Merge tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "Lots of exciting things this time!

   - support for rbd object-map and fast-diff features (myself). This
     will speed up reads, discards and things like snap diffs on sparse
     images.

   - ceph.snap.btime vxattr to expose snapshot creation time (David
     Disseldorp). This will be used to integrate with "Restore Previous
     Versions" feature added in Windows 7 for folks who reexport ceph
     through SMB.

   - security xattrs for ceph (Zheng Yan). Only selinux is supported for
     now due to the limitations of ->dentry_init_security().

   - support for MSG_ADDR2, FS_BTIME and FS_CHANGE_ATTR features (Jeff
     Layton). This is actually a single feature bit which was missing
     because of the filesystem pieces. With this in, the kernel client
     will finally be reported as "luminous" by "ceph features" -- it is
     still being reported as "jewel" even though all required Luminous
     features were implemented in 4.13.

   - stop NULL-terminating ceph vxattrs (Jeff Layton). The convention
     with xattrs is to not terminate and this was causing
     inconsistencies with ceph-fuse.

   - change filesystem time granularity from 1 us to 1 ns, again fixing
     an inconsistency with ceph-fuse (Luis Henriques).

  On top of this there are some additional dentry name handling and cap
  flushing fixes from Zheng. Finally, Jeff is formally taking over for
  Zheng as the filesystem maintainer"

* tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client: (71 commits)
  ceph: fix end offset in truncate_inode_pages_range call
  ceph: use generic_delete_inode() for ->drop_inode
  ceph: use ceph_evict_inode to cleanup inode's resource
  ceph: initialize superblock s_time_gran to 1
  MAINTAINERS: take over for Zheng as CephFS kernel client maintainer
  rbd: setallochint only if object doesn't exist
  rbd: support for object-map and fast-diff
  rbd: call rbd_dev_mapping_set() from rbd_dev_image_probe()
  libceph: export osd_req_op_data() macro
  libceph: change ceph_osdc_call() to take page vector for response
  libceph: bump CEPH_MSG_MAX_DATA_LEN (again)
  rbd: new exclusive lock wait/wake code
  rbd: quiescing lock should wait for image requests
  rbd: lock should be quiesced on reacquire
  rbd: introduce copyup state machine
  rbd: rename rbd_obj_setup_*() to rbd_obj_init_*()
  rbd: move OSD request allocation into object request state machines
  rbd: factor out __rbd_osd_setup_discard_ops()
  rbd: factor out rbd_osd_setup_copyup()
  rbd: introduce obj_req->osd_reqs list
  ...

1 files changed, 20 insertions, 22 deletions

diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 9a8eca5eda65..0b2df09b2554 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -171,14 +171,6 @@ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
 	osd_data->num_bvecs = num_bvecs;
 }
 
-#define osd_req_op_data(oreq, whch, typ, fld)				\
-({									\
-	struct ceph_osd_request *__oreq = (oreq);			\
-	unsigned int __whch = (whch);					\
-	BUG_ON(__whch >= __oreq->r_num_ops);				\
-	&__oreq->r_ops[__whch].typ.fld;					\
-})
-
 static struct ceph_osd_data *
 osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which)
 {
@@ -478,7 +470,7 @@ static void request_release_checks(struct ceph_osd_request *req)
 {
 	WARN_ON(!RB_EMPTY_NODE(&req->r_node));
 	WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node));
-	WARN_ON(!list_empty(&req->r_unsafe_item));
+	WARN_ON(!list_empty(&req->r_private_item));
 	WARN_ON(req->r_osd);
 }
 
@@ -538,7 +530,7 @@ static void request_init(struct ceph_osd_request *req)
 	init_completion(&req->r_completion);
 	RB_CLEAR_NODE(&req->r_node);
 	RB_CLEAR_NODE(&req->r_mc_node);
-	INIT_LIST_HEAD(&req->r_unsafe_item);
+	INIT_LIST_HEAD(&req->r_private_item);
 
 	target_init(&req->r_t);
 }
@@ -4914,20 +4906,26 @@ static int decode_watcher(void **p, void *end, struct ceph_watch_item *item)
 	ret = ceph_start_decoding(p, end, 2, "watch_item_t",
 				  &struct_v, &struct_len);
 	if (ret)
-		return ret;
+		goto bad;
+
+	ret = -EINVAL;
+	ceph_decode_copy_safe(p, end, &item->name, sizeof(item->name), bad);
+	ceph_decode_64_safe(p, end, item->cookie, bad);
+	ceph_decode_skip_32(p, end, bad); /* skip timeout seconds */
 
-	ceph_decode_copy(p, &item->name, sizeof(item->name));
-	item->cookie = ceph_decode_64(p);
-	*p += 4; /* skip timeout_seconds */
 	if (struct_v >= 2) {
-		ceph_decode_copy(p, &item->addr, sizeof(item->addr));
-		ceph_decode_addr(&item->addr);
+		ret = ceph_decode_entity_addr(p, end, &item->addr);
+		if (ret)
+			goto bad;
+	} else {
+		ret = 0;
 	}
 
 	dout("%s %s%llu cookie %llu addr %s\n", __func__,
 	     ENTITY_NAME(item->name), item->cookie,
 	     ceph_pr_addr(&item->addr));
-	return 0;
+bad:
+	return ret;
 }
 
 static int decode_watchers(void **p, void *end,
@@ -5044,12 +5042,12 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 		   const char *class, const char *method,
 		   unsigned int flags,
 		   struct page *req_page, size_t req_len,
-		   struct page *resp_page, size_t *resp_len)
+		   struct page **resp_pages, size_t *resp_len)
 {
 	struct ceph_osd_request *req;
 	int ret;
 
-	if (req_len > PAGE_SIZE || (resp_page && *resp_len > PAGE_SIZE))
+	if (req_len > PAGE_SIZE)
 		return -E2BIG;
 
 	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
@@ -5067,8 +5065,8 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 	if (req_page)
 		osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len,
 						  0, false, false);
-	if (resp_page)
-		osd_req_op_cls_response_data_pages(req, 0, &resp_page,
+	if (resp_pages)
+		osd_req_op_cls_response_data_pages(req, 0, resp_pages,
 						   *resp_len, 0, false, false);
 
 	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
@@ -5079,7 +5077,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 	ret = ceph_osdc_wait_request(osdc, req);
 	if (ret >= 0) {
 		ret = req->r_ops[0].rval;
-		if (resp_page)
+		if (resp_pages)
 			*resp_len = req->r_ops[0].outdata_len;
 	}