Initial commit: Linux kernel 4.19 for Unplugged OS

drivers/net/netdevsim/Makefile

@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_NETDEVSIM) += netdevsim.o
+
+netdevsim-objs := \
+	netdev.o \
+
+ifeq ($(CONFIG_BPF_SYSCALL),y)
+netdevsim-objs += \
+	bpf.o
+endif
+
+ifneq ($(CONFIG_NET_DEVLINK),)
+netdevsim-objs += devlink.o fib.o
+endif
+
+ifneq ($(CONFIG_XFRM_OFFLOAD),)
+netdevsim-objs += ipsec.o
+endif

drivers/net/netdevsim/bpf.c

@@ -0,0 +1,651 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/rtnetlink.h>
+#include <net/pkt_cls.h>
+
+#include "netdevsim.h"
+
+#define pr_vlog(env, fmt, ...)	\
+	bpf_verifier_log_write(env, "[netdevsim] " fmt, ##__VA_ARGS__)
+
+struct nsim_bpf_bound_prog {
+	struct netdevsim *ns;
+	struct bpf_prog *prog;
+	struct dentry *ddir;
+	const char *state;
+	bool is_loaded;
+	struct list_head l;
+};
+
+#define NSIM_BPF_MAX_KEYS		2
+
+struct nsim_bpf_bound_map {
+	struct netdevsim *ns;
+	struct bpf_offloaded_map *map;
+	struct mutex mutex;
+	struct nsim_map_entry {
+		void *key;
+		void *value;
+	} entry[NSIM_BPF_MAX_KEYS];
+	struct list_head l;
+};
+
+static int nsim_debugfs_bpf_string_read(struct seq_file *file, void *data)
+{
+	const char **str = file->private;
+
+	if (*str)
+		seq_printf(file, "%s\n", *str);
+
+	return 0;
+}
+
+static int nsim_debugfs_bpf_string_open(struct inode *inode, struct file *f)
+{
+	return single_open(f, nsim_debugfs_bpf_string_read, inode->i_private);
+}
+
+static const struct file_operations nsim_bpf_string_fops = {
+	.owner = THIS_MODULE,
+	.open = nsim_debugfs_bpf_string_open,
+	.release = single_release,
+	.read = seq_read,
+	.llseek = seq_lseek
+};
+
+static int
+nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn)
+{
+	struct nsim_bpf_bound_prog *state;
+
+	state = env->prog->aux->offload->dev_priv;
+	if (state->ns->bpf_bind_verifier_delay && !insn_idx)
+		msleep(state->ns->bpf_bind_verifier_delay);
+
+	if (insn_idx == env->prog->len - 1)
+		pr_vlog(env, "Hello from netdevsim!\n");
+
+	return 0;
+}
+
+static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = {
+	.insn_hook = nsim_bpf_verify_insn,
+};
+
+static bool nsim_xdp_offload_active(struct netdevsim *ns)
+{
+	return ns->xdp_hw.prog;
+}
+
+static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
+{
+	struct nsim_bpf_bound_prog *state;
+
+	if (!prog || !prog->aux->offload)
+		return;
+
+	state = prog->aux->offload->dev_priv;
+	state->is_loaded = loaded;
+}
+
+static int
+nsim_bpf_offload(struct netdevsim *ns, struct bpf_prog *prog, bool oldprog)
+{
+	nsim_prog_set_loaded(ns->bpf_offloaded, false);
+
+	WARN(!!ns->bpf_offloaded != oldprog,
+	     "bad offload state, expected offload %sto be active",
+	     oldprog ? "" : "not ");
+	ns->bpf_offloaded = prog;
+	ns->bpf_offloaded_id = prog ? prog->aux->id : 0;
+	nsim_prog_set_loaded(prog, true);
+
+	return 0;
+}
+
+int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type,
+			       void *type_data, void *cb_priv)
+{
+	struct tc_cls_bpf_offload *cls_bpf = type_data;
+	struct bpf_prog *prog = cls_bpf->prog;
+	struct netdevsim *ns = cb_priv;
+	struct bpf_prog *oldprog;
+
+	if (type != TC_SETUP_CLSBPF) {
+		NSIM_EA(cls_bpf->common.extack,
+			"only offload of BPF classifiers supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!tc_cls_can_offload_and_chain0(ns->netdev, &cls_bpf->common))
+		return -EOPNOTSUPP;
+
+	if (cls_bpf->common.protocol != htons(ETH_P_ALL)) {
+		NSIM_EA(cls_bpf->common.extack,
+			"only ETH_P_ALL supported as filter protocol");
+		return -EOPNOTSUPP;
+	}
+
+	if (!ns->bpf_tc_accept) {
+		NSIM_EA(cls_bpf->common.extack,
+			"netdevsim configured to reject BPF TC offload");
+		return -EOPNOTSUPP;
+	}
+	/* Note: progs without skip_sw will probably not be dev bound */
+	if (prog && !prog->aux->offload && !ns->bpf_tc_non_bound_accept) {
+		NSIM_EA(cls_bpf->common.extack,
+			"netdevsim configured to reject unbound programs");
+		return -EOPNOTSUPP;
+	}
+
+	if (cls_bpf->command != TC_CLSBPF_OFFLOAD)
+		return -EOPNOTSUPP;
+
+	oldprog = cls_bpf->oldprog;
+
+	/* Don't remove if oldprog doesn't match driver's state */
+	if (ns->bpf_offloaded != oldprog) {
+		oldprog = NULL;
+		if (!cls_bpf->prog)
+			return 0;
+		if (ns->bpf_offloaded) {
+			NSIM_EA(cls_bpf->common.extack,
+				"driver and netdev offload states mismatch");
+			return -EBUSY;
+		}
+	}
+
+	return nsim_bpf_offload(ns, cls_bpf->prog, oldprog);
+}
+
+int nsim_bpf_disable_tc(struct netdevsim *ns)
+{
+	if (ns->bpf_offloaded && !nsim_xdp_offload_active(ns))
+		return -EBUSY;
+	return 0;
+}
+
+static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
+{
+	if (!nsim_xdp_offload_active(ns) && !bpf->prog)
+		return 0;
+	if (!nsim_xdp_offload_active(ns) && bpf->prog && ns->bpf_offloaded) {
+		NSIM_EA(bpf->extack, "TC program is already loaded");
+		return -EBUSY;
+	}
+
+	return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns));
+}
+
+static int
+nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf,
+		  struct xdp_attachment_info *xdp)
+{
+	int err;
+
+	if (!xdp_attachment_flags_ok(xdp, bpf))
+		return -EBUSY;
+
+	if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) {
+		NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS");
+		return -EOPNOTSUPP;
+	}
+	if (bpf->command == XDP_SETUP_PROG_HW && !ns->bpf_xdpoffload_accept) {
+		NSIM_EA(bpf->extack, "XDP offload disabled in DebugFS");
+		return -EOPNOTSUPP;
+	}
+
+	if (bpf->command == XDP_SETUP_PROG_HW) {
+		err = nsim_xdp_offload_prog(ns, bpf);
+		if (err)
+			return err;
+	}
+
+	xdp_attachment_setup(xdp, bpf);
+
+	return 0;
+}
+
+static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
+{
+	struct nsim_bpf_bound_prog *state;
+	char name[16];
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	state->ns = ns;
+	state->prog = prog;
+	state->state = "verify";
+
+	/* Program id is not populated yet when we create the state. */
+	sprintf(name, "%u", ns->sdev->prog_id_gen++);
+	state->ddir = debugfs_create_dir(name, ns->sdev->ddir_bpf_bound_progs);
+	if (IS_ERR_OR_NULL(state->ddir)) {
+		kfree(state);
+		return -ENOMEM;
+	}
+
+	debugfs_create_u32("id", 0400, state->ddir, &prog->aux->id);
+	debugfs_create_file("state", 0400, state->ddir,
+			    &state->state, &nsim_bpf_string_fops);
+	debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded);
+
+	list_add_tail(&state->l, &ns->sdev->bpf_bound_progs);
+
+	prog->aux->offload->dev_priv = state;
+
+	return 0;
+}
+
+static void nsim_bpf_destroy_prog(struct bpf_prog *prog)
+{
+	struct nsim_bpf_bound_prog *state;
+
+	state = prog->aux->offload->dev_priv;
+	WARN(state->is_loaded,
+	     "offload state destroyed while program still bound");
+	debugfs_remove_recursive(state->ddir);
+	list_del(&state->l);
+	kfree(state);
+}
+
+static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
+{
+	if (bpf->prog && bpf->prog->aux->offload) {
+		NSIM_EA(bpf->extack, "attempt to load offloaded prog to drv");
+		return -EINVAL;
+	}
+	if (ns->netdev->mtu > NSIM_XDP_MAX_MTU) {
+		NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int
+nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
+{
+	struct nsim_bpf_bound_prog *state;
+
+	if (!bpf->prog)
+		return 0;
+
+	if (!bpf->prog->aux->offload) {
+		NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
+		return -EINVAL;
+	}
+	if (!bpf_offload_dev_match(bpf->prog, ns->netdev)) {
+		NSIM_EA(bpf->extack, "program bound to different dev");
+		return -EINVAL;
+	}
+
+	state = bpf->prog->aux->offload->dev_priv;
+	if (WARN_ON(strcmp(state->state, "xlated"))) {
+		NSIM_EA(bpf->extack, "offloading program in bad state");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static bool
+nsim_map_key_match(struct bpf_map *map, struct nsim_map_entry *e, void *key)
+{
+	return e->key && !memcmp(key, e->key, map->key_size);
+}
+
+static int nsim_map_key_find(struct bpf_offloaded_map *offmap, void *key)
+{
+	struct nsim_bpf_bound_map *nmap = offmap->dev_priv;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(nmap->entry); i++)
+		if (nsim_map_key_match(&offmap->map, &nmap->entry[i], key))
+			return i;
+
+	return -ENOENT;
+}
+
+static int
+nsim_map_alloc_elem(struct bpf_offloaded_map *offmap, unsigned int idx)
+{
+	struct nsim_bpf_bound_map *nmap = offmap->dev_priv;
+
+	nmap->entry[idx].key = kmalloc(offmap->map.key_size, GFP_USER);
+	if (!nmap->entry[idx].key)
+		return -ENOMEM;
+	nmap->entry[idx].value = kmalloc(offmap->map.value_size, GFP_USER);
+	if (!nmap->entry[idx].value) {
+		kfree(nmap->entry[idx].key);
+		nmap->entry[idx].key = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int
+nsim_map_get_next_key(struct bpf_offloaded_map *offmap,
+		      void *key, void *next_key)
+{
+	struct nsim_bpf_bound_map *nmap = offmap->dev_priv;
+	int idx = -ENOENT;
+
+	mutex_lock(&nmap->mutex);
+
+	if (key)
+		idx = nsim_map_key_find(offmap, key);
+	if (idx == -ENOENT)
+		idx = 0;
+	else
+		idx++;
+
+	for (; idx < ARRAY_SIZE(nmap->entry); idx++) {
+		if (nmap->entry[idx].key) {
+			memcpy(next_key, nmap->entry[idx].key,
+			       offmap->map.key_size);
+			break;
+		}
+	}
+
+	mutex_unlock(&nmap->mutex);
+
+	if (idx == ARRAY_SIZE(nmap->entry))
+		return -ENOENT;
+	return 0;
+}
+
+static int
+nsim_map_lookup_elem(struct bpf_offloaded_map *offmap, void *key, void *value)
+{
+	struct nsim_bpf_bound_map *nmap = offmap->dev_priv;
+	int idx;
+
+	mutex_lock(&nmap->mutex);
+
+	idx = nsim_map_key_find(offmap, key);
+	if (idx >= 0)
+		memcpy(value, nmap->entry[idx].value, offmap->map.value_size);
+
+	mutex_unlock(&nmap->mutex);
+
+	return idx < 0 ? idx : 0;
+}
+
+static int
+nsim_map_update_elem(struct bpf_offloaded_map *offmap,
+		     void *key, void *value, u64 flags)
+{
+	struct nsim_bpf_bound_map *nmap = offmap->dev_priv;
+	int idx, err = 0;
+
+	mutex_lock(&nmap->mutex);
+
+	idx = nsim_map_key_find(offmap, key);
+	if (idx < 0 && flags == BPF_EXIST) {
+		err = idx;
+		goto exit_unlock;
+	}
+	if (idx >= 0 && flags == BPF_NOEXIST) {
+		err = -EEXIST;
+		goto exit_unlock;
+	}
+
+	if (idx < 0) {
+		for (idx = 0; idx < ARRAY_SIZE(nmap->entry); idx++)
+			if (!nmap->entry[idx].key)
+				break;
+		if (idx == ARRAY_SIZE(nmap->entry)) {
+			err = -E2BIG;
+			goto exit_unlock;
+		}
+
+		err = nsim_map_alloc_elem(offmap, idx);
+		if (err)
+			goto exit_unlock;
+	}
+
+	memcpy(nmap->entry[idx].key, key, offmap->map.key_size);
+	memcpy(nmap->entry[idx].value, value, offmap->map.value_size);
+exit_unlock:
+	mutex_unlock(&nmap->mutex);
+
+	return err;
+}
+
+static int nsim_map_delete_elem(struct bpf_offloaded_map *offmap, void *key)
+{
+	struct nsim_bpf_bound_map *nmap = offmap->dev_priv;
+	int idx;
+
+	if (offmap->map.map_type == BPF_MAP_TYPE_ARRAY)
+		return -EINVAL;
+
+	mutex_lock(&nmap->mutex);
+
+	idx = nsim_map_key_find(offmap, key);
+	if (idx >= 0) {
+		kfree(nmap->entry[idx].key);
+		kfree(nmap->entry[idx].value);
+		memset(&nmap->entry[idx], 0, sizeof(nmap->entry[idx]));
+	}
+
+	mutex_unlock(&nmap->mutex);
+
+	return idx < 0 ? idx : 0;
+}
+
+static const struct bpf_map_dev_ops nsim_bpf_map_ops = {
+	.map_get_next_key	= nsim_map_get_next_key,
+	.map_lookup_elem	= nsim_map_lookup_elem,
+	.map_update_elem	= nsim_map_update_elem,
+	.map_delete_elem	= nsim_map_delete_elem,
+};
+
+static int
+nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
+{
+	struct nsim_bpf_bound_map *nmap;
+	int i, err;
+
+	if (WARN_ON(offmap->map.map_type != BPF_MAP_TYPE_ARRAY &&
+		    offmap->map.map_type != BPF_MAP_TYPE_HASH))
+		return -EINVAL;
+	if (offmap->map.max_entries > NSIM_BPF_MAX_KEYS)
+		return -ENOMEM;
+	if (offmap->map.map_flags)
+		return -EINVAL;
+
+	nmap = kzalloc(sizeof(*nmap), GFP_USER);
+	if (!nmap)
+		return -ENOMEM;
+
+	offmap->dev_priv = nmap;
+	nmap->ns = ns;
+	nmap->map = offmap;
+	mutex_init(&nmap->mutex);
+
+	if (offmap->map.map_type == BPF_MAP_TYPE_ARRAY) {
+		for (i = 0; i < ARRAY_SIZE(nmap->entry); i++) {
+			u32 *key;
+
+			err = nsim_map_alloc_elem(offmap, i);
+			if (err)
+				goto err_free;
+			key = nmap->entry[i].key;
+			*key = i;
+		}
+	}
+
+	offmap->dev_ops = &nsim_bpf_map_ops;
+	list_add_tail(&nmap->l, &ns->sdev->bpf_bound_maps);
+
+	return 0;
+
+err_free:
+	while (--i >= 0) {
+		kfree(nmap->entry[i].key);
+		kfree(nmap->entry[i].value);
+	}
+	kfree(nmap);
+	return err;
+}
+
+static void nsim_bpf_map_free(struct bpf_offloaded_map *offmap)
+{
+	struct nsim_bpf_bound_map *nmap = offmap->dev_priv;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(nmap->entry); i++) {
+		kfree(nmap->entry[i].key);
+		kfree(nmap->entry[i].value);
+	}
+	list_del_init(&nmap->l);
+	mutex_destroy(&nmap->mutex);
+	kfree(nmap);
+}
+
+int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	struct nsim_bpf_bound_prog *state;
+	int err;
+
+	ASSERT_RTNL();
+
+	switch (bpf->command) {
+	case BPF_OFFLOAD_VERIFIER_PREP:
+		if (!ns->bpf_bind_accept)
+			return -EOPNOTSUPP;
+
+		err = nsim_bpf_create_prog(ns, bpf->verifier.prog);
+		if (err)
+			return err;
+
+		bpf->verifier.ops = &nsim_bpf_analyzer_ops;
+		return 0;
+	case BPF_OFFLOAD_TRANSLATE:
+		state = bpf->offload.prog->aux->offload->dev_priv;
+
+		state->state = "xlated";
+		return 0;
+	case BPF_OFFLOAD_DESTROY:
+		nsim_bpf_destroy_prog(bpf->offload.prog);
+		return 0;
+	case XDP_QUERY_PROG:
+		return xdp_attachment_query(&ns->xdp, bpf);
+	case XDP_QUERY_PROG_HW:
+		return xdp_attachment_query(&ns->xdp_hw, bpf);
+	case XDP_SETUP_PROG:
+		err = nsim_setup_prog_checks(ns, bpf);
+		if (err)
+			return err;
+
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp);
+	case XDP_SETUP_PROG_HW:
+		err = nsim_setup_prog_hw_checks(ns, bpf);
+		if (err)
+			return err;
+
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw);
+	case BPF_OFFLOAD_MAP_ALLOC:
+		if (!ns->bpf_map_accept)
+			return -EOPNOTSUPP;
+
+		return nsim_bpf_map_alloc(ns, bpf->offmap);
+	case BPF_OFFLOAD_MAP_FREE:
+		nsim_bpf_map_free(bpf->offmap);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+int nsim_bpf_init(struct netdevsim *ns)
+{
+	int err;
+
+	if (ns->sdev->refcnt == 1) {
+		INIT_LIST_HEAD(&ns->sdev->bpf_bound_progs);
+		INIT_LIST_HEAD(&ns->sdev->bpf_bound_maps);
+
+		ns->sdev->ddir_bpf_bound_progs =
+			debugfs_create_dir("bpf_bound_progs", ns->sdev->ddir);
+		if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs))
+			return -ENOMEM;
+
+		ns->sdev->bpf_dev = bpf_offload_dev_create();
+		err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev);
+		if (err)
+			return err;
+	}
+
+	err = bpf_offload_dev_netdev_register(ns->sdev->bpf_dev, ns->netdev);
+	if (err)
+		goto err_destroy_bdev;
+
+	debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir,
+			   &ns->bpf_offloaded_id);
+
+	ns->bpf_bind_accept = true;
+	debugfs_create_bool("bpf_bind_accept", 0600, ns->ddir,
+			    &ns->bpf_bind_accept);
+	debugfs_create_u32("bpf_bind_verifier_delay", 0600, ns->ddir,
+			   &ns->bpf_bind_verifier_delay);
+
+	ns->bpf_tc_accept = true;
+	debugfs_create_bool("bpf_tc_accept", 0600, ns->ddir,
+			    &ns->bpf_tc_accept);
+	debugfs_create_bool("bpf_tc_non_bound_accept", 0600, ns->ddir,
+			    &ns->bpf_tc_non_bound_accept);
+	ns->bpf_xdpdrv_accept = true;
+	debugfs_create_bool("bpf_xdpdrv_accept", 0600, ns->ddir,
+			    &ns->bpf_xdpdrv_accept);
+	ns->bpf_xdpoffload_accept = true;
+	debugfs_create_bool("bpf_xdpoffload_accept", 0600, ns->ddir,
+			    &ns->bpf_xdpoffload_accept);
+
+	ns->bpf_map_accept = true;
+	debugfs_create_bool("bpf_map_accept", 0600, ns->ddir,
+			    &ns->bpf_map_accept);
+
+	return 0;
+
+err_destroy_bdev:
+	if (ns->sdev->refcnt == 1)
+		bpf_offload_dev_destroy(ns->sdev->bpf_dev);
+	return err;
+}
+
+void nsim_bpf_uninit(struct netdevsim *ns)
+{
+	WARN_ON(ns->xdp.prog);
+	WARN_ON(ns->xdp_hw.prog);
+	WARN_ON(ns->bpf_offloaded);
+	bpf_offload_dev_netdev_unregister(ns->sdev->bpf_dev, ns->netdev);
+
+	if (ns->sdev->refcnt == 1) {
+		WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs));
+		WARN_ON(!list_empty(&ns->sdev->bpf_bound_maps));
+		bpf_offload_dev_destroy(ns->sdev->bpf_dev);
+	}
+}

drivers/net/netdevsim/devlink.c

@@ -0,0 +1,295 @@
+/*
+ * Copyright (c) 2018 Cumulus Networks. All rights reserved.
+ * Copyright (c) 2018 David Ahern <dsa@cumulusnetworks.com>
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <linux/device.h>
+#include <net/devlink.h>
+#include <net/netns/generic.h>
+
+#include "netdevsim.h"
+
+static unsigned int nsim_devlink_id;
+
+/* place holder until devlink and namespaces is sorted out */
+static struct net *nsim_devlink_net(struct devlink *devlink)
+{
+	return &init_net;
+}
+
+/* IPv4
+ */
+static u64 nsim_ipv4_fib_resource_occ_get(void *priv)
+{
+	struct net *net = priv;
+
+	return nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB, false);
+}
+
+static u64 nsim_ipv4_fib_rules_res_occ_get(void *priv)
+{
+	struct net *net = priv;
+
+	return nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB_RULES, false);
+}
+
+/* IPv6
+ */
+static u64 nsim_ipv6_fib_resource_occ_get(void *priv)
+{
+	struct net *net = priv;
+
+	return nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB, false);
+}
+
+static u64 nsim_ipv6_fib_rules_res_occ_get(void *priv)
+{
+	struct net *net = priv;
+
+	return nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB_RULES, false);
+}
+
+static int devlink_resources_register(struct devlink *devlink)
+{
+	struct devlink_resource_size_params params = {
+		.size_max = (u64)-1,
+		.size_granularity = 1,
+		.unit = DEVLINK_RESOURCE_UNIT_ENTRY
+	};
+	struct net *net = nsim_devlink_net(devlink);
+	int err;
+	u64 n;
+
+	/* Resources for IPv4 */
+	err = devlink_resource_register(devlink, "IPv4", (u64)-1,
+					NSIM_RESOURCE_IPV4,
+					DEVLINK_RESOURCE_ID_PARENT_TOP,
+					&params);
+	if (err) {
+		pr_err("Failed to register IPv4 top resource\n");
+		goto out;
+	}
+
+	n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB, true);
+	err = devlink_resource_register(devlink, "fib", n,
+					NSIM_RESOURCE_IPV4_FIB,
+					NSIM_RESOURCE_IPV4, &params);
+	if (err) {
+		pr_err("Failed to register IPv4 FIB resource\n");
+		return err;
+	}
+
+	n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB_RULES, true);
+	err = devlink_resource_register(devlink, "fib-rules", n,
+					NSIM_RESOURCE_IPV4_FIB_RULES,
+					NSIM_RESOURCE_IPV4, &params);
+	if (err) {
+		pr_err("Failed to register IPv4 FIB rules resource\n");
+		return err;
+	}
+
+	/* Resources for IPv6 */
+	err = devlink_resource_register(devlink, "IPv6", (u64)-1,
+					NSIM_RESOURCE_IPV6,
+					DEVLINK_RESOURCE_ID_PARENT_TOP,
+					&params);
+	if (err) {
+		pr_err("Failed to register IPv6 top resource\n");
+		goto out;
+	}
+
+	n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB, true);
+	err = devlink_resource_register(devlink, "fib", n,
+					NSIM_RESOURCE_IPV6_FIB,
+					NSIM_RESOURCE_IPV6, &params);
+	if (err) {
+		pr_err("Failed to register IPv6 FIB resource\n");
+		return err;
+	}
+
+	n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB_RULES, true);
+	err = devlink_resource_register(devlink, "fib-rules", n,
+					NSIM_RESOURCE_IPV6_FIB_RULES,
+					NSIM_RESOURCE_IPV6, &params);
+	if (err) {
+		pr_err("Failed to register IPv6 FIB rules resource\n");
+		return err;
+	}
+
+	devlink_resource_occ_get_register(devlink,
+					  NSIM_RESOURCE_IPV4_FIB,
+					  nsim_ipv4_fib_resource_occ_get,
+					  net);
+	devlink_resource_occ_get_register(devlink,
+					  NSIM_RESOURCE_IPV4_FIB_RULES,
+					  nsim_ipv4_fib_rules_res_occ_get,
+					  net);
+	devlink_resource_occ_get_register(devlink,
+					  NSIM_RESOURCE_IPV6_FIB,
+					  nsim_ipv6_fib_resource_occ_get,
+					  net);
+	devlink_resource_occ_get_register(devlink,
+					  NSIM_RESOURCE_IPV6_FIB_RULES,
+					  nsim_ipv6_fib_rules_res_occ_get,
+					  net);
+out:
+	return err;
+}
+
+static int nsim_devlink_reload(struct devlink *devlink,
+			       struct netlink_ext_ack *extack)
+{
+	enum nsim_resource_id res_ids[] = {
+		NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES,
+		NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES
+	};
+	struct net *net = nsim_devlink_net(devlink);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(res_ids); ++i) {
+		int err;
+		u64 val;
+
+		err = devlink_resource_size_get(devlink, res_ids[i], &val);
+		if (!err) {
+			err = nsim_fib_set_max(net, res_ids[i], val, extack);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static void nsim_devlink_net_reset(struct net *net)
+{
+	enum nsim_resource_id res_ids[] = {
+		NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES,
+		NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(res_ids); ++i) {
+		if (nsim_fib_set_max(net, res_ids[i], (u64)-1, NULL)) {
+			pr_err("Failed to reset limit for resource %u\n",
+			       res_ids[i]);
+		}
+	}
+}
+
+static const struct devlink_ops nsim_devlink_ops = {
+	.reload = nsim_devlink_reload,
+};
+
+/* once devlink / namespace issues are sorted out
+ * this needs to be net in which a devlink instance
+ * is to be created. e.g., dev_net(ns->netdev)
+ */
+static struct net *nsim_to_net(struct netdevsim *ns)
+{
+	return &init_net;
+}
+
+void nsim_devlink_teardown(struct netdevsim *ns)
+{
+	if (ns->devlink) {
+		struct net *net = nsim_to_net(ns);
+		bool *reg_devlink = net_generic(net, nsim_devlink_id);
+
+		devlink_resources_unregister(ns->devlink, NULL);
+		devlink_unregister(ns->devlink);
+		devlink_free(ns->devlink);
+		ns->devlink = NULL;
+
+		nsim_devlink_net_reset(net);
+		*reg_devlink = true;
+	}
+}
+
+int nsim_devlink_setup(struct netdevsim *ns)
+{
+	struct net *net = nsim_to_net(ns);
+	bool *reg_devlink = net_generic(net, nsim_devlink_id);
+	struct devlink *devlink;
+	int err;
+
+	/* only one device per namespace controls devlink */
+	if (!*reg_devlink) {
+		ns->devlink = NULL;
+		return 0;
+	}
+
+	devlink = devlink_alloc(&nsim_devlink_ops, 0);
+	if (!devlink)
+		return -ENOMEM;
+
+	err = devlink_register(devlink, &ns->dev);
+	if (err)
+		goto err_devlink_free;
+
+	err = devlink_resources_register(devlink);
+	if (err)
+		goto err_dl_unregister;
+
+	ns->devlink = devlink;
+
+	*reg_devlink = false;
+
+	return 0;
+
+err_dl_unregister:
+	devlink_unregister(devlink);
+err_devlink_free:
+	devlink_free(devlink);
+
+	return err;
+}
+
+/* Initialize per network namespace state */
+static int __net_init nsim_devlink_netns_init(struct net *net)
+{
+	bool *reg_devlink = net_generic(net, nsim_devlink_id);
+
+	*reg_devlink = true;
+
+	return 0;
+}
+
+static struct pernet_operations nsim_devlink_net_ops = {
+	.init = nsim_devlink_netns_init,
+	.id   = &nsim_devlink_id,
+	.size = sizeof(bool),
+};
+
+void nsim_devlink_exit(void)
+{
+	unregister_pernet_subsys(&nsim_devlink_net_ops);
+	nsim_fib_exit();
+}
+
+int nsim_devlink_init(void)
+{
+	int err;
+
+	err = nsim_fib_init();
+	if (err)
+		goto err_out;
+
+	err = register_pernet_subsys(&nsim_devlink_net_ops);
+	if (err)
+		nsim_fib_exit();
+
+err_out:
+	return err;
+}

drivers/net/netdevsim/fib.c

@@ -0,0 +1,266 @@
+/*
+ * Copyright (c) 2018 Cumulus Networks. All rights reserved.
+ * Copyright (c) 2018 David Ahern <dsa@cumulusnetworks.com>
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <net/fib_notifier.h>
+#include <net/ip_fib.h>
+#include <net/ip6_fib.h>
+#include <net/fib_rules.h>
+#include <net/netns/generic.h>
+
+#include "netdevsim.h"
+
+struct nsim_fib_entry {
+	u64 max;
+	u64 num;
+};
+
+struct nsim_per_fib_data {
+	struct nsim_fib_entry fib;
+	struct nsim_fib_entry rules;
+};
+
+struct nsim_fib_data {
+	struct nsim_per_fib_data ipv4;
+	struct nsim_per_fib_data ipv6;
+};
+
+static unsigned int nsim_fib_net_id;
+
+u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max)
+{
+	struct nsim_fib_data *fib_data = net_generic(net, nsim_fib_net_id);
+	struct nsim_fib_entry *entry;
+
+	switch (res_id) {
+	case NSIM_RESOURCE_IPV4_FIB:
+		entry = &fib_data->ipv4.fib;
+		break;
+	case NSIM_RESOURCE_IPV4_FIB_RULES:
+		entry = &fib_data->ipv4.rules;
+		break;
+	case NSIM_RESOURCE_IPV6_FIB:
+		entry = &fib_data->ipv6.fib;
+		break;
+	case NSIM_RESOURCE_IPV6_FIB_RULES:
+		entry = &fib_data->ipv6.rules;
+		break;
+	default:
+		return 0;
+	}
+
+	return max ? entry->max : entry->num;
+}
+
+int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val,
+		     struct netlink_ext_ack *extack)
+{
+	struct nsim_fib_data *fib_data = net_generic(net, nsim_fib_net_id);
+	struct nsim_fib_entry *entry;
+	int err = 0;
+
+	switch (res_id) {
+	case NSIM_RESOURCE_IPV4_FIB:
+		entry = &fib_data->ipv4.fib;
+		break;
+	case NSIM_RESOURCE_IPV4_FIB_RULES:
+		entry = &fib_data->ipv4.rules;
+		break;
+	case NSIM_RESOURCE_IPV6_FIB:
+		entry = &fib_data->ipv6.fib;
+		break;
+	case NSIM_RESOURCE_IPV6_FIB_RULES:
+		entry = &fib_data->ipv6.rules;
+		break;
+	default:
+		return 0;
+	}
+
+	/* not allowing a new max to be less than curren occupancy
+	 * --> no means of evicting entries
+	 */
+	if (val < entry->num) {
+		NL_SET_ERR_MSG_MOD(extack, "New size is less than current occupancy");
+		err = -EINVAL;
+	} else {
+		entry->max = val;
+	}
+
+	return err;
+}
+
+static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add,
+				 struct netlink_ext_ack *extack)
+{
+	int err = 0;
+
+	if (add) {
+		if (entry->num < entry->max) {
+			entry->num++;
+		} else {
+			err = -ENOSPC;
+			NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib rule entries");
+		}
+	} else {
+		entry->num--;
+	}
+
+	return err;
+}
+
+static int nsim_fib_rule_event(struct fib_notifier_info *info, bool add)
+{
+	struct nsim_fib_data *data = net_generic(info->net, nsim_fib_net_id);
+	struct netlink_ext_ack *extack = info->extack;
+	int err = 0;
+
+	switch (info->family) {
+	case AF_INET:
+		err = nsim_fib_rule_account(&data->ipv4.rules, add, extack);
+		break;
+	case AF_INET6:
+		err = nsim_fib_rule_account(&data->ipv6.rules, add, extack);
+		break;
+	}
+
+	return err;
+}
+
+static int nsim_fib_account(struct nsim_fib_entry *entry, bool add,
+			    struct netlink_ext_ack *extack)
+{
+	int err = 0;
+
+	if (add) {
+		if (entry->num < entry->max) {
+			entry->num++;
+		} else {
+			err = -ENOSPC;
+			NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries");
+		}
+	} else {
+		entry->num--;
+	}
+
+	return err;
+}
+
+static int nsim_fib_event(struct fib_notifier_info *info, bool add)
+{
+	struct nsim_fib_data *data = net_generic(info->net, nsim_fib_net_id);
+	struct netlink_ext_ack *extack = info->extack;
+	int err = 0;
+
+	switch (info->family) {
+	case AF_INET:
+		err = nsim_fib_account(&data->ipv4.fib, add, extack);
+		break;
+	case AF_INET6:
+		err = nsim_fib_account(&data->ipv6.fib, add, extack);
+		break;
+	}
+
+	return err;
+}
+
+static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
+			     void *ptr)
+{
+	struct fib_notifier_info *info = ptr;
+	int err = 0;
+
+	switch (event) {
+	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_DEL:
+		err = nsim_fib_rule_event(info, event == FIB_EVENT_RULE_ADD);
+		break;
+
+	case FIB_EVENT_ENTRY_ADD:  /* fall through */
+	case FIB_EVENT_ENTRY_DEL:
+		err = nsim_fib_event(info, event == FIB_EVENT_ENTRY_ADD);
+		break;
+	}
+
+	return notifier_from_errno(err);
+}
+
+/* inconsistent dump, trying again */
+static void nsim_fib_dump_inconsistent(struct notifier_block *nb)
+{
+	struct nsim_fib_data *data;
+	struct net *net;
+
+	rcu_read_lock();
+	for_each_net_rcu(net) {
+		data = net_generic(net, nsim_fib_net_id);
+
+		data->ipv4.fib.num = 0ULL;
+		data->ipv4.rules.num = 0ULL;
+
+		data->ipv6.fib.num = 0ULL;
+		data->ipv6.rules.num = 0ULL;
+	}
+	rcu_read_unlock();
+}
+
+static struct notifier_block nsim_fib_nb = {
+	.notifier_call = nsim_fib_event_nb,
+};
+
+/* Initialize per network namespace state */
+static int __net_init nsim_fib_netns_init(struct net *net)
+{
+	struct nsim_fib_data *data = net_generic(net, nsim_fib_net_id);
+
+	data->ipv4.fib.max = (u64)-1;
+	data->ipv4.rules.max = (u64)-1;
+
+	data->ipv6.fib.max = (u64)-1;
+	data->ipv6.rules.max = (u64)-1;
+
+	return 0;
+}
+
+static struct pernet_operations nsim_fib_net_ops = {
+	.init = nsim_fib_netns_init,
+	.id   = &nsim_fib_net_id,
+	.size = sizeof(struct nsim_fib_data),
+};
+
+void nsim_fib_exit(void)
+{
+	unregister_pernet_subsys(&nsim_fib_net_ops);
+	unregister_fib_notifier(&nsim_fib_nb);
+}
+
+int nsim_fib_init(void)
+{
+	int err;
+
+	err = register_pernet_subsys(&nsim_fib_net_ops);
+	if (err < 0) {
+		pr_err("Failed to register pernet subsystem\n");
+		goto err_out;
+	}
+
+	err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent);
+	if (err < 0) {
+		pr_err("Failed to register fib notifier\n");
+		goto err_out;
+	}
+
+err_out:
+	return err;
+}

drivers/net/netdevsim/ipsec.c

@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */
+
+#include <crypto/aead.h>
+#include <linux/debugfs.h>
+#include <net/xfrm.h>
+
+#include "netdevsim.h"
+
+#define NSIM_IPSEC_AUTH_BITS	128
+
+static ssize_t nsim_dbg_netdev_ops_read(struct file *filp,
+					char __user *buffer,
+					size_t count, loff_t *ppos)
+{
+	struct netdevsim *ns = filp->private_data;
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	size_t bufsize;
+	char *buf, *p;
+	int len;
+	int i;
+
+	/* the buffer needed is
+	 * (num SAs * 3 lines each * ~60 bytes per line) + one more line
+	 */
+	bufsize = (ipsec->count * 4 * 60) + 60;
+	buf = kzalloc(bufsize, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	p = buf;
+	p += snprintf(p, bufsize - (p - buf),
+		      "SA count=%u tx=%u\n",
+		      ipsec->count, ipsec->tx);
+
+	for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+		struct nsim_sa *sap = &ipsec->sa[i];
+
+		if (!sap->used)
+			continue;
+
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n",
+			      i, (sap->rx ? 'r' : 't'), sap->ipaddr[0],
+			      sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]);
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i]    spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n",
+			      i, be32_to_cpu(sap->xs->id.spi),
+			      sap->xs->id.proto, sap->salt, sap->crypt);
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i]    key=0x%08x %08x %08x %08x\n",
+			      i, sap->key[0], sap->key[1],
+			      sap->key[2], sap->key[3]);
+	}
+
+	len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf);
+
+	kfree(buf);
+	return len;
+}
+
+static const struct file_operations ipsec_dbg_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = nsim_dbg_netdev_ops_read,
+};
+
+static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec)
+{
+	u32 i;
+
+	if (ipsec->count == NSIM_IPSEC_MAX_SA_COUNT)
+		return -ENOSPC;
+
+	/* search sa table */
+	for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+		if (!ipsec->sa[i].used)
+			return i;
+	}
+
+	return -ENOSPC;
+}
+
+static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs,
+				       u32 *mykey, u32 *mysalt)
+{
+	const char aes_gcm_name[] = "rfc4106(gcm(aes))";
+	struct net_device *dev = xs->xso.dev;
+	unsigned char *key_data;
+	char *alg_name = NULL;
+	int key_len;
+
+	if (!xs->aead) {
+		netdev_err(dev, "Unsupported IPsec algorithm\n");
+		return -EINVAL;
+	}
+
+	if (xs->aead->alg_icv_len != NSIM_IPSEC_AUTH_BITS) {
+		netdev_err(dev, "IPsec offload requires %d bit authentication\n",
+			   NSIM_IPSEC_AUTH_BITS);
+		return -EINVAL;
+	}
+
+	key_data = &xs->aead->alg_key[0];
+	key_len = xs->aead->alg_key_len;
+	alg_name = xs->aead->alg_name;
+
+	if (strcmp(alg_name, aes_gcm_name)) {
+		netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n",
+			   aes_gcm_name);
+		return -EINVAL;
+	}
+
+	/* 160 accounts for 16 byte key and 4 byte salt */
+	if (key_len > NSIM_IPSEC_AUTH_BITS) {
+		*mysalt = ((u32 *)key_data)[4];
+	} else if (key_len == NSIM_IPSEC_AUTH_BITS) {
+		*mysalt = 0;
+	} else {
+		netdev_err(dev, "IPsec hw offload only supports 128 bit keys with optional 32 bit salt\n");
+		return -EINVAL;
+	}
+	memcpy(mykey, key_data, 16);
+
+	return 0;
+}
+
+static int nsim_ipsec_add_sa(struct xfrm_state *xs)
+{
+	struct nsim_ipsec *ipsec;
+	struct net_device *dev;
+	struct netdevsim *ns;
+	struct nsim_sa sa;
+	u16 sa_idx;
+	int ret;
+
+	dev = xs->xso.dev;
+	ns = netdev_priv(dev);
+	ipsec = &ns->ipsec;
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n",
+			   xs->id.proto);
+		return -EINVAL;
+	}
+
+	if (xs->calg) {
+		netdev_err(dev, "Compression offload not supported\n");
+		return -EINVAL;
+	}
+
+	/* find the first unused index */
+	ret = nsim_ipsec_find_empty_idx(ipsec);
+	if (ret < 0) {
+		netdev_err(dev, "No space for SA in Rx table!\n");
+		return ret;
+	}
+	sa_idx = (u16)ret;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.used = true;
+	sa.xs = xs;
+
+	if (sa.xs->id.proto & IPPROTO_ESP)
+		sa.crypt = xs->ealg || xs->aead;
+
+	/* get the key and salt */
+	ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt);
+	if (ret) {
+		netdev_err(dev, "Failed to get key data for SA table\n");
+		return ret;
+	}
+
+	if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+		sa.rx = true;
+
+		if (xs->props.family == AF_INET6)
+			memcpy(sa.ipaddr, &xs->id.daddr.a6, 16);
+		else
+			memcpy(&sa.ipaddr[3], &xs->id.daddr.a4, 4);
+	}
+
+	/* the preparations worked, so save the info */
+	memcpy(&ipsec->sa[sa_idx], &sa, sizeof(sa));
+
+	/* the XFRM stack doesn't like offload_handle == 0,
+	 * so add a bitflag in case our array index is 0
+	 */
+	xs->xso.offload_handle = sa_idx | NSIM_IPSEC_VALID;
+	ipsec->count++;
+
+	return 0;
+}
+
+static void nsim_ipsec_del_sa(struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(xs->xso.dev);
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	u16 sa_idx;
+
+	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+	if (!ipsec->sa[sa_idx].used) {
+		netdev_err(ns->netdev, "Invalid SA for delete sa_idx=%d\n",
+			   sa_idx);
+		return;
+	}
+
+	memset(&ipsec->sa[sa_idx], 0, sizeof(struct nsim_sa));
+	ipsec->count--;
+}
+
+static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(xs->xso.dev);
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+
+	ipsec->ok++;
+
+	return true;
+}
+
+static const struct xfrmdev_ops nsim_xfrmdev_ops = {
+	.xdo_dev_state_add	= nsim_ipsec_add_sa,
+	.xdo_dev_state_delete	= nsim_ipsec_del_sa,
+	.xdo_dev_offload_ok	= nsim_ipsec_offload_ok,
+};
+
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	struct xfrm_state *xs;
+	struct nsim_sa *tsa;
+	u32 sa_idx;
+
+	/* do we even need to check this packet? */
+	if (!skb->sp)
+		return true;
+
+	if (unlikely(!skb->sp->len)) {
+		netdev_err(ns->netdev, "no xfrm state len = %d\n",
+			   skb->sp->len);
+		return false;
+	}
+
+	xs = xfrm_input_state(skb);
+	if (unlikely(!xs)) {
+		netdev_err(ns->netdev, "no xfrm_input_state() xs = %p\n", xs);
+		return false;
+	}
+
+	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+	if (unlikely(sa_idx >= NSIM_IPSEC_MAX_SA_COUNT)) {
+		netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n",
+			   sa_idx, NSIM_IPSEC_MAX_SA_COUNT);
+		return false;
+	}
+
+	tsa = &ipsec->sa[sa_idx];
+	if (unlikely(!tsa->used)) {
+		netdev_err(ns->netdev, "unused sa_idx=%d\n", sa_idx);
+		return false;
+	}
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(ns->netdev, "unexpected proto=%d\n", xs->id.proto);
+		return false;
+	}
+
+	ipsec->tx++;
+
+	return true;
+}
+
+void nsim_ipsec_init(struct netdevsim *ns)
+{
+	ns->netdev->xfrmdev_ops = &nsim_xfrmdev_ops;
+
+#define NSIM_ESP_FEATURES	(NETIF_F_HW_ESP | \
+				 NETIF_F_HW_ESP_TX_CSUM | \
+				 NETIF_F_GSO_ESP)
+
+	ns->netdev->features |= NSIM_ESP_FEATURES;
+	ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES;
+
+	ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, ns->ddir, ns,
+					      &ipsec_dbg_fops);
+}
+
+void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+
+	if (ipsec->count)
+		netdev_err(ns->netdev, "tearing down IPsec offload with %d SAs left\n",
+			   ipsec->count);
+	debugfs_remove_recursive(ipsec->pfile);
+}

drivers/net/netdevsim/netdev.c

@@ -0,0 +1,623 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <net/netlink.h>
+#include <net/pkt_cls.h>
+#include <net/rtnetlink.h>
+#include <net/switchdev.h>
+
+#include "netdevsim.h"
+
+struct nsim_vf_config {
+	int link_state;
+	u16 min_tx_rate;
+	u16 max_tx_rate;
+	u16 vlan;
+	__be16 vlan_proto;
+	u16 qos;
+	u8 vf_mac[ETH_ALEN];
+	bool spoofchk_enabled;
+	bool trusted;
+	bool rss_query_enabled;
+};
+
+static u32 nsim_dev_id;
+
+static struct dentry *nsim_ddir;
+static struct dentry *nsim_sdev_ddir;
+
+static int nsim_num_vf(struct device *dev)
+{
+	struct netdevsim *ns = to_nsim(dev);
+
+	return ns->num_vfs;
+}
+
+static struct bus_type nsim_bus = {
+	.name		= DRV_NAME,
+	.dev_name	= DRV_NAME,
+	.num_vf		= nsim_num_vf,
+};
+
+static int nsim_vfs_enable(struct netdevsim *ns, unsigned int num_vfs)
+{
+	ns->vfconfigs = kcalloc(num_vfs, sizeof(struct nsim_vf_config),
+				GFP_KERNEL);
+	if (!ns->vfconfigs)
+		return -ENOMEM;
+	ns->num_vfs = num_vfs;
+
+	return 0;
+}
+
+static void nsim_vfs_disable(struct netdevsim *ns)
+{
+	kfree(ns->vfconfigs);
+	ns->vfconfigs = NULL;
+	ns->num_vfs = 0;
+}
+
+static ssize_t
+nsim_numvfs_store(struct device *dev, struct device_attribute *attr,
+		  const char *buf, size_t count)
+{
+	struct netdevsim *ns = to_nsim(dev);
+	unsigned int num_vfs;
+	int ret;
+
+	ret = kstrtouint(buf, 0, &num_vfs);
+	if (ret)
+		return ret;
+
+	rtnl_lock();
+	if (ns->num_vfs == num_vfs)
+		goto exit_good;
+	if (ns->num_vfs && num_vfs) {
+		ret = -EBUSY;
+		goto exit_unlock;
+	}
+
+	if (num_vfs) {
+		ret = nsim_vfs_enable(ns, num_vfs);
+		if (ret)
+			goto exit_unlock;
+	} else {
+		nsim_vfs_disable(ns);
+	}
+exit_good:
+	ret = count;
+exit_unlock:
+	rtnl_unlock();
+
+	return ret;
+}
+
+static ssize_t
+nsim_numvfs_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct netdevsim *ns = to_nsim(dev);
+
+	return sprintf(buf, "%u\n", ns->num_vfs);
+}
+
+static struct device_attribute nsim_numvfs_attr =
+	__ATTR(sriov_numvfs, 0664, nsim_numvfs_show, nsim_numvfs_store);
+
+static struct attribute *nsim_dev_attrs[] = {
+	&nsim_numvfs_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group nsim_dev_attr_group = {
+	.attrs = nsim_dev_attrs,
+};
+
+static const struct attribute_group *nsim_dev_attr_groups[] = {
+	&nsim_dev_attr_group,
+	NULL,
+};
+
+static void nsim_dev_release(struct device *dev)
+{
+	struct netdevsim *ns = to_nsim(dev);
+
+	nsim_vfs_disable(ns);
+	free_netdev(ns->netdev);
+}
+
+static struct device_type nsim_dev_type = {
+	.groups = nsim_dev_attr_groups,
+	.release = nsim_dev_release,
+};
+
+static int
+nsim_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+		attr->u.ppid.id_len = sizeof(ns->sdev->switch_id);
+		memcpy(&attr->u.ppid.id, &ns->sdev->switch_id,
+		       attr->u.ppid.id_len);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct switchdev_ops nsim_switchdev_ops = {
+	.switchdev_port_attr_get	= nsim_port_attr_get,
+};
+
+static int nsim_init(struct net_device *dev)
+{
+	char sdev_ddir_name[10], sdev_link_name[32];
+	struct netdevsim *ns = netdev_priv(dev);
+	int err;
+
+	ns->netdev = dev;
+	ns->ddir = debugfs_create_dir(netdev_name(dev), nsim_ddir);
+	if (IS_ERR_OR_NULL(ns->ddir))
+		return -ENOMEM;
+
+	if (!ns->sdev) {
+		ns->sdev = kzalloc(sizeof(*ns->sdev), GFP_KERNEL);
+		if (!ns->sdev) {
+			err = -ENOMEM;
+			goto err_debugfs_destroy;
+		}
+		ns->sdev->refcnt = 1;
+		ns->sdev->switch_id = nsim_dev_id;
+		sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
+		ns->sdev->ddir = debugfs_create_dir(sdev_ddir_name,
+						    nsim_sdev_ddir);
+		if (IS_ERR_OR_NULL(ns->sdev->ddir)) {
+			err = PTR_ERR_OR_ZERO(ns->sdev->ddir) ?: -EINVAL;
+			goto err_sdev_free;
+		}
+	} else {
+		sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
+		ns->sdev->refcnt++;
+	}
+
+	sprintf(sdev_link_name, "../../" DRV_NAME "_sdev/%s", sdev_ddir_name);
+	debugfs_create_symlink("sdev", ns->ddir, sdev_link_name);
+
+	err = nsim_bpf_init(ns);
+	if (err)
+		goto err_sdev_destroy;
+
+	ns->dev.id = nsim_dev_id++;
+	ns->dev.bus = &nsim_bus;
+	ns->dev.type = &nsim_dev_type;
+	err = device_register(&ns->dev);
+	if (err)
+		goto err_bpf_uninit;
+
+	SET_NETDEV_DEV(dev, &ns->dev);
+	SWITCHDEV_SET_OPS(dev, &nsim_switchdev_ops);
+
+	err = nsim_devlink_setup(ns);
+	if (err)
+		goto err_unreg_dev;
+
+	nsim_ipsec_init(ns);
+
+	return 0;
+
+err_unreg_dev:
+	device_unregister(&ns->dev);
+err_bpf_uninit:
+	nsim_bpf_uninit(ns);
+err_sdev_destroy:
+	if (!--ns->sdev->refcnt) {
+		debugfs_remove_recursive(ns->sdev->ddir);
+err_sdev_free:
+		kfree(ns->sdev);
+	}
+err_debugfs_destroy:
+	debugfs_remove_recursive(ns->ddir);
+	return err;
+}
+
+static void nsim_uninit(struct net_device *dev)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	nsim_ipsec_teardown(ns);
+	nsim_devlink_teardown(ns);
+	debugfs_remove_recursive(ns->ddir);
+	nsim_bpf_uninit(ns);
+	if (!--ns->sdev->refcnt) {
+		debugfs_remove_recursive(ns->sdev->ddir);
+		kfree(ns->sdev);
+	}
+}
+
+static void nsim_free(struct net_device *dev)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	device_unregister(&ns->dev);
+	/* netdev and vf state will be freed out of device_release() */
+}
+
+static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (!nsim_ipsec_tx(ns, skb))
+		goto out;
+
+	u64_stats_update_begin(&ns->syncp);
+	ns->tx_packets++;
+	ns->tx_bytes += skb->len;
+	u64_stats_update_end(&ns->syncp);
+
+out:
+	dev_kfree_skb(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static void nsim_set_rx_mode(struct net_device *dev)
+{
+}
+
+static int nsim_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
+		return -EBUSY;
+
+	dev->mtu = new_mtu;
+
+	return 0;
+}
+
+static void
+nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	unsigned int start;
+
+	do {
+		start = u64_stats_fetch_begin(&ns->syncp);
+		stats->tx_bytes = ns->tx_bytes;
+		stats->tx_packets = ns->tx_packets;
+	} while (u64_stats_fetch_retry(&ns->syncp, start));
+}
+
+static int
+nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+{
+	return nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv);
+}
+
+static int
+nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb,
+					     ns, ns, f->extack);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int nsim_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	/* Only refuse multicast addresses, zero address can mean unset/any. */
+	if (vf >= ns->num_vfs || is_multicast_ether_addr(mac))
+		return -EINVAL;
+	memcpy(ns->vfconfigs[vf].vf_mac, mac, ETH_ALEN);
+
+	return 0;
+}
+
+static int nsim_set_vf_vlan(struct net_device *dev, int vf,
+			    u16 vlan, u8 qos, __be16 vlan_proto)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (vf >= ns->num_vfs || vlan > 4095 || qos > 7)
+		return -EINVAL;
+
+	ns->vfconfigs[vf].vlan = vlan;
+	ns->vfconfigs[vf].qos = qos;
+	ns->vfconfigs[vf].vlan_proto = vlan_proto;
+
+	return 0;
+}
+
+static int nsim_set_vf_rate(struct net_device *dev, int vf, int min, int max)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (vf >= ns->num_vfs)
+		return -EINVAL;
+
+	ns->vfconfigs[vf].min_tx_rate = min;
+	ns->vfconfigs[vf].max_tx_rate = max;
+
+	return 0;
+}
+
+static int nsim_set_vf_spoofchk(struct net_device *dev, int vf, bool val)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (vf >= ns->num_vfs)
+		return -EINVAL;
+	ns->vfconfigs[vf].spoofchk_enabled = val;
+
+	return 0;
+}
+
+static int nsim_set_vf_rss_query_en(struct net_device *dev, int vf, bool val)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (vf >= ns->num_vfs)
+		return -EINVAL;
+	ns->vfconfigs[vf].rss_query_enabled = val;
+
+	return 0;
+}
+
+static int nsim_set_vf_trust(struct net_device *dev, int vf, bool val)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (vf >= ns->num_vfs)
+		return -EINVAL;
+	ns->vfconfigs[vf].trusted = val;
+
+	return 0;
+}
+
+static int
+nsim_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (vf >= ns->num_vfs)
+		return -EINVAL;
+
+	ivi->vf = vf;
+	ivi->linkstate = ns->vfconfigs[vf].link_state;
+	ivi->min_tx_rate = ns->vfconfigs[vf].min_tx_rate;
+	ivi->max_tx_rate = ns->vfconfigs[vf].max_tx_rate;
+	ivi->vlan = ns->vfconfigs[vf].vlan;
+	ivi->vlan_proto = ns->vfconfigs[vf].vlan_proto;
+	ivi->qos = ns->vfconfigs[vf].qos;
+	memcpy(&ivi->mac, ns->vfconfigs[vf].vf_mac, ETH_ALEN);
+	ivi->spoofchk = ns->vfconfigs[vf].spoofchk_enabled;
+	ivi->trusted = ns->vfconfigs[vf].trusted;
+	ivi->rss_query_en = ns->vfconfigs[vf].rss_query_enabled;
+
+	return 0;
+}
+
+static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (vf >= ns->num_vfs)
+		return -EINVAL;
+
+	switch (state) {
+	case IFLA_VF_LINK_STATE_AUTO:
+	case IFLA_VF_LINK_STATE_ENABLE:
+	case IFLA_VF_LINK_STATE_DISABLE:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ns->vfconfigs[vf].link_state = state;
+
+	return 0;
+}
+
+static int
+nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return nsim_setup_tc_block(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nsim_set_features(struct net_device *dev, netdev_features_t features)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if ((dev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC))
+		return nsim_bpf_disable_tc(ns);
+
+	return 0;
+}
+
+static const struct net_device_ops nsim_netdev_ops = {
+	.ndo_init		= nsim_init,
+	.ndo_uninit		= nsim_uninit,
+	.ndo_start_xmit		= nsim_start_xmit,
+	.ndo_set_rx_mode	= nsim_set_rx_mode,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= nsim_change_mtu,
+	.ndo_get_stats64	= nsim_get_stats64,
+	.ndo_set_vf_mac		= nsim_set_vf_mac,
+	.ndo_set_vf_vlan	= nsim_set_vf_vlan,
+	.ndo_set_vf_rate	= nsim_set_vf_rate,
+	.ndo_set_vf_spoofchk	= nsim_set_vf_spoofchk,
+	.ndo_set_vf_trust	= nsim_set_vf_trust,
+	.ndo_get_vf_config	= nsim_get_vf_config,
+	.ndo_set_vf_link_state	= nsim_set_vf_link_state,
+	.ndo_set_vf_rss_query_en = nsim_set_vf_rss_query_en,
+	.ndo_setup_tc		= nsim_setup_tc,
+	.ndo_set_features	= nsim_set_features,
+	.ndo_bpf		= nsim_bpf,
+};
+
+static void nsim_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+	eth_hw_addr_random(dev);
+
+	dev->netdev_ops = &nsim_netdev_ops;
+	dev->priv_destructor = nsim_free;
+
+	dev->tx_queue_len = 0;
+	dev->flags |= IFF_NOARP;
+	dev->flags &= ~IFF_MULTICAST;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE |
+			   IFF_NO_QUEUE;
+	dev->features |= NETIF_F_HIGHDMA |
+			 NETIF_F_SG |
+			 NETIF_F_FRAGLIST |
+			 NETIF_F_HW_CSUM |
+			 NETIF_F_TSO;
+	dev->hw_features |= NETIF_F_HW_TC;
+	dev->max_mtu = ETH_MAX_MTU;
+}
+
+static int nsim_validate(struct nlattr *tb[], struct nlattr *data[],
+			 struct netlink_ext_ack *extack)
+{
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+			return -EINVAL;
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+			return -EADDRNOTAVAIL;
+	}
+	return 0;
+}
+
+static int nsim_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[],
+			struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (tb[IFLA_LINK]) {
+		struct net_device *joindev;
+		struct netdevsim *joinns;
+
+		joindev = __dev_get_by_index(src_net,
+					     nla_get_u32(tb[IFLA_LINK]));
+		if (!joindev)
+			return -ENODEV;
+		if (joindev->netdev_ops != &nsim_netdev_ops)
+			return -EINVAL;
+
+		joinns = netdev_priv(joindev);
+		if (!joinns->sdev || !joinns->sdev->refcnt)
+			return -EINVAL;
+		ns->sdev = joinns->sdev;
+	}
+
+	return register_netdevice(dev);
+}
+
+static void nsim_dellink(struct net_device *dev, struct list_head *head)
+{
+	unregister_netdevice_queue(dev, head);
+}
+
+static struct rtnl_link_ops nsim_link_ops __read_mostly = {
+	.kind		= DRV_NAME,
+	.priv_size	= sizeof(struct netdevsim),
+	.setup		= nsim_setup,
+	.validate	= nsim_validate,
+	.newlink	= nsim_newlink,
+	.dellink	= nsim_dellink,
+};
+
+static int __init nsim_module_init(void)
+{
+	int err;
+
+	nsim_ddir = debugfs_create_dir(DRV_NAME, NULL);
+	if (IS_ERR_OR_NULL(nsim_ddir))
+		return -ENOMEM;
+
+	nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL);
+	if (IS_ERR_OR_NULL(nsim_sdev_ddir)) {
+		err = -ENOMEM;
+		goto err_debugfs_destroy;
+	}
+
+	err = bus_register(&nsim_bus);
+	if (err)
+		goto err_sdir_destroy;
+
+	err = nsim_devlink_init();
+	if (err)
+		goto err_unreg_bus;
+
+	err = rtnl_link_register(&nsim_link_ops);
+	if (err)
+		goto err_dl_fini;
+
+	return 0;
+
+err_dl_fini:
+	nsim_devlink_exit();
+err_unreg_bus:
+	bus_unregister(&nsim_bus);
+err_sdir_destroy:
+	debugfs_remove_recursive(nsim_sdev_ddir);
+err_debugfs_destroy:
+	debugfs_remove_recursive(nsim_ddir);
+	return err;
+}
+
+static void __exit nsim_module_exit(void)
+{
+	rtnl_link_unregister(&nsim_link_ops);
+	nsim_devlink_exit();
+	bus_unregister(&nsim_bus);
+	debugfs_remove_recursive(nsim_sdev_ddir);
+	debugfs_remove_recursive(nsim_ddir);
+}
+
+module_init(nsim_module_init);
+module_exit(nsim_module_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);

drivers/net/netdevsim/netdevsim.h

@@ -0,0 +1,205 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
+
+#define DRV_NAME	"netdevsim"
+
+#define NSIM_XDP_MAX_MTU	4000
+
+#define NSIM_EA(extack, msg)	NL_SET_ERR_MSG_MOD((extack), msg)
+
+struct bpf_prog;
+struct bpf_offload_dev;
+struct dentry;
+struct nsim_vf_config;
+
+struct netdevsim_shared_dev {
+	unsigned int refcnt;
+	u32 switch_id;
+
+	struct dentry *ddir;
+
+	struct bpf_offload_dev *bpf_dev;
+
+	struct dentry *ddir_bpf_bound_progs;
+	u32 prog_id_gen;
+
+	struct list_head bpf_bound_progs;
+	struct list_head bpf_bound_maps;
+};
+
+#define NSIM_IPSEC_MAX_SA_COUNT		33
+#define NSIM_IPSEC_VALID		BIT(31)
+
+struct nsim_sa {
+	struct xfrm_state *xs;
+	__be32 ipaddr[4];
+	u32 key[4];
+	u32 salt;
+	bool used;
+	bool crypt;
+	bool rx;
+};
+
+struct nsim_ipsec {
+	struct nsim_sa sa[NSIM_IPSEC_MAX_SA_COUNT];
+	struct dentry *pfile;
+	u32 count;
+	u32 tx;
+	u32 ok;
+};
+
+struct netdevsim {
+	struct net_device *netdev;
+
+	u64 tx_packets;
+	u64 tx_bytes;
+	struct u64_stats_sync syncp;
+
+	struct device dev;
+	struct netdevsim_shared_dev *sdev;
+
+	struct dentry *ddir;
+
+	unsigned int num_vfs;
+	struct nsim_vf_config *vfconfigs;
+
+	struct bpf_prog	*bpf_offloaded;
+	u32 bpf_offloaded_id;
+
+	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
+
+	bool bpf_bind_accept;
+	u32 bpf_bind_verifier_delay;
+
+	bool bpf_tc_accept;
+	bool bpf_tc_non_bound_accept;
+	bool bpf_xdpdrv_accept;
+	bool bpf_xdpoffload_accept;
+
+	bool bpf_map_accept;
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+	struct devlink *devlink;
+#endif
+	struct nsim_ipsec ipsec;
+};
+
+#ifdef CONFIG_BPF_SYSCALL
+int nsim_bpf_init(struct netdevsim *ns);
+void nsim_bpf_uninit(struct netdevsim *ns);
+int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf);
+int nsim_bpf_disable_tc(struct netdevsim *ns);
+int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type,
+			       void *type_data, void *cb_priv);
+#else
+static inline int nsim_bpf_init(struct netdevsim *ns)
+{
+	return 0;
+}
+
+static inline void nsim_bpf_uninit(struct netdevsim *ns)
+{
+}
+
+static inline int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
+{
+	return bpf->command == XDP_QUERY_PROG ? 0 : -EOPNOTSUPP;
+}
+
+static inline int nsim_bpf_disable_tc(struct netdevsim *ns)
+{
+	return 0;
+}
+
+static inline int
+nsim_bpf_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+			   void *cb_priv)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+enum nsim_resource_id {
+	NSIM_RESOURCE_NONE,   /* DEVLINK_RESOURCE_ID_PARENT_TOP */
+	NSIM_RESOURCE_IPV4,
+	NSIM_RESOURCE_IPV4_FIB,
+	NSIM_RESOURCE_IPV4_FIB_RULES,
+	NSIM_RESOURCE_IPV6,
+	NSIM_RESOURCE_IPV6_FIB,
+	NSIM_RESOURCE_IPV6_FIB_RULES,
+};
+
+int nsim_devlink_setup(struct netdevsim *ns);
+void nsim_devlink_teardown(struct netdevsim *ns);
+
+int nsim_devlink_init(void);
+void nsim_devlink_exit(void);
+
+int nsim_fib_init(void);
+void nsim_fib_exit(void);
+u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max);
+int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val,
+		     struct netlink_ext_ack *extack);
+#else
+static inline int nsim_devlink_setup(struct netdevsim *ns)
+{
+	return 0;
+}
+
+static inline void nsim_devlink_teardown(struct netdevsim *ns)
+{
+}
+
+static inline int nsim_devlink_init(void)
+{
+	return 0;
+}
+
+static inline void nsim_devlink_exit(void)
+{
+}
+#endif
+
+#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
+void nsim_ipsec_init(struct netdevsim *ns);
+void nsim_ipsec_teardown(struct netdevsim *ns);
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb);
+#else
+static inline void nsim_ipsec_init(struct netdevsim *ns)
+{
+}
+
+static inline void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+}
+
+static inline bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	return true;
+}
+#endif
+
+static inline struct netdevsim *to_nsim(struct device *ptr)
+{
+	return container_of(ptr, struct netdevsim, dev);
+}