Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2019-04-30

1) A lot of work to remove indirections from the xfrm code.
   From Florian Westphal.

2) Support ESP offload in combination with gso partial.
   From Boris Pismenny.

3) Remove some duplicated code from vti4.
   From Jeremy Sowden.

Please note that there is merge conflict

between commit:

8742dc8 ("xfrm4: Fix uninitialized memory read in _decode_session4")

from the ipsec tree and commit:

c53ac41 ("xfrm: remove decode_session indirection from afinfo_policy")

from the ipsec-next tree. The merge conflict will appear
when those trees get merged during the merge window.
The conflict can be solved as it is done in linux-next:

https://lkml.org/lkml/2019/4/25/1207

Please pull or let me know if there are problems.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

include/net/xfrm.h

@@ -132,6 +132,17 @@ struct xfrm_state_offload {
 	u8			flags;
 };
 
+struct xfrm_mode {
+	u8 encap;
+	u8 family;
+	u8 flags;
+};
+
+/* Flags for xfrm_mode. */
+enum {
+	XFRM_MODE_FLAG_TUNNEL = 1,
+};
+
 /* Full description of state of transformer. */
 struct xfrm_state {
 	possible_net_t		xs_net;
@@ -234,9 +245,9 @@ struct xfrm_state {
 	/* Reference to data common to all the instances of this
 	 * transformer. */
 	const struct xfrm_type	*type;
-	struct xfrm_mode	*inner_mode;
-	struct xfrm_mode	*inner_mode_iaf;
-	struct xfrm_mode	*outer_mode;
+	struct xfrm_mode	inner_mode;
+	struct xfrm_mode	inner_mode_iaf;
+	struct xfrm_mode	outer_mode;
 
 	const struct xfrm_type_offload	*type_offload;
 
@@ -315,13 +326,6 @@ struct xfrm_policy_afinfo {
 					     xfrm_address_t *saddr,
 					     xfrm_address_t *daddr,
 					     u32 mark);
-	void			(*decode_session)(struct sk_buff *skb,
-						  struct flowi *fl,
-						  int reverse);
-	int			(*get_tos)(const struct flowi *fl);
-	int			(*init_path)(struct xfrm_dst *path,
-					     struct dst_entry *dst,
-					     int nfheader_len);
 	int			(*fill_dst)(struct xfrm_dst *xdst,
 					    struct net_device *dev,
 					    const struct flowi *fl);
@@ -347,7 +351,6 @@ struct xfrm_state_afinfo {
 	struct module			*owner;
 	const struct xfrm_type		*type_map[IPPROTO_MAX];
 	const struct xfrm_type_offload	*type_offload_map[IPPROTO_MAX];
-	struct xfrm_mode		*mode_map[XFRM_MODE_MAX];
 
 	int			(*init_flags)(struct xfrm_state *x);
 	void			(*init_tempsel)(struct xfrm_selector *sel,
@@ -422,78 +425,6 @@ struct xfrm_type_offload {
 int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
-struct xfrm_mode {
-	/*
-	 * Remove encapsulation header.
-	 *
-	 * The IP header will be moved over the top of the encapsulation
-	 * header.
-	 *
-	 * On entry, the transport header shall point to where the IP header
-	 * should be and the network header shall be set to where the IP
-	 * header currently is.  skb->data shall point to the start of the
-	 * payload.
-	 */
-	int (*input2)(struct xfrm_state *x, struct sk_buff *skb);
-
-	/*
-	 * This is the actual input entry point.
-	 *
-	 * For transport mode and equivalent this would be identical to
-	 * input2 (which does not need to be set).  While tunnel mode
-	 * and equivalent would set this to the tunnel encapsulation function
-	 * xfrm4_prepare_input that would in turn call input2.
-	 */
-	int (*input)(struct xfrm_state *x, struct sk_buff *skb);
-
-	/*
-	 * Add encapsulation header.
-	 *
-	 * On exit, the transport header will be set to the start of the
-	 * encapsulation header to be filled in by x->type->output and
-	 * the mac header will be set to the nextheader (protocol for
-	 * IPv4) field of the extension header directly preceding the
-	 * encapsulation header, or in its absence, that of the top IP
-	 * header.  The value of the network header will always point
-	 * to the top IP header while skb->data will point to the payload.
-	 */
-	int (*output2)(struct xfrm_state *x,struct sk_buff *skb);
-
-	/*
-	 * This is the actual output entry point.
-	 *
-	 * For transport mode and equivalent this would be identical to
-	 * output2 (which does not need to be set).  While tunnel mode
-	 * and equivalent would set this to a tunnel encapsulation function
-	 * (xfrm4_prepare_output or xfrm6_prepare_output) that would in turn
-	 * call output2.
-	 */
-	int (*output)(struct xfrm_state *x, struct sk_buff *skb);
-
-	/*
-	 * Adjust pointers into the packet and do GSO segmentation.
-	 */
-	struct sk_buff *(*gso_segment)(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features);
-
-	/*
-	 * Adjust pointers into the packet when IPsec is done at layer2.
-	 */
-	void (*xmit)(struct xfrm_state *x, struct sk_buff *skb);
-
-	struct xfrm_state_afinfo *afinfo;
-	struct module *owner;
-	unsigned int encap;
-	int flags;
-};
-
-/* Flags for xfrm_mode. */
-enum {
-	XFRM_MODE_FLAG_TUNNEL = 1,
-};
-
-int xfrm_register_mode(struct xfrm_mode *mode, int family);
-int xfrm_unregister_mode(struct xfrm_mode *mode, int family);
-
 static inline int xfrm_af2proto(unsigned int family)
 {
 	switch(family) {
@@ -506,13 +437,13 @@ static inline int xfrm_af2proto(unsigned int family)
 	}
 }
 
-static inline struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto)
+static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto)
 {
 	if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) ||
 	    (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6))
-		return x->inner_mode;
+		return &x->inner_mode;
 	else
-		return x->inner_mode_iaf;
+		return &x->inner_mode_iaf;
 }
 
 struct xfrm_tmpl {
@@ -1605,15 +1536,18 @@ int xfrm_init_replay(struct xfrm_state *x);
 int xfrm_state_mtu(struct xfrm_state *x, int mtu);
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
 int xfrm_init_state(struct xfrm_state *x);
-int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
 int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
 int xfrm_trans_queue(struct sk_buff *skb,
 		     int (*finish)(struct net *, struct sock *,
 				   struct sk_buff *));
 int xfrm_output_resume(struct sk_buff *skb, int err);
 int xfrm_output(struct sock *sk, struct sk_buff *skb);
-int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
+
+#if IS_ENABLED(CONFIG_NET_PKTGEN)
+int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb);
+#endif
+
 void xfrm_local_error(struct sk_buff *skb, int mtu);
 int xfrm4_extract_header(struct sk_buff *skb);
 int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb);
@@ -1632,10 +1566,8 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
 }
 
 int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
-int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb);
-int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
 int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol);
 int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol);
 int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
@@ -1651,15 +1583,13 @@ int xfrm6_rcv(struct sk_buff *skb);
 int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
 		     xfrm_address_t *saddr, u8 proto);
 void xfrm6_local_error(struct sk_buff *skb, u32 mtu);
-int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
 int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol);
 int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol);
 int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family);
 int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family);
 __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
 __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
 int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb);
-int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb);
 int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
@@ -2051,7 +1981,7 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
 			tunnel = true;
 		break;
 	}
-	if (tunnel && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL))
+	if (tunnel && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL))
 		return -EINVAL;
 
 	return 0;

net/core/pktgen.c

@@ -2521,7 +2521,7 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
 		skb->_skb_refdst = (unsigned long)&pkt_dev->xdst.u.dst | SKB_DST_NOREF;
 
 	rcu_read_lock_bh();
-	err = x->outer_mode->output(x, skb);
+	err = pktgen_xfrm_outer_mode_output(x, skb);
 	rcu_read_unlock_bh();
 	if (err) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);

net/ipv4/Kconfig

@@ -304,7 +304,7 @@ config NET_IPVTI
 	tristate "Virtual (secure) IP: tunneling"
 	select INET_TUNNEL
 	select NET_IP_TUNNEL
-	depends on INET_XFRM_MODE_TUNNEL
+	select XFRM
 	---help---
 	  Tunneling means encapsulating data of one protocol type within
 	  another protocol and sending it over a channel that understands the
@@ -396,33 +396,6 @@ config INET_TUNNEL
 	tristate
 	default n
 
-config INET_XFRM_MODE_TRANSPORT
-	tristate "IP: IPsec transport mode"
-	default y
-	select XFRM
-	---help---
-	  Support for IPsec transport mode.
-
-	  If unsure, say Y.
-
-config INET_XFRM_MODE_TUNNEL
-	tristate "IP: IPsec tunnel mode"
-	default y
-	select XFRM
-	---help---
-	  Support for IPsec tunnel mode.
-
-	  If unsure, say Y.
-
-config INET_XFRM_MODE_BEET
-	tristate "IP: IPsec BEET mode"
-	default y
-	select XFRM
-	---help---
-	  Support for IPsec BEET mode.
-
-	  If unsure, say Y.
-
 config INET_DIAG
 	tristate "INET: socket monitoring interface"
 	default y

net/ipv4/Makefile

@@ -37,10 +37,7 @@ obj-$(CONFIG_INET_ESP) += esp4.o
 obj-$(CONFIG_INET_ESP_OFFLOAD) += esp4_offload.o
 obj-$(CONFIG_INET_IPCOMP) += ipcomp.o
 obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o
-obj-$(CONFIG_INET_XFRM_MODE_BEET) += xfrm4_mode_beet.o
 obj-$(CONFIG_INET_TUNNEL) += tunnel4.o
-obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o
-obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o
 obj-$(CONFIG_IP_PNP) += ipconfig.o
 obj-$(CONFIG_NETFILTER)	+= netfilter.o netfilter/
 obj-$(CONFIG_INET_DIAG) += inet_diag.o

net/ipv4/esp4_offload.c

@@ -107,6 +107,44 @@ static void esp4_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
 	xo->proto = proto;
 }
 
+static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x,
+						struct sk_buff *skb,
+						netdev_features_t features)
+{
+	__skb_push(skb, skb->mac_len);
+	return skb_mac_gso_segment(skb, features);
+}
+
+static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
+						   struct sk_buff *skb,
+						   netdev_features_t features)
+{
+	const struct net_offload *ops;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb->transport_header += x->props.header_len;
+	ops = rcu_dereference(inet_offloads[xo->proto]);
+	if (likely(ops && ops->callbacks.gso_segment))
+		segs = ops->callbacks.gso_segment(skb, features);
+
+	return segs;
+}
+
+static struct sk_buff *xfrm4_outer_mode_gso_segment(struct xfrm_state *x,
+						    struct sk_buff *skb,
+						    netdev_features_t features)
+{
+	switch (x->outer_mode.encap) {
+	case XFRM_MODE_TUNNEL:
+		return xfrm4_tunnel_gso_segment(x, skb, features);
+	case XFRM_MODE_TRANSPORT:
+		return xfrm4_transport_gso_segment(x, skb, features);
+	}
+
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 				        netdev_features_t features)
 {
@@ -138,14 +176,16 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 
 	skb->encap_hdr_csum = 1;
 
-	if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev)
+	if ((!(skb->dev->gso_partial_features & NETIF_F_HW_ESP) &&
+	     !(features & NETIF_F_HW_ESP)) || x->xso.dev != skb->dev)
 		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
-	else if (!(features & NETIF_F_HW_ESP_TX_CSUM))
+	else if (!(features & NETIF_F_HW_ESP_TX_CSUM) &&
+		 !(skb->dev->gso_partial_features & NETIF_F_HW_ESP_TX_CSUM))
 		esp_features = features & ~NETIF_F_CSUM_MASK;
 
 	xo->flags |= XFRM_GSO_SEGMENT;
 
-	return x->outer_mode->gso_segment(x, skb, esp_features);
+	return xfrm4_outer_mode_gso_segment(x, skb, esp_features);
 }
 
 static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb)
@@ -181,7 +221,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 	if (!xo)
 		return -EINVAL;
 
-	if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) {
+	if ((!(features & NETIF_F_HW_ESP) &&
+	     !(skb->dev->gso_partial_features & NETIF_F_HW_ESP)) ||
+	    x->xso.dev != skb->dev) {
 		xo->flags |= CRYPTO_FALLBACK;
 		hw_offload = false;
 	}