Merge tag 'ceph-for-6.13-rc4' of https://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:
 "A handful of important CephFS fixes from Max, Alex and myself: memory
  corruption due to a buffer overrun, potential infinite loop and
  several memory leaks on the error paths. All but one marked for
  stable"

* tag 'ceph-for-6.13-rc4' of https://github.com/ceph/ceph-client:
  ceph: allocate sparse_ext map only for sparse reads
  ceph: fix memory leak in ceph_direct_read_write()
  ceph: improve error handling and short/overflow-read logic in __ceph_sync_read()
  ceph: validate snapdirname option length when mounting
  ceph: give up on paths longer than PATH_MAX
  ceph: fix memory leaks in __ceph_sync_read()

4 files changed, 46 insertions, 44 deletions

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 4b8d59ebda00..851d70200c6b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1066,7 +1066,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 	if (ceph_inode_is_shutdown(inode))
 		return -EIO;
 
-	if (!len)
+	if (!len || !i_size)
 		return 0;
 	/*
 	 * flush any page cache pages in this range.  this
@@ -1086,7 +1086,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		int num_pages;
 		size_t page_off;
 		bool more;
-		int idx;
+		int idx = 0;
 		size_t left;
 		struct ceph_osd_req_op *op;
 		u64 read_off = off;
@@ -1116,6 +1116,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			len = read_off + read_len - off;
 		more = len < iov_iter_count(to);
 
+		op = &req->r_ops[0];
+		if (sparse) {
+			extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
+			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
+			if (ret) {
+				ceph_osdc_put_request(req);
+				break;
+			}
+		}
+
 		num_pages = calc_pages_for(read_off, read_len);
 		page_off = offset_in_page(off);
 		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
@@ -1127,17 +1137,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 
 		osd_req_op_extent_osd_data_pages(req, 0, pages, read_len,
 						 offset_in_page(read_off),
-						 false, false);
-
-		op = &req->r_ops[0];
-		if (sparse) {
-			extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
-			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
-			if (ret) {
-				ceph_osdc_put_request(req);
-				break;
-			}
-		}
+						 false, true);
 
 		ceph_osdc_start_request(osdc, req);
 		ret = ceph_osdc_wait_request(osdc, req);
@@ -1160,7 +1160,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		else if (ret == -ENOENT)
 			ret = 0;
 
-		if (ret > 0 && IS_ENCRYPTED(inode)) {
+		if (ret < 0) {
+			ceph_osdc_put_request(req);
+			if (ret == -EBLOCKLISTED)
+				fsc->blocklisted = true;
+			break;
+		}
+
+		if (IS_ENCRYPTED(inode)) {
 			int fret;
 
 			fret = ceph_fscrypt_decrypt_extents(inode, pages,
@@ -1186,10 +1193,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			ret = min_t(ssize_t, fret, len);
 		}
 
-		ceph_osdc_put_request(req);
-
 		/* Short read but not EOF? Zero out the remainder. */
-		if (ret >= 0 && ret < len && (off + ret < i_size)) {
+		if (ret < len && (off + ret < i_size)) {
 			int zlen = min(len - ret, i_size - off - ret);
 			int zoff = page_off + ret;
 
@@ -1199,13 +1204,11 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			ret += zlen;
 		}
 
-		idx = 0;
-		if (ret <= 0)
-			left = 0;
-		else if (off + ret > i_size)
-			left = i_size - off;
+		if (off + ret > i_size)
+			left = (i_size > off) ? i_size - off : 0;
 		else
 			left = ret;
+
 		while (left > 0) {
 			size_t plen, copied;
 
@@ -1221,13 +1224,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 				break;
 			}
 		}
-		ceph_release_page_vector(pages, num_pages);
 
-		if (ret < 0) {
-			if (ret == -EBLOCKLISTED)
-				fsc->blocklisted = true;
-			break;
-		}
+		ceph_osdc_put_request(req);
 
 		if (off >= i_size || !more)
 			break;
@@ -1553,6 +1551,16 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 			break;
 		}
 
+		op = &req->r_ops[0];
+		if (!write && sparse) {
+			extent_cnt = __ceph_sparse_read_ext_count(inode, size);
+			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
+			if (ret) {
+				ceph_osdc_put_request(req);
+				break;
+			}
+		}
+
 		len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages);
 		if (len < 0) {
 			ceph_osdc_put_request(req);
@@ -1562,6 +1570,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		if (len != size)
 			osd_req_op_extent_update(req, 0, len);
 
+		osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
+
 		/*
 		 * To simplify error handling, allow AIO when IO within i_size
 		 * or IO can be satisfied by single OSD request.
@@ -1593,17 +1603,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 			req->r_mtime = mtime;
 		}
 
-		osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
-		op = &req->r_ops[0];
-		if (sparse) {
-			extent_cnt = __ceph_sparse_read_ext_count(inode, size);
-			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
-			if (ret) {
-				ceph_osdc_put_request(req);
-				break;
-			}
-		}
-
 		if (aio_req) {
 			aio_req->total_len += len;
 			aio_req->num_reqs++;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 219a2cc2bf3c..785fe489ef4b 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2800,12 +2800,11 @@ retry:
 
 	if (pos < 0) {
 		/*
-		 * A rename didn't occur, but somehow we didn't end up where
-		 * we thought we would. Throw a warning and try again.
+		 * The path is longer than PATH_MAX and this function
+		 * cannot ever succeed.  Creating paths that long is
+		 * possible with Ceph, but Linux cannot use them.
 		 */
-		pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n",
-			       pos);
-		goto retry;
+		return ERR_PTR(-ENAMETOOLONG);
 	}
 
 	*pbase = base;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index de03cd6eb86e..4344e1f11806 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -431,6 +431,8 @@ static int ceph_parse_mount_param(struct fs_context *fc,
 
 	switch (token) {
 	case Opt_snapdirname:
+		if (strlen(param->string) > NAME_MAX)
+			return invalfc(fc, "snapdirname too long");
 		kfree(fsopt->snapdir_name);
 		fsopt->snapdir_name = param->string;
 		param->string = NULL;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 9b1168eb77ab..b24afec24138 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1173,6 +1173,8 @@ EXPORT_SYMBOL(ceph_osdc_new_request);
 
 int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt)
 {
+	WARN_ON(op->op != CEPH_OSD_OP_SPARSE_READ);
+
 	op->extent.sparse_ext_cnt = cnt;
 	op->extent.sparse_ext = kmalloc_array(cnt,
 					      sizeof(*op->extent.sparse_ext),