freebsd-nq/sys/fs/fdescfs/fdesc_vfsops.c

244 lines
6.0 KiB
C
Raw Normal View History

/*-
* Copyright (c) 1992, 1993, 1995
1994-05-24 10:09:53 +00:00
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software donated to Berkeley by
* Jan-Simon Pendry.
*
* 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.
*
* @(#)fdesc_vfsops.c 8.4 (Berkeley) 1/21/94
*
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
/*
* /dev/fd Filesystem
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/filedesc.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/malloc.h>
#include <sys/mount.h>
1994-05-24 10:09:53 +00:00
#include <sys/proc.h>
#include <sys/racct.h>
1994-05-24 10:09:53 +00:00
#include <sys/resourcevar.h>
#include <sys/vnode.h>
#include <fs/fdescfs/fdesc.h>
1994-05-24 10:09:53 +00:00
static MALLOC_DEFINE(M_FDESCMNT, "fdesc_mount", "FDESC mount structure");
static vfs_cmount_t fdesc_cmount;
static vfs_mount_t fdesc_mount;
static vfs_unmount_t fdesc_unmount;
static vfs_statfs_t fdesc_statfs;
2005-02-10 12:09:15 +00:00
static vfs_root_t fdesc_root;
/*
* Compatibility shim for old mount(2) system call.
*/
int
fdesc_cmount(struct mntarg *ma, void *data, uint64_t flags)
{
return kernel_mount(ma, flags);
}
1994-05-24 10:09:53 +00:00
/*
* Mount the per-process file descriptors (/dev/fd)
*/
static int
fdesc_mount(struct mount *mp)
1994-05-24 10:09:53 +00:00
{
int error = 0;
struct fdescmount *fmp;
struct vnode *rvp;
/*
* Update is a no-op
*/
if (mp->mnt_flag & (MNT_UPDATE | MNT_ROOTFS))
1994-05-24 10:09:53 +00:00
return (EOPNOTSUPP);
fmp = malloc(sizeof(struct fdescmount),
M_FDESCMNT, M_WAITOK); /* XXX */
/*
* We need to initialize a few bits of our local mount point struct to
* avoid confusion in allocvp.
*/
mp->mnt_data = (qaddr_t) fmp;
fmp->flags = 0;
error = fdesc_allocvp(Froot, -1, FD_ROOT, mp, &rvp);
if (error) {
free(fmp, M_FDESCMNT);
2012-03-13 10:04:13 +00:00
mp->mnt_data = NULL;
return (error);
}
1994-05-24 10:09:53 +00:00
rvp->v_type = VDIR;
rvp->v_vflag |= VV_ROOT;
1994-05-24 10:09:53 +00:00
fmp->f_root = rvp;
VOP_UNLOCK(rvp, 0);
1994-05-24 10:09:53 +00:00
/* XXX -- don't mark as local to work around fts() problems */
/*mp->mnt_flag |= MNT_LOCAL;*/
MNT_ILOCK(mp);
mp->mnt_kern_flag |= MNTK_MPSAFE;
MNT_IUNLOCK(mp);
vfs_getnewfsid(mp);
1994-05-24 10:09:53 +00:00
vfs_mountedfrom(mp, "fdescfs");
1994-05-24 10:09:53 +00:00
return (0);
}
static int
fdesc_unmount(mp, mntflags)
1994-05-24 10:09:53 +00:00
struct mount *mp;
int mntflags;
{
struct fdescmount *fmp;
caddr_t data;
1994-05-24 10:09:53 +00:00
int error;
int flags = 0;
fmp = (struct fdescmount *)mp->mnt_data;
if (mntflags & MNT_FORCE) {
/* The hash mutex protects the private mount flags. */
mtx_lock(&fdesc_hashmtx);
fmp->flags |= FMNT_UNMOUNTF;
mtx_unlock(&fdesc_hashmtx);
1994-05-24 10:09:53 +00:00
flags |= FORCECLOSE;
}
1994-05-24 10:09:53 +00:00
/*
* Clear out buffer cache. I don't think we
* ever get anything cached at this level at the
* moment, but who knows...
*
* There is 1 extra root vnode reference corresponding
* to f_root.
1994-05-24 10:09:53 +00:00
*/
if ((error = vflush(mp, 1, flags, curthread)) != 0)
1994-05-24 10:09:53 +00:00
return (error);
/*
* Finally, throw away the fdescmount structure. Hold the hashmtx to
* protect the fdescmount structure.
1994-05-24 10:09:53 +00:00
*/
mtx_lock(&fdesc_hashmtx);
data = mp->mnt_data;
2012-03-13 10:04:13 +00:00
mp->mnt_data = NULL;
mtx_unlock(&fdesc_hashmtx);
free(data, M_FDESCMNT); /* XXX */
1994-05-24 10:09:53 +00:00
return (0);
}
2005-02-10 12:09:15 +00:00
static int
fdesc_root(mp, flags, vpp)
1994-05-24 10:09:53 +00:00
struct mount *mp;
int flags;
1994-05-24 10:09:53 +00:00
struct vnode **vpp;
{
struct vnode *vp;
/*
* Return locked reference to root.
*/
vp = VFSTOFDESC(mp)->f_root;
vget(vp, LK_EXCLUSIVE | LK_RETRY, curthread);
1994-05-24 10:09:53 +00:00
*vpp = vp;
return (0);
}
static int
fdesc_statfs(mp, sbp)
1994-05-24 10:09:53 +00:00
struct mount *mp;
struct statfs *sbp;
{
struct thread *td;
1994-05-24 10:09:53 +00:00
struct filedesc *fdp;
int lim;
int i;
int last;
int freefd;
uint64_t limit;
1994-05-24 10:09:53 +00:00
td = curthread;
1994-05-24 10:09:53 +00:00
/*
* Compute number of free file descriptors.
* [ Strange results will ensue if the open file
* limit is ever reduced below the current number
* of open files... ]
*/
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
PROC_LOCK(td->td_proc);
lim = lim_cur(td->td_proc, RLIMIT_NOFILE);
PROC_UNLOCK(td->td_proc);
fdp = td->td_proc->p_fd;
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_SLOCK(fdp);
limit = racct_get_limit(td->td_proc, RACCT_NOFILE);
if (lim > limit)
lim = limit;
1994-05-24 10:09:53 +00:00
last = min(fdp->fd_nfiles, lim);
freefd = 0;
for (i = fdp->fd_freefile; i < last; i++)
if (fdp->fd_ofiles[i] == NULL)
freefd++;
/*
* Adjust for the fact that the fdesc array may not
* have been fully allocated yet.
*/
if (fdp->fd_nfiles < lim)
freefd += (lim - fdp->fd_nfiles);
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_SUNLOCK(fdp);
1994-05-24 10:09:53 +00:00
sbp->f_flags = 0;
sbp->f_bsize = DEV_BSIZE;
sbp->f_iosize = DEV_BSIZE;
sbp->f_blocks = 2; /* 1K to keep df happy */
sbp->f_bfree = 0;
sbp->f_bavail = 0;
sbp->f_files = lim + 1; /* Allow for "." */
sbp->f_ffree = freefd; /* See comments above */
return (0);
}
static struct vfsops fdesc_vfsops = {
.vfs_cmount = fdesc_cmount,
.vfs_init = fdesc_init,
.vfs_mount = fdesc_mount,
.vfs_root = fdesc_root,
.vfs_statfs = fdesc_statfs,
.vfs_uninit = fdesc_uninit,
.vfs_unmount = fdesc_unmount,
1994-05-24 10:09:53 +00:00
};
VFS_SET(fdesc_vfsops, fdescfs, VFCF_SYNTHETIC);