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

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 122 insertions, 91 deletions

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 2d01195153e6..10b8d851fc6b 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -40,6 +40,8 @@
 #include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
 #include <linux/bitmap.h>
+#include <linux/netdevice.h>
+#include <linux/hash.h>
 #include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
@@ -92,6 +94,7 @@ struct tc_u_common {
 	struct Qdisc		*q;
 	int			refcnt;
 	u32			hgenerator;
+	struct hlist_node	hnode;
 	struct rcu_head		rcu;
 };
 
@@ -289,7 +292,7 @@ out:
 }
 
 
-static unsigned long u32_get(struct tcf_proto *tp, u32 handle)
+static void *u32_get(struct tcf_proto *tp, u32 handle)
 {
 	struct tc_u_hnode *ht;
 	struct tc_u_common *tp_c = tp->data;
@@ -300,12 +303,12 @@ static unsigned long u32_get(struct tcf_proto *tp, u32 handle)
 		ht = u32_lookup_ht(tp_c, TC_U32_HTID(handle));
 
 	if (!ht)
-		return 0;
+		return NULL;
 
 	if (TC_U32_KEY(handle) == 0)
-		return (unsigned long)ht;
+		return ht;
 
-	return (unsigned long)u32_lookup_key(ht, handle);
+	return u32_lookup_key(ht, handle);
 }
 
 static u32 gen_new_htid(struct tc_u_common *tp_c)
@@ -323,12 +326,40 @@ static u32 gen_new_htid(struct tc_u_common *tp_c)
 	return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0;
 }
 
+static struct hlist_head *tc_u_common_hash;
+
+#define U32_HASH_SHIFT 10
+#define U32_HASH_SIZE (1 << U32_HASH_SHIFT)
+
+static unsigned int tc_u_hash(const struct tcf_proto *tp)
+{
+	struct net_device *dev = tp->q->dev_queue->dev;
+	u32 qhandle = tp->q->handle;
+	int ifindex = dev->ifindex;
+
+	return hash_64((u64)ifindex << 32 | qhandle, U32_HASH_SHIFT);
+}
+
+static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp)
+{
+	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->q == tp->q)
+			return tc;
+	}
+	return NULL;
+}
+
 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 = tp->q->u32_node;
+	tp_c = tc_u_common_find(tp);
 
 	root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL);
 	if (root_ht == NULL)
@@ -345,7 +376,10 @@ static int u32_init(struct tcf_proto *tp)
 			return -ENOBUFS;
 		}
 		tp_c->q = tp->q;
-		tp->q->u32_node = tp_c;
+		INIT_HLIST_NODE(&tp_c->hnode);
+
+		h = tc_u_hash(tp);
+		hlist_add_head(&tp_c->hnode, &tc_u_common_hash[h]);
 	}
 
 	tp_c->refcnt++;
@@ -431,43 +465,35 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
-	struct tc_cls_u32_offload u32_offload = {0};
-	struct tc_to_netdev offload;
-
-	offload.type = TC_SETUP_CLSU32;
-	offload.cls_u32 = &u32_offload;
-
-	if (tc_should_offload(dev, tp, 0)) {
-		offload.cls_u32->command = TC_CLSU32_DELETE_KNODE;
-		offload.cls_u32->knode.handle = handle;
-		dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-					      tp->chain->index, tp->protocol,
-					      &offload);
-	}
+	struct tc_cls_u32_offload cls_u32 = {};
+
+	if (!tc_should_offload(dev, 0))
+		return;
+
+	tc_cls_common_offload_init(&cls_u32.common, tp);
+	cls_u32.command = TC_CLSU32_DELETE_KNODE;
+	cls_u32.knode.handle = handle;
+
+	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
 }
 
 static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 				u32 flags)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
-	struct tc_cls_u32_offload u32_offload = {0};
-	struct tc_to_netdev offload;
+	struct tc_cls_u32_offload cls_u32 = {};
 	int err;
 
-	if (!tc_should_offload(dev, tp, flags))
+	if (!tc_should_offload(dev, flags))
 		return tc_skip_sw(flags) ? -EINVAL : 0;
 
-	offload.type = TC_SETUP_CLSU32;
-	offload.cls_u32 = &u32_offload;
-
-	offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
-	offload.cls_u32->hnode.divisor = h->divisor;
-	offload.cls_u32->hnode.handle = h->handle;
-	offload.cls_u32->hnode.prio = h->prio;
+	tc_cls_common_offload_init(&cls_u32.common, tp);
+	cls_u32.command = TC_CLSU32_NEW_HNODE;
+	cls_u32.hnode.divisor = h->divisor;
+	cls_u32.hnode.handle = h->handle;
+	cls_u32.hnode.prio = h->prio;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-					    tp->chain->index, tp->protocol,
-					    &offload);
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
 	if (tc_skip_sw(flags))
 		return err;
 
@@ -477,56 +503,47 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
-	struct tc_cls_u32_offload u32_offload = {0};
-	struct tc_to_netdev offload;
+	struct tc_cls_u32_offload cls_u32 = {};
 
-	offload.type = TC_SETUP_CLSU32;
-	offload.cls_u32 = &u32_offload;
+	if (!tc_should_offload(dev, 0))
+		return;
 
-	if (tc_should_offload(dev, tp, 0)) {
-		offload.cls_u32->command = TC_CLSU32_DELETE_HNODE;
-		offload.cls_u32->hnode.divisor = h->divisor;
-		offload.cls_u32->hnode.handle = h->handle;
-		offload.cls_u32->hnode.prio = h->prio;
+	tc_cls_common_offload_init(&cls_u32.common, tp);
+	cls_u32.command = TC_CLSU32_DELETE_HNODE;
+	cls_u32.hnode.divisor = h->divisor;
+	cls_u32.hnode.handle = h->handle;
+	cls_u32.hnode.prio = h->prio;
 
-		dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-					      tp->chain->index, tp->protocol,
-					      &offload);
-	}
+	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
 }
 
 static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 				u32 flags)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
-	struct tc_cls_u32_offload u32_offload = {0};
-	struct tc_to_netdev offload;
+	struct tc_cls_u32_offload cls_u32 = {};
 	int err;
 
-	offload.type = TC_SETUP_CLSU32;
-	offload.cls_u32 = &u32_offload;
-
-	if (!tc_should_offload(dev, tp, flags))
+	if (!tc_should_offload(dev, flags))
 		return tc_skip_sw(flags) ? -EINVAL : 0;
 
-	offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
-	offload.cls_u32->knode.handle = n->handle;
-	offload.cls_u32->knode.fshift = n->fshift;
+	tc_cls_common_offload_init(&cls_u32.common, tp);
+	cls_u32.command = TC_CLSU32_REPLACE_KNODE;
+	cls_u32.knode.handle = n->handle;
+	cls_u32.knode.fshift = n->fshift;
 #ifdef CONFIG_CLS_U32_MARK
-	offload.cls_u32->knode.val = n->val;
-	offload.cls_u32->knode.mask = n->mask;
+	cls_u32.knode.val = n->val;
+	cls_u32.knode.mask = n->mask;
 #else
-	offload.cls_u32->knode.val = 0;
-	offload.cls_u32->knode.mask = 0;
+	cls_u32.knode.val = 0;
+	cls_u32.knode.mask = 0;
 #endif
-	offload.cls_u32->knode.sel = &n->sel;
-	offload.cls_u32->knode.exts = &n->exts;
+	cls_u32.knode.sel = &n->sel;
+	cls_u32.knode.exts = &n->exts;
 	if (n->ht_down)
-		offload.cls_u32->knode.link_handle = n->ht_down->handle;
+		cls_u32.knode.link_handle = n->ht_down->handle;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-					    tp->chain->index, tp->protocol,
-					    &offload);
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
 
 	if (!err)
 		n->flags |= TCA_CLS_FLAGS_IN_HW;
@@ -602,7 +619,7 @@ static void u32_destroy(struct tcf_proto *tp)
 	if (--tp_c->refcnt == 0) {
 		struct tc_u_hnode *ht;
 
-		tp->q->u32_node = NULL;
+		hlist_del(&tp_c->hnode);
 
 		for (ht = rtnl_dereference(tp_c->hlist);
 		     ht;
@@ -622,9 +639,9 @@ static void u32_destroy(struct tcf_proto *tp)
 	tp->data = NULL;
 }
 
-static int u32_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
+static int u32_delete(struct tcf_proto *tp, void *arg, bool *last)
 {
-	struct tc_u_hnode *ht = (struct tc_u_hnode *)arg;
+	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;
@@ -723,29 +740,24 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 			 struct tc_u_knode *n, struct nlattr **tb,
 			 struct nlattr *est, bool ovr)
 {
-	struct tcf_exts e;
 	int err;
 
-	err = tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE);
+	err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr);
 	if (err < 0)
 		return err;
-	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
-	if (err < 0)
-		goto errout;
 
-	err = -EINVAL;
 	if (tb[TCA_U32_LINK]) {
 		u32 handle = nla_get_u32(tb[TCA_U32_LINK]);
 		struct tc_u_hnode *ht_down = NULL, *ht_old;
 
 		if (TC_U32_KEY(handle))
-			goto errout;
+			return -EINVAL;
 
 		if (handle) {
 			ht_down = u32_lookup_ht(ht->tp_c, handle);
 
 			if (ht_down == NULL)
-				goto errout;
+				return -EINVAL;
 			ht_down->refcnt++;
 		}
 
@@ -765,16 +777,11 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 		int ret;
 		ret = tcf_change_indev(net, tb[TCA_U32_INDEV]);
 		if (ret < 0)
-			goto errout;
+			return -EINVAL;
 		n->ifindex = ret;
 	}
 #endif
-	tcf_exts_change(tp, &n->exts, &e);
-
 	return 0;
-errout:
-	tcf_exts_destroy(&e);
-	return err;
 }
 
 static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c,
@@ -858,7 +865,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
 
 static int u32_change(struct net *net, struct sk_buff *in_skb,
 		      struct tcf_proto *tp, unsigned long base, u32 handle,
-		      struct nlattr **tca, unsigned long *arg, bool ovr)
+		      struct nlattr **tca, void **arg, bool ovr)
 {
 	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_hnode *ht;
@@ -885,7 +892,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 	}
 
-	n = (struct tc_u_knode *)*arg;
+	n = *arg;
 	if (n) {
 		struct tc_u_knode *new;
 
@@ -952,7 +959,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 
 		RCU_INIT_POINTER(ht->next, tp_c->hlist);
 		rcu_assign_pointer(tp_c->hlist, ht);
-		*arg = (unsigned long)ht;
+		*arg = ht;
 
 		return 0;
 	}
@@ -1047,7 +1054,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 
 		RCU_INIT_POINTER(n->next, pins);
 		rcu_assign_pointer(*ins, n);
-		*arg = (unsigned long)n;
+		*arg = n;
 		return 0;
 	}
 
@@ -1081,7 +1088,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 		if (ht->prio != tp->prio)
 			continue;
 		if (arg->count >= arg->skip) {
-			if (arg->fn(tp, (unsigned long)ht, arg) < 0) {
+			if (arg->fn(tp, ht, arg) < 0) {
 				arg->stop = 1;
 				return;
 			}
@@ -1095,7 +1102,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 					arg->count++;
 					continue;
 				}
-				if (arg->fn(tp, (unsigned long)n, arg) < 0) {
+				if (arg->fn(tp, n, arg) < 0) {
 					arg->stop = 1;
 					return;
 				}
@@ -1105,10 +1112,18 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 	}
 }
 
-static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
+static void u32_bind_class(void *fh, u32 classid, unsigned long cl)
+{
+	struct tc_u_knode *n = fh;
+
+	if (n && n->res.classid == classid)
+		n->res.class = cl;
+}
+
+static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
 		    struct sk_buff *skb, struct tcmsg *t)
 {
-	struct tc_u_knode *n = (struct tc_u_knode *)fh;
+	struct tc_u_knode *n = fh;
 	struct tc_u_hnode *ht_up, *ht_down;
 	struct nlattr *nest;
 
@@ -1122,7 +1137,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		goto nla_put_failure;
 
 	if (TC_U32_KEY(n->handle) == 0) {
-		struct tc_u_hnode *ht = (struct tc_u_hnode *)fh;
+		struct tc_u_hnode *ht = fh;
 		u32 divisor = ht->divisor + 1;
 
 		if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor))
@@ -1235,11 +1250,14 @@ static struct tcf_proto_ops cls_u32_ops __read_mostly = {
 	.delete		=	u32_delete,
 	.walk		=	u32_walk,
 	.dump		=	u32_dump,
+	.bind_class	=	u32_bind_class,
 	.owner		=	THIS_MODULE,
 };
 
 static int __init init_u32(void)
 {
+	int i, ret;
+
 	pr_info("u32 classifier\n");
 #ifdef CONFIG_CLS_U32_PERF
 	pr_info("    Performance counters on\n");
@@ -1250,12 +1268,25 @@ static int __init init_u32(void)
 #ifdef CONFIG_NET_CLS_ACT
 	pr_info("    Actions configured\n");
 #endif
-	return register_tcf_proto_ops(&cls_u32_ops);
+	tc_u_common_hash = kvmalloc_array(U32_HASH_SIZE,
+					  sizeof(struct hlist_head),
+					  GFP_KERNEL);
+	if (!tc_u_common_hash)
+		return -ENOMEM;
+
+	for (i = 0; i < U32_HASH_SIZE; i++)
+		INIT_HLIST_HEAD(&tc_u_common_hash[i]);
+
+	ret = register_tcf_proto_ops(&cls_u32_ops);
+	if (ret)
+		kvfree(tc_u_common_hash);
+	return ret;
 }
 
 static void __exit exit_u32(void)
 {
 	unregister_tcf_proto_ops(&cls_u32_ops);
+	kvfree(tc_u_common_hash);
 }
 
 module_init(init_u32)