[PATCH ipsec-next v1 0/8] Add IP-TFS mode to xfrm

[PATCH ipsec-next v1 0/8] Add IP-TFS mode to xfrm

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

This patchset adds a new xfrm mode implementing on-demand IP-TFS. IP-TFS
(AggFrag encapsulation) has been standardized in RFC9347.

Link: https://www.rfc-editor.org/rfc/rfc9347.txt

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.

In order to allow loading this fucntionality as a module a set of callbacks
xfrm_mode_cbs has been added to xfrm as well.

[PATCH ipsec-next v1 1/8] iptfs: config: add CONFIG_XFRM_IPTFS

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Add new Kconfig option to enable IP-TFS (RFC9347) functionality.

Signed-off-by: Christian Hopps <chopps@labn.net>
---
 net/xfrm/Kconfig | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index d7b16f2c23e9..f0157702718f 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -135,6 +135,22 @@ config NET_KEY_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
 
-- 
2.43.0

[PATCH ipsec-next v1 2/8] iptfs: uapi: ip: add ip_tfs_*_hdr packet formats

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Add the on-wire basic and congestion-control IP-TFS packet headers.

Signed-off-by: Christian Hopps <chopps@labn.net>
---
 include/uapi/linux/ip.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h
index 283dec7e3645..5bd7ce934d74 100644
--- a/include/uapi/linux/ip.h
+++ b/include/uapi/linux/ip.h
@@ -137,6 +137,22 @@ struct ip_beet_phdr {
 	__u8 reserved;
 };
 
+struct ip_iptfs_hdr {
+	__u8 subtype;		/* 0*: basic, 1: CC */
+	__u8 flags;
+	__be16 block_offset;
+};
+
+struct ip_iptfs_cc_hdr {
+	__u8 subtype;		/* 0: basic, 1*: CC */
+	__u8 flags;
+	__be16 block_offset;
+	__be32 loss_rate;
+	__be64 rtt_adelay_xdelay;
+	__be32 tval;
+	__be32 techo;
+};
+
 /* index values for the variables in ipv4_devconf */
 enum
 {
-- 
2.43.0

[PATCH ipsec-next v1 3/8] iptfs: uapi: IPPROTO_AGGFRAG AGGFRAG in ESP

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Add the RFC assigned IP protocol number for AGGFRAG.

Signed-off-by: Christian Hopps <chopps@labn.net>
---
 include/uapi/linux/in.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index e682ab628dfa..e6a1f3e4c58c 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -79,6 +79,8 @@ enum {
 #define IPPROTO_MPLS		IPPROTO_MPLS
   IPPROTO_ETHERNET = 143,	/* Ethernet-within-IPv6 Encapsulation	*/
 #define IPPROTO_ETHERNET	IPPROTO_ETHERNET
+  IPPROTO_AGGFRAG = 144,	/* AGGFRAG in ESP (RFC 9347)		*/
+#define IPPROTO_AGGFRAG		IPPROTO_AGGFRAG
   IPPROTO_RAW = 255,		/* Raw IP packets			*/
 #define IPPROTO_RAW		IPPROTO_RAW
   IPPROTO_MPTCP = 262,		/* Multipath TCP connection		*/
-- 
2.43.0

[PATCH ipsec-next v1 4/8] iptfs: sysctl: allow configuration of global default values

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Add sysctls for the changing the IPTFS default SA values.

Signed-off-by: Christian Hopps <chopps@labn.net>
---
 Documentation/networking/xfrm_sysctl.rst | 30 +++++++++++++++++++
 include/net/netns/xfrm.h                 |  6 ++++
 net/xfrm/xfrm_sysctl.c                   | 38 ++++++++++++++++++++++++
 3 files changed, 74 insertions(+)

diff --git a/Documentation/networking/xfrm_sysctl.rst b/Documentation/networking/xfrm_sysctl.rst
index 47b9bbdd0179..4d900c74b405 100644
--- a/Documentation/networking/xfrm_sysctl.rst
+++ b/Documentation/networking/xfrm_sysctl.rst
@@ -9,3 +9,33 @@ XFRM Syscall
 
 xfrm_acq_expires - INTEGER
 	default 30 - hard timeout in seconds for acquire requests
+
+xfrm_iptfs_max_qsize - UNSIGNED INTEGER
+        The default IPTFS max output queue size in octets. The output queue is
+        where received packets destined for output over an IPTFS tunnel are
+        stored prior to being output in aggregated/fragmented form over the
+        IPTFS tunnel.
+
+        Default 1M.
+
+xfrm_iptfs_drop_time - UNSIGNED INTEGER
+        The default IPTFS drop time in microseconds. The drop time is the amount
+        of time before a missing out-of-order IPTFS tunnel packet is considered
+        lost. See also the reorder window.
+
+        Default 1s (1000000).
+
+xfrm_iptfs_init_delay - UNSIGNED INTEGER
+        The default IPTFS initial output delay in microseconds. The initial
+        output delay is the amount of time prior to servicing the output queue
+        after queueing the first packet on said queue. This applies anytime
+        the output queue was previously empty.
+
+        Default 0.
+
+xfrm_iptfs_reorder_window - UNSIGNED INTEGER
+        The default IPTFS reorder window size. The reorder window size dictates
+        the maximum number of IPTFS tunnel packets in a sequence that may arrive
+        out of order.
+
+        Default 3.
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 423b52eca908..e11e71c8ceef 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -66,6 +66,12 @@ struct netns_xfrm {
 	u32			sysctl_aevent_rseqth;
 	int			sysctl_larval_drop;
 	u32			sysctl_acq_expires;
+#if IS_ENABLED(CONFIG_XFRM_IPTFS)
+	u32			sysctl_iptfs_drop_time;
+	u32			sysctl_iptfs_init_delay;
+	u32			sysctl_iptfs_max_qsize;
+	u32			sysctl_iptfs_reorder_window;
+#endif
 
 	u8			policy_default[XFRM_POLICY_MAX];
 
diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c
index 7fdeafc838a7..dddb1025b7de 100644
--- a/net/xfrm/xfrm_sysctl.c
+++ b/net/xfrm/xfrm_sysctl.c
@@ -10,6 +10,12 @@ static void __net_init __xfrm_sysctl_init(struct net *net)
 	net->xfrm.sysctl_aevent_rseqth = XFRM_AE_SEQT_SIZE;
 	net->xfrm.sysctl_larval_drop = 1;
 	net->xfrm.sysctl_acq_expires = 30;
+#if IS_ENABLED(CONFIG_XFRM_IPTFS)
+	net->xfrm.sysctl_iptfs_max_qsize = 1024 * 1024; /* 1M */
+	net->xfrm.sysctl_iptfs_drop_time = 1000000;	/* 1s */
+	net->xfrm.sysctl_iptfs_init_delay = 0;		/* no initial delay */
+	net->xfrm.sysctl_iptfs_reorder_window = 3;	/* tcp folks suggested */
+#endif
 }
 
 #ifdef CONFIG_SYSCTL
@@ -38,6 +44,32 @@ static struct ctl_table xfrm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+#if IS_ENABLED(CONFIG_XFRM_IPTFS)
+	{
+		.procname	= "xfrm_iptfs_drop_time",
+		.maxlen		= sizeof(uint),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec
+	},
+	{
+		.procname	= "xfrm_iptfs_init_delay",
+		.maxlen		= sizeof(uint),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec
+	},
+	{
+		.procname	= "xfrm_iptfs_max_qsize",
+		.maxlen		= sizeof(uint),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec
+	},
+	{
+		.procname	= "xfrm_iptfs_reorder_window",
+		.maxlen		= sizeof(uint),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec
+	},
+#endif
 	{}
 };
 
@@ -55,6 +87,12 @@ int __net_init xfrm_sysctl_init(struct net *net)
 	table[1].data = &net->xfrm.sysctl_aevent_rseqth;
 	table[2].data = &net->xfrm.sysctl_larval_drop;
 	table[3].data = &net->xfrm.sysctl_acq_expires;
+#if IS_ENABLED(CONFIG_XFRM_IPTFS)
+	table[4].data = &net->xfrm.sysctl_iptfs_drop_time;
+	table[5].data = &net->xfrm.sysctl_iptfs_init_delay;
+	table[6].data = &net->xfrm.sysctl_iptfs_max_qsize;
+	table[7].data = &net->xfrm.sysctl_iptfs_reorder_window;
+#endif
 
 	/* Don't export sysctls to unprivileged users */
 	if (net->user_ns != &init_user_ns) {
-- 
2.43.0

[PATCH ipsec-next v1 5/8] iptfs: netlink: add config (netlink) options

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Add netlink options for configuring IP-TFS SAs.

Signed-off-by: Christian Hopps <chopps@labn.net>
---
 include/uapi/linux/xfrm.h |  9 ++++++++-
 net/xfrm/xfrm_compat.c    | 10 ++++++++--
 net/xfrm/xfrm_user.c      | 16 ++++++++++++++++
 3 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 6a77328be114..fcb8f1583284 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -153,7 +153,8 @@ enum {
 #define XFRM_MODE_ROUTEOPTIMIZATION 2
 #define XFRM_MODE_IN_TRIGGER 3
 #define XFRM_MODE_BEET 4
-#define XFRM_MODE_MAX 5
+#define XFRM_MODE_IPTFS 5
+#define XFRM_MODE_MAX 6
 
 /* Netlink configuration messages.  */
 enum {
@@ -315,6 +316,12 @@ enum xfrm_attr_type_t {
 	XFRMA_SET_MARK_MASK,	/* __u32 */
 	XFRMA_IF_ID,		/* __u32 */
 	XFRMA_MTIMER_THRESH,	/* __u32 in seconds for input SA */
+	XFRMA_IPTFS_PKT_SIZE,	/* __u32 Size of outer packet, 0 for PMTU */
+	XFRMA_IPTFS_MAX_QSIZE,	/* __u32 max ingress queue size */
+	XFRMA_IPTFS_DONT_FRAG,	/* don't use fragmentation */
+	XFRMA_IPTFS_DROP_TIME,	/* __u32 usec to wait for next seq */
+	XFRMA_IPTFS_REORDER_WINDOW,	/* __u16 reorder window size */
+	XFRMA_IPTFS_INIT_DELAY,	/* __u32 initial packet wait delay (usec) */
 	__XFRMA_MAX
 
 #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK	/* Compatibility */
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index 655fe4ff8621..0e533b89b17f 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -277,9 +277,15 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src)
 	case XFRMA_SET_MARK_MASK:
 	case XFRMA_IF_ID:
 	case XFRMA_MTIMER_THRESH:
+	case XFRMA_IPTFS_PKT_SIZE:
+	case XFRMA_IPTFS_MAX_QSIZE:
+	case XFRMA_IPTFS_DONT_FRAG:
+	case XFRMA_IPTFS_DROP_TIME:
+	case XFRMA_IPTFS_REORDER_WINDOW:
+	case XFRMA_IPTFS_INIT_DELAY:
 		return xfrm_nla_cpy(dst, src, nla_len(src));
 	default:
-		BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH);
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IPTFS_INIT_DELAY);
 		pr_warn_once("unsupported nla_type %d\n", src->nla_type);
 		return -EOPNOTSUPP;
 	}
@@ -434,7 +440,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
 	int err;
 
 	if (type > XFRMA_MAX) {
-		BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH);
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IPTFS_INIT_DELAY);
 		NL_SET_ERR_MSG(extack, "Bad attribute");
 		return -EOPNOTSUPP;
 	}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ad01997c3aa9..d4c88d29703e 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -272,6 +272,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 			NL_SET_ERR_MSG(extack, "TFC padding can only be used in tunnel mode");
 			goto out;
 		}
+		if ((attrs[XFRMA_IPTFS_PKT_SIZE] ||
+		     attrs[XFRMA_IPTFS_MAX_QSIZE] ||
+		     attrs[XFRMA_IPTFS_DONT_FRAG] ||
+		     attrs[XFRMA_IPTFS_DROP_TIME] ||
+		     attrs[XFRMA_IPTFS_REORDER_WINDOW] ||
+		     attrs[XFRMA_IPTFS_INIT_DELAY]) &&
+		    p->mode != XFRM_MODE_IPTFS) {
+			NL_SET_ERR_MSG(extack, "IPTFS options can only be used in IPTFS mode");
+			goto out;
+		}
 		break;
 
 	case IPPROTO_COMP:
@@ -3046,6 +3056,12 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
 	[XFRMA_IF_ID]		= { .type = NLA_U32 },
 	[XFRMA_MTIMER_THRESH]   = { .type = NLA_U32 },
+	[XFRMA_IPTFS_PKT_SIZE]	= { .type = NLA_U32 },
+	[XFRMA_IPTFS_MAX_QSIZE]	= { .type = NLA_U32 },
+	[XFRMA_IPTFS_DONT_FRAG]	= { .type = NLA_FLAG },
+	[XFRMA_IPTFS_DROP_TIME]	= { .type = NLA_U32 },
+	[XFRMA_IPTFS_REORDER_WINDOW]	= { .type = NLA_U16 },
+	[XFRMA_IPTFS_INIT_DELAY]	= { .type = NLA_U32 },
 };
 EXPORT_SYMBOL_GPL(xfrma_policy);
 
-- 
2.43.0

[PATCH ipsec-next v1 6/8] iptfs: xfrm: Add mode_cbs module functionality

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Add a set of callbacks xfrm_mode_cbs to xfrm_state. These callbacks
enable the addition of new xfrm modes, such as IP-TFS to be defined
in modules.

Signed-off-by: Christian Hopps <chopps@labn.net>
---
 include/net/xfrm.h     | 38 ++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_device.c |  3 ++-
 net/xfrm/xfrm_input.c  | 14 +++++++++++--
 net/xfrm/xfrm_output.c |  2 ++
 net/xfrm/xfrm_policy.c | 18 +++++++++-------
 net/xfrm/xfrm_state.c  | 47 ++++++++++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_user.c   | 10 +++++++++
 7 files changed, 122 insertions(+), 10 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 1d107241b901..f1d5e99f0a47 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -204,6 +204,7 @@ struct xfrm_state {
 		u16		family;
 		xfrm_address_t	saddr;
 		int		header_len;
+		int		enc_hdr_len;
 		int		trailer_len;
 		u32		extra_flags;
 		struct xfrm_mark	smark;
@@ -289,6 +290,9 @@ struct xfrm_state {
 	/* Private data of this transformer, format is opaque,
 	 * interpreted by xfrm_type methods. */
 	void			*data;
+
+	const struct xfrm_mode_cbs	*mode_cbs;
+	void				*mode_data;
 };
 
 static inline struct net *xs_net(struct xfrm_state *x)
@@ -441,6 +445,40 @@ struct xfrm_type_offload {
 int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
+struct xfrm_mode_cbs {
+	struct module	*owner;
+	/* Add/delete state in the new xfrm_state in `x`. */
+	int	(*create_state)(struct xfrm_state *x);
+	void	(*delete_state)(struct xfrm_state *x);
+
+	/* Called while handling the user netlink options. */
+	int	(*user_init)(struct net *net, struct xfrm_state *x,
+			     struct nlattr **attrs,
+			     struct netlink_ext_ack *extack);
+	int	(*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb);
+	int     (*clone)(struct xfrm_state *x, struct xfrm_state *orig);
+
+	u32	(*get_inner_mtu)(struct xfrm_state *x, int outer_mtu);
+
+	/* Called to handle received xfrm (egress) packets. */
+	int	(*input)(struct xfrm_state *x, struct sk_buff *skb);
+
+	/* Placed in dst_output of the dst when an xfrm_state is bound. */
+	int	(*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
+
+	/**
+	 * Prepare the skb for output for the given mode. Returns:
+	 *    Error value, if 0 then skb values should be as follows:
+	 *    transport_header should point at ESP header
+	 *    network_header should point at Outer IP header
+	 *    mac_header should point at protocol/nexthdr of the outer IP
+	 */
+	int	(*prepare_output)(struct xfrm_state *x, struct sk_buff *skb);
+};
+
+int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs);
+void xfrm_unregister_mode_cbs(u8 mode);
+
 static inline int xfrm_af2proto(unsigned int family)
 {
 	switch(family) {
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 3784534c9185..8b848540ea47 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -42,7 +42,8 @@ static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
 		skb->transport_header = skb->network_header + hsize;
 
 	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + x->props.header_len);
+	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,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index bd4ce21d76d7..824f7b7f90e0 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -437,6 +437,9 @@ static int xfrm_inner_mode_input(struct xfrm_state *x,
 		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;
 	}
@@ -479,6 +482,10 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		family = x->props.family;
 
+		/* An encap_type of -3 indicates reconstructed inner packet */
+		if (encap_type == -3)
+			goto resume_decapped;
+
 		/* An encap_type of -1 indicates async resumption. */
 		if (encap_type == -1) {
 			async = 1;
@@ -660,11 +667,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
 
-		if (xfrm_inner_mode_input(x, skb)) {
+		err = xfrm_inner_mode_input(x, skb);
+		if (err == -EINPROGRESS)
+			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;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 662c83beb345..8f98e42d4252 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -472,6 +472,8 @@ static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *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;
 	}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 53b7ce4a4db0..f3cd8483d427 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2713,13 +2713,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 
 		dst1->input = dst_discard;
 
-		rcu_read_lock();
-		afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
-		if (likely(afinfo))
-			dst1->output = afinfo->output;
-		else
-			dst1->output = dst_discard_out;
-		rcu_read_unlock();
+		if (xfrm[i]->mode_cbs && xfrm[i]->mode_cbs->output) {
+			dst1->output = xfrm[i]->mode_cbs->output;
+		} else {
+			rcu_read_lock();
+			afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
+			if (likely(afinfo))
+				dst1->output = afinfo->output;
+			else
+				dst1->output = dst_discard_out;
+			rcu_read_unlock();
+		}
 
 		xdst_prev = xdst;
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index bda5327bf34d..2b58e35bea63 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -513,6 +513,36 @@ static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
 	return NULL;
 }
 
+static struct xfrm_mode_cbs xfrm_mode_cbs_map[XFRM_MODE_MAX];
+
+int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs)
+{
+	if (mode >= XFRM_MODE_MAX)
+		return -EINVAL;
+
+	xfrm_mode_cbs_map[mode] = *mode_cbs;
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_register_mode_cbs);
+
+void xfrm_unregister_mode_cbs(u8 mode)
+{
+	if (mode >= XFRM_MODE_MAX)
+		return;
+
+	memset(&xfrm_mode_cbs_map[mode], 0, sizeof(xfrm_mode_cbs_map[mode]));
+}
+EXPORT_SYMBOL(xfrm_unregister_mode_cbs);
+
+static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode)
+{
+	if (mode >= XFRM_MODE_MAX)
+		return NULL;
+	if (mode == XFRM_MODE_IPTFS && !xfrm_mode_cbs_map[mode].create_state)
+		request_module("xfrm-iptfs");
+	return &xfrm_mode_cbs_map[mode];
+}
+
 void xfrm_state_free(struct xfrm_state *x)
 {
 	kmem_cache_free(xfrm_state_cache, x);
@@ -521,6 +551,8 @@ EXPORT_SYMBOL(xfrm_state_free);
 
 static void ___xfrm_state_destroy(struct xfrm_state *x)
 {
+	if (x->mode_cbs && x->mode_cbs->delete_state)
+		x->mode_cbs->delete_state(x);
 	hrtimer_cancel(&x->mtimer);
 	del_timer_sync(&x->rtimer);
 	kfree(x->aead);
@@ -678,6 +710,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		x->replay_maxage = 0;
 		x->replay_maxdiff = 0;
 		spin_lock_init(&x->lock);
+		x->mode_data = NULL;
 	}
 	return x;
 }
@@ -1745,6 +1778,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 	x->new_mapping = 0;
 	x->new_mapping_sport = 0;
 
+	if (x->mode_cbs && x->mode_cbs->clone) {
+		if (!x->mode_cbs->clone(x, orig))
+			goto error;
+	}
+
 	return x;
 
  error:
@@ -2765,6 +2803,9 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 	case XFRM_MODE_TUNNEL:
 		break;
 	default:
+		if (x->mode_cbs && x->mode_cbs->get_inner_mtu)
+			return x->mode_cbs->get_inner_mtu(x, mtu);
+
 		WARN_ON_ONCE(1);
 		break;
 	}
@@ -2850,6 +2891,12 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload,
 			goto error;
 	}
 
+	x->mode_cbs = xfrm_get_mode_cbs(x->props.mode);
+	if (x->mode_cbs && x->mode_cbs->create_state) {
+		err = x->mode_cbs->create_state(x);
+		if (err)
+			goto error;
+	}
 error:
 	return err;
 }
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index d4c88d29703e..92d11f2306e7 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -779,6 +779,12 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 			goto error;
 	}
 
+	if (x->mode_cbs && x->mode_cbs->user_init) {
+		err = x->mode_cbs->user_init(net, x, attrs, extack);
+		if (err)
+			goto error;
+	}
+
 	return x;
 
 error:
@@ -1192,6 +1198,10 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 		if (ret)
 			goto out;
 	}
+	if (x->mode_cbs && x->mode_cbs->copy_to_user)
+		ret = x->mode_cbs->copy_to_user(x, skb);
+	if (ret)
+		goto out;
 	if (x->mapping_maxage)
 		ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage);
 out:
-- 
2.43.0

Re: [devel-ipsec] [PATCH ipsec-next v1 6/8] iptfs: xfrm: Add mode_cbs module functionality

[Antony Antony]

Hi Chris,

I was testing this version.
And I ran into issues when migrating states. IP-TFS values are set to 0.
I noticed 2-3 issues both in this patch and 8/8

On Mon, Feb 19, 2024 at 03:57:33AM -0500, Christian Hopps via Devel wrote:
> From: Christian Hopps <chopps@labn.net>
> 
> Add a set of callbacks xfrm_mode_cbs to xfrm_state. These callbacks
> enable the addition of new xfrm modes, such as IP-TFS to be defined
> in modules.
> 
> Signed-off-by: Christian Hopps <chopps@labn.net>
> ---
>  include/net/xfrm.h     | 38 ++++++++++++++++++++++++++++++++++
>  net/xfrm/xfrm_device.c |  3 ++-
>  net/xfrm/xfrm_input.c  | 14 +++++++++++--
>  net/xfrm/xfrm_output.c |  2 ++
>  net/xfrm/xfrm_policy.c | 18 +++++++++-------
>  net/xfrm/xfrm_state.c  | 47 ++++++++++++++++++++++++++++++++++++++++++
>  net/xfrm/xfrm_user.c   | 10 +++++++++
>  7 files changed, 122 insertions(+), 10 deletions(-)
> 
> diff --git a/include/net/xfrm.h b/include/net/xfrm.h
> index 1d107241b901..f1d5e99f0a47 100644
> --- a/include/net/xfrm.h
> +++ b/include/net/xfrm.h
> @@ -204,6 +204,7 @@ struct xfrm_state {
>  		u16		family;
>  		xfrm_address_t	saddr;
>  		int		header_len;
> +		int		enc_hdr_len;
>  		int		trailer_len;
>  		u32		extra_flags;
>  		struct xfrm_mark	smark;
> @@ -289,6 +290,9 @@ struct xfrm_state {
>  	/* Private data of this transformer, format is opaque,
>  	 * interpreted by xfrm_type methods. */
>  	void			*data;
> +
> +	const struct xfrm_mode_cbs	*mode_cbs;
> +	void				*mode_data;
>  };
>  
>  static inline struct net *xs_net(struct xfrm_state *x)
> @@ -441,6 +445,40 @@ struct xfrm_type_offload {
>  int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
>  void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
>  
> +struct xfrm_mode_cbs {
> +	struct module	*owner;
> +	/* Add/delete state in the new xfrm_state in `x`. */
> +	int	(*create_state)(struct xfrm_state *x);
> +	void	(*delete_state)(struct xfrm_state *x);
> +
> +	/* Called while handling the user netlink options. */
> +	int	(*user_init)(struct net *net, struct xfrm_state *x,
> +			     struct nlattr **attrs,
> +			     struct netlink_ext_ack *extack);
> +	int	(*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb);
> +	int     (*clone)(struct xfrm_state *x, struct xfrm_state *orig);
> +
> +	u32	(*get_inner_mtu)(struct xfrm_state *x, int outer_mtu);
> +
> +	/* Called to handle received xfrm (egress) packets. */
> +	int	(*input)(struct xfrm_state *x, struct sk_buff *skb);
> +
> +	/* Placed in dst_output of the dst when an xfrm_state is bound. */
> +	int	(*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
> +
> +	/**
> +	 * Prepare the skb for output for the given mode. Returns:
> +	 *    Error value, if 0 then skb values should be as follows:
> +	 *    transport_header should point at ESP header
> +	 *    network_header should point at Outer IP header
> +	 *    mac_header should point at protocol/nexthdr of the outer IP
> +	 */
> +	int	(*prepare_output)(struct xfrm_state *x, struct sk_buff *skb);
> +};
> +
> +int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs);
> +void xfrm_unregister_mode_cbs(u8 mode);
> +
>  static inline int xfrm_af2proto(unsigned int family)
>  {
>  	switch(family) {
> diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
> index 3784534c9185..8b848540ea47 100644
> --- a/net/xfrm/xfrm_device.c
> +++ b/net/xfrm/xfrm_device.c
> @@ -42,7 +42,8 @@ static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
>  		skb->transport_header = skb->network_header + hsize;
>  
>  	skb_reset_mac_len(skb);
> -	pskb_pull(skb, skb->mac_len + x->props.header_len);
> +	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,
> diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
> index bd4ce21d76d7..824f7b7f90e0 100644
> --- a/net/xfrm/xfrm_input.c
> +++ b/net/xfrm/xfrm_input.c
> @@ -437,6 +437,9 @@ static int xfrm_inner_mode_input(struct xfrm_state *x,
>  		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;
>  	}
> @@ -479,6 +482,10 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
>  
>  		family = x->props.family;
>  
> +		/* An encap_type of -3 indicates reconstructed inner packet */
> +		if (encap_type == -3)
> +			goto resume_decapped;
> +
>  		/* An encap_type of -1 indicates async resumption. */
>  		if (encap_type == -1) {
>  			async = 1;
> @@ -660,11 +667,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
>  
>  		XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
>  
> -		if (xfrm_inner_mode_input(x, skb)) {
> +		err = xfrm_inner_mode_input(x, skb);
> +		if (err == -EINPROGRESS)
> +			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;
> diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
> index 662c83beb345..8f98e42d4252 100644
> --- a/net/xfrm/xfrm_output.c
> +++ b/net/xfrm/xfrm_output.c
> @@ -472,6 +472,8 @@ static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *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;
>  	}
> diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
> index 53b7ce4a4db0..f3cd8483d427 100644
> --- a/net/xfrm/xfrm_policy.c
> +++ b/net/xfrm/xfrm_policy.c
> @@ -2713,13 +2713,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
>  
>  		dst1->input = dst_discard;
>  
> -		rcu_read_lock();
> -		afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
> -		if (likely(afinfo))
> -			dst1->output = afinfo->output;
> -		else
> -			dst1->output = dst_discard_out;
> -		rcu_read_unlock();
> +		if (xfrm[i]->mode_cbs && xfrm[i]->mode_cbs->output) {
> +			dst1->output = xfrm[i]->mode_cbs->output;
> +		} else {
> +			rcu_read_lock();
> +			afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
> +			if (likely(afinfo))
> +				dst1->output = afinfo->output;
> +			else
> +				dst1->output = dst_discard_out;
> +			rcu_read_unlock();
> +		}
>  
>  		xdst_prev = xdst;
>  
> diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
> index bda5327bf34d..2b58e35bea63 100644
> --- a/net/xfrm/xfrm_state.c
> +++ b/net/xfrm/xfrm_state.c
> @@ -513,6 +513,36 @@ static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
>  	return NULL;
>  }
>  
> +static struct xfrm_mode_cbs xfrm_mode_cbs_map[XFRM_MODE_MAX];
> +
> +int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs)
> +{
> +	if (mode >= XFRM_MODE_MAX)
> +		return -EINVAL;
> +
> +	xfrm_mode_cbs_map[mode] = *mode_cbs;
> +	return 0;
> +}
> +EXPORT_SYMBOL(xfrm_register_mode_cbs);
> +
> +void xfrm_unregister_mode_cbs(u8 mode)
> +{
> +	if (mode >= XFRM_MODE_MAX)
> +		return;
> +
> +	memset(&xfrm_mode_cbs_map[mode], 0, sizeof(xfrm_mode_cbs_map[mode]));
> +}
> +EXPORT_SYMBOL(xfrm_unregister_mode_cbs);
> +
> +static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode)
> +{
> +	if (mode >= XFRM_MODE_MAX)
> +		return NULL;
> +	if (mode == XFRM_MODE_IPTFS && !xfrm_mode_cbs_map[mode].create_state)
> +		request_module("xfrm-iptfs");
> +	return &xfrm_mode_cbs_map[mode];
> +}
> +
>  void xfrm_state_free(struct xfrm_state *x)
>  {
>  	kmem_cache_free(xfrm_state_cache, x);
> @@ -521,6 +551,8 @@ EXPORT_SYMBOL(xfrm_state_free);
>  
>  static void ___xfrm_state_destroy(struct xfrm_state *x)
>  {
> +	if (x->mode_cbs && x->mode_cbs->delete_state)
> +		x->mode_cbs->delete_state(x);
>  	hrtimer_cancel(&x->mtimer);
>  	del_timer_sync(&x->rtimer);
>  	kfree(x->aead);
> @@ -678,6 +710,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
>  		x->replay_maxage = 0;
>  		x->replay_maxdiff = 0;
>  		spin_lock_init(&x->lock);
> +		x->mode_data = NULL;
>  	}
>  	return x;
>  }
> @@ -1745,6 +1778,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
>  	x->new_mapping = 0;
>  	x->new_mapping_sport = 0;
>  
> +	if (x->mode_cbs && x->mode_cbs->clone) {

I notice x->mode_cbs,  it should check old state?

+ if (orig->mode_cbs && orig->mode_cbs->clone) {

> +		if (!x->mode_cbs->clone(x, orig))

iptfs_clone()  return 0 on success. So
"!". x->mode_cbs->clone -> iptfs_clone()
also use orig?
+		if (orig->mode_cbs->clone(x, orig))


> +			goto error;
> +	}
> +
>  	return x;
>  
>   error:
> @@ -2765,6 +2803,9 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
>  	case XFRM_MODE_TUNNEL:
>  		break;
>  	default:
> +		if (x->mode_cbs && x->mode_cbs->get_inner_mtu)
> +			return x->mode_cbs->get_inner_mtu(x, mtu);
> +
>  		WARN_ON_ONCE(1);
>  		break;
>  	}
> @@ -2850,6 +2891,12 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload,
>  			goto error;
>  	}
>  
> +	x->mode_cbs = xfrm_get_mode_cbs(x->props.mode);
> +	if (x->mode_cbs && x->mode_cbs->create_state) {
> +		err = x->mode_cbs->create_state(x);
> +		if (err)
> +			goto error;
> +	}
>  error:
>  	return err;
>  }
> diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
> index d4c88d29703e..92d11f2306e7 100644
> --- a/net/xfrm/xfrm_user.c
> +++ b/net/xfrm/xfrm_user.c
> @@ -779,6 +779,12 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
>  			goto error;
>  	}
>  
> +	if (x->mode_cbs && x->mode_cbs->user_init) {
> +		err = x->mode_cbs->user_init(net, x, attrs, extack);
> +		if (err)
> +			goto error;
> +	}
> +
>  	return x;
>  
>  error:
> @@ -1192,6 +1198,10 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
>  		if (ret)
>  			goto out;
>  	}
> +	if (x->mode_cbs && x->mode_cbs->copy_to_user)
> +		ret = x->mode_cbs->copy_to_user(x, skb);
> +	if (ret)
> +		goto out;
>  	if (x->mapping_maxage)
>  		ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage);
>  out:
> -- 
> 2.43.0
> 
> -- 
> Devel mailing list
> Devel@linux-ipsec.org
> https://linux-ipsec.org/mailman/listinfo/devel

Re: [devel-ipsec] [PATCH ipsec-next v1 6/8] iptfs: xfrm: Add mode_cbs module functionality

[Christian Hopps]

[-- Attachment #1: Type: text/plain, Size: 9115 bytes --]


Antony Antony <antony@phenome.org> writes:

> Hi Chris,
>
> I was testing this version.
> And I ran into issues when migrating states. IP-TFS values are set to 0.
> I noticed 2-3 issues both in this patch and 8/8
>
> On Mon, Feb 19, 2024 at 03:57:33AM -0500, Christian Hopps via Devel wrote:
>> From: Christian Hopps <chopps@labn.net>
>>
>> Add a set of callbacks xfrm_mode_cbs to xfrm_state. These callbacks
>> enable the addition of new xfrm modes, such as IP-TFS to be defined
>> in modules.
>>
>> Signed-off-by: Christian Hopps <chopps@labn.net>
>> ---
>>  include/net/xfrm.h     | 38 ++++++++++++++++++++++++++++++++++
>>  net/xfrm/xfrm_device.c |  3 ++-
>>  net/xfrm/xfrm_input.c  | 14 +++++++++++--
>>  net/xfrm/xfrm_output.c |  2 ++
>>  net/xfrm/xfrm_policy.c | 18 +++++++++-------
>>  net/xfrm/xfrm_state.c  | 47 ++++++++++++++++++++++++++++++++++++++++++
>>  net/xfrm/xfrm_user.c   | 10 +++++++++
>>  7 files changed, 122 insertions(+), 10 deletions(-)
>>
>> diff --git a/include/net/xfrm.h b/include/net/xfrm.h
>> index 1d107241b901..f1d5e99f0a47 100644
>> --- a/include/net/xfrm.h
>> +++ b/include/net/xfrm.h
>> @@ -204,6 +204,7 @@ struct xfrm_state {
>>  		u16		family;
>>  		xfrm_address_t	saddr;
>>  		int		header_len;
>> +		int		enc_hdr_len;
>>  		int		trailer_len;
>>  		u32		extra_flags;
>>  		struct xfrm_mark	smark;
>> @@ -289,6 +290,9 @@ struct xfrm_state {
>>  	/* Private data of this transformer, format is opaque,
>>  	 * interpreted by xfrm_type methods. */
>>  	void			*data;
>> +
>> +	const struct xfrm_mode_cbs	*mode_cbs;
>> +	void				*mode_data;
>>  };
>>
>>  static inline struct net *xs_net(struct xfrm_state *x)
>> @@ -441,6 +445,40 @@ struct xfrm_type_offload {
>>  int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
>>  void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
>>
>> +struct xfrm_mode_cbs {
>> +	struct module	*owner;
>> +	/* Add/delete state in the new xfrm_state in `x`. */
>> +	int	(*create_state)(struct xfrm_state *x);
>> +	void	(*delete_state)(struct xfrm_state *x);
>> +
>> +	/* Called while handling the user netlink options. */
>> +	int	(*user_init)(struct net *net, struct xfrm_state *x,
>> +			     struct nlattr **attrs,
>> +			     struct netlink_ext_ack *extack);
>> +	int	(*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb);
>> +	int     (*clone)(struct xfrm_state *x, struct xfrm_state *orig);
>> +
>> +	u32	(*get_inner_mtu)(struct xfrm_state *x, int outer_mtu);
>> +
>> +	/* Called to handle received xfrm (egress) packets. */
>> +	int	(*input)(struct xfrm_state *x, struct sk_buff *skb);
>> +
>> +	/* Placed in dst_output of the dst when an xfrm_state is bound. */
>> +	int	(*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
>> +
>> +	/**
>> +	 * Prepare the skb for output for the given mode. Returns:
>> +	 *    Error value, if 0 then skb values should be as follows:
>> +	 *    transport_header should point at ESP header
>> +	 *    network_header should point at Outer IP header
>> +	 *    mac_header should point at protocol/nexthdr of the outer IP
>> +	 */
>> +	int	(*prepare_output)(struct xfrm_state *x, struct sk_buff *skb);
>> +};
>> +
>> +int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs);
>> +void xfrm_unregister_mode_cbs(u8 mode);
>> +
>>  static inline int xfrm_af2proto(unsigned int family)
>>  {
>>  	switch(family) {
>> diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
>> index 3784534c9185..8b848540ea47 100644
>> --- a/net/xfrm/xfrm_device.c
>> +++ b/net/xfrm/xfrm_device.c
>> @@ -42,7 +42,8 @@ static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
>>  		skb->transport_header = skb->network_header + hsize;
>>
>>  	skb_reset_mac_len(skb);
>> -	pskb_pull(skb, skb->mac_len + x->props.header_len);
>> +	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,
>> diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
>> index bd4ce21d76d7..824f7b7f90e0 100644
>> --- a/net/xfrm/xfrm_input.c
>> +++ b/net/xfrm/xfrm_input.c
>> @@ -437,6 +437,9 @@ static int xfrm_inner_mode_input(struct xfrm_state *x,
>>  		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;
>>  	}
>> @@ -479,6 +482,10 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
>>
>>  		family = x->props.family;
>>
>> +		/* An encap_type of -3 indicates reconstructed inner packet */
>> +		if (encap_type == -3)
>> +			goto resume_decapped;
>> +
>>  		/* An encap_type of -1 indicates async resumption. */
>>  		if (encap_type == -1) {
>>  			async = 1;
>> @@ -660,11 +667,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
>>
>>  		XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
>>
>> -		if (xfrm_inner_mode_input(x, skb)) {
>> +		err = xfrm_inner_mode_input(x, skb);
>> +		if (err == -EINPROGRESS)
>> +			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;
>> diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
>> index 662c83beb345..8f98e42d4252 100644
>> --- a/net/xfrm/xfrm_output.c
>> +++ b/net/xfrm/xfrm_output.c
>> @@ -472,6 +472,8 @@ static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *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;
>>  	}
>> diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
>> index 53b7ce4a4db0..f3cd8483d427 100644
>> --- a/net/xfrm/xfrm_policy.c
>> +++ b/net/xfrm/xfrm_policy.c
>> @@ -2713,13 +2713,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
>>
>>  		dst1->input = dst_discard;
>>
>> -		rcu_read_lock();
>> -		afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
>> -		if (likely(afinfo))
>> -			dst1->output = afinfo->output;
>> -		else
>> -			dst1->output = dst_discard_out;
>> -		rcu_read_unlock();
>> +		if (xfrm[i]->mode_cbs && xfrm[i]->mode_cbs->output) {
>> +			dst1->output = xfrm[i]->mode_cbs->output;
>> +		} else {
>> +			rcu_read_lock();
>> +			afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
>> +			if (likely(afinfo))
>> +				dst1->output = afinfo->output;
>> +			else
>> +				dst1->output = dst_discard_out;
>> +			rcu_read_unlock();
>> +		}
>>
>>  		xdst_prev = xdst;
>>
>> diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
>> index bda5327bf34d..2b58e35bea63 100644
>> --- a/net/xfrm/xfrm_state.c
>> +++ b/net/xfrm/xfrm_state.c
>> @@ -513,6 +513,36 @@ static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
>>  	return NULL;
>>  }
>>
>> +static struct xfrm_mode_cbs xfrm_mode_cbs_map[XFRM_MODE_MAX];
>> +
>> +int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs)
>> +{
>> +	if (mode >= XFRM_MODE_MAX)
>> +		return -EINVAL;
>> +
>> +	xfrm_mode_cbs_map[mode] = *mode_cbs;
>> +	return 0;
>> +}
>> +EXPORT_SYMBOL(xfrm_register_mode_cbs);
>> +
>> +void xfrm_unregister_mode_cbs(u8 mode)
>> +{
>> +	if (mode >= XFRM_MODE_MAX)
>> +		return;
>> +
>> +	memset(&xfrm_mode_cbs_map[mode], 0, sizeof(xfrm_mode_cbs_map[mode]));
>> +}
>> +EXPORT_SYMBOL(xfrm_unregister_mode_cbs);
>> +
>> +static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode)
>> +{
>> +	if (mode >= XFRM_MODE_MAX)
>> +		return NULL;
>> +	if (mode == XFRM_MODE_IPTFS && !xfrm_mode_cbs_map[mode].create_state)
>> +		request_module("xfrm-iptfs");
>> +	return &xfrm_mode_cbs_map[mode];
>> +}
>> +
>>  void xfrm_state_free(struct xfrm_state *x)
>>  {
>>  	kmem_cache_free(xfrm_state_cache, x);
>> @@ -521,6 +551,8 @@ EXPORT_SYMBOL(xfrm_state_free);
>>
>>  static void ___xfrm_state_destroy(struct xfrm_state *x)
>>  {
>> +	if (x->mode_cbs && x->mode_cbs->delete_state)
>> +		x->mode_cbs->delete_state(x);
>>  	hrtimer_cancel(&x->mtimer);
>>  	del_timer_sync(&x->rtimer);
>>  	kfree(x->aead);
>> @@ -678,6 +710,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
>>  		x->replay_maxage = 0;
>>  		x->replay_maxdiff = 0;
>>  		spin_lock_init(&x->lock);
>> +		x->mode_data = NULL;
>>  	}
>>  	return x;
>>  }
>> @@ -1745,6 +1778,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
>>  	x->new_mapping = 0;
>>  	x->new_mapping_sport = 0;
>>
>> +	if (x->mode_cbs && x->mode_cbs->clone) {
>
> I notice x->mode_cbs,  it should check old state?
>
> + if (orig->mode_cbs && orig->mode_cbs->clone) {

Actually we need:

+	x->mode_cbs = orig->mode_cbs;
	if (x->mode_cbs && x->mode_cbs->clone) {

>> +		if (!x->mode_cbs->clone(x, orig))
>
> iptfs_clone()  return 0 on success. So
> "!". x->mode_cbs->clone -> iptfs_clone()
> also use orig?
> +		if (orig->mode_cbs->clone(x, orig))

Thanks for catching these!
Chris.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 858 bytes --]

[PATCH ipsec-next v1 7/8] iptfs: xfrm: add generic iptfs defines and functionality

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Define `XFRM_MODE_IPTFS` and `IPSEC_MODE_IPTFS` constants, and add these to
switch case and conditionals adjacent with the existing TUNNEL modes.

Signed-off-by: Christian Hopps <chopps@labn.net>
---
 include/net/xfrm.h         |  1 +
 include/uapi/linux/ipsec.h |  3 ++-
 include/uapi/linux/snmp.h  |  2 ++
 net/ipv4/esp4.c            |  3 ++-
 net/ipv6/esp6.c            |  3 ++-
 net/netfilter/nft_xfrm.c   |  3 ++-
 net/xfrm/xfrm_device.c     |  1 +
 net/xfrm/xfrm_output.c     |  4 ++++
 net/xfrm/xfrm_policy.c     |  8 ++++++--
 net/xfrm/xfrm_proc.c       |  2 ++
 net/xfrm/xfrm_state.c      | 12 ++++++++++++
 net/xfrm/xfrm_user.c       |  3 +++
 12 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index f1d5e99f0a47..1e2af0b27631 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -37,6 +37,7 @@
 #define XFRM_PROTO_COMP		108
 #define XFRM_PROTO_IPIP		4
 #define XFRM_PROTO_IPV6		41
+#define XFRM_PROTO_IPTFS	IPPROTO_AGGFRAG
 #define XFRM_PROTO_ROUTING	IPPROTO_ROUTING
 #define XFRM_PROTO_DSTOPTS	IPPROTO_DSTOPTS
 
diff --git a/include/uapi/linux/ipsec.h b/include/uapi/linux/ipsec.h
index 50d8ee1791e2..696b790f4346 100644
--- a/include/uapi/linux/ipsec.h
+++ b/include/uapi/linux/ipsec.h
@@ -14,7 +14,8 @@ enum {
 	IPSEC_MODE_ANY		= 0,	/* We do not support this for SA */
 	IPSEC_MODE_TRANSPORT	= 1,
 	IPSEC_MODE_TUNNEL	= 2,
-	IPSEC_MODE_BEET         = 3
+	IPSEC_MODE_BEET         = 3,
+	IPSEC_MODE_IPTFS        = 4
 };
 
 enum {
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index a0819c6a5988..06907abbdab9 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -337,6 +337,8 @@ enum
 	LINUX_MIB_XFRMFWDHDRERROR,		/* XfrmFwdHdrError*/
 	LINUX_MIB_XFRMOUTSTATEINVALID,		/* XfrmOutStateInvalid */
 	LINUX_MIB_XFRMACQUIREERROR,		/* XfrmAcquireError */
+	LINUX_MIB_XFRMINIPTFSERROR,		/* XfrmInIptfsError */
+	LINUX_MIB_XFRMOUTNOQSPACE,		/* XfrmOutNoQueueSpace */
 	__LINUX_MIB_XFRMMAX
 };
 
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4ccfc104f13a..7607698690f9 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -818,7 +818,8 @@ int esp_input_done2(struct sk_buff *skb, int err)
 	}
 
 	skb_pull_rcsum(skb, hlen);
-	if (x->props.mode == XFRM_MODE_TUNNEL)
+	if (x->props.mode == XFRM_MODE_TUNNEL ||
+	    x->props.mode == XFRM_MODE_IPTFS)
 		skb_reset_transport_header(skb);
 	else
 		skb_set_transport_header(skb, -ihl);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 2cc1a45742d8..81bdaceead27 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -867,7 +867,8 @@ int esp6_input_done2(struct sk_buff *skb, int err)
 	skb_postpull_rcsum(skb, skb_network_header(skb),
 			   skb_network_header_len(skb));
 	skb_pull_rcsum(skb, hlen);
-	if (x->props.mode == XFRM_MODE_TUNNEL)
+	if (x->props.mode == XFRM_MODE_TUNNEL ||
+	    x->props.mode == XFRM_MODE_IPTFS)
 		skb_reset_transport_header(skb);
 	else
 		skb_set_transport_header(skb, -hdr_len);
diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c
index 452f8587adda..291b029391cd 100644
--- a/net/netfilter/nft_xfrm.c
+++ b/net/netfilter/nft_xfrm.c
@@ -112,7 +112,8 @@ static bool xfrm_state_addr_ok(enum nft_xfrm_keys k, u8 family, u8 mode)
 		return true;
 	}
 
-	return mode == XFRM_MODE_BEET || mode == XFRM_MODE_TUNNEL;
+	return mode == XFRM_MODE_BEET || mode == XFRM_MODE_TUNNEL ||
+	       mode == XFRM_MODE_IPTFS;
 }
 
 static void nft_xfrm_state_get_key(const struct nft_xfrm *priv,
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 8b848540ea47..a40f5e09829e 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -69,6 +69,7 @@ static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb,
 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,
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 8f98e42d4252..938b81c0a8d3 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -677,6 +677,10 @@ static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x)
 
 		return;
 	}
+	if (x->outer_mode.encap == XFRM_MODE_IPTFS) {
+		xo->inner_ipproto = IPPROTO_AGGFRAG;
+		return;
+	}
 
 	/* non-Tunnel Mode */
 	if (!skb->encapsulation)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f3cd8483d427..ed19e3d19296 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2474,6 +2474,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 		struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i];
 
 		if (tmpl->mode == XFRM_MODE_TUNNEL ||
+		    tmpl->mode == XFRM_MODE_IPTFS ||
 		    tmpl->mode == XFRM_MODE_BEET) {
 			remote = &tmpl->id.daddr;
 			local = &tmpl->saddr;
@@ -3258,7 +3259,8 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
 ok:
 	xfrm_pols_put(pols, drop_pols);
 	if (dst && dst->xfrm &&
-	    dst->xfrm->props.mode == XFRM_MODE_TUNNEL)
+	    (dst->xfrm->props.mode == XFRM_MODE_TUNNEL ||
+	     dst->xfrm->props.mode == XFRM_MODE_IPTFS))
 		dst->flags |= DST_XFRM_TUNNEL;
 	return dst;
 
@@ -4495,6 +4497,7 @@ static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tm
 		switch (t->mode) {
 		case XFRM_MODE_TUNNEL:
 		case XFRM_MODE_BEET:
+		case XFRM_MODE_IPTFS:
 			if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr,
 					    m->old_family) &&
 			    xfrm_addr_equal(&t->saddr, &m->old_saddr,
@@ -4537,7 +4540,8 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol,
 				continue;
 			n++;
 			if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL &&
-			    pol->xfrm_vec[i].mode != XFRM_MODE_BEET)
+			    pol->xfrm_vec[i].mode != XFRM_MODE_BEET &&
+			    pol->xfrm_vec[i].mode != XFRM_MODE_IPTFS)
 				continue;
 			/* update endpoints */
 			memcpy(&pol->xfrm_vec[i].id.daddr, &mp->new_daddr,
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
index fee9b5cf37a7..d92b1b760749 100644
--- a/net/xfrm/xfrm_proc.c
+++ b/net/xfrm/xfrm_proc.c
@@ -41,6 +41,8 @@ static const struct snmp_mib xfrm_mib_list[] = {
 	SNMP_MIB_ITEM("XfrmFwdHdrError", LINUX_MIB_XFRMFWDHDRERROR),
 	SNMP_MIB_ITEM("XfrmOutStateInvalid", LINUX_MIB_XFRMOUTSTATEINVALID),
 	SNMP_MIB_ITEM("XfrmAcquireError", LINUX_MIB_XFRMACQUIREERROR),
+	SNMP_MIB_ITEM("XfrmInIptfsError", LINUX_MIB_XFRMINIPTFSERROR),
+	SNMP_MIB_ITEM("XfrmOutNoQueueSpace", LINUX_MIB_XFRMOUTNOQSPACE),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 2b58e35bea63..eaa21456bbe2 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -465,6 +465,11 @@ static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = {
 		.flags = XFRM_MODE_FLAG_TUNNEL,
 		.family = AF_INET,
 	},
+	[XFRM_MODE_IPTFS] = {
+		.encap = XFRM_MODE_IPTFS,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET,
+	},
 };
 
 static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = {
@@ -486,6 +491,11 @@ static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = {
 		.flags = XFRM_MODE_FLAG_TUNNEL,
 		.family = AF_INET6,
 	},
+	[XFRM_MODE_IPTFS] = {
+		.encap = XFRM_MODE_IPTFS,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET6,
+	},
 };
 
 static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
@@ -2089,6 +2099,7 @@ static int __xfrm6_state_sort_cmp(const void *p)
 #endif
 	case XFRM_MODE_TUNNEL:
 	case XFRM_MODE_BEET:
+	case XFRM_MODE_IPTFS:
 		return 4;
 	}
 	return 5;
@@ -2115,6 +2126,7 @@ static int __xfrm6_tmpl_sort_cmp(const void *p)
 #endif
 	case XFRM_MODE_TUNNEL:
 	case XFRM_MODE_BEET:
+	case XFRM_MODE_IPTFS:
 		return 3;
 	}
 	return 4;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 92d11f2306e7..80617c0d040f 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -353,6 +353,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 	case XFRM_MODE_TUNNEL:
 	case XFRM_MODE_ROUTEOPTIMIZATION:
 	case XFRM_MODE_BEET:
+	case XFRM_MODE_IPTFS:
 		break;
 
 	default:
@@ -1830,6 +1831,8 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family,
 				return -EINVAL;
 			}
 			break;
+		case XFRM_MODE_IPTFS:
+			break;
 		default:
 			if (ut[i].family != prev_family) {
 				NL_SET_ERR_MSG(extack, "Mode in template doesn't support a family change");
-- 
2.43.0

[PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Add a new xfrm mode implementing AggFrag/IP-TFS from RFC9347.

This utilizes the new xfrm_mode_cbs to implement demand-driven IP-TFS
functionality. This functionality can be used to increase bandwidth
utilization through small packet aggregation, as well as help solve PMTU
issues through it's efficient use of fragmentation.

Link: https://www.rfc-editor.org/rfc/rfc9347.txt

Signed-off-by: Christian Hopps <chopps@labn.net>
---
 net/xfrm/Makefile      |    1 +
 net/xfrm/trace_iptfs.h |  218 ++++
 net/xfrm/xfrm_iptfs.c  | 2762 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 2981 insertions(+)
 create mode 100644 net/xfrm/trace_iptfs.h
 create mode 100644 net/xfrm/xfrm_iptfs.c

diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index 547cec77ba03..cd6520d4d777 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -20,5 +20,6 @@ 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
diff --git a/net/xfrm/trace_iptfs.h b/net/xfrm/trace_iptfs.h
new file mode 100644
index 000000000000..3ab040b58362
--- /dev/null
+++ b/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 = skb->tail;
+			   __entry->end = 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(skb_shinfo(skb)->frags[0].bv_page)
+					       : 0);
+			   __entry->pg0off = (__entry->nr_frags
+					      ? skb_shinfo(skb)->frags[0].bv_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>
diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
new file mode 100644
index 000000000000..97ac002b9f71
--- /dev/null
+++ b/net/xfrm/xfrm_iptfs.c
@@ -0,0 +1,2762 @@
+// SPDX-License-Identifier: GPL-2.0
+/* xfrm_iptfs: IPTFS encapsulation support
+ *
+ * April 21 2022, Christian Hopps <chopps@labn.net>
+ *
+ * Copyright (c) 2022, LabN Consulting, L.L.C.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/icmpv6.h>
+#include <net/gro.h>
+#include <net/icmp.h>
+#include <net/ip6_route.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+
+#include <crypto/aead.h>
+
+#include "xfrm_inout.h"
+#include "trace_iptfs.h"
+
+/* IPTFS encap (header) values. */
+#define IPTFS_SUBTYPE_BASIC 0
+#define IPTFS_SUBTYPE_CC 1
+
+/* 1) skb->head should be cache aligned.
+ * 2) when resv is for L2 headers (i.e., ethernet) we want the cacheline to
+ * start -16 from data.
+ * 3) when resv is for L3+L2 headers IOW skb->data points at the IPTFS payload
+ * we want data to be cache line aligned so all the pushed headers will be in
+ * another cacheline.
+ */
+#define XFRM_IPTFS_MIN_L3HEADROOM 128
+#define XFRM_IPTFS_MIN_L2HEADROOM (64 + 16)
+#define IPTFS_FRAG_COPY_MAX 256	/* max for copying to create iptfs frags */
+#define IPTFS_PKT_SHARE_MIN 129	/* min to try to share vs copy pkt data */
+#define NSECS_IN_USEC 1000
+
+#define IPTFS_TYPE_NOCC 0
+#define IPTFS_TYPE_CC 1
+
+#define IPTFS_HRTIMER_MODE HRTIMER_MODE_REL_SOFT
+
+struct skb_wseq {
+	struct sk_buff *skb;
+	u64 drop_time;
+};
+
+struct xfrm_iptfs_config {
+	bool dont_frag : 1;
+	u16 reorder_win_size;
+	u32 pkt_size;	    /* outer_packet_size or 0 */
+	u32 max_queue_size; /* octets */
+};
+
+struct xfrm_iptfs_data {
+	struct xfrm_iptfs_config cfg;
+
+	/* Ingress User Input */
+	struct xfrm_state *x;	    /* owning state */
+	struct sk_buff_head queue;  /* output queue */
+	u32 queue_size;		    /* octets */
+	u32 ecn_queue_size;	    /* octets above which ECN mark */
+	u64 init_delay_ns;	    /* nanoseconds */
+	struct hrtimer iptfs_timer; /* output timer */
+	time64_t iptfs_settime;	    /* time timer was set */
+	u32 payload_mtu;	    /* max payload size */
+
+	/* Tunnel input reordering */
+	bool w_seq_set;		  /* true after first seq received */
+	u64 w_wantseq;		  /* expected next sequence */
+	struct skb_wseq *w_saved; /* the saved buf array */
+	u32 w_savedlen;		  /* the saved len (not size) */
+	spinlock_t drop_lock;
+	struct hrtimer drop_timer;
+	u64 drop_time_ns;
+
+	/* Tunnel input reassembly */
+	struct sk_buff *ra_newskb; /* new pkt being reassembled */
+	u64 ra_wantseq;		   /* expected next sequence */
+	u8 ra_runt[6];		   /* last pkt bytes from last skb */
+	u8 ra_runtlen;		   /* count of ra_runt */
+};
+
+static u32 __iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu);
+static enum hrtimer_restart iptfs_delay_timer(struct hrtimer *me);
+static enum hrtimer_restart iptfs_drop_timer(struct hrtimer *me);
+
+/* ================= */
+/* Utility Functions */
+/* ================= */
+
+static u32 __trace_ip_proto(struct iphdr *iph)
+{
+	if (iph->version == 4)
+		return iph->protocol;
+	return ((struct ipv6hdr *)iph)->nexthdr;
+}
+
+static u32 __trace_ip_proto_seq(struct iphdr *iph)
+{
+	void *nexthdr;
+	u32 protocol = 0;
+
+	if (iph->version == 4) {
+		nexthdr = (void *)(iph + 1);
+		protocol = iph->protocol;
+	} else if (iph->version == 6) {
+		nexthdr = (void *)(((struct ipv6hdr *)(iph)) + 1);
+		protocol = ((struct ipv6hdr *)(iph))->nexthdr;
+	}
+	switch (protocol) {
+	case IPPROTO_ICMP:
+		return ntohs(((struct icmphdr *)nexthdr)->un.echo.sequence);
+	case IPPROTO_ICMPV6:
+		return ntohs(((struct icmp6hdr *)nexthdr)->icmp6_sequence);
+	case IPPROTO_TCP:
+		return ntohl(((struct tcphdr *)nexthdr)->seq);
+	case IPPROTO_UDP:
+		return ntohs(((struct udphdr *)nexthdr)->source);
+	default:
+		return 0;
+	}
+}
+
+static u64 __esp_seq(struct sk_buff *skb)
+{
+	u64 seq = ntohl(XFRM_SKB_CB(skb)->seq.input.low);
+
+	return seq | (u64)ntohl(XFRM_SKB_CB(skb)->seq.input.hi) << 32;
+}
+
+/* ================= */
+/* SK_BUFF Functions */
+/* ================= */
+
+/**
+ * iptfs_alloc_skb() - Allocate a new `skb` using a meta-data template.
+ * @tpl: the template to copy the new `skb`s meta-data from.
+ * @len: the linear length of the head data, zero is fine.
+ * @l3resv: true if reserve needs to support pushing L3 headers
+ *
+ * A new `skb` is allocated and it's meta-data is initialized from `tpl`, the
+ * head data is sized to `len` + reserved space set according to the @l3resv
+ * boolean. When @l3resv is false, resv is XFRM_IPTFS_MIN_L2HEADROOM which
+ * arranges for `skb->data - 16` (etherhdr space) to be the start of a cacheline.
+ * Otherwise, @l3resv is true and resv is either the size of headroom from `tpl` or
+ * XFRM_IPTFS_MIN_L3HEADROOM whichever is greater, which tries to align
+ * skb->data to a cacheline as all headers will be pushed on the previous
+ * cacheline bytes.
+ *
+ * When copying meta-data from the @tpl, the sk_buff->headers are not copied.
+ *
+ * Zero length skbs are allocated when we only need a head skb to hold new
+ * packet headers (basically the mac header) that sit on top of existing shared
+ * packet data.
+ *
+ * Return: the new skb or NULL.
+ */
+static struct sk_buff *iptfs_alloc_skb(struct sk_buff *tpl, u32 len,
+				       bool l3resv)
+{
+	struct sk_buff *skb;
+	u32 resv;
+
+	if (!l3resv) {
+		resv = XFRM_IPTFS_MIN_L2HEADROOM;
+	} else {
+		resv = skb_headroom(tpl);
+		if (resv < XFRM_IPTFS_MIN_L3HEADROOM)
+			resv = XFRM_IPTFS_MIN_L3HEADROOM;
+	}
+
+	skb = alloc_skb(len + resv, GFP_ATOMIC);
+	if (!skb) {
+		XFRM_INC_STATS(dev_net(tpl->dev), LINUX_MIB_XFRMINERROR);
+		return NULL;
+	}
+
+	skb_reserve(skb, resv);
+
+	/* Code from __copy_skb_header() -- we do not want any of the
+	 * tpl->headers copied over, so we aren't using `skb_copy_header()`.
+	 */
+	skb->tstamp = tpl->tstamp;
+	skb->dev = tpl->dev;
+	memcpy(skb->cb, tpl->cb, sizeof(skb->cb));
+	skb_dst_copy(skb, tpl);
+	__skb_ext_copy(skb, tpl);
+	__nf_copy(skb, tpl, false);
+
+	return skb;
+}
+
+/**
+ * skb_head_to_frag() - initialize a skb_frag_t based on skb head data
+ * @skb: skb with the head data
+ * @frag: frag to initialize
+ */
+static void skb_head_to_frag(const struct sk_buff *skb, skb_frag_t *frag)
+{
+	struct page *page = virt_to_head_page(skb->data);
+	unsigned char *addr = (unsigned char *)page_address(page);
+
+	BUG_ON(!skb->head_frag);
+	skb_frag_fill_page_desc(frag, page, skb->data - addr, skb_headlen(skb));
+}
+
+/**
+ * struct skb_frag_walk - use to track a walk through fragments
+ * @fragi: current fragment index
+ * @past: length of data in fragments before @fragi
+ * @total: length of data in all fragments
+ * @nr_frags: number of fragments present in array
+ * @initial_offset: the value passed in to skb_prepare_frag_walk()
+ * @pp_recycle: copy of skb->pp_recycle
+ * @frags: the page fragments inc. room for head page
+ */
+struct skb_frag_walk {
+	u32 fragi;
+	u32 past;
+	u32 total;
+	u32 nr_frags;
+	u32 initial_offset;
+	bool pp_recycle;
+	skb_frag_t frags[MAX_SKB_FRAGS + 1];
+};
+
+/**
+ * skb_prepare_frag_walk() - initialize a frag walk over an skb.
+ * @skb: the skb to walk.
+ * @initial_offset: start the walk @initial_offset into the skb.
+ * @walk: the walk to initialize
+ *
+ * Future calls to skb_add_frags() will expect the @offset value to be at
+ * least @initial_offset large.
+ */
+static void skb_prepare_frag_walk(struct sk_buff *skb, u32 initial_offset,
+				  struct skb_frag_walk *walk)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	skb_frag_t *frag, *from;
+	u32 i;
+
+	walk->initial_offset = initial_offset;
+	walk->fragi = 0;
+	walk->past = 0;
+	walk->total = 0;
+	walk->nr_frags = 0;
+	walk->pp_recycle = skb->pp_recycle;
+
+	if (skb->head_frag) {
+		if (initial_offset >= skb_headlen(skb)) {
+			initial_offset -= skb_headlen(skb);
+		} else {
+			frag = &walk->frags[walk->nr_frags++];
+			skb_head_to_frag(skb, frag);
+			frag->bv_offset += initial_offset;
+			frag->bv_len -= initial_offset;
+			walk->total += frag->bv_len;
+			initial_offset = 0;
+		}
+	} else {
+		BUG_ON(skb_headlen(skb) > initial_offset);
+		initial_offset -= skb_headlen(skb);
+	}
+
+	for (i = 0; i < shinfo->nr_frags; i++) {
+		from = &shinfo->frags[i];
+		if (initial_offset >= from->bv_len) {
+			initial_offset -= from->bv_len;
+			continue;
+		}
+		frag = &walk->frags[walk->nr_frags++];
+		*frag = *from;
+		if (initial_offset) {
+			frag->bv_offset += initial_offset;
+			frag->bv_len -= initial_offset;
+			initial_offset = 0;
+		}
+		walk->total += frag->bv_len;
+	}
+	BUG_ON(initial_offset != 0);
+}
+
+static u32 __skb_reset_frag_walk(struct skb_frag_walk *walk, u32 offset)
+{
+	/* Adjust offset to refer to internal walk values */
+	BUG_ON(offset < walk->initial_offset);
+	offset -= walk->initial_offset;
+
+	/* Get to the correct fragment for offset */
+	while (offset < walk->past) {
+		walk->past -= walk->frags[--walk->fragi].bv_len;
+		if (offset >= walk->past)
+			break;
+		BUG_ON(walk->fragi == 0);
+	}
+	while (offset >= walk->past + walk->frags[walk->fragi].bv_len)
+		walk->past += walk->frags[walk->fragi++].bv_len;
+
+	/* offset now relative to this current frag */
+	offset -= walk->past;
+	return offset;
+}
+
+/**
+ * skb_can_add_frags() - check if ok to add frags from walk to skb
+ * @skb: skb to check for adding frags to
+ * @walk: the walk that will be used as source for frags.
+ * @offset: offset from beginning of original skb to start from.
+ * @len: amount of data to add frag references to in @skb.
+ */
+static bool skb_can_add_frags(const struct sk_buff *skb,
+			      struct skb_frag_walk *walk, u32 offset, u32 len)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	u32 fragi, nr_frags, fraglen;
+
+	if (skb_has_frag_list(skb) || skb->pp_recycle != walk->pp_recycle)
+		return false;
+
+	/* Make offset relative to current frag after setting that */
+	offset = __skb_reset_frag_walk(walk, offset);
+
+	/* Verify we have array space for the fragments we need to add */
+	fragi = walk->fragi;
+	nr_frags  = shinfo->nr_frags;
+	while (len && fragi < walk->nr_frags) {
+		skb_frag_t *frag = &walk->frags[fragi];
+
+		fraglen = frag->bv_len;
+		if (offset) {
+			fraglen -= offset;
+			offset = 0;
+		}
+		if (++nr_frags > MAX_SKB_FRAGS)
+			return false;
+		if (len <= fraglen)
+			return true;
+		len -= fraglen;
+		fragi++;
+	}
+	/* We may not copy all @len but what we have will fit. */
+	return true;
+}
+
+/**
+ * skb_add_frags() - add a range of fragment references into an skb
+ * @skb: skb to add references into
+ * @walk: the walk to add referenced fragments from.
+ * @offset: offset from beginning of original skb to start from.
+ * @len: amount of data to add frag references to in @skb.
+ *
+ * skb_can_add_frags() should be called before this function to verify that the
+ * destination @skb is compatible with the walk and has space in the array for
+ * the to be added frag refrences.
+ *
+ * Return: The number of bytes not added to @skb b/c we reached the end of the
+ * walk before adding all of @len.
+ */
+static int skb_add_frags(struct sk_buff *skb, struct skb_frag_walk *walk,
+			 u32 offset, u32 len)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	u32 fraglen;
+
+	BUG_ON(skb->pp_recycle != walk->pp_recycle);
+	if (!walk->nr_frags || offset >= walk->total + walk->initial_offset)
+		return len;
+
+	/* make offset relative to current frag after setting that */
+	offset = __skb_reset_frag_walk(walk, offset);
+	BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
+
+	while (len && walk->fragi < walk->nr_frags) {
+		skb_frag_t *frag = &walk->frags[walk->fragi];
+		skb_frag_t *tofrag = &shinfo->frags[shinfo->nr_frags];
+
+		*tofrag = *frag;
+		if (offset) {
+			tofrag->bv_offset += offset;
+			tofrag->bv_len -= offset;
+			offset = 0;
+		}
+		__skb_frag_ref(tofrag);
+		shinfo->nr_frags++;
+		BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS);
+
+		/* see if we are done */
+		fraglen = tofrag->bv_len;
+		if (len < fraglen) {
+			tofrag->bv_len = len;
+			skb->len += len;
+			skb->data_len += len;
+			return 0;
+		}
+		/* advance to next source fragment */
+		len -= fraglen;		  /* careful, use dst bv_len */
+		skb->len += fraglen;	  /* careful, "   "    "     */
+		skb->data_len += fraglen; /* careful, "   "    "     */
+		walk->past +=
+			frag->bv_len; /* careful, use src bv_len */
+		walk->fragi++;
+	}
+	return len;
+}
+
+/**
+ * skb_copy_bits_seq - copy bits from a skb_seq_state to kernel buffer
+ * @st: source skb_seq_state
+ * @offset: offset in source
+ * @to: destination buffer
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from @offset bytes into the source @st to the destination
+ * buffer @to. `offset` should increase (or be unchanged) with each subsequent
+ * call to this function. If offset needs to decrease from the previous use `st`
+ * should be reset first.
+ */
+static int skb_copy_bits_seq(struct skb_seq_state *st, int offset, void *to, int len)
+{
+	const u8 *data;
+	u32 sqlen;
+
+	for (;;) {
+		sqlen = skb_seq_read(offset, &data, st);
+		if (sqlen == 0)
+			return -ENOMEM;
+		if (sqlen >= len) {
+			memcpy(to, data, len);
+			return 0;
+		}
+		memcpy(to, data, sqlen);
+		to += sqlen;
+		offset += sqlen;
+		len -= sqlen;
+	}
+}
+
+/* ================================== */
+/* IPTFS Trace Event Definitions      */
+/* ================================== */
+
+#define CREATE_TRACE_POINTS
+#include "trace_iptfs.h"
+
+/* ================================== */
+/* IPTFS Receiving (egress) Functions */
+/* ================================== */
+
+/**
+ * iptfs_pskb_add_frags() - Create and add frags into a new sk_buff.
+ * @tpl: template to create new skb from.
+ * @walk: The source for fragments to add.
+ * @off: The offset into @walk to add frags from, also used with @st and
+ *       @copy_len.
+ * @len: The length of data to add covering frags from @walk into @skb.
+ *       This must be <= @skblen.
+ * @st: The sequence state to copy from into the new head skb.
+ * @copy_len: Copy @copy_len bytes from @st at offset @off into the new skb
+ *            linear space.
+ *
+ * Create a new sk_buff `skb` using the template @tpl. Copy @copy_len bytes from
+ * @st into the new skb linear space, and then add shared fragments from the
+ * frag walk for the remaining @len of data (i.e., @len - @copy_len bytes).
+ *
+ * Return: The newly allocated sk_buff `skb` or NULL if an error occurs.
+ */
+static struct sk_buff *iptfs_pskb_add_frags(struct sk_buff *tpl,
+					    struct skb_frag_walk *walk, u32 off,
+					    u32 len, struct skb_seq_state *st,
+					    u32 copy_len)
+{
+	struct sk_buff *skb;
+
+	skb = iptfs_alloc_skb(tpl, copy_len, false);
+	if (!skb)
+		return NULL;
+
+	/* this should not normally be happening */
+	if (!skb_can_add_frags(skb, walk, off + copy_len, len - copy_len)) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	if (copy_len &&
+	    skb_copy_bits_seq(st, off, skb_put(skb, copy_len), copy_len)) {
+		XFRM_INC_STATS(dev_net(st->root_skb->dev),
+			       LINUX_MIB_XFRMINERROR);
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	skb_add_frags(skb, walk, off + copy_len, len - copy_len);
+	return skb;
+}
+
+/**
+ * iptfs_pskb_extract_seq() - Create and load data into a new sk_buff.
+ * @skblen: the total data size for `skb`.
+ * @st: The source for the rest of the data to copy into `skb`.
+ * @off: The offset into @st to copy data from.
+ * @len: The length of data to copy from @st into `skb`. This must be <=
+ *       @skblen.
+ *
+ * Create a new sk_buff `skb` with @skblen of packet data space. If non-zero,
+ * copy @rlen bytes of @runt into `skb`. Then using seq functions copy @len
+ * bytes from @st into `skb` starting from @off.
+ *
+ * It is an error for @len to be greater than the amount of data left in @st.
+ *
+ * Return: The newly allocated sk_buff `skb` or NULL if an error occurs.
+ */
+static struct sk_buff *
+iptfs_pskb_extract_seq(u32 skblen, struct skb_seq_state *st, u32 off, int len)
+{
+	struct sk_buff *skb = iptfs_alloc_skb(st->root_skb, skblen, false);
+
+	if (!skb)
+		return NULL;
+	if (skb_copy_bits_seq(st, off, skb_put(skb, len), len)) {
+		XFRM_INC_STATS(dev_net(st->root_skb->dev),
+			       LINUX_MIB_XFRMINERROR);
+		kfree_skb(skb);
+		return NULL;
+	}
+	return skb;
+}
+
+/**
+ * iptfs_input_save_runt() - save data in xtfs runt space.
+ * @xtfs: xtfs state
+ * @seq: the current sequence
+ * @buf: packet data
+ * @len: length of packet data
+ *
+ * Save the small (`len`) start of a fragmented packet in `buf` in the xtfs data
+ * runt space.
+ */
+static void iptfs_input_save_runt(struct xfrm_iptfs_data *xtfs, u64 seq,
+				  u8 *buf, int len)
+{
+	BUG_ON(xtfs->ra_newskb); /* we won't have a new SKB yet */
+
+	memcpy(xtfs->ra_runt, buf, len);
+
+	xtfs->ra_runtlen = len;
+	xtfs->ra_wantseq = seq + 1;
+}
+
+/**
+ * __iptfs_iphlen() - return the v4/v6 header length using packet data.
+ * @data: pointer at octet with version nibble
+ *
+ * The version data is expected to be valid (i.e., either 4 or 6).
+ */
+static u32 __iptfs_iphlen(u8 *data)
+{
+	struct iphdr *iph = (struct iphdr *)data;
+
+	if (iph->version == 0x4)
+		return sizeof(*iph);
+	BUG_ON(iph->version != 0x6);
+	return sizeof(struct ipv6hdr);
+}
+
+/**
+ * __iptfs_iplen() - return the v4/v6 length using packet data.
+ * @data: pointer to ip (v4/v6) packet header
+ *
+ * Grab the IPv4 or IPv6 length value in the start of the inner packet header
+ * pointed to by `data`. Assumes data len is enough for the length field only.
+ *
+ * The version data is expected to be valid (i.e., either 4 or 6).
+ */
+static u32 __iptfs_iplen(u8 *data)
+{
+	struct iphdr *iph = (struct iphdr *)data;
+
+	if (iph->version == 0x4)
+		return ntohs(iph->tot_len);
+	BUG_ON(iph->version != 0x6);
+	return ntohs(((struct ipv6hdr *)iph)->payload_len) +
+	       sizeof(struct ipv6hdr);
+}
+
+/**
+ * iptfs_complete_inner_skb() - finish preparing the inner packet for gro recv.
+ * @x: xfrm state
+ * @skb: the inner packet
+ *
+ * Finish the standard xfrm processing on the inner packet prior to sending back
+ * through gro_cells_receive. We do this separately b/c we are building a list
+ * of packets in the hopes that one day a list will be taken by
+ * xfrm_input.
+ */
+static void iptfs_complete_inner_skb(struct xfrm_state *x, struct sk_buff *skb)
+{
+	skb_reset_network_header(skb);
+
+	/* The packet is going back through gro_cells_receive no need to
+	 * set this.
+	 */
+	skb_reset_transport_header(skb);
+
+	/* Packet already has checksum value set. */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* Our skb will contain the header data copied when this outer packet
+	 * which contained the start of this inner packet. This is true
+	 * when we allocate a new skb as well as when we reuse the existing skb.
+	 */
+	if (ip_hdr(skb)->version == 0x4) {
+		struct iphdr *iph = ip_hdr(skb);
+
+		if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+			ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, iph);
+		if (!(x->props.flags & XFRM_STATE_NOECN))
+			if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
+				IP_ECN_set_ce(iph);
+
+		skb->protocol = htons(ETH_P_IP);
+	} else {
+		struct ipv6hdr *iph = ipv6_hdr(skb);
+
+		if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+			ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, iph);
+		if (!(x->props.flags & XFRM_STATE_NOECN))
+			if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
+				IP6_ECN_set_ce(skb, iph);
+
+		skb->protocol = htons(ETH_P_IPV6);
+	}
+}
+
+static void __iptfs_reassem_done(struct xfrm_iptfs_data *xtfs, bool free)
+{
+	assert_spin_locked(&xtfs->drop_lock);
+
+	/* We don't care if it works locking takes care of things */
+	hrtimer_try_to_cancel(&xtfs->drop_timer);
+	if (free)
+		kfree_skb(xtfs->ra_newskb);
+	xtfs->ra_newskb = NULL;
+}
+
+/**
+ * iptfs_reassem_done() - In-progress packet is aborted free the state.
+ * @xtfs: xtfs state
+ */
+static void iptfs_reassem_abort(struct xfrm_iptfs_data *xtfs)
+{
+	__iptfs_reassem_done(xtfs, true);
+}
+
+/**
+ * iptfs_reassem_done() - In-progress packet is complete, clear the state.
+ * @xtfs: xtfs state
+ */
+static void iptfs_reassem_done(struct xfrm_iptfs_data *xtfs)
+{
+	__iptfs_reassem_done(xtfs, false);
+}
+
+/**
+ * iptfs_reassem_cont() - Continue the reassembly of an inner packets.
+ * @xtfs: xtfs state
+ * @seq: sequence of current packet
+ * @st: seq read stat for current packet
+ * @skb: current packet
+ * @data: offset into sequential packet data
+ * @blkoff: packet blkoff value
+ * @list: list of skbs to enqueue completed packet on
+ *
+ * Process an IPTFS payload that has a non-zero `blkoff` or when we are
+ * expecting the continuation b/c we have a runt or in-progress packet.
+ */
+static u32 iptfs_reassem_cont(struct xfrm_iptfs_data *xtfs, u64 seq,
+			      struct skb_seq_state *st, struct sk_buff *skb,
+			      u32 data, u32 blkoff, struct list_head *list)
+{
+	struct skb_frag_walk _fragwalk;
+	struct skb_frag_walk *fragwalk = NULL;
+	struct sk_buff *newskb = xtfs->ra_newskb;
+	u32 remaining = skb->len - data;
+	u32 runtlen = xtfs->ra_runtlen;
+	u32 copylen, fraglen, ipremain, iphlen, iphremain, rrem;
+
+	/* Handle packet fragment we aren't expecting */
+	if (!runtlen && !xtfs->ra_newskb)
+		return data + min(blkoff, remaining);
+
+	/* Important to remember that input to this function is an ordered
+	 * packet stream (unless the user disabled the reorder window). Thus if
+	 * we are waiting for, and expecting the next packet so we can continue
+	 * assembly, a newer sequence number indicates older ones are not coming
+	 * (or if they do should be ignored). Technically we can receive older
+	 * ones when the reorder window is disabled; however, the user should
+	 * have disabled fragmentation in this case, and regardless we don't
+	 * deal with it.
+	 *
+	 * blkoff could be zero if the stream is messed up (or it's an all pad
+	 * insertion) be careful to handle that case in each of the below
+	 */
+
+	/* Too old case: This can happen when the reorder window is disabled so
+	 * ordering isn't actually guaranteed.
+	 */
+	if (seq < xtfs->ra_wantseq)
+		return data + remaining;
+
+	/* Too new case: We missed what we wanted cleanup. */
+	if (seq > xtfs->ra_wantseq) {
+		XFRM_INC_STATS(dev_net(skb->dev),
+			       LINUX_MIB_XFRMINIPTFSERROR);
+		goto abandon;
+	}
+
+	if (blkoff == 0) {
+		if ((*skb->data & 0xF0) != 0) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINIPTFSERROR);
+			goto abandon;
+		}
+		/* Handle all pad case, advance expected sequence number.
+		 * (RFC 9347 S2.2.3)
+		 */
+		xtfs->ra_wantseq++;
+		/* will end parsing */
+		return data + remaining;
+	}
+
+	if (runtlen) {
+		BUG_ON(xtfs->ra_newskb);
+
+		/* Regardless of what happens we're done with the runt */
+		xtfs->ra_runtlen = 0;
+
+		/* The start of this inner packet was at the very end of the last
+		 * iptfs payload which didn't include enough for the ip header
+		 * length field. We must have *at least* that now.
+		 */
+		rrem = sizeof(xtfs->ra_runt) - runtlen;
+		if (remaining < rrem || blkoff < rrem) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINIPTFSERROR);
+			goto abandon;
+		}
+
+		/* fill in the runt data */
+		if (skb_copy_bits_seq(st, data, &xtfs->ra_runt[runtlen],
+				      rrem)) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINBUFFERERROR);
+			goto abandon;
+		}
+
+		/* We have enough data to get the ip length value now,
+		 * allocate an in progress skb
+		 */
+		ipremain = __iptfs_iplen(xtfs->ra_runt);
+		if (ipremain < sizeof(xtfs->ra_runt)) {
+			/* length has to be at least runtsize large */
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINIPTFSERROR);
+			goto abandon;
+		}
+
+		/* For the runt case we don't attempt sharing currently. NOTE:
+		 * Currently, this IPTFS implementation will not create runts.
+		 */
+
+		newskb = iptfs_alloc_skb(skb, ipremain, false);
+		if (!newskb) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINERROR);
+			goto abandon;
+		}
+		xtfs->ra_newskb = newskb;
+
+		/* Copy the runt data into the buffer, but leave data
+		 * pointers the same as normal non-runt case. The extra `rrem`
+		 * recopied bytes are basically cacheline free. Allows using
+		 * same logic below to complete.
+		 */
+		memcpy(skb_put(newskb, runtlen), xtfs->ra_runt,
+		       sizeof(xtfs->ra_runt));
+	}
+
+	/* Continue reassembling the packet */
+	ipremain = __iptfs_iplen(newskb->data);
+	iphlen = __iptfs_iphlen(newskb->data);
+
+	/* Sanity check, we created the newskb knowing the IP length so the IP
+	 * length can't now be shorter.
+	 */
+	BUG_ON(newskb->len > ipremain);
+
+	ipremain -= newskb->len;
+	if (blkoff < ipremain) {
+		/* Corrupt data, we don't have enough to complete the packet */
+		XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINIPTFSERROR);
+		goto abandon;
+	}
+
+	/* We want the IP header in linear space */
+	if (newskb->len < iphlen)  {
+		iphremain = iphlen - newskb->len;
+		if (blkoff < iphremain) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINIPTFSERROR);
+			goto abandon;
+		}
+		fraglen = min(blkoff, remaining);
+		copylen = min(fraglen, iphremain);
+		BUG_ON(skb_tailroom(newskb) < copylen);
+		if (skb_copy_bits_seq(st, data, skb_put(newskb, copylen), copylen)) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINBUFFERERROR);
+			goto abandon;
+		}
+		/* this is a silly condition that might occur anyway */
+		if (copylen < iphremain) {
+			xtfs->ra_wantseq++;
+			return data + fraglen;
+		}
+		/* update data and things derived from it */
+		data += copylen;
+		blkoff -= copylen;
+		remaining -= copylen;
+		ipremain -= copylen;
+	}
+
+	fraglen = min(blkoff, remaining);
+	copylen = min(fraglen, ipremain);
+
+	/* If we may have the opportunity to share prepare a fragwalk. */
+	if (!skb_has_frag_list(skb) && !skb_has_frag_list(newskb) &&
+	    (skb->head_frag || skb->len == skb->data_len) &&
+	    skb->pp_recycle == newskb->pp_recycle) {
+		fragwalk = &_fragwalk;
+		skb_prepare_frag_walk(skb, data, fragwalk);
+	}
+
+	/* Try share then copy. */
+	if (fragwalk && skb_can_add_frags(newskb, fragwalk, data, copylen)) {
+		u32 leftover;
+
+		leftover = skb_add_frags(newskb, fragwalk, data, copylen);
+		BUG_ON(leftover != 0);
+	} else {
+		/* We verified this was true in the main receive routine */
+		BUG_ON(skb_tailroom(newskb) < copylen);
+
+		/* copy fragment data into newskb */
+		if (skb_copy_bits_seq(st, data, skb_put(newskb, copylen), copylen)) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINBUFFERERROR);
+			goto abandon;
+		}
+	}
+
+	if (copylen < ipremain) {
+		xtfs->ra_wantseq++;
+	} else {
+		/* We are done with packet reassembly! */
+		BUG_ON(copylen != ipremain);
+		iptfs_reassem_done(xtfs);
+		iptfs_complete_inner_skb(xtfs->x, newskb);
+		list_add_tail(&newskb->list, list);
+	}
+
+	/* will continue on to new data block or end */
+	return data + fraglen;
+
+abandon:
+	if (xtfs->ra_newskb) {
+		iptfs_reassem_abort(xtfs);
+	} else {
+		xtfs->ra_runtlen = 0;
+		xtfs->ra_wantseq = 0;
+	}
+	/* skip past fragment, maybe to end */
+	return data + min(blkoff, remaining);
+}
+
+/**
+ * iptfs_input_ordered() - handle next in order IPTFS payload.
+ * @x: xfrm state
+ * @skb: current packet
+ *
+ * Process the IPTFS payload in `skb` and consume it afterwards.
+ */
+static int iptfs_input_ordered(struct xfrm_state *x, struct sk_buff *skb)
+{
+	u8 hbytes[sizeof(struct ipv6hdr)];
+	struct ip_iptfs_cc_hdr iptcch;
+	struct skb_seq_state skbseq;
+	struct skb_frag_walk _fragwalk;
+	struct skb_frag_walk *fragwalk = NULL;
+	struct list_head sublist; /* rename this it's just a list */
+	struct sk_buff *first_skb, *defer, *next;
+	const unsigned char *old_mac;
+	struct xfrm_iptfs_data *xtfs;
+	struct ip_iptfs_hdr *ipth;
+	struct iphdr *iph;
+	struct net *net;
+	u32 remaining, first_iplen, iplen, iphlen, data, tail;
+	u32 blkoff, capturelen;
+	u64 seq;
+
+	xtfs = x->mode_data;
+	net = dev_net(skb->dev);
+	first_skb = NULL;
+	defer = NULL;
+
+	seq = __esp_seq(skb);
+
+	/* Large enough to hold both types of header */
+	ipth = (struct ip_iptfs_hdr *)&iptcch;
+
+	/* Save the old mac header if set */
+	old_mac = skb_mac_header_was_set(skb) ? skb_mac_header(skb) : NULL;
+
+	skb_prepare_seq_read(skb, 0, skb->len, &skbseq);
+
+	/* Get the IPTFS header and validate it */
+
+	if (skb_copy_bits_seq(&skbseq, 0, ipth, sizeof(*ipth))) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
+		goto done;
+	}
+	data = sizeof(*ipth);
+
+	trace_iptfs_egress_recv(skb, xtfs, htons(ipth->block_offset));
+
+	/* Set data past the basic header */
+	if (ipth->subtype == IPTFS_SUBTYPE_CC) {
+		/* Copy the rest of the CC header */
+		remaining = sizeof(iptcch) - sizeof(*ipth);
+		if (skb_copy_bits_seq(&skbseq, data, ipth + 1, remaining)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
+			goto done;
+		}
+		data += remaining;
+	} else if (ipth->subtype != IPTFS_SUBTYPE_BASIC) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
+		goto done;
+	}
+
+	if (ipth->flags != 0) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
+		goto done;
+	}
+
+	INIT_LIST_HEAD(&sublist);
+
+	/* Handle fragment at start of payload, and/or waiting reassembly. */
+
+	blkoff = ntohs(ipth->block_offset);
+	/* check before locking i.e., maybe */
+	if (blkoff || xtfs->ra_runtlen || xtfs->ra_newskb) {
+		spin_lock(&xtfs->drop_lock);
+
+		/* check again after lock */
+		if (blkoff || xtfs->ra_runtlen || xtfs->ra_newskb) {
+			data = iptfs_reassem_cont(xtfs, seq, &skbseq, skb, data,
+						  blkoff, &sublist);
+		}
+
+		spin_unlock(&xtfs->drop_lock);
+	}
+
+	/* New packets */
+
+	tail = skb->len;
+	BUG_ON(xtfs->ra_newskb && data < tail);
+
+	while (data < tail) {
+		u32 protocol = 0;
+
+		/* Gather information on the next data block.
+		 * `data` points to the start of the data block.
+		 */
+		remaining = tail - data;
+
+		/* try and copy enough bytes to read length from ipv4/ipv6 */
+		iphlen = min_t(u32, remaining, 6);
+		if (skb_copy_bits_seq(&skbseq, data, hbytes, iphlen)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
+			goto done;
+		}
+
+		iph = (struct iphdr *)hbytes;
+		if (iph->version == 0x4) {
+			/* must have at least tot_len field present */
+			if (remaining < 4) {
+				/* save the bytes we have, advance data and exit */
+				iptfs_input_save_runt(xtfs, seq, hbytes,
+						      remaining);
+				data += remaining;
+				break;
+			}
+
+			iplen = htons(iph->tot_len);
+			iphlen = iph->ihl << 2;
+			protocol = htons(ETH_P_IP);
+			XFRM_MODE_SKB_CB(skbseq.root_skb)->tos = iph->tos;
+		} else if (iph->version == 0x6) {
+			/* must have at least payload_len field present */
+			if (remaining < 6) {
+				/* save the bytes we have, advance data and exit */
+				iptfs_input_save_runt(xtfs, seq, hbytes,
+						      remaining);
+				data += remaining;
+				break;
+			}
+
+			iplen = htons(((struct ipv6hdr *)hbytes)->payload_len);
+			iplen += sizeof(struct ipv6hdr);
+			iphlen = sizeof(struct ipv6hdr);
+			protocol = htons(ETH_P_IPV6);
+			XFRM_MODE_SKB_CB(skbseq.root_skb)->tos =
+				ipv6_get_dsfield((struct ipv6hdr *)iph);
+		} else if (iph->version == 0x0) {
+			/* pad */
+			data = tail;
+			break;
+		} else {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
+			goto done;
+		}
+
+		if (unlikely(skbseq.stepped_offset)) {
+			/* We need to reset our seq read, it can't backup at
+			 * this point.
+			 */
+			struct sk_buff *save = skbseq.root_skb;
+
+			skb_abort_seq_read(&skbseq);
+			skb_prepare_seq_read(save, data, tail, &skbseq);
+		}
+
+		if (first_skb) {
+			skb = NULL;
+		} else {
+			first_skb = skb;
+			first_iplen = iplen;
+			fragwalk = NULL;
+
+			/* We are going to skip over `data` bytes to reach the
+			 * start of the IP header of `iphlen` len for `iplen`
+			 * inner packet.
+			 */
+
+			if (skb_has_frag_list(skb)) {
+				defer = skb;
+				skb = NULL;
+			} else if (data + iphlen <= skb_headlen(skb) &&
+				   /* make sure our header is 32-bit aligned? */
+				   /* ((uintptr_t)(skb->data + data) & 0x3) == 0 && */
+				   skb_tailroom(skb) + tail - data >= iplen) {
+				/* Reuse the received skb.
+				 *
+				 * We have enough headlen to pull past any
+				 * initial fragment data, leaving at least the
+				 * IP header in the linear buffer space.
+				 *
+				 * For linear buffer space we only require that
+				 * linear buffer space is large enough to
+				 * eventually hold the entire reassembled
+				 * packet (by including tailroom in the check).
+				 *
+				 * For non-linear tailroom is 0 and so we only
+				 * re-use if the entire packet is present
+				 * already.
+				 *
+				 * NOTE: there are many more options for
+				 * sharing, KISS for now. Also, this can produce
+				 * skb's with the IP header unaligned to 32
+				 * bits. If that ends up being a problem then a
+				 * check should be added to the conditional
+				 * above that the header lies on a 32-bit
+				 * boundary as well.
+				 */
+				skb_pull(skb, data);
+
+				/* our range just changed */
+				data = 0;
+				tail = skb->len;
+				remaining = skb->len;
+
+				skb->protocol = protocol;
+				skb_mac_header_rebuild(skb);
+				if (skb->mac_len)
+					eth_hdr(skb)->h_proto = skb->protocol;
+
+				/* all pointers could be changed now reset walk */
+				skb_abort_seq_read(&skbseq);
+				skb_prepare_seq_read(skb, data, tail, &skbseq);
+			} else if (skb->head_frag &&
+				   /* We have the IP header right now */
+				   remaining >= iphlen) {
+				fragwalk = &_fragwalk;
+				skb_prepare_frag_walk(skb, data, fragwalk);
+				defer = skb;
+				skb = NULL;
+			} else {
+				/* We couldn't reuse the input skb so allocate a
+				 * new one.
+				 */
+				defer = skb;
+				skb = NULL;
+			}
+
+			/* Don't trim `first_skb` until the end as we are
+			 * walking that data now.
+			 */
+		}
+
+		capturelen = min(iplen, remaining);
+		if (!skb) {
+			if (!fragwalk ||
+			    /* Large enough to be worth sharing */
+			    iplen < IPTFS_PKT_SHARE_MIN ||
+			    /* Have IP header + some data to share. */
+			    capturelen <= iphlen ||
+			    /* Try creating skb and adding frags */
+			    !(skb = iptfs_pskb_add_frags(first_skb, fragwalk,
+							 data, capturelen,
+							 &skbseq, iphlen))) {
+				skb = iptfs_pskb_extract_seq(iplen, &skbseq,
+							     data, capturelen);
+			}
+			if (!skb) {
+				/* skip to next packet or done */
+				data += capturelen;
+				continue;
+			}
+			BUG_ON(skb->len != capturelen);
+
+			skb->protocol = protocol;
+			if (old_mac) {
+				/* rebuild the mac header */
+				skb_set_mac_header(skb, -first_skb->mac_len);
+				memcpy(skb_mac_header(skb), old_mac,
+				       first_skb->mac_len);
+				eth_hdr(skb)->h_proto = skb->protocol;
+			}
+		}
+
+		data += capturelen;
+
+		if (skb->len < iplen) {
+			BUG_ON(data != tail);
+			BUG_ON(xtfs->ra_newskb);
+
+			/* Start reassembly */
+			spin_lock(&xtfs->drop_lock);
+
+			xtfs->ra_newskb = skb;
+			xtfs->ra_wantseq = seq + 1;
+			if (!hrtimer_is_queued(&xtfs->drop_timer)) {
+				/* softirq blocked lest the timer fire and interrupt us */
+				BUG_ON(!in_interrupt());
+				hrtimer_start(&xtfs->drop_timer,
+					      xtfs->drop_time_ns,
+					      IPTFS_HRTIMER_MODE);
+			}
+
+			spin_unlock(&xtfs->drop_lock);
+
+			break;
+		}
+
+		iptfs_complete_inner_skb(x, skb);
+		list_add_tail(&skb->list, &sublist);
+	}
+
+	if (data != tail)
+		/* this should not happen from the above code */
+		XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINIPTFSERROR);
+
+	if (first_skb && first_iplen && !defer && first_skb != xtfs->ra_newskb) {
+		/* first_skb is queued b/c !defer and not partial */
+		if (pskb_trim(first_skb, first_iplen)) {
+			/* error trimming */
+			list_del(&first_skb->list);
+			defer = first_skb;
+		}
+		first_skb->ip_summed = CHECKSUM_NONE;
+	}
+
+	/* Send the packets! */
+	list_for_each_entry_safe(skb, next, &sublist, list) {
+		BUG_ON(skb == defer);
+		skb_list_del_init(skb);
+		if (xfrm_input(skb, 0, 0, -3))
+			kfree_skb(skb);
+	}
+
+done:
+	skb = skbseq.root_skb;
+	skb_abort_seq_read(&skbseq);
+
+	if (defer) {
+		consume_skb(defer);
+	} else if (!first_skb) {
+		/* skb is the original passed in skb, but we didn't get far
+		 * enough to process it as the first_skb, if we had it would
+		 * either be save in ra_newskb, trimmed and sent on as an skb or
+		 * placed in defer to be freed.
+		 */
+		BUG_ON(!skb);
+		kfree_skb(skb);
+	}
+
+	return 0;
+}
+
+/* ------------------------------- */
+/* Input (Egress) Re-ordering Code */
+/* ------------------------------- */
+
+static void __vec_shift(struct xfrm_iptfs_data *xtfs, u32 shift)
+{
+	u32 savedlen = xtfs->w_savedlen;
+
+	if (shift > savedlen)
+		shift = savedlen;
+	if (shift != savedlen)
+		memcpy(xtfs->w_saved, xtfs->w_saved + shift,
+		       (savedlen - shift) * sizeof(*xtfs->w_saved));
+	memset(xtfs->w_saved + savedlen - shift, 0,
+	       shift * sizeof(*xtfs->w_saved));
+	xtfs->w_savedlen -= shift;
+}
+
+static int __reorder_past(struct xfrm_iptfs_data *xtfs, struct sk_buff *inskb,
+			  struct list_head *freelist, u32 *fcount)
+{
+	list_add_tail(&inskb->list, freelist);
+	(*fcount)++;
+	return 0;
+}
+
+static u32 __reorder_drop(struct xfrm_iptfs_data *xtfs, struct list_head *list)
+
+{
+	struct skb_wseq *s, *se;
+	const u32 savedlen = xtfs->w_savedlen;
+	time64_t now = ktime_get_raw_fast_ns();
+	u32 count = 0;
+	u32 scount = 0;
+
+	BUG_ON(!savedlen);
+	if (xtfs->w_saved[0].drop_time > now)
+		goto set_timer;
+
+	++xtfs->w_wantseq;
+
+	/* Keep flushing packets until we reach a drop time greater than now. */
+	s = xtfs->w_saved;
+	se = s + savedlen;
+	do {
+		/* Walking past empty slots until we reach a packet */
+		for (; s < se && !s->skb; s++)
+			if (s->drop_time > now)
+				goto outerdone;
+		/* Sending packets until we hit another empty slot. */
+		for (; s < se && s->skb; scount++, s++)
+			list_add_tail(&s->skb->list, list);
+	} while (s < se);
+outerdone:
+
+	count = s - xtfs->w_saved;
+	if (count) {
+		xtfs->w_wantseq += count;
+
+		/* Shift handled slots plus final empty slot into slot 0. */
+		__vec_shift(xtfs, count);
+	}
+
+	if (xtfs->w_savedlen) {
+set_timer:
+		/* Drifting is OK */
+		hrtimer_start(&xtfs->drop_timer,
+			      xtfs->w_saved[0].drop_time - now,
+			      IPTFS_HRTIMER_MODE);
+	}
+	return scount;
+}
+
+static u32 __reorder_this(struct xfrm_iptfs_data *xtfs, struct sk_buff *inskb,
+			  struct list_head *list)
+{
+	struct skb_wseq *s, *se;
+	const u32 savedlen = xtfs->w_savedlen;
+	u32 count = 0;
+
+	/* Got what we wanted. */
+	list_add_tail(&inskb->list, list);
+	++xtfs->w_wantseq;
+	if (!savedlen)
+		return 1;
+
+	/* Flush remaining consecutive packets. */
+
+	/* Keep sending until we hit another missed pkt. */
+	for (s = xtfs->w_saved, se = s + savedlen; s < se && s->skb; s++)
+		list_add_tail(&s->skb->list, list);
+	count = s - xtfs->w_saved;
+	if (count)
+		xtfs->w_wantseq += count;
+
+	/* Shift handled slots plus final empty slot into slot 0. */
+	__vec_shift(xtfs, count + 1);
+
+	return count + 1;
+}
+
+/* Set the slot's drop time and all the empty slots below it until reaching a
+ * filled slot which will already be set.
+ */
+static void iptfs_set_window_drop_times(struct xfrm_iptfs_data *xtfs, int index)
+{
+	const u32 savedlen = xtfs->w_savedlen;
+	struct skb_wseq *s = xtfs->w_saved;
+	time64_t drop_time;
+
+	assert_spin_locked(&xtfs->drop_lock);
+
+	if (savedlen > index + 1) {
+		/* we are below another, our drop time and the timer are already set */
+		BUG_ON(xtfs->w_saved[index + 1].drop_time !=
+		       xtfs->w_saved[index].drop_time);
+		return;
+	}
+	/* we are the most future so get a new drop time. */
+	drop_time = ktime_get_raw_fast_ns();
+	drop_time += xtfs->drop_time_ns;
+
+	/* Walk back through the array setting drop times as we go */
+	s[index].drop_time = drop_time;
+	while (index-- > 0 && !s[index].skb)
+		s[index].drop_time = drop_time;
+
+	/* If we walked all the way back, schedule the drop timer if needed */
+	if (index == -1 && !hrtimer_is_queued(&xtfs->drop_timer))
+		hrtimer_start(&xtfs->drop_timer, xtfs->drop_time_ns,
+			      IPTFS_HRTIMER_MODE);
+}
+
+static u32 __reorder_future_fits(struct xfrm_iptfs_data *xtfs,
+				 struct sk_buff *inskb,
+				 struct list_head *freelist, u32 *fcount)
+{
+	const u32 nslots = xtfs->cfg.reorder_win_size + 1;
+	const u64 inseq = __esp_seq(inskb);
+	const u64 wantseq = xtfs->w_wantseq;
+	const u64 distance = inseq - wantseq;
+	const u32 savedlen = xtfs->w_savedlen;
+	const u32 index = distance - 1;
+
+	BUG_ON(distance >= nslots);
+
+	/* Handle future sequence number received which fits in the window.
+	 *
+	 * We know we don't have the seq we want so we won't be able to flush
+	 * anything.
+	 */
+
+	/* slot count is 4, saved size is 3 savedlen is 2
+	 *
+	 * "window boundary" is based on the fixed window size
+	 * distance is also slot number
+	 * index is an array index (i.e., - 1 of slot)
+	 * : : - implicit NULL after array len
+	 *
+	 *          +--------- used length (savedlen == 2)
+	 *          |   +----- array size (nslots - 1 == 3)
+	 *          |   |   + window boundary (nslots == 4)
+	 *          V   V | V
+	 *                |
+	 *  0   1   2   3 |   slot number
+	 * ---  0   1   2 |   array index
+	 *     [-] [b] : :|   array
+	 *
+	 * "2" "3" "4" *5*|   seq numbers
+	 *
+	 * We receive seq number 5
+	 * distance == 3 [inseq(5) - w_wantseq(2)]
+	 * index == 2 [distance(6) - 1]
+	 */
+
+	if (xtfs->w_saved[index].skb) {
+		/* a dup of a future */
+		list_add_tail(&inskb->list, freelist);
+		(*fcount)++;
+		return 0;
+	}
+
+	xtfs->w_saved[index].skb = inskb;
+	xtfs->w_savedlen = max(savedlen, index + 1);
+	iptfs_set_window_drop_times(xtfs, index);
+
+	return 0;
+}
+
+static u32 __reorder_future_shifts(struct xfrm_iptfs_data *xtfs,
+				   struct sk_buff *inskb,
+				   struct list_head *list,
+				   struct list_head *freelist, u32 *fcount)
+{
+	const u32 nslots = xtfs->cfg.reorder_win_size + 1;
+	const u64 inseq = __esp_seq(inskb);
+	u32 savedlen = xtfs->w_savedlen;
+	u64 wantseq = xtfs->w_wantseq;
+	struct sk_buff *slot0 = NULL;
+	u64 last_drop_seq = xtfs->w_wantseq;
+	u64 distance, extra_drops, missed, s0seq;
+	u32 count = 0;
+	struct skb_wseq *wnext;
+	u32 beyond, shifting, slot;
+
+	BUG_ON(inseq <= wantseq);
+	distance = inseq - wantseq;
+	BUG_ON(distance <= nslots - 1);
+	beyond = distance - (nslots - 1);
+	missed = 0;
+
+	/* Handle future sequence number received.
+	 *
+	 * IMPORTANT: we are at least advancing w_wantseq (i.e., wantseq) by 1
+	 * b/c we are beyond the window boundary.
+	 *
+	 * We know we don't have the wantseq so that counts as a drop.
+	 */
+
+	/* ex: slot count is 4, array size is 3 savedlen is 2, slot 0 is the
+	 * missing sequence number.
+	 *
+	 * the final slot at savedlen (index savedlen - 1) is always occupied.
+	 *
+	 * beyond is "beyond array size" not savedlen.
+	 *
+	 *          +--------- array length (savedlen == 2)
+	 *          |   +----- array size (nslots - 1 == 3)
+	 *          |   |   +- window boundary (nslots == 4)
+	 *          V   V | V
+	 *                |
+	 *  0   1   2   3 |   slot number
+	 * ---  0   1   2 |   array index
+	 *     [b] [c] : :|   array
+	 *                |
+	 * "2" "3" "4" "5"|*6*  seq numbers
+	 *
+	 * We receive seq number 6
+	 * distance == 4 [inseq(6) - w_wantseq(2)]
+	 * newslot == distance
+	 * index == 3 [distance(4) - 1]
+	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
+	 * shifting == 1 [min(savedlen(2), beyond(1)]
+	 * slot0_skb == [b], and should match w_wantseq
+	 *
+	 *                +--- window boundary (nslots == 4)
+	 *  0   1   2   3 | 4   slot number
+	 * ---  0   1   2 | 3   array index
+	 *     [b] : : : :|     array
+	 * "2" "3" "4" "5" *6*  seq numbers
+	 *
+	 * We receive seq number 6
+	 * distance == 4 [inseq(6) - w_wantseq(2)]
+	 * newslot == distance
+	 * index == 3 [distance(4) - 1]
+	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
+	 * shifting == 1 [min(savedlen(1), beyond(1)]
+	 * slot0_skb == [b] and should match w_wantseq
+	 *
+	 *                +-- window boundary (nslots == 4)
+	 *  0   1   2   3 | 4   5   6   slot number
+	 * ---  0   1   2 | 3   4   5   array index
+	 *     [-] [c] : :|             array
+	 * "2" "3" "4" "5" "6" "7" *8*  seq numbers
+	 *
+	 * savedlen = 2, beyond = 3
+	 * iter 1: slot0 == NULL, missed++, lastdrop = 2 (2+1-1), slot0 = [-]
+	 * iter 2: slot0 == NULL, missed++, lastdrop = 3 (2+2-1), slot0 = [c]
+	 * 2 < 3, extra = 1 (3-2), missed += extra, lastdrop = 4 (2+2+1-1)
+	 *
+	 * We receive seq number 8
+	 * distance == 6 [inseq(8) - w_wantseq(2)]
+	 * newslot == distance
+	 * index == 5 [distance(6) - 1]
+	 * beyond == 3 [newslot(6) - lastslot((nslots(4) - 1))]
+	 * shifting == 2 [min(savedlen(2), beyond(3)]
+	 *
+	 * slot0_skb == NULL changed from [b] when "savedlen < beyond" is true.
+	 */
+
+	/* Now send any packets that are being shifted out of saved, and account
+	 * for missing packets that are exiting the window as we shift it.
+	 */
+
+	/* If savedlen > beyond we are shifting some, else all. */
+	shifting = min(savedlen, beyond);
+
+	/* slot0 is the buf that just shifted out and into slot0 */
+	slot0 = NULL;
+	s0seq = wantseq;
+	last_drop_seq = s0seq;
+	wnext = xtfs->w_saved;
+	for (slot = 1; slot <= shifting; slot++, wnext++) {
+		/* handle what was in slot0 before we occupy it */
+		if (!slot0) {
+			last_drop_seq = s0seq;
+			missed++;
+		} else {
+			list_add_tail(&slot0->list, list);
+			count++;
+		}
+		s0seq++;
+		slot0 = wnext->skb;
+		wnext->skb = NULL;
+	}
+
+	/* slot0 is now either NULL (in which case it's what we now are waiting
+	 * for, or a buf in which case we need to handle it like we received it;
+	 * however, we may be advancing past that buffer as well..
+	 */
+
+	/* Handle case where we need to shift more than we had saved, slot0 will
+	 * be NULL iff savedlen is 0, otherwise slot0 will always be
+	 * non-NULL b/c we shifted the final element, which is always set if
+	 * there is any saved, into slot0.
+	 */
+	if (savedlen < beyond) {
+		extra_drops = beyond - savedlen;
+		if (savedlen == 0) {
+			BUG_ON(slot0);
+			s0seq += extra_drops;
+			last_drop_seq = s0seq - 1;
+		} else {
+			extra_drops--; /* we aren't dropping what's in slot0 */
+			BUG_ON(!slot0);
+			list_add_tail(&slot0->list, list);
+			/* if extra_drops then we are going past this slot0
+			 * so we can safely advance last_drop_seq
+			 */
+			if (extra_drops)
+				last_drop_seq = s0seq + extra_drops;
+			s0seq += extra_drops + 1;
+			count++;
+		}
+		missed += extra_drops;
+		slot0 = NULL;
+		/* slot0 has had an empty slot pushed into it */
+	}
+	(void)last_drop_seq;	/* we want this for CC code */
+
+	/* Remove the entries */
+	__vec_shift(xtfs, beyond);
+
+	/* Advance want seq */
+	xtfs->w_wantseq += beyond;
+
+	/* Process drops here when implementing congestion control */
+
+	/* We've shifted. plug the packet in at the end. */
+	xtfs->w_savedlen = nslots - 1;
+	xtfs->w_saved[xtfs->w_savedlen - 1].skb = inskb;
+	iptfs_set_window_drop_times(xtfs, xtfs->w_savedlen - 1);
+
+	/* if we don't have a slot0 then we must wait for it */
+	if (!slot0)
+		return count;
+
+	/* If slot0, seq must match new want seq */
+	BUG_ON(xtfs->w_wantseq != __esp_seq(slot0));
+
+	/* slot0 is valid, treat like we received expected. */
+	count += __reorder_this(xtfs, slot0, list);
+	return count;
+}
+
+/* Receive a new packet into the reorder window. Return a list of ordered
+ * packets from the window.
+ */
+static u32 iptfs_input_reorder(struct xfrm_iptfs_data *xtfs,
+			       struct sk_buff *inskb, struct list_head *list,
+			       struct list_head *freelist, u32 *fcount)
+{
+	const u32 nslots = xtfs->cfg.reorder_win_size + 1;
+	u64 inseq = __esp_seq(inskb);
+	u64 wantseq;
+
+	assert_spin_locked(&xtfs->drop_lock);
+
+	if (unlikely(!xtfs->w_seq_set)) {
+		xtfs->w_seq_set = true;
+		xtfs->w_wantseq = inseq;
+	}
+	wantseq = xtfs->w_wantseq;
+
+	if (likely(inseq == wantseq))
+		return __reorder_this(xtfs, inskb, list);
+	else if (inseq < wantseq)
+		return __reorder_past(xtfs, inskb, freelist, fcount);
+	else if ((inseq - wantseq) < nslots)
+		return __reorder_future_fits(xtfs, inskb, freelist, fcount);
+	else
+		return __reorder_future_shifts(xtfs, inskb, list, freelist,
+					       fcount);
+}
+
+/**
+ * iptfs_drop_timer() - Handle drop timer expiry.
+ * @me: the timer
+ *
+ * This is similar to our input function.
+ *
+ * The drop timer is set when we start an in progress reassembly, and also when
+ * we save a future packet in the window saved array.
+ *
+ * NOTE packets in the save window are always newer WRT drop times as
+ * they get further in the future. i.e. for:
+ *
+ *    if slots (S0, S1, ... Sn) and `Dn` is the drop time for slot `Sn`,
+ *    then D(n-1) <= D(n).
+ *
+ * So, regardless of why the timer is firing we can always discard any inprogress
+ * fragment; either it's the reassembly timer, or slot 0 is going to be
+ * dropped as S0 must have the most recent drop time, and slot 0 holds the
+ * continuation fragment of the in progress packet.
+ */
+static enum hrtimer_restart iptfs_drop_timer(struct hrtimer *me)
+{
+	struct sk_buff *skb, *next;
+	struct list_head freelist, list;
+	struct xfrm_iptfs_data *xtfs;
+	struct xfrm_state *x;
+	u32 count;
+
+	xtfs = container_of(me, typeof(*xtfs), drop_timer);
+	x = xtfs->x;
+
+	spin_lock(&xtfs->drop_lock);
+
+	INIT_LIST_HEAD(&list);
+	INIT_LIST_HEAD(&freelist);
+
+	/* Drop any in progress packet */
+
+	if (xtfs->ra_newskb) {
+		kfree_skb(xtfs->ra_newskb);
+		xtfs->ra_newskb = NULL;
+	}
+
+	/* Now drop as many packets as we should from the reordering window
+	 * saved array
+	 */
+	count = xtfs->w_savedlen ? __reorder_drop(xtfs, &list) : 0;
+
+	spin_unlock(&xtfs->drop_lock);
+
+	if (count) {
+		list_for_each_entry_safe(skb, next, &list, list) {
+			skb_list_del_init(skb);
+			(void)iptfs_input_ordered(x, skb);
+		}
+	}
+	return HRTIMER_NORESTART;
+}
+
+/**
+ * iptfs_input() - handle receipt of iptfs payload
+ * @x: xfrm state
+ * @skb: the packet
+ *
+ * We have an IPTFS payload order it if needed, then process newly in order
+ * packets.
+ */
+static int iptfs_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct list_head freelist, list;
+	struct xfrm_iptfs_data *xtfs = x->mode_data;
+	struct sk_buff *next;
+	u32 count, fcount;
+
+	/* Fast path for no reorder window. */
+	if (xtfs->cfg.reorder_win_size == 0) {
+		iptfs_input_ordered(x, skb);
+		goto done;
+	}
+
+	/* Fetch list of in-order packets from the reordering window as well as
+	 * a list of buffers we need to now free.
+	 */
+	INIT_LIST_HEAD(&list);
+	INIT_LIST_HEAD(&freelist);
+	fcount = 0;
+
+	spin_lock(&xtfs->drop_lock);
+	count = iptfs_input_reorder(xtfs, skb, &list, &freelist, &fcount);
+	spin_unlock(&xtfs->drop_lock);
+
+	if (count) {
+		list_for_each_entry_safe(skb, next, &list, list) {
+			skb_list_del_init(skb);
+			(void)iptfs_input_ordered(x, skb);
+		}
+	}
+
+	if (fcount) {
+		list_for_each_entry_safe(skb, next, &freelist, list) {
+			skb_list_del_init(skb);
+			kfree_skb(skb);
+		}
+	}
+done:
+	/* We always have dealt with the input SKB, either we are re-using it,
+	 * or we have freed it. Return EINPROGRESS so that xfrm_input stops
+	 * processing it.
+	 */
+	return -EINPROGRESS;
+}
+
+/* ================================= */
+/* IPTFS Sending (ingress) Functions */
+/* ================================= */
+
+/* ------------------------- */
+/* Enqueue to send functions */
+/* ------------------------- */
+
+/**
+ * iptfs_enqueue() - enqueue packet if ok to send.
+ * @xtfs: xtfs state
+ * @skb: the packet
+ *
+ * Return: true if packet enqueued.
+ */
+static bool iptfs_enqueue(struct xfrm_iptfs_data *xtfs, struct sk_buff *skb)
+{
+	u64 newsz = xtfs->queue_size + skb->len;
+	struct iphdr *iph;
+
+	assert_spin_locked(&xtfs->x->lock);
+
+	if (newsz > xtfs->cfg.max_queue_size)
+		return false;
+
+	/* Set ECN CE if we are above our ECN queue threshold */
+	if (newsz > xtfs->ecn_queue_size) {
+		iph = ip_hdr(skb);
+		if (iph->version == 4)
+			IP_ECN_set_ce(iph);
+		else if (iph->version == 6)
+			IP6_ECN_set_ce(skb, ipv6_hdr(skb));
+	}
+
+	__skb_queue_tail(&xtfs->queue, skb);
+	xtfs->queue_size += skb->len;
+	return true;
+}
+
+static int iptfs_get_cur_pmtu(struct xfrm_state *x, struct xfrm_iptfs_data *xtfs,
+			      struct sk_buff *skb)
+{
+	struct xfrm_dst *xdst = (struct xfrm_dst *)skb_dst(skb);
+	u32 payload_mtu = xtfs->payload_mtu;
+	u32 pmtu = __iptfs_get_inner_mtu(x, xdst->child_mtu_cached);
+
+	if (payload_mtu && payload_mtu < pmtu)
+		pmtu = payload_mtu;
+
+	return pmtu;
+}
+
+static int iptfs_is_too_big(struct sock *sk, struct sk_buff *skb, u32 pmtu)
+{
+	if (skb->len <= pmtu)
+		return 0;
+
+	/* We only send ICMP too big if the user has configured us as
+	 * dont-fragment.
+	 */
+	XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMOUTERROR);
+
+	if (sk) {
+		xfrm_local_error(skb, pmtu);
+	} else if (ip_hdr(skb)->version == 4) {
+		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+			  htonl(pmtu));
+	} else {
+		WARN_ON_ONCE(ip_hdr(skb)->version != 6);
+		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, pmtu);
+	}
+	return 1;
+}
+
+/* IPv4/IPv6 packet ingress to IPTFS tunnel, arrange to send in IPTFS payload
+ * (i.e., aggregating or fragmenting as appropriate).
+ * This is set in dst->output for an SA.
+ */
+static int iptfs_output_collect(struct net *net, struct sock *sk,
+				struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x = dst->xfrm;
+	struct xfrm_iptfs_data *xtfs = x->mode_data;
+	struct sk_buff *segs, *nskb;
+	u32 pmtu = 0;
+	bool ok = true;
+	bool was_gso;
+
+	/* We have hooked into dst_entry->output which means we have skipped the
+	 * protocol specific netfilter (see xfrm4_output, xfrm6_output).
+	 * when our timer runs we will end up calling xfrm_output directly on
+	 * the encapsulated traffic.
+	 *
+	 * For both cases this is the NF_INET_POST_ROUTING hook which allows
+	 * changing the skb->dst entry which then may not be xfrm based anymore
+	 * in which case a REROUTED flag is set. and dst_output is called.
+	 *
+	 * For IPv6 we are also skipping fragmentation handling for local
+	 * sockets, which may or may not be good depending on our tunnel DF
+	 * setting. Normally with fragmentation supported we want to skip this
+	 * fragmentation.
+	 */
+
+	BUG_ON(!xtfs);
+
+	if (xtfs->cfg.dont_frag)
+		pmtu = iptfs_get_cur_pmtu(x, xtfs, skb);
+
+	/* Break apart GSO skbs. If the queue is nearing full then we want the
+	 * accounting and queuing to be based on the individual packets not on the
+	 * aggregate GSO buffer.
+	 */
+	was_gso = skb_is_gso(skb);
+	if (!was_gso) {
+		segs = skb;
+	} else {
+		segs = skb_gso_segment(skb, 0);
+		if (IS_ERR_OR_NULL(segs)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			kfree_skb(skb);
+			return PTR_ERR(segs);
+		}
+		consume_skb(skb);
+		skb = NULL;
+	}
+
+	/* We can be running on multiple cores and from the network softirq or
+	 * from user context depending on where the packet is coming from.
+	 */
+	spin_lock_bh(&x->lock);
+
+	skb_list_walk_safe(segs, skb, nskb) {
+		skb_mark_not_on_list(skb);
+
+		/* Once we drop due to no queue space we continue to drop the
+		 * rest of the packets from that GRO.
+		 */
+		if (!ok) {
+nospace:
+			trace_iptfs_no_queue_space(skb, xtfs, pmtu, was_gso);
+			XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMOUTNOQSPACE);
+			kfree_skb_reason(skb, SKB_DROP_REASON_FULL_RING);
+			continue;
+		}
+
+		/* If the user indicated no iptfs fragmenting check before
+		 * enqueue.
+		 */
+		if (xtfs->cfg.dont_frag && iptfs_is_too_big(sk, skb, pmtu)) {
+			trace_iptfs_too_big(skb, xtfs, pmtu, was_gso);
+			kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
+			continue;
+		}
+
+		/* Enqueue to send in tunnel */
+		ok = iptfs_enqueue(xtfs, skb);
+		if (!ok)
+			goto nospace;
+
+		trace_iptfs_enqueue(skb, xtfs, pmtu, was_gso);
+	}
+
+	/* Start a delay timer if we don't have one yet */
+	if (!hrtimer_is_queued(&xtfs->iptfs_timer)) {
+		hrtimer_start(&xtfs->iptfs_timer, xtfs->init_delay_ns,
+			      IPTFS_HRTIMER_MODE);
+		xtfs->iptfs_settime = ktime_get_raw_fast_ns();
+		trace_iptfs_timer_start(xtfs, xtfs->init_delay_ns);
+	}
+
+	spin_unlock_bh(&x->lock);
+	return 0;
+}
+
+/* -------------------------- */
+/* Dequeue and send functions */
+/* -------------------------- */
+
+static void iptfs_output_prepare_skb(struct sk_buff *skb, u32 blkoff)
+{
+	struct ip_iptfs_hdr *h;
+	size_t hsz = sizeof(*h);
+
+	/* now reset values to be pointing at the rest of the packets */
+	h = skb_push(skb, hsz);
+	memset(h, 0, hsz);
+	if (blkoff)
+		h->block_offset = htons(blkoff);
+
+	/* network_header current points at the inner IP packet
+	 * move it to the iptfs header
+	 */
+	skb->transport_header = skb->network_header;
+	skb->network_header -= hsz;
+
+	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
+
+	/* xfrm[46]_prepare_output sets skb->protocol here, but the resulting
+	 * called ip[6]_output functions also set this value as appropriate so
+	 * seems unnecessary
+	 *
+	 * skb->protocol = htons(ETH_P_IP) or htons(ETH_P_IPV6);
+	 */
+}
+
+/**
+ * iptfs_copy_create_frag() - create an inner fragment skb.
+ * @st: The source packet data.
+ * @offset: offset in @st of the new fragment data.
+ * @copy_len: the amount of data to copy from @st.
+ *
+ * Create a new skb holding a single IPTFS inner packet fragment. @copy_len must
+ * not be greater than the max fragment size.
+ *
+ * Return: the new fragment skb or an ERR_PTR().
+ */
+static struct sk_buff *iptfs_copy_create_frag(struct skb_seq_state *st,
+					      u32 offset, u32 copy_len)
+{
+	struct sk_buff *src = st->root_skb;
+	struct sk_buff *skb;
+	int err;
+
+	skb = iptfs_alloc_skb(src, copy_len, true);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	/* Now copy `copy_len` data from src */
+	err = skb_copy_bits_seq(st, offset, skb_put(skb, copy_len), copy_len);
+	if (err) {
+		XFRM_INC_STATS(dev_net(src->dev), LINUX_MIB_XFRMOUTERROR);
+		kfree_skb(skb);
+		return ERR_PTR(err);
+	}
+
+	return skb;
+}
+
+/**
+ * iptfs_copy_create_frags() - create and send N-1 fragments of a larger skb.
+ * @skbp: the source packet skb (IN), skb holding the last fragment in
+ *        the fragment stream (OUT).
+ * @xtfs: IPTFS SA state.
+ * @mtu: the max IPTFS fragment size.
+ *
+ * This function is responsible for fragmenting a larger inner packet into a
+ * sequence of IPTFS payload packets. The last fragment is returned rather than
+ * being sent so that the caller can append more inner packets (aggregation) if
+ * there is room.
+ */
+static int iptfs_copy_create_frags(struct sk_buff **skbp,
+				   struct xfrm_iptfs_data *xtfs, u32 mtu)
+{
+	struct skb_seq_state skbseq;
+	struct list_head sublist;
+	struct sk_buff *skb = *skbp;
+	struct sk_buff *nskb = *skbp;
+	u32 copy_len, offset;
+	u32 to_copy = skb->len - mtu;
+	u32 blkoff = 0;
+	int err = 0;
+
+	INIT_LIST_HEAD(&sublist);
+
+	BUG_ON(skb->len <= mtu);
+	skb_prepare_seq_read(skb, 0, skb->len, &skbseq);
+
+	/* A trimmed `skb` will be sent as the first fragment, later. */
+	offset = mtu;
+	to_copy = skb->len - offset;
+	while (to_copy) {
+		/* Send all but last fragment to allow agg. append */
+		trace_iptfs_first_fragmenting(nskb, mtu, to_copy, NULL);
+		list_add_tail(&nskb->list, &sublist);
+
+		/* FUTURE: if the packet has an odd/non-aligning length we could
+		 * send less data in the penultimate fragment so that the last
+		 * fragment then ends on an aligned boundary.
+		 */
+		copy_len = to_copy <= mtu ? to_copy : mtu;
+		nskb = iptfs_copy_create_frag(&skbseq, offset, copy_len);
+		if (IS_ERR(nskb)) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMOUTERROR);
+			skb_abort_seq_read(&skbseq);
+			err = PTR_ERR(nskb);
+			nskb = NULL;
+			break;
+		}
+		iptfs_output_prepare_skb(nskb, to_copy);
+		offset += copy_len;
+		to_copy -= copy_len;
+		blkoff = to_copy;
+	}
+	skb_abort_seq_read(&skbseq);
+
+	/* return last fragment that will be unsent (or NULL) */
+	*skbp = nskb;
+	if (nskb)
+		trace_iptfs_first_final_fragment(nskb, mtu, blkoff, NULL);
+
+	/* trim the original skb to MTU */
+	if (!err)
+		err = pskb_trim(skb, mtu);
+
+	if (err) {
+		/* Free all frags. Don't bother sending a partial packet we will
+		 * never complete.
+		 */
+		kfree_skb(nskb);
+		list_for_each_entry_safe(skb, nskb, &sublist, list) {
+			skb_list_del_init(skb);
+			kfree_skb(skb);
+		}
+		return err;
+	}
+
+	/* prepare the initial fragment with an iptfs header */
+	iptfs_output_prepare_skb(skb, 0);
+
+	/* Send all but last fragment, if we fail to send a fragment then free
+	 * the rest -- no point in sending a packet that can't be reassembled.
+	 */
+	list_for_each_entry_safe(skb, nskb, &sublist, list) {
+		skb_list_del_init(skb);
+		if (!err)
+			err = xfrm_output(NULL, skb);
+		else
+			kfree_skb(skb);
+	}
+	if (err)
+		kfree_skb(*skbp);
+	return err;
+}
+
+/**
+ * iptfs_first_should_copy() - determine if we should copy packet data.
+ * @first_skb: the first skb in the packet
+ * @mtu: the MTU.
+ *
+ * Determine if we should create subsequent skbs to hold the remaining data from
+ * a large inner packet by copying the packet data, or cloning the original skb
+ * and adjusting the offsets.
+ */
+static bool iptfs_first_should_copy(struct sk_buff *first_skb, u32 mtu)
+{
+	u32 frag_copy_max;
+
+	/* If we have less than frag_copy_max for remaining packet we copy
+	 * those tail bytes as it is more efficient.
+	 */
+	frag_copy_max = mtu <= IPTFS_FRAG_COPY_MAX ? mtu : IPTFS_FRAG_COPY_MAX;
+	if ((int)first_skb->len - (int)mtu < (int)frag_copy_max)
+		return true;
+
+	/* If we have non-linear skb just use copy */
+	if (skb_is_nonlinear(first_skb))
+		return true;
+
+	/* So we have a simple linear skb, easy to clone and share */
+	return false;
+}
+
+/**
+ * iptfs_first_skb() - handle the first dequeued inner packet for output
+ * @skbp: the source packet skb (IN), skb holding the last fragment in
+ *        the fragment stream (OUT).
+ * @xtfs: IPTFS SA state.
+ * @mtu: the max IPTFS fragment size.
+ *
+ * This function is responsible for fragmenting a larger inner packet into a
+ * sequence of IPTFS payload packets. If it needs to fragment into subsequent
+ * skb's, it will either do so by copying or cloning.
+ *
+ * The last fragment is returned rather than being sent so that the caller can
+ * append more inner packets (aggregation) if there is room.
+ *
+ */
+static int iptfs_first_skb(struct sk_buff **skbp, struct xfrm_iptfs_data *xtfs,
+			   u32 mtu)
+{
+	struct sk_buff *skb = *skbp;
+	int err;
+
+	/* Classic ESP skips the don't fragment ICMP error if DF is clear on
+	 * the inner packet or ignore_df is set. Otherwise it will send an ICMP
+	 * or local error if the inner packet won't fit it's MTU.
+	 *
+	 * With IPTFS we do not care about the inner packet DF bit. If the
+	 * tunnel is configured to "don't fragment" we error back if things
+	 * don't fit in our max packet size. Otherwise we iptfs-fragment as
+	 * normal.
+	 */
+
+	/* The opportunity for HW offload has ended */
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		err = skb_checksum_help(skb);
+		if (err)
+			return err;
+	}
+
+	/* We've split these up before queuing */
+	BUG_ON(skb_is_gso(skb));
+
+	trace_iptfs_first_dequeue(skb, mtu, 0, ip_hdr(skb));
+
+	/* Simple case -- it fits. `mtu` accounted for all the overhead
+	 * including the basic IPTFS header.
+	 */
+	if (skb->len <= mtu) {
+		iptfs_output_prepare_skb(skb, 0);
+		return 0;
+	}
+
+	if (iptfs_first_should_copy(skb, mtu))
+		return iptfs_copy_create_frags(skbp, xtfs, mtu);
+
+	/* For now we always copy */
+	return iptfs_copy_create_frags(skbp, xtfs, mtu);
+}
+
+static struct sk_buff **iptfs_rehome_fraglist(struct sk_buff **nextp,
+					      struct sk_buff *child)
+{
+	u32 fllen = 0;
+
+	/* It might be possible to account for a frag list in addition to page
+	 * fragment if it's a valid state to be in. The page fragments size
+	 * should be kept as data_len so only the frag_list size is removed,
+	 * this must be done above as well.
+	 */
+	BUG_ON(skb_shinfo(child)->nr_frags);
+	*nextp = skb_shinfo(child)->frag_list;
+	while (*nextp) {
+		fllen += (*nextp)->len;
+		nextp = &(*nextp)->next;
+	}
+	skb_frag_list_init(child);
+	BUG_ON(fllen > child->data_len);
+	child->len -= fllen;
+	child->data_len -= fllen;
+
+	return nextp;
+}
+
+static void iptfs_consume_frags(struct sk_buff *to, struct sk_buff *from)
+{
+	struct skb_shared_info *fromi = skb_shinfo(from);
+	struct skb_shared_info *toi = skb_shinfo(to);
+	unsigned int new_truesize;
+
+	/* If we have data in a head page, grab it */
+	if (!skb_headlen(from)) {
+		new_truesize = SKB_TRUESIZE(skb_end_offset(from));
+	} else {
+		skb_head_to_frag(from, &toi->frags[toi->nr_frags]);
+		skb_frag_ref(to, toi->nr_frags++);
+		new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff));
+	}
+
+	/* Move any other page fragments rather than copy */
+	memcpy(&toi->frags[toi->nr_frags], fromi->frags,
+	       sizeof(fromi->frags[0]) * fromi->nr_frags);
+	toi->nr_frags += fromi->nr_frags;
+	fromi->nr_frags = 0;
+	from->data_len = 0;
+	from->len = 0;
+	to->truesize += from->truesize - new_truesize;
+	from->truesize = new_truesize;
+
+	/* We are done with this SKB */
+	consume_skb(from);
+}
+
+static void iptfs_output_queued(struct xfrm_state *x, struct sk_buff_head *list)
+{
+	struct xfrm_iptfs_data *xtfs = x->mode_data;
+	struct sk_buff *skb, *skb2, **nextp;
+	struct skb_shared_info *shi, *shi2;
+
+	/* For now we are just outputting packets as fast as we can, so if we
+	 * are fragmenting we will do so until the last inner packet has been
+	 * consumed.
+	 *
+	 * When we are fragmenting we need to output all outer packets that
+	 * contain the fragments of a single inner packet, consecutively (ESP
+	 * seq-wise). Since this output function is always running from a timer
+	 * we do not need a lock to provide this guarantee. We will output our
+	 * packets consecutively before the timer is allowed to run again on
+	 * some other CPU.
+	 */
+
+	/* NOTE: for the future, for timed packet sends, if our queue is not
+	 * growing longer (i.e., we are keeping up) and a packet we are about to
+	 * fragment will not fragment in then next outer packet, we might consider
+	 * holding on to it to send whole in the next slot. The question then is
+	 * does this introduce a continuous delay in the inner packet stream
+	 * with certain packet rates and sizes?
+	 */
+
+	/* and send them on their way */
+
+	while ((skb = __skb_dequeue(list))) {
+		u32 mtu = iptfs_get_cur_pmtu(x, xtfs, skb);
+		bool share_ok = true;
+		int remaining;
+
+		/* protocol comes to us cleared sometimes */
+		skb->protocol = x->outer_mode.family == AF_INET ?
+					htons(ETH_P_IP) :
+					htons(ETH_P_IPV6);
+
+		if (skb->len > mtu && xtfs->cfg.dont_frag) {
+			/* We handle this case before enqueueing so we are only
+			 * here b/c MTU changed after we enqueued before we
+			 * dequeued, just drop these.
+			 */
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMOUTERROR);
+
+			trace_iptfs_first_toobig(skb, mtu, 0, ip_hdr(skb));
+			kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
+			continue;
+		}
+
+		/* iptfs_first_skb will free skb on error as well */
+		if (iptfs_first_skb(&skb, xtfs, mtu))
+			continue;
+
+		/* The returned skb is the last IPTFS fragment, it has it's
+		 * IPTFS header included and it's blkoff set just past the end
+		 * fragment data if needed. The space remaining to send more
+		 * inner packet data is `mtu` - (skb->len - sizeof iptfs
+		 * header). This is b/c the `mtu` value has the basic IPTFS
+		 * header len accounted for, and we added that header to the skb
+		 * so it is a part of skb->len, thus we subtract it from the skb
+		 * length.
+		 */
+		remaining = mtu - (skb->len - sizeof(struct ip_iptfs_hdr));
+
+		/* Re-home nested fragment lists. */
+		shi = skb_shinfo(skb);
+		nextp = &shi->frag_list;
+		while (*nextp) {
+			if (skb_has_frag_list(*nextp))
+				nextp = iptfs_rehome_fraglist(&(*nextp)->next,
+							      *nextp);
+			else
+				nextp = &(*nextp)->next;
+		}
+
+		if (shi->frag_list || skb_cloned(skb) || skb_shared(skb))
+			share_ok = false;
+
+		/* See if we have enough space to simply append.
+		 *
+		 * NOTE: Maybe do not append if we will be mis-aligned,
+		 * SW-based endpoints will probably have to copy in this
+		 * case.
+		 */
+		while ((skb2 = skb_peek(list))) {
+			trace_iptfs_ingress_nth_peek(skb2, remaining);
+			if (skb2->len > remaining)
+				break;
+
+			__skb_unlink(skb2, list);
+
+			/* The opportunity for HW offload has ended, if we
+			 * don't have a cksum in the packet we need to add one
+			 * before encap and transmit.
+			 */
+			if (skb2->ip_summed == CHECKSUM_PARTIAL) {
+				if (skb_checksum_help(skb2)) {
+					XFRM_INC_STATS(dev_net(skb_dst(skb2)->dev),
+						       LINUX_MIB_XFRMOUTERROR);
+					kfree_skb(skb2);
+					continue;
+				}
+			}
+
+			/* skb->pp_recycle is passed to __skb_flag_unref for all
+			 * frag pages so we can only share pages with skb's who
+			 * match ourselves.
+			 */
+			shi2 = skb_shinfo(skb2);
+			if (share_ok &&
+			    (shi2->frag_list ||
+			     (!skb2->head_frag && skb_headlen(skb)) ||
+			     skb->pp_recycle != skb2->pp_recycle ||
+			     skb_zcopy(skb2) ||
+			     (shi->nr_frags + shi2->nr_frags + 1 > MAX_SKB_FRAGS)))
+				share_ok = false;
+
+			/* do acct so we can free skb2 in share case */
+			skb->data_len += skb2->len;
+			skb->len += skb2->len;
+			remaining -= skb2->len;
+
+			trace_iptfs_ingress_nth_add(skb2, share_ok);
+
+			if (share_ok) {
+				iptfs_consume_frags(skb, skb2);
+			} else {
+				/* link on the frag_list */
+				*nextp = skb2;
+				nextp = &skb2->next;
+				BUG_ON(*nextp);
+				if (skb_has_frag_list(skb2))
+					nextp = iptfs_rehome_fraglist(nextp,
+								      skb2);
+				skb->truesize += skb2->truesize;
+			}
+		}
+
+		/* Consider fragmenting this skb2 that didn't fit. For demand
+		 * driven variable sized IPTFS pkts, though this isn't buying
+		 * a whole lot, especially if we are doing a copy which waiting
+		 * to send in a new pkt would not.
+		 */
+
+		xfrm_output(NULL, skb);
+	}
+}
+
+static enum hrtimer_restart iptfs_delay_timer(struct hrtimer *me)
+{
+	struct sk_buff_head list;
+	struct xfrm_iptfs_data *xtfs;
+	struct xfrm_state *x;
+	time64_t settime;
+
+	xtfs = container_of(me, typeof(*xtfs), iptfs_timer);
+	x = xtfs->x;
+
+	/* Process all the queued packets
+	 *
+	 * softirq execution order: timer > tasklet > hrtimer
+	 *
+	 * Network rx will have run before us giving one last chance to queue
+	 * ingress packets for us to process and transmit.
+	 */
+
+	spin_lock(&x->lock);
+	__skb_queue_head_init(&list);
+	skb_queue_splice_init(&xtfs->queue, &list);
+	xtfs->queue_size = 0;
+	settime = xtfs->iptfs_settime;
+	spin_unlock(&x->lock);
+
+	/* After the above unlock, packets can begin queuing again, and the
+	 * timer can be set again, from another CPU either in softirq or user
+	 * context (not from this one since we are running at softirq level
+	 * already).
+	 */
+
+	trace_iptfs_timer_expire(xtfs,
+				 (unsigned long long)(ktime_get_raw_fast_ns() - settime));
+
+	iptfs_output_queued(x, &list);
+
+	return HRTIMER_NORESTART;
+}
+
+/**
+ * iptfs_encap_add_ipv4() - add outer encaps
+ * @x: xfrm state
+ * @skb: the packet
+ *
+ * This was originally taken from xfrm4_tunnel_encap_add. The reason for the
+ * copy is that IP-TFS/AGGFRAG can have different functionality for how to set
+ * the TOS/DSCP bits. Sets the protocol to a different value and doesn't do
+ * anything with inner headers as they aren't pointing into a normal IP
+ * singleton inner packet.
+ */
+static int iptfs_encap_add_ipv4(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct iphdr *top_iph;
+
+	skb_reset_inner_network_header(skb);
+	skb_reset_inner_transport_header(skb);
+
+	skb_set_network_header(skb, -(x->props.header_len - x->props.enc_hdr_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 = IPPROTO_AGGFRAG;
+
+	/* As we have 0, fractional, 1 or N inner packets there's no obviously
+	 * correct DSCP mapping to inherit. ECN should be cleared per RFC9347
+	 * 3.1.
+	 */
+	top_iph->tos = 0;
+
+	top_iph->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;
+}
+
+/**
+ * iptfs_encap_add_ipv6() - add outer encaps
+ * @x: xfrm state
+ * @skb: the packet
+ *
+ * This was originally taken from xfrm6_tunnel_encap_add. The reason for the
+ * copy is that IP-TFS/AGGFRAG can have different functionality for how to set
+ * the flow label and TOS/DSCP bits. It also sets the protocol to a different
+ * value and doesn't do anything with inner headers as they aren't pointing into
+ * a normal IP singleton inner packet.
+ */
+static int iptfs_encap_add_ipv6(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct ipv6hdr *top_iph;
+	int dsfield;
+
+	skb_reset_inner_network_header(skb);
+	skb_reset_inner_transport_header(skb);
+
+	skb_set_network_header(skb,
+			       -x->props.header_len + x->props.enc_hdr_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;
+	top_iph->priority = 0;
+	memset(top_iph->flow_lbl, 0, sizeof(top_iph->flow_lbl));
+	top_iph->nexthdr = IPPROTO_AGGFRAG;
+
+	/* As we have 0, fractional, 1 or N inner packets there's no obviously
+	 * correct DSCP mapping to inherit. ECN should be cleared per RFC9347
+	 * 3.1.
+	 */
+	dsfield = 0;
+	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;
+}
+
+/**
+ * iptfs_prepare_output() -  prepare the skb for output
+ * @x: xfrm state
+ * @skb: the packet
+ *
+ * Return: Error value, if 0 then skb values should be as follows:
+ *    - transport_header should point at ESP header
+ *    - network_header should point at Outer IP header
+ *    - mac_header should point at protocol/nexthdr of the outer IP
+ */
+static int iptfs_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	if (x->outer_mode.family == AF_INET)
+		return iptfs_encap_add_ipv4(x, skb);
+	if (x->outer_mode.family == AF_INET6) {
+#if IS_ENABLED(CONFIG_IPV6)
+		return iptfs_encap_add_ipv6(x, skb);
+#else
+		WARN_ON_ONCE(1);
+		return -EAFNOSUPPORT;
+#endif
+	}
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
+}
+
+/* ========================== */
+/* State Management Functions */
+/* ========================== */
+
+/**
+ * __iptfs_get_inner_mtu() - return inner MTU with no fragmentation.
+ * @x: xfrm state.
+ * @outer_mtu: the outer mtu
+ */
+static u32 __iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu)
+{
+	struct crypto_aead *aead;
+	u32 blksize;
+
+	aead = x->data;
+	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
+	return ((outer_mtu - x->props.header_len - crypto_aead_authsize(aead)) &
+		~(blksize - 1)) - 2;
+}
+
+/**
+ * iptfs_get_mtu() - return the inner MTU for an IPTFS xfrm.
+ * @x: xfrm state.
+ * @outer_mtu: Outer MTU for the encapsulated packet.
+ *
+ * Return: Correct MTU taking in to account the encap overhead.
+ */
+static u32 iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu)
+{
+	struct xfrm_iptfs_data *xtfs = x->mode_data;
+
+	/* If not dont-frag we have no MTU */
+	if (!xtfs->cfg.dont_frag)
+		return x->outer_mode.family == AF_INET ? IP_MAX_MTU :
+							 IP6_MAX_MTU;
+	return __iptfs_get_inner_mtu(x, outer_mtu);
+}
+
+/**
+ * iptfs_user_init() - initialize the SA with IPTFS options from netlink.
+ * @net: the net data
+ * @x: xfrm state
+ * @attrs: netlink attributes
+ * @extack: extack return data
+ */
+static int iptfs_user_init(struct net *net, struct xfrm_state *x,
+			   struct nlattr **attrs,
+			   struct netlink_ext_ack *extack)
+{
+	struct xfrm_iptfs_data *xtfs = x->mode_data;
+	struct xfrm_iptfs_config *xc;
+
+	xc = &xtfs->cfg;
+	xc->reorder_win_size = net->xfrm.sysctl_iptfs_reorder_window;
+	xc->max_queue_size = net->xfrm.sysctl_iptfs_max_qsize;
+	xtfs->init_delay_ns = net->xfrm.sysctl_iptfs_init_delay * NSECS_IN_USEC;
+	xtfs->drop_time_ns = net->xfrm.sysctl_iptfs_drop_time * NSECS_IN_USEC;
+
+	if (attrs[XFRMA_IPTFS_DONT_FRAG])
+		xc->dont_frag = true;
+	if (attrs[XFRMA_IPTFS_REORDER_WINDOW])
+		xc->reorder_win_size =
+			nla_get_u16(attrs[XFRMA_IPTFS_REORDER_WINDOW]);
+	/* saved array is for saving 1..N seq nums from wantseq */
+	if (xc->reorder_win_size)
+		xtfs->w_saved = kcalloc(xc->reorder_win_size,
+					sizeof(*xtfs->w_saved), GFP_KERNEL);
+	if (attrs[XFRMA_IPTFS_PKT_SIZE]) {
+		xc->pkt_size = nla_get_u32(attrs[XFRMA_IPTFS_PKT_SIZE]);
+		if (!xc->pkt_size) {
+			xtfs->payload_mtu = 0;
+		} else if (xc->pkt_size > x->props.header_len) {
+			xtfs->payload_mtu = xc->pkt_size - x->props.header_len;
+		} else {
+			NL_SET_ERR_MSG(extack,
+				       "Packet size must be 0 or greater than IPTFS/ESP header length");
+			return -EINVAL;
+		}
+	}
+	if (attrs[XFRMA_IPTFS_MAX_QSIZE])
+		xc->max_queue_size = nla_get_u32(attrs[XFRMA_IPTFS_MAX_QSIZE]);
+	if (attrs[XFRMA_IPTFS_DROP_TIME])
+		xtfs->drop_time_ns = nla_get_u32(attrs[XFRMA_IPTFS_DROP_TIME]) *
+				     NSECS_IN_USEC;
+	if (attrs[XFRMA_IPTFS_INIT_DELAY])
+		xtfs->init_delay_ns =
+			nla_get_u32(attrs[XFRMA_IPTFS_INIT_DELAY]) *
+			NSECS_IN_USEC;
+
+	xtfs->ecn_queue_size = (u64)xc->max_queue_size * 95 / 100;
+
+	return 0;
+}
+
+static int iptfs_copy_to_user(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct xfrm_iptfs_data *xtfs = x->mode_data;
+	struct xfrm_iptfs_config *xc = &xtfs->cfg;
+	int ret;
+
+	if (xc->dont_frag) {
+		ret = nla_put_flag(skb, XFRMA_IPTFS_DONT_FRAG);
+		if (ret)
+			return ret;
+	}
+	ret = nla_put_u16(skb, XFRMA_IPTFS_REORDER_WINDOW, xc->reorder_win_size);
+	if (ret)
+		return ret;
+	ret = nla_put_u32(skb, XFRMA_IPTFS_PKT_SIZE, xc->pkt_size);
+	if (ret)
+		return ret;
+	ret = nla_put_u32(skb, XFRMA_IPTFS_MAX_QSIZE, xc->max_queue_size);
+	if (ret)
+		return ret;
+	ret = nla_put_u32(skb, XFRMA_IPTFS_DROP_TIME,
+			  xtfs->drop_time_ns / NSECS_IN_USEC);
+	if (ret)
+		return ret;
+	ret = nla_put_u32(skb, XFRMA_IPTFS_INIT_DELAY,
+			  xtfs->init_delay_ns / NSECS_IN_USEC);
+	return ret;
+}
+
+static int __iptfs_init_state(struct xfrm_state *x,
+			      struct xfrm_iptfs_data *xtfs)
+{
+	__skb_queue_head_init(&xtfs->queue);
+	hrtimer_init(&xtfs->iptfs_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE);
+	xtfs->iptfs_timer.function = iptfs_delay_timer;
+
+	spin_lock_init(&xtfs->drop_lock);
+	hrtimer_init(&xtfs->drop_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE);
+	xtfs->drop_timer.function = iptfs_drop_timer;
+
+	/* Modify type (esp) adjustment values */
+
+	if (x->props.family == AF_INET)
+		x->props.header_len += sizeof(struct iphdr) + sizeof(struct ip_iptfs_hdr);
+	else if (x->props.family == AF_INET6)
+		x->props.header_len += sizeof(struct ipv6hdr) + sizeof(struct ip_iptfs_hdr);
+	x->props.enc_hdr_len = sizeof(struct ip_iptfs_hdr);
+
+	/* Always have a module reference if x->mode_data is set */
+	if (!try_module_get(x->mode_cbs->owner))
+		return -EINVAL;
+
+	x->mode_data = xtfs;
+	xtfs->x = x;
+
+	return 0;
+}
+
+static int iptfs_clone(struct xfrm_state *x, struct xfrm_state *orig)
+{
+	struct xfrm_iptfs_data *xtfs;
+	int err;
+
+	xtfs = kmemdup(orig->mode_data, sizeof(*xtfs), GFP_KERNEL);
+	if (!xtfs)
+		return -ENOMEM;
+
+	xtfs->ra_newskb = NULL;
+	if (xtfs->cfg.reorder_win_size) {
+		xtfs->w_saved = kcalloc(xtfs->cfg.reorder_win_size,
+					sizeof(*xtfs->w_saved), GFP_KERNEL);
+		if (!xtfs->w_saved) {
+			kfree_sensitive(xtfs);
+			return -ENOMEM;
+		}
+	}
+
+	err = __iptfs_init_state(x, xtfs);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int iptfs_create_state(struct xfrm_state *x)
+{
+	struct xfrm_iptfs_data *xtfs;
+	int err;
+
+	xtfs = kzalloc(sizeof(*xtfs), GFP_KERNEL);
+	if (!xtfs)
+		return -ENOMEM;
+
+	err = __iptfs_init_state(x, xtfs);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void iptfs_delete_state(struct xfrm_state *x)
+{
+	struct xfrm_iptfs_data *xtfs = x->mode_data;
+	struct skb_wseq *s, *se;
+
+	if (!xtfs)
+		return;
+
+	spin_lock_bh(&xtfs->drop_lock);
+	hrtimer_cancel(&xtfs->iptfs_timer);
+	hrtimer_cancel(&xtfs->drop_timer);
+	spin_unlock_bh(&xtfs->drop_lock);
+
+	if (xtfs->ra_newskb)
+		kfree_skb(xtfs->ra_newskb);
+
+	for (s = xtfs->w_saved, se = s + xtfs->w_savedlen; s < se; s++)
+		if (s->skb)
+			kfree_skb(s->skb);
+
+	kfree_sensitive(xtfs->w_saved);
+	kfree_sensitive(xtfs);
+
+	module_put(x->mode_cbs->owner);
+}
+
+static const struct xfrm_mode_cbs iptfs_mode_cbs = {
+	.owner = THIS_MODULE,
+	.create_state = iptfs_create_state,
+	.delete_state = iptfs_delete_state,
+	.user_init = iptfs_user_init,
+	.copy_to_user = iptfs_copy_to_user,
+	.clone = iptfs_clone,
+	.get_inner_mtu = iptfs_get_inner_mtu,
+	.input = iptfs_input,
+	.output = iptfs_output_collect,
+	.prepare_output = iptfs_prepare_output,
+};
+
+static int __init xfrm_iptfs_init(void)
+{
+	int err;
+
+	pr_info("xfrm_iptfs: IPsec IP-TFS tunnel mode module\n");
+
+	err = xfrm_register_mode_cbs(XFRM_MODE_IPTFS, &iptfs_mode_cbs);
+	if (err < 0)
+		pr_info("%s: can't register IP-TFS\n", __func__);
+
+	return err;
+}
+
+static void __exit xfrm_iptfs_fini(void)
+{
+	xfrm_unregister_mode_cbs(XFRM_MODE_IPTFS);
+}
+
+module_init(xfrm_iptfs_init);
+module_exit(xfrm_iptfs_fini);
+MODULE_LICENSE("GPL");
-- 
2.43.0

Re: [PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[Simon Horman]

On Mon, Feb 19, 2024 at 03:57:35AM -0500, Christian Hopps wrote:
> From: Christian Hopps <chopps@labn.net>
> 
> Add a new xfrm mode implementing AggFrag/IP-TFS from RFC9347.
> 
> This utilizes the new xfrm_mode_cbs to implement demand-driven IP-TFS
> functionality. This functionality can be used to increase bandwidth
> utilization through small packet aggregation, as well as help solve PMTU
> issues through it's efficient use of fragmentation.
> 
> Link: https://www.rfc-editor.org/rfc/rfc9347.txt
> 
> Signed-off-by: Christian Hopps <chopps@labn.net>

...

> diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c

...

> +/**
> + * skb_head_to_frag() - initialize a skb_frag_t based on skb head data
> + * @skb: skb with the head data
> + * @frag: frag to initialize
> + */
> +static void skb_head_to_frag(const struct sk_buff *skb, skb_frag_t *frag)
> +{
> +	struct page *page = virt_to_head_page(skb->data);
> +	unsigned char *addr = (unsigned char *)page_address(page);
> +
> +	BUG_ON(!skb->head_frag);

Is it strictly necessary to crash the Kernel here?
Likewise, many other places in this patch.

> +	skb_frag_fill_page_desc(frag, page, skb->data - addr, skb_headlen(skb));
> +}

...

> +/**
> + * skb_add_frags() - add a range of fragment references into an skb
> + * @skb: skb to add references into
> + * @walk: the walk to add referenced fragments from.
> + * @offset: offset from beginning of original skb to start from.
> + * @len: amount of data to add frag references to in @skb.
> + *
> + * skb_can_add_frags() should be called before this function to verify that the
> + * destination @skb is compatible with the walk and has space in the array for
> + * the to be added frag refrences.

nit: references

> + *
> + * Return: The number of bytes not added to @skb b/c we reached the end of the
> + * walk before adding all of @len.
> + */

...

> +/**
> + * iptfs_reassem_done() - In-progress packet is aborted free the state.

nit: This does not match the name of the function it documents.

     Flagged by W=1 build with gcc-13.

> + * @xtfs: xtfs state
> + */
> +static void iptfs_reassem_abort(struct xfrm_iptfs_data *xtfs)
> +{
> +	__iptfs_reassem_done(xtfs, true);
> +}

...

> +/**
> + * iptfs_input_ordered() - handle next in order IPTFS payload.
> + * @x: xfrm state
> + * @skb: current packet
> + *
> + * Process the IPTFS payload in `skb` and consume it afterwards.
> + */
> +static int iptfs_input_ordered(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	u8 hbytes[sizeof(struct ipv6hdr)];
> +	struct ip_iptfs_cc_hdr iptcch;
> +	struct skb_seq_state skbseq;
> +	struct skb_frag_walk _fragwalk;
> +	struct skb_frag_walk *fragwalk = NULL;
> +	struct list_head sublist; /* rename this it's just a list */
> +	struct sk_buff *first_skb, *defer, *next;
> +	const unsigned char *old_mac;
> +	struct xfrm_iptfs_data *xtfs;
> +	struct ip_iptfs_hdr *ipth;
> +	struct iphdr *iph;
> +	struct net *net;
> +	u32 remaining, first_iplen, iplen, iphlen, data, tail;
> +	u32 blkoff, capturelen;
> +	u64 seq;
> +
> +	xtfs = x->mode_data;
> +	net = dev_net(skb->dev);
> +	first_skb = NULL;
> +	defer = NULL;
> +
> +	seq = __esp_seq(skb);
> +
> +	/* Large enough to hold both types of header */
> +	ipth = (struct ip_iptfs_hdr *)&iptcch;
> +
> +	/* Save the old mac header if set */
> +	old_mac = skb_mac_header_was_set(skb) ? skb_mac_header(skb) : NULL;
> +
> +	skb_prepare_seq_read(skb, 0, skb->len, &skbseq);
> +
> +	/* Get the IPTFS header and validate it */
> +
> +	if (skb_copy_bits_seq(&skbseq, 0, ipth, sizeof(*ipth))) {
> +		XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
> +		goto done;
> +	}
> +	data = sizeof(*ipth);
> +
> +	trace_iptfs_egress_recv(skb, xtfs, htons(ipth->block_offset));

Maybe this is backwards, because the argument to htons should be
in host byte order, but the type of ipth->block_offset is __be16.

Also, personally, i would suggest using be16_to_cpu as it better
describes the types involved.

This is flagged by Sparse along with some other problems.
Please take care not to introduce new Sparse warnings.

...

> +static u32 __reorder_future_shifts(struct xfrm_iptfs_data *xtfs,
> +				   struct sk_buff *inskb,
> +				   struct list_head *list,
> +				   struct list_head *freelist, u32 *fcount)
> +{
> +	const u32 nslots = xtfs->cfg.reorder_win_size + 1;
> +	const u64 inseq = __esp_seq(inskb);
> +	u32 savedlen = xtfs->w_savedlen;
> +	u64 wantseq = xtfs->w_wantseq;
> +	struct sk_buff *slot0 = NULL;
> +	u64 last_drop_seq = xtfs->w_wantseq;
> +	u64 distance, extra_drops, missed, s0seq;

Missed is set but otherwise unused in this function.

Flagged by W=1 build with clang-17.

> +	u32 count = 0;
> +	struct skb_wseq *wnext;
> +	u32 beyond, shifting, slot;
> +
> +	BUG_ON(inseq <= wantseq);
> +	distance = inseq - wantseq;
> +	BUG_ON(distance <= nslots - 1);
> +	beyond = distance - (nslots - 1);
> +	missed = 0;
> +
> +	/* Handle future sequence number received.
> +	 *
> +	 * IMPORTANT: we are at least advancing w_wantseq (i.e., wantseq) by 1
> +	 * b/c we are beyond the window boundary.
> +	 *
> +	 * We know we don't have the wantseq so that counts as a drop.
> +	 */
> +
> +	/* ex: slot count is 4, array size is 3 savedlen is 2, slot 0 is the
> +	 * missing sequence number.
> +	 *
> +	 * the final slot at savedlen (index savedlen - 1) is always occupied.
> +	 *
> +	 * beyond is "beyond array size" not savedlen.
> +	 *
> +	 *          +--------- array length (savedlen == 2)
> +	 *          |   +----- array size (nslots - 1 == 3)
> +	 *          |   |   +- window boundary (nslots == 4)
> +	 *          V   V | V
> +	 *                |
> +	 *  0   1   2   3 |   slot number
> +	 * ---  0   1   2 |   array index
> +	 *     [b] [c] : :|   array
> +	 *                |
> +	 * "2" "3" "4" "5"|*6*  seq numbers
> +	 *
> +	 * We receive seq number 6
> +	 * distance == 4 [inseq(6) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 3 [distance(4) - 1]
> +	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
> +	 * shifting == 1 [min(savedlen(2), beyond(1)]
> +	 * slot0_skb == [b], and should match w_wantseq
> +	 *
> +	 *                +--- window boundary (nslots == 4)
> +	 *  0   1   2   3 | 4   slot number
> +	 * ---  0   1   2 | 3   array index
> +	 *     [b] : : : :|     array
> +	 * "2" "3" "4" "5" *6*  seq numbers
> +	 *
> +	 * We receive seq number 6
> +	 * distance == 4 [inseq(6) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 3 [distance(4) - 1]
> +	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
> +	 * shifting == 1 [min(savedlen(1), beyond(1)]
> +	 * slot0_skb == [b] and should match w_wantseq
> +	 *
> +	 *                +-- window boundary (nslots == 4)
> +	 *  0   1   2   3 | 4   5   6   slot number
> +	 * ---  0   1   2 | 3   4   5   array index
> +	 *     [-] [c] : :|             array
> +	 * "2" "3" "4" "5" "6" "7" *8*  seq numbers
> +	 *
> +	 * savedlen = 2, beyond = 3
> +	 * iter 1: slot0 == NULL, missed++, lastdrop = 2 (2+1-1), slot0 = [-]
> +	 * iter 2: slot0 == NULL, missed++, lastdrop = 3 (2+2-1), slot0 = [c]
> +	 * 2 < 3, extra = 1 (3-2), missed += extra, lastdrop = 4 (2+2+1-1)
> +	 *
> +	 * We receive seq number 8
> +	 * distance == 6 [inseq(8) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 5 [distance(6) - 1]
> +	 * beyond == 3 [newslot(6) - lastslot((nslots(4) - 1))]
> +	 * shifting == 2 [min(savedlen(2), beyond(3)]
> +	 *
> +	 * slot0_skb == NULL changed from [b] when "savedlen < beyond" is true.
> +	 */
> +
> +	/* Now send any packets that are being shifted out of saved, and account
> +	 * for missing packets that are exiting the window as we shift it.
> +	 */
> +
> +	/* If savedlen > beyond we are shifting some, else all. */
> +	shifting = min(savedlen, beyond);
> +
> +	/* slot0 is the buf that just shifted out and into slot0 */
> +	slot0 = NULL;
> +	s0seq = wantseq;
> +	last_drop_seq = s0seq;
> +	wnext = xtfs->w_saved;
> +	for (slot = 1; slot <= shifting; slot++, wnext++) {
> +		/* handle what was in slot0 before we occupy it */
> +		if (!slot0) {
> +			last_drop_seq = s0seq;
> +			missed++;
> +		} else {
> +			list_add_tail(&slot0->list, list);
> +			count++;
> +		}
> +		s0seq++;
> +		slot0 = wnext->skb;
> +		wnext->skb = NULL;
> +	}
> +
> +	/* slot0 is now either NULL (in which case it's what we now are waiting
> +	 * for, or a buf in which case we need to handle it like we received it;
> +	 * however, we may be advancing past that buffer as well..
> +	 */
> +
> +	/* Handle case where we need to shift more than we had saved, slot0 will
> +	 * be NULL iff savedlen is 0, otherwise slot0 will always be
> +	 * non-NULL b/c we shifted the final element, which is always set if
> +	 * there is any saved, into slot0.
> +	 */
> +	if (savedlen < beyond) {
> +		extra_drops = beyond - savedlen;
> +		if (savedlen == 0) {
> +			BUG_ON(slot0);
> +			s0seq += extra_drops;
> +			last_drop_seq = s0seq - 1;
> +		} else {
> +			extra_drops--; /* we aren't dropping what's in slot0 */
> +			BUG_ON(!slot0);
> +			list_add_tail(&slot0->list, list);
> +			/* if extra_drops then we are going past this slot0
> +			 * so we can safely advance last_drop_seq
> +			 */
> +			if (extra_drops)
> +				last_drop_seq = s0seq + extra_drops;
> +			s0seq += extra_drops + 1;
> +			count++;
> +		}
> +		missed += extra_drops;
> +		slot0 = NULL;
> +		/* slot0 has had an empty slot pushed into it */
> +	}
> +	(void)last_drop_seq;	/* we want this for CC code */
> +
> +	/* Remove the entries */
> +	__vec_shift(xtfs, beyond);
> +
> +	/* Advance want seq */
> +	xtfs->w_wantseq += beyond;
> +
> +	/* Process drops here when implementing congestion control */
> +
> +	/* We've shifted. plug the packet in at the end. */
> +	xtfs->w_savedlen = nslots - 1;
> +	xtfs->w_saved[xtfs->w_savedlen - 1].skb = inskb;
> +	iptfs_set_window_drop_times(xtfs, xtfs->w_savedlen - 1);
> +
> +	/* if we don't have a slot0 then we must wait for it */
> +	if (!slot0)
> +		return count;
> +
> +	/* If slot0, seq must match new want seq */
> +	BUG_ON(xtfs->w_wantseq != __esp_seq(slot0));
> +
> +	/* slot0 is valid, treat like we received expected. */
> +	count += __reorder_this(xtfs, slot0, list);
> +	return count;
> +}

...

> +/**
> + * iptfs_get_mtu() - return the inner MTU for an IPTFS xfrm.

nit: This does not match the name of the function it documents.

> + * @x: xfrm state.
> + * @outer_mtu: Outer MTU for the encapsulated packet.
> + *
> + * Return: Correct MTU taking in to account the encap overhead.
> + */
> +static u32 iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu)

...

Re: [PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[Christian Hopps]

[-- Attachment #1: Type: text/plain, Size: 11263 bytes --]


Simon Horman <horms@kernel.org> writes:

> On Mon, Feb 19, 2024 at 03:57:35AM -0500, Christian Hopps wrote:
>> From: Christian Hopps <chopps@labn.net>
>>
>> Add a new xfrm mode implementing AggFrag/IP-TFS from RFC9347.
>>
>> This utilizes the new xfrm_mode_cbs to implement demand-driven IP-TFS
>> functionality. This functionality can be used to increase bandwidth
>> utilization through small packet aggregation, as well as help solve PMTU
>> issues through it's efficient use of fragmentation.
>>
>> Link: https://www.rfc-editor.org/rfc/rfc9347.txt
>>
>> Signed-off-by: Christian Hopps <chopps@labn.net>
>
> ...
>
>> diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
>
> ...
>
>> +/**
>> + * skb_head_to_frag() - initialize a skb_frag_t based on skb head data
>> + * @skb: skb with the head data
>> + * @frag: frag to initialize
>> + */
>> +static void skb_head_to_frag(const struct sk_buff *skb, skb_frag_t *frag)
>> +{
>> +	struct page *page = virt_to_head_page(skb->data);
>> +	unsigned char *addr = (unsigned char *)page_address(page);
>> +
>> +	BUG_ON(!skb->head_frag);
>
> Is it strictly necessary to crash the Kernel here?
> Likewise, many other places in this patch.

In all use cases it represents a programming error (bug) if the condition is met.

What is the correct use of BUG_ON?

>> +	skb_frag_fill_page_desc(frag, page, skb->data - addr, skb_headlen(skb));
>> +}
>
> ...
>
>> +/**
>> + * skb_add_frags() - add a range of fragment references into an skb
>> + * @skb: skb to add references into
>> + * @walk: the walk to add referenced fragments from.
>> + * @offset: offset from beginning of original skb to start from.
>> + * @len: amount of data to add frag references to in @skb.
>> + *
>> + * skb_can_add_frags() should be called before this function to verify that the
>> + * destination @skb is compatible with the walk and has space in the array for
>> + * the to be added frag refrences.
>
> nit: references

Fixed.

>> + *
>> + * Return: The number of bytes not added to @skb b/c we reached the end of the
>> + * walk before adding all of @len.
>> + */
>
> ...
>
>> +/**
>> + * iptfs_reassem_done() - In-progress packet is aborted free the state.
>
> nit: This does not match the name of the function it documents.
>
>      Flagged by W=1 build with gcc-13.

Fixed.

>
>> + * @xtfs: xtfs state
>> + */
>> +static void iptfs_reassem_abort(struct xfrm_iptfs_data *xtfs)
>> +{
>> +	__iptfs_reassem_done(xtfs, true);
>> +}
>
> ...
>
>> +/**
>> + * iptfs_input_ordered() - handle next in order IPTFS payload.
>> + * @x: xfrm state
>> + * @skb: current packet
>> + *
>> + * Process the IPTFS payload in `skb` and consume it afterwards.
>> + */
>> +static int iptfs_input_ordered(struct xfrm_state *x, struct sk_buff *skb)
>> +{
>> +	u8 hbytes[sizeof(struct ipv6hdr)];
>> +	struct ip_iptfs_cc_hdr iptcch;
>> +	struct skb_seq_state skbseq;
>> +	struct skb_frag_walk _fragwalk;
>> +	struct skb_frag_walk *fragwalk = NULL;
>> +	struct list_head sublist; /* rename this it's just a list */
>> +	struct sk_buff *first_skb, *defer, *next;
>> +	const unsigned char *old_mac;
>> +	struct xfrm_iptfs_data *xtfs;
>> +	struct ip_iptfs_hdr *ipth;
>> +	struct iphdr *iph;
>> +	struct net *net;
>> +	u32 remaining, first_iplen, iplen, iphlen, data, tail;
>> +	u32 blkoff, capturelen;
>> +	u64 seq;
>> +
>> +	xtfs = x->mode_data;
>> +	net = dev_net(skb->dev);
>> +	first_skb = NULL;
>> +	defer = NULL;
>> +
>> +	seq = __esp_seq(skb);
>> +
>> +	/* Large enough to hold both types of header */
>> +	ipth = (struct ip_iptfs_hdr *)&iptcch;
>> +
>> +	/* Save the old mac header if set */
>> +	old_mac = skb_mac_header_was_set(skb) ? skb_mac_header(skb) : NULL;
>> +
>> +	skb_prepare_seq_read(skb, 0, skb->len, &skbseq);
>> +
>> +	/* Get the IPTFS header and validate it */
>> +
>> +	if (skb_copy_bits_seq(&skbseq, 0, ipth, sizeof(*ipth))) {
>> +		XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
>> +		goto done;
>> +	}
>> +	data = sizeof(*ipth);
>> +
>> +	trace_iptfs_egress_recv(skb, xtfs, htons(ipth->block_offset));
>
> Maybe this is backwards, because the argument to htons should be
> in host byte order, but the type of ipth->block_offset is __be16.
>
> Also, personally, i would suggest using be16_to_cpu as it better
> describes the types involved.
>
> This is flagged by Sparse along with some other problems.
> Please take care not to introduce new Sparse warnings.

Cleaned these up. Switched to be16 macros..

> ...
>
>> +static u32 __reorder_future_shifts(struct xfrm_iptfs_data *xtfs,
>> +				   struct sk_buff *inskb,
>> +				   struct list_head *list,
>> +				   struct list_head *freelist, u32 *fcount)
>> +{
>> +	const u32 nslots = xtfs->cfg.reorder_win_size + 1;
>> +	const u64 inseq = __esp_seq(inskb);
>> +	u32 savedlen = xtfs->w_savedlen;
>> +	u64 wantseq = xtfs->w_wantseq;
>> +	struct sk_buff *slot0 = NULL;
>> +	u64 last_drop_seq = xtfs->w_wantseq;
>> +	u64 distance, extra_drops, missed, s0seq;
>
> Missed is set but otherwise unused in this function.
>
> Flagged by W=1 build with clang-17.

I've removed `missed`; however, it will be needed for congestion control if that gets implemented.

>
>> +	u32 count = 0;
>> +	struct skb_wseq *wnext;
>> +	u32 beyond, shifting, slot;
>> +
>> +	BUG_ON(inseq <= wantseq);
>> +	distance = inseq - wantseq;
>> +	BUG_ON(distance <= nslots - 1);
>> +	beyond = distance - (nslots - 1);
>> +	missed = 0;
>> +
>> +	/* Handle future sequence number received.
>> +	 *
>> +	 * IMPORTANT: we are at least advancing w_wantseq (i.e., wantseq) by 1
>> +	 * b/c we are beyond the window boundary.
>> +	 *
>> +	 * We know we don't have the wantseq so that counts as a drop.
>> +	 */
>> +
>> +	/* ex: slot count is 4, array size is 3 savedlen is 2, slot 0 is the
>> +	 * missing sequence number.
>> +	 *
>> +	 * the final slot at savedlen (index savedlen - 1) is always occupied.
>> +	 *
>> +	 * beyond is "beyond array size" not savedlen.
>> +	 *
>> +	 *          +--------- array length (savedlen == 2)
>> +	 *          |   +----- array size (nslots - 1 == 3)
>> +	 *          |   |   +- window boundary (nslots == 4)
>> +	 *          V   V | V
>> +	 *                |
>> +	 *  0   1   2   3 |   slot number
>> +	 * ---  0   1   2 |   array index
>> +	 *     [b] [c] : :|   array
>> +	 *                |
>> +	 * "2" "3" "4" "5"|*6*  seq numbers
>> +	 *
>> +	 * We receive seq number 6
>> +	 * distance == 4 [inseq(6) - w_wantseq(2)]
>> +	 * newslot == distance
>> +	 * index == 3 [distance(4) - 1]
>> +	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
>> +	 * shifting == 1 [min(savedlen(2), beyond(1)]
>> +	 * slot0_skb == [b], and should match w_wantseq
>> +	 *
>> +	 *                +--- window boundary (nslots == 4)
>> +	 *  0   1   2   3 | 4   slot number
>> +	 * ---  0   1   2 | 3   array index
>> +	 *     [b] : : : :|     array
>> +	 * "2" "3" "4" "5" *6*  seq numbers
>> +	 *
>> +	 * We receive seq number 6
>> +	 * distance == 4 [inseq(6) - w_wantseq(2)]
>> +	 * newslot == distance
>> +	 * index == 3 [distance(4) - 1]
>> +	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
>> +	 * shifting == 1 [min(savedlen(1), beyond(1)]
>> +	 * slot0_skb == [b] and should match w_wantseq
>> +	 *
>> +	 *                +-- window boundary (nslots == 4)
>> +	 *  0   1   2   3 | 4   5   6   slot number
>> +	 * ---  0   1   2 | 3   4   5   array index
>> +	 *     [-] [c] : :|             array
>> +	 * "2" "3" "4" "5" "6" "7" *8*  seq numbers
>> +	 *
>> +	 * savedlen = 2, beyond = 3
>> +	 * iter 1: slot0 == NULL, missed++, lastdrop = 2 (2+1-1), slot0 = [-]
>> +	 * iter 2: slot0 == NULL, missed++, lastdrop = 3 (2+2-1), slot0 = [c]
>> +	 * 2 < 3, extra = 1 (3-2), missed += extra, lastdrop = 4 (2+2+1-1)
>> +	 *
>> +	 * We receive seq number 8
>> +	 * distance == 6 [inseq(8) - w_wantseq(2)]
>> +	 * newslot == distance
>> +	 * index == 5 [distance(6) - 1]
>> +	 * beyond == 3 [newslot(6) - lastslot((nslots(4) - 1))]
>> +	 * shifting == 2 [min(savedlen(2), beyond(3)]
>> +	 *
>> +	 * slot0_skb == NULL changed from [b] when "savedlen < beyond" is true.
>> +	 */
>> +
>> +	/* Now send any packets that are being shifted out of saved, and account
>> +	 * for missing packets that are exiting the window as we shift it.
>> +	 */
>> +
>> +	/* If savedlen > beyond we are shifting some, else all. */
>> +	shifting = min(savedlen, beyond);
>> +
>> +	/* slot0 is the buf that just shifted out and into slot0 */
>> +	slot0 = NULL;
>> +	s0seq = wantseq;
>> +	last_drop_seq = s0seq;
>> +	wnext = xtfs->w_saved;
>> +	for (slot = 1; slot <= shifting; slot++, wnext++) {
>> +		/* handle what was in slot0 before we occupy it */
>> +		if (!slot0) {
>> +			last_drop_seq = s0seq;
>> +			missed++;
>> +		} else {
>> +			list_add_tail(&slot0->list, list);
>> +			count++;
>> +		}
>> +		s0seq++;
>> +		slot0 = wnext->skb;
>> +		wnext->skb = NULL;
>> +	}
>> +
>> +	/* slot0 is now either NULL (in which case it's what we now are waiting
>> +	 * for, or a buf in which case we need to handle it like we received it;
>> +	 * however, we may be advancing past that buffer as well..
>> +	 */
>> +
>> +	/* Handle case where we need to shift more than we had saved, slot0 will
>> +	 * be NULL iff savedlen is 0, otherwise slot0 will always be
>> +	 * non-NULL b/c we shifted the final element, which is always set if
>> +	 * there is any saved, into slot0.
>> +	 */
>> +	if (savedlen < beyond) {
>> +		extra_drops = beyond - savedlen;
>> +		if (savedlen == 0) {
>> +			BUG_ON(slot0);
>> +			s0seq += extra_drops;
>> +			last_drop_seq = s0seq - 1;
>> +		} else {
>> +			extra_drops--; /* we aren't dropping what's in slot0 */
>> +			BUG_ON(!slot0);
>> +			list_add_tail(&slot0->list, list);
>> +			/* if extra_drops then we are going past this slot0
>> +			 * so we can safely advance last_drop_seq
>> +			 */
>> +			if (extra_drops)
>> +				last_drop_seq = s0seq + extra_drops;
>> +			s0seq += extra_drops + 1;
>> +			count++;
>> +		}
>> +		missed += extra_drops;
>> +		slot0 = NULL;
>> +		/* slot0 has had an empty slot pushed into it */
>> +	}
>> +	(void)last_drop_seq;	/* we want this for CC code */
>> +
>> +	/* Remove the entries */
>> +	__vec_shift(xtfs, beyond);
>> +
>> +	/* Advance want seq */
>> +	xtfs->w_wantseq += beyond;
>> +
>> +	/* Process drops here when implementing congestion control */
>> +
>> +	/* We've shifted. plug the packet in at the end. */
>> +	xtfs->w_savedlen = nslots - 1;
>> +	xtfs->w_saved[xtfs->w_savedlen - 1].skb = inskb;
>> +	iptfs_set_window_drop_times(xtfs, xtfs->w_savedlen - 1);
>> +
>> +	/* if we don't have a slot0 then we must wait for it */
>> +	if (!slot0)
>> +		return count;
>> +
>> +	/* If slot0, seq must match new want seq */
>> +	BUG_ON(xtfs->w_wantseq != __esp_seq(slot0));
>> +
>> +	/* slot0 is valid, treat like we received expected. */
>> +	count += __reorder_this(xtfs, slot0, list);
>> +	return count;
>> +}
>
> ...
>
>> +/**
>> + * iptfs_get_mtu() - return the inner MTU for an IPTFS xfrm.
>
> nit: This does not match the name of the function it documents.

Fixed.

Thanks for your review!
Chris.

>> + * @x: xfrm state.
>> + * @outer_mtu: Outer MTU for the encapsulated packet.
>> + *
>> + * Return: Correct MTU taking in to account the encap overhead.
>> + */
>> +static u32 iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu)
>
> ...

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 857 bytes --]

Re: [PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[Simon Horman]

On Thu, Feb 22, 2024 at 03:23:36PM -0500, Christian Hopps wrote:
> 
> Simon Horman <horms@kernel.org> writes:
> 
> > On Mon, Feb 19, 2024 at 03:57:35AM -0500, Christian Hopps wrote:
> > > From: Christian Hopps <chopps@labn.net>
> > > 
> > > Add a new xfrm mode implementing AggFrag/IP-TFS from RFC9347.
> > > 
> > > This utilizes the new xfrm_mode_cbs to implement demand-driven IP-TFS
> > > functionality. This functionality can be used to increase bandwidth
> > > utilization through small packet aggregation, as well as help solve PMTU
> > > issues through it's efficient use of fragmentation.
> > > 
> > > Link: https://www.rfc-editor.org/rfc/rfc9347.txt
> > > 
> > > Signed-off-by: Christian Hopps <chopps@labn.net>
> > 
> > ...
> > 
> > > diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
> > 
> > ...
> > 
> > > +/**
> > > + * skb_head_to_frag() - initialize a skb_frag_t based on skb head data
> > > + * @skb: skb with the head data
> > > + * @frag: frag to initialize
> > > + */
> > > +static void skb_head_to_frag(const struct sk_buff *skb, skb_frag_t *frag)
> > > +{
> > > +	struct page *page = virt_to_head_page(skb->data);
> > > +	unsigned char *addr = (unsigned char *)page_address(page);
> > > +
> > > +	BUG_ON(!skb->head_frag);
> > 
> > Is it strictly necessary to crash the Kernel here?
> > Likewise, many other places in this patch.
> 
> In all use cases it represents a programming error (bug) if the condition is met.
> 
> What is the correct use of BUG_ON?

Hi Christian,

I would say that BUG_ON should used in situations where
there is an unrecoverable error to the extent where
the entire system cannot continue to function.

...

Re: [PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[Christian Hopps]

> On Feb 26, 2024, at 15:57, Simon Horman <horms@kernel.org> wrote:
> 
> On Thu, Feb 22, 2024 at 03:23:36PM -0500, Christian Hopps wrote:
>> 
>> Simon Horman <horms@kernel.org> writes:
>> 
>>> On Mon, Feb 19, 2024 at 03:57:35AM -0500, Christian Hopps wrote:
>>>> From: Christian Hopps <chopps@labn.net>
...
>>>> +/**
>>>> + * skb_head_to_frag() - initialize a skb_frag_t based on skb head data
>>>> + * @skb: skb with the head data
>>>> + * @frag: frag to initialize
>>>> + */
>>>> +static void skb_head_to_frag(const struct sk_buff *skb, skb_frag_t *frag)
>>>> +{
>>>> + struct page *page = virt_to_head_page(skb->data);
>>>> + unsigned char *addr = (unsigned char *)page_address(page);
>>>> +
>>>> + BUG_ON(!skb->head_frag);
>>> 
>>> Is it strictly necessary to crash the Kernel here?
>>> Likewise, many other places in this patch.
>> 
>> In all use cases it represents a programming error (bug) if the condition is met.
>> 
>> What is the correct use of BUG_ON?
> 
> Hi Christian,
> 
> I would say that BUG_ON should used in situations where
> there is an unrecoverable error to the extent where
> the entire system cannot continue to function.

Well in these cases it means that IPsec/IPTFS is in an unrecoverable state and broken. It's hard to predict how much that means "entire" to the user that expects their IPsec tunnels to be working, it may be the entire purpose of the box it's running on, so normally I don't think it's wise to try.

If you still object I will remove them.

Thanks,
Chris.

> 
> ...

Re: [PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[kernel test robot]

Hi Christian,

kernel test robot noticed the following build errors:

[auto build test ERROR on klassert-ipsec-next/master]
[also build test ERROR on klassert-ipsec/master netfilter-nf/main linus/master v6.8-rc5 next-20240220]
[cannot apply to nf-next/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Christian-Hopps/iptfs-config-add-CONFIG_XFRM_IPTFS/20240219-171931
base:   https://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git master
patch link:    https://lore.kernel.org/r/20240219085735.1220113-9-chopps%40chopps.org
patch subject: [PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl
config: i386-randconfig-r063-20240220 (https://download.01.org/0day-ci/archive/20240221/202402210751.pKXknmd9-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240221/202402210751.pKXknmd9-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202402210751.pKXknmd9-lkp@intel.com/

All errors (new ones prefixed by >>):

   ld: net/xfrm/xfrm_iptfs.o: in function `iptfs_copy_to_user':
>> net/xfrm/xfrm_iptfs.c:2624: undefined reference to `__udivdi3'
>> ld: net/xfrm/xfrm_iptfs.c:2628: undefined reference to `__udivdi3'


vim +2624 net/xfrm/xfrm_iptfs.c

  2602	
  2603	static int iptfs_copy_to_user(struct xfrm_state *x, struct sk_buff *skb)
  2604	{
  2605		struct xfrm_iptfs_data *xtfs = x->mode_data;
  2606		struct xfrm_iptfs_config *xc = &xtfs->cfg;
  2607		int ret;
  2608	
  2609		if (xc->dont_frag) {
  2610			ret = nla_put_flag(skb, XFRMA_IPTFS_DONT_FRAG);
  2611			if (ret)
  2612				return ret;
  2613		}
  2614		ret = nla_put_u16(skb, XFRMA_IPTFS_REORDER_WINDOW, xc->reorder_win_size);
  2615		if (ret)
  2616			return ret;
  2617		ret = nla_put_u32(skb, XFRMA_IPTFS_PKT_SIZE, xc->pkt_size);
  2618		if (ret)
  2619			return ret;
  2620		ret = nla_put_u32(skb, XFRMA_IPTFS_MAX_QSIZE, xc->max_queue_size);
  2621		if (ret)
  2622			return ret;
  2623		ret = nla_put_u32(skb, XFRMA_IPTFS_DROP_TIME,
> 2624				  xtfs->drop_time_ns / NSECS_IN_USEC);
  2625		if (ret)
  2626			return ret;
  2627		ret = nla_put_u32(skb, XFRMA_IPTFS_INIT_DELAY,
> 2628				  xtfs->init_delay_ns / NSECS_IN_USEC);
  2629		return ret;
  2630	}
  2631	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [devel-ipsec] [PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[Antony Antony]

Hi Chris,

This is a follow up to the 6/8 patch feedback I just sent. I noticed when 
migrating states with previous fixes I proposed. Still for me migrating 
states do not work yet.

__iptfs_init_state() called twice and IP-TFS parameters are overwritten.

check check poc patch I sent
https://linux-ipsec.org/pipermail/devel/2023/000395.html
it think this worked on v1 patch set.

see inline feedback bellow.

On Mon, Feb 19, 2024 at 03:57:35AM -0500, Christian Hopps via Devel wrote:
> From: Christian Hopps <chopps@labn.net>
> 
> Add a new xfrm mode implementing AggFrag/IP-TFS from RFC9347.
> 
> This utilizes the new xfrm_mode_cbs to implement demand-driven IP-TFS
> functionality. This functionality can be used to increase bandwidth
> utilization through small packet aggregation, as well as help solve PMTU
> issues through it's efficient use of fragmentation.
> 
> Link: https://www.rfc-editor.org/rfc/rfc9347.txt
> 
> Signed-off-by: Christian Hopps <chopps@labn.net>
> ---
>  net/xfrm/Makefile      |    1 +
>  net/xfrm/trace_iptfs.h |  218 ++++
>  net/xfrm/xfrm_iptfs.c  | 2762 ++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 2981 insertions(+)
>  create mode 100644 net/xfrm/trace_iptfs.h
>  create mode 100644 net/xfrm/xfrm_iptfs.c
> 
> diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
> index 547cec77ba03..cd6520d4d777 100644
> --- a/net/xfrm/Makefile
> +++ b/net/xfrm/Makefile
> @@ -20,5 +20,6 @@ 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
> diff --git a/net/xfrm/trace_iptfs.h b/net/xfrm/trace_iptfs.h
> new file mode 100644
> index 000000000000..3ab040b58362
> --- /dev/null
> +++ b/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 = skb->tail;
> +			   __entry->end = 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(skb_shinfo(skb)->frags[0].bv_page)
> +					       : 0);
> +			   __entry->pg0off = (__entry->nr_frags
> +					      ? skb_shinfo(skb)->frags[0].bv_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>
> diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
> new file mode 100644
> index 000000000000..97ac002b9f71
> --- /dev/null
> +++ b/net/xfrm/xfrm_iptfs.c
> @@ -0,0 +1,2762 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* xfrm_iptfs: IPTFS encapsulation support
> + *
> + * April 21 2022, Christian Hopps <chopps@labn.net>
> + *
> + * Copyright (c) 2022, LabN Consulting, L.L.C.
> + *
> + */
> +
> +#include <linux/kernel.h>
> +#include <linux/icmpv6.h>
> +#include <net/gro.h>
> +#include <net/icmp.h>
> +#include <net/ip6_route.h>
> +#include <net/inet_ecn.h>
> +#include <net/xfrm.h>
> +
> +#include <crypto/aead.h>
> +
> +#include "xfrm_inout.h"
> +#include "trace_iptfs.h"
> +
> +/* IPTFS encap (header) values. */
> +#define IPTFS_SUBTYPE_BASIC 0
> +#define IPTFS_SUBTYPE_CC 1
> +
> +/* 1) skb->head should be cache aligned.
> + * 2) when resv is for L2 headers (i.e., ethernet) we want the cacheline to
> + * start -16 from data.
> + * 3) when resv is for L3+L2 headers IOW skb->data points at the IPTFS payload
> + * we want data to be cache line aligned so all the pushed headers will be in
> + * another cacheline.
> + */
> +#define XFRM_IPTFS_MIN_L3HEADROOM 128
> +#define XFRM_IPTFS_MIN_L2HEADROOM (64 + 16)
> +#define IPTFS_FRAG_COPY_MAX 256	/* max for copying to create iptfs frags */
> +#define IPTFS_PKT_SHARE_MIN 129	/* min to try to share vs copy pkt data */
> +#define NSECS_IN_USEC 1000
> +
> +#define IPTFS_TYPE_NOCC 0
> +#define IPTFS_TYPE_CC 1
> +
> +#define IPTFS_HRTIMER_MODE HRTIMER_MODE_REL_SOFT
> +
> +struct skb_wseq {
> +	struct sk_buff *skb;
> +	u64 drop_time;
> +};
> +
> +struct xfrm_iptfs_config {
> +	bool dont_frag : 1;
> +	u16 reorder_win_size;
> +	u32 pkt_size;	    /* outer_packet_size or 0 */
> +	u32 max_queue_size; /* octets */
> +};
> +
> +struct xfrm_iptfs_data {
> +	struct xfrm_iptfs_config cfg;
> +
> +	/* Ingress User Input */
> +	struct xfrm_state *x;	    /* owning state */
> +	struct sk_buff_head queue;  /* output queue */
> +	u32 queue_size;		    /* octets */
> +	u32 ecn_queue_size;	    /* octets above which ECN mark */
> +	u64 init_delay_ns;	    /* nanoseconds */
> +	struct hrtimer iptfs_timer; /* output timer */
> +	time64_t iptfs_settime;	    /* time timer was set */
> +	u32 payload_mtu;	    /* max payload size */
> +
> +	/* Tunnel input reordering */
> +	bool w_seq_set;		  /* true after first seq received */
> +	u64 w_wantseq;		  /* expected next sequence */
> +	struct skb_wseq *w_saved; /* the saved buf array */
> +	u32 w_savedlen;		  /* the saved len (not size) */
> +	spinlock_t drop_lock;
> +	struct hrtimer drop_timer;
> +	u64 drop_time_ns;
> +
> +	/* Tunnel input reassembly */
> +	struct sk_buff *ra_newskb; /* new pkt being reassembled */
> +	u64 ra_wantseq;		   /* expected next sequence */
> +	u8 ra_runt[6];		   /* last pkt bytes from last skb */
> +	u8 ra_runtlen;		   /* count of ra_runt */
> +};
> +
> +static u32 __iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu);
> +static enum hrtimer_restart iptfs_delay_timer(struct hrtimer *me);
> +static enum hrtimer_restart iptfs_drop_timer(struct hrtimer *me);
> +
> +/* ================= */
> +/* Utility Functions */
> +/* ================= */
> +
> +static u32 __trace_ip_proto(struct iphdr *iph)
> +{
> +	if (iph->version == 4)
> +		return iph->protocol;
> +	return ((struct ipv6hdr *)iph)->nexthdr;
> +}
> +
> +static u32 __trace_ip_proto_seq(struct iphdr *iph)
> +{
> +	void *nexthdr;
> +	u32 protocol = 0;
> +
> +	if (iph->version == 4) {
> +		nexthdr = (void *)(iph + 1);
> +		protocol = iph->protocol;
> +	} else if (iph->version == 6) {
> +		nexthdr = (void *)(((struct ipv6hdr *)(iph)) + 1);
> +		protocol = ((struct ipv6hdr *)(iph))->nexthdr;
> +	}
> +	switch (protocol) {
> +	case IPPROTO_ICMP:
> +		return ntohs(((struct icmphdr *)nexthdr)->un.echo.sequence);
> +	case IPPROTO_ICMPV6:
> +		return ntohs(((struct icmp6hdr *)nexthdr)->icmp6_sequence);
> +	case IPPROTO_TCP:
> +		return ntohl(((struct tcphdr *)nexthdr)->seq);
> +	case IPPROTO_UDP:
> +		return ntohs(((struct udphdr *)nexthdr)->source);
> +	default:
> +		return 0;
> +	}
> +}
> +
> +static u64 __esp_seq(struct sk_buff *skb)
> +{
> +	u64 seq = ntohl(XFRM_SKB_CB(skb)->seq.input.low);
> +
> +	return seq | (u64)ntohl(XFRM_SKB_CB(skb)->seq.input.hi) << 32;
> +}
> +
> +/* ================= */
> +/* SK_BUFF Functions */
> +/* ================= */
> +
> +/**
> + * iptfs_alloc_skb() - Allocate a new `skb` using a meta-data template.
> + * @tpl: the template to copy the new `skb`s meta-data from.
> + * @len: the linear length of the head data, zero is fine.
> + * @l3resv: true if reserve needs to support pushing L3 headers
> + *
> + * A new `skb` is allocated and it's meta-data is initialized from `tpl`, the
> + * head data is sized to `len` + reserved space set according to the @l3resv
> + * boolean. When @l3resv is false, resv is XFRM_IPTFS_MIN_L2HEADROOM which
> + * arranges for `skb->data - 16` (etherhdr space) to be the start of a cacheline.
> + * Otherwise, @l3resv is true and resv is either the size of headroom from `tpl` or
> + * XFRM_IPTFS_MIN_L3HEADROOM whichever is greater, which tries to align
> + * skb->data to a cacheline as all headers will be pushed on the previous
> + * cacheline bytes.
> + *
> + * When copying meta-data from the @tpl, the sk_buff->headers are not copied.
> + *
> + * Zero length skbs are allocated when we only need a head skb to hold new
> + * packet headers (basically the mac header) that sit on top of existing shared
> + * packet data.
> + *
> + * Return: the new skb or NULL.
> + */
> +static struct sk_buff *iptfs_alloc_skb(struct sk_buff *tpl, u32 len,
> +				       bool l3resv)
> +{
> +	struct sk_buff *skb;
> +	u32 resv;
> +
> +	if (!l3resv) {
> +		resv = XFRM_IPTFS_MIN_L2HEADROOM;
> +	} else {
> +		resv = skb_headroom(tpl);
> +		if (resv < XFRM_IPTFS_MIN_L3HEADROOM)
> +			resv = XFRM_IPTFS_MIN_L3HEADROOM;
> +	}
> +
> +	skb = alloc_skb(len + resv, GFP_ATOMIC);
> +	if (!skb) {
> +		XFRM_INC_STATS(dev_net(tpl->dev), LINUX_MIB_XFRMINERROR);
> +		return NULL;
> +	}
> +
> +	skb_reserve(skb, resv);
> +
> +	/* Code from __copy_skb_header() -- we do not want any of the
> +	 * tpl->headers copied over, so we aren't using `skb_copy_header()`.
> +	 */
> +	skb->tstamp = tpl->tstamp;
> +	skb->dev = tpl->dev;
> +	memcpy(skb->cb, tpl->cb, sizeof(skb->cb));
> +	skb_dst_copy(skb, tpl);
> +	__skb_ext_copy(skb, tpl);
> +	__nf_copy(skb, tpl, false);
> +
> +	return skb;
> +}
> +
> +/**
> + * skb_head_to_frag() - initialize a skb_frag_t based on skb head data
> + * @skb: skb with the head data
> + * @frag: frag to initialize
> + */
> +static void skb_head_to_frag(const struct sk_buff *skb, skb_frag_t *frag)
> +{
> +	struct page *page = virt_to_head_page(skb->data);
> +	unsigned char *addr = (unsigned char *)page_address(page);
> +
> +	BUG_ON(!skb->head_frag);
> +	skb_frag_fill_page_desc(frag, page, skb->data - addr, skb_headlen(skb));
> +}
> +
> +/**
> + * struct skb_frag_walk - use to track a walk through fragments
> + * @fragi: current fragment index
> + * @past: length of data in fragments before @fragi
> + * @total: length of data in all fragments
> + * @nr_frags: number of fragments present in array
> + * @initial_offset: the value passed in to skb_prepare_frag_walk()
> + * @pp_recycle: copy of skb->pp_recycle
> + * @frags: the page fragments inc. room for head page
> + */
> +struct skb_frag_walk {
> +	u32 fragi;
> +	u32 past;
> +	u32 total;
> +	u32 nr_frags;
> +	u32 initial_offset;
> +	bool pp_recycle;
> +	skb_frag_t frags[MAX_SKB_FRAGS + 1];
> +};
> +
> +/**
> + * skb_prepare_frag_walk() - initialize a frag walk over an skb.
> + * @skb: the skb to walk.
> + * @initial_offset: start the walk @initial_offset into the skb.
> + * @walk: the walk to initialize
> + *
> + * Future calls to skb_add_frags() will expect the @offset value to be at
> + * least @initial_offset large.
> + */
> +static void skb_prepare_frag_walk(struct sk_buff *skb, u32 initial_offset,
> +				  struct skb_frag_walk *walk)
> +{
> +	struct skb_shared_info *shinfo = skb_shinfo(skb);
> +	skb_frag_t *frag, *from;
> +	u32 i;
> +
> +	walk->initial_offset = initial_offset;
> +	walk->fragi = 0;
> +	walk->past = 0;
> +	walk->total = 0;
> +	walk->nr_frags = 0;
> +	walk->pp_recycle = skb->pp_recycle;
> +
> +	if (skb->head_frag) {
> +		if (initial_offset >= skb_headlen(skb)) {
> +			initial_offset -= skb_headlen(skb);
> +		} else {
> +			frag = &walk->frags[walk->nr_frags++];
> +			skb_head_to_frag(skb, frag);
> +			frag->bv_offset += initial_offset;
> +			frag->bv_len -= initial_offset;
> +			walk->total += frag->bv_len;
> +			initial_offset = 0;
> +		}
> +	} else {
> +		BUG_ON(skb_headlen(skb) > initial_offset);
> +		initial_offset -= skb_headlen(skb);
> +	}
> +
> +	for (i = 0; i < shinfo->nr_frags; i++) {
> +		from = &shinfo->frags[i];
> +		if (initial_offset >= from->bv_len) {
> +			initial_offset -= from->bv_len;
> +			continue;
> +		}
> +		frag = &walk->frags[walk->nr_frags++];
> +		*frag = *from;
> +		if (initial_offset) {
> +			frag->bv_offset += initial_offset;
> +			frag->bv_len -= initial_offset;
> +			initial_offset = 0;
> +		}
> +		walk->total += frag->bv_len;
> +	}
> +	BUG_ON(initial_offset != 0);
> +}
> +
> +static u32 __skb_reset_frag_walk(struct skb_frag_walk *walk, u32 offset)
> +{
> +	/* Adjust offset to refer to internal walk values */
> +	BUG_ON(offset < walk->initial_offset);
> +	offset -= walk->initial_offset;
> +
> +	/* Get to the correct fragment for offset */
> +	while (offset < walk->past) {
> +		walk->past -= walk->frags[--walk->fragi].bv_len;
> +		if (offset >= walk->past)
> +			break;
> +		BUG_ON(walk->fragi == 0);
> +	}
> +	while (offset >= walk->past + walk->frags[walk->fragi].bv_len)
> +		walk->past += walk->frags[walk->fragi++].bv_len;
> +
> +	/* offset now relative to this current frag */
> +	offset -= walk->past;
> +	return offset;
> +}
> +
> +/**
> + * skb_can_add_frags() - check if ok to add frags from walk to skb
> + * @skb: skb to check for adding frags to
> + * @walk: the walk that will be used as source for frags.
> + * @offset: offset from beginning of original skb to start from.
> + * @len: amount of data to add frag references to in @skb.
> + */
> +static bool skb_can_add_frags(const struct sk_buff *skb,
> +			      struct skb_frag_walk *walk, u32 offset, u32 len)
> +{
> +	struct skb_shared_info *shinfo = skb_shinfo(skb);
> +	u32 fragi, nr_frags, fraglen;
> +
> +	if (skb_has_frag_list(skb) || skb->pp_recycle != walk->pp_recycle)
> +		return false;
> +
> +	/* Make offset relative to current frag after setting that */
> +	offset = __skb_reset_frag_walk(walk, offset);
> +
> +	/* Verify we have array space for the fragments we need to add */
> +	fragi = walk->fragi;
> +	nr_frags  = shinfo->nr_frags;
> +	while (len && fragi < walk->nr_frags) {
> +		skb_frag_t *frag = &walk->frags[fragi];
> +
> +		fraglen = frag->bv_len;
> +		if (offset) {
> +			fraglen -= offset;
> +			offset = 0;
> +		}
> +		if (++nr_frags > MAX_SKB_FRAGS)
> +			return false;
> +		if (len <= fraglen)
> +			return true;
> +		len -= fraglen;
> +		fragi++;
> +	}
> +	/* We may not copy all @len but what we have will fit. */
> +	return true;
> +}
> +
> +/**
> + * skb_add_frags() - add a range of fragment references into an skb
> + * @skb: skb to add references into
> + * @walk: the walk to add referenced fragments from.
> + * @offset: offset from beginning of original skb to start from.
> + * @len: amount of data to add frag references to in @skb.
> + *
> + * skb_can_add_frags() should be called before this function to verify that the
> + * destination @skb is compatible with the walk and has space in the array for
> + * the to be added frag refrences.
> + *
> + * Return: The number of bytes not added to @skb b/c we reached the end of the
> + * walk before adding all of @len.
> + */
> +static int skb_add_frags(struct sk_buff *skb, struct skb_frag_walk *walk,
> +			 u32 offset, u32 len)
> +{
> +	struct skb_shared_info *shinfo = skb_shinfo(skb);
> +	u32 fraglen;
> +
> +	BUG_ON(skb->pp_recycle != walk->pp_recycle);
> +	if (!walk->nr_frags || offset >= walk->total + walk->initial_offset)
> +		return len;
> +
> +	/* make offset relative to current frag after setting that */
> +	offset = __skb_reset_frag_walk(walk, offset);
> +	BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
> +
> +	while (len && walk->fragi < walk->nr_frags) {
> +		skb_frag_t *frag = &walk->frags[walk->fragi];
> +		skb_frag_t *tofrag = &shinfo->frags[shinfo->nr_frags];
> +
> +		*tofrag = *frag;
> +		if (offset) {
> +			tofrag->bv_offset += offset;
> +			tofrag->bv_len -= offset;
> +			offset = 0;
> +		}
> +		__skb_frag_ref(tofrag);
> +		shinfo->nr_frags++;
> +		BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS);
> +
> +		/* see if we are done */
> +		fraglen = tofrag->bv_len;
> +		if (len < fraglen) {
> +			tofrag->bv_len = len;
> +			skb->len += len;
> +			skb->data_len += len;
> +			return 0;
> +		}
> +		/* advance to next source fragment */
> +		len -= fraglen;		  /* careful, use dst bv_len */
> +		skb->len += fraglen;	  /* careful, "   "    "     */
> +		skb->data_len += fraglen; /* careful, "   "    "     */
> +		walk->past +=
> +			frag->bv_len; /* careful, use src bv_len */
> +		walk->fragi++;
> +	}
> +	return len;
> +}
> +
> +/**
> + * skb_copy_bits_seq - copy bits from a skb_seq_state to kernel buffer
> + * @st: source skb_seq_state
> + * @offset: offset in source
> + * @to: destination buffer
> + * @len: number of bytes to copy
> + *
> + * Copy @len bytes from @offset bytes into the source @st to the destination
> + * buffer @to. `offset` should increase (or be unchanged) with each subsequent
> + * call to this function. If offset needs to decrease from the previous use `st`
> + * should be reset first.
> + */
> +static int skb_copy_bits_seq(struct skb_seq_state *st, int offset, void *to, int len)
> +{
> +	const u8 *data;
> +	u32 sqlen;
> +
> +	for (;;) {
> +		sqlen = skb_seq_read(offset, &data, st);
> +		if (sqlen == 0)
> +			return -ENOMEM;
> +		if (sqlen >= len) {
> +			memcpy(to, data, len);
> +			return 0;
> +		}
> +		memcpy(to, data, sqlen);
> +		to += sqlen;
> +		offset += sqlen;
> +		len -= sqlen;
> +	}
> +}
> +
> +/* ================================== */
> +/* IPTFS Trace Event Definitions      */
> +/* ================================== */
> +
> +#define CREATE_TRACE_POINTS
> +#include "trace_iptfs.h"
> +
> +/* ================================== */
> +/* IPTFS Receiving (egress) Functions */
> +/* ================================== */
> +
> +/**
> + * iptfs_pskb_add_frags() - Create and add frags into a new sk_buff.
> + * @tpl: template to create new skb from.
> + * @walk: The source for fragments to add.
> + * @off: The offset into @walk to add frags from, also used with @st and
> + *       @copy_len.
> + * @len: The length of data to add covering frags from @walk into @skb.
> + *       This must be <= @skblen.
> + * @st: The sequence state to copy from into the new head skb.
> + * @copy_len: Copy @copy_len bytes from @st at offset @off into the new skb
> + *            linear space.
> + *
> + * Create a new sk_buff `skb` using the template @tpl. Copy @copy_len bytes from
> + * @st into the new skb linear space, and then add shared fragments from the
> + * frag walk for the remaining @len of data (i.e., @len - @copy_len bytes).
> + *
> + * Return: The newly allocated sk_buff `skb` or NULL if an error occurs.
> + */
> +static struct sk_buff *iptfs_pskb_add_frags(struct sk_buff *tpl,
> +					    struct skb_frag_walk *walk, u32 off,
> +					    u32 len, struct skb_seq_state *st,
> +					    u32 copy_len)
> +{
> +	struct sk_buff *skb;
> +
> +	skb = iptfs_alloc_skb(tpl, copy_len, false);
> +	if (!skb)
> +		return NULL;
> +
> +	/* this should not normally be happening */
> +	if (!skb_can_add_frags(skb, walk, off + copy_len, len - copy_len)) {
> +		kfree_skb(skb);
> +		return NULL;
> +	}
> +
> +	if (copy_len &&
> +	    skb_copy_bits_seq(st, off, skb_put(skb, copy_len), copy_len)) {
> +		XFRM_INC_STATS(dev_net(st->root_skb->dev),
> +			       LINUX_MIB_XFRMINERROR);
> +		kfree_skb(skb);
> +		return NULL;
> +	}
> +
> +	skb_add_frags(skb, walk, off + copy_len, len - copy_len);
> +	return skb;
> +}
> +
> +/**
> + * iptfs_pskb_extract_seq() - Create and load data into a new sk_buff.
> + * @skblen: the total data size for `skb`.
> + * @st: The source for the rest of the data to copy into `skb`.
> + * @off: The offset into @st to copy data from.
> + * @len: The length of data to copy from @st into `skb`. This must be <=
> + *       @skblen.
> + *
> + * Create a new sk_buff `skb` with @skblen of packet data space. If non-zero,
> + * copy @rlen bytes of @runt into `skb`. Then using seq functions copy @len
> + * bytes from @st into `skb` starting from @off.
> + *
> + * It is an error for @len to be greater than the amount of data left in @st.
> + *
> + * Return: The newly allocated sk_buff `skb` or NULL if an error occurs.
> + */
> +static struct sk_buff *
> +iptfs_pskb_extract_seq(u32 skblen, struct skb_seq_state *st, u32 off, int len)
> +{
> +	struct sk_buff *skb = iptfs_alloc_skb(st->root_skb, skblen, false);
> +
> +	if (!skb)
> +		return NULL;
> +	if (skb_copy_bits_seq(st, off, skb_put(skb, len), len)) {
> +		XFRM_INC_STATS(dev_net(st->root_skb->dev),
> +			       LINUX_MIB_XFRMINERROR);
> +		kfree_skb(skb);
> +		return NULL;
> +	}
> +	return skb;
> +}
> +
> +/**
> + * iptfs_input_save_runt() - save data in xtfs runt space.
> + * @xtfs: xtfs state
> + * @seq: the current sequence
> + * @buf: packet data
> + * @len: length of packet data
> + *
> + * Save the small (`len`) start of a fragmented packet in `buf` in the xtfs data
> + * runt space.
> + */
> +static void iptfs_input_save_runt(struct xfrm_iptfs_data *xtfs, u64 seq,
> +				  u8 *buf, int len)
> +{
> +	BUG_ON(xtfs->ra_newskb); /* we won't have a new SKB yet */
> +
> +	memcpy(xtfs->ra_runt, buf, len);
> +
> +	xtfs->ra_runtlen = len;
> +	xtfs->ra_wantseq = seq + 1;
> +}
> +
> +/**
> + * __iptfs_iphlen() - return the v4/v6 header length using packet data.
> + * @data: pointer at octet with version nibble
> + *
> + * The version data is expected to be valid (i.e., either 4 or 6).
> + */
> +static u32 __iptfs_iphlen(u8 *data)
> +{
> +	struct iphdr *iph = (struct iphdr *)data;
> +
> +	if (iph->version == 0x4)
> +		return sizeof(*iph);
> +	BUG_ON(iph->version != 0x6);
> +	return sizeof(struct ipv6hdr);
> +}
> +
> +/**
> + * __iptfs_iplen() - return the v4/v6 length using packet data.
> + * @data: pointer to ip (v4/v6) packet header
> + *
> + * Grab the IPv4 or IPv6 length value in the start of the inner packet header
> + * pointed to by `data`. Assumes data len is enough for the length field only.
> + *
> + * The version data is expected to be valid (i.e., either 4 or 6).
> + */
> +static u32 __iptfs_iplen(u8 *data)
> +{
> +	struct iphdr *iph = (struct iphdr *)data;
> +
> +	if (iph->version == 0x4)
> +		return ntohs(iph->tot_len);
> +	BUG_ON(iph->version != 0x6);
> +	return ntohs(((struct ipv6hdr *)iph)->payload_len) +
> +	       sizeof(struct ipv6hdr);
> +}
> +
> +/**
> + * iptfs_complete_inner_skb() - finish preparing the inner packet for gro recv.
> + * @x: xfrm state
> + * @skb: the inner packet
> + *
> + * Finish the standard xfrm processing on the inner packet prior to sending back
> + * through gro_cells_receive. We do this separately b/c we are building a list
> + * of packets in the hopes that one day a list will be taken by
> + * xfrm_input.
> + */
> +static void iptfs_complete_inner_skb(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	skb_reset_network_header(skb);
> +
> +	/* The packet is going back through gro_cells_receive no need to
> +	 * set this.
> +	 */
> +	skb_reset_transport_header(skb);
> +
> +	/* Packet already has checksum value set. */
> +	skb->ip_summed = CHECKSUM_NONE;
> +
> +	/* Our skb will contain the header data copied when this outer packet
> +	 * which contained the start of this inner packet. This is true
> +	 * when we allocate a new skb as well as when we reuse the existing skb.
> +	 */
> +	if (ip_hdr(skb)->version == 0x4) {
> +		struct iphdr *iph = ip_hdr(skb);
> +
> +		if (x->props.flags & XFRM_STATE_DECAP_DSCP)
> +			ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, iph);
> +		if (!(x->props.flags & XFRM_STATE_NOECN))
> +			if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
> +				IP_ECN_set_ce(iph);
> +
> +		skb->protocol = htons(ETH_P_IP);
> +	} else {
> +		struct ipv6hdr *iph = ipv6_hdr(skb);
> +
> +		if (x->props.flags & XFRM_STATE_DECAP_DSCP)
> +			ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, iph);
> +		if (!(x->props.flags & XFRM_STATE_NOECN))
> +			if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
> +				IP6_ECN_set_ce(skb, iph);
> +
> +		skb->protocol = htons(ETH_P_IPV6);
> +	}
> +}
> +
> +static void __iptfs_reassem_done(struct xfrm_iptfs_data *xtfs, bool free)
> +{
> +	assert_spin_locked(&xtfs->drop_lock);
> +
> +	/* We don't care if it works locking takes care of things */
> +	hrtimer_try_to_cancel(&xtfs->drop_timer);
> +	if (free)
> +		kfree_skb(xtfs->ra_newskb);
> +	xtfs->ra_newskb = NULL;
> +}
> +
> +/**
> + * iptfs_reassem_done() - In-progress packet is aborted free the state.
> + * @xtfs: xtfs state
> + */
> +static void iptfs_reassem_abort(struct xfrm_iptfs_data *xtfs)
> +{
> +	__iptfs_reassem_done(xtfs, true);
> +}
> +
> +/**
> + * iptfs_reassem_done() - In-progress packet is complete, clear the state.
> + * @xtfs: xtfs state
> + */
> +static void iptfs_reassem_done(struct xfrm_iptfs_data *xtfs)
> +{
> +	__iptfs_reassem_done(xtfs, false);
> +}
> +
> +/**
> + * iptfs_reassem_cont() - Continue the reassembly of an inner packets.
> + * @xtfs: xtfs state
> + * @seq: sequence of current packet
> + * @st: seq read stat for current packet
> + * @skb: current packet
> + * @data: offset into sequential packet data
> + * @blkoff: packet blkoff value
> + * @list: list of skbs to enqueue completed packet on
> + *
> + * Process an IPTFS payload that has a non-zero `blkoff` or when we are
> + * expecting the continuation b/c we have a runt or in-progress packet.
> + */
> +static u32 iptfs_reassem_cont(struct xfrm_iptfs_data *xtfs, u64 seq,
> +			      struct skb_seq_state *st, struct sk_buff *skb,
> +			      u32 data, u32 blkoff, struct list_head *list)
> +{
> +	struct skb_frag_walk _fragwalk;
> +	struct skb_frag_walk *fragwalk = NULL;
> +	struct sk_buff *newskb = xtfs->ra_newskb;
> +	u32 remaining = skb->len - data;
> +	u32 runtlen = xtfs->ra_runtlen;
> +	u32 copylen, fraglen, ipremain, iphlen, iphremain, rrem;
> +
> +	/* Handle packet fragment we aren't expecting */
> +	if (!runtlen && !xtfs->ra_newskb)
> +		return data + min(blkoff, remaining);
> +
> +	/* Important to remember that input to this function is an ordered
> +	 * packet stream (unless the user disabled the reorder window). Thus if
> +	 * we are waiting for, and expecting the next packet so we can continue
> +	 * assembly, a newer sequence number indicates older ones are not coming
> +	 * (or if they do should be ignored). Technically we can receive older
> +	 * ones when the reorder window is disabled; however, the user should
> +	 * have disabled fragmentation in this case, and regardless we don't
> +	 * deal with it.
> +	 *
> +	 * blkoff could be zero if the stream is messed up (or it's an all pad
> +	 * insertion) be careful to handle that case in each of the below
> +	 */
> +
> +	/* Too old case: This can happen when the reorder window is disabled so
> +	 * ordering isn't actually guaranteed.
> +	 */
> +	if (seq < xtfs->ra_wantseq)
> +		return data + remaining;
> +
> +	/* Too new case: We missed what we wanted cleanup. */
> +	if (seq > xtfs->ra_wantseq) {
> +		XFRM_INC_STATS(dev_net(skb->dev),
> +			       LINUX_MIB_XFRMINIPTFSERROR);
> +		goto abandon;
> +	}
> +
> +	if (blkoff == 0) {
> +		if ((*skb->data & 0xF0) != 0) {
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMINIPTFSERROR);
> +			goto abandon;
> +		}
> +		/* Handle all pad case, advance expected sequence number.
> +		 * (RFC 9347 S2.2.3)
> +		 */
> +		xtfs->ra_wantseq++;
> +		/* will end parsing */
> +		return data + remaining;
> +	}
> +
> +	if (runtlen) {
> +		BUG_ON(xtfs->ra_newskb);
> +
> +		/* Regardless of what happens we're done with the runt */
> +		xtfs->ra_runtlen = 0;
> +
> +		/* The start of this inner packet was at the very end of the last
> +		 * iptfs payload which didn't include enough for the ip header
> +		 * length field. We must have *at least* that now.
> +		 */
> +		rrem = sizeof(xtfs->ra_runt) - runtlen;
> +		if (remaining < rrem || blkoff < rrem) {
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMINIPTFSERROR);
> +			goto abandon;
> +		}
> +
> +		/* fill in the runt data */
> +		if (skb_copy_bits_seq(st, data, &xtfs->ra_runt[runtlen],
> +				      rrem)) {
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMINBUFFERERROR);
> +			goto abandon;
> +		}
> +
> +		/* We have enough data to get the ip length value now,
> +		 * allocate an in progress skb
> +		 */
> +		ipremain = __iptfs_iplen(xtfs->ra_runt);
> +		if (ipremain < sizeof(xtfs->ra_runt)) {
> +			/* length has to be at least runtsize large */
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMINIPTFSERROR);
> +			goto abandon;
> +		}
> +
> +		/* For the runt case we don't attempt sharing currently. NOTE:
> +		 * Currently, this IPTFS implementation will not create runts.
> +		 */
> +
> +		newskb = iptfs_alloc_skb(skb, ipremain, false);
> +		if (!newskb) {
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMINERROR);
> +			goto abandon;
> +		}
> +		xtfs->ra_newskb = newskb;
> +
> +		/* Copy the runt data into the buffer, but leave data
> +		 * pointers the same as normal non-runt case. The extra `rrem`
> +		 * recopied bytes are basically cacheline free. Allows using
> +		 * same logic below to complete.
> +		 */
> +		memcpy(skb_put(newskb, runtlen), xtfs->ra_runt,
> +		       sizeof(xtfs->ra_runt));
> +	}
> +
> +	/* Continue reassembling the packet */
> +	ipremain = __iptfs_iplen(newskb->data);
> +	iphlen = __iptfs_iphlen(newskb->data);
> +
> +	/* Sanity check, we created the newskb knowing the IP length so the IP
> +	 * length can't now be shorter.
> +	 */
> +	BUG_ON(newskb->len > ipremain);
> +
> +	ipremain -= newskb->len;
> +	if (blkoff < ipremain) {
> +		/* Corrupt data, we don't have enough to complete the packet */
> +		XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINIPTFSERROR);
> +		goto abandon;
> +	}
> +
> +	/* We want the IP header in linear space */
> +	if (newskb->len < iphlen)  {
> +		iphremain = iphlen - newskb->len;
> +		if (blkoff < iphremain) {
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMINIPTFSERROR);
> +			goto abandon;
> +		}
> +		fraglen = min(blkoff, remaining);
> +		copylen = min(fraglen, iphremain);
> +		BUG_ON(skb_tailroom(newskb) < copylen);
> +		if (skb_copy_bits_seq(st, data, skb_put(newskb, copylen), copylen)) {
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMINBUFFERERROR);
> +			goto abandon;
> +		}
> +		/* this is a silly condition that might occur anyway */
> +		if (copylen < iphremain) {
> +			xtfs->ra_wantseq++;
> +			return data + fraglen;
> +		}
> +		/* update data and things derived from it */
> +		data += copylen;
> +		blkoff -= copylen;
> +		remaining -= copylen;
> +		ipremain -= copylen;
> +	}
> +
> +	fraglen = min(blkoff, remaining);
> +	copylen = min(fraglen, ipremain);
> +
> +	/* If we may have the opportunity to share prepare a fragwalk. */
> +	if (!skb_has_frag_list(skb) && !skb_has_frag_list(newskb) &&
> +	    (skb->head_frag || skb->len == skb->data_len) &&
> +	    skb->pp_recycle == newskb->pp_recycle) {
> +		fragwalk = &_fragwalk;
> +		skb_prepare_frag_walk(skb, data, fragwalk);
> +	}
> +
> +	/* Try share then copy. */
> +	if (fragwalk && skb_can_add_frags(newskb, fragwalk, data, copylen)) {
> +		u32 leftover;
> +
> +		leftover = skb_add_frags(newskb, fragwalk, data, copylen);
> +		BUG_ON(leftover != 0);
> +	} else {
> +		/* We verified this was true in the main receive routine */
> +		BUG_ON(skb_tailroom(newskb) < copylen);
> +
> +		/* copy fragment data into newskb */
> +		if (skb_copy_bits_seq(st, data, skb_put(newskb, copylen), copylen)) {
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMINBUFFERERROR);
> +			goto abandon;
> +		}
> +	}
> +
> +	if (copylen < ipremain) {
> +		xtfs->ra_wantseq++;
> +	} else {
> +		/* We are done with packet reassembly! */
> +		BUG_ON(copylen != ipremain);
> +		iptfs_reassem_done(xtfs);
> +		iptfs_complete_inner_skb(xtfs->x, newskb);
> +		list_add_tail(&newskb->list, list);
> +	}
> +
> +	/* will continue on to new data block or end */
> +	return data + fraglen;
> +
> +abandon:
> +	if (xtfs->ra_newskb) {
> +		iptfs_reassem_abort(xtfs);
> +	} else {
> +		xtfs->ra_runtlen = 0;
> +		xtfs->ra_wantseq = 0;
> +	}
> +	/* skip past fragment, maybe to end */
> +	return data + min(blkoff, remaining);
> +}
> +
> +/**
> + * iptfs_input_ordered() - handle next in order IPTFS payload.
> + * @x: xfrm state
> + * @skb: current packet
> + *
> + * Process the IPTFS payload in `skb` and consume it afterwards.
> + */
> +static int iptfs_input_ordered(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	u8 hbytes[sizeof(struct ipv6hdr)];
> +	struct ip_iptfs_cc_hdr iptcch;
> +	struct skb_seq_state skbseq;
> +	struct skb_frag_walk _fragwalk;
> +	struct skb_frag_walk *fragwalk = NULL;
> +	struct list_head sublist; /* rename this it's just a list */
> +	struct sk_buff *first_skb, *defer, *next;
> +	const unsigned char *old_mac;
> +	struct xfrm_iptfs_data *xtfs;
> +	struct ip_iptfs_hdr *ipth;
> +	struct iphdr *iph;
> +	struct net *net;
> +	u32 remaining, first_iplen, iplen, iphlen, data, tail;
> +	u32 blkoff, capturelen;
> +	u64 seq;
> +
> +	xtfs = x->mode_data;
> +	net = dev_net(skb->dev);
> +	first_skb = NULL;
> +	defer = NULL;
> +
> +	seq = __esp_seq(skb);
> +
> +	/* Large enough to hold both types of header */
> +	ipth = (struct ip_iptfs_hdr *)&iptcch;
> +
> +	/* Save the old mac header if set */
> +	old_mac = skb_mac_header_was_set(skb) ? skb_mac_header(skb) : NULL;
> +
> +	skb_prepare_seq_read(skb, 0, skb->len, &skbseq);
> +
> +	/* Get the IPTFS header and validate it */
> +
> +	if (skb_copy_bits_seq(&skbseq, 0, ipth, sizeof(*ipth))) {
> +		XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
> +		goto done;
> +	}
> +	data = sizeof(*ipth);
> +
> +	trace_iptfs_egress_recv(skb, xtfs, htons(ipth->block_offset));
> +
> +	/* Set data past the basic header */
> +	if (ipth->subtype == IPTFS_SUBTYPE_CC) {
> +		/* Copy the rest of the CC header */
> +		remaining = sizeof(iptcch) - sizeof(*ipth);
> +		if (skb_copy_bits_seq(&skbseq, data, ipth + 1, remaining)) {
> +			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
> +			goto done;
> +		}
> +		data += remaining;
> +	} else if (ipth->subtype != IPTFS_SUBTYPE_BASIC) {
> +		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
> +		goto done;
> +	}
> +
> +	if (ipth->flags != 0) {
> +		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
> +		goto done;
> +	}
> +
> +	INIT_LIST_HEAD(&sublist);
> +
> +	/* Handle fragment at start of payload, and/or waiting reassembly. */
> +
> +	blkoff = ntohs(ipth->block_offset);
> +	/* check before locking i.e., maybe */
> +	if (blkoff || xtfs->ra_runtlen || xtfs->ra_newskb) {
> +		spin_lock(&xtfs->drop_lock);
> +
> +		/* check again after lock */
> +		if (blkoff || xtfs->ra_runtlen || xtfs->ra_newskb) {
> +			data = iptfs_reassem_cont(xtfs, seq, &skbseq, skb, data,
> +						  blkoff, &sublist);
> +		}
> +
> +		spin_unlock(&xtfs->drop_lock);
> +	}
> +
> +	/* New packets */
> +
> +	tail = skb->len;
> +	BUG_ON(xtfs->ra_newskb && data < tail);
> +
> +	while (data < tail) {
> +		u32 protocol = 0;
> +
> +		/* Gather information on the next data block.
> +		 * `data` points to the start of the data block.
> +		 */
> +		remaining = tail - data;
> +
> +		/* try and copy enough bytes to read length from ipv4/ipv6 */
> +		iphlen = min_t(u32, remaining, 6);
> +		if (skb_copy_bits_seq(&skbseq, data, hbytes, iphlen)) {
> +			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
> +			goto done;
> +		}
> +
> +		iph = (struct iphdr *)hbytes;
> +		if (iph->version == 0x4) {
> +			/* must have at least tot_len field present */
> +			if (remaining < 4) {
> +				/* save the bytes we have, advance data and exit */
> +				iptfs_input_save_runt(xtfs, seq, hbytes,
> +						      remaining);
> +				data += remaining;
> +				break;
> +			}
> +
> +			iplen = htons(iph->tot_len);
> +			iphlen = iph->ihl << 2;
> +			protocol = htons(ETH_P_IP);
> +			XFRM_MODE_SKB_CB(skbseq.root_skb)->tos = iph->tos;
> +		} else if (iph->version == 0x6) {
> +			/* must have at least payload_len field present */
> +			if (remaining < 6) {
> +				/* save the bytes we have, advance data and exit */
> +				iptfs_input_save_runt(xtfs, seq, hbytes,
> +						      remaining);
> +				data += remaining;
> +				break;
> +			}
> +
> +			iplen = htons(((struct ipv6hdr *)hbytes)->payload_len);
> +			iplen += sizeof(struct ipv6hdr);
> +			iphlen = sizeof(struct ipv6hdr);
> +			protocol = htons(ETH_P_IPV6);
> +			XFRM_MODE_SKB_CB(skbseq.root_skb)->tos =
> +				ipv6_get_dsfield((struct ipv6hdr *)iph);
> +		} else if (iph->version == 0x0) {
> +			/* pad */
> +			data = tail;
> +			break;
> +		} else {
> +			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
> +			goto done;
> +		}
> +
> +		if (unlikely(skbseq.stepped_offset)) {
> +			/* We need to reset our seq read, it can't backup at
> +			 * this point.
> +			 */
> +			struct sk_buff *save = skbseq.root_skb;
> +
> +			skb_abort_seq_read(&skbseq);
> +			skb_prepare_seq_read(save, data, tail, &skbseq);
> +		}
> +
> +		if (first_skb) {
> +			skb = NULL;
> +		} else {
> +			first_skb = skb;
> +			first_iplen = iplen;
> +			fragwalk = NULL;
> +
> +			/* We are going to skip over `data` bytes to reach the
> +			 * start of the IP header of `iphlen` len for `iplen`
> +			 * inner packet.
> +			 */
> +
> +			if (skb_has_frag_list(skb)) {
> +				defer = skb;
> +				skb = NULL;
> +			} else if (data + iphlen <= skb_headlen(skb) &&
> +				   /* make sure our header is 32-bit aligned? */
> +				   /* ((uintptr_t)(skb->data + data) & 0x3) == 0 && */
> +				   skb_tailroom(skb) + tail - data >= iplen) {
> +				/* Reuse the received skb.
> +				 *
> +				 * We have enough headlen to pull past any
> +				 * initial fragment data, leaving at least the
> +				 * IP header in the linear buffer space.
> +				 *
> +				 * For linear buffer space we only require that
> +				 * linear buffer space is large enough to
> +				 * eventually hold the entire reassembled
> +				 * packet (by including tailroom in the check).
> +				 *
> +				 * For non-linear tailroom is 0 and so we only
> +				 * re-use if the entire packet is present
> +				 * already.
> +				 *
> +				 * NOTE: there are many more options for
> +				 * sharing, KISS for now. Also, this can produce
> +				 * skb's with the IP header unaligned to 32
> +				 * bits. If that ends up being a problem then a
> +				 * check should be added to the conditional
> +				 * above that the header lies on a 32-bit
> +				 * boundary as well.
> +				 */
> +				skb_pull(skb, data);
> +
> +				/* our range just changed */
> +				data = 0;
> +				tail = skb->len;
> +				remaining = skb->len;
> +
> +				skb->protocol = protocol;
> +				skb_mac_header_rebuild(skb);
> +				if (skb->mac_len)
> +					eth_hdr(skb)->h_proto = skb->protocol;
> +
> +				/* all pointers could be changed now reset walk */
> +				skb_abort_seq_read(&skbseq);
> +				skb_prepare_seq_read(skb, data, tail, &skbseq);
> +			} else if (skb->head_frag &&
> +				   /* We have the IP header right now */
> +				   remaining >= iphlen) {
> +				fragwalk = &_fragwalk;
> +				skb_prepare_frag_walk(skb, data, fragwalk);
> +				defer = skb;
> +				skb = NULL;
> +			} else {
> +				/* We couldn't reuse the input skb so allocate a
> +				 * new one.
> +				 */
> +				defer = skb;
> +				skb = NULL;
> +			}
> +
> +			/* Don't trim `first_skb` until the end as we are
> +			 * walking that data now.
> +			 */
> +		}
> +
> +		capturelen = min(iplen, remaining);
> +		if (!skb) {
> +			if (!fragwalk ||
> +			    /* Large enough to be worth sharing */
> +			    iplen < IPTFS_PKT_SHARE_MIN ||
> +			    /* Have IP header + some data to share. */
> +			    capturelen <= iphlen ||
> +			    /* Try creating skb and adding frags */
> +			    !(skb = iptfs_pskb_add_frags(first_skb, fragwalk,
> +							 data, capturelen,
> +							 &skbseq, iphlen))) {
> +				skb = iptfs_pskb_extract_seq(iplen, &skbseq,
> +							     data, capturelen);
> +			}
> +			if (!skb) {
> +				/* skip to next packet or done */
> +				data += capturelen;
> +				continue;
> +			}
> +			BUG_ON(skb->len != capturelen);
> +
> +			skb->protocol = protocol;
> +			if (old_mac) {
> +				/* rebuild the mac header */
> +				skb_set_mac_header(skb, -first_skb->mac_len);
> +				memcpy(skb_mac_header(skb), old_mac,
> +				       first_skb->mac_len);
> +				eth_hdr(skb)->h_proto = skb->protocol;
> +			}
> +		}
> +
> +		data += capturelen;
> +
> +		if (skb->len < iplen) {
> +			BUG_ON(data != tail);
> +			BUG_ON(xtfs->ra_newskb);
> +
> +			/* Start reassembly */
> +			spin_lock(&xtfs->drop_lock);
> +
> +			xtfs->ra_newskb = skb;
> +			xtfs->ra_wantseq = seq + 1;
> +			if (!hrtimer_is_queued(&xtfs->drop_timer)) {
> +				/* softirq blocked lest the timer fire and interrupt us */
> +				BUG_ON(!in_interrupt());
> +				hrtimer_start(&xtfs->drop_timer,
> +					      xtfs->drop_time_ns,
> +					      IPTFS_HRTIMER_MODE);
> +			}
> +
> +			spin_unlock(&xtfs->drop_lock);
> +
> +			break;
> +		}
> +
> +		iptfs_complete_inner_skb(x, skb);
> +		list_add_tail(&skb->list, &sublist);
> +	}
> +
> +	if (data != tail)
> +		/* this should not happen from the above code */
> +		XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINIPTFSERROR);
> +
> +	if (first_skb && first_iplen && !defer && first_skb != xtfs->ra_newskb) {
> +		/* first_skb is queued b/c !defer and not partial */
> +		if (pskb_trim(first_skb, first_iplen)) {
> +			/* error trimming */
> +			list_del(&first_skb->list);
> +			defer = first_skb;
> +		}
> +		first_skb->ip_summed = CHECKSUM_NONE;
> +	}
> +
> +	/* Send the packets! */
> +	list_for_each_entry_safe(skb, next, &sublist, list) {
> +		BUG_ON(skb == defer);
> +		skb_list_del_init(skb);
> +		if (xfrm_input(skb, 0, 0, -3))
> +			kfree_skb(skb);
> +	}
> +
> +done:
> +	skb = skbseq.root_skb;
> +	skb_abort_seq_read(&skbseq);
> +
> +	if (defer) {
> +		consume_skb(defer);
> +	} else if (!first_skb) {
> +		/* skb is the original passed in skb, but we didn't get far
> +		 * enough to process it as the first_skb, if we had it would
> +		 * either be save in ra_newskb, trimmed and sent on as an skb or
> +		 * placed in defer to be freed.
> +		 */
> +		BUG_ON(!skb);
> +		kfree_skb(skb);
> +	}
> +
> +	return 0;
> +}
> +
> +/* ------------------------------- */
> +/* Input (Egress) Re-ordering Code */
> +/* ------------------------------- */
> +
> +static void __vec_shift(struct xfrm_iptfs_data *xtfs, u32 shift)
> +{
> +	u32 savedlen = xtfs->w_savedlen;
> +
> +	if (shift > savedlen)
> +		shift = savedlen;
> +	if (shift != savedlen)
> +		memcpy(xtfs->w_saved, xtfs->w_saved + shift,
> +		       (savedlen - shift) * sizeof(*xtfs->w_saved));
> +	memset(xtfs->w_saved + savedlen - shift, 0,
> +	       shift * sizeof(*xtfs->w_saved));
> +	xtfs->w_savedlen -= shift;
> +}
> +
> +static int __reorder_past(struct xfrm_iptfs_data *xtfs, struct sk_buff *inskb,
> +			  struct list_head *freelist, u32 *fcount)
> +{
> +	list_add_tail(&inskb->list, freelist);
> +	(*fcount)++;
> +	return 0;
> +}
> +
> +static u32 __reorder_drop(struct xfrm_iptfs_data *xtfs, struct list_head *list)
> +
> +{
> +	struct skb_wseq *s, *se;
> +	const u32 savedlen = xtfs->w_savedlen;
> +	time64_t now = ktime_get_raw_fast_ns();
> +	u32 count = 0;
> +	u32 scount = 0;
> +
> +	BUG_ON(!savedlen);
> +	if (xtfs->w_saved[0].drop_time > now)
> +		goto set_timer;
> +
> +	++xtfs->w_wantseq;
> +
> +	/* Keep flushing packets until we reach a drop time greater than now. */
> +	s = xtfs->w_saved;
> +	se = s + savedlen;
> +	do {
> +		/* Walking past empty slots until we reach a packet */
> +		for (; s < se && !s->skb; s++)
> +			if (s->drop_time > now)
> +				goto outerdone;
> +		/* Sending packets until we hit another empty slot. */
> +		for (; s < se && s->skb; scount++, s++)
> +			list_add_tail(&s->skb->list, list);
> +	} while (s < se);
> +outerdone:
> +
> +	count = s - xtfs->w_saved;
> +	if (count) {
> +		xtfs->w_wantseq += count;
> +
> +		/* Shift handled slots plus final empty slot into slot 0. */
> +		__vec_shift(xtfs, count);
> +	}
> +
> +	if (xtfs->w_savedlen) {
> +set_timer:
> +		/* Drifting is OK */
> +		hrtimer_start(&xtfs->drop_timer,
> +			      xtfs->w_saved[0].drop_time - now,
> +			      IPTFS_HRTIMER_MODE);
> +	}
> +	return scount;
> +}
> +
> +static u32 __reorder_this(struct xfrm_iptfs_data *xtfs, struct sk_buff *inskb,
> +			  struct list_head *list)
> +{
> +	struct skb_wseq *s, *se;
> +	const u32 savedlen = xtfs->w_savedlen;
> +	u32 count = 0;
> +
> +	/* Got what we wanted. */
> +	list_add_tail(&inskb->list, list);
> +	++xtfs->w_wantseq;
> +	if (!savedlen)
> +		return 1;
> +
> +	/* Flush remaining consecutive packets. */
> +
> +	/* Keep sending until we hit another missed pkt. */
> +	for (s = xtfs->w_saved, se = s + savedlen; s < se && s->skb; s++)
> +		list_add_tail(&s->skb->list, list);
> +	count = s - xtfs->w_saved;
> +	if (count)
> +		xtfs->w_wantseq += count;
> +
> +	/* Shift handled slots plus final empty slot into slot 0. */
> +	__vec_shift(xtfs, count + 1);
> +
> +	return count + 1;
> +}
> +
> +/* Set the slot's drop time and all the empty slots below it until reaching a
> + * filled slot which will already be set.
> + */
> +static void iptfs_set_window_drop_times(struct xfrm_iptfs_data *xtfs, int index)
> +{
> +	const u32 savedlen = xtfs->w_savedlen;
> +	struct skb_wseq *s = xtfs->w_saved;
> +	time64_t drop_time;
> +
> +	assert_spin_locked(&xtfs->drop_lock);
> +
> +	if (savedlen > index + 1) {
> +		/* we are below another, our drop time and the timer are already set */
> +		BUG_ON(xtfs->w_saved[index + 1].drop_time !=
> +		       xtfs->w_saved[index].drop_time);
> +		return;
> +	}
> +	/* we are the most future so get a new drop time. */
> +	drop_time = ktime_get_raw_fast_ns();
> +	drop_time += xtfs->drop_time_ns;
> +
> +	/* Walk back through the array setting drop times as we go */
> +	s[index].drop_time = drop_time;
> +	while (index-- > 0 && !s[index].skb)
> +		s[index].drop_time = drop_time;
> +
> +	/* If we walked all the way back, schedule the drop timer if needed */
> +	if (index == -1 && !hrtimer_is_queued(&xtfs->drop_timer))
> +		hrtimer_start(&xtfs->drop_timer, xtfs->drop_time_ns,
> +			      IPTFS_HRTIMER_MODE);
> +}
> +
> +static u32 __reorder_future_fits(struct xfrm_iptfs_data *xtfs,
> +				 struct sk_buff *inskb,
> +				 struct list_head *freelist, u32 *fcount)
> +{
> +	const u32 nslots = xtfs->cfg.reorder_win_size + 1;
> +	const u64 inseq = __esp_seq(inskb);
> +	const u64 wantseq = xtfs->w_wantseq;
> +	const u64 distance = inseq - wantseq;
> +	const u32 savedlen = xtfs->w_savedlen;
> +	const u32 index = distance - 1;
> +
> +	BUG_ON(distance >= nslots);
> +
> +	/* Handle future sequence number received which fits in the window.
> +	 *
> +	 * We know we don't have the seq we want so we won't be able to flush
> +	 * anything.
> +	 */
> +
> +	/* slot count is 4, saved size is 3 savedlen is 2
> +	 *
> +	 * "window boundary" is based on the fixed window size
> +	 * distance is also slot number
> +	 * index is an array index (i.e., - 1 of slot)
> +	 * : : - implicit NULL after array len
> +	 *
> +	 *          +--------- used length (savedlen == 2)
> +	 *          |   +----- array size (nslots - 1 == 3)
> +	 *          |   |   + window boundary (nslots == 4)
> +	 *          V   V | V
> +	 *                |
> +	 *  0   1   2   3 |   slot number
> +	 * ---  0   1   2 |   array index
> +	 *     [-] [b] : :|   array
> +	 *
> +	 * "2" "3" "4" *5*|   seq numbers
> +	 *
> +	 * We receive seq number 5
> +	 * distance == 3 [inseq(5) - w_wantseq(2)]
> +	 * index == 2 [distance(6) - 1]
> +	 */
> +
> +	if (xtfs->w_saved[index].skb) {
> +		/* a dup of a future */
> +		list_add_tail(&inskb->list, freelist);
> +		(*fcount)++;
> +		return 0;
> +	}
> +
> +	xtfs->w_saved[index].skb = inskb;
> +	xtfs->w_savedlen = max(savedlen, index + 1);
> +	iptfs_set_window_drop_times(xtfs, index);
> +
> +	return 0;
> +}
> +
> +static u32 __reorder_future_shifts(struct xfrm_iptfs_data *xtfs,
> +				   struct sk_buff *inskb,
> +				   struct list_head *list,
> +				   struct list_head *freelist, u32 *fcount)
> +{
> +	const u32 nslots = xtfs->cfg.reorder_win_size + 1;
> +	const u64 inseq = __esp_seq(inskb);
> +	u32 savedlen = xtfs->w_savedlen;
> +	u64 wantseq = xtfs->w_wantseq;
> +	struct sk_buff *slot0 = NULL;
> +	u64 last_drop_seq = xtfs->w_wantseq;
> +	u64 distance, extra_drops, missed, s0seq;
> +	u32 count = 0;
> +	struct skb_wseq *wnext;
> +	u32 beyond, shifting, slot;
> +
> +	BUG_ON(inseq <= wantseq);
> +	distance = inseq - wantseq;
> +	BUG_ON(distance <= nslots - 1);
> +	beyond = distance - (nslots - 1);
> +	missed = 0;
> +
> +	/* Handle future sequence number received.
> +	 *
> +	 * IMPORTANT: we are at least advancing w_wantseq (i.e., wantseq) by 1
> +	 * b/c we are beyond the window boundary.
> +	 *
> +	 * We know we don't have the wantseq so that counts as a drop.
> +	 */
> +
> +	/* ex: slot count is 4, array size is 3 savedlen is 2, slot 0 is the
> +	 * missing sequence number.
> +	 *
> +	 * the final slot at savedlen (index savedlen - 1) is always occupied.
> +	 *
> +	 * beyond is "beyond array size" not savedlen.
> +	 *
> +	 *          +--------- array length (savedlen == 2)
> +	 *          |   +----- array size (nslots - 1 == 3)
> +	 *          |   |   +- window boundary (nslots == 4)
> +	 *          V   V | V
> +	 *                |
> +	 *  0   1   2   3 |   slot number
> +	 * ---  0   1   2 |   array index
> +	 *     [b] [c] : :|   array
> +	 *                |
> +	 * "2" "3" "4" "5"|*6*  seq numbers
> +	 *
> +	 * We receive seq number 6
> +	 * distance == 4 [inseq(6) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 3 [distance(4) - 1]
> +	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
> +	 * shifting == 1 [min(savedlen(2), beyond(1)]
> +	 * slot0_skb == [b], and should match w_wantseq
> +	 *
> +	 *                +--- window boundary (nslots == 4)
> +	 *  0   1   2   3 | 4   slot number
> +	 * ---  0   1   2 | 3   array index
> +	 *     [b] : : : :|     array
> +	 * "2" "3" "4" "5" *6*  seq numbers
> +	 *
> +	 * We receive seq number 6
> +	 * distance == 4 [inseq(6) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 3 [distance(4) - 1]
> +	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
> +	 * shifting == 1 [min(savedlen(1), beyond(1)]
> +	 * slot0_skb == [b] and should match w_wantseq
> +	 *
> +	 *                +-- window boundary (nslots == 4)
> +	 *  0   1   2   3 | 4   5   6   slot number
> +	 * ---  0   1   2 | 3   4   5   array index
> +	 *     [-] [c] : :|             array
> +	 * "2" "3" "4" "5" "6" "7" *8*  seq numbers
> +	 *
> +	 * savedlen = 2, beyond = 3
> +	 * iter 1: slot0 == NULL, missed++, lastdrop = 2 (2+1-1), slot0 = [-]
> +	 * iter 2: slot0 == NULL, missed++, lastdrop = 3 (2+2-1), slot0 = [c]
> +	 * 2 < 3, extra = 1 (3-2), missed += extra, lastdrop = 4 (2+2+1-1)
> +	 *
> +	 * We receive seq number 8
> +	 * distance == 6 [inseq(8) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 5 [distance(6) - 1]
> +	 * beyond == 3 [newslot(6) - lastslot((nslots(4) - 1))]
> +	 * shifting == 2 [min(savedlen(2), beyond(3)]
> +	 *
> +	 * slot0_skb == NULL changed from [b] when "savedlen < beyond" is true.
> +	 */
> +
> +	/* Now send any packets that are being shifted out of saved, and account
> +	 * for missing packets that are exiting the window as we shift it.
> +	 */
> +
> +	/* If savedlen > beyond we are shifting some, else all. */
> +	shifting = min(savedlen, beyond);
> +
> +	/* slot0 is the buf that just shifted out and into slot0 */
> +	slot0 = NULL;
> +	s0seq = wantseq;
> +	last_drop_seq = s0seq;
> +	wnext = xtfs->w_saved;
> +	for (slot = 1; slot <= shifting; slot++, wnext++) {
> +		/* handle what was in slot0 before we occupy it */
> +		if (!slot0) {
> +			last_drop_seq = s0seq;
> +			missed++;
> +		} else {
> +			list_add_tail(&slot0->list, list);
> +			count++;
> +		}
> +		s0seq++;
> +		slot0 = wnext->skb;
> +		wnext->skb = NULL;
> +	}
> +
> +	/* slot0 is now either NULL (in which case it's what we now are waiting
> +	 * for, or a buf in which case we need to handle it like we received it;
> +	 * however, we may be advancing past that buffer as well..
> +	 */
> +
> +	/* Handle case where we need to shift more than we had saved, slot0 will
> +	 * be NULL iff savedlen is 0, otherwise slot0 will always be
> +	 * non-NULL b/c we shifted the final element, which is always set if
> +	 * there is any saved, into slot0.
> +	 */
> +	if (savedlen < beyond) {
> +		extra_drops = beyond - savedlen;
> +		if (savedlen == 0) {
> +			BUG_ON(slot0);
> +			s0seq += extra_drops;
> +			last_drop_seq = s0seq - 1;
> +		} else {
> +			extra_drops--; /* we aren't dropping what's in slot0 */
> +			BUG_ON(!slot0);
> +			list_add_tail(&slot0->list, list);
> +			/* if extra_drops then we are going past this slot0
> +			 * so we can safely advance last_drop_seq
> +			 */
> +			if (extra_drops)
> +				last_drop_seq = s0seq + extra_drops;
> +			s0seq += extra_drops + 1;
> +			count++;
> +		}
> +		missed += extra_drops;
> +		slot0 = NULL;
> +		/* slot0 has had an empty slot pushed into it */
> +	}
> +	(void)last_drop_seq;	/* we want this for CC code */
> +
> +	/* Remove the entries */
> +	__vec_shift(xtfs, beyond);
> +
> +	/* Advance want seq */
> +	xtfs->w_wantseq += beyond;
> +
> +	/* Process drops here when implementing congestion control */
> +
> +	/* We've shifted. plug the packet in at the end. */
> +	xtfs->w_savedlen = nslots - 1;
> +	xtfs->w_saved[xtfs->w_savedlen - 1].skb = inskb;
> +	iptfs_set_window_drop_times(xtfs, xtfs->w_savedlen - 1);
> +
> +	/* if we don't have a slot0 then we must wait for it */
> +	if (!slot0)
> +		return count;
> +
> +	/* If slot0, seq must match new want seq */
> +	BUG_ON(xtfs->w_wantseq != __esp_seq(slot0));
> +
> +	/* slot0 is valid, treat like we received expected. */
> +	count += __reorder_this(xtfs, slot0, list);
> +	return count;
> +}
> +
> +/* Receive a new packet into the reorder window. Return a list of ordered
> + * packets from the window.
> + */
> +static u32 iptfs_input_reorder(struct xfrm_iptfs_data *xtfs,
> +			       struct sk_buff *inskb, struct list_head *list,
> +			       struct list_head *freelist, u32 *fcount)
> +{
> +	const u32 nslots = xtfs->cfg.reorder_win_size + 1;
> +	u64 inseq = __esp_seq(inskb);
> +	u64 wantseq;
> +
> +	assert_spin_locked(&xtfs->drop_lock);
> +
> +	if (unlikely(!xtfs->w_seq_set)) {
> +		xtfs->w_seq_set = true;
> +		xtfs->w_wantseq = inseq;
> +	}
> +	wantseq = xtfs->w_wantseq;
> +
> +	if (likely(inseq == wantseq))
> +		return __reorder_this(xtfs, inskb, list);
> +	else if (inseq < wantseq)
> +		return __reorder_past(xtfs, inskb, freelist, fcount);
> +	else if ((inseq - wantseq) < nslots)
> +		return __reorder_future_fits(xtfs, inskb, freelist, fcount);
> +	else
> +		return __reorder_future_shifts(xtfs, inskb, list, freelist,
> +					       fcount);
> +}
> +
> +/**
> + * iptfs_drop_timer() - Handle drop timer expiry.
> + * @me: the timer
> + *
> + * This is similar to our input function.
> + *
> + * The drop timer is set when we start an in progress reassembly, and also when
> + * we save a future packet in the window saved array.
> + *
> + * NOTE packets in the save window are always newer WRT drop times as
> + * they get further in the future. i.e. for:
> + *
> + *    if slots (S0, S1, ... Sn) and `Dn` is the drop time for slot `Sn`,
> + *    then D(n-1) <= D(n).
> + *
> + * So, regardless of why the timer is firing we can always discard any inprogress
> + * fragment; either it's the reassembly timer, or slot 0 is going to be
> + * dropped as S0 must have the most recent drop time, and slot 0 holds the
> + * continuation fragment of the in progress packet.
> + */
> +static enum hrtimer_restart iptfs_drop_timer(struct hrtimer *me)
> +{
> +	struct sk_buff *skb, *next;
> +	struct list_head freelist, list;
> +	struct xfrm_iptfs_data *xtfs;
> +	struct xfrm_state *x;
> +	u32 count;
> +
> +	xtfs = container_of(me, typeof(*xtfs), drop_timer);
> +	x = xtfs->x;
> +
> +	spin_lock(&xtfs->drop_lock);
> +
> +	INIT_LIST_HEAD(&list);
> +	INIT_LIST_HEAD(&freelist);
> +
> +	/* Drop any in progress packet */
> +
> +	if (xtfs->ra_newskb) {
> +		kfree_skb(xtfs->ra_newskb);
> +		xtfs->ra_newskb = NULL;
> +	}
> +
> +	/* Now drop as many packets as we should from the reordering window
> +	 * saved array
> +	 */
> +	count = xtfs->w_savedlen ? __reorder_drop(xtfs, &list) : 0;
> +
> +	spin_unlock(&xtfs->drop_lock);
> +
> +	if (count) {
> +		list_for_each_entry_safe(skb, next, &list, list) {
> +			skb_list_del_init(skb);
> +			(void)iptfs_input_ordered(x, skb);
> +		}
> +	}
> +	return HRTIMER_NORESTART;
> +}
> +
> +/**
> + * iptfs_input() - handle receipt of iptfs payload
> + * @x: xfrm state
> + * @skb: the packet
> + *
> + * We have an IPTFS payload order it if needed, then process newly in order
> + * packets.
> + */
> +static int iptfs_input(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	struct list_head freelist, list;
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +	struct sk_buff *next;
> +	u32 count, fcount;
> +
> +	/* Fast path for no reorder window. */
> +	if (xtfs->cfg.reorder_win_size == 0) {
> +		iptfs_input_ordered(x, skb);
> +		goto done;
> +	}
> +
> +	/* Fetch list of in-order packets from the reordering window as well as
> +	 * a list of buffers we need to now free.
> +	 */
> +	INIT_LIST_HEAD(&list);
> +	INIT_LIST_HEAD(&freelist);
> +	fcount = 0;
> +
> +	spin_lock(&xtfs->drop_lock);
> +	count = iptfs_input_reorder(xtfs, skb, &list, &freelist, &fcount);
> +	spin_unlock(&xtfs->drop_lock);
> +
> +	if (count) {
> +		list_for_each_entry_safe(skb, next, &list, list) {
> +			skb_list_del_init(skb);
> +			(void)iptfs_input_ordered(x, skb);
> +		}
> +	}
> +
> +	if (fcount) {
> +		list_for_each_entry_safe(skb, next, &freelist, list) {
> +			skb_list_del_init(skb);
> +			kfree_skb(skb);
> +		}
> +	}
> +done:
> +	/* We always have dealt with the input SKB, either we are re-using it,
> +	 * or we have freed it. Return EINPROGRESS so that xfrm_input stops
> +	 * processing it.
> +	 */
> +	return -EINPROGRESS;
> +}
> +
> +/* ================================= */
> +/* IPTFS Sending (ingress) Functions */
> +/* ================================= */
> +
> +/* ------------------------- */
> +/* Enqueue to send functions */
> +/* ------------------------- */
> +
> +/**
> + * iptfs_enqueue() - enqueue packet if ok to send.
> + * @xtfs: xtfs state
> + * @skb: the packet
> + *
> + * Return: true if packet enqueued.
> + */
> +static bool iptfs_enqueue(struct xfrm_iptfs_data *xtfs, struct sk_buff *skb)
> +{
> +	u64 newsz = xtfs->queue_size + skb->len;
> +	struct iphdr *iph;
> +
> +	assert_spin_locked(&xtfs->x->lock);
> +
> +	if (newsz > xtfs->cfg.max_queue_size)
> +		return false;
> +
> +	/* Set ECN CE if we are above our ECN queue threshold */
> +	if (newsz > xtfs->ecn_queue_size) {
> +		iph = ip_hdr(skb);
> +		if (iph->version == 4)
> +			IP_ECN_set_ce(iph);
> +		else if (iph->version == 6)
> +			IP6_ECN_set_ce(skb, ipv6_hdr(skb));
> +	}
> +
> +	__skb_queue_tail(&xtfs->queue, skb);
> +	xtfs->queue_size += skb->len;
> +	return true;
> +}
> +
> +static int iptfs_get_cur_pmtu(struct xfrm_state *x, struct xfrm_iptfs_data *xtfs,
> +			      struct sk_buff *skb)
> +{
> +	struct xfrm_dst *xdst = (struct xfrm_dst *)skb_dst(skb);
> +	u32 payload_mtu = xtfs->payload_mtu;
> +	u32 pmtu = __iptfs_get_inner_mtu(x, xdst->child_mtu_cached);
> +
> +	if (payload_mtu && payload_mtu < pmtu)
> +		pmtu = payload_mtu;
> +
> +	return pmtu;
> +}
> +
> +static int iptfs_is_too_big(struct sock *sk, struct sk_buff *skb, u32 pmtu)
> +{
> +	if (skb->len <= pmtu)
> +		return 0;
> +
> +	/* We only send ICMP too big if the user has configured us as
> +	 * dont-fragment.
> +	 */
> +	XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMOUTERROR);
> +
> +	if (sk) {
> +		xfrm_local_error(skb, pmtu);
> +	} else if (ip_hdr(skb)->version == 4) {
> +		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
> +			  htonl(pmtu));
> +	} else {
> +		WARN_ON_ONCE(ip_hdr(skb)->version != 6);
> +		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, pmtu);
> +	}
> +	return 1;
> +}
> +
> +/* IPv4/IPv6 packet ingress to IPTFS tunnel, arrange to send in IPTFS payload
> + * (i.e., aggregating or fragmenting as appropriate).
> + * This is set in dst->output for an SA.
> + */
> +static int iptfs_output_collect(struct net *net, struct sock *sk,
> +				struct sk_buff *skb)
> +{
> +	struct dst_entry *dst = skb_dst(skb);
> +	struct xfrm_state *x = dst->xfrm;
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +	struct sk_buff *segs, *nskb;
> +	u32 pmtu = 0;
> +	bool ok = true;
> +	bool was_gso;
> +
> +	/* We have hooked into dst_entry->output which means we have skipped the
> +	 * protocol specific netfilter (see xfrm4_output, xfrm6_output).
> +	 * when our timer runs we will end up calling xfrm_output directly on
> +	 * the encapsulated traffic.
> +	 *
> +	 * For both cases this is the NF_INET_POST_ROUTING hook which allows
> +	 * changing the skb->dst entry which then may not be xfrm based anymore
> +	 * in which case a REROUTED flag is set. and dst_output is called.
> +	 *
> +	 * For IPv6 we are also skipping fragmentation handling for local
> +	 * sockets, which may or may not be good depending on our tunnel DF
> +	 * setting. Normally with fragmentation supported we want to skip this
> +	 * fragmentation.
> +	 */
> +
> +	BUG_ON(!xtfs);
> +
> +	if (xtfs->cfg.dont_frag)
> +		pmtu = iptfs_get_cur_pmtu(x, xtfs, skb);
> +
> +	/* Break apart GSO skbs. If the queue is nearing full then we want the
> +	 * accounting and queuing to be based on the individual packets not on the
> +	 * aggregate GSO buffer.
> +	 */
> +	was_gso = skb_is_gso(skb);
> +	if (!was_gso) {
> +		segs = skb;
> +	} else {
> +		segs = skb_gso_segment(skb, 0);
> +		if (IS_ERR_OR_NULL(segs)) {
> +			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
> +			kfree_skb(skb);
> +			return PTR_ERR(segs);
> +		}
> +		consume_skb(skb);
> +		skb = NULL;
> +	}
> +
> +	/* We can be running on multiple cores and from the network softirq or
> +	 * from user context depending on where the packet is coming from.
> +	 */
> +	spin_lock_bh(&x->lock);
> +
> +	skb_list_walk_safe(segs, skb, nskb) {
> +		skb_mark_not_on_list(skb);
> +
> +		/* Once we drop due to no queue space we continue to drop the
> +		 * rest of the packets from that GRO.
> +		 */
> +		if (!ok) {
> +nospace:
> +			trace_iptfs_no_queue_space(skb, xtfs, pmtu, was_gso);
> +			XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMOUTNOQSPACE);
> +			kfree_skb_reason(skb, SKB_DROP_REASON_FULL_RING);
> +			continue;
> +		}
> +
> +		/* If the user indicated no iptfs fragmenting check before
> +		 * enqueue.
> +		 */
> +		if (xtfs->cfg.dont_frag && iptfs_is_too_big(sk, skb, pmtu)) {
> +			trace_iptfs_too_big(skb, xtfs, pmtu, was_gso);
> +			kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
> +			continue;
> +		}
> +
> +		/* Enqueue to send in tunnel */
> +		ok = iptfs_enqueue(xtfs, skb);
> +		if (!ok)
> +			goto nospace;
> +
> +		trace_iptfs_enqueue(skb, xtfs, pmtu, was_gso);
> +	}
> +
> +	/* Start a delay timer if we don't have one yet */
> +	if (!hrtimer_is_queued(&xtfs->iptfs_timer)) {
> +		hrtimer_start(&xtfs->iptfs_timer, xtfs->init_delay_ns,
> +			      IPTFS_HRTIMER_MODE);
> +		xtfs->iptfs_settime = ktime_get_raw_fast_ns();
> +		trace_iptfs_timer_start(xtfs, xtfs->init_delay_ns);
> +	}
> +
> +	spin_unlock_bh(&x->lock);
> +	return 0;
> +}
> +
> +/* -------------------------- */
> +/* Dequeue and send functions */
> +/* -------------------------- */
> +
> +static void iptfs_output_prepare_skb(struct sk_buff *skb, u32 blkoff)
> +{
> +	struct ip_iptfs_hdr *h;
> +	size_t hsz = sizeof(*h);
> +
> +	/* now reset values to be pointing at the rest of the packets */
> +	h = skb_push(skb, hsz);
> +	memset(h, 0, hsz);
> +	if (blkoff)
> +		h->block_offset = htons(blkoff);
> +
> +	/* network_header current points at the inner IP packet
> +	 * move it to the iptfs header
> +	 */
> +	skb->transport_header = skb->network_header;
> +	skb->network_header -= hsz;
> +
> +	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
> +
> +	/* xfrm[46]_prepare_output sets skb->protocol here, but the resulting
> +	 * called ip[6]_output functions also set this value as appropriate so
> +	 * seems unnecessary
> +	 *
> +	 * skb->protocol = htons(ETH_P_IP) or htons(ETH_P_IPV6);
> +	 */
> +}
> +
> +/**
> + * iptfs_copy_create_frag() - create an inner fragment skb.
> + * @st: The source packet data.
> + * @offset: offset in @st of the new fragment data.
> + * @copy_len: the amount of data to copy from @st.
> + *
> + * Create a new skb holding a single IPTFS inner packet fragment. @copy_len must
> + * not be greater than the max fragment size.
> + *
> + * Return: the new fragment skb or an ERR_PTR().
> + */
> +static struct sk_buff *iptfs_copy_create_frag(struct skb_seq_state *st,
> +					      u32 offset, u32 copy_len)
> +{
> +	struct sk_buff *src = st->root_skb;
> +	struct sk_buff *skb;
> +	int err;
> +
> +	skb = iptfs_alloc_skb(src, copy_len, true);
> +	if (!skb)
> +		return ERR_PTR(-ENOMEM);
> +
> +	/* Now copy `copy_len` data from src */
> +	err = skb_copy_bits_seq(st, offset, skb_put(skb, copy_len), copy_len);
> +	if (err) {
> +		XFRM_INC_STATS(dev_net(src->dev), LINUX_MIB_XFRMOUTERROR);
> +		kfree_skb(skb);
> +		return ERR_PTR(err);
> +	}
> +
> +	return skb;
> +}
> +
> +/**
> + * iptfs_copy_create_frags() - create and send N-1 fragments of a larger skb.
> + * @skbp: the source packet skb (IN), skb holding the last fragment in
> + *        the fragment stream (OUT).
> + * @xtfs: IPTFS SA state.
> + * @mtu: the max IPTFS fragment size.
> + *
> + * This function is responsible for fragmenting a larger inner packet into a
> + * sequence of IPTFS payload packets. The last fragment is returned rather than
> + * being sent so that the caller can append more inner packets (aggregation) if
> + * there is room.
> + */
> +static int iptfs_copy_create_frags(struct sk_buff **skbp,
> +				   struct xfrm_iptfs_data *xtfs, u32 mtu)
> +{
> +	struct skb_seq_state skbseq;
> +	struct list_head sublist;
> +	struct sk_buff *skb = *skbp;
> +	struct sk_buff *nskb = *skbp;
> +	u32 copy_len, offset;
> +	u32 to_copy = skb->len - mtu;
> +	u32 blkoff = 0;
> +	int err = 0;
> +
> +	INIT_LIST_HEAD(&sublist);
> +
> +	BUG_ON(skb->len <= mtu);
> +	skb_prepare_seq_read(skb, 0, skb->len, &skbseq);
> +
> +	/* A trimmed `skb` will be sent as the first fragment, later. */
> +	offset = mtu;
> +	to_copy = skb->len - offset;
> +	while (to_copy) {
> +		/* Send all but last fragment to allow agg. append */
> +		trace_iptfs_first_fragmenting(nskb, mtu, to_copy, NULL);
> +		list_add_tail(&nskb->list, &sublist);
> +
> +		/* FUTURE: if the packet has an odd/non-aligning length we could
> +		 * send less data in the penultimate fragment so that the last
> +		 * fragment then ends on an aligned boundary.
> +		 */
> +		copy_len = to_copy <= mtu ? to_copy : mtu;
> +		nskb = iptfs_copy_create_frag(&skbseq, offset, copy_len);
> +		if (IS_ERR(nskb)) {
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMOUTERROR);
> +			skb_abort_seq_read(&skbseq);
> +			err = PTR_ERR(nskb);
> +			nskb = NULL;
> +			break;
> +		}
> +		iptfs_output_prepare_skb(nskb, to_copy);
> +		offset += copy_len;
> +		to_copy -= copy_len;
> +		blkoff = to_copy;
> +	}
> +	skb_abort_seq_read(&skbseq);
> +
> +	/* return last fragment that will be unsent (or NULL) */
> +	*skbp = nskb;
> +	if (nskb)
> +		trace_iptfs_first_final_fragment(nskb, mtu, blkoff, NULL);
> +
> +	/* trim the original skb to MTU */
> +	if (!err)
> +		err = pskb_trim(skb, mtu);
> +
> +	if (err) {
> +		/* Free all frags. Don't bother sending a partial packet we will
> +		 * never complete.
> +		 */
> +		kfree_skb(nskb);
> +		list_for_each_entry_safe(skb, nskb, &sublist, list) {
> +			skb_list_del_init(skb);
> +			kfree_skb(skb);
> +		}
> +		return err;
> +	}
> +
> +	/* prepare the initial fragment with an iptfs header */
> +	iptfs_output_prepare_skb(skb, 0);
> +
> +	/* Send all but last fragment, if we fail to send a fragment then free
> +	 * the rest -- no point in sending a packet that can't be reassembled.
> +	 */
> +	list_for_each_entry_safe(skb, nskb, &sublist, list) {
> +		skb_list_del_init(skb);
> +		if (!err)
> +			err = xfrm_output(NULL, skb);
> +		else
> +			kfree_skb(skb);
> +	}
> +	if (err)
> +		kfree_skb(*skbp);
> +	return err;
> +}
> +
> +/**
> + * iptfs_first_should_copy() - determine if we should copy packet data.
> + * @first_skb: the first skb in the packet
> + * @mtu: the MTU.
> + *
> + * Determine if we should create subsequent skbs to hold the remaining data from
> + * a large inner packet by copying the packet data, or cloning the original skb
> + * and adjusting the offsets.
> + */
> +static bool iptfs_first_should_copy(struct sk_buff *first_skb, u32 mtu)
> +{
> +	u32 frag_copy_max;
> +
> +	/* If we have less than frag_copy_max for remaining packet we copy
> +	 * those tail bytes as it is more efficient.
> +	 */
> +	frag_copy_max = mtu <= IPTFS_FRAG_COPY_MAX ? mtu : IPTFS_FRAG_COPY_MAX;
> +	if ((int)first_skb->len - (int)mtu < (int)frag_copy_max)
> +		return true;
> +
> +	/* If we have non-linear skb just use copy */
> +	if (skb_is_nonlinear(first_skb))
> +		return true;
> +
> +	/* So we have a simple linear skb, easy to clone and share */
> +	return false;
> +}
> +
> +/**
> + * iptfs_first_skb() - handle the first dequeued inner packet for output
> + * @skbp: the source packet skb (IN), skb holding the last fragment in
> + *        the fragment stream (OUT).
> + * @xtfs: IPTFS SA state.
> + * @mtu: the max IPTFS fragment size.
> + *
> + * This function is responsible for fragmenting a larger inner packet into a
> + * sequence of IPTFS payload packets. If it needs to fragment into subsequent
> + * skb's, it will either do so by copying or cloning.
> + *
> + * The last fragment is returned rather than being sent so that the caller can
> + * append more inner packets (aggregation) if there is room.
> + *
> + */
> +static int iptfs_first_skb(struct sk_buff **skbp, struct xfrm_iptfs_data *xtfs,
> +			   u32 mtu)
> +{
> +	struct sk_buff *skb = *skbp;
> +	int err;
> +
> +	/* Classic ESP skips the don't fragment ICMP error if DF is clear on
> +	 * the inner packet or ignore_df is set. Otherwise it will send an ICMP
> +	 * or local error if the inner packet won't fit it's MTU.
> +	 *
> +	 * With IPTFS we do not care about the inner packet DF bit. If the
> +	 * tunnel is configured to "don't fragment" we error back if things
> +	 * don't fit in our max packet size. Otherwise we iptfs-fragment as
> +	 * normal.
> +	 */
> +
> +	/* The opportunity for HW offload has ended */
> +	if (skb->ip_summed == CHECKSUM_PARTIAL) {
> +		err = skb_checksum_help(skb);
> +		if (err)
> +			return err;
> +	}
> +
> +	/* We've split these up before queuing */
> +	BUG_ON(skb_is_gso(skb));
> +
> +	trace_iptfs_first_dequeue(skb, mtu, 0, ip_hdr(skb));
> +
> +	/* Simple case -- it fits. `mtu` accounted for all the overhead
> +	 * including the basic IPTFS header.
> +	 */
> +	if (skb->len <= mtu) {
> +		iptfs_output_prepare_skb(skb, 0);
> +		return 0;
> +	}
> +
> +	if (iptfs_first_should_copy(skb, mtu))
> +		return iptfs_copy_create_frags(skbp, xtfs, mtu);
> +
> +	/* For now we always copy */
> +	return iptfs_copy_create_frags(skbp, xtfs, mtu);
> +}
> +
> +static struct sk_buff **iptfs_rehome_fraglist(struct sk_buff **nextp,
> +					      struct sk_buff *child)
> +{
> +	u32 fllen = 0;
> +
> +	/* It might be possible to account for a frag list in addition to page
> +	 * fragment if it's a valid state to be in. The page fragments size
> +	 * should be kept as data_len so only the frag_list size is removed,
> +	 * this must be done above as well.
> +	 */
> +	BUG_ON(skb_shinfo(child)->nr_frags);
> +	*nextp = skb_shinfo(child)->frag_list;
> +	while (*nextp) {
> +		fllen += (*nextp)->len;
> +		nextp = &(*nextp)->next;
> +	}
> +	skb_frag_list_init(child);
> +	BUG_ON(fllen > child->data_len);
> +	child->len -= fllen;
> +	child->data_len -= fllen;
> +
> +	return nextp;
> +}
> +
> +static void iptfs_consume_frags(struct sk_buff *to, struct sk_buff *from)
> +{
> +	struct skb_shared_info *fromi = skb_shinfo(from);
> +	struct skb_shared_info *toi = skb_shinfo(to);
> +	unsigned int new_truesize;
> +
> +	/* If we have data in a head page, grab it */
> +	if (!skb_headlen(from)) {
> +		new_truesize = SKB_TRUESIZE(skb_end_offset(from));
> +	} else {
> +		skb_head_to_frag(from, &toi->frags[toi->nr_frags]);
> +		skb_frag_ref(to, toi->nr_frags++);
> +		new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff));
> +	}
> +
> +	/* Move any other page fragments rather than copy */
> +	memcpy(&toi->frags[toi->nr_frags], fromi->frags,
> +	       sizeof(fromi->frags[0]) * fromi->nr_frags);
> +	toi->nr_frags += fromi->nr_frags;
> +	fromi->nr_frags = 0;
> +	from->data_len = 0;
> +	from->len = 0;
> +	to->truesize += from->truesize - new_truesize;
> +	from->truesize = new_truesize;
> +
> +	/* We are done with this SKB */
> +	consume_skb(from);
> +}
> +
> +static void iptfs_output_queued(struct xfrm_state *x, struct sk_buff_head *list)
> +{
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +	struct sk_buff *skb, *skb2, **nextp;
> +	struct skb_shared_info *shi, *shi2;
> +
> +	/* For now we are just outputting packets as fast as we can, so if we
> +	 * are fragmenting we will do so until the last inner packet has been
> +	 * consumed.
> +	 *
> +	 * When we are fragmenting we need to output all outer packets that
> +	 * contain the fragments of a single inner packet, consecutively (ESP
> +	 * seq-wise). Since this output function is always running from a timer
> +	 * we do not need a lock to provide this guarantee. We will output our
> +	 * packets consecutively before the timer is allowed to run again on
> +	 * some other CPU.
> +	 */
> +
> +	/* NOTE: for the future, for timed packet sends, if our queue is not
> +	 * growing longer (i.e., we are keeping up) and a packet we are about to
> +	 * fragment will not fragment in then next outer packet, we might consider
> +	 * holding on to it to send whole in the next slot. The question then is
> +	 * does this introduce a continuous delay in the inner packet stream
> +	 * with certain packet rates and sizes?
> +	 */
> +
> +	/* and send them on their way */
> +
> +	while ((skb = __skb_dequeue(list))) {
> +		u32 mtu = iptfs_get_cur_pmtu(x, xtfs, skb);
> +		bool share_ok = true;
> +		int remaining;
> +
> +		/* protocol comes to us cleared sometimes */
> +		skb->protocol = x->outer_mode.family == AF_INET ?
> +					htons(ETH_P_IP) :
> +					htons(ETH_P_IPV6);
> +
> +		if (skb->len > mtu && xtfs->cfg.dont_frag) {
> +			/* We handle this case before enqueueing so we are only
> +			 * here b/c MTU changed after we enqueued before we
> +			 * dequeued, just drop these.
> +			 */
> +			XFRM_INC_STATS(dev_net(skb->dev),
> +				       LINUX_MIB_XFRMOUTERROR);
> +
> +			trace_iptfs_first_toobig(skb, mtu, 0, ip_hdr(skb));
> +			kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
> +			continue;
> +		}
> +
> +		/* iptfs_first_skb will free skb on error as well */
> +		if (iptfs_first_skb(&skb, xtfs, mtu))
> +			continue;
> +
> +		/* The returned skb is the last IPTFS fragment, it has it's
> +		 * IPTFS header included and it's blkoff set just past the end
> +		 * fragment data if needed. The space remaining to send more
> +		 * inner packet data is `mtu` - (skb->len - sizeof iptfs
> +		 * header). This is b/c the `mtu` value has the basic IPTFS
> +		 * header len accounted for, and we added that header to the skb
> +		 * so it is a part of skb->len, thus we subtract it from the skb
> +		 * length.
> +		 */
> +		remaining = mtu - (skb->len - sizeof(struct ip_iptfs_hdr));
> +
> +		/* Re-home nested fragment lists. */
> +		shi = skb_shinfo(skb);
> +		nextp = &shi->frag_list;
> +		while (*nextp) {
> +			if (skb_has_frag_list(*nextp))
> +				nextp = iptfs_rehome_fraglist(&(*nextp)->next,
> +							      *nextp);
> +			else
> +				nextp = &(*nextp)->next;
> +		}
> +
> +		if (shi->frag_list || skb_cloned(skb) || skb_shared(skb))
> +			share_ok = false;
> +
> +		/* See if we have enough space to simply append.
> +		 *
> +		 * NOTE: Maybe do not append if we will be mis-aligned,
> +		 * SW-based endpoints will probably have to copy in this
> +		 * case.
> +		 */
> +		while ((skb2 = skb_peek(list))) {
> +			trace_iptfs_ingress_nth_peek(skb2, remaining);
> +			if (skb2->len > remaining)
> +				break;
> +
> +			__skb_unlink(skb2, list);
> +
> +			/* The opportunity for HW offload has ended, if we
> +			 * don't have a cksum in the packet we need to add one
> +			 * before encap and transmit.
> +			 */
> +			if (skb2->ip_summed == CHECKSUM_PARTIAL) {
> +				if (skb_checksum_help(skb2)) {
> +					XFRM_INC_STATS(dev_net(skb_dst(skb2)->dev),
> +						       LINUX_MIB_XFRMOUTERROR);
> +					kfree_skb(skb2);
> +					continue;
> +				}
> +			}
> +
> +			/* skb->pp_recycle is passed to __skb_flag_unref for all
> +			 * frag pages so we can only share pages with skb's who
> +			 * match ourselves.
> +			 */
> +			shi2 = skb_shinfo(skb2);
> +			if (share_ok &&
> +			    (shi2->frag_list ||
> +			     (!skb2->head_frag && skb_headlen(skb)) ||
> +			     skb->pp_recycle != skb2->pp_recycle ||
> +			     skb_zcopy(skb2) ||
> +			     (shi->nr_frags + shi2->nr_frags + 1 > MAX_SKB_FRAGS)))
> +				share_ok = false;
> +
> +			/* do acct so we can free skb2 in share case */
> +			skb->data_len += skb2->len;
> +			skb->len += skb2->len;
> +			remaining -= skb2->len;
> +
> +			trace_iptfs_ingress_nth_add(skb2, share_ok);
> +
> +			if (share_ok) {
> +				iptfs_consume_frags(skb, skb2);
> +			} else {
> +				/* link on the frag_list */
> +				*nextp = skb2;
> +				nextp = &skb2->next;
> +				BUG_ON(*nextp);
> +				if (skb_has_frag_list(skb2))
> +					nextp = iptfs_rehome_fraglist(nextp,
> +								      skb2);
> +				skb->truesize += skb2->truesize;
> +			}
> +		}
> +
> +		/* Consider fragmenting this skb2 that didn't fit. For demand
> +		 * driven variable sized IPTFS pkts, though this isn't buying
> +		 * a whole lot, especially if we are doing a copy which waiting
> +		 * to send in a new pkt would not.
> +		 */
> +
> +		xfrm_output(NULL, skb);
> +	}
> +}
> +
> +static enum hrtimer_restart iptfs_delay_timer(struct hrtimer *me)
> +{
> +	struct sk_buff_head list;
> +	struct xfrm_iptfs_data *xtfs;
> +	struct xfrm_state *x;
> +	time64_t settime;
> +
> +	xtfs = container_of(me, typeof(*xtfs), iptfs_timer);
> +	x = xtfs->x;
> +
> +	/* Process all the queued packets
> +	 *
> +	 * softirq execution order: timer > tasklet > hrtimer
> +	 *
> +	 * Network rx will have run before us giving one last chance to queue
> +	 * ingress packets for us to process and transmit.
> +	 */
> +
> +	spin_lock(&x->lock);
> +	__skb_queue_head_init(&list);
> +	skb_queue_splice_init(&xtfs->queue, &list);
> +	xtfs->queue_size = 0;
> +	settime = xtfs->iptfs_settime;
> +	spin_unlock(&x->lock);
> +
> +	/* After the above unlock, packets can begin queuing again, and the
> +	 * timer can be set again, from another CPU either in softirq or user
> +	 * context (not from this one since we are running at softirq level
> +	 * already).
> +	 */
> +
> +	trace_iptfs_timer_expire(xtfs,
> +				 (unsigned long long)(ktime_get_raw_fast_ns() - settime));
> +
> +	iptfs_output_queued(x, &list);
> +
> +	return HRTIMER_NORESTART;
> +}
> +
> +/**
> + * iptfs_encap_add_ipv4() - add outer encaps
> + * @x: xfrm state
> + * @skb: the packet
> + *
> + * This was originally taken from xfrm4_tunnel_encap_add. The reason for the
> + * copy is that IP-TFS/AGGFRAG can have different functionality for how to set
> + * the TOS/DSCP bits. Sets the protocol to a different value and doesn't do
> + * anything with inner headers as they aren't pointing into a normal IP
> + * singleton inner packet.
> + */
> +static int iptfs_encap_add_ipv4(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	struct dst_entry *dst = skb_dst(skb);
> +	struct iphdr *top_iph;
> +
> +	skb_reset_inner_network_header(skb);
> +	skb_reset_inner_transport_header(skb);
> +
> +	skb_set_network_header(skb, -(x->props.header_len - x->props.enc_hdr_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 = IPPROTO_AGGFRAG;
> +
> +	/* As we have 0, fractional, 1 or N inner packets there's no obviously
> +	 * correct DSCP mapping to inherit. ECN should be cleared per RFC9347
> +	 * 3.1.
> +	 */
> +	top_iph->tos = 0;
> +
> +	top_iph->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;
> +}
> +
> +/**
> + * iptfs_encap_add_ipv6() - add outer encaps
> + * @x: xfrm state
> + * @skb: the packet
> + *
> + * This was originally taken from xfrm6_tunnel_encap_add. The reason for the
> + * copy is that IP-TFS/AGGFRAG can have different functionality for how to set
> + * the flow label and TOS/DSCP bits. It also sets the protocol to a different
> + * value and doesn't do anything with inner headers as they aren't pointing into
> + * a normal IP singleton inner packet.
> + */
> +static int iptfs_encap_add_ipv6(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	struct dst_entry *dst = skb_dst(skb);
> +	struct ipv6hdr *top_iph;
> +	int dsfield;
> +
> +	skb_reset_inner_network_header(skb);
> +	skb_reset_inner_transport_header(skb);
> +
> +	skb_set_network_header(skb,
> +			       -x->props.header_len + x->props.enc_hdr_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;
> +	top_iph->priority = 0;
> +	memset(top_iph->flow_lbl, 0, sizeof(top_iph->flow_lbl));
> +	top_iph->nexthdr = IPPROTO_AGGFRAG;
> +
> +	/* As we have 0, fractional, 1 or N inner packets there's no obviously
> +	 * correct DSCP mapping to inherit. ECN should be cleared per RFC9347
> +	 * 3.1.
> +	 */
> +	dsfield = 0;
> +	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;
> +}
> +
> +/**
> + * iptfs_prepare_output() -  prepare the skb for output
> + * @x: xfrm state
> + * @skb: the packet
> + *
> + * Return: Error value, if 0 then skb values should be as follows:
> + *    - transport_header should point at ESP header
> + *    - network_header should point at Outer IP header
> + *    - mac_header should point at protocol/nexthdr of the outer IP
> + */
> +static int iptfs_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	if (x->outer_mode.family == AF_INET)
> +		return iptfs_encap_add_ipv4(x, skb);
> +	if (x->outer_mode.family == AF_INET6) {
> +#if IS_ENABLED(CONFIG_IPV6)
> +		return iptfs_encap_add_ipv6(x, skb);
> +#else
> +		WARN_ON_ONCE(1);
> +		return -EAFNOSUPPORT;
> +#endif
> +	}
> +	WARN_ON_ONCE(1);
> +	return -EOPNOTSUPP;
> +}
> +
> +/* ========================== */
> +/* State Management Functions */
> +/* ========================== */
> +
> +/**
> + * __iptfs_get_inner_mtu() - return inner MTU with no fragmentation.
> + * @x: xfrm state.
> + * @outer_mtu: the outer mtu
> + */
> +static u32 __iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu)
> +{
> +	struct crypto_aead *aead;
> +	u32 blksize;
> +
> +	aead = x->data;
> +	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
> +	return ((outer_mtu - x->props.header_len - crypto_aead_authsize(aead)) &
> +		~(blksize - 1)) - 2;
> +}
> +
> +/**
> + * iptfs_get_mtu() - return the inner MTU for an IPTFS xfrm.
> + * @x: xfrm state.
> + * @outer_mtu: Outer MTU for the encapsulated packet.
> + *
> + * Return: Correct MTU taking in to account the encap overhead.
> + */
> +static u32 iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu)
> +{
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +
> +	/* If not dont-frag we have no MTU */
> +	if (!xtfs->cfg.dont_frag)
> +		return x->outer_mode.family == AF_INET ? IP_MAX_MTU :
> +							 IP6_MAX_MTU;
> +	return __iptfs_get_inner_mtu(x, outer_mtu);
> +}
> +
> +/**
> + * iptfs_user_init() - initialize the SA with IPTFS options from netlink.
> + * @net: the net data
> + * @x: xfrm state
> + * @attrs: netlink attributes
> + * @extack: extack return data
> + */
> +static int iptfs_user_init(struct net *net, struct xfrm_state *x,
> +			   struct nlattr **attrs,
> +			   struct netlink_ext_ack *extack)
> +{
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +	struct xfrm_iptfs_config *xc;
> +
> +	xc = &xtfs->cfg;
> +	xc->reorder_win_size = net->xfrm.sysctl_iptfs_reorder_window;
> +	xc->max_queue_size = net->xfrm.sysctl_iptfs_max_qsize;
> +	xtfs->init_delay_ns = net->xfrm.sysctl_iptfs_init_delay * NSECS_IN_USEC;
> +	xtfs->drop_time_ns = net->xfrm.sysctl_iptfs_drop_time * NSECS_IN_USEC;
> +
> +	if (attrs[XFRMA_IPTFS_DONT_FRAG])
> +		xc->dont_frag = true;
> +	if (attrs[XFRMA_IPTFS_REORDER_WINDOW])
> +		xc->reorder_win_size =
> +			nla_get_u16(attrs[XFRMA_IPTFS_REORDER_WINDOW]);
> +	/* saved array is for saving 1..N seq nums from wantseq */
> +	if (xc->reorder_win_size)
> +		xtfs->w_saved = kcalloc(xc->reorder_win_size,
> +					sizeof(*xtfs->w_saved), GFP_KERNEL);
> +	if (attrs[XFRMA_IPTFS_PKT_SIZE]) {
> +		xc->pkt_size = nla_get_u32(attrs[XFRMA_IPTFS_PKT_SIZE]);
> +		if (!xc->pkt_size) {
> +			xtfs->payload_mtu = 0;
> +		} else if (xc->pkt_size > x->props.header_len) {
> +			xtfs->payload_mtu = xc->pkt_size - x->props.header_len;
> +		} else {
> +			NL_SET_ERR_MSG(extack,
> +				       "Packet size must be 0 or greater than IPTFS/ESP header length");
> +			return -EINVAL;
> +		}
> +	}
> +	if (attrs[XFRMA_IPTFS_MAX_QSIZE])
> +		xc->max_queue_size = nla_get_u32(attrs[XFRMA_IPTFS_MAX_QSIZE]);
> +	if (attrs[XFRMA_IPTFS_DROP_TIME])
> +		xtfs->drop_time_ns = nla_get_u32(attrs[XFRMA_IPTFS_DROP_TIME]) *
> +				     NSECS_IN_USEC;
> +	if (attrs[XFRMA_IPTFS_INIT_DELAY])
> +		xtfs->init_delay_ns =
> +			nla_get_u32(attrs[XFRMA_IPTFS_INIT_DELAY]) *
> +			NSECS_IN_USEC;
> +
> +	xtfs->ecn_queue_size = (u64)xc->max_queue_size * 95 / 100;
> +
> +	return 0;
> +}
> +
> +static int iptfs_copy_to_user(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +	struct xfrm_iptfs_config *xc = &xtfs->cfg;
> +	int ret;
> +
> +	if (xc->dont_frag) {
> +		ret = nla_put_flag(skb, XFRMA_IPTFS_DONT_FRAG);
> +		if (ret)
> +			return ret;
> +	}
> +	ret = nla_put_u16(skb, XFRMA_IPTFS_REORDER_WINDOW, xc->reorder_win_size);
> +	if (ret)
> +		return ret;
> +	ret = nla_put_u32(skb, XFRMA_IPTFS_PKT_SIZE, xc->pkt_size);
> +	if (ret)
> +		return ret;
> +	ret = nla_put_u32(skb, XFRMA_IPTFS_MAX_QSIZE, xc->max_queue_size);
> +	if (ret)
> +		return ret;
> +	ret = nla_put_u32(skb, XFRMA_IPTFS_DROP_TIME,
> +			  xtfs->drop_time_ns / NSECS_IN_USEC);
> +	if (ret)
> +		return ret;
> +	ret = nla_put_u32(skb, XFRMA_IPTFS_INIT_DELAY,
> +			  xtfs->init_delay_ns / NSECS_IN_USEC);
> +	return ret;
> +}
> +
> +static int __iptfs_init_state(struct xfrm_state *x,
> +			      struct xfrm_iptfs_data *xtfs)
> +{
> +	__skb_queue_head_init(&xtfs->queue);
> +	hrtimer_init(&xtfs->iptfs_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE);
> +	xtfs->iptfs_timer.function = iptfs_delay_timer;
> +
> +	spin_lock_init(&xtfs->drop_lock);
> +	hrtimer_init(&xtfs->drop_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE);
> +	xtfs->drop_timer.function = iptfs_drop_timer;
> +
> +	/* Modify type (esp) adjustment values */
> +
> +	if (x->props.family == AF_INET)
> +		x->props.header_len += sizeof(struct iphdr) + sizeof(struct ip_iptfs_hdr);
> +	else if (x->props.family == AF_INET6)
> +		x->props.header_len += sizeof(struct ipv6hdr) + sizeof(struct ip_iptfs_hdr);
> +	x->props.enc_hdr_len = sizeof(struct ip_iptfs_hdr);
> +
> +	/* Always have a module reference if x->mode_data is set */
> +	if (!try_module_get(x->mode_cbs->owner))

when this is called via iptfs_clone x->mode_cbs is not yet.
It would casue 

BUG: KASAN: null-ptr-deref in __iptfs_init_state+0x103/0x149


> +		return -EINVAL;
> +
> +	x->mode_data = xtfs;
> +	xtfs->x = x;
> +
> +	return 0;
> +}
> +
> +static int iptfs_clone(struct xfrm_state *x, struct xfrm_state *orig)
> +{
> +	struct xfrm_iptfs_data *xtfs;
> +	int err;
> +
> +	xtfs = kmemdup(orig->mode_data, sizeof(*xtfs), GFP_KERNEL);
> +	if (!xtfs)
> +		return -ENOMEM;
> +
> +	xtfs->ra_newskb = NULL;
> +	if (xtfs->cfg.reorder_win_size) {
> +		xtfs->w_saved = kcalloc(xtfs->cfg.reorder_win_size,
> +					sizeof(*xtfs->w_saved), GFP_KERNEL);
> +		if (!xtfs->w_saved) {
> +			kfree_sensitive(xtfs);
> +			return -ENOMEM;
> +		}
> +	}
> +
> +	err = __iptfs_init_state(x, xtfs);


xfrm_state_migrate()
1862         xc = xfrm_state_clone(x, encap) {
		iptfs_clone()
			__iptfs_init_state() # note the first call
	}

following  xfrm_state_clone ther is a call to 

1868         if (xfrm_init_state(xc) < 0) {
			__xfrm_init_state ()
				x->mode_cbs->create_state(x); -> iptfs_create_statea()
					__iptfs_init_state()  # second call.
	     }


> +	if (err)
> +		return err;
> +
> +	return 0;
> +}
> +
> +static int iptfs_create_state(struct xfrm_state *x)
> +{
> +	struct xfrm_iptfs_data *xtfs;
> +	int err;
> +
> +	xtfs = kzalloc(sizeof(*xtfs), GFP_KERNEL);
> +	if (!xtfs)
> +		return -ENOMEM;
> +
> +	err = __iptfs_init_state(x, xtfs);
> +	if (err)
> +		return err;
> +
> +	return 0;
> +}
> +
> +static void iptfs_delete_state(struct xfrm_state *x)
> +{
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +	struct skb_wseq *s, *se;
> +
> +	if (!xtfs)
> +		return;
> +
> +	spin_lock_bh(&xtfs->drop_lock);
> +	hrtimer_cancel(&xtfs->iptfs_timer);
> +	hrtimer_cancel(&xtfs->drop_timer);
> +	spin_unlock_bh(&xtfs->drop_lock);
> +
> +	if (xtfs->ra_newskb)
> +		kfree_skb(xtfs->ra_newskb);
> +
> +	for (s = xtfs->w_saved, se = s + xtfs->w_savedlen; s < se; s++)
> +		if (s->skb)
> +			kfree_skb(s->skb);
> +
> +	kfree_sensitive(xtfs->w_saved);
> +	kfree_sensitive(xtfs);
> +
> +	module_put(x->mode_cbs->owner);
> +}
> +
> +static const struct xfrm_mode_cbs iptfs_mode_cbs = {
> +	.owner = THIS_MODULE,
> +	.create_state = iptfs_create_state,
> +	.delete_state = iptfs_delete_state,
> +	.user_init = iptfs_user_init,
> +	.copy_to_user = iptfs_copy_to_user,
> +	.clone = iptfs_clone,
> +	.get_inner_mtu = iptfs_get_inner_mtu,
> +	.input = iptfs_input,
> +	.output = iptfs_output_collect,
> +	.prepare_output = iptfs_prepare_output,
> +};
> +
> +static int __init xfrm_iptfs_init(void)
> +{
> +	int err;
> +
> +	pr_info("xfrm_iptfs: IPsec IP-TFS tunnel mode module\n");
> +
> +	err = xfrm_register_mode_cbs(XFRM_MODE_IPTFS, &iptfs_mode_cbs);
> +	if (err < 0)
> +		pr_info("%s: can't register IP-TFS\n", __func__);
> +
> +	return err;
> +}
> +
> +static void __exit xfrm_iptfs_fini(void)
> +{
> +	xfrm_unregister_mode_cbs(XFRM_MODE_IPTFS);
> +}
> +
> +module_init(xfrm_iptfs_init);
> +module_exit(xfrm_iptfs_fini);
> +MODULE_LICENSE("GPL");
> -- 
> 2.43.0
> 

[PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[Sabrina Dubroca]

2024-02-19, 03:57:35 -0500, Christian Hopps wrote:
>  net/xfrm/Makefile      |    1 +
>  net/xfrm/trace_iptfs.h |  218 ++++
>  net/xfrm/xfrm_iptfs.c  | 2762 ++++++++++++++++++++++++++++++++++++++++

This should probably be split into a few patches (maybe user config,
output, reordering, input, tracepoints) to help reviewers and keep the
answers to a more reasonable length. I dropped some of the feedback I
had because this email was getting ridiculous.

> diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
> new file mode 100644

[...]
> +static struct sk_buff *iptfs_alloc_skb(struct sk_buff *tpl, u32 len,
> +				       bool l3resv)
> +{
> +	struct sk_buff *skb;
> +	u32 resv;
> +
> +	if (!l3resv) {
> +		resv = XFRM_IPTFS_MIN_L2HEADROOM;
> +	} else {
> +		resv = skb_headroom(tpl);
> +		if (resv < XFRM_IPTFS_MIN_L3HEADROOM)
> +			resv = XFRM_IPTFS_MIN_L3HEADROOM;
> +	}
> +
> +	skb = alloc_skb(len + resv, GFP_ATOMIC);
> +	if (!skb) {
> +		XFRM_INC_STATS(dev_net(tpl->dev), LINUX_MIB_XFRMINERROR);

Confusing, as iptfs_alloc_skb can be called from the output path as well.

> +		return NULL;
> +	}
> +
> +	skb_reserve(skb, resv);
> +
> +	/* Code from __copy_skb_header() -- we do not want any of the
> +	 * tpl->headers copied over, so we aren't using `skb_copy_header()`.
> +	 */

This is a bit of a bad sign for the implementation. It also worries
me, as this may not be updated when changes are made to
__copy_skb_header().

> +	skb->tstamp = tpl->tstamp;
> +	skb->dev = tpl->dev;
> +	memcpy(skb->cb, tpl->cb, sizeof(skb->cb));
> +	skb_dst_copy(skb, tpl);
> +	__skb_ext_copy(skb, tpl);
> +	__nf_copy(skb, tpl, false);
> +
> +	return skb;
> +}



> +static void skb_head_to_frag(const struct sk_buff *skb, skb_frag_t *frag)
> +static void skb_prepare_frag_walk(struct sk_buff *skb, u32 initial_offset,
> +static u32 __skb_reset_frag_walk(struct skb_frag_walk *walk, u32 offset)
> +static bool skb_can_add_frags(const struct sk_buff *skb,
> +static int skb_add_frags(struct sk_buff *skb, struct skb_frag_walk *walk,

That's a lot of new helpers. Is there no existing API that fits IPTFS's needs?


> +static int skb_copy_bits_seq(struct skb_seq_state *st, int offset, void *to, int len)

Probably belongs in net/core/skbuff.c (if this is really the right way
to implement iptfs).


[...]
> +static int iptfs_input_ordered(struct xfrm_state *x, struct sk_buff *skb)
> +{
[...]
> +	skb_prepare_seq_read(skb, 0, skb->len, &skbseq);
> +
> +	/* Get the IPTFS header and validate it */
> +
> +	if (skb_copy_bits_seq(&skbseq, 0, ipth, sizeof(*ipth))) {

Could you use pskb_may_pull here? Like the rest of networking does
when parsing headers from skbs.

> +		XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
> +		goto done;
> +	}
> +	data = sizeof(*ipth);
> +
> +	trace_iptfs_egress_recv(skb, xtfs, htons(ipth->block_offset));
> +
> +	/* Set data past the basic header */
> +	if (ipth->subtype == IPTFS_SUBTYPE_CC) {
> +		/* Copy the rest of the CC header */
> +		remaining = sizeof(iptcch) - sizeof(*ipth);
> +		if (skb_copy_bits_seq(&skbseq, data, ipth + 1, remaining)) {
> +			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
> +			goto done;
> +		}
> +		data += remaining;
> +	} else if (ipth->subtype != IPTFS_SUBTYPE_BASIC) {
> +		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
> +		goto done;
> +	}

[...]
> +		} else {
> +			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
> +			goto done;
> +		}
> +
> +		if (unlikely(skbseq.stepped_offset)) {

I don't think users of skb_seq_* should look into the internal state
of the skbseq.


[...]
> +				/* all pointers could be changed now reset walk */
> +				skb_abort_seq_read(&skbseq);
> +				skb_prepare_seq_read(skb, data, tail, &skbseq);

The fact that you have to reset the walk indicates that this is
probably not the right way to implement this.

> +			} else if (skb->head_frag &&
> +				   /* We have the IP header right now */
> +				   remaining >= iphlen) {
> +				fragwalk = &_fragwalk;
> +				skb_prepare_frag_walk(skb, data, fragwalk);
> +				defer = skb;
> +				skb = NULL;
> +			} else {
> +				/* We couldn't reuse the input skb so allocate a
> +				 * new one.
> +				 */
> +				defer = skb;
> +				skb = NULL;
> +			}

I still don't get at all how the overall defrag/reassembly process is
implemented. I can tell you're walking the skb looking for IP headers,
and (I suppose) carving out new skbs containing a single packet built
from that header and all the payload that goes with it (and then
saving the last chunk to merge with the next incoming packet), but I
don't understand how.

This chunk looks like it might be optimizations, but I'm not sure. If
this is indeed the case, I'd suggest to remove them. For the initial
submission it would be nice to have a slightly dumber version that
reviewers can fully understand. Then you can add back the
optimizations once the code is merged.



[...]
> +/* ------------------------------- */
> +/* Input (Egress) Re-ordering Code */
> +/* ------------------------------- */

nit: ingress? The whole patch seems to mix up ingress/egress and
send/receive.

[...]
> +static u32 __reorder_future_fits(struct xfrm_iptfs_data *xtfs,
> +				 struct sk_buff *inskb,
> +				 struct list_head *freelist, u32 *fcount)
> +{
[...]
> +	BUG_ON(distance >= nslots);

Really not needed. I saw what you wrote about assert philosophy, but
that's not how BUG_ON is used in the kernel. DEBUG_NET_WARN_ON_ONCE
would fit that better for conditions that really should never be
true/false.

> +	if (xtfs->w_saved[index].skb) {
> +		/* a dup of a future */
> +		list_add_tail(&inskb->list, freelist);

Why not just free it immediately?


> +static u32 __reorder_future_shifts(struct xfrm_iptfs_data *xtfs,
> +				   struct sk_buff *inskb,
> +				   struct list_head *list,
> +				   struct list_head *freelist, u32 *fcount)
> +{

[...]
> +	/* ex: slot count is 4, array size is 3 savedlen is 2, slot 0 is the
> +	 * missing sequence number.

It would help to show the state of the reorder window (and all the
related state) at the end of this function (and maybe intermediate
states, after the loop and again after the following if block).

I also struggled to parse the formatting of the diagrams (for example,
what [b] and [-] and --- mean).


> +	 * the final slot at savedlen (index savedlen - 1) is always occupied.
> +	 *
> +	 * beyond is "beyond array size" not savedlen.
> +	 *
> +	 *          +--------- array length (savedlen == 2)
> +	 *          |   +----- array size (nslots - 1 == 3)
> +	 *          |   |   +- window boundary (nslots == 4)
> +	 *          V   V | V
> +	 *                |
> +	 *  0   1   2   3 |   slot number
> +	 * ---  0   1   2 |   array index
> +	 *     [b] [c] : :|   array
> +	 *                |
> +	 * "2" "3" "4" "5"|*6*  seq numbers
> +	 *
> +	 * We receive seq number 6
> +	 * distance == 4 [inseq(6) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 3 [distance(4) - 1]
> +	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
> +	 * shifting == 1 [min(savedlen(2), beyond(1)]
> +	 * slot0_skb == [b], and should match w_wantseq

A separator between each example (maybe a long line of '*') would be
helpful.

> +	 *
> +	 *                +--- window boundary (nslots == 4)
> +	 *  0   1   2   3 | 4   slot number
> +	 * ---  0   1   2 | 3   array index
> +	 *     [b] : : : :|     array
> +	 * "2" "3" "4" "5" *6*  seq numbers
> +	 *
> +	 * We receive seq number 6
> +	 * distance == 4 [inseq(6) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 3 [distance(4) - 1]
> +	 * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))]
> +	 * shifting == 1 [min(savedlen(1), beyond(1)]
> +	 * slot0_skb == [b] and should match w_wantseq
> +	 *
> +	 *                +-- window boundary (nslots == 4)
> +	 *  0   1   2   3 | 4   5   6   slot number
> +	 * ---  0   1   2 | 3   4   5   array index
> +	 *     [-] [c] : :|             array
> +	 * "2" "3" "4" "5" "6" "7" *8*  seq numbers
> +	 *
> +	 * savedlen = 2, beyond = 3
> +	 * iter 1: slot0 == NULL, missed++, lastdrop = 2 (2+1-1), slot0 = [-]
> +	 * iter 2: slot0 == NULL, missed++, lastdrop = 3 (2+2-1), slot0 = [c]

I'm not quite sure what "iter 1" and "iter 2" refer to.

> +	 * 2 < 3, extra = 1 (3-2), missed += extra, lastdrop = 4 (2+2+1-1)
> +	 *
> +	 * We receive seq number 8
> +	 * distance == 6 [inseq(8) - w_wantseq(2)]
> +	 * newslot == distance
> +	 * index == 5 [distance(6) - 1]
> +	 * beyond == 3 [newslot(6) - lastslot((nslots(4) - 1))]
> +	 * shifting == 2 [min(savedlen(2), beyond(3)]
> +	 *
> +	 * slot0_skb == NULL changed from [b] when "savedlen < beyond" is true.
> +	 */
> +
> +	/* Now send any packets that are being shifted out of saved, and account
> +	 * for missing packets that are exiting the window as we shift it.
> +	 */
> +
> +	/* If savedlen > beyond we are shifting some, else all. */
> +	shifting = min(savedlen, beyond);
> +
> +	/* slot0 is the buf that just shifted out and into slot0 */
> +	slot0 = NULL;
> +	s0seq = wantseq;
> +	last_drop_seq = s0seq;

Set but never read.

> +	wnext = xtfs->w_saved;
> +	for (slot = 1; slot <= shifting; slot++, wnext++) {
> +		/* handle what was in slot0 before we occupy it */
> +		if (!slot0) {
> +			last_drop_seq = s0seq;
> +			missed++;

Set but never read.

> +		} else {
> +			list_add_tail(&slot0->list, list);
> +			count++;
> +		}
> +		s0seq++;
> +		slot0 = wnext->skb;
> +		wnext->skb = NULL;
> +	}

I wonder if this code would become more readable by "wasting" an array
element for slot0 (which can never be set except temporarily while
shifting and reordering packets). This function is more than 50%
comments :/

> +	/* slot0 is now either NULL (in which case it's what we now are waiting
> +	 * for, or a buf in which case we need to handle it like we received it;
> +	 * however, we may be advancing past that buffer as well..
> +	 */
> +
> +	/* Handle case where we need to shift more than we had saved, slot0 will
> +	 * be NULL iff savedlen is 0, otherwise slot0 will always be
> +	 * non-NULL b/c we shifted the final element, which is always set if
> +	 * there is any saved, into slot0.
> +	 */
> +	if (savedlen < beyond) {
> +		extra_drops = beyond - savedlen;
> +		if (savedlen == 0) {
> +			BUG_ON(slot0);
> +			s0seq += extra_drops;
> +			last_drop_seq = s0seq - 1;
> +		} else {
> +			extra_drops--; /* we aren't dropping what's in slot0 */
> +			BUG_ON(!slot0);
> +			list_add_tail(&slot0->list, list);
> +			/* if extra_drops then we are going past this slot0
> +			 * so we can safely advance last_drop_seq
> +			 */
> +			if (extra_drops)
> +				last_drop_seq = s0seq + extra_drops;
> +			s0seq += extra_drops + 1;
> +			count++;
> +		}
> +		missed += extra_drops;
> +		slot0 = NULL;
> +		/* slot0 has had an empty slot pushed into it */
> +	}
> +	(void)last_drop_seq;	/* we want this for CC code */

Ewww. Please no breadcrumbs.

> +
> +	/* Remove the entries */

This comment doesn't explain much...

> +	__vec_shift(xtfs, beyond);
> +
> +	/* Advance want seq */

and this one even less.

> +	xtfs->w_wantseq += beyond;
> +
> +	/* Process drops here when implementing congestion control */

[...]
> +static int iptfs_input(struct xfrm_state *x, struct sk_buff *skb)
> +{
> +	struct list_head freelist, list;
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +	struct sk_buff *next;
> +	u32 count, fcount;
> +
> +	/* Fast path for no reorder window. */
> +	if (xtfs->cfg.reorder_win_size == 0) {
> +		iptfs_input_ordered(x, skb);
> +		goto done;
> +	}
> +
> +	/* Fetch list of in-order packets from the reordering window as well as
> +	 * a list of buffers we need to now free.
> +	 */
> +	INIT_LIST_HEAD(&list);
> +	INIT_LIST_HEAD(&freelist);
> +	fcount = 0;
> +
> +	spin_lock(&xtfs->drop_lock);
> +	count = iptfs_input_reorder(xtfs, skb, &list, &freelist, &fcount);

iptfs_input_reorder isn't that long, it would be less messy to just
insert it here.

> +	spin_unlock(&xtfs->drop_lock);
> +
> +	if (count) {

Do we really need those counts? I hope list_for_each_entry_safe can
deal just fine with an empty list?

> +		list_for_each_entry_safe(skb, next, &list, list) {
> +			skb_list_del_init(skb);
> +			(void)iptfs_input_ordered(x, skb);
> +		}
> +	}
> +
> +	if (fcount) {
> +		list_for_each_entry_safe(skb, next, &freelist, list) {
> +			skb_list_del_init(skb);
> +			kfree_skb(skb);

Given that freelist processing is so simple, why not just free
everything directly? It would remove the need to pass more arguments
down to the other functions.

> +		}
> +	}


[...]
> +/* IPv4/IPv6 packet ingress to IPTFS tunnel, arrange to send in IPTFS payload
> + * (i.e., aggregating or fragmenting as appropriate).
> + * This is set in dst->output for an SA.
> + */
> +static int iptfs_output_collect(struct net *net, struct sock *sk,
> +				struct sk_buff *skb)
> +{
[...]
> +	} else {
> +		segs = skb_gso_segment(skb, 0);
> +		if (IS_ERR_OR_NULL(segs)) {
> +			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
> +			kfree_skb(skb);
> +			return PTR_ERR(segs);

If skb_gso_segment returned NULL, this will end up returning 0. Is
that correct?



> +static int iptfs_user_init(struct net *net, struct xfrm_state *x,
> +			   struct nlattr **attrs,
> +			   struct netlink_ext_ack *extack)
> +{
[...]
> +	if (xc->reorder_win_size)
> +		xtfs->w_saved = kcalloc(xc->reorder_win_size,
> +					sizeof(*xtfs->w_saved), GFP_KERNEL);

if (!xtfs->w_saved)
    return -ENOMEM;



> +static int iptfs_create_state(struct xfrm_state *x)
> +{
> +	struct xfrm_iptfs_data *xtfs;
> +	int err;
> +
> +	xtfs = kzalloc(sizeof(*xtfs), GFP_KERNEL);
> +	if (!xtfs)
> +		return -ENOMEM;
> +
> +	err = __iptfs_init_state(x, xtfs);
> +	if (err)
> +		return err;

kfree(xtfs) here?
iptfs_delete_state can't free it since we haven't set x->mode_data yet
when __iptfs_init_state fails.

> +
> +	return 0;
> +}
> +
> +static void iptfs_delete_state(struct xfrm_state *x)
> +{
> +	struct xfrm_iptfs_data *xtfs = x->mode_data;
> +	struct skb_wseq *s, *se;
> +
> +	if (!xtfs)
> +		return;
> +
> +	spin_lock_bh(&xtfs->drop_lock);
> +	hrtimer_cancel(&xtfs->iptfs_timer);
> +	hrtimer_cancel(&xtfs->drop_timer);
> +	spin_unlock_bh(&xtfs->drop_lock);

Does this guarantee that xtfs->queue has been flushed? If not, I guess
we need to do it now.

> +
> +	if (xtfs->ra_newskb)
> +		kfree_skb(xtfs->ra_newskb);
> +
> +	for (s = xtfs->w_saved, se = s + xtfs->w_savedlen; s < se; s++)
> +		if (s->skb)
> +			kfree_skb(s->skb);

nit: possibly better if hidden in a free_reorder_pending helper (or
some other similar name), implemented alongside all the reorder code.


> +	kfree_sensitive(xtfs->w_saved);
> +	kfree_sensitive(xtfs);
> +
> +	module_put(x->mode_cbs->owner);
> +}

-- 
Sabrina

Re: [PATCH ipsec-next v1 8/8] iptfs: impl: add new iptfs xfrm mode impl

[Christian Hopps]

I'll go through the other comments this week; however...

> On Mar 6, 2024, at 08:57, Sabrina Dubroca <sd@queasysnail.net> wrote:
> 
>> +/* ------------------------------- */
>> +/* Input (Egress) Re-ordering Code */
>> +/* ------------------------------- */
> 
> nit: ingress? The whole patch seems to mix up ingress/egress and
> send/receive.


No, they are in fact correct in the whole patch. :)

"Tunnel ingress" is handled by xfrm output functions and "Tunnel Egress" are handled by xfrm input or receive functions.

The input routines take packets from inside the tunnel and move them out of the tunnel i.e., they are exiting (egressing) the tunnel.

If you replace "Ingress" and "Egress" with their English equivalents "Enter" and "Exit" maybe it's more obvious... As a routing and briefly an operations guy though I'll say that ingress and egress are used almost exclusively for tunnels rather than "enter" and "exit". :)

Thanks,
Chris.

[PATCH ipsec-next v1 0/8] Add IP-TFS mode to xfrm

[Christian Hopps]

From: Christian Hopps <chopps@labn.net>

Summary of Changes
------------------

This patchset adds a new xfrm mode implementing on-demand IP-TFS. IP-TFS
(AggFrag encapsulation) has been standardized in RFC9347.

  Link: https://www.rfc-editor.org/rfc/rfc9347.txt

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.

In order to allow loading this fucntionality as a module a set of
callbacks xfrm_mode_cbs has been added to xfrm as well.

Patchset Changes:
-----------------

  23 files changed, 3252 insertions(+), 19 deletions(-)
  Documentation/networking/xfrm_sysctl.rst |   30 +
  include/net/netns/xfrm.h                 |    6 +
  include/net/xfrm.h                       |   40 +
  include/uapi/linux/in.h                  |    2 +
  include/uapi/linux/ip.h                  |   16 +
  include/uapi/linux/ipsec.h               |    3 +-
  include/uapi/linux/snmp.h                |    3 +
  include/uapi/linux/xfrm.h                |    9 +-
  net/ipv4/esp4.c                          |    3 +-
  net/ipv6/esp6.c                          |    3 +-
  net/netfilter/nft_xfrm.c                 |    3 +-
  net/xfrm/Makefile                        |    1 +
  net/xfrm/trace_iptfs.h                   |  218 +++
  net/xfrm/xfrm_compat.c                   |   10 +-
  net/xfrm/xfrm_device.c                   |    4 +-
  net/xfrm/xfrm_input.c                    |   14 +-
  net/xfrm/xfrm_iptfs.c                    | 2741 ++++++++++++++++++++++++++++++
  net/xfrm/xfrm_output.c                   |    6 +
  net/xfrm/xfrm_policy.c                   |   26 +-
  net/xfrm/xfrm_proc.c                     |    3 +
  net/xfrm/xfrm_state.c                    |   60 +
  net/xfrm/xfrm_sysctl.c                   |   38 +
  net/xfrm/xfrm_user.c                     |   32 +

Patchset Structure:
-------------------

The first 8 commits are changes to the xfrm infrastructure to support
the callbacks as well as more generic IP-TFS additions that may be used
outside the actual IP-TFS implementation.

  - iptfs: config: add CONFIG_XFRM_IPTFS
  - iptfs: uapi: ip: add ip_tfs_*_hdr packet formats
  - iptfs: uapi: IPPROTO_AGGFRAG AGGFRAG in ESP
  - iptfs: sysctl: allow configuration of global default values
  - iptfs: netlink: add config (netlink) options
  - iptfs: xfrm: Add mode_cbs module functionality
  - iptfs: xfrm: add generic iptfs defines and functionality

The last 9+1 commits constitute the IP-TFS implementation constructed in
layers to make review easier. The first 9 commits all apply to a single
file `net/xfrm/xfrm_iptfs.c`, the last commit adds a new tracepoint
header file along with the use of these new tracepoint calls.

  - iptfs: impl: add new iptfs xfrm mode impl
  - iptfs: impl: add user packet (tunnel ingress) handling
  - iptfs: impl: share page fragments of inner packets
  - iptfs: impl: add fragmenting of larger than MTU user packets
  - iptfs: impl: add basic receive packet (tunnel egress) handling
  - iptfs: impl: handle received fragmented inner packets
  - iptfs: impl: add reusing received skb for the tunnel egress packet
  - iptfs: impl: add skb-fragment sharing code
  - iptfs: impl: handle reordering of received packets
  - iptfs: impl: add tracepoint functionality

Patchset History:
-----------------

RFCv1 (11/10/2023)

RFCv1 -> RFCv2 (11/12/2023)

  Updates based on feedback from Simon Horman, Antony,
  Michael Richardson, and kernel test robot.

RFCv2 -> v1 (2/19/2024)

  Updates based on feedback from Sabrina Dubroca, kernel test robot

v1 -> v2 (5/19/2024)

  Updates based on feedback from Sabrina Dubroca, Simon Horman, Antony.

  o Add handling of new netlink SA direction attribute (Antony).
  o Split single patch/commit of xfrm_iptfs.c (the actual IP-TFS impl)
    into 9+1 distinct layered functionality commits for aiding review.
  - xfrm: fix return check on clone() callback
  - xfrm: add sa_len() callback in xfrm_mode_cbs for copy to user
  - iptfs: remove unneeded skb free count variable
  - iptfs: remove unused variable and "breadcrumb" for future code.
  - iptfs: use do_div() to avoid "__udivd13 missing" link failure.
  - iptfs: remove some BUG_ON() assertions questioned in review.

Re: [PATCH ipsec-next v1 0/8] Add IP-TFS mode to xfrm

[Antony Antony]

Hi Chris,

On Mon, May 20, 2024 at 05:42:38PM -0400, Christian Hopps via Devel wrote:
> From: Christian Hopps <chopps@labn.net>
> 
> Summary of Changes
> ------------------
> 
> This patchset adds a new xfrm mode implementing on-demand IP-TFS. IP-TFS
> (AggFrag encapsulation) has been standardized in RFC9347.
> 
>   Link: https://www.rfc-editor.org/rfc/rfc9347.txt
> 
> 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.
> 
> In order to allow loading this fucntionality as a module a set of
> callbacks xfrm_mode_cbs has been added to xfrm as well.
> 
> Patchset Changes:
> -----------------
> 
>   23 files changed, 3252 insertions(+), 19 deletions(-)
>   Documentation/networking/xfrm_sysctl.rst |   30 +
>   include/net/netns/xfrm.h                 |    6 +
>   include/net/xfrm.h                       |   40 +
>   include/uapi/linux/in.h                  |    2 +
>   include/uapi/linux/ip.h                  |   16 +
>   include/uapi/linux/ipsec.h               |    3 +-
>   include/uapi/linux/snmp.h                |    3 +
>   include/uapi/linux/xfrm.h                |    9 +-
>   net/ipv4/esp4.c                          |    3 +-
>   net/ipv6/esp6.c                          |    3 +-
>   net/netfilter/nft_xfrm.c                 |    3 +-
>   net/xfrm/Makefile                        |    1 +
>   net/xfrm/trace_iptfs.h                   |  218 +++
>   net/xfrm/xfrm_compat.c                   |   10 +-
>   net/xfrm/xfrm_device.c                   |    4 +-
>   net/xfrm/xfrm_input.c                    |   14 +-
>   net/xfrm/xfrm_iptfs.c                    | 2741 ++++++++++++++++++++++++++++++
>   net/xfrm/xfrm_output.c                   |    6 +
>   net/xfrm/xfrm_policy.c                   |   26 +-
>   net/xfrm/xfrm_proc.c                     |    3 +
>   net/xfrm/xfrm_state.c                    |   60 +
>   net/xfrm/xfrm_sysctl.c                   |   38 +
>   net/xfrm/xfrm_user.c                     |   32 +
> 
> Patchset Structure:
> -------------------
> 
> The first 8 commits are changes to the xfrm infrastructure to support
> the callbacks as well as more generic IP-TFS additions that may be used
> outside the actual IP-TFS implementation.
> 
>   - iptfs: config: add CONFIG_XFRM_IPTFS
>   - iptfs: uapi: ip: add ip_tfs_*_hdr packet formats
>   - iptfs: uapi: IPPROTO_AGGFRAG AGGFRAG in ESP
>   - iptfs: sysctl: allow configuration of global default values
>   - iptfs: netlink: add config (netlink) options
>   - iptfs: xfrm: Add mode_cbs module functionality
>   - iptfs: xfrm: add generic iptfs defines and functionality
> 
> The last 9+1 commits constitute the IP-TFS implementation constructed in
> layers to make review easier. The first 9 commits all apply to a single
> file `net/xfrm/xfrm_iptfs.c`, the last commit adds a new tracepoint
> header file along with the use of these new tracepoint calls.
> 
>   - iptfs: impl: add new iptfs xfrm mode impl
>   - iptfs: impl: add user packet (tunnel ingress) handling
>   - iptfs: impl: share page fragments of inner packets
>   - iptfs: impl: add fragmenting of larger than MTU user packets
>   - iptfs: impl: add basic receive packet (tunnel egress) handling
>   - iptfs: impl: handle received fragmented inner packets
>   - iptfs: impl: add reusing received skb for the tunnel egress packet
>   - iptfs: impl: add skb-fragment sharing code
>   - iptfs: impl: handle reordering of received packets
>   - iptfs: impl: add tracepoint functionality
> 
> Patchset History:
> -----------------
> 
> RFCv1 (11/10/2023)
> 
> RFCv1 -> RFCv2 (11/12/2023)
> 
>   Updates based on feedback from Simon Horman, Antony,
>   Michael Richardson, and kernel test robot.
> 
> RFCv2 -> v1 (2/19/2024)
> 
>   Updates based on feedback from Sabrina Dubroca, kernel test robot
> 
> v1 -> v2 (5/19/2024)
> 
>   Updates based on feedback from Sabrina Dubroca, Simon Horman, Antony.
> 
>   o Add handling of new netlink SA direction attribute (Antony).
>   o Split single patch/commit of xfrm_iptfs.c (the actual IP-TFS impl)
>     into 9+1 distinct layered functionality commits for aiding review.
>   - xfrm: fix return check on clone() callback
>   - xfrm: add sa_len() callback in xfrm_mode_cbs for copy to user
>   - iptfs: remove unneeded skb free count variable
>   - iptfs: remove unused variable and "breadcrumb" for future code.
>   - iptfs: use do_div() to avoid "__udivd13 missing" link failure.
>   - iptfs: remove some BUG_ON() assertions questioned in review.
> -- 

I ran a couple of tests and it hit KSAN BUG.

I was sending large ping while MTU is 1500.

north login: shed systemd-user-sessions.service - Permit User Sessions.
north login: [   78.594770] ==================================================================
[   78.595825] BUG: KASAN: null-ptr-deref in iptfs_output_collect+0x263/0x57b
[   78.596658] Read of size 8 at addr 0000000000000108 by task ping/493
[   78.597435] ng rpc-statd-notify.service - Notify NFS peers of a restart...
[   78.597651] CPU: 0 PID: 493 Comm: ping Not tainted 6.9.0-rc2-00697-g489ca863e24f-dirty #11
[   78.598645] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   78.599747] Call Trace:tty@ttyS2.service - Serial Getty on ttyS2.
[   78.600070]  <TASK>l-getty@ttyS3.service - Serial Getty on ttyS3.
[   78.600354]  dump_stack_lvl+0x2a/0x3bogin Prompts.
[   78.600817]  kasan_report+0x84/0xa6rvice - Hostname Service...
[   78.601262]  ? iptfs_output_collect+0x263/0x57bl server.
[   78.601825]  iptfs_output_collect+0x263/0x57bogin Management.
[   78.602374]  ip_send_skb+0x25/0x57vice - Notify NFS peers of a restart.
[   78.602807]  raw_sendmsg+0xee8/0x1011t - Multi-User System.
[   78.603269]  ? native_flush_tlb_one_user+0xd/0xe5e Service.
[   78.603850]  ? raw_hash_sk+0x21b/0x21b
[   78.604331]  ? kernel_init_pages+0x42/0x51
[   78.604845]  ? prep_new_page+0x44/0x51Re…line ext4 Metadata Check Snapshots.
[   78.605318]  ? get_page_from_freelist+0x72b/0x915 Interface.
[   78.605903]  ? signal_pending_state+0x77/0x77cord Runlevel Change in UTMP...
[   78.606462]  ? __might_resched+0x8a/0x240e - Record Runlevel Change in UTMP.
[   78.606966]  ? __might_sleep+0x25/0xa0
[   78.607440]  ? first_zones_zonelist+0x2c/0x43
[   78.607985]  ? __rcu_read_lock+0x2d/0x3a
[   78.608479]  ? __pte_offset_map+0x32/0xa4
[   78.608979]  ? __might_resched+0x8a/0x240
[   78.609478]  ? __might_sleep+0x25/0xa0
[   78.609949]  ? inet_send_prepare+0x54/0x54
[   78.610464]  ? sock_sendmsg_nosec+0x42/0x6c
[   78.610984]  sock_sendmsg_nosec+0x42/0x6c
[   78.611485]  __sys_sendto+0x15d/0x1cc
[   78.611947]  ? __x64_sys_getpeername+0x44/0x44
[   78.612498]  ? __handle_mm_fault+0x679/0xae4
[   78.613033]  ? find_vma+0x6b/0x8b
[   78.613457]  ? find_vma_intersection+0x8a/0x8a
[   78.614006]  ? __handle_irq_event_percpu+0x180/0x197
[   78.614617]  ? handle_mm_fault+0x38/0x154
[   78.615114]  ? handle_mm_fault+0xeb/0x154
[   78.615620]  ? preempt_latency_start+0x29/0x34
[   78.616169]  ? preempt_count_sub+0x14/0xb3
[   78.616678]  ? up_read+0x4b/0x5c
[   78.617094]  __x64_sys_sendto+0x76/0x82
[   78.617577]  do_syscall_64+0x6b/0xd7
[   78.618043]  entry_SYSCALL_64_after_hwframe+0x46/0x4e
[   78.618667] RIP: 0033:0x7fed3de99a73
[   78.619118] Code: 8b 15 a9 83 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 80 3d 71 0b 0d 00 00 41 89 ca 74 14 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 75 c3 0f 1f 40 00 55 48 83 ec 30 44 89 4c 24
[   78.621291] RSP: 002b:00007ffff6bdf478 EFLAGS: 00000202 ORIG_RAX: 000000000000002c
[   78.622205] RAX: ffffffffffffffda RBX: 000055c538159340 RCX: 00007fed3de99a73
[   78.623056] RDX: 00000000000007d8 RSI: 000055c53815f3c0 RDI: 0000000000000003
[   78.623908] RBP: 000055c53815f3c0 R08: 000055c53815b5c0 R09: 0000000000000010
[   78.624765] R10: 0000000000000000 R11: 0000000000000202 R12: 00000000000007d8
[   78.625619] R13: 00007ffff6be0b60 R14: 0000001d00000001 R15: 000055c53815c680
[   78.626480]  </TASK>
[   78.626773] ==================================================================
[   78.627656] Disabling lock debugging due to kernel taint
[   78.628305] BUG: kernel NULL pointer dereference, address: 0000000000000108
[   78.629136] #PF: supervisor read access in kernel mode
[   78.629766] #PF: error_code(0x0000) - not-present page
[   78.630402] PGD 0 P4D 0
[   78.630739] Oops: 0000 [#1] PREEMPT DEBUG_PAGEALLOC KASAN
[   78.631398] CPU: 0 PID: 493 Comm: ping Tainted: G    B              6.9.0-rc2-00697-g489ca863e24f-dirty #11
[   78.632548] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   78.633649] RIP: 0010:iptfs_output_collect+0x263/0x57b
[   78.634283] Code: 73 70 0f 84 25 01 00 00 45 39 f4 0f 83 1c 01 00 00 48 8d 7b 10 e8 27 37 62 ff 4c 8b 73 10 49 8d be 08 01 00 00 e8 17 37 62 ff <4d> 8b b6 08 01 00 00 49 8d be b0 01 00 00 e8 04 37 62 ff 49 8b 86
[   78.636444] RSP: 0018:ffffc90000d679c8 EFLAGS: 00010296
[   78.637076] RAX: 0000000000000001 RBX: ffff888110ffbc80 RCX: fffffbfff07623ad
[   78.637923] RDX: fffffbfff07623ad RSI: fffffbfff07623ad RDI: ffffffff83b11d60
[   78.638792] RBP: ffff88810e3a1400 R08: 0000000000000008 R09: 0000000000000001
[   78.639645] R10: ffffffff83b11d67 R11: fffffbfff07623ac R12: 00000000000005a2
[   78.640498] R13: 0000000000000000 R14: 0000000000000000 R15: ffff88810e9a3401
[   78.641359] FS:  00007fed3dbddc40(0000) GS:ffffffff82cb2000(0000) knlGS:0000000000000000
[   78.642324] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   78.643022] CR2: 0000000000000108 CR3: 0000000110e84000 CR4: 0000000000350ef0
[   78.643882] Call Trace:
[   78.644204]  <TASK>
[   78.644487]  ? __die_body+0x1a/0x56
[   78.644929]  ? page_fault_oops+0x45f/0x4cd
[   78.645441]  ? dump_pagetable+0x1db/0x1db
[   78.645942]  ? vprintk_emit+0x163/0x171
[   78.646425]  ? iptfs_output_collect+0x263/0x57b
[   78.646986]  ? _printk+0xb2/0xe1
[   78.647401]  ? find_first_fitting_seq+0x193/0x193
[   78.647982]  ? iptfs_output_collect+0x263/0x57b
[   78.648541]  ? do_user_addr_fault+0x14f/0x56c
[   78.649084]  ? exc_page_fault+0xa5/0xbe
[   78.649566]  ? asm_exc_page_fault+0x22/0x30
[   78.650100]  ? iptfs_output_collect+0x263/0x57b
[   78.650660]  ? iptfs_output_collect+0x263/0x57b
[   78.651221]  ip_send_skb+0x25/0x57
[   78.651652]  raw_sendmsg+0xee8/0x1011
[   78.652113]  ? native_flush_tlb_one_user+0xd/0xe5
[   78.652693]  ? raw_hash_sk+0x21b/0x21b
[   78.653166]  ? kernel_init_pages+0x42/0x51
[   78.653683]  ? prep_new_page+0x44/0x51
[   78.654160]  ? get_page_from_freelist+0x72b/0x915
[   78.654739]  ? signal_pending_state+0x77/0x77
[   78.655284]  ? __might_resched+0x8a/0x240
[   78.655784]  ? __might_sleep+0x25/0xa0
[   78.656255]  ? first_zones_zonelist+0x2c/0x43
[   78.656798]  ? __rcu_read_lock+0x2d/0x3a
[   78.657289]  ? __pte_offset_map+0x32/0xa4
[   78.657788]  ? __might_resched+0x8a/0x240
[   78.658291]  ? __might_sleep+0x25/0xa0
[   78.658763]  ? inet_send_prepare+0x54/0x54
[   78.659272]  ? sock_sendmsg_nosec+0x42/0x6c
[   78.659791]  sock_sendmsg_nosec+0x42/0x6c
[   78.660293]  __sys_sendto+0x15d/0x1cc
[   78.660755]  ? __x64_sys_getpeername+0x44/0x44
[   78.661304]  ? __handle_mm_fault+0x679/0xae4
[   78.661838]  ? find_vma+0x6b/0x8b
[   78.662272]  ? find_vma_intersection+0x8a/0x8a
[   78.662828]  ? __handle_irq_event_percpu+0x180/0x197
[   78.663436]  ? handle_mm_fault+0x38/0x154
[   78.663935]  ? handle_mm_fault+0xeb/0x154
[   78.664435]  ? preempt_latency_start+0x29/0x34
[   78.664987]  ? preempt_count_sub+0x14/0xb3
[   78.665498]  ? up_read+0x4b/0x5c
[   78.665911]  __x64_sys_sendto+0x76/0x82
[   78.666398]  do_syscall_64+0x6b/0xd7
[   78.666849]  entry_SYSCALL_64_after_hwframe+0x46/0x4e
[   78.667466] RIP: 0033:0x7fed3de99a73
[   78.667918] Code: 8b 15 a9 83 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 80 3d 71 0b 0d 00 00 41 89 ca 74 14 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 75 c3 0f 1f 40 00 55 48 83 ec 30 44 89 4c 24
[   78.670097] RSP: 002b:00007ffff6bdf478 EFLAGS: 00000202 ORIG_RAX: 000000000000002c
[   78.671002] RAX: ffffffffffffffda RBX: 000055c538159340 RCX: 00007fed3de99a73
[   78.671858] RDX: 00000000000007d8 RSI: 000055c53815f3c0 RDI: 0000000000000003
[   78.672708] RBP: 000055c53815f3c0 R08: 000055c53815b5c0 R09: 0000000000000010
[   78.673564] R10: 0000000000000000 R11: 0000000000000202 R12: 00000000000007d8
[   78.674430] R13: 00007ffff6be0b60 R14: 0000001d00000001 R15: 000055c53815c680
[   78.675287]  </TASK>
[   78.675580] Modules linked in:
[   78.675975] CR2: 0000000000000108
[   78.676396] ---[ end trace 0000000000000000 ]---
[   78.676966] RIP: 0010:iptfs_output_collect+0x263/0x57b
[   78.677596] Code: 73 70 0f 84 25 01 00 00 45 39 f4 0f 83 1c 01 00 00 48 8d 7b 10 e8 27 37 62 ff 4c 8b 73 10 49 8d be 08 01 00 00 e8 17 37 62 ff <4d> 8b b6 08 01 00 00 49 8d be b0 01 00 00 e8 04 37 62 ff 49 8b 86
[   78.679768] RSP: 0018:ffffc90000d679c8 EFLAGS: 00010296
[   78.680410] RAX: 0000000000000001 RBX: ffff888110ffbc80 RCX: fffffbfff07623ad
[   78.681264] RDX: fffffbfff07623ad RSI: fffffbfff07623ad RDI: ffffffff83b11d60
[   78.682136] RBP: ffff88810e3a1400 R08: 0000000000000008 R09: 0000000000000001
[   78.682997] R10: ffffffff83b11d67 R11: fffffbfff07623ac R12: 00000000000005a2
[   78.683853] R13: 0000000000000000 R14: 0000000000000000 R15: ffff88810e9a3401
[   78.684710] FS:  00007fed3dbddc40(0000) GS:ffffffff82cb2000(0000) knlGS:0000000000000000
[   78.685675] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   78.686387] CR2: 0000000000000108 CR3: 0000000110e84000 CR4: 0000000000350ef0
[   78.687246] Kernel panic - not syncing: Fatal exception in interrupt
[   78.688014] Kernel Offset: disabled
[   78.688460] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

ping -s 2000  -n -q -W 1 -c 2 -I 192.0.3.254  192.0.2.254

(gdb) list *iptfs_output_collect+0x263
0xffffffff81d5076f is in iptfs_output_collect (./include/net/net_namespace.h:383).
378	}
379
380	static inline struct net *read_pnet(const possible_net_t *pnet)
381	{
382	#ifdef CONFIG_NET_NS
383		return rcu_dereference_protected(pnet->net, true);
384	#else
385		return &init_net;
386	#endif
387	}

I suspect actual crash is from the line 1756 instead,
(gdb) list *iptfs_output_collect+0x256
0xffffffff81d50762 is in iptfs_output_collect (net/xfrm/xfrm_iptfs.c:1756).
1751			return 0;
1752
1753		/* We only send ICMP too big if the user has configured us as
1754		 * dont-fragment.
1755		 */
1756		XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMOUTERROR);
1757
1758		if (sk) {
1759			xfrm_local_error(skb, pmtu);
1760		} else if (ip_hdr(skb)->version == 4) {

Later I ran with gdb iptfs_is_too_big which is called twice and second time 
it crash.
Here is gdb bt. Just before the crash

#0  iptfs_is_too_big (pmtu=1442, skb=0xffff88810dbea3c0, sk=0xffff888104d4ed40) at net/xfrm/xfrm_iptfs.c:1756
#1  iptfs_output_collect (net=<optimized out>, sk=0xffff888104d4ed40, skb=0xffff88810dbea3c0) at net/xfrm/xfrm_iptfs.c:1847
#2  0xffffffff81c8a3cb in ip_send_skb (net=0xffffffff83e57f20 <init_net>, skb=0xffff88810dbea3c0)
    at net/ipv4/ip_output.c:1492
#3  0xffffffff81c8a439 in ip_push_pending_frames (sk=sk@entry=0xffff888104d4ed40, fl4=fl4@entry=0xffffc90000e3fb90)
    at net/ipv4/ip_output.c:1512
#4  0xffffffff81ccf3cf in raw_sendmsg (sk=0xffff888104d4ed40, msg=0xffffc90000e3fd80, len=<optimized out>)
    at net/ipv4/raw.c:654
#5  0xffffffff81b096ea in sock_sendmsg_nosec (sock=sock@entry=0xffff888115136040, msg=msg@entry=0xffffc90000e3fd80)
    at net/socket.c:730
#6  0xffffffff81b0c327 in __sock_sendmsg (msg=0xffffc90000e3fd80, sock=0xffff888115136040) at net/socket.c:745
#7  __sys_sendto (fd=<optimized out>, buff=buff@entry=0x558edefb73c0, len=len@entry=2008, flags=flags@entry=0,
    addr=addr@entry=0x558edefb35c0, addr_len=addr_len@entry=16) at net/socket.c:2191
#8  0xffffffff81b0c40c in __do_sys_sendto (addr_len=16, addr=0x558edefb35c0, flags=0, len=2008, buff=0x558edefb73c0,
    fd=<optimized out>) at net/socket.c:2203
#9  __se_sys_sendto (addr_len=16, addr=94072114722240, flags=0, len=2008, buff=94072114738112, fd=<optimized out>)
    at net/socket.c:2199

gdb) list
1751			return 0;
1752
1753		/* We only send ICMP too big if the user has configured us as
1754		 * dont-fragment.
1755		 */
1756		XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMOUTERROR);
1757
1758		if (sk) {
1759			xfrm_local_error(skb, pmtu);
1760		} else if (ip_hdr(skb)->version == 4) {

-antony