[PATCH 7/7] Drivers: hv: vmbus: Implement APIs to support "in place" consumption of vmbus packets

[K. Y. Srinivasan]

Implement APIs for in-place consumption of vmbus packets. Currently, each
packet is copied and processed one at a time and as part of processing
each packet we potentially may signal the host (if it is waiting for
room to produce a packet).

These APIs help batched in-place processing of vmbus packets.
We also optimize host signaling by having a separate API to signal
the end of in-place consumption. With netvsc using these APIs,
on an iperf run on average I see about 20X reduction in checks to
signal the host.

Signed-off-by: K. Y. Srinivasan <kys@xxxxxxxxxxxxx>
---
 drivers/hv/ring_buffer.c |    1 +
 include/linux/hyperv.h   |   86 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 87 insertions(+), 0 deletions(-)

diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 253311b..a2a38ab 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -132,6 +132,7 @@ hv_set_next_read_location(struct hv_ring_buffer_info *ring_info,
 		    u32 next_read_location)
 {
 	ring_info->ring_buffer->read_index = next_read_location;
+	ring_info->priv_read_index = next_read_location;
 }
 
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 8fc9b09..3fadbaf 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -126,6 +126,8 @@ struct hv_ring_buffer_info {
 
 	u32 ring_datasize;		/* < ring_size */
 	u32 ring_data_startoffset;
+	u32 priv_write_index;
+	u32 priv_read_index;
 };
 
 /*
@@ -1408,4 +1410,88 @@ static inline  bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi)
 	return false;
 }
 
+/*
+ * 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)
+{
+	struct hv_ring_buffer_info *ring_info = &channel->inbound;
+	u32 read_loc = ring_info->priv_read_index;
+	void *ring_buffer = hv_get_ring_buffer(ring_info);
+	struct vmpacket_descriptor *cur_desc;
+	u32 packetlen;
+	u32 dsize = ring_info->ring_datasize;
+	u32 delta = read_loc - ring_info->ring_buffer->read_index;
+	u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta);
+
+	if (bytes_avail_toread < sizeof(struct vmpacket_descriptor))
+		return NULL;
+
+	if ((read_loc + sizeof(*cur_desc)) > dsize)
+		return NULL;
+
+	cur_desc = ring_buffer + read_loc;
+	packetlen = cur_desc->len8 << 3;
+
+	/*
+	 * If the packet under consideration is wrapping around,
+	 * return failure.
+	 */
+	if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > (dsize - 1))
+		return NULL;
+
+	return cur_desc;
+}
+
+/*
+ * 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)
+{
+	struct hv_ring_buffer_info *ring_info = &channel->inbound;
+	u32 read_loc = ring_info->priv_read_index;
+	u32 packetlen = desc->len8 << 3;
+	u32 dsize = ring_info->ring_datasize;
+
+	if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > dsize)
+		BUG();
+	/*
+	 * Include the packet trailer.
+	 */
+	ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
+}
+
+/*
+ * This call commits the read index and potentially signals the host.
+ * Here is the pattern for using the "in-place" consumption APIs:
+ *
+ * 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.
+	 */
+	virt_rmb();
+	ring_info->ring_buffer->read_index = ring_info->priv_read_index;
+
+	if (hv_need_to_signal_on_read(ring_info))
+		vmbus_set_event(channel);
+}
+
+
 #endif /* _HYPERV_H */
-- 
1.7.4.1