d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ec2af96ad1
freebsd-nq/sys/kern/sys_socket.c

300 lines
7.4 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("$FreeBSD$");
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
#include "opt_mac.h"
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>
#include <net/route.h>
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,
.fo_ioctl = soo_ioctl,
.fo_poll = soo_poll,
.fo_kqfilter = soo_kqfilter,
.fo_stat = soo_stat,
.fo_close = soo_close,
.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;
Conditionally acquire Giant when entering the socket layer via file descriptor operations based on debug.mpsafenet, rather than acquiring Giant unconditionally.
2004-03-29 01:55:32 +00:00
NET_LOCK_GIANT();
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
Socket MAC labels so_label and so_peerlabel are now protected by SOCK_LOCK(so): - Hold socket lock over calls to MAC entry points reading or manipulating socket labels. - Assert socket lock in MAC entry point implementations. - When externalizing the socket label, first make a thread-local copy while holding the socket lock, then release the socket lock to externalize to userspace.
2004-06-13 02:50:07 +00:00
SOCK_LOCK(so);
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
error = mac_check_socket_receive(active_cred, so);
Socket MAC labels so_label and so_peerlabel are now protected by SOCK_LOCK(so): - Hold socket lock over calls to MAC entry points reading or manipulating socket labels. - Assert socket lock in MAC entry point implementations. - When externalizing the socket label, first make a thread-local copy while holding the socket lock, then release the socket lock to externalize to userspace.
2004-06-13 02:50:07 +00:00
SOCK_UNLOCK(so);
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
if (error) {
Conditionally acquire Giant when entering the socket layer via file descriptor operations based on debug.mpsafenet, rather than acquiring Giant unconditionally.
2004-03-29 01:55:32 +00:00
NET_UNLOCK_GIANT();
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 = soreceive(so, 0, uio, 0, 0, 0);
Conditionally acquire Giant when entering the socket layer via file descriptor operations based on debug.mpsafenet, rather than acquiring Giant unconditionally.
2004-03-29 01:55:32 +00:00
NET_UNLOCK_GIANT();
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
}
/* 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;
Conditionally acquire Giant when entering the socket layer via file descriptor operations based on debug.mpsafenet, rather than acquiring Giant unconditionally.
2004-03-29 01:55:32 +00:00
NET_LOCK_GIANT();
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
Socket MAC labels so_label and so_peerlabel are now protected by SOCK_LOCK(so): - Hold socket lock over calls to MAC entry points reading or manipulating socket labels. - Assert socket lock in MAC entry point implementations. - When externalizing the socket label, first make a thread-local copy while holding the socket lock, then release the socket lock to externalize to userspace.
2004-06-13 02:50:07 +00:00
SOCK_LOCK(so);
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
error = mac_check_socket_send(active_cred, so);
Socket MAC labels so_label and so_peerlabel are now protected by SOCK_LOCK(so): - Hold socket lock over calls to MAC entry points reading or manipulating socket labels. - Assert socket lock in MAC entry point implementations. - When externalizing the socket label, first make a thread-local copy while holding the socket lock, then release the socket lock to externalize to userspace.
2004-06-13 02:50:07 +00:00
SOCK_UNLOCK(so);
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
if (error) {
Conditionally acquire Giant when entering the socket layer via file descriptor operations based on debug.mpsafenet, rather than acquiring Giant unconditionally.
2004-03-29 01:55:32 +00:00
NET_UNLOCK_GIANT();
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);
psignal(uio->uio_td->td_proc, SIGPIPE);
PROC_UNLOCK(uio->uio_td->td_proc);
}
Conditionally acquire Giant when entering the socket layer via file descriptor operations based on debug.mpsafenet, rather than acquiring Giant unconditionally.
2004-03-29 01:55:32 +00:00
NET_UNLOCK_GIANT();
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
}
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
Push Giant down through ioctl. Don't grab Giant in the upper syscall/wrapper code NET_LOCK_GIANT in the socket code (sockets/fifos). mtx_lock(&Giant) in the vnode code. mtx_lock(&Giant) in the opencrypto code. (This may actually not be needed, but better safe than sorry). Devfs grabs Giant if the driver is marked as needing Giant.
2004-11-17 09:09:55 +00:00
NET_LOCK_GIANT();
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
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);
else if (IOCGROUP(cmd) == 'r')
error = rtioctl(cmd, data);
else
error = ((*so->so_proto->pr_usrreqs->pru_control)
(so, cmd, data, 0, td));
break;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
Push Giant down through ioctl. Don't grab Giant in the upper syscall/wrapper code NET_LOCK_GIANT in the socket code (sockets/fifos). mtx_lock(&Giant) in the vnode code. mtx_lock(&Giant) in the opencrypto code. (This may actually not be needed, but better safe than sorry). Devfs grabs Giant if the driver is marked as needing Giant.
2004-11-17 09:09:55 +00:00
NET_UNLOCK_GIANT();
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
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;
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;
Push Giant down through select and poll. Don't grab Giant in the upper syscall/wrapper code NET_LOCK_GIANT in the socket code (sockets/fifos). mtx_lock(&Giant) in the vnode code. Devfs grabs Giant if the driver is marked as needing Giant.
2004-11-17 08:01:10 +00:00
NET_LOCK_GIANT();
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
SOCK_LOCK(so);
error = mac_check_socket_poll(active_cred, so);
SOCK_UNLOCK(so);
if (error) {
NET_UNLOCK_GIANT();
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 = sopoll(so, events, fp->f_cred, td);
Push Giant down through select and poll. Don't grab Giant in the upper syscall/wrapper code NET_LOCK_GIANT in the socket code (sockets/fifos). mtx_lock(&Giant) in the vnode code. Devfs grabs Giant if the driver is marked as needing Giant.
2004-11-17 08:01:10 +00:00
NET_UNLOCK_GIANT();
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
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_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;
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;
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;
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
NET_LOCK_GIANT();
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
SOCK_LOCK(so);
error = mac_check_socket_stat(active_cred, so);
SOCK_UNLOCK(so);
if (error) {
NET_UNLOCK_GIANT();
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.
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
*
Move to ANSI C function headers. Re-wrap some comments.
2007-03-04 17:50:46 +00:00
* XXXRW: perhaps should lock socket buffer so st_size result is
* consistent.
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
*/
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
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;
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;
Update the st_size reported via stat(2) to accurately reflect the amount of data available to read for non-TCP sockets. Reviewed by: -net, -arch Sponsored by: NTT Multimedia Communications Labs MFC after: 2 weeks
2002-11-01 21:31:13 +00:00
ub->st_size = so->so_rcv.sb_cc - so->so_rcv.sb_ctl;
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;
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
error = (*so->so_proto->pr_usrreqs->pru_sense)(so, ub);
NET_UNLOCK_GIANT();
return (error);
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
Push acquisition of Giant from fdrop_closed() into fo_close() so that individual file object implementations can optionally acquire Giant if they require it: - soo_close(): depends on debug.mpsafenet - pipe_close(): Giant not acquired - kqueue_close(): Giant required - vn_close(): Giant required - cryptof_close(): Giant required (conservative) Notes: Giant is still acquired in close() even when closing MPSAFE objects due to kqueue requiring Giant in the calling closef() code. Microbenchmarks indicate that this removal of Giant cuts 3%-3% off of pipe create/destroy pairs from user space with SMP compiled into the kernel. The cryptodev and opencrypto code appears MPSAFE, but I'm unable to test it extensively and so have left Giant over fo_close(). It can probably be removed given some testing and review.
2004-07-22 18:35:43 +00:00
NET_LOCK_GIANT();
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);
Push acquisition of Giant from fdrop_closed() into fo_close() so that individual file object implementations can optionally acquire Giant if they require it: - soo_close(): depends on debug.mpsafenet - pipe_close(): Giant not acquired - kqueue_close(): Giant required - vn_close(): Giant required - cryptof_close(): Giant required (conservative) Notes: Giant is still acquired in close() even when closing MPSAFE objects due to kqueue requiring Giant in the calling closef() code. Microbenchmarks indicate that this removal of Giant cuts 3%-3% off of pipe create/destroy pairs from user space with SMP compiled into the kernel. The cryptodev and opencrypto code appears MPSAFE, but I'm unable to test it extensively and so have left Giant over fo_close(). It can probably be removed given some testing and review.
2004-07-22 18:35:43 +00:00
NET_UNLOCK_GIANT();
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
return (error);
}
Reference in New Issue Copy Permalink