Resguardo inicial

linux-7.2.3/drivers/net/netdevsim/Makefile

@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_NETDEVSIM) += netdevsim.o
+
+netdevsim-objs := \
+	netdev.o dev.o ethtool.o fib.o bus.o health.o hwstats.o udp_tunnels.o tc.o
+
+ifeq ($(CONFIG_BPF_SYSCALL),y)
+netdevsim-objs += \
+	bpf.o
+endif
+
+ifneq ($(CONFIG_XFRM_OFFLOAD),)
+netdevsim-objs += ipsec.o
+endif
+
+ifneq ($(CONFIG_PSAMPLE),)
+netdevsim-objs += psample.o
+endif
+
+ifneq ($(CONFIG_INET_PSP),)
+netdevsim-objs += psp.o
+endif
+
+ifneq ($(CONFIG_MACSEC),)
+netdevsim-objs += macsec.o
+endif

linux-7.2.3/drivers/net/netdevsim/bpf.c

@@ -0,0 +1,654 @@
+/*
+ * 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 nsim_dev *nsim_dev;
+	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_bpf_string_show(struct seq_file *file, void *data)
+{
+	const char **str = file->private;
+
+	if (*str)
+		seq_printf(file, "%s\n", *str);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(nsim_bpf_string);
+
+static int
+nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn)
+{
+	struct nsim_bpf_bound_prog *state;
+	int ret = 0;
+
+	state = env->prog->aux->offload->dev_priv;
+	if (state->nsim_dev->bpf_bind_verifier_delay && !insn_idx)
+		msleep(state->nsim_dev->bpf_bind_verifier_delay);
+
+	if (insn_idx == env->prog->len - 1) {
+		pr_vlog(env, "Hello from netdevsim!\n");
+
+		if (!state->nsim_dev->bpf_bind_verifier_accept)
+			ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+static int nsim_bpf_finalize(struct bpf_verifier_env *env)
+{
+	return 0;
+}
+
+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 || !bpf_prog_is_offloaded(prog->aux))
+		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 (!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 (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 nsim_dev *nsim_dev,
+				struct bpf_prog *prog)
+{
+	struct nsim_bpf_bound_prog *state;
+	char name[16];
+	int ret;
+
+	state = kzalloc_obj(*state);
+	if (!state)
+		return -ENOMEM;
+
+	state->nsim_dev = nsim_dev;
+	state->prog = prog;
+	state->state = "verify";
+
+	/* Program id is not populated yet when we create the state. */
+	sprintf(name, "%u", nsim_dev->prog_id_gen++);
+	state->ddir = debugfs_create_dir(name, nsim_dev->ddir_bpf_bound_progs);
+	if (IS_ERR(state->ddir)) {
+		ret = PTR_ERR(state->ddir);
+		kfree(state);
+		return ret;
+	}
+
+	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);
+
+	mutex_lock(&nsim_dev->progs_list_lock);
+	list_add_tail(&state->l, &nsim_dev->bpf_bound_progs);
+	mutex_unlock(&nsim_dev->progs_list_lock);
+
+	prog->aux->offload->dev_priv = state;
+
+	return 0;
+}
+
+static int nsim_bpf_verifier_prep(struct bpf_prog *prog)
+{
+	struct nsim_dev *nsim_dev =
+			bpf_offload_dev_priv(prog->aux->offload->offdev);
+
+	if (!nsim_dev->bpf_bind_accept)
+		return -EOPNOTSUPP;
+
+	return nsim_bpf_create_prog(nsim_dev, prog);
+}
+
+static int nsim_bpf_translate(struct bpf_prog *prog)
+{
+	struct nsim_bpf_bound_prog *state = prog->aux->offload->dev_priv;
+
+	state->state = "xlated";
+	return 0;
+}
+
+static void nsim_bpf_destroy_prog(struct bpf_prog *prog)
+{
+	struct nsim_bpf_bound_prog *state;
+	struct nsim_dev *nsim_dev;
+
+	state = prog->aux->offload->dev_priv;
+	nsim_dev = state->nsim_dev;
+	WARN(state->is_loaded,
+	     "offload state destroyed while program still bound");
+	debugfs_remove_recursive(state->ddir);
+	mutex_lock(&nsim_dev->progs_list_lock);
+	list_del(&state->l);
+	mutex_unlock(&nsim_dev->progs_list_lock);
+	kfree(state);
+}
+
+static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = {
+	.insn_hook	= nsim_bpf_verify_insn,
+	.finalize	= nsim_bpf_finalize,
+	.prepare	= nsim_bpf_verifier_prep,
+	.translate	= nsim_bpf_translate,
+	.destroy	= nsim_bpf_destroy_prog,
+};
+
+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 (bpf->prog && !bpf->prog->aux->xdp_has_frags &&
+	    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_is_offloaded(bpf->prog->aux)) {
+		NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
+		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_KERNEL_ACCOUNT | __GFP_NOWARN);
+	if (!nmap->entry[idx].key)
+		return -ENOMEM;
+	nmap->entry[idx].value = kmalloc(offmap->map.value_size,
+					 GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+	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_obj(*nmap, GFP_KERNEL_ACCOUNT);
+	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;
+			memset(nmap->entry[i].value, 0, offmap->map.value_size);
+		}
+	}
+
+	offmap->dev_ops = &nsim_bpf_map_ops;
+	list_add_tail(&nmap->l, &ns->nsim_dev->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);
+	int err;
+
+	ASSERT_RTNL();
+
+	switch (bpf->command) {
+	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_dev_init(struct nsim_dev *nsim_dev)
+{
+	int err;
+
+	INIT_LIST_HEAD(&nsim_dev->bpf_bound_progs);
+	INIT_LIST_HEAD(&nsim_dev->bpf_bound_maps);
+
+	nsim_dev->ddir_bpf_bound_progs = debugfs_create_dir("bpf_bound_progs",
+							    nsim_dev->ddir);
+	if (IS_ERR(nsim_dev->ddir_bpf_bound_progs))
+		return PTR_ERR(nsim_dev->ddir_bpf_bound_progs);
+
+	nsim_dev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops, nsim_dev);
+	err = PTR_ERR_OR_ZERO(nsim_dev->bpf_dev);
+	if (err)
+		return err;
+
+	nsim_dev->bpf_bind_accept = true;
+	debugfs_create_bool("bpf_bind_accept", 0600, nsim_dev->ddir,
+			    &nsim_dev->bpf_bind_accept);
+	debugfs_create_u32("bpf_bind_verifier_delay", 0600, nsim_dev->ddir,
+			   &nsim_dev->bpf_bind_verifier_delay);
+	nsim_dev->bpf_bind_verifier_accept = true;
+	debugfs_create_bool("bpf_bind_verifier_accept", 0600, nsim_dev->ddir,
+			    &nsim_dev->bpf_bind_verifier_accept);
+	return 0;
+}
+
+void nsim_bpf_dev_exit(struct nsim_dev *nsim_dev)
+{
+	WARN_ON(!list_empty(&nsim_dev->bpf_bound_progs));
+	WARN_ON(!list_empty(&nsim_dev->bpf_bound_maps));
+	bpf_offload_dev_destroy(nsim_dev->bpf_dev);
+}
+
+int nsim_bpf_init(struct netdevsim *ns)
+{
+	struct dentry *ddir = ns->nsim_dev_port->ddir;
+	int err;
+
+	err = bpf_offload_dev_netdev_register(ns->nsim_dev->bpf_dev,
+					      ns->netdev);
+	if (err)
+		return err;
+
+	debugfs_create_u32("bpf_offloaded_id", 0400, ddir,
+			   &ns->bpf_offloaded_id);
+
+	ns->bpf_tc_accept = true;
+	debugfs_create_bool("bpf_tc_accept", 0600, ddir,
+			    &ns->bpf_tc_accept);
+	debugfs_create_bool("bpf_tc_non_bound_accept", 0600, ddir,
+			    &ns->bpf_tc_non_bound_accept);
+	ns->bpf_xdpdrv_accept = true;
+	debugfs_create_bool("bpf_xdpdrv_accept", 0600, ddir,
+			    &ns->bpf_xdpdrv_accept);
+	ns->bpf_xdpoffload_accept = true;
+	debugfs_create_bool("bpf_xdpoffload_accept", 0600, ddir,
+			    &ns->bpf_xdpoffload_accept);
+
+	ns->bpf_map_accept = true;
+	debugfs_create_bool("bpf_map_accept", 0600, ddir,
+			    &ns->bpf_map_accept);
+
+	return 0;
+}
+
+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->nsim_dev->bpf_dev, ns->netdev);
+}

linux-7.2.3/drivers/net/netdevsim/bus.c

@@ -0,0 +1,540 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2019 Mellanox Technologies. All rights reserved
+ */
+
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+#include "netdevsim.h"
+
+static DEFINE_IDA(nsim_bus_dev_ids);
+static LIST_HEAD(nsim_bus_dev_list);
+static DEFINE_MUTEX(nsim_bus_dev_list_lock);
+static bool nsim_bus_enable;
+static refcount_t nsim_bus_devs; /* Including the bus itself. */
+static DECLARE_COMPLETION(nsim_bus_devs_released);
+
+static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev)
+{
+	return container_of(dev, struct nsim_bus_dev, dev);
+}
+
+static ssize_t
+nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr,
+			  const char *buf, size_t count)
+{
+	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+	unsigned int num_vfs;
+	int ret;
+
+	ret = kstrtouint(buf, 0, &num_vfs);
+	if (ret)
+		return ret;
+
+	device_lock(dev);
+	ret = -ENOENT;
+	if (dev_get_drvdata(dev))
+		ret = nsim_drv_configure_vfs(nsim_bus_dev, num_vfs);
+	device_unlock(dev);
+
+	return ret ? ret : count;
+}
+
+static ssize_t
+nsim_bus_dev_numvfs_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+
+	return sprintf(buf, "%u\n", nsim_bus_dev->num_vfs);
+}
+
+static struct device_attribute nsim_bus_dev_numvfs_attr =
+	__ATTR(sriov_numvfs, 0664, nsim_bus_dev_numvfs_show,
+	       nsim_bus_dev_numvfs_store);
+
+static ssize_t
+new_port_store(struct device *dev, struct device_attribute *attr,
+	       const char *buf, size_t count)
+{
+	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+	u8 eth_addr[ETH_ALEN] = {};
+	unsigned int port_index;
+	bool addr_set = false;
+	int ret;
+
+	/* Prevent to use nsim_bus_dev before initialization. */
+	if (!smp_load_acquire(&nsim_bus_dev->init))
+		return -EBUSY;
+
+	ret = sscanf(buf, "%u %hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &port_index,
+		     &eth_addr[0], &eth_addr[1], &eth_addr[2], &eth_addr[3],
+		     &eth_addr[4], &eth_addr[5]);
+	switch (ret) {
+	case 7:
+		if (!is_valid_ether_addr(eth_addr)) {
+			pr_err("The supplied perm_addr is not a valid MAC address\n");
+			return -EINVAL;
+		}
+		addr_set = true;
+		fallthrough;
+	case 1:
+		break;
+	default:
+		pr_err("Format for adding new port is \"id [perm_addr]\" (uint MAC).\n");
+		return -EINVAL;
+	}
+
+	ret = nsim_drv_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index,
+				addr_set ? eth_addr : NULL);
+	return ret ? ret : count;
+}
+
+static struct device_attribute nsim_bus_dev_new_port_attr = __ATTR_WO(new_port);
+
+static ssize_t
+del_port_store(struct device *dev, struct device_attribute *attr,
+	       const char *buf, size_t count)
+{
+	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+	unsigned int port_index;
+	int ret;
+
+	/* Prevent to use nsim_bus_dev before initialization. */
+	if (!smp_load_acquire(&nsim_bus_dev->init))
+		return -EBUSY;
+	ret = kstrtouint(buf, 0, &port_index);
+	if (ret)
+		return ret;
+
+	ret = nsim_drv_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index);
+	return ret ? ret : count;
+}
+
+static struct device_attribute nsim_bus_dev_del_port_attr = __ATTR_WO(del_port);
+
+static struct attribute *nsim_bus_dev_attrs[] = {
+	&nsim_bus_dev_numvfs_attr.attr,
+	&nsim_bus_dev_new_port_attr.attr,
+	&nsim_bus_dev_del_port_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group nsim_bus_dev_attr_group = {
+	.attrs = nsim_bus_dev_attrs,
+};
+
+static const struct attribute_group *nsim_bus_dev_attr_groups[] = {
+	&nsim_bus_dev_attr_group,
+	NULL,
+};
+
+static void nsim_bus_dev_release(struct device *dev)
+{
+	struct nsim_bus_dev *nsim_bus_dev;
+
+	nsim_bus_dev = container_of(dev, struct nsim_bus_dev, dev);
+	kfree(nsim_bus_dev);
+	if (refcount_dec_and_test(&nsim_bus_devs))
+		complete(&nsim_bus_devs_released);
+}
+
+static const struct device_type nsim_bus_dev_type = {
+	.groups = nsim_bus_dev_attr_groups,
+	.release = nsim_bus_dev_release,
+};
+
+static struct nsim_bus_dev *
+nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues);
+
+static ssize_t
+new_device_store(const struct bus_type *bus, const char *buf, size_t count)
+{
+	unsigned int id, port_count, num_queues;
+	struct nsim_bus_dev *nsim_bus_dev;
+	int err;
+
+	err = sscanf(buf, "%u %u %u", &id, &port_count, &num_queues);
+	switch (err) {
+	case 1:
+		port_count = 1;
+		fallthrough;
+	case 2:
+		num_queues = 1;
+		fallthrough;
+	case 3:
+		if (id > INT_MAX) {
+			pr_err("Value of \"id\" is too big.\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		pr_err("Format for adding new device is \"id port_count num_queues\" (uint uint uint).\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&nsim_bus_dev_list_lock);
+	/* Prevent to use resource before initialization. */
+	if (!smp_load_acquire(&nsim_bus_enable)) {
+		err = -EBUSY;
+		goto err;
+	}
+
+	nsim_bus_dev = nsim_bus_dev_new(id, port_count, num_queues);
+	if (IS_ERR(nsim_bus_dev)) {
+		err = PTR_ERR(nsim_bus_dev);
+		goto err;
+	}
+
+	refcount_inc(&nsim_bus_devs);
+	/* Allow using nsim_bus_dev */
+	smp_store_release(&nsim_bus_dev->init, true);
+
+	list_add_tail(&nsim_bus_dev->list, &nsim_bus_dev_list);
+	mutex_unlock(&nsim_bus_dev_list_lock);
+
+	return count;
+err:
+	mutex_unlock(&nsim_bus_dev_list_lock);
+	return err;
+}
+static BUS_ATTR_WO(new_device);
+
+static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev);
+
+static ssize_t
+del_device_store(const struct bus_type *bus, const char *buf, size_t count)
+{
+	struct nsim_bus_dev *nsim_bus_dev, *tmp;
+	unsigned int id;
+	int err;
+
+	err = sscanf(buf, "%u", &id);
+	switch (err) {
+	case 1:
+		if (id > INT_MAX) {
+			pr_err("Value of \"id\" is too big.\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		pr_err("Format for deleting device is \"id\" (uint).\n");
+		return -EINVAL;
+	}
+
+	err = -ENOENT;
+	mutex_lock(&nsim_bus_dev_list_lock);
+	/* Prevent to use resource before initialization. */
+	if (!smp_load_acquire(&nsim_bus_enable)) {
+		mutex_unlock(&nsim_bus_dev_list_lock);
+		return -EBUSY;
+	}
+	list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) {
+		if (nsim_bus_dev->dev.id != id)
+			continue;
+		list_del(&nsim_bus_dev->list);
+		nsim_bus_dev_del(nsim_bus_dev);
+		err = 0;
+		break;
+	}
+	mutex_unlock(&nsim_bus_dev_list_lock);
+	return !err ? count : err;
+}
+static BUS_ATTR_WO(del_device);
+
+static ssize_t link_device_store(const struct bus_type *bus, const char *buf, size_t count)
+{
+	struct netdevsim *nsim_a, *nsim_b, *peer;
+	struct net_device *dev_a, *dev_b;
+	unsigned int ifidx_a, ifidx_b;
+	int netnsfd_a, netnsfd_b, err;
+	struct net *ns_a, *ns_b;
+
+	err = sscanf(buf, "%d:%u %d:%u", &netnsfd_a, &ifidx_a, &netnsfd_b,
+		     &ifidx_b);
+	if (err != 4) {
+		pr_err("Format for linking two devices is \"netnsfd_a:ifidx_a netnsfd_b:ifidx_b\" (int uint int uint).\n");
+		return -EINVAL;
+	}
+
+	ns_a = get_net_ns_by_fd(netnsfd_a);
+	if (IS_ERR(ns_a)) {
+		pr_err("Could not find netns with fd: %d\n", netnsfd_a);
+		return -EINVAL;
+	}
+
+	ns_b = get_net_ns_by_fd(netnsfd_b);
+	if (IS_ERR(ns_b)) {
+		pr_err("Could not find netns with fd: %d\n", netnsfd_b);
+		put_net(ns_a);
+		return -EINVAL;
+	}
+
+	err = -EINVAL;
+	rtnl_lock();
+	dev_a = __dev_get_by_index(ns_a, ifidx_a);
+	if (!dev_a) {
+		pr_err("Could not find device with ifindex %u in netnsfd %d\n",
+		       ifidx_a, netnsfd_a);
+		goto out_err;
+	}
+
+	if (!netdev_is_nsim(dev_a)) {
+		pr_err("Device with ifindex %u in netnsfd %d is not a netdevsim\n",
+		       ifidx_a, netnsfd_a);
+		goto out_err;
+	}
+
+	dev_b = __dev_get_by_index(ns_b, ifidx_b);
+	if (!dev_b) {
+		pr_err("Could not find device with ifindex %u in netnsfd %d\n",
+		       ifidx_b, netnsfd_b);
+		goto out_err;
+	}
+
+	if (!netdev_is_nsim(dev_b)) {
+		pr_err("Device with ifindex %u in netnsfd %d is not a netdevsim\n",
+		       ifidx_b, netnsfd_b);
+		goto out_err;
+	}
+
+	if (dev_a == dev_b) {
+		pr_err("Cannot link a netdevsim to itself\n");
+		goto out_err;
+	}
+
+	err = -EBUSY;
+	nsim_a = netdev_priv(dev_a);
+	peer = rtnl_dereference(nsim_a->peer);
+	if (peer) {
+		pr_err("Netdevsim %d:%u is already linked\n", netnsfd_a,
+		       ifidx_a);
+		goto out_err;
+	}
+
+	nsim_b = netdev_priv(dev_b);
+	peer = rtnl_dereference(nsim_b->peer);
+	if (peer) {
+		pr_err("Netdevsim %d:%u is already linked\n", netnsfd_b,
+		       ifidx_b);
+		goto out_err;
+	}
+
+	err = 0;
+	rcu_assign_pointer(nsim_a->peer, nsim_b);
+	rcu_assign_pointer(nsim_b->peer, nsim_a);
+
+	if (netif_running(dev_a) && netif_running(dev_b)) {
+		netif_carrier_on(dev_a);
+		netif_carrier_on(dev_b);
+	}
+
+out_err:
+	put_net(ns_b);
+	put_net(ns_a);
+	rtnl_unlock();
+
+	return !err ? count : err;
+}
+static BUS_ATTR_WO(link_device);
+
+static ssize_t unlink_device_store(const struct bus_type *bus, const char *buf, size_t count)
+{
+	struct netdevsim *nsim, *peer;
+	struct net_device *dev;
+	unsigned int ifidx;
+	int netnsfd, err;
+	struct net *ns;
+
+	err = sscanf(buf, "%u:%u", &netnsfd, &ifidx);
+	if (err != 2) {
+		pr_err("Format for unlinking a device is \"netnsfd:ifidx\" (int uint).\n");
+		return -EINVAL;
+	}
+
+	ns = get_net_ns_by_fd(netnsfd);
+	if (IS_ERR(ns)) {
+		pr_err("Could not find netns with fd: %d\n", netnsfd);
+		return -EINVAL;
+	}
+
+	err = -EINVAL;
+	rtnl_lock();
+	dev = __dev_get_by_index(ns, ifidx);
+	if (!dev) {
+		pr_err("Could not find device with ifindex %u in netnsfd %d\n",
+		       ifidx, netnsfd);
+		goto out_put_netns;
+	}
+
+	if (!netdev_is_nsim(dev)) {
+		pr_err("Device with ifindex %u in netnsfd %d is not a netdevsim\n",
+		       ifidx, netnsfd);
+		goto out_put_netns;
+	}
+
+	nsim = netdev_priv(dev);
+	peer = rtnl_dereference(nsim->peer);
+	if (!peer)
+		goto out_put_netns;
+
+	netif_carrier_off(dev);
+	netif_carrier_off(peer->netdev);
+
+	err = 0;
+	RCU_INIT_POINTER(nsim->peer, NULL);
+	RCU_INIT_POINTER(peer->peer, NULL);
+	synchronize_net();
+	netif_tx_wake_all_queues(dev);
+	netif_tx_wake_all_queues(peer->netdev);
+
+out_put_netns:
+	put_net(ns);
+	rtnl_unlock();
+
+	return !err ? count : err;
+}
+static BUS_ATTR_WO(unlink_device);
+
+static struct attribute *nsim_bus_attrs[] = {
+	&bus_attr_new_device.attr,
+	&bus_attr_del_device.attr,
+	&bus_attr_link_device.attr,
+	&bus_attr_unlink_device.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(nsim_bus);
+
+static int nsim_bus_probe(struct device *dev)
+{
+	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+
+	return nsim_drv_probe(nsim_bus_dev);
+}
+
+static void nsim_bus_remove(struct device *dev)
+{
+	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+
+	nsim_drv_remove(nsim_bus_dev);
+}
+
+static int nsim_num_vf(struct device *dev)
+{
+	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+
+	return nsim_bus_dev->num_vfs;
+}
+
+static const struct bus_type nsim_bus = {
+	.name		= DRV_NAME,
+	.dev_name	= DRV_NAME,
+	.bus_groups	= nsim_bus_groups,
+	.probe		= nsim_bus_probe,
+	.remove		= nsim_bus_remove,
+	.num_vf		= nsim_num_vf,
+};
+
+#define NSIM_BUS_DEV_MAX_VFS 4
+
+static struct nsim_bus_dev *
+nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues)
+{
+	struct nsim_bus_dev *nsim_bus_dev;
+	int err;
+
+	nsim_bus_dev = kzalloc_obj(*nsim_bus_dev);
+	if (!nsim_bus_dev)
+		return ERR_PTR(-ENOMEM);
+
+	err = ida_alloc_range(&nsim_bus_dev_ids, id, id, GFP_KERNEL);
+	if (err < 0)
+		goto err_nsim_bus_dev_free;
+	nsim_bus_dev->dev.id = err;
+	nsim_bus_dev->dev.bus = &nsim_bus;
+	nsim_bus_dev->dev.type = &nsim_bus_dev_type;
+	nsim_bus_dev->port_count = port_count;
+	nsim_bus_dev->num_queues = num_queues;
+	nsim_bus_dev->initial_net = current->nsproxy->net_ns;
+	nsim_bus_dev->max_vfs = NSIM_BUS_DEV_MAX_VFS;
+	/* Disallow using nsim_bus_dev */
+	smp_store_release(&nsim_bus_dev->init, false);
+
+	err = device_register(&nsim_bus_dev->dev);
+	if (err)
+		goto err_nsim_bus_dev_id_free;
+
+	return nsim_bus_dev;
+
+err_nsim_bus_dev_id_free:
+	ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
+	put_device(&nsim_bus_dev->dev);
+	nsim_bus_dev = NULL;
+err_nsim_bus_dev_free:
+	kfree(nsim_bus_dev);
+	return ERR_PTR(err);
+}
+
+static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev)
+{
+	/* Disallow using nsim_bus_dev */
+	smp_store_release(&nsim_bus_dev->init, false);
+	ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
+	device_unregister(&nsim_bus_dev->dev);
+}
+
+static struct device_driver nsim_driver = {
+	.name		= DRV_NAME,
+	.bus		= &nsim_bus,
+	.owner		= THIS_MODULE,
+};
+
+int nsim_bus_init(void)
+{
+	int err;
+
+	err = bus_register(&nsim_bus);
+	if (err)
+		return err;
+	err = driver_register(&nsim_driver);
+	if (err)
+		goto err_bus_unregister;
+	refcount_set(&nsim_bus_devs, 1);
+	/* Allow using resources */
+	smp_store_release(&nsim_bus_enable, true);
+	return 0;
+
+err_bus_unregister:
+	bus_unregister(&nsim_bus);
+	return err;
+}
+
+void nsim_bus_exit(void)
+{
+	struct nsim_bus_dev *nsim_bus_dev, *tmp;
+
+	/* Disallow using resources */
+	smp_store_release(&nsim_bus_enable, false);
+	if (refcount_dec_and_test(&nsim_bus_devs))
+		complete(&nsim_bus_devs_released);
+
+	mutex_lock(&nsim_bus_dev_list_lock);
+	list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) {
+		list_del(&nsim_bus_dev->list);
+		nsim_bus_dev_del(nsim_bus_dev);
+	}
+	mutex_unlock(&nsim_bus_dev_list_lock);
+
+	wait_for_completion(&nsim_bus_devs_released);
+
+	driver_unregister(&nsim_driver);
+	bus_unregister(&nsim_bus);
+}

linux-7.2.3/drivers/net/netdevsim/ethtool.c

@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/debugfs.h>
+#include <linux/random.h>
+#include <net/netdev_queues.h>
+
+#include "netdevsim.h"
+
+static void
+nsim_get_pause_stats(struct net_device *dev,
+		     struct ethtool_pause_stats *pause_stats)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (ns->ethtool.pauseparam.report_stats_rx)
+		pause_stats->rx_pause_frames = 1;
+	if (ns->ethtool.pauseparam.report_stats_tx)
+		pause_stats->tx_pause_frames = 2;
+}
+
+static void
+nsim_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	pause->autoneg = 0; /* We don't support ksettings, so can't pretend */
+	pause->rx_pause = ns->ethtool.pauseparam.rx;
+	pause->tx_pause = ns->ethtool.pauseparam.tx;
+}
+
+static int
+nsim_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (pause->autoneg)
+		return -EINVAL;
+
+	ns->ethtool.pauseparam.rx = pause->rx_pause;
+	ns->ethtool.pauseparam.tx = pause->tx_pause;
+	return 0;
+}
+
+static int nsim_get_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	memcpy(coal, &ns->ethtool.coalesce, sizeof(ns->ethtool.coalesce));
+	return 0;
+}
+
+static int nsim_set_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	memcpy(&ns->ethtool.coalesce, coal, sizeof(ns->ethtool.coalesce));
+	return 0;
+}
+
+static void nsim_get_ringparam(struct net_device *dev,
+			       struct ethtool_ringparam *ring,
+			       struct kernel_ethtool_ringparam *kernel_ring,
+			       struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring));
+	kernel_ring->hds_thresh_max = NSIM_HDS_THRESHOLD_MAX;
+
+	if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN)
+		kernel_ring->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED;
+}
+
+static int nsim_set_ringparam(struct net_device *dev,
+			      struct ethtool_ringparam *ring,
+			      struct kernel_ethtool_ringparam *kernel_ring,
+			      struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	ns->ethtool.ring.rx_pending = ring->rx_pending;
+	ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending;
+	ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending;
+	ns->ethtool.ring.tx_pending = ring->tx_pending;
+	return 0;
+}
+
+static void
+nsim_get_channels(struct net_device *dev, struct ethtool_channels *ch)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	ch->max_combined = ns->nsim_bus_dev->num_queues;
+	ch->combined_count = ns->ethtool.channels;
+}
+
+static void
+nsim_wake_queues(struct net_device *dev)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	struct netdevsim *peer;
+
+	synchronize_net();
+	netif_tx_wake_all_queues(dev);
+
+	rcu_read_lock();
+	peer = rcu_dereference(ns->peer);
+	if (peer)
+		netif_tx_wake_all_queues(peer->netdev);
+	rcu_read_unlock();
+}
+
+static int
+nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	int err;
+
+	err = netif_set_real_num_queues(dev, ch->combined_count,
+					ch->combined_count);
+	if (err)
+		return err;
+
+	ns->ethtool.channels = ch->combined_count;
+
+	/* Only wake up queues if devices are linked */
+	if (rcu_access_pointer(ns->peer))
+		nsim_wake_queues(dev);
+
+	return 0;
+}
+
+static int
+nsim_get_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (ns->ethtool.get_err)
+		return -ns->ethtool.get_err;
+	memcpy(fecparam, &ns->ethtool.fec, sizeof(ns->ethtool.fec));
+	return 0;
+}
+
+static int
+nsim_set_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	u32 fec;
+
+	if (ns->ethtool.set_err)
+		return -ns->ethtool.set_err;
+	memcpy(&ns->ethtool.fec, fecparam, sizeof(ns->ethtool.fec));
+	fec = fecparam->fec;
+	if (fec == ETHTOOL_FEC_AUTO)
+		fec |= ETHTOOL_FEC_OFF;
+	fec |= ETHTOOL_FEC_NONE;
+	ns->ethtool.fec.active_fec = 1 << (fls(fec) - 1);
+	return 0;
+}
+
+static const struct ethtool_fec_hist_range netdevsim_fec_ranges[] = {
+	{ 0, 0},
+	{ 1, 3},
+	{ 4, 7},
+	{ 0, 0}
+};
+
+static void
+nsim_get_fec_stats(struct net_device *dev, struct ethtool_fec_stats *fec_stats,
+		   struct ethtool_fec_hist *hist)
+{
+	struct ethtool_fec_hist_value *values = hist->values;
+
+	hist->ranges = netdevsim_fec_ranges;
+
+	fec_stats->corrected_blocks.total = 123;
+	fec_stats->uncorrectable_blocks.total = 4;
+
+	values[0].per_lane[0] = 125;
+	values[0].per_lane[1] = 120;
+	values[0].per_lane[2] = 100;
+	values[0].per_lane[3] = 100;
+	values[1].sum = 12;
+	values[2].sum = 2;
+	values[2].per_lane[0] = 2;
+	values[2].per_lane[1] = 0;
+	values[2].per_lane[2] = 0;
+	values[2].per_lane[3] = 0;
+}
+
+static int nsim_get_ts_info(struct net_device *dev,
+			    struct kernel_ethtool_ts_info *info)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	info->phc_index = mock_phc_index(ns->phc);
+
+	return 0;
+}
+
+static const struct ethtool_ops nsim_ethtool_ops = {
+	.supported_coalesce_params	= ETHTOOL_COALESCE_ALL_PARAMS,
+	.supported_ring_params		= ETHTOOL_RING_USE_TCP_DATA_SPLIT |
+					  ETHTOOL_RING_USE_HDS_THRS,
+	.op_needs_rtnl			= ETHTOOL_OP_NEEDS_RTNL_SCHANNELS,
+	.get_pause_stats	        = nsim_get_pause_stats,
+	.get_pauseparam		        = nsim_get_pauseparam,
+	.set_pauseparam		        = nsim_set_pauseparam,
+	.set_coalesce			= nsim_set_coalesce,
+	.get_coalesce			= nsim_get_coalesce,
+	.get_ringparam			= nsim_get_ringparam,
+	.set_ringparam			= nsim_set_ringparam,
+	.get_channels			= nsim_get_channels,
+	.set_channels			= nsim_set_channels,
+	.get_fecparam			= nsim_get_fecparam,
+	.set_fecparam			= nsim_set_fecparam,
+	.get_fec_stats			= nsim_get_fec_stats,
+	.get_ts_info			= nsim_get_ts_info,
+};
+
+static void nsim_ethtool_ring_init(struct netdevsim *ns)
+{
+	ns->ethtool.ring.rx_pending = 512;
+	ns->ethtool.ring.rx_max_pending = 4096;
+	ns->ethtool.ring.rx_jumbo_max_pending = 4096;
+	ns->ethtool.ring.rx_mini_max_pending = 4096;
+	ns->ethtool.ring.tx_pending = 512;
+	ns->ethtool.ring.tx_max_pending = 4096;
+}
+
+void nsim_ethtool_init(struct netdevsim *ns)
+{
+	struct dentry *ethtool, *dir;
+
+	ns->netdev->ethtool_ops = &nsim_ethtool_ops;
+
+	nsim_ethtool_ring_init(ns);
+
+	ns->ethtool.pauseparam.report_stats_rx = true;
+	ns->ethtool.pauseparam.report_stats_tx = true;
+
+	ns->ethtool.fec.fec = ETHTOOL_FEC_NONE;
+	ns->ethtool.fec.active_fec = ETHTOOL_FEC_NONE;
+
+	ns->ethtool.channels = ns->nsim_bus_dev->num_queues;
+
+	ethtool = debugfs_create_dir("ethtool", ns->nsim_dev_port->ddir);
+	ns->ethtool_ddir = ethtool;
+
+	debugfs_create_u32("get_err", 0600, ethtool, &ns->ethtool.get_err);
+	debugfs_create_u32("set_err", 0600, ethtool, &ns->ethtool.set_err);
+
+	dir = debugfs_create_dir("pause", ethtool);
+	debugfs_create_bool("report_stats_rx", 0600, dir,
+			    &ns->ethtool.pauseparam.report_stats_rx);
+	debugfs_create_bool("report_stats_tx", 0600, dir,
+			    &ns->ethtool.pauseparam.report_stats_tx);
+
+	dir = debugfs_create_dir("ring", ethtool);
+	debugfs_create_u32("rx_max_pending", 0600, dir,
+			   &ns->ethtool.ring.rx_max_pending);
+	debugfs_create_u32("rx_jumbo_max_pending", 0600, dir,
+			   &ns->ethtool.ring.rx_jumbo_max_pending);
+	debugfs_create_u32("rx_mini_max_pending", 0600, dir,
+			   &ns->ethtool.ring.rx_mini_max_pending);
+	debugfs_create_u32("tx_max_pending", 0600, dir,
+			   &ns->ethtool.ring.tx_max_pending);
+}
+
+void nsim_ethtool_fini(struct netdevsim *ns)
+{
+	debugfs_remove(ns->ethtool_ddir);
+}

linux-7.2.3/drivers/net/netdevsim/health.c

@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "netdevsim.h"
+
+static int
+nsim_dev_empty_reporter_dump(struct devlink_health_reporter *reporter,
+			     struct devlink_fmsg *fmsg, void *priv_ctx,
+			     struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static int
+nsim_dev_empty_reporter_diagnose(struct devlink_health_reporter *reporter,
+				 struct devlink_fmsg *fmsg,
+				 struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static const
+struct devlink_health_reporter_ops nsim_dev_empty_reporter_ops = {
+	.name = "empty",
+	.dump = nsim_dev_empty_reporter_dump,
+	.diagnose = nsim_dev_empty_reporter_diagnose,
+};
+
+struct nsim_dev_dummy_reporter_ctx {
+	char *break_msg;
+};
+
+static int
+nsim_dev_dummy_reporter_recover(struct devlink_health_reporter *reporter,
+				void *priv_ctx,
+				struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_health *health = devlink_health_reporter_priv(reporter);
+	struct nsim_dev_dummy_reporter_ctx *ctx = priv_ctx;
+
+	if (health->fail_recover) {
+		/* For testing purposes, user set debugfs fail_recover
+		 * value to true. Fail right away.
+		 */
+		NL_SET_ERR_MSG_MOD(extack, "User setup the recover to fail for testing purposes");
+		return -EINVAL;
+	}
+	if (ctx) {
+		kfree(health->recovered_break_msg);
+		health->recovered_break_msg = kstrdup(ctx->break_msg,
+						      GFP_KERNEL);
+		if (!health->recovered_break_msg)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+static int nsim_dev_dummy_fmsg_put(struct devlink_fmsg *fmsg, u32 binary_len)
+{
+	char *binary;
+	int i;
+
+	devlink_fmsg_bool_pair_put(fmsg, "test_bool", true);
+	devlink_fmsg_u8_pair_put(fmsg, "test_u8", 1);
+	devlink_fmsg_u32_pair_put(fmsg, "test_u32", 3);
+	devlink_fmsg_u64_pair_put(fmsg, "test_u64", 4);
+	devlink_fmsg_string_pair_put(fmsg, "test_string", "somestring");
+
+	binary = kmalloc(binary_len, GFP_KERNEL | __GFP_NOWARN);
+	if (!binary)
+		return -ENOMEM;
+	get_random_bytes(binary, binary_len);
+	devlink_fmsg_binary_pair_put(fmsg, "test_binary", binary, binary_len);
+	kfree(binary);
+
+	devlink_fmsg_pair_nest_start(fmsg, "test_nest");
+	devlink_fmsg_obj_nest_start(fmsg);
+	devlink_fmsg_bool_pair_put(fmsg, "nested_test_bool", false);
+	devlink_fmsg_u8_pair_put(fmsg, "nested_test_u8", false);
+	devlink_fmsg_obj_nest_end(fmsg);
+	devlink_fmsg_pair_nest_end(fmsg);
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+	devlink_fmsg_arr_pair_nest_start(fmsg, "test_u32_array");
+
+	for (i = 0; i < 10; i++)
+		devlink_fmsg_u32_put(fmsg, i);
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+	devlink_fmsg_arr_pair_nest_start(fmsg, "test_array_of_objects");
+
+	for (i = 0; i < 10; i++) {
+		devlink_fmsg_obj_nest_start(fmsg);
+		devlink_fmsg_bool_pair_put(fmsg, "in_array_nested_test_bool",
+					   false);
+		devlink_fmsg_u8_pair_put(fmsg, "in_array_nested_test_u8", i);
+		devlink_fmsg_obj_nest_end(fmsg);
+	}
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+
+	return 0;
+}
+
+static int
+nsim_dev_dummy_reporter_dump(struct devlink_health_reporter *reporter,
+			     struct devlink_fmsg *fmsg, void *priv_ctx,
+			     struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_health *health = devlink_health_reporter_priv(reporter);
+	struct nsim_dev_dummy_reporter_ctx *ctx = priv_ctx;
+
+	if (ctx)
+		devlink_fmsg_string_pair_put(fmsg, "break_message", ctx->break_msg);
+
+	return nsim_dev_dummy_fmsg_put(fmsg, health->binary_len);
+}
+
+static int
+nsim_dev_dummy_reporter_diagnose(struct devlink_health_reporter *reporter,
+				 struct devlink_fmsg *fmsg,
+				 struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_health *health = devlink_health_reporter_priv(reporter);
+
+	if (health->recovered_break_msg)
+		devlink_fmsg_string_pair_put(fmsg, "recovered_break_message",
+					     health->recovered_break_msg);
+
+	return nsim_dev_dummy_fmsg_put(fmsg, health->binary_len);
+}
+
+static const
+struct devlink_health_reporter_ops nsim_dev_dummy_reporter_ops = {
+	.name = "dummy",
+	.recover = nsim_dev_dummy_reporter_recover,
+	.dump = nsim_dev_dummy_reporter_dump,
+	.diagnose = nsim_dev_dummy_reporter_diagnose,
+};
+
+static ssize_t nsim_dev_health_break_write(struct file *file,
+					   const char __user *data,
+					   size_t count, loff_t *ppos)
+{
+	struct nsim_dev_health *health = file->private_data;
+	struct nsim_dev_dummy_reporter_ctx ctx;
+	char *break_msg;
+	int err;
+
+	if (count == 0 || count > PAGE_SIZE)
+		return -EINVAL;
+	break_msg = memdup_user_nul(data, count);
+	if (IS_ERR(break_msg))
+		return PTR_ERR(break_msg);
+
+	if (break_msg[count - 1] == '\n')
+		break_msg[count - 1] = '\0';
+
+	ctx.break_msg = break_msg;
+	err = devlink_health_report(health->dummy_reporter, break_msg, &ctx);
+	if (err)
+		goto out;
+
+out:
+	kfree(break_msg);
+	return err ?: count;
+}
+
+static const struct file_operations nsim_dev_health_break_fops = {
+	.open = simple_open,
+	.write = nsim_dev_health_break_write,
+	.llseek = generic_file_llseek,
+	.owner = THIS_MODULE,
+};
+
+int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink)
+{
+	struct nsim_dev_health *health = &nsim_dev->health;
+	int err;
+
+	health->empty_reporter =
+		devl_health_reporter_create(devlink,
+					    &nsim_dev_empty_reporter_ops,
+					    health);
+	if (IS_ERR(health->empty_reporter))
+		return PTR_ERR(health->empty_reporter);
+
+	health->dummy_reporter =
+		devl_health_reporter_create(devlink,
+					    &nsim_dev_dummy_reporter_ops,
+					    health);
+	if (IS_ERR(health->dummy_reporter)) {
+		err = PTR_ERR(health->dummy_reporter);
+		goto err_empty_reporter_destroy;
+	}
+
+	health->ddir = debugfs_create_dir("health", nsim_dev->ddir);
+	if (IS_ERR(health->ddir)) {
+		err = PTR_ERR(health->ddir);
+		goto err_dummy_reporter_destroy;
+	}
+
+	health->recovered_break_msg = NULL;
+	debugfs_create_file("break_health", 0200, health->ddir, health,
+			    &nsim_dev_health_break_fops);
+	health->binary_len = 16;
+	debugfs_create_u32("binary_len", 0600, health->ddir,
+			   &health->binary_len);
+	health->fail_recover = false;
+	debugfs_create_bool("fail_recover", 0600, health->ddir,
+			    &health->fail_recover);
+	return 0;
+
+err_dummy_reporter_destroy:
+	devl_health_reporter_destroy(health->dummy_reporter);
+err_empty_reporter_destroy:
+	devl_health_reporter_destroy(health->empty_reporter);
+	return err;
+}
+
+void nsim_dev_health_exit(struct nsim_dev *nsim_dev)
+{
+	struct nsim_dev_health *health = &nsim_dev->health;
+
+	debugfs_remove_recursive(health->ddir);
+	kfree(health->recovered_break_msg);
+	devl_health_reporter_destroy(health->dummy_reporter);
+	devl_health_reporter_destroy(health->empty_reporter);
+}

linux-7.2.3/drivers/net/netdevsim/hwstats.c

@@ -0,0 +1,480 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/debugfs.h>
+
+#include "netdevsim.h"
+
+#define NSIM_DEV_HWSTATS_TRAFFIC_MS	100
+
+static struct list_head *
+nsim_dev_hwstats_get_list_head(struct nsim_dev_hwstats *hwstats,
+			       enum netdev_offload_xstats_type type)
+{
+	switch (type) {
+	case NETDEV_OFFLOAD_XSTATS_TYPE_L3:
+		return &hwstats->l3_list;
+	}
+
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
+static void nsim_dev_hwstats_traffic_bump(struct nsim_dev_hwstats *hwstats,
+					  enum netdev_offload_xstats_type type)
+{
+	struct nsim_dev_hwstats_netdev *hwsdev;
+	struct list_head *hwsdev_list;
+
+	hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type);
+	if (WARN_ON(!hwsdev_list))
+		return;
+
+	list_for_each_entry(hwsdev, hwsdev_list, list) {
+		if (hwsdev->enabled) {
+			hwsdev->stats.rx_packets += 1;
+			hwsdev->stats.tx_packets += 2;
+			hwsdev->stats.rx_bytes += 100;
+			hwsdev->stats.tx_bytes += 300;
+		}
+	}
+}
+
+static void nsim_dev_hwstats_traffic_work(struct work_struct *work)
+{
+	struct nsim_dev_hwstats *hwstats;
+
+	hwstats = container_of(work, struct nsim_dev_hwstats, traffic_dw.work);
+	mutex_lock(&hwstats->hwsdev_list_lock);
+	nsim_dev_hwstats_traffic_bump(hwstats, NETDEV_OFFLOAD_XSTATS_TYPE_L3);
+	mutex_unlock(&hwstats->hwsdev_list_lock);
+
+	schedule_delayed_work(&hwstats->traffic_dw,
+			      msecs_to_jiffies(NSIM_DEV_HWSTATS_TRAFFIC_MS));
+}
+
+static struct nsim_dev_hwstats_netdev *
+nsim_dev_hwslist_find_hwsdev(struct list_head *hwsdev_list,
+			     int ifindex)
+{
+	struct nsim_dev_hwstats_netdev *hwsdev;
+
+	list_for_each_entry(hwsdev, hwsdev_list, list) {
+		if (hwsdev->netdev->ifindex == ifindex)
+			return hwsdev;
+	}
+
+	return NULL;
+}
+
+static int nsim_dev_hwsdev_enable(struct nsim_dev_hwstats_netdev *hwsdev,
+				  struct netlink_ext_ack *extack)
+{
+	if (hwsdev->fail_enable) {
+		hwsdev->fail_enable = false;
+		NL_SET_ERR_MSG_MOD(extack, "Stats enablement set to fail");
+		return -ECANCELED;
+	}
+
+	hwsdev->enabled = true;
+	return 0;
+}
+
+static void nsim_dev_hwsdev_disable(struct nsim_dev_hwstats_netdev *hwsdev)
+{
+	hwsdev->enabled = false;
+	memset(&hwsdev->stats, 0, sizeof(hwsdev->stats));
+}
+
+static int
+nsim_dev_hwsdev_report_delta(struct nsim_dev_hwstats_netdev *hwsdev,
+			     struct netdev_notifier_offload_xstats_info *info)
+{
+	netdev_offload_xstats_report_delta(info->report_delta, &hwsdev->stats);
+	memset(&hwsdev->stats, 0, sizeof(hwsdev->stats));
+	return 0;
+}
+
+static void
+nsim_dev_hwsdev_report_used(struct nsim_dev_hwstats_netdev *hwsdev,
+			    struct netdev_notifier_offload_xstats_info *info)
+{
+	if (hwsdev->enabled)
+		netdev_offload_xstats_report_used(info->report_used);
+}
+
+static int nsim_dev_hwstats_event_off_xstats(struct nsim_dev_hwstats *hwstats,
+					     struct net_device *dev,
+					     unsigned long event, void *ptr)
+{
+	struct netdev_notifier_offload_xstats_info *info;
+	struct nsim_dev_hwstats_netdev *hwsdev;
+	struct list_head *hwsdev_list;
+	int err = 0;
+
+	info = ptr;
+	hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, info->type);
+	if (!hwsdev_list)
+		return 0;
+
+	mutex_lock(&hwstats->hwsdev_list_lock);
+
+	hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, dev->ifindex);
+	if (!hwsdev)
+		goto out;
+
+	switch (event) {
+	case NETDEV_OFFLOAD_XSTATS_ENABLE:
+		err = nsim_dev_hwsdev_enable(hwsdev, info->info.extack);
+		break;
+	case NETDEV_OFFLOAD_XSTATS_DISABLE:
+		nsim_dev_hwsdev_disable(hwsdev);
+		break;
+	case NETDEV_OFFLOAD_XSTATS_REPORT_USED:
+		nsim_dev_hwsdev_report_used(hwsdev, info);
+		break;
+	case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA:
+		err = nsim_dev_hwsdev_report_delta(hwsdev, info);
+		break;
+	}
+
+out:
+	mutex_unlock(&hwstats->hwsdev_list_lock);
+	return err;
+}
+
+static void nsim_dev_hwsdev_fini(struct nsim_dev_hwstats_netdev *hwsdev)
+{
+	dev_put(hwsdev->netdev);
+	kfree(hwsdev);
+}
+
+static void
+__nsim_dev_hwstats_event_unregister(struct nsim_dev_hwstats *hwstats,
+				    struct net_device *dev,
+				    enum netdev_offload_xstats_type type)
+{
+	struct nsim_dev_hwstats_netdev *hwsdev;
+	struct list_head *hwsdev_list;
+
+	hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type);
+	if (WARN_ON(!hwsdev_list))
+		return;
+
+	hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, dev->ifindex);
+	if (!hwsdev)
+		return;
+
+	list_del(&hwsdev->list);
+	nsim_dev_hwsdev_fini(hwsdev);
+}
+
+static void nsim_dev_hwstats_event_unregister(struct nsim_dev_hwstats *hwstats,
+					      struct net_device *dev)
+{
+	mutex_lock(&hwstats->hwsdev_list_lock);
+	__nsim_dev_hwstats_event_unregister(hwstats, dev,
+					    NETDEV_OFFLOAD_XSTATS_TYPE_L3);
+	mutex_unlock(&hwstats->hwsdev_list_lock);
+}
+
+static int nsim_dev_hwstats_event(struct nsim_dev_hwstats *hwstats,
+				  struct net_device *dev,
+				  unsigned long event, void *ptr)
+{
+	switch (event) {
+	case NETDEV_OFFLOAD_XSTATS_ENABLE:
+	case NETDEV_OFFLOAD_XSTATS_DISABLE:
+	case NETDEV_OFFLOAD_XSTATS_REPORT_USED:
+	case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA:
+		return nsim_dev_hwstats_event_off_xstats(hwstats, dev,
+							 event, ptr);
+	case NETDEV_UNREGISTER:
+		nsim_dev_hwstats_event_unregister(hwstats, dev);
+		break;
+	}
+
+	return 0;
+}
+
+static int nsim_dev_netdevice_event(struct notifier_block *nb,
+				    unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct nsim_dev_hwstats *hwstats;
+	int err = 0;
+
+	hwstats = container_of(nb, struct nsim_dev_hwstats, netdevice_nb);
+	err = nsim_dev_hwstats_event(hwstats, dev, event, ptr);
+	if (err)
+		return notifier_from_errno(err);
+
+	return NOTIFY_OK;
+}
+
+static int
+nsim_dev_hwstats_enable_ifindex(struct nsim_dev_hwstats *hwstats,
+				int ifindex,
+				enum netdev_offload_xstats_type type,
+				struct list_head *hwsdev_list)
+{
+	struct nsim_dev_hwstats_netdev *hwsdev;
+	struct nsim_dev *nsim_dev;
+	struct net_device *netdev;
+	struct net *net;
+	int err = 0;
+
+	nsim_dev = container_of(hwstats, struct nsim_dev, hwstats);
+	net = nsim_dev_net(nsim_dev);
+
+	rtnl_lock();
+	mutex_lock(&hwstats->hwsdev_list_lock);
+	hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex);
+	if (hwsdev)
+		goto out_unlock_list;
+
+	netdev = dev_get_by_index(net, ifindex);
+	if (!netdev) {
+		err = -ENODEV;
+		goto out_unlock_list;
+	}
+
+	hwsdev = kzalloc_obj(*hwsdev);
+	if (!hwsdev) {
+		err = -ENOMEM;
+		goto out_put_netdev;
+	}
+
+	hwsdev->netdev = netdev;
+	list_add_tail(&hwsdev->list, hwsdev_list);
+	mutex_unlock(&hwstats->hwsdev_list_lock);
+
+	if (netdev_offload_xstats_enabled(netdev, type)) {
+		nsim_dev_hwsdev_enable(hwsdev, NULL);
+		rtnl_offload_xstats_notify(netdev);
+	}
+
+	rtnl_unlock();
+	return err;
+
+out_put_netdev:
+	dev_put(netdev);
+out_unlock_list:
+	mutex_unlock(&hwstats->hwsdev_list_lock);
+	rtnl_unlock();
+	return err;
+}
+
+static int
+nsim_dev_hwstats_disable_ifindex(struct nsim_dev_hwstats *hwstats,
+				 int ifindex,
+				 enum netdev_offload_xstats_type type,
+				 struct list_head *hwsdev_list)
+{
+	struct nsim_dev_hwstats_netdev *hwsdev;
+	int err = 0;
+
+	rtnl_lock();
+	mutex_lock(&hwstats->hwsdev_list_lock);
+	hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex);
+	if (hwsdev)
+		list_del(&hwsdev->list);
+	mutex_unlock(&hwstats->hwsdev_list_lock);
+
+	if (!hwsdev) {
+		err = -ENOENT;
+		goto unlock_out;
+	}
+
+	if (netdev_offload_xstats_enabled(hwsdev->netdev, type)) {
+		netdev_offload_xstats_push_delta(hwsdev->netdev, type,
+						 &hwsdev->stats);
+		rtnl_offload_xstats_notify(hwsdev->netdev);
+	}
+	nsim_dev_hwsdev_fini(hwsdev);
+
+unlock_out:
+	rtnl_unlock();
+	return err;
+}
+
+static int
+nsim_dev_hwstats_fail_ifindex(struct nsim_dev_hwstats *hwstats,
+			      int ifindex,
+			      enum netdev_offload_xstats_type type,
+			      struct list_head *hwsdev_list)
+{
+	struct nsim_dev_hwstats_netdev *hwsdev;
+	int err = 0;
+
+	mutex_lock(&hwstats->hwsdev_list_lock);
+
+	hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex);
+	if (!hwsdev) {
+		err = -ENOENT;
+		goto err_hwsdev_list_unlock;
+	}
+
+	hwsdev->fail_enable = true;
+
+err_hwsdev_list_unlock:
+	mutex_unlock(&hwstats->hwsdev_list_lock);
+	return err;
+}
+
+enum nsim_dev_hwstats_do {
+	NSIM_DEV_HWSTATS_DO_DISABLE,
+	NSIM_DEV_HWSTATS_DO_ENABLE,
+	NSIM_DEV_HWSTATS_DO_FAIL,
+};
+
+struct nsim_dev_hwstats_fops {
+	enum nsim_dev_hwstats_do action;
+	enum netdev_offload_xstats_type type;
+};
+
+static ssize_t
+nsim_dev_hwstats_do_write(struct file *file,
+			  const char __user *data,
+			  size_t count, loff_t *ppos)
+{
+	struct nsim_dev_hwstats *hwstats = file->private_data;
+	const struct nsim_dev_hwstats_fops *hwsfops;
+	struct list_head *hwsdev_list;
+	int ifindex;
+	int err;
+
+	hwsfops = debugfs_get_aux(file);
+
+	err = kstrtoint_from_user(data, count, 0, &ifindex);
+	if (err)
+		return err;
+
+	hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, hwsfops->type);
+	if (WARN_ON(!hwsdev_list))
+		return -EINVAL;
+
+	switch (hwsfops->action) {
+	case NSIM_DEV_HWSTATS_DO_DISABLE:
+		err = nsim_dev_hwstats_disable_ifindex(hwstats, ifindex,
+						       hwsfops->type,
+						       hwsdev_list);
+		break;
+	case NSIM_DEV_HWSTATS_DO_ENABLE:
+		err = nsim_dev_hwstats_enable_ifindex(hwstats, ifindex,
+						      hwsfops->type,
+						      hwsdev_list);
+		break;
+	case NSIM_DEV_HWSTATS_DO_FAIL:
+		err = nsim_dev_hwstats_fail_ifindex(hwstats, ifindex,
+						    hwsfops->type,
+						    hwsdev_list);
+		break;
+	}
+	if (err)
+		return err;
+
+	return count;
+}
+
+static struct debugfs_short_fops debugfs_ops = {
+	.write = nsim_dev_hwstats_do_write,
+	.llseek = generic_file_llseek,
+};
+
+#define NSIM_DEV_HWSTATS_FOPS(ACTION, TYPE)			\
+	{							\
+		.action = ACTION,				\
+		.type = TYPE,					\
+	}
+
+static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_disable_fops =
+	NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_DISABLE,
+			      NETDEV_OFFLOAD_XSTATS_TYPE_L3);
+
+static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_enable_fops =
+	NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_ENABLE,
+			      NETDEV_OFFLOAD_XSTATS_TYPE_L3);
+
+static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_fail_fops =
+	NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_FAIL,
+			      NETDEV_OFFLOAD_XSTATS_TYPE_L3);
+
+#undef NSIM_DEV_HWSTATS_FOPS
+
+int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev)
+{
+	struct nsim_dev_hwstats *hwstats = &nsim_dev->hwstats;
+	struct net *net = nsim_dev_net(nsim_dev);
+	int err;
+
+	mutex_init(&hwstats->hwsdev_list_lock);
+	INIT_LIST_HEAD(&hwstats->l3_list);
+
+	hwstats->netdevice_nb.notifier_call = nsim_dev_netdevice_event;
+	err = register_netdevice_notifier_net(net, &hwstats->netdevice_nb);
+	if (err)
+		goto err_mutex_destroy;
+
+	hwstats->ddir = debugfs_create_dir("hwstats", nsim_dev->ddir);
+	if (IS_ERR(hwstats->ddir)) {
+		err = PTR_ERR(hwstats->ddir);
+		goto err_unregister_notifier;
+	}
+
+	hwstats->l3_ddir = debugfs_create_dir("l3", hwstats->ddir);
+	if (IS_ERR(hwstats->l3_ddir)) {
+		err = PTR_ERR(hwstats->l3_ddir);
+		goto err_remove_hwstats_recursive;
+	}
+
+	debugfs_create_file_aux("enable_ifindex", 0200, hwstats->l3_ddir, hwstats,
+			    &nsim_dev_hwstats_l3_enable_fops, &debugfs_ops);
+	debugfs_create_file_aux("disable_ifindex", 0200, hwstats->l3_ddir, hwstats,
+			    &nsim_dev_hwstats_l3_disable_fops, &debugfs_ops);
+	debugfs_create_file_aux("fail_next_enable", 0200, hwstats->l3_ddir, hwstats,
+			    &nsim_dev_hwstats_l3_fail_fops, &debugfs_ops);
+
+	INIT_DELAYED_WORK(&hwstats->traffic_dw,
+			  &nsim_dev_hwstats_traffic_work);
+	schedule_delayed_work(&hwstats->traffic_dw,
+			      msecs_to_jiffies(NSIM_DEV_HWSTATS_TRAFFIC_MS));
+	return 0;
+
+err_remove_hwstats_recursive:
+	debugfs_remove_recursive(hwstats->ddir);
+err_unregister_notifier:
+	unregister_netdevice_notifier_net(net, &hwstats->netdevice_nb);
+err_mutex_destroy:
+	mutex_destroy(&hwstats->hwsdev_list_lock);
+	return err;
+}
+
+static void nsim_dev_hwsdev_list_wipe(struct nsim_dev_hwstats *hwstats,
+				      enum netdev_offload_xstats_type type)
+{
+	struct nsim_dev_hwstats_netdev *hwsdev, *tmp;
+	struct list_head *hwsdev_list;
+
+	hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type);
+	if (WARN_ON(!hwsdev_list))
+		return;
+
+	mutex_lock(&hwstats->hwsdev_list_lock);
+	list_for_each_entry_safe(hwsdev, tmp, hwsdev_list, list) {
+		list_del(&hwsdev->list);
+		nsim_dev_hwsdev_fini(hwsdev);
+	}
+	mutex_unlock(&hwstats->hwsdev_list_lock);
+}
+
+void nsim_dev_hwstats_exit(struct nsim_dev *nsim_dev)
+{
+	struct nsim_dev_hwstats *hwstats = &nsim_dev->hwstats;
+	struct net *net = nsim_dev_net(nsim_dev);
+
+	cancel_delayed_work_sync(&hwstats->traffic_dw);
+	debugfs_remove_recursive(hwstats->ddir);
+	unregister_netdevice_notifier_net(net, &hwstats->netdevice_nb);
+	nsim_dev_hwsdev_list_wipe(hwstats, NETDEV_OFFLOAD_XSTATS_TYPE_L3);
+	mutex_destroy(&hwstats->hwsdev_list_lock);
+}

linux-7.2.3/drivers/net/netdevsim/ipsec.c

@@ -0,0 +1,296 @@
+// 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 += scnprintf(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;
+
+		if (sap->xs->props.family == AF_INET6)
+			p += scnprintf(p, bufsize - (p - buf),
+				       "sa[%i] %cx ipaddr=%pI6c\n",
+				       i, (sap->rx ? 'r' : 't'), &sap->ipaddr);
+		else
+			p += scnprintf(p, bufsize - (p - buf),
+				       "sa[%i] %cx ipaddr=%pI4\n",
+				       i, (sap->rx ? 'r' : 't'), &sap->ipaddr[3]);
+		p += scnprintf(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 += scnprintf(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 net_device *dev,
+				       struct xfrm_state *xs,
+				       u32 *mykey, u32 *mysalt)
+{
+	const char aes_gcm_name[] = "rfc4106(gcm(aes))";
+	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 net_device *dev,
+			     struct xfrm_state *xs,
+			     struct netlink_ext_ack *extack)
+{
+	struct nsim_ipsec *ipsec;
+	struct netdevsim *ns;
+	struct nsim_sa sa;
+	u16 sa_idx;
+	int ret;
+
+	ns = netdev_priv(dev);
+	ipsec = &ns->ipsec;
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol for ipsec offload");
+		return -EINVAL;
+	}
+
+	if (xs->calg) {
+		NL_SET_ERR_MSG_MOD(extack, "Compression offload not supported");
+		return -EINVAL;
+	}
+
+	if (xs->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported ipsec offload type");
+		return -EINVAL;
+	}
+
+	/* find the first unused index */
+	ret = nsim_ipsec_find_empty_idx(ipsec);
+	if (ret < 0) {
+		NL_SET_ERR_MSG_MOD(extack, "No space for SA in Rx table!");
+		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(dev, xs, sa.key, &sa.salt);
+	if (ret) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for SA table");
+		return ret;
+	}
+
+	if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN)
+		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 net_device *dev, struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(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 const struct xfrmdev_ops nsim_xfrmdev_ops = {
+	.xdo_dev_state_add	= nsim_ipsec_add_sa,
+	.xdo_dev_state_delete	= nsim_ipsec_del_sa,
+};
+
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	struct sec_path *sp = skb_sec_path(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 (!sp)
+		return true;
+
+	if (unlikely(!sp->len)) {
+		netdev_err(ns->netdev, "no xfrm state len = %d\n",
+			   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_features |= NSIM_ESP_FEATURES;
+	ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES;
+
+	ns->ipsec.pfile = debugfs_create_file("ipsec", 0400,
+					      ns->nsim_dev_port->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);
+}

linux-7.2.3/drivers/net/netdevsim/macsec.c

@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <net/macsec.h>
+#include "netdevsim.h"
+
+static int nsim_macsec_find_secy(struct netdevsim *ns, sci_t sci)
+{
+	int i;
+
+	for (i = 0; i < NSIM_MACSEC_MAX_SECY_COUNT; i++) {
+		if (ns->macsec.nsim_secy[i].sci == sci)
+			return i;
+	}
+
+	return -1;
+}
+
+static int nsim_macsec_find_rxsc(struct nsim_secy *ns_secy, sci_t sci)
+{
+	int i;
+
+	for (i = 0; i < NSIM_MACSEC_MAX_RXSC_COUNT; i++) {
+		if (ns_secy->nsim_rxsc[i].sci == sci)
+			return i;
+	}
+
+	return -1;
+}
+
+static int nsim_macsec_add_secy(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	if (ns->macsec.nsim_secy_count == NSIM_MACSEC_MAX_SECY_COUNT)
+		return -ENOSPC;
+
+	for (idx = 0; idx < NSIM_MACSEC_MAX_SECY_COUNT; idx++) {
+		if (!ns->macsec.nsim_secy[idx].used)
+			break;
+	}
+
+	if (idx == NSIM_MACSEC_MAX_SECY_COUNT) {
+		netdev_err(ctx->netdev, "%s: nsim_secy_count not full but all SecYs used\n",
+			   __func__);
+		return -ENOSPC;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: adding new secy with sci %016llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), idx);
+	ns->macsec.nsim_secy[idx].used = true;
+	ns->macsec.nsim_secy[idx].nsim_rxsc_count = 0;
+	ns->macsec.nsim_secy[idx].sci = ctx->secy->sci;
+	ns->macsec.nsim_secy_count++;
+
+	return 0;
+}
+
+static int nsim_macsec_upd_secy(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: updating secy with sci %016llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), idx);
+
+	return 0;
+}
+
+static int nsim_macsec_del_secy(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: removing SecY with SCI %016llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), idx);
+
+	ns->macsec.nsim_secy[idx].used = false;
+	memset(&ns->macsec.nsim_secy[idx], 0, sizeof(ns->macsec.nsim_secy[idx]));
+	ns->macsec.nsim_secy_count--;
+
+	return 0;
+}
+
+static int nsim_macsec_add_rxsc(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	if (secy->nsim_rxsc_count == NSIM_MACSEC_MAX_RXSC_COUNT)
+		return -ENOSPC;
+
+	for (idx = 0; idx < NSIM_MACSEC_MAX_RXSC_COUNT; idx++) {
+		if (!secy->nsim_rxsc[idx].used)
+			break;
+	}
+
+	if (idx == NSIM_MACSEC_MAX_RXSC_COUNT)
+		netdev_err(ctx->netdev, "%s: nsim_rxsc_count not full but all RXSCs used\n",
+			   __func__);
+
+	netdev_dbg(ctx->netdev, "%s: adding new rxsc with sci %016llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->rx_sc->sci), idx);
+	secy->nsim_rxsc[idx].used = true;
+	secy->nsim_rxsc[idx].sci = ctx->rx_sc->sci;
+	secy->nsim_rxsc_count++;
+
+	return 0;
+}
+
+static int nsim_macsec_upd_rxsc(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->rx_sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->rx_sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: updating RXSC with sci %016llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->rx_sc->sci), idx);
+
+	return 0;
+}
+
+static int nsim_macsec_del_rxsc(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->rx_sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->rx_sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: removing RXSC with sci %016llx at index %d\n",
+		   __func__, sci_to_cpu(ctx->rx_sc->sci), idx);
+
+	secy->nsim_rxsc[idx].used = false;
+	memset(&secy->nsim_rxsc[idx], 0, sizeof(secy->nsim_rxsc[idx]));
+	secy->nsim_rxsc_count--;
+
+	return 0;
+}
+
+static int nsim_macsec_add_rxsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_upd_rxsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_del_rxsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	struct nsim_secy *secy;
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+	secy = &ns->macsec.nsim_secy[idx];
+
+	idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n",
+			   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_add_txsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_upd_txsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static int nsim_macsec_del_txsa(struct macsec_context *ctx)
+{
+	struct netdevsim *ns = netdev_priv(ctx->netdev);
+	int idx;
+
+	idx = nsim_macsec_find_secy(ns, ctx->secy->sci);
+	if (idx < 0) {
+		netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n",
+			   __func__, sci_to_cpu(ctx->secy->sci));
+		return -ENOENT;
+	}
+
+	netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n",
+		   __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num);
+
+	return 0;
+}
+
+static const struct macsec_ops nsim_macsec_ops = {
+	.mdo_add_secy = nsim_macsec_add_secy,
+	.mdo_upd_secy = nsim_macsec_upd_secy,
+	.mdo_del_secy = nsim_macsec_del_secy,
+	.mdo_add_rxsc = nsim_macsec_add_rxsc,
+	.mdo_upd_rxsc = nsim_macsec_upd_rxsc,
+	.mdo_del_rxsc = nsim_macsec_del_rxsc,
+	.mdo_add_rxsa = nsim_macsec_add_rxsa,
+	.mdo_upd_rxsa = nsim_macsec_upd_rxsa,
+	.mdo_del_rxsa = nsim_macsec_del_rxsa,
+	.mdo_add_txsa = nsim_macsec_add_txsa,
+	.mdo_upd_txsa = nsim_macsec_upd_txsa,
+	.mdo_del_txsa = nsim_macsec_del_txsa,
+};
+
+void nsim_macsec_init(struct netdevsim *ns)
+{
+	ns->netdev->macsec_ops = &nsim_macsec_ops;
+	ns->netdev->features |= NETIF_F_HW_MACSEC;
+	memset(&ns->macsec, 0, sizeof(ns->macsec));
+}
+
+void nsim_macsec_teardown(struct netdevsim *ns)
+{
+}

linux-7.2.3/drivers/net/netdevsim/netdevsim.h

@@ -0,0 +1,489 @@
+/*
+ * 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/device.h>
+#include <linux/ethtool.h>
+#include <linux/ethtool_netlink.h>
+#include <linux/kernel.h>
+#include <linux/if_vlan.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/ptp_mock.h>
+#include <net/devlink.h>
+#include <net/udp_tunnel.h>
+#include <net/xdp.h>
+#include <net/macsec.h>
+
+#define DRV_NAME	"netdevsim"
+
+#define NSIM_XDP_MAX_MTU	4000
+
+#define NSIM_EA(extack, msg)	NL_SET_ERR_MSG_MOD((extack), msg)
+
+#define NSIM_IPSEC_MAX_SA_COUNT		33
+#define NSIM_IPSEC_VALID		BIT(31)
+#define NSIM_UDP_TUNNEL_N_PORTS		4
+
+#define NSIM_HDS_THRESHOLD_MAX		1024
+
+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;
+};
+
+#define NSIM_MACSEC_MAX_SECY_COUNT 3
+#define NSIM_MACSEC_MAX_RXSC_COUNT 1
+struct nsim_rxsc {
+	sci_t sci;
+	bool used;
+};
+
+struct nsim_secy {
+	sci_t sci;
+	struct nsim_rxsc nsim_rxsc[NSIM_MACSEC_MAX_RXSC_COUNT];
+	u8 nsim_rxsc_count;
+	bool used;
+};
+
+struct nsim_macsec {
+	struct nsim_secy nsim_secy[NSIM_MACSEC_MAX_SECY_COUNT];
+	u8 nsim_secy_count;
+};
+
+struct nsim_vlan {
+	DECLARE_BITMAP(ctag, VLAN_N_VID);
+	DECLARE_BITMAP(stag, VLAN_N_VID);
+};
+
+struct nsim_ethtool_pauseparam {
+	bool rx;
+	bool tx;
+	bool report_stats_rx;
+	bool report_stats_tx;
+};
+
+struct nsim_ethtool {
+	u32 get_err;
+	u32 set_err;
+	u32 channels;
+	struct nsim_ethtool_pauseparam pauseparam;
+	struct ethtool_coalesce coalesce;
+	struct ethtool_ringparam ring;
+	struct ethtool_fecparam fec;
+};
+
+struct nsim_rq {
+	struct napi_struct napi;
+	struct sk_buff_head skb_queue;
+	struct page_pool *page_pool;
+	struct hrtimer napi_timer;
+};
+
+struct netdevsim {
+	struct net_device *netdev;
+	struct nsim_dev *nsim_dev;
+	struct nsim_dev_port *nsim_dev_port;
+	struct mock_phc *phc;
+	struct nsim_rq **rq;
+
+	int rq_reset_mode;
+
+	struct {
+		atomic64_t rx_packets;
+		atomic64_t rx_bytes;
+		atomic64_t tx_packets;
+		atomic64_t tx_bytes;
+		struct psp_dev __rcu *dev;
+		struct dentry *rereg;
+		struct mutex rereg_lock;
+		u32 spi;
+		u32 assoc_cnt;
+	} psp;
+
+	struct nsim_bus_dev *nsim_bus_dev;
+
+	struct bpf_prog	*bpf_offloaded;
+	u32 bpf_offloaded_id;
+
+	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
+
+	bool bpf_tc_accept;
+	bool bpf_tc_non_bound_accept;
+	bool bpf_xdpdrv_accept;
+	bool bpf_xdpoffload_accept;
+
+	bool bpf_map_accept;
+	struct nsim_ipsec ipsec;
+	struct nsim_macsec macsec;
+	struct nsim_vlan vlan;
+	struct {
+		u32 inject_error;
+		u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS];
+		u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS];
+		struct dentry *ddir;
+		struct debugfs_u32_array dfs_ports[2];
+	} udp_ports;
+
+	struct page *page;
+	struct dentry *pp_dfs;
+	struct dentry *qr_dfs;
+	struct dentry *vlan_dfs;
+	struct dentry *ethtool_ddir;
+
+	struct nsim_ethtool ethtool;
+	struct netdevsim __rcu *peer;
+
+	struct notifier_block nb;
+	struct netdev_net_notifier nn;
+};
+
+struct netdevsim *nsim_create(struct nsim_dev *nsim_dev,
+			      struct nsim_dev_port *nsim_dev_port,
+			      u8 perm_addr[ETH_ALEN]);
+void nsim_destroy(struct netdevsim *ns);
+bool netdev_is_nsim(struct net_device *dev);
+
+void nsim_ethtool_init(struct netdevsim *ns);
+void nsim_ethtool_fini(struct netdevsim *ns);
+
+void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev);
+int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
+				 struct net_device *dev);
+void nsim_udp_tunnels_info_destroy(struct net_device *dev);
+
+#ifdef CONFIG_BPF_SYSCALL
+int nsim_bpf_dev_init(struct nsim_dev *nsim_dev);
+void nsim_bpf_dev_exit(struct nsim_dev *nsim_dev);
+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_dev_init(struct nsim_dev *nsim_dev)
+{
+	return 0;
+}
+
+static inline void nsim_bpf_dev_exit(struct nsim_dev *nsim_dev)
+{
+}
+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 -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
+
+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,
+	NSIM_RESOURCE_NEXTHOPS,
+};
+
+enum nsim_port_resource_id {
+	NSIM_PORT_RESOURCE_TEST = 1,
+};
+
+struct nsim_dev_health {
+	struct devlink_health_reporter *empty_reporter;
+	struct devlink_health_reporter *dummy_reporter;
+	struct dentry *ddir;
+	char *recovered_break_msg;
+	u32 binary_len;
+	bool fail_recover;
+};
+
+int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink);
+void nsim_dev_health_exit(struct nsim_dev *nsim_dev);
+
+struct nsim_dev_hwstats_netdev {
+	struct list_head list;
+	struct net_device *netdev;
+	struct rtnl_hw_stats64 stats;
+	bool enabled;
+	bool fail_enable;
+};
+
+struct nsim_dev_hwstats {
+	struct dentry *ddir;
+	struct dentry *l3_ddir;
+
+	struct mutex hwsdev_list_lock; /* protects hwsdev list(s) */
+	struct list_head l3_list;
+
+	struct notifier_block netdevice_nb;
+	struct delayed_work traffic_dw;
+};
+
+int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev);
+void nsim_dev_hwstats_exit(struct nsim_dev *nsim_dev);
+
+#if IS_ENABLED(CONFIG_PSAMPLE)
+int nsim_dev_psample_init(struct nsim_dev *nsim_dev);
+void nsim_dev_psample_exit(struct nsim_dev *nsim_dev);
+#else
+static inline int nsim_dev_psample_init(struct nsim_dev *nsim_dev)
+{
+	return 0;
+}
+
+static inline void nsim_dev_psample_exit(struct nsim_dev *nsim_dev)
+{
+}
+#endif
+
+enum nsim_dev_port_type {
+	NSIM_DEV_PORT_TYPE_PF,
+	NSIM_DEV_PORT_TYPE_VF,
+};
+
+#define NSIM_DEV_VF_PORT_INDEX_BASE 128
+#define NSIM_DEV_VF_PORT_INDEX_MAX UINT_MAX
+
+struct nsim_dev_port {
+	struct list_head list;
+	struct devlink_port devlink_port;
+	unsigned int port_index;
+	enum nsim_dev_port_type port_type;
+	struct dentry *ddir;
+	struct dentry *rate_parent;
+	char *parent_name;
+	u32 tc_bw[DEVLINK_RATE_TCS_MAX];
+	struct netdevsim *ns;
+};
+
+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;
+};
+
+struct nsim_dev {
+	struct nsim_bus_dev *nsim_bus_dev;
+	struct nsim_fib_data *fib_data;
+	struct nsim_trap_data *trap_data;
+	struct dentry *ddir;
+	struct dentry *ports_ddir;
+	struct dentry *take_snapshot;
+	struct dentry *nodes_ddir;
+
+	struct nsim_vf_config *vfconfigs;
+
+	struct bpf_offload_dev *bpf_dev;
+	bool bpf_bind_accept;
+	bool bpf_bind_verifier_accept;
+	u32 bpf_bind_verifier_delay;
+	struct dentry *ddir_bpf_bound_progs;
+	u32 prog_id_gen;
+	struct list_head bpf_bound_progs;
+	struct list_head bpf_bound_maps;
+	struct mutex progs_list_lock;
+	struct netdev_phys_item_id switch_id;
+	struct list_head port_list;
+	bool fw_update_status;
+	u32 fw_update_overwrite_mask;
+	u32 fw_update_flash_chunk_time_ms;
+	u32 max_macs;
+	bool test1;
+	u32 test2;
+	bool dont_allow_reload;
+	bool fail_reload;
+	struct devlink_region *dummy_region;
+	struct nsim_dev_health health;
+	struct nsim_dev_hwstats hwstats;
+	struct flow_action_cookie *fa_cookie;
+	spinlock_t fa_cookie_lock; /* protects fa_cookie */
+	bool fail_trap_group_set;
+	bool fail_trap_policer_set;
+	bool fail_trap_policer_counter_get;
+	bool fail_trap_drop_counter_get;
+	struct {
+		struct udp_tunnel_nic_shared utn_shared;
+		u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS];
+		bool sync_all;
+		bool open_only;
+		bool ipv4_only;
+		bool shared;
+		bool static_iana_vxlan;
+	} udp_ports;
+	struct nsim_dev_psample *psample;
+	u16 esw_mode;
+};
+
+static inline bool nsim_esw_mode_is_legacy(struct nsim_dev *nsim_dev)
+{
+	return nsim_dev->esw_mode == DEVLINK_ESWITCH_MODE_LEGACY;
+}
+
+static inline bool nsim_esw_mode_is_switchdev(struct nsim_dev *nsim_dev)
+{
+	return nsim_dev->esw_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV;
+}
+
+static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev)
+{
+	return devlink_net(priv_to_devlink(nsim_dev));
+}
+
+int nsim_dev_init(void);
+void nsim_dev_exit(void);
+int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev);
+void nsim_drv_remove(struct nsim_bus_dev *nsim_bus_dev);
+int nsim_drv_port_add(struct nsim_bus_dev *nsim_bus_dev,
+		      enum nsim_dev_port_type type, unsigned int port_index,
+		      u8 perm_addr[ETH_ALEN]);
+int nsim_drv_port_del(struct nsim_bus_dev *nsim_bus_dev,
+		      enum nsim_dev_port_type type,
+		      unsigned int port_index);
+int nsim_drv_configure_vfs(struct nsim_bus_dev *nsim_bus_dev,
+			   unsigned int num_vfs);
+
+unsigned int nsim_dev_get_vfs(struct nsim_dev *nsim_dev);
+
+struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
+				      struct netlink_ext_ack *extack);
+void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *fib_data);
+u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
+		     enum nsim_resource_id res_id, bool max);
+
+static inline bool nsim_dev_port_is_pf(struct nsim_dev_port *nsim_dev_port)
+{
+	return nsim_dev_port->port_type == NSIM_DEV_PORT_TYPE_PF;
+}
+
+static inline bool nsim_dev_port_is_vf(struct nsim_dev_port *nsim_dev_port)
+{
+	return nsim_dev_port->port_type == NSIM_DEV_PORT_TYPE_VF;
+}
+#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
+
+#if IS_ENABLED(CONFIG_MACSEC)
+void nsim_macsec_init(struct netdevsim *ns);
+void nsim_macsec_teardown(struct netdevsim *ns);
+#else
+static inline void nsim_macsec_init(struct netdevsim *ns)
+{
+}
+
+static inline void nsim_macsec_teardown(struct netdevsim *ns)
+{
+}
+#endif
+
+#if IS_ENABLED(CONFIG_INET_PSP)
+int nsim_psp_init(struct netdevsim *ns);
+void nsim_psp_uninit(struct netdevsim *ns);
+void nsim_psp_handle_ext(struct sk_buff *skb, struct skb_ext *psp_ext);
+enum skb_drop_reason
+nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns,
+	    struct netdevsim *peer_ns, struct skb_ext **psp_ext);
+#else
+static inline int nsim_psp_init(struct netdevsim *ns) { return 0; }
+static inline void nsim_psp_uninit(struct netdevsim *ns) {}
+static inline enum skb_drop_reason
+nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns,
+	    struct netdevsim *peer_ns, struct skb_ext **psp_ext)
+{
+	return 0;
+}
+
+static inline void
+nsim_psp_handle_ext(struct sk_buff *skb, struct skb_ext *psp_ext) {}
+#endif
+
+int nsim_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		  void *type_data);
+
+struct nsim_bus_dev {
+	struct device dev;
+	struct list_head list;
+	unsigned int port_count;
+	unsigned int num_queues; /* Number of queues for each port on this bus */
+	struct net *initial_net; /* Purpose of this is to carry net pointer
+				  * during the probe time only.
+				  */
+	unsigned int max_vfs;
+	unsigned int num_vfs;
+	bool init;
+};
+
+int nsim_bus_init(void);
+void nsim_bus_exit(void);

linux-7.2.3/drivers/net/netdevsim/psample.c

@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Mellanox Technologies. All rights reserved */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/etherdevice.h>
+#include <linux/inet.h>
+#include <linux/kernel.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <net/devlink.h>
+#include <net/ip.h>
+#include <net/psample.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/udp.h>
+
+#include "netdevsim.h"
+
+#define NSIM_PSAMPLE_REPORT_INTERVAL_MS	100
+#define NSIM_PSAMPLE_INVALID_TC		0xFFFF
+#define NSIM_PSAMPLE_L4_DATA_LEN	100
+
+struct nsim_dev_psample {
+	struct delayed_work psample_dw;
+	struct dentry *ddir;
+	struct psample_group *group;
+	u32 rate;
+	u32 group_num;
+	u32 trunc_size;
+	int in_ifindex;
+	int out_ifindex;
+	u16 out_tc;
+	u64 out_tc_occ_max;
+	u64 latency_max;
+	bool is_active;
+};
+
+static struct sk_buff *nsim_dev_psample_skb_build(void)
+{
+	int tot_len, data_len = NSIM_PSAMPLE_L4_DATA_LEN;
+	struct sk_buff *skb;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	struct iphdr *iph;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+	tot_len = sizeof(struct iphdr) + sizeof(struct udphdr) + data_len;
+
+	skb_reset_mac_header(skb);
+	eth = skb_put(skb, sizeof(struct ethhdr));
+	eth_random_addr(eth->h_dest);
+	eth_random_addr(eth->h_source);
+	eth->h_proto = htons(ETH_P_IP);
+	skb->protocol = htons(ETH_P_IP);
+
+	skb_set_network_header(skb, skb->len);
+	iph = skb_put(skb, sizeof(struct iphdr));
+	iph->protocol = IPPROTO_UDP;
+	iph->saddr = in_aton("192.0.2.1");
+	iph->daddr = in_aton("198.51.100.1");
+	iph->version = 0x4;
+	iph->frag_off = 0;
+	iph->ihl = 0x5;
+	iph->tot_len = htons(tot_len);
+	iph->id = 0;
+	iph->ttl = 100;
+	iph->check = 0;
+	iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
+
+	skb_set_transport_header(skb, skb->len);
+	udph = skb_put_zero(skb, sizeof(struct udphdr) + data_len);
+	get_random_bytes(&udph->source, sizeof(u16));
+	get_random_bytes(&udph->dest, sizeof(u16));
+	udph->len = htons(sizeof(struct udphdr) + data_len);
+
+	return skb;
+}
+
+static void nsim_dev_psample_md_prepare(const struct nsim_dev_psample *psample,
+					struct psample_metadata *md,
+					unsigned int len)
+{
+	md->trunc_size = psample->trunc_size ? psample->trunc_size : len;
+	md->in_ifindex = psample->in_ifindex;
+	md->out_ifindex = psample->out_ifindex;
+
+	if (psample->out_tc != NSIM_PSAMPLE_INVALID_TC) {
+		md->out_tc = psample->out_tc;
+		md->out_tc_valid = 1;
+	}
+
+	if (psample->out_tc_occ_max) {
+		u64 out_tc_occ;
+
+		out_tc_occ = get_random_u64();
+		md->out_tc_occ = out_tc_occ & (psample->out_tc_occ_max - 1);
+		md->out_tc_occ_valid = 1;
+	}
+
+	if (psample->latency_max) {
+		u64 latency;
+
+		latency = get_random_u64();
+		md->latency = latency & (psample->latency_max - 1);
+		md->latency_valid = 1;
+	}
+}
+
+static void nsim_dev_psample_report_work(struct work_struct *work)
+{
+	struct nsim_dev_psample *psample;
+	struct psample_metadata md = {};
+	struct sk_buff *skb;
+	unsigned long delay;
+
+	psample = container_of(work, struct nsim_dev_psample, psample_dw.work);
+
+	skb = nsim_dev_psample_skb_build();
+	if (!skb)
+		goto out;
+
+	nsim_dev_psample_md_prepare(psample, &md, skb->len);
+	psample_sample_packet(psample->group, skb, psample->rate, &md);
+	consume_skb(skb);
+
+out:
+	delay = msecs_to_jiffies(NSIM_PSAMPLE_REPORT_INTERVAL_MS);
+	schedule_delayed_work(&psample->psample_dw, delay);
+}
+
+static int nsim_dev_psample_enable(struct nsim_dev *nsim_dev)
+{
+	struct nsim_dev_psample *psample = nsim_dev->psample;
+	struct devlink *devlink;
+	unsigned long delay;
+
+	if (psample->is_active)
+		return -EBUSY;
+
+	devlink = priv_to_devlink(nsim_dev);
+	psample->group = psample_group_get(devlink_net(devlink),
+					   psample->group_num);
+	if (!psample->group)
+		return -EINVAL;
+
+	delay = msecs_to_jiffies(NSIM_PSAMPLE_REPORT_INTERVAL_MS);
+	schedule_delayed_work(&psample->psample_dw, delay);
+
+	psample->is_active = true;
+
+	return 0;
+}
+
+static int nsim_dev_psample_disable(struct nsim_dev *nsim_dev)
+{
+	struct nsim_dev_psample *psample = nsim_dev->psample;
+
+	if (!psample->is_active)
+		return -EINVAL;
+
+	psample->is_active = false;
+
+	cancel_delayed_work_sync(&psample->psample_dw);
+	psample_group_put(psample->group);
+
+	return 0;
+}
+
+static ssize_t nsim_dev_psample_enable_write(struct file *file,
+					     const char __user *data,
+					     size_t count, loff_t *ppos)
+{
+	struct nsim_dev *nsim_dev = file->private_data;
+	bool enable;
+	int err;
+
+	err = kstrtobool_from_user(data, count, &enable);
+	if (err)
+		return err;
+
+	if (enable)
+		err = nsim_dev_psample_enable(nsim_dev);
+	else
+		err = nsim_dev_psample_disable(nsim_dev);
+
+	return err ? err : count;
+}
+
+static const struct file_operations nsim_psample_enable_fops = {
+	.open = simple_open,
+	.write = nsim_dev_psample_enable_write,
+	.llseek = generic_file_llseek,
+	.owner = THIS_MODULE,
+};
+
+int nsim_dev_psample_init(struct nsim_dev *nsim_dev)
+{
+	struct nsim_dev_psample *psample;
+	int err;
+
+	psample = kzalloc_obj(*psample);
+	if (!psample)
+		return -ENOMEM;
+	nsim_dev->psample = psample;
+
+	INIT_DELAYED_WORK(&psample->psample_dw, nsim_dev_psample_report_work);
+
+	psample->ddir = debugfs_create_dir("psample", nsim_dev->ddir);
+	if (IS_ERR(psample->ddir)) {
+		err = PTR_ERR(psample->ddir);
+		goto err_psample_free;
+	}
+
+	/* Populate sampling parameters with sane defaults. */
+	psample->rate = 100;
+	debugfs_create_u32("rate", 0600, psample->ddir, &psample->rate);
+
+	psample->group_num = 10;
+	debugfs_create_u32("group_num", 0600, psample->ddir,
+			   &psample->group_num);
+
+	psample->trunc_size = 0;
+	debugfs_create_u32("trunc_size", 0600, psample->ddir,
+			   &psample->trunc_size);
+
+	psample->in_ifindex = 1;
+	debugfs_create_u32("in_ifindex", 0600, psample->ddir,
+			   &psample->in_ifindex);
+
+	psample->out_ifindex = 2;
+	debugfs_create_u32("out_ifindex", 0600, psample->ddir,
+			   &psample->out_ifindex);
+
+	psample->out_tc = 0;
+	debugfs_create_u16("out_tc", 0600, psample->ddir, &psample->out_tc);
+
+	psample->out_tc_occ_max = 10000;
+	debugfs_create_u64("out_tc_occ_max", 0600, psample->ddir,
+			   &psample->out_tc_occ_max);
+
+	psample->latency_max = 50;
+	debugfs_create_u64("latency_max", 0600, psample->ddir,
+			   &psample->latency_max);
+
+	debugfs_create_file("enable", 0200, psample->ddir, nsim_dev,
+			    &nsim_psample_enable_fops);
+
+	return 0;
+
+err_psample_free:
+	kfree(nsim_dev->psample);
+	return err;
+}
+
+void nsim_dev_psample_exit(struct nsim_dev *nsim_dev)
+{
+	debugfs_remove_recursive(nsim_dev->psample->ddir);
+	if (nsim_dev->psample->is_active) {
+		cancel_delayed_work_sync(&nsim_dev->psample->psample_dw);
+		psample_group_put(nsim_dev->psample->group);
+	}
+	kfree(nsim_dev->psample);
+}

linux-7.2.3/drivers/net/netdevsim/psp.c

@@ -0,0 +1,287 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <net/ip6_checksum.h>
+#include <net/psp.h>
+#include <net/sock.h>
+
+#include "netdevsim.h"
+
+void nsim_psp_handle_ext(struct sk_buff *skb, struct skb_ext *psp_ext)
+{
+	if (psp_ext)
+		__skb_ext_set(skb, SKB_EXT_PSP, psp_ext);
+}
+
+enum skb_drop_reason
+nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns,
+	    struct netdevsim *peer_ns, struct skb_ext **psp_ext)
+{
+	enum skb_drop_reason rc = 0;
+	struct psp_dev *peer_psd;
+	struct psp_assoc *pas;
+	struct net *net;
+	int psp_len;
+	void **ptr;
+
+	rcu_read_lock();
+	pas = psp_skb_get_assoc_rcu(skb);
+	if (!pas) {
+		rc = SKB_NOT_DROPPED_YET;
+		goto out_unlock;
+	}
+
+	if (!skb_transport_header_was_set(skb)) {
+		rc = SKB_DROP_REASON_PSP_OUTPUT;
+		goto out_unlock;
+	}
+
+	ptr = psp_assoc_drv_data(pas);
+	if (*ptr != ns) {
+		rc = SKB_DROP_REASON_PSP_OUTPUT;
+		goto out_unlock;
+	}
+
+	net = sock_net(skb->sk);
+	if (!psp_dev_encapsulate(net, skb, pas->tx.spi, pas->version, 0)) {
+		rc = SKB_DROP_REASON_PSP_OUTPUT;
+		goto out_unlock;
+	}
+
+	psp_len = skb->len - skb_inner_transport_offset(skb);
+	atomic64_inc(&ns->psp.tx_packets);
+	atomic64_add(psp_len, &ns->psp.tx_bytes);
+
+	/* Now pretend we just received this frame */
+	peer_psd = rcu_dereference(peer_ns->psp.dev);
+	if (peer_psd && peer_psd->config.versions & (1 << pas->version)) {
+		bool strip_icv = false;
+		u8 generation;
+
+		/* We cheat a bit and put the generation in the key.
+		 * In real life if generation was too old, then decryption would
+		 * fail. Here, we just make it so a bad key causes a bad
+		 * generation too, and psp_sk_rx_policy_check() will fail.
+		 */
+		generation = pas->tx.key[0];
+
+		skb_ext_reset(skb);
+		skb->mac_len = ETH_HLEN;
+		if (psp_dev_rcv(skb, peer_psd->id, generation, strip_icv)) {
+			rc = SKB_DROP_REASON_PSP_OUTPUT;
+			goto out_unlock;
+		}
+
+		*psp_ext = skb->extensions;
+		refcount_inc(&(*psp_ext)->refcnt);
+		skb->decrypted = 1;
+
+		atomic64_inc(&peer_ns->psp.rx_packets);
+		atomic64_add(psp_len, &peer_ns->psp.rx_bytes);
+	} else {
+		struct ipv6hdr *ip6h __maybe_unused;
+		struct iphdr *iph;
+		struct udphdr *uh;
+		__wsum csum;
+
+		/* Do not decapsulate. Receive the skb with the udp and psp
+		 * headers still there as if this is a normal udp packet.
+		 * psp_dev_encapsulate() sets udp checksum to 0, so we need to
+		 * provide a valid checksum here, so the skb isn't dropped.
+		 */
+		uh = udp_hdr(skb);
+		csum = skb_checksum(skb, skb_transport_offset(skb),
+				    ntohs(uh->len), 0);
+
+		switch (skb->protocol) {
+		case htons(ETH_P_IP):
+			iph = ip_hdr(skb);
+			uh->check = udp_v4_check(ntohs(uh->len), iph->saddr,
+						 iph->daddr, csum);
+			break;
+#if IS_ENABLED(CONFIG_IPV6)
+		case htons(ETH_P_IPV6):
+			ip6h = ipv6_hdr(skb);
+			uh->check = udp_v6_check(ntohs(uh->len), &ip6h->saddr,
+						 &ip6h->daddr, csum);
+			break;
+#endif
+		}
+
+		uh->check	= uh->check ?: CSUM_MANGLED_0;
+		skb->ip_summed	= CHECKSUM_NONE;
+	}
+
+out_unlock:
+	rcu_read_unlock();
+	return rc;
+}
+
+static int
+nsim_psp_set_config(struct psp_dev *psd, struct psp_dev_config *conf,
+		    struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static int
+nsim_rx_spi_alloc(struct psp_dev *psd, u32 version,
+		  struct psp_key_parsed *assoc,
+		  struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = psd->drv_priv;
+	int i;
+
+	/* Check if incrementing the spi would change the phase bit */
+	if ((ns->psp.spi & PSP_SPI_KEY_ID) == PSP_SPI_KEY_ID) {
+		NL_SET_ERR_MSG(extack, "SPI space exhausted");
+		return -ENOSPC;
+	}
+
+	assoc->spi = cpu_to_be32(++ns->psp.spi);
+	assoc->key[0] = psd->generation;
+	for (i = 1; i < PSP_MAX_KEY; i++)
+		assoc->key[i] = ns->psp.spi + i;
+
+	return 0;
+}
+
+static int nsim_assoc_add(struct psp_dev *psd, struct psp_assoc *pas,
+			  struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = psd->drv_priv;
+	void **ptr = psp_assoc_drv_data(pas);
+
+	/* Copy drv_priv from psd to assoc */
+	*ptr = psd->drv_priv;
+	ns->psp.assoc_cnt++;
+
+	return 0;
+}
+
+static int nsim_key_rotate(struct psp_dev *psd, struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = psd->drv_priv;
+
+	/* Flip key phase and reset SPI to 0 within that space
+	 * (will be pre-incremented, as 0 is an invalid SPI).
+	 */
+	if (ns->psp.spi & PSP_SPI_KEY_PHASE)
+		ns->psp.spi = 0;
+	else
+		ns->psp.spi = PSP_SPI_KEY_PHASE;
+
+	return 0;
+}
+
+static void nsim_assoc_del(struct psp_dev *psd, struct psp_assoc *pas)
+{
+	struct netdevsim *ns = psd->drv_priv;
+	void **ptr = psp_assoc_drv_data(pas);
+
+	*ptr = NULL;
+	ns->psp.assoc_cnt--;
+}
+
+static void nsim_get_stats(struct psp_dev *psd, struct psp_dev_stats *stats)
+{
+	struct netdevsim *ns = psd->drv_priv;
+
+	/* WARNING: do *not* blindly zero stats in real drivers!
+	 * All required stats must be reported by the device!
+	 */
+	memset(stats, 0, sizeof(struct psp_dev_stats));
+
+	stats->rx_bytes = atomic64_read(&ns->psp.rx_bytes);
+	stats->rx_packets = atomic64_read(&ns->psp.rx_packets);
+	stats->tx_bytes = atomic64_read(&ns->psp.tx_bytes);
+	stats->tx_packets = atomic64_read(&ns->psp.tx_packets);
+}
+
+static struct psp_dev_ops nsim_psp_ops = {
+	.set_config	= nsim_psp_set_config,
+	.rx_spi_alloc	= nsim_rx_spi_alloc,
+	.tx_key_add	= nsim_assoc_add,
+	.tx_key_del	= nsim_assoc_del,
+	.key_rotate	= nsim_key_rotate,
+	.get_stats	= nsim_get_stats,
+};
+
+static struct psp_dev_caps nsim_psp_caps = {
+	.versions = 1 << PSP_VERSION_HDR0_AES_GCM_128 |
+		    1 << PSP_VERSION_HDR0_AES_GMAC_128 |
+		    1 << PSP_VERSION_HDR0_AES_GCM_256 |
+		    1 << PSP_VERSION_HDR0_AES_GMAC_256,
+	.assoc_drv_spc = sizeof(void *),
+};
+
+static void __nsim_psp_uninit(struct netdevsim *ns, bool teardown)
+{
+	struct psp_dev *psd;
+
+	psd = rcu_dereference_protected(ns->psp.dev,
+					teardown ||
+					lockdep_is_held(&ns->psp.rereg_lock));
+	if (psd) {
+		rcu_assign_pointer(ns->psp.dev, NULL);
+		synchronize_rcu();
+		psp_dev_unregister(psd);
+	}
+	WARN_ON(ns->psp.assoc_cnt);
+}
+
+void nsim_psp_uninit(struct netdevsim *ns)
+{
+	debugfs_remove(ns->psp.rereg);
+	mutex_destroy(&ns->psp.rereg_lock);
+	__nsim_psp_uninit(ns, true);
+}
+
+static ssize_t
+nsim_psp_rereg_write(struct file *file, const char __user *data, size_t count,
+		     loff_t *ppos)
+{
+	struct netdevsim *ns = file->private_data;
+	struct psp_dev *psd;
+	ssize_t ret;
+
+	mutex_lock(&ns->psp.rereg_lock);
+	__nsim_psp_uninit(ns, false);
+
+	psd = psp_dev_create(ns->netdev, &nsim_psp_ops, &nsim_psp_caps, ns);
+	if (IS_ERR(psd)) {
+		ret = PTR_ERR(psd);
+		goto out;
+	}
+
+	rcu_assign_pointer(ns->psp.dev, psd);
+	ret = count;
+out:
+	mutex_unlock(&ns->psp.rereg_lock);
+	return ret;
+}
+
+static const struct file_operations nsim_psp_rereg_fops = {
+	.open = simple_open,
+	.write = nsim_psp_rereg_write,
+	.llseek = generic_file_llseek,
+	.owner = THIS_MODULE,
+};
+
+int nsim_psp_init(struct netdevsim *ns)
+{
+	struct dentry *ddir = ns->nsim_dev_port->ddir;
+	struct psp_dev *psd;
+
+	psd = psp_dev_create(ns->netdev, &nsim_psp_ops, &nsim_psp_caps, ns);
+	if (IS_ERR(psd))
+		return PTR_ERR(psd);
+
+	rcu_assign_pointer(ns->psp.dev, psd);
+
+	mutex_init(&ns->psp.rereg_lock);
+	ns->psp.rereg = debugfs_create_file("psp_rereg", 0200, ddir, ns,
+					    &nsim_psp_rereg_fops);
+	return 0;
+}

linux-7.2.3/drivers/net/netdevsim/tc.c

@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/netdevice.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+
+#include "netdevsim.h"
+
+static int
+nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+{
+	struct flow_cls_common_offload *common = type_data;
+	int err = 0;
+
+	switch (type) {
+	case TC_SETUP_CLSBPF:
+		err = nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv);
+		break;
+	case TC_SETUP_CLSFLOWER:
+		break;
+	default:
+		NSIM_EA(common->extack, "offload type not supported");
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static void nsim_taprio_stats(struct tc_taprio_qopt_stats *stats)
+{
+	stats->window_drops = 0;
+	stats->tx_overruns = 0;
+}
+
+static int nsim_setup_tc_taprio(struct net_device *dev,
+				struct tc_taprio_qopt_offload *offload)
+{
+	int err = 0;
+
+	switch (offload->cmd) {
+	case TAPRIO_CMD_REPLACE:
+	case TAPRIO_CMD_DESTROY:
+		break;
+	case TAPRIO_CMD_STATS:
+		nsim_taprio_stats(&offload->stats);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int nsim_setup_tc_ets(struct net_device *dev,
+			     struct tc_ets_qopt_offload *offload)
+{
+	int err = 0;
+
+	switch (offload->command) {
+	case TC_ETS_REPLACE:
+	case TC_ETS_DESTROY:
+		break;
+	case TC_ETS_STATS:
+		_bstats_update(offload->stats.bstats, 0, 0);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static LIST_HEAD(nsim_block_cb_list);
+
+int
+nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_TAPRIO:
+		return nsim_setup_tc_taprio(dev, type_data);
+	case TC_SETUP_QDISC_ETS:
+		return nsim_setup_tc_ets(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return flow_block_cb_setup_simple(type_data,
+						  &nsim_block_cb_list,
+						  nsim_setup_tc_block_cb,
+						  ns, ns, true);
+	case TC_SETUP_FT:
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+ALLOW_ERROR_INJECTION(nsim_setup_tc, ERRNO);

linux-7.2.3/drivers/net/netdevsim/udp_tunnels.c

@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2020 Facebook Inc.
+
+#include <linux/debugfs.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <net/udp_tunnel.h>
+
+#include "netdevsim.h"
+
+static int
+nsim_udp_tunnel_set_port(struct net_device *dev, unsigned int table,
+			 unsigned int entry, struct udp_tunnel_info *ti)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	int ret;
+
+	ret = -ns->udp_ports.inject_error;
+	ns->udp_ports.inject_error = 0;
+
+	if (!ret) {
+		if (ns->udp_ports.ports[table][entry]) {
+			WARN(1, "entry already in use\n");
+			ret = -EBUSY;
+		} else {
+			ns->udp_ports.ports[table][entry] =
+				be16_to_cpu(ti->port) << 16 | ti->type;
+		}
+	}
+
+	netdev_info(dev, "set [%d, %d] type %d family %d port %d - %d\n",
+		    table, entry, ti->type, ti->sa_family, ntohs(ti->port),
+		    ret);
+	return ret;
+}
+
+static int
+nsim_udp_tunnel_unset_port(struct net_device *dev, unsigned int table,
+			   unsigned int entry, struct udp_tunnel_info *ti)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	int ret;
+
+	ret = -ns->udp_ports.inject_error;
+	ns->udp_ports.inject_error = 0;
+
+	if (!ret) {
+		u32 val = be16_to_cpu(ti->port) << 16 | ti->type;
+
+		if (val == ns->udp_ports.ports[table][entry]) {
+			ns->udp_ports.ports[table][entry] = 0;
+		} else {
+			WARN(1, "entry not installed %x vs %x\n",
+			     val, ns->udp_ports.ports[table][entry]);
+			ret = -ENOENT;
+		}
+	}
+
+	netdev_info(dev, "unset [%d, %d] type %d family %d port %d - %d\n",
+		    table, entry, ti->type, ti->sa_family, ntohs(ti->port),
+		    ret);
+	return ret;
+}
+
+static int
+nsim_udp_tunnel_sync_table(struct net_device *dev, unsigned int table)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	struct udp_tunnel_info ti;
+	unsigned int i;
+	int ret;
+
+	ret = -ns->udp_ports.inject_error;
+	ns->udp_ports.inject_error = 0;
+
+	for (i = 0; i < NSIM_UDP_TUNNEL_N_PORTS; i++) {
+		udp_tunnel_nic_get_port(dev, table, i, &ti);
+		ns->udp_ports.ports[table][i] =
+			be16_to_cpu(ti.port) << 16 | ti.type;
+	}
+
+	return ret;
+}
+
+static const struct udp_tunnel_nic_info nsim_udp_tunnel_info = {
+	.set_port	= nsim_udp_tunnel_set_port,
+	.unset_port	= nsim_udp_tunnel_unset_port,
+	.sync_table	= nsim_udp_tunnel_sync_table,
+
+	.tables = {
+		{
+			.n_entries	= NSIM_UDP_TUNNEL_N_PORTS,
+			.tunnel_types	= UDP_TUNNEL_TYPE_VXLAN,
+		},
+		{
+			.n_entries	= NSIM_UDP_TUNNEL_N_PORTS,
+			.tunnel_types	= UDP_TUNNEL_TYPE_GENEVE |
+					  UDP_TUNNEL_TYPE_VXLAN_GPE,
+		},
+	},
+};
+
+static ssize_t
+nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data,
+				  size_t count, loff_t *ppos)
+{
+	struct net_device *dev = file->private_data;
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (dev->reg_state == NETREG_REGISTERED) {
+		memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports));
+		udp_tunnel_nic_reset_ntf(dev);
+	}
+
+	return count;
+}
+
+static const struct file_operations nsim_udp_tunnels_info_reset_fops = {
+	.open = simple_open,
+	.write = nsim_udp_tunnels_info_reset_write,
+	.llseek = generic_file_llseek,
+	.owner = THIS_MODULE,
+};
+
+int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
+				 struct net_device *dev)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	struct udp_tunnel_nic_info *info;
+
+	if (nsim_dev->udp_ports.shared && nsim_dev->udp_ports.open_only) {
+		dev_err(&nsim_dev->nsim_bus_dev->dev,
+			"shared can't be used in conjunction with open_only\n");
+		return -EINVAL;
+	}
+
+	if (!nsim_dev->udp_ports.shared)
+		ns->udp_ports.ports = ns->udp_ports.__ports;
+	else
+		ns->udp_ports.ports = nsim_dev->udp_ports.__ports;
+
+	ns->udp_ports.ddir = debugfs_create_dir("udp_ports",
+						ns->nsim_dev_port->ddir);
+
+	debugfs_create_u32("inject_error", 0600, ns->udp_ports.ddir,
+			   &ns->udp_ports.inject_error);
+
+	ns->udp_ports.dfs_ports[0].array = ns->udp_ports.ports[0];
+	ns->udp_ports.dfs_ports[0].n_elements = NSIM_UDP_TUNNEL_N_PORTS;
+	debugfs_create_u32_array("table0", 0400, ns->udp_ports.ddir,
+				 &ns->udp_ports.dfs_ports[0]);
+
+	ns->udp_ports.dfs_ports[1].array = ns->udp_ports.ports[1];
+	ns->udp_ports.dfs_ports[1].n_elements = NSIM_UDP_TUNNEL_N_PORTS;
+	debugfs_create_u32_array("table1", 0400, ns->udp_ports.ddir,
+				 &ns->udp_ports.dfs_ports[1]);
+
+	debugfs_create_file("reset", 0200, ns->udp_ports.ddir,
+			    dev, &nsim_udp_tunnels_info_reset_fops);
+
+	/* Note: it's not normal to allocate the info struct like this!
+	 * Drivers are expected to use a static const one, here we're testing.
+	 */
+	info = kmemdup(&nsim_udp_tunnel_info, sizeof(nsim_udp_tunnel_info),
+		       GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	if (nsim_dev->udp_ports.sync_all) {
+		info->set_port = NULL;
+		info->unset_port = NULL;
+	} else {
+		info->sync_table = NULL;
+	}
+
+	if (nsim_dev->udp_ports.open_only)
+		info->flags |= UDP_TUNNEL_NIC_INFO_OPEN_ONLY;
+	if (nsim_dev->udp_ports.ipv4_only)
+		info->flags |= UDP_TUNNEL_NIC_INFO_IPV4_ONLY;
+	if (nsim_dev->udp_ports.shared)
+		info->shared = &nsim_dev->udp_ports.utn_shared;
+	if (nsim_dev->udp_ports.static_iana_vxlan)
+		info->flags |= UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN;
+
+	dev->udp_tunnel_nic_info = info;
+	return 0;
+}
+
+void nsim_udp_tunnels_info_destroy(struct net_device *dev)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	debugfs_remove_recursive(ns->udp_ports.ddir);
+	kfree(dev->udp_tunnel_nic_info);
+	dev->udp_tunnel_nic_info = NULL;
+}
+
+void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev)
+{
+	debugfs_create_bool("udp_ports_sync_all", 0600, nsim_dev->ddir,
+			    &nsim_dev->udp_ports.sync_all);
+	debugfs_create_bool("udp_ports_open_only", 0600, nsim_dev->ddir,
+			    &nsim_dev->udp_ports.open_only);
+	debugfs_create_bool("udp_ports_ipv4_only", 0600, nsim_dev->ddir,
+			    &nsim_dev->udp_ports.ipv4_only);
+	debugfs_create_bool("udp_ports_shared", 0600, nsim_dev->ddir,
+			    &nsim_dev->udp_ports.shared);
+	debugfs_create_bool("udp_ports_static_iana_vxlan", 0600, nsim_dev->ddir,
+			    &nsim_dev->udp_ports.static_iana_vxlan);
+}