| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1469493335-3622-25-git-send-email-kirill.shutemov@linux.intel.com>
Date: Tue, 26 Jul 2016 03:35:26 +0300
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To: "Theodore Ts'o" <tytso@....edu>,
Andreas Dilger <adilger.kernel@...ger.ca>,
Jan Kara <jack@...e.com>
Cc: Alexander Viro <viro@...iv.linux.org.uk>,
Hugh Dickins <hughd@...gle.com>,
Andrea Arcangeli <aarcange@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Dave Hansen <dave.hansen@...el.com>,
Vlastimil Babka <vbabka@...e.cz>,
Matthew Wilcox <willy@...radead.org>,
Ross Zwisler <ross.zwisler@...ux.intel.com>,
linux-ext4@...r.kernel.org, linux-fsdevel@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
linux-block@...r.kernel.org,
"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCHv1, RFC 24/33] truncate: make truncate_inode_pages_range() aware about huge pages
As with shmem_undo_range(), truncate_inode_pages_range() removes huge
pages, if it fully within range.
Partial truncate of huge pages zero out this part of THP.
Unlike with shmem, it doesn't prevent us having holes in the middle of
huge page we still can skip writeback not touched buffers.
With memory-mapped IO we would loose holes in some cases when we have
THP in page cache, since we cannot track access on 4k level in this
case.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
---
fs/buffer.c | 2 +-
mm/truncate.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
2 files changed, 88 insertions(+), 9 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 2e25d0e7a233..e636dac53215 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1534,7 +1534,7 @@ void block_invalidatepage(struct page *page, unsigned int offset,
/*
* Check for overflow
*/
- BUG_ON(stop > PAGE_SIZE || stop < length);
+ BUG_ON(stop > hpage_size(page) || stop < length);
head = page_buffers(page);
bh = head;
diff --git a/mm/truncate.c b/mm/truncate.c
index ce904e4b1708..9c339e6255f2 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -90,7 +90,7 @@ void do_invalidatepage(struct page *page, unsigned int offset,
{
void (*invalidatepage)(struct page *, unsigned int, unsigned int);
- invalidatepage = page->mapping->a_ops->invalidatepage;
+ invalidatepage = page_mapping(page)->a_ops->invalidatepage;
#ifdef CONFIG_BLOCK
if (!invalidatepage)
invalidatepage = block_invalidatepage;
@@ -116,7 +116,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
return -EIO;
if (page_has_private(page))
- do_invalidatepage(page, 0, PAGE_SIZE);
+ do_invalidatepage(page, 0, hpage_size(page));
/*
* Some filesystems seem to re-dirty the page even after
@@ -288,6 +288,36 @@ void truncate_inode_pages_range(struct address_space *mapping,
unlock_page(page);
continue;
}
+
+ if (PageTransTail(page)) {
+ /* Middle of THP: zero out the page */
+ clear_highpage(page);
+ if (page_has_private(page)) {
+ int off = page - compound_head(page);
+ do_invalidatepage(compound_head(page),
+ off * PAGE_SIZE,
+ PAGE_SIZE);
+ }
+ unlock_page(page);
+ continue;
+ } else if (PageTransHuge(page)) {
+ if (index == round_down(end, HPAGE_PMD_NR)) {
+ /*
+ * Range ends in the middle of THP:
+ * zero out the page
+ */
+ clear_highpage(page);
+ if (page_has_private(page)) {
+ do_invalidatepage(page, 0,
+ PAGE_SIZE);
+ }
+ unlock_page(page);
+ continue;
+ }
+ index += HPAGE_PMD_NR - 1;
+ i += HPAGE_PMD_NR - 1;
+ }
+
truncate_inode_page(mapping, page);
unlock_page(page);
}
@@ -309,9 +339,12 @@ void truncate_inode_pages_range(struct address_space *mapping,
wait_on_page_writeback(page);
zero_user_segment(page, partial_start, top);
cleancache_invalidate_page(mapping, page);
- if (page_has_private(page))
- do_invalidatepage(page, partial_start,
- top - partial_start);
+ if (page_has_private(page)) {
+ int off = page - compound_head(page);
+ do_invalidatepage(compound_head(page),
+ off * PAGE_SIZE + partial_start,
+ top - partial_start);
+ }
unlock_page(page);
put_page(page);
}
@@ -322,9 +355,12 @@ void truncate_inode_pages_range(struct address_space *mapping,
wait_on_page_writeback(page);
zero_user_segment(page, 0, partial_end);
cleancache_invalidate_page(mapping, page);
- if (page_has_private(page))
- do_invalidatepage(page, 0,
- partial_end);
+ if (page_has_private(page)) {
+ int off = page - compound_head(page);
+ do_invalidatepage(compound_head(page),
+ off * PAGE_SIZE,
+ partial_end);
+ }
unlock_page(page);
put_page(page);
}
@@ -373,6 +409,49 @@ void truncate_inode_pages_range(struct address_space *mapping,
lock_page(page);
WARN_ON(page_to_pgoff(page) != index);
wait_on_page_writeback(page);
+
+ if (PageTransTail(page)) {
+ /* Middle of THP: zero out the page */
+ clear_highpage(page);
+ if (page_has_private(page)) {
+ int off = page - compound_head(page);
+ do_invalidatepage(compound_head(page),
+ off * PAGE_SIZE,
+ PAGE_SIZE);
+ }
+ unlock_page(page);
+ /*
+ * Partial thp truncate due 'start' in middle
+ * of THP: don't need to look on these pages
+ * again on !pvec.nr restart.
+ */
+ if (index != round_down(end, HPAGE_PMD_NR))
+ start++;
+ continue;
+ } else if (PageTransHuge(page)) {
+ if (index == round_down(end, HPAGE_PMD_NR)) {
+ /*
+ * Range ends in the middle of THP:
+ * zero out the page
+ */
+ clear_highpage(page);
+ if (page_has_private(page)) {
+ do_invalidatepage(page, 0,
+ PAGE_SIZE);
+ }
+ unlock_page(page);
+ /*
+ * Partial thp truncate due 'end' in
+ * middle of THP: don't need to look on
+ * these pages again restart.
+ */
+ start++;
+ continue;
+ }
+ index += HPAGE_PMD_NR - 1;
+ i += HPAGE_PMD_NR - 1;
+ }
+
truncate_inode_page(mapping, page);
unlock_page(page);
}
--
2.8.1
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists