linux-kernel - [PATCH v3 2/4] Keep nr

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

Message-Id: <1313334832-1150-3-git-send-email-glommer@parallels.com>
Date:	Sun, 14 Aug 2011 19:13:50 +0400
From:	Glauber Costa <glommer@...allels.com>
To:	linux-kernel@...r.kernel.org
Cc:	linux-fsdevel@...r.kernel.org,
	containers@...ts.linux-foundation.org,
	Pavel Emelyanov <xemul@...allels.com>,
	Al Viro <viro@...iv.linux.org.uk>,
	Hugh Dickins <hughd@...gle.com>,
	Nick Piggin <npiggin@...nel.dk>,
	Andrea Arcangeli <aarcange@...hat.com>,
	Rik van Riel <riel@...hat.com>,
	Dave Hansen <dave@...ux.vnet.ibm.com>,
	James Bottomley <JBottomley@...allels.com>,
	David Chinner <david@...morbit.com>,
	Glauber Costa <glommer@...allels.com>,
	Eric Dumazet <eric.dumazet@...il.com>
Subject: [PATCH v3 2/4] Keep nr_dentry per super block

Now that we have per-sb shrinkers, it makes sense to have nr_dentries
stored per sb as well. We turn them into per-cpu counters so we can
keep acessing them without locking.

Signed-off-by: Glauber Costa <glommer@...allels.com>
CC: Dave Chinner <david@...morbit.com>
CC: Eric Dumazet <eric.dumazet@...il.com>
---
 fs/dcache.c        |   12 +++++++++++-
 fs/super.c         |    4 ++++
 include/linux/fs.h |    2 ++
 3 files changed, 17 insertions(+), 1 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index b05aac3..815d9fd 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -151,7 +151,13 @@ static void __d_free(struct rcu_head *head)
 static void d_free(struct dentry *dentry)
 {
 	BUG_ON(dentry->d_count);
+	/*
+	 * It is cheaper to keep a global counter separate
+	 * then to scan through all superblocks when needed
+	 */
 	this_cpu_dec(nr_dentry);
+	percpu_counter_dec(&dentry->d_sb->s_nr_dentry);
+
 	if (dentry->d_op && dentry->d_op->d_release)
 		dentry->d_op->d_release(dentry);
 
@@ -1224,8 +1230,12 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	INIT_LIST_HEAD(&dentry->d_alias);
 	INIT_LIST_HEAD(&dentry->d_u.d_child);
 	d_set_d_op(dentry, dentry->d_sb->s_d_op);
-
+	/*
+	 * It is cheaper to keep a global counter separate
+	 * then to scan through all superblocks when needed
+	 */
 	this_cpu_inc(nr_dentry);
+	percpu_counter_inc(&dentry->d_sb->s_nr_dentry);
 
 	return dentry;
 }
diff --git a/fs/super.c b/fs/super.c
index 3f56a26..e95ac4f 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -119,6 +119,9 @@ static struct super_block *alloc_super(struct file_system_type *type)
 			s = NULL;
 			goto out;
 		}
+
+		percpu_counter_init(&s->s_nr_dentry, 0);
+
 #ifdef CONFIG_SMP
 		s->s_files = alloc_percpu(struct list_head);
 		if (!s->s_files) {
@@ -199,6 +202,7 @@ static inline void destroy_super(struct super_block *s)
 #ifdef CONFIG_SMP
 	free_percpu(s->s_files);
 #endif
+	percpu_counter_destroy(&s->s_nr_dentry);
 	security_sb_free(s);
 	kfree(s->s_subtype);
 	kfree(s->s_options);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f23bcb7..8150f52 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1399,6 +1399,8 @@ struct super_block {
 	struct list_head	s_dentry_lru;	/* unused dentry lru */
 	int			s_nr_dentry_unused;	/* # of dentry on lru */
 
+	struct percpu_counter 	s_nr_dentry;		/* # of dentry on this sb */
+
 	/* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */
 	spinlock_t		s_inode_lru_lock ____cacheline_aligned_in_smp;
 	struct list_head	s_inode_lru;		/* unused inode lru */
-- 
1.7.6

--
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/