1 files changed, 219 insertions, 81 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index b280e07e162b..52e6d5fdab6b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -84,6 +84,8 @@ const struct qstr empty_name = QSTR_INIT("", 0);
 EXPORT_SYMBOL(empty_name);
 const struct qstr slash_name = QSTR_INIT("/", 1);
 EXPORT_SYMBOL(slash_name);
+const struct qstr dotdot_name = QSTR_INIT("..", 2);
+EXPORT_SYMBOL(dotdot_name);
 
 /*
  * This is the single most critical data structure when it comes
@@ -113,10 +115,13 @@ static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent,
 	return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT);
 }
 
-
-/* Statistics gathering. */
-struct dentry_stat_t dentry_stat = {
-	.age_limit = 45,
+struct dentry_stat_t {
+	long nr_dentry;
+	long nr_unused;
+	long age_limit;		/* age in seconds */
+	long want_pages;	/* pages requested by system */
+	long nr_negative;	/* # of unused negative dentries */
+	long dummy;		/* Reserved for future use */
 };
 
 static DEFINE_PER_CPU(long, nr_dentry);
@@ -124,6 +129,10 @@ static DEFINE_PER_CPU(long, nr_dentry_unused);
 static DEFINE_PER_CPU(long, nr_dentry_negative);
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+/* Statistics gathering. */
+static struct dentry_stat_t dentry_stat = {
+	.age_limit = 45,
+};
 
 /*
  * Here we resort to our own counters instead of using generic per-cpu counters
@@ -165,14 +174,32 @@ static long get_nr_dentry_negative(void)
 	return sum < 0 ? 0 : sum;
 }
 
-int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer,
-		   size_t *lenp, loff_t *ppos)
+static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer,
+			  size_t *lenp, loff_t *ppos)
 {
 	dentry_stat.nr_dentry = get_nr_dentry();
 	dentry_stat.nr_unused = get_nr_dentry_unused();
 	dentry_stat.nr_negative = get_nr_dentry_negative();
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
+
+static struct ctl_table fs_dcache_sysctls[] = {
+	{
+		.procname	= "dentry-state",
+		.data		= &dentry_stat,
+		.maxlen		= 6*sizeof(long),
+		.mode		= 0444,
+		.proc_handler	= proc_nr_dentry,
+	},
+	{ }
+};
+
+static int __init init_fs_dcache_sysctls(void)
+{
+	register_sysctl_init("fs", fs_dcache_sysctls);
+	return 0;
+}
+fs_initcall(init_fs_dcache_sysctls);
 #endif
 
 /*
@@ -456,23 +483,6 @@ static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry,
 	list_lru_isolate_move(lru, &dentry->d_lru, list);
 }
 
-/**
- * d_drop - drop a dentry
- * @dentry: dentry to drop
- *
- * d_drop() unhashes the entry from the parent dentry hashes, so that it won't
- * be found through a VFS lookup any more. Note that this is different from
- * deleting the dentry - d_delete will try to mark the dentry negative if
- * possible, giving a successful _negative_ lookup, while d_drop will
- * just make the cache lookup fail.
- *
- * d_drop() is used mainly for stuff that wants to invalidate a dentry for some
- * reason (NFS timeouts or autofs deletes).
- *
- * __d_drop requires dentry->d_lock
- * ___d_drop doesn't mark dentry as "unhashed"
- *   (dentry->d_hash.pprev will be LIST_POISON2, not NULL).
- */
 static void ___d_drop(struct dentry *dentry)
 {
 	struct hlist_bl_head *b;
@@ -501,6 +511,24 @@ void __d_drop(struct dentry *dentry)
 }
 EXPORT_SYMBOL(__d_drop);
 
+/**
+ * d_drop - drop a dentry
+ * @dentry: dentry to drop
+ *
+ * d_drop() unhashes the entry from the parent dentry hashes, so that it won't
+ * be found through a VFS lookup any more. Note that this is different from
+ * deleting the dentry - d_delete will try to mark the dentry negative if
+ * possible, giving a successful _negative_ lookup, while d_drop will
+ * just make the cache lookup fail.
+ *
+ * d_drop() is used mainly for stuff that wants to invalidate a dentry for some
+ * reason (NFS timeouts or autofs deletes).
+ *
+ * __d_drop requires dentry->d_lock
+ *
+ * ___d_drop doesn't mark dentry as "unhashed"
+ * (dentry->d_hash.pprev will be LIST_POISON2, not NULL).
+ */
 void d_drop(struct dentry *dentry)
 {
 	spin_lock(&dentry->d_lock);
@@ -647,6 +675,10 @@ static inline bool retain_dentry(struct dentry *dentry)
 		if (dentry->d_op->d_delete(dentry))
 			return false;
 	}
+
+	if (unlikely(dentry->d_flags & DCACHE_DONTCACHE))
+		return false;
+
 	/* retain; LRU fodder */
 	dentry->d_lockref.count--;
 	if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST)))
@@ -656,6 +688,21 @@ static inline bool retain_dentry(struct dentry *dentry)
 	return true;
 }
 
+void d_mark_dontcache(struct inode *inode)
+{
+	struct dentry *de;
+
+	spin_lock(&inode->i_lock);
+	hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) {
+		spin_lock(&de->d_lock);
+		de->d_flags |= DCACHE_DONTCACHE;
+		spin_unlock(&de->d_lock);
+	}
+	inode->i_state |= I_DONTCACHE;
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(d_mark_dontcache);
+
 /*
  * Finish off a dentry we've decided to kill.
  * dentry->d_lock must be held, returns with it unlocked.
@@ -774,10 +821,17 @@ static inline bool fast_dput(struct dentry *dentry)
 	 * a reference to the dentry and change that, but
 	 * our work is done - we can leave the dentry
 	 * around with a zero refcount.
+	 *
+	 * Nevertheless, there are two cases that we should kill
+	 * the dentry anyway.
+	 * 1. free disconnected dentries as soon as their refcount
+	 *    reached zero.
+	 * 2. free dentries if they should not be cached.
 	 */
 	smp_rmb();
 	d_flags = READ_ONCE(dentry->d_flags);
-	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED;
+	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST |
+			DCACHE_DISCONNECTED | DCACHE_DONTCACHE;
 
 	/* Nothing to do? Dropping the reference was all we needed? */
 	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
@@ -970,20 +1024,6 @@ struct dentry *d_find_any_alias(struct inode *inode)
 }
 EXPORT_SYMBOL(d_find_any_alias);
 
-/**
- * d_find_alias - grab a hashed alias of inode
- * @inode: inode in question
- *
- * If inode has a hashed alias, or is a directory and has any alias,
- * acquire the reference to alias and return it. Otherwise return NULL.
- * Notice that if inode is a directory there can be only one alias and
- * it can be unhashed only if it has no children, or if it is the root
- * of a filesystem, or if the directory was renamed and d_revalidate
- * was the first vfs operation to notice.
- *
- * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
- * any other hashed alias over that one.
- */
 static struct dentry *__d_find_alias(struct inode *inode)
 {
 	struct dentry *alias;
@@ -1003,6 +1043,20 @@ static struct dentry *__d_find_alias(struct inode *inode)
 	return NULL;
 }
 
+/**
+ * d_find_alias - grab a hashed alias of inode
+ * @inode: inode in question
+ *
+ * If inode has a hashed alias, or is a directory and has any alias,
+ * acquire the reference to alias and return it. Otherwise return NULL.
+ * Notice that if inode is a directory there can be only one alias and
+ * it can be unhashed only if it has no children, or if it is the root
+ * of a filesystem, or if the directory was renamed and d_revalidate
+ * was the first vfs operation to notice.
+ *
+ * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
+ * any other hashed alias over that one.
+ */
 struct dentry *d_find_alias(struct inode *inode)
 {
 	struct dentry *de = NULL;
@@ -1017,6 +1071,31 @@ struct dentry *d_find_alias(struct inode *inode)
 EXPORT_SYMBOL(d_find_alias);
 
 /*
+ *  Caller MUST be holding rcu_read_lock() and be guaranteed
+ *  that inode won't get freed until rcu_read_unlock().
+ */
+struct dentry *d_find_alias_rcu(struct inode *inode)
+{
+	struct hlist_head *l = &inode->i_dentry;
+	struct dentry *de = NULL;
+
+	spin_lock(&inode->i_lock);
+	// ->i_dentry and ->i_rcu are colocated, but the latter won't be
+	// used without having I_FREEING set, which means no aliases left
+	if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) {
+		if (S_ISDIR(inode->i_mode)) {
+			de = hlist_entry(l->first, struct dentry, d_u.d_alias);
+		} else {
+			hlist_for_each_entry(de, l, d_u.d_alias)
+				if (!d_unhashed(de))
+					break;
+		}
+	}
+	spin_unlock(&inode->i_lock);
+	return de;
+}
+
+/*
  *	Try to kill dentries associated with this inode.
  * WARNING: you must own a reference to inode.
  */
@@ -1687,7 +1766,8 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	char *dname;
 	int err;
 
-	dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL);
+	dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru,
+				      GFP_KERNEL);
 	if (!dentry)
 		return NULL;
 
@@ -1727,7 +1807,7 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	dentry->d_lockref.count = 1;
 	dentry->d_flags = 0;
 	spin_lock_init(&dentry->d_lock);
-	seqcount_init(&dentry->d_seq);
+	seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock);
 	dentry->d_inode = NULL;
 	dentry->d_parent = dentry;
 	dentry->d_sb = sb;
@@ -2124,8 +2204,8 @@ EXPORT_SYMBOL(d_obtain_root);
  * same inode, only the actual correct case is stored in the dcache for
  * case-insensitive filesystems.
  *
- * For a case-insensitive lookup match and if the the case-exact dentry
- * already exists in in the dcache, use it and return it.
+ * For a case-insensitive lookup match and if the case-exact dentry
+ * already exists in the dcache, use it and return it.
  *
  * If no entry exists with the exact case name, allocate new dentry with
  * the exact case, and return the spliced entry.
@@ -2160,6 +2240,7 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 	}
 	res = d_splice_alias(inode, found);
 	if (res) {
+		d_lookup_done(found);
 		dput(found);
 		return res;
 	}
@@ -2167,10 +2248,16 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 }
 EXPORT_SYMBOL(d_add_ci);
 
-
-static inline bool d_same_name(const struct dentry *dentry,
-				const struct dentry *parent,
-				const struct qstr *name)
+/**
+ * d_same_name - compare dentry name with case-exact name
+ * @parent: parent dentry
+ * @dentry: the negative dentry that was passed to the parent's lookup func
+ * @name:   the case-exact name to be associated with the returned dentry
+ *
+ * Return: true if names are same, or false
+ */
+bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
+		 const struct qstr *name)
 {
 	if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) {
 		if (dentry->d_name.len != name->len)
@@ -2181,6 +2268,49 @@ static inline bool d_same_name(const struct dentry *dentry,
 				       dentry->d_name.len, dentry->d_name.name,
 				       name) == 0;
 }
+EXPORT_SYMBOL_GPL(d_same_name);
+
+/*
+ * This is __d_lookup_rcu() when the parent dentry has
+ * DCACHE_OP_COMPARE, which makes things much nastier.
+ */
+static noinline struct dentry *__d_lookup_rcu_op_compare(
+	const struct dentry *parent,
+	const struct qstr *name,
+	unsigned *seqp)
+{
+	u64 hashlen = name->hash_len;
+	struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen));
+	struct hlist_bl_node *node;
+	struct dentry *dentry;
+
+	hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
+		int tlen;
+		const char *tname;
+		unsigned seq;
+
+seqretry:
+		seq = raw_seqcount_begin(&dentry->d_seq);
+		if (dentry->d_parent != parent)
+			continue;
+		if (d_unhashed(dentry))
+			continue;
+		if (dentry->d_name.hash != hashlen_hash(hashlen))
+			continue;
+		tlen = dentry->d_name.len;
+		tname = dentry->d_name.name;
+		/* we want a consistent (name,len) pair */
+		if (read_seqcount_retry(&dentry->d_seq, seq)) {
+			cpu_relax();
+			goto seqretry;
+		}
+		if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0)
+			continue;
+		*seqp = seq;
+		return dentry;
+	}
+	return NULL;
+}
 
 /**
  * __d_lookup_rcu - search for a dentry (racy, store-free)
@@ -2228,6 +2358,9 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent,
 	 * Keep the two functions in sync.
 	 */
 
+	if (unlikely(parent->d_flags & DCACHE_OP_COMPARE))
+		return __d_lookup_rcu_op_compare(parent, name, seqp);
+
 	/*
 	 * The hash list is protected using RCU.
 	 *
@@ -2244,7 +2377,6 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent,
 	hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
 		unsigned seq;
 
-seqretry:
 		/*
 		 * The dentry sequence count protects us from concurrent
 		 * renames, and thus protects parent and name fields.
@@ -2267,28 +2399,10 @@ seqretry:
 			continue;
 		if (d_unhashed(dentry))
 			continue;
-
-		if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
-			int tlen;
-			const char *tname;
-			if (dentry->d_name.hash != hashlen_hash(hashlen))
-				continue;
-			tlen = dentry->d_name.len;
-			tname = dentry->d_name.name;
-			/* we want a consistent (name,len) pair */
-			if (read_seqcount_retry(&dentry->d_seq, seq)) {
-				cpu_relax();
-				goto seqretry;
-			}
-			if (parent->d_op->d_compare(dentry,
-						    tlen, tname, name) != 0)
-				continue;
-		} else {
-			if (dentry->d_name.hash_len != hashlen)
-				continue;
-			if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0)
-				continue;
-		}
+		if (dentry->d_name.hash_len != hashlen)
+			continue;
+		if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0)
+			continue;
 		*seqp = seq;
 		return dentry;
 	}
@@ -2483,7 +2597,7 @@ EXPORT_SYMBOL(d_rehash);
 
 static inline unsigned start_dir_add(struct inode *dir)
 {
-
+	preempt_disable_nested();
 	for (;;) {
 		unsigned n = dir->i_dir_seq;
 		if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
@@ -2492,9 +2606,12 @@ static inline unsigned start_dir_add(struct inode *dir)
 	}
 }
 
-static inline void end_dir_add(struct inode *dir, unsigned n)
+static inline void end_dir_add(struct inode *dir, unsigned int n,
+			       wait_queue_head_t *d_wait)
 {
 	smp_store_release(&dir->i_dir_seq, n + 2);
+	preempt_enable_nested();
+	wake_up_all(d_wait);
 }
 
 static void d_wait_lookup(struct dentry *dentry)
@@ -2621,32 +2738,50 @@ mismatch:
 }
 EXPORT_SYMBOL(d_alloc_parallel);
 
-void __d_lookup_done(struct dentry *dentry)
+/*
+ * - Unhash the dentry
+ * - Retrieve and clear the waitqueue head in dentry
+ * - Return the waitqueue head
+ */
+static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry)
 {
-	struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent,
-						 dentry->d_name.hash);
+	wait_queue_head_t *d_wait;
+	struct hlist_bl_head *b;
+
+	lockdep_assert_held(&dentry->d_lock);
+
+	b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash);
 	hlist_bl_lock(b);
 	dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
 	__hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
-	wake_up_all(dentry->d_wait);
+	d_wait = dentry->d_wait;
 	dentry->d_wait = NULL;
 	hlist_bl_unlock(b);
 	INIT_HLIST_NODE(&dentry->d_u.d_alias);
 	INIT_LIST_HEAD(&dentry->d_lru);
+	return d_wait;
 }
-EXPORT_SYMBOL(__d_lookup_done);
+
+void __d_lookup_unhash_wake(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	wake_up_all(__d_lookup_unhash(dentry));
+	spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL(__d_lookup_unhash_wake);
 
 /* inode->i_lock held if inode is non-NULL */
 
 static inline void __d_add(struct dentry *dentry, struct inode *inode)
 {
+	wait_queue_head_t *d_wait;
 	struct inode *dir = NULL;
 	unsigned n;
 	spin_lock(&dentry->d_lock);
 	if (unlikely(d_in_lookup(dentry))) {
 		dir = dentry->d_parent->d_inode;
 		n = start_dir_add(dir);
-		__d_lookup_done(dentry);
+		d_wait = __d_lookup_unhash(dentry);
 	}
 	if (inode) {
 		unsigned add_flags = d_flags_for_inode(inode);
@@ -2658,7 +2793,7 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode)
 	}
 	__d_rehash(dentry);
 	if (dir)
-		end_dir_add(dir, n);
+		end_dir_add(dir, n, d_wait);
 	spin_unlock(&dentry->d_lock);
 	if (inode)
 		spin_unlock(&inode->i_lock);
@@ -2805,6 +2940,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 		     bool exchange)
 {
 	struct dentry *old_parent, *p;
+	wait_queue_head_t *d_wait;
 	struct inode *dir = NULL;
 	unsigned n;
 
@@ -2835,7 +2971,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	if (unlikely(d_in_lookup(target))) {
 		dir = target->d_parent->d_inode;
 		n = start_dir_add(dir);
-		__d_lookup_done(target);
+		d_wait = __d_lookup_unhash(target);
 	}
 
 	write_seqcount_begin(&dentry->d_seq);
@@ -2871,7 +3007,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	write_seqcount_end(&dentry->d_seq);
 
 	if (dir)
-		end_dir_add(dir, n);
+		end_dir_add(dir, n, d_wait);
 
 	if (dentry->d_parent != old_parent)
 		spin_unlock(&dentry->d_parent->d_lock);
@@ -3113,8 +3249,10 @@ void d_genocide(struct dentry *parent)
 
 EXPORT_SYMBOL(d_genocide);
 
-void d_tmpfile(struct dentry *dentry, struct inode *inode)
+void d_tmpfile(struct file *file, struct inode *inode)
 {
+	struct dentry *dentry = file->f_path.dentry;
+
 	inode_dec_link_count(inode);
 	BUG_ON(dentry->d_name.name != dentry->d_iname ||
 		!hlist_unhashed(&dentry->d_u.d_alias) ||