Revision a57b70519d1f7c53be98478623652738e5ac70d5 authored by Liam Howlett on 18 October 2022, 19:17:12 UTC, committed by Andrew Morton on 21 October 2022, 04:27:23 UTC
mmap should return the start address of newly mapped area when successful.
On a successful merge of a VMA, the return address was changed and thus
was violating that expectation from userspace.

This is a restoration of functionality provided by 309d08d9b3a3
(mm/mmap.c: fix mmap return value when vma is merged after call_mmap()). 
For completeness of fixing MAP_FIXED, implement the comments from the
previous discussion to never update the address and fail if the address
changes.  Leaving the error as a WARN_ON() to avoid crashing the kernel.

Link: https://lkml.kernel.org/r/20221018191613.4133459-1-Liam.Howlett@oracle.com
Link: https://lore.kernel.org/all/Y06yk66SKxlrwwfb@lakrids/
Link: https://lore.kernel.org/all/20201203085350.22624-1-liuzixian4@huawei.com/
Fixes: 4dd1b84140c1 ("mm/mmap: use advanced maple tree API for mmap_region()")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reported-by: Mark Rutland <mark.rutland@arm.com>
Cc: Liu Zixian <liuzixian4@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
1 parent 1cd916d
Raw File
msync.c
// SPDX-License-Identifier: GPL-2.0
/*
 *	linux/mm/msync.c
 *
 * Copyright (C) 1994-1999  Linus Torvalds
 */

/*
 * The msync() system call.
 */
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/syscalls.h>
#include <linux/sched.h>

/*
 * MS_SYNC syncs the entire file - including mappings.
 *
 * MS_ASYNC does not start I/O (it used to, up to 2.5.67).
 * Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
 * Now it doesn't do anything, since dirty pages are properly tracked.
 *
 * The application may now run fsync() to
 * write out the dirty pages and wait on the writeout and check the result.
 * Or the application may run fadvise(FADV_DONTNEED) against the fd to start
 * async writeout immediately.
 * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
 * applications.
 */
SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
{
	unsigned long end;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	int unmapped_error = 0;
	int error = -EINVAL;

	start = untagged_addr(start);

	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
		goto out;
	if (offset_in_page(start))
		goto out;
	if ((flags & MS_ASYNC) && (flags & MS_SYNC))
		goto out;
	error = -ENOMEM;
	len = (len + ~PAGE_MASK) & PAGE_MASK;
	end = start + len;
	if (end < start)
		goto out;
	error = 0;
	if (end == start)
		goto out;
	/*
	 * If the interval [start,end) covers some unmapped address ranges,
	 * just ignore them, but return -ENOMEM at the end. Besides, if the
	 * flag is MS_ASYNC (w/o MS_INVALIDATE) the result would be -ENOMEM
	 * anyway and there is nothing left to do, so return immediately.
	 */
	mmap_read_lock(mm);
	vma = find_vma(mm, start);
	for (;;) {
		struct file *file;
		loff_t fstart, fend;

		/* Still start < end. */
		error = -ENOMEM;
		if (!vma)
			goto out_unlock;
		/* Here start < vma->vm_end. */
		if (start < vma->vm_start) {
			if (flags == MS_ASYNC)
				goto out_unlock;
			start = vma->vm_start;
			if (start >= end)
				goto out_unlock;
			unmapped_error = -ENOMEM;
		}
		/* Here vma->vm_start <= start < vma->vm_end. */
		if ((flags & MS_INVALIDATE) &&
				(vma->vm_flags & VM_LOCKED)) {
			error = -EBUSY;
			goto out_unlock;
		}
		file = vma->vm_file;
		fstart = (start - vma->vm_start) +
			 ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
		fend = fstart + (min(end, vma->vm_end) - start) - 1;
		start = vma->vm_end;
		if ((flags & MS_SYNC) && file &&
				(vma->vm_flags & VM_SHARED)) {
			get_file(file);
			mmap_read_unlock(mm);
			error = vfs_fsync_range(file, fstart, fend, 1);
			fput(file);
			if (error || start >= end)
				goto out;
			mmap_read_lock(mm);
			vma = find_vma(mm, start);
		} else {
			if (start >= end) {
				error = 0;
				goto out_unlock;
			}
			vma = find_vma(mm, vma->vm_end);
		}
	}
out_unlock:
	mmap_read_unlock(mm);
out:
	return error ? : unmapped_error;
}
back to top