linux-kernel - [PATCH 11/15] beginning of transition to parallel lookups

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: <1460768127-31822-11-git-send-email-viro@ZenIV.linux.org.uk>
Date:	Sat, 16 Apr 2016 01:55:23 +0100
From:	Al Viro <viro@...IV.linux.org.uk>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org
Subject: [PATCH 11/15] beginning of transition to parallel lookups - marking in-lookup dentries

From: Al Viro <viro@...iv.linux.org.uk>

marked as such when (would be) parallel lookup is about to pass them
to actual ->lookup(); unmarked when
	* __d_add() is about to make it hashed, positive or not.
	* __d_move() (from d_splice_alias(), directly or via
__d_unalias()) puts a preexisting dentry in its place
	* in caller of ->lookup() if it has escaped all of the
above.  Bug (WARN_ON, actually) if it reaches the final dput()
or d_instantiate() while still marked such.

As the result, we are guaranteed that for as long as the flag is
set, dentry will
	* remain negative unhashed with positive refcount
	* never have its ->d_alias looked at
	* never have its ->d_lru looked at
	* never have its ->d_parent and ->d_name changed

Right now we have at most one such for any given parent directory.
With parallel lookups that restriction will weaken to
	* only exist when parent is locked shared
	* at most one with given (parent,name) pair (comparison of
names is according to ->d_compare())
	* only exist when there's no hashed dentry with the same
(parent,name)

Transition will take the next several commits; unfortunately, we'll
only be able to switch to rwsem at the end of this series.  The
reason for not making it a single patch is to simplify review.

Signed-off-by: Al Viro <viro@...iv.linux.org.uk>
---
 fs/dcache.c            | 12 ++++++++++++
 fs/namei.c             |  4 ++++
 include/linux/dcache.h | 13 +++++++++++++
 3 files changed, 29 insertions(+)

diff --git a/fs/dcache.c b/fs/dcache.c
index 33cad8a..5cea3cb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -761,6 +761,8 @@ repeat:
 	/* Slow case: now with the dentry lock held */
 	rcu_read_unlock();
 
+	WARN_ON(dentry->d_flags & DCACHE_PAR_LOOKUP);
+
 	/* Unreachable? Get rid of it */
 	if (unlikely(d_unhashed(dentry)))
 		goto kill_it;
@@ -1743,6 +1745,7 @@ type_determined:
 static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 {
 	unsigned add_flags = d_flags_for_inode(inode);
+	WARN_ON(dentry->d_flags & DCACHE_PAR_LOOKUP);
 
 	spin_lock(&dentry->d_lock);
 	hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
@@ -2358,12 +2361,19 @@ void d_rehash(struct dentry * entry)
 }
 EXPORT_SYMBOL(d_rehash);
 
+void __d_not_in_lookup(struct dentry *dentry)
+{
+	dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
+	/* more stuff will land here */
+}
 
 /* inode->i_lock held if inode is non-NULL */
 
 static inline void __d_add(struct dentry *dentry, struct inode *inode)
 {
 	spin_lock(&dentry->d_lock);
+	if (unlikely(dentry->d_flags & DCACHE_PAR_LOOKUP))
+		__d_not_in_lookup(dentry);
 	if (inode) {
 		unsigned add_flags = d_flags_for_inode(inode);
 		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
@@ -2609,6 +2619,8 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	BUG_ON(d_ancestor(target, dentry));
 
 	dentry_lock_for_move(dentry, target);
+	if (unlikely(target->d_flags & DCACHE_PAR_LOOKUP))
+		__d_not_in_lookup(target);
 
 	write_seqcount_begin(&dentry->d_seq);
 	write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED);
diff --git a/fs/namei.c b/fs/namei.c
index 6fb33a7..0ee8b9d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1634,7 +1634,11 @@ static struct dentry *lookup_slow(const struct qstr *name,
 		inode_unlock(inode);
 		return ERR_PTR(-ENOMEM);
 	}
+	spin_lock(&dentry->d_lock);
+	dentry->d_flags |= DCACHE_PAR_LOOKUP;
+	spin_unlock(&dentry->d_lock);
 	old = inode->i_op->lookup(inode, dentry, flags);
+	d_not_in_lookup(dentry);
 	if (unlikely(old)) {
 		dput(dentry);
 		dentry = old;
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 7cb043d..cfc1240 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -230,6 +230,8 @@ struct dentry_operations {
 
 #define DCACHE_ENCRYPTED_WITH_KEY	0x04000000 /* dir is encrypted with a valid key */
 
+#define DCACHE_PAR_LOOKUP		0x08000000 /* being looked up (with parent locked shared) */
+
 extern seqlock_t rename_lock;
 
 /*
@@ -365,6 +367,17 @@ static inline void dont_mount(struct dentry *dentry)
 	spin_unlock(&dentry->d_lock);
 }
 
+extern void __d_not_in_lookup(struct dentry *);
+
+static inline void d_not_in_lookup(struct dentry *dentry)
+{
+	if (unlikely(dentry->d_flags & DCACHE_PAR_LOOKUP)) {
+		spin_lock(&dentry->d_lock);
+		__d_not_in_lookup(dentry);
+		spin_unlock(&dentry->d_lock);
+	}
+}
+
 extern void dput(struct dentry *);
 
 static inline bool d_managed(const struct dentry *dentry)
-- 
2.8.0.rc3