2005-01-06 23:35:40 +00:00
|
|
|
/*-
|
2017-11-20 19:43:44 +00:00
|
|
|
* SPDX-License-Identifier: BSD-3-Clause
|
|
|
|
|
*
|
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.
|
2016-09-15 13:16:20 +00:00
|
|
|
* 3. Neither the name of the University nor the names of its contributors
|
1994-05-24 10:09:53 +00:00
|
|
|
* may be used to endorse or promote products derived from this software
|
|
|
|
|
* without specific prior written permission.
|
|
|
|
|
*
|
|
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
|
|
|
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
|
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
|
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
|
|
|
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
|
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
|
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
|
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
|
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
|
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
|
|
|
* SUCH DAMAGE.
|
|
|
|
|
*
|
|
|
|
|
* @(#)sys_socket.c 8.1 (Berkeley) 6/10/93
|
|
|
|
|
*/
|
|
|
|
|
|
2003-06-11 00:56:59 +00:00
|
|
|
#include <sys/cdefs.h>
|
|
|
|
|
__FBSDID("$FreeBSD$");
|
|
|
|
|
|
1994-05-24 10:09:53 +00:00
|
|
|
#include <sys/param.h>
|
|
|
|
|
#include <sys/systm.h>
|
2016-03-01 18:12:14 +00:00
|
|
|
#include <sys/aio.h>
|
2014-09-22 16:20:47 +00:00
|
|
|
#include <sys/domain.h>
|
1994-05-24 10:09:53 +00:00
|
|
|
#include <sys/file.h>
|
2003-01-01 01:56:19 +00:00
|
|
|
#include <sys/filedesc.h>
|
2016-03-01 18:12:14 +00:00
|
|
|
#include <sys/kernel.h>
|
|
|
|
|
#include <sys/kthread.h>
|
2014-09-22 16:20:47 +00:00
|
|
|
#include <sys/malloc.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>
|
1994-05-24 10:09:53 +00:00
|
|
|
#include <sys/protosw.h>
|
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>
|
1994-05-24 10:09:53 +00:00
|
|
|
#include <sys/socket.h>
|
|
|
|
|
#include <sys/socketvar.h>
|
1997-03-24 11:52:29 +00:00
|
|
|
#include <sys/filio.h> /* XXX */
|
|
|
|
|
#include <sys/sockio.h>
|
1994-05-24 10:09:53 +00:00
|
|
|
#include <sys/stat.h>
|
2016-03-01 18:12:14 +00:00
|
|
|
#include <sys/sysctl.h>
|
|
|
|
|
#include <sys/sysproto.h>
|
|
|
|
|
#include <sys/taskqueue.h>
|
1998-03-28 10:33:27 +00:00
|
|
|
#include <sys/uio.h>
|
2000-05-11 22:08:57 +00:00
|
|
|
#include <sys/ucred.h>
|
2014-09-22 16:20:47 +00:00
|
|
|
#include <sys/un.h>
|
|
|
|
|
#include <sys/unpcb.h>
|
|
|
|
|
#include <sys/user.h>
|
1994-05-24 10:09:53 +00:00
|
|
|
|
|
|
|
|
#include <net/if.h>
|
2013-10-26 17:58:36 +00:00
|
|
|
#include <net/if_var.h>
|
1994-05-24 10:09:53 +00:00
|
|
|
#include <net/route.h>
|
2009-08-01 19:26:27 +00:00
|
|
|
#include <net/vnet.h>
|
1994-05-24 10:09:53 +00:00
|
|
|
|
2014-09-22 16:20:47 +00:00
|
|
|
#include <netinet/in.h>
|
|
|
|
|
#include <netinet/in_pcb.h>
|
|
|
|
|
|
2006-10-22 11:52:19 +00:00
|
|
|
#include <security/mac/mac_framework.h>
|
|
|
|
|
|
2016-03-01 18:12:14 +00:00
|
|
|
#include <vm/vm.h>
|
|
|
|
|
#include <vm/pmap.h>
|
|
|
|
|
#include <vm/vm_extern.h>
|
|
|
|
|
#include <vm/vm_map.h>
|
|
|
|
|
|
|
|
|
|
static SYSCTL_NODE(_kern_ipc, OID_AUTO, aio, CTLFLAG_RD, NULL,
|
|
|
|
|
"socket AIO stats");
|
|
|
|
|
|
|
|
|
|
static int empty_results;
|
|
|
|
|
SYSCTL_INT(_kern_ipc_aio, OID_AUTO, empty_results, CTLFLAG_RD, &empty_results,
|
|
|
|
|
0, "socket operation returned EAGAIN");
|
|
|
|
|
|
|
|
|
|
static int empty_retries;
|
|
|
|
|
SYSCTL_INT(_kern_ipc_aio, OID_AUTO, empty_retries, CTLFLAG_RD, &empty_retries,
|
|
|
|
|
0, "socket operation retries");
|
|
|
|
|
|
2014-08-26 14:44:08 +00:00
|
|
|
static fo_rdwr_t soo_read;
|
|
|
|
|
static fo_rdwr_t soo_write;
|
|
|
|
|
static fo_ioctl_t soo_ioctl;
|
|
|
|
|
static fo_poll_t soo_poll;
|
|
|
|
|
extern fo_kqfilter_t soo_kqfilter;
|
|
|
|
|
static fo_stat_t soo_stat;
|
|
|
|
|
static fo_close_t soo_close;
|
2014-09-22 16:20:47 +00:00
|
|
|
static fo_fill_kinfo_t soo_fill_kinfo;
|
2016-03-01 18:12:14 +00:00
|
|
|
static fo_aio_queue_t soo_aio_queue;
|
|
|
|
|
|
|
|
|
|
static void soo_aio_cancel(struct kaiocb *job);
|
2014-08-26 14:44:08 +00:00
|
|
|
|
2007-03-04 17:50:46 +00:00
|
|
|
struct fileops socketops = {
|
2003-06-18 18:16:40 +00:00
|
|
|
.fo_read = soo_read,
|
|
|
|
|
.fo_write = soo_write,
|
2014-08-26 14:44:08 +00:00
|
|
|
.fo_truncate = invfo_truncate,
|
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,
|
2011-08-16 20:07:47 +00:00
|
|
|
.fo_chmod = invfo_chmod,
|
|
|
|
|
.fo_chown = invfo_chown,
|
2013-08-15 07:54:31 +00:00
|
|
|
.fo_sendfile = invfo_sendfile,
|
2014-09-22 16:20:47 +00:00
|
|
|
.fo_fill_kinfo = soo_fill_kinfo,
|
2016-03-01 18:12:14 +00:00
|
|
|
.fo_aio_queue = soo_aio_queue,
|
2003-06-18 18:16:40 +00:00
|
|
|
.fo_flags = DFLAG_PASSABLE
|
2001-02-15 16:34:11 +00:00
|
|
|
};
|
1994-05-24 10:09:53 +00:00
|
|
|
|
2014-08-26 14:44:08 +00:00
|
|
|
static int
|
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)
|
1994-05-24 10:09:53 +00:00
|
|
|
{
|
2003-01-13 00:33:17 +00:00
|
|
|
struct socket *so = fp->f_data;
|
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
|
2007-10-24 19:04:04 +00:00
|
|
|
error = mac_socket_check_receive(active_cred, so);
|
2007-08-06 14:26:03 +00:00
|
|
|
if (error)
|
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);
|
1994-05-24 10:09:53 +00:00
|
|
|
}
|
|
|
|
|
|
2014-08-26 14:44:08 +00:00
|
|
|
static int
|
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)
|
1994-05-24 10:09:53 +00:00
|
|
|
{
|
2003-01-13 00:33:17 +00:00
|
|
|
struct socket *so = fp->f_data;
|
2002-03-15 08:03:46 +00:00
|
|
|
int error;
|
|
|
|
|
|
2002-10-06 14:39:15 +00:00
|
|
|
#ifdef MAC
|
2007-10-24 19:04:04 +00:00
|
|
|
error = mac_socket_check_send(active_cred, so);
|
2007-08-06 14:26:03 +00:00
|
|
|
if (error)
|
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);
|
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);
|
|
|
|
|
}
|
2002-03-15 08:03:46 +00:00
|
|
|
return (error);
|
1994-05-24 10:09:53 +00:00
|
|
|
}
|
|
|
|
|
|
2014-08-26 14:44:08 +00:00
|
|
|
static int
|
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)
|
1994-05-24 10:09:53 +00:00
|
|
|
{
|
2004-11-13 17:21:26 +00:00
|
|
|
struct socket *so = fp->f_data;
|
|
|
|
|
int error = 0;
|
1994-05-24 10:09:53 +00:00
|
|
|
|
|
|
|
|
switch (cmd) {
|
|
|
|
|
case FIONBIO:
|
2004-06-17 22:48:11 +00:00
|
|
|
SOCK_LOCK(so);
|
1994-05-24 10:09:53 +00:00
|
|
|
if (*(int *)data)
|
|
|
|
|
so->so_state |= SS_NBIO;
|
|
|
|
|
else
|
|
|
|
|
so->so_state &= ~SS_NBIO;
|
2004-06-17 22:48:11 +00:00
|
|
|
SOCK_UNLOCK(so);
|
2004-11-13 17:21:26 +00:00
|
|
|
break;
|
1994-05-24 10:09:53 +00:00
|
|
|
|
|
|
|
|
case FIOASYNC:
|
|
|
|
|
if (*(int *)data) {
|
2004-06-17 22:48:11 +00:00
|
|
|
SOCK_LOCK(so);
|
1994-05-24 10:09:53 +00:00
|
|
|
so->so_state |= SS_ASYNC;
|
Listening sockets improvements.
o Separate fields of struct socket that belong to listening from
fields that belong to normal dataflow, and unionize them. This
shrinks the structure a bit.
- Take out selinfo's from the socket buffers into the socket. The
first reason is to support braindamaged scenario when a socket is
added to kevent(2) and then listen(2) is cast on it. The second
reason is that there is future plan to make socket buffers pluggable,
so that for a dataflow socket a socket buffer can be changed, and
in this case we also want to keep same selinfos through the lifetime
of a socket.
- Remove struct struct so_accf. Since now listening stuff no longer
affects struct socket size, just move its fields into listening part
of the union.
- Provide sol_upcall field and enforce that so_upcall_set() may be called
only on a dataflow socket, which has buffers, and for listening sockets
provide solisten_upcall_set().
o Remove ACCEPT_LOCK() global.
- Add a mutex to socket, to be used instead of socket buffer lock to lock
fields of struct socket that don't belong to a socket buffer.
- Allow to acquire two socket locks, but the first one must belong to a
listening socket.
- Make soref()/sorele() to use atomic(9). This allows in some situations
to do soref() without owning socket lock. There is place for improvement
here, it is possible to make sorele() also to lock optionally.
- Most protocols aren't touched by this change, except UNIX local sockets.
See below for more information.
o Reduce copy-and-paste in kernel modules that accept connections from
listening sockets: provide function solisten_dequeue(), and use it in
the following modules: ctl(4), iscsi(4), ng_btsocket(4), ng_ksocket(4),
infiniband, rpc.
o UNIX local sockets.
- Removal of ACCEPT_LOCK() global uncovered several races in the UNIX
local sockets. Most races exist around spawning a new socket, when we
are connecting to a local listening socket. To cover them, we need to
hold locks on both PCBs when spawning a third one. This means holding
them across sonewconn(). This creates a LOR between pcb locks and
unp_list_lock.
- To fix the new LOR, abandon the global unp_list_lock in favor of global
unp_link_lock. Indeed, separating these two locks didn't provide us any
extra parralelism in the UNIX sockets.
- Now call into uipc_attach() may happen with unp_link_lock hold if, we
are accepting, or without unp_link_lock in case if we are just creating
a socket.
- Another problem in UNIX sockets is that uipc_close() basicly did nothing
for a listening socket. The vnode remained opened for connections. This
is fixed by removing vnode in uipc_close(). Maybe the right way would be
to do it for all sockets (not only listening), simply move the vnode
teardown from uipc_detach() to uipc_close()?
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D9770
2017-06-08 21:30:34 +00:00
|
|
|
if (SOLISTENING(so)) {
|
|
|
|
|
so->sol_sbrcv_flags |= SB_ASYNC;
|
|
|
|
|
so->sol_sbsnd_flags |= SB_ASYNC;
|
|
|
|
|
} else {
|
|
|
|
|
SOCKBUF_LOCK(&so->so_rcv);
|
|
|
|
|
so->so_rcv.sb_flags |= SB_ASYNC;
|
|
|
|
|
SOCKBUF_UNLOCK(&so->so_rcv);
|
|
|
|
|
SOCKBUF_LOCK(&so->so_snd);
|
|
|
|
|
so->so_snd.sb_flags |= SB_ASYNC;
|
|
|
|
|
SOCKBUF_UNLOCK(&so->so_snd);
|
|
|
|
|
}
|
2004-06-17 22:48:11 +00:00
|
|
|
SOCK_UNLOCK(so);
|
1994-05-24 10:09:53 +00:00
|
|
|
} else {
|
2004-06-17 22:48:11 +00:00
|
|
|
SOCK_LOCK(so);
|
1994-05-24 10:09:53 +00:00
|
|
|
so->so_state &= ~SS_ASYNC;
|
Listening sockets improvements.
o Separate fields of struct socket that belong to listening from
fields that belong to normal dataflow, and unionize them. This
shrinks the structure a bit.
- Take out selinfo's from the socket buffers into the socket. The
first reason is to support braindamaged scenario when a socket is
added to kevent(2) and then listen(2) is cast on it. The second
reason is that there is future plan to make socket buffers pluggable,
so that for a dataflow socket a socket buffer can be changed, and
in this case we also want to keep same selinfos through the lifetime
of a socket.
- Remove struct struct so_accf. Since now listening stuff no longer
affects struct socket size, just move its fields into listening part
of the union.
- Provide sol_upcall field and enforce that so_upcall_set() may be called
only on a dataflow socket, which has buffers, and for listening sockets
provide solisten_upcall_set().
o Remove ACCEPT_LOCK() global.
- Add a mutex to socket, to be used instead of socket buffer lock to lock
fields of struct socket that don't belong to a socket buffer.
- Allow to acquire two socket locks, but the first one must belong to a
listening socket.
- Make soref()/sorele() to use atomic(9). This allows in some situations
to do soref() without owning socket lock. There is place for improvement
here, it is possible to make sorele() also to lock optionally.
- Most protocols aren't touched by this change, except UNIX local sockets.
See below for more information.
o Reduce copy-and-paste in kernel modules that accept connections from
listening sockets: provide function solisten_dequeue(), and use it in
the following modules: ctl(4), iscsi(4), ng_btsocket(4), ng_ksocket(4),
infiniband, rpc.
o UNIX local sockets.
- Removal of ACCEPT_LOCK() global uncovered several races in the UNIX
local sockets. Most races exist around spawning a new socket, when we
are connecting to a local listening socket. To cover them, we need to
hold locks on both PCBs when spawning a third one. This means holding
them across sonewconn(). This creates a LOR between pcb locks and
unp_list_lock.
- To fix the new LOR, abandon the global unp_list_lock in favor of global
unp_link_lock. Indeed, separating these two locks didn't provide us any
extra parralelism in the UNIX sockets.
- Now call into uipc_attach() may happen with unp_link_lock hold if, we
are accepting, or without unp_link_lock in case if we are just creating
a socket.
- Another problem in UNIX sockets is that uipc_close() basicly did nothing
for a listening socket. The vnode remained opened for connections. This
is fixed by removing vnode in uipc_close(). Maybe the right way would be
to do it for all sockets (not only listening), simply move the vnode
teardown from uipc_detach() to uipc_close()?
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D9770
2017-06-08 21:30:34 +00:00
|
|
|
if (SOLISTENING(so)) {
|
|
|
|
|
so->sol_sbrcv_flags &= ~SB_ASYNC;
|
|
|
|
|
so->sol_sbsnd_flags &= ~SB_ASYNC;
|
|
|
|
|
} else {
|
|
|
|
|
SOCKBUF_LOCK(&so->so_rcv);
|
|
|
|
|
so->so_rcv.sb_flags &= ~SB_ASYNC;
|
|
|
|
|
SOCKBUF_UNLOCK(&so->so_rcv);
|
|
|
|
|
SOCKBUF_LOCK(&so->so_snd);
|
|
|
|
|
so->so_snd.sb_flags &= ~SB_ASYNC;
|
|
|
|
|
SOCKBUF_UNLOCK(&so->so_snd);
|
|
|
|
|
}
|
2004-06-17 22:48:11 +00:00
|
|
|
SOCK_UNLOCK(so);
|
1994-05-24 10:09:53 +00:00
|
|
|
}
|
2004-11-13 17:21:26 +00:00
|
|
|
break;
|
1994-05-24 10:09:53 +00:00
|
|
|
|
|
|
|
|
case FIONREAD:
|
2004-06-20 17:35:50 +00:00
|
|
|
/* Unlocked read. */
|
2014-11-12 09:57:15 +00:00
|
|
|
*(int *)data = sbavail(&so->so_rcv);
|
2004-11-13 17:21:26 +00:00
|
|
|
break;
|
1994-05-24 10:09:53 +00:00
|
|
|
|
There are a number of ways an application can check if there are
inbound data waiting on a filedescriptor, such as a pipe or a socket,
for instance by using select(2), poll(2), kqueue(2), ioctl(FIONREAD)
etc.
But we have no way of finding out if written data have yet to be
disposed of, for instance, transmitted (and ack'ed!) to some remote
host, or read by the applicantion at the far end of the pipe.
The closest we get, is calling shutdown(2) on a TCP socket in
non-blocking mode, but this has the undesirable sideeffect of
preventing future communication.
Add a complement to FIONREAD, called FIONWRITE, which returns the
number of bytes not yet properly disposed of. Implement it for
all sockets.
Background:
A HTTP server will want to time out connections, if no new request
arrives within a certain period after the last transmitted response
has actually been sent (and ack'ed).
For a busy HTTP server, this timeout can be subsecond duration.
In order to signal to a load-balancer that the connection is truly
dead, TCP_RST will be the preferred method, as this avoids the need
for a RTT delay for FIN handshaking, with a client which, surprisingly
often, no longer at the remote IP number.
If a slow, distant client is being served a response which is big
enough to fill the window, but small enough to fit in the socket
buffer, the write(2) call will return immediately.
If the session timeout is armed at that time, all bytes in the
response may not have been transmitted by the time it fires.
FIONWRITE allows the timeout to check that no data is outstanding
on the connection, before it TCP_RST's it.
Input & Idea from: rwatson
Approved by: re (kib)
2009-06-28 11:28:14 +00:00
|
|
|
case FIONWRITE:
|
|
|
|
|
/* Unlocked read. */
|
2014-11-12 09:57:15 +00:00
|
|
|
*(int *)data = sbavail(&so->so_snd);
|
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
|
|
|
break;
|
|
|
|
|
|
2009-06-30 13:38:49 +00:00
|
|
|
case FIONSPACE:
|
2014-11-12 09:57:15 +00:00
|
|
|
/* Unlocked read. */
|
|
|
|
|
if ((so->so_snd.sb_hiwat < sbused(&so->so_snd)) ||
|
2009-06-30 13:38:49 +00:00
|
|
|
(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:
|
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:
|
2002-10-03 02:13:00 +00:00
|
|
|
*(int *)data = fgetown(&so->so_sigio);
|
2004-11-13 17:21:26 +00:00
|
|
|
break;
|
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:
|
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
|
|
|
|
1994-05-24 10:09:53 +00:00
|
|
|
case SIOCGPGRP:
|
2002-10-03 02:13:00 +00:00
|
|
|
*(int *)data = -fgetown(&so->so_sigio);
|
2004-11-13 17:21:26 +00:00
|
|
|
break;
|
1994-05-24 10:09:53 +00:00
|
|
|
|
|
|
|
|
case SIOCATMARK:
|
2004-06-20 17:35:50 +00:00
|
|
|
/* Unlocked read. */
|
2004-06-14 18:16:22 +00:00
|
|
|
*(int *)data = (so->so_rcv.sb_state & SBS_RCVATMARK) != 0;
|
2004-11-13 17:21:26 +00:00
|
|
|
break;
|
|
|
|
|
default:
|
|
|
|
|
/*
|
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.
|
2004-11-13 17:21:26 +00:00
|
|
|
*/
|
|
|
|
|
if (IOCGROUP(cmd) == 'i')
|
|
|
|
|
error = ifioctl(so, cmd, data, td);
|
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);
|
2011-02-16 21:29:13 +00:00
|
|
|
CURVNET_RESTORE();
|
|
|
|
|
} else {
|
|
|
|
|
CURVNET_SET(so->so_vnet);
|
2004-11-13 17:21:26 +00:00
|
|
|
error = ((*so->so_proto->pr_usrreqs->pru_control)
|
|
|
|
|
(so, cmd, data, 0, td));
|
2011-02-16 21:29:13 +00:00
|
|
|
CURVNET_RESTORE();
|
|
|
|
|
}
|
2004-11-13 17:21:26 +00:00
|
|
|
break;
|
1994-05-24 10:09:53 +00:00
|
|
|
}
|
2007-08-06 14:26:03 +00:00
|
|
|
return (error);
|
1994-05-24 10:09:53 +00:00
|
|
|
}
|
|
|
|
|
|
2014-08-26 14:44:08 +00:00
|
|
|
static int
|
2007-03-04 17:50:46 +00:00
|
|
|
soo_poll(struct file *fp, int events, struct ucred *active_cred,
|
|
|
|
|
struct thread *td)
|
1994-05-24 10:09:53 +00:00
|
|
|
{
|
2003-01-13 00:33:17 +00:00
|
|
|
struct socket *so = fp->f_data;
|
2007-08-06 14:26:03 +00:00
|
|
|
#ifdef MAC
|
2004-11-13 17:21:26 +00:00
|
|
|
int error;
|
|
|
|
|
|
2007-10-24 19:04:04 +00:00
|
|
|
error = mac_socket_check_poll(active_cred, so);
|
2007-08-06 14:26:03 +00:00
|
|
|
if (error)
|
2005-04-16 18:46:29 +00:00
|
|
|
return (error);
|
|
|
|
|
#endif
|
2007-08-06 14:26:03 +00:00
|
|
|
return (sopoll(so, events, fp->f_cred, td));
|
1994-05-24 10:09:53 +00:00
|
|
|
}
|
|
|
|
|
|
2014-08-26 14:44:08 +00:00
|
|
|
static int
|
2007-03-04 17:50:46 +00:00
|
|
|
soo_stat(struct file *fp, struct stat *ub, struct ucred *active_cred,
|
|
|
|
|
struct thread *td)
|
1994-05-24 10:09:53 +00:00
|
|
|
{
|
2003-01-13 00:33:17 +00:00
|
|
|
struct socket *so = fp->f_data;
|
2007-08-06 14:26:03 +00:00
|
|
|
#ifdef MAC
|
2004-07-22 20:40:23 +00:00
|
|
|
int error;
|
2007-08-06 14:26:03 +00:00
|
|
|
#endif
|
1994-05-24 10:09:53 +00:00
|
|
|
|
|
|
|
|
bzero((caddr_t)ub, sizeof (*ub));
|
2000-07-02 23:56:45 +00:00
|
|
|
ub->st_mode = S_IFSOCK;
|
2005-04-16 18:46:29 +00:00
|
|
|
#ifdef MAC
|
2007-10-24 19:04:04 +00:00
|
|
|
error = mac_socket_check_stat(active_cred, so);
|
2007-08-06 14:26:03 +00:00
|
|
|
if (error)
|
2005-04-16 18:46:29 +00:00
|
|
|
return (error);
|
|
|
|
|
#endif
|
2017-06-09 15:54:48 +00:00
|
|
|
if (!SOLISTENING(so)) {
|
|
|
|
|
struct sockbuf *sb;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If SBS_CANTRCVMORE is set, but there's still data left
|
|
|
|
|
* in the receive buffer, the socket is still readable.
|
|
|
|
|
*/
|
|
|
|
|
sb = &so->so_rcv;
|
|
|
|
|
SOCKBUF_LOCK(sb);
|
|
|
|
|
if ((sb->sb_state & SBS_CANTRCVMORE) == 0 || sbavail(sb))
|
|
|
|
|
ub->st_mode |= S_IRUSR | S_IRGRP | S_IROTH;
|
|
|
|
|
ub->st_size = sbavail(sb) - sb->sb_ctl;
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
|
|
|
|
|
sb = &so->so_snd;
|
|
|
|
|
SOCKBUF_LOCK(sb);
|
|
|
|
|
if ((sb->sb_state & SBS_CANTSENDMORE) == 0)
|
|
|
|
|
ub->st_mode |= S_IWUSR | S_IWGRP | S_IWOTH;
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
}
|
2000-05-11 22:08:57 +00:00
|
|
|
ub->st_uid = so->so_cred->cr_uid;
|
|
|
|
|
ub->st_gid = so->so_cred->cr_gid;
|
2007-08-06 14:26:03 +00:00
|
|
|
return (*so->so_proto->pr_usrreqs->pru_sense)(so, ub);
|
1994-05-24 10:09:53 +00:00
|
|
|
}
|
|
|
|
|
|
2001-11-17 03:07:11 +00:00
|
|
|
/*
|
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.
|
2001-11-17 03:07:11 +00:00
|
|
|
*/
|
2014-08-26 14:44:08 +00:00
|
|
|
static int
|
2007-03-04 17:50:46 +00:00
|
|
|
soo_close(struct file *fp, struct thread *td)
|
1994-05-24 10:09:53 +00:00
|
|
|
{
|
|
|
|
|
int error = 0;
|
2001-11-17 03:07:11 +00:00
|
|
|
struct socket *so;
|
1994-05-24 10:09:53 +00:00
|
|
|
|
2003-01-13 00:33:17 +00:00
|
|
|
so = fp->f_data;
|
1999-08-04 18:53:50 +00:00
|
|
|
fp->f_ops = &badfileops;
|
2003-01-13 00:33:17 +00:00
|
|
|
fp->f_data = NULL;
|
2002-01-13 11:58:06 +00:00
|
|
|
|
|
|
|
|
if (so)
|
2001-11-17 03:07:11 +00:00
|
|
|
error = soclose(so);
|
1994-05-24 10:09:53 +00:00
|
|
|
return (error);
|
|
|
|
|
}
|
2014-09-22 16:20:47 +00:00
|
|
|
|
|
|
|
|
static int
|
|
|
|
|
soo_fill_kinfo(struct file *fp, struct kinfo_file *kif, struct filedesc *fdp)
|
|
|
|
|
{
|
|
|
|
|
struct sockaddr *sa;
|
|
|
|
|
struct inpcb *inpcb;
|
|
|
|
|
struct unpcb *unpcb;
|
|
|
|
|
struct socket *so;
|
|
|
|
|
int error;
|
|
|
|
|
|
|
|
|
|
kif->kf_type = KF_TYPE_SOCKET;
|
|
|
|
|
so = fp->f_data;
|
2018-01-11 20:26:17 +00:00
|
|
|
CURVNET_SET(so->so_vnet);
|
Commit the 64-bit inode project.
Extend the ino_t, dev_t, nlink_t types to 64-bit ints. Modify
struct dirent layout to add d_off, increase the size of d_fileno
to 64-bits, increase the size of d_namlen to 16-bits, and change
the required alignment. Increase struct statfs f_mntfromname[] and
f_mntonname[] array length MNAMELEN to 1024.
ABI breakage is mitigated by providing compatibility using versioned
symbols, ingenious use of the existing padding in structures, and
by employing other tricks. Unfortunately, not everything can be
fixed, especially outside the base system. For instance, third-party
APIs which pass struct stat around are broken in backward and
forward incompatible ways.
Kinfo sysctl MIBs ABI is changed in backward-compatible way, but
there is no general mechanism to handle other sysctl MIBS which
return structures where the layout has changed. It was considered
that the breakage is either in the management interfaces, where we
usually allow ABI slip, or is not important.
Struct xvnode changed layout, no compat shims are provided.
For struct xtty, dev_t tty device member was reduced to uint32_t.
It was decided that keeping ABI compat in this case is more useful
than reporting 64-bit dev_t, for the sake of pstat.
Update note: strictly follow the instructions in UPDATING. Build
and install the new kernel with COMPAT_FREEBSD11 option enabled,
then reboot, and only then install new world.
Credits: The 64-bit inode project, also known as ino64, started life
many years ago as a project by Gleb Kurtsou (gleb). Kirk McKusick
(mckusick) then picked up and updated the patch, and acted as a
flag-waver. Feedback, suggestions, and discussions were carried
by Ed Maste (emaste), John Baldwin (jhb), Jilles Tjoelker (jilles),
and Rick Macklem (rmacklem). Kris Moore (kris) performed an initial
ports investigation followed by an exp-run by Antoine Brodin (antoine).
Essential and all-embracing testing was done by Peter Holm (pho).
The heavy lifting of coordinating all these efforts and bringing the
project to completion were done by Konstantin Belousov (kib).
Sponsored by: The FreeBSD Foundation (emaste, kib)
Differential revision: https://reviews.freebsd.org/D10439
2017-05-23 09:29:05 +00:00
|
|
|
kif->kf_un.kf_sock.kf_sock_domain0 =
|
|
|
|
|
so->so_proto->pr_domain->dom_family;
|
|
|
|
|
kif->kf_un.kf_sock.kf_sock_type0 = so->so_type;
|
|
|
|
|
kif->kf_un.kf_sock.kf_sock_protocol0 = so->so_proto->pr_protocol;
|
2014-09-22 16:20:47 +00:00
|
|
|
kif->kf_un.kf_sock.kf_sock_pcb = (uintptr_t)so->so_pcb;
|
Commit the 64-bit inode project.
Extend the ino_t, dev_t, nlink_t types to 64-bit ints. Modify
struct dirent layout to add d_off, increase the size of d_fileno
to 64-bits, increase the size of d_namlen to 16-bits, and change
the required alignment. Increase struct statfs f_mntfromname[] and
f_mntonname[] array length MNAMELEN to 1024.
ABI breakage is mitigated by providing compatibility using versioned
symbols, ingenious use of the existing padding in structures, and
by employing other tricks. Unfortunately, not everything can be
fixed, especially outside the base system. For instance, third-party
APIs which pass struct stat around are broken in backward and
forward incompatible ways.
Kinfo sysctl MIBs ABI is changed in backward-compatible way, but
there is no general mechanism to handle other sysctl MIBS which
return structures where the layout has changed. It was considered
that the breakage is either in the management interfaces, where we
usually allow ABI slip, or is not important.
Struct xvnode changed layout, no compat shims are provided.
For struct xtty, dev_t tty device member was reduced to uint32_t.
It was decided that keeping ABI compat in this case is more useful
than reporting 64-bit dev_t, for the sake of pstat.
Update note: strictly follow the instructions in UPDATING. Build
and install the new kernel with COMPAT_FREEBSD11 option enabled,
then reboot, and only then install new world.
Credits: The 64-bit inode project, also known as ino64, started life
many years ago as a project by Gleb Kurtsou (gleb). Kirk McKusick
(mckusick) then picked up and updated the patch, and acted as a
flag-waver. Feedback, suggestions, and discussions were carried
by Ed Maste (emaste), John Baldwin (jhb), Jilles Tjoelker (jilles),
and Rick Macklem (rmacklem). Kris Moore (kris) performed an initial
ports investigation followed by an exp-run by Antoine Brodin (antoine).
Essential and all-embracing testing was done by Peter Holm (pho).
The heavy lifting of coordinating all these efforts and bringing the
project to completion were done by Konstantin Belousov (kib).
Sponsored by: The FreeBSD Foundation (emaste, kib)
Differential revision: https://reviews.freebsd.org/D10439
2017-05-23 09:29:05 +00:00
|
|
|
switch (kif->kf_un.kf_sock.kf_sock_domain0) {
|
2014-09-22 16:20:47 +00:00
|
|
|
case AF_INET:
|
|
|
|
|
case AF_INET6:
|
Commit the 64-bit inode project.
Extend the ino_t, dev_t, nlink_t types to 64-bit ints. Modify
struct dirent layout to add d_off, increase the size of d_fileno
to 64-bits, increase the size of d_namlen to 16-bits, and change
the required alignment. Increase struct statfs f_mntfromname[] and
f_mntonname[] array length MNAMELEN to 1024.
ABI breakage is mitigated by providing compatibility using versioned
symbols, ingenious use of the existing padding in structures, and
by employing other tricks. Unfortunately, not everything can be
fixed, especially outside the base system. For instance, third-party
APIs which pass struct stat around are broken in backward and
forward incompatible ways.
Kinfo sysctl MIBs ABI is changed in backward-compatible way, but
there is no general mechanism to handle other sysctl MIBS which
return structures where the layout has changed. It was considered
that the breakage is either in the management interfaces, where we
usually allow ABI slip, or is not important.
Struct xvnode changed layout, no compat shims are provided.
For struct xtty, dev_t tty device member was reduced to uint32_t.
It was decided that keeping ABI compat in this case is more useful
than reporting 64-bit dev_t, for the sake of pstat.
Update note: strictly follow the instructions in UPDATING. Build
and install the new kernel with COMPAT_FREEBSD11 option enabled,
then reboot, and only then install new world.
Credits: The 64-bit inode project, also known as ino64, started life
many years ago as a project by Gleb Kurtsou (gleb). Kirk McKusick
(mckusick) then picked up and updated the patch, and acted as a
flag-waver. Feedback, suggestions, and discussions were carried
by Ed Maste (emaste), John Baldwin (jhb), Jilles Tjoelker (jilles),
and Rick Macklem (rmacklem). Kris Moore (kris) performed an initial
ports investigation followed by an exp-run by Antoine Brodin (antoine).
Essential and all-embracing testing was done by Peter Holm (pho).
The heavy lifting of coordinating all these efforts and bringing the
project to completion were done by Konstantin Belousov (kib).
Sponsored by: The FreeBSD Foundation (emaste, kib)
Differential revision: https://reviews.freebsd.org/D10439
2017-05-23 09:29:05 +00:00
|
|
|
if (kif->kf_un.kf_sock.kf_sock_protocol0 == IPPROTO_TCP) {
|
2014-09-22 16:20:47 +00:00
|
|
|
if (so->so_pcb != NULL) {
|
|
|
|
|
inpcb = (struct inpcb *)(so->so_pcb);
|
|
|
|
|
kif->kf_un.kf_sock.kf_sock_inpcb =
|
|
|
|
|
(uintptr_t)inpcb->inp_ppcb;
|
2017-05-26 22:17:44 +00:00
|
|
|
kif->kf_un.kf_sock.kf_sock_sendq =
|
|
|
|
|
sbused(&so->so_snd);
|
|
|
|
|
kif->kf_un.kf_sock.kf_sock_recvq =
|
|
|
|
|
sbused(&so->so_rcv);
|
2014-09-22 16:20:47 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
break;
|
|
|
|
|
case AF_UNIX:
|
|
|
|
|
if (so->so_pcb != NULL) {
|
|
|
|
|
unpcb = (struct unpcb *)(so->so_pcb);
|
|
|
|
|
if (unpcb->unp_conn) {
|
|
|
|
|
kif->kf_un.kf_sock.kf_sock_unpconn =
|
|
|
|
|
(uintptr_t)unpcb->unp_conn;
|
|
|
|
|
kif->kf_un.kf_sock.kf_sock_rcv_sb_state =
|
|
|
|
|
so->so_rcv.sb_state;
|
|
|
|
|
kif->kf_un.kf_sock.kf_sock_snd_sb_state =
|
|
|
|
|
so->so_snd.sb_state;
|
2017-05-26 22:17:44 +00:00
|
|
|
kif->kf_un.kf_sock.kf_sock_sendq =
|
|
|
|
|
sbused(&so->so_snd);
|
|
|
|
|
kif->kf_un.kf_sock.kf_sock_recvq =
|
|
|
|
|
sbused(&so->so_rcv);
|
2014-09-22 16:20:47 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
error = so->so_proto->pr_usrreqs->pru_sockaddr(so, &sa);
|
Commit the 64-bit inode project.
Extend the ino_t, dev_t, nlink_t types to 64-bit ints. Modify
struct dirent layout to add d_off, increase the size of d_fileno
to 64-bits, increase the size of d_namlen to 16-bits, and change
the required alignment. Increase struct statfs f_mntfromname[] and
f_mntonname[] array length MNAMELEN to 1024.
ABI breakage is mitigated by providing compatibility using versioned
symbols, ingenious use of the existing padding in structures, and
by employing other tricks. Unfortunately, not everything can be
fixed, especially outside the base system. For instance, third-party
APIs which pass struct stat around are broken in backward and
forward incompatible ways.
Kinfo sysctl MIBs ABI is changed in backward-compatible way, but
there is no general mechanism to handle other sysctl MIBS which
return structures where the layout has changed. It was considered
that the breakage is either in the management interfaces, where we
usually allow ABI slip, or is not important.
Struct xvnode changed layout, no compat shims are provided.
For struct xtty, dev_t tty device member was reduced to uint32_t.
It was decided that keeping ABI compat in this case is more useful
than reporting 64-bit dev_t, for the sake of pstat.
Update note: strictly follow the instructions in UPDATING. Build
and install the new kernel with COMPAT_FREEBSD11 option enabled,
then reboot, and only then install new world.
Credits: The 64-bit inode project, also known as ino64, started life
many years ago as a project by Gleb Kurtsou (gleb). Kirk McKusick
(mckusick) then picked up and updated the patch, and acted as a
flag-waver. Feedback, suggestions, and discussions were carried
by Ed Maste (emaste), John Baldwin (jhb), Jilles Tjoelker (jilles),
and Rick Macklem (rmacklem). Kris Moore (kris) performed an initial
ports investigation followed by an exp-run by Antoine Brodin (antoine).
Essential and all-embracing testing was done by Peter Holm (pho).
The heavy lifting of coordinating all these efforts and bringing the
project to completion were done by Konstantin Belousov (kib).
Sponsored by: The FreeBSD Foundation (emaste, kib)
Differential revision: https://reviews.freebsd.org/D10439
2017-05-23 09:29:05 +00:00
|
|
|
if (error == 0 &&
|
|
|
|
|
sa->sa_len <= sizeof(kif->kf_un.kf_sock.kf_sa_local)) {
|
|
|
|
|
bcopy(sa, &kif->kf_un.kf_sock.kf_sa_local, sa->sa_len);
|
2014-09-22 16:20:47 +00:00
|
|
|
free(sa, M_SONAME);
|
|
|
|
|
}
|
|
|
|
|
error = so->so_proto->pr_usrreqs->pru_peeraddr(so, &sa);
|
Commit the 64-bit inode project.
Extend the ino_t, dev_t, nlink_t types to 64-bit ints. Modify
struct dirent layout to add d_off, increase the size of d_fileno
to 64-bits, increase the size of d_namlen to 16-bits, and change
the required alignment. Increase struct statfs f_mntfromname[] and
f_mntonname[] array length MNAMELEN to 1024.
ABI breakage is mitigated by providing compatibility using versioned
symbols, ingenious use of the existing padding in structures, and
by employing other tricks. Unfortunately, not everything can be
fixed, especially outside the base system. For instance, third-party
APIs which pass struct stat around are broken in backward and
forward incompatible ways.
Kinfo sysctl MIBs ABI is changed in backward-compatible way, but
there is no general mechanism to handle other sysctl MIBS which
return structures where the layout has changed. It was considered
that the breakage is either in the management interfaces, where we
usually allow ABI slip, or is not important.
Struct xvnode changed layout, no compat shims are provided.
For struct xtty, dev_t tty device member was reduced to uint32_t.
It was decided that keeping ABI compat in this case is more useful
than reporting 64-bit dev_t, for the sake of pstat.
Update note: strictly follow the instructions in UPDATING. Build
and install the new kernel with COMPAT_FREEBSD11 option enabled,
then reboot, and only then install new world.
Credits: The 64-bit inode project, also known as ino64, started life
many years ago as a project by Gleb Kurtsou (gleb). Kirk McKusick
(mckusick) then picked up and updated the patch, and acted as a
flag-waver. Feedback, suggestions, and discussions were carried
by Ed Maste (emaste), John Baldwin (jhb), Jilles Tjoelker (jilles),
and Rick Macklem (rmacklem). Kris Moore (kris) performed an initial
ports investigation followed by an exp-run by Antoine Brodin (antoine).
Essential and all-embracing testing was done by Peter Holm (pho).
The heavy lifting of coordinating all these efforts and bringing the
project to completion were done by Konstantin Belousov (kib).
Sponsored by: The FreeBSD Foundation (emaste, kib)
Differential revision: https://reviews.freebsd.org/D10439
2017-05-23 09:29:05 +00:00
|
|
|
if (error == 0 &&
|
|
|
|
|
sa->sa_len <= sizeof(kif->kf_un.kf_sock.kf_sa_peer)) {
|
|
|
|
|
bcopy(sa, &kif->kf_un.kf_sock.kf_sa_peer, sa->sa_len);
|
2014-09-22 16:20:47 +00:00
|
|
|
free(sa, M_SONAME);
|
|
|
|
|
}
|
|
|
|
|
strncpy(kif->kf_path, so->so_proto->pr_domain->dom_name,
|
|
|
|
|
sizeof(kif->kf_path));
|
2018-01-11 20:26:17 +00:00
|
|
|
CURVNET_RESTORE();
|
2014-09-22 16:20:47 +00:00
|
|
|
return (0);
|
|
|
|
|
}
|
2016-03-01 18:12:14 +00:00
|
|
|
|
2016-06-15 20:56:45 +00:00
|
|
|
/*
|
|
|
|
|
* Use the 'backend3' field in AIO jobs to store the amount of data
|
|
|
|
|
* completed by the AIO job so far.
|
|
|
|
|
*/
|
|
|
|
|
#define aio_done backend3
|
|
|
|
|
|
2016-03-01 18:12:14 +00:00
|
|
|
static STAILQ_HEAD(, task) soaio_jobs;
|
|
|
|
|
static struct mtx soaio_jobs_lock;
|
|
|
|
|
static struct task soaio_kproc_task;
|
|
|
|
|
static int soaio_starting, soaio_idle, soaio_queued;
|
|
|
|
|
static struct unrhdr *soaio_kproc_unr;
|
|
|
|
|
|
|
|
|
|
static int soaio_max_procs = MAX_AIO_PROCS;
|
|
|
|
|
SYSCTL_INT(_kern_ipc_aio, OID_AUTO, max_procs, CTLFLAG_RW, &soaio_max_procs, 0,
|
|
|
|
|
"Maximum number of kernel processes to use for async socket IO");
|
|
|
|
|
|
|
|
|
|
static int soaio_num_procs;
|
|
|
|
|
SYSCTL_INT(_kern_ipc_aio, OID_AUTO, num_procs, CTLFLAG_RD, &soaio_num_procs, 0,
|
|
|
|
|
"Number of active kernel processes for async socket IO");
|
|
|
|
|
|
|
|
|
|
static int soaio_target_procs = TARGET_AIO_PROCS;
|
|
|
|
|
SYSCTL_INT(_kern_ipc_aio, OID_AUTO, target_procs, CTLFLAG_RD,
|
|
|
|
|
&soaio_target_procs, 0,
|
|
|
|
|
"Preferred number of ready kernel processes for async socket IO");
|
|
|
|
|
|
|
|
|
|
static int soaio_lifetime;
|
|
|
|
|
SYSCTL_INT(_kern_ipc_aio, OID_AUTO, lifetime, CTLFLAG_RW, &soaio_lifetime, 0,
|
|
|
|
|
"Maximum lifetime for idle aiod");
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
soaio_kproc_loop(void *arg)
|
|
|
|
|
{
|
|
|
|
|
struct proc *p;
|
|
|
|
|
struct vmspace *myvm;
|
|
|
|
|
struct task *task;
|
|
|
|
|
int error, id, pending;
|
|
|
|
|
|
|
|
|
|
id = (intptr_t)arg;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Grab an extra reference on the daemon's vmspace so that it
|
|
|
|
|
* doesn't get freed by jobs that switch to a different
|
|
|
|
|
* vmspace.
|
|
|
|
|
*/
|
|
|
|
|
p = curproc;
|
|
|
|
|
myvm = vmspace_acquire_ref(p);
|
|
|
|
|
|
|
|
|
|
mtx_lock(&soaio_jobs_lock);
|
|
|
|
|
MPASS(soaio_starting > 0);
|
|
|
|
|
soaio_starting--;
|
|
|
|
|
for (;;) {
|
|
|
|
|
while (!STAILQ_EMPTY(&soaio_jobs)) {
|
|
|
|
|
task = STAILQ_FIRST(&soaio_jobs);
|
|
|
|
|
STAILQ_REMOVE_HEAD(&soaio_jobs, ta_link);
|
|
|
|
|
soaio_queued--;
|
|
|
|
|
pending = task->ta_pending;
|
|
|
|
|
task->ta_pending = 0;
|
|
|
|
|
mtx_unlock(&soaio_jobs_lock);
|
|
|
|
|
|
|
|
|
|
task->ta_func(task->ta_context, pending);
|
|
|
|
|
|
|
|
|
|
mtx_lock(&soaio_jobs_lock);
|
|
|
|
|
}
|
|
|
|
|
MPASS(soaio_queued == 0);
|
|
|
|
|
|
|
|
|
|
if (p->p_vmspace != myvm) {
|
|
|
|
|
mtx_unlock(&soaio_jobs_lock);
|
|
|
|
|
vmspace_switch_aio(myvm);
|
|
|
|
|
mtx_lock(&soaio_jobs_lock);
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
soaio_idle++;
|
|
|
|
|
error = mtx_sleep(&soaio_idle, &soaio_jobs_lock, 0, "-",
|
|
|
|
|
soaio_lifetime);
|
|
|
|
|
soaio_idle--;
|
|
|
|
|
if (error == EWOULDBLOCK && STAILQ_EMPTY(&soaio_jobs) &&
|
|
|
|
|
soaio_num_procs > soaio_target_procs)
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
soaio_num_procs--;
|
|
|
|
|
mtx_unlock(&soaio_jobs_lock);
|
|
|
|
|
free_unr(soaio_kproc_unr, id);
|
|
|
|
|
kproc_exit(0);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
soaio_kproc_create(void *context, int pending)
|
|
|
|
|
{
|
|
|
|
|
struct proc *p;
|
|
|
|
|
int error, id;
|
|
|
|
|
|
|
|
|
|
mtx_lock(&soaio_jobs_lock);
|
|
|
|
|
for (;;) {
|
|
|
|
|
if (soaio_num_procs < soaio_target_procs) {
|
|
|
|
|
/* Must create */
|
|
|
|
|
} else if (soaio_num_procs >= soaio_max_procs) {
|
|
|
|
|
/*
|
|
|
|
|
* Hit the limit on kernel processes, don't
|
|
|
|
|
* create another one.
|
|
|
|
|
*/
|
|
|
|
|
break;
|
|
|
|
|
} else if (soaio_queued <= soaio_idle + soaio_starting) {
|
|
|
|
|
/*
|
|
|
|
|
* No more AIO jobs waiting for a process to be
|
|
|
|
|
* created, so stop.
|
|
|
|
|
*/
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
soaio_starting++;
|
|
|
|
|
mtx_unlock(&soaio_jobs_lock);
|
|
|
|
|
|
|
|
|
|
id = alloc_unr(soaio_kproc_unr);
|
|
|
|
|
error = kproc_create(soaio_kproc_loop, (void *)(intptr_t)id,
|
|
|
|
|
&p, 0, 0, "soaiod%d", id);
|
|
|
|
|
if (error != 0) {
|
|
|
|
|
free_unr(soaio_kproc_unr, id);
|
|
|
|
|
mtx_lock(&soaio_jobs_lock);
|
|
|
|
|
soaio_starting--;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
mtx_lock(&soaio_jobs_lock);
|
|
|
|
|
soaio_num_procs++;
|
|
|
|
|
}
|
|
|
|
|
mtx_unlock(&soaio_jobs_lock);
|
|
|
|
|
}
|
|
|
|
|
|
2016-04-29 20:12:45 +00:00
|
|
|
void
|
2016-03-01 18:12:14 +00:00
|
|
|
soaio_enqueue(struct task *task)
|
|
|
|
|
{
|
|
|
|
|
|
|
|
|
|
mtx_lock(&soaio_jobs_lock);
|
|
|
|
|
MPASS(task->ta_pending == 0);
|
|
|
|
|
task->ta_pending++;
|
|
|
|
|
STAILQ_INSERT_TAIL(&soaio_jobs, task, ta_link);
|
|
|
|
|
soaio_queued++;
|
|
|
|
|
if (soaio_queued <= soaio_idle)
|
|
|
|
|
wakeup_one(&soaio_idle);
|
|
|
|
|
else if (soaio_num_procs < soaio_max_procs)
|
|
|
|
|
taskqueue_enqueue(taskqueue_thread, &soaio_kproc_task);
|
|
|
|
|
mtx_unlock(&soaio_jobs_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
soaio_init(void)
|
|
|
|
|
{
|
|
|
|
|
|
|
|
|
|
soaio_lifetime = AIOD_LIFETIME_DEFAULT;
|
|
|
|
|
STAILQ_INIT(&soaio_jobs);
|
|
|
|
|
mtx_init(&soaio_jobs_lock, "soaio jobs", NULL, MTX_DEF);
|
|
|
|
|
soaio_kproc_unr = new_unrhdr(1, INT_MAX, NULL);
|
|
|
|
|
TASK_INIT(&soaio_kproc_task, 0, soaio_kproc_create, NULL);
|
|
|
|
|
if (soaio_target_procs > 0)
|
|
|
|
|
taskqueue_enqueue(taskqueue_thread, &soaio_kproc_task);
|
|
|
|
|
}
|
|
|
|
|
SYSINIT(soaio, SI_SUB_VFS, SI_ORDER_ANY, soaio_init, NULL);
|
|
|
|
|
|
|
|
|
|
static __inline int
|
|
|
|
|
soaio_ready(struct socket *so, struct sockbuf *sb)
|
|
|
|
|
{
|
|
|
|
|
return (sb == &so->so_rcv ? soreadable(so) : sowriteable(so));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
soaio_process_job(struct socket *so, struct sockbuf *sb, struct kaiocb *job)
|
|
|
|
|
{
|
|
|
|
|
struct ucred *td_savedcred;
|
|
|
|
|
struct thread *td;
|
|
|
|
|
struct file *fp;
|
|
|
|
|
struct uio uio;
|
|
|
|
|
struct iovec iov;
|
2016-05-24 03:13:27 +00:00
|
|
|
size_t cnt, done;
|
2016-06-21 22:19:06 +00:00
|
|
|
long ru_before;
|
2016-03-01 18:12:14 +00:00
|
|
|
int error, flags;
|
|
|
|
|
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
aio_switch_vmspace(job);
|
|
|
|
|
td = curthread;
|
|
|
|
|
fp = job->fd_file;
|
|
|
|
|
retry:
|
|
|
|
|
td_savedcred = td->td_ucred;
|
|
|
|
|
td->td_ucred = job->cred;
|
|
|
|
|
|
2016-06-15 20:56:45 +00:00
|
|
|
done = job->aio_done;
|
2016-05-24 03:13:27 +00:00
|
|
|
cnt = job->uaiocb.aio_nbytes - done;
|
|
|
|
|
iov.iov_base = (void *)((uintptr_t)job->uaiocb.aio_buf + done);
|
2016-03-01 18:12:14 +00:00
|
|
|
iov.iov_len = cnt;
|
|
|
|
|
uio.uio_iov = &iov;
|
|
|
|
|
uio.uio_iovcnt = 1;
|
|
|
|
|
uio.uio_offset = 0;
|
|
|
|
|
uio.uio_resid = cnt;
|
|
|
|
|
uio.uio_segflg = UIO_USERSPACE;
|
|
|
|
|
uio.uio_td = td;
|
|
|
|
|
flags = MSG_NBIO;
|
|
|
|
|
|
2016-06-21 22:19:06 +00:00
|
|
|
/*
|
|
|
|
|
* For resource usage accounting, only count a completed request
|
|
|
|
|
* as a single message to avoid counting multiple calls to
|
|
|
|
|
* sosend/soreceive on a blocking socket.
|
|
|
|
|
*/
|
2016-03-01 18:12:14 +00:00
|
|
|
|
|
|
|
|
if (sb == &so->so_rcv) {
|
|
|
|
|
uio.uio_rw = UIO_READ;
|
2016-06-21 22:19:06 +00:00
|
|
|
ru_before = td->td_ru.ru_msgrcv;
|
2016-03-01 18:12:14 +00:00
|
|
|
#ifdef MAC
|
|
|
|
|
error = mac_socket_check_receive(fp->f_cred, so);
|
|
|
|
|
if (error == 0)
|
|
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
error = soreceive(so, NULL, &uio, NULL, NULL, &flags);
|
2016-06-21 22:19:06 +00:00
|
|
|
if (td->td_ru.ru_msgrcv != ru_before)
|
|
|
|
|
job->msgrcv = 1;
|
2016-03-01 18:12:14 +00:00
|
|
|
} else {
|
2017-01-06 23:41:45 +00:00
|
|
|
if (!TAILQ_EMPTY(&sb->sb_aiojobq))
|
|
|
|
|
flags |= MSG_MORETOCOME;
|
2016-03-01 18:12:14 +00:00
|
|
|
uio.uio_rw = UIO_WRITE;
|
2016-06-21 22:19:06 +00:00
|
|
|
ru_before = td->td_ru.ru_msgsnd;
|
2016-03-01 18:12:14 +00:00
|
|
|
#ifdef MAC
|
|
|
|
|
error = mac_socket_check_send(fp->f_cred, so);
|
|
|
|
|
if (error == 0)
|
|
|
|
|
#endif
|
|
|
|
|
error = sosend(so, NULL, &uio, NULL, NULL, flags, td);
|
2016-06-21 22:19:06 +00:00
|
|
|
if (td->td_ru.ru_msgsnd != ru_before)
|
|
|
|
|
job->msgsnd = 1;
|
2016-03-01 18:12:14 +00:00
|
|
|
if (error == EPIPE && (so->so_options & SO_NOSIGPIPE) == 0) {
|
|
|
|
|
PROC_LOCK(job->userproc);
|
|
|
|
|
kern_psignal(job->userproc, SIGPIPE);
|
|
|
|
|
PROC_UNLOCK(job->userproc);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2016-05-24 03:13:27 +00:00
|
|
|
done += cnt - uio.uio_resid;
|
2016-06-15 20:56:45 +00:00
|
|
|
job->aio_done = done;
|
2016-03-01 18:12:14 +00:00
|
|
|
td->td_ucred = td_savedcred;
|
|
|
|
|
|
|
|
|
|
if (error == EWOULDBLOCK) {
|
|
|
|
|
/*
|
2016-05-24 03:13:27 +00:00
|
|
|
* The request was either partially completed or not
|
|
|
|
|
* completed at all due to racing with a read() or
|
|
|
|
|
* write() on the socket. If the socket is
|
|
|
|
|
* non-blocking, return with any partial completion.
|
|
|
|
|
* If the socket is blocking or if no progress has
|
|
|
|
|
* been made, requeue this request at the head of the
|
2016-03-01 18:12:14 +00:00
|
|
|
* queue to try again when the socket is ready.
|
|
|
|
|
*/
|
2016-05-24 03:13:27 +00:00
|
|
|
MPASS(done != job->uaiocb.aio_nbytes);
|
2016-03-01 18:12:14 +00:00
|
|
|
SOCKBUF_LOCK(sb);
|
2016-05-24 03:13:27 +00:00
|
|
|
if (done == 0 || !(so->so_state & SS_NBIO)) {
|
|
|
|
|
empty_results++;
|
|
|
|
|
if (soaio_ready(so, sb)) {
|
|
|
|
|
empty_retries++;
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
goto retry;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (!aio_set_cancel_function(job, soo_aio_cancel)) {
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
if (done != 0)
|
|
|
|
|
aio_complete(job, done, 0);
|
|
|
|
|
else
|
|
|
|
|
aio_cancel(job);
|
|
|
|
|
SOCKBUF_LOCK(sb);
|
|
|
|
|
} else {
|
|
|
|
|
TAILQ_INSERT_HEAD(&sb->sb_aiojobq, job, list);
|
|
|
|
|
}
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
}
|
|
|
|
|
if (done != 0 && (error == ERESTART || error == EINTR ||
|
|
|
|
|
error == EWOULDBLOCK))
|
|
|
|
|
error = 0;
|
|
|
|
|
if (error)
|
|
|
|
|
aio_complete(job, -1, error);
|
|
|
|
|
else
|
|
|
|
|
aio_complete(job, done, 0);
|
|
|
|
|
SOCKBUF_LOCK(sb);
|
2016-03-01 18:12:14 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
soaio_process_sb(struct socket *so, struct sockbuf *sb)
|
|
|
|
|
{
|
|
|
|
|
struct kaiocb *job;
|
|
|
|
|
|
2017-07-17 16:59:22 +00:00
|
|
|
CURVNET_SET(so->so_vnet);
|
2016-03-01 18:12:14 +00:00
|
|
|
SOCKBUF_LOCK(sb);
|
|
|
|
|
while (!TAILQ_EMPTY(&sb->sb_aiojobq) && soaio_ready(so, sb)) {
|
|
|
|
|
job = TAILQ_FIRST(&sb->sb_aiojobq);
|
|
|
|
|
TAILQ_REMOVE(&sb->sb_aiojobq, job, list);
|
|
|
|
|
if (!aio_clear_cancel_function(job))
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
|
|
soaio_process_job(so, sb, job);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If there are still pending requests, the socket must not be
|
|
|
|
|
* ready so set SB_AIO to request a wakeup when the socket
|
|
|
|
|
* becomes ready.
|
|
|
|
|
*/
|
|
|
|
|
if (!TAILQ_EMPTY(&sb->sb_aiojobq))
|
|
|
|
|
sb->sb_flags |= SB_AIO;
|
|
|
|
|
sb->sb_flags &= ~SB_AIO_RUNNING;
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
|
|
|
|
|
SOCK_LOCK(so);
|
|
|
|
|
sorele(so);
|
2017-07-17 16:59:22 +00:00
|
|
|
CURVNET_RESTORE();
|
2016-03-01 18:12:14 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
soaio_rcv(void *context, int pending)
|
|
|
|
|
{
|
|
|
|
|
struct socket *so;
|
|
|
|
|
|
|
|
|
|
so = context;
|
|
|
|
|
soaio_process_sb(so, &so->so_rcv);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
soaio_snd(void *context, int pending)
|
|
|
|
|
{
|
|
|
|
|
struct socket *so;
|
|
|
|
|
|
|
|
|
|
so = context;
|
|
|
|
|
soaio_process_sb(so, &so->so_snd);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
sowakeup_aio(struct socket *so, struct sockbuf *sb)
|
|
|
|
|
{
|
|
|
|
|
|
|
|
|
|
SOCKBUF_LOCK_ASSERT(sb);
|
|
|
|
|
sb->sb_flags &= ~SB_AIO;
|
|
|
|
|
if (sb->sb_flags & SB_AIO_RUNNING)
|
|
|
|
|
return;
|
|
|
|
|
sb->sb_flags |= SB_AIO_RUNNING;
|
|
|
|
|
soref(so);
|
|
|
|
|
soaio_enqueue(&sb->sb_aiotask);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
soo_aio_cancel(struct kaiocb *job)
|
|
|
|
|
{
|
|
|
|
|
struct socket *so;
|
|
|
|
|
struct sockbuf *sb;
|
2016-05-24 21:09:05 +00:00
|
|
|
long done;
|
2016-03-01 18:12:14 +00:00
|
|
|
int opcode;
|
|
|
|
|
|
|
|
|
|
so = job->fd_file->f_data;
|
|
|
|
|
opcode = job->uaiocb.aio_lio_opcode;
|
|
|
|
|
if (opcode == LIO_READ)
|
|
|
|
|
sb = &so->so_rcv;
|
|
|
|
|
else {
|
|
|
|
|
MPASS(opcode == LIO_WRITE);
|
|
|
|
|
sb = &so->so_snd;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
SOCKBUF_LOCK(sb);
|
|
|
|
|
if (!aio_cancel_cleared(job))
|
|
|
|
|
TAILQ_REMOVE(&sb->sb_aiojobq, job, list);
|
|
|
|
|
if (TAILQ_EMPTY(&sb->sb_aiojobq))
|
|
|
|
|
sb->sb_flags &= ~SB_AIO;
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
|
2016-06-15 20:56:45 +00:00
|
|
|
done = job->aio_done;
|
2016-05-24 21:09:05 +00:00
|
|
|
if (done != 0)
|
|
|
|
|
aio_complete(job, done, 0);
|
|
|
|
|
else
|
|
|
|
|
aio_cancel(job);
|
2016-03-01 18:12:14 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int
|
|
|
|
|
soo_aio_queue(struct file *fp, struct kaiocb *job)
|
|
|
|
|
{
|
|
|
|
|
struct socket *so;
|
|
|
|
|
struct sockbuf *sb;
|
2016-04-29 20:11:09 +00:00
|
|
|
int error;
|
2016-03-01 18:12:14 +00:00
|
|
|
|
|
|
|
|
so = fp->f_data;
|
2016-04-29 20:11:09 +00:00
|
|
|
error = (*so->so_proto->pr_usrreqs->pru_aio_queue)(so, job);
|
|
|
|
|
if (error == 0)
|
|
|
|
|
return (0);
|
|
|
|
|
|
2016-03-01 18:12:14 +00:00
|
|
|
switch (job->uaiocb.aio_lio_opcode) {
|
|
|
|
|
case LIO_READ:
|
|
|
|
|
sb = &so->so_rcv;
|
|
|
|
|
break;
|
|
|
|
|
case LIO_WRITE:
|
|
|
|
|
sb = &so->so_snd;
|
|
|
|
|
break;
|
|
|
|
|
default:
|
|
|
|
|
return (EINVAL);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
SOCKBUF_LOCK(sb);
|
|
|
|
|
if (!aio_set_cancel_function(job, soo_aio_cancel))
|
|
|
|
|
panic("new job was cancelled");
|
|
|
|
|
TAILQ_INSERT_TAIL(&sb->sb_aiojobq, job, list);
|
|
|
|
|
if (!(sb->sb_flags & SB_AIO_RUNNING)) {
|
|
|
|
|
if (soaio_ready(so, sb))
|
|
|
|
|
sowakeup_aio(so, sb);
|
|
|
|
|
else
|
|
|
|
|
sb->sb_flags |= SB_AIO;
|
|
|
|
|
}
|
|
|
|
|
SOCKBUF_UNLOCK(sb);
|
|
|
|
|
return (0);
|
|
|
|
|
}
|
