freebsd-dev/sys/kern/sys_socket.c

297 lines
7.4 KiB
C
Raw Normal View History

/*-
1994-05-24 10:09:53 +00:00
* Copyright (c) 1982, 1986, 1990, 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.
*
* @(#)sys_socket.c 8.1 (Berkeley) 6/10/93
*/
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/file.h>
#include <sys/filedesc.h>
2005-03-11 15:06:16 +00:00
#include <sys/proc.h>
1994-05-24 10:09:53 +00:00
#include <sys/protosw.h>
#include <sys/sigio.h>
2005-03-11 15:06:16 +00:00
#include <sys/signal.h>
#include <sys/signalvar.h>
1994-05-24 10:09:53 +00:00
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/filio.h> /* XXX */
#include <sys/sockio.h>
1994-05-24 10:09:53 +00:00
#include <sys/stat.h>
#include <sys/uio.h>
#include <sys/ucred.h>
1994-05-24 10:09:53 +00:00
#include <net/if.h>
#include <net/route.h>
#include <net/vnet.h>
1994-05-24 10:09:53 +00:00
#include <security/mac/mac_framework.h>
struct fileops socketops = {
.fo_read = soo_read,
.fo_write = soo_write,
.fo_truncate = soo_truncate,
.fo_ioctl = soo_ioctl,
.fo_poll = soo_poll,
.fo_kqfilter = soo_kqfilter,
.fo_stat = soo_stat,
.fo_close = soo_close,
.fo_chmod = invfo_chmod,
.fo_chown = invfo_chown,
.fo_flags = DFLAG_PASSABLE
};
1994-05-24 10:09:53 +00:00
/* ARGSUSED */
int
soo_read(struct file *fp, struct uio *uio, struct ucred *active_cred,
int flags, struct thread *td)
1994-05-24 10:09:53 +00:00
{
struct socket *so = fp->f_data;
int error;
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
#ifdef MAC
error = mac_socket_check_receive(active_cred, so);
if (error)
return (error);
#endif
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
error = soreceive(so, 0, uio, 0, 0, 0);
return (error);
1994-05-24 10:09:53 +00:00
}
/* ARGSUSED */
int
soo_write(struct file *fp, struct uio *uio, struct ucred *active_cred,
int flags, struct thread *td)
1994-05-24 10:09:53 +00:00
{
struct socket *so = fp->f_data;
int error;
#ifdef MAC
error = mac_socket_check_send(active_cred, so);
if (error)
return (error);
#endif
error = sosend(so, 0, uio, 0, 0, 0, uio->uio_td);
2005-03-11 15:06:16 +00:00
if (error == EPIPE && (so->so_options & SO_NOSIGPIPE) == 0) {
PROC_LOCK(uio->uio_td->td_proc);
tdsignal(uio->uio_td, SIGPIPE);
2005-03-11 15:06:16 +00:00
PROC_UNLOCK(uio->uio_td->td_proc);
}
return (error);
1994-05-24 10:09:53 +00:00
}
int
soo_truncate(struct file *fp, off_t length, struct ucred *active_cred,
struct thread *td)
{
return (EINVAL);
}
int
soo_ioctl(struct file *fp, u_long cmd, void *data, struct ucred *active_cred,
struct thread *td)
1994-05-24 10:09:53 +00:00
{
struct socket *so = fp->f_data;
int error = 0;
1994-05-24 10:09:53 +00:00
switch (cmd) {
case FIONBIO:
SOCK_LOCK(so);
1994-05-24 10:09:53 +00:00
if (*(int *)data)
so->so_state |= SS_NBIO;
else
so->so_state &= ~SS_NBIO;
SOCK_UNLOCK(so);
break;
1994-05-24 10:09:53 +00:00
case FIOASYNC:
/*
* XXXRW: This code separately acquires SOCK_LOCK(so) and
* SOCKBUF_LOCK(&so->so_rcv) even though they are the same
* mutex to avoid introducing the assumption that they are
* the same.
*/
1994-05-24 10:09:53 +00:00
if (*(int *)data) {
SOCK_LOCK(so);
1994-05-24 10:09:53 +00:00
so->so_state |= SS_ASYNC;
SOCK_UNLOCK(so);
SOCKBUF_LOCK(&so->so_rcv);
1994-05-24 10:09:53 +00:00
so->so_rcv.sb_flags |= SB_ASYNC;
SOCKBUF_UNLOCK(&so->so_rcv);
SOCKBUF_LOCK(&so->so_snd);
1994-05-24 10:09:53 +00:00
so->so_snd.sb_flags |= SB_ASYNC;
SOCKBUF_UNLOCK(&so->so_snd);
1994-05-24 10:09:53 +00:00
} else {
SOCK_LOCK(so);
1994-05-24 10:09:53 +00:00
so->so_state &= ~SS_ASYNC;
SOCK_UNLOCK(so);
SOCKBUF_LOCK(&so->so_rcv);
1994-05-24 10:09:53 +00:00
so->so_rcv.sb_flags &= ~SB_ASYNC;
SOCKBUF_UNLOCK(&so->so_rcv);
SOCKBUF_LOCK(&so->so_snd);
1994-05-24 10:09:53 +00:00
so->so_snd.sb_flags &= ~SB_ASYNC;
SOCKBUF_UNLOCK(&so->so_snd);
1994-05-24 10:09:53 +00:00
}
break;
1994-05-24 10:09:53 +00:00
case FIONREAD:
/* Unlocked read. */
1994-05-24 10:09:53 +00:00
*(int *)data = so->so_rcv.sb_cc;
break;
1994-05-24 10:09:53 +00:00
There are a number of ways an application can check if there are inbound data waiting on a filedescriptor, such as a pipe or a socket, for instance by using select(2), poll(2), kqueue(2), ioctl(FIONREAD) etc. But we have no way of finding out if written data have yet to be disposed of, for instance, transmitted (and ack'ed!) to some remote host, or read by the applicantion at the far end of the pipe. The closest we get, is calling shutdown(2) on a TCP socket in non-blocking mode, but this has the undesirable sideeffect of preventing future communication. Add a complement to FIONREAD, called FIONWRITE, which returns the number of bytes not yet properly disposed of. Implement it for all sockets. Background: A HTTP server will want to time out connections, if no new request arrives within a certain period after the last transmitted response has actually been sent (and ack'ed). For a busy HTTP server, this timeout can be subsecond duration. In order to signal to a load-balancer that the connection is truly dead, TCP_RST will be the preferred method, as this avoids the need for a RTT delay for FIN handshaking, with a client which, surprisingly often, no longer at the remote IP number. If a slow, distant client is being served a response which is big enough to fill the window, but small enough to fit in the socket buffer, the write(2) call will return immediately. If the session timeout is armed at that time, all bytes in the response may not have been transmitted by the time it fires. FIONWRITE allows the timeout to check that no data is outstanding on the connection, before it TCP_RST's it. Input & Idea from: rwatson Approved by: re (kib)
2009-06-28 11:28:14 +00:00
case FIONWRITE:
/* Unlocked read. */
*(int *)data = so->so_snd.sb_cc;
break;
case FIONSPACE:
if ((so->so_snd.sb_hiwat < so->so_snd.sb_cc) ||
(so->so_snd.sb_mbmax < so->so_snd.sb_mbcnt))
*(int *)data = 0;
else
*(int *)data = sbspace(&so->so_snd);
break;
case FIOSETOWN:
error = fsetown(*(int *)data, &so->so_sigio);
break;
case FIOGETOWN:
*(int *)data = fgetown(&so->so_sigio);
break;
1994-05-24 10:09:53 +00:00
case SIOCSPGRP:
error = fsetown(-(*(int *)data), &so->so_sigio);
break;
1994-05-24 10:09:53 +00:00
case SIOCGPGRP:
*(int *)data = -fgetown(&so->so_sigio);
break;
1994-05-24 10:09:53 +00:00
case SIOCATMARK:
/* Unlocked read. */
*(int *)data = (so->so_rcv.sb_state & SBS_RCVATMARK) != 0;
break;
default:
/*
* Interface/routing/protocol specific ioctls: interface and
* routing ioctls should have a different entry since a
* socket is unnecessary.
*/
if (IOCGROUP(cmd) == 'i')
error = ifioctl(so, cmd, data, td);
else if (IOCGROUP(cmd) == 'r') {
CURVNET_SET(so->so_vnet);
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
error = rtioctl_fib(cmd, data, so->so_fibnum);
CURVNET_RESTORE();
} else {
CURVNET_SET(so->so_vnet);
error = ((*so->so_proto->pr_usrreqs->pru_control)
(so, cmd, data, 0, td));
CURVNET_RESTORE();
}
break;
1994-05-24 10:09:53 +00:00
}
return (error);
1994-05-24 10:09:53 +00:00
}
int
soo_poll(struct file *fp, int events, struct ucred *active_cred,
struct thread *td)
1994-05-24 10:09:53 +00:00
{
struct socket *so = fp->f_data;
#ifdef MAC
int error;
error = mac_socket_check_poll(active_cred, so);
if (error)
return (error);
#endif
return (sopoll(so, events, fp->f_cred, td));
1994-05-24 10:09:53 +00:00
}
int
soo_stat(struct file *fp, struct stat *ub, struct ucred *active_cred,
struct thread *td)
1994-05-24 10:09:53 +00:00
{
struct socket *so = fp->f_data;
#ifdef MAC
int error;
#endif
1994-05-24 10:09:53 +00:00
bzero((caddr_t)ub, sizeof (*ub));
ub->st_mode = S_IFSOCK;
#ifdef MAC
error = mac_socket_check_stat(active_cred, so);
if (error)
return (error);
#endif
/*
* If SBS_CANTRCVMORE is set, but there's still data left in the
* receive buffer, the socket is still readable.
*/
SOCKBUF_LOCK(&so->so_rcv);
if ((so->so_rcv.sb_state & SBS_CANTRCVMORE) == 0 ||
so->so_rcv.sb_cc != 0)
ub->st_mode |= S_IRUSR | S_IRGRP | S_IROTH;
ub->st_size = so->so_rcv.sb_cc - so->so_rcv.sb_ctl;
SOCKBUF_UNLOCK(&so->so_rcv);
/* Unlocked read. */
if ((so->so_snd.sb_state & SBS_CANTSENDMORE) == 0)
ub->st_mode |= S_IWUSR | S_IWGRP | S_IWOTH;
ub->st_uid = so->so_cred->cr_uid;
ub->st_gid = so->so_cred->cr_gid;
return (*so->so_proto->pr_usrreqs->pru_sense)(so, ub);
1994-05-24 10:09:53 +00:00
}
/*
* API socket close on file pointer. We call soclose() to close the socket
* (including initiating closing protocols). soclose() will sorele() the
* file reference but the actual socket will not go away until the socket's
* ref count hits 0.
*/
1994-05-24 10:09:53 +00:00
/* ARGSUSED */
int
soo_close(struct file *fp, struct thread *td)
1994-05-24 10:09:53 +00:00
{
int error = 0;
struct socket *so;
1994-05-24 10:09:53 +00:00
so = fp->f_data;
fp->f_ops = &badfileops;
fp->f_data = NULL;
if (so)
error = soclose(so);
1994-05-24 10:09:53 +00:00
return (error);
}