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

Pull networking updates from David Miller:

 1) Add VF IPSEC offload support in ixgbe, from Shannon Nelson.

 2) Add zero-copy AF_XDP support to i40e, from Björn Töpel.

 3) All in-tree drivers are converted to {g,s}et_link_ksettings() so we
    can get rid of the {g,s}et_settings ethtool callbacks, from Michal
    Kubecek.

 4) Add software timestamping to veth driver, from Michael Walle.

 5) More work to make packet classifiers and actions lockless, from Vlad
    Buslov.

 6) Support sticky FDB entries in bridge, from Nikolay Aleksandrov.

 7) Add ipv6 version of IP_MULTICAST_ALL sockopt, from Andre Naujoks.

 8) Support batching of XDP buffers in vhost_net, from Jason Wang.

 9) Add flow dissector BPF hook, from Petar Penkov.

10) i40e vf --> generic iavf conversion, from Jesse Brandeburg.

11) Add NLA_REJECT netlink attribute policy type, to signal when users
    provide attributes in situations which don't make sense. From
    Johannes Berg.

12) Switch TCP and fair-queue scheduler over to earliest departure time
    model. From Eric Dumazet.

13) Improve guest receive performance by doing rx busy polling in tx
    path of vhost networking driver, from Tonghao Zhang.

14) Add per-cgroup local storage to bpf

15) Add reference tracking to BPF, from Joe Stringer. The verifier can
    now make sure that references taken to objects are properly released
    by the program.

16) Support in-place encryption in TLS, from Vakul Garg.

17) Add new taprio packet scheduler, from Vinicius Costa Gomes.

18) Lots of selftests additions, too numerous to mention one by one here
    but all of which are very much appreciated.

19) Support offloading of eBPF programs containing BPF to BPF calls in
    nfp driver, frm Quentin Monnet.

20) Move dpaa2_ptp driver out of staging, from Yangbo Lu.

21) Lots of u32 classifier cleanups and simplifications, from Al Viro.

22) Add new strict versions of netlink message parsers, and enable them
    for some situations. From David Ahern.

23) Evict neighbour entries on carrier down, also from David Ahern.

24) Support BPF sk_msg verdict programs with kTLS, from Daniel Borkmann
    and John Fastabend.

25) Add support for filtering route dumps, from David Ahern.

26) New igc Intel driver for 2.5G parts, from Sasha Neftin et al.

27) Allow vxlan enslavement to bridges in mlxsw driver, from Ido
    Schimmel.

28) Add queue and stack map types to eBPF, from Mauricio Vasquez B.

29) Add back byte-queue-limit support to r8169, with all the bug fixes
    in other areas of the driver it works now! From Florian Westphal and
    Heiner Kallweit.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2147 commits)
  tcp: add tcp_reset_xmit_timer() helper
  qed: Fix static checker warning
  Revert "be2net: remove desc field from be_eq_obj"
  Revert "net: simplify sock_poll_wait"
  net: socionext: Reset tx queue in ndo_stop
  net: socionext: Add dummy PHY register read in phy_write()
  net: socionext: Stop PHY before resetting netsec
  net: stmmac: Set OWN bit for jumbo frames
  arm64: dts: stratix10: Support Ethernet Jumbo frame
  tls: Add maintainers
  net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode
  octeontx2-af: Support for NIXLF's UCAST/PROMISC/ALLMULTI modes
  octeontx2-af: Support for setting MAC address
  octeontx2-af: Support for changing RSS algorithm
  octeontx2-af: NIX Rx flowkey configuration for RSS
  octeontx2-af: Install ucast and bcast pkt forwarding rules
  octeontx2-af: Add LMAC channel info to NIXLF_ALLOC response
  octeontx2-af: NPC MCAM and LDATA extract minimal configuration
  octeontx2-af: Enable packet length and csum validation
  octeontx2-af: Support for VTAG strip and capture
  ...

1 files changed, 38 insertions, 83 deletions

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index b2c3406a2cf2..4b28fd44576d 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -68,7 +68,6 @@ struct tc_u_knode {
 	u32			mask;
 	u32 __percpu		*pcpu_success;
 #endif
-	struct tcf_proto	*tp;
 	struct rcu_work		rwork;
 	/* The 'sel' field MUST be the last field in structure to allow for
 	 * tc_u32_keys allocated at end of structure.
@@ -80,10 +79,10 @@ struct tc_u_hnode {
 	struct tc_u_hnode __rcu	*next;
 	u32			handle;
 	u32			prio;
-	struct tc_u_common	*tp_c;
 	int			refcnt;
 	unsigned int		divisor;
 	struct idr		handle_idr;
+	bool			is_root;
 	struct rcu_head		rcu;
 	u32			flags;
 	/* The 'ht' field MUST be the last field in structure to allow for
@@ -98,7 +97,7 @@ struct tc_u_common {
 	int			refcnt;
 	struct idr		handle_idr;
 	struct hlist_node	hnode;
-	struct rcu_head		rcu;
+	long			knodes;
 };
 
 static inline unsigned int u32_hash_fold(__be32 key,
@@ -344,19 +343,16 @@ static void *tc_u_common_ptr(const struct tcf_proto *tp)
 		return block->q;
 }
 
-static unsigned int tc_u_hash(const struct tcf_proto *tp)
+static struct hlist_head *tc_u_hash(void *key)
 {
-	return hash_ptr(tc_u_common_ptr(tp), U32_HASH_SHIFT);
+	return tc_u_common_hash + hash_ptr(key, U32_HASH_SHIFT);
 }
 
-static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp)
+static struct tc_u_common *tc_u_common_find(void *key)
 {
 	struct tc_u_common *tc;
-	unsigned int h;
-
-	h = tc_u_hash(tp);
-	hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) {
-		if (tc->ptr == tc_u_common_ptr(tp))
+	hlist_for_each_entry(tc, tc_u_hash(key), hnode) {
+		if (tc->ptr == key)
 			return tc;
 	}
 	return NULL;
@@ -365,10 +361,8 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp)
 static int u32_init(struct tcf_proto *tp)
 {
 	struct tc_u_hnode *root_ht;
-	struct tc_u_common *tp_c;
-	unsigned int h;
-
-	tp_c = tc_u_common_find(tp);
+	void *key = tc_u_common_ptr(tp);
+	struct tc_u_common *tp_c = tc_u_common_find(key);
 
 	root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL);
 	if (root_ht == NULL)
@@ -377,6 +371,7 @@ static int u32_init(struct tcf_proto *tp)
 	root_ht->refcnt++;
 	root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000;
 	root_ht->prio = tp->prio;
+	root_ht->is_root = true;
 	idr_init(&root_ht->handle_idr);
 
 	if (tp_c == NULL) {
@@ -385,18 +380,16 @@ static int u32_init(struct tcf_proto *tp)
 			kfree(root_ht);
 			return -ENOBUFS;
 		}
-		tp_c->ptr = tc_u_common_ptr(tp);
+		tp_c->ptr = key;
 		INIT_HLIST_NODE(&tp_c->hnode);
 		idr_init(&tp_c->handle_idr);
 
-		h = tc_u_hash(tp);
-		hlist_add_head(&tp_c->hnode, &tc_u_common_hash[h]);
+		hlist_add_head(&tp_c->hnode, tc_u_hash(key));
 	}
 
 	tp_c->refcnt++;
 	RCU_INIT_POINTER(root_ht->next, tp_c->hlist);
 	rcu_assign_pointer(tp_c->hlist, root_ht);
-	root_ht->tp_c = tp_c;
 
 	root_ht->refcnt++;
 	rcu_assign_pointer(tp->root, root_ht);
@@ -404,8 +397,7 @@ static int u32_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
-			   bool free_pf)
+static int u32_destroy_key(struct tc_u_knode *n, bool free_pf)
 {
 	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 
@@ -439,7 +431,7 @@ static void u32_delete_key_work(struct work_struct *work)
 					      struct tc_u_knode,
 					      rwork);
 	rtnl_lock();
-	u32_destroy_key(key->tp, key, false);
+	u32_destroy_key(key, false);
 	rtnl_unlock();
 }
 
@@ -456,12 +448,13 @@ static void u32_delete_key_freepf_work(struct work_struct *work)
 					      struct tc_u_knode,
 					      rwork);
 	rtnl_lock();
-	u32_destroy_key(key->tp, key, true);
+	u32_destroy_key(key, true);
 	rtnl_unlock();
 }
 
 static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 {
+	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_knode __rcu **kp;
 	struct tc_u_knode *pkp;
 	struct tc_u_hnode *ht = rtnl_dereference(key->ht_up);
@@ -472,6 +465,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 		     kp = &pkp->next, pkp = rtnl_dereference(*kp)) {
 			if (pkp == key) {
 				RCU_INIT_POINTER(*kp, key->next);
+				tp_c->knodes--;
 
 				tcf_unbind_filter(tp, &key->res);
 				idr_remove(&ht->handle_idr, key->handle);
@@ -586,6 +580,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 			    struct netlink_ext_ack *extack)
 {
+	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_knode *n;
 	unsigned int h;
 
@@ -593,13 +588,14 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 		while ((n = rtnl_dereference(ht->ht[h])) != NULL) {
 			RCU_INIT_POINTER(ht->ht[h],
 					 rtnl_dereference(n->next));
+			tp_c->knodes--;
 			tcf_unbind_filter(tp, &n->res);
 			u32_remove_hw_knode(tp, n, extack);
 			idr_remove(&ht->handle_idr, n->handle);
 			if (tcf_exts_get_net(&n->exts))
 				tcf_queue_work(&n->rwork, u32_delete_key_freepf_work);
 			else
-				u32_destroy_key(n->tp, n, true);
+				u32_destroy_key(n, true);
 		}
 	}
 }
@@ -632,17 +628,6 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 	return -ENOENT;
 }
 
-static bool ht_empty(struct tc_u_hnode *ht)
-{
-	unsigned int h;
-
-	for (h = 0; h <= ht->divisor; h++)
-		if (rcu_access_pointer(ht->ht[h]))
-			return false;
-
-	return true;
-}
-
 static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct tc_u_common *tp_c = tp->data;
@@ -680,20 +665,16 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
 		      struct netlink_ext_ack *extack)
 {
 	struct tc_u_hnode *ht = arg;
-	struct tc_u_hnode *root_ht = rtnl_dereference(tp->root);
 	struct tc_u_common *tp_c = tp->data;
 	int ret = 0;
 
-	if (ht == NULL)
-		goto out;
-
 	if (TC_U32_KEY(ht->handle)) {
 		u32_remove_hw_knode(tp, (struct tc_u_knode *)ht, extack);
 		ret = u32_delete_key(tp, (struct tc_u_knode *)ht);
 		goto out;
 	}
 
-	if (root_ht == ht) {
+	if (ht->is_root) {
 		NL_SET_ERR_MSG_MOD(extack, "Not allowed to delete root node");
 		return -EINVAL;
 	}
@@ -706,38 +687,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
 	}
 
 out:
-	*last = true;
-	if (root_ht) {
-		if (root_ht->refcnt > 2) {
-			*last = false;
-			goto ret;
-		}
-		if (root_ht->refcnt == 2) {
-			if (!ht_empty(root_ht)) {
-				*last = false;
-				goto ret;
-			}
-		}
-	}
-
-	if (tp_c->refcnt > 1) {
-		*last = false;
-		goto ret;
-	}
-
-	if (tp_c->refcnt == 1) {
-		struct tc_u_hnode *ht;
-
-		for (ht = rtnl_dereference(tp_c->hlist);
-		     ht;
-		     ht = rtnl_dereference(ht->next))
-			if (!ht_empty(ht)) {
-				*last = false;
-				break;
-			}
-	}
-
-ret:
+	*last = tp_c->refcnt == 1 && tp_c->knodes == 0;
 	return ret;
 }
 
@@ -768,7 +718,7 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
 };
 
 static int u32_set_parms(struct net *net, struct tcf_proto *tp,
-			 unsigned long base, struct tc_u_hnode *ht,
+			 unsigned long base,
 			 struct tc_u_knode *n, struct nlattr **tb,
 			 struct nlattr *est, bool ovr,
 			 struct netlink_ext_ack *extack)
@@ -789,12 +739,16 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 		}
 
 		if (handle) {
-			ht_down = u32_lookup_ht(ht->tp_c, handle);
+			ht_down = u32_lookup_ht(tp->data, handle);
 
 			if (!ht_down) {
 				NL_SET_ERR_MSG_MOD(extack, "Link hash table not found");
 				return -EINVAL;
 			}
+			if (ht_down->is_root) {
+				NL_SET_ERR_MSG_MOD(extack, "Not linking to root node");
+				return -EINVAL;
+			}
 			ht_down->refcnt++;
 		}
 
@@ -891,7 +845,6 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
 	/* Similarly success statistics must be moved as pointers */
 	new->pcpu_success = n->pcpu_success;
 #endif
-	new->tp = tp;
 	memcpy(&new->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key));
 
 	if (tcf_exts_init(&new->exts, TCA_U32_ACT, TCA_U32_POLICE)) {
@@ -960,18 +913,17 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		if (!new)
 			return -ENOMEM;
 
-		err = u32_set_parms(net, tp, base,
-				    rtnl_dereference(n->ht_up), new, tb,
+		err = u32_set_parms(net, tp, base, new, tb,
 				    tca[TCA_RATE], ovr, extack);
 
 		if (err) {
-			u32_destroy_key(tp, new, false);
+			u32_destroy_key(new, false);
 			return err;
 		}
 
 		err = u32_replace_hw_knode(tp, new, flags, extack);
 		if (err) {
-			u32_destroy_key(tp, new, false);
+			u32_destroy_key(new, false);
 			return err;
 		}
 
@@ -988,7 +940,11 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	if (tb[TCA_U32_DIVISOR]) {
 		unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]);
 
-		if (--divisor > 0x100) {
+		if (!is_power_of_2(divisor)) {
+			NL_SET_ERR_MSG_MOD(extack, "Divisor is not a power of 2");
+			return -EINVAL;
+		}
+		if (divisor-- > 0x100) {
 			NL_SET_ERR_MSG_MOD(extack, "Exceeded maximum 256 hash buckets");
 			return -EINVAL;
 		}
@@ -1013,7 +969,6 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 				return err;
 			}
 		}
-		ht->tp_c = tp_c;
 		ht->refcnt = 1;
 		ht->divisor = divisor;
 		ht->handle = handle;
@@ -1103,7 +1058,6 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	n->handle = handle;
 	n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
 	n->flags = flags;
-	n->tp = tp;
 
 	err = tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE);
 	if (err < 0)
@@ -1125,7 +1079,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 #endif
 
-	err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr,
+	err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], ovr,
 			    extack);
 	if (err == 0) {
 		struct tc_u_knode __rcu **ins;
@@ -1146,6 +1100,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 
 		RCU_INIT_POINTER(n->next, pins);
 		rcu_assign_pointer(*ins, n);
+		tp_c->knodes++;
 		*arg = n;
 		return 0;
 	}