Received-SPF: pass (google.com: domain of linux-nfs-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   schumaker.anna@gmail.com
To:     bfields@redhat.com, chuck.lever@oracle.com,
        linux-nfs@vger.kernel.org
Cc:     Anna.Schumaker@Netapp.com
Subject: [PATCH v4 1/5] SUNRPC/NFSD: Implement xdr_reserve_space_vec()
Date:   Mon, 17 Aug 2020 12:53:06 -0400
Message-Id: <20200817165310.354092-2-Anna.Schumaker@Netapp.com>
In-Reply-To: <20200817165310.354092-1-Anna.Schumaker@Netapp.com>
References: <20200817165310.354092-1-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>

Reserving space for a large READ payload requires special handling when
reserving space in the xdr buffer pages. One problem we can have is use
of the scratch buffer, which is used to get a pointer to a contiguous
region of data up to PAGE_SIZE. When using the scratch buffer, calls to
xdr_commit_encode() shift the data to it's proper alignment in the xdr
buffer. If we've reserved several pages in a vector, then this could
potentially invalidate earlier pointers and result in incorrect READ
data being sent to the client.

I get around this by looking at the amount of space left in the current
page, and never reserve more than that for each entry in the read
vector. This lets us place data directly where it needs to go in the
buffer pages.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfsd/nfs4xdr.c          | 28 +++---------------------
 include/linux/sunrpc/xdr.h |  2 ++
 net/sunrpc/xdr.c           | 45 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 25 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 996ac01ee977..6a1c0a7fae05 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3584,36 +3584,14 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 {
 	struct xdr_stream *xdr = &resp->xdr;
 	u32 eof;
-	int v;
 	int starting_len = xdr->buf->len - 8;
-	long len;
-	int thislen;
 	__be32 nfserr;
 	__be32 tmp;
-	__be32 *p;
 	int pad;
 
-	/*
-	 * svcrdma requires every READ payload to start somewhere
-	 * in xdr->pages.
-	 */
-	if (xdr->iov == xdr->buf->head) {
-		xdr->iov = NULL;
-		xdr->end = xdr->p;
-	}
-
-	len = maxcount;
-	v = 0;
-	while (len) {
-		thislen = min_t(long, len, PAGE_SIZE);
-		p = xdr_reserve_space(xdr, thislen);
-		WARN_ON_ONCE(!p);
-		resp->rqstp->rq_vec[v].iov_base = p;
-		resp->rqstp->rq_vec[v].iov_len = thislen;
-		v++;
-		len -= thislen;
-	}
-	read->rd_vlen = v;
+	read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount);
+	if (read->rd_vlen < 0)
+		return nfserr_resource;
 
 	nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset,
 			    resp->rqstp->rq_vec, read->rd_vlen, &maxcount,
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 22c207b2425f..bac459584dd0 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -234,6 +234,8 @@ typedef int	(*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
+extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec,
+		size_t nbytes);
 extern void xdr_commit_encode(struct xdr_stream *xdr);
 extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len);
 extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index be11d672b5b9..6dfe5dc8b35f 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -648,6 +648,51 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
 }
 EXPORT_SYMBOL_GPL(xdr_reserve_space);
 
+
+/**
+ * xdr_reserve_space_vec - Reserves a large amount of buffer space for sending
+ * @xdr: pointer to xdr_stream
+ * @vec: pointer to a kvec array
+ * @nbytes: number of bytes to reserve
+ *
+ * Reserves enough buffer space to encode 'nbytes' of data and stores the
+ * pointers in 'vec'. The size argument passed to xdr_reserve_space() is
+ * determined based on the number of bytes remaining in the current page to
+ * avoid invalidating iov_base pointers when xdr_commit_encode() is called.
+ */
+int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes)
+{
+	int thislen;
+	int v = 0;
+	__be32 *p;
+
+	/*
+	 * svcrdma requires every READ payload to start somewhere
+	 * in xdr->pages.
+	 */
+	if (xdr->iov == xdr->buf->head) {
+		xdr->iov = NULL;
+		xdr->end = xdr->p;
+	}
+
+	while (nbytes) {
+		thislen = xdr->buf->page_len % PAGE_SIZE;
+		thislen = min_t(size_t, nbytes, PAGE_SIZE - thislen);
+
+		p = xdr_reserve_space(xdr, thislen);
+		if (!p)
+			return -EIO;
+
+		vec[v].iov_base = p;
+		vec[v].iov_len = thislen;
+		v++;
+		nbytes -= thislen;
+	}
+
+	return v;
+}
+EXPORT_SYMBOL_GPL(xdr_reserve_space_vec);
+
 /**
  * xdr_truncate_encode - truncate an encode buffer
  * @xdr: pointer to xdr_stream
-- 
2.28.0