Resguardo inicial

linux-7.2.3/net/xfrm/Kconfig

@@ -0,0 +1,160 @@
+# 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_AEAD
+	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 (deprecated)"
+	select XFRM_ALGO
+	help
+	  PF_KEYv2 socket family, compatible to KAME ones.
+
+	  The PF_KEYv2 socket interface is deprecated and
+	  scheduled for removal. All maintained IKE daemons
+	  no longer need PF_KEY sockets. Please use the netlink
+	  interface (XFRM_USER) to configure IPsec.
+
+	  If unsure, say N.
+
+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_IPTFS
+	tristate "IPsec IP-TFS/AGGFRAG (RFC 9347) encapsulation support"
+	depends on XFRM
+	help
+	  Information on the IP-TFS/AGGFRAG encapsulation can be found
+	  in RFC 9347. This feature supports demand driven (i.e.,
+	  non-constant send rate) IP-TFS to take advantage of the
+	  AGGFRAG ESP payload encapsulation. This payload type
+	  supports aggregation and fragmentation of the inner IP
+	  packet stream which in turn yields higher small-packet
+	  bandwidth as well as reducing MTU/PMTU issues. Congestion
+	  control is unimplementated as the send rate is demand driven
+	  rather than constant.
+
+	  If unsure, say N.
+
+config XFRM_ESPINTCP
+	bool
+
+endif # INET

linux-7.2.3/net/xfrm/Makefile

@@ -0,0 +1,26 @@
+# 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 \
+		      xfrm_nat_keepalive.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-$(CONFIG_XFRM_IPTFS) += xfrm_iptfs.o
+obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
+obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o

linux-7.2.3/net/xfrm/espintcp.c

@@ -0,0 +1,577 @@
+// 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>
+#include <net/hotdata.h>
+
+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);
+	if (!skb->dev) {
+		XFRM_INC_STATS(sock_net(sk), LINUX_MIB_XFRMINERROR);
+		kfree_skb(skb);
+		goto out;
+	}
+	local_bh_disable();
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		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();
+out:
+	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)
+{
+	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(net_hotdata.max_backlog)) {
+		kfree_skb(skb);
+		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 ret;
+
+	do {
+		struct bio_vec bvec;
+
+		sg = &skmsg->sg.data[skmsg->sg.start];
+		if (sg_is_last(sg) && !more)
+			msghdr.msg_flags &= ~MSG_MORE;
+
+		bvec_set_page(&bvec, sg_page(sg), sg->length, sg->offset);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, sg->length);
+		ret = tcp_sendmsg_locked(sk, &msghdr, sg->length);
+		if (ret < 0)
+			return ret;
+
+		sk_msg_free_partial(sk, skmsg, ret);
+	} while (skmsg->sg.size);
+
+	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;
+	}
+	if (emsg->len) {
+		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_obj(*ctx);
+	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;
+
+	synchronize_rcu();
+
+	disable_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)
+{
+	struct sock *sk = sock->sk;
+	struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+	return datagram_poll_queue(file, sock, wait, &ctx->ike_queue);
+}
+
+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);
+}

linux-7.2.3/net/xfrm/trace_iptfs.h

@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* xfrm_trace_iptfs.h
+ *
+ * August 12 2023, Christian Hopps <chopps@labn.net>
+ *
+ * Copyright (c) 2023, LabN Consulting, L.L.C.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM iptfs
+
+#if !defined(_TRACE_IPTFS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IPTFS_H
+
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/tracepoint.h>
+#include <net/ip.h>
+
+struct xfrm_iptfs_data;
+
+TRACE_EVENT(iptfs_egress_recv,
+	    TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, u16 blkoff),
+	    TP_ARGS(skb, xtfs, blkoff),
+	    TP_STRUCT__entry(__field(struct sk_buff *, skb)
+			     __field(void *, head)
+			     __field(void *, head_pg_addr)
+			     __field(void *, pg0addr)
+			     __field(u32, skb_len)
+			     __field(u32, data_len)
+			     __field(u32, headroom)
+			     __field(u32, tailroom)
+			     __field(u32, tail)
+			     __field(u32, end)
+			     __field(u32, pg0off)
+			     __field(u8, head_frag)
+			     __field(u8, frag_list)
+			     __field(u8, nr_frags)
+			     __field(u16, blkoff)),
+	    TP_fast_assign(__entry->skb = skb;
+			   __entry->head = skb->head;
+			   __entry->skb_len = skb->len;
+			   __entry->data_len = skb->data_len;
+			   __entry->headroom = skb_headroom(skb);
+			   __entry->tailroom = skb_tailroom(skb);
+			   __entry->tail = (u32)skb->tail;
+			   __entry->end = (u32)skb->end;
+			   __entry->head_frag = skb->head_frag;
+			   __entry->frag_list = (bool)skb_shinfo(skb)->frag_list;
+			   __entry->nr_frags = skb_shinfo(skb)->nr_frags;
+			   __entry->blkoff = blkoff;
+			   __entry->head_pg_addr = page_address(virt_to_head_page(skb->head));
+			   __entry->pg0addr = (__entry->nr_frags
+					       ? page_address(netmem_to_page(skb_shinfo(skb)->frags[0].netmem))
+					       : NULL);
+			   __entry->pg0off = (__entry->nr_frags
+					      ? skb_shinfo(skb)->frags[0].offset
+					      : 0);
+		    ),
+	    TP_printk("EGRESS: skb=%p len=%u data_len=%u headroom=%u head_frag=%u frag_list=%u nr_frags=%u blkoff=%u\n\t\ttailroom=%u tail=%u end=%u head=%p hdpgaddr=%p pg0->addr=%p pg0->data=%p pg0->off=%u",
+		      __entry->skb, __entry->skb_len, __entry->data_len, __entry->headroom,
+		      __entry->head_frag, __entry->frag_list, __entry->nr_frags, __entry->blkoff,
+		      __entry->tailroom, __entry->tail, __entry->end, __entry->head,
+		      __entry->head_pg_addr, __entry->pg0addr, __entry->pg0addr + __entry->pg0off,
+		      __entry->pg0off)
+	)
+
+DECLARE_EVENT_CLASS(iptfs_ingress_preq_event,
+		    TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs,
+			     u32 pmtu, u8 was_gso),
+		    TP_ARGS(skb, xtfs, pmtu, was_gso),
+		    TP_STRUCT__entry(__field(struct sk_buff *, skb)
+				     __field(u32, skb_len)
+				     __field(u32, data_len)
+				     __field(u32, pmtu)
+				     __field(u32, queue_size)
+				     __field(u32, proto_seq)
+				     __field(u8, proto)
+				     __field(u8, was_gso)
+			    ),
+		    TP_fast_assign(__entry->skb = skb;
+				   __entry->skb_len = skb->len;
+				   __entry->data_len = skb->data_len;
+				   __entry->queue_size =
+					xtfs->cfg.max_queue_size - xtfs->queue_size;
+				   __entry->proto = __trace_ip_proto(ip_hdr(skb));
+				   __entry->proto_seq = __trace_ip_proto_seq(ip_hdr(skb));
+				   __entry->pmtu = pmtu;
+				   __entry->was_gso = was_gso;
+			    ),
+		    TP_printk("INGRPREQ: skb=%p len=%u data_len=%u qsize=%u proto=%u proto_seq=%u pmtu=%u was_gso=%u",
+			      __entry->skb, __entry->skb_len, __entry->data_len,
+			      __entry->queue_size, __entry->proto, __entry->proto_seq,
+			      __entry->pmtu, __entry->was_gso));
+
+DEFINE_EVENT(iptfs_ingress_preq_event, iptfs_enqueue,
+	     TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, u32 pmtu, u8 was_gso),
+	     TP_ARGS(skb, xtfs, pmtu, was_gso));
+
+DEFINE_EVENT(iptfs_ingress_preq_event, iptfs_no_queue_space,
+	     TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, u32 pmtu, u8 was_gso),
+	     TP_ARGS(skb, xtfs, pmtu, was_gso));
+
+DEFINE_EVENT(iptfs_ingress_preq_event, iptfs_too_big,
+	     TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, u32 pmtu, u8 was_gso),
+	     TP_ARGS(skb, xtfs, pmtu, was_gso));
+
+DECLARE_EVENT_CLASS(iptfs_ingress_postq_event,
+		    TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff, struct iphdr *iph),
+		    TP_ARGS(skb, mtu, blkoff, iph),
+		    TP_STRUCT__entry(__field(struct sk_buff *, skb)
+				     __field(u32, skb_len)
+				     __field(u32, data_len)
+				     __field(u32, mtu)
+				     __field(u32, proto_seq)
+				     __field(u16, blkoff)
+				     __field(u8, proto)),
+		    TP_fast_assign(__entry->skb = skb;
+				   __entry->skb_len = skb->len;
+				   __entry->data_len = skb->data_len;
+				   __entry->mtu = mtu;
+				   __entry->blkoff = blkoff;
+				   __entry->proto = iph ? __trace_ip_proto(iph) : 0;
+				   __entry->proto_seq = iph ? __trace_ip_proto_seq(iph) : 0;
+			    ),
+		    TP_printk("INGRPSTQ: skb=%p len=%u data_len=%u mtu=%u blkoff=%u proto=%u proto_seq=%u",
+			      __entry->skb, __entry->skb_len, __entry->data_len, __entry->mtu,
+			      __entry->blkoff, __entry->proto, __entry->proto_seq));
+
+DEFINE_EVENT(iptfs_ingress_postq_event, iptfs_first_dequeue,
+	     TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff,
+		      struct iphdr *iph),
+	     TP_ARGS(skb, mtu, blkoff, iph));
+
+DEFINE_EVENT(iptfs_ingress_postq_event, iptfs_first_fragmenting,
+	     TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff,
+		      struct iphdr *iph),
+	     TP_ARGS(skb, mtu, blkoff, iph));
+
+DEFINE_EVENT(iptfs_ingress_postq_event, iptfs_first_final_fragment,
+	     TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff,
+		      struct iphdr *iph),
+	     TP_ARGS(skb, mtu, blkoff, iph));
+
+DEFINE_EVENT(iptfs_ingress_postq_event, iptfs_first_toobig,
+	     TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff,
+		      struct iphdr *iph),
+	     TP_ARGS(skb, mtu, blkoff, iph));
+
+TRACE_EVENT(iptfs_ingress_nth_peek,
+	    TP_PROTO(struct sk_buff *skb, u32 remaining),
+	    TP_ARGS(skb, remaining),
+	    TP_STRUCT__entry(__field(struct sk_buff *, skb)
+			     __field(u32, skb_len)
+			     __field(u32, remaining)),
+	    TP_fast_assign(__entry->skb = skb;
+			   __entry->skb_len = skb->len;
+			   __entry->remaining = remaining;
+		    ),
+	    TP_printk("INGRPSTQ: NTHPEEK: skb=%p len=%u remaining=%u",
+		      __entry->skb, __entry->skb_len, __entry->remaining));
+
+TRACE_EVENT(iptfs_ingress_nth_add, TP_PROTO(struct sk_buff *skb, u8 share_ok),
+	    TP_ARGS(skb, share_ok),
+	    TP_STRUCT__entry(__field(struct sk_buff *, skb)
+			     __field(u32, skb_len)
+			     __field(u32, data_len)
+			     __field(u8, share_ok)
+			     __field(u8, head_frag)
+			     __field(u8, pp_recycle)
+			     __field(u8, cloned)
+			     __field(u8, shared)
+			     __field(u8, nr_frags)
+			     __field(u8, frag_list)
+		    ),
+	    TP_fast_assign(__entry->skb = skb;
+			   __entry->skb_len = skb->len;
+			   __entry->data_len = skb->data_len;
+			   __entry->share_ok = share_ok;
+			   __entry->head_frag = skb->head_frag;
+			   __entry->pp_recycle = skb->pp_recycle;
+			   __entry->cloned = skb_cloned(skb);
+			   __entry->shared = skb_shared(skb);
+			   __entry->nr_frags = skb_shinfo(skb)->nr_frags;
+			   __entry->frag_list = (bool)skb_shinfo(skb)->frag_list;
+		    ),
+	    TP_printk("INGRPSTQ: NTHADD: skb=%p len=%u data_len=%u share_ok=%u head_frag=%u pp_recycle=%u cloned=%u shared=%u nr_frags=%u frag_list=%u",
+		      __entry->skb, __entry->skb_len, __entry->data_len, __entry->share_ok,
+		      __entry->head_frag, __entry->pp_recycle, __entry->cloned, __entry->shared,
+		      __entry->nr_frags, __entry->frag_list));
+
+DECLARE_EVENT_CLASS(iptfs_timer_event,
+		    TP_PROTO(struct xfrm_iptfs_data *xtfs, u64 time_val),
+		    TP_ARGS(xtfs, time_val),
+		    TP_STRUCT__entry(__field(u64, time_val)
+				     __field(u64, set_time)),
+		    TP_fast_assign(__entry->time_val = time_val;
+				   __entry->set_time = xtfs->iptfs_settime;
+			    ),
+		    TP_printk("TIMER: set_time=%llu time_val=%llu",
+			      __entry->set_time, __entry->time_val));
+
+DEFINE_EVENT(iptfs_timer_event, iptfs_timer_start,
+	     TP_PROTO(struct xfrm_iptfs_data *xtfs, u64 time_val),
+	     TP_ARGS(xtfs, time_val));
+
+DEFINE_EVENT(iptfs_timer_event, iptfs_timer_expire,
+	     TP_PROTO(struct xfrm_iptfs_data *xtfs, u64 time_val),
+	     TP_ARGS(xtfs, time_val));
+
+#endif /* _TRACE_IPTFS_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../net/xfrm
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace_iptfs
+#include <trace/define_trace.h>

linux-7.2.3/net/xfrm/xfrm_algo.c

@@ -0,0 +1,841 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * xfrm algorithm interface
+ *
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ */
+
+#include <crypto/acompress.h>
+#include <crypto/aead.h>
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/pfkeyv2.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 = "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 {
+	int (*find)(const char *name, u32 type, u32 mask);
+	struct xfrm_algo_desc *algs;
+	int entries;
+};
+
+static const struct xfrm_algo_list xfrm_aead_list = {
+	.find = crypto_has_aead,
+	.algs = aead_list,
+	.entries = ARRAY_SIZE(aead_list),
+};
+
+static const struct xfrm_algo_list xfrm_aalg_list = {
+	.find = crypto_has_ahash,
+	.algs = aalg_list,
+	.entries = ARRAY_SIZE(aalg_list),
+};
+
+static const struct xfrm_algo_list xfrm_ealg_list = {
+	.find = crypto_has_skcipher,
+	.algs = ealg_list,
+	.entries = ARRAY_SIZE(ealg_list),
+};
+
+static const struct xfrm_algo_list xfrm_calg_list = {
+	.find = crypto_has_acomp,
+	.algs = calg_list,
+	.entries = ARRAY_SIZE(calg_list),
+};
+
+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 = algo_list->find(list[i].name, 0, 0);
+		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_acomp(calg_list[i].name, 0, 0);
+		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_DESCRIPTION("XFRM Algorithm interface");
+MODULE_LICENSE("GPL");

linux-7.2.3/net/xfrm/xfrm_compat.c

@@ -0,0 +1,691 @@
+// 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),
+	[XFRM_MSG_MIGRATE_STATE  - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_migrate_state),
+};
+
+static const struct nla_policy compat_policy[XFRMA_MAX+1] = {
+	[XFRMA_UNSPEC]          = { .strict_start_type = XFRMA_SA_DIR },
+	[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 },
+	[XFRMA_SA_DIR]          = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT),
+	[XFRMA_NAT_KEEPALIVE_INTERVAL]	= { .type = NLA_U32 },
+	[XFRMA_SA_PCPU]		= { .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_MIGRATE_STATE:
+	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:
+	case XFRMA_SA_DIR:
+	case XFRMA_NAT_KEEPALIVE_INTERVAL:
+	case XFRMA_SA_PCPU:
+	case XFRMA_IPTFS_DROP_TIME:
+	case XFRMA_IPTFS_REORDER_WINDOW:
+	case XFRMA_IPTFS_DONT_FRAG:
+	case XFRMA_IPTFS_INIT_DELAY:
+	case XFRMA_IPTFS_MAX_QSIZE:
+	case XFRMA_IPTFS_PKT_SIZE:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	default:
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IPTFS_PKT_SIZE);
+		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_IPTFS_PKT_SIZE);
+		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_MIGRATE_STATE:
+	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");

linux-7.2.3/net/xfrm/xfrm_device.c

@@ -0,0 +1,591 @@
+// 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 - x->props.enc_hdr_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_IPTFS:
+	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;
+	}
+
+	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 ERR_PTR(-EINPROGRESS);
+
+			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;
+	}
+
+	/* skb_gso_segment() set skb->prev to the last segment, but async
+	 * crypto may have stolen it above without updating ->prev.  Repoint
+	 * it at the last retained segment so validate_xmit_skb_list() does
+	 * not chain onto a segment now owned by the crypto engine.
+	 */
+	if (skb)
+		skb->prev = pskb;
+
+	return skb ? skb : ERR_PTR(-EINPROGRESS);
+}
+EXPORT_SYMBOL_GPL(validate_xmit_xfrm);
+
+int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
+		       const 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 (xuo->flags &
+	    ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) {
+		NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request");
+		return -EINVAL;
+	}
+
+	if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) ||
+	    (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) {
+		NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction");
+		return -EINVAL;
+	}
+
+	if (xuo->flags & XFRM_OFFLOAD_INBOUND && x->if_id) {
+		NL_SET_ERR_MSG(extack, "XFRM if_id is not supported in RX path");
+		return -EINVAL;
+	}
+
+	is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET;
+
+	/* We don't yet support TFC padding. */
+	if (x->tfcpad) {
+		NL_SET_ERR_MSG(extack, "TFC padding can't be offloaded");
+		return -EINVAL;
+	}
+
+	dev = dev_get_by_index(net, xuo->ifindex);
+	if (!dev) {
+		struct xfrm_dst_lookup_params params;
+
+		if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) {
+			saddr = &x->props.saddr;
+			daddr = &x->id.daddr;
+		} else {
+			saddr = &x->id.daddr;
+			daddr = &x->props.saddr;
+		}
+
+		memset(&params, 0, sizeof(params));
+		params.net = net;
+		params.saddr = saddr;
+		params.daddr = daddr;
+		params.mark = xfrm_smark_get(0, x);
+		dst = __xfrm_dst_lookup(x->props.family, &params);
+		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;
+	}
+
+	if (!x->type_offload) {
+		NL_SET_ERR_MSG(extack, "Type doesn't support offload");
+		dev_put(dev);
+		return -EINVAL;
+	}
+
+	xso->dev = dev;
+	xso->ifindex = dev->ifindex;
+	netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC);
+
+	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(dev, x, extack);
+	if (err) {
+		xso->dev = NULL;
+		xso->dir = 0;
+		netdev_put(dev, &xso->dev_tracker);
+		xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+
+		xfrm_unset_type_offload(x);
+		/* 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.
+		 */
+		if ((err != -EOPNOTSUPP && !is_packet_offload) || 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->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->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;
+	bool check_tunnel_size;
+
+	if (!x->type_offload ||
+	    (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap))
+		return false;
+
+	if ((!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)
+		return true;
+
+	check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET &&
+			    x->props.mode == XFRM_MODE_TUNNEL;
+	switch (skb_dst(skb)->ops->family) {
+	case AF_INET:
+		/* Check for IPv4 options */
+		if (ip_hdr(skb)->ihl != 5)
+			return false;
+		if (check_tunnel_size && xfrm4_tunnel_check_size(skb))
+			return false;
+		break;
+	case AF_INET6:
+		/* Check for IPv6 extensions */
+		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
+			return false;
+		if (check_tunnel_size && xfrm6_tunnel_check_size(skb))
+			return false;
+		break;
+	default:
+		break;
+	}
+
+	if (dev->xfrmdev_ops->xdo_dev_offload_ok)
+		return 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_unregister(struct net_device *dev)
+{
+	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:
+		return xfrm_dev_down(dev);
+
+	case NETDEV_UNREGISTER:
+		return xfrm_dev_unregister(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);
+}

linux-7.2.3/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));
+}

linux-7.2.3/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 */

linux-7.2.3/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

linux-7.2.3/net/xfrm/xfrm_input.c

@@ -0,0 +1,869 @@
+// 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 <net/hotdata.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])) {
+		const struct xfrm_input_afinfo *cur;
+
+		cur = rcu_access_pointer(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family]);
+		if (unlikely(cur != 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)
+{
+	struct xfrm_offload *xo = xfrm_offload(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);
+		if (xo)
+			xo->orig_mac_len =
+				skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0;
+		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)
+	struct xfrm_offload *xo = xfrm_offload(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);
+		if (xo)
+			xo->orig_mac_len =
+				skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0;
+		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:
+		if (x->mode_cbs && x->mode_cbs->input)
+			return x->mode_cbs->input(x, skb);
+
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+/* NOTE: encap_type - In addition to the normal (non-negative) values for
+ * encap_type, a negative value of -1 or -2 can be used to resume/restart this
+ * function after a previous invocation early terminated for async operation.
+ */
+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);
+	struct net_device *dev = 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 || (xo && (xo->flags & XFRM_GRO || encap_type == 0 ||
+				      encap_type == UDP_ENCAP_ESPINUDP))) {
+		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(dev);
+			goto drop;
+		}
+
+		family = x->props.family;
+
+		/* An encap_type of -2 indicates reconstructed inner packet */
+		if (encap_type == -2)
+			goto resume_decapped;
+
+		/* An encap_type of -1 indicates async resumption. */
+		if (encap_type == -1) {
+			async = 1;
+			seq = XFRM_SKB_CB(skb)->seq.input.low;
+			spin_lock(&x->lock);
+			goto resume;
+		}
+		/* GRO call */
+		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;
+			}
+
+			nexthdr = x->type_offload->input_tail(x, skb);
+		}
+
+		goto process;
+	}
+
+	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_input_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;
+		}
+
+		if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) {
+			secpath_reset(skb);
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR);
+			xfrm_audit_state_notfound(skb, family, spi, seq);
+			xfrm_state_put(x);
+			x = NULL;
+			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;
+		}
+
+process:
+		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;
+
+		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;
+		}
+
+		if (xfrm_tunnel_check(skb, x, family)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
+			goto drop_unlock;
+		}
+
+		if (!crypto_done) {
+			spin_unlock(&x->lock);
+			dev_hold(dev);
+
+			nexthdr = x->type->input(x, skb);
+			if (nexthdr == -EINPROGRESS) {
+				if (async)
+					dev_put(dev);
+				return 0;
+			}
+
+			dev_put(dev);
+			spin_lock(&x->lock);
+		}
+resume:
+		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 (!crypto_done && 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;
+
+		err = xfrm_inner_mode_input(x, skb);
+		if (err == -EINPROGRESS) {
+			if (async)
+				dev_put(dev);
+			return 0;
+		} else if (err) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
+			goto drop;
+		}
+resume_decapped:
+		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);
+
+	rcu_read_lock();
+	err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
+	if (err) {
+		rcu_read_unlock();
+		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);
+		if (async)
+			dev_put(dev);
+		gro_cells_receive(&gro_cells, skb);
+		rcu_read_unlock();
+		return 0;
+	} else {
+		xo = xfrm_offload(skb);
+		if (xo)
+			xfrm_gro = xo->flags & XFRM_GRO;
+
+		err = -EAFNOSUPPORT;
+		afinfo = xfrm_state_afinfo_get_rcu(x->props.family);
+		if (likely(afinfo))
+			err = afinfo->transport_finish(skb, xfrm_gro || async);
+		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);
+		}
+
+		if (async)
+			dev_put(dev);
+		rcu_read_unlock();
+		return err;
+	}
+
+drop_unlock:
+	spin_unlock(&x->lock);
+drop:
+	if (async)
+		dev_put(dev);
+	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))) {
+		struct net *net = XFRM_TRANS_SKB_CB(skb)->net;
+
+		XFRM_TRANS_SKB_CB(skb)->finish(net, NULL, skb);
+		put_net(net);
+	}
+	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;
+	struct net *hold_net;
+
+	trans = this_cpu_ptr(&xfrm_trans_tasklet);
+
+	if (skb_queue_len(&trans->queue) >= READ_ONCE(net_hotdata.max_backlog))
+		return -ENOBUFS;
+
+	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
+
+	hold_net = maybe_get_net(net);
+	if (!hold_net)
+		return -ENODEV;
+
+	XFRM_TRANS_SKB_CB(skb)->finish = finish;
+	XFRM_TRANS_SKB_CB(skb)->net = hold_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;
+
+	xfrm_napi_dev = alloc_netdev_dummy(0);
+	if (!xfrm_napi_dev)
+		panic("Failed to allocate XFRM dummy netdev\n");
+
+	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);
+	}
+}

linux-7.2.3/net/xfrm/xfrm_interface_bpf.c

@@ -0,0 +1,110 @@
+// 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;
+};
+
+__bpf_kfunc_start_defs();
+
+/* 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;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(xfrm_ifc_kfunc_set)
+BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info)
+BTF_ID_FLAGS(func, bpf_skb_set_xfrm_info)
+BTF_KFUNCS_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);
+}

linux-7.2.3/net/xfrm/xfrm_ipcomp.c

@@ -0,0 +1,368 @@
+// 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) 2003-2025 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * Todo:
+ *   - Tunable compression parameters.
+ *   - Compression stats.
+ *   - Adaptive compression.
+ */
+
+#include <crypto/acompress.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/skbuff_ref.h>
+#include <linux/slab.h>
+#include <net/ipcomp.h>
+#include <net/xfrm.h>
+
+#define IPCOMP_SCRATCH_SIZE 65400
+
+struct ipcomp_skb_cb {
+	struct xfrm_skb_cb xfrm;
+	struct acomp_req *req;
+};
+
+struct ipcomp_data {
+	u16 threshold;
+	struct crypto_acomp *tfm;
+};
+
+struct ipcomp_req_extra {
+	struct xfrm_state *x;
+	struct scatterlist sg[];
+};
+
+static inline struct ipcomp_skb_cb *ipcomp_cb(struct sk_buff *skb)
+{
+	struct ipcomp_skb_cb *cb = (void *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(*cb) > sizeof(skb->cb));
+	return cb;
+}
+
+static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
+{
+	struct acomp_req *req = ipcomp_cb(skb)->req;
+	struct ipcomp_req_extra *extra;
+	struct scatterlist *dsg;
+	int len, dlen;
+
+	if (unlikely(!req))
+		return err;
+
+	extra = acomp_request_extra(req);
+	dsg = extra->sg;
+
+	if (unlikely(err))
+		goto out_free_req;
+
+	dlen = req->dlen;
+
+	pskb_trim_unique(skb, 0);
+	__skb_put(skb, hlen);
+
+	/* Only update truesize on input. */
+	if (!hlen)
+		skb->truesize += dlen;
+	skb->data_len = dlen;
+	skb->len += dlen;
+
+	do {
+		skb_frag_t *frag;
+		struct page *page;
+
+		frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags;
+		page = sg_page(dsg);
+		dsg = sg_next(dsg);
+
+		len = PAGE_SIZE;
+		if (dlen < len)
+			len = dlen;
+
+		skb_frag_fill_page_desc(frag, page, 0, len);
+
+		skb_shinfo(skb)->nr_frags++;
+	} while ((dlen -= len));
+
+out_free_req:
+	for (; dsg && sg_page(dsg); dsg = sg_next(dsg))
+		__free_page(sg_page(dsg));
+
+	acomp_request_free(req);
+	return err;
+}
+
+static int ipcomp_input_done2(struct sk_buff *skb, int err)
+{
+	struct ip_comp_hdr *ipch = ip_comp_hdr(skb);
+	const int plen = skb->len;
+
+	skb->transport_header = skb->network_header + sizeof(*ipch);
+
+	return ipcomp_post_acomp(skb, err, 0) ?:
+	       skb->len < (plen + sizeof(ip_comp_hdr)) ? -EINVAL :
+	       ipch->nexthdr;
+}
+
+static void ipcomp_input_done(void *data, int err)
+{
+	struct sk_buff *skb = data;
+
+	xfrm_input_resume(skb, ipcomp_input_done2(skb, err));
+}
+
+static struct acomp_req *ipcomp_setup_req(struct xfrm_state *x,
+					  struct sk_buff *skb, int minhead,
+					  int dlen)
+{
+	const int dnfrags = min(MAX_SKB_FRAGS, 16);
+	struct ipcomp_data *ipcd = x->data;
+	struct ipcomp_req_extra *extra;
+	struct scatterlist *sg, *dsg;
+	const int plen = skb->len;
+	struct crypto_acomp *tfm;
+	struct acomp_req *req;
+	int nfrags;
+	int total;
+	int err;
+	int i;
+
+	ipcomp_cb(skb)->req = NULL;
+
+	do {
+		struct sk_buff *trailer;
+
+		if (skb->len > PAGE_SIZE) {
+			if (skb_linearize_cow(skb))
+				return ERR_PTR(-ENOMEM);
+			nfrags = 1;
+			break;
+		}
+
+		if (!skb_cloned(skb) && skb_headlen(skb) >= minhead) {
+			if (!skb_is_nonlinear(skb)) {
+				nfrags = 1;
+				break;
+			} else if (!skb_has_frag_list(skb)) {
+				nfrags = skb_shinfo(skb)->nr_frags;
+				nfrags++;
+				break;
+			}
+		}
+
+		nfrags = skb_cow_data(skb, skb_headlen(skb) < minhead ?
+					   minhead - skb_headlen(skb) : 0,
+				      &trailer);
+		if (nfrags < 0)
+			return ERR_PTR(nfrags);
+	} while (0);
+
+	tfm = ipcd->tfm;
+	req = acomp_request_alloc_extra(
+		tfm, sizeof(*extra) + sizeof(*sg) * (nfrags + dnfrags),
+		GFP_ATOMIC);
+	ipcomp_cb(skb)->req = req;
+	if (!req)
+		return ERR_PTR(-ENOMEM);
+
+	extra = acomp_request_extra(req);
+	extra->x = x;
+
+	dsg = extra->sg;
+	sg = dsg + dnfrags;
+	sg_init_table(sg, nfrags);
+	err = skb_to_sgvec(skb, sg, 0, plen);
+	if (unlikely(err < 0))
+		return ERR_PTR(err);
+
+	sg_init_table(dsg, dnfrags);
+	total = 0;
+	for (i = 0; i < dnfrags && total < dlen; i++) {
+		struct page *page;
+
+		page = alloc_page(GFP_ATOMIC);
+		if (!page)
+			break;
+		sg_set_page(dsg + i, page, PAGE_SIZE, 0);
+		total += PAGE_SIZE;
+	}
+	if (!i)
+		return ERR_PTR(-ENOMEM);
+	sg_mark_end(dsg + i - 1);
+	dlen = min(dlen, total);
+
+	acomp_request_set_params(req, sg, dsg, plen, dlen);
+
+	return req;
+}
+
+static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct acomp_req *req;
+	int err;
+
+	req = ipcomp_setup_req(x, skb, 0, IPCOMP_SCRATCH_SIZE);
+	err = PTR_ERR(req);
+	if (IS_ERR(req))
+		goto out;
+
+	acomp_request_set_callback(req, 0, ipcomp_input_done, skb);
+	err = crypto_acomp_decompress(req);
+	if (err == -EINPROGRESS)
+		return err;
+
+out:
+	return ipcomp_input_done2(skb, err);
+}
+
+int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ip_comp_hdr *ipch __maybe_unused;
+
+	if (!pskb_may_pull(skb, sizeof(*ipch)))
+		return -EINVAL;
+
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* Remove ipcomp header and decompress original payload */
+	__skb_pull(skb, sizeof(*ipch));
+
+	return ipcomp_decompress(x, skb);
+}
+EXPORT_SYMBOL_GPL(ipcomp_input);
+
+static int ipcomp_output_push(struct sk_buff *skb)
+{
+	skb_push(skb, -skb_network_offset(skb));
+	return 0;
+}
+
+static int ipcomp_output_done2(struct xfrm_state *x, struct sk_buff *skb,
+			       int err)
+{
+	struct ip_comp_hdr *ipch;
+
+	err = ipcomp_post_acomp(skb, err, sizeof(*ipch));
+	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:
+	return ipcomp_output_push(skb);
+}
+
+static void ipcomp_output_done(void *data, int err)
+{
+	struct ipcomp_req_extra *extra;
+	struct sk_buff *skb = data;
+	struct acomp_req *req;
+
+	req = ipcomp_cb(skb)->req;
+	extra = acomp_request_extra(req);
+
+	xfrm_output_resume(skb_to_full_sk(skb), skb,
+			   ipcomp_output_done2(extra->x, skb, err));
+}
+
+static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ip_comp_hdr *ipch __maybe_unused;
+	struct acomp_req *req;
+	int err;
+
+	req = ipcomp_setup_req(x, skb, sizeof(*ipch),
+			       skb->len - sizeof(*ipch));
+	err = PTR_ERR(req);
+	if (IS_ERR(req))
+		goto out;
+
+	acomp_request_set_callback(req, 0, ipcomp_output_done, skb);
+	err = crypto_acomp_compress(req);
+	if (err == -EINPROGRESS)
+		return err;
+
+out:
+	return ipcomp_output_done2(x, skb, err);
+}
+
+int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ipcomp_data *ipcd = x->data;
+
+	if (skb->len < ipcd->threshold) {
+		/* Don't bother compressing */
+		return ipcomp_output_push(skb);
+	}
+
+	return ipcomp_compress(x, skb);
+}
+EXPORT_SYMBOL_GPL(ipcomp_output);
+
+static void ipcomp_free_data(struct ipcomp_data *ipcd)
+{
+	crypto_free_acomp(ipcd->tfm);
+}
+
+void ipcomp_destroy(struct xfrm_state *x)
+{
+	struct ipcomp_data *ipcd = x->data;
+	if (!ipcd)
+		return;
+	ipcomp_free_data(ipcd);
+	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_obj(*ipcd);
+	if (!ipcd)
+		goto out;
+
+	ipcd->tfm = crypto_alloc_acomp(x->calg->alg_name, 0, 0);
+	if (IS_ERR(ipcd->tfm))
+		goto error;
+
+	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);
+	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>");

linux-7.2.3/net/xfrm/xfrm_nat_keepalive.c

@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * xfrm_nat_keepalive.c
+ *
+ * (c) 2024 Eyal Birger <eyal.birger@gmail.com>
+ */
+
+#include <net/inet_common.h>
+#include <net/ip6_checksum.h>
+#include <net/xfrm.h>
+
+static DEFINE_PER_CPU(struct sock_bh_locked, nat_keepalive_sk_ipv4) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
+#if IS_ENABLED(CONFIG_IPV6)
+static DEFINE_PER_CPU(struct sock_bh_locked, nat_keepalive_sk_ipv6) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
+#endif
+
+struct nat_keepalive {
+	struct net *net;
+	u16 family;
+	xfrm_address_t saddr;
+	xfrm_address_t daddr;
+	__be16 encap_sport;
+	__be16 encap_dport;
+	__u32 smark;
+};
+
+static void nat_keepalive_init(struct nat_keepalive *ka, struct xfrm_state *x)
+{
+	ka->net = xs_net(x);
+	ka->family = x->props.family;
+	ka->saddr = x->props.saddr;
+	ka->daddr = x->id.daddr;
+	ka->encap_sport = x->encap->encap_sport;
+	ka->encap_dport = x->encap->encap_dport;
+	ka->smark = xfrm_smark_get(0, x);
+}
+
+static int nat_keepalive_send_ipv4(struct sk_buff *skb,
+				   struct nat_keepalive *ka)
+{
+	struct net *net = ka->net;
+	struct flowi4 fl4;
+	struct rtable *rt;
+	struct sock *sk;
+	__u8 tos = 0;
+	int err;
+
+	flowi4_init_output(&fl4, 0 /* oif */, skb->mark, tos,
+			   RT_SCOPE_UNIVERSE, IPPROTO_UDP, 0,
+			   ka->daddr.a4, ka->saddr.a4, ka->encap_dport,
+			   ka->encap_sport, sock_net_uid(net, NULL));
+
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR(rt)) {
+		kfree_skb(skb);
+		return PTR_ERR(rt);
+	}
+
+	skb_dst_set(skb, &rt->dst);
+
+	local_lock_nested_bh(&nat_keepalive_sk_ipv4.bh_lock);
+	sk = this_cpu_read(nat_keepalive_sk_ipv4.sock);
+	sock_net_set(sk, net);
+	err = ip_build_and_send_pkt(skb, sk, fl4.saddr, fl4.daddr, NULL, tos);
+	sock_net_set(sk, &init_net);
+	local_unlock_nested_bh(&nat_keepalive_sk_ipv4.bh_lock);
+	return err;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int nat_keepalive_send_ipv6(struct sk_buff *skb,
+				   struct nat_keepalive *ka,
+				   struct udphdr *uh)
+{
+	struct net *net = ka->net;
+	struct dst_entry *dst;
+	struct flowi6 fl6;
+	struct sock *sk;
+	__wsum csum;
+	int err;
+
+	csum = skb_checksum(skb, 0, skb->len, 0);
+	uh->check = csum_ipv6_magic(&ka->saddr.in6, &ka->daddr.in6,
+				    skb->len, IPPROTO_UDP, csum);
+	if (uh->check == 0)
+		uh->check = CSUM_MANGLED_0;
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_mark = skb->mark;
+	fl6.saddr = ka->saddr.in6;
+	fl6.daddr = ka->daddr.in6;
+	fl6.flowi6_proto = IPPROTO_UDP;
+	fl6.fl6_sport = ka->encap_sport;
+	fl6.fl6_dport = ka->encap_dport;
+
+	local_lock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
+	sk = this_cpu_read(nat_keepalive_sk_ipv6.sock);
+	sock_net_set(sk, net);
+	dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL);
+	if (IS_ERR(dst)) {
+		local_unlock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
+		kfree_skb(skb);
+		return PTR_ERR(dst);
+	}
+
+	skb_dst_set(skb, dst);
+	err = ip6_xmit(sk, skb, &fl6, skb->mark, NULL, 0, 0);
+	sock_net_set(sk, &init_net);
+	local_unlock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
+	return err;
+}
+#endif
+
+static void nat_keepalive_send(struct nat_keepalive *ka)
+{
+	const int nat_ka_hdrs_len = max(sizeof(struct iphdr),
+					sizeof(struct ipv6hdr)) +
+				    sizeof(struct udphdr);
+	const u8 nat_ka_payload = 0xFF;
+	struct sk_buff *skb;
+	struct udphdr *uh;
+
+	skb = alloc_skb(nat_ka_hdrs_len + sizeof(nat_ka_payload), GFP_ATOMIC);
+	if (unlikely(!skb))
+		return;
+
+	skb_reserve(skb, nat_ka_hdrs_len);
+
+	skb_put_u8(skb, nat_ka_payload);
+
+	uh = skb_push(skb, sizeof(*uh));
+	uh->source = ka->encap_sport;
+	uh->dest = ka->encap_dport;
+	uh->len = htons(skb->len);
+	uh->check = 0;
+
+	skb->mark = ka->smark;
+
+	switch (ka->family) {
+	case AF_INET:
+		nat_keepalive_send_ipv4(skb, ka);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		nat_keepalive_send_ipv6(skb, ka, uh);
+		break;
+#endif
+	default:
+		kfree_skb(skb);
+		break;
+	}
+}
+
+enum {
+	NAT_KEEPALIVE_BATCH_SIZE = 16,
+	NAT_KEEPALIVE_BATCH_FULL = 1,
+};
+
+struct nat_keepalive_work_ctx {
+	struct xfrm_state *batch[NAT_KEEPALIVE_BATCH_SIZE];
+	unsigned int nr;
+	time64_t next_run;
+	time64_t now;
+};
+
+static int nat_keepalive_work_collect(struct xfrm_state *x, int count, void *ptr)
+{
+	struct nat_keepalive_work_ctx *ctx = ptr;
+
+	if (!READ_ONCE(x->nat_keepalive_interval))
+		return 0;
+
+	if (ctx->nr == ARRAY_SIZE(ctx->batch))
+		return NAT_KEEPALIVE_BATCH_FULL;
+
+	xfrm_state_hold(x);
+	ctx->batch[ctx->nr++] = x;
+	return 0;
+}
+
+static void nat_keepalive_work_single(struct xfrm_state *x,
+				      struct nat_keepalive_work_ctx *ctx)
+{
+	bool send_keepalive = false;
+	struct nat_keepalive ka;
+	time64_t next_run = 0;
+	u32 interval;
+	int delta;
+
+	spin_lock_bh(&x->lock);
+
+	if (x->km.state == XFRM_STATE_DEAD)
+		goto out;
+
+	interval = x->nat_keepalive_interval;
+	if (!interval)
+		goto out;
+
+	delta = (int)(ctx->now - x->lastused);
+	if (delta < interval) {
+		x->nat_keepalive_expiration = ctx->now + interval - delta;
+		next_run = x->nat_keepalive_expiration;
+	} else if (x->nat_keepalive_expiration > ctx->now) {
+		next_run = x->nat_keepalive_expiration;
+	} else {
+		next_run = ctx->now + interval;
+		nat_keepalive_init(&ka, x);
+		send_keepalive = true;
+	}
+
+out:
+	spin_unlock_bh(&x->lock);
+
+	if (send_keepalive)
+		nat_keepalive_send(&ka);
+
+	if (next_run && (!ctx->next_run || next_run < ctx->next_run))
+		ctx->next_run = next_run;
+}
+
+static void nat_keepalive_work(struct work_struct *work)
+{
+	struct nat_keepalive_work_ctx ctx;
+	struct xfrm_state_walk walk;
+	struct net *net;
+	int err, i;
+
+	ctx.next_run = 0;
+	ctx.now = ktime_get_real_seconds();
+
+	net = container_of(work, struct net, xfrm.nat_keepalive_work.work);
+	xfrm_state_walk_init(&walk, IPPROTO_ESP, NULL);
+	do {
+		ctx.nr = 0;
+		err = xfrm_state_walk(net, &walk, nat_keepalive_work_collect, &ctx);
+		local_bh_disable();
+		for (i = 0; i < ctx.nr; i++) {
+			nat_keepalive_work_single(ctx.batch[i], &ctx);
+			xfrm_state_put(ctx.batch[i]);
+		}
+		local_bh_enable();
+	} while (err == NAT_KEEPALIVE_BATCH_FULL);
+	xfrm_state_walk_done(&walk, net);
+	if (ctx.next_run)
+		schedule_delayed_work(&net->xfrm.nat_keepalive_work,
+				      (ctx.next_run - ctx.now) * HZ);
+}
+
+static int nat_keepalive_sk_init(struct sock_bh_locked __percpu *socks,
+				 unsigned short family)
+{
+	struct sock *sk;
+	int err, i;
+
+	for_each_possible_cpu(i) {
+		err = inet_ctl_sock_create(&sk, family, SOCK_RAW, IPPROTO_UDP,
+					   &init_net);
+		if (err < 0)
+			goto err;
+
+		per_cpu_ptr(socks, i)->sock = sk;
+	}
+
+	return 0;
+err:
+	for_each_possible_cpu(i)
+		inet_ctl_sock_destroy(per_cpu_ptr(socks, i)->sock);
+	return err;
+}
+
+static void nat_keepalive_sk_fini(struct sock_bh_locked __percpu *socks)
+{
+	int i;
+
+	for_each_possible_cpu(i)
+		inet_ctl_sock_destroy(per_cpu_ptr(socks, i)->sock);
+}
+
+void xfrm_nat_keepalive_state_updated(struct xfrm_state *x)
+{
+	struct net *net;
+
+	if (!x->nat_keepalive_interval)
+		return;
+
+	net = xs_net(x);
+	schedule_delayed_work(&net->xfrm.nat_keepalive_work, 0);
+}
+
+int __net_init xfrm_nat_keepalive_net_init(struct net *net)
+{
+	INIT_DELAYED_WORK(&net->xfrm.nat_keepalive_work, nat_keepalive_work);
+	return 0;
+}
+
+int xfrm_nat_keepalive_net_fini(struct net *net)
+{
+	disable_delayed_work_sync(&net->xfrm.nat_keepalive_work);
+	return 0;
+}
+
+int xfrm_nat_keepalive_init(unsigned short family)
+{
+	int err = -EAFNOSUPPORT;
+
+	switch (family) {
+	case AF_INET:
+		err = nat_keepalive_sk_init(&nat_keepalive_sk_ipv4, PF_INET);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		err = nat_keepalive_sk_init(&nat_keepalive_sk_ipv6, PF_INET6);
+		break;
+#endif
+	}
+
+	if (err)
+		pr_err("xfrm nat keepalive init: failed to init err:%d\n", err);
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_nat_keepalive_init);
+
+void xfrm_nat_keepalive_fini(unsigned short family)
+{
+	switch (family) {
+	case AF_INET:
+		nat_keepalive_sk_fini(&nat_keepalive_sk_ipv4);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		nat_keepalive_sk_fini(&nat_keepalive_sk_ipv6);
+		break;
+#endif
+	}
+}
+EXPORT_SYMBOL_GPL(xfrm_nat_keepalive_fini);

linux-7.2.3/net/xfrm/xfrm_output.c

@@ -0,0 +1,973 @@
+// 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>
+#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;
+
+	if (!skb->inner_protocol)
+		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);
+	if (!skb->inner_protocol)
+		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;
+
+	if (!skb->inner_protocol) {
+		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;
+
+	if (!skb->inner_protocol) {
+		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:
+		if (x->mode_cbs && x->mode_cbs->prepare_output)
+			return x->mode_cbs->prepare_output(x, skb);
+		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_dev_direct_output(struct sock *sk, struct xfrm_state *x,
+				  struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = xs_net(x);
+	int err;
+
+	dst = skb_dst_pop(skb);
+	if (!dst) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+		kfree_skb(skb);
+		return -EHOSTUNREACH;
+	}
+	skb_dst_set(skb, dst);
+	nf_reset_ct(skb);
+
+	err = skb_dst(skb)->ops->local_out(net, sk, skb);
+	if (unlikely(err != 1)) {
+		kfree_skb(skb);
+		return err;
+	}
+
+	/* In transport mode, network destination is
+	 * directly reachable, while in tunnel mode,
+	 * inner packet network may not be. In packet
+	 * offload type, HW is responsible for hard
+	 * header packet mangling so directly xmit skb
+	 * to netdevice.
+	 */
+	skb->dev = x->xso.dev;
+	__skb_push(skb, skb->dev->hard_header_len);
+	return dev_queue_xmit(skb);
+}
+
+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 (skb_dst(skb)->ops->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;
+	}
+	if (x->outer_mode.encap == XFRM_MODE_IPTFS) {
+		xo->inner_ipproto = IPPROTO_AGGFRAG;
+		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 family;
+	int err;
+
+	family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family
+		: skb_dst(skb)->ops->family;
+
+	switch (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;
+		}
+
+		/* Exclusive direct xmit for tunnel mode, as
+		 * some filtering or matching rules may apply
+		 * in transport mode.
+		 * Locally generated packets also require
+		 * the normal XFRM path for L2 header setup,
+		 * as the hardware needs the L2 header to match
+		 * for encryption, so skip direct output as well.
+		 */
+		if (x->props.mode == XFRM_MODE_TUNNEL && !skb->sk)
+			return xfrm_dev_direct_output(sk, x, skb);
+
+		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 && x->props.mode == XFRM_MODE_TUNNEL)
+				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);
+
+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 && sk_fullsock(skb->sk))
+			xfrm_local_error(skb, mtu);
+		else
+			icmp_send(skb, ICMP_DEST_UNREACH,
+				  ICMP_FRAG_NEEDED, htonl(mtu));
+		ret = -EMSGSIZE;
+	}
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xfrm4_tunnel_check_size);
+
+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)
+int xfrm6_tunnel_check_size(struct sk_buff *skb)
+{
+	int mtu, ret = 0;
+	struct dst_entry *dst = skb_dst(skb);
+	struct sock *sk = skb_to_full_sk(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(sk))
+			xfrm6_local_rxpmtu(skb, mtu);
+		else if (sk)
+			xfrm_local_error(skb, mtu);
+		else
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		ret = -EMSGSIZE;
+	}
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xfrm6_tunnel_check_size);
+#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);

linux-7.2.3/net/xfrm/xfrm_proc.c

@@ -0,0 +1,80 @@
+// 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_ITEM("XfrmOutStateDirError", LINUX_MIB_XFRMOUTSTATEDIRERROR),
+	SNMP_MIB_ITEM("XfrmInStateDirError", LINUX_MIB_XFRMINSTATEDIRERROR),
+	SNMP_MIB_ITEM("XfrmInIptfsError", LINUX_MIB_XFRMINIPTFSERROR),
+	SNMP_MIB_ITEM("XfrmOutNoQueueSpace", LINUX_MIB_XFRMOUTNOQSPACE),
+};
+
+static int xfrm_statistics_seq_show(struct seq_file *seq, void *v)
+{
+	unsigned long buff[ARRAY_SIZE(xfrm_mib_list)];
+	const int cnt = ARRAY_SIZE(xfrm_mib_list);
+	struct net *net = seq->private;
+	int i;
+
+	memset(buff, 0, sizeof(buff));
+
+	xfrm_state_update_stats(net);
+	snmp_get_cpu_field_batch_cnt(buff, xfrm_mib_list, cnt,
+				     net->mib.xfrm_statistics);
+	for (i = 0; i < cnt; 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);
+}

linux-7.2.3/net/xfrm/xfrm_replay.c

@@ -0,0 +1,799 @@
+// 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(oseq < replay_esn->oseq)) {
+			replay_esn->oseq_hi = ++oseq_hi;
+			if (xo->seq.low < replay_esn->oseq) {
+				XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
+				xo->seq.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;
+		xfrm_dev_state_advance_esn(x);
+
+		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 &&
+			    (!x->dir || x->dir == XFRM_SA_DIR_IN)) {
+				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);

linux-7.2.3/net/xfrm/xfrm_state_bpf.c

@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable XFRM state BPF helpers.
+ *
+ * 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.h>
+#include <linux/btf_ids.h>
+#include <net/xdp.h>
+#include <net/xfrm.h>
+
+/* bpf_xfrm_state_opts - Options for XFRM state lookup helpers
+ *
+ * Members:
+ * @error      - Out parameter, set for any errors encountered
+ *		 Values:
+ *		   -EINVAL - netns_id is less than -1
+ *		   -EINVAL - opts__sz isn't BPF_XFRM_STATE_OPTS_SZ
+ *		   -ENONET - No network namespace found for netns_id
+ *		   -ENOENT - No xfrm_state found
+ * @netns_id	- Specify the network namespace for lookup
+ *		 Values:
+ *		   BPF_F_CURRENT_NETNS (-1)
+ *		     Use namespace associated with ctx
+ *		   [0, S32_MAX]
+ *		     Network Namespace ID
+ * @mark	- XFRM mark to match on
+ * @daddr	- Destination address to match on
+ * @spi		- Security parameter index to match on
+ * @proto	- IP protocol to match on (eg. IPPROTO_ESP)
+ * @family	- Protocol family to match on (AF_INET/AF_INET6)
+ */
+struct bpf_xfrm_state_opts {
+	s32 error;
+	s32 netns_id;
+	u32 mark;
+	xfrm_address_t daddr;
+	__be32 spi;
+	u8 proto;
+	u16 family;
+};
+
+enum {
+	BPF_XFRM_STATE_OPTS_SZ = sizeof(struct bpf_xfrm_state_opts),
+};
+
+__bpf_kfunc_start_defs();
+
+/* bpf_xdp_get_xfrm_state - Get XFRM state
+ *
+ * A `struct xfrm_state *`, if found, must be released with a corresponding
+ * bpf_xdp_xfrm_state_release.
+ *
+ * Parameters:
+ * @ctx	- Pointer to ctx (xdp_md) in XDP program
+ *		    Cannot be NULL
+ * @opts	- Options for lookup (documented above)
+ *		    Cannot be NULL
+ * @opts__sz	- Length of the bpf_xfrm_state_opts structure
+ *		    Must be BPF_XFRM_STATE_OPTS_SZ
+ */
+__bpf_kfunc struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, u32 opts__sz)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+	struct net *net = dev_net(xdp->rxq->dev);
+	struct xfrm_state *x;
+
+	if (opts__sz < sizeof(opts->error))
+		return NULL;
+
+	if (opts__sz != BPF_XFRM_STATE_OPTS_SZ) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (opts->netns_id >= 0) {
+		net = get_net_ns_by_id(net, opts->netns_id);
+		if (unlikely(!net)) {
+			opts->error = -ENONET;
+			return NULL;
+		}
+	}
+
+	x = xfrm_state_lookup(net, opts->mark, &opts->daddr, opts->spi,
+			      opts->proto, opts->family);
+
+	if (opts->netns_id >= 0)
+		put_net(net);
+	if (!x)
+		opts->error = -ENOENT;
+
+	return x;
+}
+
+/* bpf_xdp_xfrm_state_release - Release acquired xfrm_state object
+ *
+ * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects
+ * the program if any references remain in the program in all of the explored
+ * states.
+ *
+ * Parameters:
+ * @x		- Pointer to referenced xfrm_state object, obtained using
+ *		  bpf_xdp_get_xfrm_state.
+ */
+__bpf_kfunc void bpf_xdp_xfrm_state_release(struct xfrm_state *x)
+{
+	xfrm_state_put(x);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(xfrm_state_kfunc_set)
+BTF_ID_FLAGS(func, bpf_xdp_get_xfrm_state, KF_RET_NULL | KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_xdp_xfrm_state_release, KF_RELEASE)
+BTF_KFUNCS_END(xfrm_state_kfunc_set)
+
+static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &xfrm_state_kfunc_set,
+};
+
+int __init register_xfrm_state_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
+					 &xfrm_state_xdp_kfunc_set);
+}

linux-7.2.3/net/xfrm/xfrm_sysctl.c

@@ -0,0 +1,88 @@
+// 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_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)
+{
+	const 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