NFSD: Pin to vfsmount for nfsd exports cache

index 3886b3b..0dde7b7 100644
@@ -1,3 +1,6 @@
+#ifndef _LINUX_FS_PIN_H
+#define _LINUX_FS_PIN_H
+
 #include <linux/wait.h>
 
 struct fs_pin {

@@ -16,9 +19,12 @@ static inline void init_fs_pin(struct fs_pin *p, void (*kill)(struct fs_pin *))
 	INIT_HLIST_NODE(&p->s_list);
 	INIT_HLIST_NODE(&p->m_list);
 	p->kill = kill;
+	p->done = 0;
 }
 
 void pin_remove(struct fs_pin *);
 void pin_insert_group(struct fs_pin *, struct vfsmount *, struct hlist_head *);
 void pin_insert(struct fs_pin *, struct vfsmount *);
 void pin_kill(struct fs_pin *);
+
+#endif

index 2928aff..edec603 100644
@@ -1270,18 +1270,13 @@ EXPORT_SYMBOL_GPL(qword_get);
  * get a header, then pass each real item in the cache
  */
 
-struct handle {
-	struct cache_detail *cd;
-};
-
 static void *c_start(struct seq_file *m, loff_t *pos)
 	__acquires(cd->hash_lock)
 {
 	loff_t n = *pos;
 	unsigned int hash, entry;
 	struct cache_head *ch;
-	struct cache_detail *cd = ((struct handle*)m->private)->cd;
-
+	struct cache_detail *cd = m->private;
 
 	read_lock(&cd->hash_lock);
 	if (!n--)

@@ -1308,7 +1303,7 @@ static void *c_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	struct cache_head *ch = p;
 	int hash = (*pos >> 32);
-	struct cache_detail *cd = ((struct handle*)m->private)->cd;
+	struct cache_detail *cd = m->private;
 
 	if (p == SEQ_START_TOKEN)
 		hash = 0;

@@ -1334,14 +1329,14 @@ static void *c_next(struct seq_file *m, void *p, loff_t *pos)
 static void c_stop(struct seq_file *m, void *p)
 	__releases(cd->hash_lock)
 {
-	struct cache_detail *cd = ((struct handle*)m->private)->cd;
+	struct cache_detail *cd = m->private;
 	read_unlock(&cd->hash_lock);
 }
 
 static int c_show(struct seq_file *m, void *p)
 {
 	struct cache_head *cp = p;
-	struct cache_detail *cd = ((struct handle*)m->private)->cd;
+	struct cache_detail *cd = m->private;
 
 	if (p == SEQ_START_TOKEN)
 		return cd->cache_show(m, cd, NULL);

@@ -1373,24 +1368,27 @@ static const struct seq_operations cache_content_op = {
 static int content_open(struct inode *inode, struct file *file,
 			struct cache_detail *cd)
 {
-	struct handle *han;
+	struct seq_file *seq;
+	int err;
 
 	if (!cd || !try_module_get(cd->owner))
 		return -EACCES;
-	han = __seq_open_private(file, &cache_content_op, sizeof(*han));
-	if (han == NULL) {
+
+	err = seq_open(file, &cache_content_op);
+	if (err) {
 		module_put(cd->owner);
-		return -ENOMEM;
+		return err;
 	}
 
-	han->cd = cd;
+	seq = file->private_data;
+	seq->private = cd;
 	return 0;
 }
 
 static int content_release(struct inode *inode, struct file *file,
 		struct cache_detail *cd)
 {
-	int ret = seq_release_private(inode, file);
+	int ret = seq_release(inode, file);
 	module_put(cd->owner);
 	return ret;
 }

index ecc0ff6..5a4b921 100644
@@ -210,6 +210,7 @@ extern int cache_check(struct cache_detail *detail,
 		       struct cache_head *h, struct cache_req *rqstp);
 extern void cache_flush(void);
 extern void cache_purge(struct cache_detail *detail);
+extern void cache_delete_entry(struct cache_detail *cd, struct cache_head *h);
 #define NEVER (0x7FFFFFFF)
 extern void __init cache_initialize(void);
 extern int cache_register_net(struct cache_detail *cd, struct net *net);

index ad2155c..8a27483 100644
@@ -458,6 +458,36 @@ static int cache_clean(void)
 	return rv;
 }
 
+void cache_delete_entry(struct cache_detail *detail, struct cache_head *h)
+{
+	struct cache_detail *tmp;
+
+	if (!detail || !h)
+		return;
+
+	spin_lock(&cache_list_lock);
+	list_for_each_entry(tmp, &cache_list, others) {
+		if (tmp == detail)
+			goto found;
+	}
+	spin_unlock(&cache_list_lock);
+	printk(KERN_WARNING "%s: Deleted cache detail %p\n", __func__, detail);
+	return ;
+
+found:
+	write_lock(&detail->hash_lock);
+
+	list_del_init(&h->cache_list);
+	detail->entries--;
+	set_bit(CACHE_CLEANED, &h->flags);
+
+	write_unlock(&detail->hash_lock);
+	spin_unlock(&cache_list_lock);
+
+	cache_put(h, detail);
+}
+EXPORT_SYMBOL_GPL(cache_delete_entry);
+
 /*
  * We want to regularly clean the cache, so we need to schedule some work ...
  */

index 1f52bfc..b559acf 100644
@@ -105,7 +105,7 @@ static inline void exp_put(struct svc_export *exp)
 
 static inline struct svc_export *exp_get(struct svc_export *exp)
 {
-	cache_get(&exp->h);
+	cache_get(&exp->h, exp->cd);
 	return exp;
 }
 struct svc_export * rqst_exp_find(struct svc_rqst *, int, u32 *);

index 5a4b921..f77b2cd 100644
@@ -101,6 +101,8 @@ struct cache_detail {
 	int			(*match)(struct cache_head *orig, struct cache_head *new);
 	void			(*init)(struct cache_head *orig, struct cache_head *new);
 	void			(*update)(struct cache_head *orig, struct cache_head *new);
+	void			(*validate)(struct cache_head *h);
+	void			(*invalidate)(struct cache_head *h);
 
 	/* fields below this comment are for internal use
 	 * and should not be touched by cache owners

@@ -185,8 +187,11 @@ sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h);
 
 extern void cache_clean_deferred(void *owner);
 
-static inline struct cache_head  *cache_get(struct cache_head *h)
+static inline struct cache_head *cache_get(struct cache_head *h, struct cache_detail *cd)
 {
+	if (cd && cd->validate)
+		cd->validate(h);
+
 	kref_get(&h->ref);
 	return h;
 }

@@ -197,6 +202,10 @@ static inline void cache_put(struct cache_head *h, struct cache_detail *cd)
 	if (atomic_read(&h->ref.refcount) <= 2 &&
 	    h->expiry_time < cd->nextcheck)
 		cd->nextcheck = h->expiry_time;
+
+	if (cd->invalidate)
+		cd->invalidate(h);
+
 	kref_put(&h->ref, cd->cache_put);
 }
 

index 1095be9..ee1faa2 100644
@@ -1520,7 +1520,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 			goto auth_err;
 		}
 		svcdata->rsci = rsci;
-		cache_get(&rsci->h);
+		cache_get(&rsci->h, NULL);
 		rqstp->rq_cred.cr_flavor = gss_svc_to_pseudoflavor(
 					rsci->mechctx->mech_type,
 					GSS_C_QOP_DEFAULT,

index 8a27483..cb7f3c0 100644
@@ -68,7 +68,7 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 			if (cache_is_expired(detail, tmp))
 				/* This entry is expired, we will discard it. */
 				break;
-			cache_get(tmp);
+			cache_get(tmp, detail);
 			read_unlock(&detail->hash_lock);
 			return tmp;
 		}

@@ -98,7 +98,7 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 				freeme = tmp;
 				break;
 			}
-			cache_get(tmp);
+			cache_get(tmp, detail);
 			write_unlock(&detail->hash_lock);
 			cache_put(new, detail);
 			return tmp;

@@ -107,7 +107,7 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 
 	list_add(&new->cache_list, head);
 	detail->entries++;
-	cache_get(new);
+	cache_get(new, detail);
 	write_unlock(&detail->hash_lock);
 
 	if (freeme)

@@ -175,7 +175,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 		detail->update(tmp, new);
 	list_add(&tmp->cache_list, &detail->hash_table[hash]);
 	detail->entries++;
-	cache_get(tmp);
+	cache_get(tmp, detail);
 	cache_fresh_locked(tmp, new->expiry_time);
 	cache_fresh_locked(old, 0);
 	write_unlock(&detail->hash_lock);

@@ -1204,7 +1204,7 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h)
 	}
 
 	crq->q.reader = 0;
-	crq->item = cache_get(h);
+	crq->item = cache_get(h, detail);
 	crq->buf = buf;
 	crq->len = 0;
 	crq->readers = 0;

@@ -1382,7 +1382,7 @@ static int c_show(struct seq_file *m, void *p)
 		seq_printf(m, "# expiry=%ld refcnt=%d flags=%lx\n",
 			   convert_to_wallclock(cp->expiry_time),
 			   atomic_read(&cp->ref.refcount), cp->flags);
-	cache_get(cp);
+	cache_get(cp, cd);
 	if (cache_check(cd, cp, NULL))
 		/* cache_check does a cache_put on failure */
 		seq_printf(m, "# ");

index 621ca7b..ebba6b7 100644
@@ -359,7 +359,7 @@ ip_map_cached_get(struct svc_xprt *xprt)
 				cache_put(&ipm->h, sn->ip_map_cache);
 				return NULL;
 			}
-			cache_get(&ipm->h);
+			cache_get(&ipm->h, NULL);
 		}
 		spin_unlock(&xprt->xpt_lock);
 	}

index 611b540..a1a4eb2 100644
@@ -17,6 +17,7 @@ void pin_remove(struct fs_pin *pin)
 	wake_up_locked(&pin->wait);
 	spin_unlock_irq(&pin->wait.lock);
 }
+EXPORT_SYMBOL(pin_remove);
 
 void pin_insert_group(struct fs_pin *pin, struct vfsmount *m, struct hlist_head *p)
 {

@@ -26,11 +27,13 @@ void pin_insert_group(struct fs_pin *pin, struct vfsmount *m, struct hlist_head
 	hlist_add_head(&pin->m_list, &real_mount(m)->mnt_pins);
 	spin_unlock(&pin_lock);
 }
+EXPORT_SYMBOL(pin_insert_group);
 
 void pin_insert(struct fs_pin *pin, struct vfsmount *m)
 {
 	pin_insert_group(pin, m, &m->mnt_sb->s_pins);
 }
+EXPORT_SYMBOL(pin_insert);
 
 void pin_kill(struct fs_pin *p)
 {

@@ -72,6 +75,7 @@ void pin_kill(struct fs_pin *p)
 	}
 	rcu_read_unlock();
 }
+EXPORT_SYMBOL(pin_kill);
 
 void mnt_pin_kill(struct mount *m)
 {

index 4a8d998b..ac71c65 100644
@@ -492,6 +492,32 @@ void path_put(const struct path *path)
 }
 EXPORT_SYMBOL(path_put);
 
+/**
+ * path_get_pin - get a reference to a path's dentry
+ *                and pin to path's vfsmnt
+ * @path: path to get the reference to
+ * @p: the fs_pin pin to vfsmnt
+ */
+void path_get_pin(struct path *path, struct fs_pin *p)
+{
+	dget(path->dentry);
+	pin_insert_group(p, path->mnt, NULL);
+}
+EXPORT_SYMBOL(path_get_pin);
+
+/**
+ * path_put_unpin - put a reference to a path's dentry
+ *                  and remove pin to path's vfsmnt
+ * @path: path to put the reference to
+ * @p: the fs_pin removed from vfsmnt
+ */
+void path_put_unpin(struct path *path, struct fs_pin *p)
+{
+	dput(path->dentry);
+	pin_remove(p);
+}
+EXPORT_SYMBOL(path_put_unpin);
+
 struct nameidata {
 	struct path	path;
 	struct qstr	last;

index d137218..34599fb 100644
@@ -3,6 +3,7 @@
 
 struct dentry;
 struct vfsmount;
+struct fs_pin;
 
 struct path {
 	struct vfsmount *mnt;

@@ -12,6 +13,9 @@ struct path {
 extern void path_get(const struct path *);
 extern void path_put(const struct path *);
 
+extern void path_get_pin(struct path *, struct fs_pin *);
+extern void path_put_unpin(struct path *, struct fs_pin *);
+
 static inline int path_equal(const struct path *path1, const struct path *path2)
 {
 	return path1->mnt == path2->mnt && path1->dentry == path2->dentry;

index 1f4f9da..f31d165 100644
@@ -1142,6 +1142,25 @@ struct vfsmount *mntget(struct vfsmount *mnt)
 }
 EXPORT_SYMBOL(mntget);
 
+struct vfsmount *legitimize_mntget(struct vfsmount *vfsmnt)
+{
+	struct mount *mnt;
+
+	if (vfsmnt == NULL)
+		return NULL;
+
+	read_seqlock_excl(&mount_lock);
+	mnt = real_mount(vfsmnt);
+	if (vfsmnt->mnt_flags & (MNT_SYNC_UMOUNT | MNT_UMOUNT | MNT_DOOMED))
+		vfsmnt = NULL;
+	else
+		mnt_add_count(mnt, 1);
+	read_sequnlock_excl(&mount_lock);
+
+	return vfsmnt;
+}
+EXPORT_SYMBOL(legitimize_mntget);
+
 struct vfsmount *mnt_clone_internal(struct path *path)
 {
 	struct mount *p;

index f822c3c..8ae9dc0 100644
@@ -79,6 +79,7 @@ extern void mnt_drop_write(struct vfsmount *mnt);
 extern void mnt_drop_write_file(struct file *file);
 extern void mntput(struct vfsmount *mnt);
 extern struct vfsmount *mntget(struct vfsmount *mnt);
+extern struct vfsmount *legitimize_mntget(struct vfsmount *vfsmnt);
 extern struct vfsmount *mnt_clone_internal(struct path *path);
 extern int __mnt_is_readonly(struct vfsmount *mnt);
 

index 002d3a9..34a384c 100644
@@ -1075,73 +1075,6 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	return rv;
 }
 
-/* Iterator */
-
-static void *e_start(struct seq_file *m, loff_t *pos)
-	__acquires(((struct cache_detail *)m->private)->hash_lock)
-{
-	loff_t n = *pos;
-	unsigned hash, export;
-	struct cache_head *ch;
-	struct cache_detail *cd = m->private;
-	struct cache_head **export_table = cd->hash_table;
-
-	read_lock(&cd->hash_lock);
-	if (!n--)
-		return SEQ_START_TOKEN;
-	hash = n >> 32;
-	export = n & ((1LL<<32) - 1);
-
-	
-	for (ch=export_table[hash]; ch; ch=ch->next)
-		if (!export--)
-			return ch;
-	n &= ~((1LL<<32) - 1);
-	do {
-		hash++;
-		n += 1LL<<32;
-	} while(hash < EXPORT_HASHMAX && export_table[hash]==NULL);
-	if (hash >= EXPORT_HASHMAX)
-		return NULL;
-	*pos = n+1;
-	return export_table[hash];
-}
-
-static void *e_next(struct seq_file *m, void *p, loff_t *pos)
-{
-	struct cache_head *ch = p;
-	int hash = (*pos >> 32);
-	struct cache_detail *cd = m->private;
-	struct cache_head **export_table = cd->hash_table;
-
-	if (p == SEQ_START_TOKEN)
-		hash = 0;
-	else if (ch->next == NULL) {
-		hash++;
-		*pos += 1LL<<32;
-	} else {
-		++*pos;
-		return ch->next;
-	}
-	*pos &= ~((1LL<<32) - 1);
-	while (hash < EXPORT_HASHMAX && export_table[hash] == NULL) {
-		hash++;
-		*pos += 1LL<<32;
-	}
-	if (hash >= EXPORT_HASHMAX)
-		return NULL;
-	++*pos;
-	return export_table[hash];
-}
-
-static void e_stop(struct seq_file *m, void *p)
-	__releases(((struct cache_detail *)m->private)->hash_lock)
-{
-	struct cache_detail *cd = m->private;
-
-	read_unlock(&cd->hash_lock);
-}
-
 static struct flags {
 	int flag;
 	char *name[2];

@@ -1270,9 +1203,9 @@ static int e_show(struct seq_file *m, void *p)
 }
 
 const struct seq_operations nfs_exports_op = {
-	.start	= e_start,
-	.next	= e_next,
-	.stop	= e_stop,
+	.start	= cache_seq_start,
+	.next	= cache_seq_next,
+	.stop	= cache_seq_stop,
 	.show	= e_show,
 };
 

index 437ddb6..04ee5a2 100644
@@ -224,6 +224,11 @@ extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *,
 					umode_t, struct cache_detail *);
 extern void sunrpc_cache_unregister_pipefs(struct cache_detail *);
 
+/* Must store cache_detail in seq_file->private if using next three functions */
+extern void *cache_seq_start(struct seq_file *file, loff_t *pos);
+extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos);
+extern void cache_seq_stop(struct seq_file *file, void *p);
+
 extern void qword_add(char **bpp, int *lp, char *str);
 extern void qword_addhex(char **bpp, int *lp, char *buf, int blen);
 extern int qword_get(char **bpp, char *dest, int bufsize);

index edec603..673c2fa 100644
@@ -1270,7 +1270,7 @@ EXPORT_SYMBOL_GPL(qword_get);
  * get a header, then pass each real item in the cache
  */
 
-static void *c_start(struct seq_file *m, loff_t *pos)
+void *cache_seq_start(struct seq_file *m, loff_t *pos)
 	__acquires(cd->hash_lock)
 {
 	loff_t n = *pos;

@@ -1298,8 +1298,9 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 	*pos = n+1;
 	return cd->hash_table[hash];
 }
+EXPORT_SYMBOL_GPL(cache_seq_start);
 
-static void *c_next(struct seq_file *m, void *p, loff_t *pos)
+void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	struct cache_head *ch = p;
 	int hash = (*pos >> 32);

@@ -1325,13 +1326,15 @@ static void *c_next(struct seq_file *m, void *p, loff_t *pos)
 	++*pos;
 	return cd->hash_table[hash];
 }
+EXPORT_SYMBOL_GPL(cache_seq_next);
 
-static void c_stop(struct seq_file *m, void *p)
+void cache_seq_stop(struct seq_file *m, void *p)
 	__releases(cd->hash_lock)
 {
 	struct cache_detail *cd = m->private;
 	read_unlock(&cd->hash_lock);
 }
+EXPORT_SYMBOL_GPL(cache_seq_stop);
 
 static int c_show(struct seq_file *m, void *p)
 {

@@ -1359,9 +1362,9 @@ static int c_show(struct seq_file *m, void *p)
 }
 
 static const struct seq_operations cache_content_op = {
-	.start	= c_start,
-	.next	= c_next,
-	.stop	= c_stop,
+	.start	= cache_seq_start,
+	.next	= cache_seq_next,
+	.stop	= cache_seq_stop,
 	.show	= c_show,
 };
 

index 04ee5a2..ecc0ff6 100644
@@ -46,7 +46,7 @@
  * 
  */
 struct cache_head {
-	struct cache_head * next;
+	struct list_head	cache_list;
 	time_t		expiry_time;	/* After time time, don't use the data */
 	time_t		last_refresh;   /* If CACHE_PENDING, this is when upcall 
 					 * was sent, else this is when update was received

@@ -73,7 +73,7 @@ struct cache_detail_pipefs {
 struct cache_detail {
 	struct module *		owner;
 	int			hash_size;
-	struct cache_head **	hash_table;
+	struct list_head *	hash_table;
 	rwlock_t		hash_lock;
 
 	atomic_t		inuse; /* active user-space update or lookup */

212 lines not on this page · raw message

index 34a384c..f7b1aa8 100644
@@ -37,15 +37,23 @@
 #define	EXPKEY_HASHMAX		(1 << EXPKEY_HASHBITS)
 #define	EXPKEY_HASHMASK		(EXPKEY_HASHMAX -1)
 
+static void expkey_destroy(struct svc_expkey *key)
+{
+	auth_domain_put(key->ek_client);
+	kfree_rcu(key, rcu_head);
+}
+
 static void expkey_put(struct kref *ref)
 {
 	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
 
 	if (test_bit(CACHE_VALID, &key->h.flags) &&
-	    !test_bit(CACHE_NEGATIVE, &key->h.flags))
-		path_put(&key->ek_path);
-	auth_domain_put(key->ek_client);
-	kfree(key);
+	    !test_bit(CACHE_NEGATIVE, &key->h.flags)) {
+		rcu_read_lock();
+		complete(&key->ek_done);
+		pin_kill(&key->ek_pin);
+	} else
+		expkey_destroy(key);
 }
 
 static void expkey_request(struct cache_detail *cd,

@@ -83,7 +91,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
 		return -EINVAL;
 	mesg[mlen-1] = 0;
 
-	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
 	err = -ENOMEM;
 	if (!buf)
 		goto out;

@@ -119,6 +127,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
 	if (key.h.expiry_time == 0)
 		goto out;
 
+	key.cd = cd;
 	key.ek_client = dom;	
 	key.ek_fsidtype = fsidtype;
 	memcpy(key.ek_fsid, buf, len);

@@ -210,6 +219,59 @@ static inline void expkey_init(struct cache_head *cnew,
 	new->ek_fsidtype = item->ek_fsidtype;
 
 	memcpy(new->ek_fsid, item->ek_fsid, sizeof(new->ek_fsid));
+	new->cd = item->cd;
+}
+
+static void expkey_validate(struct cache_head *h)
+{
+	struct svc_expkey *key = container_of(h, struct svc_expkey, h);
+
+	if (!test_bit(CACHE_VALID, &key->h.flags) ||
+	    test_bit(CACHE_NEGATIVE, &key->h.flags))
+		return;
+
+	if (atomic_read(&h->ref.refcount) == 1) {
+		mutex_lock(&key->ek_mutex);
+		if (legitimize_mntget(key->ek_path.mnt) == NULL) {
+			printk(KERN_WARNING "%s: Get mnt for %pd2 failed!\n",
+				__func__, key->ek_path.dentry);
+			set_bit(CACHE_NEGATIVE, &h->flags);
+		} else
+			key->ek_mnt_ref = true;
+		mutex_unlock(&key->ek_mutex);
+	}
+}
+
+static void expkey_invalidate(struct cache_head *h)
+{
+	struct svc_expkey *key = container_of(h, struct svc_expkey, h);
+
+	if (atomic_read(&h->ref.refcount) == 2) {
+		mutex_lock(&key->ek_mutex);
+		if (key->ek_mnt_ref) {
+			mntput(key->ek_path.mnt);
+			key->ek_mnt_ref = false;
+		}
+		mutex_unlock(&key->ek_mutex);
+	}
+}
+
+static void expkey_pin_kill(struct fs_pin *pin)
+{
+	struct svc_expkey *key = container_of(pin, struct svc_expkey, ek_pin);
+
+	if (!completion_done(&key->ek_done)) {
+		schedule_work(&key->ek_work);
+		wait_for_completion(&key->ek_done);
+	}
+	path_put_unpin(&key->ek_path, &key->ek_pin);
+	expkey_destroy(key);
+}
+
+static void expkey_close_work(struct work_struct *work)
+{
+	struct svc_expkey *key = container_of(work, struct svc_expkey, ek_work);
+	cache_delete_entry(key->cd, &key->h);
 }
 
 static inline void expkey_update(struct cache_head *cnew,

@@ -218,16 +280,20 @@ static inline void expkey_update(struct cache_head *cnew,
 	struct svc_expkey *new = container_of(cnew, struct svc_expkey, h);
 	struct svc_expkey *item = container_of(citem, struct svc_expkey, h);
 
+	init_fs_pin(&new->ek_pin, expkey_pin_kill);
 	new->ek_path = item->ek_path;
-	path_get(&item->ek_path);
+	path_get_pin(&new->ek_path, &new->ek_pin);
 }
 
 static struct cache_head *expkey_alloc(void)
 {
-	struct svc_expkey *i = kmalloc(sizeof(*i), GFP_KERNEL);
-	if (i)
+	struct svc_expkey *i = kzalloc(sizeof(*i), GFP_KERNEL);
+	if (i) {
+		INIT_WORK(&i->ek_work, expkey_close_work);
+		init_completion(&i->ek_done);
+		mutex_init(&i->ek_mutex);
 		return &i->h;
-	else
+	} else
 		return NULL;
 }
 

@@ -243,6 +309,8 @@ static struct cache_detail svc_expkey_cache_template = {
 	.init		= expkey_init,
 	.update       	= expkey_update,
 	.alloc		= expkey_alloc,
+	.validate	= expkey_validate,
+	.invalidate	= expkey_invalidate,
 };
 
 static int

@@ -306,14 +374,21 @@ static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc)
 	fsloc->locations = NULL;
 }
 
-static void svc_export_put(struct kref *ref)
+static void svc_export_destroy(struct svc_export *exp)
 {
-	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
-	path_put(&exp->ex_path);
 	auth_domain_put(exp->ex_client);
 	nfsd4_fslocs_free(&exp->ex_fslocs);
 	kfree(exp->ex_uuid);
-	kfree(exp);
+	kfree_rcu(exp, rcu_head);
+}
+
+static void svc_export_put(struct kref *ref)
+{
+	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
+
+	rcu_read_lock();
+	complete(&exp->ex_done);
+	pin_kill(&exp->ex_pin);
 }
 
 static void svc_export_request(struct cache_detail *cd,

@@ -520,7 +595,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 		return -EINVAL;
 	mesg[mlen-1] = 0;
 
-	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 

@@ -694,15 +769,67 @@ static int svc_export_match(struct cache_head *a, struct cache_head *b)
 		path_equal(&orig->ex_path, &new->ex_path);
 }
 
+static void export_validate(struct cache_head *h)
+{
+	struct svc_export *exp = container_of(h, struct svc_export, h);
+
+	if (test_bit(CACHE_NEGATIVE, &h->flags))
+		return;
+
+	if (atomic_read(&h->ref.refcount) == 1) {
+		mutex_lock(&exp->ex_mutex);
+		if (legitimize_mntget(exp->ex_path.mnt) == NULL) {
+			printk(KERN_WARNING "%s: Get mnt for %pd2 failed!\n",
+				__func__, exp->ex_path.dentry);
+			set_bit(CACHE_NEGATIVE, &h->flags);
+		} else
+			exp->ex_mnt_ref = true;
+		mutex_unlock(&exp->ex_mutex);
+	}
+}
+
+static void export_invalidate(struct cache_head *h)
+{
+	struct svc_export *exp = container_of(h, struct svc_export, h);
+
+	if (atomic_read(&h->ref.refcount) == 2) {
+		mutex_lock(&exp->ex_mutex);
+		if (exp->ex_mnt_ref) {
+			mntput(exp->ex_path.mnt);
+			exp->ex_mnt_ref = false;
+		}
+		mutex_unlock(&exp->ex_mutex);
+	}
+}
+
+static void export_pin_kill(struct fs_pin *pin)
+{
+	struct svc_export *exp = container_of(pin, struct svc_export, ex_pin);
+
+	if (!completion_done(&exp->ex_done)) {
+		schedule_work(&exp->ex_work);
+		wait_for_completion(&exp->ex_done);
+	}
+	path_put_unpin(&exp->ex_path, &exp->ex_pin);
+	svc_export_destroy(exp);
+}
+
+static void export_close_work(struct work_struct *work)
+{
+	struct svc_export *exp = container_of(work, struct svc_export, ex_work);
+	cache_delete_entry(exp->cd, &exp->h);
+}
+
 static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
 {
 	struct svc_export *new = container_of(cnew, struct svc_export, h);
 	struct svc_export *item = container_of(citem, struct svc_export, h);
 
+	init_fs_pin(&new->ex_pin, export_pin_kill);
 	kref_get(&item->ex_client->ref);
 	new->ex_client = item->ex_client;
 	new->ex_path = item->ex_path;
-	path_get(&item->ex_path);
+	path_get_pin(&new->ex_path, &new->ex_pin);
 	new->ex_fslocs.locations = NULL;
 	new->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = 0;

@@ -740,10 +867,13 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 
 static struct cache_head *svc_export_alloc(void)
 {
-	struct svc_export *i = kmalloc(sizeof(*i), GFP_KERNEL);
-	if (i)
+	struct svc_export *i = kzalloc(sizeof(*i), GFP_KERNEL);
+	if (i) {
+		INIT_WORK(&i->ex_work, export_close_work);
+		init_completion(&i->ex_done);
+		mutex_init(&i->ex_mutex);
 		return &i->h;
-	else
+	} else
 		return NULL;
 }
 

@@ -759,6 +889,8 @@ static struct cache_detail svc_export_cache_template = {
 	.init		= svc_export_init,
 	.update		= export_update,
 	.alloc		= svc_export_alloc,
+	.validate	= export_validate,
+	.invalidate	= export_invalidate,
 };
 
 static int

@@ -809,6 +941,7 @@ exp_find_key(struct cache_detail *cd, struct auth_domain *clp, int fsid_type,
 	if (!clp)
 		return ERR_PTR(-ENOENT);
 
+	key.cd = cd;
 	key.ek_client = clp;
 	key.ek_fsidtype = fsid_type;
 	memcpy(key.ek_fsid, fsidv, key_len(fsid_type));

index b559acf..1b5c5f8 100644
@@ -4,6 +4,7 @@
 #ifndef NFSD_EXPORT_H
 #define NFSD_EXPORT_H
 
+#include <linux/fs_pin.h>
 #include <linux/sunrpc/cache.h>
 #include <uapi/linux/nfsd/export.h>
 

@@ -46,6 +47,8 @@ struct exp_flavor_info {
 
 struct svc_export {
 	struct cache_head	h;
+	struct cache_detail	*cd;
+
 	struct auth_domain *	ex_client;
 	int			ex_flags;
 	struct path		ex_path;

@@ -58,7 +61,16 @@ struct svc_export {
 	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
 	enum pnfs_layouttype	ex_layout_type;
 	struct nfsd4_deviceid_map *ex_devid_map;
-	struct cache_detail	*cd;
+
+	struct fs_pin		ex_pin;
+	struct rcu_head		rcu_head;
+
+	bool			ex_mnt_ref;
+	struct mutex		ex_mutex;
+
+	/* For cache_put and fs umounting window */
+	struct completion	ex_done;
+	struct work_struct	ex_work;
 };
 
 /* an "export key" (expkey) maps a filehandlefragement to an

@@ -67,12 +79,22 @@ struct svc_export {
  */
 struct svc_expkey {
 	struct cache_head	h;
+	struct cache_detail	*cd;
 
 	struct auth_domain *	ek_client;
 	int			ek_fsidtype;
 	u32			ek_fsid[6];
 
 	struct path		ek_path;
+	struct fs_pin		ek_pin;
+	struct rcu_head		rcu_head;
+
+	bool			ek_mnt_ref;
+	struct mutex		ek_mutex;
+
+	/* For cache_put and fs umounting window */
+	struct completion	ek_done;
+	struct work_struct	ek_work;
 };
 
 #define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))