Merge tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The two main items are support for disabling automatic rbd exclusive
  lock transfers from myself and the long awaited -ENOSPC handling
  series from Jeff.

  The former will allow rbd users to take advantage of exclusive lock's
  built-in blacklist/break-lock functionality while staying in control
  of who owns the lock. With the latter in place, we will abort
  filesystem writes on -ENOSPC instead of having them block
  indefinitely.

  Beyond that we've got the usual pile of filesystem fixes from Zheng,
  some refcount_t conversion patches from Elena and a patch for an
  ancient open() flags handling bug from Alexander"

* tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client: (31 commits)
  ceph: fix memory leak in __ceph_setxattr()
  ceph: fix file open flags on ppc64
  ceph: choose readdir frag based on previous readdir reply
  rbd: exclusive map option
  rbd: return ResponseMessage result from rbd_handle_request_lock()
  rbd: kill rbd_is_lock_supported()
  rbd: support updating the lock cookie without releasing the lock
  rbd: store lock cookie
  rbd: ignore unlock errors
  rbd: fix error handling around rbd_init_disk()
  rbd: move rbd_unregister_watch() call into rbd_dev_image_release()
  rbd: move rbd_dev_destroy() call out of rbd_dev_image_release()
  ceph: when seeing write errors on an inode, switch to sync writes
  Revert "ceph: SetPageError() for writeback pages if writepages fails"
  ceph: handle epoch barriers in cap messages
  libceph: add an epoch_barrier field to struct ceph_osd_client
  libceph: abort already submitted but abortable requests when map or pool goes full
  libceph: allow requests to return immediately on full conditions if caller wishes
  libceph: remove req->r_replay_version
  ceph: make seeky readdir more efficient
  ...

fs/ceph/addr.c

@@ -670,8 +670,12 @@ static void writepages_finish(struct ceph_osd_request *req)
 	bool remove_page;
 
 	dout("writepages_finish %p rc %d\n", inode, rc);
-	if (rc < 0)
+	if (rc < 0) {
 		mapping_set_error(mapping, rc);
+		ceph_set_error_write(ci);
+	} else {
+		ceph_clear_error_write(ci);
+	}
 
 	/*
 	 * We lost the cache cap, need to truncate the page before
@@ -703,9 +707,6 @@ static void writepages_finish(struct ceph_osd_request *req)
 				clear_bdi_congested(inode_to_bdi(inode),
 						    BLK_RW_ASYNC);
 
-			if (rc < 0)
-				SetPageError(page);
-
 			ceph_put_snap_context(page_snap_context(page));
 			page->private = 0;
 			ClearPagePrivate(page);
@@ -1892,6 +1893,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 	err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
 
 	wr_req->r_mtime = ci->vfs_inode.i_mtime;
+	wr_req->r_abort_on_full = true;
 	err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
 
 	if (!err)

fs/ceph/caps.c

@@ -1015,6 +1015,7 @@ static int send_cap_msg(struct cap_msg_args *arg)
 	void *p;
 	size_t extra_len;
 	struct timespec zerotime = {0};
+	struct ceph_osd_client *osdc = &arg->session->s_mdsc->fsc->client->osdc;
 
 	dout("send_cap_msg %s %llx %llx caps %s wanted %s dirty %s"
 	     " seq %u/%u tid %llu/%llu mseq %u follows %lld size %llu/%llu"
@@ -1076,8 +1077,12 @@ static int send_cap_msg(struct cap_msg_args *arg)
 	ceph_encode_64(&p, arg->inline_data ? 0 : CEPH_INLINE_NONE);
 	/* inline data size */
 	ceph_encode_32(&p, 0);
-	/* osd_epoch_barrier (version 5) */
-	ceph_encode_32(&p, 0);
+	/*
+	 * osd_epoch_barrier (version 5)
+	 * The epoch_barrier is protected osdc->lock, so READ_ONCE here in
+	 * case it was recently changed
+	 */
+	ceph_encode_32(&p, READ_ONCE(osdc->epoch_barrier));
 	/* oldest_flush_tid (version 6) */
 	ceph_encode_64(&p, arg->oldest_flush_tid);
 
@@ -1389,7 +1394,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 		first_tid = cf->tid + 1;
 
 		capsnap = container_of(cf, struct ceph_cap_snap, cap_flush);
-		atomic_inc(&capsnap->nref);
+		refcount_inc(&capsnap->nref);
 		spin_unlock(&ci->i_ceph_lock);
 
 		dout("__flush_snaps %p capsnap %p tid %llu %s\n",
@@ -2202,7 +2207,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 			     inode, capsnap, cf->tid,
 			     ceph_cap_string(capsnap->dirty));
 
-			atomic_inc(&capsnap->nref);
+			refcount_inc(&capsnap->nref);
 			spin_unlock(&ci->i_ceph_lock);
 
 			ret = __send_flush_snap(inode, session, capsnap, cap->mseq,
@@ -3633,13 +3638,19 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		p += inline_len;
 	}
 
+	if (le16_to_cpu(msg->hdr.version) >= 5) {
+		struct ceph_osd_client	*osdc = &mdsc->fsc->client->osdc;
+		u32			epoch_barrier;
+
+		ceph_decode_32_safe(&p, end, epoch_barrier, bad);
+		ceph_osdc_update_epoch_barrier(osdc, epoch_barrier);
+	}
+
 	if (le16_to_cpu(msg->hdr.version) >= 8) {
 		u64 flush_tid;
 		u32 caller_uid, caller_gid;
-		u32 osd_epoch_barrier;
 		u32 pool_ns_len;
-		/* version >= 5 */
-		ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad);
+
 		/* version >= 6 */
 		ceph_decode_64_safe(&p, end, flush_tid, bad);
 		/* version >= 7 */

fs/ceph/debugfs.c

@@ -22,20 +22,19 @@ static int mdsmap_show(struct seq_file *s, void *p)
 {
 	int i;
 	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mdsmap *mdsmap;
 
 	if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL)
 		return 0;
-	seq_printf(s, "epoch %d\n", fsc->mdsc->mdsmap->m_epoch);
-	seq_printf(s, "root %d\n", fsc->mdsc->mdsmap->m_root);
-	seq_printf(s, "session_timeout %d\n",
-		       fsc->mdsc->mdsmap->m_session_timeout);
-	seq_printf(s, "session_autoclose %d\n",
-		       fsc->mdsc->mdsmap->m_session_autoclose);
-	for (i = 0; i < fsc->mdsc->mdsmap->m_max_mds; i++) {
-		struct ceph_entity_addr *addr =
-			&fsc->mdsc->mdsmap->m_info[i].addr;
-		int state = fsc->mdsc->mdsmap->m_info[i].state;
-
+	mdsmap = fsc->mdsc->mdsmap;
+	seq_printf(s, "epoch %d\n", mdsmap->m_epoch);
+	seq_printf(s, "root %d\n", mdsmap->m_root);
+	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++) {
+		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,
 			       ceph_pr_addr(&addr->in_addr),
 			       ceph_mds_state_name(state));

fs/ceph/dir.c

@@ -294,7 +294,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	int i;
 	int err;
-	u32 ftype;
+	unsigned frag = -1;
 	struct ceph_mds_reply_info_parsed *rinfo;
 
 	dout("readdir %p file %p pos %llx\n", inode, file, ctx->pos);
@@ -341,7 +341,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	/* do we have the correct frag content buffered? */
 	if (need_send_readdir(fi, ctx->pos)) {
 		struct ceph_mds_request *req;
-		unsigned frag;
 		int op = ceph_snap(inode) == CEPH_SNAPDIR ?
 			CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;
 
@@ -352,8 +351,11 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		}
 
 		if (is_hash_order(ctx->pos)) {
-			frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
-						NULL, NULL);
+			/* fragtree isn't always accurate. choose frag
+			 * based on previous reply when possible. */
+			if (frag == (unsigned)-1)
+				frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
+							NULL, NULL);
 		} else {
 			frag = fpos_frag(ctx->pos);
 		}
@@ -378,7 +380,11 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 				ceph_mdsc_put_request(req);
 				return -ENOMEM;
 			}
+		} else if (is_hash_order(ctx->pos)) {
+			req->r_args.readdir.offset_hash =
+				cpu_to_le32(fpos_hash(ctx->pos));
 		}
+
 		req->r_dir_release_cnt = fi->dir_release_count;
 		req->r_dir_ordered_cnt = fi->dir_ordered_count;
 		req->r_readdir_cache_idx = fi->readdir_cache_idx;
@@ -476,6 +482,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
 		struct ceph_vino vino;
 		ino_t ino;
+		u32 ftype;
 
 		BUG_ON(rde->offset < ctx->pos);
 
@@ -498,15 +505,17 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		ctx->pos++;
 	}
 
+	ceph_mdsc_put_request(fi->last_readdir);
+	fi->last_readdir = NULL;
+
 	if (fi->next_offset > 2) {
-		ceph_mdsc_put_request(fi->last_readdir);
-		fi->last_readdir = NULL;
+		frag = fi->frag;
 		goto more;
 	}
 
 	/* more frags? */
 	if (!ceph_frag_is_rightmost(fi->frag)) {
-		unsigned frag = ceph_frag_next(fi->frag);
+		frag = ceph_frag_next(fi->frag);
 		if (is_hash_order(ctx->pos)) {
 			loff_t new_pos = ceph_make_fpos(ceph_frag_value(frag),
 							fi->next_offset, true);

fs/ceph/file.c

@@ -13,6 +13,38 @@
 #include "mds_client.h"
 #include "cache.h"
 
+static __le32 ceph_flags_sys2wire(u32 flags)
+{
+	u32 wire_flags = 0;
+
+	switch (flags & O_ACCMODE) {
+	case O_RDONLY:
+		wire_flags |= CEPH_O_RDONLY;
+		break;
+	case O_WRONLY:
+		wire_flags |= CEPH_O_WRONLY;
+		break;
+	case O_RDWR:
+		wire_flags |= CEPH_O_RDWR;
+		break;
+	}
+
+#define ceph_sys2wire(a) if (flags & a) { wire_flags |= CEPH_##a; flags &= ~a; }
+
+	ceph_sys2wire(O_CREAT);
+	ceph_sys2wire(O_EXCL);
+	ceph_sys2wire(O_TRUNC);
+	ceph_sys2wire(O_DIRECTORY);
+	ceph_sys2wire(O_NOFOLLOW);
+
+#undef ceph_sys2wire
+
+	if (flags)
+		dout("unused open flags: %x", flags);
+
+	return cpu_to_le32(wire_flags);
+}
+
 /*
  * Ceph file operations
  *
@@ -120,7 +152,7 @@ prepare_open_request(struct super_block *sb, int flags, int create_mode)
 	if (IS_ERR(req))
 		goto out;
 	req->r_fmode = ceph_flags_to_mode(flags);
-	req->r_args.open.flags = cpu_to_le32(flags);
+	req->r_args.open.flags = ceph_flags_sys2wire(flags);
 	req->r_args.open.mode = cpu_to_le32(create_mode);
 out:
 	return req;
@@ -189,7 +221,7 @@ int ceph_renew_caps(struct inode *inode)
 	spin_lock(&ci->i_ceph_lock);
 	wanted = __ceph_caps_file_wanted(ci);
 	if (__ceph_is_any_real_caps(ci) &&
-	    (!(wanted & CEPH_CAP_ANY_WR) == 0 || ci->i_auth_cap)) {
+	    (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
 		int issued = __ceph_caps_issued(ci, NULL);
 		spin_unlock(&ci->i_ceph_lock);
 		dout("renew caps %p want %s issued %s updating mds_wanted\n",
@@ -778,6 +810,7 @@ static void ceph_aio_retry_work(struct work_struct *work)
 	req->r_callback = ceph_aio_complete_req;
 	req->r_inode = inode;
 	req->r_priv = aio_req;
+	req->r_abort_on_full = true;
 
 	ret = ceph_osdc_start_request(req->r_osdc, req, false);
 out:
@@ -1085,19 +1118,22 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 
 out:
 		ceph_osdc_put_request(req);
-		if (ret == 0) {
-			pos += len;
-			written += len;
-
-			if (pos > i_size_read(inode)) {
-				check_caps = ceph_inode_set_size(inode, pos);
-				if (check_caps)
-					ceph_check_caps(ceph_inode(inode),
-							CHECK_CAPS_AUTHONLY,
-							NULL);
-			}
-		} else
+		if (ret != 0) {
+			ceph_set_error_write(ci);
 			break;
+		}
+
+		ceph_clear_error_write(ci);
+		pos += len;
+		written += len;
+		if (pos > i_size_read(inode)) {
+			check_caps = ceph_inode_set_size(inode, pos);
+			if (check_caps)
+				ceph_check_caps(ceph_inode(inode),
+						CHECK_CAPS_AUTHONLY,
+						NULL);
+		}
+
 	}
 
 	if (ret != -EOLDSNAPC && written > 0) {
@@ -1303,6 +1339,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 retry_snap:
+	/* FIXME: not complete since it doesn't account for being at quota */
 	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) {
 		err = -ENOSPC;
 		goto out;
@@ -1324,7 +1361,8 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	     inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
-	    (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+	    (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC) ||
+	    (ci->i_ceph_flags & CEPH_I_ERROR_WRITE)) {
 		struct ceph_snap_context *snapc;
 		struct iov_iter data;
 		inode_unlock(inode);

fs/ceph/inode.c

@@ -1482,10 +1482,17 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags))
 		return readdir_prepopulate_inodes_only(req, session);
 
-	if (rinfo->hash_order && req->r_path2) {
-		last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
-					  req->r_path2, strlen(req->r_path2));
-		last_hash = ceph_frag_value(last_hash);
+	if (rinfo->hash_order) {
+		if (req->r_path2) {
+			last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
+						  req->r_path2,
+						  strlen(req->r_path2));
+			last_hash = ceph_frag_value(last_hash);
+		} else if (rinfo->offset_hash) {
+			/* mds understands offset_hash */
+			WARN_ON_ONCE(req->r_readdir_offset != 2);
+			last_hash = le32_to_cpu(rhead->args.readdir.offset_hash);
+		}
 	}
 
 	if (rinfo->dir_dir &&
@@ -1510,7 +1517,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	}
 
 	if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 &&
-	    !(rinfo->hash_order && req->r_path2)) {
+	    !(rinfo->hash_order && last_hash)) {
 		/* note dir version at start of readdir so we can tell
 		 * if any dentries get dropped */
 		req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);