libceph: variable-sized ceph_object_id

Currently ceph_object_id can hold object names of up to 100
(CEPH_MAX_OID_NAME_LEN) characters.  This is enough for all use cases,
expect one - long rbd image names:

- a format 1 header is named "<imgname>.rbd"
- an object that points to a format 2 header is named "rbd_id.<imgname>"

We operate on these potentially long-named objects during rbd map, and,
for format 1 images, during header refresh.  (A format 2 header name is
a small system-generated string.)

Lift this 100 character limit by making ceph_object_id be able to point
to an externally-allocated string.  Apart from being able to work with
almost arbitrarily-long named objects, this allows us to reduce the
size of ceph_object_id from >100 bytes to 64 bytes.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

3 files changed, 103 insertions, 8 deletions

diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index b902fbc7863e..6f8413293d15 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -161,7 +161,7 @@ static int osdc_show(struct seq_file *s, void *pp)
 			   req->r_osd ? req->r_osd->o_osd : -1,
 			   req->r_pgid.pool, req->r_pgid.seed);
 
-		seq_printf(s, "%.*s", req->r_base_oid.name_len,
+		seq_printf(s, "%*pE", req->r_base_oid.name_len,
 			   req->r_base_oid.name);
 
 		if (req->r_reassert_version.epoch)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 75e27bd3d372..95910aed8e2e 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -334,7 +334,10 @@ static void ceph_osdc_release_request(struct kref *kref)
 	for (which = 0; which < req->r_num_ops; which++)
 		osd_req_op_data_release(req, which);
 
+	ceph_oid_destroy(&req->r_base_oid);
+	ceph_oid_destroy(&req->r_target_oid);
 	ceph_put_snap_context(req->r_snapc);
+
 	if (req->r_mempool)
 		mempool_free(req, req->r_osdc->req_mempool);
 	else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS)
@@ -401,7 +404,9 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	INIT_LIST_HEAD(&req->r_req_lru_item);
 	INIT_LIST_HEAD(&req->r_osd_item);
 
+	ceph_oid_init(&req->r_base_oid);
 	req->r_base_oloc.pool = -1;
+	ceph_oid_init(&req->r_target_oid);
 	req->r_target_oloc.pool = -1;
 
 	dout("%s req %p\n", __func__, req);
@@ -415,6 +420,8 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
 	struct ceph_msg *msg;
 	int msg_size;
 
+	WARN_ON(ceph_oid_empty(&req->r_base_oid));
+
 	/* create request message */
 	msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */
 	msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */
@@ -859,10 +866,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	}
 
 	req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
-
-	snprintf(req->r_base_oid.name, sizeof(req->r_base_oid.name),
-		 "%llx.%08llx", vino.ino, objnum);
-	req->r_base_oid.name_len = strlen(req->r_base_oid.name);
+	ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
 
 	r = ceph_osdc_alloc_messages(req, GFP_NOFS);
 	if (r)
@@ -1410,7 +1414,7 @@ static int __calc_request_pg(struct ceph_osdmap *osdmap,
 		req->r_target_oloc = req->r_base_oloc; /* struct */
 		need_check_tiering = true;
 	}
-	if (req->r_target_oid.name_len == 0) {
+	if (ceph_oid_empty(&req->r_target_oid)) {
 		ceph_oid_copy(&req->r_target_oid, &req->r_base_oid);
 		need_check_tiering = true;
 	}
@@ -2501,7 +2505,7 @@ void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off,
 	/* oid */
 	ceph_encode_32(&p, req->r_base_oid.name_len);
 	memcpy(p, req->r_base_oid.name, req->r_base_oid.name_len);
-	dout("oid '%.*s' len %d\n", req->r_base_oid.name_len,
+	dout("oid %*pE len %d\n", req->r_base_oid.name_len,
 	     req->r_base_oid.name, req->r_base_oid.name_len);
 	p += req->r_base_oid.name_len;
 
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 243574c8cf33..4668b871ca47 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1381,8 +1381,99 @@ bad:
 	return ERR_PTR(err);
 }
 
+void ceph_oid_copy(struct ceph_object_id *dest,
+		   const struct ceph_object_id *src)
+{
+	WARN_ON(!ceph_oid_empty(dest));
+
+	if (src->name != src->inline_name) {
+		/* very rare, see ceph_object_id definition */
+		dest->name = kmalloc(src->name_len + 1,
+				     GFP_NOIO | __GFP_NOFAIL);
+	}
 
+	memcpy(dest->name, src->name, src->name_len + 1);
+	dest->name_len = src->name_len;
+}
+EXPORT_SYMBOL(ceph_oid_copy);
 
+static __printf(2, 0)
+int oid_printf_vargs(struct ceph_object_id *oid, const char *fmt, va_list ap)
+{
+	int len;
+
+	WARN_ON(!ceph_oid_empty(oid));
+
+	len = vsnprintf(oid->inline_name, sizeof(oid->inline_name), fmt, ap);
+	if (len >= sizeof(oid->inline_name))
+		return len;
+
+	oid->name_len = len;
+	return 0;
+}
+
+/*
+ * If oid doesn't fit into inline buffer, BUG.
+ */
+void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	BUG_ON(oid_printf_vargs(oid, fmt, ap));
+	va_end(ap);
+}
+EXPORT_SYMBOL(ceph_oid_printf);
+
+static __printf(3, 0)
+int oid_aprintf_vargs(struct ceph_object_id *oid, gfp_t gfp,
+		      const char *fmt, va_list ap)
+{
+	va_list aq;
+	int len;
+
+	va_copy(aq, ap);
+	len = oid_printf_vargs(oid, fmt, aq);
+	va_end(aq);
+
+	if (len) {
+		char *external_name;
+
+		external_name = kmalloc(len + 1, gfp);
+		if (!external_name)
+			return -ENOMEM;
+
+		oid->name = external_name;
+		WARN_ON(vsnprintf(oid->name, len + 1, fmt, ap) != len);
+		oid->name_len = len;
+	}
+
+	return 0;
+}
+
+/*
+ * If oid doesn't fit into inline buffer, allocate.
+ */
+int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,
+		     const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = oid_aprintf_vargs(oid, gfp, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+EXPORT_SYMBOL(ceph_oid_aprintf);
+
+void ceph_oid_destroy(struct ceph_object_id *oid)
+{
+	if (oid->name != oid->inline_name)
+		kfree(oid->name);
+}
+EXPORT_SYMBOL(ceph_oid_destroy);
 
 /*
  * calculate file layout from given offset, length.
@@ -1474,7 +1565,7 @@ int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
 	pg_out->seed = ceph_str_hash(pi->object_hash, oid->name,
 				     oid->name_len);
 
-	dout("%s '%.*s' pgid %llu.%x\n", __func__, oid->name_len, oid->name,
+	dout("%s %*pE pgid %llu.%x\n", __func__, oid->name_len, oid->name,
 	     pg_out->pool, pg_out->seed);
 	return 0;
 }