gve: Add support for raw addressing to the rx path

Add support to use raw dma addresses in the rx path. Due to this new
support we can alloc a new buffer instead of making a copy.

RX buffers are handed to the networking stack and are
re-allocated as needed, avoiding the need to use
skb_copy_to_linear_data() as in "qpl" mode.

Reviewed-by: Yangchun Fu <yangchun@google.com>
Signed-off-by: Catherine Sullivan <csully@google.com>
Signed-off-by: David Awogbemila <awogbemila@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 782e279..d8bba0b 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -38,6 +38,8 @@
 #define NIC_TX_STATS_REPORT_NUM	0
 #define NIC_RX_STATS_REPORT_NUM	4
 
+#define GVE_DATA_SLOT_ADDR_PAGE_MASK (~(PAGE_SIZE - 1))
+
 /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */
 struct gve_rx_desc_queue {
 	struct gve_rx_desc *desc_ring; /* the descriptor ring */
@@ -49,7 +51,7 @@ struct gve_rx_desc_queue {
 struct gve_rx_slot_page_info {
 	struct page *page;
 	void *page_address;
-	u32 page_offset; /* offset to write to in page */
+	u8 page_offset; /* flipped to second half? */
 };
 
 /* A list of pages registered with the device during setup and used by a queue
@@ -64,10 +66,11 @@ struct gve_queue_page_list {
 
 /* Each slot in the data ring has a 1:1 mapping to a slot in the desc ring */
 struct gve_rx_data_queue {
-	struct gve_rx_data_slot *data_ring; /* read by NIC */
+	union gve_rx_data_slot *data_ring; /* read by NIC */
 	dma_addr_t data_bus; /* dma mapping of the slots */
 	struct gve_rx_slot_page_info *page_info; /* page info of the buffers */
 	struct gve_queue_page_list *qpl; /* qpl assigned to this queue */
+	u8 raw_addressing; /* use raw_addressing? */
 };
 
 struct gve_priv;
@@ -82,6 +85,7 @@ struct gve_rx_ring {
 	u32 cnt; /* free-running total number of completed packets */
 	u32 fill_cnt; /* free-running total number of descs and buffs posted */
 	u32 mask; /* masks the cnt and fill_cnt to the size of the ring */
+	u32 db_threshold; /* threshold for posting new buffs and descs */
 	u64 rx_copybreak_pkt; /* free-running count of copybreak packets */
 	u64 rx_copied_pkt; /* free-running total number of copied packets */
 	u64 rx_skb_alloc_fail; /* free-running count of skb alloc fails */
@@ -194,7 +198,7 @@ struct gve_priv {
 	u16 tx_desc_cnt; /* num desc per ring */
 	u16 rx_desc_cnt; /* num desc per ring */
 	u16 tx_pages_per_qpl; /* tx buffer length */
-	u16 rx_pages_per_qpl; /* rx buffer length */
+	u16 rx_data_slot_cnt; /* rx buffer length */
 	u64 max_registered_pages;
 	u64 num_registered_pages; /* num pages registered with NIC */
 	u32 rx_copybreak; /* copy packets smaller than this */
@@ -444,7 +448,7 @@ static inline u32 gve_num_tx_qpls(struct gve_priv *priv)
  */
 static inline u32 gve_num_rx_qpls(struct gve_priv *priv)
 {
-	return priv->rx_cfg.num_queues;
+	return priv->raw_addressing ? 0 : priv->rx_cfg.num_queues;
 }
 
 /* Returns a pointer to the next available tx qpl in the list of qpls