linux-kernel - [PATCH RFC] mm: abort inode pruning if it has active pages

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 16 Nov 2011 17:47:47 +0300
From:	Konstantin Khlebnikov <khlebnikov@...nvz.org>
To:	linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc:	Andrew Morton <akpm@...ux-foundation.org>
Subject: [PATCH RFC] mm: abort inode pruning if it has active pages

Inode cache pruning can throw out some usefull data from page cache.
This patch aborts inode invalidation and keep inode alive if it still has
active pages. It improves interaction between inode cache and page cache.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@...nvz.org>
---
 fs/inode.c         |    4 ++--
 include/linux/fs.h |    2 ++
 mm/truncate.c      |   46 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/fs/inode.c b/fs/inode.c
index 1f6c48d..8d55a63 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -663,8 +663,8 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
 			spin_unlock(&inode->i_lock);
 			spin_unlock(&sb->s_inode_lru_lock);
 			if (remove_inode_buffers(inode))
-				reap += invalidate_mapping_pages(&inode->i_data,
-								0, -1);
+				reap += invalidate_inode_inactive_pages(
+						&inode->i_data, 0, -1);
 			iput(inode);
 			spin_lock(&sb->s_inode_lru_lock);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0c4df26..05875d7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2211,6 +2211,8 @@ extern int invalidate_partition(struct gendisk *, int);
 #endif
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
+unsigned long invalidate_inode_inactive_pages(struct address_space *mapping,
+					pgoff_t start, pgoff_t end);
 
 static inline void invalidate_remote_inode(struct inode *inode)
 {
diff --git a/mm/truncate.c b/mm/truncate.c
index 632b15e..ac739bc 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -379,6 +379,52 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
 /*
+ * This is like invalidate_mapping_pages(),
+ * except it aborts invalidation at the first active page.
+ */
+unsigned long invalidate_inode_inactive_pages(struct address_space *mapping,
+					    pgoff_t start, pgoff_t end)
+{
+	struct pagevec pvec;
+	pgoff_t index = start;
+	unsigned long ret;
+	unsigned long count = 0;
+	int i;
+
+	pagevec_init(&pvec, 0);
+	while (index <= end && pagevec_lookup(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+
+		mem_cgroup_uncharge_start();
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+
+			if (PageActive(page)) {
+				index = end;
+				break;
+			}
+
+			/* We rely upon deletion not changing page->index */
+			index = page->index;
+			if (index > end)
+				break;
+
+			if (!trylock_page(page))
+				continue;
+			WARN_ON(page->index != index);
+			ret = invalidate_inode_page(page);
+			unlock_page(page);
+			count += ret;
+		}
+		pagevec_release(&pvec);
+		mem_cgroup_uncharge_end();
+		cond_resched();
+		index++;
+	}
+	return count;
+}
+
+/*
  * This is like invalidate_complete_page(), except it ignores the page's
  * refcount.  We do this because invalidate_inode_pages2() needs stronger
  * invalidation guarantees, and cannot afford to leave pages behind because

--
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/