4 files changed, 79 insertions, 77 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 70f7cb383228..cb6f5482d203 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -158,7 +158,6 @@ struct hv_netvsc_packet {
 	u8 cp_partial; /* partial copy into send buffer */
 
 	u8 rmsg_size; /* RNDIS header and PPI size */
-	u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */
 	u8 page_buf_cnt;
 
 	u16 q_idx;
@@ -893,6 +892,18 @@ struct nvsp_message {
 				 sizeof(struct nvsp_message))
 #define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor)
 
+/* Maximum # of contiguous data ranges that can make up a trasmitted packet.
+ * Typically it's the max SKB fragments plus 2 for the rndis packet and the
+ * linear portion of the SKB. But if MAX_SKB_FRAGS is large, the value may
+ * need to be limited to MAX_PAGE_BUFFER_COUNT, which is the max # of entries
+ * in a GPA direct packet sent to netvsp over VMBus.
+ */
+#if MAX_SKB_FRAGS + 2 < MAX_PAGE_BUFFER_COUNT
+#define MAX_DATA_RANGES (MAX_SKB_FRAGS + 2)
+#else
+#define MAX_DATA_RANGES MAX_PAGE_BUFFER_COUNT
+#endif
+
 /* Estimated requestor size:
  * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size
  */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index d6f5b9ea3109..720104661d7f 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -953,8 +953,7 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		     + pend_size;
 	int i;
 	u32 padding = 0;
-	u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt :
-		packet->page_buf_cnt;
+	u32 page_count = packet->cp_partial ? 1 : packet->page_buf_cnt;
 	u32 remain;
 
 	/* Add padding */
@@ -1055,6 +1054,42 @@ static int netvsc_dma_map(struct hv_device *hv_dev,
 	return 0;
 }
 
+/* Build an "array" of mpb entries describing the data to be transferred
+ * over VMBus. After the desc header fields, each "array" entry is variable
+ * size, and each entry starts after the end of the previous entry. The
+ * "offset" and "len" fields for each entry imply the size of the entry.
+ *
+ * The pfns are in HV_HYP_PAGE_SIZE, because all communication with Hyper-V
+ * uses that granularity, even if the system page size of the guest is larger.
+ * Each entry in the input "pb" array must describe a contiguous range of
+ * guest physical memory so that the pfns are sequential if the range crosses
+ * a page boundary. The offset field must be < HV_HYP_PAGE_SIZE.
+ */
+static inline void netvsc_build_mpb_array(struct hv_page_buffer *pb,
+				u32 page_buffer_count,
+				struct vmbus_packet_mpb_array *desc,
+				u32 *desc_size)
+{
+	struct hv_mpb_array *mpb_entry = &desc->range;
+	int i, j;
+
+	for (i = 0; i < page_buffer_count; i++) {
+		u32 offset = pb[i].offset;
+		u32 len = pb[i].len;
+
+		mpb_entry->offset = offset;
+		mpb_entry->len = len;
+
+		for (j = 0; j < HVPFN_UP(offset + len); j++)
+			mpb_entry->pfn_array[j] = pb[i].pfn + j;
+
+		mpb_entry = (struct hv_mpb_array *)&mpb_entry->pfn_array[j];
+	}
+
+	desc->rangecount = page_buffer_count;
+	*desc_size = (char *)mpb_entry - (char *)desc;
+}
+
 static inline int netvsc_send_pkt(
 	struct hv_device *device,
 	struct hv_netvsc_packet *packet,
@@ -1097,8 +1132,11 @@ static inline int netvsc_send_pkt(
 
 	packet->dma_range = NULL;
 	if (packet->page_buf_cnt) {
+		struct vmbus_channel_packet_page_buffer desc;
+		u32 desc_size;
+
 		if (packet->cp_partial)
-			pb += packet->rmsg_pgcnt;
+			pb++;
 
 		ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb);
 		if (ret) {
@@ -1106,11 +1144,12 @@ static inline int netvsc_send_pkt(
 			goto exit;
 		}
 
-		ret = vmbus_sendpacket_pagebuffer(out_channel,
-						  pb, packet->page_buf_cnt,
-						  &nvmsg, sizeof(nvmsg),
-						  req_id);
-
+		netvsc_build_mpb_array(pb, packet->page_buf_cnt,
+				(struct vmbus_packet_mpb_array *)&desc,
+				 &desc_size);
+		ret = vmbus_sendpacket_mpb_desc(out_channel,
+				(struct vmbus_packet_mpb_array *)&desc,
+				desc_size, &nvmsg, sizeof(nvmsg), req_id);
 		if (ret)
 			netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 	} else {
@@ -1259,7 +1298,7 @@ int netvsc_send(struct net_device *ndev,
 		packet->send_buf_index = section_index;
 
 		if (packet->cp_partial) {
-			packet->page_buf_cnt -= packet->rmsg_pgcnt;
+			packet->page_buf_cnt--;
 			packet->total_data_buflen = msd_len + packet->rmsg_size;
 		} else {
 			packet->page_buf_cnt = 0;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c51b318b8a72..d8b169ac0343 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -326,43 +326,10 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	return txq;
 }
 
-static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len,
-		       struct hv_page_buffer *pb)
-{
-	int j = 0;
-
-	hvpfn += offset >> HV_HYP_PAGE_SHIFT;
-	offset = offset & ~HV_HYP_PAGE_MASK;
-
-	while (len > 0) {
-		unsigned long bytes;
-
-		bytes = HV_HYP_PAGE_SIZE - offset;
-		if (bytes > len)
-			bytes = len;
-		pb[j].pfn = hvpfn;
-		pb[j].offset = offset;
-		pb[j].len = bytes;
-
-		offset += bytes;
-		len -= bytes;
-
-		if (offset == HV_HYP_PAGE_SIZE && len) {
-			hvpfn++;
-			offset = 0;
-			j++;
-		}
-	}
-
-	return j + 1;
-}
-
 static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 			   struct hv_netvsc_packet *packet,
 			   struct hv_page_buffer *pb)
 {
-	u32 slots_used = 0;
-	char *data = skb->data;
 	int frags = skb_shinfo(skb)->nr_frags;
 	int i;
 
@@ -371,28 +338,27 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 	 * 2. skb linear data
 	 * 3. skb fragment data
 	 */
-	slots_used += fill_pg_buf(virt_to_hvpfn(hdr),
-				  offset_in_hvpage(hdr),
-				  len,
-				  &pb[slots_used]);
 
+	pb[0].offset = offset_in_hvpage(hdr);
+	pb[0].len = len;
+	pb[0].pfn = virt_to_hvpfn(hdr);
 	packet->rmsg_size = len;
-	packet->rmsg_pgcnt = slots_used;
 
-	slots_used += fill_pg_buf(virt_to_hvpfn(data),
-				  offset_in_hvpage(data),
-				  skb_headlen(skb),
-				  &pb[slots_used]);
+	pb[1].offset = offset_in_hvpage(skb->data);
+	pb[1].len = skb_headlen(skb);
+	pb[1].pfn = virt_to_hvpfn(skb->data);
 
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+		struct hv_page_buffer *cur_pb = &pb[i + 2];
+		u64 pfn = page_to_hvpfn(skb_frag_page(frag));
+		u32 offset = skb_frag_off(frag);
 
-		slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)),
-					  skb_frag_off(frag),
-					  skb_frag_size(frag),
-					  &pb[slots_used]);
+		cur_pb->offset = offset_in_hvpage(offset);
+		cur_pb->len = skb_frag_size(frag);
+		cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT);
 	}
-	return slots_used;
+	return frags + 2;
 }
 
 static int count_skb_frag_slots(struct sk_buff *skb)
@@ -483,7 +449,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
 	struct net_device *vf_netdev;
 	u32 rndis_msg_size;
 	u32 hash;
-	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
+	struct hv_page_buffer pb[MAX_DATA_RANGES];
 
 	/* If VF is present and up then redirect packets to it.
 	 * Skip the VF if it is marked down or has no carrier.
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 82747dfacd70..9e73959e61ee 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -225,8 +225,7 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 				  struct rndis_request *req)
 {
 	struct hv_netvsc_packet *packet;
-	struct hv_page_buffer page_buf[2];
-	struct hv_page_buffer *pb = page_buf;
+	struct hv_page_buffer pb;
 	int ret;
 
 	/* Setup the packet to send it */
@@ -235,27 +234,14 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 	packet->total_data_buflen = req->request_msg.msg_len;
 	packet->page_buf_cnt = 1;
 
-	pb[0].pfn = virt_to_phys(&req->request_msg) >>
-					HV_HYP_PAGE_SHIFT;
-	pb[0].len = req->request_msg.msg_len;
-	pb[0].offset = offset_in_hvpage(&req->request_msg);
-
-	/* Add one page_buf when request_msg crossing page boundary */
-	if (pb[0].offset + pb[0].len > HV_HYP_PAGE_SIZE) {
-		packet->page_buf_cnt++;
-		pb[0].len = HV_HYP_PAGE_SIZE -
-			pb[0].offset;
-		pb[1].pfn = virt_to_phys((void *)&req->request_msg
-			+ pb[0].len) >> HV_HYP_PAGE_SHIFT;
-		pb[1].offset = 0;
-		pb[1].len = req->request_msg.msg_len -
-			pb[0].len;
-	}
+	pb.pfn = virt_to_phys(&req->request_msg) >> HV_HYP_PAGE_SHIFT;
+	pb.len = req->request_msg.msg_len;
+	pb.offset = offset_in_hvpage(&req->request_msg);
 
 	trace_rndis_send(dev->ndev, 0, &req->request_msg);
 
 	rcu_read_lock_bh();
-	ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL, false);
+	ret = netvsc_send(dev->ndev, packet, NULL, &pb, NULL, false);
 	rcu_read_unlock_bh();
 
 	return ret;