gve: Add XDP REDIRECT support for GQI-QPL format

This patch contains the following changes:
1) Support for XDP REDIRECT action on rx
2) ndo_xdp_xmit callback support

In GQI-QPL queue format, the driver needs to allocate a fixed size
memory, the size specified by vNIC device, for RX/TX and register this
memory as a bounce buffer with the vNIC device when a queue is created.
The number of pages in the bounce buffer is limited and the pages need to
be made available to the vNIC by copying the RX data out to prevent
head-of-line blocking. The XDP_REDIRECT packets are therefore immediately
copied to a newly allocated page.

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>

1 files changed, 45 insertions, 3 deletions

diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 3e96ee7537ce..d928c3c79618 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -173,6 +173,10 @@ static int gve_clean_xdp_done(struct gve_priv *priv, struct gve_tx_ring *tx,
 		pkts++;
 
 		info->xdp.size = 0;
+		if (info->xdp_frame) {
+			xdp_return_frame(info->xdp_frame);
+			info->xdp_frame = NULL;
+		}
 		space_freed += gve_tx_clear_buffer_state(info);
 	}
 
@@ -233,6 +237,7 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx)
 	/* Make sure everything is zeroed to start */
 	memset(tx, 0, sizeof(*tx));
 	spin_lock_init(&tx->clean_lock);
+	spin_lock_init(&tx->xdp_lock);
 	tx->q_num = idx;
 
 	tx->mask = slots - 1;
@@ -715,7 +720,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
 }
 
 static int gve_tx_fill_xdp(struct gve_priv *priv, struct gve_tx_ring *tx,
-			   void *data, int len)
+			   void *data, int len, void *frame_p)
 {
 	int pad, nfrags, ndescs, iovi, offset;
 	struct gve_tx_buffer_state *info;
@@ -725,6 +730,7 @@ static int gve_tx_fill_xdp(struct gve_priv *priv, struct gve_tx_ring *tx,
 	if (pad >= GVE_TX_MAX_HEADER_SIZE)
 		pad = 0;
 	info = &tx->info[reqi & tx->mask];
+	info->xdp_frame = frame_p;
 	info->xdp.size = len;
 
 	nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, pad + len,
@@ -759,15 +765,51 @@ static int gve_tx_fill_xdp(struct gve_priv *priv, struct gve_tx_ring *tx,
 	return ndescs;
 }
 
+int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		 u32 flags)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_tx_ring *tx;
+	int i, err = 0, qid;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	qid = gve_xdp_tx_queue_id(priv,
+				  smp_processor_id() % priv->num_xdp_queues);
+
+	tx = &priv->tx[qid];
+
+	spin_lock(&tx->xdp_lock);
+	for (i = 0; i < n; i++) {
+		err = gve_xdp_xmit_one(priv, tx, frames[i]->data,
+				       frames[i]->len, frames[i]);
+		if (err)
+			break;
+	}
+
+	if (flags & XDP_XMIT_FLUSH)
+		gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
+
+	spin_unlock(&tx->xdp_lock);
+
+	u64_stats_update_begin(&tx->statss);
+	tx->xdp_xmit += n;
+	tx->xdp_xmit_errors += n - i;
+	u64_stats_update_end(&tx->statss);
+
+	return i ? i : err;
+}
+
 int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx,
-		     void *data, int len)
+		     void *data, int len, void *frame_p)
 {
 	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);
+	nsegs = gve_tx_fill_xdp(priv, tx, data, len, frame_p);
 	tx->req += nsegs;
 
 	return 0;