pnfs: allow splicing pre-encoded pages into the layoutcommit args

Currently there is no XDR buffer space allocated for the per-layout driver
layoutcommit payload, which leads to server buffer overflows in the
blocklayout driver even under simple workloads.  As we can't do per-layout
sizes for XDR operations we'll have to splice a previously encoded list
of pages into the XDR stream, similar to how we handle ACL buffers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>

3 files changed, 30 insertions, 7 deletions

diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e13b59d8d9aa..f2cd957adb90 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -395,7 +395,10 @@ static int nfs4_stat_to_errno(int);
 				2 /* last byte written */ + \
 				1 /* nt_timechanged (false) */ + \
 				1 /* layoutupdate4 layout type */ + \
-				1 /* NULL filelayout layoutupdate4 payload */)
+				1 /* layoutupdate4 opaqueue len */)
+				  /* the actual content of layoutupdate4 should
+				     be allocated by drivers and spliced in
+				     using xdr_write_pages */
 #define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3)
 #define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \
 				encode_stateid_maxsz + \
@@ -1990,7 +1993,7 @@ encode_layoutget(struct xdr_stream *xdr,
 static int
 encode_layoutcommit(struct xdr_stream *xdr,
 		    struct inode *inode,
-		    const struct nfs4_layoutcommit_args *args,
+		    struct nfs4_layoutcommit_args *args,
 		    struct compound_hdr *hdr)
 {
 	__be32 *p;
@@ -2011,11 +2014,16 @@ encode_layoutcommit(struct xdr_stream *xdr,
 	*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
 	*p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
 
-	if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit)
+	if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) {
 		NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
 			NFS_I(inode)->layout, xdr, args);
-	else
-		encode_uint32(xdr, 0); /* no layout-type payload */
+	} else {
+		encode_uint32(xdr, args->layoutupdate_len);
+		if (args->layoutupdate_pages) {
+			xdr_write_pages(xdr, args->layoutupdate_pages, 0,
+					args->layoutupdate_len);
+		}
+	}
 
 	return 0;
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 57b5728e0b8e..8827ab130ed3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1854,6 +1854,7 @@ void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 int
 pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 	struct nfs4_layoutcommit_data *data;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	loff_t end_pos;
@@ -1904,6 +1905,20 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	data->args.lastbytewritten = end_pos - 1;
 	data->res.server = NFS_SERVER(inode);
 
+	if (ld->prepare_layoutcommit) {
+		status = ld->prepare_layoutcommit(&data->args);
+		if (status) {
+			spin_lock(&inode->i_lock);
+			if (end_pos < nfsi->layout->plh_lwb)
+				nfsi->layout->plh_lwb = end_pos;
+			spin_unlock(&inode->i_lock);
+			put_rpccred(data->cred);
+			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
+			goto clear_layoutcommitting;
+		}
+	}
+
+
 	status = nfs4_proc_layoutcommit(data, sync);
 out:
 	if (status)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 1dd8a5e96c9f..8835b5a320cc 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -128,8 +128,8 @@ struct pnfs_layoutdriver_type {
 				     const struct nfs4_layoutreturn_args *args);
 
 	void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data);
-
-	void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid,
+	int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args);
+	void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo,
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutcommit_args *args);
 };