nfs4: resend LAYOUTGET when there is a race that changes the seqid

commit 4f2e9dce upstream.

pnfs_layout_process will check the returned layout stateid against what
the kernel has in-core. If it turns out that the stateid we received is
older, then we should resend the LAYOUTGET instead of falling back to
MDS I/O.
Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

fs/nfs/pnfs.c

@@ -872,33 +872,38 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 
 	dprintk("--> %s\n", __func__);
 
-	lgp = kzalloc(sizeof(*lgp), gfp_flags);
-	if (lgp == NULL)
-		return NULL;
+	/*
+	 * Synchronously retrieve layout information from server and
+	 * store in lseg. If we race with a concurrent seqid morphing
+	 * op, then re-send the LAYOUTGET.
+	 */
+	do {
+		lgp = kzalloc(sizeof(*lgp), gfp_flags);
+		if (lgp == NULL)
+			return NULL;
+
+		i_size = i_size_read(ino);
+
+		lgp->args.minlength = PAGE_CACHE_SIZE;
+		if (lgp->args.minlength > range->length)
+			lgp->args.minlength = range->length;
+		if (range->iomode == IOMODE_READ) {
+			if (range->offset >= i_size)
+				lgp->args.minlength = 0;
+			else if (i_size - range->offset < lgp->args.minlength)
+				lgp->args.minlength = i_size - range->offset;
+		}
+		lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
+		lgp->args.range = *range;
+		lgp->args.type = server->pnfs_curr_ld->id;
+		lgp->args.inode = ino;
+		lgp->args.ctx = get_nfs_open_context(ctx);
+		lgp->gfp_flags = gfp_flags;
+		lgp->cred = lo->plh_lc_cred;
 
-	i_size = i_size_read(ino);
+		lseg = nfs4_proc_layoutget(lgp, gfp_flags);
+	} while (lseg == ERR_PTR(-EAGAIN));
 
-	lgp->args.minlength = PAGE_CACHE_SIZE;
-	if (lgp->args.minlength > range->length)
-		lgp->args.minlength = range->length;
-	if (range->iomode == IOMODE_READ) {
-		if (range->offset >= i_size)
-			lgp->args.minlength = 0;
-		else if (i_size - range->offset < lgp->args.minlength)
-			lgp->args.minlength = i_size - range->offset;
-	}
-	lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
-	lgp->args.range = *range;
-	lgp->args.type = server->pnfs_curr_ld->id;
-	lgp->args.inode = ino;
-	lgp->args.ctx = get_nfs_open_context(ctx);
-	lgp->gfp_flags = gfp_flags;
-	lgp->cred = lo->plh_lc_cred;
-
-	/* Synchronously retrieve layout information from server and
-	 * store in lseg.
-	 */
-	lseg = nfs4_proc_layoutget(lgp, gfp_flags);
 	if (IS_ERR(lseg)) {
 		switch (PTR_ERR(lseg)) {
 		case -ENOMEM:
@@ -1687,6 +1692,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		/* existing state ID, make sure the sequence number matches. */
 		if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
 			dprintk("%s forget reply due to sequence\n", __func__);
+			status = -EAGAIN;
 			goto out_forget_reply;
 		}
 		pnfs_set_layout_stateid(lo, &res->stateid, false);