Implement interface link header precomputation API.

Add if_requestencap() interface method which is capable of calculating
  various link headers for given interface. Right now there is support
  for INET/INET6/ARP llheader calculation (IFENCAP_LL type request).
  Other types are planned to support more complex calculation
  (L2 multipath lagg nexthops, tunnel encap nexthops, etc..).

Reshape 'struct route' to be able to pass additional data (with is length)
  to prepend to mbuf.

These two changes permits routing code to pass pre-calculated nexthop data
  (like L2 header for route w/gateway) down to the stack eliminating the
  need for other lookups. It also brings us closer to more complex scenarios
  like transparently handling MPLS nexthops and tunnel interfaces.
  Last, but not least, it removes layering violation introduced by flowtable
  code (ro_lle) and simplifies handling of existing if_output consumers.

ARP/ND changes:
Make arp/ndp stack pre-calculate link header upon installing/updating lle
  record. Interface link address change are handled by re-calculating
  headers for all lles based on if_lladdr event. After these changes,
  arpresolve()/nd6_resolve() returns full pre-calculated header for
  supported interfaces thus simplifying if_output().
Move these lookups to separate ether_resolve_addr() function which ether
  returs error or fully-prepared link header. Add <arp|nd6_>resolve_addr()
  compat versions to return link addresses instead of pre-calculated data.

BPF changes:
Raw bpf writes occupied _two_ cases: AF_UNSPEC and pseudo_AF_HDRCMPLT.
Despite the naming, both of there have ther header "complete". The only
  difference is that interface source mac has to be filled by OS for
  AF_UNSPEC (controlled via BIOCGHDRCMPLT). This logic has to stay inside
  BPF and not pollute if_output() routines. Convert BPF to pass prepend data
  via new 'struct route' mechanism. Note that it does not change
  non-optimized if_output(): ro_prepend handling is purely optional.
Side note: hackish pseudo_AF_HDRCMPLT is supported for ethernet and FDDI.
  It is not needed for ethernet anymore. The only remaining FDDI user is
  dev/pdq mostly untouched since 2007. FDDI support was eliminated from
  OpenBSD in 2013 (sys/net/if_fddisubr.c rev 1.65).

Flowtable changes:
  Flowtable violates layering by saving (and not correctly managing)
  rtes/lles. Instead of passing lle pointer, pass pointer to pre-calculated
  header data from that lle.

Differential Revision:	https://reviews.freebsd.org/D4102

1 files changed, 12 insertions, 8 deletions

diff --git a/sys/net/if_llatbl.h b/sys/net/if_llatbl.h
index 8a300c3..b6111c6 100644
--- a/sys/net/if_llatbl.h
+++ b/sys/net/if_llatbl.h
@@ -48,6 +48,7 @@ extern struct rwlock lltable_rwlock;
 #define	LLTABLE_WUNLOCK()	rw_wunlock(&lltable_rwlock)
 #define	LLTABLE_LOCK_ASSERT()	rw_assert(&lltable_rwlock, RA_LOCKED)
 
+#define	LLE_MAX_LINKHDR		24	/* Full IB header */
 /*
  * Code referencing llentry must at least hold
  * a shared lock
@@ -58,14 +59,11 @@ struct llentry {
 		struct in_addr	addr4;
 		struct in6_addr	addr6;
 	} r_l3addr;
-	union {
-		uint64_t	mac_aligned;
-		uint16_t	mac16[3];
-		uint8_t		mac8[20];	/* IB needs 20 bytes. */
-	} ll_addr;
+	char			r_linkdata[LLE_MAX_LINKHDR]; /* L2 data */
+	uint8_t			r_hdrlen;	/* length for LL header */
+	uint8_t			spare0[3];
 	uint16_t		r_flags;	/* LLE runtime flags */
 	uint16_t		r_skip_req;	/* feedback from fast path */
-	uint64_t		spare1;
 
 	struct lltable		 *lle_tbl;
 	struct llentries	 *lle_head;
@@ -82,6 +80,7 @@ struct llentry {
 	time_t			lle_remtime;	/* Real time remaining */
 	time_t			lle_hittime;	/* Time when r_skip_req was unset */
 	int			 lle_refcnt;
+	char			*ll_addr;	/* link-layer address */
 
 	LIST_ENTRY(llentry)	lle_chain;	/* chain of deleted items */
 	struct callout		lle_timer;
@@ -198,6 +197,8 @@ MALLOC_DECLARE(M_LLTABLE);
 /* LLE request flags */
 #define	LLE_EXCLUSIVE	0x2000	/* return lle xlocked  */
 #define	LLE_UNLOCKED	0x4000	/* return lle unlocked */
+#define	LLE_ADDRONLY	0x4000	/* return lladdr instead of full header */
+#define	LLE_CREATE	0x8000	/* hint to avoid lle lookup */
 
 /* LLE flags used by fastpath code */
 #define	RLLE_VALID	0x0001		/* entry is valid */
@@ -223,10 +224,13 @@ struct llentry  *llentry_alloc(struct ifnet *, struct lltable *,
 /* helper functions */
 size_t lltable_drop_entry_queue(struct llentry *);
 void lltable_set_entry_addr(struct ifnet *ifp, struct llentry *lle,
-    const char *lladdr);
+    const char *linkhdr, size_t linkhdrsize, int lladdr_off);
 int lltable_try_set_entry_addr(struct ifnet *ifp, struct llentry *lle,
-    const char *lladdr);
+    const char *linkhdr, size_t linkhdrsize, int lladdr_off);
 
+int lltable_calc_llheader(struct ifnet *ifp, int family, char *lladdr,
+    char *buf, size_t *bufsize, int *lladdr_off);
+void lltable_update_ifaddr(struct lltable *llt);
 struct llentry *lltable_alloc_entry(struct lltable *llt, u_int flags,
     const struct sockaddr *l4addr);
 void lltable_free_entry(struct lltable *llt, struct llentry *lle);