1 files changed, 149 insertions, 82 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 22e536705c4..182bc41cd88 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -23,21 +23,44 @@
 #include <linux/uaccess.h>
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
+#include <linux/bootmem.h>
 #include "pnode.h"
 #include "internal.h"
 
-#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head))
-#define HASH_SIZE (1UL << HASH_SHIFT)
+static unsigned int m_hash_mask __read_mostly;
+static unsigned int m_hash_shift __read_mostly;
+static unsigned int mp_hash_mask __read_mostly;
+static unsigned int mp_hash_shift __read_mostly;
 
-static int event;
+static __initdata unsigned long mhash_entries;
+static int __init set_mhash_entries(char *str)
+{
+	if (!str)
+		return 0;
+	mhash_entries = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("mhash_entries=", set_mhash_entries);
+
+static __initdata unsigned long mphash_entries;
+static int __init set_mphash_entries(char *str)
+{
+	if (!str)
+		return 0;
+	mphash_entries = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("mphash_entries=", set_mphash_entries);
+
+static u64 event;
 static DEFINE_IDA(mnt_id_ida);
 static DEFINE_IDA(mnt_group_ida);
 static DEFINE_SPINLOCK(mnt_id_lock);
 static int mnt_id_start = 0;
 static int mnt_group_start = 1;
 
-static struct list_head *mount_hashtable __read_mostly;
-static struct list_head *mountpoint_hashtable __read_mostly;
+static struct hlist_head *mount_hashtable __read_mostly;
+static struct hlist_head *mountpoint_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
 static DECLARE_RWSEM(namespace_sem);
 
@@ -55,12 +78,19 @@ EXPORT_SYMBOL_GPL(fs_kobj);
  */
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
 
-static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
+static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry)
 {
 	unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
 	tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
-	tmp = tmp + (tmp >> HASH_SHIFT);
-	return tmp & (HASH_SIZE - 1);
+	tmp = tmp + (tmp >> m_hash_shift);
+	return &mount_hashtable[tmp & m_hash_mask];
+}
+
+static inline struct hlist_head *mp_hash(struct dentry *dentry)
+{
+	unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES);
+	tmp = tmp + (tmp >> mp_hash_shift);
+	return &mountpoint_hashtable[tmp & mp_hash_mask];
 }
 
 /*
@@ -187,7 +217,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		mnt->mnt_writers = 0;
 #endif
 
-		INIT_LIST_HEAD(&mnt->mnt_hash);
+		INIT_HLIST_NODE(&mnt->mnt_hash);
 		INIT_LIST_HEAD(&mnt->mnt_child);
 		INIT_LIST_HEAD(&mnt->mnt_mounts);
 		INIT_LIST_HEAD(&mnt->mnt_list);
@@ -384,9 +414,7 @@ EXPORT_SYMBOL_GPL(mnt_clone_write);
  */
 int __mnt_want_write_file(struct file *file)
 {
-	struct inode *inode = file_inode(file);
-
-	if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
+	if (!(file->f_mode & FMODE_WRITER))
 		return __mnt_want_write(file->f_path.mnt);
 	else
 		return mnt_clone_write(file->f_path.mnt);
@@ -540,13 +568,17 @@ int sb_prepare_remount_readonly(struct super_block *sb)
 static void free_vfsmnt(struct mount *mnt)
 {
 	kfree(mnt->mnt_devname);
-	mnt_free_id(mnt);
 #ifdef CONFIG_SMP
 	free_percpu(mnt->mnt_pcp);
 #endif
 	kmem_cache_free(mnt_cache, mnt);
 }
 
+static void delayed_free_vfsmnt(struct rcu_head *head)
+{
+	free_vfsmnt(container_of(head, struct mount, mnt_rcu));
+}
+
 /* call under rcu_read_lock */
 bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 {
@@ -575,10 +607,10 @@ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
  */
 struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 {
-	struct list_head *head = mount_hashtable + hash(mnt, dentry);
+	struct hlist_head *head = m_hash(mnt, dentry);
 	struct mount *p;
 
-	list_for_each_entry_rcu(p, head, mnt_hash)
+	hlist_for_each_entry_rcu(p, head, mnt_hash)
 		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
 			return p;
 	return NULL;
@@ -590,13 +622,17 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
  */
 struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
 {
-	struct list_head *head = mount_hashtable + hash(mnt, dentry);
-	struct mount *p;
-
-	list_for_each_entry_reverse(p, head, mnt_hash)
-		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
-			return p;
-	return NULL;
+	struct mount *p, *res;
+	res = p = __lookup_mnt(mnt, dentry);
+	if (!p)
+		goto out;
+	hlist_for_each_entry_continue(p, mnt_hash) {
+		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
+			break;
+		res = p;
+	}
+out:
+	return res;
 }
 
 /*
@@ -633,11 +669,11 @@ struct vfsmount *lookup_mnt(struct path *path)
 
 static struct mountpoint *new_mountpoint(struct dentry *dentry)
 {
-	struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry);
+	struct hlist_head *chain = mp_hash(dentry);
 	struct mountpoint *mp;
 	int ret;
 
-	list_for_each_entry(mp, chain, m_hash) {
+	hlist_for_each_entry(mp, chain, m_hash) {
 		if (mp->m_dentry == dentry) {
 			/* might be worth a WARN_ON() */
 			if (d_unlinked(dentry))
@@ -659,7 +695,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry)
 
 	mp->m_dentry = dentry;
 	mp->m_count = 1;
-	list_add(&mp->m_hash, chain);
+	hlist_add_head(&mp->m_hash, chain);
 	return mp;
 }
 
@@ -670,7 +706,7 @@ static void put_mountpoint(struct mountpoint *mp)
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
 		spin_unlock(&dentry->d_lock);
-		list_del(&mp->m_hash);
+		hlist_del(&mp->m_hash);
 		kfree(mp);
 	}
 }
@@ -712,7 +748,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path)
 	mnt->mnt_parent = mnt;
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	list_del_init(&mnt->mnt_child);
-	list_del_init(&mnt->mnt_hash);
+	hlist_del_init_rcu(&mnt->mnt_hash);
 	put_mountpoint(mnt->mnt_mp);
 	mnt->mnt_mp = NULL;
 }
@@ -739,15 +775,14 @@ static void attach_mnt(struct mount *mnt,
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	list_add_tail(&mnt->mnt_hash, mount_hashtable +
-			hash(&parent->mnt, mp->m_dentry));
+	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt)
+static void commit_tree(struct mount *mnt, struct mount *shadows)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -762,8 +797,11 @@ static void commit_tree(struct mount *mnt)
 
 	list_splice(&head, n->list.prev);
 
-	list_add_tail(&mnt->mnt_hash, mount_hashtable +
-				hash(&parent->mnt, mnt->mnt_mountpoint));
+	if (shadows)
+		hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
+	else
+		hlist_add_head_rcu(&mnt->mnt_hash,
+				m_hash(&parent->mnt, mnt->mnt_mountpoint));
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
 	touch_mnt_namespace(n);
 }
@@ -812,6 +850,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
 
 	root = mount_fs(type, flags, name, data);
 	if (IS_ERR(root)) {
+		mnt_free_id(mnt);
 		free_vfsmnt(mnt);
 		return ERR_CAST(root);
 	}
@@ -849,7 +888,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 			goto out_free;
 	}
 
-	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
 	/* Don't allow unprivileged users to change mount flags */
 	if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
 		mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
@@ -892,20 +931,11 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	return mnt;
 
  out_free:
+	mnt_free_id(mnt);
 	free_vfsmnt(mnt);
 	return ERR_PTR(err);
 }
 
-static void delayed_free(struct rcu_head *head)
-{
-	struct mount *mnt = container_of(head, struct mount, mnt_rcu);
-	kfree(mnt->mnt_devname);
-#ifdef CONFIG_SMP
-	free_percpu(mnt->mnt_pcp);
-#endif
-	kmem_cache_free(mnt_cache, mnt);
-}
-
 static void mntput_no_expire(struct mount *mnt)
 {
 put_again:
@@ -955,7 +985,7 @@ put_again:
 	dput(mnt->mnt.mnt_root);
 	deactivate_super(mnt->mnt.mnt_sb);
 	mnt_free_id(mnt);
-	call_rcu(&mnt->mnt_rcu, delayed_free);
+	call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt);
 }
 
 void mntput(struct vfsmount *mnt)
@@ -1064,14 +1094,29 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	struct proc_mounts *p = proc_mounts(m);
 
 	down_read(&namespace_sem);
-	return seq_list_start(&p->ns->list, *pos);
+	if (p->cached_event == p->ns->event) {
+		void *v = p->cached_mount;
+		if (*pos == p->cached_index)
+			return v;
+		if (*pos == p->cached_index + 1) {
+			v = seq_list_next(v, &p->ns->list, &p->cached_index);
+			return p->cached_mount = v;
+		}
+	}
+
+	p->cached_event = p->ns->event;
+	p->cached_mount = seq_list_start(&p->ns->list, *pos);
+	p->cached_index = *pos;
+	return p->cached_mount;
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct proc_mounts *p = proc_mounts(m);
 
-	return seq_list_next(v, &p->ns->list, pos);
+	p->cached_mount = seq_list_next(v, &p->ns->list, pos);
+	p->cached_index = *pos;
+	return p->cached_mount;
 }
 
 static void m_stop(struct seq_file *m, void *v)
@@ -1153,26 +1198,28 @@ int may_umount(struct vfsmount *mnt)
 
 EXPORT_SYMBOL(may_umount);
 
-static LIST_HEAD(unmounted);	/* protected by namespace_sem */
+static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
 
 static void namespace_unlock(void)
 {
 	struct mount *mnt;
-	LIST_HEAD(head);
+	struct hlist_head head = unmounted;
 
-	if (likely(list_empty(&unmounted))) {
+	if (likely(hlist_empty(&head))) {
 		up_write(&namespace_sem);
 		return;
 	}
 
-	list_splice_init(&unmounted, &head);
+	head.first->pprev = &head.first;
+	INIT_HLIST_HEAD(&unmounted);
+
 	up_write(&namespace_sem);
 
 	synchronize_rcu();
 
-	while (!list_empty(&head)) {
-		mnt = list_first_entry(&head, struct mount, mnt_hash);
-		list_del_init(&mnt->mnt_hash);
+	while (!hlist_empty(&head)) {
+		mnt = hlist_entry(head.first, struct mount, mnt_hash);
+		hlist_del_init(&mnt->mnt_hash);
 		if (mnt->mnt_ex_mountpoint.mnt)
 			path_put(&mnt->mnt_ex_mountpoint);
 		mntput(&mnt->mnt);
@@ -1193,16 +1240,19 @@ static inline void namespace_lock(void)
  */
 void umount_tree(struct mount *mnt, int how)
 {
-	LIST_HEAD(tmp_list);
+	HLIST_HEAD(tmp_list);
 	struct mount *p;
+	struct mount *last = NULL;
 
-	for (p = mnt; p; p = next_mnt(p, mnt))
-		list_move(&p->mnt_hash, &tmp_list);
+	for (p = mnt; p; p = next_mnt(p, mnt)) {
+		hlist_del_init_rcu(&p->mnt_hash);
+		hlist_add_head(&p->mnt_hash, &tmp_list);
+	}
 
 	if (how)
 		propagate_umount(&tmp_list);
 
-	list_for_each_entry(p, &tmp_list, mnt_hash) {
+	hlist_for_each_entry(p, &tmp_list, mnt_hash) {
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
@@ -1220,8 +1270,13 @@ void umount_tree(struct mount *mnt, int how)
 			p->mnt_mp = NULL;
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
+		last = p;
+	}
+	if (last) {
+		last->mnt_hash.next = unmounted.first;
+		unmounted.first = tmp_list.first;
+		unmounted.first->pprev = &unmounted.first;
 	}
-	list_splice(&tmp_list, &unmounted);
 }
 
 static void shrink_submounts(struct mount *mnt);
@@ -1605,24 +1660,23 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			struct mountpoint *dest_mp,
 			struct path *parent_path)
 {
-	LIST_HEAD(tree_list);
+	HLIST_HEAD(tree_list);
 	struct mount *child, *p;
+	struct hlist_node *n;
 	int err;
 
 	if (IS_MNT_SHARED(dest_mnt)) {
 		err = invent_group_ids(source_mnt, true);
 		if (err)
 			goto out;
-	}
-	err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
-	if (err)
-		goto out_cleanup_ids;
-
-	lock_mount_hash();
-
-	if (IS_MNT_SHARED(dest_mnt)) {
+		err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
+		lock_mount_hash();
+		if (err)
+			goto out_cleanup_ids;
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
+	} else {
+		lock_mount_hash();
 	}
 	if (parent_path) {
 		detach_mnt(source_mnt, parent_path);
@@ -1630,20 +1684,27 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt);
+		commit_tree(source_mnt, NULL);
 	}
 
-	list_for_each_entry_safe(child, p, &tree_list, mnt_hash) {
-		list_del_init(&child->mnt_hash);
-		commit_tree(child);
+	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
+		struct mount *q;
+		hlist_del_init(&child->mnt_hash);
+		q = __lookup_mnt_last(&child->mnt_parent->mnt,
+				      child->mnt_mountpoint);
+		commit_tree(child, q);
 	}
 	unlock_mount_hash();
 
 	return 0;
 
  out_cleanup_ids:
-	if (IS_MNT_SHARED(dest_mnt))
-		cleanup_group_ids(source_mnt, NULL);
+	while (!hlist_empty(&tree_list)) {
+		child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+		umount_tree(child, 0);
+	}
+	unlock_mount_hash();
+	cleanup_group_ids(source_mnt, NULL);
  out:
 	return err;
 }
@@ -1997,7 +2058,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 	struct mount *parent;
 	int err;
 
-	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT);
+	mnt_flags &= ~MNT_INTERNAL_FLAGS;
 
 	mp = lock_mount(path);
 	if (IS_ERR(mp))
@@ -2777,18 +2838,24 @@ void __init mnt_init(void)
 	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
 			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
 
-	mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
-	mountpoint_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
+	mount_hashtable = alloc_large_system_hash("Mount-cache",
+				sizeof(struct hlist_head),
+				mhash_entries, 19,
+				0,
+				&m_hash_shift, &m_hash_mask, 0, 0);
+	mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
+				sizeof(struct hlist_head),
+				mphash_entries, 19,
+				0,
+				&mp_hash_shift, &mp_hash_mask, 0, 0);
 
 	if (!mount_hashtable || !mountpoint_hashtable)
 		panic("Failed to allocate mount hash table\n");
 
-	printk(KERN_INFO "Mount-cache hash table entries: %lu\n", HASH_SIZE);
-
-	for (u = 0; u < HASH_SIZE; u++)
-		INIT_LIST_HEAD(&mount_hashtable[u]);
-	for (u = 0; u < HASH_SIZE; u++)
-		INIT_LIST_HEAD(&mountpoint_hashtable[u]);
+	for (u = 0; u <= m_hash_mask; u++)
+		INIT_HLIST_HEAD(&mount_hashtable[u]);
+	for (u = 0; u <= mp_hash_mask; u++)
+		INIT_HLIST_HEAD(&mountpoint_hashtable[u]);
 
 	kernfs_init();