| 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
| ||
|
Date: Sun, 4 Aug 2013 05:17:21 +0300
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To: Andrea Arcangeli <aarcange@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>
Cc: Al Viro <viro@...iv.linux.org.uk>, Hugh Dickins <hughd@...gle.com>,
Wu Fengguang <fengguang.wu@...el.com>, Jan Kara <jack@...e.cz>,
Mel Gorman <mgorman@...e.de>, linux-mm@...ck.org,
Andi Kleen <ak@...ux.intel.com>,
Matthew Wilcox <willy@...ux.intel.com>,
"Kirill A. Shutemov" <kirill@...temov.name>,
Hillf Danton <dhillf@...il.com>, Dave Hansen <dave@...1.net>,
Ning Qu <quning@...gle.com>, linux-fsdevel@...r.kernel.org,
linux-kernel@...r.kernel.org,
"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCH 19/23] truncate: support huge pages
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
truncate_inode_pages_range() drops whole huge page at once if it's fully
inside the range.
If a huge page is only partly in the range we zero out the part,
exactly like we do for partial small pages.
invalidate_mapping_pages() just skips huge pages if they are not fully
in the range.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
---
mm/truncate.c | 108 +++++++++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 84 insertions(+), 24 deletions(-)
diff --git a/mm/truncate.c b/mm/truncate.c
index 353b683..fcef7cb 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -205,8 +205,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
{
pgoff_t start; /* inclusive */
pgoff_t end; /* exclusive */
- unsigned int partial_start; /* inclusive */
- unsigned int partial_end; /* exclusive */
+ bool partial_thp_start = false, partial_thp_end = false;
struct pagevec pvec;
pgoff_t index;
int i;
@@ -215,15 +214,9 @@ void truncate_inode_pages_range(struct address_space *mapping,
if (mapping->nrpages == 0)
return;
- /* Offsets within partial pages */
- partial_start = lstart & (PAGE_CACHE_SIZE - 1);
- partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);
-
/*
* 'start' and 'end' always covers the range of pages to be fully
- * truncated. Partial pages are covered with 'partial_start' at the
- * start of the range and 'partial_end' at the end of the range.
- * Note that 'end' is exclusive while 'lend' is inclusive.
+ * truncated. Note that 'end' is exclusive while 'lend' is inclusive.
*/
start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (lend == -1)
@@ -249,6 +242,23 @@ void truncate_inode_pages_range(struct address_space *mapping,
if (index >= end)
break;
+ if (PageTransTailCache(page)) {
+ /* part of already handled huge page */
+ if (!page->mapping)
+ continue;
+ /* the range starts in middle of huge page */
+ partial_thp_start = true;
+ start = index & ~HPAGE_CACHE_INDEX_MASK;
+ continue;
+ }
+ /* the range ends on huge page */
+ if (PageTransHugeCache(page) &&
+ index == (end & ~HPAGE_CACHE_INDEX_MASK)) {
+ partial_thp_end = true;
+ end = index;
+ break;
+ }
+
if (!trylock_page(page))
continue;
WARN_ON(page->index != index);
@@ -265,34 +275,74 @@ void truncate_inode_pages_range(struct address_space *mapping,
index++;
}
- if (partial_start) {
- struct page *page = find_lock_page(mapping, start - 1);
+ if (partial_thp_start || lstart & ~PAGE_CACHE_MASK) {
+ pgoff_t off;
+ struct page *page;
+ unsigned pstart, pend;
+ void (*zero_segment)(struct page *page,
+ unsigned start, unsigned len);
+retry_partial_start:
+ if (partial_thp_start) {
+ zero_segment = zero_huge_user_segment;
+ off = (start - 1) & ~HPAGE_CACHE_INDEX_MASK;
+ pstart = lstart & ~HPAGE_PMD_MASK;
+ if ((end & ~HPAGE_CACHE_INDEX_MASK) == off)
+ pend = (lend - 1) & ~HPAGE_PMD_MASK;
+ else
+ pend = HPAGE_PMD_SIZE;
+ } else {
+ zero_segment = zero_user_segment;
+ off = start - 1;
+ pstart = lstart & ~PAGE_CACHE_MASK;
+ if (start > end)
+ pend = (lend - 1) & ~PAGE_CACHE_MASK;
+ else
+ pend = PAGE_CACHE_SIZE;
+ }
+
+ page = find_get_page(mapping, off);
if (page) {
- unsigned int top = PAGE_CACHE_SIZE;
- if (start > end) {
- /* Truncation within a single page */
- top = partial_end;
- partial_end = 0;
+ /* the last tail page*/
+ if (PageTransTailCache(page)) {
+ partial_thp_start = true;
+ page_cache_release(page);
+ goto retry_partial_start;
}
+
+ lock_page(page);
wait_on_page_writeback(page);
- zero_user_segment(page, partial_start, top);
+ zero_segment(page, pstart, pend);
cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
- do_invalidatepage(page, partial_start,
- top - partial_start);
+ do_invalidatepage(page, pstart,
+ pend - pstart);
unlock_page(page);
page_cache_release(page);
}
}
- if (partial_end) {
- struct page *page = find_lock_page(mapping, end);
+ if (partial_thp_end || (lend + 1) & ~PAGE_CACHE_MASK) {
+ pgoff_t off;
+ struct page *page;
+ unsigned pend;
+ void (*zero_segment)(struct page *page,
+ unsigned start, unsigned len);
+ if (partial_thp_end) {
+ zero_segment = zero_huge_user_segment;
+ off = end & ~HPAGE_CACHE_INDEX_MASK;
+ pend = (lend - 1) & ~HPAGE_PMD_MASK;
+ } else {
+ zero_segment = zero_user_segment;
+ off = end;
+ pend = (lend - 1) & ~PAGE_CACHE_MASK;
+ }
+
+ page = find_lock_page(mapping, end);
if (page) {
wait_on_page_writeback(page);
- zero_user_segment(page, 0, partial_end);
+ zero_segment(page, 0, pend);
cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
- do_invalidatepage(page, 0,
- partial_end);
+ do_invalidatepage(page, 0, pend);
unlock_page(page);
page_cache_release(page);
}
@@ -327,6 +377,9 @@ void truncate_inode_pages_range(struct address_space *mapping,
if (index >= end)
break;
+ if (PageTransTailCache(page))
+ continue;
+
lock_page(page);
WARN_ON(page->index != index);
wait_on_page_writeback(page);
@@ -401,6 +454,13 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
if (index > end)
break;
+ /* skip huge page if it's not fully in the range */
+ if (PageTransHugeCache(page) &&
+ index + HPAGE_CACHE_NR - 1 > end)
+ continue;
+ if (PageTransTailCache(page))
+ continue;
+
if (!trylock_page(page))
continue;
WARN_ON(page->index != index);
--
1.8.3.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists