Merge tag 'ceph-for-5.6-rc1' of https://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:

 - a set of patches that fixes various corner cases in mount and umount
   code (Xiubo Li). This has to do with choosing an MDS, distinguishing
   between laggy and down MDSes and parsing the server path.

 - inode initialization fixes (Jeff Layton). The one included here
   mostly concerns things like open_by_handle() and there is another one
   that will come through Al.

 - copy_file_range() now uses the new copy-from2 op (Luis Henriques).
   The existing copy-from op turned out to be infeasible for generic
   filesystem use; we disable the copy offload if OSDs don't support
   copy-from2.

 - a patch to link "rbd" and "block" devices together in sysfs (Hannes
   Reinecke)

... and a smattering of cleanups from Xiubo, Jeff and Chengguang.

* tag 'ceph-for-5.6-rc1' of https://github.com/ceph/ceph-client: (25 commits)
  rbd: set the 'device' link in sysfs
  ceph: move net/ceph/ceph_fs.c to fs/ceph/util.c
  ceph: print name of xattr in __ceph_{get,set}xattr() douts
  ceph: print r_direct_hash in hex in __choose_mds() dout
  ceph: use copy-from2 op in copy_file_range
  ceph: close holes in structs ceph_mds_session and ceph_mds_request
  rbd: work around -Wuninitialized warning
  ceph: allocate the correct amount of extra bytes for the session features
  ceph: rename get_session and switch to use ceph_get_mds_session
  ceph: remove the extra slashes in the server path
  ceph: add possible_max_rank and make the code more readable
  ceph: print dentry offset in hex and fix xattr_version type
  ceph: only touch the caps which have the subset mask requested
  ceph: don't clear I_NEW until inode metadata is fully populated
  ceph: retry the same mds later after the new session is opened
  ceph: check availability of mds cluster on mount after wait timeout
  ceph: keep the session state until it is released
  ceph: add __send_request helper
  ceph: ensure we have a new cap before continuing in fill_inode
  ceph: drop unused ttl_from parameter from fill_inode
  ...

drivers/block/rbd.c

@@ -2662,7 +2662,7 @@ static int rbd_img_fill_nodata(struct rbd_img_request *img_req,
 			       u64 off, u64 len)
 {
 	struct ceph_file_extent ex = { off, len };
-	union rbd_img_fill_iter dummy;
+	union rbd_img_fill_iter dummy = {};
 	struct rbd_img_fill_ctx fctx = {
 		.pos_type = OBJ_REQUEST_NODATA,
 		.pos = &dummy,
@@ -7143,7 +7143,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	if (rc)
 		goto err_out_image_lock;
 
-	add_disk(rbd_dev->disk);
+	device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL);
 	/* see rbd_init_disk() */
 	blk_put_queue(rbd_dev->disk->queue);
 

fs/ceph/Makefile

@@ -8,7 +8,7 @@ obj-$(CONFIG_CEPH_FS) += ceph.o
 ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
 	export.o caps.o snap.o xattr.o quota.o io.o \
 	mds_client.o mdsmap.o strings.o ceph_frag.o \
-	debugfs.o
+	debugfs.o util.o
 
 ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
 ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o

fs/ceph/acl.c

@@ -222,8 +222,8 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
 		err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
 		if (err)
 			goto out_err;
-		err = ceph_pagelist_encode_string(pagelist,
-						  XATTR_NAME_POSIX_ACL_DEFAULT, len);
+		ceph_pagelist_encode_string(pagelist,
+					  XATTR_NAME_POSIX_ACL_DEFAULT, len);
 		err = posix_acl_to_xattr(&init_user_ns, default_acl,
 					 tmp_buf, val_size2);
 		if (err < 0)

fs/ceph/caps.c

@@ -908,7 +908,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 						       ci_node);
 					if (!__cap_is_valid(cap))
 						continue;
-					__touch_cap(cap);
+					if (cap->issued & mask)
+						__touch_cap(cap);
 				}
 			}
 			return 1;

fs/ceph/debugfs.c

@@ -33,7 +33,7 @@ static int mdsmap_show(struct seq_file *s, void *p)
 	seq_printf(s, "max_mds %d\n", mdsmap->m_max_mds);
 	seq_printf(s, "session_timeout %d\n", mdsmap->m_session_timeout);
 	seq_printf(s, "session_autoclose %d\n", mdsmap->m_session_autoclose);
-	for (i = 0; i < mdsmap->m_num_mds; i++) {
+	for (i = 0; i < mdsmap->possible_max_rank; i++) {
 		struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr;
 		int state = mdsmap->m_info[i].state;
 		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,

fs/ceph/dir.c

@@ -1186,7 +1186,7 @@ void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di)
 	struct dentry *dn = di->dentry;
 	struct ceph_mds_client *mdsc;
 
-	dout("dentry_dir_lease_touch %p %p '%pd' (offset %lld)\n",
+	dout("dentry_dir_lease_touch %p %p '%pd' (offset 0x%llx)\n",
 	     di, dn, dn, di->offset);
 
 	if (!list_empty(&di->lease_list)) {
@@ -1567,7 +1567,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		inode = d_inode(dentry);
 	}
 
-	dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
+	dout("d_revalidate %p '%pd' inode %p offset 0x%llx\n", dentry,
 	     dentry, inode, ceph_dentry(dentry)->offset);
 
 	/* always trust cached snapped dentries, snapdir dentry */

fs/ceph/file.c

@@ -1974,6 +1974,9 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	if (ceph_test_mount_opt(src_fsc, NOCOPYFROM))
 		return -EOPNOTSUPP;
 
+	if (!src_fsc->have_copy_from2)
+		return -EOPNOTSUPP;
+
 	/*
 	 * Striped file layouts require that we copy partial objects, but the
 	 * OSD copy-from operation only supports full-object copies.  Limit
@@ -2101,8 +2104,14 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 			CEPH_OSD_OP_FLAG_FADVISE_NOCACHE,
 			&dst_oid, &dst_oloc,
 			CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
-			CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, 0);
+			CEPH_OSD_OP_FLAG_FADVISE_DONTNEED,
+			dst_ci->i_truncate_seq, dst_ci->i_truncate_size,
+			CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ);
 		if (err) {
+			if (err == -EOPNOTSUPP) {
+				src_fsc->have_copy_from2 = false;
+				pr_notice("OSDs don't support copy-from2; disabling copy offload\n");
+			}
 			dout("ceph_osdc_copy_from returned %d\n", err);
 			if (!ret)
 				ret = err;

fs/ceph/inode.c

@@ -55,11 +55,9 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
 	inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
-	if (inode->i_state & I_NEW) {
+	if (inode->i_state & I_NEW)
 		dout("get_inode created new inode %p %llx.%llx ino %llx\n",
 		     inode, ceph_vinop(inode), (u64)inode->i_ino);
-		unlock_new_inode(inode);
-	}
 
 	dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino,
 	     vino.snap, inode);
@@ -88,6 +86,10 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 	inode->i_fop = &ceph_snapdir_fops;
 	ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
 	ci->i_rbytes = 0;
+
+	if (inode->i_state & I_NEW)
+		unlock_new_inode(inode);
+
 	return inode;
 }
 
@@ -728,8 +730,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 static int fill_inode(struct inode *inode, struct page *locked_page,
 		      struct ceph_mds_reply_info_in *iinfo,
 		      struct ceph_mds_reply_dirfrag *dirinfo,
-		      struct ceph_mds_session *session,
-		      unsigned long ttl_from, int cap_fmode,
+		      struct ceph_mds_session *session, int cap_fmode,
 		      struct ceph_cap_reservation *caps_reservation)
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
@@ -754,8 +755,11 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	info_caps = le32_to_cpu(info->cap.caps);
 
 	/* prealloc new cap struct */
-	if (info_caps && ceph_snap(inode) == CEPH_NOSNAP)
+	if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) {
 		new_cap = ceph_get_cap(mdsc, caps_reservation);
+		if (!new_cap)
+			return -ENOMEM;
+	}
 
 	/*
 	 * prealloc xattr data, if it looks like we'll need it.  only
@@ -1237,7 +1241,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 		if (dir) {
 			err = fill_inode(dir, NULL,
 					 &rinfo->diri, rinfo->dirfrag,
-					 session, req->r_request_started, -1,
+					 session, -1,
 					 &req->r_caps_reservation);
 			if (err < 0)
 				goto done;
@@ -1302,18 +1306,22 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			err = PTR_ERR(in);
 			goto done;
 		}
-		req->r_target_inode = in;
 
 		err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
-				session, req->r_request_started,
+				session,
 				(!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
-				rinfo->head->result == 0) ?  req->r_fmode : -1,
+				 rinfo->head->result == 0) ?  req->r_fmode : -1,
 				&req->r_caps_reservation);
 		if (err < 0) {
 			pr_err("fill_inode badness %p %llx.%llx\n",
 				in, ceph_vinop(in));
+			if (in->i_state & I_NEW)
+				discard_new_inode(in);
 			goto done;
 		}
+		req->r_target_inode = in;
+		if (in->i_state & I_NEW)
+			unlock_new_inode(in);
 	}
 
 	/*
@@ -1493,12 +1501,18 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
 			continue;
 		}
 		rc = fill_inode(in, NULL, &rde->inode, NULL, session,
-				req->r_request_started, -1,
-				&req->r_caps_reservation);
+				-1, &req->r_caps_reservation);
 		if (rc < 0) {
 			pr_err("fill_inode badness on %p got %d\n", in, rc);
 			err = rc;
+			if (in->i_state & I_NEW) {
+				ihold(in);
+				discard_new_inode(in);
+			}
+		} else if (in->i_state & I_NEW) {
+			unlock_new_inode(in);
 		}
+
 		/* avoid calling iput_final() in mds dispatch threads */
 		ceph_async_iput(in);
 	}
@@ -1694,19 +1708,24 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 		}
 
 		ret = fill_inode(in, NULL, &rde->inode, NULL, session,
-				 req->r_request_started, -1,
-				 &req->r_caps_reservation);
+				 -1, &req->r_caps_reservation);
 		if (ret < 0) {
 			pr_err("fill_inode badness on %p\n", in);
 			if (d_really_is_negative(dn)) {
 				/* avoid calling iput_final() in mds
 				 * dispatch threads */
+				if (in->i_state & I_NEW) {
+					ihold(in);
+					discard_new_inode(in);
+				}
 				ceph_async_iput(in);
 			}
 			d_drop(dn);
 			err = ret;
 			goto next_item;
 		}
+		if (in->i_state & I_NEW)
+			unlock_new_inode(in);
 
 		if (d_really_is_negative(dn)) {
 			if (ceph_security_xattr_deadlock(in)) {