Received-SPF: pass (google.com: best guess record for domain of linux-nfs-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   schumaker.anna@gmail.com
To:     bfields@redhat.com, linux-nfs@vger.kernel.org
Cc:     Anna.Schumaker@Netapp.com
Subject: [PATCH v2 2/4] NFSD: Add READ_PLUS data support
Date:   Fri, 14 Feb 2020 16:12:04 -0500
Message-Id: <20200214211206.407725-3-Anna.Schumaker@Netapp.com>
In-Reply-To: <20200214211206.407725-1-Anna.Schumaker@Netapp.com>
References: <20200214211206.407725-1-Anna.Schumaker@Netapp.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-nfs-owner@vger.kernel.org
Precedence: bulk

From: Anna Schumaker <Anna.Schumaker@Netapp.com>

This patch adds READ_PLUS support for returning a single
NFS4_CONTENT_DATA segment to the client. This is basically the same as
the READ operation, only with the extra information about data segments.

Note that Wireshark 3.0 will report "malformed packed" when trying to
decode NFS4_CONTENT_DATA segments. This is because the actual data is
encoded as a variable length array, which RFC 4506 says should start
with a 32-bit length value. Wireshark incorrectly expects length to be a
64-bit value instead.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfsd/nfs4proc.c | 17 +++++++++
 fs/nfsd/nfs4xdr.c  | 90 ++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 101 insertions(+), 6 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 0e75f7fb5fec..9643181591e3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2522,6 +2522,16 @@ static inline u32 nfsd4_read_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 	return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_read_plus_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	u32 maxcount = svc_max_payload(rqstp);
+	u32 rlen = min(op->u.read.rd_length, maxcount);
+	/* enough extra xdr space for encoding either a hole or data segment. */
+	u32 segments = 1 + 2 + 2;
+
+	return (op_encode_hdr_size + 2 + segments + XDR_QUADLEN(rlen)) * sizeof(__be32);
+}
+
 static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	u32 maxcount = 0, rlen = 0;
@@ -3058,6 +3068,13 @@ static const struct nfsd4_operation nfsd4_ops[] = {
 		.op_name = "OP_COPY",
 		.op_rsize_bop = nfsd4_copy_rsize,
 	},
+	[OP_READ_PLUS] = {
+		.op_func = nfsd4_read,
+		.op_release = nfsd4_read_release,
+		.op_name = "OP_READ_PLUS",
+		.op_rsize_bop = nfsd4_read_plus_rsize,
+		.op_get_currentstateid = nfsd4_get_readstateid,
+	},
 	[OP_SEEK] = {
 		.op_func = nfsd4_seek,
 		.op_name = "OP_SEEK",
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 45f0623f6488..8efb59d4fda4 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1957,7 +1957,7 @@ static const nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_LAYOUTSTATS]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_OFFLOAD_CANCEL]	= (nfsd4_dec)nfsd4_decode_offload_status,
 	[OP_OFFLOAD_STATUS]	= (nfsd4_dec)nfsd4_decode_offload_status,
-	[OP_READ_PLUS]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_READ_PLUS]		= (nfsd4_dec)nfsd4_decode_read,
 	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_CLONE]		= (nfsd4_dec)nfsd4_decode_clone,
@@ -3664,10 +3664,11 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 
 	if (nfserr)
 		xdr_truncate_encode(xdr, starting_len);
-
-	read->rd_length = maxcount;
-	*p++ = htonl(eof);
-	*p++ = htonl(maxcount);
+	else {
+		read->rd_length = maxcount;
+		*p++ = htonl(eof);
+		*p++ = htonl(maxcount);
+	}
 
 	return nfserr;
 }
@@ -4379,6 +4380,83 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr,
 		return nfserr_resource;
 	p = xdr_encode_hyper(p, os->count);
 	*p++ = cpu_to_be32(0);
+	return nfserr;
+}
+
+static __be32
+nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
+			    struct nfsd4_read *read,
+			    unsigned long maxcount,  u32 *eof)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	struct file *file = read->rd_nf->nf_file;
+	__be32 nfserr;
+	__be32 *p;
+
+	/* Content type, offset, byte count */
+	p = xdr_reserve_space(xdr, 4 + 8 + 4);
+	if (!p)
+		return nfserr_resource;
+	xdr_commit_encode(xdr);
+
+	if (file->f_op->splice_read &&
+	    test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags))
+		nfserr = nfsd4_encode_splice_read(resp, read, file, &maxcount, eof);
+	else
+		nfserr = nfsd4_encode_readv(resp, read, file, &maxcount, eof);
+
+	if (nfserr)
+		return nfserr;
+
+	*p++ = htonl(NFS4_CONTENT_DATA);
+	 p   = xdr_encode_hyper(p, read->rd_offset);
+	*p++ = htonl(maxcount);
+
+	read->rd_offset += maxcount;
+	read->rd_length  = (maxcount > 0) ? read->rd_length - maxcount : 0;
+	return nfserr;
+}
+
+static __be32
+nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr,
+		       struct nfsd4_read *read)
+{
+	unsigned long maxcount;
+	u32 eof;
+	struct xdr_stream *xdr = &resp->xdr;
+	struct file *file;
+	int starting_len = xdr->buf->len;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+	file = read->rd_nf->nf_file;
+
+	/* eof flag, segment count */
+	p = xdr_reserve_space(xdr, 4 + 4);
+	if (!p) {
+		WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags));
+		return nfserr_resource;
+	}
+	if (resp->xdr.buf->page_len &&
+	    test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) {
+		WARN_ON_ONCE(1);
+		return nfserr_resource;
+	}
+	xdr_commit_encode(xdr);
+
+	maxcount = svc_max_payload(resp->rqstp);
+	maxcount = min_t(unsigned long, maxcount,
+			 (xdr->buf->buflen - xdr->buf->len));
+	maxcount = min_t(unsigned long, maxcount, read->rd_length);
+
+	nfserr = nfsd4_encode_read_plus_data(resp, read, maxcount, &eof);
+	if (nfserr)
+		xdr_truncate_encode(xdr, starting_len);
+	else {
+		*p++ = htonl(eof);
+		*p++ = htonl(1);
+	}
 
 	return nfserr;
 }
@@ -4521,7 +4599,7 @@ static const nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_LAYOUTSTATS]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_OFFLOAD_CANCEL]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_OFFLOAD_STATUS]	= (nfsd4_enc)nfsd4_encode_offload_status,
-	[OP_READ_PLUS]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_READ_PLUS]		= (nfsd4_enc)nfsd4_encode_read_plus,
 	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_CLONE]		= (nfsd4_enc)nfsd4_encode_noop,
-- 
2.25.0