1 files changed, 105 insertions, 67 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 0f497c39ff82..3bc72b47fe4d 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2681,8 +2681,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
  * ceph_mdsc_build_path - build a path string to a given dentry
  * @mdsc: mds client
  * @dentry: dentry to which path should be built
- * @plen: returned length of string
- * @pbase: returned base inode number
+ * @path_info: output path, length, base ino+snap, and freepath ownership flag
  * @for_wire: is this path going to be sent to the MDS?
  *
  * Build a string that represents the path to the dentry. This is mostly called
@@ -2700,7 +2699,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
  *   foo/.snap/bar -> foo//bar
  */
 char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
-			   int *plen, u64 *pbase, int for_wire)
+			   struct ceph_path_info *path_info, int for_wire)
 {
 	struct ceph_client *cl = mdsc->fsc->client;
 	struct dentry *cur;
@@ -2810,16 +2809,28 @@ retry:
 		return ERR_PTR(-ENAMETOOLONG);
 	}
 
-	*pbase = base;
-	*plen = PATH_MAX - 1 - pos;
+	/* Initialize the output structure */
+	memset(path_info, 0, sizeof(*path_info));
+
+	path_info->vino.ino = base;
+	path_info->pathlen = PATH_MAX - 1 - pos;
+	path_info->path = path + pos;
+	path_info->freepath = true;
+
+	/* Set snap from dentry if available */
+	if (d_inode(dentry))
+		path_info->vino.snap = ceph_snap(d_inode(dentry));
+	else
+		path_info->vino.snap = CEPH_NOSNAP;
+
 	doutc(cl, "on %p %d built %llx '%.*s'\n", dentry, d_count(dentry),
-	      base, *plen, path + pos);
+	      base, PATH_MAX - 1 - pos, path + pos);
 	return path + pos;
 }
 
 static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
-			     struct inode *dir, const char **ppath, int *ppathlen,
-			     u64 *pino, bool *pfreepath, bool parent_locked)
+			     struct inode *dir, struct ceph_path_info *path_info,
+			     bool parent_locked)
 {
 	char *path;
 
@@ -2828,41 +2839,47 @@ static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry
 		dir = d_inode_rcu(dentry->d_parent);
 	if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP &&
 	    !IS_ENCRYPTED(dir)) {
-		*pino = ceph_ino(dir);
+		path_info->vino.ino = ceph_ino(dir);
+		path_info->vino.snap = ceph_snap(dir);
 		rcu_read_unlock();
-		*ppath = dentry->d_name.name;
-		*ppathlen = dentry->d_name.len;
+		path_info->path = dentry->d_name.name;
+		path_info->pathlen = dentry->d_name.len;
+		path_info->freepath = false;
 		return 0;
 	}
 	rcu_read_unlock();
-	path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1);
+	path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
-	*ppath = path;
-	*pfreepath = true;
+	/*
+	 * ceph_mdsc_build_path already fills path_info, including snap handling.
+	 */
 	return 0;
 }
 
-static int build_inode_path(struct inode *inode,
-			    const char **ppath, int *ppathlen, u64 *pino,
-			    bool *pfreepath)
+static int build_inode_path(struct inode *inode, struct ceph_path_info *path_info)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 	struct dentry *dentry;
 	char *path;
 
 	if (ceph_snap(inode) == CEPH_NOSNAP) {
-		*pino = ceph_ino(inode);
-		*ppathlen = 0;
+		path_info->vino.ino = ceph_ino(inode);
+		path_info->vino.snap = ceph_snap(inode);
+		path_info->pathlen = 0;
+		path_info->freepath = false;
 		return 0;
 	}
 	dentry = d_find_alias(inode);
-	path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1);
+	path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1);
 	dput(dentry);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
-	*ppath = path;
-	*pfreepath = true;
+	/*
+	 * ceph_mdsc_build_path already fills path_info, including snap from dentry.
+	 * Override with inode's snap since that's what this function is for.
+	 */
+	path_info->vino.snap = ceph_snap(inode);
 	return 0;
 }
 
@@ -2872,26 +2889,32 @@ static int build_inode_path(struct inode *inode,
  */
 static int set_request_path_attr(struct ceph_mds_client *mdsc, struct inode *rinode,
 				 struct dentry *rdentry, struct inode *rdiri,
-				 const char *rpath, u64 rino, const char **ppath,
-				 int *pathlen, u64 *ino, bool *freepath,
+				 const char *rpath, u64 rino,
+				 struct ceph_path_info *path_info,
 				 bool parent_locked)
 {
 	struct ceph_client *cl = mdsc->fsc->client;
 	int r = 0;
 
+	/* Initialize the output structure */
+	memset(path_info, 0, sizeof(*path_info));
+
 	if (rinode) {
-		r = build_inode_path(rinode, ppath, pathlen, ino, freepath);
+		r = build_inode_path(rinode, path_info);
 		doutc(cl, " inode %p %llx.%llx\n", rinode, ceph_ino(rinode),
 		      ceph_snap(rinode));
 	} else if (rdentry) {
-		r = build_dentry_path(mdsc, rdentry, rdiri, ppath, pathlen, ino,
-					freepath, parent_locked);
-		doutc(cl, " dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath);
+		r = build_dentry_path(mdsc, rdentry, rdiri, path_info, parent_locked);
+		doutc(cl, " dentry %p %llx/%.*s\n", rdentry, path_info->vino.ino,
+		      path_info->pathlen, path_info->path);
 	} else if (rpath || rino) {
-		*ino = rino;
-		*ppath = rpath;
-		*pathlen = rpath ? strlen(rpath) : 0;
-		doutc(cl, " path %.*s\n", *pathlen, rpath);
+		path_info->vino.ino = rino;
+		path_info->vino.snap = CEPH_NOSNAP;
+		path_info->path = rpath;
+		path_info->pathlen = rpath ? strlen(rpath) : 0;
+		path_info->freepath = false;
+
+		doutc(cl, " path %.*s\n", path_info->pathlen, rpath);
 	}
 
 	return r;
@@ -2968,11 +2991,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_msg *msg;
 	struct ceph_mds_request_head_legacy *lhead;
-	const char *path1 = NULL;
-	const char *path2 = NULL;
-	u64 ino1 = 0, ino2 = 0;
-	int pathlen1 = 0, pathlen2 = 0;
-	bool freepath1 = false, freepath2 = false;
+	struct ceph_path_info path_info1 = {0};
+	struct ceph_path_info path_info2 = {0};
 	struct dentry *old_dentry = NULL;
 	int len;
 	u16 releases;
@@ -2982,25 +3002,49 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	u16 request_head_version = mds_supported_head_version(session);
 	kuid_t caller_fsuid = req->r_cred->fsuid;
 	kgid_t caller_fsgid = req->r_cred->fsgid;
+	bool parent_locked = test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 
 	ret = set_request_path_attr(mdsc, req->r_inode, req->r_dentry,
-			      req->r_parent, req->r_path1, req->r_ino1.ino,
-			      &path1, &pathlen1, &ino1, &freepath1,
-			      test_bit(CEPH_MDS_R_PARENT_LOCKED,
-					&req->r_req_flags));
+				    req->r_parent, req->r_path1, req->r_ino1.ino,
+				    &path_info1, parent_locked);
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
 		goto out;
 	}
 
+	/*
+	 * When the parent directory's i_rwsem is *not* locked, req->r_parent may
+	 * have become stale (e.g. after a concurrent rename) between the time the
+	 * dentry was looked up and now.  If we detect that the stored r_parent
+	 * does not match the inode number we just encoded for the request, switch
+	 * to the correct inode so that the MDS receives a valid parent reference.
+	 */
+	if (!parent_locked && req->r_parent && path_info1.vino.ino &&
+	    ceph_ino(req->r_parent) != path_info1.vino.ino) {
+		struct inode *old_parent = req->r_parent;
+		struct inode *correct_dir = ceph_get_inode(mdsc->fsc->sb, path_info1.vino, NULL);
+		if (!IS_ERR(correct_dir)) {
+			WARN_ONCE(1, "ceph: r_parent mismatch (had %llx wanted %llx) - updating\n",
+			          ceph_ino(old_parent), path_info1.vino.ino);
+			/*
+			 * Transfer CEPH_CAP_PIN from the old parent to the new one.
+			 * The pin was taken earlier in ceph_mdsc_submit_request().
+			 */
+			ceph_put_cap_refs(ceph_inode(old_parent), CEPH_CAP_PIN);
+			iput(old_parent);
+			req->r_parent = correct_dir;
+			ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
+		}
+	}
+
 	/* If r_old_dentry is set, then assume that its parent is locked */
 	if (req->r_old_dentry &&
 	    !(req->r_old_dentry->d_flags & DCACHE_DISCONNECTED))
 		old_dentry = req->r_old_dentry;
 	ret = set_request_path_attr(mdsc, NULL, old_dentry,
-			      req->r_old_dentry_dir,
-			      req->r_path2, req->r_ino2.ino,
-			      &path2, &pathlen2, &ino2, &freepath2, true);
+				    req->r_old_dentry_dir,
+				    req->r_path2, req->r_ino2.ino,
+				    &path_info2, true);
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
 		goto out_free1;
@@ -3031,7 +3075,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 
 	/* filepaths */
 	len += 2 * (1 + sizeof(u32) + sizeof(u64));
-	len += pathlen1 + pathlen2;
+	len += path_info1.pathlen + path_info2.pathlen;
 
 	/* cap releases */
 	len += sizeof(struct ceph_mds_request_release) *
@@ -3039,9 +3083,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		 !!req->r_old_inode_drop + !!req->r_old_dentry_drop);
 
 	if (req->r_dentry_drop)
-		len += pathlen1;
+		len += path_info1.pathlen;
 	if (req->r_old_dentry_drop)
-		len += pathlen2;
+		len += path_info2.pathlen;
 
 	/* MClientRequest tail */
 
@@ -3154,8 +3198,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	lhead->ino = cpu_to_le64(req->r_deleg_ino);
 	lhead->args = req->r_args;
 
-	ceph_encode_filepath(&p, end, ino1, path1);
-	ceph_encode_filepath(&p, end, ino2, path2);
+	ceph_encode_filepath(&p, end, path_info1.vino.ino, path_info1.path);
+	ceph_encode_filepath(&p, end, path_info2.vino.ino, path_info2.path);
 
 	/* make note of release offset, in case we need to replay */
 	req->r_request_release_offset = p - msg->front.iov_base;
@@ -3218,11 +3262,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	msg->hdr.data_off = cpu_to_le16(0);
 
 out_free2:
-	if (freepath2)
-		ceph_mdsc_free_path((char *)path2, pathlen2);
+	ceph_mdsc_free_path_info(&path_info2);
 out_free1:
-	if (freepath1)
-		ceph_mdsc_free_path((char *)path1, pathlen1);
+	ceph_mdsc_free_path_info(&path_info1);
 out:
 	return msg;
 out_err:
@@ -4579,24 +4621,20 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 	struct ceph_pagelist *pagelist = recon_state->pagelist;
 	struct dentry *dentry;
 	struct ceph_cap *cap;
-	char *path;
-	int pathlen = 0, err;
-	u64 pathbase;
+	struct ceph_path_info path_info = {0};
+	int err;
 	u64 snap_follows;
 
 	dentry = d_find_primary(inode);
 	if (dentry) {
 		/* set pathbase to parent dir when msg_version >= 2 */
-		path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase,
+		char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info,
 					    recon_state->msg_version >= 2);
 		dput(dentry);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			goto out_err;
 		}
-	} else {
-		path = NULL;
-		pathbase = 0;
 	}
 
 	spin_lock(&ci->i_ceph_lock);
@@ -4629,7 +4667,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 		rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci));
 		rec.v2.issued = cpu_to_le32(cap->issued);
 		rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
-		rec.v2.pathbase = cpu_to_le64(pathbase);
+		rec.v2.pathbase = cpu_to_le64(path_info.vino.ino);
 		rec.v2.flock_len = (__force __le32)
 			((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1);
 	} else {
@@ -4644,7 +4682,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 		ts = inode_get_atime(inode);
 		ceph_encode_timespec64(&rec.v1.atime, &ts);
 		rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
-		rec.v1.pathbase = cpu_to_le64(pathbase);
+		rec.v1.pathbase = cpu_to_le64(path_info.vino.ino);
 	}
 
 	if (list_empty(&ci->i_cap_snaps)) {
@@ -4706,7 +4744,7 @@ encode_again:
 			    sizeof(struct ceph_filelock);
 		rec.v2.flock_len = cpu_to_le32(struct_len);
 
-		struct_len += sizeof(u32) + pathlen + sizeof(rec.v2);
+		struct_len += sizeof(u32) + path_info.pathlen + sizeof(rec.v2);
 
 		if (struct_v >= 2)
 			struct_len += sizeof(u64); /* snap_follows */
@@ -4730,7 +4768,7 @@ encode_again:
 			ceph_pagelist_encode_8(pagelist, 1);
 			ceph_pagelist_encode_32(pagelist, struct_len);
 		}
-		ceph_pagelist_encode_string(pagelist, path, pathlen);
+		ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen);
 		ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2));
 		ceph_locks_to_pagelist(flocks, pagelist,
 				       num_fcntl_locks, num_flock_locks);
@@ -4741,17 +4779,17 @@ out_freeflocks:
 	} else {
 		err = ceph_pagelist_reserve(pagelist,
 					    sizeof(u64) + sizeof(u32) +
-					    pathlen + sizeof(rec.v1));
+					    path_info.pathlen + sizeof(rec.v1));
 		if (err)
 			goto out_err;
 
 		ceph_pagelist_encode_64(pagelist, ceph_ino(inode));
-		ceph_pagelist_encode_string(pagelist, path, pathlen);
+		ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen);
 		ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1));
 	}
 
 out_err:
-	ceph_mdsc_free_path(path, pathlen);
+	ceph_mdsc_free_path_info(&path_info);
 	if (!err)
 		recon_state->nr_caps++;
 	return err;