[bpf-next V3 PATCH 12/14] xdp: generic XDP handling of xdp_rxq_info

[Jesper Dangaard Brouer <brouer@redhat.com>]

Hook points for xdp_rxq_info:
 * reg  : netif_alloc_rx_queues
 * unreg: netif_free_rx_queues

The net_device have some members (num_rx_queues + real_num_rx_queues)
and data-area (dev->_rx with struct netdev_rx_queue's) that were
primarily used for exporting information about RPS (CONFIG_RPS) queues
to sysfs (CONFIG_SYSFS).

For generic XDP extend struct netdev_rx_queue with the xdp_rxq_info,
and remove some of the CONFIG_SYSFS ifdefs.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 include/linux/netdevice.h |    2 +
 net/core/dev.c            |   69 ++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 61 insertions(+), 10 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 352066e4eeef..143aa9afc30f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -44,6 +44,7 @@
 #include <net/dcbnl.h>
 #endif
 #include <net/netprio_cgroup.h>
+#include <net/xdp.h>
 
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
@@ -686,6 +687,7 @@ struct netdev_rx_queue {
 #endif
 	struct kobject			kobj;
 	struct net_device		*dev;
+	struct xdp_rxq_info		xdp_rxq;
 } ____cacheline_aligned_in_smp;
 
 /*
diff --git a/net/core/dev.c b/net/core/dev.c
index 2eb66c0d9cdb..d7925ef8743d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3906,9 +3906,33 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	return NET_RX_DROP;
 }
 
+static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	struct netdev_rx_queue *rxqueue;
+
+	rxqueue = dev->_rx;
+
+	if (skb_rx_queue_recorded(skb)) {
+		u16 index = skb_get_rx_queue(skb);
+
+		if (unlikely(index >= dev->real_num_rx_queues)) {
+			WARN_ONCE(dev->real_num_rx_queues > 1,
+				  "%s received packet on queue %u, but number "
+				  "of RX queues is %u\n",
+				  dev->name, index, dev->real_num_rx_queues);
+
+			return rxqueue; /* Return first rxqueue */
+		}
+		rxqueue += index;
+	}
+	return rxqueue;
+}
+
 static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 				     struct bpf_prog *xdp_prog)
 {
+	struct netdev_rx_queue *rxqueue;
 	u32 metalen, act = XDP_DROP;
 	struct xdp_buff xdp;
 	void *orig_data;
@@ -3952,6 +3976,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	xdp.data_hard_start = skb->data - skb_headroom(skb);
 	orig_data = xdp.data;
 
+	rxqueue = netif_get_rxqueue(skb);
+	xdp.rxq = &rxqueue->xdp_rxq;
+
 	act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
 	off = xdp.data - orig_data;
@@ -7589,12 +7616,12 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 }
 EXPORT_SYMBOL(netif_stacked_transfer_operstate);
 
-#ifdef CONFIG_SYSFS
 static int netif_alloc_rx_queues(struct net_device *dev)
 {
 	unsigned int i, count = dev->num_rx_queues;
 	struct netdev_rx_queue *rx;
 	size_t sz = count * sizeof(*rx);
+	int err = 0;
 
 	BUG_ON(count < 1);
 
@@ -7604,11 +7631,39 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 
 	dev->_rx = rx;
 
-	for (i = 0; i < count; i++)
+	for (i = 0; i < count; i++) {
 		rx[i].dev = dev;
+
+		/* XDP RX-queue setup */
+		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+		if (err < 0)
+			goto err_rxq_info;
+	}
 	return 0;
+
+err_rxq_info:
+	/* Rollback successful reg's and free other resources */
+	while (i--)
+		xdp_rxq_info_unreg(&rx[i].xdp_rxq);
+	kfree(dev->_rx);
+	dev->_rx = NULL;
+	return err;
+}
+
+static void netif_free_rx_queues(struct net_device *dev)
+{
+	unsigned int i, count = dev->num_rx_queues;
+	struct netdev_rx_queue *rx;
+
+	/* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */
+	if (!dev->_rx)
+		return;
+
+	rx = dev->_rx;
+
+	for (i = 0; i < count; i++)
+		xdp_rxq_info_unreg(&rx[i].xdp_rxq);
 }
-#endif
 
 static void netdev_init_one_queue(struct net_device *dev,
 				  struct netdev_queue *queue, void *_unused)
@@ -8169,12 +8224,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		return NULL;
 	}
 
-#ifdef CONFIG_SYSFS
 	if (rxqs < 1) {
 		pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
 		return NULL;
 	}
-#endif
 
 	alloc_size = sizeof(struct net_device);
 	if (sizeof_priv) {
@@ -8231,12 +8284,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	if (netif_alloc_netdev_queues(dev))
 		goto free_all;
 
-#ifdef CONFIG_SYSFS
 	dev->num_rx_queues = rxqs;
 	dev->real_num_rx_queues = rxqs;
 	if (netif_alloc_rx_queues(dev))
 		goto free_all;
-#endif
 
 	strcpy(dev->name, name);
 	dev->name_assign_type = name_assign_type;
@@ -8275,9 +8326,7 @@ void free_netdev(struct net_device *dev)
 
 	might_sleep();
 	netif_free_tx_queues(dev);
-#ifdef CONFIG_SYSFS
-	kvfree(dev->_rx);
-#endif
+	netif_free_rx_queues(dev);
 
 	kfree(rcu_dereference_protected(dev->ingress_queue, 1));