Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-05-17

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Provide a new BPF helper for doing a FIB and neighbor lookup
   in the kernel tables from an XDP or tc BPF program. The helper
   provides a fast-path for forwarding packets. The API supports
   IPv4, IPv6 and MPLS protocols, but currently IPv4 and IPv6 are
   implemented in this initial work, from David (Ahern).

2) Just a tiny diff but huge feature enabled for nfp driver by
   extending the BPF offload beyond a pure host processing offload.
   Offloaded XDP programs are allowed to set the RX queue index and
   thus opening the door for defining a fully programmable RSS/n-tuple
   filter replacement. Once BPF decided on a queue already, the device
   data-path will skip the conventional RSS processing completely,
   from Jakub.

3) The original sockmap implementation was array based similar to
   devmap. However unlike devmap where an ifindex has a 1:1 mapping
   into the map there are use cases with sockets that need to be
   referenced using longer keys. Hence, sockhash map is added reusing
   as much of the sockmap code as possible, from John.

4) Introduce BTF ID. The ID is allocatd through an IDR similar as
   with BPF maps and progs. It also makes BTF accessible to user
   space via BPF_BTF_GET_FD_BY_ID and adds exposure of the BTF data
   through BPF_OBJ_GET_INFO_BY_FD, from Martin.

5) Enable BPF stackmap with build_id also in NMI context. Due to the
   up_read() of current->mm->mmap_sem build_id cannot be parsed.
   This work defers the up_read() via a per-cpu irq_work so that
   at least limited support can be enabled, from Song.

6) Various BPF JIT follow-up cleanups and fixups after the LD_ABS/LD_IND
   JIT conversion as well as implementation of an optimized 32/64 bit
   immediate load in the arm64 JIT that allows to reduce the number of
   emitted instructions; in case of tested real-world programs they
   were shrinking by three percent, from Daniel.

7) Add ifindex parameter to the libbpf loader in order to enable
   BPF offload support. Right now only iproute2 can load offloaded
   BPF and this will also enable libbpf for direct integration into
   other applications, from David (Beckett).

8) Convert the plain text documentation under Documentation/bpf/ into
   RST format since this is the appropriate standard the kernel is
   moving to for all documentation. Also add an overview README.rst,
   from Jesper.

9) Add __printf verification attribute to the bpf_verifier_vlog()
   helper. Though it uses va_list we can still allow gcc to check
   the format string, from Mathieu.

10) Fix a bash reference in the BPF selftest's Makefile. The '|& ...'
    is a bash 4.0+ feature which is not guaranteed to be available
    when calling out to shell, therefore use a more portable variant,
    from Joe.

11) Fix a 64 bit division in xdp_umem_reg() by using div_u64()
    instead of relying on the gcc built-in, from Björn.

12) Fix a sock hashmap kmalloc warning reported by syzbot when an
    overly large key size is used in hashmap then causing overflows
    in htab->elem_size. Reject bogus attr->key_size early in the
    sock_hash_alloc(), from Yonghong.

13) Ensure in BPF selftests when urandom_read is being linked that
    --build-id is always enabled so that test_stacktrace_build_id[_nmi]
    won't be failing, from Alexei.

14) Add bitsperlong.h as well as errno.h uapi headers into the tools
    header infrastructure which point to one of the arch specific
    uapi headers. This was needed in order to fix a build error on
    some systems for the BPF selftests, from Sirio.

15) Allow for short options to be used in the xdp_monitor BPF sample
    code. And also a bpf.h tools uapi header sync in order to fix a
    selftest build failure. Both from Prashant.

16) More formally clarify the meaning of ID in the direct packet access
    section of the BPF documentation, from Wang.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 210 insertions, 64 deletions

diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 32b564dfd02a..2fe754fd4f5e 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -134,8 +134,39 @@ static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1,
 	return -EAFNOSUPPORT;
 }
 
+static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id)
+{
+	return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table,
+			       int oif, struct flowi6 *fl6, int flags)
+{
+	return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+			 int flags)
+{
+	return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
+				   struct flowi6 *fl6, int oif,
+				   const struct sk_buff *skb, int strict)
+{
+	return f6i;
+}
+
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
-	.ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
+	.ipv6_dst_lookup   = eafnosupport_ipv6_dst_lookup,
+	.fib6_get_table    = eafnosupport_fib6_get_table,
+	.fib6_table_lookup = eafnosupport_fib6_table_lookup,
+	.fib6_lookup       = eafnosupport_fib6_lookup,
+	.fib6_multipath_select = eafnosupport_fib6_multipath_select,
 };
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d0af96e0d109..50de8b0d4f70 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -889,7 +889,11 @@ static struct pernet_operations inet6_net_ops = {
 static const struct ipv6_stub ipv6_stub_impl = {
 	.ipv6_sock_mc_join = ipv6_sock_mc_join,
 	.ipv6_sock_mc_drop = ipv6_sock_mc_drop,
-	.ipv6_dst_lookup = ip6_dst_lookup,
+	.ipv6_dst_lookup   = ip6_dst_lookup,
+	.fib6_get_table	   = fib6_get_table,
+	.fib6_table_lookup = fib6_table_lookup,
+	.fib6_lookup       = fib6_lookup,
+	.fib6_multipath_select = fib6_multipath_select,
 	.udpv6_encap_enable = udpv6_encap_enable,
 	.ndisc_send_na = ndisc_send_na,
 	.nd_tbl	= &nd_tbl,
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 6547fc6491a6..f590446595d8 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -60,6 +60,39 @@ unsigned int fib6_rules_seq_read(struct net *net)
 	return fib_rules_seq_read(net, AF_INET6);
 }
 
+/* called with rcu lock held; no reference taken on fib6_info */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+			      int flags)
+{
+	struct fib6_info *f6i;
+	int err;
+
+	if (net->ipv6.fib6_has_custom_rules) {
+		struct fib_lookup_arg arg = {
+			.lookup_ptr = fib6_table_lookup,
+			.lookup_data = &oif,
+			.flags = FIB_LOOKUP_NOREF,
+		};
+
+		l3mdev_update_flow(net, flowi6_to_flowi(fl6));
+
+		err = fib_rules_lookup(net->ipv6.fib6_rules_ops,
+				       flowi6_to_flowi(fl6), flags, &arg);
+		if (err)
+			return ERR_PTR(err);
+
+		f6i = arg.result ? : net->ipv6.fib6_null_entry;
+	} else {
+		f6i = fib6_table_lookup(net, net->ipv6.fib6_local_tbl,
+					oif, fl6, flags);
+		if (!f6i || f6i == net->ipv6.fib6_null_entry)
+			f6i = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
+						oif, fl6, flags);
+	}
+
+	return f6i;
+}
+
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup)
@@ -96,8 +129,73 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	return &net->ipv6.ip6_null_entry->dst;
 }
 
-static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
-			    int flags, struct fib_lookup_arg *arg)
+static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags,
+			   struct flowi6 *flp6, const struct net_device *dev)
+{
+	struct fib6_rule *r = (struct fib6_rule *)rule;
+
+	/* If we need to find a source address for this traffic,
+	 * we check the result if it meets requirement of the rule.
+	 */
+	if ((rule->flags & FIB_RULE_FIND_SADDR) &&
+	    r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
+		struct in6_addr saddr;
+
+		if (ipv6_dev_get_saddr(net, dev, &flp6->daddr,
+				       rt6_flags2srcprefs(flags), &saddr))
+			return -EAGAIN;
+
+		if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen))
+			return -EAGAIN;
+
+		flp6->saddr = saddr;
+	}
+
+	return 0;
+}
+
+static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
+				int flags, struct fib_lookup_arg *arg)
+{
+	struct flowi6 *flp6 = &flp->u.ip6;
+	struct net *net = rule->fr_net;
+	struct fib6_table *table;
+	struct fib6_info *f6i;
+	int err = -EAGAIN, *oif;
+	u32 tb_id;
+
+	switch (rule->action) {
+	case FR_ACT_TO_TBL:
+		break;
+	case FR_ACT_UNREACHABLE:
+		return -ENETUNREACH;
+	case FR_ACT_PROHIBIT:
+		return -EACCES;
+	case FR_ACT_BLACKHOLE:
+	default:
+		return -EINVAL;
+	}
+
+	tb_id = fib_rule_get_table(rule, arg);
+	table = fib6_get_table(net, tb_id);
+	if (!table)
+		return -EAGAIN;
+
+	oif = (int *)arg->lookup_data;
+	f6i = fib6_table_lookup(net, table, *oif, flp6, flags);
+	if (f6i != net->ipv6.fib6_null_entry) {
+		err = fib6_rule_saddr(net, rule, flags, flp6,
+				      fib6_info_nh_dev(f6i));
+
+		if (likely(!err))
+			arg->result = f6i;
+	}
+
+	return err;
+}
+
+static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
+			      int flags, struct fib_lookup_arg *arg)
 {
 	struct flowi6 *flp6 = &flp->u.ip6;
 	struct rt6_info *rt = NULL;
@@ -134,27 +232,12 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 
 	rt = lookup(net, table, flp6, arg->lookup_data, flags);
 	if (rt != net->ipv6.ip6_null_entry) {
-		struct fib6_rule *r = (struct fib6_rule *)rule;
-
-		/*
-		 * If we need to find a source address for this traffic,
-		 * we check the result if it meets requirement of the rule.
-		 */
-		if ((rule->flags & FIB_RULE_FIND_SADDR) &&
-		    r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
-			struct in6_addr saddr;
-
-			if (ipv6_dev_get_saddr(net,
-					       ip6_dst_idev(&rt->dst)->dev,
-					       &flp6->daddr,
-					       rt6_flags2srcprefs(flags),
-					       &saddr))
-				goto again;
-			if (!ipv6_prefix_equal(&saddr, &r->src.addr,
-					       r->src.plen))
-				goto again;
-			flp6->saddr = saddr;
-		}
+		err = fib6_rule_saddr(net, rule, flags, flp6,
+				      ip6_dst_idev(&rt->dst)->dev);
+
+		if (err == -EAGAIN)
+			goto again;
+
 		err = rt->dst.error;
 		if (err != -EAGAIN)
 			goto out;
@@ -172,6 +255,15 @@ out:
 	return err;
 }
 
+static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
+			    int flags, struct fib_lookup_arg *arg)
+{
+	if (arg->lookup_ptr == fib6_table_lookup)
+		return fib6_rule_action_alt(rule, flp, flags, arg);
+
+	return __fib6_rule_action(rule, flp, flags, arg);
+}
+
 static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
 {
 	struct rt6_info *rt = (struct rt6_info *) arg->result;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index f0a4262a4789..d1dc6017f5a6 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -354,6 +354,13 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	return &rt->dst;
 }
 
+/* called with rcu lock held; no reference taken on fib6_info */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+			      int flags)
+{
+	return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, flags);
+}
+
 static void __net_init fib6_tables_init(struct net *net)
 {
 	fib6_link_table(net, net->ipv6.fib6_main_tbl);
@@ -1354,8 +1361,8 @@ struct lookup_args {
 	const struct in6_addr	*addr;		/* search key			*/
 };
 
-static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
-				       struct lookup_args *args)
+static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root,
+					    struct lookup_args *args)
 {
 	struct fib6_node *fn;
 	__be32 dir;
@@ -1400,7 +1407,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 #ifdef CONFIG_IPV6_SUBTREES
 				if (subtree) {
 					struct fib6_node *sfn;
-					sfn = fib6_lookup_1(subtree, args + 1);
+					sfn = fib6_node_lookup_1(subtree,
+								 args + 1);
 					if (!sfn)
 						goto backtrack;
 					fn = sfn;
@@ -1422,8 +1430,9 @@ backtrack:
 
 /* called with rcu_read_lock() held
  */
-struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
-			      const struct in6_addr *saddr)
+struct fib6_node *fib6_node_lookup(struct fib6_node *root,
+				   const struct in6_addr *daddr,
+				   const struct in6_addr *saddr)
 {
 	struct fib6_node *fn;
 	struct lookup_args args[] = {
@@ -1442,7 +1451,7 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad
 		}
 	};
 
-	fn = fib6_lookup_1(root, daddr ? args : args + 1);
+	fn = fib6_node_lookup_1(root, daddr ? args : args + 1);
 	if (!fn || fn->fn_flags & RTN_TL_ROOT)
 		fn = root;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index af0416701fb2..cc24ed3bc334 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -419,11 +419,11 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
-static struct fib6_info *rt6_multipath_select(const struct net *net,
-					      struct fib6_info *match,
-					     struct flowi6 *fl6, int oif,
-					     const struct sk_buff *skb,
-					     int strict)
+struct fib6_info *fib6_multipath_select(const struct net *net,
+					struct fib6_info *match,
+					struct flowi6 *fl6, int oif,
+					const struct sk_buff *skb,
+					int strict)
 {
 	struct fib6_info *sibling, *next_sibling;
 
@@ -1006,7 +1006,7 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
 		pn = rcu_dereference(fn->parent);
 		sn = FIB6_SUBTREE(pn);
 		if (sn && sn != fn)
-			fn = fib6_lookup(sn, NULL, saddr);
+			fn = fib6_node_lookup(sn, NULL, saddr);
 		else
 			fn = pn;
 		if (fn->fn_flags & RTN_RTINFO)
@@ -1059,7 +1059,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 		flags &= ~RT6_LOOKUP_F_IFACE;
 
 	rcu_read_lock();
-	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
 	f6i = rcu_dereference(fn->leaf);
 	if (!f6i) {
@@ -1068,8 +1068,9 @@ restart:
 		f6i = rt6_device_match(net, f6i, &fl6->saddr,
 				      fl6->flowi6_oif, flags);
 		if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0)
-			f6i = rt6_multipath_select(net, f6i, fl6,
-						   fl6->flowi6_oif, skb, flags);
+			f6i = fib6_multipath_select(net, f6i, fl6,
+						    fl6->flowi6_oif, skb,
+						    flags);
 	}
 	if (f6i == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
@@ -1077,6 +1078,8 @@ restart:
 			goto restart;
 	}
 
+	trace_fib6_table_lookup(net, f6i, table, fl6);
+
 	/* Search through exception table */
 	rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
 	if (rt) {
@@ -1095,8 +1098,6 @@ restart:
 
 	rcu_read_unlock();
 
-	trace_fib6_table_lookup(net, rt, table, fl6);
-
 	return rt;
 }
 
@@ -1799,23 +1800,14 @@ void rt6_age_exceptions(struct fib6_info *rt,
 	rcu_read_unlock_bh();
 }
 
-struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
-			       int oif, struct flowi6 *fl6,
-			       const struct sk_buff *skb, int flags)
+/* must be called with rcu lock held */
+struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
+				    int oif, struct flowi6 *fl6, int strict)
 {
 	struct fib6_node *fn, *saved_fn;
 	struct fib6_info *f6i;
-	struct rt6_info *rt;
-	int strict = 0;
 
-	strict |= flags & RT6_LOOKUP_F_IFACE;
-	strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
-	if (net->ipv6.devconf_all->forwarding == 0)
-		strict |= RT6_LOOKUP_F_REACHABLE;
-
-	rcu_read_lock();
-
-	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 	saved_fn = fn;
 
 	if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
@@ -1823,8 +1815,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 
 redo_rt6_select:
 	f6i = rt6_select(net, fn, oif, strict);
-	if (f6i->fib6_nsiblings)
-		f6i = rt6_multipath_select(net, f6i, fl6, oif, skb, strict);
 	if (f6i == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
@@ -1837,11 +1827,34 @@ redo_rt6_select:
 		}
 	}
 
+	trace_fib6_table_lookup(net, f6i, table, fl6);
+
+	return f6i;
+}
+
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+			       int oif, struct flowi6 *fl6,
+			       const struct sk_buff *skb, int flags)
+{
+	struct fib6_info *f6i;
+	struct rt6_info *rt;
+	int strict = 0;
+
+	strict |= flags & RT6_LOOKUP_F_IFACE;
+	strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
+	if (net->ipv6.devconf_all->forwarding == 0)
+		strict |= RT6_LOOKUP_F_REACHABLE;
+
+	rcu_read_lock();
+
+	f6i = fib6_table_lookup(net, table, oif, fl6, strict);
+	if (f6i->fib6_nsiblings)
+		f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
+
 	if (f6i == net->ipv6.fib6_null_entry) {
 		rt = net->ipv6.ip6_null_entry;
 		rcu_read_unlock();
 		dst_hold(&rt->dst);
-		trace_fib6_table_lookup(net, rt, table, fl6);
 		return rt;
 	}
 
@@ -1852,7 +1865,6 @@ redo_rt6_select:
 			dst_use_noref(&rt->dst, jiffies);
 
 		rcu_read_unlock();
-		trace_fib6_table_lookup(net, rt, table, fl6);
 		return rt;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
 			    !(f6i->fib6_flags & RTF_GATEWAY))) {
@@ -1878,9 +1890,7 @@ redo_rt6_select:
 			dst_hold(&uncached_rt->dst);
 		}
 
-		trace_fib6_table_lookup(net, uncached_rt, table, fl6);
 		return uncached_rt;
-
 	} else {
 		/* Get a percpu copy */
 
@@ -1894,7 +1904,7 @@ redo_rt6_select:
 
 		local_bh_enable();
 		rcu_read_unlock();
-		trace_fib6_table_lookup(net, pcpu_rt, table, fl6);
+
 		return pcpu_rt;
 	}
 }
@@ -2425,7 +2435,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	 */
 
 	rcu_read_lock();
-	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
 	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
@@ -2479,7 +2489,7 @@ out:
 
 	rcu_read_unlock();
 
-	trace_fib6_table_lookup(net, ret, table, fl6);
+	trace_fib6_table_lookup(net, rt, table, fl6);
 	return ret;
 };