/*
 *	linux/mm/mlock.c
 *
 *  (C) Copyright 1995 Linus Torvalds
 *  (C) Copyright 2002 Christoph Hellwig
 */

#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>

#include "internal.h"

int can_do_mlock(void)
{
	if (capable(CAP_IPC_LOCK))
		return 1;
	if (rlimit(RLIMIT_MEMLOCK) != 0)
		return 1;
	return 0;
}
EXPORT_SYMBOL(can_do_mlock);


void __clear_page_mlock(struct page *page)
{
	VM_BUG_ON(!PageLocked(page));

	if (!page->mapping) {	
		return;
	}

	dec_zone_page_state(page, NR_MLOCK);
	count_vm_event(UNEVICTABLE_PGCLEARED);
	if (!isolate_lru_page(page)) {
		putback_lru_page(page);
	} else {
		if (PageUnevictable(page))
			count_vm_event(UNEVICTABLE_PGSTRANDED);
	}
}

void mlock_vma_page(struct page *page)
{
	/* Serialize with page migration */
	BUG_ON(!PageLocked(page));

	if (!TestSetPageMlocked(page)) {
		inc_zone_page_state(page, NR_MLOCK);
		count_vm_event(UNEVICTABLE_PGMLOCKED);
		if (!isolate_lru_page(page))
			putback_lru_page(page);
	}
}

void munlock_vma_page(struct page *page)
{
	/* For try_to_munlock() and to serialize with page migration */
	BUG_ON(!PageLocked(page));

	if (TestClearPageMlocked(page)) {
		dec_zone_page_state(page, NR_MLOCK);
		if (!isolate_lru_page(page)) {
			int ret = SWAP_AGAIN;

			if (page_mapcount(page) > 1)
				ret = try_to_munlock(page);
			if (ret != SWAP_MLOCK)
				count_vm_event(UNEVICTABLE_PGMUNLOCKED);

			putback_lru_page(page);
		} else {
			if (PageUnevictable(page))
				count_vm_event(UNEVICTABLE_PGSTRANDED);
			else
				count_vm_event(UNEVICTABLE_PGMUNLOCKED);
		}
	}
}

static long __mlock_vma_pages_range(struct vm_area_struct *vma,
				    unsigned long start, unsigned long end,
				    int *nonblocking)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long addr = start;
	int nr_pages = (end - start) / PAGE_SIZE;
	int gup_flags;

	VM_BUG_ON(start & ~PAGE_MASK);
	VM_BUG_ON(end   & ~PAGE_MASK);
	VM_BUG_ON(start < vma->vm_start);
	VM_BUG_ON(end   > vma->vm_end);
	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));

	gup_flags = FOLL_TOUCH | FOLL_MLOCK;
	if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
		gup_flags |= FOLL_WRITE;

	if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
		gup_flags |= FOLL_FORCE;

	return __get_user_pages(current, mm, addr, nr_pages, gup_flags,
				NULL, NULL, nonblocking);
}

static int __mlock_posix_error_return(long retval)
{
	if (retval == -EFAULT)
		retval = -ENOMEM;
	else if (retval == -ENOMEM)
		retval = -EAGAIN;
	return retval;
}

long mlock_vma_pages_range(struct vm_area_struct *vma,
			unsigned long start, unsigned long end)
{
	int nr_pages = (end - start) / PAGE_SIZE;
	BUG_ON(!(vma->vm_flags & VM_LOCKED));

	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
		goto no_mlock;

	if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
			is_vm_hugetlb_page(vma) ||
			vma == get_gate_vma(current->mm))) {

		__mlock_vma_pages_range(vma, start, end, NULL);

		
		return 0;
	}

	make_pages_present(start, end);

no_mlock:
	vma->vm_flags &= ~VM_LOCKED;	
	return nr_pages;		
}

void munlock_vma_pages_range(struct vm_area_struct *vma,
			     unsigned long start, unsigned long end)
{
	unsigned long addr;

	lru_add_drain();
	vma->vm_flags &= ~VM_LOCKED;

	for (addr = start; addr < end; addr += PAGE_SIZE) {
		struct page *page;
		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
		if (page && !IS_ERR(page)) {
			lock_page(page);
			if (page->mapping)
				munlock_vma_page(page);
			unlock_page(page);
			put_page(page);
		}
		cond_resched();
	}
}

static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
	unsigned long start, unsigned long end, vm_flags_t newflags)
{
	struct mm_struct *mm = vma->vm_mm;
	pgoff_t pgoff;
	int nr_pages;
	int ret = 0;
	int lock = !!(newflags & VM_LOCKED);

	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
		goto out;	

	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
			  vma->vm_file, pgoff, vma_policy(vma));
	if (*prev) {
		vma = *prev;
		goto success;
	}

	if (start != vma->vm_start) {
		ret = split_vma(mm, vma, start, 1);
		if (ret)
			goto out;
	}

	if (end != vma->vm_end) {
		ret = split_vma(mm, vma, end, 0);
		if (ret)
			goto out;
	}

success:
	nr_pages = (end - start) >> PAGE_SHIFT;
	if (!lock)
		nr_pages = -nr_pages;
	mm->locked_vm += nr_pages;


	if (lock)
		vma->vm_flags = newflags;
	else
		munlock_vma_pages_range(vma, start, end);

out:
	*prev = vma;
	return ret;
}

static int do_mlock(unsigned long start, size_t len, int on)
{
	unsigned long nstart, end, tmp;
	struct vm_area_struct * vma, * prev;
	int error;

	VM_BUG_ON(start & ~PAGE_MASK);
	VM_BUG_ON(len != PAGE_ALIGN(len));
	end = start + len;
	if (end < start)
		return -EINVAL;
	if (end == start)
		return 0;
	vma = find_vma(current->mm, start);
	if (!vma || vma->vm_start > start)
		return -ENOMEM;

	prev = vma->vm_prev;
	if (start > vma->vm_start)
		prev = vma;

	for (nstart = start ; ; ) {
		vm_flags_t newflags;

		

		newflags = vma->vm_flags | VM_LOCKED;
		if (!on)
			newflags &= ~VM_LOCKED;

		tmp = vma->vm_end;
		if (tmp > end)
			tmp = end;
		error = mlock_fixup(vma, &prev, nstart, tmp, newflags);
		if (error)
			break;
		nstart = tmp;
		if (nstart < prev->vm_end)
			nstart = prev->vm_end;
		if (nstart >= end)
			break;

		vma = prev->vm_next;
		if (!vma || vma->vm_start != nstart) {
			error = -ENOMEM;
			break;
		}
	}
	return error;
}

static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors)
{
	struct mm_struct *mm = current->mm;
	unsigned long end, nstart, nend;
	struct vm_area_struct *vma = NULL;
	int locked = 0;
	int ret = 0;

	VM_BUG_ON(start & ~PAGE_MASK);
	VM_BUG_ON(len != PAGE_ALIGN(len));
	end = start + len;

	for (nstart = start; nstart < end; nstart = nend) {
		if (!locked) {
			locked = 1;
			down_read(&mm->mmap_sem);
			vma = find_vma(mm, nstart);
		} else if (nstart >= vma->vm_end)
			vma = vma->vm_next;
		if (!vma || vma->vm_start >= end)
			break;
		nend = min(end, vma->vm_end);
		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
			continue;
		if (nstart < vma->vm_start)
			nstart = vma->vm_start;
		ret = __mlock_vma_pages_range(vma, nstart, nend, &locked);
		if (ret < 0) {
			if (ignore_errors) {
				ret = 0;
				continue;	
			}
			ret = __mlock_posix_error_return(ret);
			break;
		}
		nend = nstart + ret * PAGE_SIZE;
		ret = 0;
	}
	if (locked)
		up_read(&mm->mmap_sem);
	return ret;	
}

SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
	unsigned long locked;
	unsigned long lock_limit;
	int error = -ENOMEM;

	if (!can_do_mlock())
		return -EPERM;

	lru_add_drain_all();	

	down_write(&current->mm->mmap_sem);
	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
	start &= PAGE_MASK;

	locked = len >> PAGE_SHIFT;
	locked += current->mm->locked_vm;

	lock_limit = rlimit(RLIMIT_MEMLOCK);
	lock_limit >>= PAGE_SHIFT;

	
	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
		error = do_mlock(start, len, 1);
	up_write(&current->mm->mmap_sem);
	if (!error)
		error = do_mlock_pages(start, len, 0);
	return error;
}

SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
	int ret;

	down_write(&current->mm->mmap_sem);
	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
	start &= PAGE_MASK;
	ret = do_mlock(start, len, 0);
	up_write(&current->mm->mmap_sem);
	return ret;
}

static int do_mlockall(int flags)
{
	struct vm_area_struct * vma, * prev = NULL;
	unsigned int def_flags = 0;

	if (flags & MCL_FUTURE)
		def_flags = VM_LOCKED;
	current->mm->def_flags = def_flags;
	if (flags == MCL_FUTURE)
		goto out;

	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
		vm_flags_t newflags;

		newflags = vma->vm_flags | VM_LOCKED;
		if (!(flags & MCL_CURRENT))
			newflags &= ~VM_LOCKED;

		
		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
	}
out:
	return 0;
}

SYSCALL_DEFINE1(mlockall, int, flags)
{
	unsigned long lock_limit;
	int ret = -EINVAL;

	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
		goto out;

	ret = -EPERM;
	if (!can_do_mlock())
		goto out;

	if (flags & MCL_CURRENT)
		lru_add_drain_all();	

	down_write(&current->mm->mmap_sem);

	lock_limit = rlimit(RLIMIT_MEMLOCK);
	lock_limit >>= PAGE_SHIFT;

	ret = -ENOMEM;
	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
	    capable(CAP_IPC_LOCK))
		ret = do_mlockall(flags);
	up_write(&current->mm->mmap_sem);
	if (!ret && (flags & MCL_CURRENT)) {
		
		do_mlock_pages(0, TASK_SIZE, 1);
	}
out:
	return ret;
}

SYSCALL_DEFINE0(munlockall)
{
	int ret;

	down_write(&current->mm->mmap_sem);
	ret = do_mlockall(0);
	up_write(&current->mm->mmap_sem);
	return ret;
}

static DEFINE_SPINLOCK(shmlock_user_lock);

int user_shm_lock(size_t size, struct user_struct *user)
{
	unsigned long lock_limit, locked;
	int allowed = 0;

	locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	lock_limit = rlimit(RLIMIT_MEMLOCK);
	if (lock_limit == RLIM_INFINITY)
		allowed = 1;
	lock_limit >>= PAGE_SHIFT;
	spin_lock(&shmlock_user_lock);
	if (!allowed &&
	    locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
		goto out;
	get_uid(user);
	user->locked_shm += locked;
	allowed = 1;
out:
	spin_unlock(&shmlock_user_lock);
	return allowed;
}

void user_shm_unlock(size_t size, struct user_struct *user)
{
	spin_lock(&shmlock_user_lock);
	user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	spin_unlock(&shmlock_user_lock);
	free_uid(user);
}