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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 125 insertions, 86 deletions

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 0e79c3408569..5cba71d2dc44 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -38,6 +38,7 @@
 #endif
 
 struct rt6_info;
+struct fib6_info;
 
 struct fib6_config {
 	u32		fc_table;
@@ -74,12 +75,12 @@ struct fib6_node {
 #ifdef CONFIG_IPV6_SUBTREES
 	struct fib6_node __rcu	*subtree;
 #endif
-	struct rt6_info __rcu	*leaf;
+	struct fib6_info __rcu	*leaf;
 
 	__u16			fn_bit;		/* bit key */
 	__u16			fn_flags;
 	int			fn_sernum;
-	struct rt6_info __rcu	*rr_ptr;
+	struct fib6_info __rcu	*rr_ptr;
 	struct rcu_head		rcu;
 };
 
@@ -94,11 +95,6 @@ struct fib6_gc_args {
 #define FIB6_SUBTREE(fn)	(rcu_dereference_protected((fn)->subtree, 1))
 #endif
 
-struct mx6_config {
-	const u32 *mx;
-	DECLARE_BITMAP(mx_valid, RTAX_MAX);
-};
-
 /*
  *	routing information
  *
@@ -127,92 +123,104 @@ struct rt6_exception {
 #define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT)
 #define FIB6_MAX_DEPTH 5
 
-struct rt6_info {
-	struct dst_entry		dst;
-	struct rt6_info __rcu		*rt6_next;
-	struct rt6_info			*from;
+struct fib6_nh {
+	struct in6_addr		nh_gw;
+	struct net_device	*nh_dev;
+	struct lwtunnel_state	*nh_lwtstate;
 
-	/*
-	 * Tail elements of dst_entry (__refcnt etc.)
-	 * and these elements (rarely used in hot path) are in
-	 * the same cache line.
-	 */
-	struct fib6_table		*rt6i_table;
-	struct fib6_node __rcu		*rt6i_node;
+	unsigned int		nh_flags;
+	atomic_t		nh_upper_bound;
+	int			nh_weight;
+};
 
-	struct in6_addr			rt6i_gateway;
+struct fib6_info {
+	struct fib6_table		*fib6_table;
+	struct fib6_info __rcu		*fib6_next;
+	struct fib6_node __rcu		*fib6_node;
 
 	/* Multipath routes:
-	 * siblings is a list of rt6_info that have the the same metric/weight,
+	 * siblings is a list of fib6_info that have the the same metric/weight,
 	 * destination, but not the same gateway. nsiblings is just a cache
 	 * to speed up lookup.
 	 */
-	struct list_head		rt6i_siblings;
-	unsigned int			rt6i_nsiblings;
-	atomic_t			rt6i_nh_upper_bound;
+	struct list_head		fib6_siblings;
+	unsigned int			fib6_nsiblings;
 
-	atomic_t			rt6i_ref;
+	atomic_t			fib6_ref;
+	unsigned long			expires;
+	struct dst_metrics		*fib6_metrics;
+#define fib6_pmtu		fib6_metrics->metrics[RTAX_MTU-1]
 
-	unsigned int			rt6i_nh_flags;
+	struct rt6key			fib6_dst;
+	u32				fib6_flags;
+	struct rt6key			fib6_src;
+	struct rt6key			fib6_prefsrc;
 
-	/* These are in a separate cache line. */
-	struct rt6key			rt6i_dst ____cacheline_aligned_in_smp;
-	u32				rt6i_flags;
+	struct rt6_info * __percpu	*rt6i_pcpu;
+	struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
+
+	u32				fib6_metric;
+	u8				fib6_protocol;
+	u8				fib6_type;
+	u8				exception_bucket_flushed:1,
+					should_flush:1,
+					dst_nocount:1,
+					dst_nopolicy:1,
+					dst_host:1,
+					unused:3;
+
+	struct fib6_nh			fib6_nh;
+};
+
+struct rt6_info {
+	struct dst_entry		dst;
+	struct fib6_info __rcu		*from;
+
+	struct rt6key			rt6i_dst;
 	struct rt6key			rt6i_src;
+	struct in6_addr			rt6i_gateway;
+	struct inet6_dev		*rt6i_idev;
+	u32				rt6i_flags;
 	struct rt6key			rt6i_prefsrc;
 
 	struct list_head		rt6i_uncached;
 	struct uncached_list		*rt6i_uncached_list;
 
-	struct inet6_dev		*rt6i_idev;
-	struct rt6_info * __percpu	*rt6i_pcpu;
-	struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
-
-	u32				rt6i_metric;
-	u32				rt6i_pmtu;
 	/* more non-fragment space at head required */
-	int				rt6i_nh_weight;
 	unsigned short			rt6i_nfheader_len;
-	u8				rt6i_protocol;
-	u8				exception_bucket_flushed:1,
-					should_flush:1,
-					unused:6;
 };
 
 #define for_each_fib6_node_rt_rcu(fn)					\
 	for (rt = rcu_dereference((fn)->leaf); rt;			\
-	     rt = rcu_dereference(rt->rt6_next))
+	     rt = rcu_dereference(rt->fib6_next))
 
 #define for_each_fib6_walker_rt(w)					\
 	for (rt = (w)->leaf; rt;					\
-	     rt = rcu_dereference_protected(rt->rt6_next, 1))
+	     rt = rcu_dereference_protected(rt->fib6_next, 1))
 
 static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
 {
 	return ((struct rt6_info *)dst)->rt6i_idev;
 }
 
-static inline void rt6_clean_expires(struct rt6_info *rt)
+static inline void fib6_clean_expires(struct fib6_info *f6i)
 {
-	rt->rt6i_flags &= ~RTF_EXPIRES;
-	rt->dst.expires = 0;
+	f6i->fib6_flags &= ~RTF_EXPIRES;
+	f6i->expires = 0;
 }
 
-static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
+static inline void fib6_set_expires(struct fib6_info *f6i,
+				    unsigned long expires)
 {
-	rt->dst.expires = expires;
-	rt->rt6i_flags |= RTF_EXPIRES;
+	f6i->expires = expires;
+	f6i->fib6_flags |= RTF_EXPIRES;
 }
 
-static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
+static inline bool fib6_check_expired(const struct fib6_info *f6i)
 {
-	struct rt6_info *rt;
-
-	for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES); rt = rt->from);
-	if (rt && rt != rt0)
-		rt0->dst.expires = rt->dst.expires;
-	dst_set_expires(&rt0->dst, timeout);
-	rt0->rt6i_flags |= RTF_EXPIRES;
+	if (f6i->fib6_flags & RTF_EXPIRES)
+		return time_after(jiffies, f6i->expires);
+	return false;
 }
 
 /* Function to safely get fn->sernum for passed in rt
@@ -220,14 +228,13 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
  * Return true if we can get cookie safely
  * Return false if not
  */
-static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
-				       u32 *cookie)
+static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i,
+					u32 *cookie)
 {
 	struct fib6_node *fn;
 	bool status = false;
 
-	rcu_read_lock();
-	fn = rcu_dereference(rt->rt6i_node);
+	fn = rcu_dereference(f6i->fib6_node);
 
 	if (fn) {
 		*cookie = fn->fn_sernum;
@@ -236,19 +243,22 @@ static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
 		status = true;
 	}
 
-	rcu_read_unlock();
 	return status;
 }
 
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
+	struct fib6_info *from;
 	u32 cookie = 0;
 
-	if (rt->rt6i_flags & RTF_PCPU ||
-	    (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from))
-		rt = rt->from;
+	rcu_read_lock();
+
+	from = rcu_dereference(rt->from);
+	if (from && (rt->rt6i_flags & RTF_PCPU ||
+	    unlikely(!list_empty(&rt->rt6i_uncached))))
+		fib6_get_cookie_safe(from, &cookie);
 
-	rt6_get_cookie_safe(rt, &cookie);
+	rcu_read_unlock();
 
 	return cookie;
 }
@@ -262,20 +272,18 @@ static inline void ip6_rt_put(struct rt6_info *rt)
 	dst_release(&rt->dst);
 }
 
-void rt6_free_pcpu(struct rt6_info *non_pcpu_rt);
+struct fib6_info *fib6_info_alloc(gfp_t gfp_flags);
+void fib6_info_destroy(struct fib6_info *f6i);
 
-static inline void rt6_hold(struct rt6_info *rt)
+static inline void fib6_info_hold(struct fib6_info *f6i)
 {
-	atomic_inc(&rt->rt6i_ref);
+	atomic_inc(&f6i->fib6_ref);
 }
 
-static inline void rt6_release(struct rt6_info *rt)
+static inline void fib6_info_release(struct fib6_info *f6i)
 {
-	if (atomic_dec_and_test(&rt->rt6i_ref)) {
-		rt6_free_pcpu(rt);
-		dst_dev_put(&rt->dst);
-		dst_release(&rt->dst);
-	}
+	if (f6i && atomic_dec_and_test(&f6i->fib6_ref))
+		fib6_info_destroy(f6i);
 }
 
 enum fib6_walk_state {
@@ -291,7 +299,7 @@ enum fib6_walk_state {
 struct fib6_walker {
 	struct list_head lh;
 	struct fib6_node *root, *node;
-	struct rt6_info *leaf;
+	struct fib6_info *leaf;
 	enum fib6_walk_state state;
 	unsigned int skip;
 	unsigned int count;
@@ -355,7 +363,7 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *,
 
 struct fib6_entry_notifier_info {
 	struct fib_notifier_info info; /* must be first */
-	struct rt6_info *rt;
+	struct fib6_info *rt;
 };
 
 /*
@@ -368,24 +376,49 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup);
 
-struct fib6_node *fib6_lookup(struct fib6_node *root,
-			      const struct in6_addr *daddr,
-			      const struct in6_addr *saddr);
+/* called with rcu lock held; can return error pointer
+ * caller needs to select path
+ */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+			      int flags);
+
+/* called with rcu lock held; caller needs to select path */
+struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
+				    int oif, struct flowi6 *fl6, 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_node *fib6_node_lookup(struct fib6_node *root,
+				   const struct in6_addr *daddr,
+				   const struct in6_addr *saddr);
 
 struct fib6_node *fib6_locate(struct fib6_node *root,
 			      const struct in6_addr *daddr, int dst_len,
 			      const struct in6_addr *saddr, int src_len,
 			      bool exact_match);
 
-void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
+void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg),
 		    void *arg);
 
-int fib6_add(struct fib6_node *root, struct rt6_info *rt,
-	     struct nl_info *info, struct mx6_config *mxc,
-	     struct netlink_ext_ack *extack);
-int fib6_del(struct rt6_info *rt, struct nl_info *info);
+int fib6_add(struct fib6_node *root, struct fib6_info *rt,
+	     struct nl_info *info, struct netlink_ext_ack *extack);
+int fib6_del(struct fib6_info *rt, struct nl_info *info);
+
+static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i)
+{
+	return f6i->fib6_nh.nh_dev;
+}
+
+static inline
+struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i)
+{
+	return f6i->fib6_nh.nh_lwtstate;
+}
 
-void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
+void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		     unsigned int flags);
 
 void fib6_run_gc(unsigned long expires, struct net *net, bool force);
@@ -416,8 +449,14 @@ void __net_exit fib6_notifier_exit(struct net *net);
 unsigned int fib6_tables_seq_read(struct net *net);
 int fib6_tables_dump(struct net *net, struct notifier_block *nb);
 
-void fib6_update_sernum(struct rt6_info *rt);
-void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt);
+void fib6_update_sernum(struct net *net, struct fib6_info *rt);
+void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt);
+
+void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val);
+static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric)
+{
+	return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric));
+}
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 int fib6_rules_init(void);