freebsd-dev/sys/net/if_var.h

911 lines
29 KiB
C
Raw Normal View History

/*-
* Copyright (c) 1982, 1986, 1989, 1993
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* From: @(#)if.h 8.1 (Berkeley) 6/10/93
1999-08-28 01:08:13 +00:00
* $FreeBSD$
*/
#ifndef _NET_IF_VAR_H_
#define _NET_IF_VAR_H_
/*
* Structures defining a network interface, providing a packet
* transport mechanism (ala level 0 of the PUP protocols).
*
* Each interface accepts output datagrams of a specified maximum
* length, and provides higher level routines with input datagrams
* received from its medium.
*
* Output occurs when the routine if_output is called, with three parameters:
* (*ifp->if_output)(ifp, m, dst, rt)
* Here m is the mbuf chain to be sent and dst is the destination address.
* The output routine encapsulates the supplied datagram if necessary,
* and then transmits it on its medium.
*
* On input, each interface unwraps the data received by it, and either
* places it on the input queue of an internetwork datagram routine
* and posts the associated software interrupt, or passes the datagram to a raw
* packet input routine.
*
* Routines exist for locating interfaces by their addresses
* or for locating an interface on a certain network, as well as more general
* routing and gateway routines maintaining information used to locate
* interfaces. These routines live in the files if.c and route.c
*/
#ifdef __STDC__
/*
* Forward structure declarations for function prototypes [sic].
*/
struct mbuf;
struct thread;
struct rtentry;
struct rt_addrinfo;
struct socket;
struct ether_header;
struct carp_if;
struct carp_softc;
2006-01-30 13:45:15 +00:00
struct ifvlantrunk;
struct route;
struct vnet;
#endif
#include <sys/queue.h> /* get TAILQ macros */
#ifdef _KERNEL
#include <sys/mbuf.h>
#include <sys/eventhandler.h>
#include <sys/buf_ring.h>
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)
2009-07-14 22:48:30 +00:00
#include <net/vnet.h>
#endif /* _KERNEL */
#include <sys/lock.h> /* XXX */
#include <sys/mutex.h> /* XXX */
#include <sys/rwlock.h> /* XXX */
#include <sys/sx.h> /* XXX */
#include <sys/event.h> /* XXX */
#include <sys/_task.h>
#define IF_DUNIT_NONE -1
#include <altq/if_altq.h>
TAILQ_HEAD(ifnethead, ifnet); /* we use TAILQs so that the order of */
TAILQ_HEAD(ifaddrhead, ifaddr); /* instantiation is preserved in the list */
TAILQ_HEAD(ifmultihead, ifmultiaddr);
TAILQ_HEAD(ifgrouphead, ifg_group);
/*
* Structure defining a queue for a network interface.
*/
struct ifqueue {
struct mbuf *ifq_head;
struct mbuf *ifq_tail;
int ifq_len;
int ifq_maxlen;
int ifq_drops;
struct mtx ifq_mtx;
};
/*
* Structure defining a network interface.
*
* (Would like to call this struct ``if'', but C isn't PL/1.)
*/
struct ifnet {
void *if_softc; /* pointer to driver state */
void *if_l2com; /* pointer to protocol bits */
Permit buiding kernels with options VIMAGE, restricted to only a single active network stack instance. Turning on options VIMAGE at compile time yields the following changes relative to default kernel build: 1) V_ accessor macros for virtualized variables resolve to structure fields via base pointers, instead of being resolved as fields in global structs or plain global variables. As an example, V_ifnet becomes: options VIMAGE: ((struct vnet_net *) vnet_net)->_ifnet default build: vnet_net_0._ifnet options VIMAGE_GLOBALS: ifnet 2) INIT_VNET_* macros will declare and set up base pointers to be used by V_ accessor macros, instead of resolving to whitespace: INIT_VNET_NET(ifp->if_vnet); becomes struct vnet_net *vnet_net = (ifp->if_vnet)->mod_data[VNET_MOD_NET]; 3) Memory for vnet modules registered via vnet_mod_register() is now allocated at run time in sys/kern/kern_vimage.c, instead of per vnet module structs being declared as globals. If required, vnet modules can now request the framework to provide them with allocated bzeroed memory by filling in the vmi_size field in their vmi_modinfo structures. 4) structs socket, ifnet, inpcbinfo, tcpcb and syncache_head are extended to hold a pointer to the parent vnet. options VIMAGE builds will fill in those fields as required. 5) curvnet is introduced as a new global variable in options VIMAGE builds, always pointing to the default and only struct vnet. 6) struct sysctl_oid has been extended with additional two fields to store major and minor virtualization module identifiers, oid_v_subs and oid_v_mod. SYSCTL_V_* family of macros will fill in those fields accordingly, and store the offset in the appropriate vnet container struct in oid_arg1. In sysctl handlers dealing with virtualized sysctls, the SYSCTL_RESOLVE_V_ARG1() macro will compute the address of the target variable and make it available in arg1 variable for further processing. Unused fields in structs vnet_inet, vnet_inet6 and vnet_ipfw have been deleted. Reviewed by: bz, rwatson Approved by: julian (mentor)
2009-04-30 13:36:26 +00:00
struct vnet *if_vnet; /* pointer to network stack instance */
TAILQ_ENTRY(ifnet) if_link; /* all struct ifnets are chained */
char if_xname[IFNAMSIZ]; /* external name (name + unit) */
const char *if_dname; /* driver name */
int if_dunit; /* unit or IF_DUNIT_NONE */
Start to address a number of races relating to use of ifnet pointers after the corresponding interface has been destroyed: (1) Add an ifnet refcount, ifp->if_refcount. Initialize it to 1 in if_alloc(), and modify if_free_type() to decrement and check the refcount. (2) Add new if_ref() and if_rele() interfaces to allow kernel code walking global interface lists to release IFNET_[RW]LOCK() yet keep the ifnet stable. Currently, if_rele() is a no-op wrapper around if_free(), but this may change in the future. (3) Add new ifnet field, if_alloctype, which caches the type passed to if_alloc(), but unlike if_type, won't be changed by drivers. This allows asynchronous free's of the interface after the driver has released it to still use the right type. Use that instead of the type passed to if_free_type(), but assert that they are the same (might have to rethink this if that doesn't work out). (4) Add a new ifnet_byindex_ref(), which looks up an interface by index and returns a reference rather than a pointer to it. (5) Fix if_alloc() to fully initialize the if_addr_mtx before hooking up the ifnet to global lists. (6) Modify sysctls in if_mib.c to use ifnet_byindex_ref() and release the ifnet when done. When this change is MFC'd, it will need to replace if_ispare fields rather than adding new fields in order to avoid breaking the binary interface. Once this change is MFC'd, if_free_type() should be removed, as its 'type' argument is now optional. This refcount is not appropriate for counting mbuf pkthdr references, and also not for counting entry into the device driver via ifnet function pointers. An rmlock may be appropriate for the latter. Rather, this is about ensuring data structure stability when reaching an ifnet via global ifnet lists and tables followed by copy in or out of userspace. MFC after: 3 weeks Reported by: mdtancsa Reviewed by: brooks
2009-04-21 22:43:32 +00:00
u_int if_refcount; /* reference count */
struct ifaddrhead if_addrhead; /* linked list of addresses per if */
/*
* if_addrhead is the list of all addresses associated to
* an interface.
* Some code in the kernel assumes that first element
* of the list has type AF_LINK, and contains sockaddr_dl
* addresses which store the link-level address and the name
* of the interface.
* However, access to the AF_LINK address through this
* field is deprecated. Use if_addr or ifaddr_byindex() instead.
*/
int if_pcount; /* number of promiscuous listeners */
struct carp_if *if_carp; /* carp interface structure */
struct bpf_if *if_bpf; /* packet filter structure */
u_short if_index; /* numeric abbreviation for this if */
short if_index_reserved; /* spare space to grow if_index */
2006-01-30 13:45:15 +00:00
struct ifvlantrunk *if_vlantrunk; /* pointer to 802.1q data */
int if_flags; /* up/down, broadcast, etc. */
int if_capabilities; /* interface features & capabilities */
int if_capenable; /* enabled features & capabilities */
void *if_linkmib; /* link-type-specific MIB data */
size_t if_linkmiblen; /* length of above data */
struct if_data if_data;
struct ifmultihead if_multiaddrs; /* multicast addresses configured */
int if_amcount; /* number of all-multicast requests */
/* procedure handles */
int (*if_output) /* output routine (enqueue) */
2002-03-19 21:54:18 +00:00
(struct ifnet *, struct mbuf *, struct sockaddr *,
struct route *);
void (*if_input) /* input routine (from h/w driver) */
(struct ifnet *, struct mbuf *);
void (*if_start) /* initiate output routine */
2002-03-19 21:54:18 +00:00
(struct ifnet *);
int (*if_ioctl) /* ioctl routine */
2002-03-19 21:54:18 +00:00
(struct ifnet *, u_long, caddr_t);
void (*if_init) /* Init routine */
2002-03-19 21:54:18 +00:00
(void *);
int (*if_resolvemulti) /* validate/resolve multicast */
2002-03-19 21:54:18 +00:00
(struct ifnet *, struct sockaddr **, struct sockaddr *);
void (*if_qflush) /* flush any queues */
(struct ifnet *);
int (*if_transmit) /* initiate output routine */
(struct ifnet *, struct mbuf *);
void (*if_reassign) /* reassign to vnet routine */
(struct ifnet *, struct vnet *, char *);
struct vnet *if_home_vnet; /* where this ifnet originates from */
struct ifaddr *if_addr; /* pointer to link-level address */
void *if_llsoftc; /* link layer softc */
int if_drv_flags; /* driver-managed status flags */
struct ifaltq if_snd; /* output queue (includes altq) */
const u_int8_t *if_broadcastaddr; /* linklevel broadcast bytestring */
void *if_bridge; /* bridge glue */
Modify the MAC Framework so that instead of embedding a (struct label) in various kernel objects to represent security data, we embed a (struct label *) pointer, which now references labels allocated using a UMA zone (mac_label.c). This allows the size and shape of struct label to be varied without changing the size and shape of these kernel objects, which become part of the frozen ABI with 5-STABLE. This opens the door for boot-time selection of the number of label slots, and hence changes to the bound on the number of simultaneous labeled policies at boot-time instead of compile-time. This also makes it easier to embed label references in new objects as required for locking/caching with fine-grained network stack locking, such as inpcb structures. This change also moves us further in the direction of hiding the structure of kernel objects from MAC policy modules, not to mention dramatically reducing the number of '&' symbols appearing in both the MAC Framework and MAC policy modules, and improving readability. While this results in minimal performance change with MAC enabled, it will observably shrink the size of a number of critical kernel data structures for the !MAC case, and should have a small (but measurable) performance benefit (i.e., struct vnode, struct socket) do to memory conservation and reduced cost of zeroing memory. NOTE: Users of MAC must recompile their kernel and all MAC modules as a result of this change. Because this is an API change, third party MAC modules will also need to be updated to make less use of the '&' symbol. Suggestions from: bmilekic Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2003-11-12 03:14:31 +00:00
struct label *if_label; /* interface MAC label */
/* these are only used by IPv6 */
void *if_unused[2];
void *if_afdata[AF_MAX];
int if_afdata_initialized;
struct rwlock if_afdata_lock;
struct task if_linktask; /* task for link change events */
struct rwlock if_addr_lock; /* lock to protect address lists */
LIST_ENTRY(ifnet) if_clones; /* interfaces of a cloner */
TAILQ_HEAD(, ifg_list) if_groups; /* linked list of groups per if */
/* protected by if_addr_lock */
void *if_pf_kif;
void *if_lagg; /* lagg glue */
char *if_description; /* interface description */
u_int if_fib; /* interface FIB */
u_char if_alloctype; /* if_type at time of allocation */
/*
* Spare fields are added so that we can modify sensitive data
* structures without changing the kernel binary interface, and must
* be used with care where binary compatibility is required.
*/
char if_cspare[3];
int if_ispare[4];
void *if_pspare[8]; /* 1 netmap, 7 TDB */
};
2002-03-19 21:54:18 +00:00
typedef void if_init_f_t(void *);
/*
* XXX These aliases are terribly dangerous because they could apply
* to anything.
*/
#define if_mtu if_data.ifi_mtu
#define if_type if_data.ifi_type
#define if_physical if_data.ifi_physical
#define if_addrlen if_data.ifi_addrlen
#define if_hdrlen if_data.ifi_hdrlen
#define if_metric if_data.ifi_metric
#define if_link_state if_data.ifi_link_state
#define if_baudrate if_data.ifi_baudrate
#define if_hwassist if_data.ifi_hwassist
#define if_ipackets if_data.ifi_ipackets
#define if_ierrors if_data.ifi_ierrors
#define if_opackets if_data.ifi_opackets
#define if_oerrors if_data.ifi_oerrors
#define if_collisions if_data.ifi_collisions
#define if_ibytes if_data.ifi_ibytes
#define if_obytes if_data.ifi_obytes
#define if_imcasts if_data.ifi_imcasts
#define if_omcasts if_data.ifi_omcasts
#define if_iqdrops if_data.ifi_iqdrops
#define if_noproto if_data.ifi_noproto
#define if_lastchange if_data.ifi_lastchange
/* for compatibility with other BSDs */
#define if_addrlist if_addrhead
#define if_list if_link
#define if_name(ifp) ((ifp)->if_xname)
/*
* Locks for address lists on the network interface.
*/
#define IF_ADDR_LOCK_INIT(if) rw_init(&(if)->if_addr_lock, "if_addr_lock")
#define IF_ADDR_LOCK_DESTROY(if) rw_destroy(&(if)->if_addr_lock)
#define IF_ADDR_WLOCK(if) rw_wlock(&(if)->if_addr_lock)
#define IF_ADDR_WUNLOCK(if) rw_wunlock(&(if)->if_addr_lock)
#define IF_ADDR_RLOCK(if) rw_rlock(&(if)->if_addr_lock)
#define IF_ADDR_RUNLOCK(if) rw_runlock(&(if)->if_addr_lock)
#define IF_ADDR_LOCK_ASSERT(if) rw_assert(&(if)->if_addr_lock, RA_LOCKED)
#define IF_ADDR_WLOCK_ASSERT(if) rw_assert(&(if)->if_addr_lock, RA_WLOCKED)
/*
* Function variations on locking macros intended to be used by loadable
* kernel modules in order to divorce them from the internals of address list
* locking.
*/
void if_addr_rlock(struct ifnet *ifp); /* if_addrhead */
void if_addr_runlock(struct ifnet *ifp); /* if_addrhead */
void if_maddr_rlock(struct ifnet *ifp); /* if_multiaddrs */
void if_maddr_runlock(struct ifnet *ifp); /* if_multiaddrs */
/*
* Output queues (ifp->if_snd) and slow device input queues (*ifp->if_slowq)
* are queues of messages stored on ifqueue structures
* (defined above). Entries are added to and deleted from these structures
* by these macros, which should be called with ipl raised to splimp().
*/
Change and clean the mutex lock interface. mtx_enter(lock, type) becomes: mtx_lock(lock) for sleep locks (MTX_DEF-initialized locks) mtx_lock_spin(lock) for spin locks (MTX_SPIN-initialized) similarily, for releasing a lock, we now have: mtx_unlock(lock) for MTX_DEF and mtx_unlock_spin(lock) for MTX_SPIN. We change the caller interface for the two different types of locks because the semantics are entirely different for each case, and this makes it explicitly clear and, at the same time, it rids us of the extra `type' argument. The enter->lock and exit->unlock change has been made with the idea that we're "locking data" and not "entering locked code" in mind. Further, remove all additional "flags" previously passed to the lock acquire/release routines with the exception of two: MTX_QUIET and MTX_NOSWITCH The functionality of these flags is preserved and they can be passed to the lock/unlock routines by calling the corresponding wrappers: mtx_{lock, unlock}_flags(lock, flag(s)) and mtx_{lock, unlock}_spin_flags(lock, flag(s)) for MTX_DEF and MTX_SPIN locks, respectively. Re-inline some lock acq/rel code; in the sleep lock case, we only inline the _obtain_lock()s in order to ensure that the inlined code fits into a cache line. In the spin lock case, we inline recursion and actually only perform a function call if we need to spin. This change has been made with the idea that we generally tend to avoid spin locks and that also the spin locks that we do have and are heavily used (i.e. sched_lock) do recurse, and therefore in an effort to reduce function call overhead for some architectures (such as alpha), we inline recursion for this case. Create a new malloc type for the witness code and retire from using the M_DEV type. The new type is called M_WITNESS and is only declared if WITNESS is enabled. Begin cleaning up some machdep/mutex.h code - specifically updated the "optimized" inlined code in alpha/mutex.h and wrote MTX_LOCK_SPIN and MTX_UNLOCK_SPIN asm macros for the i386/mutex.h as we presently need those. Finally, caught up to the interface changes in all sys code. Contributors: jake, jhb, jasone (in no particular order)
2001-02-09 06:11:45 +00:00
#define IF_LOCK(ifq) mtx_lock(&(ifq)->ifq_mtx)
#define IF_UNLOCK(ifq) mtx_unlock(&(ifq)->ifq_mtx)
#define IF_LOCK_ASSERT(ifq) mtx_assert(&(ifq)->ifq_mtx, MA_OWNED)
#define _IF_QFULL(ifq) ((ifq)->ifq_len >= (ifq)->ifq_maxlen)
#define _IF_DROP(ifq) ((ifq)->ifq_drops++)
#define _IF_QLEN(ifq) ((ifq)->ifq_len)
#define _IF_ENQUEUE(ifq, m) do { \
(m)->m_nextpkt = NULL; \
if ((ifq)->ifq_tail == NULL) \
(ifq)->ifq_head = m; \
else \
(ifq)->ifq_tail->m_nextpkt = m; \
(ifq)->ifq_tail = m; \
(ifq)->ifq_len++; \
} while (0)
#define IF_ENQUEUE(ifq, m) do { \
IF_LOCK(ifq); \
_IF_ENQUEUE(ifq, m); \
IF_UNLOCK(ifq); \
} while (0)
#define _IF_PREPEND(ifq, m) do { \
(m)->m_nextpkt = (ifq)->ifq_head; \
if ((ifq)->ifq_tail == NULL) \
(ifq)->ifq_tail = (m); \
(ifq)->ifq_head = (m); \
(ifq)->ifq_len++; \
} while (0)
#define IF_PREPEND(ifq, m) do { \
IF_LOCK(ifq); \
_IF_PREPEND(ifq, m); \
IF_UNLOCK(ifq); \
} while (0)
#define _IF_DEQUEUE(ifq, m) do { \
(m) = (ifq)->ifq_head; \
if (m) { \
if (((ifq)->ifq_head = (m)->m_nextpkt) == NULL) \
(ifq)->ifq_tail = NULL; \
(m)->m_nextpkt = NULL; \
(ifq)->ifq_len--; \
} \
} while (0)
#define IF_DEQUEUE(ifq, m) do { \
IF_LOCK(ifq); \
_IF_DEQUEUE(ifq, m); \
IF_UNLOCK(ifq); \
} while (0)
#define _IF_DEQUEUE_ALL(ifq, m) do { \
(m) = (ifq)->ifq_head; \
(ifq)->ifq_head = (ifq)->ifq_tail = NULL; \
(ifq)->ifq_len = 0; \
} while (0)
#define IF_DEQUEUE_ALL(ifq, m) do { \
IF_LOCK(ifq); \
_IF_DEQUEUE_ALL(ifq, m); \
IF_UNLOCK(ifq); \
} while (0)
#define _IF_POLL(ifq, m) ((m) = (ifq)->ifq_head)
#define IF_POLL(ifq, m) _IF_POLL(ifq, m)
#define _IF_DRAIN(ifq) do { \
struct mbuf *m; \
for (;;) { \
_IF_DEQUEUE(ifq, m); \
if (m == NULL) \
break; \
m_freem(m); \
} \
} while (0)
#define IF_DRAIN(ifq) do { \
IF_LOCK(ifq); \
_IF_DRAIN(ifq); \
IF_UNLOCK(ifq); \
} while(0)
#ifdef _KERNEL
/* interface link layer address change event */
typedef void (*iflladdr_event_handler_t)(void *, struct ifnet *);
EVENTHANDLER_DECLARE(iflladdr_event, iflladdr_event_handler_t);
/* interface address change event */
typedef void (*ifaddr_event_handler_t)(void *, struct ifnet *);
EVENTHANDLER_DECLARE(ifaddr_event, ifaddr_event_handler_t);
/* new interface arrival event */
typedef void (*ifnet_arrival_event_handler_t)(void *, struct ifnet *);
EVENTHANDLER_DECLARE(ifnet_arrival_event, ifnet_arrival_event_handler_t);
/* interface departure event */
typedef void (*ifnet_departure_event_handler_t)(void *, struct ifnet *);
EVENTHANDLER_DECLARE(ifnet_departure_event, ifnet_departure_event_handler_t);
/* Interface link state change event */
typedef void (*ifnet_link_event_handler_t)(void *, struct ifnet *, int);
EVENTHANDLER_DECLARE(ifnet_link_event, ifnet_link_event_handler_t);
/*
* interface groups
*/
struct ifg_group {
char ifg_group[IFNAMSIZ];
u_int ifg_refcnt;
void *ifg_pf_kif;
TAILQ_HEAD(, ifg_member) ifg_members;
TAILQ_ENTRY(ifg_group) ifg_next;
};
struct ifg_member {
TAILQ_ENTRY(ifg_member) ifgm_next;
struct ifnet *ifgm_ifp;
};
struct ifg_list {
struct ifg_group *ifgl_group;
TAILQ_ENTRY(ifg_list) ifgl_next;
};
/* group attach event */
typedef void (*group_attach_event_handler_t)(void *, struct ifg_group *);
EVENTHANDLER_DECLARE(group_attach_event, group_attach_event_handler_t);
/* group detach event */
typedef void (*group_detach_event_handler_t)(void *, struct ifg_group *);
EVENTHANDLER_DECLARE(group_detach_event, group_detach_event_handler_t);
/* group change event */
typedef void (*group_change_event_handler_t)(void *, const char *);
EVENTHANDLER_DECLARE(group_change_event, group_change_event_handler_t);
#define IF_AFDATA_LOCK_INIT(ifp) \
rw_init(&(ifp)->if_afdata_lock, "if_afdata")
#define IF_AFDATA_WLOCK(ifp) rw_wlock(&(ifp)->if_afdata_lock)
#define IF_AFDATA_RLOCK(ifp) rw_rlock(&(ifp)->if_afdata_lock)
#define IF_AFDATA_WUNLOCK(ifp) rw_wunlock(&(ifp)->if_afdata_lock)
#define IF_AFDATA_RUNLOCK(ifp) rw_runlock(&(ifp)->if_afdata_lock)
#define IF_AFDATA_LOCK(ifp) IF_AFDATA_WLOCK(ifp)
#define IF_AFDATA_UNLOCK(ifp) IF_AFDATA_WUNLOCK(ifp)
#define IF_AFDATA_TRYLOCK(ifp) rw_try_wlock(&(ifp)->if_afdata_lock)
#define IF_AFDATA_DESTROY(ifp) rw_destroy(&(ifp)->if_afdata_lock)
#define IF_AFDATA_LOCK_ASSERT(ifp) rw_assert(&(ifp)->if_afdata_lock, RA_LOCKED)
#define IF_AFDATA_RLOCK_ASSERT(ifp) rw_assert(&(ifp)->if_afdata_lock, RA_RLOCKED)
#define IF_AFDATA_WLOCK_ASSERT(ifp) rw_assert(&(ifp)->if_afdata_lock, RA_WLOCKED)
#define IF_AFDATA_UNLOCK_ASSERT(ifp) rw_assert(&(ifp)->if_afdata_lock, RA_UNLOCKED)
int if_handoff(struct ifqueue *ifq, struct mbuf *m, struct ifnet *ifp,
int adjust);
#define IF_HANDOFF(ifq, m, ifp) \
if_handoff((struct ifqueue *)ifq, m, ifp, 0)
#define IF_HANDOFF_ADJ(ifq, m, ifp, adj) \
if_handoff((struct ifqueue *)ifq, m, ifp, adj)
void if_start(struct ifnet *);
#define IFQ_ENQUEUE(ifq, m, err) \
do { \
IF_LOCK(ifq); \
if (ALTQ_IS_ENABLED(ifq)) \
ALTQ_ENQUEUE(ifq, m, NULL, err); \
else { \
if (_IF_QFULL(ifq)) { \
m_freem(m); \
(err) = ENOBUFS; \
} else { \
_IF_ENQUEUE(ifq, m); \
(err) = 0; \
} \
} \
if (err) \
(ifq)->ifq_drops++; \
IF_UNLOCK(ifq); \
} while (0)
#define IFQ_DEQUEUE_NOLOCK(ifq, m) \
do { \
if (TBR_IS_ENABLED(ifq)) \
(m) = tbr_dequeue_ptr(ifq, ALTDQ_REMOVE); \
else if (ALTQ_IS_ENABLED(ifq)) \
ALTQ_DEQUEUE(ifq, m); \
else \
_IF_DEQUEUE(ifq, m); \
} while (0)
#define IFQ_DEQUEUE(ifq, m) \
do { \
IF_LOCK(ifq); \
IFQ_DEQUEUE_NOLOCK(ifq, m); \
IF_UNLOCK(ifq); \
} while (0)
#define IFQ_POLL_NOLOCK(ifq, m) \
do { \
if (TBR_IS_ENABLED(ifq)) \
(m) = tbr_dequeue_ptr(ifq, ALTDQ_POLL); \
else if (ALTQ_IS_ENABLED(ifq)) \
ALTQ_POLL(ifq, m); \
else \
_IF_POLL(ifq, m); \
} while (0)
#define IFQ_POLL(ifq, m) \
do { \
IF_LOCK(ifq); \
IFQ_POLL_NOLOCK(ifq, m); \
IF_UNLOCK(ifq); \
} while (0)
#define IFQ_PURGE_NOLOCK(ifq) \
do { \
if (ALTQ_IS_ENABLED(ifq)) { \
ALTQ_PURGE(ifq); \
} else \
_IF_DRAIN(ifq); \
} while (0)
#define IFQ_PURGE(ifq) \
do { \
IF_LOCK(ifq); \
IFQ_PURGE_NOLOCK(ifq); \
IF_UNLOCK(ifq); \
} while (0)
#define IFQ_SET_READY(ifq) \
do { ((ifq)->altq_flags |= ALTQF_READY); } while (0)
#define IFQ_LOCK(ifq) IF_LOCK(ifq)
#define IFQ_UNLOCK(ifq) IF_UNLOCK(ifq)
#define IFQ_LOCK_ASSERT(ifq) IF_LOCK_ASSERT(ifq)
#define IFQ_IS_EMPTY(ifq) ((ifq)->ifq_len == 0)
#define IFQ_INC_LEN(ifq) ((ifq)->ifq_len++)
#define IFQ_DEC_LEN(ifq) (--(ifq)->ifq_len)
#define IFQ_INC_DROPS(ifq) ((ifq)->ifq_drops++)
#define IFQ_SET_MAXLEN(ifq, len) ((ifq)->ifq_maxlen = (len))
/*
* The IFF_DRV_OACTIVE test should really occur in the device driver, not in
* the handoff logic, as that flag is locked by the device driver.
*/
#define IFQ_HANDOFF_ADJ(ifp, m, adj, err) \
do { \
int len; \
short mflags; \
\
len = (m)->m_pkthdr.len; \
mflags = (m)->m_flags; \
IFQ_ENQUEUE(&(ifp)->if_snd, m, err); \
if ((err) == 0) { \
(ifp)->if_obytes += len + (adj); \
if (mflags & M_MCAST) \
(ifp)->if_omcasts++; \
if (((ifp)->if_drv_flags & IFF_DRV_OACTIVE) == 0) \
if_start(ifp); \
} \
} while (0)
#define IFQ_HANDOFF(ifp, m, err) \
2004-06-15 03:40:39 +00:00
IFQ_HANDOFF_ADJ(ifp, m, 0, err)
#define IFQ_DRV_DEQUEUE(ifq, m) \
do { \
(m) = (ifq)->ifq_drv_head; \
if (m) { \
if (((ifq)->ifq_drv_head = (m)->m_nextpkt) == NULL) \
(ifq)->ifq_drv_tail = NULL; \
(m)->m_nextpkt = NULL; \
(ifq)->ifq_drv_len--; \
} else { \
IFQ_LOCK(ifq); \
IFQ_DEQUEUE_NOLOCK(ifq, m); \
while ((ifq)->ifq_drv_len < (ifq)->ifq_drv_maxlen) { \
struct mbuf *m0; \
IFQ_DEQUEUE_NOLOCK(ifq, m0); \
if (m0 == NULL) \
break; \
m0->m_nextpkt = NULL; \
if ((ifq)->ifq_drv_tail == NULL) \
(ifq)->ifq_drv_head = m0; \
else \
(ifq)->ifq_drv_tail->m_nextpkt = m0; \
(ifq)->ifq_drv_tail = m0; \
(ifq)->ifq_drv_len++; \
} \
IFQ_UNLOCK(ifq); \
} \
} while (0)
#define IFQ_DRV_PREPEND(ifq, m) \
do { \
(m)->m_nextpkt = (ifq)->ifq_drv_head; \
if ((ifq)->ifq_drv_tail == NULL) \
(ifq)->ifq_drv_tail = (m); \
(ifq)->ifq_drv_head = (m); \
(ifq)->ifq_drv_len++; \
} while (0)
#define IFQ_DRV_IS_EMPTY(ifq) \
(((ifq)->ifq_drv_len == 0) && ((ifq)->ifq_len == 0))
#define IFQ_DRV_PURGE(ifq) \
do { \
struct mbuf *m, *n = (ifq)->ifq_drv_head; \
while((m = n) != NULL) { \
n = m->m_nextpkt; \
m_freem(m); \
} \
(ifq)->ifq_drv_head = (ifq)->ifq_drv_tail = NULL; \
(ifq)->ifq_drv_len = 0; \
IFQ_PURGE(ifq); \
} while (0)
#ifdef _KERNEL
static __inline void
drbr_stats_update(struct ifnet *ifp, int len, int mflags)
{
#ifndef NO_SLOW_STATS
ifp->if_obytes += len;
if (mflags & M_MCAST)
ifp->if_omcasts++;
#endif
}
static __inline int
drbr_enqueue(struct ifnet *ifp, struct buf_ring *br, struct mbuf *m)
{
int error = 0;
int len = m->m_pkthdr.len;
int mflags = m->m_flags;
#ifdef ALTQ
if (ALTQ_IS_ENABLED(&ifp->if_snd)) {
IFQ_ENQUEUE(&ifp->if_snd, m, error);
return (error);
}
#endif
if ((error = buf_ring_enqueue_bytes(br, m, len)) == ENOBUFS) {
br->br_drops++;
m_freem(m);
} else
drbr_stats_update(ifp, len, mflags);
return (error);
}
static __inline void
drbr_flush(struct ifnet *ifp, struct buf_ring *br)
{
struct mbuf *m;
#ifdef ALTQ
if (ifp != NULL && ALTQ_IS_ENABLED(&ifp->if_snd))
IFQ_PURGE(&ifp->if_snd);
#endif
while ((m = buf_ring_dequeue_sc(br)) != NULL)
m_freem(m);
}
static __inline void
drbr_free(struct buf_ring *br, struct malloc_type *type)
{
drbr_flush(NULL, br);
buf_ring_free(br, type);
}
static __inline struct mbuf *
drbr_dequeue(struct ifnet *ifp, struct buf_ring *br)
{
#ifdef ALTQ
struct mbuf *m;
if (ALTQ_IS_ENABLED(&ifp->if_snd)) {
IFQ_DEQUEUE(&ifp->if_snd, m);
return (m);
}
#endif
return (buf_ring_dequeue_sc(br));
}
static __inline struct mbuf *
drbr_dequeue_cond(struct ifnet *ifp, struct buf_ring *br,
int (*func) (struct mbuf *, void *), void *arg)
{
struct mbuf *m;
#ifdef ALTQ
if (ALTQ_IS_ENABLED(&ifp->if_snd)) {
IFQ_LOCK(&ifp->if_snd);
IFQ_POLL_NOLOCK(&ifp->if_snd, m);
if (m != NULL && func(m, arg) == 0) {
IFQ_UNLOCK(&ifp->if_snd);
return (NULL);
}
IFQ_DEQUEUE_NOLOCK(&ifp->if_snd, m);
IFQ_UNLOCK(&ifp->if_snd);
return (m);
}
#endif
m = buf_ring_peek(br);
if (m == NULL || func(m, arg) == 0)
return (NULL);
return (buf_ring_dequeue_sc(br));
}
static __inline int
drbr_empty(struct ifnet *ifp, struct buf_ring *br)
{
#ifdef ALTQ
if (ALTQ_IS_ENABLED(&ifp->if_snd))
return (IFQ_IS_EMPTY(&ifp->if_snd));
#endif
return (buf_ring_empty(br));
}
static __inline int
drbr_needs_enqueue(struct ifnet *ifp, struct buf_ring *br)
{
#ifdef ALTQ
if (ALTQ_IS_ENABLED(&ifp->if_snd))
return (1);
#endif
return (!buf_ring_empty(br));
}
static __inline int
drbr_inuse(struct ifnet *ifp, struct buf_ring *br)
{
#ifdef ALTQ
if (ALTQ_IS_ENABLED(&ifp->if_snd))
return (ifp->if_snd.ifq_len);
#endif
return (buf_ring_count(br));
}
#endif
/*
* 72 was chosen below because it is the size of a TCP/IP
* header (40) + the minimum mss (32).
*/
#define IF_MINMTU 72
#define IF_MAXMTU 65535
#define TOEDEV(ifp) ((ifp)->if_llsoftc)
#endif /* _KERNEL */
/*
* The ifaddr structure contains information about one address
* of an interface. They are maintained by the different address families,
* are allocated and attached when an address is set, and are linked
* together so all addresses for an interface can be located.
*
* NOTE: a 'struct ifaddr' is always at the beginning of a larger
* chunk of malloc'ed memory, where we store the three addresses
* (ifa_addr, ifa_dstaddr and ifa_netmask) referenced here.
*/
struct ifaddr {
struct sockaddr *ifa_addr; /* address of interface */
struct sockaddr *ifa_dstaddr; /* other end of p-to-p link */
#define ifa_broadaddr ifa_dstaddr /* broadcast address interface */
struct sockaddr *ifa_netmask; /* used to determine subnet */
struct if_data if_data; /* not all members are meaningful */
struct ifnet *ifa_ifp; /* back-pointer to interface */
struct carp_softc *ifa_carp; /* pointer to CARP data */
TAILQ_ENTRY(ifaddr) ifa_link; /* queue macro glue */
void (*ifa_rtrequest) /* check or clean routes (+ or -)'d */
2002-03-19 21:54:18 +00:00
(int, struct rtentry *, struct rt_addrinfo *);
u_short ifa_flags; /* mostly rt_flags for cloning */
u_int ifa_refcnt; /* references to this structure */
int ifa_metric; /* cost of going out this interface */
int (*ifa_claim_addr) /* check if an addr goes to this if */
2002-03-19 21:54:18 +00:00
(struct ifaddr *, struct sockaddr *);
2002-12-18 11:46:59 +00:00
struct mtx ifa_mtx;
};
#define IFA_ROUTE RTF_UP /* route installed */
#define IFA_RTSELF RTF_HOST /* loopback route to self installed */
/* for compatibility with other BSDs */
#define ifa_list ifa_link
#ifdef _KERNEL
2002-12-18 11:46:59 +00:00
#define IFA_LOCK(ifa) mtx_lock(&(ifa)->ifa_mtx)
#define IFA_UNLOCK(ifa) mtx_unlock(&(ifa)->ifa_mtx)
void ifa_free(struct ifaddr *ifa);
void ifa_init(struct ifaddr *ifa);
void ifa_ref(struct ifaddr *ifa);
#endif
2002-12-18 11:46:59 +00:00
/*
* Multicast address structure. This is analogous to the ifaddr
* structure except that it keeps track of multicast addresses.
*/
struct ifmultiaddr {
TAILQ_ENTRY(ifmultiaddr) ifma_link; /* queue macro glue */
struct sockaddr *ifma_addr; /* address this membership is for */
struct sockaddr *ifma_lladdr; /* link-layer translation, if any */
struct ifnet *ifma_ifp; /* back-pointer to interface */
u_int ifma_refcount; /* reference count */
void *ifma_protospec; /* protocol-specific state, if any */
struct ifmultiaddr *ifma_llifma; /* pointer to ifma for ifma_lladdr */
};
#ifdef _KERNEL
extern struct rwlock ifnet_rwlock;
extern struct sx ifnet_sxlock;
#define IFNET_LOCK_INIT() do { \
rw_init_flags(&ifnet_rwlock, "ifnet_rw", RW_RECURSE); \
sx_init_flags(&ifnet_sxlock, "ifnet_sx", SX_RECURSE); \
} while(0)
#define IFNET_WLOCK() do { \
sx_xlock(&ifnet_sxlock); \
rw_wlock(&ifnet_rwlock); \
} while (0)
#define IFNET_WUNLOCK() do { \
rw_wunlock(&ifnet_rwlock); \
sx_xunlock(&ifnet_sxlock); \
} while (0)
/*
* To assert the ifnet lock, you must know not only whether it's for read or
* write, but also whether it was acquired with sleep support or not.
*/
#define IFNET_RLOCK_ASSERT() sx_assert(&ifnet_sxlock, SA_SLOCKED)
#define IFNET_RLOCK_NOSLEEP_ASSERT() rw_assert(&ifnet_rwlock, RA_RLOCKED)
#define IFNET_WLOCK_ASSERT() do { \
sx_assert(&ifnet_sxlock, SA_XLOCKED); \
rw_assert(&ifnet_rwlock, RA_WLOCKED); \
} while (0)
#define IFNET_RLOCK() sx_slock(&ifnet_sxlock)
#define IFNET_RLOCK_NOSLEEP() rw_rlock(&ifnet_rwlock)
#define IFNET_RUNLOCK() sx_sunlock(&ifnet_sxlock)
#define IFNET_RUNLOCK_NOSLEEP() rw_runlock(&ifnet_rwlock)
2002-12-22 05:35:03 +00:00
Start to address a number of races relating to use of ifnet pointers after the corresponding interface has been destroyed: (1) Add an ifnet refcount, ifp->if_refcount. Initialize it to 1 in if_alloc(), and modify if_free_type() to decrement and check the refcount. (2) Add new if_ref() and if_rele() interfaces to allow kernel code walking global interface lists to release IFNET_[RW]LOCK() yet keep the ifnet stable. Currently, if_rele() is a no-op wrapper around if_free(), but this may change in the future. (3) Add new ifnet field, if_alloctype, which caches the type passed to if_alloc(), but unlike if_type, won't be changed by drivers. This allows asynchronous free's of the interface after the driver has released it to still use the right type. Use that instead of the type passed to if_free_type(), but assert that they are the same (might have to rethink this if that doesn't work out). (4) Add a new ifnet_byindex_ref(), which looks up an interface by index and returns a reference rather than a pointer to it. (5) Fix if_alloc() to fully initialize the if_addr_mtx before hooking up the ifnet to global lists. (6) Modify sysctls in if_mib.c to use ifnet_byindex_ref() and release the ifnet when done. When this change is MFC'd, it will need to replace if_ispare fields rather than adding new fields in order to avoid breaking the binary interface. Once this change is MFC'd, if_free_type() should be removed, as its 'type' argument is now optional. This refcount is not appropriate for counting mbuf pkthdr references, and also not for counting entry into the device driver via ifnet function pointers. An rmlock may be appropriate for the latter. Rather, this is about ensuring data structure stability when reaching an ifnet via global ifnet lists and tables followed by copy in or out of userspace. MFC after: 3 weeks Reported by: mdtancsa Reviewed by: brooks
2009-04-21 22:43:32 +00:00
/*
* Look up an ifnet given its index; the _ref variant also acquires a
* reference that must be freed using if_rele(). It is almost always a bug
* to call ifnet_byindex() instead if ifnet_byindex_ref().
*/
struct ifnet *ifnet_byindex(u_short idx);
Change the curvnet variable from a global const struct vnet *, previously always pointing to the default vnet context, to a dynamically changing thread-local one. The currvnet context should be set on entry to networking code via CURVNET_SET() macros, and reverted to previous state via CURVNET_RESTORE(). Recursions on curvnet are permitted, though strongly discuouraged. This change should have no functional impact on nooptions VIMAGE kernel builds, where CURVNET_* macros expand to whitespace. The curthread->td_vnet (aka curvnet) variable's purpose is to be an indicator of the vnet context in which the current network-related operation takes place, in case we cannot deduce the current vnet context from any other source, such as by looking at mbuf's m->m_pkthdr.rcvif->if_vnet, sockets's so->so_vnet etc. Moreover, so far curvnet has turned out to be an invaluable consistency checking aid: it helps to catch cases when sockets, ifnets or any other vnet-aware structures may have leaked from one vnet to another. The exact placement of the CURVNET_SET() / CURVNET_RESTORE() macros was a result of an empirical iterative process, whith an aim to reduce recursions on CURVNET_SET() to a minimum, while still reducing the scope of CURVNET_SET() to networking only operations - the alternative would be calling CURVNET_SET() on each system call entry. In general, curvnet has to be set in three typicall cases: when processing socket-related requests from userspace or from within the kernel; when processing inbound traffic flowing from device drivers to upper layers of the networking stack, and when executing timer-driven networking functions. This change also introduces a DDB subcommand to show the list of all vnet instances. Approved by: julian (mentor)
2009-05-05 10:56:12 +00:00
struct ifnet *ifnet_byindex_locked(u_short idx);
Start to address a number of races relating to use of ifnet pointers after the corresponding interface has been destroyed: (1) Add an ifnet refcount, ifp->if_refcount. Initialize it to 1 in if_alloc(), and modify if_free_type() to decrement and check the refcount. (2) Add new if_ref() and if_rele() interfaces to allow kernel code walking global interface lists to release IFNET_[RW]LOCK() yet keep the ifnet stable. Currently, if_rele() is a no-op wrapper around if_free(), but this may change in the future. (3) Add new ifnet field, if_alloctype, which caches the type passed to if_alloc(), but unlike if_type, won't be changed by drivers. This allows asynchronous free's of the interface after the driver has released it to still use the right type. Use that instead of the type passed to if_free_type(), but assert that they are the same (might have to rethink this if that doesn't work out). (4) Add a new ifnet_byindex_ref(), which looks up an interface by index and returns a reference rather than a pointer to it. (5) Fix if_alloc() to fully initialize the if_addr_mtx before hooking up the ifnet to global lists. (6) Modify sysctls in if_mib.c to use ifnet_byindex_ref() and release the ifnet when done. When this change is MFC'd, it will need to replace if_ispare fields rather than adding new fields in order to avoid breaking the binary interface. Once this change is MFC'd, if_free_type() should be removed, as its 'type' argument is now optional. This refcount is not appropriate for counting mbuf pkthdr references, and also not for counting entry into the device driver via ifnet function pointers. An rmlock may be appropriate for the latter. Rather, this is about ensuring data structure stability when reaching an ifnet via global ifnet lists and tables followed by copy in or out of userspace. MFC after: 3 weeks Reported by: mdtancsa Reviewed by: brooks
2009-04-21 22:43:32 +00:00
struct ifnet *ifnet_byindex_ref(u_short idx);
2008-08-20 03:14:48 +00:00
/*
* Given the index, ifaddr_byindex() returns the one and only
* link-level ifaddr for the interface. You are not supposed to use
* it to traverse the list of addresses associated to the interface.
*/
struct ifaddr *ifaddr_byindex(u_short idx);
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)
2009-07-14 22:48:30 +00:00
VNET_DECLARE(struct ifnethead, ifnet);
VNET_DECLARE(struct ifgrouphead, ifg_head);
VNET_DECLARE(int, if_index);
VNET_DECLARE(struct ifnet *, loif); /* first loopback interface */
VNET_DECLARE(int, useloopback);
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)
2009-07-14 22:48:30 +00:00
#define V_ifnet VNET(ifnet)
#define V_ifg_head VNET(ifg_head)
#define V_if_index VNET(if_index)
#define V_loif VNET(loif)
#define V_useloopback VNET(useloopback)
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)
2009-07-14 22:48:30 +00:00
extern int ifqmaxlen;
int if_addgroup(struct ifnet *, const char *);
int if_delgroup(struct ifnet *, const char *);
2002-03-19 21:54:18 +00:00
int if_addmulti(struct ifnet *, struct sockaddr *, struct ifmultiaddr **);
int if_allmulti(struct ifnet *, int);
struct ifnet* if_alloc(u_char);
2002-03-19 21:54:18 +00:00
void if_attach(struct ifnet *);
void if_dead(struct ifnet *);
2002-03-19 21:54:18 +00:00
int if_delmulti(struct ifnet *, struct sockaddr *);
void if_delmulti_ifma(struct ifmultiaddr *);
2002-03-19 21:54:18 +00:00
void if_detach(struct ifnet *);
void if_vmove(struct ifnet *, struct vnet *);
void if_purgeaddrs(struct ifnet *);
void if_delallmulti(struct ifnet *);
2002-03-19 21:54:18 +00:00
void if_down(struct ifnet *);
struct ifmultiaddr *
if_findmulti(struct ifnet *, struct sockaddr *);
void if_free(struct ifnet *);
void if_initname(struct ifnet *, const char *, int);
void if_link_state_change(struct ifnet *, int);
int if_printf(struct ifnet *, const char *, ...) __printflike(2, 3);
void if_qflush(struct ifnet *);
Start to address a number of races relating to use of ifnet pointers after the corresponding interface has been destroyed: (1) Add an ifnet refcount, ifp->if_refcount. Initialize it to 1 in if_alloc(), and modify if_free_type() to decrement and check the refcount. (2) Add new if_ref() and if_rele() interfaces to allow kernel code walking global interface lists to release IFNET_[RW]LOCK() yet keep the ifnet stable. Currently, if_rele() is a no-op wrapper around if_free(), but this may change in the future. (3) Add new ifnet field, if_alloctype, which caches the type passed to if_alloc(), but unlike if_type, won't be changed by drivers. This allows asynchronous free's of the interface after the driver has released it to still use the right type. Use that instead of the type passed to if_free_type(), but assert that they are the same (might have to rethink this if that doesn't work out). (4) Add a new ifnet_byindex_ref(), which looks up an interface by index and returns a reference rather than a pointer to it. (5) Fix if_alloc() to fully initialize the if_addr_mtx before hooking up the ifnet to global lists. (6) Modify sysctls in if_mib.c to use ifnet_byindex_ref() and release the ifnet when done. When this change is MFC'd, it will need to replace if_ispare fields rather than adding new fields in order to avoid breaking the binary interface. Once this change is MFC'd, if_free_type() should be removed, as its 'type' argument is now optional. This refcount is not appropriate for counting mbuf pkthdr references, and also not for counting entry into the device driver via ifnet function pointers. An rmlock may be appropriate for the latter. Rather, this is about ensuring data structure stability when reaching an ifnet via global ifnet lists and tables followed by copy in or out of userspace. MFC after: 3 weeks Reported by: mdtancsa Reviewed by: brooks
2009-04-21 22:43:32 +00:00
void if_ref(struct ifnet *);
void if_rele(struct ifnet *);
2002-03-19 21:54:18 +00:00
int if_setlladdr(struct ifnet *, const u_char *, int);
void if_up(struct ifnet *);
int ifioctl(struct socket *, u_long, caddr_t, struct thread *);
int ifpromisc(struct ifnet *, int);
struct ifnet *ifunit(const char *);
struct ifnet *ifunit_ref(const char *);
2002-03-19 21:54:18 +00:00
void ifq_init(struct ifaltq *, struct ifnet *ifp);
void ifq_delete(struct ifaltq *);
int ifa_add_loopback_route(struct ifaddr *, struct sockaddr *);
int ifa_del_loopback_route(struct ifaddr *, struct sockaddr *);
2002-03-19 21:54:18 +00:00
struct ifaddr *ifa_ifwithaddr(struct sockaddr *);
int ifa_ifwithaddr_check(struct sockaddr *);
struct ifaddr *ifa_ifwithbroadaddr(struct sockaddr *);
2002-03-19 21:54:18 +00:00
struct ifaddr *ifa_ifwithdstaddr(struct sockaddr *);
struct ifaddr *ifa_ifwithnet(struct sockaddr *, int);
2002-03-19 21:54:18 +00:00
struct ifaddr *ifa_ifwithroute(int, struct sockaddr *, struct sockaddr *);
Add code to allow the system to handle multiple routing tables. This particular implementation is designed to be fully backwards compatible and to be MFC-able to 7.x (and 6.x) Currently the only protocol that can make use of the multiple tables is IPv4 Similar functionality exists in OpenBSD and Linux. From my notes: ----- One thing where FreeBSD has been falling behind, and which by chance I have some time to work on is "policy based routing", which allows different packet streams to be routed by more than just the destination address. Constraints: ------------ I want to make some form of this available in the 6.x tree (and by extension 7.x) , but FreeBSD in general needs it so I might as well do it in -current and back port the portions I need. One of the ways that this can be done is to have the ability to instantiate multiple kernel routing tables (which I will now refer to as "Forwarding Information Bases" or "FIBs" for political correctness reasons). Which FIB a particular packet uses to make the next hop decision can be decided by a number of mechanisms. The policies these mechanisms implement are the "Policies" referred to in "Policy based routing". One of the constraints I have if I try to back port this work to 6.x is that it must be implemented as a EXTENSION to the existing ABIs in 6.x so that third party applications do not need to be recompiled in timespan of the branch. This first version will not have some of the bells and whistles that will come with later versions. It will, for example, be limited to 16 tables in the first commit. Implementation method, Compatible version. (part 1) ------------------------------- For this reason I have implemented a "sufficient subset" of a multiple routing table solution in Perforce, and back-ported it to 6.x. (also in Perforce though not always caught up with what I have done in -current/P4). The subset allows a number of FIBs to be defined at compile time (8 is sufficient for my purposes in 6.x) and implements the changes needed to allow IPV4 to use them. I have not done the changes for ipv6 simply because I do not need it, and I do not have enough knowledge of ipv6 (e.g. neighbor discovery) needed to do it. Other protocol families are left untouched and should there be users with proprietary protocol families, they should continue to work and be oblivious to the existence of the extra FIBs. To understand how this is done, one must know that the current FIB code starts everything off with a single dimensional array of pointers to FIB head structures (One per protocol family), each of which in turn points to the trie of routes available to that family. The basic change in the ABI compatible version of the change is to extent that array to be a 2 dimensional array, so that instead of protocol family X looking at rt_tables[X] for the table it needs, it looks at rt_tables[Y][X] when for all protocol families except ipv4 Y is always 0. Code that is unaware of the change always just sees the first row of the table, which of course looks just like the one dimensional array that existed before. The entry points rtrequest(), rtalloc(), rtalloc1(), rtalloc_ign() are all maintained, but refer only to the first row of the array, so that existing callers in proprietary protocols can continue to do the "right thing". Some new entry points are added, for the exclusive use of ipv4 code called in_rtrequest(), in_rtalloc(), in_rtalloc1() and in_rtalloc_ign(), which have an extra argument which refers the code to the correct row. In addition, there are some new entry points (currently called rtalloc_fib() and friends) that check the Address family being looked up and call either rtalloc() (and friends) if the protocol is not IPv4 forcing the action to row 0 or to the appropriate row if it IS IPv4 (and that info is available). These are for calling from code that is not specific to any particular protocol. The way these are implemented would change in the non ABI preserving code to be added later. One feature of the first version of the code is that for ipv4, the interface routes show up automatically on all the FIBs, so that no matter what FIB you select you always have the basic direct attached hosts available to you. (rtinit() does this automatically). You CAN delete an interface route from one FIB should you want to but by default it's there. ARP information is also available in each FIB. It's assumed that the same machine would have the same MAC address, regardless of which FIB you are using to get to it. This brings us as to how the correct FIB is selected for an outgoing IPV4 packet. Firstly, all packets have a FIB associated with them. if nothing has been done to change it, it will be FIB 0. The FIB is changed in the following ways. Packets fall into one of a number of classes. 1/ locally generated packets, coming from a socket/PCB. Such packets select a FIB from a number associated with the socket/PCB. This in turn is inherited from the process, but can be changed by a socket option. The process in turn inherits it on fork. I have written a utility call setfib that acts a bit like nice.. setfib -3 ping target.example.com # will use fib 3 for ping. It is an obvious extension to make it a property of a jail but I have not done so. It can be achieved by combining the setfib and jail commands. 2/ packets received on an interface for forwarding. By default these packets would use table 0, (or possibly a number settable in a sysctl(not yet)). but prior to routing the firewall can inspect them (see below). (possibly in the future you may be able to associate a FIB with packets received on an interface.. An ifconfig arg, but not yet.) 3/ packets inspected by a packet classifier, which can arbitrarily associate a fib with it on a packet by packet basis. A fib assigned to a packet by a packet classifier (such as ipfw) would over-ride a fib associated by a more default source. (such as cases 1 or 2). 4/ a tcp listen socket associated with a fib will generate accept sockets that are associated with that same fib. 5/ Packets generated in response to some other packet (e.g. reset or icmp packets). These should use the FIB associated with the packet being reponded to. 6/ Packets generated during encapsulation. gif, tun and other tunnel interfaces will encapsulate using the FIB that was in effect withthe proces that set up the tunnel. thus setfib 1 ifconfig gif0 [tunnel instructions] will set the fib for the tunnel to use to be fib 1. Routing messages would be associated with their process, and thus select one FIB or another. messages from the kernel would be associated with the fib they refer to and would only be received by a routing socket associated with that fib. (not yet implemented) In addition Netstat has been edited to be able to cope with the fact that the array is now 2 dimensional. (It looks in system memory using libkvm (!)). Old versions of netstat see only the first FIB. In addition two sysctls are added to give: a) the number of FIBs compiled in (active) b) the default FIB of the calling process. Early testing experience: ------------------------- Basically our (IronPort's) appliance does this functionality already using ipfw fwd but that method has some drawbacks. For example, It can't fully simulate a routing table because it can't influence the socket's choice of local address when a connect() is done. Testing during the generating of these changes has been remarkably smooth so far. Multiple tables have co-existed with no notable side effects, and packets have been routes accordingly. ipfw has grown 2 new keywords: setfib N ip from anay to any count ip from any to any fib N In pf there seems to be a requirement to be able to give symbolic names to the fibs but I do not have that capacity. I am not sure if it is required. SCTP has interestingly enough built in support for this, called VRFs in Cisco parlance. it will be interesting to see how that handles it when it suddenly actually does something. Where to next: -------------------- After committing the ABI compatible version and MFCing it, I'd like to proceed in a forward direction in -current. this will result in some roto-tilling in the routing code. Firstly: the current code's idea of having a separate tree per protocol family, all of the same format, and pointed to by the 1 dimensional array is a bit silly. Especially when one considers that there is code that makes assumptions about every protocol having the same internal structures there. Some protocols don't WANT that sort of structure. (for example the whole idea of a netmask is foreign to appletalk). This needs to be made opaque to the external code. My suggested first change is to add routing method pointers to the 'domain' structure, along with information pointing the data. instead of having an array of pointers to uniform structures, there would be an array pointing to the 'domain' structures for each protocol address domain (protocol family), and the methods this reached would be called. The methods would have an argument that gives FIB number, but the protocol would be free to ignore it. When the ABI can be changed it raises the possibilty of the addition of a fib entry into the "struct route". Currently, the structure contains the sockaddr of the desination, and the resulting fib entry. To make this work fully, one could add a fib number so that given an address and a fib, one can find the third element, the fib entry. Interaction with the ARP layer/ LL layer would need to be revisited as well. Qing Li has been working on this already. This work was sponsored by Ironport Systems/Cisco Reviewed by: several including rwatson, bz and mlair (parts each) Obtained from: Ironport systems/Cisco
2008-05-09 23:03:00 +00:00
struct ifaddr *ifa_ifwithroute_fib(int, struct sockaddr *, struct sockaddr *, u_int);
2002-03-19 21:54:18 +00:00
struct ifaddr *ifaof_ifpforaddr(struct sockaddr *, struct ifnet *);
int if_simloop(struct ifnet *ifp, struct mbuf *m, int af, int hlen);
typedef void *if_com_alloc_t(u_char type, struct ifnet *ifp);
typedef void if_com_free_t(void *com, u_char type);
void if_register_com_alloc(u_char type, if_com_alloc_t *a, if_com_free_t *f);
void if_deregister_com_alloc(u_char type);
#define IF_LLADDR(ifp) \
LLADDR((struct sockaddr_dl *)((ifp)->if_addr->ifa_addr))
Device Polling code for -current. Non-SMP, i386-only, no polling in the idle loop at the moment. To use this code you must compile a kernel with options DEVICE_POLLING and at runtime enable polling with sysctl kern.polling.enable=1 The percentage of CPU reserved to userland can be set with sysctl kern.polling.user_frac=NN (default is 50) while the remainder is used by polling device drivers and netisr's. These are the only two variables that you should need to touch. There are a few more parameters in kern.polling but the default values are adequate for all purposes. See the code in kern_poll.c for more details on them. Polling in the idle loop will be implemented shortly by introducing a kernel thread which does the job. Until then, the amount of CPU dedicated to polling will never exceed (100-user_frac). The equivalent (actually, better) code for -stable is at http://info.iet.unipi.it/~luigi/polling/ and also supports polling in the idle loop. NOTE to Alpha developers: There is really nothing in this code that is i386-specific. If you move the 2 lines supporting the new option from sys/conf/{files,options}.i386 to sys/conf/{files,options} I am pretty sure that this should work on the Alpha as well, just that I do not have a suitable test box to try it. If someone feels like trying it, I would appreciate it. NOTE to other developers: sure some things could be done better, and as always I am open to constructive criticism, which a few of you have already given and I greatly appreciated. However, before proposing radical architectural changes, please take some time to possibly try out this code, or at the very least read the comments in kern_poll.c, especially re. the reason why I am using a soft netisr and cannot (I believe) replace it with a simple timeout. Quick description of files touched by this commit: sys/conf/files.i386 new file kern/kern_poll.c sys/conf/options.i386 new option sys/i386/i386/trap.c poll in trap (disabled by default) sys/kern/kern_clock.c initialization and hardclock hooks. sys/kern/kern_intr.c minor swi_net changes sys/kern/kern_poll.c the bulk of the code. sys/net/if.h new flag sys/net/if_var.h declaration for functions used in device drivers. sys/net/netisr.h NETISR_POLL sys/dev/fxp/if_fxp.c sys/dev/fxp/if_fxpvar.h sys/pci/if_dc.c sys/pci/if_dcreg.h sys/pci/if_sis.c sys/pci/if_sisreg.h device driver modifications
2001-12-14 17:56:12 +00:00
#ifdef DEVICE_POLLING
Big polling(4) cleanup. o Axe poll in trap. o Axe IFF_POLLING flag from if_flags. o Rework revision 1.21 (Giant removal), in such a way that poll_mtx is not dropped during call to polling handler. This fixes problem with idle polling. o Make registration and deregistration from polling in a functional way, insted of next tick/interrupt. o Obsolete kern.polling.enable. Polling is turned on/off with ifconfig. Detailed kern_poll.c changes: - Remove polling handler flags, introduced in 1.21. The are not needed now. - Forget and do not check if_flags, if_capenable and if_drv_flags. - Call all registered polling handlers unconditionally. - Do not drop poll_mtx, when entering polling handlers. - In ether_poll() NET_LOCK_GIANT prior to locking poll_mtx. - In netisr_poll() axe the block, where polling code asks drivers to unregister. - In netisr_poll() and ether_poll() do polling always, if any handlers are present. - In ether_poll_[de]register() remove a lot of error hiding code. Assert that arguments are correct, instead. - In ether_poll_[de]register() use standard return values in case of error or success. - Introduce poll_switch() that is a sysctl handler for kern.polling.enable. poll_switch() goes through interface list and enabled/disables polling. A message that kern.polling.enable is deprecated is printed. Detailed driver changes: - On attach driver announces IFCAP_POLLING in if_capabilities, but not in if_capenable. - On detach driver calls ether_poll_deregister() if polling is enabled. - In polling handler driver obtains its lock and checks IFF_DRV_RUNNING flag. If there is no, then unlocks and returns. - In ioctl handler driver checks for IFCAP_POLLING flag requested to be set or cleared. Driver first calls ether_poll_[de]register(), then obtains driver lock and [dis/en]ables interrupts. - In interrupt handler driver checks IFCAP_POLLING flag in if_capenable. If present, then returns.This is important to protect from spurious interrupts. Reviewed by: ru, sam, jhb
2005-10-01 18:56:19 +00:00
enum poll_cmd { POLL_ONLY, POLL_AND_CHECK_STATUS };
Device Polling code for -current. Non-SMP, i386-only, no polling in the idle loop at the moment. To use this code you must compile a kernel with options DEVICE_POLLING and at runtime enable polling with sysctl kern.polling.enable=1 The percentage of CPU reserved to userland can be set with sysctl kern.polling.user_frac=NN (default is 50) while the remainder is used by polling device drivers and netisr's. These are the only two variables that you should need to touch. There are a few more parameters in kern.polling but the default values are adequate for all purposes. See the code in kern_poll.c for more details on them. Polling in the idle loop will be implemented shortly by introducing a kernel thread which does the job. Until then, the amount of CPU dedicated to polling will never exceed (100-user_frac). The equivalent (actually, better) code for -stable is at http://info.iet.unipi.it/~luigi/polling/ and also supports polling in the idle loop. NOTE to Alpha developers: There is really nothing in this code that is i386-specific. If you move the 2 lines supporting the new option from sys/conf/{files,options}.i386 to sys/conf/{files,options} I am pretty sure that this should work on the Alpha as well, just that I do not have a suitable test box to try it. If someone feels like trying it, I would appreciate it. NOTE to other developers: sure some things could be done better, and as always I am open to constructive criticism, which a few of you have already given and I greatly appreciated. However, before proposing radical architectural changes, please take some time to possibly try out this code, or at the very least read the comments in kern_poll.c, especially re. the reason why I am using a soft netisr and cannot (I believe) replace it with a simple timeout. Quick description of files touched by this commit: sys/conf/files.i386 new file kern/kern_poll.c sys/conf/options.i386 new option sys/i386/i386/trap.c poll in trap (disabled by default) sys/kern/kern_clock.c initialization and hardclock hooks. sys/kern/kern_intr.c minor swi_net changes sys/kern/kern_poll.c the bulk of the code. sys/net/if.h new flag sys/net/if_var.h declaration for functions used in device drivers. sys/net/netisr.h NETISR_POLL sys/dev/fxp/if_fxp.c sys/dev/fxp/if_fxpvar.h sys/pci/if_dc.c sys/pci/if_dcreg.h sys/pci/if_sis.c sys/pci/if_sisreg.h device driver modifications
2001-12-14 17:56:12 +00:00
typedef int poll_handler_t(struct ifnet *ifp, enum poll_cmd cmd, int count);
2002-03-19 21:54:18 +00:00
int ether_poll_register(poll_handler_t *h, struct ifnet *ifp);
int ether_poll_deregister(struct ifnet *ifp);
Device Polling code for -current. Non-SMP, i386-only, no polling in the idle loop at the moment. To use this code you must compile a kernel with options DEVICE_POLLING and at runtime enable polling with sysctl kern.polling.enable=1 The percentage of CPU reserved to userland can be set with sysctl kern.polling.user_frac=NN (default is 50) while the remainder is used by polling device drivers and netisr's. These are the only two variables that you should need to touch. There are a few more parameters in kern.polling but the default values are adequate for all purposes. See the code in kern_poll.c for more details on them. Polling in the idle loop will be implemented shortly by introducing a kernel thread which does the job. Until then, the amount of CPU dedicated to polling will never exceed (100-user_frac). The equivalent (actually, better) code for -stable is at http://info.iet.unipi.it/~luigi/polling/ and also supports polling in the idle loop. NOTE to Alpha developers: There is really nothing in this code that is i386-specific. If you move the 2 lines supporting the new option from sys/conf/{files,options}.i386 to sys/conf/{files,options} I am pretty sure that this should work on the Alpha as well, just that I do not have a suitable test box to try it. If someone feels like trying it, I would appreciate it. NOTE to other developers: sure some things could be done better, and as always I am open to constructive criticism, which a few of you have already given and I greatly appreciated. However, before proposing radical architectural changes, please take some time to possibly try out this code, or at the very least read the comments in kern_poll.c, especially re. the reason why I am using a soft netisr and cannot (I believe) replace it with a simple timeout. Quick description of files touched by this commit: sys/conf/files.i386 new file kern/kern_poll.c sys/conf/options.i386 new option sys/i386/i386/trap.c poll in trap (disabled by default) sys/kern/kern_clock.c initialization and hardclock hooks. sys/kern/kern_intr.c minor swi_net changes sys/kern/kern_poll.c the bulk of the code. sys/net/if.h new flag sys/net/if_var.h declaration for functions used in device drivers. sys/net/netisr.h NETISR_POLL sys/dev/fxp/if_fxp.c sys/dev/fxp/if_fxpvar.h sys/pci/if_dc.c sys/pci/if_dcreg.h sys/pci/if_sis.c sys/pci/if_sisreg.h device driver modifications
2001-12-14 17:56:12 +00:00
#endif /* DEVICE_POLLING */
#endif /* _KERNEL */
#endif /* !_NET_IF_VAR_H_ */