freebsd-nq/sys/compat/svr4/svr4_filio.c

250 lines
6.5 KiB
C
Raw Normal View History

/*-
* Copyright (c) 1998 Mark Newton
* Copyright (c) 1994 Christos Zoulas
* 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.
* 3. The name of the author may not be used to endorse or promote products
* derived from this software without specific prior written permission
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 AUTHOR 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.
*/
2003-06-10 21:44:29 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/proc.h>
#include <sys/systm.h>
#include <sys/capability.h>
#include <sys/file.h>
#include <sys/filio.h>
#include <sys/lock.h>
#include <sys/signal.h>
#include <sys/filedesc.h>
#include <sys/poll.h>
#include <sys/malloc.h>
#include <sys/mutex.h>
#include <sys/sysproto.h>
#include <compat/svr4/svr4.h>
#include <compat/svr4/svr4_types.h>
#include <compat/svr4/svr4_util.h>
#include <compat/svr4/svr4_signal.h>
#include <compat/svr4/svr4_proto.h>
#include <compat/svr4/svr4_ioctl.h>
#include <compat/svr4/svr4_filio.h>
/*#define GROTTY_READ_HACK*/
int
svr4_sys_poll(td, uap)
struct thread *td;
struct svr4_sys_poll_args *uap;
{
int error;
struct poll_args pa;
struct pollfd *pfd;
int idx = 0, cerr;
u_long siz;
if (uap->nfds > maxfilesperproc && uap->nfds > FD_SETSIZE)
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
return (EINVAL);
2002-12-14 01:56:26 +00:00
pa.fds = uap->fds;
pa.nfds = uap->nfds;
pa.timeout = uap->timeout;
2002-12-14 01:56:26 +00:00
siz = uap->nfds * sizeof(struct pollfd);
pfd = (struct pollfd *)malloc(siz, M_TEMP, M_WAITOK);
error = sys_poll(td, (struct poll_args *)uap);
2002-12-14 01:56:26 +00:00
if ((cerr = copyin(uap->fds, pfd, siz)) != 0) {
error = cerr;
goto done;
}
2002-12-14 01:56:26 +00:00
for (idx = 0; idx < uap->nfds; idx++) {
/* POLLWRNORM already equals POLLOUT, so we don't worry about that */
if (pfd[idx].revents & (POLLOUT | POLLWRNORM | POLLWRBAND))
pfd[idx].revents |= (POLLOUT | POLLWRNORM | POLLWRBAND);
}
2002-12-14 01:56:26 +00:00
if ((cerr = copyout(pfd, uap->fds, siz)) != 0) {
error = cerr;
goto done; /* yeah, I know it's the next line, but this way I won't
forget to update it if I add more code */
}
done:
free(pfd, M_TEMP);
return error;
}
#if defined(READ_TEST)
int
svr4_sys_read(td, uap)
struct thread *td;
struct svr4_sys_read_args *uap;
{
struct read_args ra;
struct file *fp;
struct socket *so = NULL;
int so_state;
sigset_t sigmask;
int rv;
2002-12-14 01:56:26 +00:00
ra.fd = uap->fd;
ra.buf = uap->buf;
ra.nbyte = uap->nbyte;
if (fget(td, uap->fd, CAP_READ, &fp) != 0) {
DPRINTF(("Something fishy with the user-supplied file descriptor...\n"));
return EBADF;
}
if (fp->f_type == DTYPE_SOCKET) {
so = fp->f_data;
2002-12-14 01:56:26 +00:00
DPRINTF(("fd %d is a socket\n", uap->fd));
if (so->so_state & SS_ASYNC) {
2002-12-14 01:56:26 +00:00
DPRINTF(("fd %d is an ASYNC socket!\n", uap->fd));
}
DPRINTF(("Here are its flags: 0x%x\n", so->so_state));
#if defined(GROTTY_READ_HACK)
so_state = so->so_state;
so->so_state &= ~SS_NBIO;
#endif
}
rv = read(td, &ra);
DPRINTF(("svr4_read(%d, 0x%0x, %d) = %d\n",
2002-12-14 01:56:26 +00:00
uap->fd, uap->buf, uap->nbyte, rv));
if (rv == EAGAIN) {
#ifdef DEBUG_SVR4
struct sigacts *ps;
PROC_LOCK(td->td_proc);
ps = td->td_proc->p_sigacts;
mtx_lock(&ps->ps_mtx);
#endif
DPRINTF(("sigmask = 0x%x\n", td->td_sigmask));
DPRINTF(("sigignore = 0x%x\n", ps->ps_sigignore));
DPRINTF(("sigcaught = 0x%x\n", ps->ps_sigcatch));
DPRINTF(("siglist = 0x%x\n", td->td_siglist));
#ifdef DEBUG_SVR4
mtx_unlock(&ps->ps_mtx);
PROC_UNLOCK(td->td_proc);
#endif
}
#if defined(GROTTY_READ_HACK)
if (so) { /* We've already checked to see if this is a socket */
so->so_state = so_state;
}
#endif
fdrop(fp, td);
return(rv);
}
#endif /* READ_TEST */
#if defined(BOGUS)
int
svr4_sys_write(td, uap)
struct thread *td;
struct svr4_sys_write_args *uap;
{
struct write_args wa;
struct file *fp;
int rv;
2002-12-14 01:56:26 +00:00
wa.fd = uap->fd;
wa.buf = uap->buf;
wa.nbyte = uap->nbyte;
rv = write(td, &wa);
DPRINTF(("svr4_write(%d, 0x%0x, %d) = %d\n",
2002-12-14 01:56:26 +00:00
uap->fd, uap->buf, uap->nbyte, rv));
return(rv);
}
#endif /* BOGUS */
int
svr4_fil_ioctl(fp, td, retval, fd, cmd, data)
struct file *fp;
struct thread *td;
register_t *retval;
int fd;
u_long cmd;
caddr_t data;
{
int error;
int num;
struct filedesc *fdp = td->td_proc->p_fd;
*retval = 0;
switch (cmd) {
case SVR4_FIOCLEX:
Replace custom file descriptor array sleep lock constructed using a mutex and flags with an sxlock. This leads to a significant and measurable performance improvement as a result of access to shared locking for frequent lookup operations, reduced general overhead, and reduced overhead in the event of contention. All of these are imported for threaded applications where simultaneous access to a shared file descriptor array occurs frequently. Kris has reported 2x-4x transaction rate improvements on 8-core MySQL benchmarks; smaller improvements can be expected for many workloads as a result of reduced overhead. - Generally eliminate the distinction between "fast" and regular acquisisition of the filedesc lock; the plan is that they will now all be fast. Change all locking instances to either shared or exclusive locks. - Correct a bug (pointed out by kib) in fdfree() where previously msleep() was called without the mutex held; sx_sleep() is now always called with the sxlock held exclusively. - Universally hold the struct file lock over changes to struct file, rather than the filedesc lock or no lock. Always update the f_ops field last. A further memory barrier is required here in the future (discussed with jhb). - Improve locking and reference management in linux_at(), which fails to properly acquire vnode references before using vnode pointers. Annotate improper use of vn_fullpath(), which will be replaced at a future date. In fcntl(), we conservatively acquire an exclusive lock, even though in some cases a shared lock may be sufficient, which should be revisited. The dropping of the filedesc lock in fdgrowtable() is no longer required as the sxlock can be held over the sleep operation; we should consider removing that (pointed out by attilio). Tested by: kris Discussed with: jhb, kris, attilio, jeff
2007-04-04 09:11:34 +00:00
FILEDESC_XLOCK(fdp);
fdp->fd_ofileflags[fd] |= UF_EXCLOSE;
Replace custom file descriptor array sleep lock constructed using a mutex and flags with an sxlock. This leads to a significant and measurable performance improvement as a result of access to shared locking for frequent lookup operations, reduced general overhead, and reduced overhead in the event of contention. All of these are imported for threaded applications where simultaneous access to a shared file descriptor array occurs frequently. Kris has reported 2x-4x transaction rate improvements on 8-core MySQL benchmarks; smaller improvements can be expected for many workloads as a result of reduced overhead. - Generally eliminate the distinction between "fast" and regular acquisisition of the filedesc lock; the plan is that they will now all be fast. Change all locking instances to either shared or exclusive locks. - Correct a bug (pointed out by kib) in fdfree() where previously msleep() was called without the mutex held; sx_sleep() is now always called with the sxlock held exclusively. - Universally hold the struct file lock over changes to struct file, rather than the filedesc lock or no lock. Always update the f_ops field last. A further memory barrier is required here in the future (discussed with jhb). - Improve locking and reference management in linux_at(), which fails to properly acquire vnode references before using vnode pointers. Annotate improper use of vn_fullpath(), which will be replaced at a future date. In fcntl(), we conservatively acquire an exclusive lock, even though in some cases a shared lock may be sufficient, which should be revisited. The dropping of the filedesc lock in fdgrowtable() is no longer required as the sxlock can be held over the sleep operation; we should consider removing that (pointed out by attilio). Tested by: kris Discussed with: jhb, kris, attilio, jeff
2007-04-04 09:11:34 +00:00
FILEDESC_XUNLOCK(fdp);
return 0;
case SVR4_FIONCLEX:
Replace custom file descriptor array sleep lock constructed using a mutex and flags with an sxlock. This leads to a significant and measurable performance improvement as a result of access to shared locking for frequent lookup operations, reduced general overhead, and reduced overhead in the event of contention. All of these are imported for threaded applications where simultaneous access to a shared file descriptor array occurs frequently. Kris has reported 2x-4x transaction rate improvements on 8-core MySQL benchmarks; smaller improvements can be expected for many workloads as a result of reduced overhead. - Generally eliminate the distinction between "fast" and regular acquisisition of the filedesc lock; the plan is that they will now all be fast. Change all locking instances to either shared or exclusive locks. - Correct a bug (pointed out by kib) in fdfree() where previously msleep() was called without the mutex held; sx_sleep() is now always called with the sxlock held exclusively. - Universally hold the struct file lock over changes to struct file, rather than the filedesc lock or no lock. Always update the f_ops field last. A further memory barrier is required here in the future (discussed with jhb). - Improve locking and reference management in linux_at(), which fails to properly acquire vnode references before using vnode pointers. Annotate improper use of vn_fullpath(), which will be replaced at a future date. In fcntl(), we conservatively acquire an exclusive lock, even though in some cases a shared lock may be sufficient, which should be revisited. The dropping of the filedesc lock in fdgrowtable() is no longer required as the sxlock can be held over the sleep operation; we should consider removing that (pointed out by attilio). Tested by: kris Discussed with: jhb, kris, attilio, jeff
2007-04-04 09:11:34 +00:00
FILEDESC_XLOCK(fdp);
fdp->fd_ofileflags[fd] &= ~UF_EXCLOSE;
Replace custom file descriptor array sleep lock constructed using a mutex and flags with an sxlock. This leads to a significant and measurable performance improvement as a result of access to shared locking for frequent lookup operations, reduced general overhead, and reduced overhead in the event of contention. All of these are imported for threaded applications where simultaneous access to a shared file descriptor array occurs frequently. Kris has reported 2x-4x transaction rate improvements on 8-core MySQL benchmarks; smaller improvements can be expected for many workloads as a result of reduced overhead. - Generally eliminate the distinction between "fast" and regular acquisisition of the filedesc lock; the plan is that they will now all be fast. Change all locking instances to either shared or exclusive locks. - Correct a bug (pointed out by kib) in fdfree() where previously msleep() was called without the mutex held; sx_sleep() is now always called with the sxlock held exclusively. - Universally hold the struct file lock over changes to struct file, rather than the filedesc lock or no lock. Always update the f_ops field last. A further memory barrier is required here in the future (discussed with jhb). - Improve locking and reference management in linux_at(), which fails to properly acquire vnode references before using vnode pointers. Annotate improper use of vn_fullpath(), which will be replaced at a future date. In fcntl(), we conservatively acquire an exclusive lock, even though in some cases a shared lock may be sufficient, which should be revisited. The dropping of the filedesc lock in fdgrowtable() is no longer required as the sxlock can be held over the sleep operation; we should consider removing that (pointed out by attilio). Tested by: kris Discussed with: jhb, kris, attilio, jeff
2007-04-04 09:11:34 +00:00
FILEDESC_XUNLOCK(fdp);
return 0;
case SVR4_FIOGETOWN:
case SVR4_FIOSETOWN:
case SVR4_FIOASYNC:
case SVR4_FIONBIO:
case SVR4_FIONREAD:
if ((error = copyin(data, &num, sizeof(num))) != 0)
return error;
switch (cmd) {
case SVR4_FIOGETOWN: cmd = FIOGETOWN; break;
case SVR4_FIOSETOWN: cmd = FIOSETOWN; break;
case SVR4_FIOASYNC: cmd = FIOASYNC; break;
case SVR4_FIONBIO: cmd = FIONBIO; break;
case SVR4_FIONREAD: cmd = FIONREAD; break;
}
#ifdef SVR4_DEBUG
if (cmd == FIOASYNC) DPRINTF(("FIOASYNC\n"));
#endif
error = fo_ioctl(fp, cmd, (caddr_t) &num, td->td_ucred, td);
if (error)
return error;
return copyout(&num, data, sizeof(num));
default:
DPRINTF(("Unknown svr4 filio %lx\n", cmd));
return 0; /* ENOSYS really */
}
}