Revision 0ee7c3e25d8c28845fceb4dd1c3cb5f50b9c45a9 authored by Linus Torvalds on 31 August 2021, 18:13:35 UTC, committed by Linus Torvalds on 31 August 2021, 18:13:35 UTC
Pull iomap updates from Darrick Wong: "The most notable externally visible change for this cycle is the addition of support for reads to inline tail fragments of files, which was requested by the erofs developers; and a correction for a kernel memory corruption bug if the sysadmin tries to activate a swapfile with more pages than the swapfile header suggests. We also now report writeback completion errors to the file mapping correctly, instead of munging all errors into EIO. Internally, the bulk of the changes are Christoph's patchset to reduce the indirect function call count by a third to a half by converting iomap iteration from a loop pattern to a generator/consumer pattern. As an added bonus, fsdax no longer open-codes iomap apply loops. Summary: - Simplify the bio_end_page usage in the buffered IO code. - Support reading inline data at nonzero offsets for erofs. - Fix some typos and bad grammar. - Convert kmap_atomic usage in the inline data read path. - Add some extra inline data input checking. - Fix a memory corruption bug stemming from iomap_swapfile_activate trying to activate more pages than mm was expecting. - Pass errnos through the page writeback code so that writeback errors are reported correctly instead of being munged to EIO. - Replace iomap_apply with a open-coded iterator loops to reduce the number of indirect calls by a third to a half. - Refactor the fsdax code to use iomap iterators instead of the open-coded iomap_apply code that it had before. - Format file range iomap tracepoint data in hexadecimal and standardize the names used in the pretty-print string" * tag 'iomap-5.15-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (41 commits) iomap: standardize tracepoint formatting and storage mm/swap: consider max pages in iomap_swapfile_add_extent iomap: move loop control code to iter.c iomap: constify iomap_iter_srcmap fsdax: switch the fault handlers to use iomap_iter fsdax: factor out a dax_fault_actor() helper fsdax: factor out helpers to simplify the dax fault code iomap: rework unshare flag iomap: pass an iomap_iter to various buffered I/O helpers iomap: remove iomap_apply fsdax: switch dax_iomap_rw to use iomap_iter iomap: switch iomap_swapfile_activate to use iomap_iter iomap: switch iomap_seek_data to use iomap_iter iomap: switch iomap_seek_hole to use iomap_iter iomap: switch iomap_bmap to use iomap_iter iomap: switch iomap_fiemap to use iomap_iter iomap: switch __iomap_dio_rw to use iomap_iter iomap: switch iomap_page_mkwrite to use iomap_iter iomap: switch iomap_zero_range to use iomap_iter iomap: switch iomap_file_unshare to use iomap_iter ...
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 = vma->vm_next;
}
}
out_unlock:
mmap_read_unlock(mm);
out:
return error ? : unmapped_error;
}
Computing file changes ...