vmbus: introduce in-place packet iterator

This is mostly just a refactoring of previous functions
(get_pkt_next_raw, put_pkt_raw and commit_rd_index) to make it easier
to use for other drivers and NAPI.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/hv/ring_buffer.c

@@ -32,6 +32,8 @@
 
 #include "hyperv_vmbus.h"
 
+#define VMBUS_PKT_TRAILER	8
+
 /*
  * When we write to the ring buffer, check if the host needs to
  * be signaled. Here is the details of this protocol:
@@ -336,6 +338,12 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 	return 0;
 }
 
+static inline void
+init_cached_read_index(struct hv_ring_buffer_info *rbi)
+{
+	rbi->cached_read_index = rbi->ring_buffer->read_index;
+}
+
 int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
 		       u64 *requestid, bool raw)
@@ -366,7 +374,8 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 		return ret;
 	}
 
-	init_cached_read_index(channel);
+	init_cached_read_index(inring_info);
+
 	next_read_location = hv_get_next_read_location(inring_info);
 	next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc,
 						    sizeof(desc),
@@ -410,3 +419,86 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 
 	return ret;
 }
+
+/*
+ * Determine number of bytes available in ring buffer after
+ * the current iterator (priv_read_index) location.
+ *
+ * This is similar to hv_get_bytes_to_read but with private
+ * read index instead.
+ */
+static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
+{
+	u32 priv_read_loc = rbi->priv_read_index;
+	u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index);
+
+	if (write_loc >= priv_read_loc)
+		return write_loc - priv_read_loc;
+	else
+		return (rbi->ring_datasize - priv_read_loc) + write_loc;
+}
+
+/*
+ * Get first vmbus packet from ring buffer after read_index
+ *
+ * If ring buffer is empty, returns NULL and no other action needed.
+ */
+struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+	/* set state for later hv_signal_on_read() */
+	init_cached_read_index(rbi);
+
+	if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
+		return NULL;
+
+	return hv_get_ring_buffer(rbi) + rbi->priv_read_index;
+}
+EXPORT_SYMBOL_GPL(hv_pkt_iter_first);
+
+/*
+ * Get next vmbus packet from ring buffer.
+ *
+ * Advances the current location (priv_read_index) and checks for more
+ * data. If the end of the ring buffer is reached, then return NULL.
+ */
+struct vmpacket_descriptor *
+__hv_pkt_iter_next(struct vmbus_channel *channel,
+		   const struct vmpacket_descriptor *desc)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+	u32 packetlen = desc->len8 << 3;
+	u32 dsize = rbi->ring_datasize;
+
+	/* bump offset to next potential packet */
+	rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
+	if (rbi->priv_read_index >= dsize)
+		rbi->priv_read_index -= dsize;
+
+	/* more data? */
+	if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
+		return NULL;
+	else
+		return hv_get_ring_buffer(rbi) + rbi->priv_read_index;
+}
+EXPORT_SYMBOL_GPL(__hv_pkt_iter_next);
+
+/*
+ * Update host ring buffer after iterating over packets.
+ */
+void hv_pkt_iter_close(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+	/*
+	 * Make sure all reads are done before we update the read index since
+	 * the writer may start writing to the read area once the read index
+	 * is updated.
+	 */
+	virt_rmb();
+	rbi->ring_buffer->read_index = rbi->priv_read_index;
+
+	hv_signal_on_read(channel);
+}
+EXPORT_SYMBOL_GPL(hv_pkt_iter_close);

drivers/net/hyperv/netvsc.c

@@ -647,14 +647,11 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 static void netvsc_send_completion(struct netvsc_device *net_device,
 				   struct vmbus_channel *incoming_channel,
 				   struct hv_device *device,
-				   struct vmpacket_descriptor *packet)
+				   const struct vmpacket_descriptor *desc)
 {
-	struct nvsp_message *nvsp_packet;
+	struct nvsp_message *nvsp_packet = hv_pkt_data(desc);
 	struct net_device *ndev = hv_get_drvdata(device);
 
-	nvsp_packet = (struct nvsp_message *)((unsigned long)packet +
-					      (packet->offset8 << 3));
-
 	switch (nvsp_packet->hdr.msg_type) {
 	case NVSP_MSG_TYPE_INIT_COMPLETE:
 	case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE:
@@ -668,7 +665,7 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 
 	case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE:
 		netvsc_send_tx_complete(net_device, incoming_channel,
-					device, packet);
+					device, desc);
 		break;
 
 	default:
@@ -1071,9 +1068,11 @@ static void netvsc_receive(struct net_device *ndev,
 		   struct net_device_context *net_device_ctx,
 		   struct hv_device *device,
 		   struct vmbus_channel *channel,
-		   struct vmtransfer_page_packet_header *vmxferpage_packet,
+		   const struct vmpacket_descriptor *desc,
 		   struct nvsp_message *nvsp)
 {
+	const struct vmtransfer_page_packet_header *vmxferpage_packet
+		= container_of(desc, const struct vmtransfer_page_packet_header, d);
 	char *recv_buf = net_device->recv_buf;
 	u32 status = NVSP_STAT_SUCCESS;
 	int i;
@@ -1185,12 +1184,10 @@ static void netvsc_process_raw_pkt(struct hv_device *device,
 				   struct netvsc_device *net_device,
 				   struct net_device *ndev,
 				   u64 request_id,
-				   struct vmpacket_descriptor *desc)
+				   const struct vmpacket_descriptor *desc)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct nvsp_message *nvmsg
-		= (struct nvsp_message *)((unsigned long)desc
-					  + (desc->offset8 << 3));
+	struct nvsp_message *nvmsg = hv_pkt_data(desc);
 
 	switch (desc->type) {
 	case VM_PKT_COMP:
@@ -1199,9 +1196,7 @@ static void netvsc_process_raw_pkt(struct hv_device *device,
 
 	case VM_PKT_DATA_USING_XFER_PAGES:
 		netvsc_receive(ndev, net_device, net_device_ctx,
-			       device, channel,
-			       (struct vmtransfer_page_packet_header *)desc,
-			       nvmsg);
+			       device, channel, desc, nvmsg);
 		break;
 
 	case VM_PKT_DATA_INBAND:
@@ -1223,7 +1218,6 @@ void netvsc_channel_cb(void *context)
 	struct netvsc_device *net_device;
 	struct vmpacket_descriptor *desc;
 	struct net_device *ndev;
-	bool need_to_commit = false;
 
 	if (channel->primary_channel != NULL)
 		device = channel->primary_channel->device_obj;
@@ -1239,20 +1233,12 @@ void netvsc_channel_cb(void *context)
 	    netvsc_channel_idle(net_device, q_idx))
 		return;
 
-	/* commit_rd_index() -> hv_signal_on_read() needs this. */
-	init_cached_read_index(channel);
-
-	while ((desc = get_next_pkt_raw(channel)) != NULL) {
+	foreach_vmbus_pkt(desc, channel) {
 		netvsc_process_raw_pkt(device, channel, net_device,
 				       ndev, desc->trans_id, desc);
 
-		put_pkt_raw(channel, desc);
-		need_to_commit = true;
 	}
 
-	if (need_to_commit)
-		commit_rd_index(channel);
-
 	netvsc_chk_recv_comp(net_device, channel, q_idx);
 }
 

include/linux/hyperv.h

@@ -1504,14 +1504,6 @@ static inline  void hv_signal_on_read(struct vmbus_channel *channel)
 	return;
 }
 
-static inline void
-init_cached_read_index(struct vmbus_channel *channel)
-{
-	struct hv_ring_buffer_info *rbi = &channel->inbound;
-
-	rbi->cached_read_index = rbi->ring_buffer->read_index;
-}
-
 /*
  * Mask off host interrupt callback notifications
  */
@@ -1545,76 +1537,48 @@ static inline u32 hv_end_read(struct hv_ring_buffer_info *rbi)
 /*
  * An API to support in-place processing of incoming VMBUS packets.
  */
-#define VMBUS_PKT_TRAILER	8
 
-static inline struct vmpacket_descriptor *
-get_next_pkt_raw(struct vmbus_channel *channel)
+/* Get data payload associated with descriptor */
+static inline void *hv_pkt_data(const struct vmpacket_descriptor *desc)
 {
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 priv_read_loc = ring_info->priv_read_index;
-	void *ring_buffer = hv_get_ring_buffer(ring_info);
-	u32 dsize = ring_info->ring_datasize;
-	/*
-	 * delta is the difference between what is available to read and
-	 * what was already consumed in place. We commit read index after
-	 * the whole batch is processed.
-	 */
-	u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ?
-		priv_read_loc - ring_info->ring_buffer->read_index :
-		(dsize - ring_info->ring_buffer->read_index) + priv_read_loc;
-	u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta);
-
-	if (bytes_avail_toread < sizeof(struct vmpacket_descriptor))
-		return NULL;
-
-	return ring_buffer + priv_read_loc;
+	return (void *)((unsigned long)desc + (desc->offset8 << 3));
 }
 
-/*
- * A helper function to step through packets "in-place"
- * This API is to be called after each successful call
- * get_next_pkt_raw().
- */
-static inline void put_pkt_raw(struct vmbus_channel *channel,
-				struct vmpacket_descriptor *desc)
+/* Get data size associated with descriptor */
+static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc)
 {
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 packetlen = desc->len8 << 3;
-	u32 dsize = ring_info->ring_datasize;
-
-	/*
-	 * Include the packet trailer.
-	 */
-	ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
-	ring_info->priv_read_index %= dsize;
+	return (desc->len8 << 3) - (desc->offset8 << 3);
 }
 
+
+struct vmpacket_descriptor *
+hv_pkt_iter_first(struct vmbus_channel *channel);
+
+struct vmpacket_descriptor *
+__hv_pkt_iter_next(struct vmbus_channel *channel,
+		   const struct vmpacket_descriptor *pkt);
+
+void hv_pkt_iter_close(struct vmbus_channel *channel);
+
 /*
- * This call commits the read index and potentially signals the host.
- * Here is the pattern for using the "in-place" consumption APIs:
- *
- * init_cached_read_index();
- *
- * while (get_next_pkt_raw() {
- *	process the packet "in-place";
- *	put_pkt_raw();
- * }
- * if (packets processed in place)
- *	commit_rd_index();
- */
-static inline void commit_rd_index(struct vmbus_channel *channel)
-{
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	/*
-	 * Make sure all reads are done before we update the read index since
-	 * the writer may start writing to the read area once the read index
-	 * is updated.
+ * Get next packet descriptor from iterator
+ * If at end of list, return NULL and update host.
  */
-	virt_rmb();
-	ring_info->ring_buffer->read_index = ring_info->priv_read_index;
+static inline struct vmpacket_descriptor *
+hv_pkt_iter_next(struct vmbus_channel *channel,
+		 const struct vmpacket_descriptor *pkt)
+{
+	struct vmpacket_descriptor *nxt;
+
+	nxt = __hv_pkt_iter_next(channel, pkt);
+	if (!nxt)
+		hv_pkt_iter_close(channel);
 
-	hv_signal_on_read(channel);
+	return nxt;
 }
 
+#define foreach_vmbus_pkt(pkt, channel) \
+	for (pkt = hv_pkt_iter_first(channel); pkt; \
+	    pkt = hv_pkt_iter_next(channel, pkt))
 
 #endif /* _HYPERV_H */