gve: Add XDP DROP and TX support for GQI-QPL format

Add support for XDP PASS, DROP and TX actions.

This patch contains the following changes:
1) Support installing/uninstalling XDP program
2) Add dedicated XDP TX queues
3) Add support for XDP DROP action
4) Add support for XDP TX action

Signed-off-by: Praveen Kaligineedi <[email protected]>
Reviewed-by: Jeroen de Borst <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: praveenkaligineedi

drivers/net/ethernet/google/gve/gve.h

@@ -47,6 +47,10 @@
 
 #define GVE_RX_BUFFER_SIZE_DQO 2048
 
+#define GVE_XDP_ACTIONS 5
+
+#define GVE_TX_MAX_HEADER_SIZE 182
+
 /* 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 */
@@ -230,14 +234,19 @@ struct gve_rx_ring {
 	u64 rx_frag_flip_cnt; /* free-running count of rx segments where page_flip was used */
 	u64 rx_frag_copy_cnt; /* free-running count of rx segments copied */
 	u64 rx_frag_alloc_cnt; /* free-running count of rx page allocations */
-
+	u64 xdp_tx_errors;
+	u64 xdp_redirect_errors;
+	u64 xdp_actions[GVE_XDP_ACTIONS];
 	u32 q_num; /* queue index */
 	u32 ntfy_id; /* notification block index */
 	struct gve_queue_resources *q_resources; /* head and tail pointer idx */
 	dma_addr_t q_resources_bus; /* dma address for the queue resources */
 	struct u64_stats_sync statss; /* sync stats for 32bit archs */
 
 	struct gve_rx_ctx ctx; /* Info for packet currently being processed in this ring. */
+
+	/* XDP stuff */
+	struct xdp_rxq_info xdp_rxq;
 };
 
 /* A TX desc ring entry */
@@ -259,6 +268,9 @@ struct gve_tx_iovec {
  */
 struct gve_tx_buffer_state {
 	struct sk_buff *skb; /* skb for this pkt */
+	struct {
+		u16 size; /* size of xmitted xdp pkt */
+	} xdp;
 	union {
 		struct gve_tx_iovec iov[GVE_TX_MAX_IOVEC]; /* segments of this pkt */
 		struct {
@@ -526,9 +538,11 @@ struct gve_priv {
 	u16 rx_data_slot_cnt; /* rx buffer length */
 	u64 max_registered_pages;
 	u64 num_registered_pages; /* num pages registered with NIC */
+	struct bpf_prog *xdp_prog; /* XDP BPF program */
 	u32 rx_copybreak; /* copy packets smaller than this */
 	u16 default_num_queues; /* default num queues to set up */
 
+	u16 num_xdp_queues;
 	struct gve_queue_config tx_cfg;
 	struct gve_queue_config rx_cfg;
 	struct gve_qpl_config qpl_cfg; /* map used QPL ids */
@@ -785,7 +799,17 @@ static inline u32 gve_num_tx_qpls(struct gve_priv *priv)
 	if (priv->queue_format != GVE_GQI_QPL_FORMAT)
 		return 0;
 
-	return priv->tx_cfg.num_queues;
+	return priv->tx_cfg.num_queues + priv->num_xdp_queues;
+}
+
+/* Returns the number of XDP tx queue page lists
+ */
+static inline u32 gve_num_xdp_qpls(struct gve_priv *priv)
+{
+	if (priv->queue_format != GVE_GQI_QPL_FORMAT)
+		return 0;
+
+	return priv->num_xdp_queues;
 }
 
 /* Returns the number of rx queue page lists
@@ -874,7 +898,17 @@ static inline bool gve_is_gqi(struct gve_priv *priv)
 
 static inline u32 gve_num_tx_queues(struct gve_priv *priv)
 {
-	return priv->tx_cfg.num_queues;
+	return priv->tx_cfg.num_queues + priv->num_xdp_queues;
+}
+
+static inline u32 gve_xdp_tx_queue_id(struct gve_priv *priv, u32 queue_id)
+{
+	return priv->tx_cfg.num_queues + queue_id;
+}
+
+static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv)
+{
+	return gve_xdp_tx_queue_id(priv, 0);
 }
 
 /* buffers */
@@ -885,7 +919,11 @@ void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma,
 		   enum dma_data_direction);
 /* tx handling */
 netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev);
+int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx,
+		     void *data, int len);
+void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid);
 bool gve_tx_poll(struct gve_notify_block *block, int budget);
+bool gve_xdp_poll(struct gve_notify_block *block, int budget);
 int gve_tx_alloc_rings(struct gve_priv *priv, int start_id, int num_rings);
 void gve_tx_free_rings_gqi(struct gve_priv *priv, int start_id, int num_rings);
 u32 gve_tx_load_event_counter(struct gve_priv *priv,

drivers/net/ethernet/google/gve/gve_ethtool.c

@@ -34,6 +34,11 @@ static u32 gve_get_msglevel(struct net_device *netdev)
 	return priv->msg_enable;
 }
 
+/* For the following stats column string names, make sure the order
+ * matches how it is filled in the code. For xdp_aborted, xdp_drop,
+ * xdp_pass, xdp_tx, xdp_redirect, make sure it also matches the order
+ * as declared in enum xdp_action inside file uapi/linux/bpf.h .
+ */
 static const char gve_gstrings_main_stats[][ETH_GSTRING_LEN] = {
 	"rx_packets", "tx_packets", "rx_bytes", "tx_bytes",
 	"rx_dropped", "tx_dropped", "tx_timeouts",
@@ -49,6 +54,9 @@ static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = {
 	"rx_dropped_pkt[%u]", "rx_copybreak_pkt[%u]", "rx_copied_pkt[%u]",
 	"rx_queue_drop_cnt[%u]", "rx_no_buffers_posted[%u]",
 	"rx_drops_packet_over_mru[%u]", "rx_drops_invalid_checksum[%u]",
+	"rx_xdp_aborted[%u]", "rx_xdp_drop[%u]", "rx_xdp_pass[%u]",
+	"rx_xdp_tx[%u]", "rx_xdp_redirect[%u]",
+	"rx_xdp_tx_errors[%u]", "rx_xdp_redirect_errors[%u]",
 };
 
 static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = {
@@ -289,14 +297,25 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			if (skip_nic_stats) {
 				/* skip NIC rx stats */
 				i += NIC_RX_STATS_REPORT_NUM;
-				continue;
-			}
-			for (j = 0; j < NIC_RX_STATS_REPORT_NUM; j++) {
-				u64 value =
-				be64_to_cpu(report_stats[rx_qid_to_stats_idx[ring] + j].value);
+			} else {
+				stats_idx = rx_qid_to_stats_idx[ring];
+				for (j = 0; j < NIC_RX_STATS_REPORT_NUM; j++) {
+					u64 value =
+						be64_to_cpu(report_stats[stats_idx + j].value);
 
-				data[i++] = value;
+					data[i++] = value;
+				}
 			}
+			/* XDP rx counters */
+			do {
+				start =	u64_stats_fetch_begin(&priv->rx[ring].statss);
+				for (j = 0; j < GVE_XDP_ACTIONS; j++)
+					data[i + j] = rx->xdp_actions[j];
+				data[i + j++] = rx->xdp_tx_errors;
+				data[i + j++] = rx->xdp_redirect_errors;
+			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+						       start));
+			i += GVE_XDP_ACTIONS + 2; /* XDP rx counters */
 		}
 	} else {
 		i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS;
@@ -418,6 +437,12 @@ static int gve_set_channels(struct net_device *netdev,
 	if (!new_rx || !new_tx)
 		return -EINVAL;
 
+	if (priv->num_xdp_queues &&
+	    (new_tx != new_rx || (2 * new_tx > priv->tx_cfg.max_queues))) {
+		dev_err(&priv->pdev->dev, "XDP load failed: The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues");
+		return -EINVAL;
+	}
+
 	if (!netif_carrier_ok(netdev)) {
 		priv->tx_cfg.num_queues = new_tx;
 		priv->rx_cfg.num_queues = new_rx;