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 <pkaligineedi@google.com>
Reviewed-by: Jeroen de Borst <jeroendb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

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 */
@@ -230,7 +234,9 @@ 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 */
@@ -238,6 +244,9 @@ struct gve_rx_ring {
 	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;

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

@@ -8,6 +8,8 @@
 #include "gve_adminq.h"
 #include "gve_utils.h"
 #include <linux/etherdevice.h>
+#include <linux/filter.h>
+#include <net/xdp.h>
 
 static void gve_rx_free_buffer(struct device *dev,
 			       struct gve_rx_slot_page_info *page_info,
@@ -591,6 +593,43 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx,
 	return skb;
 }
 
+static void gve_xdp_done(struct gve_priv *priv, struct gve_rx_ring *rx,
+			 struct xdp_buff *xdp, struct bpf_prog *xprog,
+			 int xdp_act)
+{
+	struct gve_tx_ring *tx;
+	int tx_qid;
+	int err;
+
+	switch (xdp_act) {
+	case XDP_ABORTED:
+	case XDP_DROP:
+	default:
+		break;
+	case XDP_TX:
+		tx_qid = gve_xdp_tx_queue_id(priv, rx->q_num);
+		tx = &priv->tx[tx_qid];
+		err = gve_xdp_xmit_one(priv, tx, xdp->data,
+				       xdp->data_end - xdp->data);
+
+		if (unlikely(err)) {
+			u64_stats_update_begin(&rx->statss);
+			rx->xdp_tx_errors++;
+			u64_stats_update_end(&rx->statss);
+		}
+		break;
+	case XDP_REDIRECT:
+		u64_stats_update_begin(&rx->statss);
+		rx->xdp_redirect_errors++;
+		u64_stats_update_end(&rx->statss);
+		break;
+	}
+	u64_stats_update_begin(&rx->statss);
+	if ((u32)xdp_act < GVE_XDP_ACTIONS)
+		rx->xdp_actions[xdp_act]++;
+	u64_stats_update_end(&rx->statss);
+}
+
 #define GVE_PKTCONT_BIT_IS_SET(x) (GVE_RXF_PKT_CONT & (x))
 static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat,
 		   struct gve_rx_desc *desc, u32 idx,
@@ -603,9 +642,12 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat,
 	union gve_rx_data_slot *data_slot;
 	struct gve_priv *priv = rx->gve;
 	struct sk_buff *skb = NULL;
+	struct bpf_prog *xprog;
+	struct xdp_buff xdp;
 	dma_addr_t page_bus;
 	void *va;
 
+	u16 len = frag_size;
 	struct napi_struct *napi = &priv->ntfy_blocks[rx->ntfy_id].napi;
 	bool is_first_frag = ctx->frag_cnt == 0;
 
@@ -645,9 +687,35 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat,
 	dma_sync_single_for_cpu(&priv->pdev->dev, page_bus,
 				PAGE_SIZE, DMA_FROM_DEVICE);
 	page_info->pad = is_first_frag ? GVE_RX_PAD : 0;
+	len -= page_info->pad;
 	frag_size -= page_info->pad;
 
-	skb = gve_rx_skb(priv, rx, page_info, napi, frag_size,
+	xprog = READ_ONCE(priv->xdp_prog);
+	if (xprog && is_only_frag) {
+		void *old_data;
+		int xdp_act;
+
+		xdp_init_buff(&xdp, rx->packet_buffer_size, &rx->xdp_rxq);
+		xdp_prepare_buff(&xdp, page_info->page_address +
+				 page_info->page_offset, GVE_RX_PAD,
+				 len, false);
+		old_data = xdp.data;
+		xdp_act = bpf_prog_run_xdp(xprog, &xdp);
+		if (xdp_act != XDP_PASS) {
+			gve_xdp_done(priv, rx, &xdp, xprog, xdp_act);
+			ctx->total_size += frag_size;
+			goto finish_ok_pkt;
+		}
+
+		page_info->pad += xdp.data - old_data;
+		len = xdp.data_end - xdp.data;
+
+		u64_stats_update_begin(&rx->statss);
+		rx->xdp_actions[XDP_PASS]++;
+		u64_stats_update_end(&rx->statss);
+	}
+
+	skb = gve_rx_skb(priv, rx, page_info, napi, len,
 			 data_slot, is_only_frag);
 	if (!skb) {
 		u64_stats_update_begin(&rx->statss);
@@ -773,6 +841,7 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx)
 static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget,
 			     netdev_features_t feat)
 {
+	u64 xdp_txs = rx->xdp_actions[XDP_TX];
 	struct gve_rx_ctx *ctx = &rx->ctx;
 	struct gve_priv *priv = rx->gve;
 	struct gve_rx_cnts cnts = {0};
@@ -820,6 +889,9 @@ static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget,
 		u64_stats_update_end(&rx->statss);
 	}
 
+	if (xdp_txs != rx->xdp_actions[XDP_TX])
+		gve_xdp_tx_flush(priv, rx->q_num);
+
 	/* restock ring slots */
 	if (!rx->data.raw_addressing) {
 		/* In QPL mode buffs are refilled as the desc are processed */

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

@@ -19,6 +19,14 @@ static inline void gve_tx_put_doorbell(struct gve_priv *priv,
 	iowrite32be(val, &priv->db_bar2[be32_to_cpu(q_resources->db_index)]);
 }
 
+void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid)
+{
+	u32 tx_qid = gve_xdp_tx_queue_id(priv, xdp_qid);
+	struct gve_tx_ring *tx = &priv->tx[tx_qid];
+
+	gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
+}
+
 /* gvnic can only transmit from a Registered Segment.
  * We copy skb payloads into the registered segment before writing Tx
  * descriptors and ringing the Tx doorbell.
@@ -132,6 +140,50 @@ static void gve_tx_free_fifo(struct gve_tx_fifo *fifo, size_t bytes)
 	atomic_add(bytes, &fifo->available);
 }
 
+static size_t gve_tx_clear_buffer_state(struct gve_tx_buffer_state *info)
+{
+	size_t space_freed = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(info->iov); i++) {
+		space_freed += info->iov[i].iov_len + info->iov[i].iov_padding;
+		info->iov[i].iov_len = 0;
+		info->iov[i].iov_padding = 0;
+	}
+	return space_freed;
+}
+
+static int gve_clean_xdp_done(struct gve_priv *priv, struct gve_tx_ring *tx,
+			      u32 to_do)
+{
+	struct gve_tx_buffer_state *info;
+	u32 clean_end = tx->done + to_do;
+	u64 pkts = 0, bytes = 0;
+	size_t space_freed = 0;
+	u32 idx;
+
+	for (; tx->done < clean_end; tx->done++) {
+		idx = tx->done & tx->mask;
+		info = &tx->info[idx];
+
+		if (unlikely(!info->xdp.size))
+			continue;
+
+		bytes += info->xdp.size;
+		pkts++;
+
+		info->xdp.size = 0;
+		space_freed += gve_tx_clear_buffer_state(info);
+	}
+
+	gve_tx_free_fifo(&tx->tx_fifo, space_freed);
+	u64_stats_update_begin(&tx->statss);
+	tx->bytes_done += bytes;
+	tx->pkt_done += pkts;
+	u64_stats_update_end(&tx->statss);
+	return pkts;
+}
+
 static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
 			     u32 to_do, bool try_to_wake);
 
@@ -144,8 +196,12 @@ static void gve_tx_free_ring(struct gve_priv *priv, int idx)
 
 	gve_tx_remove_from_block(priv, idx);
 	slots = tx->mask + 1;
-	gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false);
-	netdev_tx_reset_queue(tx->netdev_txq);
+	if (tx->q_num < priv->tx_cfg.num_queues) {
+		gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false);
+		netdev_tx_reset_queue(tx->netdev_txq);
+	} else {
+		gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt);
+	}
 
 	dma_free_coherent(hdev, sizeof(*tx->q_resources),
 			  tx->q_resources, tx->q_resources_bus);
@@ -213,7 +269,8 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx)
 
 	netif_dbg(priv, drv, priv->dev, "tx[%d]->bus=%lx\n", idx,
 		  (unsigned long)tx->bus);
-	tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx);
+	if (idx < priv->tx_cfg.num_queues)
+		tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx);
 	gve_tx_add_to_block(priv, idx);
 
 	return 0;
@@ -657,6 +714,65 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
+static int gve_tx_fill_xdp(struct gve_priv *priv, struct gve_tx_ring *tx,
+			   void *data, int len)
+{
+	int pad, nfrags, ndescs, iovi, offset;
+	struct gve_tx_buffer_state *info;
+	u32 reqi = tx->req;
+
+	pad = gve_tx_fifo_pad_alloc_one_frag(&tx->tx_fifo, len);
+	if (pad >= GVE_TX_MAX_HEADER_SIZE)
+		pad = 0;
+	info = &tx->info[reqi & tx->mask];
+	info->xdp.size = len;
+
+	nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, pad + len,
+				   &info->iov[0]);
+	iovi = pad > 0;
+	ndescs = nfrags - iovi;
+	offset = 0;
+
+	while (iovi < nfrags) {
+		if (!offset)
+			gve_tx_fill_pkt_desc(&tx->desc[reqi & tx->mask], 0,
+					     CHECKSUM_NONE, false, 0, ndescs,
+					     info->iov[iovi].iov_len,
+					     info->iov[iovi].iov_offset, len);
+		else
+			gve_tx_fill_seg_desc(&tx->desc[reqi & tx->mask],
+					     0, 0, false, false,
+					     info->iov[iovi].iov_len,
+					     info->iov[iovi].iov_offset);
+
+		memcpy(tx->tx_fifo.base + info->iov[iovi].iov_offset,
+		       data + offset, info->iov[iovi].iov_len);
+		gve_dma_sync_for_device(&priv->pdev->dev,
+					tx->tx_fifo.qpl->page_buses,
+					info->iov[iovi].iov_offset,
+					info->iov[iovi].iov_len);
+		offset += info->iov[iovi].iov_len;
+		iovi++;
+		reqi++;
+	}
+
+	return ndescs;
+}
+
+int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx,
+		     void *data, int len)
+{
+	int nsegs;
+
+	if (!gve_can_tx(tx, len + GVE_TX_MAX_HEADER_SIZE - 1))
+		return -EBUSY;
+
+	nsegs = gve_tx_fill_xdp(priv, tx, data, len);
+	tx->req += nsegs;
+
+	return 0;
+}
+
 #define GVE_TX_START_THRESH	PAGE_SIZE
 
 static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
@@ -666,8 +782,8 @@ static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
 	u64 pkts = 0, bytes = 0;
 	size_t space_freed = 0;
 	struct sk_buff *skb;
-	int i, j;
 	u32 idx;
+	int j;
 
 	for (j = 0; j < to_do; j++) {
 		idx = tx->done & tx->mask;
@@ -689,12 +805,7 @@ static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
 			dev_consume_skb_any(skb);
 			if (tx->raw_addressing)
 				continue;
-			/* FIFO free */
-			for (i = 0; i < ARRAY_SIZE(info->iov); i++) {
-				space_freed += info->iov[i].iov_len + info->iov[i].iov_padding;
-				info->iov[i].iov_len = 0;
-				info->iov[i].iov_padding = 0;
-			}
+			space_freed += gve_tx_clear_buffer_state(info);
 		}
 	}
 
@@ -729,6 +840,24 @@ u32 gve_tx_load_event_counter(struct gve_priv *priv,
 	return be32_to_cpu(counter);
 }
 
+bool gve_xdp_poll(struct gve_notify_block *block, int budget)
+{
+	struct gve_priv *priv = block->priv;
+	struct gve_tx_ring *tx = block->tx;
+	u32 nic_done;
+	u32 to_do;
+
+	/* If budget is 0, do all the work */
+	if (budget == 0)
+		budget = INT_MAX;
+
+	/* Find out how much work there is to be done */
+	nic_done = gve_tx_load_event_counter(priv, tx);
+	to_do = min_t(u32, (nic_done - tx->done), budget);
+	gve_clean_xdp_done(priv, tx, to_do);
+	return nic_done != tx->done;
+}
+
 bool gve_tx_poll(struct gve_notify_block *block, int budget)
 {
 	struct gve_priv *priv = block->priv;