Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965546AbcJYAOo (ORCPT ); Mon, 24 Oct 2016 20:14:44 -0400 Received: from mga14.intel.com ([192.55.52.115]:52610 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965180AbcJYAOe (ORCPT ); Mon, 24 Oct 2016 20:14:34 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.31,543,1473145200"; d="scan'208";a="1058554117" From: "Kirill A. Shutemov" To: "Theodore Ts'o" , Andreas Dilger , Jan Kara , Andrew Morton Cc: Alexander Viro , Hugh Dickins , Andrea Arcangeli , Dave Hansen , Vlastimil Babka , Matthew Wilcox , Ross Zwisler , linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-block@vger.kernel.org, "Kirill A. Shutemov" Subject: [PATCHv4 38/43] ext4: handle writeback with huge pages Date: Tue, 25 Oct 2016 03:13:37 +0300 Message-Id: <20161025001342.76126-39-kirill.shutemov@linux.intel.com> X-Mailer: git-send-email 2.9.3 In-Reply-To: <20161025001342.76126-1-kirill.shutemov@linux.intel.com> References: <20161025001342.76126-1-kirill.shutemov@linux.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5128 Lines: 158 Modify mpage_map_and_submit_buffers() and mpage_release_unused_pages() to deal with huge pages. Mostly result of try-and-error. Critical view would be appriciated. Signed-off-by: Kirill A. Shutemov --- fs/ext4/inode.c | 61 ++++++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 43 insertions(+), 18 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 869df0504174..d179467f82e7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1659,20 +1659,32 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; + struct page *page = compound_head(pvec.pages[i]); + if (page->index > end) break; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); if (invalidate) { + unsigned long offset, len; + + offset = (index % hpage_nr_pages(page)); + len = min_t(unsigned long, end - page->index, + hpage_nr_pages(page)); + if (page_mapped(page)) clear_page_dirty_for_io(page); - block_invalidatepage(page, 0, PAGE_SIZE); + block_invalidatepage(page, offset << PAGE_SHIFT, + len << PAGE_SHIFT); ClearPageUptodate(page); } unlock_page(page); + if (PageTransHuge(page)) + break; } - index = pvec.pages[nr_pages - 1]->index + 1; + index = page_to_pgoff(pvec.pages[nr_pages - 1]) + 1; + if (PageTransCompound(pvec.pages[nr_pages - 1])) + index = round_up(index, HPAGE_PMD_NR); pagevec_release(&pvec); } } @@ -2106,16 +2118,16 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) loff_t size = i_size_read(mpd->inode); int err; - BUG_ON(page->index != mpd->first_page); - if (page->index == size >> PAGE_SHIFT) - len = size & ~PAGE_MASK; - else - len = PAGE_SIZE; + page = compound_head(page); + len = hpage_size(page); + if (page->index + hpage_nr_pages(page) - 1 == size >> PAGE_SHIFT) + len = size & ~hpage_mask(page); + clear_page_dirty_for_io(page); err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false); if (!err) - mpd->wbc->nr_to_write--; - mpd->first_page++; + mpd->wbc->nr_to_write -= hpage_nr_pages(page); + mpd->first_page = round_up(mpd->first_page + 1, hpage_nr_pages(page)); return err; } @@ -2263,12 +2275,16 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + unsigned long diff; - if (page->index > end) + if (page_to_pgoff(page) > end) break; /* Up to 'end' pages must be contiguous */ - BUG_ON(page->index != start); + BUG_ON(page_to_pgoff(page) != start); + diff = (page - compound_head(page)) << bpp_bits; bh = head = page_buffers(page); + while (diff--) + bh = bh->b_this_page; do { if (lblk < mpd->map.m_lblk) continue; @@ -2305,7 +2321,10 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) * supports blocksize < pagesize as we will try to * convert potentially unmapped parts of inode. */ - mpd->io_submit.io_end->size += PAGE_SIZE; + if (PageTransCompound(page)) + mpd->io_submit.io_end->size += HPAGE_PMD_SIZE; + else + mpd->io_submit.io_end->size += PAGE_SIZE; /* Page fully mapped - let IO run! */ err = mpage_submit_page(mpd, page); if (err < 0) { @@ -2313,6 +2332,10 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) return err; } start++; + if (PageTransCompound(page)) { + start = round_up(start, HPAGE_PMD_NR); + break; + } } pagevec_release(&pvec); } @@ -2552,7 +2575,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) * mapping. However, page->index will not change * because we have a reference on the page. */ - if (page->index > end) + if (page_to_pgoff(page) > end) goto out; /* @@ -2567,7 +2590,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) goto out; /* If we can't merge this page, we are done. */ - if (mpd->map.m_len > 0 && mpd->next_page != page->index) + if (mpd->map.m_len > 0 && mpd->next_page != page_to_pgoff(page)) goto out; lock_page(page); @@ -2581,7 +2604,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) if (!PageDirty(page) || (PageWriteback(page) && (mpd->wbc->sync_mode == WB_SYNC_NONE)) || - unlikely(page->mapping != mapping)) { + unlikely(page_mapping(page) != mapping)) { unlock_page(page); continue; } @@ -2590,8 +2613,10 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) BUG_ON(PageWriteback(page)); if (mpd->map.m_len == 0) - mpd->first_page = page->index; - mpd->next_page = page->index + 1; + mpd->first_page = page_to_pgoff(page); + page = compound_head(page); + mpd->next_page = round_up(page->index + 1, + hpage_nr_pages(page)); /* Add all dirty buffers to mpd */ lblk = ((ext4_lblk_t)page->index) << (PAGE_SHIFT - blkbits); -- 2.9.3