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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 165 insertions, 56 deletions

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 5f3ee9e4b5bf..5c4171c5d2bd 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -16,6 +16,8 @@
 #include <linux/types.h>
 #include <linux/skbuff.h>
 #include <linux/filter.h>
+#include <linux/bpf.h>
+
 #include <net/rtnetlink.h>
 #include <net/pkt_cls.h>
 #include <net/sock.h>
@@ -24,6 +26,8 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
 MODULE_DESCRIPTION("TC BPF based classifier");
 
+#define CLS_BPF_NAME_LEN	256
+
 struct cls_bpf_head {
 	struct list_head plist;
 	u32 hgen;
@@ -32,18 +36,24 @@ struct cls_bpf_head {
 
 struct cls_bpf_prog {
 	struct bpf_prog *filter;
-	struct sock_filter *bpf_ops;
-	struct tcf_exts exts;
-	struct tcf_result res;
 	struct list_head link;
+	struct tcf_result res;
+	struct tcf_exts exts;
 	u32 handle;
-	u16 bpf_num_ops;
+	union {
+		u32 bpf_fd;
+		u16 bpf_num_ops;
+	};
+	struct sock_filter *bpf_ops;
+	const char *bpf_name;
 	struct tcf_proto *tp;
 	struct rcu_head rcu;
 };
 
 static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
 	[TCA_BPF_CLASSID]	= { .type = NLA_U32 },
+	[TCA_BPF_FD]		= { .type = NLA_U32 },
+	[TCA_BPF_NAME]		= { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN },
 	[TCA_BPF_OPS_LEN]	= { .type = NLA_U16 },
 	[TCA_BPF_OPS]		= { .type = NLA_BINARY,
 				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
@@ -54,8 +64,10 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 {
 	struct cls_bpf_head *head = rcu_dereference_bh(tp->root);
 	struct cls_bpf_prog *prog;
-	int ret;
+	int ret = -1;
 
+	/* Needed here for accessing maps. */
+	rcu_read_lock();
 	list_for_each_entry_rcu(prog, &head->plist, link) {
 		int filter_res = BPF_PROG_RUN(prog->filter, skb);
 
@@ -70,10 +82,16 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		if (ret < 0)
 			continue;
 
-		return ret;
+		break;
 	}
+	rcu_read_unlock();
 
-	return -1;
+	return ret;
+}
+
+static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog)
+{
+	return !prog->bpf_ops;
 }
 
 static int cls_bpf_init(struct tcf_proto *tp)
@@ -94,8 +112,12 @@ static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
 {
 	tcf_exts_destroy(&prog->exts);
 
-	bpf_prog_destroy(prog->filter);
+	if (cls_bpf_is_ebpf(prog))
+		bpf_prog_put(prog->filter);
+	else
+		bpf_prog_destroy(prog->filter);
 
+	kfree(prog->bpf_name);
 	kfree(prog->bpf_ops);
 	kfree(prog);
 }
@@ -114,14 +136,18 @@ static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
 	list_del_rcu(&prog->link);
 	tcf_unbind_filter(tp, &prog->res);
 	call_rcu(&prog->rcu, __cls_bpf_delete_prog);
+
 	return 0;
 }
 
-static void cls_bpf_destroy(struct tcf_proto *tp)
+static bool cls_bpf_destroy(struct tcf_proto *tp, bool force)
 {
 	struct cls_bpf_head *head = rtnl_dereference(tp->root);
 	struct cls_bpf_prog *prog, *tmp;
 
+	if (!force && !list_empty(&head->plist))
+		return false;
+
 	list_for_each_entry_safe(prog, tmp, &head->plist, link) {
 		list_del_rcu(&prog->link);
 		tcf_unbind_filter(tp, &prog->res);
@@ -130,6 +156,7 @@ static void cls_bpf_destroy(struct tcf_proto *tp)
 
 	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
+	return true;
 }
 
 static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
@@ -151,69 +178,121 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
 	return ret;
 }
 
-static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
-				   struct cls_bpf_prog *prog,
-				   unsigned long base, struct nlattr **tb,
-				   struct nlattr *est, bool ovr)
+static int cls_bpf_prog_from_ops(struct nlattr **tb,
+				 struct cls_bpf_prog *prog, u32 classid)
 {
 	struct sock_filter *bpf_ops;
-	struct tcf_exts exts;
-	struct sock_fprog_kern tmp;
+	struct sock_fprog_kern fprog_tmp;
 	struct bpf_prog *fp;
 	u16 bpf_size, bpf_num_ops;
-	u32 classid;
 	int ret;
 
-	if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID])
-		return -EINVAL;
-
-	tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE);
-	ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr);
-	if (ret < 0)
-		return ret;
-
-	classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
 	bpf_num_ops = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
-	if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) {
-		ret = -EINVAL;
-		goto errout;
-	}
+	if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0)
+		return -EINVAL;
 
 	bpf_size = bpf_num_ops * sizeof(*bpf_ops);
-	if (bpf_size != nla_len(tb[TCA_BPF_OPS])) {
-		ret = -EINVAL;
-		goto errout;
-	}
+	if (bpf_size != nla_len(tb[TCA_BPF_OPS]))
+		return -EINVAL;
 
 	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
-	if (bpf_ops == NULL) {
-		ret = -ENOMEM;
-		goto errout;
-	}
+	if (bpf_ops == NULL)
+		return -ENOMEM;
 
 	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
 
-	tmp.len = bpf_num_ops;
-	tmp.filter = bpf_ops;
+	fprog_tmp.len = bpf_num_ops;
+	fprog_tmp.filter = bpf_ops;
 
-	ret = bpf_prog_create(&fp, &tmp);
-	if (ret)
-		goto errout_free;
+	ret = bpf_prog_create(&fp, &fprog_tmp);
+	if (ret < 0) {
+		kfree(bpf_ops);
+		return ret;
+	}
 
-	prog->bpf_num_ops = bpf_num_ops;
 	prog->bpf_ops = bpf_ops;
+	prog->bpf_num_ops = bpf_num_ops;
+	prog->bpf_name = NULL;
+
+	prog->filter = fp;
+	prog->res.classid = classid;
+
+	return 0;
+}
+
+static int cls_bpf_prog_from_efd(struct nlattr **tb,
+				 struct cls_bpf_prog *prog, u32 classid)
+{
+	struct bpf_prog *fp;
+	char *name = NULL;
+	u32 bpf_fd;
+
+	bpf_fd = nla_get_u32(tb[TCA_BPF_FD]);
+
+	fp = bpf_prog_get(bpf_fd);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
+
+	if (fp->type != BPF_PROG_TYPE_SCHED_CLS) {
+		bpf_prog_put(fp);
+		return -EINVAL;
+	}
+
+	if (tb[TCA_BPF_NAME]) {
+		name = kmemdup(nla_data(tb[TCA_BPF_NAME]),
+			       nla_len(tb[TCA_BPF_NAME]),
+			       GFP_KERNEL);
+		if (!name) {
+			bpf_prog_put(fp);
+			return -ENOMEM;
+		}
+	}
+
+	prog->bpf_ops = NULL;
+	prog->bpf_fd = bpf_fd;
+	prog->bpf_name = name;
+
 	prog->filter = fp;
 	prog->res.classid = classid;
 
+	return 0;
+}
+
+static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
+				   struct cls_bpf_prog *prog,
+				   unsigned long base, struct nlattr **tb,
+				   struct nlattr *est, bool ovr)
+{
+	struct tcf_exts exts;
+	bool is_bpf, is_ebpf;
+	u32 classid;
+	int ret;
+
+	is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS];
+	is_ebpf = tb[TCA_BPF_FD];
+
+	if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) ||
+	    !tb[TCA_BPF_CLASSID])
+		return -EINVAL;
+
+	tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE);
+	ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr);
+	if (ret < 0)
+		return ret;
+
+	classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
+
+	ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog, classid) :
+		       cls_bpf_prog_from_efd(tb, prog, classid);
+	if (ret < 0) {
+		tcf_exts_destroy(&exts);
+		return ret;
+	}
+
 	tcf_bind_filter(tp, &prog->res, base);
 	tcf_exts_change(tp, &prog->exts, &exts);
 
 	return 0;
-errout_free:
-	kfree(bpf_ops);
-errout:
-	tcf_exts_destroy(&exts);
-	return ret;
 }
 
 static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
@@ -297,11 +376,43 @@ errout:
 	return ret;
 }
 
+static int cls_bpf_dump_bpf_info(const struct cls_bpf_prog *prog,
+				 struct sk_buff *skb)
+{
+	struct nlattr *nla;
+
+	if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops))
+		return -EMSGSIZE;
+
+	nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops *
+			  sizeof(struct sock_filter));
+	if (nla == NULL)
+		return -EMSGSIZE;
+
+	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+
+	return 0;
+}
+
+static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog,
+				  struct sk_buff *skb)
+{
+	if (nla_put_u32(skb, TCA_BPF_FD, prog->bpf_fd))
+		return -EMSGSIZE;
+
+	if (prog->bpf_name &&
+	    nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 			struct sk_buff *skb, struct tcmsg *tm)
 {
 	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh;
-	struct nlattr *nest, *nla;
+	struct nlattr *nest;
+	int ret;
 
 	if (prog == NULL)
 		return skb->len;
@@ -314,16 +425,14 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 
 	if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
 		goto nla_put_failure;
-	if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops))
-		goto nla_put_failure;
 
-	nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops *
-			  sizeof(struct sock_filter));
-	if (nla == NULL)
+	if (cls_bpf_is_ebpf(prog))
+		ret = cls_bpf_dump_ebpf_info(prog, skb);
+	else
+		ret = cls_bpf_dump_bpf_info(prog, skb);
+	if (ret)
 		goto nla_put_failure;
 
-	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
-
 	if (tcf_exts_dump(skb, &prog->exts) < 0)
 		goto nla_put_failure;