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

Conflicts:
net/xfrm/xfrm_policy.c

Steffen Klassert says:

====================
This pull request has a merge conflict between commits be7928d20bab
("net: xfrm: xfrm_policy: fix inline not at beginning of declaration") and
da7c224b1baa ("net: xfrm: xfrm_policy: silence compiler warning") from
the net-next tree and commit 2f3ea9a95c58 ("xfrm: checkpatch erros with
inline keyword position") from the ipsec-next tree.

The version from net-next can be used, like it is done in linux-next.

1) Checkpatch cleanups, from Weilong Chen.

2) Fix lockdep complaints when pktgen is used with IPsec,
from Fan Du.

3) Update pktgen to allow any combination of IPsec transport/tunnel mode
and AH/ESP/IPcomp type, from Fan Du.

4) Make pktgen_dst_metrics static, Fengguang Wu.

5) Compile fix for pktgen when CONFIG_XFRM is not set,
from Fan Du.
====================

Signed-off-by: David S. Miller <[e-mail]>

Documentation/networking/pktgen.txt

···
                               MPLS_RND, VID_RND, SVID_RND
                               QUEUE_MAP_RND # queue map random
                               QUEUE_MAP_CPU # queue map mirrors smp_processor_id()
+                              IPSEC # Make IPsec encapsulation for packet
 
+ pgset spi SPI_VALUE     Set specific SA used to transform packet.
 
  pgset "udp_src_min 9"   set UDP source port min, If < udp_src_max, then
                          cycle through the port range.
···
 /proc/irq/XX/smp_affinity so the TX-interrupts gets bound to the same CPU.
 as this reduces cache bouncing when freeing skb's.
 
+Enable IPsec
+============
+Default IPsec transformation with ESP encapsulation plus Transport mode
+could be enabled by simply setting:
+
+pgset "flag IPSEC"
+pgset "flows 1"
+
+To avoid breaking existing testbed scripts for using AH type and tunnel mode,
+user could use "pgset spi SPI_VALUE" to specify which formal of transformation
+to employ.
+
 
 Current commands and configuration options
 ==========================================
···
   UDPDST_RND
   MACSRC_RND
   MACDST_RND
+  IPSEC
 
 dst_min
 dst_max

include/net/xfrm.h

···
 				       xfrm_address_t *saddr,
 				       unsigned short family,
 				       u8 mode, u8 proto, u32 reqid);
+struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
+					      unsigned short family);
 int xfrm_state_check_expire(struct xfrm_state *x);
 void xfrm_state_insert(struct xfrm_state *x);
 int xfrm_state_add(struct xfrm_state *x);

net/core/pktgen.c

···
 #ifdef CONFIG_XFRM
 	__u8	ipsmode;		/* IPSEC mode (config) */
 	__u8	ipsproto;		/* IPSEC type (config) */
+	__u32	spi;
+	struct dst_entry dst;
+	struct dst_ops dstops;
 #endif
 	char result[512];
 };
···
 	}
 
 #ifdef CONFIG_XFRM
-	if (pkt_dev->flags & F_IPSEC_ON)
+	if (pkt_dev->flags & F_IPSEC_ON) {
 		seq_printf(seq,  "IPSEC  ");
+		if (pkt_dev->spi)
+			seq_printf(seq, "spi:%u", pkt_dev->spi);
+	}
 #endif
 
 	if (pkt_dev->flags & F_MACSRC_RND)
···
 		sprintf(pg_result, "OK: flows=%u", pkt_dev->cflows);
 		return count;
 	}
+#ifdef CONFIG_XFRM
+	if (!strcmp(name, "spi")) {
+		len = num_arg(&user_buffer[i], 10, &value);
+		if (len < 0)
+			return len;
 
+		i += len;
+		pkt_dev->spi = value;
+		sprintf(pg_result, "OK: spi=%u", pkt_dev->spi);
+		return count;
+	}
+#endif
 	if (!strcmp(name, "flowlen")) {
 		len = num_arg(&user_buffer[i], 10, &value);
 		if (len < 0)
···
 	struct xfrm_state *x = pkt_dev->flows[flow].x;
 	struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id);
 	if (!x) {
-		/*slow path: we dont already have xfrm_state*/
-		x = xfrm_stateonly_find(pn->net, DUMMY_MARK,
-					(xfrm_address_t *)&pkt_dev->cur_daddr,
-					(xfrm_address_t *)&pkt_dev->cur_saddr,
-					AF_INET,
-					pkt_dev->ipsmode,
-					pkt_dev->ipsproto, 0);
+
+		if (pkt_dev->spi) {
+			/* We need as quick as possible to find the right SA
+			 * Searching with minimum criteria to archieve this.
+			 */
+			x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET);
+		} else {
+			/* slow path: we dont already have xfrm_state */
+			x = xfrm_stateonly_find(pn->net, DUMMY_MARK,
+						(xfrm_address_t *)&pkt_dev->cur_daddr,
+						(xfrm_address_t *)&pkt_dev->cur_saddr,
+						AF_INET,
+						pkt_dev->ipsmode,
+						pkt_dev->ipsproto, 0);
+		}
 		if (x) {
 			pkt_dev->flows[flow].x = x;
 			set_pkt_overhead(pkt_dev);
···
 
 
 #ifdef CONFIG_XFRM
+static u32 pktgen_dst_metrics[RTAX_MAX + 1] = {
+
+	[RTAX_HOPLIMIT] = 0x5, /* Set a static hoplimit */
+};
+
 static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
 {
 	struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x;
 	int err = 0;
+	struct net *net = dev_net(pkt_dev->odev);
 
 	if (!x)
 		return 0;
 	/* XXX: we dont support tunnel mode for now until
 	 * we resolve the dst issue */
-	if (x->props.mode != XFRM_MODE_TRANSPORT)
+	if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0))
 		return 0;
 
-	spin_lock(&x->lock);
+	/* But when user specify an valid SPI, transformation
+	 * supports both transport/tunnel mode + ESP/AH type.
+	 */
+	if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0))
+		skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF;
 
+	rcu_read_lock_bh();
 	err = x->outer_mode->output(x, skb);
-	if (err)
+	rcu_read_unlock_bh();
+	if (err) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
 		goto error;
+	}
 	err = x->type->output(x, skb);
-	if (err)
+	if (err) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
 		goto error;
-
+	}
+	spin_lock_bh(&x->lock);
 	x->curlft.bytes += skb->len;
 	x->curlft.packets++;
+	spin_unlock_bh(&x->lock);
 error:
-	spin_unlock(&x->lock);
 	return err;
 }
 
···
 #ifdef CONFIG_XFRM
 	pkt_dev->ipsmode = XFRM_MODE_TRANSPORT;
 	pkt_dev->ipsproto = IPPROTO_ESP;
+
+	/* xfrm tunnel mode needs additional dst to extract outter
+	 * ip header protocol/ttl/id field, here creat a phony one.
+	 * instead of looking for a valid rt, which definitely hurting
+	 * performance under such circumstance.
+	 */
+	pkt_dev->dstops.family = AF_INET;
+	pkt_dev->dst.dev = pkt_dev->odev;
+	dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false);
+	pkt_dev->dst.child = &pkt_dev->dst;
+	pkt_dev->dst.ops = &pkt_dev->dstops;
 #endif
 
 	return add_dev_to_thread(t, pkt_dev);

net/xfrm/xfrm_input.c

···
 	case IPPROTO_COMP:
 		if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr)))
 			return -EINVAL;
-		*spi = htonl(ntohs(*(__be16*)(skb_transport_header(skb) + 2)));
+		*spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2)));
 		*seq = 0;
 		return 0;
 	default:
···
 	if (!pskb_may_pull(skb, hlen))
 		return -EINVAL;
 
-	*spi = *(__be32*)(skb_transport_header(skb) + offset);
-	*seq = *(__be32*)(skb_transport_header(skb) + offset_seq);
+	*spi = *(__be32 *)(skb_transport_header(skb) + offset);
+	*seq = *(__be32 *)(skb_transport_header(skb) + offset_seq);
 	return 0;
 }
 

net/xfrm/xfrm_policy.c

···
 
 static void xfrm_policy_timer(unsigned long data)
 {
-	struct xfrm_policy *xp = (struct xfrm_policy*)data;
+	struct xfrm_policy *xp = (struct xfrm_policy *)data;
 	unsigned long now = get_seconds();
 	long next = LONG_MAX;
 	int warn = 0;
···
 	xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family);
 	xfrm_address_t tmp;
 
-	for (nx=0, i = 0; i < policy->xfrm_nr; i++) {
+	for (nx = 0, i = 0; i < policy->xfrm_nr; i++) {
 		struct xfrm_state *x;
 		xfrm_address_t *remote = daddr;
 		xfrm_address_t *local  = saddr;
···
 			error = (x->km.state == XFRM_STATE_ERROR ?
 				 -EINVAL : -EAGAIN);
 			xfrm_state_put(x);
-		}
-		else if (error == -ESRCH)
+		} else if (error == -ESRCH) {
 			error = -EAGAIN;
+		}
 
 		if (!tmpl->optional)
 			goto fail;
···
 	return nx;
 
 fail:
-	for (nx--; nx>=0; nx--)
+	for (nx--; nx >= 0; nx--)
 		xfrm_state_put(xfrm[nx]);
 	return error;
 }
···
 	return cnx;
 
  fail:
-	for (cnx--; cnx>=0; cnx--)
+	for (cnx--; cnx >= 0; cnx--)
 		xfrm_state_put(tpp[cnx]);
 	return error;
 
···
 				xfrm_pols_put(pols, *num_pols);
 				return PTR_ERR(pols[1]);
 			}
-			(*num_pols) ++;
+			(*num_pols)++;
 			(*num_xfrms) += pols[1]->xfrm_nr;
 		}
 	}
···
 	}
 
 	xdst->num_pols = num_pols;
-	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 	xdst->policy_genid = atomic_read(&pols[0]->genid);
 
 	return xdst;
···
 	}
 	xdst->num_pols = num_pols;
 	xdst->num_xfrms = num_xfrms;
-	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 
 	dst_hold(&xdst->u.dst);
 	return &xdst->flo;
···
 
 		num_pols = xdst->num_pols;
 		num_xfrms = xdst->num_xfrms;
-		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols);
+		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols);
 		route = xdst->route;
 	}
 
···
 	if (skb->sp) {
 		int i;
 
-		for (i=skb->sp->len-1; i>=0; i--) {
+		for (i = skb->sp->len-1; i >= 0; i--) {
 			struct xfrm_state *x = skb->sp->xvec[i];
 			if (!xfrm_selector_match(&x->sel, &fl, family)) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
···
 	pol->curlft.use_time = get_seconds();
 
 	pols[0] = pol;
-	npols ++;
+	npols++;
 #ifdef CONFIG_XFRM_SUB_POLICY
 	if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
 		pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN,
···
 				return 0;
 			}
 			pols[1]->curlft.use_time = get_seconds();
-			npols ++;
+			npols++;
 		}
 	}
 #endif
···
 		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
 				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
 
-	switch(sel->family) {
+	switch (sel->family) {
 	case AF_INET:
 		audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4);
 		if (sel->prefixlen_s != 32)
···
 	return false;
 }
 
-static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel,
-						     u8 dir, u8 type, struct net *net)
+static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
+						    u8 dir, u8 type, struct net *net)
 {
 	struct xfrm_policy *pol, *ret = NULL;
 	struct hlist_head *chain;

net/xfrm/xfrm_proc.c

···
 {
 	struct net *net = seq->private;
 	int i;
-	for (i=0; xfrm_mib_list[i].name; i++)
+	for (i = 0; xfrm_mib_list[i].name; i++)
 		seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name,
 			   snmp_fold_field((void __percpu **)
 					   net->mib.xfrm_statistics,

net/xfrm/xfrm_state.c

···
 		return secs*HZ;
 }
 
-static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me)
+static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
 	struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
 	struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
···
 	if (warn)
 		km_state_expired(x, 0, 0);
 resched:
-	if (next != LONG_MAX){
+	if (next != LONG_MAX) {
 		tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
 	}
 
···
 	unsigned int h;
 	struct xfrm_state *rx = NULL, *x = NULL;
 
-	spin_lock(&net->xfrm.xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
 	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 		if (x->props.family == family &&
···
 
 	if (rx)
 		xfrm_state_hold(rx);
-	spin_unlock(&net->xfrm.xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 
 	return rx;
 }
 EXPORT_SYMBOL(xfrm_stateonly_find);
+
+struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
+					      unsigned short family)
+{
+	struct xfrm_state *x;
+	struct xfrm_state_walk *w;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	list_for_each_entry(w, &net->xfrm.state_all, all) {
+		x = container_of(w, struct xfrm_state, km);
+		if (x->props.family != family ||
+			x->id.spi != spi)
+			continue;
+
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		xfrm_state_hold(x);
+		return x;
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return NULL;
+}
+EXPORT_SYMBOL(xfrm_state_lookup_byspi);
 
 static void __xfrm_state_insert(struct xfrm_state *x)
 {
···
 }
 EXPORT_SYMBOL(xfrm_migrate_state_find);
 
-struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
-				       struct xfrm_migrate *m)
+struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
+				      struct xfrm_migrate *m)
 {
 	struct xfrm_state *xc;
 	int err;
···
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(0,0), HRTIMER_MODE_REL);
+		tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL);
 		return -EINVAL;
 	}
 
···
 		x->id.spi = minspi;
 	} else {
 		u32 spi = 0;
-		for (h=0; h<high-low+1; h++) {
+		for (h = 0; h < high-low+1; h++) {
 			spi = low + net_random()%(high-low+1);
 			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
 			if (x0 == NULL) {
···
 
 static void xfrm_replay_timer_handler(unsigned long data)
 {
-	struct xfrm_state *x = (struct xfrm_state*)data;
+	struct xfrm_state *x = (struct xfrm_state *)data;
 
 	spin_lock(&x->lock);
 
···
 		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
 				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
 
-	switch(x->props.family) {
+	switch (x->props.family) {
 	case AF_INET:
 		audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
 				 &x->props.saddr.a4, &x->id.daddr.a4);
···
 		iph6 = ipv6_hdr(skb);
 		audit_log_format(audit_buf,
 				 " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x",
-				 &iph6->saddr,&iph6->daddr,
+				 &iph6->saddr, &iph6->daddr,
 				 iph6->flow_lbl[0] & 0x0f,
 				 iph6->flow_lbl[1],
 				 iph6->flow_lbl[2]);

net/xfrm/xfrm_user.c

···
 		return -EMSGSIZE;
 
 	id = nlmsg_data(nlh);
-	memcpy(&id->sa_id.daddr, &x->id.daddr,sizeof(x->id.daddr));
+	memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr));
 	id->sa_id.spi = x->id.spi;
 	id->sa_id.family = x->props.family;
 	id->sa_id.proto = x->id.proto;
-	memcpy(&id->saddr, &x->props.saddr,sizeof(x->props.saddr));
+	memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr));
 	id->reqid = x->props.reqid;
 	id->flags = c->data.aevent;
 
···
 	struct net *net = sock_net(skb->sk);
 	struct xfrm_state *x;
 	struct km_event c;
-	int err = - EINVAL;
+	int err = -EINVAL;
 	u32 mark = 0;
 	struct xfrm_mark m;
 	struct xfrm_aevent_id *p = nlmsg_data(nlh);