Merge tag 'ceph-for-4.15-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "We have a set of file locking improvements from Zheng, rbd rw/ro state
  handling code cleanup from myself and some assorted CephFS fixes from
  Jeff.

  rbd now defaults to single-major=Y, lifting the limit of ~240 rbd
  images per host for everyone"

* tag 'ceph-for-4.15-rc1' of git://github.com/ceph/ceph-client:
  rbd: default to single-major device number scheme
  libceph: don't WARN() if user tries to add invalid key
  rbd: set discard_alignment to zero
  ceph: silence sparse endianness warning in encode_caps_cb
  ceph: remove the bump of i_version
  ceph: present consistent fsid, regardless of arch endianness
  ceph: clean up spinlocking and list handling around cleanup_cap_releases()
  rbd: get rid of rbd_mapping::read_only
  rbd: fix and simplify rbd_ioctl_set_ro()
  ceph: remove unused and redundant variable dropping
  ceph: mark expected switch fall-throughs
  ceph: -EINVAL on decoding failure in ceph_mdsc_handle_fsmap()
  ceph: disable cached readdir after dropping positive dentry
  ceph: fix bool initialization/comparison
  ceph: handle 'session get evicted while there are file locks'
  ceph: optimize flock encoding during reconnect
  ceph: make lock_to_ceph_filelock() static
  ceph: keep auth cap when inode has flocks or posix locks

drivers/block/rbd.c

@@ -348,7 +348,6 @@ struct rbd_client_id {
 struct rbd_mapping {
 	u64                     size;
 	u64                     features;
-	bool			read_only;
 };
 
 /*
@@ -450,12 +449,11 @@ static DEFINE_IDA(rbd_dev_id_ida);
 static struct workqueue_struct *rbd_wq;
 
 /*
- * Default to false for now, as single-major requires >= 0.75 version of
- * userspace rbd utility.
+ * single-major requires >= 0.75 version of userspace rbd utility.
  */
-static bool single_major = false;
+static bool single_major = true;
 module_param(single_major, bool, S_IRUGO);
-MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (default: false)");
+MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (default: true)");
 
 static int rbd_img_request_submit(struct rbd_img_request *img_request);
 
@@ -608,9 +606,6 @@ static int rbd_open(struct block_device *bdev, fmode_t mode)
 	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
 	bool removing = false;
 
-	if ((mode & FMODE_WRITE) && rbd_dev->mapping.read_only)
-		return -EROFS;
-
 	spin_lock_irq(&rbd_dev->lock);
 	if (test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags))
 		removing = true;
@@ -640,46 +635,24 @@ static void rbd_release(struct gendisk *disk, fmode_t mode)
 
 static int rbd_ioctl_set_ro(struct rbd_device *rbd_dev, unsigned long arg)
 {
-	int ret = 0;
-	int val;
-	bool ro;
-	bool ro_changed = false;
+	int ro;
 
-	/* get_user() may sleep, so call it before taking rbd_dev->lock */
-	if (get_user(val, (int __user *)(arg)))
+	if (get_user(ro, (int __user *)arg))
 		return -EFAULT;
 
-	ro = val ? true : false;
-	/* Snapshot doesn't allow to write*/
+	/* Snapshots can't be marked read-write */
 	if (rbd_dev->spec->snap_id != CEPH_NOSNAP && !ro)
 		return -EROFS;
 
-	spin_lock_irq(&rbd_dev->lock);
-	/* prevent others open this device */
-	if (rbd_dev->open_count > 1) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	if (rbd_dev->mapping.read_only != ro) {
-		rbd_dev->mapping.read_only = ro;
-		ro_changed = true;
-	}
-
-out:
-	spin_unlock_irq(&rbd_dev->lock);
-	/* set_disk_ro() may sleep, so call it after releasing rbd_dev->lock */
-	if (ret == 0 && ro_changed)
-		set_disk_ro(rbd_dev->disk, ro ? 1 : 0);
-
-	return ret;
+	/* Let blkdev_roset() handle it */
+	return -ENOTTY;
 }
 
 static int rbd_ioctl(struct block_device *bdev, fmode_t mode,
 			unsigned int cmd, unsigned long arg)
 {
 	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
-	int ret = 0;
+	int ret;
 
 	switch (cmd) {
 	case BLKROSET:
@@ -4050,15 +4023,8 @@ static void rbd_queue_workfn(struct work_struct *work)
 		goto err_rq;
 	}
 
-	/* Only reads are allowed to a read-only device */
-
-	if (op_type != OBJ_OP_READ) {
-		if (rbd_dev->mapping.read_only) {
-			result = -EROFS;
-			goto err_rq;
-		}
-		rbd_assert(rbd_dev->spec->snap_id == CEPH_NOSNAP);
-	}
+	rbd_assert(op_type == OBJ_OP_READ ||
+		   rbd_dev->spec->snap_id == CEPH_NOSNAP);
 
 	/*
 	 * Quit early if the mapped snapshot no longer exists.  It's
@@ -4423,7 +4389,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	/* enable the discard support */
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	q->limits.discard_granularity = segment_size;
-	q->limits.discard_alignment = segment_size;
 	blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
 	blk_queue_max_write_zeroes_sectors(q, segment_size / SECTOR_SIZE);
 
@@ -5994,7 +5959,7 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 		goto err_out_disk;
 
 	set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
-	set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only);
+	set_disk_ro(rbd_dev->disk, rbd_dev->opts->read_only);
 
 	ret = dev_set_name(&rbd_dev->dev, "%d", rbd_dev->dev_id);
 	if (ret)
@@ -6145,7 +6110,6 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	struct rbd_options *rbd_opts = NULL;
 	struct rbd_spec *spec = NULL;
 	struct rbd_client *rbdc;
-	bool read_only;
 	int rc;
 
 	if (!try_module_get(THIS_MODULE))
@@ -6194,11 +6158,8 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	}
 
 	/* If we are mapping a snapshot it must be marked read-only */
-
-	read_only = rbd_dev->opts->read_only;
 	if (rbd_dev->spec->snap_id != CEPH_NOSNAP)
-		read_only = true;
-	rbd_dev->mapping.read_only = read_only;
+		rbd_dev->opts->read_only = true;
 
 	rc = rbd_dev_device_setup(rbd_dev);
 	if (rc)

fs/ceph/caps.c

@@ -1160,15 +1160,14 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	struct ceph_inode_info *ci = cap->ci;
 	struct inode *inode = &ci->vfs_inode;
 	struct cap_msg_args arg;
-	int held, revoking, dropping;
+	int held, revoking;
 	int wake = 0;
 	int delayed = 0;
 	int ret;
 
 	held = cap->issued | cap->implemented;
 	revoking = cap->implemented & ~cap->issued;
 	retain &= ~revoking;
-	dropping = cap->issued & ~retain;
 
 	dout("__send_cap %p cap %p session %p %s -> %s (revoking %s)\n",
 	     inode, cap, cap->session,
@@ -1712,7 +1711,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 
 	/* if we are unmounting, flush any unused caps immediately. */
 	if (mdsc->stopping)
-		is_delayed = 1;
+		is_delayed = true;
 
 	spin_lock(&ci->i_ceph_lock);
 
@@ -3189,8 +3188,8 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 	int dirty = le32_to_cpu(m->dirty);
 	int cleaned = 0;
 	bool drop = false;
-	bool wake_ci = 0;
-	bool wake_mdsc = 0;
+	bool wake_ci = false;
+	bool wake_mdsc = false;
 
 	list_for_each_entry_safe(cf, tmp_cf, &ci->i_cap_flush_list, i_list) {
 		if (cf->tid == flush_tid)

fs/ceph/inode.c

@@ -493,6 +493,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_wb_ref = 0;
 	ci->i_wrbuffer_ref = 0;
 	ci->i_wrbuffer_ref_head = 0;
+	atomic_set(&ci->i_filelock_ref, 0);
 	ci->i_shared_gen = 0;
 	ci->i_rdcache_gen = 0;
 	ci->i_rdcache_revoking = 0;
@@ -786,7 +787,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 
 	/* update inode */
 	ci->i_version = le64_to_cpu(info->version);
-	inode->i_version++;
 	inode->i_rdev = le32_to_cpu(info->rdev);
 	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
 
@@ -1185,6 +1185,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 				    ceph_snap(d_inode(dn)) != tvino.snap)) {
 				dout(" dn %p points to wrong inode %p\n",
 				     dn, d_inode(dn));
+				ceph_dir_clear_ordered(dir);
 				d_delete(dn);
 				dput(dn);
 				goto retry_lookup;
@@ -1322,6 +1323,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
 			     dn, d_inode(dn), ceph_vinop(d_inode(dn)),
 			     ceph_vinop(in));
+			ceph_dir_clear_ordered(dir);
 			d_invalidate(dn);
 			have_lease = false;
 		}
@@ -1573,6 +1575,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 			    ceph_snap(d_inode(dn)) != tvino.snap)) {
 			dout(" dn %p points to wrong inode %p\n",
 			     dn, d_inode(dn));
+			__ceph_dir_clear_ordered(ci);
 			d_delete(dn);
 			dput(dn);
 			goto retry_lookup;
@@ -1597,7 +1600,9 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 				 &req->r_caps_reservation);
 		if (ret < 0) {
 			pr_err("fill_inode badness on %p\n", in);
-			if (d_really_is_negative(dn))
+			if (d_really_is_positive(dn))
+				__ceph_dir_clear_ordered(ci);
+			else
 				iput(in);
 			d_drop(dn);
 			err = ret;