libceph: don't build request in ceph_osdc_new_request()

This patch moves the call to ceph_osdc_build_request() out of
ceph_osdc_new_request() and into its caller.

This is in order to defer formatting osd operation information into
the request message until just before request is started.

The only unusual (ab)user of ceph_osdc_build_request() is
ceph_writepages_start(), where the final length of write request may
change (downward) based on the current inode size or the oldest
snapshot context with dirty data for the inode.

The remaining callers don't change anything in the request after has
been built.

This means the ops array is now supplied by the caller.  It also
means there is no need to pass the mtime to ceph_osdc_new_request()
(it gets provided to ceph_osdc_build_request()).  And rather than
passing a do_sync flag, have the number of ops in the ops array
supplied imply adding a second STARTSYNC operation after the READ or
WRITE requested.

This and some of the patches that follow are related to having the
messenger (only) be responsible for filling the content of the
message header, as described here:
    http://tracker.ceph.com/issues/4589

Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

2 files changed, 36 insertions, 20 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index ae438d0..681463d 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -284,7 +284,9 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 		&ceph_inode_to_client(inode)->client->osdc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct page *page = list_entry(page_list->prev, struct page, lru);
+	struct ceph_vino vino;
 	struct ceph_osd_request *req;
+	struct ceph_osd_req_op op;
 	u64 off;
 	u64 len;
 	int i;
@@ -308,16 +310,17 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 	len = nr_pages << PAGE_CACHE_SHIFT;
 	dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages,
 	     off, len);
-
-	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode),
-				    off, &len,
-				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
-				    NULL, 0,
+	vino = ceph_vino(inode);
+	req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len,
+				    1, &op, CEPH_OSD_OP_READ,
+				    CEPH_OSD_FLAG_READ, NULL,
 				    ci->i_truncate_seq, ci->i_truncate_size,
-				    NULL, false);
+				    false);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	ceph_osdc_build_request(req, off, 1, &op, NULL, vino.snap, NULL);
+
 	/* build page vector */
 	nr_pages = calc_pages_for(0, len);
 	pages = kmalloc(sizeof(*pages) * nr_pages, GFP_NOFS);
@@ -736,6 +739,7 @@ retry:
 	last_snapc = snapc;
 
 	while (!done && index <= end) {
+		struct ceph_osd_req_op ops[2];
 		unsigned i;
 		int first;
 		pgoff_t next;
@@ -825,20 +829,22 @@ get_more_pages:
 
 			/* ok */
 			if (locked_pages == 0) {
+				struct ceph_vino vino;
+				int num_ops = do_sync ? 2 : 1;
+
 				/* prepare async write request */
 				offset = (u64) page_offset(page);
 				len = wsize;
+				vino = ceph_vino(inode);
+				/* BUG_ON(vino.snap != CEPH_NOSNAP); */
 				req = ceph_osdc_new_request(&fsc->client->osdc,
-					    &ci->i_layout,
-					    ceph_vino(inode),
-					    offset, &len,
+					    &ci->i_layout, vino, offset, &len,
+					    num_ops, ops,
 					    CEPH_OSD_OP_WRITE,
 					    CEPH_OSD_FLAG_WRITE |
 						    CEPH_OSD_FLAG_ONDISK,
-					    snapc, do_sync,
-					    ci->i_truncate_seq,
-					    ci->i_truncate_size,
-					    &inode->i_mtime, true);
+					    snapc, ci->i_truncate_seq,
+					    ci->i_truncate_size, true);
 
 				if (IS_ERR(req)) {
 					rc = PTR_ERR(req);
@@ -846,6 +852,10 @@ get_more_pages:
 					break;
 				}
 
+				ceph_osdc_build_request(req, offset,
+					num_ops, ops, snapc, vino.snap,
+					&inode->i_mtime);
+
 				req->r_data_out.type = CEPH_OSD_DATA_TYPE_PAGES;
 				req->r_data_out.length = len;
 				req->r_data_out.alignment = 0;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index aeafa67..3d6dcf2 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -475,14 +475,17 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_snap_context *snapc;
+	struct ceph_vino vino;
 	struct ceph_osd_request *req;
+	struct ceph_osd_req_op ops[2];
+	int num_ops = 1;
 	struct page **pages;
 	int num_pages;
 	long long unsigned pos;
 	u64 len;
 	int written = 0;
 	int flags;
-	int do_sync = 0;
 	int check_caps = 0;
 	int page_align, io_align;
 	unsigned long buf_align;
@@ -516,7 +519,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
 	if ((file->f_flags & (O_SYNC|O_DIRECT)) == 0)
 		flags |= CEPH_OSD_FLAG_ACK;
 	else
-		do_sync = 1;
+		num_ops++;	/* Also include a 'startsync' command. */
 
 	/*
 	 * we may need to do multiple writes here if we span an object
@@ -527,16 +530,19 @@ more:
 	buf_align = (unsigned long)data & ~PAGE_MASK;
 	len = left;
 
+	snapc = ci->i_snap_realm->cached_context;
+	vino = ceph_vino(inode);
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
-				    ceph_vino(inode), pos, &len,
-				    CEPH_OSD_OP_WRITE, flags,
-				    ci->i_snap_realm->cached_context,
-				    do_sync,
+				    vino, pos, &len, num_ops, ops,
+				    CEPH_OSD_OP_WRITE, flags, snapc,
 				    ci->i_truncate_seq, ci->i_truncate_size,
-				    &mtime, false);
+				    false);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	ceph_osdc_build_request(req, pos, num_ops, ops,
+				snapc, vino.snap, &mtime);
+
 	/* write from beginning of first page, regardless of io alignment */
 	page_align = file->f_flags & O_DIRECT ? buf_align : io_align;
 	num_pages = calc_pages_for(page_align, len);