Merge tag 'ceph-for-5.11-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The big ticket item here is support for msgr2 on-wire protocol, which
  adds the option of full in-transit encryption using AES-GCM algorithm
  (myself).

  On top of that we have a series to avoid intermittent errors during
  recovery with recover_session=clean and some MDS request encoding work
  from Jeff, a cap handling fix and assorted observability improvements
  from Luis and Xiubo and a good number of cleanups.

  Luis also ran into a corner case with quotas which sadly means that we
  are back to denying cross-quota-realm renames"

* tag 'ceph-for-5.11-rc1' of git://github.com/ceph/ceph-client: (59 commits)
  libceph: drop ceph_auth_{create,update}_authorizer()
  libceph, ceph: make use of __ceph_auth_get_authorizer() in msgr1
  libceph, ceph: implement msgr2.1 protocol (crc and secure modes)
  libceph: introduce connection modes and ms_mode option
  libceph, rbd: ignore addr->type while comparing in some cases
  libceph, ceph: get and handle cluster maps with addrvecs
  libceph: factor out finish_auth()
  libceph: drop ac->ops->name field
  libceph: amend cephx init_protocol() and build_request()
  libceph, ceph: incorporate nautilus cephx changes
  libceph: safer en/decoding of cephx requests and replies
  libceph: more insight into ticket expiry and invalidation
  libceph: move msgr1 protocol specific fields to its own struct
  libceph: move msgr1 protocol implementation to its own file
  libceph: separate msgr1 protocol implementation
  libceph: export remaining protocol independent infrastructure
  libceph: export zero_page
  libceph: rename and export con->flags bits
  libceph: rename and export con->state states
  libceph: make con->state an int
  ...

1 files changed, 23 insertions, 18 deletions

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 526faf4778ce..adc8fc3c5d85 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1315,15 +1315,10 @@ retry_lookup:
 	}
 
 	if (rinfo->head->is_target) {
-		tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
-		tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
-
-		in = ceph_get_inode(sb, tvino);
-		if (IS_ERR(in)) {
-			err = PTR_ERR(in);
-			goto done;
-		}
+		/* Should be filled in by handle_reply */
+		BUG_ON(!req->r_target_inode);
 
+		in = req->r_target_inode;
 		err = ceph_fill_inode(in, req->r_locked_page, &rinfo->targeti,
 				NULL, session,
 				(!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
@@ -1333,11 +1328,13 @@ retry_lookup:
 		if (err < 0) {
 			pr_err("ceph_fill_inode badness %p %llx.%llx\n",
 				in, ceph_vinop(in));
+			req->r_target_inode = NULL;
 			if (in->i_state & I_NEW)
 				discard_new_inode(in);
+			else
+				iput(in);
 			goto done;
 		}
-		req->r_target_inode = in;
 		if (in->i_state & I_NEW)
 			unlock_new_inode(in);
 	}
@@ -1597,8 +1594,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	struct dentry *dn;
 	struct inode *in;
 	int err = 0, skipped = 0, ret, i;
-	struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
-	u32 frag = le32_to_cpu(rhead->args.readdir.frag);
+	u32 frag = le32_to_cpu(req->r_args.readdir.frag);
 	u32 last_hash = 0;
 	u32 fpos_offset;
 	struct ceph_readdir_cache_control cache_ctl = {};
@@ -1615,7 +1611,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 		} 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);
+			last_hash = le32_to_cpu(req->r_args.readdir.offset_hash);
 		}
 	}
 
@@ -1888,7 +1884,7 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 
 	mutex_lock(&ci->i_truncate_mutex);
 
-	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+	if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
 		pr_warn_ratelimited("invalidate_pages %p %lld forced umount\n",
 				    inode, ceph_ino(inode));
 		mapping_set_error(inode->i_mapping, -EIO);
@@ -2340,15 +2336,23 @@ int ceph_permission(struct inode *inode, int mask)
 }
 
 /* Craft a mask of needed caps given a set of requested statx attrs. */
-static int statx_to_caps(u32 want)
+static int statx_to_caps(u32 want, umode_t mode)
 {
 	int mask = 0;
 
 	if (want & (STATX_MODE|STATX_UID|STATX_GID|STATX_CTIME|STATX_BTIME))
 		mask |= CEPH_CAP_AUTH_SHARED;
 
-	if (want & (STATX_NLINK|STATX_CTIME))
-		mask |= CEPH_CAP_LINK_SHARED;
+	if (want & (STATX_NLINK|STATX_CTIME)) {
+		/*
+		 * The link count for directories depends on inode->i_subdirs,
+		 * and that is only updated when Fs caps are held.
+		 */
+		if (S_ISDIR(mode))
+			mask |= CEPH_CAP_FILE_SHARED;
+		else
+			mask |= CEPH_CAP_LINK_SHARED;
+	}
 
 	if (want & (STATX_ATIME|STATX_MTIME|STATX_CTIME|STATX_SIZE|
 		    STATX_BLOCKS))
@@ -2374,8 +2378,9 @@ int ceph_getattr(const struct path *path, struct kstat *stat,
 
 	/* Skip the getattr altogether if we're asked not to sync */
 	if (!(flags & AT_STATX_DONT_SYNC)) {
-		err = ceph_do_getattr(inode, statx_to_caps(request_mask),
-				      flags & AT_STATX_FORCE_SYNC);
+		err = ceph_do_getattr(inode,
+				statx_to_caps(request_mask, inode->i_mode),
+				flags & AT_STATX_FORCE_SYNC);
 		if (err)
 			return err;
 	}