d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
17885a7bfd
freebsd-nq/sys/kern/sys_socket.c

299 lines
7.5 KiB
C
Raw Normal View History

/* -> /*- for copyright notices, minor format tweaks as necessary
2005-01-06 23:35:40 +00:00
/*-
BSD 4.4 Lite Kernel Sources
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
*/
Use __FBSDID().
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/file.h>
When compiling the kernel do not implicitly include filedesc.h from proc.h, this was causing filedesc work to be very painful. In order to make this work split out sigio definitions to thier own header (sigio.h) which is included from proc.h for the time being.
2003-01-01 01:56:19 +00:00
#include <sys/filedesc.h>
The SO_NOSIGPIPE socket option allows a user process to mark a socket so that the socket does not generate SIGPIPE, only EPIPE, when a write is attempted after socket shutdown. When the option was introduced in 2002, this required the logic for determining whether SIGPIPE was generated to be pushed down from dofilewrite() to the socket layer so that the socket options could be considered. However, the change in 2002 omitted modification to soo_write() required to add that logic, resulting in SIGPIPE not being generated even without SO_NOSIGPIPE when the socket was written to using write() or related generic system calls. This change adds the EPIPE logic to soo_write(), generating a SIGPIPE signal to the process associated with the passed uio in the event that the SO_NOSIGPIPE option is not set. Notes: - The are upsides and downsides to placing this logic in the socket layer as opposed to the file descriptor layer. This is really fd layer logic, but because we need so_options, we have a choice of layering violations and pick this one. - SIGPIPE possibly should be delivered to the thread performing the write, not the process performing the write. - uio->uio_td and the td argument to soo_write() might potentially differ; we use the thread in the uio argument. - The "sigpipe" regression test in src/tools/regression/sockets/sigpipe tests for the bug. Submitted by: Mikko Tyolajarvi <mbsd at pacbell dot net> Talked with: glebius, alfred PR: 78478 MFC after: 1 week
2005-03-11 15:06:16 +00:00
#include <sys/proc.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <sys/protosw.h>
When compiling the kernel do not implicitly include filedesc.h from proc.h, this was causing filedesc work to be very painful. In order to make this work split out sigio definitions to thier own header (sigio.h) which is included from proc.h for the time being.
2003-01-01 01:56:19 +00:00
#include <sys/sigio.h>
The SO_NOSIGPIPE socket option allows a user process to mark a socket so that the socket does not generate SIGPIPE, only EPIPE, when a write is attempted after socket shutdown. When the option was introduced in 2002, this required the logic for determining whether SIGPIPE was generated to be pushed down from dofilewrite() to the socket layer so that the socket options could be considered. However, the change in 2002 omitted modification to soo_write() required to add that logic, resulting in SIGPIPE not being generated even without SO_NOSIGPIPE when the socket was written to using write() or related generic system calls. This change adds the EPIPE logic to soo_write(), generating a SIGPIPE signal to the process associated with the passed uio in the event that the SO_NOSIGPIPE option is not set. Notes: - The are upsides and downsides to placing this logic in the socket layer as opposed to the file descriptor layer. This is really fd layer logic, but because we need so_options, we have a choice of layering violations and pick this one. - SIGPIPE possibly should be delivered to the thread performing the write, not the process performing the write. - uio->uio_td and the td argument to soo_write() might potentially differ; we use the thread in the uio argument. - The "sigpipe" regression test in src/tools/regression/sockets/sigpipe tests for the bug. Submitted by: Mikko Tyolajarvi <mbsd at pacbell dot net> Talked with: glebius, alfred PR: 78478 MFC after: 1 week
2005-03-11 15:06:16 +00:00
#include <sys/signal.h>
#include <sys/signalvar.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <sys/socket.h>
#include <sys/socketvar.h>
Don't include <sys/ioctl.h> in the kernel. Stage 4: include <sys/ttycom.h> and sometimes <sys/filio.h> instead of <sys/ioctl.h> in miscellaneous files. Most of these files have nothing to do with ttys but need to include <sys/ttycom.h> to get the definitions of TIOC[SG]PGRP which are (ab)used to convert F[SG]ETOWN fcntls into ioctls.
1997-03-24 11:52:29 +00:00
#include <sys/filio.h> /* XXX */
#include <sys/sockio.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <sys/stat.h>
Moved some #includes from <sys/param.h> nearer to where they are actually used.
1998-03-28 10:33:27 +00:00
#include <sys/uio.h>
Include the UID and GID values filled in by socreate() into socket->so_cred for stat() calls. Reviewed by: phk
2000-05-11 22:08:57 +00:00
#include <sys/ucred.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <net/if.h>
The r48589 promised to remove implicit inclusion of if_var.h soon. Prepare to this event, adding if_var.h to files that do need it. Also, include all includes that now are included due to implicit pollution via if_var.h Sponsored by: Netflix Sponsored by: Nginx, Inc.
2013-10-26 17:58:36 +00:00
#include <net/if_var.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <net/route.h>
Merge the remainder of kern_vimage.c and vimage.h into vnet.c and vnet.h, we now use jails (rather than vimages) as the abstraction for virtualization management, and what remained was specific to virtual network stacks. Minor cleanups are done in the process, and comments updated to reflect these changes. Reviewed by: bz Approved by: re (vimage blanket)
2009-08-01 19:26:27 +00:00
#include <net/vnet.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
Complete break-out of sys/sys/mac.h into sys/security/mac/mac_framework.h begun with a repo-copy of mac.h to mac_framework.h. sys/mac.h now contains the userspace and user<->kernel API and definitions, with all in-kernel interfaces moved to mac_framework.h, which is now included across most of the kernel instead. This change is the first step in a larger cleanup and sweep of MAC Framework interfaces in the kernel, and will not be MFC'd. Obtained from: TrustedBSD Project Sponsored by: SPARTA
2006-10-22 11:52:19 +00:00
#include <security/mac/mac_framework.h>
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
struct fileops socketops = {
Initialize struct fileops with C99 sparse initialization.
2003-06-18 18:16:40 +00:00
.fo_read = soo_read,
.fo_write = soo_write,
Make ftruncate a 'struct file' operation rather than a vnode operation. This makes it possible to support ftruncate() on non-vnode file types in the future. - 'struct fileops' grows a 'fo_truncate' method to handle an ftruncate() on a given file descriptor. - ftruncate() moves to kern/sys_generic.c and now just fetches a file object and invokes fo_truncate(). - The vnode-specific portions of ftruncate() move to vn_truncate() in vfs_vnops.c which implements fo_truncate() for vnode file types. - Non-vnode file types return EINVAL in their fo_truncate() method. Submitted by: rwatson
2008-01-07 20:05:19 +00:00
.fo_truncate = soo_truncate,
Initialize struct fileops with C99 sparse initialization.
2003-06-18 18:16:40 +00:00
.fo_ioctl = soo_ioctl,
.fo_poll = soo_poll,
.fo_kqfilter = soo_kqfilter,
.fo_stat = soo_stat,
.fo_close = soo_close,
Add the fo_chown and fo_chmod methods to struct fileops and use them to implement fchown(2) and fchmod(2) support for several file types that previously lacked it. Add MAC entries for chown/chmod done on posix shared memory and (old) in-kernel posix semaphores. Based on the submission by: glebius Reviewed by: rwatson Approved by: re (bz)
2011-08-16 20:07:47 +00:00
.fo_chmod = invfo_chmod,
.fo_chown = invfo_chown,
Make sendfile() a method in the struct fileops. Currently only vnode backed file descriptors have this method implemented. Reviewed by: kib Sponsored by: Nginx, Inc. Sponsored by: Netflix
2013-08-15 07:54:31 +00:00
.fo_sendfile = invfo_sendfile,
Initialize struct fileops with C99 sparse initialization.
2003-06-18 18:16:40 +00:00
.fo_flags = DFLAG_PASSABLE
Extend kqueue down to the device layer. Backwards compatible approach suggested by: peter
2001-02-15 16:34:11 +00:00
};
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
/* ARGSUSED */
Unstaticized routines which are needed by the svr4 KLD and the streams garbage needed to support SysVR4 networking.
1999-01-30 06:25:00 +00:00
int
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
soo_read(struct file *fp, struct uio *uio, struct ucred *active_cred,
int flags, struct thread *td)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
Bow to the whining masses and change a union back into void *. Retain removal of unnecessary casts and throw in some minor cleanups to see if anyone complains, just for the hell of it.
2003-01-13 00:33:17 +00:00
struct socket *so = fp->f_data;
Giant pushdown for read/write/pread/pwrite syscalls. kern/kern_descrip.c: Aquire Giant in fdrop_locked when file refcount hits zero, this removes the requirement for the caller to own Giant for the most part. kern/kern_ktrace.c: Aquire Giant in ktrgenio, simplifies locking in upper read/write syscalls. kern/vfs_bio.c: Aquire Giant in bwillwrite if needed. kern/sys_generic.c Giant pushdown, remove Giant for: read, pread, write and pwrite. readv and writev aren't done yet because of the possible malloc calls for iov to uio processing. kern/sys_socket.c Grab giant in the socket fo_read/write functions. kern/vfs_vnops.c Grab giant in the vnode fo_read/write functions.
2002-03-15 08:03:46 +00:00
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
Merge first in a series of TrustedBSD MAC Framework KPI changes from Mac OS X Leopard--rationalize naming for entry points to the following general forms: mac_<object>_<method/action> mac_<object>_check_<method/action> The previous naming scheme was inconsistent and mostly reversed from the new scheme. Also, make object types more consistent and remove spaces from object types that contain multiple parts ("posix_sem" -> "posixsem") to make mechanical parsing easier. Introduce a new "netinet" object type for certain IPv4/IPv6-related methods. Also simplify, slightly, some entry point names. All MAC policy modules will need to be recompiled, and modules not updates as part of this commit will need to be modified to conform to the new KPI. Sponsored by: SPARTA (original patches against Mac OS X) Obtained from: TrustedBSD Project, Apple Computer
2007-10-24 19:04:04 +00:00
error = mac_socket_check_receive(active_cred, so);
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
if (error)
Integrate mac_check_socket_send() and mac_check_socket_receive() checks from the MAC tree: allow policies to perform access control for the ability of a process to send and receive data via a socket. At some point, we might also pass in additional address information if an explicit address is requested on send. Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2002-10-06 14:39:15 +00:00
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);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
/* ARGSUSED */
Unstaticized routines which are needed by the svr4 KLD and the streams garbage needed to support SysVR4 networking.
1999-01-30 06:25:00 +00:00
int
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
soo_write(struct file *fp, struct uio *uio, struct ucred *active_cred,
int flags, struct thread *td)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
Bow to the whining masses and change a union back into void *. Retain removal of unnecessary casts and throw in some minor cleanups to see if anyone complains, just for the hell of it.
2003-01-13 00:33:17 +00:00
struct socket *so = fp->f_data;
Giant pushdown for read/write/pread/pwrite syscalls. kern/kern_descrip.c: Aquire Giant in fdrop_locked when file refcount hits zero, this removes the requirement for the caller to own Giant for the most part. kern/kern_ktrace.c: Aquire Giant in ktrgenio, simplifies locking in upper read/write syscalls. kern/vfs_bio.c: Aquire Giant in bwillwrite if needed. kern/sys_generic.c Giant pushdown, remove Giant for: read, pread, write and pwrite. readv and writev aren't done yet because of the possible malloc calls for iov to uio processing. kern/sys_socket.c Grab giant in the socket fo_read/write functions. kern/vfs_vnops.c Grab giant in the vnode fo_read/write functions.
2002-03-15 08:03:46 +00:00
int error;
Integrate mac_check_socket_send() and mac_check_socket_receive() checks from the MAC tree: allow policies to perform access control for the ability of a process to send and receive data via a socket. At some point, we might also pass in additional address information if an explicit address is requested on send. Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2002-10-06 14:39:15 +00:00
#ifdef MAC
Merge first in a series of TrustedBSD MAC Framework KPI changes from Mac OS X Leopard--rationalize naming for entry points to the following general forms: mac_<object>_<method/action> mac_<object>_check_<method/action> The previous naming scheme was inconsistent and mostly reversed from the new scheme. Also, make object types more consistent and remove spaces from object types that contain multiple parts ("posix_sem" -> "posixsem") to make mechanical parsing easier. Introduce a new "netinet" object type for certain IPv4/IPv6-related methods. Also simplify, slightly, some entry point names. All MAC policy modules will need to be recompiled, and modules not updates as part of this commit will need to be modified to conform to the new KPI. Sponsored by: SPARTA (original patches against Mac OS X) Obtained from: TrustedBSD Project, Apple Computer
2007-10-24 19:04:04 +00:00
error = mac_socket_check_send(active_cred, so);
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
if (error)
Integrate mac_check_socket_send() and mac_check_socket_receive() checks from the MAC tree: allow policies to perform access control for the ability of a process to send and receive data via a socket. At some point, we might also pass in additional address information if an explicit address is requested on send. Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2002-10-06 14:39:15 +00:00
return (error);
#endif
soreceive_generic(), and sopoll_generic(). Add new functions sosend(), soreceive(), and sopoll(), which are wrappers for pru_sosend, pru_soreceive, and pru_sopoll, and are now used univerally by socket consumers rather than either directly invoking the old so*() functions or directly invoking the protocol switch method (about an even split prior to this commit). This completes an architectural change that was begun in 1996 to permit protocols to provide substitute implementations, as now used by UDP. Consumers now uniformly invoke sosend(), soreceive(), and sopoll() to perform these operations on sockets -- in particular, distributed file systems and socket system calls. Architectural head nod: sam, gnn, wollman
2006-07-24 15:20:08 +00:00
error = sosend(so, 0, uio, 0, 0, 0, uio->uio_td);
The SO_NOSIGPIPE socket option allows a user process to mark a socket so that the socket does not generate SIGPIPE, only EPIPE, when a write is attempted after socket shutdown. When the option was introduced in 2002, this required the logic for determining whether SIGPIPE was generated to be pushed down from dofilewrite() to the socket layer so that the socket options could be considered. However, the change in 2002 omitted modification to soo_write() required to add that logic, resulting in SIGPIPE not being generated even without SO_NOSIGPIPE when the socket was written to using write() or related generic system calls. This change adds the EPIPE logic to soo_write(), generating a SIGPIPE signal to the process associated with the passed uio in the event that the SO_NOSIGPIPE option is not set. Notes: - The are upsides and downsides to placing this logic in the socket layer as opposed to the file descriptor layer. This is really fd layer logic, but because we need so_options, we have a choice of layering violations and pick this one. - SIGPIPE possibly should be delivered to the thread performing the write, not the process performing the write. - uio->uio_td and the td argument to soo_write() might potentially differ; we use the thread in the uio argument. - The "sigpipe" regression test in src/tools/regression/sockets/sigpipe tests for the bug. Submitted by: Mikko Tyolajarvi <mbsd at pacbell dot net> Talked with: glebius, alfred PR: 78478 MFC after: 1 week
2005-03-11 15:06:16 +00:00
if (error == EPIPE && (so->so_options & SO_NOSIGPIPE) == 0) {
PROC_LOCK(uio->uio_td->td_proc);
Send SIGPIPE to the thread that issued the offending system call rather than to the entire process. Reported by: Anit Chakraborty Reviewed by: kib, deischen (concept) MFC after: 1 week
2010-06-29 20:44:19 +00:00
tdsignal(uio->uio_td, SIGPIPE);
The SO_NOSIGPIPE socket option allows a user process to mark a socket so that the socket does not generate SIGPIPE, only EPIPE, when a write is attempted after socket shutdown. When the option was introduced in 2002, this required the logic for determining whether SIGPIPE was generated to be pushed down from dofilewrite() to the socket layer so that the socket options could be considered. However, the change in 2002 omitted modification to soo_write() required to add that logic, resulting in SIGPIPE not being generated even without SO_NOSIGPIPE when the socket was written to using write() or related generic system calls. This change adds the EPIPE logic to soo_write(), generating a SIGPIPE signal to the process associated with the passed uio in the event that the SO_NOSIGPIPE option is not set. Notes: - The are upsides and downsides to placing this logic in the socket layer as opposed to the file descriptor layer. This is really fd layer logic, but because we need so_options, we have a choice of layering violations and pick this one. - SIGPIPE possibly should be delivered to the thread performing the write, not the process performing the write. - uio->uio_td and the td argument to soo_write() might potentially differ; we use the thread in the uio argument. - The "sigpipe" regression test in src/tools/regression/sockets/sigpipe tests for the bug. Submitted by: Mikko Tyolajarvi <mbsd at pacbell dot net> Talked with: glebius, alfred PR: 78478 MFC after: 1 week
2005-03-11 15:06:16 +00:00
PROC_UNLOCK(uio->uio_td->td_proc);
}
Giant pushdown for read/write/pread/pwrite syscalls. kern/kern_descrip.c: Aquire Giant in fdrop_locked when file refcount hits zero, this removes the requirement for the caller to own Giant for the most part. kern/kern_ktrace.c: Aquire Giant in ktrgenio, simplifies locking in upper read/write syscalls. kern/vfs_bio.c: Aquire Giant in bwillwrite if needed. kern/sys_generic.c Giant pushdown, remove Giant for: read, pread, write and pwrite. readv and writev aren't done yet because of the possible malloc calls for iov to uio processing. kern/sys_socket.c Grab giant in the socket fo_read/write functions. kern/vfs_vnops.c Grab giant in the vnode fo_read/write functions.
2002-03-15 08:03:46 +00:00
return (error);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
Make ftruncate a 'struct file' operation rather than a vnode operation. This makes it possible to support ftruncate() on non-vnode file types in the future. - 'struct fileops' grows a 'fo_truncate' method to handle an ftruncate() on a given file descriptor. - ftruncate() moves to kern/sys_generic.c and now just fetches a file object and invokes fo_truncate(). - The vnode-specific portions of ftruncate() move to vn_truncate() in vfs_vnops.c which implements fo_truncate() for vnode file types. - Non-vnode file types return EINVAL in their fo_truncate() method. Submitted by: rwatson
2008-01-07 20:05:19 +00:00
int
soo_truncate(struct file *fp, off_t length, struct ucred *active_cred,
struct thread *td)
{
return (EINVAL);
}
The big 4.4BSD Lite to FreeBSD 2.0.0 (Development) patch. Reviewed by: Rodney W. Grimes Submitted by: John Dyson and David Greenman
1994-05-25 09:21:21 +00:00
int
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
soo_ioctl(struct file *fp, u_long cmd, void *data, struct ucred *active_cred,
struct thread *td)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
struct socket *so = fp->f_data;
int error = 0;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
switch (cmd) {
case FIONBIO:
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCK_LOCK(so);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
if (*(int *)data)
so->so_state |= SS_NBIO;
else
so->so_state &= ~SS_NBIO;
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCK_UNLOCK(so);
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
break;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
case FIOASYNC:
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
/*
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
* 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.
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
*/
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
if (*(int *)data) {
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCK_LOCK(so);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
so->so_state |= SS_ASYNC;
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCK_UNLOCK(so);
SOCKBUF_LOCK(&so->so_rcv);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
so->so_rcv.sb_flags |= SB_ASYNC;
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCKBUF_UNLOCK(&so->so_rcv);
SOCKBUF_LOCK(&so->so_snd);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
so->so_snd.sb_flags |= SB_ASYNC;
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCKBUF_UNLOCK(&so->so_snd);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
} else {
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCK_LOCK(so);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
so->so_state &= ~SS_ASYNC;
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCK_UNLOCK(so);
SOCKBUF_LOCK(&so->so_rcv);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
so->so_rcv.sb_flags &= ~SB_ASYNC;
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCKBUF_UNLOCK(&so->so_rcv);
SOCKBUF_LOCK(&so->so_snd);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
so->so_snd.sb_flags &= ~SB_ASYNC;
Merge additional socket buffer locking from rwatson_netperf: - Lock down low hanging fruit use of sb_flags with socket buffer lock. - Lock down low hanging fruit use of so_state with socket lock. - Lock down low hanging fruit use of so_options. - Lock down low-hanging fruit use of sb_lowwat and sb_hiwat with socket buffer lock. - Annotate situations in which we unlock the socket lock and then grab the receive socket buffer lock, which are currently actually the same lock. Depending on how we want to play our cards, we may want to coallesce these lock uses to reduce overhead. - Convert a if()->panic() into a KASSERT relating to so_state in soaccept(). - Remove a number of splnet()/splx() references. More complex merging of socket and socket buffer locking to follow.
2004-06-17 22:48:11 +00:00
SOCKBUF_UNLOCK(&so->so_snd);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
break;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
case FIONREAD:
Annotate two intentionally unlocked reads with comments. Annotate a potentially inconsistent result returned to user space when performing fstaT() on a socket due to not using socket buffer locking.
2004-06-20 17:35:50 +00:00
/* Unlocked read. */
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
*(int *)data = so->so_rcv.sb_cc;
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
break;
BSD 4.4 Lite Kernel Sources
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;
Add FIONSPACE from NetBSD. FIONSPACE is provided so that programs may easily determine how much space is left in the send queue; they do not need to know the send queue size. NetBSD revisions: sys_socket.c r1.41, 1.42 filio.h r1.9 Obtained from: NetBSD Approved by: re (kensmith)
2009-06-30 13:38:49 +00:00
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;
Installed the second patch attached to kern/7899 with some changes suggested by bde, a few other tweaks to get the patch to apply cleanly again and some improvements to the comments. This change closes some fairly minor security holes associated with F_SETOWN, fixes a few bugs, and removes some limitations that F_SETOWN had on tty devices. For more details, see the description on the PR. Because this patch increases the size of the proc and pgrp structures, it is necessary to re-install the includes and recompile libkvm, the vinum lkm, fstat, gcore, gdb, ipfilter, ps, top, and w. PR: kern/7899 Reviewed by: bde, elvind
1998-11-11 10:04:13 +00:00
case FIOSETOWN:
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
error = fsetown(*(int *)data, &so->so_sigio);
break;
Installed the second patch attached to kern/7899 with some changes suggested by bde, a few other tweaks to get the patch to apply cleanly again and some improvements to the comments. This change closes some fairly minor security holes associated with F_SETOWN, fixes a few bugs, and removes some limitations that F_SETOWN had on tty devices. For more details, see the description on the PR. Because this patch increases the size of the proc and pgrp structures, it is necessary to re-install the includes and recompile libkvm, the vinum lkm, fstat, gcore, gdb, ipfilter, ps, top, and w. PR: kern/7899 Reviewed by: bde, elvind
1998-11-11 10:04:13 +00:00
case FIOGETOWN:
In an SMP environment post-Giant it is no longer safe to blindly dereference the struct sigio pointer without any locking. Change fgetown() to take a reference to the pointer instead of a copy of the pointer and call SIGIO_LOCK() before copying the pointer and dereferencing it. Reviewed by: rwatson
2002-10-03 02:13:00 +00:00
*(int *)data = fgetown(&so->so_sigio);
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
break;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
Installed the second patch attached to kern/7899 with some changes suggested by bde, a few other tweaks to get the patch to apply cleanly again and some improvements to the comments. This change closes some fairly minor security holes associated with F_SETOWN, fixes a few bugs, and removes some limitations that F_SETOWN had on tty devices. For more details, see the description on the PR. Because this patch increases the size of the proc and pgrp structures, it is necessary to re-install the includes and recompile libkvm, the vinum lkm, fstat, gcore, gdb, ipfilter, ps, top, and w. PR: kern/7899 Reviewed by: bde, elvind
1998-11-11 10:04:13 +00:00
case SIOCSPGRP:
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
error = fsetown(-(*(int *)data), &so->so_sigio);
break;
Installed the second patch attached to kern/7899 with some changes suggested by bde, a few other tweaks to get the patch to apply cleanly again and some improvements to the comments. This change closes some fairly minor security holes associated with F_SETOWN, fixes a few bugs, and removes some limitations that F_SETOWN had on tty devices. For more details, see the description on the PR. Because this patch increases the size of the proc and pgrp structures, it is necessary to re-install the includes and recompile libkvm, the vinum lkm, fstat, gcore, gdb, ipfilter, ps, top, and w. PR: kern/7899 Reviewed by: bde, elvind
1998-11-11 10:04:13 +00:00
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
case SIOCGPGRP:
In an SMP environment post-Giant it is no longer safe to blindly dereference the struct sigio pointer without any locking. Change fgetown() to take a reference to the pointer instead of a copy of the pointer and call SIGIO_LOCK() before copying the pointer and dereferencing it. Reviewed by: rwatson
2002-10-03 02:13:00 +00:00
*(int *)data = -fgetown(&so->so_sigio);
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
break;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
case SIOCATMARK:
Annotate two intentionally unlocked reads with comments. Annotate a potentially inconsistent result returned to user space when performing fstaT() on a socket due to not using socket buffer locking.
2004-06-20 17:35:50 +00:00
/* Unlocked read. */
The socket field so_state is used to hold a variety of socket related flags relating to several aspects of socket functionality. This change breaks out several bits relating to send and receive operation into a new per-socket buffer field, sb_state, in order to facilitate locking. This is required because, in order to provide more granular locking of sockets, different state fields have different locking properties. The following fields are moved to sb_state: SS_CANTRCVMORE (so_state) SS_CANTSENDMORE (so_state) SS_RCVATMARK (so_state) Rename respectively to: SBS_CANTRCVMORE (so_rcv.sb_state) SBS_CANTSENDMORE (so_snd.sb_state) SBS_RCVATMARK (so_rcv.sb_state) This facilitates locking by isolating fields to be located with other identically locked fields, and permits greater granularity in socket locking by avoiding storing fields with different locking semantics in the same short (avoiding locking conflicts). In the future, we may wish to coallesce sb_state and sb_flags; for the time being I leave them separate and there is no additional memory overhead due to the packing/alignment of shorts in the socket buffer structure.
2004-06-14 18:16:22 +00:00
*(int *)data = (so->so_rcv.sb_state & SBS_RCVATMARK) != 0;
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
break;
default:
/*
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
* Interface/routing/protocol specific ioctls: interface and
* routing ioctls should have a different entry since a
* socket is unnecessary.
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
*/
if (IOCGROUP(cmd) == 'i')
error = ifioctl(so, cmd, data, td);
Mfp4 CH=177274,177280,177284-177285,177297,177324-177325 VNET socket push back: try to minimize the number of places where we have to switch vnets and narrow down the time we stay switched. Add assertions to the socket code to catch possibly unset vnets as seen in r204147. While this reduces the number of vnet recursion in some places like NFS, POSIX local sockets and some netgraph, .. recursions are impossible to fix. The current expectations are documented at the beginning of uipc_socket.c along with the other information there. Sponsored by: The FreeBSD Foundation Sponsored by: CK Software GmbH Reviewed by: jhb Tested by: zec Tested by: Mikolaj Golub (to.my.trociny gmail.com) MFC after: 2 weeks
2011-02-16 21:29:13 +00:00
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);
Mfp4 CH=177274,177280,177284-177285,177297,177324-177325 VNET socket push back: try to minimize the number of places where we have to switch vnets and narrow down the time we stay switched. Add assertions to the socket code to catch possibly unset vnets as seen in r204147. While this reduces the number of vnet recursion in some places like NFS, POSIX local sockets and some netgraph, .. recursions are impossible to fix. The current expectations are documented at the beginning of uipc_socket.c along with the other information there. Sponsored by: The FreeBSD Foundation Sponsored by: CK Software GmbH Reviewed by: jhb Tested by: zec Tested by: Mikolaj Golub (to.my.trociny gmail.com) MFC after: 2 weeks
2011-02-16 21:29:13 +00:00
CURVNET_RESTORE();
} else {
CURVNET_SET(so->so_vnet);
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
error = ((*so->so_proto->pr_usrreqs->pru_control)
(so, cmd, data, 0, td));
Mfp4 CH=177274,177280,177284-177285,177297,177324-177325 VNET socket push back: try to minimize the number of places where we have to switch vnets and narrow down the time we stay switched. Add assertions to the socket code to catch possibly unset vnets as seen in r204147. While this reduces the number of vnet recursion in some places like NFS, POSIX local sockets and some netgraph, .. recursions are impossible to fix. The current expectations are documented at the beginning of uipc_socket.c along with the other information there. Sponsored by: The FreeBSD Foundation Sponsored by: CK Software GmbH Reviewed by: jhb Tested by: zec Tested by: Mikolaj Golub (to.my.trociny gmail.com) MFC after: 2 weeks
2011-02-16 21:29:13 +00:00
CURVNET_RESTORE();
}
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
break;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
return (error);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
The big 4.4BSD Lite to FreeBSD 2.0.0 (Development) patch. Reviewed by: Rodney W. Grimes Submitted by: John Dyson and David Greenman
1994-05-25 09:21:21 +00:00
int
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
soo_poll(struct file *fp, int events, struct ucred *active_cred,
struct thread *td)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
Bow to the whining masses and change a union back into void *. Retain removal of unnecessary casts and throw in some minor cleanups to see if anyone complains, just for the hell of it.
2003-01-13 00:33:17 +00:00
struct socket *so = fp->f_data;
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
#ifdef MAC
Polish two functions a bit so that it is easier to wrap them in locks if/when we need that.
2004-11-13 17:21:26 +00:00
int error;
Merge first in a series of TrustedBSD MAC Framework KPI changes from Mac OS X Leopard--rationalize naming for entry points to the following general forms: mac_<object>_<method/action> mac_<object>_check_<method/action> The previous naming scheme was inconsistent and mostly reversed from the new scheme. Also, make object types more consistent and remove spaces from object types that contain multiple parts ("posix_sem" -> "posixsem") to make mechanical parsing easier. Introduce a new "netinet" object type for certain IPv4/IPv6-related methods. Also simplify, slightly, some entry point names. All MAC policy modules will need to be recompiled, and modules not updates as part of this commit will need to be modified to conform to the new KPI. Sponsored by: SPARTA (original patches against Mac OS X) Obtained from: TrustedBSD Project, Apple Computer
2007-10-24 19:04:04 +00:00
error = mac_socket_check_poll(active_cred, so);
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
if (error)
Introduce three additional MAC Framework and MAC Policy entry points to control socket poll() (select()), fstat(), and accept() operations, required for some policies: poll() mac_check_socket_poll() fstat() mac_check_socket_stat() accept() mac_check_socket_accept() Update mac_stub and mac_test policies to be aware of these entry points. While here, add missing entry point implementations for: mac_stub.c stub_check_socket_receive() mac_stub.c stub_check_socket_send() mac_test.c mac_test_check_socket_send() mac_test.c mac_test_check_socket_visible() Obtained from: TrustedBSD Project Sponsored by: SPAWAR, SPARTA
2005-04-16 18:46:29 +00:00
return (error);
#endif
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
return (sopoll(so, events, fp->f_cred, td));
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
The big 4.4BSD Lite to FreeBSD 2.0.0 (Development) patch. Reviewed by: Rodney W. Grimes Submitted by: John Dyson and David Greenman
1994-05-25 09:21:21 +00:00
int
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
soo_stat(struct file *fp, struct stat *ub, struct ucred *active_cred,
struct thread *td)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
Bow to the whining masses and change a union back into void *. Retain removal of unnecessary casts and throw in some minor cleanups to see if anyone complains, just for the hell of it.
2003-01-13 00:33:17 +00:00
struct socket *so = fp->f_data;
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
#ifdef MAC
Push Giant acquisition down into fo_stat() from most callers. Acquire Giant conditional on debug.mpsafenet in the socket soo_stat() routine, unconditionally in vn_statfile() for VFS, and otherwise don't acquire Giant. Accept an unlocked read in kqueue_stat(), and cryptof_stat() is a no-op. Don't acquire Giant in fstat() system call. Note: in fdescfs, fo_stat() is called while holding Giant due to the VFS stack sitting on top, and therefore there will still be Giant recursion in this case.
2004-07-22 20:40:23 +00:00
int error;
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
#endif
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
bzero((caddr_t)ub, sizeof (*ub));
Instead of just blindly setting -rw-rw-rw-: o Set access mode to -r--r--r-- if SS_CANTRCVMORE is set and the receive buffer is empty. o Set access mode to --w--w--w- is SS_CANTSENDMORE is set. Discussed with: alfred
2000-07-02 23:56:45 +00:00
ub->st_mode = S_IFSOCK;
Introduce three additional MAC Framework and MAC Policy entry points to control socket poll() (select()), fstat(), and accept() operations, required for some policies: poll() mac_check_socket_poll() fstat() mac_check_socket_stat() accept() mac_check_socket_accept() Update mac_stub and mac_test policies to be aware of these entry points. While here, add missing entry point implementations for: mac_stub.c stub_check_socket_receive() mac_stub.c stub_check_socket_send() mac_test.c mac_test_check_socket_send() mac_test.c mac_test_check_socket_visible() Obtained from: TrustedBSD Project Sponsored by: SPAWAR, SPARTA
2005-04-16 18:46:29 +00:00
#ifdef MAC
Merge first in a series of TrustedBSD MAC Framework KPI changes from Mac OS X Leopard--rationalize naming for entry points to the following general forms: mac_<object>_<method/action> mac_<object>_check_<method/action> The previous naming scheme was inconsistent and mostly reversed from the new scheme. Also, make object types more consistent and remove spaces from object types that contain multiple parts ("posix_sem" -> "posixsem") to make mechanical parsing easier. Introduce a new "netinet" object type for certain IPv4/IPv6-related methods. Also simplify, slightly, some entry point names. All MAC policy modules will need to be recompiled, and modules not updates as part of this commit will need to be modified to conform to the new KPI. Sponsored by: SPARTA (original patches against Mac OS X) Obtained from: TrustedBSD Project, Apple Computer
2007-10-24 19:04:04 +00:00
error = mac_socket_check_stat(active_cred, so);
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
if (error)
Introduce three additional MAC Framework and MAC Policy entry points to control socket poll() (select()), fstat(), and accept() operations, required for some policies: poll() mac_check_socket_poll() fstat() mac_check_socket_stat() accept() mac_check_socket_accept() Update mac_stub and mac_test policies to be aware of these entry points. While here, add missing entry point implementations for: mac_stub.c stub_check_socket_receive() mac_stub.c stub_check_socket_send() mac_test.c mac_test_check_socket_send() mac_test.c mac_test_check_socket_visible() Obtained from: TrustedBSD Project Sponsored by: SPAWAR, SPARTA
2005-04-16 18:46:29 +00:00
return (error);
#endif
Instead of just blindly setting -rw-rw-rw-: o Set access mode to -r--r--r-- if SS_CANTRCVMORE is set and the receive buffer is empty. o Set access mode to --w--w--w- is SS_CANTSENDMORE is set. Discussed with: alfred
2000-07-02 23:56:45 +00:00
/*
The socket field so_state is used to hold a variety of socket related flags relating to several aspects of socket functionality. This change breaks out several bits relating to send and receive operation into a new per-socket buffer field, sb_state, in order to facilitate locking. This is required because, in order to provide more granular locking of sockets, different state fields have different locking properties. The following fields are moved to sb_state: SS_CANTRCVMORE (so_state) SS_CANTSENDMORE (so_state) SS_RCVATMARK (so_state) Rename respectively to: SBS_CANTRCVMORE (so_rcv.sb_state) SBS_CANTSENDMORE (so_snd.sb_state) SBS_RCVATMARK (so_rcv.sb_state) This facilitates locking by isolating fields to be located with other identically locked fields, and permits greater granularity in socket locking by avoiding storing fields with different locking semantics in the same short (avoiding locking conflicts). In the future, we may wish to coallesce sb_state and sb_flags; for the time being I leave them separate and there is no additional memory overhead due to the packing/alignment of shorts in the socket buffer structure.
2004-06-14 18:16:22 +00:00
* If SBS_CANTRCVMORE is set, but there's still data left in the
Instead of just blindly setting -rw-rw-rw-: o Set access mode to -r--r--r-- if SS_CANTRCVMORE is set and the receive buffer is empty. o Set access mode to --w--w--w- is SS_CANTSENDMORE is set. Discussed with: alfred
2000-07-02 23:56:45 +00:00
* receive buffer, the socket is still readable.
*/
Lock receive socket buffer in soo_stat() rather than commenting that we should lock it, which may marginally improve the consistency of the results. Remove comment. MFC after: 3 days
2008-10-07 07:10:28 +00:00
SOCKBUF_LOCK(&so->so_rcv);
The socket field so_state is used to hold a variety of socket related flags relating to several aspects of socket functionality. This change breaks out several bits relating to send and receive operation into a new per-socket buffer field, sb_state, in order to facilitate locking. This is required because, in order to provide more granular locking of sockets, different state fields have different locking properties. The following fields are moved to sb_state: SS_CANTRCVMORE (so_state) SS_CANTSENDMORE (so_state) SS_RCVATMARK (so_state) Rename respectively to: SBS_CANTRCVMORE (so_rcv.sb_state) SBS_CANTSENDMORE (so_snd.sb_state) SBS_RCVATMARK (so_rcv.sb_state) This facilitates locking by isolating fields to be located with other identically locked fields, and permits greater granularity in socket locking by avoiding storing fields with different locking semantics in the same short (avoiding locking conflicts). In the future, we may wish to coallesce sb_state and sb_flags; for the time being I leave them separate and there is no additional memory overhead due to the packing/alignment of shorts in the socket buffer structure.
2004-06-14 18:16:22 +00:00
if ((so->so_rcv.sb_state & SBS_CANTRCVMORE) == 0 ||
Instead of just blindly setting -rw-rw-rw-: o Set access mode to -r--r--r-- if SS_CANTRCVMORE is set and the receive buffer is empty. o Set access mode to --w--w--w- is SS_CANTSENDMORE is set. Discussed with: alfred
2000-07-02 23:56:45 +00:00
so->so_rcv.sb_cc != 0)
ub->st_mode |= S_IRUSR | S_IRGRP | S_IROTH;
Lock receive socket buffer in soo_stat() rather than commenting that we should lock it, which may marginally improve the consistency of the results. Remove comment. MFC after: 3 days
2008-10-07 07:10:28 +00:00
ub->st_size = so->so_rcv.sb_cc - so->so_rcv.sb_ctl;
SOCKBUF_UNLOCK(&so->so_rcv);
/* Unlocked read. */
The socket field so_state is used to hold a variety of socket related flags relating to several aspects of socket functionality. This change breaks out several bits relating to send and receive operation into a new per-socket buffer field, sb_state, in order to facilitate locking. This is required because, in order to provide more granular locking of sockets, different state fields have different locking properties. The following fields are moved to sb_state: SS_CANTRCVMORE (so_state) SS_CANTSENDMORE (so_state) SS_RCVATMARK (so_state) Rename respectively to: SBS_CANTRCVMORE (so_rcv.sb_state) SBS_CANTSENDMORE (so_snd.sb_state) SBS_RCVATMARK (so_rcv.sb_state) This facilitates locking by isolating fields to be located with other identically locked fields, and permits greater granularity in socket locking by avoiding storing fields with different locking semantics in the same short (avoiding locking conflicts). In the future, we may wish to coallesce sb_state and sb_flags; for the time being I leave them separate and there is no additional memory overhead due to the packing/alignment of shorts in the socket buffer structure.
2004-06-14 18:16:22 +00:00
if ((so->so_snd.sb_state & SBS_CANTSENDMORE) == 0)
Instead of just blindly setting -rw-rw-rw-: o Set access mode to -r--r--r-- if SS_CANTRCVMORE is set and the receive buffer is empty. o Set access mode to --w--w--w- is SS_CANTSENDMORE is set. Discussed with: alfred
2000-07-02 23:56:45 +00:00
ub->st_mode |= S_IWUSR | S_IWGRP | S_IWOTH;
Include the UID and GID values filled in by socreate() into socket->so_cred for stat() calls. Reviewed by: phk
2000-05-11 22:08:57 +00:00
ub->st_uid = so->so_cred->cr_uid;
ub->st_gid = so->so_cred->cr_gid;
Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which previously conditionally acquired Giant based on debug.mpsafenet. As that has now been removed, they are no longer required. Removing them significantly simplifies error-handling in the socket layer, eliminated quite a bit of unwinding of locking in error cases. While here clean up the now unneeded opt_net.h, which previously was used for the NET_WITH_GIANT kernel option. Clean up some related gotos for consistency. Reviewed by: bz, csjp Tested by: kris Approved by: re (kensmith)
2007-08-06 14:26:03 +00:00
return (*so->so_proto->pr_usrreqs->pru_sense)(so, ub);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
Give struct socket structures a ref counting interface similar to vnodes. This will hopefully serve as a base from which we can expand the MP code. We currently do not attempt to obtain any mutex or SX locks, but the door is open to add them when we nail down exactly how that part of it is going to work.
2001-11-17 03:07:11 +00:00
/*
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +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.
Give struct socket structures a ref counting interface similar to vnodes. This will hopefully serve as a base from which we can expand the MP code. We currently do not attempt to obtain any mutex or SX locks, but the door is open to add them when we nail down exactly how that part of it is going to work.
2001-11-17 03:07:11 +00:00
*/
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
/* ARGSUSED */
Unstaticized routines which are needed by the svr4 KLD and the streams garbage needed to support SysVR4 networking.
1999-01-30 06:25:00 +00:00
int
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
soo_close(struct file *fp, struct thread *td)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
int error = 0;
Give struct socket structures a ref counting interface similar to vnodes. This will hopefully serve as a base from which we can expand the MP code. We currently do not attempt to obtain any mutex or SX locks, but the door is open to add them when we nail down exactly how that part of it is going to work.
2001-11-17 03:07:11 +00:00
struct socket *so;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
Bow to the whining masses and change a union back into void *. Retain removal of unnecessary casts and throw in some minor cleanups to see if anyone complains, just for the hell of it.
2003-01-13 00:33:17 +00:00
so = fp->f_data;
Fix fd race conditions (during shared fd table usage.) Badfileops is now used in f_ops in place of NULL, and modifications to the files are more carefully ordered. f_ops should also be set to &badfileops upon "close" of a file. This does not fix other problems mentioned in this PR than the first one. PR: 11629 Reviewed by: peter
1999-08-04 18:53:50 +00:00
fp->f_ops = &badfileops;
Bow to the whining masses and change a union back into void *. Retain removal of unnecessary casts and throw in some minor cleanups to see if anyone complains, just for the hell of it.
2003-01-13 00:33:17 +00:00
fp->f_data = NULL;
SMP Lock struct file, filedesc and the global file list. Seigo Tanimura (tanimura) posted the initial delta. I've polished it quite a bit reducing the need for locking and adapting it for KSE. Locks: 1 mutex in each filedesc protects all the fields. protects "struct file" initialization, while a struct file is being changed from &badfileops -> &pipeops or something the filedesc should be locked. 1 mutex in each struct file protects the refcount fields. doesn't protect anything else. the flags used for garbage collection have been moved to f_gcflag which was the FILLER short, this doesn't need locking because the garbage collection is a single threaded container. could likely be made to use a pool mutex. 1 sx lock for the global filelist. struct file * fhold(struct file *fp); /* increments reference count on a file */ struct file * fhold_locked(struct file *fp); /* like fhold but expects file to locked */ struct file * ffind_hold(struct thread *, int fd); /* finds the struct file in thread, adds one reference and returns it unlocked */ struct file * ffind_lock(struct thread *, int fd); /* ffind_hold, but returns file locked */ I still have to smp-safe the fget cruft, I'll get to that asap.
2002-01-13 11:58:06 +00:00
if (so)
Give struct socket structures a ref counting interface similar to vnodes. This will hopefully serve as a base from which we can expand the MP code. We currently do not attempt to obtain any mutex or SX locks, but the door is open to add them when we nail down exactly how that part of it is going to work.
2001-11-17 03:07:11 +00:00
error = soclose(so);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
return (error);
}
Reference in New Issue Copy Permalink