Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

5 files changed, 524 insertions, 58 deletions

diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile
index 449b2a1a1800..0fee1d06c084 100644
--- a/drivers/net/netdevsim/Makefile
+++ b/drivers/net/netdevsim/Makefile
@@ -13,3 +13,7 @@ endif
 ifneq ($(CONFIG_NET_DEVLINK),)
 netdevsim-objs += devlink.o fib.o
 endif
+
+ifneq ($(CONFIG_XFRM_OFFLOAD),)
+netdevsim-objs += ipsec.o
+endif
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 75c25306d234..81444208b216 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -92,7 +92,7 @@ static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = {
 
 static bool nsim_xdp_offload_active(struct netdevsim *ns)
 {
-	return ns->xdp_prog_mode == XDP_ATTACHED_HW;
+	return ns->xdp_hw.prog;
 }
 
 static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
@@ -195,14 +195,14 @@ static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 	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)
+static int
+nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf,
+		  struct xdp_attachment_info *xdp)
 {
 	int err;
 
-	if (ns->xdp_prog && (bpf->flags ^ ns->xdp_flags) & XDP_FLAGS_MODES) {
-		NSIM_EA(bpf->extack, "program loaded with different flags");
+	if (!xdp_attachment_flags_ok(xdp, bpf))
 		return -EBUSY;
-	}
 
 	if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) {
 		NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS");
@@ -219,18 +219,7 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 			return err;
 	}
 
-	if (ns->xdp_prog)
-		bpf_prog_put(ns->xdp_prog);
-
-	ns->xdp_prog = bpf->prog;
-	ns->xdp_flags = bpf->flags;
-
-	if (!bpf->prog)
-		ns->xdp_prog_mode = XDP_ATTACHED_NONE;
-	else if (bpf->command == XDP_SETUP_PROG)
-		ns->xdp_prog_mode = XDP_ATTACHED_DRV;
-	else
-		ns->xdp_prog_mode = XDP_ATTACHED_HW;
+	xdp_attachment_setup(xdp, bpf);
 
 	return 0;
 }
@@ -249,8 +238,8 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 	state->state = "verify";
 
 	/* Program id is not populated yet when we create the state. */
-	sprintf(name, "%u", ns->prog_id_gen++);
-	state->ddir = debugfs_create_dir(name, ns->ddir_bpf_bound_progs);
+	sprintf(name, "%u", ns->sdev->prog_id_gen++);
+	state->ddir = debugfs_create_dir(name, ns->sdev->ddir_bpf_bound_progs);
 	if (IS_ERR_OR_NULL(state->ddir)) {
 		kfree(state);
 		return -ENOMEM;
@@ -261,7 +250,7 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 			    &state->state, &nsim_bpf_string_fops);
 	debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded);
 
-	list_add_tail(&state->l, &ns->bpf_bound_progs);
+	list_add_tail(&state->l, &ns->sdev->bpf_bound_progs);
 
 	prog->aux->offload->dev_priv = state;
 
@@ -290,10 +279,6 @@ static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 		NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled");
 		return -EINVAL;
 	}
-	if (nsim_xdp_offload_active(ns)) {
-		NSIM_EA(bpf->extack, "xdp offload active, can't load drv prog");
-		return -EBUSY;
-	}
 	return 0;
 }
 
@@ -309,7 +294,7 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 		NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
 		return -EINVAL;
 	}
-	if (bpf->prog->aux->offload->netdev != ns->netdev) {
+	if (!bpf_offload_dev_match(bpf->prog, ns->netdev)) {
 		NSIM_EA(bpf->extack, "program bound to different dev");
 		return -EINVAL;
 	}
@@ -512,7 +497,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 	}
 
 	offmap->dev_ops = &nsim_bpf_map_ops;
-	list_add_tail(&nmap->l, &ns->bpf_bound_maps);
+	list_add_tail(&nmap->l, &ns->sdev->bpf_bound_maps);
 
 	return 0;
 
@@ -567,22 +552,21 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		nsim_bpf_destroy_prog(bpf->offload.prog);
 		return 0;
 	case XDP_QUERY_PROG:
-		bpf->prog_attached = ns->xdp_prog_mode;
-		bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0;
-		bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0;
-		return 0;
+		return xdp_attachment_query(&ns->xdp, bpf);
+	case XDP_QUERY_PROG_HW:
+		return xdp_attachment_query(&ns->xdp_hw, bpf);
 	case XDP_SETUP_PROG:
 		err = nsim_setup_prog_checks(ns, bpf);
 		if (err)
 			return err;
 
-		return nsim_xdp_set_prog(ns, bpf);
+		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);
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw);
 	case BPF_OFFLOAD_MAP_ALLOC:
 		if (!ns->bpf_map_accept)
 			return -EOPNOTSUPP;
@@ -598,8 +582,26 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 
 int nsim_bpf_init(struct netdevsim *ns)
 {
-	INIT_LIST_HEAD(&ns->bpf_bound_progs);
-	INIT_LIST_HEAD(&ns->bpf_bound_maps);
+	int err;
+
+	if (ns->sdev->refcnt == 1) {
+		INIT_LIST_HEAD(&ns->sdev->bpf_bound_progs);
+		INIT_LIST_HEAD(&ns->sdev->bpf_bound_maps);
+
+		ns->sdev->ddir_bpf_bound_progs =
+			debugfs_create_dir("bpf_bound_progs", ns->sdev->ddir);
+		if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs))
+			return -ENOMEM;
+
+		ns->sdev->bpf_dev = bpf_offload_dev_create();
+		err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev);
+		if (err)
+			return err;
+	}
+
+	err = bpf_offload_dev_netdev_register(ns->sdev->bpf_dev, ns->netdev);
+	if (err)
+		goto err_destroy_bdev;
 
 	debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir,
 			   &ns->bpf_offloaded_id);
@@ -609,10 +611,6 @@ int nsim_bpf_init(struct netdevsim *ns)
 			    &ns->bpf_bind_accept);
 	debugfs_create_u32("bpf_bind_verifier_delay", 0600, ns->ddir,
 			   &ns->bpf_bind_verifier_delay);
-	ns->ddir_bpf_bound_progs =
-		debugfs_create_dir("bpf_bound_progs", ns->ddir);
-	if (IS_ERR_OR_NULL(ns->ddir_bpf_bound_progs))
-		return -ENOMEM;
 
 	ns->bpf_tc_accept = true;
 	debugfs_create_bool("bpf_tc_accept", 0600, ns->ddir,
@@ -631,12 +629,23 @@ int nsim_bpf_init(struct netdevsim *ns)
 			    &ns->bpf_map_accept);
 
 	return 0;
+
+err_destroy_bdev:
+	if (ns->sdev->refcnt == 1)
+		bpf_offload_dev_destroy(ns->sdev->bpf_dev);
+	return err;
 }
 
 void nsim_bpf_uninit(struct netdevsim *ns)
 {
-	WARN_ON(!list_empty(&ns->bpf_bound_progs));
-	WARN_ON(!list_empty(&ns->bpf_bound_maps));
-	WARN_ON(ns->xdp_prog);
+	WARN_ON(ns->xdp.prog);
+	WARN_ON(ns->xdp_hw.prog);
 	WARN_ON(ns->bpf_offloaded);
+	bpf_offload_dev_netdev_unregister(ns->sdev->bpf_dev, ns->netdev);
+
+	if (ns->sdev->refcnt == 1) {
+		WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs));
+		WARN_ON(!list_empty(&ns->sdev->bpf_bound_maps));
+		bpf_offload_dev_destroy(ns->sdev->bpf_dev);
+	}
 }
diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c
new file mode 100644
index 000000000000..2dcf6cc269d0
--- /dev/null
+++ b/drivers/net/netdevsim/ipsec.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */
+
+#include <crypto/aead.h>
+#include <linux/debugfs.h>
+#include <net/xfrm.h>
+
+#include "netdevsim.h"
+
+#define NSIM_IPSEC_AUTH_BITS	128
+
+static ssize_t nsim_dbg_netdev_ops_read(struct file *filp,
+					char __user *buffer,
+					size_t count, loff_t *ppos)
+{
+	struct netdevsim *ns = filp->private_data;
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	size_t bufsize;
+	char *buf, *p;
+	int len;
+	int i;
+
+	/* the buffer needed is
+	 * (num SAs * 3 lines each * ~60 bytes per line) + one more line
+	 */
+	bufsize = (ipsec->count * 4 * 60) + 60;
+	buf = kzalloc(bufsize, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	p = buf;
+	p += snprintf(p, bufsize - (p - buf),
+		      "SA count=%u tx=%u\n",
+		      ipsec->count, ipsec->tx);
+
+	for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+		struct nsim_sa *sap = &ipsec->sa[i];
+
+		if (!sap->used)
+			continue;
+
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n",
+			      i, (sap->rx ? 'r' : 't'), sap->ipaddr[0],
+			      sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]);
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i]    spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n",
+			      i, be32_to_cpu(sap->xs->id.spi),
+			      sap->xs->id.proto, sap->salt, sap->crypt);
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i]    key=0x%08x %08x %08x %08x\n",
+			      i, sap->key[0], sap->key[1],
+			      sap->key[2], sap->key[3]);
+	}
+
+	len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf);
+
+	kfree(buf);
+	return len;
+}
+
+static const struct file_operations ipsec_dbg_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = nsim_dbg_netdev_ops_read,
+};
+
+static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec)
+{
+	u32 i;
+
+	if (ipsec->count == NSIM_IPSEC_MAX_SA_COUNT)
+		return -ENOSPC;
+
+	/* search sa table */
+	for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+		if (!ipsec->sa[i].used)
+			return i;
+	}
+
+	return -ENOSPC;
+}
+
+static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs,
+				       u32 *mykey, u32 *mysalt)
+{
+	const char aes_gcm_name[] = "rfc4106(gcm(aes))";
+	struct net_device *dev = xs->xso.dev;
+	unsigned char *key_data;
+	char *alg_name = NULL;
+	int key_len;
+
+	if (!xs->aead) {
+		netdev_err(dev, "Unsupported IPsec algorithm\n");
+		return -EINVAL;
+	}
+
+	if (xs->aead->alg_icv_len != NSIM_IPSEC_AUTH_BITS) {
+		netdev_err(dev, "IPsec offload requires %d bit authentication\n",
+			   NSIM_IPSEC_AUTH_BITS);
+		return -EINVAL;
+	}
+
+	key_data = &xs->aead->alg_key[0];
+	key_len = xs->aead->alg_key_len;
+	alg_name = xs->aead->alg_name;
+
+	if (strcmp(alg_name, aes_gcm_name)) {
+		netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n",
+			   aes_gcm_name);
+		return -EINVAL;
+	}
+
+	/* 160 accounts for 16 byte key and 4 byte salt */
+	if (key_len > NSIM_IPSEC_AUTH_BITS) {
+		*mysalt = ((u32 *)key_data)[4];
+	} else if (key_len == NSIM_IPSEC_AUTH_BITS) {
+		*mysalt = 0;
+	} else {
+		netdev_err(dev, "IPsec hw offload only supports 128 bit keys with optional 32 bit salt\n");
+		return -EINVAL;
+	}
+	memcpy(mykey, key_data, 16);
+
+	return 0;
+}
+
+static int nsim_ipsec_add_sa(struct xfrm_state *xs)
+{
+	struct nsim_ipsec *ipsec;
+	struct net_device *dev;
+	struct netdevsim *ns;
+	struct nsim_sa sa;
+	u16 sa_idx;
+	int ret;
+
+	dev = xs->xso.dev;
+	ns = netdev_priv(dev);
+	ipsec = &ns->ipsec;
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n",
+			   xs->id.proto);
+		return -EINVAL;
+	}
+
+	if (xs->calg) {
+		netdev_err(dev, "Compression offload not supported\n");
+		return -EINVAL;
+	}
+
+	/* find the first unused index */
+	ret = nsim_ipsec_find_empty_idx(ipsec);
+	if (ret < 0) {
+		netdev_err(dev, "No space for SA in Rx table!\n");
+		return ret;
+	}
+	sa_idx = (u16)ret;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.used = true;
+	sa.xs = xs;
+
+	if (sa.xs->id.proto & IPPROTO_ESP)
+		sa.crypt = xs->ealg || xs->aead;
+
+	/* get the key and salt */
+	ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt);
+	if (ret) {
+		netdev_err(dev, "Failed to get key data for SA table\n");
+		return ret;
+	}
+
+	if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+		sa.rx = true;
+
+		if (xs->props.family == AF_INET6)
+			memcpy(sa.ipaddr, &xs->id.daddr.a6, 16);
+		else
+			memcpy(&sa.ipaddr[3], &xs->id.daddr.a4, 4);
+	}
+
+	/* the preparations worked, so save the info */
+	memcpy(&ipsec->sa[sa_idx], &sa, sizeof(sa));
+
+	/* the XFRM stack doesn't like offload_handle == 0,
+	 * so add a bitflag in case our array index is 0
+	 */
+	xs->xso.offload_handle = sa_idx | NSIM_IPSEC_VALID;
+	ipsec->count++;
+
+	return 0;
+}
+
+static void nsim_ipsec_del_sa(struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(xs->xso.dev);
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	u16 sa_idx;
+
+	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+	if (!ipsec->sa[sa_idx].used) {
+		netdev_err(ns->netdev, "Invalid SA for delete sa_idx=%d\n",
+			   sa_idx);
+		return;
+	}
+
+	memset(&ipsec->sa[sa_idx], 0, sizeof(struct nsim_sa));
+	ipsec->count--;
+}
+
+static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(xs->xso.dev);
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+
+	ipsec->ok++;
+
+	return true;
+}
+
+static const struct xfrmdev_ops nsim_xfrmdev_ops = {
+	.xdo_dev_state_add	= nsim_ipsec_add_sa,
+	.xdo_dev_state_delete	= nsim_ipsec_del_sa,
+	.xdo_dev_offload_ok	= nsim_ipsec_offload_ok,
+};
+
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	struct xfrm_state *xs;
+	struct nsim_sa *tsa;
+	u32 sa_idx;
+
+	/* do we even need to check this packet? */
+	if (!skb->sp)
+		return true;
+
+	if (unlikely(!skb->sp->len)) {
+		netdev_err(ns->netdev, "no xfrm state len = %d\n",
+			   skb->sp->len);
+		return false;
+	}
+
+	xs = xfrm_input_state(skb);
+	if (unlikely(!xs)) {
+		netdev_err(ns->netdev, "no xfrm_input_state() xs = %p\n", xs);
+		return false;
+	}
+
+	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+	if (unlikely(sa_idx >= NSIM_IPSEC_MAX_SA_COUNT)) {
+		netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n",
+			   sa_idx, NSIM_IPSEC_MAX_SA_COUNT);
+		return false;
+	}
+
+	tsa = &ipsec->sa[sa_idx];
+	if (unlikely(!tsa->used)) {
+		netdev_err(ns->netdev, "unused sa_idx=%d\n", sa_idx);
+		return false;
+	}
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(ns->netdev, "unexpected proto=%d\n", xs->id.proto);
+		return false;
+	}
+
+	ipsec->tx++;
+
+	return true;
+}
+
+void nsim_ipsec_init(struct netdevsim *ns)
+{
+	ns->netdev->xfrmdev_ops = &nsim_xfrmdev_ops;
+
+#define NSIM_ESP_FEATURES	(NETIF_F_HW_ESP | \
+				 NETIF_F_HW_ESP_TX_CSUM | \
+				 NETIF_F_GSO_ESP)
+
+	ns->netdev->features |= NSIM_ESP_FEATURES;
+	ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES;
+
+	ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, ns->ddir, ns,
+					      &ipsec_dbg_fops);
+}
+
+void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+
+	if (ipsec->count)
+		netdev_err(ns->netdev, "tearing down IPsec offload with %d SAs left\n",
+			   ipsec->count);
+	debugfs_remove_recursive(ipsec->pfile);
+}
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index ec68f38213d9..8d8e2b3f263e 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -22,6 +22,7 @@
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
+#include <net/switchdev.h>
 
 #include "netdevsim.h"
 
@@ -40,6 +41,9 @@ struct nsim_vf_config {
 
 static u32 nsim_dev_id;
 
+static struct dentry *nsim_ddir;
+static struct dentry *nsim_sdev_ddir;
+
 static int nsim_num_vf(struct device *dev)
 {
 	struct netdevsim *ns = to_nsim(dev);
@@ -144,8 +148,29 @@ static struct device_type nsim_dev_type = {
 	.release = nsim_dev_release,
 };
 
+static int
+nsim_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+		attr->u.ppid.id_len = sizeof(ns->sdev->switch_id);
+		memcpy(&attr->u.ppid.id, &ns->sdev->switch_id,
+		       attr->u.ppid.id_len);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct switchdev_ops nsim_switchdev_ops = {
+	.switchdev_port_attr_get	= nsim_port_attr_get,
+};
+
 static int nsim_init(struct net_device *dev)
 {
+	char sdev_ddir_name[10], sdev_link_name[32];
 	struct netdevsim *ns = netdev_priv(dev);
 	int err;
 
@@ -154,9 +179,32 @@ static int nsim_init(struct net_device *dev)
 	if (IS_ERR_OR_NULL(ns->ddir))
 		return -ENOMEM;
 
+	if (!ns->sdev) {
+		ns->sdev = kzalloc(sizeof(*ns->sdev), GFP_KERNEL);
+		if (!ns->sdev) {
+			err = -ENOMEM;
+			goto err_debugfs_destroy;
+		}
+		ns->sdev->refcnt = 1;
+		ns->sdev->switch_id = nsim_dev_id;
+		sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
+		ns->sdev->ddir = debugfs_create_dir(sdev_ddir_name,
+						    nsim_sdev_ddir);
+		if (IS_ERR_OR_NULL(ns->sdev->ddir)) {
+			err = PTR_ERR_OR_ZERO(ns->sdev->ddir) ?: -EINVAL;
+			goto err_sdev_free;
+		}
+	} else {
+		sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
+		ns->sdev->refcnt++;
+	}
+
+	sprintf(sdev_link_name, "../../" DRV_NAME "_sdev/%s", sdev_ddir_name);
+	debugfs_create_symlink("sdev", ns->ddir, sdev_link_name);
+
 	err = nsim_bpf_init(ns);
 	if (err)
-		goto err_debugfs_destroy;
+		goto err_sdev_destroy;
 
 	ns->dev.id = nsim_dev_id++;
 	ns->dev.bus = &nsim_bus;
@@ -166,17 +214,26 @@ static int nsim_init(struct net_device *dev)
 		goto err_bpf_uninit;
 
 	SET_NETDEV_DEV(dev, &ns->dev);
+	SWITCHDEV_SET_OPS(dev, &nsim_switchdev_ops);
 
 	err = nsim_devlink_setup(ns);
 	if (err)
 		goto err_unreg_dev;
 
+	nsim_ipsec_init(ns);
+
 	return 0;
 
 err_unreg_dev:
 	device_unregister(&ns->dev);
 err_bpf_uninit:
 	nsim_bpf_uninit(ns);
+err_sdev_destroy:
+	if (!--ns->sdev->refcnt) {
+		debugfs_remove_recursive(ns->sdev->ddir);
+err_sdev_free:
+		kfree(ns->sdev);
+	}
 err_debugfs_destroy:
 	debugfs_remove_recursive(ns->ddir);
 	return err;
@@ -186,9 +243,14 @@ static void nsim_uninit(struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
+	nsim_ipsec_teardown(ns);
 	nsim_devlink_teardown(ns);
 	debugfs_remove_recursive(ns->ddir);
 	nsim_bpf_uninit(ns);
+	if (!--ns->sdev->refcnt) {
+		debugfs_remove_recursive(ns->sdev->ddir);
+		kfree(ns->sdev);
+	}
 }
 
 static void nsim_free(struct net_device *dev)
@@ -203,11 +265,15 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
+	if (!nsim_ipsec_tx(ns, skb))
+		goto out;
+
 	u64_stats_update_begin(&ns->syncp);
 	ns->tx_packets++;
 	ns->tx_bytes += skb->len;
 	u64_stats_update_end(&ns->syncp);
 
+out:
 	dev_kfree_skb(skb);
 
 	return NETDEV_TX_OK;
@@ -221,8 +287,7 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
-	if (ns->xdp_prog_mode == XDP_ATTACHED_DRV &&
-	    new_mtu > NSIM_XDP_MAX_MTU)
+	if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
 		return -EBUSY;
 
 	dev->mtu = new_mtu;
@@ -260,7 +325,7 @@ nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f)
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb,
-					     ns, ns);
+					     ns, ns, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns);
 		return 0;
@@ -464,15 +529,46 @@ static int nsim_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
+static int nsim_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[],
+			struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (tb[IFLA_LINK]) {
+		struct net_device *joindev;
+		struct netdevsim *joinns;
+
+		joindev = __dev_get_by_index(src_net,
+					     nla_get_u32(tb[IFLA_LINK]));
+		if (!joindev)
+			return -ENODEV;
+		if (joindev->netdev_ops != &nsim_netdev_ops)
+			return -EINVAL;
+
+		joinns = netdev_priv(joindev);
+		if (!joinns->sdev || !joinns->sdev->refcnt)
+			return -EINVAL;
+		ns->sdev = joinns->sdev;
+	}
+
+	return register_netdevice(dev);
+}
+
+static void nsim_dellink(struct net_device *dev, struct list_head *head)
+{
+	unregister_netdevice_queue(dev, head);
+}
+
 static struct rtnl_link_ops nsim_link_ops __read_mostly = {
 	.kind		= DRV_NAME,
 	.priv_size	= sizeof(struct netdevsim),
 	.setup		= nsim_setup,
 	.validate	= nsim_validate,
+	.newlink	= nsim_newlink,
+	.dellink	= nsim_dellink,
 };
 
-struct dentry *nsim_ddir;
-
 static int __init nsim_module_init(void)
 {
 	int err;
@@ -481,9 +577,15 @@ static int __init nsim_module_init(void)
 	if (IS_ERR_OR_NULL(nsim_ddir))
 		return -ENOMEM;
 
+	nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL);
+	if (IS_ERR_OR_NULL(nsim_sdev_ddir)) {
+		err = -ENOMEM;
+		goto err_debugfs_destroy;
+	}
+
 	err = bus_register(&nsim_bus);
 	if (err)
-		goto err_debugfs_destroy;
+		goto err_sdir_destroy;
 
 	err = nsim_devlink_init();
 	if (err)
@@ -499,6 +601,8 @@ err_dl_fini:
 	nsim_devlink_exit();
 err_unreg_bus:
 	bus_unregister(&nsim_bus);
+err_sdir_destroy:
+	debugfs_remove_recursive(nsim_sdev_ddir);
 err_debugfs_destroy:
 	debugfs_remove_recursive(nsim_ddir);
 	return err;
@@ -509,6 +613,7 @@ static void __exit nsim_module_exit(void)
 	rtnl_link_unregister(&nsim_link_ops);
 	nsim_devlink_exit();
 	bus_unregister(&nsim_bus);
+	debugfs_remove_recursive(nsim_sdev_ddir);
 	debugfs_remove_recursive(nsim_ddir);
 }
 
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 8ca50b72c328..384c254fafc5 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -18,6 +18,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
 
 #define DRV_NAME	"netdevsim"
 
@@ -26,9 +27,46 @@
 #define NSIM_EA(extack, msg)	NL_SET_ERR_MSG_MOD((extack), msg)
 
 struct bpf_prog;
+struct bpf_offload_dev;
 struct dentry;
 struct nsim_vf_config;
 
+struct netdevsim_shared_dev {
+	unsigned int refcnt;
+	u32 switch_id;
+
+	struct dentry *ddir;
+
+	struct bpf_offload_dev *bpf_dev;
+
+	struct dentry *ddir_bpf_bound_progs;
+	u32 prog_id_gen;
+
+	struct list_head bpf_bound_progs;
+	struct list_head bpf_bound_maps;
+};
+
+#define NSIM_IPSEC_MAX_SA_COUNT		33
+#define NSIM_IPSEC_VALID		BIT(31)
+
+struct nsim_sa {
+	struct xfrm_state *xs;
+	__be32 ipaddr[4];
+	u32 key[4];
+	u32 salt;
+	bool used;
+	bool crypt;
+	bool rx;
+};
+
+struct nsim_ipsec {
+	struct nsim_sa sa[NSIM_IPSEC_MAX_SA_COUNT];
+	struct dentry *pfile;
+	u32 count;
+	u32 tx;
+	u32 ok;
+};
+
 struct netdevsim {
 	struct net_device *netdev;
 
@@ -37,6 +75,7 @@ struct netdevsim {
 	struct u64_stats_sync syncp;
 
 	struct device dev;
+	struct netdevsim_shared_dev *sdev;
 
 	struct dentry *ddir;
 
@@ -46,16 +85,11 @@ struct netdevsim {
 	struct bpf_prog	*bpf_offloaded;
 	u32 bpf_offloaded_id;
 
-	u32 xdp_flags;
-	int xdp_prog_mode;
-	struct bpf_prog	*xdp_prog;
-
-	u32 prog_id_gen;
+	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
 
 	bool bpf_bind_accept;
 	u32 bpf_bind_verifier_delay;
-	struct dentry *ddir_bpf_bound_progs;
-	struct list_head bpf_bound_progs;
 
 	bool bpf_tc_accept;
 	bool bpf_tc_non_bound_accept;
@@ -63,14 +97,12 @@ struct netdevsim {
 	bool bpf_xdpoffload_accept;
 
 	bool bpf_map_accept;
-	struct list_head bpf_bound_maps;
 #if IS_ENABLED(CONFIG_NET_DEVLINK)
 	struct devlink *devlink;
 #endif
+	struct nsim_ipsec ipsec;
 };
 
-extern struct dentry *nsim_ddir;
-
 #ifdef CONFIG_BPF_SYSCALL
 int nsim_bpf_init(struct netdevsim *ns);
 void nsim_bpf_uninit(struct netdevsim *ns);
@@ -148,6 +180,25 @@ static inline void nsim_devlink_exit(void)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
+void nsim_ipsec_init(struct netdevsim *ns);
+void nsim_ipsec_teardown(struct netdevsim *ns);
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb);
+#else
+static inline void nsim_ipsec_init(struct netdevsim *ns)
+{
+}
+
+static inline void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+}
+
+static inline bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	return true;
+}
+#endif
+
 static inline struct netdevsim *to_nsim(struct device *ptr)
 {
 	return container_of(ptr, struct netdevsim, dev);