Merge tag 'ceph-for-5.20-rc1' of https://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "We have a good pile of various fixes and cleanups from Xiubo, Jeff,
  Luis and others, almost exclusively in the filesystem.

  Several patches touch files outside of our normal purview to set the
  stage for bringing in Jeff's long awaited ceph+fscrypt series in the
  near future. All of them have appropriate acks and sat in linux-next
  for a while"

* tag 'ceph-for-5.20-rc1' of https://github.com/ceph/ceph-client: (27 commits)
  libceph: clean up ceph_osdc_start_request prototype
  libceph: fix ceph_pagelist_reserve() comment typo
  ceph: remove useless check for the folio
  ceph: don't truncate file in atomic_open
  ceph: make f_bsize always equal to f_frsize
  ceph: flush the dirty caps immediatelly when quota is approaching
  libceph: print fsid and epoch with osd id
  libceph: check pointer before assigned to "c->rules[]"
  ceph: don't get the inline data for new creating files
  ceph: update the auth cap when the async create req is forwarded
  ceph: make change_auth_cap_ses a global symbol
  ceph: fix incorrect old_size length in ceph_mds_request_args
  ceph: switch back to testing for NULL folio->private in ceph_dirty_folio
  ceph: call netfs_subreq_terminated with was_async == false
  ceph: convert to generic_file_llseek
  ceph: fix the incorrect comment for the ceph_mds_caps struct
  ceph: don't leak snap_rwsem in handle_cap_grant
  ceph: prevent a client from exceeding the MDS maximum xattr size
  ceph: choose auth MDS for getxattr with the Xs caps
  ceph: add session already open notify support
  ...

Author: torvalds

drivers/block/rbd.c

@@ -1297,7 +1297,7 @@ static void rbd_osd_submit(struct ceph_osd_request *osd_req)
 	dout("%s osd_req %p for obj_req %p objno %llu %llu~%llu\n",
 	     __func__, osd_req, obj_req, obj_req->ex.oe_objno,
 	     obj_req->ex.oe_off, obj_req->ex.oe_len);
-	ceph_osdc_start_request(osd_req->r_osdc, osd_req, false);
+	ceph_osdc_start_request(osd_req->r_osdc, osd_req);
 }
 
 /*
@@ -2081,7 +2081,7 @@ static int rbd_object_map_update(struct rbd_obj_request *obj_req, u64 snap_id,
 	if (ret)
 		return ret;
 
-	ceph_osdc_start_request(osdc, req, false);
+	ceph_osdc_start_request(osdc, req);
 	return 0;
 }
 
@@ -4768,7 +4768,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
 	if (ret)
 		goto out_req;
 
-	ceph_osdc_start_request(osdc, req, false);
+	ceph_osdc_start_request(osdc, req);
 	ret = ceph_osdc_wait_request(osdc, req);
 	if (ret >= 0)
 		ceph_copy_from_page_vector(pages, buf, 0, ret);

fs/ceph/addr.c

@@ -122,7 +122,7 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 	 * Reference snap context in folio->private.  Also set
 	 * PagePrivate so that we get invalidate_folio callback.
 	 */
-	VM_BUG_ON_FOLIO(folio_test_private(folio), folio);
+	VM_WARN_ON_FOLIO(folio->private, folio);
 	folio_attach_private(folio, snapc);
 
 	return ceph_fscache_dirty_folio(mapping, folio);
@@ -237,7 +237,7 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	if (err >= 0 && err < subreq->len)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 
-	netfs_subreq_terminated(subreq, err, true);
+	netfs_subreq_terminated(subreq, err, false);
 
 	num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
 	ceph_put_page_vector(osd_data->pages, num_pages, false);
@@ -313,8 +313,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	int err = 0;
 	u64 len = subreq->len;
 
-	if (ci->i_inline_version != CEPH_INLINE_NONE &&
-	    ceph_netfs_issue_op_inline(subreq))
+	if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq))
 		return;
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
@@ -338,16 +337,15 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	/* should always give us a page-aligned read */
 	WARN_ON_ONCE(page_off);
 	len = err;
+	err = 0;
 
 	osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
 	req->r_callback = finish_netfs_read;
 	req->r_priv = subreq;
 	req->r_inode = inode;
 	ihold(inode);
 
-	err = ceph_osdc_start_request(req->r_osdc, req, false);
-	if (err)
-		iput(inode);
+	ceph_osdc_start_request(req->r_osdc, req);
 out:
 	ceph_osdc_put_request(req);
 	if (err)
@@ -621,9 +619,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len);
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(osdc, req, true);
-	if (!err)
-		err = ceph_osdc_wait_request(osdc, req);
+	ceph_osdc_start_request(osdc, req);
+	err = ceph_osdc_wait_request(osdc, req);
 
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
@@ -1151,8 +1148,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 		}
 
 		req->r_mtime = inode->i_mtime;
-		rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
-		BUG_ON(rc);
+		ceph_osdc_start_request(&fsc->client->osdc, req);
 		req = NULL;
 
 		wbc->nr_to_write -= i;
@@ -1327,16 +1323,13 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 	int r;
 
 	r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
-	if (r == 0)
-		folio_wait_fscache(folio);
-	if (r < 0) {
-		if (folio)
-			folio_put(folio);
-	} else {
-		WARN_ON_ONCE(!folio_test_locked(folio));
-		*pagep = &folio->page;
-	}
-	return r;
+	if (r < 0)
+		return r;
+
+	folio_wait_fscache(folio);
+	WARN_ON_ONCE(!folio_test_locked(folio));
+	*pagep = &folio->page;
+	return 0;
 }
 
 /*
@@ -1439,7 +1432,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 	     inode, off, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
-	    ci->i_inline_version == CEPH_INLINE_NONE) {
+	    !ceph_has_inline_data(ci)) {
 		CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
 		ceph_add_rw_context(fi, &rw_ctx);
 		ret = filemap_fault(vmf);
@@ -1696,9 +1689,8 @@ int ceph_uninline_data(struct file *file)
 	}
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+	ceph_osdc_start_request(&fsc->client->osdc, req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, req);
 	ceph_osdc_put_request(req);
 	if (err < 0)
 		goto out_unlock;
@@ -1739,9 +1731,8 @@ int ceph_uninline_data(struct file *file)
 	}
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+	ceph_osdc_start_request(&fsc->client->osdc, req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
@@ -1912,15 +1903,13 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 
 	osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE,
 				     0, false, true);
-	err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
+	ceph_osdc_start_request(&fsc->client->osdc, rd_req);
 
 	wr_req->r_mtime = ci->netfs.inode.i_mtime;
-	err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
+	ceph_osdc_start_request(&fsc->client->osdc, wr_req);
 
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
-	if (!err2)
-		err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
+	err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
 
 	if (err >= 0 || err == -ENOENT)
 		have |= POOL_READ;

fs/ceph/caps.c

@@ -602,8 +602,8 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
  * @ci: inode to be moved
  * @session: new auth caps session
  */
-static void change_auth_cap_ses(struct ceph_inode_info *ci,
-				struct ceph_mds_session *session)
+void change_auth_cap_ses(struct ceph_inode_info *ci,
+			 struct ceph_mds_session *session)
 {
 	lockdep_assert_held(&ci->i_ceph_lock);
 
@@ -1978,14 +1978,15 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 	}
 
 	dout("check_caps %llx.%llx file_want %s used %s dirty %s flushing %s"
-	     " issued %s revoking %s retain %s %s%s\n", ceph_vinop(inode),
+	     " issued %s revoking %s retain %s %s%s%s\n", ceph_vinop(inode),
 	     ceph_cap_string(file_wanted),
 	     ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
 	     ceph_cap_string(ci->i_flushing_caps),
 	     ceph_cap_string(issued), ceph_cap_string(revoking),
 	     ceph_cap_string(retain),
 	     (flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "",
-	     (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "");
+	     (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "",
+	     (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "");
 
 	/*
 	 * If we no longer need to hold onto old our caps, and we may
@@ -3005,7 +3006,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 		}
 
 		if (S_ISREG(ci->netfs.inode.i_mode) &&
-		    ci->i_inline_version != CEPH_INLINE_NONE &&
+		    ceph_has_inline_data(ci) &&
 		    (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
 		    i_size_read(inode) > 0) {
 			struct page *page =
@@ -3578,24 +3579,23 @@ static void handle_cap_grant(struct inode *inode,
 			fill_inline = true;
 	}
 
-	if (ci->i_auth_cap == cap &&
-	    le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
-		if (newcaps & ~extra_info->issued)
-			wake = true;
+	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
+		if (ci->i_auth_cap == cap) {
+			if (newcaps & ~extra_info->issued)
+				wake = true;
 
-		if (ci->i_requested_max_size > max_size ||
-		    !(le32_to_cpu(grant->wanted) & CEPH_CAP_ANY_FILE_WR)) {
-			/* re-request max_size if necessary */
-			ci->i_requested_max_size = 0;
-			wake = true;
-		}
+			if (ci->i_requested_max_size > max_size ||
+			    !(le32_to_cpu(grant->wanted) & CEPH_CAP_ANY_FILE_WR)) {
+				/* re-request max_size if necessary */
+				ci->i_requested_max_size = 0;
+				wake = true;
+			}
 
-		ceph_kick_flushing_inode_caps(session, ci);
-		spin_unlock(&ci->i_ceph_lock);
+			ceph_kick_flushing_inode_caps(session, ci);
+		}
 		up_read(&session->s_mdsc->snap_rwsem);
-	} else {
-		spin_unlock(&ci->i_ceph_lock);
 	}
+	spin_unlock(&ci->i_ceph_lock);
 
 	if (fill_inline)
 		ceph_fill_inline_data(inode, NULL, extra_info->inline_data,