm);
}
#else
#define validate_mm_rb(root, ignore) do { } while (0)
#define validate_mm(mm) do { } while (0)
#endif

RB_DECLARE_CALLBACKS_MAX(static, vma_gap_callbacks,
			 struct vm_area_struct, vm_rb,
			 unsigned long, rb_subtree_gap, vma_compute_gap)

/*
 * Update augmented rbtree rb_subtree_gap values after vma->vm_start or
 * vma->vm_prev->vm_end values changed, without modifying the vma's position
 * in the rbtree.
 */
static void vma_gap_update(struct vm_area_struct *vma)
{
	/*
	 * As it turns out, RB_DECLARE_CALLBACKS_MAX() already created
	 * a callback function that does exactly what we want.
	 */
	vma_gap_callbacks_propagate(&vma->vm_rb, NULL);
}

static inline void vma_rb_insert(struct vm_area_struct *vma,
				 struct rb_root *root)
{
	/* All rb_subtree_gap values must be consistent prior to insertion */
	validate_mm_rb(root, NULL);

	rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
}

static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root)
{
	/*
	 * Note rb_erase_augmented is a fairly large inline function,
	 * so make sure we instantiate it only once with our desired
	 * augmented rbtree callbacks.
	 */
	rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
}

static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
						struct rb_root *root,
						struct vm_area_struct *ignore)
{
	/*
	 * All rb_subtree_gap values must be consistent prior to erase,
	 * with the possible exception of the "next" vma being erased if
	 * next->vm_start was reduced.
	 */
	validate_mm_rb(root, ignore);

	__vma_rb_erase(vma, root);
}

static __always_inline void vma_rb_erase(struct vm_area_struct *vma,
					 struct rb_root *root)
{
	/*
	 * All rb_subtree_gap values must be consistent prior to erase,
	 * with the possible exception of the vma being erased.
	 */
	validate_mm_rb(root, vma);

	__vma_rb_erase(vma, root);
}

/*
 * vma has some anon_vma assigned, and is already inserted on that
 * anon_vma's interval trees.
 *
 * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the
 * vma must be removed from the anon_vma's interval trees using
 * anon_vma_interval_tree_pre_update_vma().
 *
 * After the update, the vma will be reinserted using
 * anon_vma_interval_tree_post_update_vma().
 *
 * The entire update must be protected by exclusive mmap_sem and by
 * the root anon_vma's mutex.
 */
static inline void
anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma)
{
	struct anon_vma_chain *avc;

	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
		anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root);
}

static inline void
anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
{
	struct anon_vma_chain *avc;

	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
		anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
}

static int find_vma_links(struct mm_struct *mm, unsigned long addr,
		unsigned long end, struct vm_area_struct **pprev,
		struct rb_node ***rb_link, struct rb_node **rb_parent)
{
	struct rb_node **__rb_link, *__rb_parent, *rb_prev;

	__rb_link = &mm->mm_rb.rb_node;
	rb_prev = __rb_parent = NULL;

	while (*__rb_link) {
		struct vm_area_struct *vma_tmp;

		__rb_parent = *__rb_link;
		vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb);

		if (vma_tmp->vm_end > addr) {
			/* Fail if an existing vma overlaps the area */
			if (vma_tmp->vm_start < end)
				return -ENOMEM;
			__rb_link = &__rb_parent->rb_left;
		} else {
			rb_prev = __rb_parent;
			__rb_link = &__rb_parent->rb_right;
		}
	}

	*pprev = NULL;
	if (rb_prev)
		*pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
	*rb_link = __rb_link;
	*rb_parent = __rb_parent;
	return 0;
}

static unsigned long count_vma_pages_range(struct mm_struct *mm,
		unsigned long addr, unsigned long end)
{
	unsigned long nr_pages = 0;
	struct vm_area_struct *vma;

	/* Find first overlaping mapping */
	vma = find_vma_intersection(mm, addr, end);
	if (!vma)
		return 0;

	nr_pages = (min(end, vma->vm_end) -
		max(addr, vma->vm_start)) >> PAGE_SHIFT;

	/* Iterate over the rest of the overlaps */
	for (vma = vma->vm_next; vma; vma = vma->vm_next) {
		unsigned long overlap_len;

		if (vma->vm_start > end)
			break;

		overlap_len = min(end, vma->vm_end) - vma->vm_start;
		nr_pages += overlap_len >> PAGE_SHIFT;
	}

	return nr_pages;
}

void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
		struct rb_node **rb_link, struct rb_node *rb_parent)
{
	/* Update tracking information for the gap following the new vma. */
	if (vma->vm_next)
		vma_gap_update(vma->vm_next);
	else
		mm->highest_vm_end = vm_end_gap(vma);

	/*
	 * vma->vm_prev wasn't known when we followed the rbtree to find the
	 * correct insertion point for that vma. As a result, we could not
	 * update the vma vm_rb parents rb_subtree_gap values on the way down.
	 * So, we first insert the vma with a zero rb_subtree_gap value
	 * (to be consistent with what we did on the way down), and then
	 * immediately update the gap to the correct value. Finally we
	 * rebalance the rbtree after all augmented values have been set.
	 */
	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
	vma->rb_subtree_gap = 0;
	vma_gap_update(vma);
	vma_rb_insert(vma, &mm->mm_rb);
}

static void __vma_link_file(struct vm_area_struct *vma)
{
	struct file *file;

	file = vma->vm_file;
	if (file) {
		struct address_space *mapping = file->f_mapping;

		if (vma->vm_flags & VM_DENYWRITE)
			atomic_dec(&file_inode(file)->i_writecount);
		if (vma->vm_flags & VM_SHARED)
			atomic_inc(&mapping->i_mmap_writable);

		flush_dcache_mmap_lock(mapping);
		vma_interval_tree_insert(vma, &mapping->i_mmap);
		flush_dcache_mmap_unlock(mapping);
	}
}

static void
__vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
	struct vm_area_struct *prev, struct rb_node **rb_link,
	struct rb_node *rb_parent)
{
	__vma_link_list(mm, vma, prev);
	__vma_link_rb(mm, vma, rb_link, rb_parent);
}

static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
			struct vm_area_struct *prev, struct rb_node **rb_link,
			struct rb_node *rb_parent)
{
	struct address_space *mapping = NULL;

	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;
		i_mmap_lock_write(mapping);
	}

	__vma_link(mm, vma, prev, rb_link, rb_parent);
	__vma_link_file(vma);

	if (mapping)
		i_mmap_unlock_write(mapping);

	mm->map_count++;
	validate_mm(mm);
}

/*
 * Helper for vma_adjust() in the split_vma insert case: insert a vma into the
 * mm's list and rbtree.  It has already been inserted into the interval tree.
 */
static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
{
	struct vm_area_struct *prev;
	struct rb_node **rb_link, *rb_parent;

	if (find_vma_links(mm, vma->vm_start, vma->vm_end,
			   &prev, &rb_link, &rb_parent))
		BUG();
	__vma_link(mm, vma, prev, rb_link, rb_parent);
	mm->map_count++;
}

static __always_inline void __vma_unlink_common(struct mm_struct *mm,
						struct vm_area_struct *vma,
						struct vm_area_struct *ignore)
{
	vma_rb_erase_ignore(vma, &mm->mm_rb, ignore);
	__vma_unlink_list(mm, vma);
	/* Kill the cache */
	vmacache_invalidate(mm);
}

/*
 * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that
 * is already present in an i_mmap tree without adjusting the tree.
 * The following helper function should be used when such adjustments
 * are necessary.  The "insert" vma (if any) is to be inserted
 * before we drop the necessary locks.
 */
int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
	unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert,
	struct vm_area_struct *expand)
{
	struct mm_struct *mm = vma->vm_mm;
	struct vm_area_struct *next = vma->vm_next, *orig_vma = vma;
	struct address_space *mapping = NULL;
	struct rb_root_cached *root = NULL;
	struct anon_vma *anon_vma = NULL;
	struct file *file = vma->vm_file;
	bool start_changed = false, end_changed = false;
	long adjust_next = 0;
	int remove_next = 0;

	if (next && !insert) {
		struct vm_area_struct *exporter = NULL, *importer = NULL;

		if (end >= next->vm_end) {
			/*
			 * vma expands, overlapping all the next, and
			 * perhaps the one after too (mprotect case 6).
			 * The only other cases that gets here are
			 * case 1, case 7 and case 8.
			 */
			if (next == expand) {
				/*
				 * The only case where we don't expand "vma"
				 * and we expand "next" instead is case 8.
				 */
				VM_WARN_ON(end != next->vm_end);
				/*
				 * remove_next == 3 means we're
				 * removing "vma" and that to do so we
				 * swapped "vma" and "next".
				 */
				remove_next = 3;
				VM_WARN_ON(file != next->vm_file);
				swap(vma, next);
			} else {
				VM_WARN_ON(expand != vma);
				/*
				 * case 1, 6, 7, remove_next == 2 is case 6,
				 * remove_next == 1 is case 1 or 7.
				 */
				remove_next = 1 + (end > next->vm_end);
				VM_WARN_ON(remove_next == 2 &&
					   end != next->vm_next->vm_end);
				/* trim end to next, for case 6 first pass */
				end = next->vm_end;
			}

			exporter = next;
			importer = vma;

			/*
			 * If next doesn't have anon_vma, import from vma after
			 * next, if the vma overlaps with it.
			 */
			if (remove_next == 2 && !next->anon_vma)
				exporter = next->vm_next;

		} else if (end > next->vm_start) {
			/*
			 * vma expands, overlapping part of the next:
			 * mprotect case 5 shifting the boundary up.
			 */
			adjust_next = (end - next->vm_start) >> PAGE_SHIFT;
			exporter = next;
			importer = vma;
			VM_WARN_ON(expand != importer);
		} else if (end < vma->vm_end) {
			/*
			 * vma shrinks, and !insert tells it's not
			 * split_vma inserting another: so it must be
			 * mprotect case 4 shifting the boundary down.
			 */
			adjust_next = -((vma->vm_end - end) >> PAGE_SHIFT);
			exporter = vma;
			importer = next;
			VM_WARN_ON(expand != importer);
		}

		/*
		 * Easily overlooked: when mprotect shifts the boundary,
		 * make sure the expanding vma has anon_vma set if the
		 * shrinking vma had, to cover any anon pages imported.
		 */
		if (exporter && exporter->anon_vma && !importer->anon_vma) {
			int error;

			importer->anon_vma = exporter->anon_vma;
			error = anon_vma_clone(importer, exporter);
			if (error)
				return error;
		}
	}
again:
	vma_adjust_trans_huge(orig_vma, start, end, adjust_next);

	if (file) {
		mapping = file->f_mapping;
		root = &mapping->i_mmap;
		uprobe_munmap(vma, vma->vm_start, vma->vm_end);

		if (adjust_next)
			uprobe_munmap(next, next->vm_start, next->vm_end);

		i_mmap_lock_write(mapping);
		if (insert) {
			/*
			 * Put into interval tree now, so instantiated pages
			 * are visible to arm/parisc __flush_dcache_page
			 * throughout; but we cannot insert into address
			 * space until vma start or end is updated.
			 */
			__vma_link_file(insert);
		}
	}

	anon_vma = vma->anon_vma;
	if (!anon_vma && adjust_next)
		anon_vma = next->anon_vma;
	if (anon_vma) {
		VM_WARN_ON(adjust_next && next->anon_vma &&
			   anon_vma != next->anon_vma);
		anon_vma_lock_write(anon_vma);
		anon_vma_interval_tree_pre_update_vma(vma);
		if (adjust_next)
			anon_vma_interval_tree_pre_update_vma(next);
	}

	if (root) {
		flush_dcache_mmap_lock(mapping);
		vma_interval_tree_remove(vma, root);
		if (adjust_next)
			vma_interval_tree_remove(next, root);
	}

	if (start != vma->vm_start) {
		vma->vm_start = start;
		start_changed = true;
	}
	if (end != vma->vm_end) {
		vma->vm_end = end;
		end_changed = true;
	}
	vma->vm_pgoff = pgoff;
	if (adjust_next) {
		next->vm_start += adjust_next << PAGE_SHIFT;
		next->vm_pgoff += adjust_next;
	}

	if (root) {
		if (adjust_next)
			vma_interval_tree_insert(next, root);
		vma_interval_tree_insert(vma, root);
		flush_dcache_mmap_unlock(mapping);
	}

	if (remove_next) {
		/*
		 * vma_merge has merged next into vma, and needs
		 * us to remove next before dropping the locks.
		 */
		if (remove_next != 3)
			__vma_unlink_common(mm, next, next);
		else
			/*
			 * vma is not before next if they've been
			 * swapped.
			 *
			 * pre-swap() next->vm_start was reduced so
			 * tell validate_mm_rb to ignore pre-swap()
			 * "next" (which is stored in post-swap()
			 * "vma").
			 */
			__vma_unlink_common(mm, next, vma);
		if (file)
			__remove_shared_vm_struct(next, file, mapping);
	} else if (insert) {
		/*
		 * split_vma has split insert from vma, and needs
		 * us to insert it before dropping the locks
		 * (it may either follow vma or precede it).
		 */
		__insert_vm_struct(mm, insert);
	} else {
		if (start_changed)
			vma_gap_update(vma);
		if (end_changed) {
			if (!next)
				mm->highest_vm_end = vm_end_gap(vma);
			else if (!adjust_next)
				vma_gap_update(next);
		}
	}

	if (anon_vma) {
		anon_vma_interval_tree_post_update_vma(vma);
		if (adjust_next)
			anon_vma_interval_tree_post_update_vma(next);
		anon_vma_unlock_write(anon_vma);
	}
	if (mapping)
		i_mmap_unlock_write(mapping);

	if (root) {
		uprobe_mmap(vma);

		if (adjust_next)
			uprobe_mmap(next);
	}

	if (remove_next) {
		if (file) {
			uprobe_munmap(next, next->vm_start, next->vm_end);
			fput(file);
		}
		if (next->anon_vma)
			anon_vma_merge(vma, next);
		mm->map_count--;
		mpol_put(vma_policy(next));
		vm_area_free(next);
		/*
		 * In mprotect's case 6 (see comments on vma_merge),
		 * we must remove another next too. It would clutter
		 * up the code too much to do both in one go.
		 */
		if (remove_next != 3) {
			/*
			 * If "next" was removed and vma->vm_end was
			 * expanded (up) over it, in turn
			 * "next->vm_prev->vm_end" changed and the
			 * "vma->vm_next" gap must be updated.
			 */
			next = vma->vm_next;
		} else {
			/*
			 * For the scope of the comment "next" and
			 * "vma" considered pre-swap(): if "vma" was
			 * removed, next->vm_start was expanded (down)
			 * over it and the "next" gap must be updated.
			 * Because of the swap() the post-swap() "vma"
			 * actually points to pre-swap() "next"
			 * (post-swap() "next" as opposed is now a
			 * dangling pointer).
			 */
			next = vma;
		}
		if (remove_next == 2) {
			remove_next = 1;
			end = next->vm_end;
			goto again;
		}
		else if (next)
			vma_gap_update(next);
		else {
			/*
			 * If remove_next == 2 we obviously can't
			 * reach this path.
			 *
			 * If remove_next == 3 we can't reach this
			 * path because pre-swap() next is always not
			 * NULL. pre-swap() "next" is not being
			 * removed and its next->vm_end is not altered
			 * (and furthermore "end" already matches
			 * next->vm_end in remove_next == 3).
			 *
			 * We reach this only in the remove_next == 1
			 * case if the "next" vma that was removed was
			 * the highest vma of the mm. However in such
			 * case next->vm_end == "end" and the extended
			 * "vma" has vma->vm_end == next->vm_end so
			 * mm->highest_vm_end doesn't need any update
			 * in remove_next == 1 case.
			 */
			VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma));
		}
	}
	if (insert && file)
		uprobe_mmap(insert);

	validate_mm(mm);

	return 0;
}

/*
 * If the vma has a ->close operation then the driver probably needs to release
 * per-vma resources, so we don't attempt to merge those.
 */
static inline int is_mergeable_vma(struct vm_area_struct *vma,
				struct file *file, unsigned long vm_flags,
				struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
{
	/*
	 * VM_SOFTDIRTY should not prevent from VMA merging, if we
	 * match the flags but dirty bit -- the caller should mark
	 * merged VMA as dirty. If dirty bit won't be excluded from
	 * comparison, we increase pressure on the memory system forcing
	 * the kernel to generate new VMAs when old one could be
	 * extended instead.
	 */
	if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY)