Merge tag 'ceph-for-7.0-rc4' of https://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:
 "A small pile of CephFS and messenger bug fixes, all marked for stable"

* tag 'ceph-for-7.0-rc4' of https://github.com/ceph/ceph-client:
  libceph: Fix potential out-of-bounds access in ceph_handle_auth_reply()
  libceph: Use u32 for non-negative values in ceph_monmap_decode()
  MAINTAINERS: update email address of Dongsheng Yang
  libceph: reject preamble if control segment is empty
  libceph: admit message frames only in CEPH_CON_S_OPEN state
  libceph: prevent potential out-of-bounds reads in process_message_header()
  ceph: do not skip the first folio of the next object in writeback
  ceph: fix memory leaks in ceph_mdsc_build_path()
  ceph: add a bunch of missing ceph_path_info initializers
  ceph: fix i_nlink underrun during async unlink

Author: torvalds

MAINTAINERS

@@ -21937,7 +21937,7 @@ F:	drivers/media/radio/radio-tea5777.c
 
 RADOS BLOCK DEVICE (RBD)
 M:	Ilya Dryomov <idryomov@gmail.com>
-R:	Dongsheng Yang <dongsheng.yang@easystack.cn>
+R:	Dongsheng Yang <dongsheng.yang@linux.dev>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/

fs/ceph/addr.c

@@ -1326,7 +1326,6 @@ void ceph_process_folio_batch(struct address_space *mapping,
 			continue;
 		} else if (rc == -E2BIG) {
 			folio_unlock(folio);
-			ceph_wbc->fbatch.folios[i] = NULL;
 			break;
 		}
 

fs/ceph/debugfs.c

@@ -79,7 +79,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 		if (req->r_inode) {
 			seq_printf(s, " #%llx", ceph_ino(req->r_inode));
 		} else if (req->r_dentry) {
-			struct ceph_path_info path_info;
+			struct ceph_path_info path_info = {0};
 			path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0);
 			if (IS_ERR(path))
 				path = NULL;
@@ -98,7 +98,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 		}
 
 		if (req->r_old_dentry) {
-			struct ceph_path_info path_info;
+			struct ceph_path_info path_info = {0};
 			path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0);
 			if (IS_ERR(path))
 				path = NULL;

fs/ceph/dir.c

@@ -1339,6 +1339,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = d_inode(dentry);
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
 	bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS);
 	struct dentry *dn;
@@ -1363,7 +1364,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	if (!dn) {
 		try_async = false;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
 		if (IS_ERR(path)) {
 			try_async = false;
@@ -1424,7 +1425,19 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 			 * We have enough caps, so we assume that the unlink
 			 * will succeed. Fix up the target inode and dcache.
 			 */
-			drop_nlink(inode);
+
+			/*
+			 * Protect the i_nlink update with i_ceph_lock
+			 * to precent racing against ceph_fill_inode()
+			 * handling our completion on a worker thread
+			 * and don't decrement if i_nlink has already
+			 * been updated to zero by this completion.
+			 */
+			spin_lock(&ci->i_ceph_lock);
+			if (inode->i_nlink > 0)
+				drop_nlink(inode);
+			spin_unlock(&ci->i_ceph_lock);
+
 			d_delete(dentry);
 		} else {
 			spin_lock(&fsc->async_unlink_conflict_lock);

fs/ceph/file.c

@@ -397,7 +397,7 @@ int ceph_open(struct inode *inode, struct file *file)
 	if (!dentry) {
 		do_sync = true;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 		if (IS_ERR(path)) {
 			do_sync = true;
@@ -807,7 +807,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (!dn) {
 		try_async = false;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
 		if (IS_ERR(path)) {
 			try_async = false;

fs/ceph/inode.c

@@ -2551,7 +2551,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
 	if (!dentry) {
 		do_sync = true;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 		if (IS_ERR(path)) {
 			do_sync = true;

fs/ceph/mds_client.c

@@ -2768,6 +2768,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
 			if (ret < 0) {
 				dput(parent);
 				dput(cur);
+				__putname(path);
 				return ERR_PTR(ret);
 			}
 
@@ -2777,6 +2778,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
 				if (len < 0) {
 					dput(parent);
 					dput(cur);
+					__putname(path);
 					return ERR_PTR(len);
 				}
 			}
@@ -2813,6 +2815,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
 		 * cannot ever succeed.  Creating paths that long is
 		 * possible with Ceph, but Linux cannot use them.
 		 */
+		__putname(path);
 		return ERR_PTR(-ENAMETOOLONG);
 	}
 

net/ceph/auth.c

@@ -205,9 +205,9 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 	s32 result;
 	u64 global_id;
 	void *payload, *payload_end;
-	int payload_len;
+	u32 payload_len;
 	char *result_msg;
-	int result_msg_len;
+	u32 result_msg_len;
 	int ret = -EINVAL;
 
 	mutex_lock(&ac->mutex);
@@ -217,10 +217,12 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 	result = ceph_decode_32(&p);
 	global_id = ceph_decode_64(&p);
 	payload_len = ceph_decode_32(&p);
+	ceph_decode_need(&p, end, payload_len, bad);
 	payload = p;
 	p += payload_len;
 	ceph_decode_need(&p, end, sizeof(u32), bad);
 	result_msg_len = ceph_decode_32(&p);
+	ceph_decode_need(&p, end, result_msg_len, bad);
 	result_msg = p;
 	p += result_msg_len;
 	if (p != end)

net/ceph/messenger_v2.c

@@ -392,7 +392,7 @@ static int head_onwire_len(int ctrl_len, bool secure)
 	int head_len;
 	int rem_len;
 
-	BUG_ON(ctrl_len < 0 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN);
+	BUG_ON(ctrl_len < 1 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN);
 
 	if (secure) {
 		head_len = CEPH_PREAMBLE_SECURE_LEN;
@@ -401,9 +401,7 @@ static int head_onwire_len(int ctrl_len, bool secure)
 			head_len += padded_len(rem_len) + CEPH_GCM_TAG_LEN;
 		}
 	} else {
-		head_len = CEPH_PREAMBLE_PLAIN_LEN;
-		if (ctrl_len)
-			head_len += ctrl_len + CEPH_CRC_LEN;
+		head_len = CEPH_PREAMBLE_PLAIN_LEN + ctrl_len + CEPH_CRC_LEN;
 	}
 	return head_len;
 }
@@ -528,11 +526,16 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc)
 		desc->fd_aligns[i] = ceph_decode_16(&p);
 	}
 
-	if (desc->fd_lens[0] < 0 ||
+	/*
+	 * This would fire for FRAME_TAG_WAIT (it has one empty
+	 * segment), but we should never get it as client.
+	 */
+	if (desc->fd_lens[0] < 1 ||
 	    desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) {
 		pr_err("bad control segment length %d\n", desc->fd_lens[0]);
 		return -EINVAL;
 	}
+
 	if (desc->fd_lens[1] < 0 ||
 	    desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) {
 		pr_err("bad front segment length %d\n", desc->fd_lens[1]);
@@ -549,10 +552,6 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc)
 		return -EINVAL;
 	}
 
-	/*
-	 * This would fire for FRAME_TAG_WAIT (it has one empty
-	 * segment), but we should never get it as client.
-	 */
 	if (!desc->fd_lens[desc->fd_seg_cnt - 1]) {
 		pr_err("last segment empty, segment count %d\n",
 		       desc->fd_seg_cnt);
@@ -2833,12 +2832,15 @@ static int process_message_header(struct ceph_connection *con,
 				  void *p, void *end)
 {
 	struct ceph_frame_desc *desc = &con->v2.in_desc;
-	struct ceph_msg_header2 *hdr2 = p;
+	struct ceph_msg_header2 *hdr2;
 	struct ceph_msg_header hdr;
 	int skip;
 	int ret;
 	u64 seq;
 
+	ceph_decode_need(&p, end, sizeof(*hdr2), bad);
+	hdr2 = p;
+
 	/* verify seq# */
 	seq = le64_to_cpu(hdr2->seq);
 	if ((s64)seq - (s64)con->in_seq < 1) {
@@ -2869,6 +2871,10 @@ static int process_message_header(struct ceph_connection *con,
 	WARN_ON(!con->in_msg);
 	WARN_ON(con->in_msg->con != con);
 	return 1;
+
+bad:
+	pr_err("failed to decode message header\n");
+	return -EINVAL;
 }
 
 static int process_message(struct ceph_connection *con)
@@ -2898,6 +2904,11 @@ static int __handle_control(struct ceph_connection *con, void *p)
 	if (con->v2.in_desc.fd_tag != FRAME_TAG_MESSAGE)
 		return process_control(con, p, end);
 
+	if (con->state != CEPH_CON_S_OPEN) {
+		con->error_msg = "protocol error, unexpected message";
+		return -EINVAL;
+	}
+
 	ret = process_message_header(con, p, end);
 	if (ret < 0)
 		return ret;

net/ceph/mon_client.c

@@ -72,8 +72,8 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 	struct ceph_monmap *monmap = NULL;
 	struct ceph_fsid fsid;
 	u32 struct_len;
-	int blob_len;
-	int num_mon;
+	u32 blob_len;
+	u32 num_mon;
 	u8 struct_v;
 	u32 epoch;
 	int ret;
@@ -112,7 +112,7 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 	}
 	ceph_decode_32_safe(p, end, num_mon, e_inval);
 
-	dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch,
+	dout("%s fsid %pU epoch %u num_mon %u\n", __func__, &fsid, epoch,
 	     num_mon);
 	if (num_mon > CEPH_MAX_MON)
 		goto e_inval;