Merge branch 'bpf-xdp-stack-uninit-and-offload-tests'

Jakub Kicinski says:

====================
The purpose of this series is to add a software model of BPF offloads
to make it easier for everyone to test them and make some of the more
arcane rules and assumptions more clear.

The series starts with 3 patches aiming to make XDP handling in the
drivers less error prone.  Currently driver authors have to remember
to free XDP programs if XDP is active during unregister.  With this
series the core will disable XDP on its own.  It will take place
after close, drivers are not expected to perform reconfiguration
when disabling XDP on a downed device.

Next two patches add the software netdev driver, followed by a python
test which exercises all the corner cases which came to my mind.

Test needs to be run as root.  It will print basic information to
stdout, but can also create a more detailed log of all commands
when --log option is passed.  Log is in Emacs Org-mode format.

  ./tools/testing/selftests/bpf/test_offload.py --log /tmp/log

Last two patches replace the SR-IOV API implementation of dummy.

v3:
 - move the freeing of vfs to release (Phil).
v2:
 - free device from the release function;
 - use bus-based name generatin instead of netdev name.
v1:
 - replace the SR-IOV API implementation of dummy;
 - make the dev_xdp_uninstall() also handle the XDP generic (Daniel).
====================

Signed-off-by: Daniel Borkmann <[email protected]>

Author: borkmann

MAINTAINERS

@@ -9599,6 +9599,11 @@ NETWORKING [WIRELESS]
 L:	[email protected]
 Q:	http://patchwork.kernel.org/project/linux-wireless/list/
 
+NETDEVSIM
+M:	Jakub Kicinski <[email protected]>
+S:	Maintained
+F:	drivers/net/netdevsim/*
+
 NETXEN (1/10) GbE SUPPORT
 M:	Manish Chopra <[email protected]>
 M:	Rahul Verma <[email protected]>

drivers/net/Kconfig

@@ -497,4 +497,15 @@ config THUNDERBOLT_NET
 
 source "drivers/net/hyperv/Kconfig"
 
+config NETDEVSIM
+	tristate "Simulated networking device"
+	depends on DEBUG_FS
+	help
+	  This driver is a developer testing tool and software model that can
+	  be used to test various control path networking APIs, especially
+	  HW-offload related.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called netdevsim.
+
 endif # NETDEVICES

drivers/net/Makefile

@@ -78,3 +78,4 @@ obj-$(CONFIG_FUJITSU_ES) += fjes/
 
 thunderbolt-net-y += thunderbolt.o
 obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o
+obj-$(CONFIG_NETDEVSIM) += netdevsim/

drivers/net/dummy.c

@@ -42,48 +42,7 @@
 #define DRV_NAME	"dummy"
 #define DRV_VERSION	"1.0"
 
-#undef pr_fmt
-#define pr_fmt(fmt) DRV_NAME ": " fmt
-
 static int numdummies = 1;
-static int num_vfs;
-
-struct vf_data_storage {
-	u8	vf_mac[ETH_ALEN];
-	u16	pf_vlan; /* When set, guest VLAN config not allowed. */
-	u16	pf_qos;
-	__be16	vlan_proto;
-	u16	min_tx_rate;
-	u16	max_tx_rate;
-	u8	spoofchk_enabled;
-	bool	rss_query_enabled;
-	u8	trusted;
-	int	link_state;
-};
-
-struct dummy_priv {
-	struct vf_data_storage	*vfinfo;
-};
-
-static int dummy_num_vf(struct device *dev)
-{
-	return num_vfs;
-}
-
-static struct bus_type dummy_bus = {
-	.name	= "dummy",
-	.num_vf	= dummy_num_vf,
-};
-
-static void release_dummy_parent(struct device *dev)
-{
-}
-
-static struct device dummy_parent = {
-	.init_name	= "dummy",
-	.bus		= &dummy_bus,
-	.release	= release_dummy_parent,
-};
 
 /* fake multicast ability */
 static void set_multicast_list(struct net_device *dev)
@@ -133,25 +92,10 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int dummy_dev_init(struct net_device *dev)
 {
-	struct dummy_priv *priv = netdev_priv(dev);
-
 	dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
 	if (!dev->dstats)
 		return -ENOMEM;
 
-	priv->vfinfo = NULL;
-
-	if (!num_vfs)
-		return 0;
-
-	dev->dev.parent = &dummy_parent;
-	priv->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage),
-			       GFP_KERNEL);
-	if (!priv->vfinfo) {
-		free_percpu(dev->dstats);
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -169,117 +113,6 @@ static int dummy_change_carrier(struct net_device *dev, bool new_carrier)
 	return 0;
 }
 
-static int dummy_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (!is_valid_ether_addr(mac) || (vf >= num_vfs))
-		return -EINVAL;
-
-	memcpy(priv->vfinfo[vf].vf_mac, mac, ETH_ALEN);
-
-	return 0;
-}
-
-static int dummy_set_vf_vlan(struct net_device *dev, int vf,
-			     u16 vlan, u8 qos, __be16 vlan_proto)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if ((vf >= num_vfs) || (vlan > 4095) || (qos > 7))
-		return -EINVAL;
-
-	priv->vfinfo[vf].pf_vlan = vlan;
-	priv->vfinfo[vf].pf_qos = qos;
-	priv->vfinfo[vf].vlan_proto = vlan_proto;
-
-	return 0;
-}
-
-static int dummy_set_vf_rate(struct net_device *dev, int vf, int min, int max)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].min_tx_rate = min;
-	priv->vfinfo[vf].max_tx_rate = max;
-
-	return 0;
-}
-
-static int dummy_set_vf_spoofchk(struct net_device *dev, int vf, bool val)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].spoofchk_enabled = val;
-
-	return 0;
-}
-
-static int dummy_set_vf_rss_query_en(struct net_device *dev, int vf, bool val)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].rss_query_enabled = val;
-
-	return 0;
-}
-
-static int dummy_set_vf_trust(struct net_device *dev, int vf, bool val)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].trusted = val;
-
-	return 0;
-}
-
-static int dummy_get_vf_config(struct net_device *dev,
-			       int vf, struct ifla_vf_info *ivi)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	ivi->vf = vf;
-	memcpy(&ivi->mac, priv->vfinfo[vf].vf_mac, ETH_ALEN);
-	ivi->vlan = priv->vfinfo[vf].pf_vlan;
-	ivi->qos = priv->vfinfo[vf].pf_qos;
-	ivi->spoofchk = priv->vfinfo[vf].spoofchk_enabled;
-	ivi->linkstate = priv->vfinfo[vf].link_state;
-	ivi->min_tx_rate = priv->vfinfo[vf].min_tx_rate;
-	ivi->max_tx_rate = priv->vfinfo[vf].max_tx_rate;
-	ivi->rss_query_en = priv->vfinfo[vf].rss_query_enabled;
-	ivi->trusted = priv->vfinfo[vf].trusted;
-	ivi->vlan_proto = priv->vfinfo[vf].vlan_proto;
-
-	return 0;
-}
-
-static int dummy_set_vf_link_state(struct net_device *dev, int vf, int state)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].link_state = state;
-
-	return 0;
-}
-
 static const struct net_device_ops dummy_netdev_ops = {
 	.ndo_init		= dummy_dev_init,
 	.ndo_uninit		= dummy_dev_uninit,
@@ -289,14 +122,6 @@ static const struct net_device_ops dummy_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_get_stats64	= dummy_get_stats64,
 	.ndo_change_carrier	= dummy_change_carrier,
-	.ndo_set_vf_mac		= dummy_set_vf_mac,
-	.ndo_set_vf_vlan	= dummy_set_vf_vlan,
-	.ndo_set_vf_rate	= dummy_set_vf_rate,
-	.ndo_set_vf_spoofchk	= dummy_set_vf_spoofchk,
-	.ndo_set_vf_trust	= dummy_set_vf_trust,
-	.ndo_get_vf_config	= dummy_get_vf_config,
-	.ndo_set_vf_link_state	= dummy_set_vf_link_state,
-	.ndo_set_vf_rss_query_en = dummy_set_vf_rss_query_en,
 };
 
 static void dummy_get_drvinfo(struct net_device *dev,
@@ -323,13 +148,6 @@ static const struct ethtool_ops dummy_ethtool_ops = {
 	.get_ts_info		= dummy_get_ts_info,
 };
 
-static void dummy_free_netdev(struct net_device *dev)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	kfree(priv->vfinfo);
-}
-
 static void dummy_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -338,7 +156,6 @@ static void dummy_setup(struct net_device *dev)
 	dev->netdev_ops = &dummy_netdev_ops;
 	dev->ethtool_ops = &dummy_ethtool_ops;
 	dev->needs_free_netdev = true;
-	dev->priv_destructor = dummy_free_netdev;
 
 	/* Fill in device structure with ethernet-generic values. */
 	dev->flags |= IFF_NOARP;
@@ -370,7 +187,6 @@ static int dummy_validate(struct nlattr *tb[], struct nlattr *data[],
 
 static struct rtnl_link_ops dummy_link_ops __read_mostly = {
 	.kind		= DRV_NAME,
-	.priv_size	= sizeof(struct dummy_priv),
 	.setup		= dummy_setup,
 	.validate	= dummy_validate,
 };
@@ -379,16 +195,12 @@ static struct rtnl_link_ops dummy_link_ops __read_mostly = {
 module_param(numdummies, int, 0);
 MODULE_PARM_DESC(numdummies, "Number of dummy pseudo devices");
 
-module_param(num_vfs, int, 0);
-MODULE_PARM_DESC(num_vfs, "Number of dummy VFs per dummy device");
-
 static int __init dummy_init_one(void)
 {
 	struct net_device *dev_dummy;
 	int err;
 
-	dev_dummy = alloc_netdev(sizeof(struct dummy_priv),
-				 "dummy%d", NET_NAME_ENUM, dummy_setup);
+	dev_dummy = alloc_netdev(0, "dummy%d", NET_NAME_ENUM, dummy_setup);
 	if (!dev_dummy)
 		return -ENOMEM;
 
@@ -407,21 +219,6 @@ static int __init dummy_init_module(void)
 {
 	int i, err = 0;
 
-	if (num_vfs) {
-		err = bus_register(&dummy_bus);
-		if (err < 0) {
-			pr_err("registering dummy bus failed\n");
-			return err;
-		}
-
-		err = device_register(&dummy_parent);
-		if (err < 0) {
-			pr_err("registering dummy parent device failed\n");
-			bus_unregister(&dummy_bus);
-			return err;
-		}
-	}
-
 	rtnl_lock();
 	err = __rtnl_link_register(&dummy_link_ops);
 	if (err < 0)
@@ -437,22 +234,12 @@ static int __init dummy_init_module(void)
 out:
 	rtnl_unlock();
 
-	if (err && num_vfs) {
-		device_unregister(&dummy_parent);
-		bus_unregister(&dummy_bus);
-	}
-
 	return err;
 }
 
 static void __exit dummy_cleanup_module(void)
 {
 	rtnl_link_unregister(&dummy_link_ops);
-
-	if (num_vfs) {
-		device_unregister(&dummy_parent);
-		bus_unregister(&dummy_bus);
-	}
 }
 
 module_init(dummy_init_module);

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -7800,8 +7800,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
 	bp->edev = NULL;
-	if (bp->xdp_prog)
-		bpf_prog_put(bp->xdp_prog);
 	bnxt_cleanup_pci(bp);
 	free_netdev(dev);
 }

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -4308,9 +4308,6 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
 	mlx5e_ipsec_cleanup(priv);
 	mlx5e_vxlan_cleanup(priv);
-
-	if (priv->channels.params.xdp_prog)
-		bpf_prog_put(priv->channels.params.xdp_prog);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)

drivers/net/ethernet/netronome/nfp/bpf/main.c

@@ -82,12 +82,6 @@ static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn)
 	return nfp_net_ebpf_capable(nn) ? "BPF" : "";
 }
 
-static void nfp_bpf_vnic_free(struct nfp_app *app, struct nfp_net *nn)
-{
-	if (nn->dp.bpf_offload_xdp)
-		nfp_bpf_xdp_offload(app, nn, NULL);
-}
-
 static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type,
 				     void *type_data, void *cb_priv)
 {
@@ -168,7 +162,6 @@ const struct nfp_app_type app_bpf = {
 	.extra_cap	= nfp_bpf_extra_cap,
 
 	.vnic_alloc	= nfp_app_nic_vnic_alloc,
-	.vnic_free	= nfp_bpf_vnic_free,
 
 	.setup_tc	= nfp_bpf_setup_tc,
 	.tc_busy	= nfp_bpf_tc_busy,

drivers/net/ethernet/netronome/nfp/nfp_net_common.c

@@ -3392,6 +3392,7 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 		if (nn->dp.bpf_offload_xdp)
 			xdp->prog_attached = XDP_ATTACHED_HW;
 		xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
+		xdp->flags = nn->xdp_prog ? nn->xdp_flags : 0;
 		return 0;
 	case BPF_OFFLOAD_VERIFIER_PREP:
 		return nfp_app_bpf_verifier_prep(nn->app, nn, xdp);
@@ -3561,9 +3562,6 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
  */
 void nfp_net_free(struct nfp_net *nn)
 {
-	if (nn->xdp_prog)
-		bpf_prog_put(nn->xdp_prog);
-
 	if (nn->dp.netdev)
 		free_netdev(nn->dp.netdev);
 	else