Replace hugetlbfs_read_iter() with generic_file_read_iter(), teach filemap_get_pages() to be aware of hugetlb pagesize while calculating 'last_index'. [1] https://lore.kernel.org/linux-mm/aeZwAz6PcdlqSnJ2@casper.infradead.org/ Suggested-by: Matthew Wilcox Signed-off-by: Jane Chu --- fs/hugetlbfs/inode.c | 84 +------------------------------------------- mm/filemap.c | 15 ++++++-- 2 files changed, 14 insertions(+), 85 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f1f8c3f7388f..1c25485c91b9 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -187,88 +187,6 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return mm_get_unmapped_area_vmflags(file, addr0, len, pgoff, flags, 0); } -/* - * Support for read() - Find the page attached to f_mapping and copy out the - * data. This provides functionality similar to filemap_read(). - */ -static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) -{ - struct file *file = iocb->ki_filp; - struct hstate *h = hstate_file(file); - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - unsigned long index = iocb->ki_pos >> huge_page_shift(h); - unsigned long offset = iocb->ki_pos & ~huge_page_mask(h); - unsigned long end_index; - loff_t isize; - ssize_t retval = 0; - - while (iov_iter_count(to)) { - struct folio *folio; - size_t nr, copied, want; - - /* nr is the maximum number of bytes to copy from this page */ - nr = huge_page_size(h); - isize = i_size_read(inode); - if (!isize) - break; - end_index = (isize - 1) >> huge_page_shift(h); - if (index > end_index) - break; - if (index == end_index) { - nr = ((isize - 1) & ~huge_page_mask(h)) + 1; - if (nr <= offset) - break; - } - nr = nr - offset; - - /* Find the folio */ - folio = filemap_lock_hugetlb_folio(h, mapping, index); - if (IS_ERR(folio)) { - /* - * We have a HOLE, zero out the user-buffer for the - * length of the hole or request. - */ - copied = iov_iter_zero(nr, to); - } else { - folio_unlock(folio); - - if (!folio_test_hwpoison(folio)) - want = nr; - else { - /* - * Adjust how many bytes safe to read without - * touching the 1st raw HWPOISON page after - * offset. - */ - want = adjust_range_hwpoison(folio, offset, nr); - if (want == 0) { - folio_put(folio); - retval = -EIO; - break; - } - } - - /* - * We have the folio, copy it to user space buffer. - */ - copied = copy_folio_to_iter(folio, offset, want, to); - folio_put(folio); - } - offset += copied; - retval += copied; - if (copied != nr && iov_iter_count(to)) { - if (!retval) - retval = -EFAULT; - break; - } - index += offset >> huge_page_shift(h); - offset &= ~huge_page_mask(h); - } - iocb->ki_pos = ((loff_t)index << huge_page_shift(h)) + offset; - return retval; -} - static int hugetlbfs_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, @@ -1181,7 +1099,7 @@ static void init_once(void *foo) } static const struct file_operations hugetlbfs_file_operations = { - .read_iter = hugetlbfs_read_iter, + .read_iter = generic_file_read_iter, .mmap = hugetlbfs_file_mmap, .fsync = noop_fsync, .get_unmapped_area = hugetlb_get_unmapped_area, diff --git a/mm/filemap.c b/mm/filemap.c index df8543573570..eb03b31791fc 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2672,20 +2672,30 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count, { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; + bool is_hugetlbfs = is_file_hugepages(filp); pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; unsigned int flags; + size_t min_folio_bytes; int err = 0; /* "last_index" is the index of the folio beyond the end of the read */ - last_index = round_up(iocb->ki_pos + count, - mapping_min_folio_nrbytes(mapping)) >> PAGE_SHIFT; + if (is_hugetlbfs) + min_folio_bytes = huge_page_size(hstate_file(filp)); + else + min_folio_bytes = mapping_min_folio_nrbytes(mapping); + last_index = round_up(iocb->ki_pos + count, min_folio_bytes) >> PAGE_SHIFT; + retry: if (fatal_signal_pending(current)) return -EINTR; filemap_get_read_batch(mapping, index, last_index - 1, fbatch); + + if (is_hugetlbfs) + goto done; + if (!folio_batch_count(fbatch)) { DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index); @@ -2724,6 +2734,7 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count, goto err; } +done: trace_mm_filemap_get_pages(mapping, index, last_index - 1); return 0; err: -- 2.43.5