svcrdma: Don't overrun the SGE array in svc_rdma_send_ctxt

Receive buffers are always the same size, but each Send WR has a
variable number of SGEs, based on the contents of the xdr_buf being
sent.

While assembling a Send WR, keep track of the number of SGEs so that
we don't exceed the device's maximum, or walk off the end of the
Send SGE array.

For now the Send path just fails if it exceeds the maximum.

The current logic in svc_rdma_accept bases the maximum number of
Send SGEs on the largest NFS request that can be sent or received.
In the transport layer, the limit is actually based on the
capabilities of the underlying device, not on properties of the
Upper Layer Protocol.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

3 files changed, 33 insertions, 25 deletions

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index d3e2bb331264..bfb8824e31e1 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -96,7 +96,7 @@ struct svcxprt_rdma {
 	struct rdma_cm_id    *sc_cm_id;		/* RDMA connection id */
 	struct list_head     sc_accept_q;	/* Conn. waiting accept */
 	int		     sc_ord;		/* RDMA read limit */
-	int                  sc_max_sge;
+	int                  sc_max_send_sges;
 	bool		     sc_snd_w_inv;	/* OK to use Send With Invalidate */
 
 	atomic_t             sc_sq_avail;	/* SQEs ready to be consumed */
@@ -158,17 +158,14 @@ struct svc_rdma_recv_ctxt {
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
-enum {
-	RPCRDMA_MAX_SGES	= 1 + (RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE),
-};
-
 struct svc_rdma_send_ctxt {
 	struct list_head	sc_list;
 	struct ib_send_wr	sc_send_wr;
 	struct ib_cqe		sc_cqe;
 	int			sc_page_count;
+	int			sc_cur_sge_no;
 	struct page		*sc_pages[RPCSVC_MAXPAGES];
-	struct ib_sge		sc_sges[RPCRDMA_MAX_SGES];
+	struct ib_sge		sc_sges[];
 };
 
 /* svc_rdma_backchannel.c */
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index b286d6a6e429..53d8db6bfaf2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -127,9 +127,12 @@ static struct svc_rdma_send_ctxt *
 svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_send_ctxt *ctxt;
+	size_t size;
 	int i;
 
-	ctxt = kmalloc(sizeof(*ctxt), GFP_KERNEL);
+	size = sizeof(*ctxt);
+	size += rdma->sc_max_send_sges * sizeof(struct ib_sge);
+	ctxt = kmalloc(size, GFP_KERNEL);
 	if (!ctxt)
 		return NULL;
 
@@ -138,7 +141,7 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 	ctxt->sc_send_wr.wr_cqe = &ctxt->sc_cqe;
 	ctxt->sc_send_wr.sg_list = ctxt->sc_sges;
 	ctxt->sc_send_wr.send_flags = IB_SEND_SIGNALED;
-	for (i = 0; i < ARRAY_SIZE(ctxt->sc_sges); i++)
+	for (i = 0; i < rdma->sc_max_send_sges; i++)
 		ctxt->sc_sges[i].lkey = rdma->sc_pd->local_dma_lkey;
 	return ctxt;
 }
@@ -482,7 +485,6 @@ static u32 svc_rdma_get_inv_rkey(__be32 *rdma_argp,
 
 static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma,
 				 struct svc_rdma_send_ctxt *ctxt,
-				 unsigned int sge_no,
 				 struct page *page,
 				 unsigned long offset,
 				 unsigned int len)
@@ -494,8 +496,8 @@ static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma,
 	if (ib_dma_mapping_error(dev, dma_addr))
 		goto out_maperr;
 
-	ctxt->sc_sges[sge_no].addr = dma_addr;
-	ctxt->sc_sges[sge_no].length = len;
+	ctxt->sc_sges[ctxt->sc_cur_sge_no].addr = dma_addr;
+	ctxt->sc_sges[ctxt->sc_cur_sge_no].length = len;
 	ctxt->sc_send_wr.num_sge++;
 	return 0;
 
@@ -509,11 +511,10 @@ out_maperr:
  */
 static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
 				struct svc_rdma_send_ctxt *ctxt,
-				unsigned int sge_no,
 				unsigned char *base,
 				unsigned int len)
 {
-	return svc_rdma_dma_map_page(rdma, ctxt, sge_no, virt_to_page(base),
+	return svc_rdma_dma_map_page(rdma, ctxt, virt_to_page(base),
 				     offset_in_page(base), len);
 }
 
@@ -535,7 +536,8 @@ int svc_rdma_map_reply_hdr(struct svcxprt_rdma *rdma,
 {
 	ctxt->sc_pages[0] = virt_to_page(rdma_resp);
 	ctxt->sc_page_count++;
-	return svc_rdma_dma_map_page(rdma, ctxt, 0, ctxt->sc_pages[0], 0, len);
+	ctxt->sc_cur_sge_no = 0;
+	return svc_rdma_dma_map_page(rdma, ctxt, ctxt->sc_pages[0], 0, len);
 }
 
 /* Load the xdr_buf into the ctxt's sge array, and DMA map each
@@ -547,16 +549,16 @@ static int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *ctxt,
 				  struct xdr_buf *xdr, __be32 *wr_lst)
 {
-	unsigned int len, sge_no, remaining;
+	unsigned int len, remaining;
 	unsigned long page_off;
 	struct page **ppages;
 	unsigned char *base;
 	u32 xdr_pad;
 	int ret;
 
-	sge_no = 1;
-
-	ret = svc_rdma_dma_map_buf(rdma, ctxt, sge_no++,
+	if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
+		return -EIO;
+	ret = svc_rdma_dma_map_buf(rdma, ctxt,
 				   xdr->head[0].iov_base,
 				   xdr->head[0].iov_len);
 	if (ret < 0)
@@ -586,8 +588,10 @@ static int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 	while (remaining) {
 		len = min_t(u32, PAGE_SIZE - page_off, remaining);
 
-		ret = svc_rdma_dma_map_page(rdma, ctxt, sge_no++,
-					    *ppages++, page_off, len);
+		if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
+			return -EIO;
+		ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++,
+					    page_off, len);
 		if (ret < 0)
 			return ret;
 
@@ -599,7 +603,9 @@ static int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 	len = xdr->tail[0].iov_len;
 tail:
 	if (len) {
-		ret = svc_rdma_dma_map_buf(rdma, ctxt, sge_no++, base, len);
+		if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
+			return -EIO;
+		ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 3de81735a6cc..e9535a66bab0 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -476,8 +476,13 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 
 	/* Qualify the transport resource defaults with the
 	 * capabilities of this particular device */
-	newxprt->sc_max_sge = min((size_t)dev->attrs.max_sge,
-				  (size_t)RPCSVC_MAXPAGES);
+	newxprt->sc_max_send_sges = dev->attrs.max_sge;
+	/* transport hdr, head iovec, one page list entry, tail iovec */
+	if (newxprt->sc_max_send_sges < 4) {
+		pr_err("svcrdma: too few Send SGEs available (%d)\n",
+		       newxprt->sc_max_send_sges);
+		goto errout;
+	}
 	newxprt->sc_max_req_size = svcrdma_max_req_size;
 	newxprt->sc_max_requests = svcrdma_max_requests;
 	newxprt->sc_max_bc_requests = svcrdma_max_bc_requests;
@@ -525,7 +530,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	qp_attr.cap.max_rdma_ctxs = ctxts;
 	qp_attr.cap.max_send_wr = newxprt->sc_sq_depth - ctxts;
 	qp_attr.cap.max_recv_wr = rq_depth;
-	qp_attr.cap.max_send_sge = newxprt->sc_max_sge;
+	qp_attr.cap.max_send_sge = newxprt->sc_max_send_sges;
 	qp_attr.cap.max_recv_sge = 1;
 	qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
 	qp_attr.qp_type = IB_QPT_RC;
@@ -586,7 +591,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	dprintk("    local address   : %pIS:%u\n", sap, rpc_get_port(sap));
 	sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
 	dprintk("    remote address  : %pIS:%u\n", sap, rpc_get_port(sap));
-	dprintk("    max_sge         : %d\n", newxprt->sc_max_sge);
+	dprintk("    max_sge         : %d\n", newxprt->sc_max_send_sges);
 	dprintk("    sq_depth        : %d\n", newxprt->sc_sq_depth);
 	dprintk("    rdma_rw_ctxs    : %d\n", ctxts);
 	dprintk("    max_requests    : %d\n", newxprt->sc_max_requests);