Merge tag 'ceph-for-6.11-rc1' of https://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "A small patchset to address bogus I/O errors and ultimately an
  assertion failure in the face of watch errors with -o exclusive
  mappings in RBD marked for stable and some assorted CephFS fixes"

* tag 'ceph-for-6.11-rc1' of https://github.com/ceph/ceph-client:
  rbd: don't assume rbd_is_lock_owner() for exclusive mappings
  rbd: don't assume RBD_LOCK_STATE_LOCKED for exclusive mappings
  rbd: rename RBD_LOCK_STATE_RELEASING and releasing_wait
  ceph: fix incorrect kmalloc size of pagevec mempool
  ceph: periodically flush the cap releases
  ceph: convert comma to semicolon in __ceph_dentry_dir_lease_touch()
  ceph: use cap_wait_list only if debugfs is enabled

Author: torvalds

drivers/block/rbd.c

@@ -362,7 +362,7 @@ enum rbd_watch_state {
 enum rbd_lock_state {
 	RBD_LOCK_STATE_UNLOCKED,
 	RBD_LOCK_STATE_LOCKED,
-	RBD_LOCK_STATE_RELEASING,
+	RBD_LOCK_STATE_QUIESCING,
 };
 
 /* WatchNotify::ClientId */
@@ -422,7 +422,7 @@ struct rbd_device {
 	struct list_head	running_list;
 	struct completion	acquire_wait;
 	int			acquire_err;
-	struct completion	releasing_wait;
+	struct completion	quiescing_wait;
 
 	spinlock_t		object_map_lock;
 	u8			*object_map;
@@ -525,7 +525,7 @@ static bool __rbd_is_lock_owner(struct rbd_device *rbd_dev)
 	lockdep_assert_held(&rbd_dev->lock_rwsem);
 
 	return rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED ||
-	       rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING;
+	       rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING;
 }
 
 static bool rbd_is_lock_owner(struct rbd_device *rbd_dev)
@@ -3457,13 +3457,14 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req)
 	lockdep_assert_held(&rbd_dev->lock_rwsem);
 	spin_lock(&rbd_dev->lock_lists_lock);
 	if (!list_empty(&img_req->lock_item)) {
+		rbd_assert(!list_empty(&rbd_dev->running_list));
 		list_del_init(&img_req->lock_item);
-		need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+		need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING &&
 			       list_empty(&rbd_dev->running_list));
 	}
 	spin_unlock(&rbd_dev->lock_lists_lock);
 	if (need_wakeup)
-		complete(&rbd_dev->releasing_wait);
+		complete(&rbd_dev->quiescing_wait);
 }
 
 static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
@@ -3476,11 +3477,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
 	if (rbd_lock_add_request(img_req))
 		return 1;
 
-	if (rbd_dev->opts->exclusive) {
-		WARN_ON(1); /* lock got released? */
-		return -EROFS;
-	}
-
 	/*
 	 * Note the use of mod_delayed_work() in rbd_acquire_lock()
 	 * and cancel_delayed_work() in wake_lock_waiters().
@@ -4181,16 +4177,16 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev)
 	/*
 	 * Ensure that all in-flight IO is flushed.
 	 */
-	rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING;
-	rbd_assert(!completion_done(&rbd_dev->releasing_wait));
+	rbd_dev->lock_state = RBD_LOCK_STATE_QUIESCING;
+	rbd_assert(!completion_done(&rbd_dev->quiescing_wait));
 	if (list_empty(&rbd_dev->running_list))
 		return true;
 
 	up_write(&rbd_dev->lock_rwsem);
-	wait_for_completion(&rbd_dev->releasing_wait);
+	wait_for_completion(&rbd_dev->quiescing_wait);
 
 	down_write(&rbd_dev->lock_rwsem);
-	if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING)
+	if (rbd_dev->lock_state != RBD_LOCK_STATE_QUIESCING)
 		return false;
 
 	rbd_assert(list_empty(&rbd_dev->running_list));
@@ -4601,6 +4597,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev)
 			rbd_warn(rbd_dev, "failed to update lock cookie: %d",
 				 ret);
 
+		if (rbd_dev->opts->exclusive)
+			rbd_warn(rbd_dev,
+			     "temporarily releasing lock on exclusive mapping");
+
 		/*
 		 * Lock cookie cannot be updated on older OSDs, so do
 		 * a manual release and queue an acquire.
@@ -5376,7 +5376,7 @@ static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec)
 	INIT_LIST_HEAD(&rbd_dev->acquiring_list);
 	INIT_LIST_HEAD(&rbd_dev->running_list);
 	init_completion(&rbd_dev->acquire_wait);
-	init_completion(&rbd_dev->releasing_wait);
+	init_completion(&rbd_dev->quiescing_wait);
 
 	spin_lock_init(&rbd_dev->object_map_lock);
 
@@ -6582,11 +6582,6 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
 	if (ret)
 		return ret;
 
-	/*
-	 * The lock may have been released by now, unless automatic lock
-	 * transitions are disabled.
-	 */
-	rbd_assert(!rbd_dev->opts->exclusive || rbd_is_lock_owner(rbd_dev));
 	return 0;
 }
 

fs/ceph/caps.c

@@ -3067,10 +3067,13 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 				       flags, &_got);
 		WARN_ON_ONCE(ret == -EAGAIN);
 		if (!ret) {
+#ifdef CONFIG_DEBUG_FS
 			struct ceph_mds_client *mdsc = fsc->mdsc;
 			struct cap_wait cw;
+#endif
 			DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+#ifdef CONFIG_DEBUG_FS
 			cw.ino = ceph_ino(inode);
 			cw.tgid = current->tgid;
 			cw.need = need;
@@ -3079,6 +3082,7 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 			spin_lock(&mdsc->caps_list_lock);
 			list_add(&cw.list, &mdsc->cap_wait_list);
 			spin_unlock(&mdsc->caps_list_lock);
+#endif
 
 			/* make sure used fmode not timeout */
 			ceph_get_fmode(ci, flags, FMODE_WAIT_BIAS);
@@ -3097,9 +3101,11 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 			remove_wait_queue(&ci->i_cap_wq, &wait);
 			ceph_put_fmode(ci, flags, FMODE_WAIT_BIAS);
 
+#ifdef CONFIG_DEBUG_FS
 			spin_lock(&mdsc->caps_list_lock);
 			list_del(&cw.list);
 			spin_unlock(&mdsc->caps_list_lock);
+#endif
 
 			if (ret == -EAGAIN)
 				continue;

fs/ceph/dir.c

@@ -1589,7 +1589,7 @@ void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di)
 	}
 
 	spin_lock(&mdsc->dentry_list_lock);
-	__dentry_dir_lease_touch(mdsc, di),
+	__dentry_dir_lease_touch(mdsc, di);
 	spin_unlock(&mdsc->dentry_list_lock);
 }
 

fs/ceph/mds_client.c

@@ -5446,6 +5446,8 @@ static void delayed_work(struct work_struct *work)
 		}
 		mutex_unlock(&mdsc->mutex);
 
+		ceph_flush_cap_releases(mdsc, s);
+
 		mutex_lock(&s->s_mutex);
 		if (renew_caps)
 			send_renew_caps(mdsc, s);
@@ -5505,7 +5507,9 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	INIT_DELAYED_WORK(&mdsc->delayed_work, delayed_work);
 	mdsc->last_renew_caps = jiffies;
 	INIT_LIST_HEAD(&mdsc->cap_delay_list);
+#ifdef CONFIG_DEBUG_FS
 	INIT_LIST_HEAD(&mdsc->cap_wait_list);
+#endif
 	spin_lock_init(&mdsc->cap_delay_lock);
 	INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list);
 	INIT_LIST_HEAD(&mdsc->snap_flush_list);

fs/ceph/mds_client.h

@@ -416,6 +416,8 @@ struct ceph_quotarealm_inode {
 	struct inode *inode;
 };
 
+#ifdef CONFIG_DEBUG_FS
+
 struct cap_wait {
 	struct list_head	list;
 	u64			ino;
@@ -424,6 +426,8 @@ struct cap_wait {
 	int			want;
 };
 
+#endif
+
 enum {
 	CEPH_MDSC_STOPPING_BEGIN = 1,
 	CEPH_MDSC_STOPPING_FLUSHING = 2,
@@ -512,7 +516,9 @@ struct ceph_mds_client {
 	spinlock_t	caps_list_lock;
 	struct		list_head caps_list; /* unused (reserved or
 						unreserved) */
+#ifdef CONFIG_DEBUG_FS
 	struct		list_head cap_wait_list;
+#endif
 	int		caps_total_count;    /* total caps allocated */
 	int		caps_use_count;      /* in use */
 	int		caps_use_max;	     /* max used caps */

fs/ceph/super.c

@@ -961,7 +961,8 @@ static int __init init_caches(void)
 	if (!ceph_mds_request_cachep)
 		goto bad_mds_req;
 
-	ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT);
+	ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10,
+	    (CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT) * sizeof(struct page *));
 	if (!ceph_wb_pagevec_pool)
 		goto bad_pagevec_pool;