Build on Jeff Roberson's linker-set based dynamic per-CPU allocator

(DPCPU), as suggested by Peter Wemm, and implement a new per-virtual
network stack memory allocator.  Modify vnet to use the allocator
instead of monolithic global container structures (vinet, ...).  This
change solves many binary compatibility problems associated with
VIMAGE, and restores ELF symbols for virtualized global variables.

Each virtualized global variable exists as a "reference copy", and also
once per virtual network stack.  Virtualized global variables are
tagged at compile-time, placing the in a special linker set, which is
loaded into a contiguous region of kernel memory.  Virtualized global
variables in the base kernel are linked as normal, but those in modules
are copied and relocated to a reserved portion of the kernel's vnet
region with the help of a the kernel linker.

Virtualized global variables exist in per-vnet memory set up when the
network stack instance is created, and are initialized statically from
the reference copy.  Run-time access occurs via an accessor macro, which
converts from the current vnet and requested symbol to a per-vnet
address.  When "options VIMAGE" is not compiled into the kernel, normal
global ELF symbols will be used instead and indirection is avoided.

This change restores static initialization for network stack global
variables, restores support for non-global symbols and types, eliminates
the need for many subsystem constructors, eliminates large per-subsystem
structures that caused many binary compatibility issues both for
monitoring applications (netstat) and kernel modules, removes the
per-function INIT_VNET_*() macros throughout the stack, eliminates the
need for vnet_symmap ksym(2) munging, and eliminates duplicate
definitions of virtualized globals under VIMAGE_GLOBALS.

Bump __FreeBSD_version and update UPDATING.

Portions submitted by:  bz
Reviewed by:            bz, zec
Discussed with:         gnn, jamie, jeff, jhb, julian, sam
Suggested by:           peter
Approved by:            re (kensmith)

1 files changed, 6 insertions, 25 deletions

diff --git a/sys/netinet/raw_ip.c b/sys/netinet/raw_ip.c
index 00ec423..c3a0a74 100644
--- a/sys/netinet/raw_ip.c
+++ b/sys/netinet/raw_ip.c
@@ -68,18 +68,17 @@ __FBSDID("$FreeBSD$");
 #include <netinet/ip_var.h>
 #include <netinet/ip_mroute.h>
 
-#include <netinet/vinet.h>
-
 #ifdef IPSEC
 #include <netipsec/ipsec.h>
 #endif /*IPSEC*/
 
 #include <security/mac/mac_framework.h>
 
-#ifdef VIMAGE_GLOBALS
-struct	inpcbhead ripcb;
-struct	inpcbinfo ripcbinfo;
-#endif
+VNET_DEFINE(struct inpcbhead, ripcb);
+VNET_DEFINE(struct inpcbinfo, ripcbinfo);
+
+#define	V_ripcb			VNET_GET(ripcb)
+#define	V_ripcbinfo		VNET_GET(ripcbinfo)
 
 /*
  * Control and data hooks for ipfw and dummynet.
@@ -99,9 +98,7 @@ int (*ip_dn_io_ptr)(struct mbuf **m, int dir, struct ip_fw_args *fwa) = NULL;
 /*
  * The socket used to communicate with the multicast routing daemon.
  */
-#ifdef VIMAGE_GLOBALS
-struct socket  *ip_mrouter;
-#endif
+VNET_DEFINE(struct socket *, ip_mrouter);
 
 /*
  * The various mrouter and rsvp functions.
@@ -168,7 +165,6 @@ rip_delhash(struct inpcb *inp)
 static void
 rip_zone_change(void *tag)
 {
-	INIT_VNET_INET(curvnet);
 
 	uma_zone_set_max(V_ripcbinfo.ipi_zone, maxsockets);
 }
@@ -185,7 +181,6 @@ rip_inpcb_init(void *mem, int size, int flags)
 void
 rip_init(void)
 {
-	INIT_VNET_INET(curvnet);
 
 	INP_INFO_LOCK_INIT(&V_ripcbinfo, "rip");
 	LIST_INIT(&V_ripcb);
@@ -208,7 +203,6 @@ rip_init(void)
 void
 rip_destroy(void)
 {
-	INIT_VNET_INET(curvnet);
 
 	hashdestroy(V_ripcbinfo.ipi_hashbase, M_PCB,
 	    V_ripcbinfo.ipi_hashmask);
@@ -268,7 +262,6 @@ rip_append(struct inpcb *last, struct ip *ip, struct mbuf *n,
 void
 rip_input(struct mbuf *m, int off)
 {
-	INIT_VNET_INET(curvnet);
 	struct ifnet *ifp;
 	struct ip *ip = mtod(m, struct ip *);
 	int proto = ip->ip_p;
@@ -398,7 +391,6 @@ rip_input(struct mbuf *m, int off)
 int
 rip_output(struct mbuf *m, struct socket *so, u_long dst)
 {
-	INIT_VNET_INET(so->so_vnet);
 	struct ip *ip;
 	int error;
 	struct inpcb *inp = sotoinpcb(so);
@@ -670,7 +662,6 @@ rip_ctloutput(struct socket *so, struct sockopt *sopt)
 void
 rip_ctlinput(int cmd, struct sockaddr *sa, void *vip)
 {
-	INIT_VNET_INET(curvnet);
 	struct in_ifaddr *ia;
 	struct ifnet *ifp;
 	int err;
@@ -741,7 +732,6 @@ SYSCTL_ULONG(_net_inet_raw, OID_AUTO, recvspace, CTLFLAG_RW,
 static int
 rip_attach(struct socket *so, int proto, struct thread *td)
 {
-	INIT_VNET_INET(so->so_vnet);
 	struct inpcb *inp;
 	int error;
 
@@ -775,7 +765,6 @@ rip_attach(struct socket *so, int proto, struct thread *td)
 static void
 rip_detach(struct socket *so)
 {
-	INIT_VNET_INET(so->so_vnet);
 	struct inpcb *inp;
 
 	inp = sotoinpcb(so);
@@ -815,7 +804,6 @@ rip_dodisconnect(struct socket *so, struct inpcb *inp)
 static void
 rip_abort(struct socket *so)
 {
-	INIT_VNET_INET(so->so_vnet);
 	struct inpcb *inp;
 
 	inp = sotoinpcb(so);
@@ -831,7 +819,6 @@ rip_abort(struct socket *so)
 static void
 rip_close(struct socket *so)
 {
-	INIT_VNET_INET(so->so_vnet);
 	struct inpcb *inp;
 
 	inp = sotoinpcb(so);
@@ -847,7 +834,6 @@ rip_close(struct socket *so)
 static int
 rip_disconnect(struct socket *so)
 {
-	INIT_VNET_INET(so->so_vnet);
 	struct inpcb *inp;
 
 	if ((so->so_state & SS_ISCONNECTED) == 0)
@@ -867,8 +853,6 @@ rip_disconnect(struct socket *so)
 static int
 rip_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
 {
-	INIT_VNET_NET(so->so_vnet);
-	INIT_VNET_INET(so->so_vnet);
 	struct sockaddr_in *addr = (struct sockaddr_in *)nam;
 	struct inpcb *inp;
 	int error;
@@ -903,8 +887,6 @@ rip_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
 static int
 rip_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
 {
-	INIT_VNET_NET(so->so_vnet);
-	INIT_VNET_INET(so->so_vnet);
 	struct sockaddr_in *addr = (struct sockaddr_in *)nam;
 	struct inpcb *inp;
 
@@ -975,7 +957,6 @@ rip_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam,
 static int
 rip_pcblist(SYSCTL_HANDLER_ARGS)
 {
-	INIT_VNET_INET(curvnet);
 	int error, i, n;
 	struct inpcb *inp, **inp_list;
 	inp_gen_t gencnt;