freebsd-dev/sys/kern/kern_mib.c

659 lines
22 KiB
C
Raw Normal View History

/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1982, 1986, 1989, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Mike Karels at Berkeley Software Design, Inc.
*
* Quite extensively rewritten by Poul-Henning Kamp of the FreeBSD
* project, to make these variables more userfriendly.
*
* 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. 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.
*
* @(#)kern_sysctl.c 8.4 (Berkeley) 4/14/94
*/
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_posix.h"
#include "opt_config.h"
#include <sys/param.h>
#include <sys/boot.h>
Huge cleanup of random(4) code. * GENERAL - Update copyright. - Make kernel options for RANDOM_YARROW and RANDOM_DUMMY. Set neither to ON, which means we want Fortuna - If there is no 'device random' in the kernel, there will be NO random(4) device in the kernel, and the KERN_ARND sysctl will return nothing. With RANDOM_DUMMY there will be a random(4) that always blocks. - Repair kern.arandom (KERN_ARND sysctl). The old version went through arc4random(9) and was a bit weird. - Adjust arc4random stirring a bit - the existing code looks a little suspect. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Redo read_random(9) so as to duplicate random(4)'s read internals. This makes it a first-class citizen rather than a hack. - Move stuff out of locked regions when it does not need to be there. - Trim RANDOM_DEBUG printfs. Some are excess to requirement, some behind boot verbose. - Use SYSINIT to sequence the startup. - Fix init/deinit sysctl stuff. - Make relevant sysctls also tunables. - Add different harvesting "styles" to allow for different requirements (direct, queue, fast). - Add harvesting of FFS atime events. This needs to be checked for weighing down the FS code. - Add harvesting of slab allocator events. This needs to be checked for weighing down the allocator code. - Fix the random(9) manpage. - Loadable modules are not present for now. These will be re-engineered when the dust settles. - Use macros for locks. - Fix comments. * src/share/man/... - Update the man pages. * src/etc/... - The startup/shutdown work is done in D2924. * src/UPDATING - Add UPDATING announcement. * src/sys/dev/random/build.sh - Add copyright. - Add libz for unit tests. * src/sys/dev/random/dummy.c - Remove; no longer needed. Functionality incorporated into randomdev.*. * live_entropy_sources.c live_entropy_sources.h - Remove; content moved. - move content to randomdev.[ch] and optimise. * src/sys/dev/random/random_adaptors.c src/sys/dev/random/random_adaptors.h - Remove; plugability is no longer used. Compile-time algorithm selection is the way to go. * src/sys/dev/random/random_harvestq.c src/sys/dev/random/random_harvestq.h - Add early (re)boot-time randomness caching. * src/sys/dev/random/randomdev_soft.c src/sys/dev/random/randomdev_soft.h - Remove; no longer needed. * src/sys/dev/random/uint128.h - Provide a fake uint128_t; if a real one ever arrived, we can use that instead. All that is needed here is N=0, N++, N==0, and some localised trickery is used to manufacture a 128-bit 0ULLL. * src/sys/dev/random/unit_test.c src/sys/dev/random/unit_test.h - Improve unit tests; previously the testing human needed clairvoyance; now the test will do a basic check of compressibility. Clairvoyant talent is still a good idea. - This is still a long way off a proper unit test. * src/sys/dev/random/fortuna.c src/sys/dev/random/fortuna.h - Improve messy union to just uint128_t. - Remove unneeded 'static struct fortuna_start_cache'. - Tighten up up arithmetic. - Provide a method to allow eternal junk to be introduced; harden it against blatant by compress/hashing. - Assert that locks are held correctly. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Turn into self-sufficient module (no longer requires randomdev_soft.[ch]) * src/sys/dev/random/yarrow.c src/sys/dev/random/yarrow.h - Improve messy union to just uint128_t. - Remove unneeded 'staic struct start_cache'. - Tighten up up arithmetic. - Provide a method to allow eternal junk to be introduced; harden it against blatant by compress/hashing. - Assert that locks are held correctly. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Turn into self-sufficient module (no longer requires randomdev_soft.[ch]) - Fix some magic numbers elsewhere used as FAST and SLOW. Differential Revision: https://reviews.freebsd.org/D2025 Reviewed by: vsevolod,delphij,rwatson,trasz,jmg Approved by: so (delphij)
2015-06-30 17:00:45 +00:00
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/mutex.h>
Huge cleanup of random(4) code. * GENERAL - Update copyright. - Make kernel options for RANDOM_YARROW and RANDOM_DUMMY. Set neither to ON, which means we want Fortuna - If there is no 'device random' in the kernel, there will be NO random(4) device in the kernel, and the KERN_ARND sysctl will return nothing. With RANDOM_DUMMY there will be a random(4) that always blocks. - Repair kern.arandom (KERN_ARND sysctl). The old version went through arc4random(9) and was a bit weird. - Adjust arc4random stirring a bit - the existing code looks a little suspect. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Redo read_random(9) so as to duplicate random(4)'s read internals. This makes it a first-class citizen rather than a hack. - Move stuff out of locked regions when it does not need to be there. - Trim RANDOM_DEBUG printfs. Some are excess to requirement, some behind boot verbose. - Use SYSINIT to sequence the startup. - Fix init/deinit sysctl stuff. - Make relevant sysctls also tunables. - Add different harvesting "styles" to allow for different requirements (direct, queue, fast). - Add harvesting of FFS atime events. This needs to be checked for weighing down the FS code. - Add harvesting of slab allocator events. This needs to be checked for weighing down the allocator code. - Fix the random(9) manpage. - Loadable modules are not present for now. These will be re-engineered when the dust settles. - Use macros for locks. - Fix comments. * src/share/man/... - Update the man pages. * src/etc/... - The startup/shutdown work is done in D2924. * src/UPDATING - Add UPDATING announcement. * src/sys/dev/random/build.sh - Add copyright. - Add libz for unit tests. * src/sys/dev/random/dummy.c - Remove; no longer needed. Functionality incorporated into randomdev.*. * live_entropy_sources.c live_entropy_sources.h - Remove; content moved. - move content to randomdev.[ch] and optimise. * src/sys/dev/random/random_adaptors.c src/sys/dev/random/random_adaptors.h - Remove; plugability is no longer used. Compile-time algorithm selection is the way to go. * src/sys/dev/random/random_harvestq.c src/sys/dev/random/random_harvestq.h - Add early (re)boot-time randomness caching. * src/sys/dev/random/randomdev_soft.c src/sys/dev/random/randomdev_soft.h - Remove; no longer needed. * src/sys/dev/random/uint128.h - Provide a fake uint128_t; if a real one ever arrived, we can use that instead. All that is needed here is N=0, N++, N==0, and some localised trickery is used to manufacture a 128-bit 0ULLL. * src/sys/dev/random/unit_test.c src/sys/dev/random/unit_test.h - Improve unit tests; previously the testing human needed clairvoyance; now the test will do a basic check of compressibility. Clairvoyant talent is still a good idea. - This is still a long way off a proper unit test. * src/sys/dev/random/fortuna.c src/sys/dev/random/fortuna.h - Improve messy union to just uint128_t. - Remove unneeded 'static struct fortuna_start_cache'. - Tighten up up arithmetic. - Provide a method to allow eternal junk to be introduced; harden it against blatant by compress/hashing. - Assert that locks are held correctly. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Turn into self-sufficient module (no longer requires randomdev_soft.[ch]) * src/sys/dev/random/yarrow.c src/sys/dev/random/yarrow.h - Improve messy union to just uint128_t. - Remove unneeded 'staic struct start_cache'. - Tighten up up arithmetic. - Provide a method to allow eternal junk to be introduced; harden it against blatant by compress/hashing. - Assert that locks are held correctly. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Turn into self-sufficient module (no longer requires randomdev_soft.[ch]) - Fix some magic numbers elsewhere used as FAST and SLOW. Differential Revision: https://reviews.freebsd.org/D2025 Reviewed by: vsevolod,delphij,rwatson,trasz,jmg Approved by: so (delphij)
2015-06-30 17:00:45 +00:00
#include <sys/proc.h>
#include <sys/random.h>
#include <sys/sbuf.h>
Overhaul of the SMP code. Several portions of the SMP kernel support have been made machine independent and various other adjustments have been made to support Alpha SMP. - It splits the per-process portions of hardclock() and statclock() off into hardclock_process() and statclock_process() respectively. hardclock() and statclock() call the *_process() functions for the current process so that UP systems will run as before. For SMP systems, it is simply necessary to ensure that all other processors execute the *_process() functions when the main clock functions are triggered on one CPU by an interrupt. For the alpha 4100, clock interrupts are delievered in a staggered broadcast fashion, so we simply call hardclock/statclock on the boot CPU and call the *_process() functions on the secondaries. For x86, we call statclock and hardclock as usual and then call forward_hardclock/statclock in the MD code to send an IPI to cause the AP's to execute forwared_hardclock/statclock which then call the *_process() functions. - forward_signal() and forward_roundrobin() have been reworked to be MI and to involve less hackery. Now the cpu doing the forward sets any flags, etc. and sends a very simple IPI_AST to the other cpu(s). AST IPIs now just basically return so that they can execute ast() and don't bother with setting the astpending or needresched flags themselves. This also removes the loop in forward_signal() as sched_lock closes the race condition that the loop worked around. - need_resched(), resched_wanted() and clear_resched() have been changed to take a process to act on rather than assuming curproc so that they can be used to implement forward_roundrobin() as described above. - Various other SMP variables have been moved to a MI subr_smp.c and a new header sys/smp.h declares MI SMP variables and API's. The IPI API's from machine/ipl.h have moved to machine/smp.h which is included by sys/smp.h. - The globaldata_register() and globaldata_find() functions as well as the SLIST of globaldata structures has become MI and moved into subr_smp.c. Also, the globaldata list is only available if SMP support is compiled in. Reviewed by: jake, peter Looked over by: eivind
2001-04-27 19:28:25 +00:00
#include <sys/smp.h>
#include <sys/sx.h>
#include <sys/vmmeter.h>
Huge cleanup of random(4) code. * GENERAL - Update copyright. - Make kernel options for RANDOM_YARROW and RANDOM_DUMMY. Set neither to ON, which means we want Fortuna - If there is no 'device random' in the kernel, there will be NO random(4) device in the kernel, and the KERN_ARND sysctl will return nothing. With RANDOM_DUMMY there will be a random(4) that always blocks. - Repair kern.arandom (KERN_ARND sysctl). The old version went through arc4random(9) and was a bit weird. - Adjust arc4random stirring a bit - the existing code looks a little suspect. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Redo read_random(9) so as to duplicate random(4)'s read internals. This makes it a first-class citizen rather than a hack. - Move stuff out of locked regions when it does not need to be there. - Trim RANDOM_DEBUG printfs. Some are excess to requirement, some behind boot verbose. - Use SYSINIT to sequence the startup. - Fix init/deinit sysctl stuff. - Make relevant sysctls also tunables. - Add different harvesting "styles" to allow for different requirements (direct, queue, fast). - Add harvesting of FFS atime events. This needs to be checked for weighing down the FS code. - Add harvesting of slab allocator events. This needs to be checked for weighing down the allocator code. - Fix the random(9) manpage. - Loadable modules are not present for now. These will be re-engineered when the dust settles. - Use macros for locks. - Fix comments. * src/share/man/... - Update the man pages. * src/etc/... - The startup/shutdown work is done in D2924. * src/UPDATING - Add UPDATING announcement. * src/sys/dev/random/build.sh - Add copyright. - Add libz for unit tests. * src/sys/dev/random/dummy.c - Remove; no longer needed. Functionality incorporated into randomdev.*. * live_entropy_sources.c live_entropy_sources.h - Remove; content moved. - move content to randomdev.[ch] and optimise. * src/sys/dev/random/random_adaptors.c src/sys/dev/random/random_adaptors.h - Remove; plugability is no longer used. Compile-time algorithm selection is the way to go. * src/sys/dev/random/random_harvestq.c src/sys/dev/random/random_harvestq.h - Add early (re)boot-time randomness caching. * src/sys/dev/random/randomdev_soft.c src/sys/dev/random/randomdev_soft.h - Remove; no longer needed. * src/sys/dev/random/uint128.h - Provide a fake uint128_t; if a real one ever arrived, we can use that instead. All that is needed here is N=0, N++, N==0, and some localised trickery is used to manufacture a 128-bit 0ULLL. * src/sys/dev/random/unit_test.c src/sys/dev/random/unit_test.h - Improve unit tests; previously the testing human needed clairvoyance; now the test will do a basic check of compressibility. Clairvoyant talent is still a good idea. - This is still a long way off a proper unit test. * src/sys/dev/random/fortuna.c src/sys/dev/random/fortuna.h - Improve messy union to just uint128_t. - Remove unneeded 'static struct fortuna_start_cache'. - Tighten up up arithmetic. - Provide a method to allow eternal junk to be introduced; harden it against blatant by compress/hashing. - Assert that locks are held correctly. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Turn into self-sufficient module (no longer requires randomdev_soft.[ch]) * src/sys/dev/random/yarrow.c src/sys/dev/random/yarrow.h - Improve messy union to just uint128_t. - Remove unneeded 'staic struct start_cache'. - Tighten up up arithmetic. - Provide a method to allow eternal junk to be introduced; harden it against blatant by compress/hashing. - Assert that locks are held correctly. - Fix the nasty pre- and post-read overloading by providing explictit functions to do these tasks. - Turn into self-sufficient module (no longer requires randomdev_soft.[ch]) - Fix some magic numbers elsewhere used as FAST and SLOW. Differential Revision: https://reviews.freebsd.org/D2025 Reviewed by: vsevolod,delphij,rwatson,trasz,jmg Approved by: so (delphij)
2015-06-30 17:00:45 +00:00
#include <sys/sysctl.h>
#include <sys/systm.h>
#include <sys/unistd.h>
SYSCTL_ROOT_NODE(0, sysctl, CTLFLAG_RW, 0,
"Sysctl internal magic");
SYSCTL_ROOT_NODE(CTL_KERN, kern, CTLFLAG_RW|CTLFLAG_CAPRD, 0,
"High kernel, proc, limits &c");
SYSCTL_ROOT_NODE(CTL_VM, vm, CTLFLAG_RW, 0,
"Virtual memory");
SYSCTL_ROOT_NODE(CTL_VFS, vfs, CTLFLAG_RW, 0,
"File system");
SYSCTL_ROOT_NODE(CTL_NET, net, CTLFLAG_RW, 0,
"Network, (see socket.h)");
SYSCTL_ROOT_NODE(CTL_DEBUG, debug, CTLFLAG_RW, 0,
"Debugging");
SYSCTL_NODE(_debug, OID_AUTO, sizeof, CTLFLAG_RW, 0,
"Sizeof various things");
SYSCTL_ROOT_NODE(CTL_HW, hw, CTLFLAG_RW, 0,
"hardware");
SYSCTL_ROOT_NODE(CTL_MACHDEP, machdep, CTLFLAG_RW, 0,
"machine dependent");
SYSCTL_NODE(_machdep, OID_AUTO, mitigations, CTLFLAG_RW, 0,
"Machine dependent platform mitigations.");
SYSCTL_ROOT_NODE(CTL_USER, user, CTLFLAG_RW, 0,
"user-level");
SYSCTL_ROOT_NODE(CTL_P1003_1B, p1003_1b, CTLFLAG_RW, 0,
"p1003_1b, (see p1003_1b.h)");
SYSCTL_ROOT_NODE(OID_AUTO, compat, CTLFLAG_RW, 0,
1999-08-27 19:47:41 +00:00
"Compatibility code");
SYSCTL_ROOT_NODE(OID_AUTO, security, CTLFLAG_RW, 0,
"Security");
#ifdef REGRESSION
SYSCTL_ROOT_NODE(OID_AUTO, regression, CTLFLAG_RW, 0,
"Regression test MIB");
#endif
1999-08-27 19:47:41 +00:00
SYSCTL_STRING(_kern, OID_AUTO, ident, CTLFLAG_RD|CTLFLAG_MPSAFE,
kern_ident, 0, "Kernel identifier");
SYSCTL_INT(_kern, KERN_OSREV, osrevision, CTLFLAG_RD|CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, BSD, "Operating system revision");
SYSCTL_STRING(_kern, KERN_VERSION, version, CTLFLAG_RD|CTLFLAG_MPSAFE,
version, 0, "Kernel version");
SYSCTL_STRING(_kern, OID_AUTO, compiler_version, CTLFLAG_RD|CTLFLAG_MPSAFE,
compiler_version, 0, "Version of compiler used to compile kernel");
SYSCTL_STRING(_kern, KERN_OSTYPE, ostype, CTLFLAG_RD|CTLFLAG_MPSAFE|
CTLFLAG_CAPRD, ostype, 0, "Operating system type");
SYSCTL_INT(_kern, KERN_MAXPROC, maxproc, CTLFLAG_RDTUN | CTLFLAG_NOFETCH,
&maxproc, 0, "Maximum number of processes");
SYSCTL_INT(_kern, KERN_MAXPROCPERUID, maxprocperuid, CTLFLAG_RW,
&maxprocperuid, 0, "Maximum processes allowed per userid");
SYSCTL_INT(_kern, OID_AUTO, maxusers, CTLFLAG_RDTUN | CTLFLAG_NOFETCH,
&maxusers, 0, "Hint for kernel tuning");
SYSCTL_INT(_kern, KERN_ARGMAX, argmax, CTLFLAG_RD|CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, ARG_MAX, "Maximum bytes of argument to execve(2)");
SYSCTL_INT(_kern, KERN_POSIX1, posix1version, CTLFLAG_RD|CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, _POSIX_VERSION, "Version of POSIX attempting to comply to");
SYSCTL_INT(_kern, KERN_NGROUPS, ngroups, CTLFLAG_RDTUN |
CTLFLAG_NOFETCH | CTLFLAG_CAPRD, &ngroups_max, 0,
"Maximum number of supplemental groups a user can belong to");
SYSCTL_INT(_kern, KERN_JOB_CONTROL, job_control, CTLFLAG_RD|CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, 1, "Whether job control is available");
#ifdef _POSIX_SAVED_IDS
SYSCTL_INT(_kern, KERN_SAVED_IDS, saved_ids, CTLFLAG_RD|CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, 1, "Whether saved set-group/user ID is available");
#else
SYSCTL_INT(_kern, KERN_SAVED_IDS, saved_ids, CTLFLAG_RD|CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, 0, "Whether saved set-group/user ID is available");
#endif
char kernelname[MAXPATHLEN] = PATH_KERNEL; /* XXX bloat */
SYSCTL_STRING(_kern, KERN_BOOTFILE, bootfile, CTLFLAG_RW | CTLFLAG_MPSAFE,
kernelname, sizeof kernelname, "Name of kernel file booted");
SYSCTL_INT(_kern, KERN_MAXPHYS, maxphys, CTLFLAG_RD | CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, MAXPHYS, "Maximum block I/O access size");
SYSCTL_INT(_hw, HW_NCPU, ncpu, CTLFLAG_RD|CTLFLAG_CAPRD,
&mp_ncpus, 0, "Number of active CPUs");
SYSCTL_INT(_hw, HW_BYTEORDER, byteorder, CTLFLAG_RD|CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, BYTE_ORDER, "System byte order");
SYSCTL_INT(_hw, HW_PAGESIZE, pagesize, CTLFLAG_RD|CTLFLAG_CAPRD,
SYSCTL_NULL_INT_PTR, PAGE_SIZE, "System memory page size");
static int
sysctl_kern_arnd(SYSCTL_HANDLER_ARGS)
{
char buf[256];
size_t len;
random(4): Block read_random(9) on initial seeding read_random() is/was used, mostly without error checking, in a lot of very sensitive places in the kernel -- including seeding the widely used arc4random(9). Most uses, especially arc4random(9), should block until the device is seeded rather than proceeding with a bogus or empty seed. I did not spy any obvious kernel consumers where blocking would be inappropriate (in the sense that lack of entropy would be ok -- I did not investigate locking angle thoroughly). In many instances, arc4random_buf(9) or that family of APIs would be more appropriate anyway; that work was done in r345865. A minor cleanup was made to the implementation of the READ_RANDOM function: instead of using a variable-length array on the stack to temporarily store all full random blocks sufficient to satisfy the requested 'len', only store a single block on the stack. This has some benefit in terms of reducing stack usage, reducing memcpy overhead and reducing devrandom output leakage via the stack. Additionally, the stack block is now safely zeroed if it was used. One caveat of this change is that the kern.arandom sysctl no longer returns zero bytes immediately if the random device is not seeded. This means that FreeBSD-specific userspace applications which attempted to handle an unseeded random device may be broken by this change. If such behavior is needed, it can be replaced by the more portable getrandom(2) GRND_NONBLOCK option. On any typical FreeBSD system, entropy is persisted on read/write media and used to seed the random device very early in boot, and blocking is never a problem. This change primarily impacts the behavior of /dev/random on embedded systems with read-only media that do not configure "nodevice random". We toggle the default from 'charge on blindly with no entropy' to 'block indefinitely.' This default is safer, but may cause frustration. Embedded system designers using FreeBSD have several options. The most obvious is to plan to have a small writable NVRAM or NAND to persist entropy, like larger systems. Early entropy can be fed from any loader, or by writing directly to /dev/random during boot. Some embedded SoCs now provide a fast hardware entropy source; this would also work for quickly seeding Fortuna. A 3rd option would be creating an embedded-specific, more simplistic random module, like that designed by DJB in [1] (this design still requires a small rewritable media for forward secrecy). Finally, the least preferred option might be "nodevice random", although I plan to remove this in a subsequent revision. To help developers emulate the behavior of these embedded systems on ordinary workstations, the tunable kern.random.block_seeded_status was added. When set to 1, it blocks the random device. I attempted to document this change in random.4 and random.9 and ran into a bunch of out-of-date or irrelevant or inaccurate content and ended up rototilling those documents more than I intended to. Sorry. I think they're in a better state now. PR: 230875 Reviewed by: delphij, markm (earlier version) Approved by: secteam(delphij), devrandom(markm) Relnotes: yes Differential Revision: https://reviews.freebsd.org/D19744
2019-04-15 18:40:36 +00:00
len = MIN(req->oldlen, sizeof(buf));
read_random(buf, len);
return (SYSCTL_OUT(req, buf, len));
}
SYSCTL_PROC(_kern, KERN_ARND, arandom,
CTLTYPE_OPAQUE | CTLFLAG_RD | CTLFLAG_MPSAFE | CTLFLAG_CAPRD, NULL, 0,
sysctl_kern_arnd, "", "arc4rand");
static int
sysctl_hw_physmem(SYSCTL_HANDLER_ARGS)
{
u_long val, p;
p = SIZE_T_MAX >> PAGE_SHIFT;
if (physmem < p)
p = physmem;
val = ctob(p);
return (sysctl_handle_long(oidp, &val, 0, req));
}
SYSCTL_PROC(_hw, HW_PHYSMEM, physmem, CTLTYPE_ULONG | CTLFLAG_RD,
0, 0, sysctl_hw_physmem, "LU",
"Amount of physical memory (in bytes)");
static int
sysctl_hw_realmem(SYSCTL_HANDLER_ARGS)
{
u_long val, p;
p = SIZE_T_MAX >> PAGE_SHIFT;
if (realmem < p)
p = realmem;
val = ctob(p);
return (sysctl_handle_long(oidp, &val, 0, req));
}
SYSCTL_PROC(_hw, HW_REALMEM, realmem, CTLTYPE_ULONG | CTLFLAG_RD,
0, 0, sysctl_hw_realmem, "LU",
"Amount of memory (in bytes) reported by the firmware");
static int
sysctl_hw_usermem(SYSCTL_HANDLER_ARGS)
{
u_long val, p, p1;
p1 = physmem - vm_wire_count();
p = SIZE_T_MAX >> PAGE_SHIFT;
if (p1 < p)
p = p1;
val = ctob(p);
return (sysctl_handle_long(oidp, &val, 0, req));
}
SYSCTL_PROC(_hw, HW_USERMEM, usermem, CTLTYPE_ULONG | CTLFLAG_RD,
0, 0, sysctl_hw_usermem, "LU",
"Amount of memory (in bytes) which is not wired");
SYSCTL_LONG(_hw, OID_AUTO, availpages, CTLFLAG_RD, &physmem, 0,
"Amount of physical memory (in pages)");
u_long pagesizes[MAXPAGESIZES] = { PAGE_SIZE };
static int
sysctl_hw_pagesizes(SYSCTL_HANDLER_ARGS)
{
int error;
#ifdef SCTL_MASK32
int i;
uint32_t pagesizes32[MAXPAGESIZES];
if (req->flags & SCTL_MASK32) {
/*
* Recreate the "pagesizes" array with 32-bit elements. Truncate
* any page size greater than UINT32_MAX to zero.
*/
for (i = 0; i < MAXPAGESIZES; i++)
pagesizes32[i] = (uint32_t)pagesizes[i];
error = SYSCTL_OUT(req, pagesizes32, sizeof(pagesizes32));
} else
#endif
error = SYSCTL_OUT(req, pagesizes, sizeof(pagesizes));
return (error);
}
SYSCTL_PROC(_hw, OID_AUTO, pagesizes, CTLTYPE_ULONG | CTLFLAG_RD,
NULL, 0, sysctl_hw_pagesizes, "LU", "Supported page sizes");
#ifdef SCTL_MASK32
int adaptive_machine_arch = 1;
SYSCTL_INT(_debug, OID_AUTO, adaptive_machine_arch, CTLFLAG_RW,
&adaptive_machine_arch, 1,
"Adapt reported machine architecture to the ABI of the binary");
#endif
static int
sysctl_hw_machine_arch(SYSCTL_HANDLER_ARGS)
{
int error;
static const char machine_arch[] = MACHINE_ARCH;
#ifdef SCTL_MASK32
static const char machine_arch32[] = MACHINE_ARCH32;
if ((req->flags & SCTL_MASK32) != 0 && adaptive_machine_arch)
error = SYSCTL_OUT(req, machine_arch32, sizeof(machine_arch32));
else
#endif
error = SYSCTL_OUT(req, machine_arch, sizeof(machine_arch));
return (error);
}
SYSCTL_PROC(_hw, HW_MACHINE_ARCH, machine_arch, CTLTYPE_STRING | CTLFLAG_RD |
CTLFLAG_MPSAFE, NULL, 0, sysctl_hw_machine_arch, "A",
"System architecture");
SYSCTL_STRING(_kern, OID_AUTO, supported_archs, CTLFLAG_RD | CTLFLAG_MPSAFE,
#ifdef COMPAT_FREEBSD32
MACHINE_ARCH " " MACHINE_ARCH32, 0, "Supported architectures for binaries");
#else
MACHINE_ARCH, 0, "Supported architectures for binaries");
#endif
This Implements the mumbled about "Jail" feature. This is a seriously beefed up chroot kind of thing. The process is jailed along the same lines as a chroot does it, but with additional tough restrictions imposed on what the superuser can do. For all I know, it is safe to hand over the root bit inside a prison to the customer living in that prison, this is what it was developed for in fact: "real virtual servers". Each prison has an ip number associated with it, which all IP communications will be coerced to use and each prison has its own hostname. Needless to say, you need more RAM this way, but the advantage is that each customer can run their own particular version of apache and not stomp on the toes of their neighbors. It generally does what one would expect, but setting up a jail still takes a little knowledge. A few notes: I have no scripts for setting up a jail, don't ask me for them. The IP number should be an alias on one of the interfaces. mount a /proc in each jail, it will make ps more useable. /proc/<pid>/status tells the hostname of the prison for jailed processes. Quotas are only sensible if you have a mountpoint per prison. There are no privisions for stopping resource-hogging. Some "#ifdef INET" and similar may be missing (send patches!) If somebody wants to take it from here and develop it into more of a "virtual machine" they should be most welcome! Tools, comments, patches & documentation most welcome. Have fun... Sponsored by: http://www.rndassociates.com/ Run for almost a year by: http://www.servetheweb.com/
1999-04-28 11:38:52 +00:00
static int
sysctl_hostname(SYSCTL_HANDLER_ARGS)
This Implements the mumbled about "Jail" feature. This is a seriously beefed up chroot kind of thing. The process is jailed along the same lines as a chroot does it, but with additional tough restrictions imposed on what the superuser can do. For all I know, it is safe to hand over the root bit inside a prison to the customer living in that prison, this is what it was developed for in fact: "real virtual servers". Each prison has an ip number associated with it, which all IP communications will be coerced to use and each prison has its own hostname. Needless to say, you need more RAM this way, but the advantage is that each customer can run their own particular version of apache and not stomp on the toes of their neighbors. It generally does what one would expect, but setting up a jail still takes a little knowledge. A few notes: I have no scripts for setting up a jail, don't ask me for them. The IP number should be an alias on one of the interfaces. mount a /proc in each jail, it will make ps more useable. /proc/<pid>/status tells the hostname of the prison for jailed processes. Quotas are only sensible if you have a mountpoint per prison. There are no privisions for stopping resource-hogging. Some "#ifdef INET" and similar may be missing (send patches!) If somebody wants to take it from here and develop it into more of a "virtual machine" they should be most welcome! Tools, comments, patches & documentation most welcome. Have fun... Sponsored by: http://www.rndassociates.com/ Run for almost a year by: http://www.servetheweb.com/
1999-04-28 11:38:52 +00:00
{
struct prison *pr, *cpr;
size_t pr_offset;
char tmpname[MAXHOSTNAMELEN];
int descend, error, len;
/*
* This function can set: hostname domainname hostuuid.
* Keep that in mind when comments say "hostname".
*/
pr_offset = (size_t)arg1;
len = arg2;
KASSERT(len <= sizeof(tmpname),
("length %d too long for %s", len, __func__));
This Implements the mumbled about "Jail" feature. This is a seriously beefed up chroot kind of thing. The process is jailed along the same lines as a chroot does it, but with additional tough restrictions imposed on what the superuser can do. For all I know, it is safe to hand over the root bit inside a prison to the customer living in that prison, this is what it was developed for in fact: "real virtual servers". Each prison has an ip number associated with it, which all IP communications will be coerced to use and each prison has its own hostname. Needless to say, you need more RAM this way, but the advantage is that each customer can run their own particular version of apache and not stomp on the toes of their neighbors. It generally does what one would expect, but setting up a jail still takes a little knowledge. A few notes: I have no scripts for setting up a jail, don't ask me for them. The IP number should be an alias on one of the interfaces. mount a /proc in each jail, it will make ps more useable. /proc/<pid>/status tells the hostname of the prison for jailed processes. Quotas are only sensible if you have a mountpoint per prison. There are no privisions for stopping resource-hogging. Some "#ifdef INET" and similar may be missing (send patches!) If somebody wants to take it from here and develop it into more of a "virtual machine" they should be most welcome! Tools, comments, patches & documentation most welcome. Have fun... Sponsored by: http://www.rndassociates.com/ Run for almost a year by: http://www.servetheweb.com/
1999-04-28 11:38:52 +00:00
pr = req->td->td_ucred->cr_prison;
if (!(pr->pr_allow & PR_ALLOW_SET_HOSTNAME) && req->newptr)
return (EPERM);
/*
* Make a local copy of hostname to get/set so we don't have to hold
* the jail mutex during the sysctl copyin/copyout activities.
*/
mtx_lock(&pr->pr_mtx);
bcopy((char *)pr + pr_offset, tmpname, len);
mtx_unlock(&pr->pr_mtx);
error = sysctl_handle_string(oidp, tmpname, len, req);
if (req->newptr != NULL && error == 0) {
/*
* Copy the locally set hostname to all jails that share
* this host info.
*/
sx_slock(&allprison_lock);
while (!(pr->pr_flags & PR_HOST))
pr = pr->pr_parent;
mtx_lock(&pr->pr_mtx);
bcopy(tmpname, (char *)pr + pr_offset, len);
FOREACH_PRISON_DESCENDANT_LOCKED(pr, cpr, descend)
if (cpr->pr_flags & PR_HOST)
descend = 0;
else
bcopy(tmpname, (char *)cpr + pr_offset, len);
mtx_unlock(&pr->pr_mtx);
sx_sunlock(&allprison_lock);
}
This Implements the mumbled about "Jail" feature. This is a seriously beefed up chroot kind of thing. The process is jailed along the same lines as a chroot does it, but with additional tough restrictions imposed on what the superuser can do. For all I know, it is safe to hand over the root bit inside a prison to the customer living in that prison, this is what it was developed for in fact: "real virtual servers". Each prison has an ip number associated with it, which all IP communications will be coerced to use and each prison has its own hostname. Needless to say, you need more RAM this way, but the advantage is that each customer can run their own particular version of apache and not stomp on the toes of their neighbors. It generally does what one would expect, but setting up a jail still takes a little knowledge. A few notes: I have no scripts for setting up a jail, don't ask me for them. The IP number should be an alias on one of the interfaces. mount a /proc in each jail, it will make ps more useable. /proc/<pid>/status tells the hostname of the prison for jailed processes. Quotas are only sensible if you have a mountpoint per prison. There are no privisions for stopping resource-hogging. Some "#ifdef INET" and similar may be missing (send patches!) If somebody wants to take it from here and develop it into more of a "virtual machine" they should be most welcome! Tools, comments, patches & documentation most welcome. Have fun... Sponsored by: http://www.rndassociates.com/ Run for almost a year by: http://www.servetheweb.com/
1999-04-28 11:38:52 +00:00
return (error);
}
SYSCTL_PROC(_kern, KERN_HOSTNAME, hostname,
CTLTYPE_STRING | CTLFLAG_RW | CTLFLAG_PRISON | CTLFLAG_CAPRD | CTLFLAG_MPSAFE,
(void *)(offsetof(struct prison, pr_hostname)), MAXHOSTNAMELEN,
sysctl_hostname, "A", "Hostname");
SYSCTL_PROC(_kern, KERN_NISDOMAINNAME, domainname,
CTLTYPE_STRING | CTLFLAG_RW | CTLFLAG_PRISON | CTLFLAG_CAPRD | CTLFLAG_MPSAFE,
(void *)(offsetof(struct prison, pr_domainname)), MAXHOSTNAMELEN,
sysctl_hostname, "A", "Name of the current YP/NIS domain");
SYSCTL_PROC(_kern, KERN_HOSTUUID, hostuuid,
CTLTYPE_STRING | CTLFLAG_RW | CTLFLAG_PRISON | CTLFLAG_CAPRD | CTLFLAG_MPSAFE,
(void *)(offsetof(struct prison, pr_hostuuid)), HOSTUUIDLEN,
sysctl_hostname, "A", "Host UUID");
static int regression_securelevel_nonmonotonic = 0;
#ifdef REGRESSION
SYSCTL_INT(_regression, OID_AUTO, securelevel_nonmonotonic, CTLFLAG_RW,
&regression_securelevel_nonmonotonic, 0, "securelevel may be lowered");
#endif
static int
sysctl_kern_securelvl(SYSCTL_HANDLER_ARGS)
{
struct prison *pr, *cpr;
int descend, error, level;
pr = req->td->td_ucred->cr_prison;
/*
* Reading the securelevel is easy, since the current jail's level
* is known to be at least as secure as any higher levels. Perform
* a lockless read since the securelevel is an integer.
*/
level = pr->pr_securelevel;
error = sysctl_handle_int(oidp, &level, 0, req);
if (error || !req->newptr)
return (error);
/* Permit update only if the new securelevel exceeds the old. */
sx_slock(&allprison_lock);
mtx_lock(&pr->pr_mtx);
if (!regression_securelevel_nonmonotonic &&
level < pr->pr_securelevel) {
mtx_unlock(&pr->pr_mtx);
sx_sunlock(&allprison_lock);
return (EPERM);
}
pr->pr_securelevel = level;
/*
* Set all child jails to be at least this level, but do not lower
* them (even if regression_securelevel_nonmonotonic).
*/
FOREACH_PRISON_DESCENDANT_LOCKED(pr, cpr, descend) {
if (cpr->pr_securelevel < level)
cpr->pr_securelevel = level;
}
mtx_unlock(&pr->pr_mtx);
sx_sunlock(&allprison_lock);
return (error);
}
SYSCTL_PROC(_kern, KERN_SECURELVL, securelevel,
CTLTYPE_INT|CTLFLAG_RW|CTLFLAG_PRISON, 0, 0, sysctl_kern_securelvl,
"I", "Current secure level");
#ifdef INCLUDE_CONFIG_FILE
/* Actual kernel configuration options. */
extern char kernconfstring[];
SYSCTL_STRING(_kern, OID_AUTO, conftxt, CTLFLAG_RD | CTLFLAG_MPSAFE,
kernconfstring, 0, "Kernel configuration file");
#endif
static int
sysctl_hostid(SYSCTL_HANDLER_ARGS)
{
struct prison *pr, *cpr;
u_long tmpid;
int descend, error;
/*
* Like sysctl_hostname, except it operates on a u_long
* instead of a string, and is used only for hostid.
*/
pr = req->td->td_ucred->cr_prison;
if (!(pr->pr_allow & PR_ALLOW_SET_HOSTNAME) && req->newptr)
return (EPERM);
tmpid = pr->pr_hostid;
error = sysctl_handle_long(oidp, &tmpid, 0, req);
if (req->newptr != NULL && error == 0) {
sx_slock(&allprison_lock);
while (!(pr->pr_flags & PR_HOST))
pr = pr->pr_parent;
mtx_lock(&pr->pr_mtx);
pr->pr_hostid = tmpid;
FOREACH_PRISON_DESCENDANT_LOCKED(pr, cpr, descend)
if (cpr->pr_flags & PR_HOST)
descend = 0;
else
cpr->pr_hostid = tmpid;
mtx_unlock(&pr->pr_mtx);
sx_sunlock(&allprison_lock);
}
return (error);
}
SYSCTL_PROC(_kern, KERN_HOSTID, hostid,
2016-02-23 23:37:10 +00:00
CTLTYPE_ULONG | CTLFLAG_RW | CTLFLAG_PRISON | CTLFLAG_MPSAFE | CTLFLAG_CAPRD,
NULL, 0, sysctl_hostid, "LU", "Host ID");
/*
* The osrelease string is copied from the global (osrelease in vers.c) into
* prison0 by a sysinit and is inherited by child jails if not changed at jail
* creation, so we always return the copy from the current prison data.
*/
static int
sysctl_osrelease(SYSCTL_HANDLER_ARGS)
{
struct prison *pr;
pr = req->td->td_ucred->cr_prison;
return (SYSCTL_OUT(req, pr->pr_osrelease, strlen(pr->pr_osrelease) + 1));
}
SYSCTL_PROC(_kern, KERN_OSRELEASE, osrelease,
CTLTYPE_STRING | CTLFLAG_CAPRD | CTLFLAG_RD | CTLFLAG_MPSAFE,
NULL, 0, sysctl_osrelease, "A", "Operating system release");
/*
* The osreldate number is copied from the global (osreldate in vers.c) into
* prison0 by a sysinit and is inherited by child jails if not changed at jail
* creation, so we always return the value from the current prison data.
*/
static int
sysctl_osreldate(SYSCTL_HANDLER_ARGS)
{
struct prison *pr;
pr = req->td->td_ucred->cr_prison;
return (SYSCTL_OUT(req, &pr->pr_osreldate, sizeof(pr->pr_osreldate)));
}
/*
* NOTICE: The *userland* release date is available in
* /usr/include/osreldate.h
*/
SYSCTL_PROC(_kern, KERN_OSRELDATE, osreldate,
CTLTYPE_INT | CTLFLAG_CAPRD | CTLFLAG_RD | CTLFLAG_MPSAFE,
NULL, 0, sysctl_osreldate, "I", "Kernel release date");
/*
* The build-id is copied from the ELF section .note.gnu.build-id. The linker
* script defines two variables to expose the beginning and end. LLVM
* currently uses a SHA-1 hash, but other formats can be supported by checking
* the length of the section.
*/
extern char __build_id_start[];
extern char __build_id_end[];
#define BUILD_ID_HEADER_LEN 0x10
#define BUILD_ID_HASH_MAXLEN 0x14
static int
sysctl_build_id(SYSCTL_HANDLER_ARGS)
{
uintptr_t sectionlen = (uintptr_t)(__build_id_end - __build_id_start);
int hashlen;
char buf[2*BUILD_ID_HASH_MAXLEN+1];
/*
* The ELF note section has a four byte length for the vendor name,
* four byte length for the value, and a four byte vendor specific
* type. The name for the build id is "GNU\0". We skip the first 16
* bytes to read the build hash. We will return the remaining bytes up
* to 20 (SHA-1) hash size. If the hash happens to be a custom number
* of bytes we will pad the value with zeros, as the section should be
* four byte aligned.
*/
if (sectionlen <= BUILD_ID_HEADER_LEN ||
sectionlen > (BUILD_ID_HEADER_LEN + BUILD_ID_HASH_MAXLEN)) {
return (ENOENT);
}
hashlen = sectionlen - BUILD_ID_HEADER_LEN;
for (int i = 0; i < hashlen; i++) {
uint8_t c = __build_id_start[i+BUILD_ID_HEADER_LEN];
snprintf(&buf[2*i], 3, "%02x", c);
}
return (SYSCTL_OUT(req, buf, strlen(buf) + 1));
}
SYSCTL_PROC(_kern, OID_AUTO, build_id,
CTLTYPE_STRING | CTLFLAG_CAPRD | CTLFLAG_RD | CTLFLAG_MPSAFE,
NULL, 0, sysctl_build_id, "A", "Operating system build-id");
SYSCTL_NODE(_kern, OID_AUTO, features, CTLFLAG_RD, 0, "Kernel Features");
#ifdef COMPAT_FREEBSD4
FEATURE(compat_freebsd4, "Compatible with FreeBSD 4");
#endif
#ifdef COMPAT_FREEBSD5
FEATURE(compat_freebsd5, "Compatible with FreeBSD 5");
#endif
#ifdef COMPAT_FREEBSD6
FEATURE(compat_freebsd6, "Compatible with FreeBSD 6");
#endif
#ifdef COMPAT_FREEBSD7
FEATURE(compat_freebsd7, "Compatible with FreeBSD 7");
#endif
/*
* This is really cheating. These actually live in the libc, something
* which I'm not quite sure is a good idea anyway, but in order for
* getnext and friends to actually work, we define dummies here.
*
* XXXRW: These probably should be CTLFLAG_CAPRD.
*/
SYSCTL_STRING(_user, USER_CS_PATH, cs_path, CTLFLAG_RD,
"", 0, "PATH that finds all the standard utilities");
SYSCTL_INT(_user, USER_BC_BASE_MAX, bc_base_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Max ibase/obase values in bc(1)");
SYSCTL_INT(_user, USER_BC_DIM_MAX, bc_dim_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Max array size in bc(1)");
SYSCTL_INT(_user, USER_BC_SCALE_MAX, bc_scale_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Max scale value in bc(1)");
SYSCTL_INT(_user, USER_BC_STRING_MAX, bc_string_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Max string length in bc(1)");
SYSCTL_INT(_user, USER_COLL_WEIGHTS_MAX, coll_weights_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Maximum number of weights assigned to an LC_COLLATE locale entry");
SYSCTL_INT(_user, USER_EXPR_NEST_MAX, expr_nest_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "");
SYSCTL_INT(_user, USER_LINE_MAX, line_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Max length (bytes) of a text-processing utility's input line");
SYSCTL_INT(_user, USER_RE_DUP_MAX, re_dup_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Maximum number of repeats of a regexp permitted");
SYSCTL_INT(_user, USER_POSIX2_VERSION, posix2_version, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0,
"The version of POSIX 1003.2 with which the system attempts to comply");
SYSCTL_INT(_user, USER_POSIX2_C_BIND, posix2_c_bind, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Whether C development supports the C bindings option");
SYSCTL_INT(_user, USER_POSIX2_C_DEV, posix2_c_dev, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Whether system supports the C development utilities option");
SYSCTL_INT(_user, USER_POSIX2_CHAR_TERM, posix2_char_term, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "");
SYSCTL_INT(_user, USER_POSIX2_FORT_DEV, posix2_fort_dev, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Whether system supports FORTRAN development utilities");
SYSCTL_INT(_user, USER_POSIX2_FORT_RUN, posix2_fort_run, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Whether system supports FORTRAN runtime utilities");
SYSCTL_INT(_user, USER_POSIX2_LOCALEDEF, posix2_localedef, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Whether system supports creation of locales");
SYSCTL_INT(_user, USER_POSIX2_SW_DEV, posix2_sw_dev, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Whether system supports software development utilities");
SYSCTL_INT(_user, USER_POSIX2_UPE, posix2_upe, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Whether system supports the user portability utilities");
SYSCTL_INT(_user, USER_STREAM_MAX, stream_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Min Maximum number of streams a process may have open at one time");
SYSCTL_INT(_user, USER_TZNAME_MAX, tzname_max, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, 0, "Min Maximum number of types supported for timezone names");
#include <sys/vnode.h>
SYSCTL_INT(_debug_sizeof, OID_AUTO, vnode, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, sizeof(struct vnode), "sizeof(struct vnode)");
SYSCTL_INT(_debug_sizeof, OID_AUTO, proc, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, sizeof(struct proc), "sizeof(struct proc)");
1999-07-20 07:19:32 +00:00
static int
sysctl_kern_pid_max(SYSCTL_HANDLER_ARGS)
{
int error, pm;
pm = pid_max;
error = sysctl_handle_int(oidp, &pm, 0, req);
if (error || !req->newptr)
return (error);
sx_xlock(&proctree_lock);
sx_xlock(&allproc_lock);
/*
* Only permit the values less then PID_MAX.
* As a safety measure, do not allow to limit the pid_max too much.
*/
if (pm < 300 || pm > PID_MAX)
error = EINVAL;
else
pid_max = pm;
sx_xunlock(&allproc_lock);
sx_xunlock(&proctree_lock);
return (error);
}
SYSCTL_PROC(_kern, OID_AUTO, pid_max, CTLTYPE_INT |
CTLFLAG_RWTUN | CTLFLAG_NOFETCH | CTLFLAG_MPSAFE,
0, 0, sysctl_kern_pid_max, "I", "Maximum allowed pid");
#include <sys/bio.h>
#include <sys/buf.h>
SYSCTL_INT(_debug_sizeof, OID_AUTO, bio, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, sizeof(struct bio), "sizeof(struct bio)");
SYSCTL_INT(_debug_sizeof, OID_AUTO, buf, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, sizeof(struct buf), "sizeof(struct buf)");
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
#include <sys/user.h>
SYSCTL_INT(_debug_sizeof, OID_AUTO, kinfo_proc, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, sizeof(struct kinfo_proc), "sizeof(struct kinfo_proc)");
/* Used by kernel debuggers. */
const int pcb_size = sizeof(struct pcb);
SYSCTL_INT(_debug_sizeof, OID_AUTO, pcb, CTLFLAG_RD,
SYSCTL_NULL_INT_PTR, sizeof(struct pcb), "sizeof(struct pcb)");
/* XXX compatibility, remove for 6.0 */
#include <sys/imgact.h>
#include <sys/imgact_elf.h>
SYSCTL_INT(_kern, OID_AUTO, fallback_elf_brand, CTLFLAG_RW,
&__elfN(fallback_brand), sizeof(__elfN(fallback_brand)),
"compatibility for kern.fallback_elf_brand");