Adding upstream version 6.6.15.upstream/6.6.15

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

20 files changed, 19136 insertions, 0 deletions

diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
new file mode 100644
index 0000000000..3adf31a83a
--- /dev/null
+++ b/net/xfrm/Kconfig
@@ -0,0 +1,140 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# XFRM configuration
+#
+config XFRM
+	bool
+	depends on INET
+	select GRO_CELLS
+	select SKB_EXTENSIONS
+
+config XFRM_OFFLOAD
+	bool
+
+config XFRM_ALGO
+	tristate
+	select XFRM
+	select CRYPTO
+	select CRYPTO_HASH
+	select CRYPTO_SKCIPHER
+
+if INET
+config XFRM_USER
+	tristate "Transformation user configuration interface"
+	select XFRM_ALGO
+	help
+	  Support for Transformation(XFRM) user configuration interface
+	  like IPsec used by native Linux tools.
+
+	  If unsure, say Y.
+
+config XFRM_USER_COMPAT
+	tristate "Compatible ABI support"
+	depends on XFRM_USER && COMPAT_FOR_U64_ALIGNMENT && \
+		HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select WANT_COMPAT_NETLINK_MESSAGES
+	help
+	  Transformation(XFRM) user configuration interface like IPsec
+	  used by compatible Linux applications.
+
+	  If unsure, say N.
+
+config XFRM_INTERFACE
+	tristate "Transformation virtual interface"
+	depends on XFRM && IPV6
+	help
+	  This provides a virtual interface to route IPsec traffic.
+
+	  If unsure, say N.
+
+config XFRM_SUB_POLICY
+	bool "Transformation sub policy support"
+	depends on XFRM
+	help
+	  Support sub policy for developers. By using sub policy with main
+	  one, two policies can be applied to the same packet at once.
+	  Policy which lives shorter time in kernel should be a sub.
+
+	  If unsure, say N.
+
+config XFRM_MIGRATE
+	bool "Transformation migrate database"
+	depends on XFRM
+	help
+	  A feature to update locator(s) of a given IPsec security
+	  association dynamically.  This feature is required, for
+	  instance, in a Mobile IPv6 environment with IPsec configuration
+	  where mobile nodes change their attachment point to the Internet.
+
+	  If unsure, say N.
+
+config XFRM_STATISTICS
+	bool "Transformation statistics"
+	depends on XFRM && PROC_FS
+	help
+	  This statistics is not a SNMP/MIB specification but shows
+	  statistics about transformation error (or almost error) factor
+	  at packet processing for developer.
+
+	  If unsure, say N.
+
+# This option selects XFRM_ALGO along with the AH authentication algorithms that
+# RFC 8221 lists as MUST be implemented.
+config XFRM_AH
+	tristate
+	select XFRM_ALGO
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_SHA256
+
+# This option selects XFRM_ALGO along with the ESP encryption and authentication
+# algorithms that RFC 8221 lists as MUST be implemented.
+config XFRM_ESP
+	tristate
+	select XFRM_ALGO
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_AUTHENC
+	select CRYPTO_CBC
+	select CRYPTO_ECHAINIV
+	select CRYPTO_GCM
+	select CRYPTO_HMAC
+	select CRYPTO_SEQIV
+	select CRYPTO_SHA256
+
+config XFRM_IPCOMP
+	tristate
+	select XFRM_ALGO
+	select CRYPTO
+	select CRYPTO_DEFLATE
+
+config NET_KEY
+	tristate "PF_KEY sockets"
+	select XFRM_ALGO
+	help
+	  PF_KEYv2 socket family, compatible to KAME ones.
+	  They are required if you are going to use IPsec tools ported
+	  from KAME.
+
+	  Say Y unless you know what you are doing.
+
+config NET_KEY_MIGRATE
+	bool "PF_KEY MIGRATE"
+	depends on NET_KEY
+	select XFRM_MIGRATE
+	help
+	  Add a PF_KEY MIGRATE message to PF_KEYv2 socket family.
+	  The PF_KEY MIGRATE message is used to dynamically update
+	  locator(s) of a given IPsec security association.
+	  This feature is required, for instance, in a Mobile IPv6
+	  environment with IPsec configuration where mobile nodes
+	  change their attachment point to the Internet.  Detail
+	  information can be found in the internet-draft
+	  <draft-sugimoto-mip6-pfkey-migrate>.
+
+	  If unsure, say N.
+
+config XFRM_ESPINTCP
+	bool
+
+endif # INET
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
new file mode 100644
index 0000000000..cd47f88921
--- /dev/null
+++ b/net/xfrm/Makefile
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the XFRM subsystem.
+#
+
+xfrm_interface-$(CONFIG_XFRM_INTERFACE) += xfrm_interface_core.o
+
+ifeq ($(CONFIG_XFRM_INTERFACE),m)
+xfrm_interface-$(CONFIG_DEBUG_INFO_BTF_MODULES) += xfrm_interface_bpf.o
+else ifeq ($(CONFIG_XFRM_INTERFACE),y)
+xfrm_interface-$(CONFIG_DEBUG_INFO_BTF) += xfrm_interface_bpf.o
+endif
+
+obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \
+		      xfrm_input.o xfrm_output.o \
+		      xfrm_sysctl.o xfrm_replay.o xfrm_device.o
+obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o
+obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o
+obj-$(CONFIG_XFRM_USER) += xfrm_user.o
+obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
+obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
+obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
+obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
new file mode 100644
index 0000000000..d3b3f9e720
--- /dev/null
+++ b/net/xfrm/espintcp.c
@@ -0,0 +1,589 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <net/tcp.h>
+#include <net/strparser.h>
+#include <net/xfrm.h>
+#include <net/esp.h>
+#include <net/espintcp.h>
+#include <linux/skmsg.h>
+#include <net/inet_common.h>
+#include <trace/events/sock.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6_stubs.h>
+#endif
+
+static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb,
+			  struct sock *sk)
+{
+	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf ||
+	    !sk_rmem_schedule(sk, skb, skb->truesize)) {
+		XFRM_INC_STATS(sock_net(sk), LINUX_MIB_XFRMINERROR);
+		kfree_skb(skb);
+		return;
+	}
+
+	skb_set_owner_r(skb, sk);
+
+	memset(skb->cb, 0, sizeof(skb->cb));
+	skb_queue_tail(&ctx->ike_queue, skb);
+	ctx->saved_data_ready(sk);
+}
+
+static void handle_esp(struct sk_buff *skb, struct sock *sk)
+{
+	struct tcp_skb_cb *tcp_cb = (struct tcp_skb_cb *)skb->cb;
+
+	skb_reset_transport_header(skb);
+
+	/* restore IP CB, we need at least IP6CB->nhoff */
+	memmove(skb->cb, &tcp_cb->header, sizeof(tcp_cb->header));
+
+	rcu_read_lock();
+	skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
+	local_bh_disable();
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		ipv6_stub->xfrm6_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP);
+	else
+#endif
+		xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP);
+	local_bh_enable();
+	rcu_read_unlock();
+}
+
+static void espintcp_rcv(struct strparser *strp, struct sk_buff *skb)
+{
+	struct espintcp_ctx *ctx = container_of(strp, struct espintcp_ctx,
+						strp);
+	struct strp_msg *rxm = strp_msg(skb);
+	int len = rxm->full_len - 2;
+	u32 nonesp_marker;
+	int err;
+
+	/* keepalive packet? */
+	if (unlikely(len == 1)) {
+		u8 data;
+
+		err = skb_copy_bits(skb, rxm->offset + 2, &data, 1);
+		if (err < 0) {
+			XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR);
+			kfree_skb(skb);
+			return;
+		}
+
+		if (data == 0xff) {
+			kfree_skb(skb);
+			return;
+		}
+	}
+
+	/* drop other short messages */
+	if (unlikely(len <= sizeof(nonesp_marker))) {
+		XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR);
+		kfree_skb(skb);
+		return;
+	}
+
+	err = skb_copy_bits(skb, rxm->offset + 2, &nonesp_marker,
+			    sizeof(nonesp_marker));
+	if (err < 0) {
+		XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR);
+		kfree_skb(skb);
+		return;
+	}
+
+	/* remove header, leave non-ESP marker/SPI */
+	if (!pskb_pull(skb, rxm->offset + 2)) {
+		XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR);
+		kfree_skb(skb);
+		return;
+	}
+
+	if (pskb_trim(skb, rxm->full_len - 2) != 0) {
+		XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR);
+		kfree_skb(skb);
+		return;
+	}
+
+	if (nonesp_marker == 0)
+		handle_nonesp(ctx, skb, strp->sk);
+	else
+		handle_esp(skb, strp->sk);
+}
+
+static int espintcp_parse(struct strparser *strp, struct sk_buff *skb)
+{
+	struct strp_msg *rxm = strp_msg(skb);
+	__be16 blen;
+	u16 len;
+	int err;
+
+	if (skb->len < rxm->offset + 2)
+		return 0;
+
+	err = skb_copy_bits(skb, rxm->offset, &blen, sizeof(blen));
+	if (err < 0)
+		return err;
+
+	len = be16_to_cpu(blen);
+	if (len < 2)
+		return -EINVAL;
+
+	return len;
+}
+
+static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			    int flags, int *addr_len)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+	struct sk_buff *skb;
+	int err = 0;
+	int copied;
+	int off = 0;
+
+	skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, &off, &err);
+	if (!skb) {
+		if (err == -EAGAIN && sk->sk_shutdown & RCV_SHUTDOWN)
+			return 0;
+		return err;
+	}
+
+	copied = len;
+	if (copied > skb->len)
+		copied = skb->len;
+	else if (copied < skb->len)
+		msg->msg_flags |= MSG_TRUNC;
+
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
+	if (unlikely(err)) {
+		kfree_skb(skb);
+		return err;
+	}
+
+	if (flags & MSG_TRUNC)
+		copied = skb->len;
+	kfree_skb(skb);
+	return copied;
+}
+
+int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+	if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog))
+		return -ENOBUFS;
+
+	__skb_queue_tail(&ctx->out_queue, skb);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(espintcp_queue_out);
+
+/* espintcp length field is 2B and length includes the length field's size */
+#define MAX_ESPINTCP_MSG (((1 << 16) - 1) - 2)
+
+static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg,
+				   int flags)
+{
+	do {
+		int ret;
+
+		ret = skb_send_sock_locked(sk, emsg->skb,
+					   emsg->offset, emsg->len);
+		if (ret < 0)
+			return ret;
+
+		emsg->len -= ret;
+		emsg->offset += ret;
+	} while (emsg->len > 0);
+
+	kfree_skb(emsg->skb);
+	memset(emsg, 0, sizeof(*emsg));
+
+	return 0;
+}
+
+static int espintcp_sendskmsg_locked(struct sock *sk,
+				     struct espintcp_msg *emsg, int flags)
+{
+	struct msghdr msghdr = {
+		.msg_flags = flags | MSG_SPLICE_PAGES | MSG_MORE,
+	};
+	struct sk_msg *skmsg = &emsg->skmsg;
+	bool more = flags & MSG_MORE;
+	struct scatterlist *sg;
+	int done = 0;
+	int ret;
+
+	sg = &skmsg->sg.data[skmsg->sg.start];
+	do {
+		struct bio_vec bvec;
+		size_t size = sg->length - emsg->offset;
+		int offset = sg->offset + emsg->offset;
+		struct page *p;
+
+		emsg->offset = 0;
+
+		if (sg_is_last(sg) && !more)
+			msghdr.msg_flags &= ~MSG_MORE;
+
+		p = sg_page(sg);
+retry:
+		bvec_set_page(&bvec, p, size, offset);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size);
+		ret = tcp_sendmsg_locked(sk, &msghdr, size);
+		if (ret < 0) {
+			emsg->offset = offset - sg->offset;
+			skmsg->sg.start += done;
+			return ret;
+		}
+
+		if (ret != size) {
+			offset += ret;
+			size -= ret;
+			goto retry;
+		}
+
+		done++;
+		put_page(p);
+		sk_mem_uncharge(sk, sg->length);
+		sg = sg_next(sg);
+	} while (sg);
+
+	memset(emsg, 0, sizeof(*emsg));
+
+	return 0;
+}
+
+static int espintcp_push_msgs(struct sock *sk, int flags)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+	struct espintcp_msg *emsg = &ctx->partial;
+	int err;
+
+	if (!emsg->len)
+		return 0;
+
+	if (ctx->tx_running)
+		return -EAGAIN;
+	ctx->tx_running = 1;
+
+	if (emsg->skb)
+		err = espintcp_sendskb_locked(sk, emsg, flags);
+	else
+		err = espintcp_sendskmsg_locked(sk, emsg, flags);
+	if (err == -EAGAIN) {
+		ctx->tx_running = 0;
+		return flags & MSG_DONTWAIT ? -EAGAIN : 0;
+	}
+	if (!err)
+		memset(emsg, 0, sizeof(*emsg));
+
+	ctx->tx_running = 0;
+
+	return err;
+}
+
+int espintcp_push_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+	struct espintcp_msg *emsg = &ctx->partial;
+	unsigned int len;
+	int offset;
+
+	if (sk->sk_state != TCP_ESTABLISHED) {
+		kfree_skb(skb);
+		return -ECONNRESET;
+	}
+
+	offset = skb_transport_offset(skb);
+	len = skb->len - offset;
+
+	espintcp_push_msgs(sk, 0);
+
+	if (emsg->len) {
+		kfree_skb(skb);
+		return -ENOBUFS;
+	}
+
+	skb_set_owner_w(skb, sk);
+
+	emsg->offset = offset;
+	emsg->len = len;
+	emsg->skb = skb;
+
+	espintcp_push_msgs(sk, 0);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(espintcp_push_skb);
+
+static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+	long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+	struct espintcp_msg *emsg = &ctx->partial;
+	struct iov_iter pfx_iter;
+	struct kvec pfx_iov = {};
+	size_t msglen = size + 2;
+	char buf[2] = {0};
+	int err, end;
+
+	if (msg->msg_flags & ~MSG_DONTWAIT)
+		return -EOPNOTSUPP;
+
+	if (size > MAX_ESPINTCP_MSG)
+		return -EMSGSIZE;
+
+	if (msg->msg_controllen)
+		return -EOPNOTSUPP;
+
+	lock_sock(sk);
+
+	err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT);
+	if (err < 0) {
+		if (err != -EAGAIN || !(msg->msg_flags & MSG_DONTWAIT))
+			err = -ENOBUFS;
+		goto unlock;
+	}
+
+	sk_msg_init(&emsg->skmsg);
+	while (1) {
+		/* only -ENOMEM is possible since we don't coalesce */
+		err = sk_msg_alloc(sk, &emsg->skmsg, msglen, 0);
+		if (!err)
+			break;
+
+		err = sk_stream_wait_memory(sk, &timeo);
+		if (err)
+			goto fail;
+	}
+
+	*((__be16 *)buf) = cpu_to_be16(msglen);
+	pfx_iov.iov_base = buf;
+	pfx_iov.iov_len = sizeof(buf);
+	iov_iter_kvec(&pfx_iter, ITER_SOURCE, &pfx_iov, 1, pfx_iov.iov_len);
+
+	err = sk_msg_memcopy_from_iter(sk, &pfx_iter, &emsg->skmsg,
+				       pfx_iov.iov_len);
+	if (err < 0)
+		goto fail;
+
+	err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, &emsg->skmsg, size);
+	if (err < 0)
+		goto fail;
+
+	end = emsg->skmsg.sg.end;
+	emsg->len = size;
+	sk_msg_iter_var_prev(end);
+	sg_mark_end(sk_msg_elem(&emsg->skmsg, end));
+
+	tcp_rate_check_app_limited(sk);
+
+	err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT);
+	/* this message could be partially sent, keep it */
+
+	release_sock(sk);
+
+	return size;
+
+fail:
+	sk_msg_free(sk, &emsg->skmsg);
+	memset(emsg, 0, sizeof(*emsg));
+unlock:
+	release_sock(sk);
+	return err;
+}
+
+static struct proto espintcp_prot __ro_after_init;
+static struct proto_ops espintcp_ops __ro_after_init;
+static struct proto espintcp6_prot;
+static struct proto_ops espintcp6_ops;
+static DEFINE_MUTEX(tcpv6_prot_mutex);
+
+static void espintcp_data_ready(struct sock *sk)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+	trace_sk_data_ready(sk);
+
+	strp_data_ready(&ctx->strp);
+}
+
+static void espintcp_tx_work(struct work_struct *work)
+{
+	struct espintcp_ctx *ctx = container_of(work,
+						struct espintcp_ctx, work);
+	struct sock *sk = ctx->strp.sk;
+
+	lock_sock(sk);
+	if (!ctx->tx_running)
+		espintcp_push_msgs(sk, 0);
+	release_sock(sk);
+}
+
+static void espintcp_write_space(struct sock *sk)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+	schedule_work(&ctx->work);
+	ctx->saved_write_space(sk);
+}
+
+static void espintcp_destruct(struct sock *sk)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+	ctx->saved_destruct(sk);
+	kfree(ctx);
+}
+
+bool tcp_is_ulp_esp(struct sock *sk)
+{
+	return sk->sk_prot == &espintcp_prot || sk->sk_prot == &espintcp6_prot;
+}
+EXPORT_SYMBOL_GPL(tcp_is_ulp_esp);
+
+static void build_protos(struct proto *espintcp_prot,
+			 struct proto_ops *espintcp_ops,
+			 const struct proto *orig_prot,
+			 const struct proto_ops *orig_ops);
+static int espintcp_init_sk(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct strp_callbacks cb = {
+		.rcv_msg = espintcp_rcv,
+		.parse_msg = espintcp_parse,
+	};
+	struct espintcp_ctx *ctx;
+	int err;
+
+	/* sockmap is not compatible with espintcp */
+	if (sk->sk_user_data)
+		return -EBUSY;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	err = strp_init(&ctx->strp, sk, &cb);
+	if (err)
+		goto free;
+
+	__sk_dst_reset(sk);
+
+	strp_check_rcv(&ctx->strp);
+	skb_queue_head_init(&ctx->ike_queue);
+	skb_queue_head_init(&ctx->out_queue);
+
+	if (sk->sk_family == AF_INET) {
+		sk->sk_prot = &espintcp_prot;
+		sk->sk_socket->ops = &espintcp_ops;
+	} else {
+		mutex_lock(&tcpv6_prot_mutex);
+		if (!espintcp6_prot.recvmsg)
+			build_protos(&espintcp6_prot, &espintcp6_ops, sk->sk_prot, sk->sk_socket->ops);
+		mutex_unlock(&tcpv6_prot_mutex);
+
+		sk->sk_prot = &espintcp6_prot;
+		sk->sk_socket->ops = &espintcp6_ops;
+	}
+	ctx->saved_data_ready = sk->sk_data_ready;
+	ctx->saved_write_space = sk->sk_write_space;
+	ctx->saved_destruct = sk->sk_destruct;
+	sk->sk_data_ready = espintcp_data_ready;
+	sk->sk_write_space = espintcp_write_space;
+	sk->sk_destruct = espintcp_destruct;
+	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
+	INIT_WORK(&ctx->work, espintcp_tx_work);
+
+	/* avoid using task_frag */
+	sk->sk_allocation = GFP_ATOMIC;
+	sk->sk_use_task_frag = false;
+
+	return 0;
+
+free:
+	kfree(ctx);
+	return err;
+}
+
+static void espintcp_release(struct sock *sk)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+	struct sk_buff_head queue;
+	struct sk_buff *skb;
+
+	__skb_queue_head_init(&queue);
+	skb_queue_splice_init(&ctx->out_queue, &queue);
+
+	while ((skb = __skb_dequeue(&queue)))
+		espintcp_push_skb(sk, skb);
+
+	tcp_release_cb(sk);
+}
+
+static void espintcp_close(struct sock *sk, long timeout)
+{
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+	struct espintcp_msg *emsg = &ctx->partial;
+
+	strp_stop(&ctx->strp);
+
+	sk->sk_prot = &tcp_prot;
+	barrier();
+
+	cancel_work_sync(&ctx->work);
+	strp_done(&ctx->strp);
+
+	skb_queue_purge(&ctx->out_queue);
+	skb_queue_purge(&ctx->ike_queue);
+
+	if (emsg->len) {
+		if (emsg->skb)
+			kfree_skb(emsg->skb);
+		else
+			sk_msg_free(sk, &emsg->skmsg);
+	}
+
+	tcp_close(sk, timeout);
+}
+
+static __poll_t espintcp_poll(struct file *file, struct socket *sock,
+			      poll_table *wait)
+{
+	__poll_t mask = datagram_poll(file, sock, wait);
+	struct sock *sk = sock->sk;
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+	if (!skb_queue_empty(&ctx->ike_queue))
+		mask |= EPOLLIN | EPOLLRDNORM;
+
+	return mask;
+}
+
+static void build_protos(struct proto *espintcp_prot,
+			 struct proto_ops *espintcp_ops,
+			 const struct proto *orig_prot,
+			 const struct proto_ops *orig_ops)
+{
+	memcpy(espintcp_prot, orig_prot, sizeof(struct proto));
+	memcpy(espintcp_ops, orig_ops, sizeof(struct proto_ops));
+	espintcp_prot->sendmsg = espintcp_sendmsg;
+	espintcp_prot->recvmsg = espintcp_recvmsg;
+	espintcp_prot->close = espintcp_close;
+	espintcp_prot->release_cb = espintcp_release;
+	espintcp_ops->poll = espintcp_poll;
+}
+
+static struct tcp_ulp_ops espintcp_ulp __read_mostly = {
+	.name = "espintcp",
+	.owner = THIS_MODULE,
+	.init = espintcp_init_sk,
+};
+
+void __init espintcp_init(void)
+{
+	build_protos(&espintcp_prot, &espintcp_ops, &tcp_prot, &inet_stream_ops);
+
+	tcp_register_ulp(&espintcp_ulp);
+}
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
new file mode 100644
index 0000000000..094734fbec
--- /dev/null
+++ b/net/xfrm/xfrm_algo.c
@@ -0,0 +1,866 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * xfrm algorithm interface
+ *
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ */
+
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/pfkeyv2.h>
+#include <linux/crypto.h>
+#include <linux/scatterlist.h>
+#include <net/xfrm.h>
+#if IS_ENABLED(CONFIG_INET_ESP) || IS_ENABLED(CONFIG_INET6_ESP)
+#include <net/esp.h>
+#endif
+
+/*
+ * Algorithms supported by IPsec.  These entries contain properties which
+ * are used in key negotiation and xfrm processing, and are used to verify
+ * that instantiated crypto transforms have correct parameters for IPsec
+ * purposes.
+ */
+static struct xfrm_algo_desc aead_list[] = {
+{
+	.name = "rfc4106(gcm(aes))",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqiv",
+			.icv_truncbits = 64,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AES_GCM_ICV8,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "rfc4106(gcm(aes))",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqiv",
+			.icv_truncbits = 96,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AES_GCM_ICV12,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "rfc4106(gcm(aes))",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqiv",
+			.icv_truncbits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AES_GCM_ICV16,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "rfc4309(ccm(aes))",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqiv",
+			.icv_truncbits = 64,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AES_CCM_ICV8,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "rfc4309(ccm(aes))",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqiv",
+			.icv_truncbits = 96,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AES_CCM_ICV12,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "rfc4309(ccm(aes))",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqiv",
+			.icv_truncbits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AES_CCM_ICV16,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "rfc4543(gcm(aes))",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqiv",
+			.icv_truncbits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_NULL_AES_GMAC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "rfc7539esp(chacha20,poly1305)",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqiv",
+			.icv_truncbits = 128,
+		}
+	},
+
+	.pfkey_supported = 0,
+},
+};
+
+static struct xfrm_algo_desc aalg_list[] = {
+{
+	.name = "digest_null",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 0,
+			.icv_fullbits = 0,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_NULL,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 0,
+		.sadb_alg_maxbits = 0
+	}
+},
+{
+	.name = "hmac(md5)",
+	.compat = "md5",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_AALG_MD5HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 128
+	}
+},
+{
+	.name = "hmac(sha1)",
+	.compat = "sha1",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 160,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_AALG_SHA1HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 160,
+		.sadb_alg_maxbits = 160
+	}
+},
+{
+	.name = "hmac(sha256)",
+	.compat = "sha256",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 256,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_SHA2_256HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 256,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "hmac(sha384)",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 192,
+			.icv_fullbits = 384,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_SHA2_384HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 384,
+		.sadb_alg_maxbits = 384
+	}
+},
+{
+	.name = "hmac(sha512)",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 256,
+			.icv_fullbits = 512,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_SHA2_512HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 512,
+		.sadb_alg_maxbits = 512
+	}
+},
+{
+	.name = "hmac(rmd160)",
+	.compat = "rmd160",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 160,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_RIPEMD160HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 160,
+		.sadb_alg_maxbits = 160
+	}
+},
+{
+	.name = "xcbc(aes)",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_AES_XCBC_MAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 128
+	}
+},
+{
+	/* rfc4494 */
+	.name = "cmac(aes)",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 128,
+		}
+	},
+
+	.pfkey_supported = 0,
+},
+{
+	.name = "hmac(sm3)",
+	.compat = "sm3",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 256,
+			.icv_fullbits = 256,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_SM3_256HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 256,
+		.sadb_alg_maxbits = 256
+	}
+},
+};
+
+static struct xfrm_algo_desc ealg_list[] = {
+{
+	.name = "ecb(cipher_null)",
+	.compat = "cipher_null",
+
+	.uinfo = {
+		.encr = {
+			.blockbits = 8,
+			.defkeybits = 0,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id =	SADB_EALG_NULL,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 0,
+		.sadb_alg_maxbits = 0
+	}
+},
+{
+	.name = "cbc(des)",
+	.compat = "des",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 64,
+			.defkeybits = 64,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_EALG_DESCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 64,
+		.sadb_alg_maxbits = 64
+	}
+},
+{
+	.name = "cbc(des3_ede)",
+	.compat = "des3_ede",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 64,
+			.defkeybits = 192,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_EALG_3DESCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 192,
+		.sadb_alg_maxbits = 192
+	}
+},
+{
+	.name = "cbc(cast5)",
+	.compat = "cast5",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 64,
+			.defkeybits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_CASTCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 40,
+		.sadb_alg_maxbits = 128
+	}
+},
+{
+	.name = "cbc(blowfish)",
+	.compat = "blowfish",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 64,
+			.defkeybits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_BLOWFISHCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 40,
+		.sadb_alg_maxbits = 448
+	}
+},
+{
+	.name = "cbc(aes)",
+	.compat = "aes",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 128,
+			.defkeybits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AESCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "cbc(serpent)",
+	.compat = "serpent",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 128,
+			.defkeybits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_SERPENTCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256,
+	}
+},
+{
+	.name = "cbc(camellia)",
+	.compat = "camellia",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 128,
+			.defkeybits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_CAMELLIACBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "cbc(twofish)",
+	.compat = "twofish",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 128,
+			.defkeybits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_TWOFISHCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "rfc3686(ctr(aes))",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "seqiv",
+			.blockbits = 128,
+			.defkeybits = 160, /* 128-bit key + 32-bit nonce */
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AESCTR,
+		.sadb_alg_ivlen	= 8,
+		.sadb_alg_minbits = 160,
+		.sadb_alg_maxbits = 288
+	}
+},
+{
+	.name = "cbc(sm4)",
+	.compat = "sm4",
+
+	.uinfo = {
+		.encr = {
+			.geniv = "echainiv",
+			.blockbits = 128,
+			.defkeybits = 128,
+		}
+	},
+
+	.pfkey_supported = 1,
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_SM4CBC,
+		.sadb_alg_ivlen	= 16,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+};
+
+static struct xfrm_algo_desc calg_list[] = {
+{
+	.name = "deflate",
+	.uinfo = {
+		.comp = {
+			.threshold = 90,
+		}
+	},
+	.pfkey_supported = 1,
+	.desc = { .sadb_alg_id = SADB_X_CALG_DEFLATE }
+},
+{
+	.name = "lzs",
+	.uinfo = {
+		.comp = {
+			.threshold = 90,
+		}
+	},
+	.pfkey_supported = 1,
+	.desc = { .sadb_alg_id = SADB_X_CALG_LZS }
+},
+{
+	.name = "lzjh",
+	.uinfo = {
+		.comp = {
+			.threshold = 50,
+		}
+	},
+	.pfkey_supported = 1,
+	.desc = { .sadb_alg_id = SADB_X_CALG_LZJH }
+},
+};
+
+static inline int aalg_entries(void)
+{
+	return ARRAY_SIZE(aalg_list);
+}
+
+static inline int ealg_entries(void)
+{
+	return ARRAY_SIZE(ealg_list);
+}
+
+static inline int calg_entries(void)
+{
+	return ARRAY_SIZE(calg_list);
+}
+
+struct xfrm_algo_list {
+	struct xfrm_algo_desc *algs;
+	int entries;
+	u32 type;
+	u32 mask;
+};
+
+static const struct xfrm_algo_list xfrm_aead_list = {
+	.algs = aead_list,
+	.entries = ARRAY_SIZE(aead_list),
+	.type = CRYPTO_ALG_TYPE_AEAD,
+	.mask = CRYPTO_ALG_TYPE_MASK,
+};
+
+static const struct xfrm_algo_list xfrm_aalg_list = {
+	.algs = aalg_list,
+	.entries = ARRAY_SIZE(aalg_list),
+	.type = CRYPTO_ALG_TYPE_HASH,
+	.mask = CRYPTO_ALG_TYPE_HASH_MASK,
+};
+
+static const struct xfrm_algo_list xfrm_ealg_list = {
+	.algs = ealg_list,
+	.entries = ARRAY_SIZE(ealg_list),
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.mask = CRYPTO_ALG_TYPE_MASK,
+};
+
+static const struct xfrm_algo_list xfrm_calg_list = {
+	.algs = calg_list,
+	.entries = ARRAY_SIZE(calg_list),
+	.type = CRYPTO_ALG_TYPE_COMPRESS,
+	.mask = CRYPTO_ALG_TYPE_MASK,
+};
+
+static struct xfrm_algo_desc *xfrm_find_algo(
+	const struct xfrm_algo_list *algo_list,
+	int match(const struct xfrm_algo_desc *entry, const void *data),
+	const void *data, int probe)
+{
+	struct xfrm_algo_desc *list = algo_list->algs;
+	int i, status;
+
+	for (i = 0; i < algo_list->entries; i++) {
+		if (!match(list + i, data))
+			continue;
+
+		if (list[i].available)
+			return &list[i];
+
+		if (!probe)
+			break;
+
+		status = crypto_has_alg(list[i].name, algo_list->type,
+					algo_list->mask);
+		if (!status)
+			break;
+
+		list[i].available = status;
+		return &list[i];
+	}
+	return NULL;
+}
+
+static int xfrm_alg_id_match(const struct xfrm_algo_desc *entry,
+			     const void *data)
+{
+	return entry->desc.sadb_alg_id == (unsigned long)data;
+}
+
+struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id)
+{
+	return xfrm_find_algo(&xfrm_aalg_list, xfrm_alg_id_match,
+			      (void *)(unsigned long)alg_id, 1);
+}
+EXPORT_SYMBOL_GPL(xfrm_aalg_get_byid);
+
+struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id)
+{
+	return xfrm_find_algo(&xfrm_ealg_list, xfrm_alg_id_match,
+			      (void *)(unsigned long)alg_id, 1);
+}
+EXPORT_SYMBOL_GPL(xfrm_ealg_get_byid);
+
+struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id)
+{
+	return xfrm_find_algo(&xfrm_calg_list, xfrm_alg_id_match,
+			      (void *)(unsigned long)alg_id, 1);
+}
+EXPORT_SYMBOL_GPL(xfrm_calg_get_byid);
+
+static int xfrm_alg_name_match(const struct xfrm_algo_desc *entry,
+			       const void *data)
+{
+	const char *name = data;
+
+	return name && (!strcmp(name, entry->name) ||
+			(entry->compat && !strcmp(name, entry->compat)));
+}
+
+struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe)
+{
+	return xfrm_find_algo(&xfrm_aalg_list, xfrm_alg_name_match, name,
+			      probe);
+}
+EXPORT_SYMBOL_GPL(xfrm_aalg_get_byname);
+
+struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe)
+{
+	return xfrm_find_algo(&xfrm_ealg_list, xfrm_alg_name_match, name,
+			      probe);
+}
+EXPORT_SYMBOL_GPL(xfrm_ealg_get_byname);
+
+struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe)
+{
+	return xfrm_find_algo(&xfrm_calg_list, xfrm_alg_name_match, name,
+			      probe);
+}
+EXPORT_SYMBOL_GPL(xfrm_calg_get_byname);
+
+struct xfrm_aead_name {
+	const char *name;
+	int icvbits;
+};
+
+static int xfrm_aead_name_match(const struct xfrm_algo_desc *entry,
+				const void *data)
+{
+	const struct xfrm_aead_name *aead = data;
+	const char *name = aead->name;
+
+	return aead->icvbits == entry->uinfo.aead.icv_truncbits && name &&
+	       !strcmp(name, entry->name);
+}
+
+struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len, int probe)
+{
+	struct xfrm_aead_name data = {
+		.name = name,
+		.icvbits = icv_len,
+	};
+
+	return xfrm_find_algo(&xfrm_aead_list, xfrm_aead_name_match, &data,
+			      probe);
+}
+EXPORT_SYMBOL_GPL(xfrm_aead_get_byname);
+
+struct xfrm_algo_desc *xfrm_aalg_get_byidx(unsigned int idx)
+{
+	if (idx >= aalg_entries())
+		return NULL;
+
+	return &aalg_list[idx];
+}
+EXPORT_SYMBOL_GPL(xfrm_aalg_get_byidx);
+
+struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx)
+{
+	if (idx >= ealg_entries())
+		return NULL;
+
+	return &ealg_list[idx];
+}
+EXPORT_SYMBOL_GPL(xfrm_ealg_get_byidx);
+
+/*
+ * Probe for the availability of crypto algorithms, and set the available
+ * flag for any algorithms found on the system.  This is typically called by
+ * pfkey during userspace SA add, update or register.
+ */
+void xfrm_probe_algs(void)
+{
+	int i, status;
+
+	BUG_ON(in_softirq());
+
+	for (i = 0; i < aalg_entries(); i++) {
+		status = crypto_has_ahash(aalg_list[i].name, 0, 0);
+		if (aalg_list[i].available != status)
+			aalg_list[i].available = status;
+	}
+
+	for (i = 0; i < ealg_entries(); i++) {
+		status = crypto_has_skcipher(ealg_list[i].name, 0, 0);
+		if (ealg_list[i].available != status)
+			ealg_list[i].available = status;
+	}
+
+	for (i = 0; i < calg_entries(); i++) {
+		status = crypto_has_comp(calg_list[i].name, 0,
+					 CRYPTO_ALG_ASYNC);
+		if (calg_list[i].available != status)
+			calg_list[i].available = status;
+	}
+}
+EXPORT_SYMBOL_GPL(xfrm_probe_algs);
+
+int xfrm_count_pfkey_auth_supported(void)
+{
+	int i, n;
+
+	for (i = 0, n = 0; i < aalg_entries(); i++)
+		if (aalg_list[i].available && aalg_list[i].pfkey_supported)
+			n++;
+	return n;
+}
+EXPORT_SYMBOL_GPL(xfrm_count_pfkey_auth_supported);
+
+int xfrm_count_pfkey_enc_supported(void)
+{
+	int i, n;
+
+	for (i = 0, n = 0; i < ealg_entries(); i++)
+		if (ealg_list[i].available && ealg_list[i].pfkey_supported)
+			n++;
+	return n;
+}
+EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported);
+
+MODULE_LICENSE("GPL");
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
new file mode 100644
index 0000000000..655fe4ff86
--- /dev/null
+++ b/net/xfrm/xfrm_compat.c
@@ -0,0 +1,675 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * XFRM compat layer
+ * Author: Dmitry Safonov <dima@arista.com>
+ * Based on code and translator idea by: Florian Westphal <fw@strlen.de>
+ */
+#include <linux/compat.h>
+#include <linux/nospec.h>
+#include <linux/xfrm.h>
+#include <net/xfrm.h>
+
+struct compat_xfrm_lifetime_cfg {
+	compat_u64 soft_byte_limit, hard_byte_limit;
+	compat_u64 soft_packet_limit, hard_packet_limit;
+	compat_u64 soft_add_expires_seconds, hard_add_expires_seconds;
+	compat_u64 soft_use_expires_seconds, hard_use_expires_seconds;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_lifetime_cur {
+	compat_u64 bytes, packets, add_time, use_time;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_userpolicy_info {
+	struct xfrm_selector sel;
+	struct compat_xfrm_lifetime_cfg lft;
+	struct compat_xfrm_lifetime_cur curlft;
+	__u32 priority, index;
+	u8 dir, action, flags, share;
+	/* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_usersa_info {
+	struct xfrm_selector sel;
+	struct xfrm_id id;
+	xfrm_address_t saddr;
+	struct compat_xfrm_lifetime_cfg lft;
+	struct compat_xfrm_lifetime_cur curlft;
+	struct xfrm_stats stats;
+	__u32 seq, reqid;
+	u16 family;
+	u8 mode, replay_window, flags;
+	/* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_user_acquire {
+	struct xfrm_id id;
+	xfrm_address_t saddr;
+	struct xfrm_selector sel;
+	struct compat_xfrm_userpolicy_info policy;
+	/* 4 bytes additional padding on 64bit */
+	__u32 aalgos, ealgos, calgos, seq;
+};
+
+struct compat_xfrm_userspi_info {
+	struct compat_xfrm_usersa_info info;
+	/* 4 bytes additional padding on 64bit */
+	__u32 min, max;
+};
+
+struct compat_xfrm_user_expire {
+	struct compat_xfrm_usersa_info state;
+	/* 8 bytes additional padding on 64bit */
+	u8 hard;
+};
+
+struct compat_xfrm_user_polexpire {
+	struct compat_xfrm_userpolicy_info pol;
+	/* 8 bytes additional padding on 64bit */
+	u8 hard;
+};
+
+#define XMSGSIZE(type) sizeof(struct type)
+
+static const int compat_msg_min[XFRM_NR_MSGTYPES] = {
+	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_NEWPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+	[XFRM_MSG_DELPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_GETPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_ALLOCSPI    - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info),
+	[XFRM_MSG_ACQUIRE     - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire),
+	[XFRM_MSG_EXPIRE      - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire),
+	[XFRM_MSG_UPDPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+	[XFRM_MSG_UPDSA       - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+	[XFRM_MSG_POLEXPIRE   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire),
+	[XFRM_MSG_FLUSHSA     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush),
+	[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0,
+	[XFRM_MSG_NEWAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_REPORT      - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report),
+	[XFRM_MSG_MIGRATE     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_NEWSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_MAPPING     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping)
+};
+
+static const struct nla_policy compat_policy[XFRMA_MAX+1] = {
+	[XFRMA_SA]		= { .len = XMSGSIZE(compat_xfrm_usersa_info)},
+	[XFRMA_POLICY]		= { .len = XMSGSIZE(compat_xfrm_userpolicy_info)},
+	[XFRMA_LASTUSED]	= { .type = NLA_U64},
+	[XFRMA_ALG_AUTH_TRUNC]	= { .len = sizeof(struct xfrm_algo_auth)},
+	[XFRMA_ALG_AEAD]	= { .len = sizeof(struct xfrm_algo_aead) },
+	[XFRMA_ALG_AUTH]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_CRYPT]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_COMP]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ENCAP]		= { .len = sizeof(struct xfrm_encap_tmpl) },
+	[XFRMA_TMPL]		= { .len = sizeof(struct xfrm_user_tmpl) },
+	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_user_sec_ctx) },
+	[XFRMA_LTIME_VAL]	= { .len = sizeof(struct xfrm_lifetime_cur) },
+	[XFRMA_REPLAY_VAL]	= { .len = sizeof(struct xfrm_replay_state) },
+	[XFRMA_REPLAY_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_ETIMER_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_SRCADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_COADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_POLICY_TYPE]	= { .len = sizeof(struct xfrm_userpolicy_type)},
+	[XFRMA_MIGRATE]		= { .len = sizeof(struct xfrm_user_migrate) },
+	[XFRMA_KMADDRESS]	= { .len = sizeof(struct xfrm_user_kmaddress) },
+	[XFRMA_MARK]		= { .len = sizeof(struct xfrm_mark) },
+	[XFRMA_TFCPAD]		= { .type = NLA_U32 },
+	[XFRMA_REPLAY_ESN_VAL]	= { .len = sizeof(struct xfrm_replay_state_esn) },
+	[XFRMA_SA_EXTRA_FLAGS]	= { .type = NLA_U32 },
+	[XFRMA_PROTO]		= { .type = NLA_U8 },
+	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
+	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
+	[XFRMA_SET_MARK]	= { .type = NLA_U32 },
+	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
+	[XFRMA_IF_ID]		= { .type = NLA_U32 },
+	[XFRMA_MTIMER_THRESH]	= { .type = NLA_U32 },
+};
+
+static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb,
+			const struct nlmsghdr *nlh_src, u16 type)
+{
+	int payload = compat_msg_min[type];
+	int src_len = xfrm_msg_min[type];
+	struct nlmsghdr *nlh_dst;
+
+	/* Compat messages are shorter or equal to native (+padding) */
+	if (WARN_ON_ONCE(src_len < payload))
+		return ERR_PTR(-EMSGSIZE);
+
+	nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq,
+			    nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags);
+	if (!nlh_dst)
+		return ERR_PTR(-EMSGSIZE);
+
+	memset(nlmsg_data(nlh_dst), 0, payload);
+
+	switch (nlh_src->nlmsg_type) {
+	/* Compat message has the same layout as native */
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_DELPOLICY:
+	case XFRM_MSG_FLUSHSA:
+	case XFRM_MSG_FLUSHPOLICY:
+	case XFRM_MSG_NEWAE:
+	case XFRM_MSG_REPORT:
+	case XFRM_MSG_MIGRATE:
+	case XFRM_MSG_NEWSADINFO:
+	case XFRM_MSG_NEWSPDINFO:
+	case XFRM_MSG_MAPPING:
+		WARN_ON_ONCE(src_len != payload);
+		memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len);
+		break;
+	/* 4 byte alignment for trailing u64 on native, but not on compat */
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_UPDPOLICY:
+		WARN_ON_ONCE(src_len != payload + 4);
+		memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload);
+		break;
+	case XFRM_MSG_EXPIRE: {
+		const struct xfrm_user_expire *src_ue  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_expire has 4-byte smaller state */
+		memcpy(dst_ue, src_ue, sizeof(dst_ue->state));
+		dst_ue->hard = src_ue->hard;
+		break;
+	}
+	case XFRM_MSG_ACQUIRE: {
+		const struct xfrm_user_acquire *src_ua  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst);
+
+		memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+		dst_ua->aalgos = src_ua->aalgos;
+		dst_ua->ealgos = src_ua->ealgos;
+		dst_ua->calgos = src_ua->calgos;
+		dst_ua->seq    = src_ua->seq;
+		break;
+	}
+	case XFRM_MSG_POLEXPIRE: {
+		const struct xfrm_user_polexpire *src_upe  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_upe, src_upe, sizeof(dst_upe->pol));
+		dst_upe->hard = src_upe->hard;
+		break;
+	}
+	case XFRM_MSG_ALLOCSPI: {
+		const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src);
+		struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+		dst_usi->min = src_usi->min;
+		dst_usi->max = src_usi->max;
+		break;
+	}
+	/* Not being sent by kernel */
+	case XFRM_MSG_GETSA:
+	case XFRM_MSG_GETPOLICY:
+	case XFRM_MSG_GETAE:
+	case XFRM_MSG_GETSADINFO:
+	case XFRM_MSG_GETSPDINFO:
+	default:
+		pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	return nlh_dst;
+}
+
+static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len)
+{
+	return nla_put(dst, src->nla_type, len, nla_data(src));
+}
+
+static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src)
+{
+	switch (src->nla_type) {
+	case XFRMA_PAD:
+		/* Ignore */
+		return 0;
+	case XFRMA_UNSPEC:
+	case XFRMA_ALG_AUTH:
+	case XFRMA_ALG_CRYPT:
+	case XFRMA_ALG_COMP:
+	case XFRMA_ENCAP:
+	case XFRMA_TMPL:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_SA:
+		return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info));
+	case XFRMA_POLICY:
+		return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info));
+	case XFRMA_SEC_CTX:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_LTIME_VAL:
+		return nla_put_64bit(dst, src->nla_type, nla_len(src),
+			nla_data(src), XFRMA_PAD);
+	case XFRMA_REPLAY_VAL:
+	case XFRMA_REPLAY_THRESH:
+	case XFRMA_ETIMER_THRESH:
+	case XFRMA_SRCADDR:
+	case XFRMA_COADDR:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_LASTUSED:
+		return nla_put_64bit(dst, src->nla_type, nla_len(src),
+			nla_data(src), XFRMA_PAD);
+	case XFRMA_POLICY_TYPE:
+	case XFRMA_MIGRATE:
+	case XFRMA_ALG_AEAD:
+	case XFRMA_KMADDRESS:
+	case XFRMA_ALG_AUTH_TRUNC:
+	case XFRMA_MARK:
+	case XFRMA_TFCPAD:
+	case XFRMA_REPLAY_ESN_VAL:
+	case XFRMA_SA_EXTRA_FLAGS:
+	case XFRMA_PROTO:
+	case XFRMA_ADDRESS_FILTER:
+	case XFRMA_OFFLOAD_DEV:
+	case XFRMA_SET_MARK:
+	case XFRMA_SET_MARK_MASK:
+	case XFRMA_IF_ID:
+	case XFRMA_MTIMER_THRESH:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	default:
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH);
+		pr_warn_once("unsupported nla_type %d\n", src->nla_type);
+		return -EOPNOTSUPP;
+	}
+}
+
+/* Take kernel-built (64bit layout) and create 32bit layout for userspace */
+static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src)
+{
+	u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+	const struct nlattr *nla, *attrs;
+	struct nlmsghdr *nlh_dst;
+	int len, remaining;
+
+	nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type);
+	if (IS_ERR(nlh_dst))
+		return PTR_ERR(nlh_dst);
+
+	attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]);
+	len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]);
+
+	nla_for_each_attr(nla, attrs, len, remaining) {
+		int err;
+
+		switch (nlh_src->nlmsg_type) {
+		case XFRM_MSG_NEWSPDINFO:
+			err = xfrm_nla_cpy(dst, nla, nla_len(nla));
+			break;
+		default:
+			err = xfrm_xlate64_attr(dst, nla);
+			break;
+		}
+		if (err)
+			return err;
+	}
+
+	nlmsg_end(dst, nlh_dst);
+
+	return 0;
+}
+
+static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src)
+{
+	u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+	struct sk_buff *new = NULL;
+	int err;
+
+	if (type >= ARRAY_SIZE(xfrm_msg_min)) {
+		pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type);
+		return -EOPNOTSUPP;
+	}
+
+	if (skb_shinfo(skb)->frag_list == NULL) {
+		new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC);
+		if (!new)
+			return -ENOMEM;
+		skb_shinfo(skb)->frag_list = new;
+	}
+
+	err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src);
+	if (err) {
+		if (new) {
+			kfree_skb(new);
+			skb_shinfo(skb)->frag_list = NULL;
+		}
+		return err;
+	}
+
+	return 0;
+}
+
+/* Calculates len of translated 64-bit message. */
+static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
+					    struct nlattr *attrs[XFRMA_MAX + 1],
+					    int maxtype)
+{
+	size_t len = nlmsg_len(src);
+
+	switch (src->nlmsg_type) {
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_ALLOCSPI:
+	case XFRM_MSG_ACQUIRE:
+	case XFRM_MSG_UPDPOLICY:
+	case XFRM_MSG_UPDSA:
+		len += 4;
+		break;
+	case XFRM_MSG_EXPIRE:
+	case XFRM_MSG_POLEXPIRE:
+		len += 8;
+		break;
+	case XFRM_MSG_NEWSPDINFO:
+		/* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */
+		return len;
+	default:
+		break;
+	}
+
+	/* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please
+	 * correct both 64=>32-bit and 32=>64-bit translators to copy
+	 * new attributes.
+	 */
+	if (WARN_ON_ONCE(maxtype))
+		return len;
+
+	if (attrs[XFRMA_SA])
+		len += 4;
+	if (attrs[XFRMA_POLICY])
+		len += 4;
+
+	/* XXX: some attrs may need to be realigned
+	 * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	 */
+
+	return len;
+}
+
+static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src,
+			   size_t size, int copy_len, int payload)
+{
+	struct nlmsghdr *nlmsg = dst;
+	struct nlattr *nla;
+
+	/* xfrm_user_rcv_msg_compat() relies on fact that 32-bit messages
+	 * have the same len or shorted than 64-bit ones.
+	 * 32-bit translation that is bigger than 64-bit original is unexpected.
+	 */
+	if (WARN_ON_ONCE(copy_len > payload))
+		copy_len = payload;
+
+	if (size - *pos < nla_attr_size(payload))
+		return -ENOBUFS;
+
+	nla = dst + *pos;
+
+	memcpy(nla, src, nla_attr_size(copy_len));
+	nla->nla_len = nla_attr_size(payload);
+	*pos += nla_attr_size(copy_len);
+	nlmsg->nlmsg_len += nla->nla_len;
+
+	memset(dst + *pos, 0, payload - copy_len);
+	*pos += payload - copy_len;
+
+	return 0;
+}
+
+static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
+			     size_t *pos, size_t size,
+			     struct netlink_ext_ack *extack)
+{
+	int type = nla_type(nla);
+	u16 pol_len32, pol_len64;
+	int err;
+
+	if (type > XFRMA_MAX) {
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH);
+		NL_SET_ERR_MSG(extack, "Bad attribute");
+		return -EOPNOTSUPP;
+	}
+	type = array_index_nospec(type, XFRMA_MAX + 1);
+	if (nla_len(nla) < compat_policy[type].len) {
+		NL_SET_ERR_MSG(extack, "Attribute bad length");
+		return -EOPNOTSUPP;
+	}
+
+	pol_len32 = compat_policy[type].len;
+	pol_len64 = xfrma_policy[type].len;
+
+	/* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */
+	if (pol_len32 != pol_len64) {
+		if (nla_len(nla) != compat_policy[type].len) {
+			NL_SET_ERR_MSG(extack, "Attribute bad length");
+			return -EOPNOTSUPP;
+		}
+		err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64);
+		if (err)
+			return err;
+	}
+
+	return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(nla));
+}
+
+static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
+			struct nlattr *attrs[XFRMA_MAX+1],
+			size_t size, u8 type, int maxtype,
+			struct netlink_ext_ack *extack)
+{
+	size_t pos;
+	int i;
+
+	memcpy(dst, src, NLMSG_HDRLEN);
+	dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type];
+	memset(nlmsg_data(dst), 0, xfrm_msg_min[type]);
+
+	switch (src->nlmsg_type) {
+	/* Compat message has the same layout as native */
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_GETSA:
+	case XFRM_MSG_DELPOLICY:
+	case XFRM_MSG_GETPOLICY:
+	case XFRM_MSG_FLUSHSA:
+	case XFRM_MSG_FLUSHPOLICY:
+	case XFRM_MSG_NEWAE:
+	case XFRM_MSG_GETAE:
+	case XFRM_MSG_REPORT:
+	case XFRM_MSG_MIGRATE:
+	case XFRM_MSG_NEWSADINFO:
+	case XFRM_MSG_GETSADINFO:
+	case XFRM_MSG_NEWSPDINFO:
+	case XFRM_MSG_GETSPDINFO:
+	case XFRM_MSG_MAPPING:
+		memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+		break;
+	/* 4 byte alignment for trailing u64 on native, but not on compat */
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_UPDPOLICY:
+		memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+		break;
+	case XFRM_MSG_EXPIRE: {
+		const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src);
+		struct xfrm_user_expire *dst_ue = nlmsg_data(dst);
+
+		/* compat_xfrm_user_expire has 4-byte smaller state */
+		memcpy(dst_ue, src_ue, sizeof(src_ue->state));
+		dst_ue->hard = src_ue->hard;
+		break;
+	}
+	case XFRM_MSG_ACQUIRE: {
+		const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src);
+		struct xfrm_user_acquire *dst_ua = nlmsg_data(dst);
+
+		memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+		dst_ua->aalgos = src_ua->aalgos;
+		dst_ua->ealgos = src_ua->ealgos;
+		dst_ua->calgos = src_ua->calgos;
+		dst_ua->seq    = src_ua->seq;
+		break;
+	}
+	case XFRM_MSG_POLEXPIRE: {
+		const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src);
+		struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_upe, src_upe, sizeof(src_upe->pol));
+		dst_upe->hard = src_upe->hard;
+		break;
+	}
+	case XFRM_MSG_ALLOCSPI: {
+		const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src);
+		struct xfrm_userspi_info *dst_usi = nlmsg_data(dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+		dst_usi->min = src_usi->min;
+		dst_usi->max = src_usi->max;
+		break;
+	}
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported message type");
+		return -EOPNOTSUPP;
+	}
+	pos = dst->nlmsg_len;
+
+	if (maxtype) {
+		/* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */
+		WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO);
+
+		for (i = 1; i <= maxtype; i++) {
+			int err;
+
+			if (!attrs[i])
+				continue;
+
+			/* just copy - no need for translation */
+			err = xfrm_attr_cpy32(dst, &pos, attrs[i], size,
+					nla_len(attrs[i]), nla_len(attrs[i]));
+			if (err)
+				return err;
+		}
+		return 0;
+	}
+
+	for (i = 1; i < XFRMA_MAX + 1; i++) {
+		int err;
+
+		if (i == XFRMA_PAD)
+			continue;
+
+		if (!attrs[i])
+			continue;
+
+		err = xfrm_xlate32_attr(dst, attrs[i], &pos, size, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32,
+			int maxtype, const struct nla_policy *policy,
+			struct netlink_ext_ack *extack)
+{
+	/* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */
+	u16 type = h32->nlmsg_type - XFRM_MSG_BASE;
+	struct nlattr *attrs[XFRMA_MAX+1];
+	struct nlmsghdr *h64;
+	size_t len;
+	int err;
+
+	BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min));
+
+	if (type >= ARRAY_SIZE(xfrm_msg_min))
+		return ERR_PTR(-EINVAL);
+
+	/* Don't call parse: the message might have only nlmsg header */
+	if ((h32->nlmsg_type == XFRM_MSG_GETSA ||
+	     h32->nlmsg_type == XFRM_MSG_GETPOLICY) &&
+	    (h32->nlmsg_flags & NLM_F_DUMP))
+		return NULL;
+
+	err = nlmsg_parse_deprecated(h32, compat_msg_min[type], attrs,
+			maxtype ? : XFRMA_MAX, policy ? : compat_policy, extack);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype);
+	/* The message doesn't need translation */
+	if (len == nlmsg_len(h32))
+		return NULL;
+
+	len += NLMSG_HDRLEN;
+	h64 = kvmalloc(len, GFP_KERNEL);
+	if (!h64)
+		return ERR_PTR(-ENOMEM);
+
+	err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack);
+	if (err < 0) {
+		kvfree(h64);
+		return ERR_PTR(err);
+	}
+
+	return h64;
+}
+
+static int xfrm_user_policy_compat(u8 **pdata32, int optlen)
+{
+	struct compat_xfrm_userpolicy_info *p = (void *)*pdata32;
+	u8 *src_templates, *dst_templates;
+	u8 *data64;
+
+	if (optlen < sizeof(*p))
+		return -EINVAL;
+
+	data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN);
+	if (!data64)
+		return -ENOMEM;
+
+	memcpy(data64, *pdata32, sizeof(*p));
+	memset(data64 + sizeof(*p), 0, 4);
+
+	src_templates = *pdata32 + sizeof(*p);
+	dst_templates = data64 + sizeof(*p) + 4;
+	memcpy(dst_templates, src_templates, optlen - sizeof(*p));
+
+	kfree(*pdata32);
+	*pdata32 = data64;
+	return 0;
+}
+
+static struct xfrm_translator xfrm_translator = {
+	.owner				= THIS_MODULE,
+	.alloc_compat			= xfrm_alloc_compat,
+	.rcv_msg_compat			= xfrm_user_rcv_msg_compat,
+	.xlate_user_policy_sockptr	= xfrm_user_policy_compat,
+};
+
+static int __init xfrm_compat_init(void)
+{
+	return xfrm_register_translator(&xfrm_translator);
+}
+
+static void __exit xfrm_compat_exit(void)
+{
+	xfrm_unregister_translator(&xfrm_translator);
+}
+
+module_init(xfrm_compat_init);
+module_exit(xfrm_compat_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dmitry Safonov");
+MODULE_DESCRIPTION("XFRM 32-bit compatibility layer");
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
new file mode 100644
index 0000000000..3784534c91
--- /dev/null
+++ b/net/xfrm/xfrm_device.c
@@ -0,0 +1,539 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * xfrm_device.c - IPsec device offloading code.
+ *
+ * Copyright (c) 2015 secunet Security Networks AG
+ *
+ * Author:
+ * Steffen Klassert <steffen.klassert@secunet.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <net/dst.h>
+#include <net/gso.h>
+#include <net/xfrm.h>
+#include <linux/notifier.h>
+
+#ifdef CONFIG_XFRM_OFFLOAD
+static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb,
+				  unsigned int hsize)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb_reset_mac_len(skb);
+	if (xo->flags & XFRM_GSO_SEGMENT)
+		skb->transport_header -= x->props.header_len;
+
+	pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len);
+}
+
+static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
+				    unsigned int hsize)
+
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	if (xo->flags & XFRM_GSO_SEGMENT)
+		skb->transport_header = skb->network_header + hsize;
+
+	skb_reset_mac_len(skb);
+	pskb_pull(skb, skb->mac_len + x->props.header_len);
+}
+
+static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb,
+				  unsigned int hsize)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	int phlen = 0;
+
+	if (xo->flags & XFRM_GSO_SEGMENT)
+		skb->transport_header = skb->network_header + hsize;
+
+	skb_reset_mac_len(skb);
+	if (x->sel.family != AF_INET6) {
+		phlen = IPV4_BEET_PHMAXLEN;
+		if (x->outer_mode.family == AF_INET6)
+			phlen += sizeof(struct ipv6hdr) - sizeof(struct iphdr);
+	}
+
+	pskb_pull(skb, skb->mac_len + hsize + (x->props.header_len - phlen));
+}
+
+/* Adjust pointers into the packet when IPsec is done at layer2 */
+static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->outer_mode.encap) {
+	case XFRM_MODE_TUNNEL:
+		if (x->outer_mode.family == AF_INET)
+			return __xfrm_mode_tunnel_prep(x, skb,
+						       sizeof(struct iphdr));
+		if (x->outer_mode.family == AF_INET6)
+			return __xfrm_mode_tunnel_prep(x, skb,
+						       sizeof(struct ipv6hdr));
+		break;
+	case XFRM_MODE_TRANSPORT:
+		if (x->outer_mode.family == AF_INET)
+			return __xfrm_transport_prep(x, skb,
+						     sizeof(struct iphdr));
+		if (x->outer_mode.family == AF_INET6)
+			return __xfrm_transport_prep(x, skb,
+						     sizeof(struct ipv6hdr));
+		break;
+	case XFRM_MODE_BEET:
+		if (x->outer_mode.family == AF_INET)
+			return __xfrm_mode_beet_prep(x, skb,
+						     sizeof(struct iphdr));
+		if (x->outer_mode.family == AF_INET6)
+			return __xfrm_mode_beet_prep(x, skb,
+						     sizeof(struct ipv6hdr));
+		break;
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+	case XFRM_MODE_IN_TRIGGER:
+		break;
+	}
+}
+
+static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	__u32 seq = xo->seq.low;
+
+	seq += skb_shinfo(skb)->gso_segs;
+	if (unlikely(seq < xo->seq.low))
+		return true;
+
+	return false;
+}
+
+struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again)
+{
+	int err;
+	unsigned long flags;
+	struct xfrm_state *x;
+	struct softnet_data *sd;
+	struct sk_buff *skb2, *nskb, *pskb = NULL;
+	netdev_features_t esp_features = features;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct net_device *dev = skb->dev;
+	struct sec_path *sp;
+
+	if (!xo || (xo->flags & XFRM_XMIT))
+		return skb;
+
+	if (!(features & NETIF_F_HW_ESP))
+		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
+
+	sp = skb_sec_path(skb);
+	x = sp->xvec[sp->len - 1];
+	if (xo->flags & XFRM_GRO || x->xso.dir == XFRM_DEV_OFFLOAD_IN)
+		return skb;
+
+	/* The packet was sent to HW IPsec packet offload engine,
+	 * but to wrong device. Drop the packet, so it won't skip
+	 * XFRM stack.
+	 */
+	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->xso.dev != dev) {
+		kfree_skb(skb);
+		dev_core_stats_tx_dropped_inc(dev);
+		return NULL;
+	}
+
+	/* This skb was already validated on the upper/virtual dev */
+	if ((x->xso.dev != dev) && (x->xso.real_dev == dev))
+		return skb;
+
+	local_irq_save(flags);
+	sd = this_cpu_ptr(&softnet_data);
+	err = !skb_queue_empty(&sd->xfrm_backlog);
+	local_irq_restore(flags);
+
+	if (err) {
+		*again = true;
+		return skb;
+	}
+
+	if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) ||
+				unlikely(xmit_xfrm_check_overflow(skb)))) {
+		struct sk_buff *segs;
+
+		/* Packet got rerouted, fixup features and segment it. */
+		esp_features = esp_features & ~(NETIF_F_HW_ESP | NETIF_F_GSO_ESP);
+
+		segs = skb_gso_segment(skb, esp_features);
+		if (IS_ERR(segs)) {
+			kfree_skb(skb);
+			dev_core_stats_tx_dropped_inc(dev);
+			return NULL;
+		} else {
+			consume_skb(skb);
+			skb = segs;
+		}
+	}
+
+	if (!skb->next) {
+		esp_features |= skb->dev->gso_partial_features;
+		xfrm_outer_mode_prep(x, skb);
+
+		xo->flags |= XFRM_DEV_RESUME;
+
+		err = x->type_offload->xmit(x, skb, esp_features);
+		if (err) {
+			if (err == -EINPROGRESS)
+				return NULL;
+
+			XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
+			kfree_skb(skb);
+			return NULL;
+		}
+
+		skb_push(skb, skb->data - skb_mac_header(skb));
+
+		return skb;
+	}
+
+	skb_list_walk_safe(skb, skb2, nskb) {
+		esp_features |= skb->dev->gso_partial_features;
+		skb_mark_not_on_list(skb2);
+
+		xo = xfrm_offload(skb2);
+		xo->flags |= XFRM_DEV_RESUME;
+
+		xfrm_outer_mode_prep(x, skb2);
+
+		err = x->type_offload->xmit(x, skb2, esp_features);
+		if (!err) {
+			skb2->next = nskb;
+		} else if (err != -EINPROGRESS) {
+			XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
+			skb2->next = nskb;
+			kfree_skb_list(skb2);
+			return NULL;
+		} else {
+			if (skb == skb2)
+				skb = nskb;
+			else
+				pskb->next = nskb;
+
+			continue;
+		}
+
+		skb_push(skb2, skb2->data - skb_mac_header(skb2));
+		pskb = skb2;
+	}
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(validate_xmit_xfrm);
+
+int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
+		       struct xfrm_user_offload *xuo,
+		       struct netlink_ext_ack *extack)
+{
+	int err;
+	struct dst_entry *dst;
+	struct net_device *dev;
+	struct xfrm_dev_offload *xso = &x->xso;
+	xfrm_address_t *saddr;
+	xfrm_address_t *daddr;
+	bool is_packet_offload;
+
+	if (!x->type_offload) {
+		NL_SET_ERR_MSG(extack, "Type doesn't support offload");
+		return -EINVAL;
+	}
+
+	if (xuo->flags &
+	    ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) {
+		NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request");
+		return -EINVAL;
+	}
+
+	is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET;
+
+	/* We don't yet support UDP encapsulation and TFC padding. */
+	if ((!is_packet_offload && x->encap) || x->tfcpad) {
+		NL_SET_ERR_MSG(extack, "Encapsulation and TFC padding can't be offloaded");
+		return -EINVAL;
+	}
+
+	dev = dev_get_by_index(net, xuo->ifindex);
+	if (!dev) {
+		if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) {
+			saddr = &x->props.saddr;
+			daddr = &x->id.daddr;
+		} else {
+			saddr = &x->id.daddr;
+			daddr = &x->props.saddr;
+		}
+
+		dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr,
+					x->props.family,
+					xfrm_smark_get(0, x));
+		if (IS_ERR(dst))
+			return (is_packet_offload) ? -EINVAL : 0;
+
+		dev = dst->dev;
+
+		dev_hold(dev);
+		dst_release(dst);
+	}
+
+	if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) {
+		xso->dev = NULL;
+		dev_put(dev);
+		return (is_packet_offload) ? -EINVAL : 0;
+	}
+
+	if (!is_packet_offload && x->props.flags & XFRM_STATE_ESN &&
+	    !dev->xfrmdev_ops->xdo_dev_state_advance_esn) {
+		NL_SET_ERR_MSG(extack, "Device doesn't support offload with ESN");
+		xso->dev = NULL;
+		dev_put(dev);
+		return -EINVAL;
+	}
+
+	xso->dev = dev;
+	netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC);
+	xso->real_dev = dev;
+
+	if (xuo->flags & XFRM_OFFLOAD_INBOUND)
+		xso->dir = XFRM_DEV_OFFLOAD_IN;
+	else
+		xso->dir = XFRM_DEV_OFFLOAD_OUT;
+
+	if (is_packet_offload)
+		xso->type = XFRM_DEV_OFFLOAD_PACKET;
+	else
+		xso->type = XFRM_DEV_OFFLOAD_CRYPTO;
+
+	err = dev->xfrmdev_ops->xdo_dev_state_add(x, extack);
+	if (err) {
+		xso->dev = NULL;
+		xso->dir = 0;
+		xso->real_dev = NULL;
+		netdev_put(dev, &xso->dev_tracker);
+		xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+
+		/* User explicitly requested packet offload mode and configured
+		 * policy in addition to the XFRM state. So be civil to users,
+		 * and return an error instead of taking fallback path.
+		 *
+		 * This WARN_ON() can be seen as a documentation for driver
+		 * authors to do not return -EOPNOTSUPP in packet offload mode.
+		 */
+		WARN_ON(err == -EOPNOTSUPP && is_packet_offload);
+		if (err != -EOPNOTSUPP || is_packet_offload) {
+			NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state");
+			return err;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xfrm_dev_state_add);
+
+int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp,
+			struct xfrm_user_offload *xuo, u8 dir,
+			struct netlink_ext_ack *extack)
+{
+	struct xfrm_dev_offload *xdo = &xp->xdo;
+	struct net_device *dev;
+	int err;
+
+	if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) {
+		/* We support only packet offload mode and it means
+		 * that user must set XFRM_OFFLOAD_PACKET bit.
+		 */
+		NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request");
+		return -EINVAL;
+	}
+
+	dev = dev_get_by_index(net, xuo->ifindex);
+	if (!dev)
+		return -EINVAL;
+
+	if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) {
+		xdo->dev = NULL;
+		dev_put(dev);
+		NL_SET_ERR_MSG(extack, "Policy offload is not supported");
+		return -EINVAL;
+	}
+
+	xdo->dev = dev;
+	netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC);
+	xdo->real_dev = dev;
+	xdo->type = XFRM_DEV_OFFLOAD_PACKET;
+	switch (dir) {
+	case XFRM_POLICY_IN:
+		xdo->dir = XFRM_DEV_OFFLOAD_IN;
+		break;
+	case XFRM_POLICY_OUT:
+		xdo->dir = XFRM_DEV_OFFLOAD_OUT;
+		break;
+	case XFRM_POLICY_FWD:
+		xdo->dir = XFRM_DEV_OFFLOAD_FWD;
+		break;
+	default:
+		xdo->dev = NULL;
+		netdev_put(dev, &xdo->dev_tracker);
+		NL_SET_ERR_MSG(extack, "Unrecognized offload direction");
+		return -EINVAL;
+	}
+
+	err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack);
+	if (err) {
+		xdo->dev = NULL;
+		xdo->real_dev = NULL;
+		xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+		xdo->dir = 0;
+		netdev_put(dev, &xdo->dev_tracker);
+		NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this policy");
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xfrm_dev_policy_add);
+
+bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
+{
+	int mtu;
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
+	struct net_device *dev = x->xso.dev;
+
+	if (!x->type_offload || x->encap)
+		return false;
+
+	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET ||
+	    ((!dev || (dev == xfrm_dst_path(dst)->dev)) &&
+	     !xdst->child->xfrm)) {
+		mtu = xfrm_state_mtu(x, xdst->child_mtu_cached);
+		if (skb->len <= mtu)
+			goto ok;
+
+		if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
+			goto ok;
+	}
+
+	return false;
+
+ok:
+	if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_offload_ok)
+		return x->xso.dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok);
+
+void xfrm_dev_resume(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	int ret = NETDEV_TX_BUSY;
+	struct netdev_queue *txq;
+	struct softnet_data *sd;
+	unsigned long flags;
+
+	rcu_read_lock();
+	txq = netdev_core_pick_tx(dev, skb, NULL);
+
+	HARD_TX_LOCK(dev, txq, smp_processor_id());
+	if (!netif_xmit_frozen_or_stopped(txq))
+		skb = dev_hard_start_xmit(skb, dev, txq, &ret);
+	HARD_TX_UNLOCK(dev, txq);
+
+	if (!dev_xmit_complete(ret)) {
+		local_irq_save(flags);
+		sd = this_cpu_ptr(&softnet_data);
+		skb_queue_tail(&sd->xfrm_backlog, skb);
+		raise_softirq_irqoff(NET_TX_SOFTIRQ);
+		local_irq_restore(flags);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(xfrm_dev_resume);
+
+void xfrm_dev_backlog(struct softnet_data *sd)
+{
+	struct sk_buff_head *xfrm_backlog = &sd->xfrm_backlog;
+	struct sk_buff_head list;
+	struct sk_buff *skb;
+
+	if (skb_queue_empty(xfrm_backlog))
+		return;
+
+	__skb_queue_head_init(&list);
+
+	spin_lock(&xfrm_backlog->lock);
+	skb_queue_splice_init(xfrm_backlog, &list);
+	spin_unlock(&xfrm_backlog->lock);
+
+	while (!skb_queue_empty(&list)) {
+		skb = __skb_dequeue(&list);
+		xfrm_dev_resume(skb);
+	}
+
+}
+#endif
+
+static int xfrm_api_check(struct net_device *dev)
+{
+#ifdef CONFIG_XFRM_OFFLOAD
+	if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) &&
+	    !(dev->features & NETIF_F_HW_ESP))
+		return NOTIFY_BAD;
+
+	if ((dev->features & NETIF_F_HW_ESP) &&
+	    (!(dev->xfrmdev_ops &&
+	       dev->xfrmdev_ops->xdo_dev_state_add &&
+	       dev->xfrmdev_ops->xdo_dev_state_delete)))
+		return NOTIFY_BAD;
+#else
+	if (dev->features & (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM))
+		return NOTIFY_BAD;
+#endif
+
+	return NOTIFY_DONE;
+}
+
+static int xfrm_dev_down(struct net_device *dev)
+{
+	if (dev->features & NETIF_F_HW_ESP) {
+		xfrm_dev_state_flush(dev_net(dev), dev, true);
+		xfrm_dev_policy_flush(dev_net(dev), dev, true);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		return xfrm_api_check(dev);
+
+	case NETDEV_FEAT_CHANGE:
+		return xfrm_api_check(dev);
+
+	case NETDEV_DOWN:
+	case NETDEV_UNREGISTER:
+		return xfrm_dev_down(dev);
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block xfrm_dev_notifier = {
+	.notifier_call	= xfrm_dev_event,
+};
+
+void __init xfrm_dev_init(void)
+{
+	register_netdevice_notifier(&xfrm_dev_notifier);
+}
diff --git a/net/xfrm/xfrm_hash.c b/net/xfrm/xfrm_hash.c
new file mode 100644
index 0000000000..eca8d84d99
--- /dev/null
+++ b/net/xfrm/xfrm_hash.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* xfrm_hash.c: Common hash table code.
+ *
+ * Copyright (C) 2006 David S. Miller (davem@davemloft.net)
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/xfrm.h>
+
+#include "xfrm_hash.h"
+
+struct hlist_head *xfrm_hash_alloc(unsigned int sz)
+{
+	struct hlist_head *n;
+
+	if (sz <= PAGE_SIZE)
+		n = kzalloc(sz, GFP_KERNEL);
+	else if (hashdist)
+		n = vzalloc(sz);
+	else
+		n = (struct hlist_head *)
+			__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
+					 get_order(sz));
+
+	return n;
+}
+
+void xfrm_hash_free(struct hlist_head *n, unsigned int sz)
+{
+	if (sz <= PAGE_SIZE)
+		kfree(n);
+	else if (hashdist)
+		vfree(n);
+	else
+		free_pages((unsigned long)n, get_order(sz));
+}
diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h
new file mode 100644
index 0000000000..d12bb906c9
--- /dev/null
+++ b/net/xfrm/xfrm_hash.h
@@ -0,0 +1,199 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _XFRM_HASH_H
+#define _XFRM_HASH_H
+
+#include <linux/xfrm.h>
+#include <linux/socket.h>
+#include <linux/jhash.h>
+
+static inline unsigned int __xfrm4_addr_hash(const xfrm_address_t *addr)
+{
+	return ntohl(addr->a4);
+}
+
+static inline unsigned int __xfrm6_addr_hash(const xfrm_address_t *addr)
+{
+	return jhash2((__force u32 *)addr->a6, 4, 0);
+}
+
+static inline unsigned int __xfrm4_daddr_saddr_hash(const xfrm_address_t *daddr,
+						    const xfrm_address_t *saddr)
+{
+	u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4;
+	return ntohl((__force __be32)sum);
+}
+
+static inline unsigned int __xfrm6_daddr_saddr_hash(const xfrm_address_t *daddr,
+						    const xfrm_address_t *saddr)
+{
+	return __xfrm6_addr_hash(daddr) ^ __xfrm6_addr_hash(saddr);
+}
+
+static inline u32 __bits2mask32(__u8 bits)
+{
+	u32 mask32 = 0xffffffff;
+
+	if (bits == 0)
+		mask32 = 0;
+	else if (bits < 32)
+		mask32 <<= (32 - bits);
+
+	return mask32;
+}
+
+static inline unsigned int __xfrm4_dpref_spref_hash(const xfrm_address_t *daddr,
+						    const xfrm_address_t *saddr,
+						    __u8 dbits,
+						    __u8 sbits)
+{
+	return jhash_2words(ntohl(daddr->a4) & __bits2mask32(dbits),
+			    ntohl(saddr->a4) & __bits2mask32(sbits),
+			    0);
+}
+
+static inline unsigned int __xfrm6_pref_hash(const xfrm_address_t *addr,
+					     __u8 prefixlen)
+{
+	unsigned int pdw;
+	unsigned int pbi;
+	u32 initval = 0;
+
+	pdw = prefixlen >> 5;     /* num of whole u32 in prefix */
+	pbi = prefixlen &  0x1f;  /* num of bits in incomplete u32 in prefix */
+
+	if (pbi) {
+		__be32 mask;
+
+		mask = htonl((0xffffffff) << (32 - pbi));
+
+		initval = (__force u32)(addr->a6[pdw] & mask);
+	}
+
+	return jhash2((__force u32 *)addr->a6, pdw, initval);
+}
+
+static inline unsigned int __xfrm6_dpref_spref_hash(const xfrm_address_t *daddr,
+						    const xfrm_address_t *saddr,
+						    __u8 dbits,
+						    __u8 sbits)
+{
+	return __xfrm6_pref_hash(daddr, dbits) ^
+	       __xfrm6_pref_hash(saddr, sbits);
+}
+
+static inline unsigned int __xfrm_dst_hash(const xfrm_address_t *daddr,
+					   const xfrm_address_t *saddr,
+					   u32 reqid, unsigned short family,
+					   unsigned int hmask)
+{
+	unsigned int h = family ^ reqid;
+	switch (family) {
+	case AF_INET:
+		h ^= __xfrm4_daddr_saddr_hash(daddr, saddr);
+		break;
+	case AF_INET6:
+		h ^= __xfrm6_daddr_saddr_hash(daddr, saddr);
+		break;
+	}
+	return (h ^ (h >> 16)) & hmask;
+}
+
+static inline unsigned int __xfrm_src_hash(const xfrm_address_t *daddr,
+					   const xfrm_address_t *saddr,
+					   unsigned short family,
+					   unsigned int hmask)
+{
+	unsigned int h = family;
+	switch (family) {
+	case AF_INET:
+		h ^= __xfrm4_daddr_saddr_hash(daddr, saddr);
+		break;
+	case AF_INET6:
+		h ^= __xfrm6_daddr_saddr_hash(daddr, saddr);
+		break;
+	}
+	return (h ^ (h >> 16)) & hmask;
+}
+
+static inline unsigned int
+__xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto,
+		unsigned short family, unsigned int hmask)
+{
+	unsigned int h = (__force u32)spi ^ proto;
+	switch (family) {
+	case AF_INET:
+		h ^= __xfrm4_addr_hash(daddr);
+		break;
+	case AF_INET6:
+		h ^= __xfrm6_addr_hash(daddr);
+		break;
+	}
+	return (h ^ (h >> 10) ^ (h >> 20)) & hmask;
+}
+
+static inline unsigned int
+__xfrm_seq_hash(u32 seq, unsigned int hmask)
+{
+	unsigned int h = seq;
+	return (h ^ (h >> 10) ^ (h >> 20)) & hmask;
+}
+
+static inline unsigned int __idx_hash(u32 index, unsigned int hmask)
+{
+	return (index ^ (index >> 8)) & hmask;
+}
+
+static inline unsigned int __sel_hash(const struct xfrm_selector *sel,
+				      unsigned short family, unsigned int hmask,
+				      u8 dbits, u8 sbits)
+{
+	const xfrm_address_t *daddr = &sel->daddr;
+	const xfrm_address_t *saddr = &sel->saddr;
+	unsigned int h = 0;
+
+	switch (family) {
+	case AF_INET:
+		if (sel->prefixlen_d < dbits ||
+		    sel->prefixlen_s < sbits)
+			return hmask + 1;
+
+		h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits);
+		break;
+
+	case AF_INET6:
+		if (sel->prefixlen_d < dbits ||
+		    sel->prefixlen_s < sbits)
+			return hmask + 1;
+
+		h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits);
+		break;
+	}
+	h ^= (h >> 16);
+	return h & hmask;
+}
+
+static inline unsigned int __addr_hash(const xfrm_address_t *daddr,
+				       const xfrm_address_t *saddr,
+				       unsigned short family,
+				       unsigned int hmask,
+				       u8 dbits, u8 sbits)
+{
+	unsigned int h = 0;
+
+	switch (family) {
+	case AF_INET:
+		h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits);
+		break;
+
+	case AF_INET6:
+		h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits);
+		break;
+	}
+	h ^= (h >> 16);
+	return h & hmask;
+}
+
+struct hlist_head *xfrm_hash_alloc(unsigned int sz);
+void xfrm_hash_free(struct hlist_head *n, unsigned int sz);
+
+#endif /* _XFRM_HASH_H */
diff --git a/net/xfrm/xfrm_inout.h b/net/xfrm/xfrm_inout.h
new file mode 100644
index 0000000000..efc5e6b2e8
--- /dev/null
+++ b/net/xfrm/xfrm_inout.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/ipv6.h>
+#include <net/dsfield.h>
+#include <net/xfrm.h>
+
+#ifndef XFRM_INOUT_H
+#define XFRM_INOUT_H 1
+
+static inline void xfrm4_extract_header(struct sk_buff *skb)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+
+	XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph);
+	XFRM_MODE_SKB_CB(skb)->id = iph->id;
+	XFRM_MODE_SKB_CB(skb)->frag_off = iph->frag_off;
+	XFRM_MODE_SKB_CB(skb)->tos = iph->tos;
+	XFRM_MODE_SKB_CB(skb)->ttl = iph->ttl;
+	XFRM_MODE_SKB_CB(skb)->optlen = iph->ihl * 4 - sizeof(*iph);
+	memset(XFRM_MODE_SKB_CB(skb)->flow_lbl, 0,
+	       sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl));
+}
+
+static inline void xfrm6_extract_header(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct ipv6hdr *iph = ipv6_hdr(skb);
+
+	XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph);
+	XFRM_MODE_SKB_CB(skb)->id = 0;
+	XFRM_MODE_SKB_CB(skb)->frag_off = htons(IP_DF);
+	XFRM_MODE_SKB_CB(skb)->tos = ipv6_get_dsfield(iph);
+	XFRM_MODE_SKB_CB(skb)->ttl = iph->hop_limit;
+	XFRM_MODE_SKB_CB(skb)->optlen = 0;
+	memcpy(XFRM_MODE_SKB_CB(skb)->flow_lbl, iph->flow_lbl,
+	       sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl));
+#else
+	WARN_ON_ONCE(1);
+#endif
+}
+
+static inline void xfrm6_beet_make_header(struct sk_buff *skb)
+{
+	struct ipv6hdr *iph = ipv6_hdr(skb);
+
+	iph->version = 6;
+
+	memcpy(iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
+	       sizeof(iph->flow_lbl));
+	iph->nexthdr = XFRM_MODE_SKB_CB(skb)->protocol;
+
+	ipv6_change_dsfield(iph, 0, XFRM_MODE_SKB_CB(skb)->tos);
+	iph->hop_limit = XFRM_MODE_SKB_CB(skb)->ttl;
+}
+
+static inline void xfrm4_beet_make_header(struct sk_buff *skb)
+{
+	struct iphdr *iph = ip_hdr(skb);
+
+	iph->ihl = 5;
+	iph->version = 4;
+
+	iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol;
+	iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
+
+	iph->id = XFRM_MODE_SKB_CB(skb)->id;
+	iph->frag_off = XFRM_MODE_SKB_CB(skb)->frag_off;
+	iph->ttl = XFRM_MODE_SKB_CB(skb)->ttl;
+}
+
+#endif
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
new file mode 100644
index 0000000000..d5ee96789d
--- /dev/null
+++ b/net/xfrm/xfrm_input.c
@@ -0,0 +1,810 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * xfrm_input.c
+ *
+ * Changes:
+ * 	YOSHIFUJI Hideaki @USAGI
+ * 		Split up af-specific portion
+ *
+ */
+
+#include <linux/bottom_half.h>
+#include <linux/cache.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/percpu.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+#include <net/ip_tunnels.h>
+#include <net/ip6_tunnel.h>
+#include <net/dst_metadata.h>
+
+#include "xfrm_inout.h"
+
+struct xfrm_trans_tasklet {
+	struct work_struct work;
+	spinlock_t queue_lock;
+	struct sk_buff_head queue;
+};
+
+struct xfrm_trans_cb {
+	union {
+		struct inet_skb_parm	h4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct inet6_skb_parm	h6;
+#endif
+	} header;
+	int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb);
+	struct net *net;
+};
+
+#define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0]))
+
+static DEFINE_SPINLOCK(xfrm_input_afinfo_lock);
+static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[2][AF_INET6 + 1];
+
+static struct gro_cells gro_cells;
+static struct net_device xfrm_napi_dev;
+
+static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet);
+
+int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo)
+{
+	int err = 0;
+
+	if (WARN_ON(afinfo->family > AF_INET6))
+		return -EAFNOSUPPORT;
+
+	spin_lock_bh(&xfrm_input_afinfo_lock);
+	if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family]))
+		err = -EEXIST;
+	else
+		rcu_assign_pointer(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], afinfo);
+	spin_unlock_bh(&xfrm_input_afinfo_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_input_register_afinfo);
+
+int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_input_afinfo_lock);
+	if (likely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) {
+		if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family] != afinfo))
+			err = -EINVAL;
+		else
+			RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], NULL);
+	}
+	spin_unlock_bh(&xfrm_input_afinfo_lock);
+	synchronize_rcu();
+	return err;
+}
+EXPORT_SYMBOL(xfrm_input_unregister_afinfo);
+
+static const struct xfrm_input_afinfo *xfrm_input_get_afinfo(u8 family, bool is_ipip)
+{
+	const struct xfrm_input_afinfo *afinfo;
+
+	if (WARN_ON_ONCE(family > AF_INET6))
+		return NULL;
+
+	rcu_read_lock();
+	afinfo = rcu_dereference(xfrm_input_afinfo[is_ipip][family]);
+	if (unlikely(!afinfo))
+		rcu_read_unlock();
+	return afinfo;
+}
+
+static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol,
+		       int err)
+{
+	bool is_ipip = (protocol == IPPROTO_IPIP || protocol == IPPROTO_IPV6);
+	const struct xfrm_input_afinfo *afinfo;
+	int ret;
+
+	afinfo = xfrm_input_get_afinfo(family, is_ipip);
+	if (!afinfo)
+		return -EAFNOSUPPORT;
+
+	ret = afinfo->callback(skb, protocol, err);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+struct sec_path *secpath_set(struct sk_buff *skb)
+{
+	struct sec_path *sp, *tmp = skb_ext_find(skb, SKB_EXT_SEC_PATH);
+
+	sp = skb_ext_add(skb, SKB_EXT_SEC_PATH);
+	if (!sp)
+		return NULL;
+
+	if (tmp) /* reused existing one (was COW'd if needed) */
+		return sp;
+
+	/* allocated new secpath */
+	memset(sp->ovec, 0, sizeof(sp->ovec));
+	sp->olen = 0;
+	sp->len = 0;
+	sp->verified_cnt = 0;
+
+	return sp;
+}
+EXPORT_SYMBOL(secpath_set);
+
+/* Fetch spi and seq from ipsec header */
+
+int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq)
+{
+	int offset, offset_seq;
+	int hlen;
+
+	switch (nexthdr) {
+	case IPPROTO_AH:
+		hlen = sizeof(struct ip_auth_hdr);
+		offset = offsetof(struct ip_auth_hdr, spi);
+		offset_seq = offsetof(struct ip_auth_hdr, seq_no);
+		break;
+	case IPPROTO_ESP:
+		hlen = sizeof(struct ip_esp_hdr);
+		offset = offsetof(struct ip_esp_hdr, spi);
+		offset_seq = offsetof(struct ip_esp_hdr, seq_no);
+		break;
+	case IPPROTO_COMP:
+		if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr)))
+			return -EINVAL;
+		*spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2)));
+		*seq = 0;
+		return 0;
+	default:
+		return 1;
+	}
+
+	if (!pskb_may_pull(skb, hlen))
+		return -EINVAL;
+
+	*spi = *(__be32 *)(skb_transport_header(skb) + offset);
+	*seq = *(__be32 *)(skb_transport_header(skb) + offset_seq);
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_parse_spi);
+
+static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	int optlen = 0;
+	int err = -EINVAL;
+
+	skb->protocol = htons(ETH_P_IP);
+
+	if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) {
+		struct ip_beet_phdr *ph;
+		int phlen;
+
+		if (!pskb_may_pull(skb, sizeof(*ph)))
+			goto out;
+
+		ph = (struct ip_beet_phdr *)skb->data;
+
+		phlen = sizeof(*ph) + ph->padlen;
+		optlen = ph->hdrlen * 8 + (IPV4_BEET_PHMAXLEN - phlen);
+		if (optlen < 0 || optlen & 3 || optlen > 250)
+			goto out;
+
+		XFRM_MODE_SKB_CB(skb)->protocol = ph->nexthdr;
+
+		if (!pskb_may_pull(skb, phlen))
+			goto out;
+		__skb_pull(skb, phlen);
+	}
+
+	skb_push(skb, sizeof(*iph));
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
+	xfrm4_beet_make_header(skb);
+
+	iph = ip_hdr(skb);
+
+	iph->ihl += optlen / 4;
+	iph->tot_len = htons(skb->len);
+	iph->daddr = x->sel.daddr.a4;
+	iph->saddr = x->sel.saddr.a4;
+	iph->check = 0;
+	iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
+	err = 0;
+out:
+	return err;
+}
+
+static void ipip_ecn_decapsulate(struct sk_buff *skb)
+{
+	struct iphdr *inner_iph = ipip_hdr(skb);
+
+	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
+		IP_ECN_set_ce(inner_iph);
+}
+
+static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = -EINVAL;
+
+	skb->protocol = htons(ETH_P_IP);
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto out;
+
+	err = skb_unclone(skb, GFP_ATOMIC);
+	if (err)
+		goto out;
+
+	if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+		ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipip_hdr(skb));
+	if (!(x->props.flags & XFRM_STATE_NOECN))
+		ipip_ecn_decapsulate(skb);
+
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+	if (skb->mac_len)
+		eth_hdr(skb)->h_proto = skb->protocol;
+
+	err = 0;
+
+out:
+	return err;
+}
+
+static void ipip6_ecn_decapsulate(struct sk_buff *skb)
+{
+	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
+
+	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
+		IP6_ECN_set_ce(skb, inner_iph);
+}
+
+static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = -EINVAL;
+
+	skb->protocol = htons(ETH_P_IPV6);
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		goto out;
+
+	err = skb_unclone(skb, GFP_ATOMIC);
+	if (err)
+		goto out;
+
+	if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+		ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb));
+	if (!(x->props.flags & XFRM_STATE_NOECN))
+		ipip6_ecn_decapsulate(skb);
+
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+	if (skb->mac_len)
+		eth_hdr(skb)->h_proto = skb->protocol;
+
+	err = 0;
+
+out:
+	return err;
+}
+
+static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ipv6hdr *ip6h;
+	int size = sizeof(struct ipv6hdr);
+	int err;
+
+	skb->protocol = htons(ETH_P_IPV6);
+
+	err = skb_cow_head(skb, size + skb->mac_len);
+	if (err)
+		goto out;
+
+	__skb_push(skb, size);
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
+	xfrm6_beet_make_header(skb);
+
+	ip6h = ipv6_hdr(skb);
+	ip6h->payload_len = htons(skb->len - size);
+	ip6h->daddr = x->sel.daddr.in6;
+	ip6h->saddr = x->sel.saddr.in6;
+	err = 0;
+out:
+	return err;
+}
+
+/* Remove encapsulation header.
+ *
+ * The IP header will be moved over the top of the encapsulation
+ * header.
+ *
+ * On entry, the transport header shall point to where the IP header
+ * should be and the network header shall be set to where the IP
+ * header currently is.  skb->data shall point to the start of the
+ * payload.
+ */
+static int
+xfrm_inner_mode_encap_remove(struct xfrm_state *x,
+			     struct sk_buff *skb)
+{
+	switch (x->props.mode) {
+	case XFRM_MODE_BEET:
+		switch (x->sel.family) {
+		case AF_INET:
+			return xfrm4_remove_beet_encap(x, skb);
+		case AF_INET6:
+			return xfrm6_remove_beet_encap(x, skb);
+		}
+		break;
+	case XFRM_MODE_TUNNEL:
+		switch (XFRM_MODE_SKB_CB(skb)->protocol) {
+		case IPPROTO_IPIP:
+			return xfrm4_remove_tunnel_encap(x, skb);
+		case IPPROTO_IPV6:
+			return xfrm6_remove_tunnel_encap(x, skb);
+		break;
+		}
+		return -EINVAL;
+	}
+
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
+}
+
+static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->props.family) {
+	case AF_INET:
+		xfrm4_extract_header(skb);
+		break;
+	case AF_INET6:
+		xfrm6_extract_header(skb);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EAFNOSUPPORT;
+	}
+
+	return xfrm_inner_mode_encap_remove(x, skb);
+}
+
+/* Remove encapsulation header.
+ *
+ * The IP header will be moved over the top of the encapsulation header.
+ *
+ * On entry, skb_transport_header() shall point to where the IP header
+ * should be and skb_network_header() shall be set to where the IP header
+ * currently is.  skb->data shall point to the start of the payload.
+ */
+static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int ihl = skb->data - skb_transport_header(skb);
+
+	if (skb->transport_header != skb->network_header) {
+		memmove(skb_transport_header(skb),
+			skb_network_header(skb), ihl);
+		skb->network_header = skb->transport_header;
+	}
+	ip_hdr(skb)->tot_len = htons(skb->len + ihl);
+	skb_reset_transport_header(skb);
+	return 0;
+}
+
+static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	int ihl = skb->data - skb_transport_header(skb);
+
+	if (skb->transport_header != skb->network_header) {
+		memmove(skb_transport_header(skb),
+			skb_network_header(skb), ihl);
+		skb->network_header = skb->transport_header;
+	}
+	ipv6_hdr(skb)->payload_len = htons(skb->len + ihl -
+					   sizeof(struct ipv6hdr));
+	skb_reset_transport_header(skb);
+	return 0;
+#else
+	WARN_ON_ONCE(1);
+	return -EAFNOSUPPORT;
+#endif
+}
+
+static int xfrm_inner_mode_input(struct xfrm_state *x,
+				 struct sk_buff *skb)
+{
+	switch (x->props.mode) {
+	case XFRM_MODE_BEET:
+	case XFRM_MODE_TUNNEL:
+		return xfrm_prepare_input(x, skb);
+	case XFRM_MODE_TRANSPORT:
+		if (x->props.family == AF_INET)
+			return xfrm4_transport_input(x, skb);
+		if (x->props.family == AF_INET6)
+			return xfrm6_transport_input(x, skb);
+		break;
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+		WARN_ON_ONCE(1);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	const struct xfrm_state_afinfo *afinfo;
+	struct net *net = dev_net(skb->dev);
+	int err;
+	__be32 seq;
+	__be32 seq_hi;
+	struct xfrm_state *x = NULL;
+	xfrm_address_t *daddr;
+	u32 mark = skb->mark;
+	unsigned int family = AF_UNSPEC;
+	int decaps = 0;
+	int async = 0;
+	bool xfrm_gro = false;
+	bool crypto_done = false;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct sec_path *sp;
+
+	if (encap_type < 0) {
+		x = xfrm_input_state(skb);
+
+		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
+			if (x->km.state == XFRM_STATE_ACQ)
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
+			else
+				XFRM_INC_STATS(net,
+					       LINUX_MIB_XFRMINSTATEINVALID);
+
+			if (encap_type == -1)
+				dev_put(skb->dev);
+			goto drop;
+		}
+
+		family = x->props.family;
+
+		/* An encap_type of -1 indicates async resumption. */
+		if (encap_type == -1) {
+			async = 1;
+			seq = XFRM_SKB_CB(skb)->seq.input.low;
+			goto resume;
+		}
+
+		/* encap_type < -1 indicates a GRO call. */
+		encap_type = 0;
+		seq = XFRM_SPI_SKB_CB(skb)->seq;
+
+		if (xo && (xo->flags & CRYPTO_DONE)) {
+			crypto_done = true;
+			family = XFRM_SPI_SKB_CB(skb)->family;
+
+			if (!(xo->status & CRYPTO_SUCCESS)) {
+				if (xo->status &
+				    (CRYPTO_TRANSPORT_AH_AUTH_FAILED |
+				     CRYPTO_TRANSPORT_ESP_AUTH_FAILED |
+				     CRYPTO_TUNNEL_AH_AUTH_FAILED |
+				     CRYPTO_TUNNEL_ESP_AUTH_FAILED)) {
+
+					xfrm_audit_state_icvfail(x, skb,
+								 x->type->proto);
+					x->stats.integrity_failed++;
+					XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR);
+					goto drop;
+				}
+
+				if (xo->status & CRYPTO_INVALID_PROTOCOL) {
+					XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR);
+					goto drop;
+				}
+
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
+				goto drop;
+			}
+
+			if (xfrm_parse_spi(skb, nexthdr, &spi, &seq)) {
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
+				goto drop;
+			}
+		}
+
+		goto lock;
+	}
+
+	family = XFRM_SPI_SKB_CB(skb)->family;
+
+	/* if tunnel is present override skb->mark value with tunnel i_key */
+	switch (family) {
+	case AF_INET:
+		if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4)
+			mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key);
+		break;
+	case AF_INET6:
+		if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6)
+			mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key);
+		break;
+	}
+
+	sp = secpath_set(skb);
+	if (!sp) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR);
+		goto drop;
+	}
+
+	seq = 0;
+	if (!spi && xfrm_parse_spi(skb, nexthdr, &spi, &seq)) {
+		secpath_reset(skb);
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
+		goto drop;
+	}
+
+	daddr = (xfrm_address_t *)(skb_network_header(skb) +
+				   XFRM_SPI_SKB_CB(skb)->daddroff);
+	do {
+		sp = skb_sec_path(skb);
+
+		if (sp->len == XFRM_MAX_DEPTH) {
+			secpath_reset(skb);
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
+			goto drop;
+		}
+
+		x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family);
+		if (x == NULL) {
+			secpath_reset(skb);
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
+			xfrm_audit_state_notfound(skb, family, spi, seq);
+			goto drop;
+		}
+
+		skb->mark = xfrm_smark_get(skb->mark, x);
+
+		sp->xvec[sp->len++] = x;
+
+		skb_dst_force(skb);
+		if (!skb_dst(skb)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR);
+			goto drop;
+		}
+
+lock:
+		spin_lock(&x->lock);
+
+		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
+			if (x->km.state == XFRM_STATE_ACQ)
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
+			else
+				XFRM_INC_STATS(net,
+					       LINUX_MIB_XFRMINSTATEINVALID);
+			goto drop_unlock;
+		}
+
+		if ((x->encap ? x->encap->encap_type : 0) != encap_type) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
+			goto drop_unlock;
+		}
+
+		if (xfrm_replay_check(x, skb, seq)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
+			goto drop_unlock;
+		}
+
+		if (xfrm_state_check_expire(x)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEEXPIRED);
+			goto drop_unlock;
+		}
+
+		spin_unlock(&x->lock);
+
+		if (xfrm_tunnel_check(skb, x, family)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
+			goto drop;
+		}
+
+		seq_hi = htonl(xfrm_replay_seqhi(x, seq));
+
+		XFRM_SKB_CB(skb)->seq.input.low = seq;
+		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
+
+		dev_hold(skb->dev);
+
+		if (crypto_done)
+			nexthdr = x->type_offload->input_tail(x, skb);
+		else
+			nexthdr = x->type->input(x, skb);
+
+		if (nexthdr == -EINPROGRESS)
+			return 0;
+resume:
+		dev_put(skb->dev);
+
+		spin_lock(&x->lock);
+		if (nexthdr < 0) {
+			if (nexthdr == -EBADMSG) {
+				xfrm_audit_state_icvfail(x, skb,
+							 x->type->proto);
+				x->stats.integrity_failed++;
+			}
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR);
+			goto drop_unlock;
+		}
+
+		/* only the first xfrm gets the encap type */
+		encap_type = 0;
+
+		if (xfrm_replay_recheck(x, skb, seq)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
+			goto drop_unlock;
+		}
+
+		xfrm_replay_advance(x, seq);
+
+		x->curlft.bytes += skb->len;
+		x->curlft.packets++;
+		x->lastused = ktime_get_real_seconds();
+
+		spin_unlock(&x->lock);
+
+		XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
+
+		if (xfrm_inner_mode_input(x, skb)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
+			goto drop;
+		}
+
+		if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL) {
+			decaps = 1;
+			break;
+		}
+
+		/*
+		 * We need the inner address.  However, we only get here for
+		 * transport mode so the outer address is identical.
+		 */
+		daddr = &x->id.daddr;
+		family = x->props.family;
+
+		err = xfrm_parse_spi(skb, nexthdr, &spi, &seq);
+		if (err < 0) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
+			goto drop;
+		}
+		crypto_done = false;
+	} while (!err);
+
+	err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
+	if (err)
+		goto drop;
+
+	nf_reset_ct(skb);
+
+	if (decaps) {
+		sp = skb_sec_path(skb);
+		if (sp)
+			sp->olen = 0;
+		if (skb_valid_dst(skb))
+			skb_dst_drop(skb);
+		gro_cells_receive(&gro_cells, skb);
+		return 0;
+	} else {
+		xo = xfrm_offload(skb);
+		if (xo)
+			xfrm_gro = xo->flags & XFRM_GRO;
+
+		err = -EAFNOSUPPORT;
+		rcu_read_lock();
+		afinfo = xfrm_state_afinfo_get_rcu(x->props.family);
+		if (likely(afinfo))
+			err = afinfo->transport_finish(skb, xfrm_gro || async);
+		rcu_read_unlock();
+		if (xfrm_gro) {
+			sp = skb_sec_path(skb);
+			if (sp)
+				sp->olen = 0;
+			if (skb_valid_dst(skb))
+				skb_dst_drop(skb);
+			gro_cells_receive(&gro_cells, skb);
+			return err;
+		}
+
+		return err;
+	}
+
+drop_unlock:
+	spin_unlock(&x->lock);
+drop:
+	xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1);
+	kfree_skb(skb);
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_input);
+
+int xfrm_input_resume(struct sk_buff *skb, int nexthdr)
+{
+	return xfrm_input(skb, nexthdr, 0, -1);
+}
+EXPORT_SYMBOL(xfrm_input_resume);
+
+static void xfrm_trans_reinject(struct work_struct *work)
+{
+	struct xfrm_trans_tasklet *trans = container_of(work, struct xfrm_trans_tasklet, work);
+	struct sk_buff_head queue;
+	struct sk_buff *skb;
+
+	__skb_queue_head_init(&queue);
+	spin_lock_bh(&trans->queue_lock);
+	skb_queue_splice_init(&trans->queue, &queue);
+	spin_unlock_bh(&trans->queue_lock);
+
+	local_bh_disable();
+	while ((skb = __skb_dequeue(&queue)))
+		XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
+					       NULL, skb);
+	local_bh_enable();
+}
+
+int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
+			 int (*finish)(struct net *, struct sock *,
+				       struct sk_buff *))
+{
+	struct xfrm_trans_tasklet *trans;
+
+	trans = this_cpu_ptr(&xfrm_trans_tasklet);
+
+	if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog))
+		return -ENOBUFS;
+
+	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
+
+	XFRM_TRANS_SKB_CB(skb)->finish = finish;
+	XFRM_TRANS_SKB_CB(skb)->net = net;
+	spin_lock_bh(&trans->queue_lock);
+	__skb_queue_tail(&trans->queue, skb);
+	spin_unlock_bh(&trans->queue_lock);
+	schedule_work(&trans->work);
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_trans_queue_net);
+
+int xfrm_trans_queue(struct sk_buff *skb,
+		     int (*finish)(struct net *, struct sock *,
+				   struct sk_buff *))
+{
+	return xfrm_trans_queue_net(dev_net(skb->dev), skb, finish);
+}
+EXPORT_SYMBOL(xfrm_trans_queue);
+
+void __init xfrm_input_init(void)
+{
+	int err;
+	int i;
+
+	init_dummy_netdev(&xfrm_napi_dev);
+	err = gro_cells_init(&gro_cells, &xfrm_napi_dev);
+	if (err)
+		gro_cells.cells = NULL;
+
+	for_each_possible_cpu(i) {
+		struct xfrm_trans_tasklet *trans;
+
+		trans = &per_cpu(xfrm_trans_tasklet, i);
+		spin_lock_init(&trans->queue_lock);
+		__skb_queue_head_init(&trans->queue);
+		INIT_WORK(&trans->work, xfrm_trans_reinject);
+	}
+}
diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c
new file mode 100644
index 0000000000..d74f3fd20f
--- /dev/null
+++ b/net/xfrm/xfrm_interface_bpf.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable XFRM Helpers for TC-BPF hook
+ *
+ * These are called from SCHED_CLS BPF programs. Note that it is
+ * allowed to break compatibility for these functions since the interface they
+ * are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+
+#include <net/dst_metadata.h>
+#include <net/xfrm.h>
+
+/* bpf_xfrm_info - XFRM metadata information
+ *
+ * Members:
+ * @if_id	- XFRM if_id:
+ *		    Transmit: if_id to be used in policy and state lookups
+ *		    Receive: if_id of the state matched for the incoming packet
+ * @link	- Underlying device ifindex:
+ *		    Transmit: used as the underlying device in VRF routing
+ *		    Receive: the device on which the packet had been received
+ */
+struct bpf_xfrm_info {
+	u32 if_id;
+	int link;
+};
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in xfrm_interface BTF");
+
+/* bpf_skb_get_xfrm_info - Get XFRM metadata
+ *
+ * Parameters:
+ * @skb_ctx	- Pointer to ctx (__sk_buff) in TC program
+ *		    Cannot be NULL
+ * @to		- Pointer to memory to which the metadata will be copied
+ *		    Cannot be NULL
+ */
+__bpf_kfunc int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to)
+{
+	struct sk_buff *skb = (struct sk_buff *)skb_ctx;
+	struct xfrm_md_info *info;
+
+	info = skb_xfrm_md_info(skb);
+	if (!info)
+		return -EINVAL;
+
+	to->if_id = info->if_id;
+	to->link = info->link;
+	return 0;
+}
+
+/* bpf_skb_get_xfrm_info - Set XFRM metadata
+ *
+ * Parameters:
+ * @skb_ctx	- Pointer to ctx (__sk_buff) in TC program
+ *		    Cannot be NULL
+ * @from	- Pointer to memory from which the metadata will be copied
+ *		    Cannot be NULL
+ */
+__bpf_kfunc int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, const struct bpf_xfrm_info *from)
+{
+	struct sk_buff *skb = (struct sk_buff *)skb_ctx;
+	struct metadata_dst *md_dst;
+	struct xfrm_md_info *info;
+
+	if (unlikely(skb_metadata_dst(skb)))
+		return -EINVAL;
+
+	if (!xfrm_bpf_md_dst) {
+		struct metadata_dst __percpu *tmp;
+
+		tmp = metadata_dst_alloc_percpu(0, METADATA_XFRM, GFP_ATOMIC);
+		if (!tmp)
+			return -ENOMEM;
+		if (cmpxchg(&xfrm_bpf_md_dst, NULL, tmp))
+			metadata_dst_free_percpu(tmp);
+	}
+	md_dst = this_cpu_ptr(xfrm_bpf_md_dst);
+
+	info = &md_dst->u.xfrm_info;
+
+	info->if_id = from->if_id;
+	info->link = from->link;
+	skb_dst_force(skb);
+	info->dst_orig = skb_dst(skb);
+
+	dst_hold((struct dst_entry *)md_dst);
+	skb_dst_set(skb, (struct dst_entry *)md_dst);
+	return 0;
+}
+
+__diag_pop()
+
+BTF_SET8_START(xfrm_ifc_kfunc_set)
+BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info)
+BTF_ID_FLAGS(func, bpf_skb_set_xfrm_info)
+BTF_SET8_END(xfrm_ifc_kfunc_set)
+
+static const struct btf_kfunc_id_set xfrm_interface_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &xfrm_ifc_kfunc_set,
+};
+
+int __init register_xfrm_interface_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS,
+					 &xfrm_interface_kfunc_set);
+}
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
new file mode 100644
index 0000000000..e21cc71095
--- /dev/null
+++ b/net/xfrm/xfrm_interface_core.c
@@ -0,0 +1,1257 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *	XFRM virtual interface
+ *
+ *	Copyright (C) 2018 secunet Security Networks AG
+ *
+ *	Author:
+ *	Steffen Klassert <steffen.klassert@secunet.com>
+ */
+
+#include <linux/module.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/sockios.h>
+#include <linux/icmp.h>
+#include <linux/if.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/if_link.h>
+#include <linux/if_arp.h>
+#include <linux/icmpv6.h>
+#include <linux/init.h>
+#include <linux/route.h>
+#include <linux/rtnetlink.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/slab.h>
+#include <linux/hash.h>
+
+#include <linux/uaccess.h>
+#include <linux/atomic.h>
+
+#include <net/gso.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/ip_tunnels.h>
+#include <net/addrconf.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/dst_metadata.h>
+#include <net/netns/generic.h>
+#include <linux/etherdevice.h>
+
+static int xfrmi_dev_init(struct net_device *dev);
+static void xfrmi_dev_setup(struct net_device *dev);
+static struct rtnl_link_ops xfrmi_link_ops __read_mostly;
+static unsigned int xfrmi_net_id __read_mostly;
+static const struct net_device_ops xfrmi_netdev_ops;
+
+#define XFRMI_HASH_BITS	8
+#define XFRMI_HASH_SIZE	BIT(XFRMI_HASH_BITS)
+
+struct xfrmi_net {
+	/* lists for storing interfaces in use */
+	struct xfrm_if __rcu *xfrmi[XFRMI_HASH_SIZE];
+	struct xfrm_if __rcu *collect_md_xfrmi;
+};
+
+static const struct nla_policy xfrm_lwt_policy[LWT_XFRM_MAX + 1] = {
+	[LWT_XFRM_IF_ID]	= NLA_POLICY_MIN(NLA_U32, 1),
+	[LWT_XFRM_LINK]		= NLA_POLICY_MIN(NLA_U32, 1),
+};
+
+static void xfrmi_destroy_state(struct lwtunnel_state *lwt)
+{
+}
+
+static int xfrmi_build_state(struct net *net, struct nlattr *nla,
+			     unsigned int family, const void *cfg,
+			     struct lwtunnel_state **ts,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[LWT_XFRM_MAX + 1];
+	struct lwtunnel_state *new_state;
+	struct xfrm_md_info *info;
+	int ret;
+
+	ret = nla_parse_nested(tb, LWT_XFRM_MAX, nla, xfrm_lwt_policy, extack);
+	if (ret < 0)
+		return ret;
+
+	if (!tb[LWT_XFRM_IF_ID]) {
+		NL_SET_ERR_MSG(extack, "if_id must be set");
+		return -EINVAL;
+	}
+
+	new_state = lwtunnel_state_alloc(sizeof(*info));
+	if (!new_state) {
+		NL_SET_ERR_MSG(extack, "failed to create encap info");
+		return -ENOMEM;
+	}
+
+	new_state->type = LWTUNNEL_ENCAP_XFRM;
+
+	info = lwt_xfrm_info(new_state);
+
+	info->if_id = nla_get_u32(tb[LWT_XFRM_IF_ID]);
+
+	if (tb[LWT_XFRM_LINK])
+		info->link = nla_get_u32(tb[LWT_XFRM_LINK]);
+
+	*ts = new_state;
+	return 0;
+}
+
+static int xfrmi_fill_encap_info(struct sk_buff *skb,
+				 struct lwtunnel_state *lwt)
+{
+	struct xfrm_md_info *info = lwt_xfrm_info(lwt);
+
+	if (nla_put_u32(skb, LWT_XFRM_IF_ID, info->if_id) ||
+	    (info->link && nla_put_u32(skb, LWT_XFRM_LINK, info->link)))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int xfrmi_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+	return nla_total_size(sizeof(u32)) + /* LWT_XFRM_IF_ID */
+		nla_total_size(sizeof(u32)); /* LWT_XFRM_LINK */
+}
+
+static int xfrmi_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+	struct xfrm_md_info *a_info = lwt_xfrm_info(a);
+	struct xfrm_md_info *b_info = lwt_xfrm_info(b);
+
+	return memcmp(a_info, b_info, sizeof(*a_info));
+}
+
+static const struct lwtunnel_encap_ops xfrmi_encap_ops = {
+	.build_state	= xfrmi_build_state,
+	.destroy_state	= xfrmi_destroy_state,
+	.fill_encap	= xfrmi_fill_encap_info,
+	.get_encap_size = xfrmi_encap_nlsize,
+	.cmp_encap	= xfrmi_encap_cmp,
+	.owner		= THIS_MODULE,
+};
+
+#define for_each_xfrmi_rcu(start, xi) \
+	for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next))
+
+static u32 xfrmi_hash(u32 if_id)
+{
+	return hash_32(if_id, XFRMI_HASH_BITS);
+}
+
+static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x)
+{
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+	struct xfrm_if *xi;
+
+	for_each_xfrmi_rcu(xfrmn->xfrmi[xfrmi_hash(x->if_id)], xi) {
+		if (x->if_id == xi->p.if_id &&
+		    (xi->dev->flags & IFF_UP))
+			return xi;
+	}
+
+	xi = rcu_dereference(xfrmn->collect_md_xfrmi);
+	if (xi && (xi->dev->flags & IFF_UP))
+		return xi;
+
+	return NULL;
+}
+
+static bool xfrmi_decode_session(struct sk_buff *skb,
+				 unsigned short family,
+				 struct xfrm_if_decode_session_result *res)
+{
+	struct net_device *dev;
+	struct xfrm_if *xi;
+	int ifindex = 0;
+
+	if (!secpath_exists(skb) || !skb->dev)
+		return false;
+
+	switch (family) {
+	case AF_INET6:
+		ifindex = inet6_sdif(skb);
+		break;
+	case AF_INET:
+		ifindex = inet_sdif(skb);
+		break;
+	}
+
+	if (ifindex) {
+		struct net *net = xs_net(xfrm_input_state(skb));
+
+		dev = dev_get_by_index_rcu(net, ifindex);
+	} else {
+		dev = skb->dev;
+	}
+
+	if (!dev || !(dev->flags & IFF_UP))
+		return false;
+	if (dev->netdev_ops != &xfrmi_netdev_ops)
+		return false;
+
+	xi = netdev_priv(dev);
+	res->net = xi->net;
+
+	if (xi->p.collect_md)
+		res->if_id = xfrm_input_state(skb)->if_id;
+	else
+		res->if_id = xi->p.if_id;
+	return true;
+}
+
+static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi)
+{
+	struct xfrm_if __rcu **xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)];
+
+	rcu_assign_pointer(xi->next , rtnl_dereference(*xip));
+	rcu_assign_pointer(*xip, xi);
+}
+
+static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi)
+{
+	struct xfrm_if __rcu **xip;
+	struct xfrm_if *iter;
+
+	for (xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)];
+	     (iter = rtnl_dereference(*xip)) != NULL;
+	     xip = &iter->next) {
+		if (xi == iter) {
+			rcu_assign_pointer(*xip, xi->next);
+			break;
+		}
+	}
+}
+
+static void xfrmi_dev_free(struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+
+	gro_cells_destroy(&xi->gro_cells);
+	free_percpu(dev->tstats);
+}
+
+static int xfrmi_create(struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct net *net = dev_net(dev);
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+	int err;
+
+	dev->rtnl_link_ops = &xfrmi_link_ops;
+	err = register_netdevice(dev);
+	if (err < 0)
+		goto out;
+
+	if (xi->p.collect_md)
+		rcu_assign_pointer(xfrmn->collect_md_xfrmi, xi);
+	else
+		xfrmi_link(xfrmn, xi);
+
+	return 0;
+
+out:
+	return err;
+}
+
+static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p)
+{
+	struct xfrm_if __rcu **xip;
+	struct xfrm_if *xi;
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+
+	for (xip = &xfrmn->xfrmi[xfrmi_hash(p->if_id)];
+	     (xi = rtnl_dereference(*xip)) != NULL;
+	     xip = &xi->next)
+		if (xi->p.if_id == p->if_id)
+			return xi;
+
+	return NULL;
+}
+
+static void xfrmi_dev_uninit(struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id);
+
+	if (xi->p.collect_md)
+		RCU_INIT_POINTER(xfrmn->collect_md_xfrmi, NULL);
+	else
+		xfrmi_unlink(xfrmn, xi);
+}
+
+static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
+{
+	skb_clear_tstamp(skb);
+	skb->pkt_type = PACKET_HOST;
+	skb->skb_iif = 0;
+	skb->ignore_df = 0;
+	skb_dst_drop(skb);
+	nf_reset_ct(skb);
+	nf_reset_trace(skb);
+
+	if (!xnet)
+		return;
+
+	ipvs_reset(skb);
+	secpath_reset(skb);
+	skb_orphan(skb);
+	skb->mark = 0;
+}
+
+static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi,
+		       int encap_type, unsigned short family)
+{
+	struct sec_path *sp;
+
+	sp = skb_sec_path(skb);
+	if (sp && (sp->len || sp->olen) &&
+	    !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+		goto discard;
+
+	XFRM_SPI_SKB_CB(skb)->family = family;
+	if (family == AF_INET) {
+		XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+	} else {
+		XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+	}
+
+	return xfrm_input(skb, nexthdr, spi, encap_type);
+discard:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int xfrmi4_rcv(struct sk_buff *skb)
+{
+	return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET);
+}
+
+static int xfrmi6_rcv(struct sk_buff *skb)
+{
+	return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
+			   0, 0, AF_INET6);
+}
+
+static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET);
+}
+
+static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6);
+}
+
+static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
+{
+	const struct xfrm_mode *inner_mode;
+	struct net_device *dev;
+	struct xfrm_state *x;
+	struct xfrm_if *xi;
+	bool xnet;
+	int link;
+
+	if (err && !secpath_exists(skb))
+		return 0;
+
+	x = xfrm_input_state(skb);
+
+	xi = xfrmi_lookup(xs_net(x), x);
+	if (!xi)
+		return 1;
+
+	link = skb->dev->ifindex;
+	dev = xi->dev;
+	skb->dev = dev;
+
+	if (err) {
+		DEV_STATS_INC(dev, rx_errors);
+		DEV_STATS_INC(dev, rx_dropped);
+
+		return 0;
+	}
+
+	xnet = !net_eq(xi->net, dev_net(skb->dev));
+
+	if (xnet) {
+		inner_mode = &x->inner_mode;
+
+		if (x->sel.family == AF_UNSPEC) {
+			inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
+			if (inner_mode == NULL) {
+				XFRM_INC_STATS(dev_net(skb->dev),
+					       LINUX_MIB_XFRMINSTATEMODEERROR);
+				return -EINVAL;
+			}
+		}
+
+		if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb,
+				       inner_mode->family))
+			return -EPERM;
+	}
+
+	xfrmi_scrub_packet(skb, xnet);
+	if (xi->p.collect_md) {
+		struct metadata_dst *md_dst;
+
+		md_dst = metadata_dst_alloc(0, METADATA_XFRM, GFP_ATOMIC);
+		if (!md_dst)
+			return -ENOMEM;
+
+		md_dst->u.xfrm_info.if_id = x->if_id;
+		md_dst->u.xfrm_info.link = link;
+		skb_dst_set(skb, (struct dst_entry *)md_dst);
+	}
+	dev_sw_netstats_rx_add(dev, skb->len);
+
+	return 0;
+}
+
+static int
+xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct dst_entry *dst = skb_dst(skb);
+	unsigned int length = skb->len;
+	struct net_device *tdev;
+	struct xfrm_state *x;
+	int err = -1;
+	u32 if_id;
+	int mtu;
+
+	if (xi->p.collect_md) {
+		struct xfrm_md_info *md_info = skb_xfrm_md_info(skb);
+
+		if (unlikely(!md_info))
+			return -EINVAL;
+
+		if_id = md_info->if_id;
+		fl->flowi_oif = md_info->link;
+		if (md_info->dst_orig) {
+			struct dst_entry *tmp_dst = dst;
+
+			dst = md_info->dst_orig;
+			skb_dst_set(skb, dst);
+			md_info->dst_orig = NULL;
+			dst_release(tmp_dst);
+		}
+	} else {
+		if_id = xi->p.if_id;
+	}
+
+	dst_hold(dst);
+	dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, if_id);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		dst = NULL;
+		goto tx_err_link_failure;
+	}
+
+	x = dst->xfrm;
+	if (!x)
+		goto tx_err_link_failure;
+
+	if (x->if_id != if_id)
+		goto tx_err_link_failure;
+
+	tdev = dst->dev;
+
+	if (tdev == dev) {
+		DEV_STATS_INC(dev, collisions);
+		net_warn_ratelimited("%s: Local routing loop detected!\n",
+				     dev->name);
+		goto tx_err_dst_release;
+	}
+
+	mtu = dst_mtu(dst);
+	if ((!skb_is_gso(skb) && skb->len > mtu) ||
+	    (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))) {
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
+
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			if (mtu < IPV6_MIN_MTU)
+				mtu = IPV6_MIN_MTU;
+
+			if (skb->len > 1280)
+				icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			else
+				goto xmit;
+		} else {
+			if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
+				goto xmit;
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				      htonl(mtu));
+		}
+
+		dst_release(dst);
+		return -EMSGSIZE;
+	}
+
+xmit:
+	xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev)));
+	skb_dst_set(skb, dst);
+	skb->dev = tdev;
+
+	err = dst_output(xi->net, skb->sk, skb);
+	if (net_xmit_eval(err) == 0) {
+		dev_sw_netstats_tx_add(dev, 1, length);
+	} else {
+		DEV_STATS_INC(dev, tx_errors);
+		DEV_STATS_INC(dev, tx_aborted_errors);
+	}
+
+	return 0;
+tx_err_link_failure:
+	DEV_STATS_INC(dev, tx_carrier_errors);
+	dst_link_failure(skb);
+tx_err_dst_release:
+	dst_release(dst);
+	return err;
+}
+
+static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct dst_entry *dst = skb_dst(skb);
+	struct flowi fl;
+	int ret;
+
+	memset(&fl, 0, sizeof(fl));
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IPV6):
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		xfrm_decode_session(skb, &fl, AF_INET6);
+		if (!dst) {
+			fl.u.ip6.flowi6_oif = dev->ifindex;
+			fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+			dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6);
+			if (dst->error) {
+				dst_release(dst);
+				DEV_STATS_INC(dev, tx_carrier_errors);
+				goto tx_err;
+			}
+			skb_dst_set(skb, dst);
+		}
+		break;
+	case htons(ETH_P_IP):
+		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		xfrm_decode_session(skb, &fl, AF_INET);
+		if (!dst) {
+			struct rtable *rt;
+
+			fl.u.ip4.flowi4_oif = dev->ifindex;
+			fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+			rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4);
+			if (IS_ERR(rt)) {
+				DEV_STATS_INC(dev, tx_carrier_errors);
+				goto tx_err;
+			}
+			skb_dst_set(skb, &rt->dst);
+		}
+		break;
+	default:
+		goto tx_err;
+	}
+
+	fl.flowi_oif = xi->p.link;
+
+	ret = xfrmi_xmit2(skb, dev, &fl);
+	if (ret < 0)
+		goto tx_err;
+
+	return NETDEV_TX_OK;
+
+tx_err:
+	DEV_STATS_INC(dev, tx_errors);
+	DEV_STATS_INC(dev, tx_dropped);
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static int xfrmi4_err(struct sk_buff *skb, u32 info)
+{
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
+	struct net *net = dev_net(skb->dev);
+	int protocol = iph->protocol;
+	struct ip_comp_hdr *ipch;
+	struct ip_esp_hdr *esph;
+	struct ip_auth_hdr *ah ;
+	struct xfrm_state *x;
+	struct xfrm_if *xi;
+	__be32 spi;
+
+	switch (protocol) {
+	case IPPROTO_ESP:
+		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
+		spi = esph->spi;
+		break;
+	case IPPROTO_AH:
+		ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
+		spi = ah->spi;
+		break;
+	case IPPROTO_COMP:
+		ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
+		spi = htonl(ntohs(ipch->cpi));
+		break;
+	default:
+		return 0;
+	}
+
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+			return 0;
+		break;
+	case ICMP_REDIRECT:
+		break;
+	default:
+		return 0;
+	}
+
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      spi, protocol, AF_INET);
+	if (!x)
+		return 0;
+
+	xi = xfrmi_lookup(net, x);
+	if (!xi) {
+		xfrm_state_put(x);
+		return -1;
+	}
+
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+		ipv4_update_pmtu(skb, net, info, 0, protocol);
+	else
+		ipv4_redirect(skb, net, 0, protocol);
+	xfrm_state_put(x);
+
+	return 0;
+}
+
+static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		    u8 type, u8 code, int offset, __be32 info)
+{
+	const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
+	struct net *net = dev_net(skb->dev);
+	int protocol = iph->nexthdr;
+	struct ip_comp_hdr *ipch;
+	struct ip_esp_hdr *esph;
+	struct ip_auth_hdr *ah;
+	struct xfrm_state *x;
+	struct xfrm_if *xi;
+	__be32 spi;
+
+	switch (protocol) {
+	case IPPROTO_ESP:
+		esph = (struct ip_esp_hdr *)(skb->data + offset);
+		spi = esph->spi;
+		break;
+	case IPPROTO_AH:
+		ah = (struct ip_auth_hdr *)(skb->data + offset);
+		spi = ah->spi;
+		break;
+	case IPPROTO_COMP:
+		ipch = (struct ip_comp_hdr *)(skb->data + offset);
+		spi = htonl(ntohs(ipch->cpi));
+		break;
+	default:
+		return 0;
+	}
+
+	if (type != ICMPV6_PKT_TOOBIG &&
+	    type != NDISC_REDIRECT)
+		return 0;
+
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      spi, protocol, AF_INET6);
+	if (!x)
+		return 0;
+
+	xi = xfrmi_lookup(net, x);
+	if (!xi) {
+		xfrm_state_put(x);
+		return -1;
+	}
+
+	if (type == NDISC_REDIRECT)
+		ip6_redirect(skb, net, skb->dev->ifindex, 0,
+			     sock_net_uid(net, NULL));
+	else
+		ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
+	xfrm_state_put(x);
+
+	return 0;
+}
+
+static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p)
+{
+	if (xi->p.link != p->link)
+		return -EINVAL;
+
+	xi->p.if_id = p->if_id;
+
+	return 0;
+}
+
+static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p)
+{
+	struct net *net = xi->net;
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+	int err;
+
+	xfrmi_unlink(xfrmn, xi);
+	synchronize_net();
+	err = xfrmi_change(xi, p);
+	xfrmi_link(xfrmn, xi);
+	netdev_state_change(xi->dev);
+	return err;
+}
+
+static int xfrmi_get_iflink(const struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+
+	return xi->p.link;
+}
+
+static const struct net_device_ops xfrmi_netdev_ops = {
+	.ndo_init	= xfrmi_dev_init,
+	.ndo_uninit	= xfrmi_dev_uninit,
+	.ndo_start_xmit = xfrmi_xmit,
+	.ndo_get_stats64 = dev_get_tstats64,
+	.ndo_get_iflink = xfrmi_get_iflink,
+};
+
+static void xfrmi_dev_setup(struct net_device *dev)
+{
+	dev->netdev_ops 	= &xfrmi_netdev_ops;
+	dev->header_ops		= &ip_tunnel_header_ops;
+	dev->type		= ARPHRD_NONE;
+	dev->mtu		= ETH_DATA_LEN;
+	dev->min_mtu		= ETH_MIN_MTU;
+	dev->max_mtu		= IP_MAX_MTU;
+	dev->flags 		= IFF_NOARP;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= xfrmi_dev_free;
+	netif_keep_dst(dev);
+
+	eth_broadcast_addr(dev->broadcast);
+}
+
+#define XFRMI_FEATURES (NETIF_F_SG |		\
+			NETIF_F_FRAGLIST |	\
+			NETIF_F_GSO_SOFTWARE |	\
+			NETIF_F_HW_CSUM)
+
+static int xfrmi_dev_init(struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct net_device *phydev = __dev_get_by_index(xi->net, xi->p.link);
+	int err;
+
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
+	err = gro_cells_init(&xi->gro_cells, dev);
+	if (err) {
+		free_percpu(dev->tstats);
+		return err;
+	}
+
+	dev->features |= NETIF_F_LLTX;
+	dev->features |= XFRMI_FEATURES;
+	dev->hw_features |= XFRMI_FEATURES;
+
+	if (phydev) {
+		dev->needed_headroom = phydev->needed_headroom;
+		dev->needed_tailroom = phydev->needed_tailroom;
+
+		if (is_zero_ether_addr(dev->dev_addr))
+			eth_hw_addr_inherit(dev, phydev);
+		if (is_zero_ether_addr(dev->broadcast))
+			memcpy(dev->broadcast, phydev->broadcast,
+			       dev->addr_len);
+	} else {
+		eth_hw_addr_random(dev);
+		eth_broadcast_addr(dev->broadcast);
+	}
+
+	return 0;
+}
+
+static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[],
+			 struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static void xfrmi_netlink_parms(struct nlattr *data[],
+			       struct xfrm_if_parms *parms)
+{
+	memset(parms, 0, sizeof(*parms));
+
+	if (!data)
+		return;
+
+	if (data[IFLA_XFRM_LINK])
+		parms->link = nla_get_u32(data[IFLA_XFRM_LINK]);
+
+	if (data[IFLA_XFRM_IF_ID])
+		parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]);
+
+	if (data[IFLA_XFRM_COLLECT_METADATA])
+		parms->collect_md = true;
+}
+
+static int xfrmi_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[],
+			struct netlink_ext_ack *extack)
+{
+	struct net *net = dev_net(dev);
+	struct xfrm_if_parms p = {};
+	struct xfrm_if *xi;
+	int err;
+
+	xfrmi_netlink_parms(data, &p);
+	if (p.collect_md) {
+		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+
+		if (p.link || p.if_id) {
+			NL_SET_ERR_MSG(extack, "link and if_id must be zero");
+			return -EINVAL;
+		}
+
+		if (rtnl_dereference(xfrmn->collect_md_xfrmi))
+			return -EEXIST;
+
+	} else {
+		if (!p.if_id) {
+			NL_SET_ERR_MSG(extack, "if_id must be non zero");
+			return -EINVAL;
+		}
+
+		xi = xfrmi_locate(net, &p);
+		if (xi)
+			return -EEXIST;
+	}
+
+	xi = netdev_priv(dev);
+	xi->p = p;
+	xi->net = net;
+	xi->dev = dev;
+
+	err = xfrmi_create(dev);
+	return err;
+}
+
+static void xfrmi_dellink(struct net_device *dev, struct list_head *head)
+{
+	unregister_netdevice_queue(dev, head);
+}
+
+static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
+			   struct nlattr *data[],
+			   struct netlink_ext_ack *extack)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct net *net = xi->net;
+	struct xfrm_if_parms p = {};
+
+	xfrmi_netlink_parms(data, &p);
+	if (!p.if_id) {
+		NL_SET_ERR_MSG(extack, "if_id must be non zero");
+		return -EINVAL;
+	}
+
+	if (p.collect_md) {
+		NL_SET_ERR_MSG(extack, "collect_md can't be changed");
+		return -EINVAL;
+	}
+
+	xi = xfrmi_locate(net, &p);
+	if (!xi) {
+		xi = netdev_priv(dev);
+	} else {
+		if (xi->dev != dev)
+			return -EEXIST;
+		if (xi->p.collect_md) {
+			NL_SET_ERR_MSG(extack,
+				       "device can't be changed to collect_md");
+			return -EINVAL;
+		}
+	}
+
+	return xfrmi_update(xi, &p);
+}
+
+static size_t xfrmi_get_size(const struct net_device *dev)
+{
+	return
+		/* IFLA_XFRM_LINK */
+		nla_total_size(4) +
+		/* IFLA_XFRM_IF_ID */
+		nla_total_size(4) +
+		/* IFLA_XFRM_COLLECT_METADATA */
+		nla_total_size(0) +
+		0;
+}
+
+static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct xfrm_if_parms *parm = &xi->p;
+
+	if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) ||
+	    nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id) ||
+	    (xi->p.collect_md && nla_put_flag(skb, IFLA_XFRM_COLLECT_METADATA)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static struct net *xfrmi_get_link_net(const struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+
+	return xi->net;
+}
+
+static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = {
+	[IFLA_XFRM_UNSPEC]		= { .strict_start_type = IFLA_XFRM_COLLECT_METADATA },
+	[IFLA_XFRM_LINK]		= { .type = NLA_U32 },
+	[IFLA_XFRM_IF_ID]		= { .type = NLA_U32 },
+	[IFLA_XFRM_COLLECT_METADATA]	= { .type = NLA_FLAG },
+};
+
+static struct rtnl_link_ops xfrmi_link_ops __read_mostly = {
+	.kind		= "xfrm",
+	.maxtype	= IFLA_XFRM_MAX,
+	.policy		= xfrmi_policy,
+	.priv_size	= sizeof(struct xfrm_if),
+	.setup		= xfrmi_dev_setup,
+	.validate	= xfrmi_validate,
+	.newlink	= xfrmi_newlink,
+	.dellink	= xfrmi_dellink,
+	.changelink	= xfrmi_changelink,
+	.get_size	= xfrmi_get_size,
+	.fill_info	= xfrmi_fill_info,
+	.get_link_net	= xfrmi_get_link_net,
+};
+
+static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list)
+{
+	struct net *net;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+	list_for_each_entry(net, net_exit_list, exit_list) {
+		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+		struct xfrm_if __rcu **xip;
+		struct xfrm_if *xi;
+		int i;
+
+		for (i = 0; i < XFRMI_HASH_SIZE; i++) {
+			for (xip = &xfrmn->xfrmi[i];
+			     (xi = rtnl_dereference(*xip)) != NULL;
+			     xip = &xi->next)
+				unregister_netdevice_queue(xi->dev, &list);
+		}
+		xi = rtnl_dereference(xfrmn->collect_md_xfrmi);
+		if (xi)
+			unregister_netdevice_queue(xi->dev, &list);
+	}
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+}
+
+static struct pernet_operations xfrmi_net_ops = {
+	.exit_batch = xfrmi_exit_batch_net,
+	.id   = &xfrmi_net_id,
+	.size = sizeof(struct xfrmi_net),
+};
+
+static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = {
+	.handler	=	xfrmi6_rcv,
+	.input_handler	=	xfrmi6_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	10,
+};
+
+static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = {
+	.handler	=	xfrm6_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	10,
+};
+
+static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = {
+	.handler	=	xfrm6_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	10,
+};
+
+#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
+static int xfrmi6_rcv_tunnel(struct sk_buff *skb)
+{
+	const xfrm_address_t *saddr;
+	__be32 spi;
+
+	saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr;
+	spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr);
+
+	return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL);
+}
+
+static struct xfrm6_tunnel xfrmi_ipv6_handler __read_mostly = {
+	.handler	=	xfrmi6_rcv_tunnel,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	2,
+};
+
+static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
+	.handler	=	xfrmi6_rcv_tunnel,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	2,
+};
+#endif
+
+static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = {
+	.handler	=	xfrmi4_rcv,
+	.input_handler	=	xfrmi4_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	10,
+};
+
+static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = {
+	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	10,
+};
+
+static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = {
+	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	10,
+};
+
+#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL)
+static int xfrmi4_rcv_tunnel(struct sk_buff *skb)
+{
+	return xfrm4_rcv_spi(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr);
+}
+
+static struct xfrm_tunnel xfrmi_ipip_handler __read_mostly = {
+	.handler	=	xfrmi4_rcv_tunnel,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	3,
+};
+
+static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = {
+	.handler	=	xfrmi4_rcv_tunnel,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	2,
+};
+#endif
+
+static int __init xfrmi4_init(void)
+{
+	int err;
+
+	err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP);
+	if (err < 0)
+		goto xfrm_proto_esp_failed;
+	err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH);
+	if (err < 0)
+		goto xfrm_proto_ah_failed;
+	err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
+	if (err < 0)
+		goto xfrm_proto_comp_failed;
+#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL)
+	err = xfrm4_tunnel_register(&xfrmi_ipip_handler, AF_INET);
+	if (err < 0)
+		goto xfrm_tunnel_ipip_failed;
+	err = xfrm4_tunnel_register(&xfrmi_ipip6_handler, AF_INET6);
+	if (err < 0)
+		goto xfrm_tunnel_ipip6_failed;
+#endif
+
+	return 0;
+
+#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL)
+xfrm_tunnel_ipip6_failed:
+	xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET);
+xfrm_tunnel_ipip_failed:
+	xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
+#endif
+xfrm_proto_comp_failed:
+	xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH);
+xfrm_proto_ah_failed:
+	xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP);
+xfrm_proto_esp_failed:
+	return err;
+}
+
+static void xfrmi4_fini(void)
+{
+#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL)
+	xfrm4_tunnel_deregister(&xfrmi_ipip6_handler, AF_INET6);
+	xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET);
+#endif
+	xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
+	xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH);
+	xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP);
+}
+
+static int __init xfrmi6_init(void)
+{
+	int err;
+
+	err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP);
+	if (err < 0)
+		goto xfrm_proto_esp_failed;
+	err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH);
+	if (err < 0)
+		goto xfrm_proto_ah_failed;
+	err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
+	if (err < 0)
+		goto xfrm_proto_comp_failed;
+#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
+	err = xfrm6_tunnel_register(&xfrmi_ipv6_handler, AF_INET6);
+	if (err < 0)
+		goto xfrm_tunnel_ipv6_failed;
+	err = xfrm6_tunnel_register(&xfrmi_ip6ip_handler, AF_INET);
+	if (err < 0)
+		goto xfrm_tunnel_ip6ip_failed;
+#endif
+
+	return 0;
+
+#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
+xfrm_tunnel_ip6ip_failed:
+	xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6);
+xfrm_tunnel_ipv6_failed:
+	xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
+#endif
+xfrm_proto_comp_failed:
+	xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH);
+xfrm_proto_ah_failed:
+	xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP);
+xfrm_proto_esp_failed:
+	return err;
+}
+
+static void xfrmi6_fini(void)
+{
+#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
+	xfrm6_tunnel_deregister(&xfrmi_ip6ip_handler, AF_INET);
+	xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6);
+#endif
+	xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
+	xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH);
+	xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP);
+}
+
+static const struct xfrm_if_cb xfrm_if_cb = {
+	.decode_session =	xfrmi_decode_session,
+};
+
+static int __init xfrmi_init(void)
+{
+	const char *msg;
+	int err;
+
+	pr_info("IPsec XFRM device driver\n");
+
+	msg = "tunnel device";
+	err = register_pernet_device(&xfrmi_net_ops);
+	if (err < 0)
+		goto pernet_dev_failed;
+
+	msg = "xfrm4 protocols";
+	err = xfrmi4_init();
+	if (err < 0)
+		goto xfrmi4_failed;
+
+	msg = "xfrm6 protocols";
+	err = xfrmi6_init();
+	if (err < 0)
+		goto xfrmi6_failed;
+
+
+	msg = "netlink interface";
+	err = rtnl_link_register(&xfrmi_link_ops);
+	if (err < 0)
+		goto rtnl_link_failed;
+
+	err = register_xfrm_interface_bpf();
+	if (err < 0)
+		goto kfunc_failed;
+
+	lwtunnel_encap_add_ops(&xfrmi_encap_ops, LWTUNNEL_ENCAP_XFRM);
+
+	xfrm_if_register_cb(&xfrm_if_cb);
+
+	return err;
+
+kfunc_failed:
+	rtnl_link_unregister(&xfrmi_link_ops);
+rtnl_link_failed:
+	xfrmi6_fini();
+xfrmi6_failed:
+	xfrmi4_fini();
+xfrmi4_failed:
+	unregister_pernet_device(&xfrmi_net_ops);
+pernet_dev_failed:
+	pr_err("xfrmi init: failed to register %s\n", msg);
+	return err;
+}
+
+static void __exit xfrmi_fini(void)
+{
+	xfrm_if_unregister_cb();
+	lwtunnel_encap_del_ops(&xfrmi_encap_ops, LWTUNNEL_ENCAP_XFRM);
+	rtnl_link_unregister(&xfrmi_link_ops);
+	xfrmi4_fini();
+	xfrmi6_fini();
+	unregister_pernet_device(&xfrmi_net_ops);
+}
+
+module_init(xfrmi_init);
+module_exit(xfrmi_fini);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("xfrm");
+MODULE_ALIAS_NETDEV("xfrm0");
+MODULE_AUTHOR("Steffen Klassert");
+MODULE_DESCRIPTION("XFRM virtual interface");
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
new file mode 100644
index 0000000000..9c0fa0e178
--- /dev/null
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -0,0 +1,375 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * IP Payload Compression Protocol (IPComp) - RFC3173.
+ *
+ * Copyright (c) 2003 James Morris <jmorris@intercode.com.au>
+ * Copyright (c) 2003-2008 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * Todo:
+ *   - Tunable compression parameters.
+ *   - Compression stats.
+ *   - Adaptive compression.
+ */
+
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/vmalloc.h>
+#include <net/ip.h>
+#include <net/ipcomp.h>
+#include <net/xfrm.h>
+
+struct ipcomp_tfms {
+	struct list_head list;
+	struct crypto_comp * __percpu *tfms;
+	int users;
+};
+
+static DEFINE_MUTEX(ipcomp_resource_mutex);
+static void * __percpu *ipcomp_scratches;
+static int ipcomp_scratch_users;
+static LIST_HEAD(ipcomp_tfms_list);
+
+static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ipcomp_data *ipcd = x->data;
+	const int plen = skb->len;
+	int dlen = IPCOMP_SCRATCH_SIZE;
+	const u8 *start = skb->data;
+	u8 *scratch = *this_cpu_ptr(ipcomp_scratches);
+	struct crypto_comp *tfm = *this_cpu_ptr(ipcd->tfms);
+	int err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen);
+	int len;
+
+	if (err)
+		return err;
+
+	if (dlen < (plen + sizeof(struct ip_comp_hdr)))
+		return -EINVAL;
+
+	len = dlen - plen;
+	if (len > skb_tailroom(skb))
+		len = skb_tailroom(skb);
+
+	__skb_put(skb, len);
+
+	len += plen;
+	skb_copy_to_linear_data(skb, scratch, len);
+
+	while ((scratch += len, dlen -= len) > 0) {
+		skb_frag_t *frag;
+		struct page *page;
+
+		if (WARN_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS))
+			return -EMSGSIZE;
+
+		frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags;
+		page = alloc_page(GFP_ATOMIC);
+
+		if (!page)
+			return -ENOMEM;
+
+		len = PAGE_SIZE;
+		if (dlen < len)
+			len = dlen;
+
+		skb_frag_fill_page_desc(frag, page, 0, len);
+		memcpy(skb_frag_address(frag), scratch, len);
+
+		skb->truesize += len;
+		skb->data_len += len;
+		skb->len += len;
+
+		skb_shinfo(skb)->nr_frags++;
+	}
+
+	return 0;
+}
+
+int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int nexthdr;
+	int err = -ENOMEM;
+	struct ip_comp_hdr *ipch;
+
+	if (skb_linearize_cow(skb))
+		goto out;
+
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* Remove ipcomp header and decompress original payload */
+	ipch = (void *)skb->data;
+	nexthdr = ipch->nexthdr;
+
+	skb->transport_header = skb->network_header + sizeof(*ipch);
+	__skb_pull(skb, sizeof(*ipch));
+	err = ipcomp_decompress(x, skb);
+	if (err)
+		goto out;
+
+	err = nexthdr;
+
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(ipcomp_input);
+
+static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ipcomp_data *ipcd = x->data;
+	const int plen = skb->len;
+	int dlen = IPCOMP_SCRATCH_SIZE;
+	u8 *start = skb->data;
+	struct crypto_comp *tfm;
+	u8 *scratch;
+	int err;
+
+	local_bh_disable();
+	scratch = *this_cpu_ptr(ipcomp_scratches);
+	tfm = *this_cpu_ptr(ipcd->tfms);
+	err = crypto_comp_compress(tfm, start, plen, scratch, &dlen);
+	if (err)
+		goto out;
+
+	if ((dlen + sizeof(struct ip_comp_hdr)) >= plen) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen);
+	local_bh_enable();
+
+	pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr));
+	return 0;
+
+out:
+	local_bh_enable();
+	return err;
+}
+
+int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+	struct ip_comp_hdr *ipch;
+	struct ipcomp_data *ipcd = x->data;
+
+	if (skb->len < ipcd->threshold) {
+		/* Don't bother compressing */
+		goto out_ok;
+	}
+
+	if (skb_linearize_cow(skb))
+		goto out_ok;
+
+	err = ipcomp_compress(x, skb);
+
+	if (err) {
+		goto out_ok;
+	}
+
+	/* Install ipcomp header, convert into ipcomp datagram. */
+	ipch = ip_comp_hdr(skb);
+	ipch->nexthdr = *skb_mac_header(skb);
+	ipch->flags = 0;
+	ipch->cpi = htons((u16 )ntohl(x->id.spi));
+	*skb_mac_header(skb) = IPPROTO_COMP;
+out_ok:
+	skb_push(skb, -skb_network_offset(skb));
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipcomp_output);
+
+static void ipcomp_free_scratches(void)
+{
+	int i;
+	void * __percpu *scratches;
+
+	if (--ipcomp_scratch_users)
+		return;
+
+	scratches = ipcomp_scratches;
+	if (!scratches)
+		return;
+
+	for_each_possible_cpu(i)
+		vfree(*per_cpu_ptr(scratches, i));
+
+	free_percpu(scratches);
+	ipcomp_scratches = NULL;
+}
+
+static void * __percpu *ipcomp_alloc_scratches(void)
+{
+	void * __percpu *scratches;
+	int i;
+
+	if (ipcomp_scratch_users++)
+		return ipcomp_scratches;
+
+	scratches = alloc_percpu(void *);
+	if (!scratches)
+		return NULL;
+
+	ipcomp_scratches = scratches;
+
+	for_each_possible_cpu(i) {
+		void *scratch;
+
+		scratch = vmalloc_node(IPCOMP_SCRATCH_SIZE, cpu_to_node(i));
+		if (!scratch)
+			return NULL;
+		*per_cpu_ptr(scratches, i) = scratch;
+	}
+
+	return scratches;
+}
+
+static void ipcomp_free_tfms(struct crypto_comp * __percpu *tfms)
+{
+	struct ipcomp_tfms *pos;
+	int cpu;
+
+	list_for_each_entry(pos, &ipcomp_tfms_list, list) {
+		if (pos->tfms == tfms)
+			break;
+	}
+
+	WARN_ON(list_entry_is_head(pos, &ipcomp_tfms_list, list));
+
+	if (--pos->users)
+		return;
+
+	list_del(&pos->list);
+	kfree(pos);
+
+	if (!tfms)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct crypto_comp *tfm = *per_cpu_ptr(tfms, cpu);
+		crypto_free_comp(tfm);
+	}
+	free_percpu(tfms);
+}
+
+static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name)
+{
+	struct ipcomp_tfms *pos;
+	struct crypto_comp * __percpu *tfms;
+	int cpu;
+
+
+	list_for_each_entry(pos, &ipcomp_tfms_list, list) {
+		struct crypto_comp *tfm;
+
+		/* This can be any valid CPU ID so we don't need locking. */
+		tfm = this_cpu_read(*pos->tfms);
+
+		if (!strcmp(crypto_comp_name(tfm), alg_name)) {
+			pos->users++;
+			return pos->tfms;
+		}
+	}
+
+	pos = kmalloc(sizeof(*pos), GFP_KERNEL);
+	if (!pos)
+		return NULL;
+
+	pos->users = 1;
+	INIT_LIST_HEAD(&pos->list);
+	list_add(&pos->list, &ipcomp_tfms_list);
+
+	pos->tfms = tfms = alloc_percpu(struct crypto_comp *);
+	if (!tfms)
+		goto error;
+
+	for_each_possible_cpu(cpu) {
+		struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0,
+							    CRYPTO_ALG_ASYNC);
+		if (IS_ERR(tfm))
+			goto error;
+		*per_cpu_ptr(tfms, cpu) = tfm;
+	}
+
+	return tfms;
+
+error:
+	ipcomp_free_tfms(tfms);
+	return NULL;
+}
+
+static void ipcomp_free_data(struct ipcomp_data *ipcd)
+{
+	if (ipcd->tfms)
+		ipcomp_free_tfms(ipcd->tfms);
+	ipcomp_free_scratches();
+}
+
+void ipcomp_destroy(struct xfrm_state *x)
+{
+	struct ipcomp_data *ipcd = x->data;
+	if (!ipcd)
+		return;
+	xfrm_state_delete_tunnel(x);
+	mutex_lock(&ipcomp_resource_mutex);
+	ipcomp_free_data(ipcd);
+	mutex_unlock(&ipcomp_resource_mutex);
+	kfree(ipcd);
+}
+EXPORT_SYMBOL_GPL(ipcomp_destroy);
+
+int ipcomp_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack)
+{
+	int err;
+	struct ipcomp_data *ipcd;
+	struct xfrm_algo_desc *calg_desc;
+
+	err = -EINVAL;
+	if (!x->calg) {
+		NL_SET_ERR_MSG(extack, "Missing required compression algorithm");
+		goto out;
+	}
+
+	if (x->encap) {
+		NL_SET_ERR_MSG(extack, "IPComp is not compatible with encapsulation");
+		goto out;
+	}
+
+	err = -ENOMEM;
+	ipcd = kzalloc(sizeof(*ipcd), GFP_KERNEL);
+	if (!ipcd)
+		goto out;
+
+	mutex_lock(&ipcomp_resource_mutex);
+	if (!ipcomp_alloc_scratches())
+		goto error;
+
+	ipcd->tfms = ipcomp_alloc_tfms(x->calg->alg_name);
+	if (!ipcd->tfms)
+		goto error;
+	mutex_unlock(&ipcomp_resource_mutex);
+
+	calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0);
+	BUG_ON(!calg_desc);
+	ipcd->threshold = calg_desc->uinfo.comp.threshold;
+	x->data = ipcd;
+	err = 0;
+out:
+	return err;
+
+error:
+	ipcomp_free_data(ipcd);
+	mutex_unlock(&ipcomp_resource_mutex);
+	kfree(ipcd);
+	goto out;
+}
+EXPORT_SYMBOL_GPL(ipcomp_init_state);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) - RFC3173");
+MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
new file mode 100644
index 0000000000..662c83beb3
--- /dev/null
+++ b/net/xfrm/xfrm_output.c
@@ -0,0 +1,908 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * xfrm_output.c - Common IPsec encapsulation code.
+ *
+ * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/netfilter.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <net/dst.h>
+#include <net/gso.h>
+#include <net/icmp.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_route.h>
+#include <net/ipv6_stubs.h>
+#endif
+
+#include "xfrm_inout.h"
+
+static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);
+static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
+
+static int xfrm_skb_check_space(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	int nhead = dst->header_len + LL_RESERVED_SPACE(dst->dev)
+		- skb_headroom(skb);
+	int ntail = dst->dev->needed_tailroom - skb_tailroom(skb);
+
+	if (nhead <= 0) {
+		if (ntail <= 0)
+			return 0;
+		nhead = 0;
+	} else if (ntail < 0)
+		ntail = 0;
+
+	return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
+}
+
+/* Children define the path of the packet through the
+ * Linux networking.  Thus, destinations are stackable.
+ */
+
+static struct dst_entry *skb_dst_pop(struct sk_buff *skb)
+{
+	struct dst_entry *child = dst_clone(xfrm_dst_child(skb_dst(skb)));
+
+	skb_dst_drop(skb);
+	return child;
+}
+
+/* Add encapsulation header.
+ *
+ * The IP header will be moved forward to make space for the encapsulation
+ * header.
+ */
+static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct iphdr *iph = ip_hdr(skb);
+	int ihl = iph->ihl * 4;
+
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->mac_header = skb->network_header +
+			  offsetof(struct iphdr, protocol);
+	skb->transport_header = skb->network_header + ihl;
+	__skb_pull(skb, ihl);
+	memmove(skb_network_header(skb), iph, ihl);
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+static int mip6_rthdr_offset(struct sk_buff *skb, u8 **nexthdr, int type)
+{
+	const unsigned char *nh = skb_network_header(skb);
+	unsigned int offset = sizeof(struct ipv6hdr);
+	unsigned int packet_len;
+	int found_rhdr = 0;
+
+	packet_len = skb_tail_pointer(skb) - nh;
+	*nexthdr = &ipv6_hdr(skb)->nexthdr;
+
+	while (offset <= packet_len) {
+		struct ipv6_opt_hdr *exthdr;
+
+		switch (**nexthdr) {
+		case NEXTHDR_HOP:
+			break;
+		case NEXTHDR_ROUTING:
+			if (type == IPPROTO_ROUTING && offset + 3 <= packet_len) {
+				struct ipv6_rt_hdr *rt;
+
+				rt = (struct ipv6_rt_hdr *)(nh + offset);
+				if (rt->type != 0)
+					return offset;
+			}
+			found_rhdr = 1;
+			break;
+		case NEXTHDR_DEST:
+			/* HAO MUST NOT appear more than once.
+			 * XXX: It is better to try to find by the end of
+			 * XXX: packet if HAO exists.
+			 */
+			if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) {
+				net_dbg_ratelimited("mip6: hao exists already, override\n");
+				return offset;
+			}
+
+			if (found_rhdr)
+				return offset;
+
+			break;
+		default:
+			return offset;
+		}
+
+		if (offset + sizeof(struct ipv6_opt_hdr) > packet_len)
+			return -EINVAL;
+
+		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
+						 offset);
+		offset += ipv6_optlen(exthdr);
+		if (offset > IPV6_MAXPLEN)
+			return -EINVAL;
+		*nexthdr = &exthdr->nexthdr;
+	}
+
+	return -EINVAL;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int xfrm6_hdr_offset(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr)
+{
+	switch (x->type->proto) {
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+	case IPPROTO_DSTOPTS:
+	case IPPROTO_ROUTING:
+		return mip6_rthdr_offset(skb, prevhdr, x->type->proto);
+#endif
+	default:
+		break;
+	}
+
+	return ip6_find_1stfragopt(skb, prevhdr);
+}
+#endif
+
+/* Add encapsulation header.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the encapsulation header.
+ */
+static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct ipv6hdr *iph;
+	u8 *prevhdr;
+	int hdr_len;
+
+	iph = ipv6_hdr(skb);
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+	hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr);
+	if (hdr_len < 0)
+		return hdr_len;
+	skb_set_mac_header(skb,
+			   (prevhdr - x->props.header_len) - skb->data);
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->transport_header = skb->network_header + hdr_len;
+	__skb_pull(skb, hdr_len);
+	memmove(ipv6_hdr(skb), iph, hdr_len);
+	return 0;
+#else
+	WARN_ON_ONCE(1);
+	return -EAFNOSUPPORT;
+#endif
+}
+
+/* Add route optimization header space.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the route optimization header.
+ */
+static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct ipv6hdr *iph;
+	u8 *prevhdr;
+	int hdr_len;
+
+	iph = ipv6_hdr(skb);
+
+	hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr);
+	if (hdr_len < 0)
+		return hdr_len;
+	skb_set_mac_header(skb,
+			   (prevhdr - x->props.header_len) - skb->data);
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->transport_header = skb->network_header + hdr_len;
+	__skb_pull(skb, hdr_len);
+	memmove(ipv6_hdr(skb), iph, hdr_len);
+
+	return 0;
+#else
+	WARN_ON_ONCE(1);
+	return -EAFNOSUPPORT;
+#endif
+}
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
+ */
+static int xfrm4_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ip_beet_phdr *ph;
+	struct iphdr *top_iph;
+	int hdrlen, optlen;
+
+	hdrlen = 0;
+	optlen = XFRM_MODE_SKB_CB(skb)->optlen;
+	if (unlikely(optlen))
+		hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4);
+
+	skb_set_network_header(skb, -x->props.header_len - hdrlen +
+			       (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph)));
+	if (x->sel.family != AF_INET6)
+		skb->network_header += IPV4_BEET_PHMAXLEN;
+	skb->mac_header = skb->network_header +
+			  offsetof(struct iphdr, protocol);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
+
+	xfrm4_beet_make_header(skb);
+
+	ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen);
+
+	top_iph = ip_hdr(skb);
+
+	if (unlikely(optlen)) {
+		if (WARN_ON(optlen < 0))
+			return -EINVAL;
+
+		ph->padlen = 4 - (optlen & 4);
+		ph->hdrlen = optlen / 8;
+		ph->nexthdr = top_iph->protocol;
+		if (ph->padlen)
+			memset(ph + 1, IPOPT_NOP, ph->padlen);
+
+		top_iph->protocol = IPPROTO_BEETPH;
+		top_iph->ihl = sizeof(struct iphdr) / 4;
+	}
+
+	top_iph->saddr = x->props.saddr.a4;
+	top_iph->daddr = x->id.daddr.a4;
+
+	return 0;
+}
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per RFC 2401.
+ */
+static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+	bool small_ipv6 = (skb->protocol == htons(ETH_P_IPV6)) && (skb->len <= IPV6_MIN_MTU);
+	struct dst_entry *dst = skb_dst(skb);
+	struct iphdr *top_iph;
+	int flags;
+
+	skb_set_inner_network_header(skb, skb_network_offset(skb));
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->mac_header = skb->network_header +
+			  offsetof(struct iphdr, protocol);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
+	top_iph = ip_hdr(skb);
+
+	top_iph->ihl = 5;
+	top_iph->version = 4;
+
+	top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
+
+	/* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
+	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
+		top_iph->tos = 0;
+	else
+		top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
+	top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
+					    XFRM_MODE_SKB_CB(skb)->tos);
+
+	flags = x->props.flags;
+	if (flags & XFRM_STATE_NOECN)
+		IP_ECN_clear(top_iph);
+
+	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) || small_ipv6 ?
+		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
+
+	top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst));
+
+	top_iph->saddr = x->props.saddr.a4;
+	top_iph->daddr = x->id.daddr.a4;
+	ip_select_ident(dev_net(dst->dev), skb, NULL);
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int xfrm6_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct ipv6hdr *top_iph;
+	int dsfield;
+
+	skb_set_inner_network_header(skb, skb_network_offset(skb));
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->mac_header = skb->network_header +
+			  offsetof(struct ipv6hdr, nexthdr);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
+	top_iph = ipv6_hdr(skb);
+
+	top_iph->version = 6;
+
+	memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
+	       sizeof(top_iph->flow_lbl));
+	top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);
+
+	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
+		dsfield = 0;
+	else
+		dsfield = XFRM_MODE_SKB_CB(skb)->tos;
+	dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos);
+	if (x->props.flags & XFRM_STATE_NOECN)
+		dsfield &= ~INET_ECN_MASK;
+	ipv6_change_dsfield(top_iph, 0, dsfield);
+	top_iph->hop_limit = ip6_dst_hoplimit(xfrm_dst_child(dst));
+	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
+	return 0;
+}
+
+static int xfrm6_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ipv6hdr *top_iph;
+	struct ip_beet_phdr *ph;
+	int optlen, hdr_len;
+
+	hdr_len = 0;
+	optlen = XFRM_MODE_SKB_CB(skb)->optlen;
+	if (unlikely(optlen))
+		hdr_len += IPV4_BEET_PHMAXLEN - (optlen & 4);
+
+	skb_set_network_header(skb, -x->props.header_len - hdr_len);
+	if (x->sel.family != AF_INET6)
+		skb->network_header += IPV4_BEET_PHMAXLEN;
+	skb->mac_header = skb->network_header +
+			  offsetof(struct ipv6hdr, nexthdr);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
+	ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdr_len);
+
+	xfrm6_beet_make_header(skb);
+
+	top_iph = ipv6_hdr(skb);
+	if (unlikely(optlen)) {
+		if (WARN_ON(optlen < 0))
+			return -EINVAL;
+
+		ph->padlen = 4 - (optlen & 4);
+		ph->hdrlen = optlen / 8;
+		ph->nexthdr = top_iph->nexthdr;
+		if (ph->padlen)
+			memset(ph + 1, IPOPT_NOP, ph->padlen);
+
+		top_iph->nexthdr = IPPROTO_BEETPH;
+	}
+
+	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
+	return 0;
+}
+#endif
+
+/* Add encapsulation header.
+ *
+ * On exit, the transport header will be set to the start of the
+ * encapsulation header to be filled in by x->type->output and the mac
+ * header will be set to the nextheader (protocol for IPv4) field of the
+ * extension header directly preceding the encapsulation header, or in
+ * its absence, that of the top IP header.
+ * The value of the network header will always point to the top IP header
+ * while skb->data will point to the payload.
+ */
+static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+
+	err = xfrm_inner_extract_output(x, skb);
+	if (err)
+		return err;
+
+	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
+	skb->protocol = htons(ETH_P_IP);
+
+	switch (x->props.mode) {
+	case XFRM_MODE_BEET:
+		return xfrm4_beet_encap_add(x, skb);
+	case XFRM_MODE_TUNNEL:
+		return xfrm4_tunnel_encap_add(x, skb);
+	}
+
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
+}
+
+static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	int err;
+
+	err = xfrm_inner_extract_output(x, skb);
+	if (err)
+		return err;
+
+	skb->ignore_df = 1;
+	skb->protocol = htons(ETH_P_IPV6);
+
+	switch (x->props.mode) {
+	case XFRM_MODE_BEET:
+		return xfrm6_beet_encap_add(x, skb);
+	case XFRM_MODE_TUNNEL:
+		return xfrm6_tunnel_encap_add(x, skb);
+	default:
+		WARN_ON_ONCE(1);
+		return -EOPNOTSUPP;
+	}
+#endif
+	WARN_ON_ONCE(1);
+	return -EAFNOSUPPORT;
+}
+
+static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->props.mode) {
+	case XFRM_MODE_BEET:
+	case XFRM_MODE_TUNNEL:
+		if (x->props.family == AF_INET)
+			return xfrm4_prepare_output(x, skb);
+		if (x->props.family == AF_INET6)
+			return xfrm6_prepare_output(x, skb);
+		break;
+	case XFRM_MODE_TRANSPORT:
+		if (x->props.family == AF_INET)
+			return xfrm4_transport_output(x, skb);
+		if (x->props.family == AF_INET6)
+			return xfrm6_transport_output(x, skb);
+		break;
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+		if (x->props.family == AF_INET6)
+			return xfrm6_ro_output(x, skb);
+		WARN_ON_ONCE(1);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+#if IS_ENABLED(CONFIG_NET_PKTGEN)
+int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	return xfrm_outer_mode_output(x, skb);
+}
+EXPORT_SYMBOL_GPL(pktgen_xfrm_outer_mode_output);
+#endif
+
+static int xfrm_output_one(struct sk_buff *skb, int err)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x = dst->xfrm;
+	struct net *net = xs_net(x);
+
+	if (err <= 0 || x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+		goto resume;
+
+	do {
+		err = xfrm_skb_check_space(skb);
+		if (err) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			goto error_nolock;
+		}
+
+		skb->mark = xfrm_smark_get(skb->mark, x);
+
+		err = xfrm_outer_mode_output(x, skb);
+		if (err) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
+			goto error_nolock;
+		}
+
+		spin_lock_bh(&x->lock);
+
+		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID);
+			err = -EINVAL;
+			goto error;
+		}
+
+		err = xfrm_state_check_expire(x);
+		if (err) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED);
+			goto error;
+		}
+
+		err = xfrm_replay_overflow(x, skb);
+		if (err) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
+			goto error;
+		}
+
+		x->curlft.bytes += skb->len;
+		x->curlft.packets++;
+		x->lastused = ktime_get_real_seconds();
+
+		spin_unlock_bh(&x->lock);
+
+		skb_dst_force(skb);
+		if (!skb_dst(skb)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			err = -EHOSTUNREACH;
+			goto error_nolock;
+		}
+
+		if (xfrm_offload(skb)) {
+			x->type_offload->encap(x, skb);
+		} else {
+			/* Inner headers are invalid now. */
+			skb->encapsulation = 0;
+
+			err = x->type->output(x, skb);
+			if (err == -EINPROGRESS)
+				goto out;
+		}
+
+resume:
+		if (err) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
+			goto error_nolock;
+		}
+
+		dst = skb_dst_pop(skb);
+		if (!dst) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			err = -EHOSTUNREACH;
+			goto error_nolock;
+		}
+		skb_dst_set(skb, dst);
+		x = dst->xfrm;
+	} while (x && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL));
+
+	return 0;
+
+error:
+	spin_unlock_bh(&x->lock);
+error_nolock:
+	kfree_skb(skb);
+out:
+	return err;
+}
+
+int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err)
+{
+	struct net *net = xs_net(skb_dst(skb)->xfrm);
+
+	while (likely((err = xfrm_output_one(skb, err)) == 0)) {
+		nf_reset_ct(skb);
+
+		err = skb_dst(skb)->ops->local_out(net, sk, skb);
+		if (unlikely(err != 1))
+			goto out;
+
+		if (!skb_dst(skb)->xfrm)
+			return dst_output(net, sk, skb);
+
+		err = nf_hook(skb_dst(skb)->ops->family,
+			      NF_INET_POST_ROUTING, net, sk, skb,
+			      NULL, skb_dst(skb)->dev, xfrm_output2);
+		if (unlikely(err != 1))
+			goto out;
+	}
+
+	if (err == -EINPROGRESS)
+		err = 0;
+
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_output_resume);
+
+static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	return xfrm_output_resume(sk, skb, 1);
+}
+
+static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *segs, *nskb;
+
+	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET);
+	BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_GSO_CB_OFFSET);
+	segs = skb_gso_segment(skb, 0);
+	kfree_skb(skb);
+	if (IS_ERR(segs))
+		return PTR_ERR(segs);
+	if (segs == NULL)
+		return -EINVAL;
+
+	skb_list_walk_safe(segs, segs, nskb) {
+		int err;
+
+		skb_mark_not_on_list(segs);
+		err = xfrm_output2(net, sk, segs);
+
+		if (unlikely(err)) {
+			kfree_skb_list(nskb);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+/* For partial checksum offload, the outer header checksum is calculated
+ * by software and the inner header checksum is calculated by hardware.
+ * This requires hardware to know the inner packet type to calculate
+ * the inner header checksum. Save inner ip protocol here to avoid
+ * traversing the packet in the vendor's xmit code.
+ * For IPsec tunnel mode save the ip protocol from the IP header of the
+ * plain text packet. Otherwise If the encap type is IPIP, just save
+ * skb->inner_ipproto in any other case get the ip protocol from the IP
+ * header.
+ */
+static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	const struct ethhdr *eth;
+
+	if (!xo)
+		return;
+
+	if (x->outer_mode.encap == XFRM_MODE_TUNNEL) {
+		switch (x->outer_mode.family) {
+		case AF_INET:
+			xo->inner_ipproto = ip_hdr(skb)->protocol;
+			break;
+		case AF_INET6:
+			xo->inner_ipproto = ipv6_hdr(skb)->nexthdr;
+			break;
+		default:
+			break;
+		}
+
+		return;
+	}
+
+	/* non-Tunnel Mode */
+	if (!skb->encapsulation)
+		return;
+
+	if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) {
+		xo->inner_ipproto = skb->inner_ipproto;
+		return;
+	}
+
+	if (skb->inner_protocol_type != ENCAP_TYPE_ETHER)
+		return;
+
+	eth = (struct ethhdr *)skb_inner_mac_header(skb);
+
+	switch (ntohs(eth->h_proto)) {
+	case ETH_P_IPV6:
+		xo->inner_ipproto = inner_ipv6_hdr(skb)->nexthdr;
+		break;
+	case ETH_P_IP:
+		xo->inner_ipproto = inner_ip_hdr(skb)->protocol;
+		break;
+	}
+}
+
+int xfrm_output(struct sock *sk, struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+	int err;
+
+	switch (x->outer_mode.family) {
+	case AF_INET:
+		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
+		break;
+	case AF_INET6:
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
+		IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
+		break;
+	}
+
+	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) {
+		if (!xfrm_dev_offload_ok(skb, x)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			kfree_skb(skb);
+			return -EHOSTUNREACH;
+		}
+
+		return xfrm_output_resume(sk, skb, 0);
+	}
+
+	secpath_reset(skb);
+
+	if (xfrm_dev_offload_ok(skb, x)) {
+		struct sec_path *sp;
+
+		sp = secpath_set(skb);
+		if (!sp) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+
+		sp->olen++;
+		sp->xvec[sp->len++] = x;
+		xfrm_state_hold(x);
+
+		xfrm_get_inner_ipproto(skb, x);
+		skb->encapsulation = 1;
+
+		if (skb_is_gso(skb)) {
+			if (skb->inner_protocol)
+				return xfrm_output_gso(net, sk, skb);
+
+			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			goto out;
+		}
+
+		if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
+			goto out;
+	} else {
+		if (skb_is_gso(skb))
+			return xfrm_output_gso(net, sk, skb);
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		err = skb_checksum_help(skb);
+		if (err) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			kfree_skb(skb);
+			return err;
+		}
+	}
+
+out:
+	return xfrm_output2(net, sk, skb);
+}
+EXPORT_SYMBOL_GPL(xfrm_output);
+
+static int xfrm4_tunnel_check_size(struct sk_buff *skb)
+{
+	int mtu, ret = 0;
+
+	if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE)
+		goto out;
+
+	if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->ignore_df)
+		goto out;
+
+	mtu = dst_mtu(skb_dst(skb));
+	if ((!skb_is_gso(skb) && skb->len > mtu) ||
+	    (skb_is_gso(skb) &&
+	     !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) {
+		skb->protocol = htons(ETH_P_IP);
+
+		if (skb->sk)
+			xfrm_local_error(skb, mtu);
+		else
+			icmp_send(skb, ICMP_DEST_UNREACH,
+				  ICMP_FRAG_NEEDED, htonl(mtu));
+		ret = -EMSGSIZE;
+	}
+out:
+	return ret;
+}
+
+static int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+
+	if (x->outer_mode.encap == XFRM_MODE_BEET &&
+	    ip_is_fragment(ip_hdr(skb))) {
+		net_warn_ratelimited("BEET mode doesn't support inner IPv4 fragments\n");
+		return -EAFNOSUPPORT;
+	}
+
+	err = xfrm4_tunnel_check_size(skb);
+	if (err)
+		return err;
+
+	XFRM_MODE_SKB_CB(skb)->protocol = ip_hdr(skb)->protocol;
+
+	xfrm4_extract_header(skb);
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int xfrm6_tunnel_check_size(struct sk_buff *skb)
+{
+	int mtu, ret = 0;
+	struct dst_entry *dst = skb_dst(skb);
+
+	if (skb->ignore_df)
+		goto out;
+
+	mtu = dst_mtu(dst);
+	if (mtu < IPV6_MIN_MTU)
+		mtu = IPV6_MIN_MTU;
+
+	if ((!skb_is_gso(skb) && skb->len > mtu) ||
+	    (skb_is_gso(skb) &&
+	     !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) {
+		skb->dev = dst->dev;
+		skb->protocol = htons(ETH_P_IPV6);
+
+		if (xfrm6_local_dontfrag(skb->sk))
+			ipv6_stub->xfrm6_local_rxpmtu(skb, mtu);
+		else if (skb->sk)
+			xfrm_local_error(skb, mtu);
+		else
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		ret = -EMSGSIZE;
+	}
+out:
+	return ret;
+}
+#endif
+
+static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	int err;
+
+	err = xfrm6_tunnel_check_size(skb);
+	if (err)
+		return err;
+
+	XFRM_MODE_SKB_CB(skb)->protocol = ipv6_hdr(skb)->nexthdr;
+
+	xfrm6_extract_header(skb);
+	return 0;
+#else
+	WARN_ON_ONCE(1);
+	return -EAFNOSUPPORT;
+#endif
+}
+
+static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		return xfrm4_extract_output(x, skb);
+	case htons(ETH_P_IPV6):
+		return xfrm6_extract_output(x, skb);
+	}
+
+	return -EAFNOSUPPORT;
+}
+
+void xfrm_local_error(struct sk_buff *skb, int mtu)
+{
+	unsigned int proto;
+	struct xfrm_state_afinfo *afinfo;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		proto = AF_INET;
+	else if (skb->protocol == htons(ETH_P_IPV6) &&
+		 skb->sk->sk_family == AF_INET6)
+		proto = AF_INET6;
+	else
+		return;
+
+	afinfo = xfrm_state_get_afinfo(proto);
+	if (afinfo) {
+		afinfo->local_error(skb, mtu);
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL_GPL(xfrm_local_error);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
new file mode 100644
index 0000000000..d24b4d4f62
--- /dev/null
+++ b/net/xfrm/xfrm_policy.c
@@ -0,0 +1,4584 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * xfrm_policy.c
+ *
+ * Changes:
+ *	Mitsuru KANDA @USAGI
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * 		IPv6 support
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	YOSHIFUJI Hideaki
+ * 		Split up af-specific portion
+ *	Derek Atkins <derek@ihtfp.com>		Add the post_input processor
+ *
+ */
+
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/netfilter.h>
+#include <linux/module.h>
+#include <linux/cache.h>
+#include <linux/cpu.h>
+#include <linux/audit.h>
+#include <linux/rhashtable.h>
+#include <linux/if_tunnel.h>
+#include <net/dst.h>
+#include <net/flow.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+#include <net/ip.h>
+#include <net/gre.h>
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+#include <net/mip6.h>
+#endif
+#ifdef CONFIG_XFRM_STATISTICS
+#include <net/snmp.h>
+#endif
+#ifdef CONFIG_XFRM_ESPINTCP
+#include <net/espintcp.h>
+#endif
+
+#include "xfrm_hash.h"
+
+#define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10))
+#define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
+#define XFRM_MAX_QUEUE_LEN	100
+
+struct xfrm_flo {
+	struct dst_entry *dst_orig;
+	u8 flags;
+};
+
+/* prefixes smaller than this are stored in lists, not trees. */
+#define INEXACT_PREFIXLEN_IPV4	16
+#define INEXACT_PREFIXLEN_IPV6	48
+
+struct xfrm_pol_inexact_node {
+	struct rb_node node;
+	union {
+		xfrm_address_t addr;
+		struct rcu_head rcu;
+	};
+	u8 prefixlen;
+
+	struct rb_root root;
+
+	/* the policies matching this node, can be empty list */
+	struct hlist_head hhead;
+};
+
+/* xfrm inexact policy search tree:
+ * xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
+ *  |
+ * +---- root_d: sorted by daddr:prefix
+ * |                 |
+ * |        xfrm_pol_inexact_node
+ * |                 |
+ * |                 +- root: sorted by saddr/prefix
+ * |                 |              |
+ * |                 |         xfrm_pol_inexact_node
+ * |                 |              |
+ * |                 |              + root: unused
+ * |                 |              |
+ * |                 |              + hhead: saddr:daddr policies
+ * |                 |
+ * |                 +- coarse policies and all any:daddr policies
+ * |
+ * +---- root_s: sorted by saddr:prefix
+ * |                 |
+ * |        xfrm_pol_inexact_node
+ * |                 |
+ * |                 + root: unused
+ * |                 |
+ * |                 + hhead: saddr:any policies
+ * |
+ * +---- coarse policies and all any:any policies
+ *
+ * Lookups return four candidate lists:
+ * 1. any:any list from top-level xfrm_pol_inexact_bin
+ * 2. any:daddr list from daddr tree
+ * 3. saddr:daddr list from 2nd level daddr tree
+ * 4. saddr:any list from saddr tree
+ *
+ * This result set then needs to be searched for the policy with
+ * the lowest priority.  If two results have same prio, youngest one wins.
+ */
+
+struct xfrm_pol_inexact_key {
+	possible_net_t net;
+	u32 if_id;
+	u16 family;
+	u8 dir, type;
+};
+
+struct xfrm_pol_inexact_bin {
+	struct xfrm_pol_inexact_key k;
+	struct rhash_head head;
+	/* list containing '*:*' policies */
+	struct hlist_head hhead;
+
+	seqcount_spinlock_t count;
+	/* tree sorted by daddr/prefix */
+	struct rb_root root_d;
+
+	/* tree sorted by saddr/prefix */
+	struct rb_root root_s;
+
+	/* slow path below */
+	struct list_head inexact_bins;
+	struct rcu_head rcu;
+};
+
+enum xfrm_pol_inexact_candidate_type {
+	XFRM_POL_CAND_BOTH,
+	XFRM_POL_CAND_SADDR,
+	XFRM_POL_CAND_DADDR,
+	XFRM_POL_CAND_ANY,
+
+	XFRM_POL_CAND_MAX,
+};
+
+struct xfrm_pol_inexact_candidates {
+	struct hlist_head *res[XFRM_POL_CAND_MAX];
+};
+
+static DEFINE_SPINLOCK(xfrm_if_cb_lock);
+static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
+
+static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
+static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
+						__read_mostly;
+
+static struct kmem_cache *xfrm_dst_cache __ro_after_init;
+
+static struct rhashtable xfrm_policy_inexact_table;
+static const struct rhashtable_params xfrm_pol_inexact_params;
+
+static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr);
+static int stale_bundle(struct dst_entry *dst);
+static int xfrm_bundle_ok(struct xfrm_dst *xdst);
+static void xfrm_policy_queue_process(struct timer_list *t);
+
+static void __xfrm_policy_link(struct xfrm_policy *pol, int dir);
+static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
+						int dir);
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir,
+			   u32 if_id);
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup_rcu(struct net *net,
+			       u8 type, u16 family, u8 dir, u32 if_id);
+static struct xfrm_policy *
+xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
+			bool excl);
+static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
+					    struct xfrm_policy *policy);
+
+static bool
+xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
+				    struct xfrm_pol_inexact_bin *b,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr);
+
+static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy)
+{
+	return refcount_inc_not_zero(&policy->refcnt);
+}
+
+static inline bool
+__xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
+{
+	const struct flowi4 *fl4 = &fl->u.ip4;
+
+	return  addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) &&
+		addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) &&
+		!((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) &&
+		(fl4->flowi4_proto == sel->proto || !sel->proto) &&
+		(fl4->flowi4_oif == sel->ifindex || !sel->ifindex);
+}
+
+static inline bool
+__xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
+{
+	const struct flowi6 *fl6 = &fl->u.ip6;
+
+	return  addr_match(&fl6->daddr, &sel->daddr, sel->prefixlen_d) &&
+		addr_match(&fl6->saddr, &sel->saddr, sel->prefixlen_s) &&
+		!((xfrm_flowi_dport(fl, &fl6->uli) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl, &fl6->uli) ^ sel->sport) & sel->sport_mask) &&
+		(fl6->flowi6_proto == sel->proto || !sel->proto) &&
+		(fl6->flowi6_oif == sel->ifindex || !sel->ifindex);
+}
+
+bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl,
+			 unsigned short family)
+{
+	switch (family) {
+	case AF_INET:
+		return __xfrm4_selector_match(sel, fl);
+	case AF_INET6:
+		return __xfrm6_selector_match(sel, fl);
+	}
+	return false;
+}
+
+static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family)
+{
+	const struct xfrm_policy_afinfo *afinfo;
+
+	if (unlikely(family >= ARRAY_SIZE(xfrm_policy_afinfo)))
+		return NULL;
+	rcu_read_lock();
+	afinfo = rcu_dereference(xfrm_policy_afinfo[family]);
+	if (unlikely(!afinfo))
+		rcu_read_unlock();
+	return afinfo;
+}
+
+/* Called with rcu_read_lock(). */
+static const struct xfrm_if_cb *xfrm_if_get_cb(void)
+{
+	return rcu_dereference(xfrm_if_cb);
+}
+
+struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr,
+				    int family, u32 mark)
+{
+	const struct xfrm_policy_afinfo *afinfo;
+	struct dst_entry *dst;
+
+	afinfo = xfrm_policy_get_afinfo(family);
+	if (unlikely(afinfo == NULL))
+		return ERR_PTR(-EAFNOSUPPORT);
+
+	dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr, mark);
+
+	rcu_read_unlock();
+
+	return dst;
+}
+EXPORT_SYMBOL(__xfrm_dst_lookup);
+
+static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
+						int tos, int oif,
+						xfrm_address_t *prev_saddr,
+						xfrm_address_t *prev_daddr,
+						int family, u32 mark)
+{
+	struct net *net = xs_net(x);
+	xfrm_address_t *saddr = &x->props.saddr;
+	xfrm_address_t *daddr = &x->id.daddr;
+	struct dst_entry *dst;
+
+	if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) {
+		saddr = x->coaddr;
+		daddr = prev_daddr;
+	}
+	if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) {
+		saddr = prev_saddr;
+		daddr = x->coaddr;
+	}
+
+	dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family, mark);
+
+	if (!IS_ERR(dst)) {
+		if (prev_saddr != saddr)
+			memcpy(prev_saddr, saddr,  sizeof(*prev_saddr));
+		if (prev_daddr != daddr)
+			memcpy(prev_daddr, daddr,  sizeof(*prev_daddr));
+	}
+
+	return dst;
+}
+
+static inline unsigned long make_jiffies(long secs)
+{
+	if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ)
+		return MAX_SCHEDULE_TIMEOUT-1;
+	else
+		return secs*HZ;
+}
+
+static void xfrm_policy_timer(struct timer_list *t)
+{
+	struct xfrm_policy *xp = from_timer(xp, t, timer);
+	time64_t now = ktime_get_real_seconds();
+	time64_t next = TIME64_MAX;
+	int warn = 0;
+	int dir;
+
+	read_lock(&xp->lock);
+
+	if (unlikely(xp->walk.dead))
+		goto out;
+
+	dir = xfrm_policy_id2dir(xp->index);
+
+	if (xp->lft.hard_add_expires_seconds) {
+		time64_t tmo = xp->lft.hard_add_expires_seconds +
+			xp->curlft.add_time - now;
+		if (tmo <= 0)
+			goto expired;
+		if (tmo < next)
+			next = tmo;
+	}
+	if (xp->lft.hard_use_expires_seconds) {
+		time64_t tmo = xp->lft.hard_use_expires_seconds +
+			(READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now;
+		if (tmo <= 0)
+			goto expired;
+		if (tmo < next)
+			next = tmo;
+	}
+	if (xp->lft.soft_add_expires_seconds) {
+		time64_t tmo = xp->lft.soft_add_expires_seconds +
+			xp->curlft.add_time - now;
+		if (tmo <= 0) {
+			warn = 1;
+			tmo = XFRM_KM_TIMEOUT;
+		}
+		if (tmo < next)
+			next = tmo;
+	}
+	if (xp->lft.soft_use_expires_seconds) {
+		time64_t tmo = xp->lft.soft_use_expires_seconds +
+			(READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now;
+		if (tmo <= 0) {
+			warn = 1;
+			tmo = XFRM_KM_TIMEOUT;
+		}
+		if (tmo < next)
+			next = tmo;
+	}
+
+	if (warn)
+		km_policy_expired(xp, dir, 0, 0);
+	if (next != TIME64_MAX &&
+	    !mod_timer(&xp->timer, jiffies + make_jiffies(next)))
+		xfrm_pol_hold(xp);
+
+out:
+	read_unlock(&xp->lock);
+	xfrm_pol_put(xp);
+	return;
+
+expired:
+	read_unlock(&xp->lock);
+	if (!xfrm_policy_delete(xp, dir))
+		km_policy_expired(xp, dir, 1, 0);
+	xfrm_pol_put(xp);
+}
+
+/* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2
+ * SPD calls.
+ */
+
+struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
+{
+	struct xfrm_policy *policy;
+
+	policy = kzalloc(sizeof(struct xfrm_policy), gfp);
+
+	if (policy) {
+		write_pnet(&policy->xp_net, net);
+		INIT_LIST_HEAD(&policy->walk.all);
+		INIT_HLIST_NODE(&policy->bydst_inexact_list);
+		INIT_HLIST_NODE(&policy->bydst);
+		INIT_HLIST_NODE(&policy->byidx);
+		rwlock_init(&policy->lock);
+		refcount_set(&policy->refcnt, 1);
+		skb_queue_head_init(&policy->polq.hold_queue);
+		timer_setup(&policy->timer, xfrm_policy_timer, 0);
+		timer_setup(&policy->polq.hold_timer,
+			    xfrm_policy_queue_process, 0);
+	}
+	return policy;
+}
+EXPORT_SYMBOL(xfrm_policy_alloc);
+
+static void xfrm_policy_destroy_rcu(struct rcu_head *head)
+{
+	struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu);
+
+	security_xfrm_policy_free(policy->security);
+	kfree(policy);
+}
+
+/* Destroy xfrm_policy: descendant resources must be released to this moment. */
+
+void xfrm_policy_destroy(struct xfrm_policy *policy)
+{
+	BUG_ON(!policy->walk.dead);
+
+	if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer))
+		BUG();
+
+	xfrm_dev_policy_free(policy);
+	call_rcu(&policy->rcu, xfrm_policy_destroy_rcu);
+}
+EXPORT_SYMBOL(xfrm_policy_destroy);
+
+/* Rule must be locked. Release descendant resources, announce
+ * entry dead. The rule must be unlinked from lists to the moment.
+ */
+
+static void xfrm_policy_kill(struct xfrm_policy *policy)
+{
+	write_lock_bh(&policy->lock);
+	policy->walk.dead = 1;
+	write_unlock_bh(&policy->lock);
+
+	atomic_inc(&policy->genid);
+
+	if (del_timer(&policy->polq.hold_timer))
+		xfrm_pol_put(policy);
+	skb_queue_purge(&policy->polq.hold_queue);
+
+	if (del_timer(&policy->timer))
+		xfrm_pol_put(policy);
+
+	xfrm_pol_put(policy);
+}
+
+static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024;
+
+static inline unsigned int idx_hash(struct net *net, u32 index)
+{
+	return __idx_hash(index, net->xfrm.policy_idx_hmask);
+}
+
+/* calculate policy hash thresholds */
+static void __get_hash_thresh(struct net *net,
+			      unsigned short family, int dir,
+			      u8 *dbits, u8 *sbits)
+{
+	switch (family) {
+	case AF_INET:
+		*dbits = net->xfrm.policy_bydst[dir].dbits4;
+		*sbits = net->xfrm.policy_bydst[dir].sbits4;
+		break;
+
+	case AF_INET6:
+		*dbits = net->xfrm.policy_bydst[dir].dbits6;
+		*sbits = net->xfrm.policy_bydst[dir].sbits6;
+		break;
+
+	default:
+		*dbits = 0;
+		*sbits = 0;
+	}
+}
+
+static struct hlist_head *policy_hash_bysel(struct net *net,
+					    const struct xfrm_selector *sel,
+					    unsigned short family, int dir)
+{
+	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
+	unsigned int hash;
+	u8 dbits;
+	u8 sbits;
+
+	__get_hash_thresh(net, family, dir, &dbits, &sbits);
+	hash = __sel_hash(sel, family, hmask, dbits, sbits);
+
+	if (hash == hmask + 1)
+		return NULL;
+
+	return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
+		     lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash;
+}
+
+static struct hlist_head *policy_hash_direct(struct net *net,
+					     const xfrm_address_t *daddr,
+					     const xfrm_address_t *saddr,
+					     unsigned short family, int dir)
+{
+	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
+	unsigned int hash;
+	u8 dbits;
+	u8 sbits;
+
+	__get_hash_thresh(net, family, dir, &dbits, &sbits);
+	hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits);
+
+	return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
+		     lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash;
+}
+
+static void xfrm_dst_hash_transfer(struct net *net,
+				   struct hlist_head *list,
+				   struct hlist_head *ndsttable,
+				   unsigned int nhashmask,
+				   int dir)
+{
+	struct hlist_node *tmp, *entry0 = NULL;
+	struct xfrm_policy *pol;
+	unsigned int h0 = 0;
+	u8 dbits;
+	u8 sbits;
+
+redo:
+	hlist_for_each_entry_safe(pol, tmp, list, bydst) {
+		unsigned int h;
+
+		__get_hash_thresh(net, pol->family, dir, &dbits, &sbits);
+		h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr,
+				pol->family, nhashmask, dbits, sbits);
+		if (!entry0 || pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+			hlist_del_rcu(&pol->bydst);
+			hlist_add_head_rcu(&pol->bydst, ndsttable + h);
+			h0 = h;
+		} else {
+			if (h != h0)
+				continue;
+			hlist_del_rcu(&pol->bydst);
+			hlist_add_behind_rcu(&pol->bydst, entry0);
+		}
+		entry0 = &pol->bydst;
+	}
+	if (!hlist_empty(list)) {
+		entry0 = NULL;
+		goto redo;
+	}
+}
+
+static void xfrm_idx_hash_transfer(struct hlist_head *list,
+				   struct hlist_head *nidxtable,
+				   unsigned int nhashmask)
+{
+	struct hlist_node *tmp;
+	struct xfrm_policy *pol;
+
+	hlist_for_each_entry_safe(pol, tmp, list, byidx) {
+		unsigned int h;
+
+		h = __idx_hash(pol->index, nhashmask);
+		hlist_add_head(&pol->byidx, nidxtable+h);
+	}
+}
+
+static unsigned long xfrm_new_hash_mask(unsigned int old_hmask)
+{
+	return ((old_hmask + 1) << 1) - 1;
+}
+
+static void xfrm_bydst_resize(struct net *net, int dir)
+{
+	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
+	unsigned int nhashmask = xfrm_new_hash_mask(hmask);
+	unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head);
+	struct hlist_head *ndst = xfrm_hash_alloc(nsize);
+	struct hlist_head *odst;
+	int i;
+
+	if (!ndst)
+		return;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
+
+	odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
+				lockdep_is_held(&net->xfrm.xfrm_policy_lock));
+
+	for (i = hmask; i >= 0; i--)
+		xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir);
+
+	rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst);
+	net->xfrm.policy_bydst[dir].hmask = nhashmask;
+
+	write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	synchronize_rcu();
+
+	xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head));
+}
+
+static void xfrm_byidx_resize(struct net *net)
+{
+	unsigned int hmask = net->xfrm.policy_idx_hmask;
+	unsigned int nhashmask = xfrm_new_hash_mask(hmask);
+	unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head);
+	struct hlist_head *oidx = net->xfrm.policy_byidx;
+	struct hlist_head *nidx = xfrm_hash_alloc(nsize);
+	int i;
+
+	if (!nidx)
+		return;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+
+	for (i = hmask; i >= 0; i--)
+		xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask);
+
+	net->xfrm.policy_byidx = nidx;
+	net->xfrm.policy_idx_hmask = nhashmask;
+
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head));
+}
+
+static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total)
+{
+	unsigned int cnt = net->xfrm.policy_count[dir];
+	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
+
+	if (total)
+		*total += cnt;
+
+	if ((hmask + 1) < xfrm_policy_hashmax &&
+	    cnt > hmask)
+		return 1;
+
+	return 0;
+}
+
+static inline int xfrm_byidx_should_resize(struct net *net, int total)
+{
+	unsigned int hmask = net->xfrm.policy_idx_hmask;
+
+	if ((hmask + 1) < xfrm_policy_hashmax &&
+	    total > hmask)
+		return 1;
+
+	return 0;
+}
+
+void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
+{
+	si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
+	si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
+	si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
+	si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX];
+	si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX];
+	si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
+	si->spdhcnt = net->xfrm.policy_idx_hmask;
+	si->spdhmcnt = xfrm_policy_hashmax;
+}
+EXPORT_SYMBOL(xfrm_spd_getinfo);
+
+static DEFINE_MUTEX(hash_resize_mutex);
+static void xfrm_hash_resize(struct work_struct *work)
+{
+	struct net *net = container_of(work, struct net, xfrm.policy_hash_work);
+	int dir, total;
+
+	mutex_lock(&hash_resize_mutex);
+
+	total = 0;
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
+		if (xfrm_bydst_should_resize(net, dir, &total))
+			xfrm_bydst_resize(net, dir);
+	}
+	if (xfrm_byidx_should_resize(net, total))
+		xfrm_byidx_resize(net);
+
+	mutex_unlock(&hash_resize_mutex);
+}
+
+/* Make sure *pol can be inserted into fastbin.
+ * Useful to check that later insert requests will be successful
+ * (provided xfrm_policy_lock is held throughout).
+ */
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
+{
+	struct xfrm_pol_inexact_bin *bin, *prev;
+	struct xfrm_pol_inexact_key k = {
+		.family = pol->family,
+		.type = pol->type,
+		.dir = dir,
+		.if_id = pol->if_id,
+	};
+	struct net *net = xp_net(pol);
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	write_pnet(&k.net, net);
+	bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k,
+				     xfrm_pol_inexact_params);
+	if (bin)
+		return bin;
+
+	bin = kzalloc(sizeof(*bin), GFP_ATOMIC);
+	if (!bin)
+		return NULL;
+
+	bin->k = k;
+	INIT_HLIST_HEAD(&bin->hhead);
+	bin->root_d = RB_ROOT;
+	bin->root_s = RB_ROOT;
+	seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock);
+
+	prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
+						&bin->k, &bin->head,
+						xfrm_pol_inexact_params);
+	if (!prev) {
+		list_add(&bin->inexact_bins, &net->xfrm.inexact_bins);
+		return bin;
+	}
+
+	kfree(bin);
+
+	return IS_ERR(prev) ? NULL : prev;
+}
+
+static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr,
+					       int family, u8 prefixlen)
+{
+	if (xfrm_addr_any(addr, family))
+		return true;
+
+	if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6)
+		return true;
+
+	if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4)
+		return true;
+
+	return false;
+}
+
+static bool
+xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy)
+{
+	const xfrm_address_t *addr;
+	bool saddr_any, daddr_any;
+	u8 prefixlen;
+
+	addr = &policy->selector.saddr;
+	prefixlen = policy->selector.prefixlen_s;
+
+	saddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
+						       policy->family,
+						       prefixlen);
+	addr = &policy->selector.daddr;
+	prefixlen = policy->selector.prefixlen_d;
+	daddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
+						       policy->family,
+						       prefixlen);
+	return saddr_any && daddr_any;
+}
+
+static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node,
+				       const xfrm_address_t *addr, u8 prefixlen)
+{
+	node->addr = *addr;
+	node->prefixlen = prefixlen;
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen)
+{
+	struct xfrm_pol_inexact_node *node;
+
+	node = kzalloc(sizeof(*node), GFP_ATOMIC);
+	if (node)
+		xfrm_pol_inexact_node_init(node, addr, prefixlen);
+
+	return node;
+}
+
+static int xfrm_policy_addr_delta(const xfrm_address_t *a,
+				  const xfrm_address_t *b,
+				  u8 prefixlen, u16 family)
+{
+	u32 ma, mb, mask;
+	unsigned int pdw, pbi;
+	int delta = 0;
+
+	switch (family) {
+	case AF_INET:
+		if (prefixlen == 0)
+			return 0;
+		mask = ~0U << (32 - prefixlen);
+		ma = ntohl(a->a4) & mask;
+		mb = ntohl(b->a4) & mask;
+		if (ma < mb)
+			delta = -1;
+		else if (ma > mb)
+			delta = 1;
+		break;
+	case AF_INET6:
+		pdw = prefixlen >> 5;
+		pbi = prefixlen & 0x1f;
+
+		if (pdw) {
+			delta = memcmp(a->a6, b->a6, pdw << 2);
+			if (delta)
+				return delta;
+		}
+		if (pbi) {
+			mask = ~0U << (32 - pbi);
+			ma = ntohl(a->a6[pdw]) & mask;
+			mb = ntohl(b->a6[pdw]) & mask;
+			if (ma < mb)
+				delta = -1;
+			else if (ma > mb)
+				delta = 1;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return delta;
+}
+
+static void xfrm_policy_inexact_list_reinsert(struct net *net,
+					      struct xfrm_pol_inexact_node *n,
+					      u16 family)
+{
+	unsigned int matched_s, matched_d;
+	struct xfrm_policy *policy, *p;
+
+	matched_s = 0;
+	matched_d = 0;
+
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		struct hlist_node *newpos = NULL;
+		bool matches_s, matches_d;
+
+		if (policy->walk.dead || !policy->bydst_reinsert)
+			continue;
+
+		WARN_ON_ONCE(policy->family != family);
+
+		policy->bydst_reinsert = false;
+		hlist_for_each_entry(p, &n->hhead, bydst) {
+			if (policy->priority > p->priority)
+				newpos = &p->bydst;
+			else if (policy->priority == p->priority &&
+				 policy->pos > p->pos)
+				newpos = &p->bydst;
+			else
+				break;
+		}
+
+		if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
+			hlist_add_behind_rcu(&policy->bydst, newpos);
+		else
+			hlist_add_head_rcu(&policy->bydst, &n->hhead);
+
+		/* paranoia checks follow.
+		 * Check that the reinserted policy matches at least
+		 * saddr or daddr for current node prefix.
+		 *
+		 * Matching both is fine, matching saddr in one policy
+		 * (but not daddr) and then matching only daddr in another
+		 * is a bug.
+		 */
+		matches_s = xfrm_policy_addr_delta(&policy->selector.saddr,
+						   &n->addr,
+						   n->prefixlen,
+						   family) == 0;
+		matches_d = xfrm_policy_addr_delta(&policy->selector.daddr,
+						   &n->addr,
+						   n->prefixlen,
+						   family) == 0;
+		if (matches_s && matches_d)
+			continue;
+
+		WARN_ON_ONCE(!matches_s && !matches_d);
+		if (matches_s)
+			matched_s++;
+		if (matches_d)
+			matched_d++;
+		WARN_ON_ONCE(matched_s && matched_d);
+	}
+}
+
+static void xfrm_policy_inexact_node_reinsert(struct net *net,
+					      struct xfrm_pol_inexact_node *n,
+					      struct rb_root *new,
+					      u16 family)
+{
+	struct xfrm_pol_inexact_node *node;
+	struct rb_node **p, *parent;
+
+	/* we should not have another subtree here */
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root));
+restart:
+	parent = NULL;
+	p = &new->rb_node;
+	while (*p) {
+		u8 prefixlen;
+		int delta;
+
+		parent = *p;
+		node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
+
+		prefixlen = min(node->prefixlen, n->prefixlen);
+
+		delta = xfrm_policy_addr_delta(&n->addr, &node->addr,
+					       prefixlen, family);
+		if (delta < 0) {
+			p = &parent->rb_left;
+		} else if (delta > 0) {
+			p = &parent->rb_right;
+		} else {
+			bool same_prefixlen = node->prefixlen == n->prefixlen;
+			struct xfrm_policy *tmp;
+
+			hlist_for_each_entry(tmp, &n->hhead, bydst) {
+				tmp->bydst_reinsert = true;
+				hlist_del_rcu(&tmp->bydst);
+			}
+
+			node->prefixlen = prefixlen;
+
+			xfrm_policy_inexact_list_reinsert(net, node, family);
+
+			if (same_prefixlen) {
+				kfree_rcu(n, rcu);
+				return;
+			}
+
+			rb_erase(*p, new);
+			kfree_rcu(n, rcu);
+			n = node;
+			goto restart;
+		}
+	}
+
+	rb_link_node_rcu(&n->node, parent, p);
+	rb_insert_color(&n->node, new);
+}
+
+/* merge nodes v and n */
+static void xfrm_policy_inexact_node_merge(struct net *net,
+					   struct xfrm_pol_inexact_node *v,
+					   struct xfrm_pol_inexact_node *n,
+					   u16 family)
+{
+	struct xfrm_pol_inexact_node *node;
+	struct xfrm_policy *tmp;
+	struct rb_node *rnode;
+
+	/* To-be-merged node v has a subtree.
+	 *
+	 * Dismantle it and insert its nodes to n->root.
+	 */
+	while ((rnode = rb_first(&v->root)) != NULL) {
+		node = rb_entry(rnode, struct xfrm_pol_inexact_node, node);
+		rb_erase(&node->node, &v->root);
+		xfrm_policy_inexact_node_reinsert(net, node, &n->root,
+						  family);
+	}
+
+	hlist_for_each_entry(tmp, &v->hhead, bydst) {
+		tmp->bydst_reinsert = true;
+		hlist_del_rcu(&tmp->bydst);
+	}
+
+	xfrm_policy_inexact_list_reinsert(net, n, family);
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_policy_inexact_insert_node(struct net *net,
+				struct rb_root *root,
+				xfrm_address_t *addr,
+				u16 family, u8 prefixlen, u8 dir)
+{
+	struct xfrm_pol_inexact_node *cached = NULL;
+	struct rb_node **p, *parent = NULL;
+	struct xfrm_pol_inexact_node *node;
+
+	p = &root->rb_node;
+	while (*p) {
+		int delta;
+
+		parent = *p;
+		node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
+
+		delta = xfrm_policy_addr_delta(addr, &node->addr,
+					       node->prefixlen,
+					       family);
+		if (delta == 0 && prefixlen >= node->prefixlen) {
+			WARN_ON_ONCE(cached); /* ipsec policies got lost */
+			return node;
+		}
+
+		if (delta < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+
+		if (prefixlen < node->prefixlen) {
+			delta = xfrm_policy_addr_delta(addr, &node->addr,
+						       prefixlen,
+						       family);
+			if (delta)
+				continue;
+
+			/* This node is a subnet of the new prefix. It needs
+			 * to be removed and re-inserted with the smaller
+			 * prefix and all nodes that are now also covered
+			 * by the reduced prefixlen.
+			 */
+			rb_erase(&node->node, root);
+
+			if (!cached) {
+				xfrm_pol_inexact_node_init(node, addr,
+							   prefixlen);
+				cached = node;
+			} else {
+				/* This node also falls within the new
+				 * prefixlen. Merge the to-be-reinserted
+				 * node and this one.
+				 */
+				xfrm_policy_inexact_node_merge(net, node,
+							       cached, family);
+				kfree_rcu(node, rcu);
+			}
+
+			/* restart */
+			p = &root->rb_node;
+			parent = NULL;
+		}
+	}
+
+	node = cached;
+	if (!node) {
+		node = xfrm_pol_inexact_node_alloc(addr, prefixlen);
+		if (!node)
+			return NULL;
+	}
+
+	rb_link_node_rcu(&node->node, parent, p);
+	rb_insert_color(&node->node, root);
+
+	return node;
+}
+
+static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm)
+{
+	struct xfrm_pol_inexact_node *node;
+	struct rb_node *rn = rb_first(r);
+
+	while (rn) {
+		node = rb_entry(rn, struct xfrm_pol_inexact_node, node);
+
+		xfrm_policy_inexact_gc_tree(&node->root, rm);
+		rn = rb_next(rn);
+
+		if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) {
+			WARN_ON_ONCE(rm);
+			continue;
+		}
+
+		rb_erase(&node->node, r);
+		kfree_rcu(node, rcu);
+	}
+}
+
+static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit)
+{
+	write_seqcount_begin(&b->count);
+	xfrm_policy_inexact_gc_tree(&b->root_d, net_exit);
+	xfrm_policy_inexact_gc_tree(&b->root_s, net_exit);
+	write_seqcount_end(&b->count);
+
+	if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) ||
+	    !hlist_empty(&b->hhead)) {
+		WARN_ON_ONCE(net_exit);
+		return;
+	}
+
+	if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head,
+				   xfrm_pol_inexact_params) == 0) {
+		list_del(&b->inexact_bins);
+		kfree_rcu(b, rcu);
+	}
+}
+
+static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b)
+{
+	struct net *net = read_pnet(&b->k.net);
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	__xfrm_policy_inexact_prune_bin(b, false);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+}
+
+static void __xfrm_policy_inexact_flush(struct net *net)
+{
+	struct xfrm_pol_inexact_bin *bin, *t;
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins)
+		__xfrm_policy_inexact_prune_bin(bin, false);
+}
+
+static struct hlist_head *
+xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
+				struct xfrm_policy *policy, u8 dir)
+{
+	struct xfrm_pol_inexact_node *n;
+	struct net *net;
+
+	net = xp_net(policy);
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	if (xfrm_policy_inexact_insert_use_any_list(policy))
+		return &bin->hhead;
+
+	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
+					       policy->family,
+					       policy->selector.prefixlen_d)) {
+		write_seqcount_begin(&bin->count);
+		n = xfrm_policy_inexact_insert_node(net,
+						    &bin->root_s,
+						    &policy->selector.saddr,
+						    policy->family,
+						    policy->selector.prefixlen_s,
+						    dir);
+		write_seqcount_end(&bin->count);
+		if (!n)
+			return NULL;
+
+		return &n->hhead;
+	}
+
+	/* daddr is fixed */
+	write_seqcount_begin(&bin->count);
+	n = xfrm_policy_inexact_insert_node(net,
+					    &bin->root_d,
+					    &policy->selector.daddr,
+					    policy->family,
+					    policy->selector.prefixlen_d, dir);
+	write_seqcount_end(&bin->count);
+	if (!n)
+		return NULL;
+
+	/* saddr is wildcard */
+	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
+					       policy->family,
+					       policy->selector.prefixlen_s))
+		return &n->hhead;
+
+	write_seqcount_begin(&bin->count);
+	n = xfrm_policy_inexact_insert_node(net,
+					    &n->root,
+					    &policy->selector.saddr,
+					    policy->family,
+					    policy->selector.prefixlen_s, dir);
+	write_seqcount_end(&bin->count);
+	if (!n)
+		return NULL;
+
+	return &n->hhead;
+}
+
+static struct xfrm_policy *
+xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
+{
+	struct xfrm_pol_inexact_bin *bin;
+	struct xfrm_policy *delpol;
+	struct hlist_head *chain;
+	struct net *net;
+
+	bin = xfrm_policy_inexact_alloc_bin(policy, dir);
+	if (!bin)
+		return ERR_PTR(-ENOMEM);
+
+	net = xp_net(policy);
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir);
+	if (!chain) {
+		__xfrm_policy_inexact_prune_bin(bin, false);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	delpol = xfrm_policy_insert_list(chain, policy, excl);
+	if (delpol && excl) {
+		__xfrm_policy_inexact_prune_bin(bin, false);
+		return ERR_PTR(-EEXIST);
+	}
+
+	chain = &net->xfrm.policy_inexact[dir];
+	xfrm_policy_insert_inexact_list(chain, policy);
+
+	if (delpol)
+		__xfrm_policy_inexact_prune_bin(bin, false);
+
+	return delpol;
+}
+
+static void xfrm_hash_rebuild(struct work_struct *work)
+{
+	struct net *net = container_of(work, struct net,
+				       xfrm.policy_hthresh.work);
+	unsigned int hmask;
+	struct xfrm_policy *pol;
+	struct xfrm_policy *policy;
+	struct hlist_head *chain;
+	struct hlist_head *odst;
+	struct hlist_node *newpos;
+	int i;
+	int dir;
+	unsigned seq;
+	u8 lbits4, rbits4, lbits6, rbits6;
+
+	mutex_lock(&hash_resize_mutex);
+
+	/* read selector prefixlen thresholds */
+	do {
+		seq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
+
+		lbits4 = net->xfrm.policy_hthresh.lbits4;
+		rbits4 = net->xfrm.policy_hthresh.rbits4;
+		lbits6 = net->xfrm.policy_hthresh.lbits6;
+		rbits6 = net->xfrm.policy_hthresh.rbits6;
+	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
+
+	/* make sure that we can insert the indirect policies again before
+	 * we start with destructive action.
+	 */
+	list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
+		struct xfrm_pol_inexact_bin *bin;
+		u8 dbits, sbits;
+
+		if (policy->walk.dead)
+			continue;
+
+		dir = xfrm_policy_id2dir(policy->index);
+		if (dir >= XFRM_POLICY_MAX)
+			continue;
+
+		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+			if (policy->family == AF_INET) {
+				dbits = rbits4;
+				sbits = lbits4;
+			} else {
+				dbits = rbits6;
+				sbits = lbits6;
+			}
+		} else {
+			if (policy->family == AF_INET) {
+				dbits = lbits4;
+				sbits = rbits4;
+			} else {
+				dbits = lbits6;
+				sbits = rbits6;
+			}
+		}
+
+		if (policy->selector.prefixlen_d < dbits ||
+		    policy->selector.prefixlen_s < sbits)
+			continue;
+
+		bin = xfrm_policy_inexact_alloc_bin(policy, dir);
+		if (!bin)
+			goto out_unlock;
+
+		if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir))
+			goto out_unlock;
+	}
+
+	/* reset the bydst and inexact table in all directions */
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
+		struct hlist_node *n;
+
+		hlist_for_each_entry_safe(policy, n,
+					  &net->xfrm.policy_inexact[dir],
+					  bydst_inexact_list) {
+			hlist_del_rcu(&policy->bydst);
+			hlist_del_init(&policy->bydst_inexact_list);
+		}
+
+		hmask = net->xfrm.policy_bydst[dir].hmask;
+		odst = net->xfrm.policy_bydst[dir].table;
+		for (i = hmask; i >= 0; i--) {
+			hlist_for_each_entry_safe(policy, n, odst + i, bydst)
+				hlist_del_rcu(&policy->bydst);
+		}
+		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+			/* dir out => dst = remote, src = local */
+			net->xfrm.policy_bydst[dir].dbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = rbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = lbits6;
+		} else {
+			/* dir in/fwd => dst = local, src = remote */
+			net->xfrm.policy_bydst[dir].dbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = lbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = rbits6;
+		}
+	}
+
+	/* re-insert all policies by order of creation */
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		if (policy->walk.dead)
+			continue;
+		dir = xfrm_policy_id2dir(policy->index);
+		if (dir >= XFRM_POLICY_MAX) {
+			/* skip socket policies */
+			continue;
+		}
+		newpos = NULL;
+		chain = policy_hash_bysel(net, &policy->selector,
+					  policy->family, dir);
+
+		if (!chain) {
+			void *p = xfrm_policy_inexact_insert(policy, dir, 0);
+
+			WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p));
+			continue;
+		}
+
+		hlist_for_each_entry(pol, chain, bydst) {
+			if (policy->priority >= pol->priority)
+				newpos = &pol->bydst;
+			else
+				break;
+		}
+		if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
+			hlist_add_behind_rcu(&policy->bydst, newpos);
+		else
+			hlist_add_head_rcu(&policy->bydst, chain);
+	}
+
+out_unlock:
+	__xfrm_policy_inexact_flush(net);
+	write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	mutex_unlock(&hash_resize_mutex);
+}
+
+void xfrm_policy_hash_rebuild(struct net *net)
+{
+	schedule_work(&net->xfrm.policy_hthresh.work);
+}
+EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
+
+/* Generate new index... KAME seems to generate them ordered by cost
+ * of an absolute inpredictability of ordering of rules. This will not pass. */
+static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
+{
+	for (;;) {
+		struct hlist_head *list;
+		struct xfrm_policy *p;
+		u32 idx;
+		int found;
+
+		if (!index) {
+			idx = (net->xfrm.idx_generator | dir);
+			net->xfrm.idx_generator += 8;
+		} else {
+			idx = index;
+			index = 0;
+		}
+
+		if (idx == 0)
+			idx = 8;
+		list = net->xfrm.policy_byidx + idx_hash(net, idx);
+		found = 0;
+		hlist_for_each_entry(p, list, byidx) {
+			if (p->index == idx) {
+				found = 1;
+				break;
+			}
+		}
+		if (!found)
+			return idx;
+	}
+}
+
+static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s2)
+{
+	u32 *p1 = (u32 *) s1;
+	u32 *p2 = (u32 *) s2;
+	int len = sizeof(struct xfrm_selector) / sizeof(u32);
+	int i;
+
+	for (i = 0; i < len; i++) {
+		if (p1[i] != p2[i])
+			return 1;
+	}
+
+	return 0;
+}
+
+static void xfrm_policy_requeue(struct xfrm_policy *old,
+				struct xfrm_policy *new)
+{
+	struct xfrm_policy_queue *pq = &old->polq;
+	struct sk_buff_head list;
+
+	if (skb_queue_empty(&pq->hold_queue))
+		return;
+
+	__skb_queue_head_init(&list);
+
+	spin_lock_bh(&pq->hold_queue.lock);
+	skb_queue_splice_init(&pq->hold_queue, &list);
+	if (del_timer(&pq->hold_timer))
+		xfrm_pol_put(old);
+	spin_unlock_bh(&pq->hold_queue.lock);
+
+	pq = &new->polq;
+
+	spin_lock_bh(&pq->hold_queue.lock);
+	skb_queue_splice(&list, &pq->hold_queue);
+	pq->timeout = XFRM_QUEUE_TMO_MIN;
+	if (!mod_timer(&pq->hold_timer, jiffies))
+		xfrm_pol_hold(new);
+	spin_unlock_bh(&pq->hold_queue.lock);
+}
+
+static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark,
+					  struct xfrm_policy *pol)
+{
+	return mark->v == pol->mark.v && mark->m == pol->mark.m;
+}
+
+static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
+{
+	const struct xfrm_pol_inexact_key *k = data;
+	u32 a = k->type << 24 | k->dir << 16 | k->family;
+
+	return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)),
+			    seed);
+}
+
+static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed)
+{
+	const struct xfrm_pol_inexact_bin *b = data;
+
+	return xfrm_pol_bin_key(&b->k, 0, seed);
+}
+
+static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg,
+			    const void *ptr)
+{
+	const struct xfrm_pol_inexact_key *key = arg->key;
+	const struct xfrm_pol_inexact_bin *b = ptr;
+	int ret;
+
+	if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net)))
+		return -1;
+
+	ret = b->k.dir ^ key->dir;
+	if (ret)
+		return ret;
+
+	ret = b->k.type ^ key->type;
+	if (ret)
+		return ret;
+
+	ret = b->k.family ^ key->family;
+	if (ret)
+		return ret;
+
+	return b->k.if_id ^ key->if_id;
+}
+
+static const struct rhashtable_params xfrm_pol_inexact_params = {
+	.head_offset		= offsetof(struct xfrm_pol_inexact_bin, head),
+	.hashfn			= xfrm_pol_bin_key,
+	.obj_hashfn		= xfrm_pol_bin_obj,
+	.obj_cmpfn		= xfrm_pol_bin_cmp,
+	.automatic_shrinking	= true,
+};
+
+static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
+					    struct xfrm_policy *policy)
+{
+	struct xfrm_policy *pol, *delpol = NULL;
+	struct hlist_node *newpos = NULL;
+	int i = 0;
+
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+		if (pol->type == policy->type &&
+		    pol->if_id == policy->if_id &&
+		    !selector_cmp(&pol->selector, &policy->selector) &&
+		    xfrm_policy_mark_match(&policy->mark, pol) &&
+		    xfrm_sec_ctx_match(pol->security, policy->security) &&
+		    !WARN_ON(delpol)) {
+			delpol = pol;
+			if (policy->priority > pol->priority)
+				continue;
+		} else if (policy->priority >= pol->priority) {
+			newpos = &pol->bydst_inexact_list;
+			continue;
+		}
+		if (delpol)
+			break;
+	}
+
+	if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
+		hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
+	else
+		hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
+
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+		pol->pos = i;
+		i++;
+	}
+}
+
+static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
+						   struct xfrm_policy *policy,
+						   bool excl)
+{
+	struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL;
+
+	hlist_for_each_entry(pol, chain, bydst) {
+		if (pol->type == policy->type &&
+		    pol->if_id == policy->if_id &&
+		    !selector_cmp(&pol->selector, &policy->selector) &&
+		    xfrm_policy_mark_match(&policy->mark, pol) &&
+		    xfrm_sec_ctx_match(pol->security, policy->security) &&
+		    !WARN_ON(delpol)) {
+			if (excl)
+				return ERR_PTR(-EEXIST);
+			delpol = pol;
+			if (policy->priority > pol->priority)
+				continue;
+		} else if (policy->priority >= pol->priority) {
+			newpos = pol;
+			continue;
+		}
+		if (delpol)
+			break;
+	}
+
+	if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
+		hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
+	else
+		/* Packet offload policies enter to the head
+		 * to speed-up lookups.
+		 */
+		hlist_add_head_rcu(&policy->bydst, chain);
+
+	return delpol;
+}
+
+int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
+{
+	struct net *net = xp_net(policy);
+	struct xfrm_policy *delpol;
+	struct hlist_head *chain;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
+	if (chain)
+		delpol = xfrm_policy_insert_list(chain, policy, excl);
+	else
+		delpol = xfrm_policy_inexact_insert(policy, dir, excl);
+
+	if (IS_ERR(delpol)) {
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		return PTR_ERR(delpol);
+	}
+
+	__xfrm_policy_link(policy, dir);
+
+	/* After previous checking, family can either be AF_INET or AF_INET6 */
+	if (policy->family == AF_INET)
+		rt_genid_bump_ipv4(net);
+	else
+		rt_genid_bump_ipv6(net);
+
+	if (delpol) {
+		xfrm_policy_requeue(delpol, policy);
+		__xfrm_policy_unlink(delpol, dir);
+	}
+	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
+	hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
+	policy->curlft.add_time = ktime_get_real_seconds();
+	policy->curlft.use_time = 0;
+	if (!mod_timer(&policy->timer, jiffies + HZ))
+		xfrm_pol_hold(policy);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	if (delpol)
+		xfrm_policy_kill(delpol);
+	else if (xfrm_bydst_should_resize(net, dir, NULL))
+		schedule_work(&net->xfrm.policy_hash_work);
+
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_policy_insert);
+
+static struct xfrm_policy *
+__xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark,
+			u32 if_id, u8 type, int dir, struct xfrm_selector *sel,
+			struct xfrm_sec_ctx *ctx)
+{
+	struct xfrm_policy *pol;
+
+	if (!chain)
+		return NULL;
+
+	hlist_for_each_entry(pol, chain, bydst) {
+		if (pol->type == type &&
+		    pol->if_id == if_id &&
+		    xfrm_policy_mark_match(mark, pol) &&
+		    !selector_cmp(sel, &pol->selector) &&
+		    xfrm_sec_ctx_match(ctx, pol->security))
+			return pol;
+	}
+
+	return NULL;
+}
+
+struct xfrm_policy *
+xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id,
+		      u8 type, int dir, struct xfrm_selector *sel,
+		      struct xfrm_sec_ctx *ctx, int delete, int *err)
+{
+	struct xfrm_pol_inexact_bin *bin = NULL;
+	struct xfrm_policy *pol, *ret = NULL;
+	struct hlist_head *chain;
+
+	*err = 0;
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	chain = policy_hash_bysel(net, sel, sel->family, dir);
+	if (!chain) {
+		struct xfrm_pol_inexact_candidates cand;
+		int i;
+
+		bin = xfrm_policy_inexact_lookup(net, type,
+						 sel->family, dir, if_id);
+		if (!bin) {
+			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+			return NULL;
+		}
+
+		if (!xfrm_policy_find_inexact_candidates(&cand, bin,
+							 &sel->saddr,
+							 &sel->daddr)) {
+			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+			return NULL;
+		}
+
+		pol = NULL;
+		for (i = 0; i < ARRAY_SIZE(cand.res); i++) {
+			struct xfrm_policy *tmp;
+
+			tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark,
+						      if_id, type, dir,
+						      sel, ctx);
+			if (!tmp)
+				continue;
+
+			if (!pol || tmp->pos < pol->pos)
+				pol = tmp;
+		}
+	} else {
+		pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir,
+					      sel, ctx);
+	}
+
+	if (pol) {
+		xfrm_pol_hold(pol);
+		if (delete) {
+			*err = security_xfrm_policy_delete(pol->security);
+			if (*err) {
+				spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+				return pol;
+			}
+			__xfrm_policy_unlink(pol, dir);
+		}
+		ret = pol;
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	if (ret && delete)
+		xfrm_policy_kill(ret);
+	if (bin && delete)
+		xfrm_policy_inexact_prune_bin(bin);
+	return ret;
+}
+EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
+
+struct xfrm_policy *
+xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id,
+		 u8 type, int dir, u32 id, int delete, int *err)
+{
+	struct xfrm_policy *pol, *ret;
+	struct hlist_head *chain;
+
+	*err = -ENOENT;
+	if (xfrm_policy_id2dir(id) != dir)
+		return NULL;
+
+	*err = 0;
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	chain = net->xfrm.policy_byidx + idx_hash(net, id);
+	ret = NULL;
+	hlist_for_each_entry(pol, chain, byidx) {
+		if (pol->type == type && pol->index == id &&
+		    pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) {
+			xfrm_pol_hold(pol);
+			if (delete) {
+				*err = security_xfrm_policy_delete(
+								pol->security);
+				if (*err) {
+					spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+					return pol;
+				}
+				__xfrm_policy_unlink(pol, dir);
+			}
+			ret = pol;
+			break;
+		}
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	if (ret && delete)
+		xfrm_policy_kill(ret);
+	return ret;
+}
+EXPORT_SYMBOL(xfrm_policy_byid);
+
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+static inline int
+xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
+{
+	struct xfrm_policy *pol;
+	int err = 0;
+
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		if (pol->walk.dead ||
+		    xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
+		    pol->type != type)
+			continue;
+
+		err = security_xfrm_policy_delete(pol->security);
+		if (err) {
+			xfrm_audit_policy_delete(pol, 0, task_valid);
+			return err;
+		}
+	}
+	return err;
+}
+
+static inline int xfrm_dev_policy_flush_secctx_check(struct net *net,
+						     struct net_device *dev,
+						     bool task_valid)
+{
+	struct xfrm_policy *pol;
+	int err = 0;
+
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		if (pol->walk.dead ||
+		    xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
+		    pol->xdo.dev != dev)
+			continue;
+
+		err = security_xfrm_policy_delete(pol->security);
+		if (err) {
+			xfrm_audit_policy_delete(pol, 0, task_valid);
+			return err;
+		}
+	}
+	return err;
+}
+#else
+static inline int
+xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
+{
+	return 0;
+}
+
+static inline int xfrm_dev_policy_flush_secctx_check(struct net *net,
+						     struct net_device *dev,
+						     bool task_valid)
+{
+	return 0;
+}
+#endif
+
+int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
+{
+	int dir, err = 0, cnt = 0;
+	struct xfrm_policy *pol;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+
+	err = xfrm_policy_flush_secctx_check(net, type, task_valid);
+	if (err)
+		goto out;
+
+again:
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		if (pol->walk.dead)
+			continue;
+
+		dir = xfrm_policy_id2dir(pol->index);
+		if (dir >= XFRM_POLICY_MAX ||
+		    pol->type != type)
+			continue;
+
+		__xfrm_policy_unlink(pol, dir);
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_dev_policy_delete(pol);
+		cnt++;
+		xfrm_audit_policy_delete(pol, 1, task_valid);
+		xfrm_policy_kill(pol);
+		spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+		goto again;
+	}
+	if (cnt)
+		__xfrm_policy_inexact_flush(net);
+	else
+		err = -ESRCH;
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_policy_flush);
+
+int xfrm_dev_policy_flush(struct net *net, struct net_device *dev,
+			  bool task_valid)
+{
+	int dir, err = 0, cnt = 0;
+	struct xfrm_policy *pol;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+
+	err = xfrm_dev_policy_flush_secctx_check(net, dev, task_valid);
+	if (err)
+		goto out;
+
+again:
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		if (pol->walk.dead)
+			continue;
+
+		dir = xfrm_policy_id2dir(pol->index);
+		if (dir >= XFRM_POLICY_MAX ||
+		    pol->xdo.dev != dev)
+			continue;
+
+		__xfrm_policy_unlink(pol, dir);
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_dev_policy_delete(pol);
+		cnt++;
+		xfrm_audit_policy_delete(pol, 1, task_valid);
+		xfrm_policy_kill(pol);
+		spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+		goto again;
+	}
+	if (cnt)
+		__xfrm_policy_inexact_flush(net);
+	else
+		err = -ESRCH;
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_dev_policy_flush);
+
+int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
+		     int (*func)(struct xfrm_policy *, int, int, void*),
+		     void *data)
+{
+	struct xfrm_policy *pol;
+	struct xfrm_policy_walk_entry *x;
+	int error = 0;
+
+	if (walk->type >= XFRM_POLICY_TYPE_MAX &&
+	    walk->type != XFRM_POLICY_TYPE_ANY)
+		return -EINVAL;
+
+	if (list_empty(&walk->walk.all) && walk->seq != 0)
+		return 0;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	if (list_empty(&walk->walk.all))
+		x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all);
+	else
+		x = list_first_entry(&walk->walk.all,
+				     struct xfrm_policy_walk_entry, all);
+
+	list_for_each_entry_from(x, &net->xfrm.policy_all, all) {
+		if (x->dead)
+			continue;
+		pol = container_of(x, struct xfrm_policy, walk);
+		if (walk->type != XFRM_POLICY_TYPE_ANY &&
+		    walk->type != pol->type)
+			continue;
+		error = func(pol, xfrm_policy_id2dir(pol->index),
+			     walk->seq, data);
+		if (error) {
+			list_move_tail(&walk->walk.all, &x->all);
+			goto out;
+		}
+		walk->seq++;
+	}
+	if (walk->seq == 0) {
+		error = -ENOENT;
+		goto out;
+	}
+	list_del_init(&walk->walk.all);
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+	return error;
+}
+EXPORT_SYMBOL(xfrm_policy_walk);
+
+void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type)
+{
+	INIT_LIST_HEAD(&walk->walk.all);
+	walk->walk.dead = 1;
+	walk->type = type;
+	walk->seq = 0;
+}
+EXPORT_SYMBOL(xfrm_policy_walk_init);
+
+void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net)
+{
+	if (list_empty(&walk->walk.all))
+		return;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */
+	list_del(&walk->walk.all);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+}
+EXPORT_SYMBOL(xfrm_policy_walk_done);
+
+/*
+ * Find policy to apply to this flow.
+ *
+ * Returns 0 if policy found, else an -errno.
+ */
+static int xfrm_policy_match(const struct xfrm_policy *pol,
+			     const struct flowi *fl,
+			     u8 type, u16 family, u32 if_id)
+{
+	const struct xfrm_selector *sel = &pol->selector;
+	int ret = -ESRCH;
+	bool match;
+
+	if (pol->family != family ||
+	    pol->if_id != if_id ||
+	    (fl->flowi_mark & pol->mark.m) != pol->mark.v ||
+	    pol->type != type)
+		return ret;
+
+	match = xfrm_selector_match(sel, fl, family);
+	if (match)
+		ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid);
+	return ret;
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_policy_lookup_inexact_addr(const struct rb_root *r,
+				seqcount_spinlock_t *count,
+				const xfrm_address_t *addr, u16 family)
+{
+	const struct rb_node *parent;
+	int seq;
+
+again:
+	seq = read_seqcount_begin(count);
+
+	parent = rcu_dereference_raw(r->rb_node);
+	while (parent) {
+		struct xfrm_pol_inexact_node *node;
+		int delta;
+
+		node = rb_entry(parent, struct xfrm_pol_inexact_node, node);
+
+		delta = xfrm_policy_addr_delta(addr, &node->addr,
+					       node->prefixlen, family);
+		if (delta < 0) {
+			parent = rcu_dereference_raw(parent->rb_left);
+			continue;
+		} else if (delta > 0) {
+			parent = rcu_dereference_raw(parent->rb_right);
+			continue;
+		}
+
+		return node;
+	}
+
+	if (read_seqcount_retry(count, seq))
+		goto again;
+
+	return NULL;
+}
+
+static bool
+xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
+				    struct xfrm_pol_inexact_bin *b,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr)
+{
+	struct xfrm_pol_inexact_node *n;
+	u16 family;
+
+	if (!b)
+		return false;
+
+	family = b->k.family;
+	memset(cand, 0, sizeof(*cand));
+	cand->res[XFRM_POL_CAND_ANY] = &b->hhead;
+
+	n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr,
+					    family);
+	if (n) {
+		cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
+		n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr,
+						    family);
+		if (n)
+			cand->res[XFRM_POL_CAND_BOTH] = &n->hhead;
+	}
+
+	n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr,
+					    family);
+	if (n)
+		cand->res[XFRM_POL_CAND_SADDR] = &n->hhead;
+
+	return true;
+}
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family,
+			       u8 dir, u32 if_id)
+{
+	struct xfrm_pol_inexact_key k = {
+		.family = family,
+		.type = type,
+		.dir = dir,
+		.if_id = if_id,
+	};
+
+	write_pnet(&k.net, net);
+
+	return rhashtable_lookup(&xfrm_policy_inexact_table, &k,
+				 xfrm_pol_inexact_params);
+}
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family,
+			   u8 dir, u32 if_id)
+{
+	struct xfrm_pol_inexact_bin *bin;
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	rcu_read_lock();
+	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
+	rcu_read_unlock();
+
+	return bin;
+}
+
+static struct xfrm_policy *
+__xfrm_policy_eval_candidates(struct hlist_head *chain,
+			      struct xfrm_policy *prefer,
+			      const struct flowi *fl,
+			      u8 type, u16 family, u32 if_id)
+{
+	u32 priority = prefer ? prefer->priority : ~0u;
+	struct xfrm_policy *pol;
+
+	if (!chain)
+		return NULL;
+
+	hlist_for_each_entry_rcu(pol, chain, bydst) {
+		int err;
+
+		if (pol->priority > priority)
+			break;
+
+		err = xfrm_policy_match(pol, fl, type, family, if_id);
+		if (err) {
+			if (err != -ESRCH)
+				return ERR_PTR(err);
+
+			continue;
+		}
+
+		if (prefer) {
+			/* matches.  Is it older than *prefer? */
+			if (pol->priority == priority &&
+			    prefer->pos < pol->pos)
+				return prefer;
+		}
+
+		return pol;
+	}
+
+	return NULL;
+}
+
+static struct xfrm_policy *
+xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand,
+			    struct xfrm_policy *prefer,
+			    const struct flowi *fl,
+			    u8 type, u16 family, u32 if_id)
+{
+	struct xfrm_policy *tmp;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cand->res); i++) {
+		tmp = __xfrm_policy_eval_candidates(cand->res[i],
+						    prefer,
+						    fl, type, family, if_id);
+		if (!tmp)
+			continue;
+
+		if (IS_ERR(tmp))
+			return tmp;
+		prefer = tmp;
+	}
+
+	return prefer;
+}
+
+static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
+						     const struct flowi *fl,
+						     u16 family, u8 dir,
+						     u32 if_id)
+{
+	struct xfrm_pol_inexact_candidates cand;
+	const xfrm_address_t *daddr, *saddr;
+	struct xfrm_pol_inexact_bin *bin;
+	struct xfrm_policy *pol, *ret;
+	struct hlist_head *chain;
+	unsigned int sequence;
+	int err;
+
+	daddr = xfrm_flowi_daddr(fl, family);
+	saddr = xfrm_flowi_saddr(fl, family);
+	if (unlikely(!daddr || !saddr))
+		return NULL;
+
+	rcu_read_lock();
+ retry:
+	do {
+		sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
+		chain = policy_hash_direct(net, daddr, saddr, family, dir);
+	} while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence));
+
+	ret = NULL;
+	hlist_for_each_entry_rcu(pol, chain, bydst) {
+		err = xfrm_policy_match(pol, fl, type, family, if_id);
+		if (err) {
+			if (err == -ESRCH)
+				continue;
+			else {
+				ret = ERR_PTR(err);
+				goto fail;
+			}
+		} else {
+			ret = pol;
+			break;
+		}
+	}
+	if (ret && ret->xdo.type == XFRM_DEV_OFFLOAD_PACKET)
+		goto skip_inexact;
+
+	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
+	if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr,
+							 daddr))
+		goto skip_inexact;
+
+	pol = xfrm_policy_eval_candidates(&cand, ret, fl, type,
+					  family, if_id);
+	if (pol) {
+		ret = pol;
+		if (IS_ERR(pol))
+			goto fail;
+	}
+
+skip_inexact:
+	if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence))
+		goto retry;
+
+	if (ret && !xfrm_pol_hold_rcu(ret))
+		goto retry;
+fail:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static struct xfrm_policy *xfrm_policy_lookup(struct net *net,
+					      const struct flowi *fl,
+					      u16 family, u8 dir, u32 if_id)
+{
+#ifdef CONFIG_XFRM_SUB_POLICY
+	struct xfrm_policy *pol;
+
+	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family,
+					dir, if_id);
+	if (pol != NULL)
+		return pol;
+#endif
+	return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family,
+					 dir, if_id);
+}
+
+static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
+						 const struct flowi *fl,
+						 u16 family, u32 if_id)
+{
+	struct xfrm_policy *pol;
+
+	rcu_read_lock();
+ again:
+	pol = rcu_dereference(sk->sk_policy[dir]);
+	if (pol != NULL) {
+		bool match;
+		int err = 0;
+
+		if (pol->family != family) {
+			pol = NULL;
+			goto out;
+		}
+
+		match = xfrm_selector_match(&pol->selector, fl, family);
+		if (match) {
+			if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v ||
+			    pol->if_id != if_id) {
+				pol = NULL;
+				goto out;
+			}
+			err = security_xfrm_policy_lookup(pol->security,
+						      fl->flowi_secid);
+			if (!err) {
+				if (!xfrm_pol_hold_rcu(pol))
+					goto again;
+			} else if (err == -ESRCH) {
+				pol = NULL;
+			} else {
+				pol = ERR_PTR(err);
+			}
+		} else
+			pol = NULL;
+	}
+out:
+	rcu_read_unlock();
+	return pol;
+}
+
+static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
+{
+	struct net *net = xp_net(pol);
+
+	list_add(&pol->walk.all, &net->xfrm.policy_all);
+	net->xfrm.policy_count[dir]++;
+	xfrm_pol_hold(pol);
+}
+
+static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
+						int dir)
+{
+	struct net *net = xp_net(pol);
+
+	if (list_empty(&pol->walk.all))
+		return NULL;
+
+	/* Socket policies are not hashed. */
+	if (!hlist_unhashed(&pol->bydst)) {
+		hlist_del_rcu(&pol->bydst);
+		hlist_del_init(&pol->bydst_inexact_list);
+		hlist_del(&pol->byidx);
+	}
+
+	list_del_init(&pol->walk.all);
+	net->xfrm.policy_count[dir]--;
+
+	return pol;
+}
+
+static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir)
+{
+	__xfrm_policy_link(pol, XFRM_POLICY_MAX + dir);
+}
+
+static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir)
+{
+	__xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir);
+}
+
+int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
+{
+	struct net *net = xp_net(pol);
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	pol = __xfrm_policy_unlink(pol, dir);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+	if (pol) {
+		xfrm_dev_policy_delete(pol);
+		xfrm_policy_kill(pol);
+		return 0;
+	}
+	return -ENOENT;
+}
+EXPORT_SYMBOL(xfrm_policy_delete);
+
+int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
+{
+	struct net *net = sock_net(sk);
+	struct xfrm_policy *old_pol;
+
+#ifdef CONFIG_XFRM_SUB_POLICY
+	if (pol && pol->type != XFRM_POLICY_TYPE_MAIN)
+		return -EINVAL;
+#endif
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	old_pol = rcu_dereference_protected(sk->sk_policy[dir],
+				lockdep_is_held(&net->xfrm.xfrm_policy_lock));
+	if (pol) {
+		pol->curlft.add_time = ktime_get_real_seconds();
+		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
+		xfrm_sk_policy_link(pol, dir);
+	}
+	rcu_assign_pointer(sk->sk_policy[dir], pol);
+	if (old_pol) {
+		if (pol)
+			xfrm_policy_requeue(old_pol, pol);
+
+		/* Unlinking succeeds always. This is the only function
+		 * allowed to delete or replace socket policy.
+		 */
+		xfrm_sk_policy_unlink(old_pol, dir);
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	if (old_pol) {
+		xfrm_policy_kill(old_pol);
+	}
+	return 0;
+}
+
+static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
+{
+	struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC);
+	struct net *net = xp_net(old);
+
+	if (newp) {
+		newp->selector = old->selector;
+		if (security_xfrm_policy_clone(old->security,
+					       &newp->security)) {
+			kfree(newp);
+			return NULL;  /* ENOMEM */
+		}
+		newp->lft = old->lft;
+		newp->curlft = old->curlft;
+		newp->mark = old->mark;
+		newp->if_id = old->if_id;
+		newp->action = old->action;
+		newp->flags = old->flags;
+		newp->xfrm_nr = old->xfrm_nr;
+		newp->index = old->index;
+		newp->type = old->type;
+		newp->family = old->family;
+		memcpy(newp->xfrm_vec, old->xfrm_vec,
+		       newp->xfrm_nr*sizeof(struct xfrm_tmpl));
+		spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_sk_policy_link(newp, dir);
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_pol_put(newp);
+	}
+	return newp;
+}
+
+int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
+{
+	const struct xfrm_policy *p;
+	struct xfrm_policy *np;
+	int i, ret = 0;
+
+	rcu_read_lock();
+	for (i = 0; i < 2; i++) {
+		p = rcu_dereference(osk->sk_policy[i]);
+		if (p) {
+			np = clone_policy(p, i);
+			if (unlikely(!np)) {
+				ret = -ENOMEM;
+				break;
+			}
+			rcu_assign_pointer(sk->sk_policy[i], np);
+		}
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static int
+xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local,
+	       xfrm_address_t *remote, unsigned short family, u32 mark)
+{
+	int err;
+	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+
+	if (unlikely(afinfo == NULL))
+		return -EINVAL;
+	err = afinfo->get_saddr(net, oif, local, remote, mark);
+	rcu_read_unlock();
+	return err;
+}
+
+/* Resolve list of templates for the flow, given policy. */
+
+static int
+xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
+		      struct xfrm_state **xfrm, unsigned short family)
+{
+	struct net *net = xp_net(policy);
+	int nx;
+	int i, error;
+	xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family);
+	xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family);
+	xfrm_address_t tmp;
+
+	for (nx = 0, i = 0; i < policy->xfrm_nr; i++) {
+		struct xfrm_state *x;
+		xfrm_address_t *remote = daddr;
+		xfrm_address_t *local  = saddr;
+		struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i];
+
+		if (tmpl->mode == XFRM_MODE_TUNNEL ||
+		    tmpl->mode == XFRM_MODE_BEET) {
+			remote = &tmpl->id.daddr;
+			local = &tmpl->saddr;
+			if (xfrm_addr_any(local, tmpl->encap_family)) {
+				error = xfrm_get_saddr(net, fl->flowi_oif,
+						       &tmp, remote,
+						       tmpl->encap_family, 0);
+				if (error)
+					goto fail;
+				local = &tmp;
+			}
+		}
+
+		x = xfrm_state_find(remote, local, fl, tmpl, policy, &error,
+				    family, policy->if_id);
+
+		if (x && x->km.state == XFRM_STATE_VALID) {
+			xfrm[nx++] = x;
+			daddr = remote;
+			saddr = local;
+			continue;
+		}
+		if (x) {
+			error = (x->km.state == XFRM_STATE_ERROR ?
+				 -EINVAL : -EAGAIN);
+			xfrm_state_put(x);
+		} else if (error == -ESRCH) {
+			error = -EAGAIN;
+		}
+
+		if (!tmpl->optional)
+			goto fail;
+	}
+	return nx;
+
+fail:
+	for (nx--; nx >= 0; nx--)
+		xfrm_state_put(xfrm[nx]);
+	return error;
+}
+
+static int
+xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
+		  struct xfrm_state **xfrm, unsigned short family)
+{
+	struct xfrm_state *tp[XFRM_MAX_DEPTH];
+	struct xfrm_state **tpp = (npols > 1) ? tp : xfrm;
+	int cnx = 0;
+	int error;
+	int ret;
+	int i;
+
+	for (i = 0; i < npols; i++) {
+		if (cnx + pols[i]->xfrm_nr >= XFRM_MAX_DEPTH) {
+			error = -ENOBUFS;
+			goto fail;
+		}
+
+		ret = xfrm_tmpl_resolve_one(pols[i], fl, &tpp[cnx], family);
+		if (ret < 0) {
+			error = ret;
+			goto fail;
+		} else
+			cnx += ret;
+	}
+
+	/* found states are sorted for outbound processing */
+	if (npols > 1)
+		xfrm_state_sort(xfrm, tpp, cnx, family);
+
+	return cnx;
+
+ fail:
+	for (cnx--; cnx >= 0; cnx--)
+		xfrm_state_put(tpp[cnx]);
+	return error;
+
+}
+
+static int xfrm_get_tos(const struct flowi *fl, int family)
+{
+	if (family == AF_INET)
+		return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos;
+
+	return 0;
+}
+
+static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
+{
+	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+	struct dst_ops *dst_ops;
+	struct xfrm_dst *xdst;
+
+	if (!afinfo)
+		return ERR_PTR(-EINVAL);
+
+	switch (family) {
+	case AF_INET:
+		dst_ops = &net->xfrm.xfrm4_dst_ops;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		dst_ops = &net->xfrm.xfrm6_dst_ops;
+		break;
+#endif
+	default:
+		BUG();
+	}
+	xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
+
+	if (likely(xdst)) {
+		memset_after(xdst, 0, u.dst);
+	} else
+		xdst = ERR_PTR(-ENOBUFS);
+
+	rcu_read_unlock();
+
+	return xdst;
+}
+
+static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
+			   int nfheader_len)
+{
+	if (dst->ops->family == AF_INET6) {
+		struct rt6_info *rt = (struct rt6_info *)dst;
+		path->path_cookie = rt6_get_cookie(rt);
+		path->u.rt6.rt6i_nfheader_len = nfheader_len;
+	}
+}
+
+static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
+				const struct flowi *fl)
+{
+	const struct xfrm_policy_afinfo *afinfo =
+		xfrm_policy_get_afinfo(xdst->u.dst.ops->family);
+	int err;
+
+	if (!afinfo)
+		return -EINVAL;
+
+	err = afinfo->fill_dst(xdst, dev, fl);
+
+	rcu_read_unlock();
+
+	return err;
+}
+
+
+/* Allocate chain of dst_entry's, attach known xfrm's, calculate
+ * all the metrics... Shortly, bundle a bundle.
+ */
+
+static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
+					    struct xfrm_state **xfrm,
+					    struct xfrm_dst **bundle,
+					    int nx,
+					    const struct flowi *fl,
+					    struct dst_entry *dst)
+{
+	const struct xfrm_state_afinfo *afinfo;
+	const struct xfrm_mode *inner_mode;
+	struct net *net = xp_net(policy);
+	unsigned long now = jiffies;
+	struct net_device *dev;
+	struct xfrm_dst *xdst_prev = NULL;
+	struct xfrm_dst *xdst0 = NULL;
+	int i = 0;
+	int err;
+	int header_len = 0;
+	int nfheader_len = 0;
+	int trailer_len = 0;
+	int tos;
+	int family = policy->selector.family;
+	xfrm_address_t saddr, daddr;
+
+	xfrm_flowi_addr_get(fl, &saddr, &daddr, family);
+
+	tos = xfrm_get_tos(fl, family);
+
+	dst_hold(dst);
+
+	for (; i < nx; i++) {
+		struct xfrm_dst *xdst = xfrm_alloc_dst(net, family);
+		struct dst_entry *dst1 = &xdst->u.dst;
+
+		err = PTR_ERR(xdst);
+		if (IS_ERR(xdst)) {
+			dst_release(dst);
+			goto put_states;
+		}
+
+		bundle[i] = xdst;
+		if (!xdst_prev)
+			xdst0 = xdst;
+		else
+			/* Ref count is taken during xfrm_alloc_dst()
+			 * No need to do dst_clone() on dst1
+			 */
+			xfrm_dst_set_child(xdst_prev, &xdst->u.dst);
+
+		if (xfrm[i]->sel.family == AF_UNSPEC) {
+			inner_mode = xfrm_ip2inner_mode(xfrm[i],
+							xfrm_af2proto(family));
+			if (!inner_mode) {
+				err = -EAFNOSUPPORT;
+				dst_release(dst);
+				goto put_states;
+			}
+		} else
+			inner_mode = &xfrm[i]->inner_mode;
+
+		xdst->route = dst;
+		dst_copy_metrics(dst1, dst);
+
+		if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
+			__u32 mark = 0;
+			int oif;
+
+			if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
+				mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
+
+			family = xfrm[i]->props.family;
+			oif = fl->flowi_oif ? : fl->flowi_l3mdev;
+			dst = xfrm_dst_lookup(xfrm[i], tos, oif,
+					      &saddr, &daddr, family, mark);
+			err = PTR_ERR(dst);
+			if (IS_ERR(dst))
+				goto put_states;
+		} else
+			dst_hold(dst);
+
+		dst1->xfrm = xfrm[i];
+		xdst->xfrm_genid = xfrm[i]->genid;
+
+		dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
+		dst1->lastuse = now;
+
+		dst1->input = dst_discard;
+
+		rcu_read_lock();
+		afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
+		if (likely(afinfo))
+			dst1->output = afinfo->output;
+		else
+			dst1->output = dst_discard_out;
+		rcu_read_unlock();
+
+		xdst_prev = xdst;
+
+		header_len += xfrm[i]->props.header_len;
+		if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT)
+			nfheader_len += xfrm[i]->props.header_len;
+		trailer_len += xfrm[i]->props.trailer_len;
+	}
+
+	xfrm_dst_set_child(xdst_prev, dst);
+	xdst0->path = dst;
+
+	err = -ENODEV;
+	dev = dst->dev;
+	if (!dev)
+		goto free_dst;
+
+	xfrm_init_path(xdst0, dst, nfheader_len);
+	xfrm_init_pmtu(bundle, nx);
+
+	for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst;
+	     xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) {
+		err = xfrm_fill_dst(xdst_prev, dev, fl);
+		if (err)
+			goto free_dst;
+
+		xdst_prev->u.dst.header_len = header_len;
+		xdst_prev->u.dst.trailer_len = trailer_len;
+		header_len -= xdst_prev->u.dst.xfrm->props.header_len;
+		trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len;
+	}
+
+	return &xdst0->u.dst;
+
+put_states:
+	for (; i < nx; i++)
+		xfrm_state_put(xfrm[i]);
+free_dst:
+	if (xdst0)
+		dst_release_immediate(&xdst0->u.dst);
+
+	return ERR_PTR(err);
+}
+
+static int xfrm_expand_policies(const struct flowi *fl, u16 family,
+				struct xfrm_policy **pols,
+				int *num_pols, int *num_xfrms)
+{
+	int i;
+
+	if (*num_pols == 0 || !pols[0]) {
+		*num_pols = 0;
+		*num_xfrms = 0;
+		return 0;
+	}
+	if (IS_ERR(pols[0])) {
+		*num_pols = 0;
+		return PTR_ERR(pols[0]);
+	}
+
+	*num_xfrms = pols[0]->xfrm_nr;
+
+#ifdef CONFIG_XFRM_SUB_POLICY
+	if (pols[0]->action == XFRM_POLICY_ALLOW &&
+	    pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
+		pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]),
+						    XFRM_POLICY_TYPE_MAIN,
+						    fl, family,
+						    XFRM_POLICY_OUT,
+						    pols[0]->if_id);
+		if (pols[1]) {
+			if (IS_ERR(pols[1])) {
+				xfrm_pols_put(pols, *num_pols);
+				*num_pols = 0;
+				return PTR_ERR(pols[1]);
+			}
+			(*num_pols)++;
+			(*num_xfrms) += pols[1]->xfrm_nr;
+		}
+	}
+#endif
+	for (i = 0; i < *num_pols; i++) {
+		if (pols[i]->action != XFRM_POLICY_ALLOW) {
+			*num_xfrms = -1;
+			break;
+		}
+	}
+
+	return 0;
+
+}
+
+static struct xfrm_dst *
+xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
+			       const struct flowi *fl, u16 family,
+			       struct dst_entry *dst_orig)
+{
+	struct net *net = xp_net(pols[0]);
+	struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
+	struct xfrm_dst *bundle[XFRM_MAX_DEPTH];
+	struct xfrm_dst *xdst;
+	struct dst_entry *dst;
+	int err;
+
+	/* Try to instantiate a bundle */
+	err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family);
+	if (err <= 0) {
+		if (err == 0)
+			return NULL;
+
+		if (err != -EAGAIN)
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+		return ERR_PTR(err);
+	}
+
+	dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig);
+	if (IS_ERR(dst)) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
+		return ERR_CAST(dst);
+	}
+
+	xdst = (struct xfrm_dst *)dst;
+	xdst->num_xfrms = err;
+	xdst->num_pols = num_pols;
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
+	xdst->policy_genid = atomic_read(&pols[0]->genid);
+
+	return xdst;
+}
+
+static void xfrm_policy_queue_process(struct timer_list *t)
+{
+	struct sk_buff *skb;
+	struct sock *sk;
+	struct dst_entry *dst;
+	struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer);
+	struct net *net = xp_net(pol);
+	struct xfrm_policy_queue *pq = &pol->polq;
+	struct flowi fl;
+	struct sk_buff_head list;
+	__u32 skb_mark;
+
+	spin_lock(&pq->hold_queue.lock);
+	skb = skb_peek(&pq->hold_queue);
+	if (!skb) {
+		spin_unlock(&pq->hold_queue.lock);
+		goto out;
+	}
+	dst = skb_dst(skb);
+	sk = skb->sk;
+
+	/* Fixup the mark to support VTI. */
+	skb_mark = skb->mark;
+	skb->mark = pol->mark.v;
+	xfrm_decode_session(skb, &fl, dst->ops->family);
+	skb->mark = skb_mark;
+	spin_unlock(&pq->hold_queue.lock);
+
+	dst_hold(xfrm_dst_path(dst));
+	dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE);
+	if (IS_ERR(dst))
+		goto purge_queue;
+
+	if (dst->flags & DST_XFRM_QUEUE) {
+		dst_release(dst);
+
+		if (pq->timeout >= XFRM_QUEUE_TMO_MAX)
+			goto purge_queue;
+
+		pq->timeout = pq->timeout << 1;
+		if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout))
+			xfrm_pol_hold(pol);
+		goto out;
+	}
+
+	dst_release(dst);
+
+	__skb_queue_head_init(&list);
+
+	spin_lock(&pq->hold_queue.lock);
+	pq->timeout = 0;
+	skb_queue_splice_init(&pq->hold_queue, &list);
+	spin_unlock(&pq->hold_queue.lock);
+
+	while (!skb_queue_empty(&list)) {
+		skb = __skb_dequeue(&list);
+
+		/* Fixup the mark to support VTI. */
+		skb_mark = skb->mark;
+		skb->mark = pol->mark.v;
+		xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family);
+		skb->mark = skb_mark;
+
+		dst_hold(xfrm_dst_path(skb_dst(skb)));
+		dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0);
+		if (IS_ERR(dst)) {
+			kfree_skb(skb);
+			continue;
+		}
+
+		nf_reset_ct(skb);
+		skb_dst_drop(skb);
+		skb_dst_set(skb, dst);
+
+		dst_output(net, skb->sk, skb);
+	}
+
+out:
+	xfrm_pol_put(pol);
+	return;
+
+purge_queue:
+	pq->timeout = 0;
+	skb_queue_purge(&pq->hold_queue);
+	xfrm_pol_put(pol);
+}
+
+static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	unsigned long sched_next;
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
+	struct xfrm_policy *pol = xdst->pols[0];
+	struct xfrm_policy_queue *pq = &pol->polq;
+
+	if (unlikely(skb_fclone_busy(sk, skb))) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) {
+		kfree_skb(skb);
+		return -EAGAIN;
+	}
+
+	skb_dst_force(skb);
+
+	spin_lock_bh(&pq->hold_queue.lock);
+
+	if (!pq->timeout)
+		pq->timeout = XFRM_QUEUE_TMO_MIN;
+
+	sched_next = jiffies + pq->timeout;
+
+	if (del_timer(&pq->hold_timer)) {
+		if (time_before(pq->hold_timer.expires, sched_next))
+			sched_next = pq->hold_timer.expires;
+		xfrm_pol_put(pol);
+	}
+
+	__skb_queue_tail(&pq->hold_queue, skb);
+	if (!mod_timer(&pq->hold_timer, sched_next))
+		xfrm_pol_hold(pol);
+
+	spin_unlock_bh(&pq->hold_queue.lock);
+
+	return 0;
+}
+
+static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
+						 struct xfrm_flo *xflo,
+						 const struct flowi *fl,
+						 int num_xfrms,
+						 u16 family)
+{
+	int err;
+	struct net_device *dev;
+	struct dst_entry *dst;
+	struct dst_entry *dst1;
+	struct xfrm_dst *xdst;
+
+	xdst = xfrm_alloc_dst(net, family);
+	if (IS_ERR(xdst))
+		return xdst;
+
+	if (!(xflo->flags & XFRM_LOOKUP_QUEUE) ||
+	    net->xfrm.sysctl_larval_drop ||
+	    num_xfrms <= 0)
+		return xdst;
+
+	dst = xflo->dst_orig;
+	dst1 = &xdst->u.dst;
+	dst_hold(dst);
+	xdst->route = dst;
+
+	dst_copy_metrics(dst1, dst);
+
+	dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
+	dst1->flags |= DST_XFRM_QUEUE;
+	dst1->lastuse = jiffies;
+
+	dst1->input = dst_discard;
+	dst1->output = xdst_queue_output;
+
+	dst_hold(dst);
+	xfrm_dst_set_child(xdst, dst);
+	xdst->path = dst;
+
+	xfrm_init_path((struct xfrm_dst *)dst1, dst, 0);
+
+	err = -ENODEV;
+	dev = dst->dev;
+	if (!dev)
+		goto free_dst;
+
+	err = xfrm_fill_dst(xdst, dev, fl);
+	if (err)
+		goto free_dst;
+
+out:
+	return xdst;
+
+free_dst:
+	dst_release(dst1);
+	xdst = ERR_PTR(err);
+	goto out;
+}
+
+static struct xfrm_dst *xfrm_bundle_lookup(struct net *net,
+					   const struct flowi *fl,
+					   u16 family, u8 dir,
+					   struct xfrm_flo *xflo, u32 if_id)
+{
+	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
+	int num_pols = 0, num_xfrms = 0, err;
+	struct xfrm_dst *xdst;
+
+	/* Resolve policies to use if we couldn't get them from
+	 * previous cache entry */
+	num_pols = 1;
+	pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id);
+	err = xfrm_expand_policies(fl, family, pols,
+					   &num_pols, &num_xfrms);
+	if (err < 0)
+		goto inc_error;
+	if (num_pols == 0)
+		return NULL;
+	if (num_xfrms <= 0)
+		goto make_dummy_bundle;
+
+	xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
+					      xflo->dst_orig);
+	if (IS_ERR(xdst)) {
+		err = PTR_ERR(xdst);
+		if (err == -EREMOTE) {
+			xfrm_pols_put(pols, num_pols);
+			return NULL;
+		}
+
+		if (err != -EAGAIN)
+			goto error;
+		goto make_dummy_bundle;
+	} else if (xdst == NULL) {
+		num_xfrms = 0;
+		goto make_dummy_bundle;
+	}
+
+	return xdst;
+
+make_dummy_bundle:
+	/* We found policies, but there's no bundles to instantiate:
+	 * either because the policy blocks, has no transformations or
+	 * we could not build template (no xfrm_states).*/
+	xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family);
+	if (IS_ERR(xdst)) {
+		xfrm_pols_put(pols, num_pols);
+		return ERR_CAST(xdst);
+	}
+	xdst->num_pols = num_pols;
+	xdst->num_xfrms = num_xfrms;
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
+
+	return xdst;
+
+inc_error:
+	XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+error:
+	xfrm_pols_put(pols, num_pols);
+	return ERR_PTR(err);
+}
+
+static struct dst_entry *make_blackhole(struct net *net, u16 family,
+					struct dst_entry *dst_orig)
+{
+	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+	struct dst_entry *ret;
+
+	if (!afinfo) {
+		dst_release(dst_orig);
+		return ERR_PTR(-EINVAL);
+	} else {
+		ret = afinfo->blackhole_route(net, dst_orig);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/* Finds/creates a bundle for given flow and if_id
+ *
+ * At the moment we eat a raw IP route. Mostly to speed up lookups
+ * on interfaces with disabled IPsec.
+ *
+ * xfrm_lookup uses an if_id of 0 by default, and is provided for
+ * compatibility
+ */
+struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
+					struct dst_entry *dst_orig,
+					const struct flowi *fl,
+					const struct sock *sk,
+					int flags, u32 if_id)
+{
+	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
+	struct xfrm_dst *xdst;
+	struct dst_entry *dst, *route;
+	u16 family = dst_orig->ops->family;
+	u8 dir = XFRM_POLICY_OUT;
+	int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
+
+	dst = NULL;
+	xdst = NULL;
+	route = NULL;
+
+	sk = sk_const_to_full_sk(sk);
+	if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
+		num_pols = 1;
+		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family,
+						if_id);
+		err = xfrm_expand_policies(fl, family, pols,
+					   &num_pols, &num_xfrms);
+		if (err < 0)
+			goto dropdst;
+
+		if (num_pols) {
+			if (num_xfrms <= 0) {
+				drop_pols = num_pols;
+				goto no_transform;
+			}
+
+			xdst = xfrm_resolve_and_create_bundle(
+					pols, num_pols, fl,
+					family, dst_orig);
+
+			if (IS_ERR(xdst)) {
+				xfrm_pols_put(pols, num_pols);
+				err = PTR_ERR(xdst);
+				if (err == -EREMOTE)
+					goto nopol;
+
+				goto dropdst;
+			} else if (xdst == NULL) {
+				num_xfrms = 0;
+				drop_pols = num_pols;
+				goto no_transform;
+			}
+
+			route = xdst->route;
+		}
+	}
+
+	if (xdst == NULL) {
+		struct xfrm_flo xflo;
+
+		xflo.dst_orig = dst_orig;
+		xflo.flags = flags;
+
+		/* To accelerate a bit...  */
+		if (!if_id && ((dst_orig->flags & DST_NOXFRM) ||
+			       !net->xfrm.policy_count[XFRM_POLICY_OUT]))
+			goto nopol;
+
+		xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id);
+		if (xdst == NULL)
+			goto nopol;
+		if (IS_ERR(xdst)) {
+			err = PTR_ERR(xdst);
+			goto dropdst;
+		}
+
+		num_pols = xdst->num_pols;
+		num_xfrms = xdst->num_xfrms;
+		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols);
+		route = xdst->route;
+	}
+
+	dst = &xdst->u.dst;
+	if (route == NULL && num_xfrms > 0) {
+		/* The only case when xfrm_bundle_lookup() returns a
+		 * bundle with null route, is when the template could
+		 * not be resolved. It means policies are there, but
+		 * bundle could not be created, since we don't yet
+		 * have the xfrm_state's. We need to wait for KM to
+		 * negotiate new SA's or bail out with error.*/
+		if (net->xfrm.sysctl_larval_drop) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
+			err = -EREMOTE;
+			goto error;
+		}
+
+		err = -EAGAIN;
+
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
+		goto error;
+	}
+
+no_transform:
+	if (num_pols == 0)
+		goto nopol;
+
+	if ((flags & XFRM_LOOKUP_ICMP) &&
+	    !(pols[0]->flags & XFRM_POLICY_ICMP)) {
+		err = -ENOENT;
+		goto error;
+	}
+
+	for (i = 0; i < num_pols; i++)
+		WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds());
+
+	if (num_xfrms < 0) {
+		/* Prohibit the flow */
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK);
+		err = -EPERM;
+		goto error;
+	} else if (num_xfrms > 0) {
+		/* Flow transformed */
+		dst_release(dst_orig);
+	} else {
+		/* Flow passes untransformed */
+		dst_release(dst);
+		dst = dst_orig;
+	}
+ok:
+	xfrm_pols_put(pols, drop_pols);
+	if (dst && dst->xfrm &&
+	    dst->xfrm->props.mode == XFRM_MODE_TUNNEL)
+		dst->flags |= DST_XFRM_TUNNEL;
+	return dst;
+
+nopol:
+	if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
+	    net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
+		err = -EPERM;
+		goto error;
+	}
+	if (!(flags & XFRM_LOOKUP_ICMP)) {
+		dst = dst_orig;
+		goto ok;
+	}
+	err = -ENOENT;
+error:
+	dst_release(dst);
+dropdst:
+	if (!(flags & XFRM_LOOKUP_KEEP_DST_REF))
+		dst_release(dst_orig);
+	xfrm_pols_put(pols, drop_pols);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(xfrm_lookup_with_ifid);
+
+/* Main function: finds/creates a bundle for given flow.
+ *
+ * At the moment we eat a raw IP route. Mostly to speed up lookups
+ * on interfaces with disabled IPsec.
+ */
+struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
+			      const struct flowi *fl, const struct sock *sk,
+			      int flags)
+{
+	return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0);
+}
+EXPORT_SYMBOL(xfrm_lookup);
+
+/* Callers of xfrm_lookup_route() must ensure a call to dst_output().
+ * Otherwise we may send out blackholed packets.
+ */
+struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
+				    const struct flowi *fl,
+				    const struct sock *sk, int flags)
+{
+	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk,
+					    flags | XFRM_LOOKUP_QUEUE |
+					    XFRM_LOOKUP_KEEP_DST_REF);
+
+	if (PTR_ERR(dst) == -EREMOTE)
+		return make_blackhole(net, dst_orig->ops->family, dst_orig);
+
+	if (IS_ERR(dst))
+		dst_release(dst_orig);
+
+	return dst;
+}
+EXPORT_SYMBOL(xfrm_lookup_route);
+
+static inline int
+xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
+{
+	struct sec_path *sp = skb_sec_path(skb);
+	struct xfrm_state *x;
+
+	if (!sp || idx < 0 || idx >= sp->len)
+		return 0;
+	x = sp->xvec[idx];
+	if (!x->type->reject)
+		return 0;
+	return x->type->reject(x, skb, fl);
+}
+
+/* When skb is transformed back to its "native" form, we have to
+ * check policy restrictions. At the moment we make this in maximally
+ * stupid way. Shame on me. :-) Of course, connected sockets must
+ * have policy cached at them.
+ */
+
+static inline int
+xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x,
+	      unsigned short family, u32 if_id)
+{
+	if (xfrm_state_kern(x))
+		return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family);
+	return	x->id.proto == tmpl->id.proto &&
+		(x->id.spi == tmpl->id.spi || !tmpl->id.spi) &&
+		(x->props.reqid == tmpl->reqid || !tmpl->reqid) &&
+		x->props.mode == tmpl->mode &&
+		(tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) ||
+		 !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) &&
+		!(x->props.mode != XFRM_MODE_TRANSPORT &&
+		  xfrm_state_addr_cmp(tmpl, x, family)) &&
+		(if_id == 0 || if_id == x->if_id);
+}
+
+/*
+ * 0 or more than 0 is returned when validation is succeeded (either bypass
+ * because of optional transport mode, or next index of the matched secpath
+ * state with the template.
+ * -1 is returned when no matching template is found.
+ * Otherwise "-2 - errored_index" is returned.
+ */
+static inline int
+xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start,
+	       unsigned short family, u32 if_id)
+{
+	int idx = start;
+
+	if (tmpl->optional) {
+		if (tmpl->mode == XFRM_MODE_TRANSPORT)
+			return start;
+	} else
+		start = -1;
+	for (; idx < sp->len; idx++) {
+		if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id))
+			return ++idx;
+		if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) {
+			if (idx < sp->verified_cnt) {
+				/* Secpath entry previously verified, consider optional and
+				 * continue searching
+				 */
+				continue;
+			}
+
+			if (start == -1)
+				start = -2-idx;
+			break;
+		}
+	}
+	return start;
+}
+
+static void
+decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	int ihl = iph->ihl;
+	u8 *xprth = skb_network_header(skb) + ihl * 4;
+	struct flowi4 *fl4 = &fl->u.ip4;
+	int oif = 0;
+
+	if (skb_dst(skb) && skb_dst(skb)->dev)
+		oif = skb_dst(skb)->dev->ifindex;
+
+	memset(fl4, 0, sizeof(struct flowi4));
+	fl4->flowi4_mark = skb->mark;
+	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
+
+	fl4->flowi4_proto = iph->protocol;
+	fl4->daddr = reverse ? iph->saddr : iph->daddr;
+	fl4->saddr = reverse ? iph->daddr : iph->saddr;
+	fl4->flowi4_tos = iph->tos & ~INET_ECN_MASK;
+
+	if (!ip_is_fragment(iph)) {
+		switch (iph->protocol) {
+		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ports;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				ports = (__be16 *)xprth;
+
+				fl4->fl4_sport = ports[!!reverse];
+				fl4->fl4_dport = ports[!reverse];
+			}
+			break;
+		case IPPROTO_ICMP:
+			if (xprth + 2 < skb->data ||
+			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
+				u8 *icmp;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				icmp = xprth;
+
+				fl4->fl4_icmp_type = icmp[0];
+				fl4->fl4_icmp_code = icmp[1];
+			}
+			break;
+		case IPPROTO_GRE:
+			if (xprth + 12 < skb->data ||
+			    pskb_may_pull(skb, xprth + 12 - skb->data)) {
+				__be16 *greflags;
+				__be32 *gre_hdr;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				greflags = (__be16 *)xprth;
+				gre_hdr = (__be32 *)xprth;
+
+				if (greflags[0] & GRE_KEY) {
+					if (greflags[0] & GRE_CSUM)
+						gre_hdr++;
+					fl4->fl4_gre_key = gre_hdr[1];
+				}
+			}
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static void
+decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
+{
+	struct flowi6 *fl6 = &fl->u.ip6;
+	int onlyproto = 0;
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	u32 offset = sizeof(*hdr);
+	struct ipv6_opt_hdr *exthdr;
+	const unsigned char *nh = skb_network_header(skb);
+	u16 nhoff = IP6CB(skb)->nhoff;
+	int oif = 0;
+	u8 nexthdr;
+
+	if (!nhoff)
+		nhoff = offsetof(struct ipv6hdr, nexthdr);
+
+	nexthdr = nh[nhoff];
+
+	if (skb_dst(skb) && skb_dst(skb)->dev)
+		oif = skb_dst(skb)->dev->ifindex;
+
+	memset(fl6, 0, sizeof(struct flowi6));
+	fl6->flowi6_mark = skb->mark;
+	fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
+
+	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
+	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
+
+	while (nh + offset + sizeof(*exthdr) < skb->data ||
+	       pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) {
+		nh = skb_network_header(skb);
+		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
+
+		switch (nexthdr) {
+		case NEXTHDR_FRAGMENT:
+			onlyproto = 1;
+			fallthrough;
+		case NEXTHDR_ROUTING:
+		case NEXTHDR_HOP:
+		case NEXTHDR_DEST:
+			offset += ipv6_optlen(exthdr);
+			nexthdr = exthdr->nexthdr;
+			break;
+		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
+			if (!onlyproto && (nh + offset + 4 < skb->data ||
+			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
+				__be16 *ports;
+
+				nh = skb_network_header(skb);
+				ports = (__be16 *)(nh + offset);
+				fl6->fl6_sport = ports[!!reverse];
+				fl6->fl6_dport = ports[!reverse];
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+		case IPPROTO_ICMPV6:
+			if (!onlyproto && (nh + offset + 2 < skb->data ||
+			    pskb_may_pull(skb, nh + offset + 2 - skb->data))) {
+				u8 *icmp;
+
+				nh = skb_network_header(skb);
+				icmp = (u8 *)(nh + offset);
+				fl6->fl6_icmp_type = icmp[0];
+				fl6->fl6_icmp_code = icmp[1];
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+		case IPPROTO_GRE:
+			if (!onlyproto &&
+			    (nh + offset + 12 < skb->data ||
+			     pskb_may_pull(skb, nh + offset + 12 - skb->data))) {
+				struct gre_base_hdr *gre_hdr;
+				__be32 *gre_key;
+
+				nh = skb_network_header(skb);
+				gre_hdr = (struct gre_base_hdr *)(nh + offset);
+				gre_key = (__be32 *)(gre_hdr + 1);
+
+				if (gre_hdr->flags & GRE_KEY) {
+					if (gre_hdr->flags & GRE_CSUM)
+						gre_key++;
+					fl6->fl6_gre_key = *gre_key;
+				}
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+		case IPPROTO_MH:
+			offset += ipv6_optlen(exthdr);
+			if (!onlyproto && (nh + offset + 3 < skb->data ||
+			    pskb_may_pull(skb, nh + offset + 3 - skb->data))) {
+				struct ip6_mh *mh;
+
+				nh = skb_network_header(skb);
+				mh = (struct ip6_mh *)(nh + offset);
+				fl6->fl6_mh_type = mh->ip6mh_type;
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+#endif
+		default:
+			fl6->flowi6_proto = nexthdr;
+			return;
+		}
+	}
+}
+#endif
+
+int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
+			  unsigned int family, int reverse)
+{
+	switch (family) {
+	case AF_INET:
+		decode_session4(skb, fl, reverse);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		decode_session6(skb, fl, reverse);
+		break;
+#endif
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	return security_xfrm_decode_session(skb, &fl->flowi_secid);
+}
+EXPORT_SYMBOL(__xfrm_decode_session);
+
+static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int *idxp)
+{
+	for (; k < sp->len; k++) {
+		if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) {
+			*idxp = k;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
+			unsigned short family)
+{
+	struct net *net = dev_net(skb->dev);
+	struct xfrm_policy *pol;
+	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
+	int npols = 0;
+	int xfrm_nr;
+	int pi;
+	int reverse;
+	struct flowi fl;
+	int xerr_idx = -1;
+	const struct xfrm_if_cb *ifcb;
+	struct sec_path *sp;
+	u32 if_id = 0;
+
+	rcu_read_lock();
+	ifcb = xfrm_if_get_cb();
+
+	if (ifcb) {
+		struct xfrm_if_decode_session_result r;
+
+		if (ifcb->decode_session(skb, family, &r)) {
+			if_id = r.if_id;
+			net = r.net;
+		}
+	}
+	rcu_read_unlock();
+
+	reverse = dir & ~XFRM_POLICY_MASK;
+	dir &= XFRM_POLICY_MASK;
+
+	if (__xfrm_decode_session(skb, &fl, family, reverse) < 0) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
+		return 0;
+	}
+
+	nf_nat_decode_session(skb, &fl, family);
+
+	/* First, check used SA against their selectors. */
+	sp = skb_sec_path(skb);
+	if (sp) {
+		int i;
+
+		for (i = sp->len - 1; i >= 0; i--) {
+			struct xfrm_state *x = sp->xvec[i];
+			if (!xfrm_selector_match(&x->sel, &fl, family)) {
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
+				return 0;
+			}
+		}
+	}
+
+	pol = NULL;
+	sk = sk_to_full_sk(sk);
+	if (sk && sk->sk_policy[dir]) {
+		pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id);
+		if (IS_ERR(pol)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
+			return 0;
+		}
+	}
+
+	if (!pol)
+		pol = xfrm_policy_lookup(net, &fl, family, dir, if_id);
+
+	if (IS_ERR(pol)) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
+		return 0;
+	}
+
+	if (!pol) {
+		if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
+			return 0;
+		}
+
+		if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) {
+			xfrm_secpath_reject(xerr_idx, skb, &fl);
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
+			return 0;
+		}
+		return 1;
+	}
+
+	/* This lockless write can happen from different cpus. */
+	WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds());
+
+	pols[0] = pol;
+	npols++;
+#ifdef CONFIG_XFRM_SUB_POLICY
+	if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
+		pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN,
+						    &fl, family,
+						    XFRM_POLICY_IN, if_id);
+		if (pols[1]) {
+			if (IS_ERR(pols[1])) {
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
+				xfrm_pol_put(pols[0]);
+				return 0;
+			}
+			/* This write can happen from different cpus. */
+			WRITE_ONCE(pols[1]->curlft.use_time,
+				   ktime_get_real_seconds());
+			npols++;
+		}
+	}
+#endif
+
+	if (pol->action == XFRM_POLICY_ALLOW) {
+		static struct sec_path dummy;
+		struct xfrm_tmpl *tp[XFRM_MAX_DEPTH];
+		struct xfrm_tmpl *stp[XFRM_MAX_DEPTH];
+		struct xfrm_tmpl **tpp = tp;
+		int ti = 0;
+		int i, k;
+
+		sp = skb_sec_path(skb);
+		if (!sp)
+			sp = &dummy;
+
+		for (pi = 0; pi < npols; pi++) {
+			if (pols[pi] != pol &&
+			    pols[pi]->action != XFRM_POLICY_ALLOW) {
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK);
+				goto reject;
+			}
+			if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) {
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
+				goto reject_error;
+			}
+			for (i = 0; i < pols[pi]->xfrm_nr; i++)
+				tpp[ti++] = &pols[pi]->xfrm_vec[i];
+		}
+		xfrm_nr = ti;
+
+		if (npols > 1) {
+			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
+			tpp = stp;
+		}
+
+		/* For each tunnel xfrm, find the first matching tmpl.
+		 * For each tmpl before that, find corresponding xfrm.
+		 * Order is _important_. Later we will implement
+		 * some barriers, but at the moment barriers
+		 * are implied between each two transformations.
+		 * Upon success, marks secpath entries as having been
+		 * verified to allow them to be skipped in future policy
+		 * checks (e.g. nested tunnels).
+		 */
+		for (i = xfrm_nr-1, k = 0; i >= 0; i--) {
+			k = xfrm_policy_ok(tpp[i], sp, k, family, if_id);
+			if (k < 0) {
+				if (k < -1)
+					/* "-2 - errored_index" returned */
+					xerr_idx = -(2+k);
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH);
+				goto reject;
+			}
+		}
+
+		if (secpath_has_nontransport(sp, k, &xerr_idx)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH);
+			goto reject;
+		}
+
+		xfrm_pols_put(pols, npols);
+		sp->verified_cnt = k;
+
+		return 1;
+	}
+	XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK);
+
+reject:
+	xfrm_secpath_reject(xerr_idx, skb, &fl);
+reject_error:
+	xfrm_pols_put(pols, npols);
+	return 0;
+}
+EXPORT_SYMBOL(__xfrm_policy_check);
+
+int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
+{
+	struct net *net = dev_net(skb->dev);
+	struct flowi fl;
+	struct dst_entry *dst;
+	int res = 1;
+
+	if (xfrm_decode_session(skb, &fl, family) < 0) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR);
+		return 0;
+	}
+
+	skb_dst_force(skb);
+	if (!skb_dst(skb)) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR);
+		return 0;
+	}
+
+	dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE);
+	if (IS_ERR(dst)) {
+		res = 0;
+		dst = NULL;
+	}
+	skb_dst_set(skb, dst);
+	return res;
+}
+EXPORT_SYMBOL(__xfrm_route_forward);
+
+/* Optimize later using cookies and generation ids. */
+
+static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie)
+{
+	/* Code (such as __xfrm4_bundle_create()) sets dst->obsolete
+	 * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to
+	 * get validated by dst_ops->check on every use.  We do this
+	 * because when a normal route referenced by an XFRM dst is
+	 * obsoleted we do not go looking around for all parent
+	 * referencing XFRM dsts so that we can invalidate them.  It
+	 * is just too much work.  Instead we make the checks here on
+	 * every use.  For example:
+	 *
+	 *	XFRM dst A --> IPv4 dst X
+	 *
+	 * X is the "xdst->route" of A (X is also the "dst->path" of A
+	 * in this example).  If X is marked obsolete, "A" will not
+	 * notice.  That's what we are validating here via the
+	 * stale_bundle() check.
+	 *
+	 * When a dst is removed from the fib tree, DST_OBSOLETE_DEAD will
+	 * be marked on it.
+	 * This will force stale_bundle() to fail on any xdst bundle with
+	 * this dst linked in it.
+	 */
+	if (dst->obsolete < 0 && !stale_bundle(dst))
+		return dst;
+
+	return NULL;
+}
+
+static int stale_bundle(struct dst_entry *dst)
+{
+	return !xfrm_bundle_ok((struct xfrm_dst *)dst);
+}
+
+void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
+{
+	while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) {
+		dst->dev = blackhole_netdev;
+		dev_hold(dst->dev);
+		dev_put(dev);
+	}
+}
+EXPORT_SYMBOL(xfrm_dst_ifdown);
+
+static void xfrm_link_failure(struct sk_buff *skb)
+{
+	/* Impossible. Such dst must be popped before reaches point of failure. */
+}
+
+static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst)
+{
+	if (dst) {
+		if (dst->obsolete) {
+			dst_release(dst);
+			dst = NULL;
+		}
+	}
+	return dst;
+}
+
+static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr)
+{
+	while (nr--) {
+		struct xfrm_dst *xdst = bundle[nr];
+		u32 pmtu, route_mtu_cached;
+		struct dst_entry *dst;
+
+		dst = &xdst->u.dst;
+		pmtu = dst_mtu(xfrm_dst_child(dst));
+		xdst->child_mtu_cached = pmtu;
+
+		pmtu = xfrm_state_mtu(dst->xfrm, pmtu);
+
+		route_mtu_cached = dst_mtu(xdst->route);
+		xdst->route_mtu_cached = route_mtu_cached;
+
+		if (pmtu > route_mtu_cached)
+			pmtu = route_mtu_cached;
+
+		dst_metric_set(dst, RTAX_MTU, pmtu);
+	}
+}
+
+/* Check that the bundle accepts the flow and its components are
+ * still valid.
+ */
+
+static int xfrm_bundle_ok(struct xfrm_dst *first)
+{
+	struct xfrm_dst *bundle[XFRM_MAX_DEPTH];
+	struct dst_entry *dst = &first->u.dst;
+	struct xfrm_dst *xdst;
+	int start_from, nr;
+	u32 mtu;
+
+	if (!dst_check(xfrm_dst_path(dst), ((struct xfrm_dst *)dst)->path_cookie) ||
+	    (dst->dev && !netif_running(dst->dev)))
+		return 0;
+
+	if (dst->flags & DST_XFRM_QUEUE)
+		return 1;
+
+	start_from = nr = 0;
+	do {
+		struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
+
+		if (dst->xfrm->km.state != XFRM_STATE_VALID)
+			return 0;
+		if (xdst->xfrm_genid != dst->xfrm->genid)
+			return 0;
+		if (xdst->num_pols > 0 &&
+		    xdst->policy_genid != atomic_read(&xdst->pols[0]->genid))
+			return 0;
+
+		bundle[nr++] = xdst;
+
+		mtu = dst_mtu(xfrm_dst_child(dst));
+		if (xdst->child_mtu_cached != mtu) {
+			start_from = nr;
+			xdst->child_mtu_cached = mtu;
+		}
+
+		if (!dst_check(xdst->route, xdst->route_cookie))
+			return 0;
+		mtu = dst_mtu(xdst->route);
+		if (xdst->route_mtu_cached != mtu) {
+			start_from = nr;
+			xdst->route_mtu_cached = mtu;
+		}
+
+		dst = xfrm_dst_child(dst);
+	} while (dst->xfrm);
+
+	if (likely(!start_from))
+		return 1;
+
+	xdst = bundle[start_from - 1];
+	mtu = xdst->child_mtu_cached;
+	while (start_from--) {
+		dst = &xdst->u.dst;
+
+		mtu = xfrm_state_mtu(dst->xfrm, mtu);
+		if (mtu > xdst->route_mtu_cached)
+			mtu = xdst->route_mtu_cached;
+		dst_metric_set(dst, RTAX_MTU, mtu);
+		if (!start_from)
+			break;
+
+		xdst = bundle[start_from - 1];
+		xdst->child_mtu_cached = mtu;
+	}
+
+	return 1;
+}
+
+static unsigned int xfrm_default_advmss(const struct dst_entry *dst)
+{
+	return dst_metric_advmss(xfrm_dst_path(dst));
+}
+
+static unsigned int xfrm_mtu(const struct dst_entry *dst)
+{
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst_mtu(xfrm_dst_path(dst));
+}
+
+static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst,
+					const void *daddr)
+{
+	while (dst->xfrm) {
+		const struct xfrm_state *xfrm = dst->xfrm;
+
+		dst = xfrm_dst_child(dst);
+
+		if (xfrm->props.mode == XFRM_MODE_TRANSPORT)
+			continue;
+		if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR)
+			daddr = xfrm->coaddr;
+		else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR))
+			daddr = &xfrm->id.daddr;
+	}
+	return daddr;
+}
+
+static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
+					   struct sk_buff *skb,
+					   const void *daddr)
+{
+	const struct dst_entry *path = xfrm_dst_path(dst);
+
+	if (!skb)
+		daddr = xfrm_get_dst_nexthop(dst, daddr);
+	return path->ops->neigh_lookup(path, skb, daddr);
+}
+
+static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr)
+{
+	const struct dst_entry *path = xfrm_dst_path(dst);
+
+	daddr = xfrm_get_dst_nexthop(dst, daddr);
+	path->ops->confirm_neigh(path, daddr);
+}
+
+int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family)
+{
+	int err = 0;
+
+	if (WARN_ON(family >= ARRAY_SIZE(xfrm_policy_afinfo)))
+		return -EAFNOSUPPORT;
+
+	spin_lock(&xfrm_policy_afinfo_lock);
+	if (unlikely(xfrm_policy_afinfo[family] != NULL))
+		err = -EEXIST;
+	else {
+		struct dst_ops *dst_ops = afinfo->dst_ops;
+		if (likely(dst_ops->kmem_cachep == NULL))
+			dst_ops->kmem_cachep = xfrm_dst_cache;
+		if (likely(dst_ops->check == NULL))
+			dst_ops->check = xfrm_dst_check;
+		if (likely(dst_ops->default_advmss == NULL))
+			dst_ops->default_advmss = xfrm_default_advmss;
+		if (likely(dst_ops->mtu == NULL))
+			dst_ops->mtu = xfrm_mtu;
+		if (likely(dst_ops->negative_advice == NULL))
+			dst_ops->negative_advice = xfrm_negative_advice;
+		if (likely(dst_ops->link_failure == NULL))
+			dst_ops->link_failure = xfrm_link_failure;
+		if (likely(dst_ops->neigh_lookup == NULL))
+			dst_ops->neigh_lookup = xfrm_neigh_lookup;
+		if (likely(!dst_ops->confirm_neigh))
+			dst_ops->confirm_neigh = xfrm_confirm_neigh;
+		rcu_assign_pointer(xfrm_policy_afinfo[family], afinfo);
+	}
+	spin_unlock(&xfrm_policy_afinfo_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(xfrm_policy_register_afinfo);
+
+void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo)
+{
+	struct dst_ops *dst_ops = afinfo->dst_ops;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) {
+		if (xfrm_policy_afinfo[i] != afinfo)
+			continue;
+		RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL);
+		break;
+	}
+
+	synchronize_rcu();
+
+	dst_ops->kmem_cachep = NULL;
+	dst_ops->check = NULL;
+	dst_ops->negative_advice = NULL;
+	dst_ops->link_failure = NULL;
+}
+EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
+
+void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb)
+{
+	spin_lock(&xfrm_if_cb_lock);
+	rcu_assign_pointer(xfrm_if_cb, ifcb);
+	spin_unlock(&xfrm_if_cb_lock);
+}
+EXPORT_SYMBOL(xfrm_if_register_cb);
+
+void xfrm_if_unregister_cb(void)
+{
+	RCU_INIT_POINTER(xfrm_if_cb, NULL);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL(xfrm_if_unregister_cb);
+
+#ifdef CONFIG_XFRM_STATISTICS
+static int __net_init xfrm_statistics_init(struct net *net)
+{
+	int rv;
+	net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib);
+	if (!net->mib.xfrm_statistics)
+		return -ENOMEM;
+	rv = xfrm_proc_init(net);
+	if (rv < 0)
+		free_percpu(net->mib.xfrm_statistics);
+	return rv;
+}
+
+static void xfrm_statistics_fini(struct net *net)
+{
+	xfrm_proc_fini(net);
+	free_percpu(net->mib.xfrm_statistics);
+}
+#else
+static int __net_init xfrm_statistics_init(struct net *net)
+{
+	return 0;
+}
+
+static void xfrm_statistics_fini(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm_policy_init(struct net *net)
+{
+	unsigned int hmask, sz;
+	int dir, err;
+
+	if (net_eq(net, &init_net)) {
+		xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache",
+					   sizeof(struct xfrm_dst),
+					   0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
+					   NULL);
+		err = rhashtable_init(&xfrm_policy_inexact_table,
+				      &xfrm_pol_inexact_params);
+		BUG_ON(err);
+	}
+
+	hmask = 8 - 1;
+	sz = (hmask+1) * sizeof(struct hlist_head);
+
+	net->xfrm.policy_byidx = xfrm_hash_alloc(sz);
+	if (!net->xfrm.policy_byidx)
+		goto out_byidx;
+	net->xfrm.policy_idx_hmask = hmask;
+
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
+		struct xfrm_policy_hash *htab;
+
+		net->xfrm.policy_count[dir] = 0;
+		net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0;
+		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
+
+		htab = &net->xfrm.policy_bydst[dir];
+		htab->table = xfrm_hash_alloc(sz);
+		if (!htab->table)
+			goto out_bydst;
+		htab->hmask = hmask;
+		htab->dbits4 = 32;
+		htab->sbits4 = 32;
+		htab->dbits6 = 128;
+		htab->sbits6 = 128;
+	}
+	net->xfrm.policy_hthresh.lbits4 = 32;
+	net->xfrm.policy_hthresh.rbits4 = 32;
+	net->xfrm.policy_hthresh.lbits6 = 128;
+	net->xfrm.policy_hthresh.rbits6 = 128;
+
+	seqlock_init(&net->xfrm.policy_hthresh.lock);
+
+	INIT_LIST_HEAD(&net->xfrm.policy_all);
+	INIT_LIST_HEAD(&net->xfrm.inexact_bins);
+	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
+	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
+	return 0;
+
+out_bydst:
+	for (dir--; dir >= 0; dir--) {
+		struct xfrm_policy_hash *htab;
+
+		htab = &net->xfrm.policy_bydst[dir];
+		xfrm_hash_free(htab->table, sz);
+	}
+	xfrm_hash_free(net->xfrm.policy_byidx, sz);
+out_byidx:
+	return -ENOMEM;
+}
+
+static void xfrm_policy_fini(struct net *net)
+{
+	struct xfrm_pol_inexact_bin *b, *t;
+	unsigned int sz;
+	int dir;
+
+	flush_work(&net->xfrm.policy_hash_work);
+#ifdef CONFIG_XFRM_SUB_POLICY
+	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false);
+#endif
+	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false);
+
+	WARN_ON(!list_empty(&net->xfrm.policy_all));
+
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
+		struct xfrm_policy_hash *htab;
+
+		WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir]));
+
+		htab = &net->xfrm.policy_bydst[dir];
+		sz = (htab->hmask + 1) * sizeof(struct hlist_head);
+		WARN_ON(!hlist_empty(htab->table));
+		xfrm_hash_free(htab->table, sz);
+	}
+
+	sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head);
+	WARN_ON(!hlist_empty(net->xfrm.policy_byidx));
+	xfrm_hash_free(net->xfrm.policy_byidx, sz);
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins)
+		__xfrm_policy_inexact_prune_bin(b, true);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+}
+
+static int __net_init xfrm_net_init(struct net *net)
+{
+	int rv;
+
+	/* Initialize the per-net locks here */
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	spin_lock_init(&net->xfrm.xfrm_policy_lock);
+	seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock);
+	mutex_init(&net->xfrm.xfrm_cfg_mutex);
+	net->xfrm.policy_default[XFRM_POLICY_IN] = XFRM_USERPOLICY_ACCEPT;
+	net->xfrm.policy_default[XFRM_POLICY_FWD] = XFRM_USERPOLICY_ACCEPT;
+	net->xfrm.policy_default[XFRM_POLICY_OUT] = XFRM_USERPOLICY_ACCEPT;
+
+	rv = xfrm_statistics_init(net);
+	if (rv < 0)
+		goto out_statistics;
+	rv = xfrm_state_init(net);
+	if (rv < 0)
+		goto out_state;
+	rv = xfrm_policy_init(net);
+	if (rv < 0)
+		goto out_policy;
+	rv = xfrm_sysctl_init(net);
+	if (rv < 0)
+		goto out_sysctl;
+
+	return 0;
+
+out_sysctl:
+	xfrm_policy_fini(net);
+out_policy:
+	xfrm_state_fini(net);
+out_state:
+	xfrm_statistics_fini(net);
+out_statistics:
+	return rv;
+}
+
+static void __net_exit xfrm_net_exit(struct net *net)
+{
+	xfrm_sysctl_fini(net);
+	xfrm_policy_fini(net);
+	xfrm_state_fini(net);
+	xfrm_statistics_fini(net);
+}
+
+static struct pernet_operations __net_initdata xfrm_net_ops = {
+	.init = xfrm_net_init,
+	.exit = xfrm_net_exit,
+};
+
+void __init xfrm_init(void)
+{
+	register_pernet_subsys(&xfrm_net_ops);
+	xfrm_dev_init();
+	xfrm_input_init();
+
+#ifdef CONFIG_XFRM_ESPINTCP
+	espintcp_init();
+#endif
+}
+
+#ifdef CONFIG_AUDITSYSCALL
+static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp,
+					 struct audit_buffer *audit_buf)
+{
+	struct xfrm_sec_ctx *ctx = xp->security;
+	struct xfrm_selector *sel = &xp->selector;
+
+	if (ctx)
+		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
+				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
+
+	switch (sel->family) {
+	case AF_INET:
+		audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4);
+		if (sel->prefixlen_s != 32)
+			audit_log_format(audit_buf, " src_prefixlen=%d",
+					 sel->prefixlen_s);
+		audit_log_format(audit_buf, " dst=%pI4", &sel->daddr.a4);
+		if (sel->prefixlen_d != 32)
+			audit_log_format(audit_buf, " dst_prefixlen=%d",
+					 sel->prefixlen_d);
+		break;
+	case AF_INET6:
+		audit_log_format(audit_buf, " src=%pI6", sel->saddr.a6);
+		if (sel->prefixlen_s != 128)
+			audit_log_format(audit_buf, " src_prefixlen=%d",
+					 sel->prefixlen_s);
+		audit_log_format(audit_buf, " dst=%pI6", sel->daddr.a6);
+		if (sel->prefixlen_d != 128)
+			audit_log_format(audit_buf, " dst_prefixlen=%d",
+					 sel->prefixlen_d);
+		break;
+	}
+}
+
+void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid)
+{
+	struct audit_buffer *audit_buf;
+
+	audit_buf = xfrm_audit_start("SPD-add");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
+	audit_log_format(audit_buf, " res=%u", result);
+	xfrm_audit_common_policyinfo(xp, audit_buf);
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_policy_add);
+
+void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
+			      bool task_valid)
+{
+	struct audit_buffer *audit_buf;
+
+	audit_buf = xfrm_audit_start("SPD-delete");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
+	audit_log_format(audit_buf, " res=%u", result);
+	xfrm_audit_common_policyinfo(xp, audit_buf);
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete);
+#endif
+
+#ifdef CONFIG_XFRM_MIGRATE
+static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
+					const struct xfrm_selector *sel_tgt)
+{
+	if (sel_cmp->proto == IPSEC_ULPROTO_ANY) {
+		if (sel_tgt->family == sel_cmp->family &&
+		    xfrm_addr_equal(&sel_tgt->daddr, &sel_cmp->daddr,
+				    sel_cmp->family) &&
+		    xfrm_addr_equal(&sel_tgt->saddr, &sel_cmp->saddr,
+				    sel_cmp->family) &&
+		    sel_tgt->prefixlen_d == sel_cmp->prefixlen_d &&
+		    sel_tgt->prefixlen_s == sel_cmp->prefixlen_s) {
+			return true;
+		}
+	} else {
+		if (memcmp(sel_tgt, sel_cmp, sizeof(*sel_tgt)) == 0) {
+			return true;
+		}
+	}
+	return false;
+}
+
+static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
+						    u8 dir, u8 type, struct net *net, u32 if_id)
+{
+	struct xfrm_policy *pol, *ret = NULL;
+	struct hlist_head *chain;
+	u32 priority = ~0U;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
+	hlist_for_each_entry(pol, chain, bydst) {
+		if ((if_id == 0 || pol->if_id == if_id) &&
+		    xfrm_migrate_selector_match(sel, &pol->selector) &&
+		    pol->type == type) {
+			ret = pol;
+			priority = ret->priority;
+			break;
+		}
+	}
+	chain = &net->xfrm.policy_inexact[dir];
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+		if ((pol->priority >= priority) && ret)
+			break;
+
+		if ((if_id == 0 || pol->if_id == if_id) &&
+		    xfrm_migrate_selector_match(sel, &pol->selector) &&
+		    pol->type == type) {
+			ret = pol;
+			break;
+		}
+	}
+
+	xfrm_pol_hold(ret);
+
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	return ret;
+}
+
+static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t)
+{
+	int match = 0;
+
+	if (t->mode == m->mode && t->id.proto == m->proto &&
+	    (m->reqid == 0 || t->reqid == m->reqid)) {
+		switch (t->mode) {
+		case XFRM_MODE_TUNNEL:
+		case XFRM_MODE_BEET:
+			if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr,
+					    m->old_family) &&
+			    xfrm_addr_equal(&t->saddr, &m->old_saddr,
+					    m->old_family)) {
+				match = 1;
+			}
+			break;
+		case XFRM_MODE_TRANSPORT:
+			/* in case of transport mode, template does not store
+			   any IP addresses, hence we just compare mode and
+			   protocol */
+			match = 1;
+			break;
+		default:
+			break;
+		}
+	}
+	return match;
+}
+
+/* update endpoint address(es) of template(s) */
+static int xfrm_policy_migrate(struct xfrm_policy *pol,
+			       struct xfrm_migrate *m, int num_migrate,
+			       struct netlink_ext_ack *extack)
+{
+	struct xfrm_migrate *mp;
+	int i, j, n = 0;
+
+	write_lock_bh(&pol->lock);
+	if (unlikely(pol->walk.dead)) {
+		/* target policy has been deleted */
+		NL_SET_ERR_MSG(extack, "Target policy not found");
+		write_unlock_bh(&pol->lock);
+		return -ENOENT;
+	}
+
+	for (i = 0; i < pol->xfrm_nr; i++) {
+		for (j = 0, mp = m; j < num_migrate; j++, mp++) {
+			if (!migrate_tmpl_match(mp, &pol->xfrm_vec[i]))
+				continue;
+			n++;
+			if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL &&
+			    pol->xfrm_vec[i].mode != XFRM_MODE_BEET)
+				continue;
+			/* update endpoints */
+			memcpy(&pol->xfrm_vec[i].id.daddr, &mp->new_daddr,
+			       sizeof(pol->xfrm_vec[i].id.daddr));
+			memcpy(&pol->xfrm_vec[i].saddr, &mp->new_saddr,
+			       sizeof(pol->xfrm_vec[i].saddr));
+			pol->xfrm_vec[i].encap_family = mp->new_family;
+			/* flush bundles */
+			atomic_inc(&pol->genid);
+		}
+	}
+
+	write_unlock_bh(&pol->lock);
+
+	if (!n)
+		return -ENODATA;
+
+	return 0;
+}
+
+static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate,
+			      struct netlink_ext_ack *extack)
+{
+	int i, j;
+
+	if (num_migrate < 1 || num_migrate > XFRM_MAX_DEPTH) {
+		NL_SET_ERR_MSG(extack, "Invalid number of SAs to migrate, must be 0 < num <= XFRM_MAX_DEPTH (6)");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < num_migrate; i++) {
+		if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) ||
+		    xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) {
+			NL_SET_ERR_MSG(extack, "Addresses in the MIGRATE attribute's list cannot be null");
+			return -EINVAL;
+		}
+
+		/* check if there is any duplicated entry */
+		for (j = i + 1; j < num_migrate; j++) {
+			if (!memcmp(&m[i].old_daddr, &m[j].old_daddr,
+				    sizeof(m[i].old_daddr)) &&
+			    !memcmp(&m[i].old_saddr, &m[j].old_saddr,
+				    sizeof(m[i].old_saddr)) &&
+			    m[i].proto == m[j].proto &&
+			    m[i].mode == m[j].mode &&
+			    m[i].reqid == m[j].reqid &&
+			    m[i].old_family == m[j].old_family) {
+				NL_SET_ERR_MSG(extack, "Entries in the MIGRATE attribute's list must be unique");
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+
+int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+		 struct xfrm_migrate *m, int num_migrate,
+		 struct xfrm_kmaddress *k, struct net *net,
+		 struct xfrm_encap_tmpl *encap, u32 if_id,
+		 struct netlink_ext_ack *extack)
+{
+	int i, err, nx_cur = 0, nx_new = 0;
+	struct xfrm_policy *pol = NULL;
+	struct xfrm_state *x, *xc;
+	struct xfrm_state *x_cur[XFRM_MAX_DEPTH];
+	struct xfrm_state *x_new[XFRM_MAX_DEPTH];
+	struct xfrm_migrate *mp;
+
+	/* Stage 0 - sanity checks */
+	err = xfrm_migrate_check(m, num_migrate, extack);
+	if (err < 0)
+		goto out;
+
+	if (dir >= XFRM_POLICY_MAX) {
+		NL_SET_ERR_MSG(extack, "Invalid policy direction");
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* Stage 1 - find policy */
+	pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id);
+	if (!pol) {
+		NL_SET_ERR_MSG(extack, "Target policy not found");
+		err = -ENOENT;
+		goto out;
+	}
+
+	/* Stage 2 - find and update state(s) */
+	for (i = 0, mp = m; i < num_migrate; i++, mp++) {
+		if ((x = xfrm_migrate_state_find(mp, net, if_id))) {
+			x_cur[nx_cur] = x;
+			nx_cur++;
+			xc = xfrm_state_migrate(x, mp, encap);
+			if (xc) {
+				x_new[nx_new] = xc;
+				nx_new++;
+			} else {
+				err = -ENODATA;
+				goto restore_state;
+			}
+		}
+	}
+
+	/* Stage 3 - update policy */
+	err = xfrm_policy_migrate(pol, m, num_migrate, extack);
+	if (err < 0)
+		goto restore_state;
+
+	/* Stage 4 - delete old state(s) */
+	if (nx_cur) {
+		xfrm_states_put(x_cur, nx_cur);
+		xfrm_states_delete(x_cur, nx_cur);
+	}
+
+	/* Stage 5 - announce */
+	km_migrate(sel, dir, type, m, num_migrate, k, encap);
+
+	xfrm_pol_put(pol);
+
+	return 0;
+out:
+	return err;
+
+restore_state:
+	if (pol)
+		xfrm_pol_put(pol);
+	if (nx_cur)
+		xfrm_states_put(x_cur, nx_cur);
+	if (nx_new)
+		xfrm_states_delete(x_new, nx_new);
+
+	return err;
+}
+EXPORT_SYMBOL(xfrm_migrate);
+#endif
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
new file mode 100644
index 0000000000..fee9b5cf37
--- /dev/null
+++ b/net/xfrm/xfrm_proc.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * xfrm_proc.c
+ *
+ * Copyright (C)2006-2007 USAGI/WIDE Project
+ *
+ * Authors:	Masahide NAKAMURA <nakam@linux-ipv6.org>
+ */
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/export.h>
+#include <net/snmp.h>
+#include <net/xfrm.h>
+
+static const struct snmp_mib xfrm_mib_list[] = {
+	SNMP_MIB_ITEM("XfrmInError", LINUX_MIB_XFRMINERROR),
+	SNMP_MIB_ITEM("XfrmInBufferError", LINUX_MIB_XFRMINBUFFERERROR),
+	SNMP_MIB_ITEM("XfrmInHdrError", LINUX_MIB_XFRMINHDRERROR),
+	SNMP_MIB_ITEM("XfrmInNoStates", LINUX_MIB_XFRMINNOSTATES),
+	SNMP_MIB_ITEM("XfrmInStateProtoError", LINUX_MIB_XFRMINSTATEPROTOERROR),
+	SNMP_MIB_ITEM("XfrmInStateModeError", LINUX_MIB_XFRMINSTATEMODEERROR),
+	SNMP_MIB_ITEM("XfrmInStateSeqError", LINUX_MIB_XFRMINSTATESEQERROR),
+	SNMP_MIB_ITEM("XfrmInStateExpired", LINUX_MIB_XFRMINSTATEEXPIRED),
+	SNMP_MIB_ITEM("XfrmInStateMismatch", LINUX_MIB_XFRMINSTATEMISMATCH),
+	SNMP_MIB_ITEM("XfrmInStateInvalid", LINUX_MIB_XFRMINSTATEINVALID),
+	SNMP_MIB_ITEM("XfrmInTmplMismatch", LINUX_MIB_XFRMINTMPLMISMATCH),
+	SNMP_MIB_ITEM("XfrmInNoPols", LINUX_MIB_XFRMINNOPOLS),
+	SNMP_MIB_ITEM("XfrmInPolBlock", LINUX_MIB_XFRMINPOLBLOCK),
+	SNMP_MIB_ITEM("XfrmInPolError", LINUX_MIB_XFRMINPOLERROR),
+	SNMP_MIB_ITEM("XfrmOutError", LINUX_MIB_XFRMOUTERROR),
+	SNMP_MIB_ITEM("XfrmOutBundleGenError", LINUX_MIB_XFRMOUTBUNDLEGENERROR),
+	SNMP_MIB_ITEM("XfrmOutBundleCheckError", LINUX_MIB_XFRMOUTBUNDLECHECKERROR),
+	SNMP_MIB_ITEM("XfrmOutNoStates", LINUX_MIB_XFRMOUTNOSTATES),
+	SNMP_MIB_ITEM("XfrmOutStateProtoError", LINUX_MIB_XFRMOUTSTATEPROTOERROR),
+	SNMP_MIB_ITEM("XfrmOutStateModeError", LINUX_MIB_XFRMOUTSTATEMODEERROR),
+	SNMP_MIB_ITEM("XfrmOutStateSeqError", LINUX_MIB_XFRMOUTSTATESEQERROR),
+	SNMP_MIB_ITEM("XfrmOutStateExpired", LINUX_MIB_XFRMOUTSTATEEXPIRED),
+	SNMP_MIB_ITEM("XfrmOutPolBlock", LINUX_MIB_XFRMOUTPOLBLOCK),
+	SNMP_MIB_ITEM("XfrmOutPolDead", LINUX_MIB_XFRMOUTPOLDEAD),
+	SNMP_MIB_ITEM("XfrmOutPolError", LINUX_MIB_XFRMOUTPOLERROR),
+	SNMP_MIB_ITEM("XfrmFwdHdrError", LINUX_MIB_XFRMFWDHDRERROR),
+	SNMP_MIB_ITEM("XfrmOutStateInvalid", LINUX_MIB_XFRMOUTSTATEINVALID),
+	SNMP_MIB_ITEM("XfrmAcquireError", LINUX_MIB_XFRMACQUIREERROR),
+	SNMP_MIB_SENTINEL
+};
+
+static int xfrm_statistics_seq_show(struct seq_file *seq, void *v)
+{
+	unsigned long buff[LINUX_MIB_XFRMMAX];
+	struct net *net = seq->private;
+	int i;
+
+	memset(buff, 0, sizeof(unsigned long) * LINUX_MIB_XFRMMAX);
+
+	snmp_get_cpu_field_batch(buff, xfrm_mib_list,
+				 net->mib.xfrm_statistics);
+	for (i = 0; xfrm_mib_list[i].name; i++)
+		seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name,
+						buff[i]);
+
+	return 0;
+}
+
+int __net_init xfrm_proc_init(struct net *net)
+{
+	if (!proc_create_net_single("xfrm_stat", 0444, net->proc_net,
+			 xfrm_statistics_seq_show, NULL))
+		return -ENOMEM;
+	return 0;
+}
+
+void xfrm_proc_fini(struct net *net)
+{
+	remove_proc_entry("xfrm_stat", net->proc_net);
+}
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
new file mode 100644
index 0000000000..ce56d659c5
--- /dev/null
+++ b/net/xfrm/xfrm_replay.c
@@ -0,0 +1,795 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * xfrm_replay.c - xfrm replay detection, derived from xfrm_state.c.
+ *
+ * Copyright (C) 2010 secunet Security Networks AG
+ * Copyright (C) 2010 Steffen Klassert <steffen.klassert@secunet.com>
+ */
+
+#include <linux/export.h>
+#include <net/xfrm.h>
+
+u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq)
+{
+	u32 seq, seq_hi, bottom;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+
+	if (!(x->props.flags & XFRM_STATE_ESN))
+		return 0;
+
+	seq = ntohl(net_seq);
+	seq_hi = replay_esn->seq_hi;
+	bottom = replay_esn->seq - replay_esn->replay_window + 1;
+
+	if (likely(replay_esn->seq >= replay_esn->replay_window - 1)) {
+		/* A. same subspace */
+		if (unlikely(seq < bottom))
+			seq_hi++;
+	} else {
+		/* B. window spans two subspaces */
+		if (unlikely(seq >= bottom))
+			seq_hi--;
+	}
+
+	return seq_hi;
+}
+EXPORT_SYMBOL(xfrm_replay_seqhi);
+
+static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event);
+static void xfrm_replay_notify_esn(struct xfrm_state *x, int event);
+
+void xfrm_replay_notify(struct xfrm_state *x, int event)
+{
+	struct km_event c;
+	/* we send notify messages in case
+	 *  1. we updated on of the sequence numbers, and the seqno difference
+	 *     is at least x->replay_maxdiff, in this case we also update the
+	 *     timeout of our timer function
+	 *  2. if x->replay_maxage has elapsed since last update,
+	 *     and there were changes
+	 *
+	 *  The state structure must be locked!
+	 */
+
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		xfrm_replay_notify_bmp(x, event);
+		return;
+	case XFRM_REPLAY_MODE_ESN:
+		xfrm_replay_notify_esn(x, event);
+		return;
+	}
+
+	switch (event) {
+	case XFRM_REPLAY_UPDATE:
+		if (!x->replay_maxdiff ||
+		    ((x->replay.seq - x->preplay.seq < x->replay_maxdiff) &&
+		    (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff))) {
+			if (x->xflags & XFRM_TIME_DEFER)
+				event = XFRM_REPLAY_TIMEOUT;
+			else
+				return;
+		}
+
+		break;
+
+	case XFRM_REPLAY_TIMEOUT:
+		if (memcmp(&x->replay, &x->preplay,
+			   sizeof(struct xfrm_replay_state)) == 0) {
+			x->xflags |= XFRM_TIME_DEFER;
+			return;
+		}
+
+		break;
+	}
+
+	memcpy(&x->preplay, &x->replay, sizeof(struct xfrm_replay_state));
+	c.event = XFRM_MSG_NEWAE;
+	c.data.aevent = event;
+	km_state_notify(x, &c);
+
+	if (x->replay_maxage &&
+	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage))
+		x->xflags &= ~XFRM_TIME_DEFER;
+}
+
+static int __xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct net *net = xs_net(x);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq;
+		XFRM_SKB_CB(skb)->seq.output.hi = 0;
+		if (unlikely(x->replay.oseq == 0) &&
+		    !(x->props.extra_flags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP)) {
+			x->replay.oseq--;
+			xfrm_audit_state_replay_overflow(x, skb);
+			err = -EOVERFLOW;
+
+			return err;
+		}
+		if (xfrm_aevent_is_on(net))
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_check_legacy(struct xfrm_state *x,
+				    struct sk_buff *skb, __be32 net_seq)
+{
+	u32 diff;
+	u32 seq = ntohl(net_seq);
+
+	if (!x->props.replay_window)
+		return 0;
+
+	if (unlikely(seq == 0))
+		goto err;
+
+	if (likely(seq > x->replay.seq))
+		return 0;
+
+	diff = x->replay.seq - seq;
+	if (diff >= x->props.replay_window) {
+		x->stats.replay_window++;
+		goto err;
+	}
+
+	if (x->replay.bitmap & (1U << diff)) {
+		x->stats.replay++;
+		goto err;
+	}
+	return 0;
+
+err:
+	xfrm_audit_state_replay(x, skb, net_seq);
+	return -EINVAL;
+}
+
+static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq);
+static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq);
+
+void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq)
+{
+	u32 diff, seq;
+
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		return xfrm_replay_advance_bmp(x, net_seq);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_advance_esn(x, net_seq);
+	}
+
+	if (!x->props.replay_window)
+		return;
+
+	seq = ntohl(net_seq);
+	if (seq > x->replay.seq) {
+		diff = seq - x->replay.seq;
+		if (diff < x->props.replay_window)
+			x->replay.bitmap = ((x->replay.bitmap) << diff) | 1;
+		else
+			x->replay.bitmap = 1;
+		x->replay.seq = seq;
+	} else {
+		diff = x->replay.seq - seq;
+		x->replay.bitmap |= (1U << diff);
+	}
+
+	if (xfrm_aevent_is_on(xs_net(x)))
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+}
+
+static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct net *net = xs_net(x);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq;
+		XFRM_SKB_CB(skb)->seq.output.hi = 0;
+		if (unlikely(replay_esn->oseq == 0) &&
+		    !(x->props.extra_flags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP)) {
+			replay_esn->oseq--;
+			xfrm_audit_state_replay_overflow(x, skb);
+			err = -EOVERFLOW;
+
+			return err;
+		}
+		if (xfrm_aevent_is_on(net))
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_check_bmp(struct xfrm_state *x,
+				 struct sk_buff *skb, __be32 net_seq)
+{
+	unsigned int bitnr, nr;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	u32 pos;
+	u32 seq = ntohl(net_seq);
+	u32 diff =  replay_esn->seq - seq;
+
+	if (!replay_esn->replay_window)
+		return 0;
+
+	if (unlikely(seq == 0))
+		goto err;
+
+	if (likely(seq > replay_esn->seq))
+		return 0;
+
+	if (diff >= replay_esn->replay_window) {
+		x->stats.replay_window++;
+		goto err;
+	}
+
+	pos = (replay_esn->seq - 1) % replay_esn->replay_window;
+
+	if (pos >= diff)
+		bitnr = (pos - diff) % replay_esn->replay_window;
+	else
+		bitnr = replay_esn->replay_window - (diff - pos);
+
+	nr = bitnr >> 5;
+	bitnr = bitnr & 0x1F;
+	if (replay_esn->bmp[nr] & (1U << bitnr))
+		goto err_replay;
+
+	return 0;
+
+err_replay:
+	x->stats.replay++;
+err:
+	xfrm_audit_state_replay(x, skb, net_seq);
+	return -EINVAL;
+}
+
+static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq)
+{
+	unsigned int bitnr, nr, i;
+	u32 diff;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	u32 seq = ntohl(net_seq);
+	u32 pos;
+
+	if (!replay_esn->replay_window)
+		return;
+
+	pos = (replay_esn->seq - 1) % replay_esn->replay_window;
+
+	if (seq > replay_esn->seq) {
+		diff = seq - replay_esn->seq;
+
+		if (diff < replay_esn->replay_window) {
+			for (i = 1; i < diff; i++) {
+				bitnr = (pos + i) % replay_esn->replay_window;
+				nr = bitnr >> 5;
+				bitnr = bitnr & 0x1F;
+				replay_esn->bmp[nr] &=  ~(1U << bitnr);
+			}
+		} else {
+			nr = (replay_esn->replay_window - 1) >> 5;
+			for (i = 0; i <= nr; i++)
+				replay_esn->bmp[i] = 0;
+		}
+
+		bitnr = (pos + diff) % replay_esn->replay_window;
+		replay_esn->seq = seq;
+	} else {
+		diff = replay_esn->seq - seq;
+
+		if (pos >= diff)
+			bitnr = (pos - diff) % replay_esn->replay_window;
+		else
+			bitnr = replay_esn->replay_window - (diff - pos);
+	}
+
+	nr = bitnr >> 5;
+	bitnr = bitnr & 0x1F;
+	replay_esn->bmp[nr] |= (1U << bitnr);
+
+	if (xfrm_aevent_is_on(xs_net(x)))
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+}
+
+static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event)
+{
+	struct km_event c;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct xfrm_replay_state_esn *preplay_esn = x->preplay_esn;
+
+	/* we send notify messages in case
+	 *  1. we updated on of the sequence numbers, and the seqno difference
+	 *     is at least x->replay_maxdiff, in this case we also update the
+	 *     timeout of our timer function
+	 *  2. if x->replay_maxage has elapsed since last update,
+	 *     and there were changes
+	 *
+	 *  The state structure must be locked!
+	 */
+
+	switch (event) {
+	case XFRM_REPLAY_UPDATE:
+		if (!x->replay_maxdiff ||
+		    ((replay_esn->seq - preplay_esn->seq < x->replay_maxdiff) &&
+		    (replay_esn->oseq - preplay_esn->oseq
+		     < x->replay_maxdiff))) {
+			if (x->xflags & XFRM_TIME_DEFER)
+				event = XFRM_REPLAY_TIMEOUT;
+			else
+				return;
+		}
+
+		break;
+
+	case XFRM_REPLAY_TIMEOUT:
+		if (memcmp(x->replay_esn, x->preplay_esn,
+			   xfrm_replay_state_esn_len(replay_esn)) == 0) {
+			x->xflags |= XFRM_TIME_DEFER;
+			return;
+		}
+
+		break;
+	}
+
+	memcpy(x->preplay_esn, x->replay_esn,
+	       xfrm_replay_state_esn_len(replay_esn));
+	c.event = XFRM_MSG_NEWAE;
+	c.data.aevent = event;
+	km_state_notify(x, &c);
+
+	if (x->replay_maxage &&
+	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage))
+		x->xflags &= ~XFRM_TIME_DEFER;
+}
+
+static void xfrm_replay_notify_esn(struct xfrm_state *x, int event)
+{
+	u32 seq_diff, oseq_diff;
+	struct km_event c;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct xfrm_replay_state_esn *preplay_esn = x->preplay_esn;
+
+	/* we send notify messages in case
+	 *  1. we updated on of the sequence numbers, and the seqno difference
+	 *     is at least x->replay_maxdiff, in this case we also update the
+	 *     timeout of our timer function
+	 *  2. if x->replay_maxage has elapsed since last update,
+	 *     and there were changes
+	 *
+	 *  The state structure must be locked!
+	 */
+
+	switch (event) {
+	case XFRM_REPLAY_UPDATE:
+		if (x->replay_maxdiff) {
+			if (replay_esn->seq_hi == preplay_esn->seq_hi)
+				seq_diff = replay_esn->seq - preplay_esn->seq;
+			else
+				seq_diff = ~preplay_esn->seq + replay_esn->seq
+					   + 1;
+
+			if (replay_esn->oseq_hi == preplay_esn->oseq_hi)
+				oseq_diff = replay_esn->oseq
+					    - preplay_esn->oseq;
+			else
+				oseq_diff = ~preplay_esn->oseq
+					    + replay_esn->oseq + 1;
+
+			if (seq_diff >= x->replay_maxdiff ||
+			    oseq_diff >= x->replay_maxdiff)
+				break;
+		}
+
+		if (x->xflags & XFRM_TIME_DEFER)
+			event = XFRM_REPLAY_TIMEOUT;
+		else
+			return;
+
+		break;
+
+	case XFRM_REPLAY_TIMEOUT:
+		if (memcmp(x->replay_esn, x->preplay_esn,
+			   xfrm_replay_state_esn_len(replay_esn)) == 0) {
+			x->xflags |= XFRM_TIME_DEFER;
+			return;
+		}
+
+		break;
+	}
+
+	memcpy(x->preplay_esn, x->replay_esn,
+	       xfrm_replay_state_esn_len(replay_esn));
+	c.event = XFRM_MSG_NEWAE;
+	c.data.aevent = event;
+	km_state_notify(x, &c);
+
+	if (x->replay_maxage &&
+	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage))
+		x->xflags &= ~XFRM_TIME_DEFER;
+}
+
+static int xfrm_replay_overflow_esn(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct net *net = xs_net(x);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq;
+		XFRM_SKB_CB(skb)->seq.output.hi = replay_esn->oseq_hi;
+
+		if (unlikely(replay_esn->oseq == 0)) {
+			XFRM_SKB_CB(skb)->seq.output.hi = ++replay_esn->oseq_hi;
+
+			if (replay_esn->oseq_hi == 0) {
+				replay_esn->oseq--;
+				replay_esn->oseq_hi--;
+				xfrm_audit_state_replay_overflow(x, skb);
+				err = -EOVERFLOW;
+
+				return err;
+			}
+		}
+		if (xfrm_aevent_is_on(net))
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_check_esn(struct xfrm_state *x,
+				 struct sk_buff *skb, __be32 net_seq)
+{
+	unsigned int bitnr, nr;
+	u32 diff;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	u32 pos;
+	u32 seq = ntohl(net_seq);
+	u32 wsize = replay_esn->replay_window;
+	u32 top = replay_esn->seq;
+	u32 bottom = top - wsize + 1;
+
+	if (!wsize)
+		return 0;
+
+	if (unlikely(seq == 0 && replay_esn->seq_hi == 0 &&
+		     (replay_esn->seq < replay_esn->replay_window - 1)))
+		goto err;
+
+	diff = top - seq;
+
+	if (likely(top >= wsize - 1)) {
+		/* A. same subspace */
+		if (likely(seq > top) || seq < bottom)
+			return 0;
+	} else {
+		/* B. window spans two subspaces */
+		if (likely(seq > top && seq < bottom))
+			return 0;
+		if (seq >= bottom)
+			diff = ~seq + top + 1;
+	}
+
+	if (diff >= replay_esn->replay_window) {
+		x->stats.replay_window++;
+		goto err;
+	}
+
+	pos = (replay_esn->seq - 1) % replay_esn->replay_window;
+
+	if (pos >= diff)
+		bitnr = (pos - diff) % replay_esn->replay_window;
+	else
+		bitnr = replay_esn->replay_window - (diff - pos);
+
+	nr = bitnr >> 5;
+	bitnr = bitnr & 0x1F;
+	if (replay_esn->bmp[nr] & (1U << bitnr))
+		goto err_replay;
+
+	return 0;
+
+err_replay:
+	x->stats.replay++;
+err:
+	xfrm_audit_state_replay(x, skb, net_seq);
+	return -EINVAL;
+}
+
+int xfrm_replay_check(struct xfrm_state *x,
+		      struct sk_buff *skb, __be32 net_seq)
+{
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		return xfrm_replay_check_bmp(x, skb, net_seq);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_check_esn(x, skb, net_seq);
+	}
+
+	return xfrm_replay_check_legacy(x, skb, net_seq);
+}
+
+static int xfrm_replay_recheck_esn(struct xfrm_state *x,
+				   struct sk_buff *skb, __be32 net_seq)
+{
+	if (unlikely(XFRM_SKB_CB(skb)->seq.input.hi !=
+		     htonl(xfrm_replay_seqhi(x, net_seq)))) {
+			x->stats.replay_window++;
+			return -EINVAL;
+	}
+
+	return xfrm_replay_check_esn(x, skb, net_seq);
+}
+
+int xfrm_replay_recheck(struct xfrm_state *x,
+			struct sk_buff *skb, __be32 net_seq)
+{
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		/* no special recheck treatment */
+		return xfrm_replay_check_bmp(x, skb, net_seq);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_recheck_esn(x, skb, net_seq);
+	}
+
+	return xfrm_replay_check_legacy(x, skb, net_seq);
+}
+
+static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq)
+{
+	unsigned int bitnr, nr, i;
+	int wrap;
+	u32 diff, pos, seq, seq_hi;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+
+	if (!replay_esn->replay_window)
+		return;
+
+	seq = ntohl(net_seq);
+	pos = (replay_esn->seq - 1) % replay_esn->replay_window;
+	seq_hi = xfrm_replay_seqhi(x, net_seq);
+	wrap = seq_hi - replay_esn->seq_hi;
+
+	if ((!wrap && seq > replay_esn->seq) || wrap > 0) {
+		if (likely(!wrap))
+			diff = seq - replay_esn->seq;
+		else
+			diff = ~replay_esn->seq + seq + 1;
+
+		if (diff < replay_esn->replay_window) {
+			for (i = 1; i < diff; i++) {
+				bitnr = (pos + i) % replay_esn->replay_window;
+				nr = bitnr >> 5;
+				bitnr = bitnr & 0x1F;
+				replay_esn->bmp[nr] &=  ~(1U << bitnr);
+			}
+		} else {
+			nr = (replay_esn->replay_window - 1) >> 5;
+			for (i = 0; i <= nr; i++)
+				replay_esn->bmp[i] = 0;
+		}
+
+		bitnr = (pos + diff) % replay_esn->replay_window;
+		replay_esn->seq = seq;
+
+		if (unlikely(wrap > 0))
+			replay_esn->seq_hi++;
+	} else {
+		diff = replay_esn->seq - seq;
+
+		if (pos >= diff)
+			bitnr = (pos - diff) % replay_esn->replay_window;
+		else
+			bitnr = replay_esn->replay_window - (diff - pos);
+	}
+
+	xfrm_dev_state_advance_esn(x);
+
+	nr = bitnr >> 5;
+	bitnr = bitnr & 0x1F;
+	replay_esn->bmp[nr] |= (1U << bitnr);
+
+	if (xfrm_aevent_is_on(xs_net(x)))
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+}
+
+#ifdef CONFIG_XFRM_OFFLOAD
+static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct net *net = xs_net(x);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	__u32 oseq = x->replay.oseq;
+
+	if (!xo)
+		return __xfrm_replay_overflow(x, skb);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		if (!skb_is_gso(skb)) {
+			XFRM_SKB_CB(skb)->seq.output.low = ++oseq;
+			xo->seq.low = oseq;
+		} else {
+			XFRM_SKB_CB(skb)->seq.output.low = oseq + 1;
+			xo->seq.low = oseq + 1;
+			oseq += skb_shinfo(skb)->gso_segs;
+		}
+
+		XFRM_SKB_CB(skb)->seq.output.hi = 0;
+		xo->seq.hi = 0;
+		if (unlikely(oseq < x->replay.oseq) &&
+		    !(x->props.extra_flags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP)) {
+			xfrm_audit_state_replay_overflow(x, skb);
+			err = -EOVERFLOW;
+
+			return err;
+		}
+
+		x->replay.oseq = oseq;
+
+		if (xfrm_aevent_is_on(net))
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_overflow_offload_bmp(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct net *net = xs_net(x);
+	__u32 oseq = replay_esn->oseq;
+
+	if (!xo)
+		return xfrm_replay_overflow_bmp(x, skb);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		if (!skb_is_gso(skb)) {
+			XFRM_SKB_CB(skb)->seq.output.low = ++oseq;
+			xo->seq.low = oseq;
+		} else {
+			XFRM_SKB_CB(skb)->seq.output.low = oseq + 1;
+			xo->seq.low = oseq + 1;
+			oseq += skb_shinfo(skb)->gso_segs;
+		}
+
+		XFRM_SKB_CB(skb)->seq.output.hi = 0;
+		xo->seq.hi = 0;
+		if (unlikely(oseq < replay_esn->oseq) &&
+		    !(x->props.extra_flags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP)) {
+			xfrm_audit_state_replay_overflow(x, skb);
+			err = -EOVERFLOW;
+
+			return err;
+		} else {
+			replay_esn->oseq = oseq;
+		}
+
+		if (xfrm_aevent_is_on(net))
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct net *net = xs_net(x);
+	__u32 oseq = replay_esn->oseq;
+	__u32 oseq_hi = replay_esn->oseq_hi;
+
+	if (!xo)
+		return xfrm_replay_overflow_esn(x, skb);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		if (!skb_is_gso(skb)) {
+			XFRM_SKB_CB(skb)->seq.output.low = ++oseq;
+			XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
+			xo->seq.low = oseq;
+			xo->seq.hi = oseq_hi;
+		} else {
+			XFRM_SKB_CB(skb)->seq.output.low = oseq + 1;
+			XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
+			xo->seq.low = oseq + 1;
+			xo->seq.hi = oseq_hi;
+			oseq += skb_shinfo(skb)->gso_segs;
+		}
+
+		if (unlikely(xo->seq.low < replay_esn->oseq)) {
+			XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi;
+			xo->seq.hi = oseq_hi;
+			replay_esn->oseq_hi = oseq_hi;
+			if (replay_esn->oseq_hi == 0) {
+				replay_esn->oseq--;
+				replay_esn->oseq_hi--;
+				xfrm_audit_state_replay_overflow(x, skb);
+				err = -EOVERFLOW;
+
+				return err;
+			}
+		}
+
+		replay_esn->oseq = oseq;
+
+		if (xfrm_aevent_is_on(net))
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		return xfrm_replay_overflow_offload_bmp(x, skb);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_overflow_offload_esn(x, skb);
+	}
+
+	return xfrm_replay_overflow_offload(x, skb);
+}
+#else
+int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		return xfrm_replay_overflow_bmp(x, skb);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_overflow_esn(x, skb);
+	}
+
+	return __xfrm_replay_overflow(x, skb);
+}
+#endif
+
+int xfrm_init_replay(struct xfrm_state *x, struct netlink_ext_ack *extack)
+{
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+
+	if (replay_esn) {
+		if (replay_esn->replay_window >
+		    replay_esn->bmp_len * sizeof(__u32) * 8) {
+			NL_SET_ERR_MSG(extack, "ESN replay window is too large for the chosen bitmap size");
+			return -EINVAL;
+		}
+
+		if (x->props.flags & XFRM_STATE_ESN) {
+			if (replay_esn->replay_window == 0) {
+				NL_SET_ERR_MSG(extack, "ESN replay window must be > 0");
+				return -EINVAL;
+			}
+			x->repl_mode = XFRM_REPLAY_MODE_ESN;
+		} else {
+			x->repl_mode = XFRM_REPLAY_MODE_BMP;
+		}
+	} else {
+		x->repl_mode = XFRM_REPLAY_MODE_LEGACY;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_init_replay);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
new file mode 100644
index 0000000000..bda5327bf3
--- /dev/null
+++ b/net/xfrm/xfrm_state.c
@@ -0,0 +1,3096 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * xfrm_state.c
+ *
+ * Changes:
+ *	Mitsuru KANDA @USAGI
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * 		IPv6 support
+ * 	YOSHIFUJI Hideaki @USAGI
+ * 		Split up af-specific functions
+ *	Derek Atkins <derek@ihtfp.com>
+ *		Add UDP Encapsulation
+ *
+ */
+
+#include <linux/compat.h>
+#include <linux/workqueue.h>
+#include <net/xfrm.h>
+#include <linux/pfkeyv2.h>
+#include <linux/ipsec.h>
+#include <linux/module.h>
+#include <linux/cache.h>
+#include <linux/audit.h>
+#include <linux/uaccess.h>
+#include <linux/ktime.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+
+#include <crypto/aead.h>
+
+#include "xfrm_hash.h"
+
+#define xfrm_state_deref_prot(table, net) \
+	rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
+
+static void xfrm_state_gc_task(struct work_struct *work);
+
+/* Each xfrm_state may be linked to two tables:
+
+   1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl)
+   2. Hash table by (daddr,family,reqid) to find what SAs exist for given
+      destination/tunnel endpoint. (output)
+ */
+
+static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
+static struct kmem_cache *xfrm_state_cache __ro_after_init;
+
+static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
+static HLIST_HEAD(xfrm_state_gc_list);
+
+static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
+{
+	return refcount_inc_not_zero(&x->refcnt);
+}
+
+static inline unsigned int xfrm_dst_hash(struct net *net,
+					 const xfrm_address_t *daddr,
+					 const xfrm_address_t *saddr,
+					 u32 reqid,
+					 unsigned short family)
+{
+	return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask);
+}
+
+static inline unsigned int xfrm_src_hash(struct net *net,
+					 const xfrm_address_t *daddr,
+					 const xfrm_address_t *saddr,
+					 unsigned short family)
+{
+	return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask);
+}
+
+static inline unsigned int
+xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr,
+	      __be32 spi, u8 proto, unsigned short family)
+{
+	return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
+}
+
+static unsigned int xfrm_seq_hash(struct net *net, u32 seq)
+{
+	return __xfrm_seq_hash(seq, net->xfrm.state_hmask);
+}
+
+#define XFRM_STATE_INSERT(by, _n, _h, _type)                               \
+	{                                                                  \
+		struct xfrm_state *_x = NULL;                              \
+									   \
+		if (_type != XFRM_DEV_OFFLOAD_PACKET) {                    \
+			hlist_for_each_entry_rcu(_x, _h, by) {             \
+				if (_x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \
+					continue;                          \
+				break;                                     \
+			}                                                  \
+		}                                                          \
+									   \
+		if (!_x || _x->xso.type == XFRM_DEV_OFFLOAD_PACKET)        \
+			/* SAD is empty or consist from HW SAs only */     \
+			hlist_add_head_rcu(_n, _h);                        \
+		else                                                       \
+			hlist_add_before_rcu(_n, &_x->by);                 \
+	}
+
+static void xfrm_hash_transfer(struct hlist_head *list,
+			       struct hlist_head *ndsttable,
+			       struct hlist_head *nsrctable,
+			       struct hlist_head *nspitable,
+			       struct hlist_head *nseqtable,
+			       unsigned int nhashmask)
+{
+	struct hlist_node *tmp;
+	struct xfrm_state *x;
+
+	hlist_for_each_entry_safe(x, tmp, list, bydst) {
+		unsigned int h;
+
+		h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr,
+				    x->props.reqid, x->props.family,
+				    nhashmask);
+		XFRM_STATE_INSERT(bydst, &x->bydst, ndsttable + h, x->xso.type);
+
+		h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr,
+				    x->props.family,
+				    nhashmask);
+		XFRM_STATE_INSERT(bysrc, &x->bysrc, nsrctable + h, x->xso.type);
+
+		if (x->id.spi) {
+			h = __xfrm_spi_hash(&x->id.daddr, x->id.spi,
+					    x->id.proto, x->props.family,
+					    nhashmask);
+			XFRM_STATE_INSERT(byspi, &x->byspi, nspitable + h,
+					  x->xso.type);
+		}
+
+		if (x->km.seq) {
+			h = __xfrm_seq_hash(x->km.seq, nhashmask);
+			XFRM_STATE_INSERT(byseq, &x->byseq, nseqtable + h,
+					  x->xso.type);
+		}
+	}
+}
+
+static unsigned long xfrm_hash_new_size(unsigned int state_hmask)
+{
+	return ((state_hmask + 1) << 1) * sizeof(struct hlist_head);
+}
+
+static void xfrm_hash_resize(struct work_struct *work)
+{
+	struct net *net = container_of(work, struct net, xfrm.state_hash_work);
+	struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq;
+	unsigned long nsize, osize;
+	unsigned int nhashmask, ohashmask;
+	int i;
+
+	nsize = xfrm_hash_new_size(net->xfrm.state_hmask);
+	ndst = xfrm_hash_alloc(nsize);
+	if (!ndst)
+		return;
+	nsrc = xfrm_hash_alloc(nsize);
+	if (!nsrc) {
+		xfrm_hash_free(ndst, nsize);
+		return;
+	}
+	nspi = xfrm_hash_alloc(nsize);
+	if (!nspi) {
+		xfrm_hash_free(ndst, nsize);
+		xfrm_hash_free(nsrc, nsize);
+		return;
+	}
+	nseq = xfrm_hash_alloc(nsize);
+	if (!nseq) {
+		xfrm_hash_free(ndst, nsize);
+		xfrm_hash_free(nsrc, nsize);
+		xfrm_hash_free(nspi, nsize);
+		return;
+	}
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
+
+	nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
+	odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net);
+	for (i = net->xfrm.state_hmask; i >= 0; i--)
+		xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask);
+
+	osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net);
+	ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net);
+	oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net);
+	ohashmask = net->xfrm.state_hmask;
+
+	rcu_assign_pointer(net->xfrm.state_bydst, ndst);
+	rcu_assign_pointer(net->xfrm.state_bysrc, nsrc);
+	rcu_assign_pointer(net->xfrm.state_byspi, nspi);
+	rcu_assign_pointer(net->xfrm.state_byseq, nseq);
+	net->xfrm.state_hmask = nhashmask;
+
+	write_seqcount_end(&net->xfrm.xfrm_state_hash_generation);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	osize = (ohashmask + 1) * sizeof(struct hlist_head);
+
+	synchronize_rcu();
+
+	xfrm_hash_free(odst, osize);
+	xfrm_hash_free(osrc, osize);
+	xfrm_hash_free(ospi, osize);
+	xfrm_hash_free(oseq, osize);
+}
+
+static DEFINE_SPINLOCK(xfrm_state_afinfo_lock);
+static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO];
+
+static DEFINE_SPINLOCK(xfrm_state_gc_lock);
+
+int __xfrm_state_delete(struct xfrm_state *x);
+
+int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
+static bool km_is_alive(const struct km_event *c);
+void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
+
+int xfrm_register_type(const struct xfrm_type *type, unsigned short family)
+{
+	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	int err = 0;
+
+	if (!afinfo)
+		return -EAFNOSUPPORT;
+
+#define X(afi, T, name) do {			\
+		WARN_ON((afi)->type_ ## name);	\
+		(afi)->type_ ## name = (T);	\
+	} while (0)
+
+	switch (type->proto) {
+	case IPPROTO_COMP:
+		X(afinfo, type, comp);
+		break;
+	case IPPROTO_AH:
+		X(afinfo, type, ah);
+		break;
+	case IPPROTO_ESP:
+		X(afinfo, type, esp);
+		break;
+	case IPPROTO_IPIP:
+		X(afinfo, type, ipip);
+		break;
+	case IPPROTO_DSTOPTS:
+		X(afinfo, type, dstopts);
+		break;
+	case IPPROTO_ROUTING:
+		X(afinfo, type, routing);
+		break;
+	case IPPROTO_IPV6:
+		X(afinfo, type, ipip6);
+		break;
+	default:
+		WARN_ON(1);
+		err = -EPROTONOSUPPORT;
+		break;
+	}
+#undef X
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(xfrm_register_type);
+
+void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family)
+{
+	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+
+	if (unlikely(afinfo == NULL))
+		return;
+
+#define X(afi, T, name) do {				\
+		WARN_ON((afi)->type_ ## name != (T));	\
+		(afi)->type_ ## name = NULL;		\
+	} while (0)
+
+	switch (type->proto) {
+	case IPPROTO_COMP:
+		X(afinfo, type, comp);
+		break;
+	case IPPROTO_AH:
+		X(afinfo, type, ah);
+		break;
+	case IPPROTO_ESP:
+		X(afinfo, type, esp);
+		break;
+	case IPPROTO_IPIP:
+		X(afinfo, type, ipip);
+		break;
+	case IPPROTO_DSTOPTS:
+		X(afinfo, type, dstopts);
+		break;
+	case IPPROTO_ROUTING:
+		X(afinfo, type, routing);
+		break;
+	case IPPROTO_IPV6:
+		X(afinfo, type, ipip6);
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+#undef X
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(xfrm_unregister_type);
+
+static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
+{
+	const struct xfrm_type *type = NULL;
+	struct xfrm_state_afinfo *afinfo;
+	int modload_attempted = 0;
+
+retry:
+	afinfo = xfrm_state_get_afinfo(family);
+	if (unlikely(afinfo == NULL))
+		return NULL;
+
+	switch (proto) {
+	case IPPROTO_COMP:
+		type = afinfo->type_comp;
+		break;
+	case IPPROTO_AH:
+		type = afinfo->type_ah;
+		break;
+	case IPPROTO_ESP:
+		type = afinfo->type_esp;
+		break;
+	case IPPROTO_IPIP:
+		type = afinfo->type_ipip;
+		break;
+	case IPPROTO_DSTOPTS:
+		type = afinfo->type_dstopts;
+		break;
+	case IPPROTO_ROUTING:
+		type = afinfo->type_routing;
+		break;
+	case IPPROTO_IPV6:
+		type = afinfo->type_ipip6;
+		break;
+	default:
+		break;
+	}
+
+	if (unlikely(type && !try_module_get(type->owner)))
+		type = NULL;
+
+	rcu_read_unlock();
+
+	if (!type && !modload_attempted) {
+		request_module("xfrm-type-%d-%d", family, proto);
+		modload_attempted = 1;
+		goto retry;
+	}
+
+	return type;
+}
+
+static void xfrm_put_type(const struct xfrm_type *type)
+{
+	module_put(type->owner);
+}
+
+int xfrm_register_type_offload(const struct xfrm_type_offload *type,
+			       unsigned short family)
+{
+	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	int err = 0;
+
+	if (unlikely(afinfo == NULL))
+		return -EAFNOSUPPORT;
+
+	switch (type->proto) {
+	case IPPROTO_ESP:
+		WARN_ON(afinfo->type_offload_esp);
+		afinfo->type_offload_esp = type;
+		break;
+	default:
+		WARN_ON(1);
+		err = -EPROTONOSUPPORT;
+		break;
+	}
+
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(xfrm_register_type_offload);
+
+void xfrm_unregister_type_offload(const struct xfrm_type_offload *type,
+				  unsigned short family)
+{
+	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+
+	if (unlikely(afinfo == NULL))
+		return;
+
+	switch (type->proto) {
+	case IPPROTO_ESP:
+		WARN_ON(afinfo->type_offload_esp != type);
+		afinfo->type_offload_esp = NULL;
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(xfrm_unregister_type_offload);
+
+static const struct xfrm_type_offload *
+xfrm_get_type_offload(u8 proto, unsigned short family, bool try_load)
+{
+	const struct xfrm_type_offload *type = NULL;
+	struct xfrm_state_afinfo *afinfo;
+
+retry:
+	afinfo = xfrm_state_get_afinfo(family);
+	if (unlikely(afinfo == NULL))
+		return NULL;
+
+	switch (proto) {
+	case IPPROTO_ESP:
+		type = afinfo->type_offload_esp;
+		break;
+	default:
+		break;
+	}
+
+	if ((type && !try_module_get(type->owner)))
+		type = NULL;
+
+	rcu_read_unlock();
+
+	if (!type && try_load) {
+		request_module("xfrm-offload-%d-%d", family, proto);
+		try_load = false;
+		goto retry;
+	}
+
+	return type;
+}
+
+static void xfrm_put_type_offload(const struct xfrm_type_offload *type)
+{
+	module_put(type->owner);
+}
+
+static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = {
+	[XFRM_MODE_BEET] = {
+		.encap = XFRM_MODE_BEET,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET,
+	},
+	[XFRM_MODE_TRANSPORT] = {
+		.encap = XFRM_MODE_TRANSPORT,
+		.family = AF_INET,
+	},
+	[XFRM_MODE_TUNNEL] = {
+		.encap = XFRM_MODE_TUNNEL,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET,
+	},
+};
+
+static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = {
+	[XFRM_MODE_BEET] = {
+		.encap = XFRM_MODE_BEET,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET6,
+	},
+	[XFRM_MODE_ROUTEOPTIMIZATION] = {
+		.encap = XFRM_MODE_ROUTEOPTIMIZATION,
+		.family = AF_INET6,
+	},
+	[XFRM_MODE_TRANSPORT] = {
+		.encap = XFRM_MODE_TRANSPORT,
+		.family = AF_INET6,
+	},
+	[XFRM_MODE_TUNNEL] = {
+		.encap = XFRM_MODE_TUNNEL,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET6,
+	},
+};
+
+static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
+{
+	const struct xfrm_mode *mode;
+
+	if (unlikely(encap >= XFRM_MODE_MAX))
+		return NULL;
+
+	switch (family) {
+	case AF_INET:
+		mode = &xfrm4_mode_map[encap];
+		if (mode->family == family)
+			return mode;
+		break;
+	case AF_INET6:
+		mode = &xfrm6_mode_map[encap];
+		if (mode->family == family)
+			return mode;
+		break;
+	default:
+		break;
+	}
+
+	return NULL;
+}
+
+void xfrm_state_free(struct xfrm_state *x)
+{
+	kmem_cache_free(xfrm_state_cache, x);
+}
+EXPORT_SYMBOL(xfrm_state_free);
+
+static void ___xfrm_state_destroy(struct xfrm_state *x)
+{
+	hrtimer_cancel(&x->mtimer);
+	del_timer_sync(&x->rtimer);
+	kfree(x->aead);
+	kfree(x->aalg);
+	kfree(x->ealg);
+	kfree(x->calg);
+	kfree(x->encap);
+	kfree(x->coaddr);
+	kfree(x->replay_esn);
+	kfree(x->preplay_esn);
+	if (x->type_offload)
+		xfrm_put_type_offload(x->type_offload);
+	if (x->type) {
+		x->type->destructor(x);
+		xfrm_put_type(x->type);
+	}
+	if (x->xfrag.page)
+		put_page(x->xfrag.page);
+	xfrm_dev_state_free(x);
+	security_xfrm_state_free(x);
+	xfrm_state_free(x);
+}
+
+static void xfrm_state_gc_task(struct work_struct *work)
+{
+	struct xfrm_state *x;
+	struct hlist_node *tmp;
+	struct hlist_head gc_list;
+
+	spin_lock_bh(&xfrm_state_gc_lock);
+	hlist_move_list(&xfrm_state_gc_list, &gc_list);
+	spin_unlock_bh(&xfrm_state_gc_lock);
+
+	synchronize_rcu();
+
+	hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
+		___xfrm_state_destroy(x);
+}
+
+static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
+{
+	struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer);
+	enum hrtimer_restart ret = HRTIMER_NORESTART;
+	time64_t now = ktime_get_real_seconds();
+	time64_t next = TIME64_MAX;
+	int warn = 0;
+	int err = 0;
+
+	spin_lock(&x->lock);
+	xfrm_dev_state_update_curlft(x);
+
+	if (x->km.state == XFRM_STATE_DEAD)
+		goto out;
+	if (x->km.state == XFRM_STATE_EXPIRED)
+		goto expired;
+	if (x->lft.hard_add_expires_seconds) {
+		time64_t tmo = x->lft.hard_add_expires_seconds +
+			x->curlft.add_time - now;
+		if (tmo <= 0) {
+			if (x->xflags & XFRM_SOFT_EXPIRE) {
+				/* enter hard expire without soft expire first?!
+				 * setting a new date could trigger this.
+				 * workaround: fix x->curflt.add_time by below:
+				 */
+				x->curlft.add_time = now - x->saved_tmo - 1;
+				tmo = x->lft.hard_add_expires_seconds - x->saved_tmo;
+			} else
+				goto expired;
+		}
+		if (tmo < next)
+			next = tmo;
+	}
+	if (x->lft.hard_use_expires_seconds) {
+		time64_t tmo = x->lft.hard_use_expires_seconds +
+			(READ_ONCE(x->curlft.use_time) ? : now) - now;
+		if (tmo <= 0)
+			goto expired;
+		if (tmo < next)
+			next = tmo;
+	}
+	if (x->km.dying)
+		goto resched;
+	if (x->lft.soft_add_expires_seconds) {
+		time64_t tmo = x->lft.soft_add_expires_seconds +
+			x->curlft.add_time - now;
+		if (tmo <= 0) {
+			warn = 1;
+			x->xflags &= ~XFRM_SOFT_EXPIRE;
+		} else if (tmo < next) {
+			next = tmo;
+			x->xflags |= XFRM_SOFT_EXPIRE;
+			x->saved_tmo = tmo;
+		}
+	}
+	if (x->lft.soft_use_expires_seconds) {
+		time64_t tmo = x->lft.soft_use_expires_seconds +
+			(READ_ONCE(x->curlft.use_time) ? : now) - now;
+		if (tmo <= 0)
+			warn = 1;
+		else if (tmo < next)
+			next = tmo;
+	}
+
+	x->km.dying = warn;
+	if (warn)
+		km_state_expired(x, 0, 0);
+resched:
+	if (next != TIME64_MAX) {
+		hrtimer_forward_now(&x->mtimer, ktime_set(next, 0));
+		ret = HRTIMER_RESTART;
+	}
+
+	goto out;
+
+expired:
+	if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0)
+		x->km.state = XFRM_STATE_EXPIRED;
+
+	err = __xfrm_state_delete(x);
+	if (!err)
+		km_state_expired(x, 1, 0);
+
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
+
+out:
+	spin_unlock(&x->lock);
+	return ret;
+}
+
+static void xfrm_replay_timer_handler(struct timer_list *t);
+
+struct xfrm_state *xfrm_state_alloc(struct net *net)
+{
+	struct xfrm_state *x;
+
+	x = kmem_cache_zalloc(xfrm_state_cache, GFP_ATOMIC);
+
+	if (x) {
+		write_pnet(&x->xs_net, net);
+		refcount_set(&x->refcnt, 1);
+		atomic_set(&x->tunnel_users, 0);
+		INIT_LIST_HEAD(&x->km.all);
+		INIT_HLIST_NODE(&x->bydst);
+		INIT_HLIST_NODE(&x->bysrc);
+		INIT_HLIST_NODE(&x->byspi);
+		INIT_HLIST_NODE(&x->byseq);
+		hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
+		x->mtimer.function = xfrm_timer_handler;
+		timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
+		x->curlft.add_time = ktime_get_real_seconds();
+		x->lft.soft_byte_limit = XFRM_INF;
+		x->lft.soft_packet_limit = XFRM_INF;
+		x->lft.hard_byte_limit = XFRM_INF;
+		x->lft.hard_packet_limit = XFRM_INF;
+		x->replay_maxage = 0;
+		x->replay_maxdiff = 0;
+		spin_lock_init(&x->lock);
+	}
+	return x;
+}
+EXPORT_SYMBOL(xfrm_state_alloc);
+
+void __xfrm_state_destroy(struct xfrm_state *x, bool sync)
+{
+	WARN_ON(x->km.state != XFRM_STATE_DEAD);
+
+	if (sync) {
+		synchronize_rcu();
+		___xfrm_state_destroy(x);
+	} else {
+		spin_lock_bh(&xfrm_state_gc_lock);
+		hlist_add_head(&x->gclist, &xfrm_state_gc_list);
+		spin_unlock_bh(&xfrm_state_gc_lock);
+		schedule_work(&xfrm_state_gc_work);
+	}
+}
+EXPORT_SYMBOL(__xfrm_state_destroy);
+
+int __xfrm_state_delete(struct xfrm_state *x)
+{
+	struct net *net = xs_net(x);
+	int err = -ESRCH;
+
+	if (x->km.state != XFRM_STATE_DEAD) {
+		x->km.state = XFRM_STATE_DEAD;
+		spin_lock(&net->xfrm.xfrm_state_lock);
+		list_del(&x->km.all);
+		hlist_del_rcu(&x->bydst);
+		hlist_del_rcu(&x->bysrc);
+		if (x->km.seq)
+			hlist_del_rcu(&x->byseq);
+		if (x->id.spi)
+			hlist_del_rcu(&x->byspi);
+		net->xfrm.state_num--;
+		spin_unlock(&net->xfrm.xfrm_state_lock);
+
+		if (x->encap_sk)
+			sock_put(rcu_dereference_raw(x->encap_sk));
+
+		xfrm_dev_state_delete(x);
+
+		/* All xfrm_state objects are created by xfrm_state_alloc.
+		 * The xfrm_state_alloc call gives a reference, and that
+		 * is what we are dropping here.
+		 */
+		xfrm_state_put(x);
+		err = 0;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(__xfrm_state_delete);
+
+int xfrm_state_delete(struct xfrm_state *x)
+{
+	int err;
+
+	spin_lock_bh(&x->lock);
+	err = __xfrm_state_delete(x);
+	spin_unlock_bh(&x->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(xfrm_state_delete);
+
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+static inline int
+xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
+{
+	int i, err = 0;
+
+	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+		struct xfrm_state *x;
+
+		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+			if (xfrm_id_proto_match(x->id.proto, proto) &&
+			   (err = security_xfrm_state_delete(x)) != 0) {
+				xfrm_audit_state_delete(x, 0, task_valid);
+				return err;
+			}
+		}
+	}
+
+	return err;
+}
+
+static inline int
+xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid)
+{
+	int i, err = 0;
+
+	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+		struct xfrm_state *x;
+		struct xfrm_dev_offload *xso;
+
+		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+			xso = &x->xso;
+
+			if (xso->dev == dev &&
+			   (err = security_xfrm_state_delete(x)) != 0) {
+				xfrm_audit_state_delete(x, 0, task_valid);
+				return err;
+			}
+		}
+	}
+
+	return err;
+}
+#else
+static inline int
+xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
+{
+	return 0;
+}
+
+static inline int
+xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid)
+{
+	return 0;
+}
+#endif
+
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync)
+{
+	int i, err = 0, cnt = 0;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	err = xfrm_state_flush_secctx_check(net, proto, task_valid);
+	if (err)
+		goto out;
+
+	err = -ESRCH;
+	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+		struct xfrm_state *x;
+restart:
+		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+			if (!xfrm_state_kern(x) &&
+			    xfrm_id_proto_match(x->id.proto, proto)) {
+				xfrm_state_hold(x);
+				spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+				err = xfrm_state_delete(x);
+				xfrm_audit_state_delete(x, err ? 0 : 1,
+							task_valid);
+				if (sync)
+					xfrm_state_put_sync(x);
+				else
+					xfrm_state_put(x);
+				if (!err)
+					cnt++;
+
+				spin_lock_bh(&net->xfrm.xfrm_state_lock);
+				goto restart;
+			}
+		}
+	}
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	if (cnt)
+		err = 0;
+
+	return err;
+}
+EXPORT_SYMBOL(xfrm_state_flush);
+
+int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid)
+{
+	int i, err = 0, cnt = 0;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	err = xfrm_dev_state_flush_secctx_check(net, dev, task_valid);
+	if (err)
+		goto out;
+
+	err = -ESRCH;
+	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+		struct xfrm_state *x;
+		struct xfrm_dev_offload *xso;
+restart:
+		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+			xso = &x->xso;
+
+			if (!xfrm_state_kern(x) && xso->dev == dev) {
+				xfrm_state_hold(x);
+				spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+				err = xfrm_state_delete(x);
+				xfrm_audit_state_delete(x, err ? 0 : 1,
+							task_valid);
+				xfrm_state_put(x);
+				if (!err)
+					cnt++;
+
+				spin_lock_bh(&net->xfrm.xfrm_state_lock);
+				goto restart;
+			}
+		}
+	}
+	if (cnt)
+		err = 0;
+
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_dev_state_flush);
+
+void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
+{
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	si->sadcnt = net->xfrm.state_num;
+	si->sadhcnt = net->xfrm.state_hmask + 1;
+	si->sadhmcnt = xfrm_state_hashmax;
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+}
+EXPORT_SYMBOL(xfrm_sad_getinfo);
+
+static void
+__xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
+{
+	const struct flowi4 *fl4 = &fl->u.ip4;
+
+	sel->daddr.a4 = fl4->daddr;
+	sel->saddr.a4 = fl4->saddr;
+	sel->dport = xfrm_flowi_dport(fl, &fl4->uli);
+	sel->dport_mask = htons(0xffff);
+	sel->sport = xfrm_flowi_sport(fl, &fl4->uli);
+	sel->sport_mask = htons(0xffff);
+	sel->family = AF_INET;
+	sel->prefixlen_d = 32;
+	sel->prefixlen_s = 32;
+	sel->proto = fl4->flowi4_proto;
+	sel->ifindex = fl4->flowi4_oif;
+}
+
+static void
+__xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
+{
+	const struct flowi6 *fl6 = &fl->u.ip6;
+
+	/* Initialize temporary selector matching only to current session. */
+	*(struct in6_addr *)&sel->daddr = fl6->daddr;
+	*(struct in6_addr *)&sel->saddr = fl6->saddr;
+	sel->dport = xfrm_flowi_dport(fl, &fl6->uli);
+	sel->dport_mask = htons(0xffff);
+	sel->sport = xfrm_flowi_sport(fl, &fl6->uli);
+	sel->sport_mask = htons(0xffff);
+	sel->family = AF_INET6;
+	sel->prefixlen_d = 128;
+	sel->prefixlen_s = 128;
+	sel->proto = fl6->flowi6_proto;
+	sel->ifindex = fl6->flowi6_oif;
+}
+
+static void
+xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
+		    const struct xfrm_tmpl *tmpl,
+		    const xfrm_address_t *daddr, const xfrm_address_t *saddr,
+		    unsigned short family)
+{
+	switch (family) {
+	case AF_INET:
+		__xfrm4_init_tempsel(&x->sel, fl);
+		break;
+	case AF_INET6:
+		__xfrm6_init_tempsel(&x->sel, fl);
+		break;
+	}
+
+	x->id = tmpl->id;
+
+	switch (tmpl->encap_family) {
+	case AF_INET:
+		if (x->id.daddr.a4 == 0)
+			x->id.daddr.a4 = daddr->a4;
+		x->props.saddr = tmpl->saddr;
+		if (x->props.saddr.a4 == 0)
+			x->props.saddr.a4 = saddr->a4;
+		break;
+	case AF_INET6:
+		if (ipv6_addr_any((struct in6_addr *)&x->id.daddr))
+			memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
+		memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr));
+		if (ipv6_addr_any((struct in6_addr *)&x->props.saddr))
+			memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr));
+		break;
+	}
+
+	x->props.mode = tmpl->mode;
+	x->props.reqid = tmpl->reqid;
+	x->props.family = tmpl->encap_family;
+}
+
+static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
+						  const xfrm_address_t *daddr,
+						  __be32 spi, u8 proto,
+						  unsigned short family,
+						  struct xfrm_dev_offload *xdo)
+{
+	unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+	struct xfrm_state *x;
+
+	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+#ifdef CONFIG_XFRM_OFFLOAD
+		if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) {
+			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
+				/* HW states are in the head of list, there is
+				 * no need to iterate further.
+				 */
+				break;
+
+			/* Packet offload: both policy and SA should
+			 * have same device.
+			 */
+			if (xdo->dev != x->xso.dev)
+				continue;
+		} else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+			/* Skip HW policy for SW lookups */
+			continue;
+#endif
+		if (x->props.family != family ||
+		    x->id.spi       != spi ||
+		    x->id.proto     != proto ||
+		    !xfrm_addr_equal(&x->id.daddr, daddr, family))
+			continue;
+
+		if ((mark & x->mark.m) != x->mark.v)
+			continue;
+		if (!xfrm_state_hold_rcu(x))
+			continue;
+		return x;
+	}
+
+	return NULL;
+}
+
+static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
+					      const xfrm_address_t *daddr,
+					      __be32 spi, u8 proto,
+					      unsigned short family)
+{
+	unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+	struct xfrm_state *x;
+
+	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+		if (x->props.family != family ||
+		    x->id.spi       != spi ||
+		    x->id.proto     != proto ||
+		    !xfrm_addr_equal(&x->id.daddr, daddr, family))
+			continue;
+
+		if ((mark & x->mark.m) != x->mark.v)
+			continue;
+		if (!xfrm_state_hold_rcu(x))
+			continue;
+		return x;
+	}
+
+	return NULL;
+}
+
+static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+						     const xfrm_address_t *daddr,
+						     const xfrm_address_t *saddr,
+						     u8 proto, unsigned short family)
+{
+	unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
+	struct xfrm_state *x;
+
+	hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) {
+		if (x->props.family != family ||
+		    x->id.proto     != proto ||
+		    !xfrm_addr_equal(&x->id.daddr, daddr, family) ||
+		    !xfrm_addr_equal(&x->props.saddr, saddr, family))
+			continue;
+
+		if ((mark & x->mark.m) != x->mark.v)
+			continue;
+		if (!xfrm_state_hold_rcu(x))
+			continue;
+		return x;
+	}
+
+	return NULL;
+}
+
+static inline struct xfrm_state *
+__xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
+{
+	struct net *net = xs_net(x);
+	u32 mark = x->mark.v & x->mark.m;
+
+	if (use_spi)
+		return __xfrm_state_lookup(net, mark, &x->id.daddr,
+					   x->id.spi, x->id.proto, family);
+	else
+		return __xfrm_state_lookup_byaddr(net, mark,
+						  &x->id.daddr,
+						  &x->props.saddr,
+						  x->id.proto, family);
+}
+
+static void xfrm_hash_grow_check(struct net *net, int have_hash_collision)
+{
+	if (have_hash_collision &&
+	    (net->xfrm.state_hmask + 1) < xfrm_state_hashmax &&
+	    net->xfrm.state_num > net->xfrm.state_hmask)
+		schedule_work(&net->xfrm.state_hash_work);
+}
+
+static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
+			       const struct flowi *fl, unsigned short family,
+			       struct xfrm_state **best, int *acq_in_progress,
+			       int *error)
+{
+	/* Resolution logic:
+	 * 1. There is a valid state with matching selector. Done.
+	 * 2. Valid state with inappropriate selector. Skip.
+	 *
+	 * Entering area of "sysdeps".
+	 *
+	 * 3. If state is not valid, selector is temporary, it selects
+	 *    only session which triggered previous resolution. Key
+	 *    manager will do something to install a state with proper
+	 *    selector.
+	 */
+	if (x->km.state == XFRM_STATE_VALID) {
+		if ((x->sel.family &&
+		     (x->sel.family != family ||
+		      !xfrm_selector_match(&x->sel, fl, family))) ||
+		    !security_xfrm_state_pol_flow_match(x, pol,
+							&fl->u.__fl_common))
+			return;
+
+		if (!*best ||
+		    (*best)->km.dying > x->km.dying ||
+		    ((*best)->km.dying == x->km.dying &&
+		     (*best)->curlft.add_time < x->curlft.add_time))
+			*best = x;
+	} else if (x->km.state == XFRM_STATE_ACQ) {
+		*acq_in_progress = 1;
+	} else if (x->km.state == XFRM_STATE_ERROR ||
+		   x->km.state == XFRM_STATE_EXPIRED) {
+		if ((!x->sel.family ||
+		     (x->sel.family == family &&
+		      xfrm_selector_match(&x->sel, fl, family))) &&
+		    security_xfrm_state_pol_flow_match(x, pol,
+						       &fl->u.__fl_common))
+			*error = -ESRCH;
+	}
+}
+
+struct xfrm_state *
+xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
+		const struct flowi *fl, struct xfrm_tmpl *tmpl,
+		struct xfrm_policy *pol, int *err,
+		unsigned short family, u32 if_id)
+{
+	static xfrm_address_t saddr_wildcard = { };
+	struct net *net = xp_net(pol);
+	unsigned int h, h_wildcard;
+	struct xfrm_state *x, *x0, *to_put;
+	int acquire_in_progress = 0;
+	int error = 0;
+	struct xfrm_state *best = NULL;
+	u32 mark = pol->mark.v & pol->mark.m;
+	unsigned short encap_family = tmpl->encap_family;
+	unsigned int sequence;
+	struct km_event c;
+
+	to_put = NULL;
+
+	sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
+
+	rcu_read_lock();
+	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
+	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
+#ifdef CONFIG_XFRM_OFFLOAD
+		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
+				/* HW states are in the head of list, there is
+				 * no need to iterate further.
+				 */
+				break;
+
+			/* Packet offload: both policy and SA should
+			 * have same device.
+			 */
+			if (pol->xdo.dev != x->xso.dev)
+				continue;
+		} else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+			/* Skip HW policy for SW lookups */
+			continue;
+#endif
+		if (x->props.family == encap_family &&
+		    x->props.reqid == tmpl->reqid &&
+		    (mark & x->mark.m) == x->mark.v &&
+		    x->if_id == if_id &&
+		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
+		    xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
+		    tmpl->mode == x->props.mode &&
+		    tmpl->id.proto == x->id.proto &&
+		    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
+			xfrm_state_look_at(pol, x, fl, family,
+					   &best, &acquire_in_progress, &error);
+	}
+	if (best || acquire_in_progress)
+		goto found;
+
+	h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
+	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) {
+#ifdef CONFIG_XFRM_OFFLOAD
+		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
+				/* HW states are in the head of list, there is
+				 * no need to iterate further.
+				 */
+				break;
+
+			/* Packet offload: both policy and SA should
+			 * have same device.
+			 */
+			if (pol->xdo.dev != x->xso.dev)
+				continue;
+		} else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+			/* Skip HW policy for SW lookups */
+			continue;
+#endif
+		if (x->props.family == encap_family &&
+		    x->props.reqid == tmpl->reqid &&
+		    (mark & x->mark.m) == x->mark.v &&
+		    x->if_id == if_id &&
+		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
+		    xfrm_addr_equal(&x->id.daddr, daddr, encap_family) &&
+		    tmpl->mode == x->props.mode &&
+		    tmpl->id.proto == x->id.proto &&
+		    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
+			xfrm_state_look_at(pol, x, fl, family,
+					   &best, &acquire_in_progress, &error);
+	}
+
+found:
+	x = best;
+	if (!x && !error && !acquire_in_progress) {
+		if (tmpl->id.spi &&
+		    (x0 = __xfrm_state_lookup_all(net, mark, daddr,
+						  tmpl->id.spi, tmpl->id.proto,
+						  encap_family,
+						  &pol->xdo)) != NULL) {
+			to_put = x0;
+			error = -EEXIST;
+			goto out;
+		}
+
+		c.net = net;
+		/* If the KMs have no listeners (yet...), avoid allocating an SA
+		 * for each and every packet - garbage collection might not
+		 * handle the flood.
+		 */
+		if (!km_is_alive(&c)) {
+			error = -ESRCH;
+			goto out;
+		}
+
+		x = xfrm_state_alloc(net);
+		if (x == NULL) {
+			error = -ENOMEM;
+			goto out;
+		}
+		/* Initialize temporary state matching only
+		 * to current session. */
+		xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family);
+		memcpy(&x->mark, &pol->mark, sizeof(x->mark));
+		x->if_id = if_id;
+
+		error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid);
+		if (error) {
+			x->km.state = XFRM_STATE_DEAD;
+			to_put = x;
+			x = NULL;
+			goto out;
+		}
+#ifdef CONFIG_XFRM_OFFLOAD
+		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+			struct xfrm_dev_offload *xdo = &pol->xdo;
+			struct xfrm_dev_offload *xso = &x->xso;
+
+			xso->type = XFRM_DEV_OFFLOAD_PACKET;
+			xso->dir = xdo->dir;
+			xso->dev = xdo->dev;
+			xso->real_dev = xdo->real_dev;
+			xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ;
+			netdev_tracker_alloc(xso->dev, &xso->dev_tracker,
+					     GFP_ATOMIC);
+			error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL);
+			if (error) {
+				xso->dir = 0;
+				netdev_put(xso->dev, &xso->dev_tracker);
+				xso->dev = NULL;
+				xso->real_dev = NULL;
+				xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+				x->km.state = XFRM_STATE_DEAD;
+				to_put = x;
+				x = NULL;
+				goto out;
+			}
+		}
+#endif
+		if (km_query(x, tmpl, pol) == 0) {
+			spin_lock_bh(&net->xfrm.xfrm_state_lock);
+			x->km.state = XFRM_STATE_ACQ;
+			list_add(&x->km.all, &net->xfrm.state_all);
+			XFRM_STATE_INSERT(bydst, &x->bydst,
+					  net->xfrm.state_bydst + h,
+					  x->xso.type);
+			h = xfrm_src_hash(net, daddr, saddr, encap_family);
+			XFRM_STATE_INSERT(bysrc, &x->bysrc,
+					  net->xfrm.state_bysrc + h,
+					  x->xso.type);
+			if (x->id.spi) {
+				h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
+				XFRM_STATE_INSERT(byspi, &x->byspi,
+						  net->xfrm.state_byspi + h,
+						  x->xso.type);
+			}
+			if (x->km.seq) {
+				h = xfrm_seq_hash(net, x->km.seq);
+				XFRM_STATE_INSERT(byseq, &x->byseq,
+						  net->xfrm.state_byseq + h,
+						  x->xso.type);
+			}
+			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
+			hrtimer_start(&x->mtimer,
+				      ktime_set(net->xfrm.sysctl_acq_expires, 0),
+				      HRTIMER_MODE_REL_SOFT);
+			net->xfrm.state_num++;
+			xfrm_hash_grow_check(net, x->bydst.next != NULL);
+			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		} else {
+#ifdef CONFIG_XFRM_OFFLOAD
+			struct xfrm_dev_offload *xso = &x->xso;
+
+			if (xso->type == XFRM_DEV_OFFLOAD_PACKET) {
+				xfrm_dev_state_delete(x);
+				xfrm_dev_state_free(x);
+			}
+#endif
+			x->km.state = XFRM_STATE_DEAD;
+			to_put = x;
+			x = NULL;
+			error = -ESRCH;
+		}
+	}
+out:
+	if (x) {
+		if (!xfrm_state_hold_rcu(x)) {
+			*err = -EAGAIN;
+			x = NULL;
+		}
+	} else {
+		*err = acquire_in_progress ? -EAGAIN : error;
+	}
+	rcu_read_unlock();
+	if (to_put)
+		xfrm_state_put(to_put);
+
+	if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) {
+		*err = -EAGAIN;
+		if (x) {
+			xfrm_state_put(x);
+			x = NULL;
+		}
+	}
+
+	return x;
+}
+
+struct xfrm_state *
+xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id,
+		    xfrm_address_t *daddr, xfrm_address_t *saddr,
+		    unsigned short family, u8 mode, u8 proto, u32 reqid)
+{
+	unsigned int h;
+	struct xfrm_state *rx = NULL, *x = NULL;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
+	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+		if (x->props.family == family &&
+		    x->props.reqid == reqid &&
+		    (mark & x->mark.m) == x->mark.v &&
+		    x->if_id == if_id &&
+		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
+		    xfrm_state_addr_check(x, daddr, saddr, family) &&
+		    mode == x->props.mode &&
+		    proto == x->id.proto &&
+		    x->km.state == XFRM_STATE_VALID) {
+			rx = x;
+			break;
+		}
+	}
+
+	if (rx)
+		xfrm_state_hold(rx);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+
+	return rx;
+}
+EXPORT_SYMBOL(xfrm_stateonly_find);
+
+struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
+					      unsigned short family)
+{
+	struct xfrm_state *x;
+	struct xfrm_state_walk *w;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	list_for_each_entry(w, &net->xfrm.state_all, all) {
+		x = container_of(w, struct xfrm_state, km);
+		if (x->props.family != family ||
+			x->id.spi != spi)
+			continue;
+
+		xfrm_state_hold(x);
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		return x;
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return NULL;
+}
+EXPORT_SYMBOL(xfrm_state_lookup_byspi);
+
+static void __xfrm_state_insert(struct xfrm_state *x)
+{
+	struct net *net = xs_net(x);
+	unsigned int h;
+
+	list_add(&x->km.all, &net->xfrm.state_all);
+
+	h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr,
+			  x->props.reqid, x->props.family);
+	XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
+			  x->xso.type);
+
+	h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family);
+	XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h,
+			  x->xso.type);
+
+	if (x->id.spi) {
+		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto,
+				  x->props.family);
+
+		XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h,
+				  x->xso.type);
+	}
+
+	if (x->km.seq) {
+		h = xfrm_seq_hash(net, x->km.seq);
+
+		XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h,
+				  x->xso.type);
+	}
+
+	hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
+	if (x->replay_maxage)
+		mod_timer(&x->rtimer, jiffies + x->replay_maxage);
+
+	net->xfrm.state_num++;
+
+	xfrm_hash_grow_check(net, x->bydst.next != NULL);
+}
+
+/* net->xfrm.xfrm_state_lock is held */
+static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
+{
+	struct net *net = xs_net(xnew);
+	unsigned short family = xnew->props.family;
+	u32 reqid = xnew->props.reqid;
+	struct xfrm_state *x;
+	unsigned int h;
+	u32 mark = xnew->mark.v & xnew->mark.m;
+	u32 if_id = xnew->if_id;
+
+	h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family);
+	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+		if (x->props.family	== family &&
+		    x->props.reqid	== reqid &&
+		    x->if_id		== if_id &&
+		    (mark & x->mark.m) == x->mark.v &&
+		    xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) &&
+		    xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family))
+			x->genid++;
+	}
+}
+
+void xfrm_state_insert(struct xfrm_state *x)
+{
+	struct net *net = xs_net(x);
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	__xfrm_state_bump_genids(x);
+	__xfrm_state_insert(x);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+}
+EXPORT_SYMBOL(xfrm_state_insert);
+
+/* net->xfrm.xfrm_state_lock is held */
+static struct xfrm_state *__find_acq_core(struct net *net,
+					  const struct xfrm_mark *m,
+					  unsigned short family, u8 mode,
+					  u32 reqid, u32 if_id, u8 proto,
+					  const xfrm_address_t *daddr,
+					  const xfrm_address_t *saddr,
+					  int create)
+{
+	unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
+	struct xfrm_state *x;
+	u32 mark = m->v & m->m;
+
+	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+		if (x->props.reqid  != reqid ||
+		    x->props.mode   != mode ||
+		    x->props.family != family ||
+		    x->km.state     != XFRM_STATE_ACQ ||
+		    x->id.spi       != 0 ||
+		    x->id.proto	    != proto ||
+		    (mark & x->mark.m) != x->mark.v ||
+		    !xfrm_addr_equal(&x->id.daddr, daddr, family) ||
+		    !xfrm_addr_equal(&x->props.saddr, saddr, family))
+			continue;
+
+		xfrm_state_hold(x);
+		return x;
+	}
+
+	if (!create)
+		return NULL;
+
+	x = xfrm_state_alloc(net);
+	if (likely(x)) {
+		switch (family) {
+		case AF_INET:
+			x->sel.daddr.a4 = daddr->a4;
+			x->sel.saddr.a4 = saddr->a4;
+			x->sel.prefixlen_d = 32;
+			x->sel.prefixlen_s = 32;
+			x->props.saddr.a4 = saddr->a4;
+			x->id.daddr.a4 = daddr->a4;
+			break;
+
+		case AF_INET6:
+			x->sel.daddr.in6 = daddr->in6;
+			x->sel.saddr.in6 = saddr->in6;
+			x->sel.prefixlen_d = 128;
+			x->sel.prefixlen_s = 128;
+			x->props.saddr.in6 = saddr->in6;
+			x->id.daddr.in6 = daddr->in6;
+			break;
+		}
+
+		x->km.state = XFRM_STATE_ACQ;
+		x->id.proto = proto;
+		x->props.family = family;
+		x->props.mode = mode;
+		x->props.reqid = reqid;
+		x->if_id = if_id;
+		x->mark.v = m->v;
+		x->mark.m = m->m;
+		x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
+		xfrm_state_hold(x);
+		hrtimer_start(&x->mtimer,
+			      ktime_set(net->xfrm.sysctl_acq_expires, 0),
+			      HRTIMER_MODE_REL_SOFT);
+		list_add(&x->km.all, &net->xfrm.state_all);
+		XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
+				  x->xso.type);
+		h = xfrm_src_hash(net, daddr, saddr, family);
+		XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h,
+				  x->xso.type);
+
+		net->xfrm.state_num++;
+
+		xfrm_hash_grow_check(net, x->bydst.next != NULL);
+	}
+
+	return x;
+}
+
+static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq);
+
+int xfrm_state_add(struct xfrm_state *x)
+{
+	struct net *net = xs_net(x);
+	struct xfrm_state *x1, *to_put;
+	int family;
+	int err;
+	u32 mark = x->mark.v & x->mark.m;
+	int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
+
+	family = x->props.family;
+
+	to_put = NULL;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+
+	x1 = __xfrm_state_locate(x, use_spi, family);
+	if (x1) {
+		to_put = x1;
+		x1 = NULL;
+		err = -EEXIST;
+		goto out;
+	}
+
+	if (use_spi && x->km.seq) {
+		x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq);
+		if (x1 && ((x1->id.proto != x->id.proto) ||
+		    !xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) {
+			to_put = x1;
+			x1 = NULL;
+		}
+	}
+
+	if (use_spi && !x1)
+		x1 = __find_acq_core(net, &x->mark, family, x->props.mode,
+				     x->props.reqid, x->if_id, x->id.proto,
+				     &x->id.daddr, &x->props.saddr, 0);
+
+	__xfrm_state_bump_genids(x);
+	__xfrm_state_insert(x);
+	err = 0;
+
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	if (x1) {
+		xfrm_state_delete(x1);
+		xfrm_state_put(x1);
+	}
+
+	if (to_put)
+		xfrm_state_put(to_put);
+
+	return err;
+}
+EXPORT_SYMBOL(xfrm_state_add);
+
+#ifdef CONFIG_XFRM_MIGRATE
+static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security)
+{
+	struct xfrm_user_sec_ctx *uctx;
+	int size = sizeof(*uctx) + security->ctx_len;
+	int err;
+
+	uctx = kmalloc(size, GFP_KERNEL);
+	if (!uctx)
+		return -ENOMEM;
+
+	uctx->exttype = XFRMA_SEC_CTX;
+	uctx->len = size;
+	uctx->ctx_doi = security->ctx_doi;
+	uctx->ctx_alg = security->ctx_alg;
+	uctx->ctx_len = security->ctx_len;
+	memcpy(uctx + 1, security->ctx_str, security->ctx_len);
+	err = security_xfrm_state_alloc(x, uctx);
+	kfree(uctx);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
+					   struct xfrm_encap_tmpl *encap)
+{
+	struct net *net = xs_net(orig);
+	struct xfrm_state *x = xfrm_state_alloc(net);
+	if (!x)
+		goto out;
+
+	memcpy(&x->id, &orig->id, sizeof(x->id));
+	memcpy(&x->sel, &orig->sel, sizeof(x->sel));
+	memcpy(&x->lft, &orig->lft, sizeof(x->lft));
+	x->props.mode = orig->props.mode;
+	x->props.replay_window = orig->props.replay_window;
+	x->props.reqid = orig->props.reqid;
+	x->props.family = orig->props.family;
+	x->props.saddr = orig->props.saddr;
+
+	if (orig->aalg) {
+		x->aalg = xfrm_algo_auth_clone(orig->aalg);
+		if (!x->aalg)
+			goto error;
+	}
+	x->props.aalgo = orig->props.aalgo;
+
+	if (orig->aead) {
+		x->aead = xfrm_algo_aead_clone(orig->aead);
+		x->geniv = orig->geniv;
+		if (!x->aead)
+			goto error;
+	}
+	if (orig->ealg) {
+		x->ealg = xfrm_algo_clone(orig->ealg);
+		if (!x->ealg)
+			goto error;
+	}
+	x->props.ealgo = orig->props.ealgo;
+
+	if (orig->calg) {
+		x->calg = xfrm_algo_clone(orig->calg);
+		if (!x->calg)
+			goto error;
+	}
+	x->props.calgo = orig->props.calgo;
+
+	if (encap || orig->encap) {
+		if (encap)
+			x->encap = kmemdup(encap, sizeof(*x->encap),
+					GFP_KERNEL);
+		else
+			x->encap = kmemdup(orig->encap, sizeof(*x->encap),
+					GFP_KERNEL);
+
+		if (!x->encap)
+			goto error;
+	}
+
+	if (orig->security)
+		if (clone_security(x, orig->security))
+			goto error;
+
+	if (orig->coaddr) {
+		x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr),
+				    GFP_KERNEL);
+		if (!x->coaddr)
+			goto error;
+	}
+
+	if (orig->replay_esn) {
+		if (xfrm_replay_clone(x, orig))
+			goto error;
+	}
+
+	memcpy(&x->mark, &orig->mark, sizeof(x->mark));
+	memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark));
+
+	x->props.flags = orig->props.flags;
+	x->props.extra_flags = orig->props.extra_flags;
+
+	x->if_id = orig->if_id;
+	x->tfcpad = orig->tfcpad;
+	x->replay_maxdiff = orig->replay_maxdiff;
+	x->replay_maxage = orig->replay_maxage;
+	memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft));
+	x->km.state = orig->km.state;
+	x->km.seq = orig->km.seq;
+	x->replay = orig->replay;
+	x->preplay = orig->preplay;
+	x->mapping_maxage = orig->mapping_maxage;
+	x->lastused = orig->lastused;
+	x->new_mapping = 0;
+	x->new_mapping_sport = 0;
+
+	return x;
+
+ error:
+	xfrm_state_put(x);
+out:
+	return NULL;
+}
+
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net,
+						u32 if_id)
+{
+	unsigned int h;
+	struct xfrm_state *x = NULL;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+
+	if (m->reqid) {
+		h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
+				  m->reqid, m->old_family);
+		hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+			if (x->props.mode != m->mode ||
+			    x->id.proto != m->proto)
+				continue;
+			if (m->reqid && x->props.reqid != m->reqid)
+				continue;
+			if (if_id != 0 && x->if_id != if_id)
+				continue;
+			if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
+					     m->old_family) ||
+			    !xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
+					     m->old_family))
+				continue;
+			xfrm_state_hold(x);
+			break;
+		}
+	} else {
+		h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
+				  m->old_family);
+		hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) {
+			if (x->props.mode != m->mode ||
+			    x->id.proto != m->proto)
+				continue;
+			if (if_id != 0 && x->if_id != if_id)
+				continue;
+			if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
+					     m->old_family) ||
+			    !xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
+					     m->old_family))
+				continue;
+			xfrm_state_hold(x);
+			break;
+		}
+	}
+
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	return x;
+}
+EXPORT_SYMBOL(xfrm_migrate_state_find);
+
+struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
+				      struct xfrm_migrate *m,
+				      struct xfrm_encap_tmpl *encap)
+{
+	struct xfrm_state *xc;
+
+	xc = xfrm_state_clone(x, encap);
+	if (!xc)
+		return NULL;
+
+	xc->props.family = m->new_family;
+
+	if (xfrm_init_state(xc) < 0)
+		goto error;
+
+	memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr));
+	memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr));
+
+	/* add state */
+	if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) {
+		/* a care is needed when the destination address of the
+		   state is to be updated as it is a part of triplet */
+		xfrm_state_insert(xc);
+	} else {
+		if (xfrm_state_add(xc) < 0)
+			goto error;
+	}
+
+	return xc;
+error:
+	xfrm_state_put(xc);
+	return NULL;
+}
+EXPORT_SYMBOL(xfrm_state_migrate);
+#endif
+
+int xfrm_state_update(struct xfrm_state *x)
+{
+	struct xfrm_state *x1, *to_put;
+	int err;
+	int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
+	struct net *net = xs_net(x);
+
+	to_put = NULL;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	x1 = __xfrm_state_locate(x, use_spi, x->props.family);
+
+	err = -ESRCH;
+	if (!x1)
+		goto out;
+
+	if (xfrm_state_kern(x1)) {
+		to_put = x1;
+		err = -EEXIST;
+		goto out;
+	}
+
+	if (x1->km.state == XFRM_STATE_ACQ) {
+		__xfrm_state_insert(x);
+		x = NULL;
+	}
+	err = 0;
+
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	if (to_put)
+		xfrm_state_put(to_put);
+
+	if (err)
+		return err;
+
+	if (!x) {
+		xfrm_state_delete(x1);
+		xfrm_state_put(x1);
+		return 0;
+	}
+
+	err = -EINVAL;
+	spin_lock_bh(&x1->lock);
+	if (likely(x1->km.state == XFRM_STATE_VALID)) {
+		if (x->encap && x1->encap &&
+		    x->encap->encap_type == x1->encap->encap_type)
+			memcpy(x1->encap, x->encap, sizeof(*x1->encap));
+		else if (x->encap || x1->encap)
+			goto fail;
+
+		if (x->coaddr && x1->coaddr) {
+			memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr));
+		}
+		if (!use_spi && memcmp(&x1->sel, &x->sel, sizeof(x1->sel)))
+			memcpy(&x1->sel, &x->sel, sizeof(x1->sel));
+		memcpy(&x1->lft, &x->lft, sizeof(x1->lft));
+		x1->km.dying = 0;
+
+		hrtimer_start(&x1->mtimer, ktime_set(1, 0),
+			      HRTIMER_MODE_REL_SOFT);
+		if (READ_ONCE(x1->curlft.use_time))
+			xfrm_state_check_expire(x1);
+
+		if (x->props.smark.m || x->props.smark.v || x->if_id) {
+			spin_lock_bh(&net->xfrm.xfrm_state_lock);
+
+			if (x->props.smark.m || x->props.smark.v)
+				x1->props.smark = x->props.smark;
+
+			if (x->if_id)
+				x1->if_id = x->if_id;
+
+			__xfrm_state_bump_genids(x1);
+			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		}
+
+		err = 0;
+		x->km.state = XFRM_STATE_DEAD;
+		__xfrm_state_put(x);
+	}
+
+fail:
+	spin_unlock_bh(&x1->lock);
+
+	xfrm_state_put(x1);
+
+	return err;
+}
+EXPORT_SYMBOL(xfrm_state_update);
+
+int xfrm_state_check_expire(struct xfrm_state *x)
+{
+	xfrm_dev_state_update_curlft(x);
+
+	if (!READ_ONCE(x->curlft.use_time))
+		WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds());
+
+	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
+	    x->curlft.packets >= x->lft.hard_packet_limit) {
+		x->km.state = XFRM_STATE_EXPIRED;
+		hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT);
+		return -EINVAL;
+	}
+
+	if (!x->km.dying &&
+	    (x->curlft.bytes >= x->lft.soft_byte_limit ||
+	     x->curlft.packets >= x->lft.soft_packet_limit)) {
+		x->km.dying = 1;
+		km_state_expired(x, 0, 0);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_state_check_expire);
+
+struct xfrm_state *
+xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
+		  u8 proto, unsigned short family)
+{
+	struct xfrm_state *x;
+
+	rcu_read_lock();
+	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+	rcu_read_unlock();
+	return x;
+}
+EXPORT_SYMBOL(xfrm_state_lookup);
+
+struct xfrm_state *
+xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+			 const xfrm_address_t *daddr, const xfrm_address_t *saddr,
+			 u8 proto, unsigned short family)
+{
+	struct xfrm_state *x;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return x;
+}
+EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
+
+struct xfrm_state *
+xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
+	      u32 if_id, u8 proto, const xfrm_address_t *daddr,
+	      const xfrm_address_t *saddr, int create, unsigned short family)
+{
+	struct xfrm_state *x;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	return x;
+}
+EXPORT_SYMBOL(xfrm_find_acq);
+
+#ifdef CONFIG_XFRM_SUB_POLICY
+#if IS_ENABLED(CONFIG_IPV6)
+/* distribution counting sort function for xfrm_state and xfrm_tmpl */
+static void
+__xfrm6_sort(void **dst, void **src, int n,
+	     int (*cmp)(const void *p), int maxclass)
+{
+	int count[XFRM_MAX_DEPTH] = { };
+	int class[XFRM_MAX_DEPTH];
+	int i;
+
+	for (i = 0; i < n; i++) {
+		int c = cmp(src[i]);
+
+		class[i] = c;
+		count[c]++;
+	}
+
+	for (i = 2; i < maxclass; i++)
+		count[i] += count[i - 1];
+
+	for (i = 0; i < n; i++) {
+		dst[count[class[i] - 1]++] = src[i];
+		src[i] = NULL;
+	}
+}
+
+/* Rule for xfrm_state:
+ *
+ * rule 1: select IPsec transport except AH
+ * rule 2: select MIPv6 RO or inbound trigger
+ * rule 3: select IPsec transport AH
+ * rule 4: select IPsec tunnel
+ * rule 5: others
+ */
+static int __xfrm6_state_sort_cmp(const void *p)
+{
+	const struct xfrm_state *v = p;
+
+	switch (v->props.mode) {
+	case XFRM_MODE_TRANSPORT:
+		if (v->id.proto != IPPROTO_AH)
+			return 1;
+		else
+			return 3;
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+	case XFRM_MODE_IN_TRIGGER:
+		return 2;
+#endif
+	case XFRM_MODE_TUNNEL:
+	case XFRM_MODE_BEET:
+		return 4;
+	}
+	return 5;
+}
+
+/* Rule for xfrm_tmpl:
+ *
+ * rule 1: select IPsec transport
+ * rule 2: select MIPv6 RO or inbound trigger
+ * rule 3: select IPsec tunnel
+ * rule 4: others
+ */
+static int __xfrm6_tmpl_sort_cmp(const void *p)
+{
+	const struct xfrm_tmpl *v = p;
+
+	switch (v->mode) {
+	case XFRM_MODE_TRANSPORT:
+		return 1;
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+	case XFRM_MODE_IN_TRIGGER:
+		return 2;
+#endif
+	case XFRM_MODE_TUNNEL:
+	case XFRM_MODE_BEET:
+		return 3;
+	}
+	return 4;
+}
+#else
+static inline int __xfrm6_state_sort_cmp(const void *p) { return 5; }
+static inline int __xfrm6_tmpl_sort_cmp(const void *p) { return 4; }
+
+static inline void
+__xfrm6_sort(void **dst, void **src, int n,
+	     int (*cmp)(const void *p), int maxclass)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		dst[i] = src[i];
+}
+#endif /* CONFIG_IPV6 */
+
+void
+xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
+	       unsigned short family)
+{
+	int i;
+
+	if (family == AF_INET6)
+		__xfrm6_sort((void **)dst, (void **)src, n,
+			     __xfrm6_tmpl_sort_cmp, 5);
+	else
+		for (i = 0; i < n; i++)
+			dst[i] = src[i];
+}
+
+void
+xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
+		unsigned short family)
+{
+	int i;
+
+	if (family == AF_INET6)
+		__xfrm6_sort((void **)dst, (void **)src, n,
+			     __xfrm6_state_sort_cmp, 6);
+	else
+		for (i = 0; i < n; i++)
+			dst[i] = src[i];
+}
+#endif
+
+/* Silly enough, but I'm lazy to build resolution list */
+
+static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
+{
+	unsigned int h = xfrm_seq_hash(net, seq);
+	struct xfrm_state *x;
+
+	hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) {
+		if (x->km.seq == seq &&
+		    (mark & x->mark.m) == x->mark.v &&
+		    x->km.state == XFRM_STATE_ACQ) {
+			xfrm_state_hold(x);
+			return x;
+		}
+	}
+
+	return NULL;
+}
+
+struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
+{
+	struct xfrm_state *x;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	x = __xfrm_find_acq_byseq(net, mark, seq);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return x;
+}
+EXPORT_SYMBOL(xfrm_find_acq_byseq);
+
+u32 xfrm_get_acqseq(void)
+{
+	u32 res;
+	static atomic_t acqseq;
+
+	do {
+		res = atomic_inc_return(&acqseq);
+	} while (!res);
+
+	return res;
+}
+EXPORT_SYMBOL(xfrm_get_acqseq);
+
+int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack)
+{
+	switch (proto) {
+	case IPPROTO_AH:
+	case IPPROTO_ESP:
+		break;
+
+	case IPPROTO_COMP:
+		/* IPCOMP spi is 16-bits. */
+		if (max >= 0x10000) {
+			NL_SET_ERR_MSG(extack, "IPCOMP SPI must be <= 65535");
+			return -EINVAL;
+		}
+		break;
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid protocol, must be one of AH, ESP, IPCOMP");
+		return -EINVAL;
+	}
+
+	if (min > max) {
+		NL_SET_ERR_MSG(extack, "Invalid SPI range: min > max");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(verify_spi_info);
+
+int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
+		   struct netlink_ext_ack *extack)
+{
+	struct net *net = xs_net(x);
+	unsigned int h;
+	struct xfrm_state *x0;
+	int err = -ENOENT;
+	__be32 minspi = htonl(low);
+	__be32 maxspi = htonl(high);
+	__be32 newspi = 0;
+	u32 mark = x->mark.v & x->mark.m;
+
+	spin_lock_bh(&x->lock);
+	if (x->km.state == XFRM_STATE_DEAD) {
+		NL_SET_ERR_MSG(extack, "Target ACQUIRE is in DEAD state");
+		goto unlock;
+	}
+
+	err = 0;
+	if (x->id.spi)
+		goto unlock;
+
+	err = -ENOENT;
+
+	if (minspi == maxspi) {
+		x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family);
+		if (x0) {
+			NL_SET_ERR_MSG(extack, "Requested SPI is already in use");
+			xfrm_state_put(x0);
+			goto unlock;
+		}
+		newspi = minspi;
+	} else {
+		u32 spi = 0;
+		for (h = 0; h < high-low+1; h++) {
+			spi = get_random_u32_inclusive(low, high);
+			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
+			if (x0 == NULL) {
+				newspi = htonl(spi);
+				break;
+			}
+			xfrm_state_put(x0);
+		}
+	}
+	if (newspi) {
+		spin_lock_bh(&net->xfrm.xfrm_state_lock);
+		x->id.spi = newspi;
+		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
+		XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h,
+				  x->xso.type);
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+		err = 0;
+	} else {
+		NL_SET_ERR_MSG(extack, "No SPI available in the requested range");
+	}
+
+unlock:
+	spin_unlock_bh(&x->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(xfrm_alloc_spi);
+
+static bool __xfrm_state_filter_match(struct xfrm_state *x,
+				      struct xfrm_address_filter *filter)
+{
+	if (filter) {
+		if ((filter->family == AF_INET ||
+		     filter->family == AF_INET6) &&
+		    x->props.family != filter->family)
+			return false;
+
+		return addr_match(&x->props.saddr, &filter->saddr,
+				  filter->splen) &&
+		       addr_match(&x->id.daddr, &filter->daddr,
+				  filter->dplen);
+	}
+	return true;
+}
+
+int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
+		    int (*func)(struct xfrm_state *, int, void*),
+		    void *data)
+{
+	struct xfrm_state *state;
+	struct xfrm_state_walk *x;
+	int err = 0;
+
+	if (walk->seq != 0 && list_empty(&walk->all))
+		return 0;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	if (list_empty(&walk->all))
+		x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all);
+	else
+		x = list_first_entry(&walk->all, struct xfrm_state_walk, all);
+	list_for_each_entry_from(x, &net->xfrm.state_all, all) {
+		if (x->state == XFRM_STATE_DEAD)
+			continue;
+		state = container_of(x, struct xfrm_state, km);
+		if (!xfrm_id_proto_match(state->id.proto, walk->proto))
+			continue;
+		if (!__xfrm_state_filter_match(state, walk->filter))
+			continue;
+		err = func(state, walk->seq, data);
+		if (err) {
+			list_move_tail(&walk->all, &x->all);
+			goto out;
+		}
+		walk->seq++;
+	}
+	if (walk->seq == 0) {
+		err = -ENOENT;
+		goto out;
+	}
+	list_del_init(&walk->all);
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_state_walk);
+
+void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto,
+			  struct xfrm_address_filter *filter)
+{
+	INIT_LIST_HEAD(&walk->all);
+	walk->proto = proto;
+	walk->state = XFRM_STATE_DEAD;
+	walk->seq = 0;
+	walk->filter = filter;
+}
+EXPORT_SYMBOL(xfrm_state_walk_init);
+
+void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net)
+{
+	kfree(walk->filter);
+
+	if (list_empty(&walk->all))
+		return;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	list_del(&walk->all);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+}
+EXPORT_SYMBOL(xfrm_state_walk_done);
+
+static void xfrm_replay_timer_handler(struct timer_list *t)
+{
+	struct xfrm_state *x = from_timer(x, t, rtimer);
+
+	spin_lock(&x->lock);
+
+	if (x->km.state == XFRM_STATE_VALID) {
+		if (xfrm_aevent_is_on(xs_net(x)))
+			xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT);
+		else
+			x->xflags |= XFRM_TIME_DEFER;
+	}
+
+	spin_unlock(&x->lock);
+}
+
+static LIST_HEAD(xfrm_km_list);
+
+void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
+{
+	struct xfrm_mgr *km;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list)
+		if (km->notify_policy)
+			km->notify_policy(xp, dir, c);
+	rcu_read_unlock();
+}
+
+void km_state_notify(struct xfrm_state *x, const struct km_event *c)
+{
+	struct xfrm_mgr *km;
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list)
+		if (km->notify)
+			km->notify(x, c);
+	rcu_read_unlock();
+}
+
+EXPORT_SYMBOL(km_policy_notify);
+EXPORT_SYMBOL(km_state_notify);
+
+void km_state_expired(struct xfrm_state *x, int hard, u32 portid)
+{
+	struct km_event c;
+
+	c.data.hard = hard;
+	c.portid = portid;
+	c.event = XFRM_MSG_EXPIRE;
+	km_state_notify(x, &c);
+}
+
+EXPORT_SYMBOL(km_state_expired);
+/*
+ * We send to all registered managers regardless of failure
+ * We are happy with one success
+*/
+int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol)
+{
+	int err = -EINVAL, acqret;
+	struct xfrm_mgr *km;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+		acqret = km->acquire(x, t, pol);
+		if (!acqret)
+			err = acqret;
+	}
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(km_query);
+
+static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport)
+{
+	int err = -EINVAL;
+	struct xfrm_mgr *km;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+		if (km->new_mapping)
+			err = km->new_mapping(x, ipaddr, sport);
+		if (!err)
+			break;
+	}
+	rcu_read_unlock();
+	return err;
+}
+
+int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport)
+{
+	int ret = 0;
+
+	if (x->mapping_maxage) {
+		if ((jiffies / HZ - x->new_mapping) > x->mapping_maxage ||
+		    x->new_mapping_sport != sport) {
+			x->new_mapping_sport = sport;
+			x->new_mapping = jiffies / HZ;
+			ret = __km_new_mapping(x, ipaddr, sport);
+		}
+	} else {
+		ret = __km_new_mapping(x, ipaddr, sport);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(km_new_mapping);
+
+void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid)
+{
+	struct km_event c;
+
+	c.data.hard = hard;
+	c.portid = portid;
+	c.event = XFRM_MSG_POLEXPIRE;
+	km_policy_notify(pol, dir, &c);
+}
+EXPORT_SYMBOL(km_policy_expired);
+
+#ifdef CONFIG_XFRM_MIGRATE
+int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+	       const struct xfrm_migrate *m, int num_migrate,
+	       const struct xfrm_kmaddress *k,
+	       const struct xfrm_encap_tmpl *encap)
+{
+	int err = -EINVAL;
+	int ret;
+	struct xfrm_mgr *km;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+		if (km->migrate) {
+			ret = km->migrate(sel, dir, type, m, num_migrate, k,
+					  encap);
+			if (!ret)
+				err = ret;
+		}
+	}
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(km_migrate);
+#endif
+
+int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr)
+{
+	int err = -EINVAL;
+	int ret;
+	struct xfrm_mgr *km;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+		if (km->report) {
+			ret = km->report(net, proto, sel, addr);
+			if (!ret)
+				err = ret;
+		}
+	}
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(km_report);
+
+static bool km_is_alive(const struct km_event *c)
+{
+	struct xfrm_mgr *km;
+	bool is_alive = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+		if (km->is_alive && km->is_alive(c)) {
+			is_alive = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return is_alive;
+}
+
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+static DEFINE_SPINLOCK(xfrm_translator_lock);
+static struct xfrm_translator __rcu *xfrm_translator;
+
+struct xfrm_translator *xfrm_get_translator(void)
+{
+	struct xfrm_translator *xtr;
+
+	rcu_read_lock();
+	xtr = rcu_dereference(xfrm_translator);
+	if (unlikely(!xtr))
+		goto out;
+	if (!try_module_get(xtr->owner))
+		xtr = NULL;
+out:
+	rcu_read_unlock();
+	return xtr;
+}
+EXPORT_SYMBOL_GPL(xfrm_get_translator);
+
+void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+	module_put(xtr->owner);
+}
+EXPORT_SYMBOL_GPL(xfrm_put_translator);
+
+int xfrm_register_translator(struct xfrm_translator *xtr)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_translator_lock);
+	if (unlikely(xfrm_translator != NULL))
+		err = -EEXIST;
+	else
+		rcu_assign_pointer(xfrm_translator, xtr);
+	spin_unlock_bh(&xfrm_translator_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_register_translator);
+
+int xfrm_unregister_translator(struct xfrm_translator *xtr)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_translator_lock);
+	if (likely(xfrm_translator != NULL)) {
+		if (rcu_access_pointer(xfrm_translator) != xtr)
+			err = -EINVAL;
+		else
+			RCU_INIT_POINTER(xfrm_translator, NULL);
+	}
+	spin_unlock_bh(&xfrm_translator_lock);
+	synchronize_rcu();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_unregister_translator);
+#endif
+
+int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
+{
+	int err;
+	u8 *data;
+	struct xfrm_mgr *km;
+	struct xfrm_policy *pol = NULL;
+
+	if (sockptr_is_null(optval) && !optlen) {
+		xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
+		xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL);
+		__sk_dst_reset(sk);
+		return 0;
+	}
+
+	if (optlen <= 0 || optlen > PAGE_SIZE)
+		return -EMSGSIZE;
+
+	data = memdup_sockptr(optval, optlen);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	if (in_compat_syscall()) {
+		struct xfrm_translator *xtr = xfrm_get_translator();
+
+		if (!xtr) {
+			kfree(data);
+			return -EOPNOTSUPP;
+		}
+
+		err = xtr->xlate_user_policy_sockptr(&data, optlen);
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree(data);
+			return err;
+		}
+	}
+
+	err = -EINVAL;
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+		pol = km->compile_policy(sk, optname, data,
+					 optlen, &err);
+		if (err >= 0)
+			break;
+	}
+	rcu_read_unlock();
+
+	if (err >= 0) {
+		xfrm_sk_policy_insert(sk, err, pol);
+		xfrm_pol_put(pol);
+		__sk_dst_reset(sk);
+		err = 0;
+	}
+
+	kfree(data);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_user_policy);
+
+static DEFINE_SPINLOCK(xfrm_km_lock);
+
+void xfrm_register_km(struct xfrm_mgr *km)
+{
+	spin_lock_bh(&xfrm_km_lock);
+	list_add_tail_rcu(&km->list, &xfrm_km_list);
+	spin_unlock_bh(&xfrm_km_lock);
+}
+EXPORT_SYMBOL(xfrm_register_km);
+
+void xfrm_unregister_km(struct xfrm_mgr *km)
+{
+	spin_lock_bh(&xfrm_km_lock);
+	list_del_rcu(&km->list);
+	spin_unlock_bh(&xfrm_km_lock);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL(xfrm_unregister_km);
+
+int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo)
+{
+	int err = 0;
+
+	if (WARN_ON(afinfo->family >= NPROTO))
+		return -EAFNOSUPPORT;
+
+	spin_lock_bh(&xfrm_state_afinfo_lock);
+	if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL))
+		err = -EEXIST;
+	else
+		rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo);
+	spin_unlock_bh(&xfrm_state_afinfo_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_state_register_afinfo);
+
+int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo)
+{
+	int err = 0, family = afinfo->family;
+
+	if (WARN_ON(family >= NPROTO))
+		return -EAFNOSUPPORT;
+
+	spin_lock_bh(&xfrm_state_afinfo_lock);
+	if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) {
+		if (rcu_access_pointer(xfrm_state_afinfo[family]) != afinfo)
+			err = -EINVAL;
+		else
+			RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL);
+	}
+	spin_unlock_bh(&xfrm_state_afinfo_lock);
+	synchronize_rcu();
+	return err;
+}
+EXPORT_SYMBOL(xfrm_state_unregister_afinfo);
+
+struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family)
+{
+	if (unlikely(family >= NPROTO))
+		return NULL;
+
+	return rcu_dereference(xfrm_state_afinfo[family]);
+}
+EXPORT_SYMBOL_GPL(xfrm_state_afinfo_get_rcu);
+
+struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
+{
+	struct xfrm_state_afinfo *afinfo;
+	if (unlikely(family >= NPROTO))
+		return NULL;
+	rcu_read_lock();
+	afinfo = rcu_dereference(xfrm_state_afinfo[family]);
+	if (unlikely(!afinfo))
+		rcu_read_unlock();
+	return afinfo;
+}
+
+void xfrm_flush_gc(void)
+{
+	flush_work(&xfrm_state_gc_work);
+}
+EXPORT_SYMBOL(xfrm_flush_gc);
+
+/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
+void xfrm_state_delete_tunnel(struct xfrm_state *x)
+{
+	if (x->tunnel) {
+		struct xfrm_state *t = x->tunnel;
+
+		if (atomic_read(&t->tunnel_users) == 2)
+			xfrm_state_delete(t);
+		atomic_dec(&t->tunnel_users);
+		xfrm_state_put_sync(t);
+		x->tunnel = NULL;
+	}
+}
+EXPORT_SYMBOL(xfrm_state_delete_tunnel);
+
+u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
+{
+	const struct xfrm_type *type = READ_ONCE(x->type);
+	struct crypto_aead *aead;
+	u32 blksize, net_adj = 0;
+
+	if (x->km.state != XFRM_STATE_VALID ||
+	    !type || type->proto != IPPROTO_ESP)
+		return mtu - x->props.header_len;
+
+	aead = x->data;
+	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
+
+	switch (x->props.mode) {
+	case XFRM_MODE_TRANSPORT:
+	case XFRM_MODE_BEET:
+		if (x->props.family == AF_INET)
+			net_adj = sizeof(struct iphdr);
+		else if (x->props.family == AF_INET6)
+			net_adj = sizeof(struct ipv6hdr);
+		break;
+	case XFRM_MODE_TUNNEL:
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
+		 net_adj) & ~(blksize - 1)) + net_adj - 2;
+}
+EXPORT_SYMBOL_GPL(xfrm_state_mtu);
+
+int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload,
+		      struct netlink_ext_ack *extack)
+{
+	const struct xfrm_mode *inner_mode;
+	const struct xfrm_mode *outer_mode;
+	int family = x->props.family;
+	int err;
+
+	if (family == AF_INET &&
+	    READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc))
+		x->props.flags |= XFRM_STATE_NOPMTUDISC;
+
+	err = -EPROTONOSUPPORT;
+
+	if (x->sel.family != AF_UNSPEC) {
+		inner_mode = xfrm_get_mode(x->props.mode, x->sel.family);
+		if (inner_mode == NULL) {
+			NL_SET_ERR_MSG(extack, "Requested mode not found");
+			goto error;
+		}
+
+		if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) &&
+		    family != x->sel.family) {
+			NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate a change of family");
+			goto error;
+		}
+
+		x->inner_mode = *inner_mode;
+	} else {
+		const struct xfrm_mode *inner_mode_iaf;
+		int iafamily = AF_INET;
+
+		inner_mode = xfrm_get_mode(x->props.mode, x->props.family);
+		if (inner_mode == NULL) {
+			NL_SET_ERR_MSG(extack, "Requested mode not found");
+			goto error;
+		}
+
+		x->inner_mode = *inner_mode;
+
+		if (x->props.family == AF_INET)
+			iafamily = AF_INET6;
+
+		inner_mode_iaf = xfrm_get_mode(x->props.mode, iafamily);
+		if (inner_mode_iaf) {
+			if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL)
+				x->inner_mode_iaf = *inner_mode_iaf;
+		}
+	}
+
+	x->type = xfrm_get_type(x->id.proto, family);
+	if (x->type == NULL) {
+		NL_SET_ERR_MSG(extack, "Requested type not found");
+		goto error;
+	}
+
+	x->type_offload = xfrm_get_type_offload(x->id.proto, family, offload);
+
+	err = x->type->init_state(x, extack);
+	if (err)
+		goto error;
+
+	outer_mode = xfrm_get_mode(x->props.mode, family);
+	if (!outer_mode) {
+		NL_SET_ERR_MSG(extack, "Requested mode not found");
+		err = -EPROTONOSUPPORT;
+		goto error;
+	}
+
+	x->outer_mode = *outer_mode;
+	if (init_replay) {
+		err = xfrm_init_replay(x, extack);
+		if (err)
+			goto error;
+	}
+
+error:
+	return err;
+}
+
+EXPORT_SYMBOL(__xfrm_init_state);
+
+int xfrm_init_state(struct xfrm_state *x)
+{
+	int err;
+
+	err = __xfrm_init_state(x, true, false, NULL);
+	if (!err)
+		x->km.state = XFRM_STATE_VALID;
+
+	return err;
+}
+
+EXPORT_SYMBOL(xfrm_init_state);
+
+int __net_init xfrm_state_init(struct net *net)
+{
+	unsigned int sz;
+
+	if (net_eq(net, &init_net))
+		xfrm_state_cache = KMEM_CACHE(xfrm_state,
+					      SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+
+	INIT_LIST_HEAD(&net->xfrm.state_all);
+
+	sz = sizeof(struct hlist_head) * 8;
+
+	net->xfrm.state_bydst = xfrm_hash_alloc(sz);
+	if (!net->xfrm.state_bydst)
+		goto out_bydst;
+	net->xfrm.state_bysrc = xfrm_hash_alloc(sz);
+	if (!net->xfrm.state_bysrc)
+		goto out_bysrc;
+	net->xfrm.state_byspi = xfrm_hash_alloc(sz);
+	if (!net->xfrm.state_byspi)
+		goto out_byspi;
+	net->xfrm.state_byseq = xfrm_hash_alloc(sz);
+	if (!net->xfrm.state_byseq)
+		goto out_byseq;
+	net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1);
+
+	net->xfrm.state_num = 0;
+	INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation,
+			       &net->xfrm.xfrm_state_lock);
+	return 0;
+
+out_byseq:
+	xfrm_hash_free(net->xfrm.state_byspi, sz);
+out_byspi:
+	xfrm_hash_free(net->xfrm.state_bysrc, sz);
+out_bysrc:
+	xfrm_hash_free(net->xfrm.state_bydst, sz);
+out_bydst:
+	return -ENOMEM;
+}
+
+void xfrm_state_fini(struct net *net)
+{
+	unsigned int sz;
+
+	flush_work(&net->xfrm.state_hash_work);
+	flush_work(&xfrm_state_gc_work);
+	xfrm_state_flush(net, 0, false, true);
+
+	WARN_ON(!list_empty(&net->xfrm.state_all));
+
+	sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head);
+	WARN_ON(!hlist_empty(net->xfrm.state_byseq));
+	xfrm_hash_free(net->xfrm.state_byseq, sz);
+	WARN_ON(!hlist_empty(net->xfrm.state_byspi));
+	xfrm_hash_free(net->xfrm.state_byspi, sz);
+	WARN_ON(!hlist_empty(net->xfrm.state_bysrc));
+	xfrm_hash_free(net->xfrm.state_bysrc, sz);
+	WARN_ON(!hlist_empty(net->xfrm.state_bydst));
+	xfrm_hash_free(net->xfrm.state_bydst, sz);
+}
+
+#ifdef CONFIG_AUDITSYSCALL
+static void xfrm_audit_helper_sainfo(struct xfrm_state *x,
+				     struct audit_buffer *audit_buf)
+{
+	struct xfrm_sec_ctx *ctx = x->security;
+	u32 spi = ntohl(x->id.spi);
+
+	if (ctx)
+		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
+				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
+
+	switch (x->props.family) {
+	case AF_INET:
+		audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
+				 &x->props.saddr.a4, &x->id.daddr.a4);
+		break;
+	case AF_INET6:
+		audit_log_format(audit_buf, " src=%pI6 dst=%pI6",
+				 x->props.saddr.a6, x->id.daddr.a6);
+		break;
+	}
+
+	audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi);
+}
+
+static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
+				      struct audit_buffer *audit_buf)
+{
+	const struct iphdr *iph4;
+	const struct ipv6hdr *iph6;
+
+	switch (family) {
+	case AF_INET:
+		iph4 = ip_hdr(skb);
+		audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
+				 &iph4->saddr, &iph4->daddr);
+		break;
+	case AF_INET6:
+		iph6 = ipv6_hdr(skb);
+		audit_log_format(audit_buf,
+				 " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x",
+				 &iph6->saddr, &iph6->daddr,
+				 iph6->flow_lbl[0] & 0x0f,
+				 iph6->flow_lbl[1],
+				 iph6->flow_lbl[2]);
+		break;
+	}
+}
+
+void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid)
+{
+	struct audit_buffer *audit_buf;
+
+	audit_buf = xfrm_audit_start("SAD-add");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
+	xfrm_audit_helper_sainfo(x, audit_buf);
+	audit_log_format(audit_buf, " res=%u", result);
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_state_add);
+
+void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid)
+{
+	struct audit_buffer *audit_buf;
+
+	audit_buf = xfrm_audit_start("SAD-delete");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
+	xfrm_audit_helper_sainfo(x, audit_buf);
+	audit_log_format(audit_buf, " res=%u", result);
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_state_delete);
+
+void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
+				      struct sk_buff *skb)
+{
+	struct audit_buffer *audit_buf;
+	u32 spi;
+
+	audit_buf = xfrm_audit_start("SA-replay-overflow");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf);
+	/* don't record the sequence number because it's inherent in this kind
+	 * of audit message */
+	spi = ntohl(x->id.spi);
+	audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi);
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_state_replay_overflow);
+
+void xfrm_audit_state_replay(struct xfrm_state *x,
+			     struct sk_buff *skb, __be32 net_seq)
+{
+	struct audit_buffer *audit_buf;
+	u32 spi;
+
+	audit_buf = xfrm_audit_start("SA-replayed-pkt");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf);
+	spi = ntohl(x->id.spi);
+	audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u",
+			 spi, spi, ntohl(net_seq));
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_state_replay);
+
+void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family)
+{
+	struct audit_buffer *audit_buf;
+
+	audit_buf = xfrm_audit_start("SA-notfound");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_pktinfo(skb, family, audit_buf);
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound_simple);
+
+void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family,
+			       __be32 net_spi, __be32 net_seq)
+{
+	struct audit_buffer *audit_buf;
+	u32 spi;
+
+	audit_buf = xfrm_audit_start("SA-notfound");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_pktinfo(skb, family, audit_buf);
+	spi = ntohl(net_spi);
+	audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u",
+			 spi, spi, ntohl(net_seq));
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound);
+
+void xfrm_audit_state_icvfail(struct xfrm_state *x,
+			      struct sk_buff *skb, u8 proto)
+{
+	struct audit_buffer *audit_buf;
+	__be32 net_spi;
+	__be32 net_seq;
+
+	audit_buf = xfrm_audit_start("SA-icv-failure");
+	if (audit_buf == NULL)
+		return;
+	xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf);
+	if (xfrm_parse_spi(skb, proto, &net_spi, &net_seq) == 0) {
+		u32 spi = ntohl(net_spi);
+		audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u",
+				 spi, spi, ntohl(net_seq));
+	}
+	audit_log_end(audit_buf);
+}
+EXPORT_SYMBOL_GPL(xfrm_audit_state_icvfail);
+#endif /* CONFIG_AUDITSYSCALL */
diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c
new file mode 100644
index 0000000000..7fdeafc838
--- /dev/null
+++ b/net/xfrm/xfrm_sysctl.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sysctl.h>
+#include <linux/slab.h>
+#include <net/net_namespace.h>
+#include <net/xfrm.h>
+
+static void __net_init __xfrm_sysctl_init(struct net *net)
+{
+	net->xfrm.sysctl_aevent_etime = XFRM_AE_ETIME;
+	net->xfrm.sysctl_aevent_rseqth = XFRM_AE_SEQT_SIZE;
+	net->xfrm.sysctl_larval_drop = 1;
+	net->xfrm.sysctl_acq_expires = 30;
+}
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table xfrm_table[] = {
+	{
+		.procname	= "xfrm_aevent_etime",
+		.maxlen		= sizeof(u32),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec
+	},
+	{
+		.procname	= "xfrm_aevent_rseqth",
+		.maxlen		= sizeof(u32),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec
+	},
+	{
+		.procname	= "xfrm_larval_drop",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "xfrm_acq_expires",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{}
+};
+
+int __net_init xfrm_sysctl_init(struct net *net)
+{
+	struct ctl_table *table;
+	size_t table_size = ARRAY_SIZE(xfrm_table);
+
+	__xfrm_sysctl_init(net);
+
+	table = kmemdup(xfrm_table, sizeof(xfrm_table), GFP_KERNEL);
+	if (!table)
+		goto out_kmemdup;
+	table[0].data = &net->xfrm.sysctl_aevent_etime;
+	table[1].data = &net->xfrm.sysctl_aevent_rseqth;
+	table[2].data = &net->xfrm.sysctl_larval_drop;
+	table[3].data = &net->xfrm.sysctl_acq_expires;
+
+	/* Don't export sysctls to unprivileged users */
+	if (net->user_ns != &init_user_ns) {
+		table[0].procname = NULL;
+		table_size = 0;
+	}
+
+	net->xfrm.sysctl_hdr = register_net_sysctl_sz(net, "net/core", table,
+						      table_size);
+	if (!net->xfrm.sysctl_hdr)
+		goto out_register;
+	return 0;
+
+out_register:
+	kfree(table);
+out_kmemdup:
+	return -ENOMEM;
+}
+
+void __net_exit xfrm_sysctl_fini(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->xfrm.sysctl_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->xfrm.sysctl_hdr);
+	kfree(table);
+}
+#else
+int __net_init xfrm_sysctl_init(struct net *net)
+{
+	__xfrm_sysctl_init(net);
+	return 0;
+}
+#endif
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
new file mode 100644
index 0000000000..ad01997c3a
--- /dev/null
+++ b/net/xfrm/xfrm_user.c
@@ -0,0 +1,3892 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* xfrm_user.c: User interface to configure xfrm engine.
+ *
+ * Copyright (C) 2002 David S. Miller (davem@redhat.com)
+ *
+ * Changes:
+ *	Mitsuru KANDA @USAGI
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * 		IPv6 support
+ *
+ */
+
+#include <linux/compat.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/string.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/pfkeyv2.h>
+#include <linux/ipsec.h>
+#include <linux/init.h>
+#include <linux/security.h>
+#include <net/sock.h>
+#include <net/xfrm.h>
+#include <net/netlink.h>
+#include <net/ah.h>
+#include <linux/uaccess.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/in6.h>
+#endif
+#include <asm/unaligned.h>
+
+static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *rt = attrs[type];
+	struct xfrm_algo *algp;
+
+	if (!rt)
+		return 0;
+
+	algp = nla_data(rt);
+	if (nla_len(rt) < (int)xfrm_alg_len(algp)) {
+		NL_SET_ERR_MSG(extack, "Invalid AUTH/CRYPT/COMP attribute length");
+		return -EINVAL;
+	}
+
+	switch (type) {
+	case XFRMA_ALG_AUTH:
+	case XFRMA_ALG_CRYPT:
+	case XFRMA_ALG_COMP:
+		break;
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid algorithm attribute type");
+		return -EINVAL;
+	}
+
+	algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
+	return 0;
+}
+
+static int verify_auth_trunc(struct nlattr **attrs,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *rt = attrs[XFRMA_ALG_AUTH_TRUNC];
+	struct xfrm_algo_auth *algp;
+
+	if (!rt)
+		return 0;
+
+	algp = nla_data(rt);
+	if (nla_len(rt) < (int)xfrm_alg_auth_len(algp)) {
+		NL_SET_ERR_MSG(extack, "Invalid AUTH_TRUNC attribute length");
+		return -EINVAL;
+	}
+
+	algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
+	return 0;
+}
+
+static int verify_aead(struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct nlattr *rt = attrs[XFRMA_ALG_AEAD];
+	struct xfrm_algo_aead *algp;
+
+	if (!rt)
+		return 0;
+
+	algp = nla_data(rt);
+	if (nla_len(rt) < (int)aead_len(algp)) {
+		NL_SET_ERR_MSG(extack, "Invalid AEAD attribute length");
+		return -EINVAL;
+	}
+
+	algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
+	return 0;
+}
+
+static void verify_one_addr(struct nlattr **attrs, enum xfrm_attr_type_t type,
+			   xfrm_address_t **addrp)
+{
+	struct nlattr *rt = attrs[type];
+
+	if (rt && addrp)
+		*addrp = nla_data(rt);
+}
+
+static inline int verify_sec_ctx_len(struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct nlattr *rt = attrs[XFRMA_SEC_CTX];
+	struct xfrm_user_sec_ctx *uctx;
+
+	if (!rt)
+		return 0;
+
+	uctx = nla_data(rt);
+	if (uctx->len > nla_len(rt) ||
+	    uctx->len != (sizeof(struct xfrm_user_sec_ctx) + uctx->ctx_len)) {
+		NL_SET_ERR_MSG(extack, "Invalid security context length");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static inline int verify_replay(struct xfrm_usersa_info *p,
+				struct nlattr **attrs,
+				struct netlink_ext_ack *extack)
+{
+	struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL];
+	struct xfrm_replay_state_esn *rs;
+
+	if (!rt) {
+		if (p->flags & XFRM_STATE_ESN) {
+			NL_SET_ERR_MSG(extack, "Missing required attribute for ESN");
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	rs = nla_data(rt);
+
+	if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) {
+		NL_SET_ERR_MSG(extack, "ESN bitmap length must be <= 128");
+		return -EINVAL;
+	}
+
+	if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) &&
+	    nla_len(rt) != sizeof(*rs)) {
+		NL_SET_ERR_MSG(extack, "ESN attribute is too short to fit the full bitmap length");
+		return -EINVAL;
+	}
+
+	/* As only ESP and AH support ESN feature. */
+	if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) {
+		NL_SET_ERR_MSG(extack, "ESN only supported for ESP and AH");
+		return -EINVAL;
+	}
+
+	if (p->replay_window != 0) {
+		NL_SET_ERR_MSG(extack, "ESN not compatible with legacy replay_window");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int verify_newsa_info(struct xfrm_usersa_info *p,
+			     struct nlattr **attrs,
+			     struct netlink_ext_ack *extack)
+{
+	int err;
+
+	err = -EINVAL;
+	switch (p->family) {
+	case AF_INET:
+		break;
+
+	case AF_INET6:
+#if IS_ENABLED(CONFIG_IPV6)
+		break;
+#else
+		err = -EAFNOSUPPORT;
+		NL_SET_ERR_MSG(extack, "IPv6 support disabled");
+		goto out;
+#endif
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid address family");
+		goto out;
+	}
+
+	switch (p->sel.family) {
+	case AF_UNSPEC:
+		break;
+
+	case AF_INET:
+		if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) {
+			NL_SET_ERR_MSG(extack, "Invalid prefix length in selector (must be <= 32 for IPv4)");
+			goto out;
+		}
+
+		break;
+
+	case AF_INET6:
+#if IS_ENABLED(CONFIG_IPV6)
+		if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) {
+			NL_SET_ERR_MSG(extack, "Invalid prefix length in selector (must be <= 128 for IPv6)");
+			goto out;
+		}
+
+		break;
+#else
+		NL_SET_ERR_MSG(extack, "IPv6 support disabled");
+		err = -EAFNOSUPPORT;
+		goto out;
+#endif
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid address family in selector");
+		goto out;
+	}
+
+	err = -EINVAL;
+	switch (p->id.proto) {
+	case IPPROTO_AH:
+		if (!attrs[XFRMA_ALG_AUTH]	&&
+		    !attrs[XFRMA_ALG_AUTH_TRUNC]) {
+			NL_SET_ERR_MSG(extack, "Missing required attribute for AH: AUTH_TRUNC or AUTH");
+			goto out;
+		}
+
+		if (attrs[XFRMA_ALG_AEAD]	||
+		    attrs[XFRMA_ALG_CRYPT]	||
+		    attrs[XFRMA_ALG_COMP]	||
+		    attrs[XFRMA_TFCPAD]) {
+			NL_SET_ERR_MSG(extack, "Invalid attributes for AH: AEAD, CRYPT, COMP, TFCPAD");
+			goto out;
+		}
+		break;
+
+	case IPPROTO_ESP:
+		if (attrs[XFRMA_ALG_COMP]) {
+			NL_SET_ERR_MSG(extack, "Invalid attribute for ESP: COMP");
+			goto out;
+		}
+
+		if (!attrs[XFRMA_ALG_AUTH] &&
+		    !attrs[XFRMA_ALG_AUTH_TRUNC] &&
+		    !attrs[XFRMA_ALG_CRYPT] &&
+		    !attrs[XFRMA_ALG_AEAD]) {
+			NL_SET_ERR_MSG(extack, "Missing required attribute for ESP: at least one of AUTH, AUTH_TRUNC, CRYPT, AEAD");
+			goto out;
+		}
+
+		if ((attrs[XFRMA_ALG_AUTH] ||
+		     attrs[XFRMA_ALG_AUTH_TRUNC] ||
+		     attrs[XFRMA_ALG_CRYPT]) &&
+		    attrs[XFRMA_ALG_AEAD]) {
+			NL_SET_ERR_MSG(extack, "Invalid attribute combination for ESP: AEAD can't be used with AUTH, AUTH_TRUNC, CRYPT");
+			goto out;
+		}
+
+		if (attrs[XFRMA_TFCPAD] &&
+		    p->mode != XFRM_MODE_TUNNEL) {
+			NL_SET_ERR_MSG(extack, "TFC padding can only be used in tunnel mode");
+			goto out;
+		}
+		break;
+
+	case IPPROTO_COMP:
+		if (!attrs[XFRMA_ALG_COMP]) {
+			NL_SET_ERR_MSG(extack, "Missing required attribute for COMP: COMP");
+			goto out;
+		}
+
+		if (attrs[XFRMA_ALG_AEAD]	||
+		    attrs[XFRMA_ALG_AUTH]	||
+		    attrs[XFRMA_ALG_AUTH_TRUNC]	||
+		    attrs[XFRMA_ALG_CRYPT]	||
+		    attrs[XFRMA_TFCPAD]) {
+			NL_SET_ERR_MSG(extack, "Invalid attributes for COMP: AEAD, AUTH, AUTH_TRUNC, CRYPT, TFCPAD");
+			goto out;
+		}
+
+		if (ntohl(p->id.spi) >= 0x10000) {
+			NL_SET_ERR_MSG(extack, "SPI is too large for COMP (must be < 0x10000)");
+			goto out;
+		}
+		break;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	case IPPROTO_DSTOPTS:
+	case IPPROTO_ROUTING:
+		if (attrs[XFRMA_ALG_COMP]	||
+		    attrs[XFRMA_ALG_AUTH]	||
+		    attrs[XFRMA_ALG_AUTH_TRUNC]	||
+		    attrs[XFRMA_ALG_AEAD]	||
+		    attrs[XFRMA_ALG_CRYPT]	||
+		    attrs[XFRMA_ENCAP]		||
+		    attrs[XFRMA_SEC_CTX]	||
+		    attrs[XFRMA_TFCPAD]) {
+			NL_SET_ERR_MSG(extack, "Invalid attributes for DSTOPTS/ROUTING");
+			goto out;
+		}
+
+		if (!attrs[XFRMA_COADDR]) {
+			NL_SET_ERR_MSG(extack, "Missing required COADDR attribute for DSTOPTS/ROUTING");
+			goto out;
+		}
+		break;
+#endif
+
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported protocol");
+		goto out;
+	}
+
+	if ((err = verify_aead(attrs, extack)))
+		goto out;
+	if ((err = verify_auth_trunc(attrs, extack)))
+		goto out;
+	if ((err = verify_one_alg(attrs, XFRMA_ALG_AUTH, extack)))
+		goto out;
+	if ((err = verify_one_alg(attrs, XFRMA_ALG_CRYPT, extack)))
+		goto out;
+	if ((err = verify_one_alg(attrs, XFRMA_ALG_COMP, extack)))
+		goto out;
+	if ((err = verify_sec_ctx_len(attrs, extack)))
+		goto out;
+	if ((err = verify_replay(p, attrs, extack)))
+		goto out;
+
+	err = -EINVAL;
+	switch (p->mode) {
+	case XFRM_MODE_TRANSPORT:
+	case XFRM_MODE_TUNNEL:
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+	case XFRM_MODE_BEET:
+		break;
+
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported mode");
+		goto out;
+	}
+
+	err = 0;
+
+	if (attrs[XFRMA_MTIMER_THRESH]) {
+		if (!attrs[XFRMA_ENCAP]) {
+			NL_SET_ERR_MSG(extack, "MTIMER_THRESH attribute can only be set on ENCAP states");
+			err = -EINVAL;
+			goto out;
+		}
+	}
+
+out:
+	return err;
+}
+
+static int attach_one_algo(struct xfrm_algo **algpp, u8 *props,
+			   struct xfrm_algo_desc *(*get_byname)(const char *, int),
+			   struct nlattr *rta, struct netlink_ext_ack *extack)
+{
+	struct xfrm_algo *p, *ualg;
+	struct xfrm_algo_desc *algo;
+
+	if (!rta)
+		return 0;
+
+	ualg = nla_data(rta);
+
+	algo = get_byname(ualg->alg_name, 1);
+	if (!algo) {
+		NL_SET_ERR_MSG(extack, "Requested COMP algorithm not found");
+		return -ENOSYS;
+	}
+	*props = algo->desc.sadb_alg_id;
+
+	p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	strcpy(p->alg_name, algo->name);
+	*algpp = p;
+	return 0;
+}
+
+static int attach_crypt(struct xfrm_state *x, struct nlattr *rta,
+			struct netlink_ext_ack *extack)
+{
+	struct xfrm_algo *p, *ualg;
+	struct xfrm_algo_desc *algo;
+
+	if (!rta)
+		return 0;
+
+	ualg = nla_data(rta);
+
+	algo = xfrm_ealg_get_byname(ualg->alg_name, 1);
+	if (!algo) {
+		NL_SET_ERR_MSG(extack, "Requested CRYPT algorithm not found");
+		return -ENOSYS;
+	}
+	x->props.ealgo = algo->desc.sadb_alg_id;
+
+	p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	strcpy(p->alg_name, algo->name);
+	x->ealg = p;
+	x->geniv = algo->uinfo.encr.geniv;
+	return 0;
+}
+
+static int attach_auth(struct xfrm_algo_auth **algpp, u8 *props,
+		       struct nlattr *rta, struct netlink_ext_ack *extack)
+{
+	struct xfrm_algo *ualg;
+	struct xfrm_algo_auth *p;
+	struct xfrm_algo_desc *algo;
+
+	if (!rta)
+		return 0;
+
+	ualg = nla_data(rta);
+
+	algo = xfrm_aalg_get_byname(ualg->alg_name, 1);
+	if (!algo) {
+		NL_SET_ERR_MSG(extack, "Requested AUTH algorithm not found");
+		return -ENOSYS;
+	}
+	*props = algo->desc.sadb_alg_id;
+
+	p = kmalloc(sizeof(*p) + (ualg->alg_key_len + 7) / 8, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	strcpy(p->alg_name, algo->name);
+	p->alg_key_len = ualg->alg_key_len;
+	p->alg_trunc_len = algo->uinfo.auth.icv_truncbits;
+	memcpy(p->alg_key, ualg->alg_key, (ualg->alg_key_len + 7) / 8);
+
+	*algpp = p;
+	return 0;
+}
+
+static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props,
+			     struct nlattr *rta, struct netlink_ext_ack *extack)
+{
+	struct xfrm_algo_auth *p, *ualg;
+	struct xfrm_algo_desc *algo;
+
+	if (!rta)
+		return 0;
+
+	ualg = nla_data(rta);
+
+	algo = xfrm_aalg_get_byname(ualg->alg_name, 1);
+	if (!algo) {
+		NL_SET_ERR_MSG(extack, "Requested AUTH_TRUNC algorithm not found");
+		return -ENOSYS;
+	}
+	if (ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits) {
+		NL_SET_ERR_MSG(extack, "Invalid length requested for truncated ICV");
+		return -EINVAL;
+	}
+	*props = algo->desc.sadb_alg_id;
+
+	p = kmemdup(ualg, xfrm_alg_auth_len(ualg), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	strcpy(p->alg_name, algo->name);
+	if (!p->alg_trunc_len)
+		p->alg_trunc_len = algo->uinfo.auth.icv_truncbits;
+
+	*algpp = p;
+	return 0;
+}
+
+static int attach_aead(struct xfrm_state *x, struct nlattr *rta,
+		       struct netlink_ext_ack *extack)
+{
+	struct xfrm_algo_aead *p, *ualg;
+	struct xfrm_algo_desc *algo;
+
+	if (!rta)
+		return 0;
+
+	ualg = nla_data(rta);
+
+	algo = xfrm_aead_get_byname(ualg->alg_name, ualg->alg_icv_len, 1);
+	if (!algo) {
+		NL_SET_ERR_MSG(extack, "Requested AEAD algorithm not found");
+		return -ENOSYS;
+	}
+	x->props.ealgo = algo->desc.sadb_alg_id;
+
+	p = kmemdup(ualg, aead_len(ualg), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	strcpy(p->alg_name, algo->name);
+	x->aead = p;
+	x->geniv = algo->uinfo.aead.geniv;
+	return 0;
+}
+
+static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_esn,
+					 struct nlattr *rp,
+					 struct netlink_ext_ack *extack)
+{
+	struct xfrm_replay_state_esn *up;
+	unsigned int ulen;
+
+	if (!replay_esn || !rp)
+		return 0;
+
+	up = nla_data(rp);
+	ulen = xfrm_replay_state_esn_len(up);
+
+	/* Check the overall length and the internal bitmap length to avoid
+	 * potential overflow. */
+	if (nla_len(rp) < (int)ulen) {
+		NL_SET_ERR_MSG(extack, "ESN attribute is too short");
+		return -EINVAL;
+	}
+
+	if (xfrm_replay_state_esn_len(replay_esn) != ulen) {
+		NL_SET_ERR_MSG(extack, "New ESN size doesn't match the existing SA's ESN size");
+		return -EINVAL;
+	}
+
+	if (replay_esn->bmp_len != up->bmp_len) {
+		NL_SET_ERR_MSG(extack, "New ESN bitmap size doesn't match the existing SA's ESN bitmap");
+		return -EINVAL;
+	}
+
+	if (up->replay_window > up->bmp_len * sizeof(__u32) * 8) {
+		NL_SET_ERR_MSG(extack, "ESN replay window is longer than the bitmap");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn,
+				       struct xfrm_replay_state_esn **preplay_esn,
+				       struct nlattr *rta)
+{
+	struct xfrm_replay_state_esn *p, *pp, *up;
+	unsigned int klen, ulen;
+
+	if (!rta)
+		return 0;
+
+	up = nla_data(rta);
+	klen = xfrm_replay_state_esn_len(up);
+	ulen = nla_len(rta) >= (int)klen ? klen : sizeof(*up);
+
+	p = kzalloc(klen, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pp = kzalloc(klen, GFP_KERNEL);
+	if (!pp) {
+		kfree(p);
+		return -ENOMEM;
+	}
+
+	memcpy(p, up, ulen);
+	memcpy(pp, up, ulen);
+
+	*replay_esn = p;
+	*preplay_esn = pp;
+
+	return 0;
+}
+
+static inline unsigned int xfrm_user_sec_ctx_size(struct xfrm_sec_ctx *xfrm_ctx)
+{
+	unsigned int len = 0;
+
+	if (xfrm_ctx) {
+		len += sizeof(struct xfrm_user_sec_ctx);
+		len += xfrm_ctx->ctx_len;
+	}
+	return len;
+}
+
+static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
+{
+	memcpy(&x->id, &p->id, sizeof(x->id));
+	memcpy(&x->sel, &p->sel, sizeof(x->sel));
+	memcpy(&x->lft, &p->lft, sizeof(x->lft));
+	x->props.mode = p->mode;
+	x->props.replay_window = min_t(unsigned int, p->replay_window,
+					sizeof(x->replay.bitmap) * 8);
+	x->props.reqid = p->reqid;
+	x->props.family = p->family;
+	memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr));
+	x->props.flags = p->flags;
+
+	if (!x->sel.family && !(p->flags & XFRM_STATE_AF_UNSPEC))
+		x->sel.family = p->family;
+}
+
+/*
+ * someday when pfkey also has support, we could have the code
+ * somehow made shareable and move it to xfrm_state.c - JHS
+ *
+*/
+static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs,
+				  int update_esn)
+{
+	struct nlattr *rp = attrs[XFRMA_REPLAY_VAL];
+	struct nlattr *re = update_esn ? attrs[XFRMA_REPLAY_ESN_VAL] : NULL;
+	struct nlattr *lt = attrs[XFRMA_LTIME_VAL];
+	struct nlattr *et = attrs[XFRMA_ETIMER_THRESH];
+	struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH];
+	struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH];
+
+	if (re && x->replay_esn && x->preplay_esn) {
+		struct xfrm_replay_state_esn *replay_esn;
+		replay_esn = nla_data(re);
+		memcpy(x->replay_esn, replay_esn,
+		       xfrm_replay_state_esn_len(replay_esn));
+		memcpy(x->preplay_esn, replay_esn,
+		       xfrm_replay_state_esn_len(replay_esn));
+	}
+
+	if (rp) {
+		struct xfrm_replay_state *replay;
+		replay = nla_data(rp);
+		memcpy(&x->replay, replay, sizeof(*replay));
+		memcpy(&x->preplay, replay, sizeof(*replay));
+	}
+
+	if (lt) {
+		struct xfrm_lifetime_cur *ltime;
+		ltime = nla_data(lt);
+		x->curlft.bytes = ltime->bytes;
+		x->curlft.packets = ltime->packets;
+		x->curlft.add_time = ltime->add_time;
+		x->curlft.use_time = ltime->use_time;
+	}
+
+	if (et)
+		x->replay_maxage = nla_get_u32(et);
+
+	if (rt)
+		x->replay_maxdiff = nla_get_u32(rt);
+
+	if (mt)
+		x->mapping_maxage = nla_get_u32(mt);
+}
+
+static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m)
+{
+	if (attrs[XFRMA_SET_MARK]) {
+		m->v = nla_get_u32(attrs[XFRMA_SET_MARK]);
+		if (attrs[XFRMA_SET_MARK_MASK])
+			m->m = nla_get_u32(attrs[XFRMA_SET_MARK_MASK]);
+		else
+			m->m = 0xffffffff;
+	} else {
+		m->v = m->m = 0;
+	}
+}
+
+static struct xfrm_state *xfrm_state_construct(struct net *net,
+					       struct xfrm_usersa_info *p,
+					       struct nlattr **attrs,
+					       int *errp,
+					       struct netlink_ext_ack *extack)
+{
+	struct xfrm_state *x = xfrm_state_alloc(net);
+	int err = -ENOMEM;
+
+	if (!x)
+		goto error_no_put;
+
+	copy_from_user_state(x, p);
+
+	if (attrs[XFRMA_ENCAP]) {
+		x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]),
+				   sizeof(*x->encap), GFP_KERNEL);
+		if (x->encap == NULL)
+			goto error;
+	}
+
+	if (attrs[XFRMA_COADDR]) {
+		x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]),
+				    sizeof(*x->coaddr), GFP_KERNEL);
+		if (x->coaddr == NULL)
+			goto error;
+	}
+
+	if (attrs[XFRMA_SA_EXTRA_FLAGS])
+		x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]);
+
+	if ((err = attach_aead(x, attrs[XFRMA_ALG_AEAD], extack)))
+		goto error;
+	if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo,
+				     attrs[XFRMA_ALG_AUTH_TRUNC], extack)))
+		goto error;
+	if (!x->props.aalgo) {
+		if ((err = attach_auth(&x->aalg, &x->props.aalgo,
+				       attrs[XFRMA_ALG_AUTH], extack)))
+			goto error;
+	}
+	if ((err = attach_crypt(x, attrs[XFRMA_ALG_CRYPT], extack)))
+		goto error;
+	if ((err = attach_one_algo(&x->calg, &x->props.calgo,
+				   xfrm_calg_get_byname,
+				   attrs[XFRMA_ALG_COMP], extack)))
+		goto error;
+
+	if (attrs[XFRMA_TFCPAD])
+		x->tfcpad = nla_get_u32(attrs[XFRMA_TFCPAD]);
+
+	xfrm_mark_get(attrs, &x->mark);
+
+	xfrm_smark_init(attrs, &x->props.smark);
+
+	if (attrs[XFRMA_IF_ID])
+		x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
+	err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV], extack);
+	if (err)
+		goto error;
+
+	if (attrs[XFRMA_SEC_CTX]) {
+		err = security_xfrm_state_alloc(x,
+						nla_data(attrs[XFRMA_SEC_CTX]));
+		if (err)
+			goto error;
+	}
+
+	if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn,
+					       attrs[XFRMA_REPLAY_ESN_VAL])))
+		goto error;
+
+	x->km.seq = p->seq;
+	x->replay_maxdiff = net->xfrm.sysctl_aevent_rseqth;
+	/* sysctl_xfrm_aevent_etime is in 100ms units */
+	x->replay_maxage = (net->xfrm.sysctl_aevent_etime*HZ)/XFRM_AE_ETH_M;
+
+	if ((err = xfrm_init_replay(x, extack)))
+		goto error;
+
+	/* override default values from above */
+	xfrm_update_ae_params(x, attrs, 0);
+
+	/* configure the hardware if offload is requested */
+	if (attrs[XFRMA_OFFLOAD_DEV]) {
+		err = xfrm_dev_state_add(net, x,
+					 nla_data(attrs[XFRMA_OFFLOAD_DEV]),
+					 extack);
+		if (err)
+			goto error;
+	}
+
+	return x;
+
+error:
+	x->km.state = XFRM_STATE_DEAD;
+	xfrm_state_put(x);
+error_no_put:
+	*errp = err;
+	return NULL;
+}
+
+static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
+		       struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_usersa_info *p = nlmsg_data(nlh);
+	struct xfrm_state *x;
+	int err;
+	struct km_event c;
+
+	err = verify_newsa_info(p, attrs, extack);
+	if (err)
+		return err;
+
+	x = xfrm_state_construct(net, p, attrs, &err, extack);
+	if (!x)
+		return err;
+
+	xfrm_state_hold(x);
+	if (nlh->nlmsg_type == XFRM_MSG_NEWSA)
+		err = xfrm_state_add(x);
+	else
+		err = xfrm_state_update(x);
+
+	xfrm_audit_state_add(x, err ? 0 : 1, true);
+
+	if (err < 0) {
+		x->km.state = XFRM_STATE_DEAD;
+		xfrm_dev_state_delete(x);
+		__xfrm_state_put(x);
+		goto out;
+	}
+
+	if (x->km.state == XFRM_STATE_VOID)
+		x->km.state = XFRM_STATE_VALID;
+
+	c.seq = nlh->nlmsg_seq;
+	c.portid = nlh->nlmsg_pid;
+	c.event = nlh->nlmsg_type;
+
+	km_state_notify(x, &c);
+out:
+	xfrm_state_put(x);
+	return err;
+}
+
+static struct xfrm_state *xfrm_user_state_lookup(struct net *net,
+						 struct xfrm_usersa_id *p,
+						 struct nlattr **attrs,
+						 int *errp)
+{
+	struct xfrm_state *x = NULL;
+	struct xfrm_mark m;
+	int err;
+	u32 mark = xfrm_mark_get(attrs, &m);
+
+	if (xfrm_id_proto_match(p->proto, IPSEC_PROTO_ANY)) {
+		err = -ESRCH;
+		x = xfrm_state_lookup(net, mark, &p->daddr, p->spi, p->proto, p->family);
+	} else {
+		xfrm_address_t *saddr = NULL;
+
+		verify_one_addr(attrs, XFRMA_SRCADDR, &saddr);
+		if (!saddr) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		err = -ESRCH;
+		x = xfrm_state_lookup_byaddr(net, mark,
+					     &p->daddr, saddr,
+					     p->proto, p->family);
+	}
+
+ out:
+	if (!x && errp)
+		*errp = err;
+	return x;
+}
+
+static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
+		       struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_state *x;
+	int err = -ESRCH;
+	struct km_event c;
+	struct xfrm_usersa_id *p = nlmsg_data(nlh);
+
+	x = xfrm_user_state_lookup(net, p, attrs, &err);
+	if (x == NULL)
+		return err;
+
+	if ((err = security_xfrm_state_delete(x)) != 0)
+		goto out;
+
+	if (xfrm_state_kern(x)) {
+		NL_SET_ERR_MSG(extack, "SA is in use by tunnels");
+		err = -EPERM;
+		goto out;
+	}
+
+	err = xfrm_state_delete(x);
+	if (err < 0)
+		goto out;
+
+	c.seq = nlh->nlmsg_seq;
+	c.portid = nlh->nlmsg_pid;
+	c.event = nlh->nlmsg_type;
+	km_state_notify(x, &c);
+
+out:
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
+	xfrm_state_put(x);
+	return err;
+}
+
+static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
+{
+	memset(p, 0, sizeof(*p));
+	memcpy(&p->id, &x->id, sizeof(p->id));
+	memcpy(&p->sel, &x->sel, sizeof(p->sel));
+	memcpy(&p->lft, &x->lft, sizeof(p->lft));
+	if (x->xso.dev)
+		xfrm_dev_state_update_curlft(x);
+	memcpy(&p->curlft, &x->curlft, sizeof(p->curlft));
+	put_unaligned(x->stats.replay_window, &p->stats.replay_window);
+	put_unaligned(x->stats.replay, &p->stats.replay);
+	put_unaligned(x->stats.integrity_failed, &p->stats.integrity_failed);
+	memcpy(&p->saddr, &x->props.saddr, sizeof(p->saddr));
+	p->mode = x->props.mode;
+	p->replay_window = x->props.replay_window;
+	p->reqid = x->props.reqid;
+	p->family = x->props.family;
+	p->flags = x->props.flags;
+	p->seq = x->km.seq;
+}
+
+struct xfrm_dump_info {
+	struct sk_buff *in_skb;
+	struct sk_buff *out_skb;
+	u32 nlmsg_seq;
+	u16 nlmsg_flags;
+};
+
+static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb)
+{
+	struct xfrm_user_sec_ctx *uctx;
+	struct nlattr *attr;
+	int ctx_size = sizeof(*uctx) + s->ctx_len;
+
+	attr = nla_reserve(skb, XFRMA_SEC_CTX, ctx_size);
+	if (attr == NULL)
+		return -EMSGSIZE;
+
+	uctx = nla_data(attr);
+	uctx->exttype = XFRMA_SEC_CTX;
+	uctx->len = ctx_size;
+	uctx->ctx_doi = s->ctx_doi;
+	uctx->ctx_alg = s->ctx_alg;
+	uctx->ctx_len = s->ctx_len;
+	memcpy(uctx + 1, s->ctx_str, s->ctx_len);
+
+	return 0;
+}
+
+static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb)
+{
+	struct xfrm_user_offload *xuo;
+	struct nlattr *attr;
+
+	attr = nla_reserve(skb, XFRMA_OFFLOAD_DEV, sizeof(*xuo));
+	if (attr == NULL)
+		return -EMSGSIZE;
+
+	xuo = nla_data(attr);
+	memset(xuo, 0, sizeof(*xuo));
+	xuo->ifindex = xso->dev->ifindex;
+	if (xso->dir == XFRM_DEV_OFFLOAD_IN)
+		xuo->flags = XFRM_OFFLOAD_INBOUND;
+	if (xso->type == XFRM_DEV_OFFLOAD_PACKET)
+		xuo->flags |= XFRM_OFFLOAD_PACKET;
+
+	return 0;
+}
+
+static bool xfrm_redact(void)
+{
+	return IS_ENABLED(CONFIG_SECURITY) &&
+		security_locked_down(LOCKDOWN_XFRM_SECRET);
+}
+
+static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
+{
+	struct xfrm_algo *algo;
+	struct xfrm_algo_auth *ap;
+	struct nlattr *nla;
+	bool redact_secret = xfrm_redact();
+
+	nla = nla_reserve(skb, XFRMA_ALG_AUTH,
+			  sizeof(*algo) + (auth->alg_key_len + 7) / 8);
+	if (!nla)
+		return -EMSGSIZE;
+	algo = nla_data(nla);
+	strncpy(algo->alg_name, auth->alg_name, sizeof(algo->alg_name));
+
+	if (redact_secret && auth->alg_key_len)
+		memset(algo->alg_key, 0, (auth->alg_key_len + 7) / 8);
+	else
+		memcpy(algo->alg_key, auth->alg_key,
+		       (auth->alg_key_len + 7) / 8);
+	algo->alg_key_len = auth->alg_key_len;
+
+	nla = nla_reserve(skb, XFRMA_ALG_AUTH_TRUNC, xfrm_alg_auth_len(auth));
+	if (!nla)
+		return -EMSGSIZE;
+	ap = nla_data(nla);
+	memcpy(ap, auth, sizeof(struct xfrm_algo_auth));
+	if (redact_secret && auth->alg_key_len)
+		memset(ap->alg_key, 0, (auth->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, auth->alg_key,
+		       (auth->alg_key_len + 7) / 8);
+	return 0;
+}
+
+static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb)
+{
+	struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_AEAD, aead_len(aead));
+	struct xfrm_algo_aead *ap;
+	bool redact_secret = xfrm_redact();
+
+	if (!nla)
+		return -EMSGSIZE;
+
+	ap = nla_data(nla);
+	strscpy_pad(ap->alg_name, aead->alg_name, sizeof(ap->alg_name));
+	ap->alg_key_len = aead->alg_key_len;
+	ap->alg_icv_len = aead->alg_icv_len;
+
+	if (redact_secret && aead->alg_key_len)
+		memset(ap->alg_key, 0, (aead->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, aead->alg_key,
+		       (aead->alg_key_len + 7) / 8);
+	return 0;
+}
+
+static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb)
+{
+	struct xfrm_algo *ap;
+	bool redact_secret = xfrm_redact();
+	struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_CRYPT,
+					 xfrm_alg_len(ealg));
+	if (!nla)
+		return -EMSGSIZE;
+
+	ap = nla_data(nla);
+	strscpy_pad(ap->alg_name, ealg->alg_name, sizeof(ap->alg_name));
+	ap->alg_key_len = ealg->alg_key_len;
+
+	if (redact_secret && ealg->alg_key_len)
+		memset(ap->alg_key, 0, (ealg->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, ealg->alg_key,
+		       (ealg->alg_key_len + 7) / 8);
+
+	return 0;
+}
+
+static int copy_to_user_calg(struct xfrm_algo *calg, struct sk_buff *skb)
+{
+	struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_COMP, sizeof(*calg));
+	struct xfrm_algo *ap;
+
+	if (!nla)
+		return -EMSGSIZE;
+
+	ap = nla_data(nla);
+	strscpy_pad(ap->alg_name, calg->alg_name, sizeof(ap->alg_name));
+	ap->alg_key_len = 0;
+
+	return 0;
+}
+
+static int copy_to_user_encap(struct xfrm_encap_tmpl *ep, struct sk_buff *skb)
+{
+	struct nlattr *nla = nla_reserve(skb, XFRMA_ENCAP, sizeof(*ep));
+	struct xfrm_encap_tmpl *uep;
+
+	if (!nla)
+		return -EMSGSIZE;
+
+	uep = nla_data(nla);
+	memset(uep, 0, sizeof(*uep));
+
+	uep->encap_type = ep->encap_type;
+	uep->encap_sport = ep->encap_sport;
+	uep->encap_dport = ep->encap_dport;
+	uep->encap_oa = ep->encap_oa;
+
+	return 0;
+}
+
+static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m)
+{
+	int ret = 0;
+
+	if (m->v | m->m) {
+		ret = nla_put_u32(skb, XFRMA_SET_MARK, m->v);
+		if (!ret)
+			ret = nla_put_u32(skb, XFRMA_SET_MARK_MASK, m->m);
+	}
+	return ret;
+}
+
+/* Don't change this without updating xfrm_sa_len! */
+static int copy_to_user_state_extra(struct xfrm_state *x,
+				    struct xfrm_usersa_info *p,
+				    struct sk_buff *skb)
+{
+	int ret = 0;
+
+	copy_to_user_state(x, p);
+
+	if (x->props.extra_flags) {
+		ret = nla_put_u32(skb, XFRMA_SA_EXTRA_FLAGS,
+				  x->props.extra_flags);
+		if (ret)
+			goto out;
+	}
+
+	if (x->coaddr) {
+		ret = nla_put(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr);
+		if (ret)
+			goto out;
+	}
+	if (x->lastused) {
+		ret = nla_put_u64_64bit(skb, XFRMA_LASTUSED, x->lastused,
+					XFRMA_PAD);
+		if (ret)
+			goto out;
+	}
+	if (x->aead) {
+		ret = copy_to_user_aead(x->aead, skb);
+		if (ret)
+			goto out;
+	}
+	if (x->aalg) {
+		ret = copy_to_user_auth(x->aalg, skb);
+		if (ret)
+			goto out;
+	}
+	if (x->ealg) {
+		ret = copy_to_user_ealg(x->ealg, skb);
+		if (ret)
+			goto out;
+	}
+	if (x->calg) {
+		ret = copy_to_user_calg(x->calg, skb);
+		if (ret)
+			goto out;
+	}
+	if (x->encap) {
+		ret = copy_to_user_encap(x->encap, skb);
+		if (ret)
+			goto out;
+	}
+	if (x->tfcpad) {
+		ret = nla_put_u32(skb, XFRMA_TFCPAD, x->tfcpad);
+		if (ret)
+			goto out;
+	}
+	ret = xfrm_mark_put(skb, &x->mark);
+	if (ret)
+		goto out;
+
+	ret = xfrm_smark_put(skb, &x->props.smark);
+	if (ret)
+		goto out;
+
+	if (x->replay_esn)
+		ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL,
+			      xfrm_replay_state_esn_len(x->replay_esn),
+			      x->replay_esn);
+	else
+		ret = nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay),
+			      &x->replay);
+	if (ret)
+		goto out;
+	if(x->xso.dev)
+		ret = copy_user_offload(&x->xso, skb);
+	if (ret)
+		goto out;
+	if (x->if_id) {
+		ret = nla_put_u32(skb, XFRMA_IF_ID, x->if_id);
+		if (ret)
+			goto out;
+	}
+	if (x->security) {
+		ret = copy_sec_ctx(x->security, skb);
+		if (ret)
+			goto out;
+	}
+	if (x->mapping_maxage)
+		ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage);
+out:
+	return ret;
+}
+
+static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
+{
+	struct xfrm_dump_info *sp = ptr;
+	struct sk_buff *in_skb = sp->in_skb;
+	struct sk_buff *skb = sp->out_skb;
+	struct xfrm_translator *xtr;
+	struct xfrm_usersa_info *p;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, sp->nlmsg_seq,
+			XFRM_MSG_NEWSA, sizeof(*p), sp->nlmsg_flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	p = nlmsg_data(nlh);
+
+	err = copy_to_user_state_extra(x, p, skb);
+	if (err) {
+		nlmsg_cancel(skb, nlh);
+		return err;
+	}
+	nlmsg_end(skb, nlh);
+
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlh);
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			nlmsg_cancel(skb, nlh);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int xfrm_dump_sa_done(struct netlink_callback *cb)
+{
+	struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
+	struct sock *sk = cb->skb->sk;
+	struct net *net = sock_net(sk);
+
+	if (cb->args[0])
+		xfrm_state_walk_done(walk, net);
+	return 0;
+}
+
+static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
+	struct xfrm_dump_info info;
+
+	BUILD_BUG_ON(sizeof(struct xfrm_state_walk) >
+		     sizeof(cb->args) - sizeof(cb->args[0]));
+
+	info.in_skb = cb->skb;
+	info.out_skb = skb;
+	info.nlmsg_seq = cb->nlh->nlmsg_seq;
+	info.nlmsg_flags = NLM_F_MULTI;
+
+	if (!cb->args[0]) {
+		struct nlattr *attrs[XFRMA_MAX+1];
+		struct xfrm_address_filter *filter = NULL;
+		u8 proto = 0;
+		int err;
+
+		err = nlmsg_parse_deprecated(cb->nlh, 0, attrs, XFRMA_MAX,
+					     xfrma_policy, cb->extack);
+		if (err < 0)
+			return err;
+
+		if (attrs[XFRMA_ADDRESS_FILTER]) {
+			filter = kmemdup(nla_data(attrs[XFRMA_ADDRESS_FILTER]),
+					 sizeof(*filter), GFP_KERNEL);
+			if (filter == NULL)
+				return -ENOMEM;
+
+			/* see addr_match(), (prefix length >> 5) << 2
+			 * will be used to compare xfrm_address_t
+			 */
+			if (filter->splen > (sizeof(xfrm_address_t) << 3) ||
+			    filter->dplen > (sizeof(xfrm_address_t) << 3)) {
+				kfree(filter);
+				return -EINVAL;
+			}
+		}
+
+		if (attrs[XFRMA_PROTO])
+			proto = nla_get_u8(attrs[XFRMA_PROTO]);
+
+		xfrm_state_walk_init(walk, proto, filter);
+		cb->args[0] = 1;
+	}
+
+	(void) xfrm_state_walk(net, walk, dump_one_state, &info);
+
+	return skb->len;
+}
+
+static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb,
+					  struct xfrm_state *x, u32 seq)
+{
+	struct xfrm_dump_info info;
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	info.in_skb = in_skb;
+	info.out_skb = skb;
+	info.nlmsg_seq = seq;
+	info.nlmsg_flags = 0;
+
+	err = dump_one_state(x, 0, &info);
+	if (err) {
+		kfree_skb(skb);
+		return ERR_PTR(err);
+	}
+
+	return skb;
+}
+
+/* A wrapper for nlmsg_multicast() checking that nlsk is still available.
+ * Must be called with RCU read lock.
+ */
+static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
+				       u32 pid, unsigned int group)
+{
+	struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
+	struct xfrm_translator *xtr;
+
+	if (!nlsk) {
+		kfree_skb(skb);
+		return -EPIPE;
+	}
+
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		int err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree_skb(skb);
+			return err;
+		}
+	}
+
+	return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
+}
+
+static inline unsigned int xfrm_spdinfo_msgsize(void)
+{
+	return NLMSG_ALIGN(4)
+	       + nla_total_size(sizeof(struct xfrmu_spdinfo))
+	       + nla_total_size(sizeof(struct xfrmu_spdhinfo))
+	       + nla_total_size(sizeof(struct xfrmu_spdhthresh))
+	       + nla_total_size(sizeof(struct xfrmu_spdhthresh));
+}
+
+static int build_spdinfo(struct sk_buff *skb, struct net *net,
+			 u32 portid, u32 seq, u32 flags)
+{
+	struct xfrmk_spdinfo si;
+	struct xfrmu_spdinfo spc;
+	struct xfrmu_spdhinfo sph;
+	struct xfrmu_spdhthresh spt4, spt6;
+	struct nlmsghdr *nlh;
+	int err;
+	u32 *f;
+	unsigned lseq;
+
+	nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0);
+	if (nlh == NULL) /* shouldn't really happen ... */
+		return -EMSGSIZE;
+
+	f = nlmsg_data(nlh);
+	*f = flags;
+	xfrm_spd_getinfo(net, &si);
+	spc.incnt = si.incnt;
+	spc.outcnt = si.outcnt;
+	spc.fwdcnt = si.fwdcnt;
+	spc.inscnt = si.inscnt;
+	spc.outscnt = si.outscnt;
+	spc.fwdscnt = si.fwdscnt;
+	sph.spdhcnt = si.spdhcnt;
+	sph.spdhmcnt = si.spdhmcnt;
+
+	do {
+		lseq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
+
+		spt4.lbits = net->xfrm.policy_hthresh.lbits4;
+		spt4.rbits = net->xfrm.policy_hthresh.rbits4;
+		spt6.lbits = net->xfrm.policy_hthresh.lbits6;
+		spt6.rbits = net->xfrm.policy_hthresh.rbits6;
+	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, lseq));
+
+	err = nla_put(skb, XFRMA_SPD_INFO, sizeof(spc), &spc);
+	if (!err)
+		err = nla_put(skb, XFRMA_SPD_HINFO, sizeof(sph), &sph);
+	if (!err)
+		err = nla_put(skb, XFRMA_SPD_IPV4_HTHRESH, sizeof(spt4), &spt4);
+	if (!err)
+		err = nla_put(skb, XFRMA_SPD_IPV6_HTHRESH, sizeof(spt6), &spt6);
+	if (err) {
+		nlmsg_cancel(skb, nlh);
+		return err;
+	}
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int xfrm_set_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct nlattr **attrs,
+			    struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrmu_spdhthresh *thresh4 = NULL;
+	struct xfrmu_spdhthresh *thresh6 = NULL;
+
+	/* selector prefixlen thresholds to hash policies */
+	if (attrs[XFRMA_SPD_IPV4_HTHRESH]) {
+		struct nlattr *rta = attrs[XFRMA_SPD_IPV4_HTHRESH];
+
+		if (nla_len(rta) < sizeof(*thresh4)) {
+			NL_SET_ERR_MSG(extack, "Invalid SPD_IPV4_HTHRESH attribute length");
+			return -EINVAL;
+		}
+		thresh4 = nla_data(rta);
+		if (thresh4->lbits > 32 || thresh4->rbits > 32) {
+			NL_SET_ERR_MSG(extack, "Invalid hash threshold (must be <= 32 for IPv4)");
+			return -EINVAL;
+		}
+	}
+	if (attrs[XFRMA_SPD_IPV6_HTHRESH]) {
+		struct nlattr *rta = attrs[XFRMA_SPD_IPV6_HTHRESH];
+
+		if (nla_len(rta) < sizeof(*thresh6)) {
+			NL_SET_ERR_MSG(extack, "Invalid SPD_IPV6_HTHRESH attribute length");
+			return -EINVAL;
+		}
+		thresh6 = nla_data(rta);
+		if (thresh6->lbits > 128 || thresh6->rbits > 128) {
+			NL_SET_ERR_MSG(extack, "Invalid hash threshold (must be <= 128 for IPv6)");
+			return -EINVAL;
+		}
+	}
+
+	if (thresh4 || thresh6) {
+		write_seqlock(&net->xfrm.policy_hthresh.lock);
+		if (thresh4) {
+			net->xfrm.policy_hthresh.lbits4 = thresh4->lbits;
+			net->xfrm.policy_hthresh.rbits4 = thresh4->rbits;
+		}
+		if (thresh6) {
+			net->xfrm.policy_hthresh.lbits6 = thresh6->lbits;
+			net->xfrm.policy_hthresh.rbits6 = thresh6->rbits;
+		}
+		write_sequnlock(&net->xfrm.policy_hthresh.lock);
+
+		xfrm_policy_hash_rebuild(net);
+	}
+
+	return 0;
+}
+
+static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct nlattr **attrs,
+			    struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct sk_buff *r_skb;
+	u32 *flags = nlmsg_data(nlh);
+	u32 sportid = NETLINK_CB(skb).portid;
+	u32 seq = nlh->nlmsg_seq;
+	int err;
+
+	r_skb = nlmsg_new(xfrm_spdinfo_msgsize(), GFP_ATOMIC);
+	if (r_skb == NULL)
+		return -ENOMEM;
+
+	err = build_spdinfo(r_skb, net, sportid, seq, *flags);
+	BUG_ON(err < 0);
+
+	return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid);
+}
+
+static inline unsigned int xfrm_sadinfo_msgsize(void)
+{
+	return NLMSG_ALIGN(4)
+	       + nla_total_size(sizeof(struct xfrmu_sadhinfo))
+	       + nla_total_size(4); /* XFRMA_SAD_CNT */
+}
+
+static int build_sadinfo(struct sk_buff *skb, struct net *net,
+			 u32 portid, u32 seq, u32 flags)
+{
+	struct xfrmk_sadinfo si;
+	struct xfrmu_sadhinfo sh;
+	struct nlmsghdr *nlh;
+	int err;
+	u32 *f;
+
+	nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSADINFO, sizeof(u32), 0);
+	if (nlh == NULL) /* shouldn't really happen ... */
+		return -EMSGSIZE;
+
+	f = nlmsg_data(nlh);
+	*f = flags;
+	xfrm_sad_getinfo(net, &si);
+
+	sh.sadhmcnt = si.sadhmcnt;
+	sh.sadhcnt = si.sadhcnt;
+
+	err = nla_put_u32(skb, XFRMA_SAD_CNT, si.sadcnt);
+	if (!err)
+		err = nla_put(skb, XFRMA_SAD_HINFO, sizeof(sh), &sh);
+	if (err) {
+		nlmsg_cancel(skb, nlh);
+		return err;
+	}
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct nlattr **attrs,
+			    struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct sk_buff *r_skb;
+	u32 *flags = nlmsg_data(nlh);
+	u32 sportid = NETLINK_CB(skb).portid;
+	u32 seq = nlh->nlmsg_seq;
+	int err;
+
+	r_skb = nlmsg_new(xfrm_sadinfo_msgsize(), GFP_ATOMIC);
+	if (r_skb == NULL)
+		return -ENOMEM;
+
+	err = build_sadinfo(r_skb, net, sportid, seq, *flags);
+	BUG_ON(err < 0);
+
+	return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid);
+}
+
+static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
+		       struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_usersa_id *p = nlmsg_data(nlh);
+	struct xfrm_state *x;
+	struct sk_buff *resp_skb;
+	int err = -ESRCH;
+
+	x = xfrm_user_state_lookup(net, p, attrs, &err);
+	if (x == NULL)
+		goto out_noput;
+
+	resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq);
+	if (IS_ERR(resp_skb)) {
+		err = PTR_ERR(resp_skb);
+	} else {
+		err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
+	}
+	xfrm_state_put(x);
+out_noput:
+	return err;
+}
+
+static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
+			      struct nlattr **attrs,
+			      struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_state *x;
+	struct xfrm_userspi_info *p;
+	struct xfrm_translator *xtr;
+	struct sk_buff *resp_skb;
+	xfrm_address_t *daddr;
+	int family;
+	int err;
+	u32 mark;
+	struct xfrm_mark m;
+	u32 if_id = 0;
+
+	p = nlmsg_data(nlh);
+	err = verify_spi_info(p->info.id.proto, p->min, p->max, extack);
+	if (err)
+		goto out_noput;
+
+	family = p->info.family;
+	daddr = &p->info.id.daddr;
+
+	x = NULL;
+
+	mark = xfrm_mark_get(attrs, &m);
+
+	if (attrs[XFRMA_IF_ID])
+		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
+	if (p->info.seq) {
+		x = xfrm_find_acq_byseq(net, mark, p->info.seq);
+		if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) {
+			xfrm_state_put(x);
+			x = NULL;
+		}
+	}
+
+	if (!x)
+		x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid,
+				  if_id, p->info.id.proto, daddr,
+				  &p->info.saddr, 1,
+				  family);
+	err = -ENOENT;
+	if (!x) {
+		NL_SET_ERR_MSG(extack, "Target ACQUIRE not found");
+		goto out_noput;
+	}
+
+	err = xfrm_alloc_spi(x, p->min, p->max, extack);
+	if (err)
+		goto out;
+
+	resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq);
+	if (IS_ERR(resp_skb)) {
+		err = PTR_ERR(resp_skb);
+		goto out;
+	}
+
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree_skb(resp_skb);
+			goto out;
+		}
+	}
+
+	err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
+
+out:
+	xfrm_state_put(x);
+out_noput:
+	return err;
+}
+
+static int verify_policy_dir(u8 dir, struct netlink_ext_ack *extack)
+{
+	switch (dir) {
+	case XFRM_POLICY_IN:
+	case XFRM_POLICY_OUT:
+	case XFRM_POLICY_FWD:
+		break;
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid policy direction");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int verify_policy_type(u8 type, struct netlink_ext_ack *extack)
+{
+	switch (type) {
+	case XFRM_POLICY_TYPE_MAIN:
+#ifdef CONFIG_XFRM_SUB_POLICY
+	case XFRM_POLICY_TYPE_SUB:
+#endif
+		break;
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid policy type");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int verify_newpolicy_info(struct xfrm_userpolicy_info *p,
+				 struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	switch (p->share) {
+	case XFRM_SHARE_ANY:
+	case XFRM_SHARE_SESSION:
+	case XFRM_SHARE_USER:
+	case XFRM_SHARE_UNIQUE:
+		break;
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid policy share");
+		return -EINVAL;
+	}
+
+	switch (p->action) {
+	case XFRM_POLICY_ALLOW:
+	case XFRM_POLICY_BLOCK:
+		break;
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid policy action");
+		return -EINVAL;
+	}
+
+	switch (p->sel.family) {
+	case AF_INET:
+		if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) {
+			NL_SET_ERR_MSG(extack, "Invalid prefix length in selector (must be <= 32 for IPv4)");
+			return -EINVAL;
+		}
+
+		break;
+
+	case AF_INET6:
+#if IS_ENABLED(CONFIG_IPV6)
+		if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) {
+			NL_SET_ERR_MSG(extack, "Invalid prefix length in selector (must be <= 128 for IPv6)");
+			return -EINVAL;
+		}
+
+		break;
+#else
+		NL_SET_ERR_MSG(extack, "IPv6 support disabled");
+		return  -EAFNOSUPPORT;
+#endif
+
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid selector family");
+		return -EINVAL;
+	}
+
+	ret = verify_policy_dir(p->dir, extack);
+	if (ret)
+		return ret;
+	if (p->index && (xfrm_policy_id2dir(p->index) != p->dir)) {
+		NL_SET_ERR_MSG(extack, "Policy index doesn't match direction");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs)
+{
+	struct nlattr *rt = attrs[XFRMA_SEC_CTX];
+	struct xfrm_user_sec_ctx *uctx;
+
+	if (!rt)
+		return 0;
+
+	uctx = nla_data(rt);
+	return security_xfrm_policy_alloc(&pol->security, uctx, GFP_KERNEL);
+}
+
+static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
+			   int nr)
+{
+	int i;
+
+	xp->xfrm_nr = nr;
+	for (i = 0; i < nr; i++, ut++) {
+		struct xfrm_tmpl *t = &xp->xfrm_vec[i];
+
+		memcpy(&t->id, &ut->id, sizeof(struct xfrm_id));
+		memcpy(&t->saddr, &ut->saddr,
+		       sizeof(xfrm_address_t));
+		t->reqid = ut->reqid;
+		t->mode = ut->mode;
+		t->share = ut->share;
+		t->optional = ut->optional;
+		t->aalgos = ut->aalgos;
+		t->ealgos = ut->ealgos;
+		t->calgos = ut->calgos;
+		/* If all masks are ~0, then we allow all algorithms. */
+		t->allalgs = !~(t->aalgos & t->ealgos & t->calgos);
+		t->encap_family = ut->family;
+	}
+}
+
+static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family,
+			 int dir, struct netlink_ext_ack *extack)
+{
+	u16 prev_family;
+	int i;
+
+	if (nr > XFRM_MAX_DEPTH) {
+		NL_SET_ERR_MSG(extack, "Template count must be <= XFRM_MAX_DEPTH (" __stringify(XFRM_MAX_DEPTH) ")");
+		return -EINVAL;
+	}
+
+	prev_family = family;
+
+	for (i = 0; i < nr; i++) {
+		/* We never validated the ut->family value, so many
+		 * applications simply leave it at zero.  The check was
+		 * never made and ut->family was ignored because all
+		 * templates could be assumed to have the same family as
+		 * the policy itself.  Now that we will have ipv4-in-ipv6
+		 * and ipv6-in-ipv4 tunnels, this is no longer true.
+		 */
+		if (!ut[i].family)
+			ut[i].family = family;
+
+		switch (ut[i].mode) {
+		case XFRM_MODE_TUNNEL:
+		case XFRM_MODE_BEET:
+			if (ut[i].optional && dir == XFRM_POLICY_OUT) {
+				NL_SET_ERR_MSG(extack, "Mode in optional template not allowed in outbound policy");
+				return -EINVAL;
+			}
+			break;
+		default:
+			if (ut[i].family != prev_family) {
+				NL_SET_ERR_MSG(extack, "Mode in template doesn't support a family change");
+				return -EINVAL;
+			}
+			break;
+		}
+		if (ut[i].mode >= XFRM_MODE_MAX) {
+			NL_SET_ERR_MSG(extack, "Mode in template must be < XFRM_MODE_MAX (" __stringify(XFRM_MODE_MAX) ")");
+			return -EINVAL;
+		}
+
+		prev_family = ut[i].family;
+
+		switch (ut[i].family) {
+		case AF_INET:
+			break;
+#if IS_ENABLED(CONFIG_IPV6)
+		case AF_INET6:
+			break;
+#endif
+		default:
+			NL_SET_ERR_MSG(extack, "Invalid family in template");
+			return -EINVAL;
+		}
+
+		if (!xfrm_id_proto_valid(ut[i].id.proto)) {
+			NL_SET_ERR_MSG(extack, "Invalid XFRM protocol in template");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs,
+			       int dir, struct netlink_ext_ack *extack)
+{
+	struct nlattr *rt = attrs[XFRMA_TMPL];
+
+	if (!rt) {
+		pol->xfrm_nr = 0;
+	} else {
+		struct xfrm_user_tmpl *utmpl = nla_data(rt);
+		int nr = nla_len(rt) / sizeof(*utmpl);
+		int err;
+
+		err = validate_tmpl(nr, utmpl, pol->family, dir, extack);
+		if (err)
+			return err;
+
+		copy_templates(pol, utmpl, nr);
+	}
+	return 0;
+}
+
+static int copy_from_user_policy_type(u8 *tp, struct nlattr **attrs,
+				      struct netlink_ext_ack *extack)
+{
+	struct nlattr *rt = attrs[XFRMA_POLICY_TYPE];
+	struct xfrm_userpolicy_type *upt;
+	u8 type = XFRM_POLICY_TYPE_MAIN;
+	int err;
+
+	if (rt) {
+		upt = nla_data(rt);
+		type = upt->type;
+	}
+
+	err = verify_policy_type(type, extack);
+	if (err)
+		return err;
+
+	*tp = type;
+	return 0;
+}
+
+static void copy_from_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p)
+{
+	xp->priority = p->priority;
+	xp->index = p->index;
+	memcpy(&xp->selector, &p->sel, sizeof(xp->selector));
+	memcpy(&xp->lft, &p->lft, sizeof(xp->lft));
+	xp->action = p->action;
+	xp->flags = p->flags;
+	xp->family = p->sel.family;
+	/* XXX xp->share = p->share; */
+}
+
+static void copy_to_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p, int dir)
+{
+	memset(p, 0, sizeof(*p));
+	memcpy(&p->sel, &xp->selector, sizeof(p->sel));
+	memcpy(&p->lft, &xp->lft, sizeof(p->lft));
+	memcpy(&p->curlft, &xp->curlft, sizeof(p->curlft));
+	p->priority = xp->priority;
+	p->index = xp->index;
+	p->sel.family = xp->family;
+	p->dir = dir;
+	p->action = xp->action;
+	p->flags = xp->flags;
+	p->share = XFRM_SHARE_ANY; /* XXX xp->share */
+}
+
+static struct xfrm_policy *xfrm_policy_construct(struct net *net,
+						 struct xfrm_userpolicy_info *p,
+						 struct nlattr **attrs,
+						 int *errp,
+						 struct netlink_ext_ack *extack)
+{
+	struct xfrm_policy *xp = xfrm_policy_alloc(net, GFP_KERNEL);
+	int err;
+
+	if (!xp) {
+		*errp = -ENOMEM;
+		return NULL;
+	}
+
+	copy_from_user_policy(xp, p);
+
+	err = copy_from_user_policy_type(&xp->type, attrs, extack);
+	if (err)
+		goto error;
+
+	if (!(err = copy_from_user_tmpl(xp, attrs, p->dir, extack)))
+		err = copy_from_user_sec_ctx(xp, attrs);
+	if (err)
+		goto error;
+
+	xfrm_mark_get(attrs, &xp->mark);
+
+	if (attrs[XFRMA_IF_ID])
+		xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
+	/* configure the hardware if offload is requested */
+	if (attrs[XFRMA_OFFLOAD_DEV]) {
+		err = xfrm_dev_policy_add(net, xp,
+					  nla_data(attrs[XFRMA_OFFLOAD_DEV]),
+					  p->dir, extack);
+		if (err)
+			goto error;
+	}
+
+	return xp;
+ error:
+	*errp = err;
+	xp->walk.dead = 1;
+	xfrm_policy_destroy(xp);
+	return NULL;
+}
+
+static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
+			   struct nlattr **attrs,
+			   struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_userpolicy_info *p = nlmsg_data(nlh);
+	struct xfrm_policy *xp;
+	struct km_event c;
+	int err;
+	int excl;
+
+	err = verify_newpolicy_info(p, extack);
+	if (err)
+		return err;
+	err = verify_sec_ctx_len(attrs, extack);
+	if (err)
+		return err;
+
+	xp = xfrm_policy_construct(net, p, attrs, &err, extack);
+	if (!xp)
+		return err;
+
+	/* shouldn't excl be based on nlh flags??
+	 * Aha! this is anti-netlink really i.e  more pfkey derived
+	 * in netlink excl is a flag and you wouldn't need
+	 * a type XFRM_MSG_UPDPOLICY - JHS */
+	excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY;
+	err = xfrm_policy_insert(p->dir, xp, excl);
+	xfrm_audit_policy_add(xp, err ? 0 : 1, true);
+
+	if (err) {
+		xfrm_dev_policy_delete(xp);
+		xfrm_dev_policy_free(xp);
+		security_xfrm_policy_free(xp->security);
+		kfree(xp);
+		return err;
+	}
+
+	c.event = nlh->nlmsg_type;
+	c.seq = nlh->nlmsg_seq;
+	c.portid = nlh->nlmsg_pid;
+	km_policy_notify(xp, p->dir, &c);
+
+	xfrm_pol_put(xp);
+
+	return 0;
+}
+
+static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb)
+{
+	struct xfrm_user_tmpl vec[XFRM_MAX_DEPTH];
+	int i;
+
+	if (xp->xfrm_nr == 0)
+		return 0;
+
+	for (i = 0; i < xp->xfrm_nr; i++) {
+		struct xfrm_user_tmpl *up = &vec[i];
+		struct xfrm_tmpl *kp = &xp->xfrm_vec[i];
+
+		memset(up, 0, sizeof(*up));
+		memcpy(&up->id, &kp->id, sizeof(up->id));
+		up->family = kp->encap_family;
+		memcpy(&up->saddr, &kp->saddr, sizeof(up->saddr));
+		up->reqid = kp->reqid;
+		up->mode = kp->mode;
+		up->share = kp->share;
+		up->optional = kp->optional;
+		up->aalgos = kp->aalgos;
+		up->ealgos = kp->ealgos;
+		up->calgos = kp->calgos;
+	}
+
+	return nla_put(skb, XFRMA_TMPL,
+		       sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr, vec);
+}
+
+static inline int copy_to_user_state_sec_ctx(struct xfrm_state *x, struct sk_buff *skb)
+{
+	if (x->security) {
+		return copy_sec_ctx(x->security, skb);
+	}
+	return 0;
+}
+
+static inline int copy_to_user_sec_ctx(struct xfrm_policy *xp, struct sk_buff *skb)
+{
+	if (xp->security)
+		return copy_sec_ctx(xp->security, skb);
+	return 0;
+}
+static inline unsigned int userpolicy_type_attrsize(void)
+{
+#ifdef CONFIG_XFRM_SUB_POLICY
+	return nla_total_size(sizeof(struct xfrm_userpolicy_type));
+#else
+	return 0;
+#endif
+}
+
+#ifdef CONFIG_XFRM_SUB_POLICY
+static int copy_to_user_policy_type(u8 type, struct sk_buff *skb)
+{
+	struct xfrm_userpolicy_type upt;
+
+	/* Sadly there are two holes in struct xfrm_userpolicy_type */
+	memset(&upt, 0, sizeof(upt));
+	upt.type = type;
+
+	return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt);
+}
+
+#else
+static inline int copy_to_user_policy_type(u8 type, struct sk_buff *skb)
+{
+	return 0;
+}
+#endif
+
+static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr)
+{
+	struct xfrm_dump_info *sp = ptr;
+	struct xfrm_userpolicy_info *p;
+	struct sk_buff *in_skb = sp->in_skb;
+	struct sk_buff *skb = sp->out_skb;
+	struct xfrm_translator *xtr;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, sp->nlmsg_seq,
+			XFRM_MSG_NEWPOLICY, sizeof(*p), sp->nlmsg_flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	p = nlmsg_data(nlh);
+	copy_to_user_policy(xp, p, dir);
+	err = copy_to_user_tmpl(xp, skb);
+	if (!err)
+		err = copy_to_user_sec_ctx(xp, skb);
+	if (!err)
+		err = copy_to_user_policy_type(xp->type, skb);
+	if (!err)
+		err = xfrm_mark_put(skb, &xp->mark);
+	if (!err)
+		err = xfrm_if_id_put(skb, xp->if_id);
+	if (!err && xp->xdo.dev)
+		err = copy_user_offload(&xp->xdo, skb);
+	if (err) {
+		nlmsg_cancel(skb, nlh);
+		return err;
+	}
+	nlmsg_end(skb, nlh);
+
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlh);
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			nlmsg_cancel(skb, nlh);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int xfrm_dump_policy_done(struct netlink_callback *cb)
+{
+	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
+	struct net *net = sock_net(cb->skb->sk);
+
+	xfrm_policy_walk_done(walk, net);
+	return 0;
+}
+
+static int xfrm_dump_policy_start(struct netlink_callback *cb)
+{
+	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
+
+	BUILD_BUG_ON(sizeof(*walk) > sizeof(cb->args));
+
+	xfrm_policy_walk_init(walk, XFRM_POLICY_TYPE_ANY);
+	return 0;
+}
+
+static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
+	struct xfrm_dump_info info;
+
+	info.in_skb = cb->skb;
+	info.out_skb = skb;
+	info.nlmsg_seq = cb->nlh->nlmsg_seq;
+	info.nlmsg_flags = NLM_F_MULTI;
+
+	(void) xfrm_policy_walk(net, walk, dump_one_policy, &info);
+
+	return skb->len;
+}
+
+static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb,
+					  struct xfrm_policy *xp,
+					  int dir, u32 seq)
+{
+	struct xfrm_dump_info info;
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	info.in_skb = in_skb;
+	info.out_skb = skb;
+	info.nlmsg_seq = seq;
+	info.nlmsg_flags = 0;
+
+	err = dump_one_policy(xp, dir, 0, &info);
+	if (err) {
+		kfree_skb(skb);
+		return ERR_PTR(err);
+	}
+
+	return skb;
+}
+
+static int xfrm_notify_userpolicy(struct net *net)
+{
+	struct xfrm_userpolicy_default *up;
+	int len = NLMSG_ALIGN(sizeof(*up));
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_GETDEFAULT, sizeof(*up), 0);
+	if (nlh == NULL) {
+		kfree_skb(skb);
+		return -EMSGSIZE;
+	}
+
+	up = nlmsg_data(nlh);
+	up->in = net->xfrm.policy_default[XFRM_POLICY_IN];
+	up->fwd = net->xfrm.policy_default[XFRM_POLICY_FWD];
+	up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
+
+	nlmsg_end(skb, nlh);
+
+	rcu_read_lock();
+	err = xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
+	rcu_read_unlock();
+
+	return err;
+}
+
+static bool xfrm_userpolicy_is_valid(__u8 policy)
+{
+	return policy == XFRM_USERPOLICY_BLOCK ||
+	       policy == XFRM_USERPOLICY_ACCEPT;
+}
+
+static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_userpolicy_default *up = nlmsg_data(nlh);
+
+	if (xfrm_userpolicy_is_valid(up->in))
+		net->xfrm.policy_default[XFRM_POLICY_IN] = up->in;
+
+	if (xfrm_userpolicy_is_valid(up->fwd))
+		net->xfrm.policy_default[XFRM_POLICY_FWD] = up->fwd;
+
+	if (xfrm_userpolicy_is_valid(up->out))
+		net->xfrm.policy_default[XFRM_POLICY_OUT] = up->out;
+
+	rt_genid_bump_all(net);
+
+	xfrm_notify_userpolicy(net);
+	return 0;
+}
+
+static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct sk_buff *r_skb;
+	struct nlmsghdr *r_nlh;
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_userpolicy_default *r_up;
+	int len = NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_default));
+	u32 portid = NETLINK_CB(skb).portid;
+	u32 seq = nlh->nlmsg_seq;
+
+	r_skb = nlmsg_new(len, GFP_ATOMIC);
+	if (!r_skb)
+		return -ENOMEM;
+
+	r_nlh = nlmsg_put(r_skb, portid, seq, XFRM_MSG_GETDEFAULT, sizeof(*r_up), 0);
+	if (!r_nlh) {
+		kfree_skb(r_skb);
+		return -EMSGSIZE;
+	}
+
+	r_up = nlmsg_data(r_nlh);
+	r_up->in = net->xfrm.policy_default[XFRM_POLICY_IN];
+	r_up->fwd = net->xfrm.policy_default[XFRM_POLICY_FWD];
+	r_up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
+	nlmsg_end(r_skb, r_nlh);
+
+	return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid);
+}
+
+static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
+			   struct nlattr **attrs,
+			   struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_policy *xp;
+	struct xfrm_userpolicy_id *p;
+	u8 type = XFRM_POLICY_TYPE_MAIN;
+	int err;
+	struct km_event c;
+	int delete;
+	struct xfrm_mark m;
+	u32 if_id = 0;
+
+	p = nlmsg_data(nlh);
+	delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY;
+
+	err = copy_from_user_policy_type(&type, attrs, extack);
+	if (err)
+		return err;
+
+	err = verify_policy_dir(p->dir, extack);
+	if (err)
+		return err;
+
+	if (attrs[XFRMA_IF_ID])
+		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
+	xfrm_mark_get(attrs, &m);
+
+	if (p->index)
+		xp = xfrm_policy_byid(net, &m, if_id, type, p->dir,
+				      p->index, delete, &err);
+	else {
+		struct nlattr *rt = attrs[XFRMA_SEC_CTX];
+		struct xfrm_sec_ctx *ctx;
+
+		err = verify_sec_ctx_len(attrs, extack);
+		if (err)
+			return err;
+
+		ctx = NULL;
+		if (rt) {
+			struct xfrm_user_sec_ctx *uctx = nla_data(rt);
+
+			err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
+			if (err)
+				return err;
+		}
+		xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir,
+					   &p->sel, ctx, delete, &err);
+		security_xfrm_policy_free(ctx);
+	}
+	if (xp == NULL)
+		return -ENOENT;
+
+	if (!delete) {
+		struct sk_buff *resp_skb;
+
+		resp_skb = xfrm_policy_netlink(skb, xp, p->dir, nlh->nlmsg_seq);
+		if (IS_ERR(resp_skb)) {
+			err = PTR_ERR(resp_skb);
+		} else {
+			err = nlmsg_unicast(net->xfrm.nlsk, resp_skb,
+					    NETLINK_CB(skb).portid);
+		}
+	} else {
+		xfrm_dev_policy_delete(xp);
+		xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
+
+		if (err != 0)
+			goto out;
+
+		c.data.byid = p->index;
+		c.event = nlh->nlmsg_type;
+		c.seq = nlh->nlmsg_seq;
+		c.portid = nlh->nlmsg_pid;
+		km_policy_notify(xp, p->dir, &c);
+	}
+
+out:
+	xfrm_pol_put(xp);
+	return err;
+}
+
+static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
+			 struct nlattr **attrs,
+			 struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct km_event c;
+	struct xfrm_usersa_flush *p = nlmsg_data(nlh);
+	int err;
+
+	err = xfrm_state_flush(net, p->proto, true, false);
+	if (err) {
+		if (err == -ESRCH) /* empty table */
+			return 0;
+		return err;
+	}
+	c.data.proto = p->proto;
+	c.event = nlh->nlmsg_type;
+	c.seq = nlh->nlmsg_seq;
+	c.portid = nlh->nlmsg_pid;
+	c.net = net;
+	km_state_notify(NULL, &c);
+
+	return 0;
+}
+
+static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x)
+{
+	unsigned int replay_size = x->replay_esn ?
+			      xfrm_replay_state_esn_len(x->replay_esn) :
+			      sizeof(struct xfrm_replay_state);
+
+	return NLMSG_ALIGN(sizeof(struct xfrm_aevent_id))
+	       + nla_total_size(replay_size)
+	       + nla_total_size_64bit(sizeof(struct xfrm_lifetime_cur))
+	       + nla_total_size(sizeof(struct xfrm_mark))
+	       + nla_total_size(4) /* XFRM_AE_RTHR */
+	       + nla_total_size(4); /* XFRM_AE_ETHR */
+}
+
+static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
+{
+	struct xfrm_aevent_id *id;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_NEWAE, sizeof(*id), 0);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	id = nlmsg_data(nlh);
+	memset(&id->sa_id, 0, sizeof(id->sa_id));
+	memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr));
+	id->sa_id.spi = x->id.spi;
+	id->sa_id.family = x->props.family;
+	id->sa_id.proto = x->id.proto;
+	memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr));
+	id->reqid = x->props.reqid;
+	id->flags = c->data.aevent;
+
+	if (x->replay_esn) {
+		err = nla_put(skb, XFRMA_REPLAY_ESN_VAL,
+			      xfrm_replay_state_esn_len(x->replay_esn),
+			      x->replay_esn);
+	} else {
+		err = nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay),
+			      &x->replay);
+	}
+	if (err)
+		goto out_cancel;
+	err = nla_put_64bit(skb, XFRMA_LTIME_VAL, sizeof(x->curlft), &x->curlft,
+			    XFRMA_PAD);
+	if (err)
+		goto out_cancel;
+
+	if (id->flags & XFRM_AE_RTHR) {
+		err = nla_put_u32(skb, XFRMA_REPLAY_THRESH, x->replay_maxdiff);
+		if (err)
+			goto out_cancel;
+	}
+	if (id->flags & XFRM_AE_ETHR) {
+		err = nla_put_u32(skb, XFRMA_ETIMER_THRESH,
+				  x->replay_maxage * 10 / HZ);
+		if (err)
+			goto out_cancel;
+	}
+	err = xfrm_mark_put(skb, &x->mark);
+	if (err)
+		goto out_cancel;
+
+	err = xfrm_if_id_put(skb, x->if_id);
+	if (err)
+		goto out_cancel;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+out_cancel:
+	nlmsg_cancel(skb, nlh);
+	return err;
+}
+
+static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
+		       struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_state *x;
+	struct sk_buff *r_skb;
+	int err;
+	struct km_event c;
+	u32 mark;
+	struct xfrm_mark m;
+	struct xfrm_aevent_id *p = nlmsg_data(nlh);
+	struct xfrm_usersa_id *id = &p->sa_id;
+
+	mark = xfrm_mark_get(attrs, &m);
+
+	x = xfrm_state_lookup(net, mark, &id->daddr, id->spi, id->proto, id->family);
+	if (x == NULL)
+		return -ESRCH;
+
+	r_skb = nlmsg_new(xfrm_aevent_msgsize(x), GFP_ATOMIC);
+	if (r_skb == NULL) {
+		xfrm_state_put(x);
+		return -ENOMEM;
+	}
+
+	/*
+	 * XXX: is this lock really needed - none of the other
+	 * gets lock (the concern is things getting updated
+	 * while we are still reading) - jhs
+	*/
+	spin_lock_bh(&x->lock);
+	c.data.aevent = p->flags;
+	c.seq = nlh->nlmsg_seq;
+	c.portid = nlh->nlmsg_pid;
+
+	err = build_aevent(r_skb, x, &c);
+	BUG_ON(err < 0);
+
+	err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).portid);
+	spin_unlock_bh(&x->lock);
+	xfrm_state_put(x);
+	return err;
+}
+
+static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
+		       struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_state *x;
+	struct km_event c;
+	int err = -EINVAL;
+	u32 mark = 0;
+	struct xfrm_mark m;
+	struct xfrm_aevent_id *p = nlmsg_data(nlh);
+	struct nlattr *rp = attrs[XFRMA_REPLAY_VAL];
+	struct nlattr *re = attrs[XFRMA_REPLAY_ESN_VAL];
+	struct nlattr *lt = attrs[XFRMA_LTIME_VAL];
+	struct nlattr *et = attrs[XFRMA_ETIMER_THRESH];
+	struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH];
+
+	if (!lt && !rp && !re && !et && !rt) {
+		NL_SET_ERR_MSG(extack, "Missing required attribute for AE");
+		return err;
+	}
+
+	/* pedantic mode - thou shalt sayeth replaceth */
+	if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) {
+		NL_SET_ERR_MSG(extack, "NLM_F_REPLACE flag is required");
+		return err;
+	}
+
+	mark = xfrm_mark_get(attrs, &m);
+
+	x = xfrm_state_lookup(net, mark, &p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family);
+	if (x == NULL)
+		return -ESRCH;
+
+	if (x->km.state != XFRM_STATE_VALID) {
+		NL_SET_ERR_MSG(extack, "SA must be in VALID state");
+		goto out;
+	}
+
+	err = xfrm_replay_verify_len(x->replay_esn, re, extack);
+	if (err)
+		goto out;
+
+	spin_lock_bh(&x->lock);
+	xfrm_update_ae_params(x, attrs, 1);
+	spin_unlock_bh(&x->lock);
+
+	c.event = nlh->nlmsg_type;
+	c.seq = nlh->nlmsg_seq;
+	c.portid = nlh->nlmsg_pid;
+	c.data.aevent = XFRM_AE_CU;
+	km_state_notify(x, &c);
+	err = 0;
+out:
+	xfrm_state_put(x);
+	return err;
+}
+
+static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct nlattr **attrs,
+			     struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct km_event c;
+	u8 type = XFRM_POLICY_TYPE_MAIN;
+	int err;
+
+	err = copy_from_user_policy_type(&type, attrs, extack);
+	if (err)
+		return err;
+
+	err = xfrm_policy_flush(net, type, true);
+	if (err) {
+		if (err == -ESRCH) /* empty table */
+			return 0;
+		return err;
+	}
+
+	c.data.type = type;
+	c.event = nlh->nlmsg_type;
+	c.seq = nlh->nlmsg_seq;
+	c.portid = nlh->nlmsg_pid;
+	c.net = net;
+	km_policy_notify(NULL, 0, &c);
+	return 0;
+}
+
+static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct nlattr **attrs,
+			       struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_policy *xp;
+	struct xfrm_user_polexpire *up = nlmsg_data(nlh);
+	struct xfrm_userpolicy_info *p = &up->pol;
+	u8 type = XFRM_POLICY_TYPE_MAIN;
+	int err = -ENOENT;
+	struct xfrm_mark m;
+	u32 if_id = 0;
+
+	err = copy_from_user_policy_type(&type, attrs, extack);
+	if (err)
+		return err;
+
+	err = verify_policy_dir(p->dir, extack);
+	if (err)
+		return err;
+
+	if (attrs[XFRMA_IF_ID])
+		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
+	xfrm_mark_get(attrs, &m);
+
+	if (p->index)
+		xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index,
+				      0, &err);
+	else {
+		struct nlattr *rt = attrs[XFRMA_SEC_CTX];
+		struct xfrm_sec_ctx *ctx;
+
+		err = verify_sec_ctx_len(attrs, extack);
+		if (err)
+			return err;
+
+		ctx = NULL;
+		if (rt) {
+			struct xfrm_user_sec_ctx *uctx = nla_data(rt);
+
+			err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
+			if (err)
+				return err;
+		}
+		xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir,
+					   &p->sel, ctx, 0, &err);
+		security_xfrm_policy_free(ctx);
+	}
+	if (xp == NULL)
+		return -ENOENT;
+
+	if (unlikely(xp->walk.dead))
+		goto out;
+
+	err = 0;
+	if (up->hard) {
+		xfrm_policy_delete(xp, p->dir);
+		xfrm_audit_policy_delete(xp, 1, true);
+	}
+	km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid);
+
+out:
+	xfrm_pol_put(xp);
+	return err;
+}
+
+static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
+			      struct nlattr **attrs,
+			      struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_state *x;
+	int err;
+	struct xfrm_user_expire *ue = nlmsg_data(nlh);
+	struct xfrm_usersa_info *p = &ue->state;
+	struct xfrm_mark m;
+	u32 mark = xfrm_mark_get(attrs, &m);
+
+	x = xfrm_state_lookup(net, mark, &p->id.daddr, p->id.spi, p->id.proto, p->family);
+
+	err = -ENOENT;
+	if (x == NULL)
+		return err;
+
+	spin_lock_bh(&x->lock);
+	err = -EINVAL;
+	if (x->km.state != XFRM_STATE_VALID) {
+		NL_SET_ERR_MSG(extack, "SA must be in VALID state");
+		goto out;
+	}
+
+	km_state_expired(x, ue->hard, nlh->nlmsg_pid);
+
+	if (ue->hard) {
+		__xfrm_state_delete(x);
+		xfrm_audit_state_delete(x, 1, true);
+	}
+	err = 0;
+out:
+	spin_unlock_bh(&x->lock);
+	xfrm_state_put(x);
+	return err;
+}
+
+static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct nlattr **attrs,
+			    struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_policy *xp;
+	struct xfrm_user_tmpl *ut;
+	int i;
+	struct nlattr *rt = attrs[XFRMA_TMPL];
+	struct xfrm_mark mark;
+
+	struct xfrm_user_acquire *ua = nlmsg_data(nlh);
+	struct xfrm_state *x = xfrm_state_alloc(net);
+	int err = -ENOMEM;
+
+	if (!x)
+		goto nomem;
+
+	xfrm_mark_get(attrs, &mark);
+
+	err = verify_newpolicy_info(&ua->policy, extack);
+	if (err)
+		goto free_state;
+	err = verify_sec_ctx_len(attrs, extack);
+	if (err)
+		goto free_state;
+
+	/*   build an XP */
+	xp = xfrm_policy_construct(net, &ua->policy, attrs, &err, extack);
+	if (!xp)
+		goto free_state;
+
+	memcpy(&x->id, &ua->id, sizeof(ua->id));
+	memcpy(&x->props.saddr, &ua->saddr, sizeof(ua->saddr));
+	memcpy(&x->sel, &ua->sel, sizeof(ua->sel));
+	xp->mark.m = x->mark.m = mark.m;
+	xp->mark.v = x->mark.v = mark.v;
+	ut = nla_data(rt);
+	/* extract the templates and for each call km_key */
+	for (i = 0; i < xp->xfrm_nr; i++, ut++) {
+		struct xfrm_tmpl *t = &xp->xfrm_vec[i];
+		memcpy(&x->id, &t->id, sizeof(x->id));
+		x->props.mode = t->mode;
+		x->props.reqid = t->reqid;
+		x->props.family = ut->family;
+		t->aalgos = ua->aalgos;
+		t->ealgos = ua->ealgos;
+		t->calgos = ua->calgos;
+		err = km_query(x, t, xp);
+
+	}
+
+	xfrm_state_free(x);
+	kfree(xp);
+
+	return 0;
+
+free_state:
+	xfrm_state_free(x);
+nomem:
+	return err;
+}
+
+#ifdef CONFIG_XFRM_MIGRATE
+static int copy_from_user_migrate(struct xfrm_migrate *ma,
+				  struct xfrm_kmaddress *k,
+				  struct nlattr **attrs, int *num,
+				  struct netlink_ext_ack *extack)
+{
+	struct nlattr *rt = attrs[XFRMA_MIGRATE];
+	struct xfrm_user_migrate *um;
+	int i, num_migrate;
+
+	if (k != NULL) {
+		struct xfrm_user_kmaddress *uk;
+
+		uk = nla_data(attrs[XFRMA_KMADDRESS]);
+		memcpy(&k->local, &uk->local, sizeof(k->local));
+		memcpy(&k->remote, &uk->remote, sizeof(k->remote));
+		k->family = uk->family;
+		k->reserved = uk->reserved;
+	}
+
+	um = nla_data(rt);
+	num_migrate = nla_len(rt) / sizeof(*um);
+
+	if (num_migrate <= 0 || num_migrate > XFRM_MAX_DEPTH) {
+		NL_SET_ERR_MSG(extack, "Invalid number of SAs to migrate, must be 0 < num <= XFRM_MAX_DEPTH (6)");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < num_migrate; i++, um++, ma++) {
+		memcpy(&ma->old_daddr, &um->old_daddr, sizeof(ma->old_daddr));
+		memcpy(&ma->old_saddr, &um->old_saddr, sizeof(ma->old_saddr));
+		memcpy(&ma->new_daddr, &um->new_daddr, sizeof(ma->new_daddr));
+		memcpy(&ma->new_saddr, &um->new_saddr, sizeof(ma->new_saddr));
+
+		ma->proto = um->proto;
+		ma->mode = um->mode;
+		ma->reqid = um->reqid;
+
+		ma->old_family = um->old_family;
+		ma->new_family = um->new_family;
+	}
+
+	*num = i;
+	return 0;
+}
+
+static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
+			   struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	struct xfrm_userpolicy_id *pi = nlmsg_data(nlh);
+	struct xfrm_migrate m[XFRM_MAX_DEPTH];
+	struct xfrm_kmaddress km, *kmp;
+	u8 type;
+	int err;
+	int n = 0;
+	struct net *net = sock_net(skb->sk);
+	struct xfrm_encap_tmpl  *encap = NULL;
+	u32 if_id = 0;
+
+	if (!attrs[XFRMA_MIGRATE]) {
+		NL_SET_ERR_MSG(extack, "Missing required MIGRATE attribute");
+		return -EINVAL;
+	}
+
+	kmp = attrs[XFRMA_KMADDRESS] ? &km : NULL;
+
+	err = copy_from_user_policy_type(&type, attrs, extack);
+	if (err)
+		return err;
+
+	err = copy_from_user_migrate(m, kmp, attrs, &n, extack);
+	if (err)
+		return err;
+
+	if (!n)
+		return 0;
+
+	if (attrs[XFRMA_ENCAP]) {
+		encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]),
+				sizeof(*encap), GFP_KERNEL);
+		if (!encap)
+			return -ENOMEM;
+	}
+
+	if (attrs[XFRMA_IF_ID])
+		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
+	err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap,
+			   if_id, extack);
+
+	kfree(encap);
+
+	return err;
+}
+#else
+static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
+			   struct nlattr **attrs, struct netlink_ext_ack *extack)
+{
+	return -ENOPROTOOPT;
+}
+#endif
+
+#ifdef CONFIG_XFRM_MIGRATE
+static int copy_to_user_migrate(const struct xfrm_migrate *m, struct sk_buff *skb)
+{
+	struct xfrm_user_migrate um;
+
+	memset(&um, 0, sizeof(um));
+	um.proto = m->proto;
+	um.mode = m->mode;
+	um.reqid = m->reqid;
+	um.old_family = m->old_family;
+	memcpy(&um.old_daddr, &m->old_daddr, sizeof(um.old_daddr));
+	memcpy(&um.old_saddr, &m->old_saddr, sizeof(um.old_saddr));
+	um.new_family = m->new_family;
+	memcpy(&um.new_daddr, &m->new_daddr, sizeof(um.new_daddr));
+	memcpy(&um.new_saddr, &m->new_saddr, sizeof(um.new_saddr));
+
+	return nla_put(skb, XFRMA_MIGRATE, sizeof(um), &um);
+}
+
+static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff *skb)
+{
+	struct xfrm_user_kmaddress uk;
+
+	memset(&uk, 0, sizeof(uk));
+	uk.family = k->family;
+	uk.reserved = k->reserved;
+	memcpy(&uk.local, &k->local, sizeof(uk.local));
+	memcpy(&uk.remote, &k->remote, sizeof(uk.remote));
+
+	return nla_put(skb, XFRMA_KMADDRESS, sizeof(uk), &uk);
+}
+
+static inline unsigned int xfrm_migrate_msgsize(int num_migrate, int with_kma,
+						int with_encp)
+{
+	return NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_id))
+	      + (with_kma ? nla_total_size(sizeof(struct xfrm_kmaddress)) : 0)
+	      + (with_encp ? nla_total_size(sizeof(struct xfrm_encap_tmpl)) : 0)
+	      + nla_total_size(sizeof(struct xfrm_user_migrate) * num_migrate)
+	      + userpolicy_type_attrsize();
+}
+
+static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m,
+			 int num_migrate, const struct xfrm_kmaddress *k,
+			 const struct xfrm_selector *sel,
+			 const struct xfrm_encap_tmpl *encap, u8 dir, u8 type)
+{
+	const struct xfrm_migrate *mp;
+	struct xfrm_userpolicy_id *pol_id;
+	struct nlmsghdr *nlh;
+	int i, err;
+
+	nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_MIGRATE, sizeof(*pol_id), 0);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	pol_id = nlmsg_data(nlh);
+	/* copy data from selector, dir, and type to the pol_id */
+	memset(pol_id, 0, sizeof(*pol_id));
+	memcpy(&pol_id->sel, sel, sizeof(pol_id->sel));
+	pol_id->dir = dir;
+
+	if (k != NULL) {
+		err = copy_to_user_kmaddress(k, skb);
+		if (err)
+			goto out_cancel;
+	}
+	if (encap) {
+		err = nla_put(skb, XFRMA_ENCAP, sizeof(*encap), encap);
+		if (err)
+			goto out_cancel;
+	}
+	err = copy_to_user_policy_type(type, skb);
+	if (err)
+		goto out_cancel;
+	for (i = 0, mp = m ; i < num_migrate; i++, mp++) {
+		err = copy_to_user_migrate(mp, skb);
+		if (err)
+			goto out_cancel;
+	}
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+out_cancel:
+	nlmsg_cancel(skb, nlh);
+	return err;
+}
+
+static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+			     const struct xfrm_migrate *m, int num_migrate,
+			     const struct xfrm_kmaddress *k,
+			     const struct xfrm_encap_tmpl *encap)
+{
+	struct net *net = &init_net;
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k, !!encap),
+			GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	/* build migrate */
+	err = build_migrate(skb, m, num_migrate, k, sel, encap, dir, type);
+	BUG_ON(err < 0);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE);
+}
+#else
+static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+			     const struct xfrm_migrate *m, int num_migrate,
+			     const struct xfrm_kmaddress *k,
+			     const struct xfrm_encap_tmpl *encap)
+{
+	return -ENOPROTOOPT;
+}
+#endif
+
+#define XMSGSIZE(type) sizeof(struct type)
+
+const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
+	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info),
+	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_NEWPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info),
+	[XFRM_MSG_DELPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_GETPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_ALLOCSPI    - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userspi_info),
+	[XFRM_MSG_ACQUIRE     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_acquire),
+	[XFRM_MSG_EXPIRE      - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_expire),
+	[XFRM_MSG_UPDPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info),
+	[XFRM_MSG_UPDSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info),
+	[XFRM_MSG_POLEXPIRE   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_polexpire),
+	[XFRM_MSG_FLUSHSA     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush),
+	[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0,
+	[XFRM_MSG_NEWAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_REPORT      - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report),
+	[XFRM_MSG_MIGRATE     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_SETDEFAULT  - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default),
+	[XFRM_MSG_GETDEFAULT  - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default),
+};
+EXPORT_SYMBOL_GPL(xfrm_msg_min);
+
+#undef XMSGSIZE
+
+const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
+	[XFRMA_SA]		= { .len = sizeof(struct xfrm_usersa_info)},
+	[XFRMA_POLICY]		= { .len = sizeof(struct xfrm_userpolicy_info)},
+	[XFRMA_LASTUSED]	= { .type = NLA_U64},
+	[XFRMA_ALG_AUTH_TRUNC]	= { .len = sizeof(struct xfrm_algo_auth)},
+	[XFRMA_ALG_AEAD]	= { .len = sizeof(struct xfrm_algo_aead) },
+	[XFRMA_ALG_AUTH]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_CRYPT]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_COMP]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ENCAP]		= { .len = sizeof(struct xfrm_encap_tmpl) },
+	[XFRMA_TMPL]		= { .len = sizeof(struct xfrm_user_tmpl) },
+	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_user_sec_ctx) },
+	[XFRMA_LTIME_VAL]	= { .len = sizeof(struct xfrm_lifetime_cur) },
+	[XFRMA_REPLAY_VAL]	= { .len = sizeof(struct xfrm_replay_state) },
+	[XFRMA_REPLAY_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_ETIMER_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_SRCADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_COADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_POLICY_TYPE]	= { .len = sizeof(struct xfrm_userpolicy_type)},
+	[XFRMA_MIGRATE]		= { .len = sizeof(struct xfrm_user_migrate) },
+	[XFRMA_KMADDRESS]	= { .len = sizeof(struct xfrm_user_kmaddress) },
+	[XFRMA_MARK]		= { .len = sizeof(struct xfrm_mark) },
+	[XFRMA_TFCPAD]		= { .type = NLA_U32 },
+	[XFRMA_REPLAY_ESN_VAL]	= { .len = sizeof(struct xfrm_replay_state_esn) },
+	[XFRMA_SA_EXTRA_FLAGS]	= { .type = NLA_U32 },
+	[XFRMA_PROTO]		= { .type = NLA_U8 },
+	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
+	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
+	[XFRMA_SET_MARK]	= { .type = NLA_U32 },
+	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
+	[XFRMA_IF_ID]		= { .type = NLA_U32 },
+	[XFRMA_MTIMER_THRESH]   = { .type = NLA_U32 },
+};
+EXPORT_SYMBOL_GPL(xfrma_policy);
+
+static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
+	[XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
+	[XFRMA_SPD_IPV6_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
+};
+
+static const struct xfrm_link {
+	int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **,
+		    struct netlink_ext_ack *);
+	int (*start)(struct netlink_callback *);
+	int (*dump)(struct sk_buff *, struct netlink_callback *);
+	int (*done)(struct netlink_callback *);
+	const struct nla_policy *nla_pol;
+	int nla_max;
+} xfrm_dispatch[XFRM_NR_MSGTYPES] = {
+	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = { .doit = xfrm_add_sa        },
+	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = { .doit = xfrm_del_sa        },
+	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = { .doit = xfrm_get_sa,
+						   .dump = xfrm_dump_sa,
+						   .done = xfrm_dump_sa_done  },
+	[XFRM_MSG_NEWPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_add_policy    },
+	[XFRM_MSG_DELPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_get_policy    },
+	[XFRM_MSG_GETPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_get_policy,
+						   .start = xfrm_dump_policy_start,
+						   .dump = xfrm_dump_policy,
+						   .done = xfrm_dump_policy_done },
+	[XFRM_MSG_ALLOCSPI    - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi },
+	[XFRM_MSG_ACQUIRE     - XFRM_MSG_BASE] = { .doit = xfrm_add_acquire   },
+	[XFRM_MSG_EXPIRE      - XFRM_MSG_BASE] = { .doit = xfrm_add_sa_expire },
+	[XFRM_MSG_UPDPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_add_policy    },
+	[XFRM_MSG_UPDSA       - XFRM_MSG_BASE] = { .doit = xfrm_add_sa        },
+	[XFRM_MSG_POLEXPIRE   - XFRM_MSG_BASE] = { .doit = xfrm_add_pol_expire},
+	[XFRM_MSG_FLUSHSA     - XFRM_MSG_BASE] = { .doit = xfrm_flush_sa      },
+	[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_flush_policy  },
+	[XFRM_MSG_NEWAE       - XFRM_MSG_BASE] = { .doit = xfrm_new_ae  },
+	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = { .doit = xfrm_get_ae  },
+	[XFRM_MSG_MIGRATE     - XFRM_MSG_BASE] = { .doit = xfrm_do_migrate    },
+	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = { .doit = xfrm_get_sadinfo   },
+	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = { .doit = xfrm_set_spdinfo,
+						   .nla_pol = xfrma_spd_policy,
+						   .nla_max = XFRMA_SPD_MAX },
+	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = { .doit = xfrm_get_spdinfo   },
+	[XFRM_MSG_SETDEFAULT  - XFRM_MSG_BASE] = { .doit = xfrm_set_default   },
+	[XFRM_MSG_GETDEFAULT  - XFRM_MSG_BASE] = { .doit = xfrm_get_default   },
+};
+
+static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *attrs[XFRMA_MAX+1];
+	const struct xfrm_link *link;
+	struct nlmsghdr *nlh64 = NULL;
+	int type, err;
+
+	type = nlh->nlmsg_type;
+	if (type > XFRM_MSG_MAX)
+		return -EINVAL;
+
+	type -= XFRM_MSG_BASE;
+	link = &xfrm_dispatch[type];
+
+	/* All operations require privileges, even GET */
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (in_compat_syscall()) {
+		struct xfrm_translator *xtr = xfrm_get_translator();
+
+		if (!xtr)
+			return -EOPNOTSUPP;
+
+		nlh64 = xtr->rcv_msg_compat(nlh, link->nla_max,
+					    link->nla_pol, extack);
+		xfrm_put_translator(xtr);
+		if (IS_ERR(nlh64))
+			return PTR_ERR(nlh64);
+		if (nlh64)
+			nlh = nlh64;
+	}
+
+	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
+	     type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) &&
+	    (nlh->nlmsg_flags & NLM_F_DUMP)) {
+		struct netlink_dump_control c = {
+			.start = link->start,
+			.dump = link->dump,
+			.done = link->done,
+		};
+
+		if (link->dump == NULL) {
+			err = -EINVAL;
+			goto err;
+		}
+
+		err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+		goto err;
+	}
+
+	err = nlmsg_parse_deprecated(nlh, xfrm_msg_min[type], attrs,
+				     link->nla_max ? : XFRMA_MAX,
+				     link->nla_pol ? : xfrma_policy, extack);
+	if (err < 0)
+		goto err;
+
+	if (link->doit == NULL) {
+		err = -EINVAL;
+		goto err;
+	}
+
+	err = link->doit(skb, nlh, attrs, extack);
+
+	/* We need to free skb allocated in xfrm_alloc_compat() before
+	 * returning from this function, because consume_skb() won't take
+	 * care of frag_list since netlink destructor sets
+	 * sbk->head to NULL. (see netlink_skb_destructor())
+	 */
+	if (skb_has_frag_list(skb)) {
+		kfree_skb(skb_shinfo(skb)->frag_list);
+		skb_shinfo(skb)->frag_list = NULL;
+	}
+
+err:
+	kvfree(nlh64);
+	return err;
+}
+
+static void xfrm_netlink_rcv(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+
+	mutex_lock(&net->xfrm.xfrm_cfg_mutex);
+	netlink_rcv_skb(skb, &xfrm_user_rcv_msg);
+	mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
+}
+
+static inline unsigned int xfrm_expire_msgsize(void)
+{
+	return NLMSG_ALIGN(sizeof(struct xfrm_user_expire))
+	       + nla_total_size(sizeof(struct xfrm_mark));
+}
+
+static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
+{
+	struct xfrm_user_expire *ue;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = nlmsg_put(skb, c->portid, 0, XFRM_MSG_EXPIRE, sizeof(*ue), 0);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ue = nlmsg_data(nlh);
+	copy_to_user_state(x, &ue->state);
+	ue->hard = (c->data.hard != 0) ? 1 : 0;
+	/* clear the padding bytes */
+	memset_after(ue, 0, hard);
+
+	err = xfrm_mark_put(skb, &x->mark);
+	if (err)
+		return err;
+
+	err = xfrm_if_id_put(skb, x->if_id);
+	if (err)
+		return err;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c)
+{
+	struct net *net = xs_net(x);
+	struct sk_buff *skb;
+
+	skb = nlmsg_new(xfrm_expire_msgsize(), GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	if (build_expire(skb, x, c) < 0) {
+		kfree_skb(skb);
+		return -EMSGSIZE;
+	}
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
+}
+
+static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c)
+{
+	struct net *net = xs_net(x);
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(xfrm_aevent_msgsize(x), GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	err = build_aevent(skb, x, c);
+	BUG_ON(err < 0);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS);
+}
+
+static int xfrm_notify_sa_flush(const struct km_event *c)
+{
+	struct net *net = c->net;
+	struct xfrm_usersa_flush *p;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	int len = NLMSG_ALIGN(sizeof(struct xfrm_usersa_flush));
+
+	skb = nlmsg_new(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_FLUSHSA, sizeof(*p), 0);
+	if (nlh == NULL) {
+		kfree_skb(skb);
+		return -EMSGSIZE;
+	}
+
+	p = nlmsg_data(nlh);
+	p->proto = c->data.proto;
+
+	nlmsg_end(skb, nlh);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
+}
+
+static inline unsigned int xfrm_sa_len(struct xfrm_state *x)
+{
+	unsigned int l = 0;
+	if (x->aead)
+		l += nla_total_size(aead_len(x->aead));
+	if (x->aalg) {
+		l += nla_total_size(sizeof(struct xfrm_algo) +
+				    (x->aalg->alg_key_len + 7) / 8);
+		l += nla_total_size(xfrm_alg_auth_len(x->aalg));
+	}
+	if (x->ealg)
+		l += nla_total_size(xfrm_alg_len(x->ealg));
+	if (x->calg)
+		l += nla_total_size(sizeof(*x->calg));
+	if (x->encap)
+		l += nla_total_size(sizeof(*x->encap));
+	if (x->tfcpad)
+		l += nla_total_size(sizeof(x->tfcpad));
+	if (x->replay_esn)
+		l += nla_total_size(xfrm_replay_state_esn_len(x->replay_esn));
+	else
+		l += nla_total_size(sizeof(struct xfrm_replay_state));
+	if (x->security)
+		l += nla_total_size(sizeof(struct xfrm_user_sec_ctx) +
+				    x->security->ctx_len);
+	if (x->coaddr)
+		l += nla_total_size(sizeof(*x->coaddr));
+	if (x->props.extra_flags)
+		l += nla_total_size(sizeof(x->props.extra_flags));
+	if (x->xso.dev)
+		 l += nla_total_size(sizeof(struct xfrm_user_offload));
+	if (x->props.smark.v | x->props.smark.m) {
+		l += nla_total_size(sizeof(x->props.smark.v));
+		l += nla_total_size(sizeof(x->props.smark.m));
+	}
+	if (x->if_id)
+		l += nla_total_size(sizeof(x->if_id));
+
+	/* Must count x->lastused as it may become non-zero behind our back. */
+	l += nla_total_size_64bit(sizeof(u64));
+
+	if (x->mapping_maxage)
+		l += nla_total_size(sizeof(x->mapping_maxage));
+
+	return l;
+}
+
+static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c)
+{
+	struct net *net = xs_net(x);
+	struct xfrm_usersa_info *p;
+	struct xfrm_usersa_id *id;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	unsigned int len = xfrm_sa_len(x);
+	unsigned int headlen;
+	int err;
+
+	headlen = sizeof(*p);
+	if (c->event == XFRM_MSG_DELSA) {
+		len += nla_total_size(headlen);
+		headlen = sizeof(*id);
+		len += nla_total_size(sizeof(struct xfrm_mark));
+	}
+	len += NLMSG_ALIGN(headlen);
+
+	skb = nlmsg_new(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(skb, c->portid, c->seq, c->event, headlen, 0);
+	err = -EMSGSIZE;
+	if (nlh == NULL)
+		goto out_free_skb;
+
+	p = nlmsg_data(nlh);
+	if (c->event == XFRM_MSG_DELSA) {
+		struct nlattr *attr;
+
+		id = nlmsg_data(nlh);
+		memset(id, 0, sizeof(*id));
+		memcpy(&id->daddr, &x->id.daddr, sizeof(id->daddr));
+		id->spi = x->id.spi;
+		id->family = x->props.family;
+		id->proto = x->id.proto;
+
+		attr = nla_reserve(skb, XFRMA_SA, sizeof(*p));
+		err = -EMSGSIZE;
+		if (attr == NULL)
+			goto out_free_skb;
+
+		p = nla_data(attr);
+	}
+	err = copy_to_user_state_extra(x, p, skb);
+	if (err)
+		goto out_free_skb;
+
+	nlmsg_end(skb, nlh);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
+
+out_free_skb:
+	kfree_skb(skb);
+	return err;
+}
+
+static int xfrm_send_state_notify(struct xfrm_state *x, const struct km_event *c)
+{
+
+	switch (c->event) {
+	case XFRM_MSG_EXPIRE:
+		return xfrm_exp_state_notify(x, c);
+	case XFRM_MSG_NEWAE:
+		return xfrm_aevent_state_notify(x, c);
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_NEWSA:
+		return xfrm_notify_sa(x, c);
+	case XFRM_MSG_FLUSHSA:
+		return xfrm_notify_sa_flush(c);
+	default:
+		printk(KERN_NOTICE "xfrm_user: Unknown SA event %d\n",
+		       c->event);
+		break;
+	}
+
+	return 0;
+
+}
+
+static inline unsigned int xfrm_acquire_msgsize(struct xfrm_state *x,
+						struct xfrm_policy *xp)
+{
+	return NLMSG_ALIGN(sizeof(struct xfrm_user_acquire))
+	       + nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr)
+	       + nla_total_size(sizeof(struct xfrm_mark))
+	       + nla_total_size(xfrm_user_sec_ctx_size(x->security))
+	       + userpolicy_type_attrsize();
+}
+
+static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
+			 struct xfrm_tmpl *xt, struct xfrm_policy *xp)
+{
+	__u32 seq = xfrm_get_acqseq();
+	struct xfrm_user_acquire *ua;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_ACQUIRE, sizeof(*ua), 0);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ua = nlmsg_data(nlh);
+	memcpy(&ua->id, &x->id, sizeof(ua->id));
+	memcpy(&ua->saddr, &x->props.saddr, sizeof(ua->saddr));
+	memcpy(&ua->sel, &x->sel, sizeof(ua->sel));
+	copy_to_user_policy(xp, &ua->policy, XFRM_POLICY_OUT);
+	ua->aalgos = xt->aalgos;
+	ua->ealgos = xt->ealgos;
+	ua->calgos = xt->calgos;
+	ua->seq = x->km.seq = seq;
+
+	err = copy_to_user_tmpl(xp, skb);
+	if (!err)
+		err = copy_to_user_state_sec_ctx(x, skb);
+	if (!err)
+		err = copy_to_user_policy_type(xp->type, skb);
+	if (!err)
+		err = xfrm_mark_put(skb, &xp->mark);
+	if (!err)
+		err = xfrm_if_id_put(skb, xp->if_id);
+	if (!err && xp->xdo.dev)
+		err = copy_user_offload(&xp->xdo, skb);
+	if (err) {
+		nlmsg_cancel(skb, nlh);
+		return err;
+	}
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
+			     struct xfrm_policy *xp)
+{
+	struct net *net = xs_net(x);
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(xfrm_acquire_msgsize(x, xp), GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	err = build_acquire(skb, x, xt, xp);
+	BUG_ON(err < 0);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE);
+}
+
+/* User gives us xfrm_user_policy_info followed by an array of 0
+ * or more templates.
+ */
+static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt,
+					       u8 *data, int len, int *dir)
+{
+	struct net *net = sock_net(sk);
+	struct xfrm_userpolicy_info *p = (struct xfrm_userpolicy_info *)data;
+	struct xfrm_user_tmpl *ut = (struct xfrm_user_tmpl *) (p + 1);
+	struct xfrm_policy *xp;
+	int nr;
+
+	switch (sk->sk_family) {
+	case AF_INET:
+		if (opt != IP_XFRM_POLICY) {
+			*dir = -EOPNOTSUPP;
+			return NULL;
+		}
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		if (opt != IPV6_XFRM_POLICY) {
+			*dir = -EOPNOTSUPP;
+			return NULL;
+		}
+		break;
+#endif
+	default:
+		*dir = -EINVAL;
+		return NULL;
+	}
+
+	*dir = -EINVAL;
+
+	if (len < sizeof(*p) ||
+	    verify_newpolicy_info(p, NULL))
+		return NULL;
+
+	nr = ((len - sizeof(*p)) / sizeof(*ut));
+	if (validate_tmpl(nr, ut, p->sel.family, p->dir, NULL))
+		return NULL;
+
+	if (p->dir > XFRM_POLICY_OUT)
+		return NULL;
+
+	xp = xfrm_policy_alloc(net, GFP_ATOMIC);
+	if (xp == NULL) {
+		*dir = -ENOBUFS;
+		return NULL;
+	}
+
+	copy_from_user_policy(xp, p);
+	xp->type = XFRM_POLICY_TYPE_MAIN;
+	copy_templates(xp, ut, nr);
+
+	*dir = p->dir;
+
+	return xp;
+}
+
+static inline unsigned int xfrm_polexpire_msgsize(struct xfrm_policy *xp)
+{
+	return NLMSG_ALIGN(sizeof(struct xfrm_user_polexpire))
+	       + nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr)
+	       + nla_total_size(xfrm_user_sec_ctx_size(xp->security))
+	       + nla_total_size(sizeof(struct xfrm_mark))
+	       + userpolicy_type_attrsize();
+}
+
+static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
+			   int dir, const struct km_event *c)
+{
+	struct xfrm_user_polexpire *upe;
+	int hard = c->data.hard;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = nlmsg_put(skb, c->portid, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe), 0);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	upe = nlmsg_data(nlh);
+	copy_to_user_policy(xp, &upe->pol, dir);
+	err = copy_to_user_tmpl(xp, skb);
+	if (!err)
+		err = copy_to_user_sec_ctx(xp, skb);
+	if (!err)
+		err = copy_to_user_policy_type(xp->type, skb);
+	if (!err)
+		err = xfrm_mark_put(skb, &xp->mark);
+	if (!err)
+		err = xfrm_if_id_put(skb, xp->if_id);
+	if (!err && xp->xdo.dev)
+		err = copy_user_offload(&xp->xdo, skb);
+	if (err) {
+		nlmsg_cancel(skb, nlh);
+		return err;
+	}
+	upe->hard = !!hard;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
+{
+	struct net *net = xp_net(xp);
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(xfrm_polexpire_msgsize(xp), GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	err = build_polexpire(skb, xp, dir, c);
+	BUG_ON(err < 0);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
+}
+
+static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c)
+{
+	unsigned int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr);
+	struct net *net = xp_net(xp);
+	struct xfrm_userpolicy_info *p;
+	struct xfrm_userpolicy_id *id;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	unsigned int headlen;
+	int err;
+
+	headlen = sizeof(*p);
+	if (c->event == XFRM_MSG_DELPOLICY) {
+		len += nla_total_size(headlen);
+		headlen = sizeof(*id);
+	}
+	len += userpolicy_type_attrsize();
+	len += nla_total_size(sizeof(struct xfrm_mark));
+	len += NLMSG_ALIGN(headlen);
+
+	skb = nlmsg_new(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(skb, c->portid, c->seq, c->event, headlen, 0);
+	err = -EMSGSIZE;
+	if (nlh == NULL)
+		goto out_free_skb;
+
+	p = nlmsg_data(nlh);
+	if (c->event == XFRM_MSG_DELPOLICY) {
+		struct nlattr *attr;
+
+		id = nlmsg_data(nlh);
+		memset(id, 0, sizeof(*id));
+		id->dir = dir;
+		if (c->data.byid)
+			id->index = xp->index;
+		else
+			memcpy(&id->sel, &xp->selector, sizeof(id->sel));
+
+		attr = nla_reserve(skb, XFRMA_POLICY, sizeof(*p));
+		err = -EMSGSIZE;
+		if (attr == NULL)
+			goto out_free_skb;
+
+		p = nla_data(attr);
+	}
+
+	copy_to_user_policy(xp, p, dir);
+	err = copy_to_user_tmpl(xp, skb);
+	if (!err)
+		err = copy_to_user_policy_type(xp->type, skb);
+	if (!err)
+		err = xfrm_mark_put(skb, &xp->mark);
+	if (!err)
+		err = xfrm_if_id_put(skb, xp->if_id);
+	if (!err && xp->xdo.dev)
+		err = copy_user_offload(&xp->xdo, skb);
+	if (err)
+		goto out_free_skb;
+
+	nlmsg_end(skb, nlh);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
+
+out_free_skb:
+	kfree_skb(skb);
+	return err;
+}
+
+static int xfrm_notify_policy_flush(const struct km_event *c)
+{
+	struct net *net = c->net;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(userpolicy_type_attrsize(), GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_FLUSHPOLICY, 0, 0);
+	err = -EMSGSIZE;
+	if (nlh == NULL)
+		goto out_free_skb;
+	err = copy_to_user_policy_type(c->data.type, skb);
+	if (err)
+		goto out_free_skb;
+
+	nlmsg_end(skb, nlh);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
+
+out_free_skb:
+	kfree_skb(skb);
+	return err;
+}
+
+static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
+{
+
+	switch (c->event) {
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDPOLICY:
+	case XFRM_MSG_DELPOLICY:
+		return xfrm_notify_policy(xp, dir, c);
+	case XFRM_MSG_FLUSHPOLICY:
+		return xfrm_notify_policy_flush(c);
+	case XFRM_MSG_POLEXPIRE:
+		return xfrm_exp_policy_notify(xp, dir, c);
+	default:
+		printk(KERN_NOTICE "xfrm_user: Unknown Policy event %d\n",
+		       c->event);
+	}
+
+	return 0;
+
+}
+
+static inline unsigned int xfrm_report_msgsize(void)
+{
+	return NLMSG_ALIGN(sizeof(struct xfrm_user_report));
+}
+
+static int build_report(struct sk_buff *skb, u8 proto,
+			struct xfrm_selector *sel, xfrm_address_t *addr)
+{
+	struct xfrm_user_report *ur;
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_REPORT, sizeof(*ur), 0);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ur = nlmsg_data(nlh);
+	ur->proto = proto;
+	memcpy(&ur->sel, sel, sizeof(ur->sel));
+
+	if (addr) {
+		int err = nla_put(skb, XFRMA_COADDR, sizeof(*addr), addr);
+		if (err) {
+			nlmsg_cancel(skb, nlh);
+			return err;
+		}
+	}
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int xfrm_send_report(struct net *net, u8 proto,
+			    struct xfrm_selector *sel, xfrm_address_t *addr)
+{
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(xfrm_report_msgsize(), GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	err = build_report(skb, proto, sel, addr);
+	BUG_ON(err < 0);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT);
+}
+
+static inline unsigned int xfrm_mapping_msgsize(void)
+{
+	return NLMSG_ALIGN(sizeof(struct xfrm_user_mapping));
+}
+
+static int build_mapping(struct sk_buff *skb, struct xfrm_state *x,
+			 xfrm_address_t *new_saddr, __be16 new_sport)
+{
+	struct xfrm_user_mapping *um;
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_MAPPING, sizeof(*um), 0);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	um = nlmsg_data(nlh);
+
+	memcpy(&um->id.daddr, &x->id.daddr, sizeof(um->id.daddr));
+	um->id.spi = x->id.spi;
+	um->id.family = x->props.family;
+	um->id.proto = x->id.proto;
+	memcpy(&um->new_saddr, new_saddr, sizeof(um->new_saddr));
+	memcpy(&um->old_saddr, &x->props.saddr, sizeof(um->old_saddr));
+	um->new_sport = new_sport;
+	um->old_sport = x->encap->encap_sport;
+	um->reqid = x->props.reqid;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
+			     __be16 sport)
+{
+	struct net *net = xs_net(x);
+	struct sk_buff *skb;
+	int err;
+
+	if (x->id.proto != IPPROTO_ESP)
+		return -EINVAL;
+
+	if (!x->encap)
+		return -EINVAL;
+
+	skb = nlmsg_new(xfrm_mapping_msgsize(), GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	err = build_mapping(skb, x, ipaddr, sport);
+	BUG_ON(err < 0);
+
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING);
+}
+
+static bool xfrm_is_alive(const struct km_event *c)
+{
+	return (bool)xfrm_acquire_is_on(c->net);
+}
+
+static struct xfrm_mgr netlink_mgr = {
+	.notify		= xfrm_send_state_notify,
+	.acquire	= xfrm_send_acquire,
+	.compile_policy	= xfrm_compile_policy,
+	.notify_policy	= xfrm_send_policy_notify,
+	.report		= xfrm_send_report,
+	.migrate	= xfrm_send_migrate,
+	.new_mapping	= xfrm_send_mapping,
+	.is_alive	= xfrm_is_alive,
+};
+
+static int __net_init xfrm_user_net_init(struct net *net)
+{
+	struct sock *nlsk;
+	struct netlink_kernel_cfg cfg = {
+		.groups	= XFRMNLGRP_MAX,
+		.input	= xfrm_netlink_rcv,
+	};
+
+	nlsk = netlink_kernel_create(net, NETLINK_XFRM, &cfg);
+	if (nlsk == NULL)
+		return -ENOMEM;
+	net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */
+	rcu_assign_pointer(net->xfrm.nlsk, nlsk);
+	return 0;
+}
+
+static void __net_exit xfrm_user_net_pre_exit(struct net *net)
+{
+	RCU_INIT_POINTER(net->xfrm.nlsk, NULL);
+}
+
+static void __net_exit xfrm_user_net_exit(struct list_head *net_exit_list)
+{
+	struct net *net;
+
+	list_for_each_entry(net, net_exit_list, exit_list)
+		netlink_kernel_release(net->xfrm.nlsk_stash);
+}
+
+static struct pernet_operations xfrm_user_net_ops = {
+	.init	    = xfrm_user_net_init,
+	.pre_exit   = xfrm_user_net_pre_exit,
+	.exit_batch = xfrm_user_net_exit,
+};
+
+static int __init xfrm_user_init(void)
+{
+	int rv;
+
+	printk(KERN_INFO "Initializing XFRM netlink socket\n");
+
+	rv = register_pernet_subsys(&xfrm_user_net_ops);
+	if (rv < 0)
+		return rv;
+	xfrm_register_km(&netlink_mgr);
+	return 0;
+}
+
+static void __exit xfrm_user_exit(void)
+{
+	xfrm_unregister_km(&netlink_mgr);
+	unregister_pernet_subsys(&xfrm_user_net_ops);
+}
+
+module_init(xfrm_user_init);
+module_exit(xfrm_user_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM);