linux/kernel/sysctl.c

2846 lines
65 KiB
C
Raw Normal View History

/*
* sysctl.c: General linux system control interface
*
* Begun 24 March 1995, Stephen Tweedie
* Added /proc support, Dec 1995
* Added bdflush entry and intvec min/max checking, 2/23/96, Tom Dyas.
* Added hooks for /proc/sys/net (minor, minor patch), 96/4/1, Mike Shaver.
* Added kernel/java-{interpreter,appletviewer}, 96/5/10, Mike Shaver.
* Dynamic registration fixes, Stephen Tweedie.
* Added kswapd-interval, ctrl-alt-del, printk stuff, 1/8/97, Chris Horn.
* Made sysctl support optional via CONFIG_SYSCTL, 1/10/97, Chris
* Horn.
* Added proc_doulongvec_ms_jiffies_minmax, 09/08/99, Carlos H. Bauer.
* Added proc_doulongvec_minmax, 09/08/99, Carlos H. Bauer.
* Changed linked lists to use list.h instead of lists.h, 02/24/00, Bill
* Wendling.
* The list_for_each() macro wasn't appropriate for the sysctl loop.
* Removed it and replaced it with older style, 03/23/00, Bill Wendling
*/
#include <linux/module.h>
#include <linux/aio.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/bitmap.h>
#include <linux/signal.h>
kptr_restrict for hiding kernel pointers from unprivileged users Add the %pK printk format specifier and the /proc/sys/kernel/kptr_restrict sysctl. The %pK format specifier is designed to hide exposed kernel pointers, specifically via /proc interfaces. Exposing these pointers provides an easy target for kernel write vulnerabilities, since they reveal the locations of writable structures containing easily triggerable function pointers. The behavior of %pK depends on the kptr_restrict sysctl. If kptr_restrict is set to 0, no deviation from the standard %p behavior occurs. If kptr_restrict is set to 1, the default, if the current user (intended to be a reader via seq_printf(), etc.) does not have CAP_SYSLOG (currently in the LSM tree), kernel pointers using %pK are printed as 0's. If kptr_restrict is set to 2, kernel pointers using %pK are printed as 0's regardless of privileges. Replacing with 0's was chosen over the default "(null)", which cannot be parsed by userland %p, which expects "(nil)". [akpm@linux-foundation.org: check for IRQ context when !kptr_restrict, save an indent level, s/WARN/WARN_ONCE/] [akpm@linux-foundation.org: coding-style fixup] [randy.dunlap@oracle.com: fix kernel/sysctl.c warning] Signed-off-by: Dan Rosenberg <drosenberg@vsecurity.com> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: James Morris <jmorris@namei.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Thomas Graf <tgraf@infradead.org> Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Kees Cook <kees.cook@canonical.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: David S. Miller <davem@davemloft.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Eric Paris <eparis@parisplace.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-13 00:59:41 +00:00
#include <linux/printk.h>
#include <linux/proc_fs.h>
V3 file capabilities: alter behavior of cap_setpcap The non-filesystem capability meaning of CAP_SETPCAP is that a process, p1, can change the capabilities of another process, p2. This is not the meaning that was intended for this capability at all, and this implementation came about purely because, without filesystem capabilities, there was no way to use capabilities without one process bestowing them on another. Since we now have a filesystem support for capabilities we can fix the implementation of CAP_SETPCAP. The most significant thing about this change is that, with it in effect, no process can set the capabilities of another process. The capabilities of a program are set via the capability convolution rules: pI(post-exec) = pI(pre-exec) pP(post-exec) = (X(aka cap_bset) & fP) | (pI(post-exec) & fI) pE(post-exec) = fE ? pP(post-exec) : 0 at exec() time. As such, the only influence the pre-exec() program can have on the post-exec() program's capabilities are through the pI capability set. The correct implementation for CAP_SETPCAP (and that enabled by this patch) is that it can be used to add extra pI capabilities to the current process - to be picked up by subsequent exec()s when the above convolution rules are applied. Here is how it works: Let's say we have a process, p. It has capability sets, pE, pP and pI. Generally, p, can change the value of its own pI to pI' where (pI' & ~pI) & ~pP = 0. That is, the only new things in pI' that were not present in pI need to be present in pP. The role of CAP_SETPCAP is basically to permit changes to pI beyond the above: if (pE & CAP_SETPCAP) { pI' = anything; /* ie., even (pI' & ~pI) & ~pP != 0 */ } This capability is useful for things like login, which (say, via pam_cap) might want to raise certain inheritable capabilities for use by the children of the logged-in user's shell, but those capabilities are not useful to or needed by the login program itself. One such use might be to limit who can run ping. You set the capabilities of the 'ping' program to be "= cap_net_raw+i", and then only shells that have (pI & CAP_NET_RAW) will be able to run it. Without CAP_SETPCAP implemented as described above, login(pam_cap) would have to also have (pP & CAP_NET_RAW) in order to raise this capability and pass it on through the inheritable set. Signed-off-by: Andrew Morgan <morgan@kernel.org> Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Casey Schaufler <casey@schaufler-ca.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-18 10:05:59 +00:00
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/kmemcheck.h>
sysctl: suppress kmemleak messages register_sysctl_table() is a strange function, as it makes internal allocations (a header) to register a sysctl_table. This header is a handle to the table that is created, and can be used to unregister the table. But if the table is permanent and never unregistered, the header acts the same as a static variable. Unfortunately, this allocation of memory that is never expected to be freed fools kmemleak in thinking that we have leaked memory. For those sysctl tables that are never unregistered, and have no pointer referencing them, kmemleak will think that these are memory leaks: unreferenced object 0xffff880079fb9d40 (size 192): comm "swapper/0", pid 0, jiffies 4294667316 (age 12614.152s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8146b590>] kmemleak_alloc+0x73/0x98 [<ffffffff8110a935>] kmemleak_alloc_recursive.constprop.42+0x16/0x18 [<ffffffff8110b852>] __kmalloc+0x107/0x153 [<ffffffff8116fa72>] kzalloc.constprop.8+0xe/0x10 [<ffffffff811703c9>] __register_sysctl_paths+0xe1/0x160 [<ffffffff81170463>] register_sysctl_paths+0x1b/0x1d [<ffffffff8117047d>] register_sysctl_table+0x18/0x1a [<ffffffff81afb0a1>] sysctl_init+0x10/0x14 [<ffffffff81b05a6f>] proc_sys_init+0x2f/0x31 [<ffffffff81b0584c>] proc_root_init+0xa5/0xa7 [<ffffffff81ae5b7e>] start_kernel+0x3d0/0x40a [<ffffffff81ae52a7>] x86_64_start_reservations+0xae/0xb2 [<ffffffff81ae53ad>] x86_64_start_kernel+0x102/0x111 [<ffffffffffffffff>] 0xffffffffffffffff The sysctl_base_table used by sysctl itself is one such instance that registers the table to never be unregistered. Use kmemleak_not_leak() to suppress the kmemleak false positive. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-30 21:42:48 +00:00
#include <linux/kmemleak.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kobject.h>
#include <linux/net.h>
#include <linux/sysrq.h>
#include <linux/highuid.h>
#include <linux/writeback.h>
#include <linux/ratelimit.h>
#include <linux/compaction.h>
#include <linux/hugetlb.h>
#include <linux/initrd.h>
#include <linux/key.h>
#include <linux/times.h>
#include <linux/limits.h>
#include <linux/dcache.h>
#include <linux/dnotify.h>
#include <linux/syscalls.h>
#include <linux/vmstat.h>
#include <linux/nfs_fs.h>
#include <linux/acpi.h>
#include <linux/reboot.h>
#include <linux/ftrace.h>
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
#include <linux/perf_event.h>
#include <linux/kprobes.h>
#include <linux/pipe_fs_i.h>
#include <linux/oom.h>
#include <linux/kmod.h>
#include <linux/capability.h>
#include <linux/binfmts.h>
#include <linux/sched/sysctl.h>
kexec: add sysctl to disable kexec_load For general-purpose (i.e. distro) kernel builds it makes sense to build with CONFIG_KEXEC to allow end users to choose what kind of things they want to do with kexec. However, in the face of trying to lock down a system with such a kernel, there needs to be a way to disable kexec_load (much like module loading can be disabled). Without this, it is too easy for the root user to modify kernel memory even when CONFIG_STRICT_DEVMEM and modules_disabled are set. With this change, it is still possible to load an image for use later, then disable kexec_load so the image (or lack of image) can't be altered. The intention is for using this in environments where "perfect" enforcement is hard. Without a verified boot, along with verified modules, and along with verified kexec, this is trying to give a system a better chance to defend itself (or at least grow the window of discoverability) against attack in the face of a privilege escalation. In my mind, I consider several boot scenarios: 1) Verified boot of read-only verified root fs loading fd-based verification of kexec images. 2) Secure boot of writable root fs loading signed kexec images. 3) Regular boot loading kexec (e.g. kcrash) image early and locking it. 4) Regular boot with no control of kexec image at all. 1 and 2 don't exist yet, but will soon once the verified kexec series has landed. 4 is the state of things now. The gap between 2 and 4 is too large, so this change creates scenario 3, a middle-ground above 4 when 2 and 1 are not possible for a system. Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Rik van Riel <riel@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-23 23:55:59 +00:00
#include <linux/kexec.h>
bpf: enable non-root eBPF programs In order to let unprivileged users load and execute eBPF programs teach verifier to prevent pointer leaks. Verifier will prevent - any arithmetic on pointers (except R10+Imm which is used to compute stack addresses) - comparison of pointers (except if (map_value_ptr == 0) ... ) - passing pointers to helper functions - indirectly passing pointers in stack to helper functions - returning pointer from bpf program - storing pointers into ctx or maps Spill/fill of pointers into stack is allowed, but mangling of pointers stored in the stack or reading them byte by byte is not. Within bpf programs the pointers do exist, since programs need to be able to access maps, pass skb pointer to LD_ABS insns, etc but programs cannot pass such pointer values to the outside or obfuscate them. Only allow BPF_PROG_TYPE_SOCKET_FILTER unprivileged programs, so that socket filters (tcpdump), af_packet (quic acceleration) and future kcm can use it. tracing and tc cls/act program types still require root permissions, since tracing actually needs to be able to see all kernel pointers and tc is for root only. For example, the following unprivileged socket filter program is allowed: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += skb->len; return 0; } but the following program is not: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += (u64) skb; return 0; } since it would leak the kernel address into the map. Unprivileged socket filter bpf programs have access to the following helper functions: - map lookup/update/delete (but they cannot store kernel pointers into them) - get_random (it's already exposed to unprivileged user space) - get_smp_processor_id - tail_call into another socket filter program - ktime_get_ns The feature is controlled by sysctl kernel.unprivileged_bpf_disabled. This toggle defaults to off (0), but can be set true (1). Once true, bpf programs and maps cannot be accessed from unprivileged process, and the toggle cannot be set back to false. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-08 05:23:21 +00:00
#include <linux/bpf.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
#ifdef CONFIG_X86
#include <asm/nmi.h>
#include <asm/stacktrace.h>
#include <asm/io.h>
#endif
#ifdef CONFIG_SPARC
#include <asm/setup.h>
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
#include <linux/acct.h>
#endif
#ifdef CONFIG_RT_MUTEXES
#include <linux/rtmutex.h>
#endif
#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT)
#include <linux/lockdep.h>
#endif
#ifdef CONFIG_CHR_DEV_SG
#include <scsi/sg.h>
#endif
lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Eric Paris <eparis@redhat.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2010-05-07 21:11:44 +00:00
#ifdef CONFIG_LOCKUP_DETECTOR
#include <linux/nmi.h>
#endif
#if defined(CONFIG_SYSCTL)
/* External variables not in a header file. */
[PATCH] setuid core dump Add a new `suid_dumpable' sysctl: This value can be used to query and set the core dump mode for setuid or otherwise protected/tainted binaries. The modes are 0 - (default) - traditional behaviour. Any process which has changed privilege levels or is execute only will not be dumped 1 - (debug) - all processes dump core when possible. The core dump is owned by the current user and no security is applied. This is intended for system debugging situations only. Ptrace is unchecked. 2 - (suidsafe) - any binary which normally would not be dumped is dumped readable by root only. This allows the end user to remove such a dump but not access it directly. For security reasons core dumps in this mode will not overwrite one another or other files. This mode is appropriate when adminstrators are attempting to debug problems in a normal environment. (akpm: > > +EXPORT_SYMBOL(suid_dumpable); > > EXPORT_SYMBOL_GPL? No problem to me. > > if (current->euid == current->uid && current->egid == current->gid) > > current->mm->dumpable = 1; > > Should this be SUID_DUMP_USER? Actually the feedback I had from last time was that the SUID_ defines should go because its clearer to follow the numbers. They can go everywhere (and there are lots of places where dumpable is tested/used as a bool in untouched code) > Maybe this should be renamed to `dump_policy' or something. Doing that > would help us catch any code which isn't using the #defines, too. Fair comment. The patch was designed to be easy to maintain for Red Hat rather than for merging. Changing that field would create a gigantic diff because it is used all over the place. ) Signed-off-by: Alan Cox <alan@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 07:09:43 +00:00
extern int suid_dumpable;
#ifdef CONFIG_COREDUMP
extern int core_uses_pid;
extern char core_pattern[];
extern unsigned int core_pipe_limit;
#endif
extern int pid_max;
extern int pid_max_min, pid_max_max;
extern int percpu_pagelist_fraction;
extern int compat_log;
extern int latencytop_enabled;
extern int sysctl_nr_open_min, sysctl_nr_open_max;
#ifndef CONFIG_MMU
extern int sysctl_nr_trim_pages;
#endif
/* Constants used for minimum and maximum */
#ifdef CONFIG_LOCKUP_DETECTOR
static int sixty = 60;
#endif
static int __maybe_unused neg_one = -1;
static int zero;
static int __maybe_unused one = 1;
static int __maybe_unused two = 2;
2014-04-03 21:48:19 +00:00
static int __maybe_unused four = 4;
static unsigned long one_ul = 1;
static int one_hundred = 100;
#ifdef CONFIG_PRINTK
static int ten_thousand = 10000;
#endif
mm: prevent divide error for small values of vm_dirty_bytes Avoid setting less than two pages for vm_dirty_bytes: this is necessary to avoid potential division by 0 (like the following) in get_dirty_limits(). [ 49.951610] divide error: 0000 [#1] PREEMPT SMP [ 49.952195] last sysfs file: /sys/devices/pci0000:00/0000:00:01.1/host0/target0:0:0/0:0:0:0/block/sda/uevent [ 49.952195] CPU 1 [ 49.952195] Modules linked in: pcspkr [ 49.952195] Pid: 3064, comm: dd Not tainted 2.6.30-rc3 #1 [ 49.952195] RIP: 0010:[<ffffffff802d39a9>] [<ffffffff802d39a9>] get_dirty_limits+0xe9/0x2c0 [ 49.952195] RSP: 0018:ffff88001de03a98 EFLAGS: 00010202 [ 49.952195] RAX: 00000000000000c0 RBX: ffff88001de03b80 RCX: 28f5c28f5c28f5c3 [ 49.952195] RDX: 0000000000000000 RSI: 00000000000000c0 RDI: 0000000000000000 [ 49.952195] RBP: ffff88001de03ae8 R08: 0000000000000000 R09: 0000000000000000 [ 49.952195] R10: ffff88001ddda9a0 R11: 0000000000000001 R12: 0000000000000001 [ 49.952195] R13: ffff88001fbc8218 R14: ffff88001de03b70 R15: ffff88001de03b78 [ 49.952195] FS: 00007fe9a435b6f0(0000) GS:ffff8800025d9000(0000) knlGS:0000000000000000 [ 49.952195] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 49.952195] CR2: 00007fe9a39ab000 CR3: 000000001de38000 CR4: 00000000000006e0 [ 49.952195] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 49.952195] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 49.952195] Process dd (pid: 3064, threadinfo ffff88001de02000, task ffff88001ddda250) [ 49.952195] Stack: [ 49.952195] ffff88001fa0de00 ffff88001f2dbd70 ffff88001f9fe800 000080b900000000 [ 49.952195] 00000000000000c0 ffff8800027a6100 0000000000000400 ffff88001fbc8218 [ 49.952195] 0000000000000000 0000000000000600 ffff88001de03bb8 ffffffff802d3ed7 [ 49.952195] Call Trace: [ 49.952195] [<ffffffff802d3ed7>] balance_dirty_pages_ratelimited_nr+0x1d7/0x3f0 [ 49.952195] [<ffffffff80368f8e>] ? ext3_writeback_write_end+0x9e/0x120 [ 49.952195] [<ffffffff802cc7df>] generic_file_buffered_write+0x12f/0x330 [ 49.952195] [<ffffffff802cce8d>] __generic_file_aio_write_nolock+0x26d/0x460 [ 49.952195] [<ffffffff802cda32>] ? generic_file_aio_write+0x52/0xd0 [ 49.952195] [<ffffffff802cda49>] generic_file_aio_write+0x69/0xd0 [ 49.952195] [<ffffffff80365fa6>] ext3_file_write+0x26/0xc0 [ 49.952195] [<ffffffff803034d1>] do_sync_write+0xf1/0x140 [ 49.952195] [<ffffffff80290d1a>] ? get_lock_stats+0x2a/0x60 [ 49.952195] [<ffffffff80280730>] ? autoremove_wake_function+0x0/0x40 [ 49.952195] [<ffffffff8030411b>] vfs_write+0xcb/0x190 [ 49.952195] [<ffffffff803042d0>] sys_write+0x50/0x90 [ 49.952195] [<ffffffff8022ff6b>] system_call_fastpath+0x16/0x1b [ 49.952195] Code: 00 00 00 2b 05 09 1c 17 01 48 89 c6 49 0f af f4 48 c1 ee 02 48 89 f0 48 f7 e1 48 89 d6 31 d2 48 c1 ee 02 48 0f af 75 d0 48 89 f0 <48> f7 f7 41 8b 95 ac 01 00 00 48 89 c7 49 0f af d4 48 c1 ea 02 [ 49.952195] RIP [<ffffffff802d39a9>] get_dirty_limits+0xe9/0x2c0 [ 49.952195] RSP <ffff88001de03a98> [ 50.096523] ---[ end trace 008d7aa02f244d7b ]--- Signed-off-by: Andrea Righi <righi.andrea@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-30 22:08:57 +00:00
/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
static int maxolduid = 65535;
static int minolduid;
static int ngroups_max = NGROUPS_MAX;
static const int cap_last_cap = CAP_LAST_CAP;
/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */
#ifdef CONFIG_DETECT_HUNG_TASK
static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
#endif
#ifdef CONFIG_INOTIFY_USER
#include <linux/inotify.h>
#endif
#ifdef CONFIG_SPARC
#endif
#ifdef __hppa__
extern int pwrsw_enabled;
#endif
#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
extern int unaligned_enabled;
#endif
#ifdef CONFIG_IA64
extern int unaligned_dump_stack;
#endif
#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
extern int no_unaligned_warning;
#endif
#ifdef CONFIG_PROC_SYSCTL
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
#define SYSCTL_WRITES_LEGACY -1
#define SYSCTL_WRITES_WARN 0
#define SYSCTL_WRITES_STRICT 1
static int sysctl_writes_strict = SYSCTL_WRITES_STRICT;
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
static int proc_taint(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
#ifdef CONFIG_PRINTK
static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#ifdef CONFIG_COREDUMP
static int proc_dostring_coredump(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
#ifdef CONFIG_MAGIC_SYSRQ
/* Note: sysrq code uses it's own private copy */
static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE;
static int sysrq_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int error;
error = proc_dointvec(table, write, buffer, lenp, ppos);
if (error)
return error;
if (write)
sysrq_toggle_support(__sysrq_enabled);
return 0;
}
#endif
static struct ctl_table kern_table[];
static struct ctl_table vm_table[];
static struct ctl_table fs_table[];
static struct ctl_table debug_table[];
static struct ctl_table dev_table[];
extern struct ctl_table random_table[];
epoll: introduce resource usage limits It has been thought that the per-user file descriptors limit would also limit the resources that a normal user can request via the epoll interface. Vegard Nossum reported a very simple program (a modified version attached) that can make a normal user to request a pretty large amount of kernel memory, well within the its maximum number of fds. To solve such problem, default limits are now imposed, and /proc based configuration has been introduced. A new directory has been created, named /proc/sys/fs/epoll/ and inside there, there are two configuration points: max_user_instances = Maximum number of devices - per user max_user_watches = Maximum number of "watched" fds - per user The current default for "max_user_watches" limits the memory used by epoll to store "watches", to 1/32 of the amount of the low RAM. As example, a 256MB 32bit machine, will have "max_user_watches" set to roughly 90000. That should be enough to not break existing heavy epoll users. The default value for "max_user_instances" is set to 128, that should be enough too. This also changes the userspace, because a new error code can now come out from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already listed, so that should be ok. [akpm@linux-foundation.org: use get_current_user()] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: <stable@kernel.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Reported-by: Vegard Nossum <vegardno@ifi.uio.no> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 21:13:55 +00:00
#ifdef CONFIG_EPOLL
extern struct ctl_table epoll_table[];
#endif
#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
int sysctl_legacy_va_layout;
#endif
/* The default sysctl tables: */
static struct ctl_table sysctl_base_table[] = {
{
.procname = "kernel",
.mode = 0555,
.child = kern_table,
},
{
.procname = "vm",
.mode = 0555,
.child = vm_table,
},
{
.procname = "fs",
.mode = 0555,
.child = fs_table,
},
{
.procname = "debug",
.mode = 0555,
.child = debug_table,
},
{
.procname = "dev",
.mode = 0555,
.child = dev_table,
},
{ }
};
#ifdef CONFIG_SCHED_DEBUG
static int min_sched_granularity_ns = 100000; /* 100 usecs */
static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */
static int min_wakeup_granularity_ns; /* 0 usecs */
static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */
#ifdef CONFIG_SMP
static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
#endif /* CONFIG_SMP */
#endif /* CONFIG_SCHED_DEBUG */
#ifdef CONFIG_COMPACTION
static int min_extfrag_threshold;
static int max_extfrag_threshold = 1000;
#endif
static struct ctl_table kern_table[] = {
{
.procname = "sched_child_runs_first",
.data = &sysctl_sched_child_runs_first,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_SCHED_DEBUG
{
.procname = "sched_min_granularity_ns",
.data = &sysctl_sched_min_granularity,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = sched_proc_update_handler,
.extra1 = &min_sched_granularity_ns,
.extra2 = &max_sched_granularity_ns,
},
{
.procname = "sched_latency_ns",
.data = &sysctl_sched_latency,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = sched_proc_update_handler,
.extra1 = &min_sched_granularity_ns,
.extra2 = &max_sched_granularity_ns,
},
{
.procname = "sched_wakeup_granularity_ns",
.data = &sysctl_sched_wakeup_granularity,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = sched_proc_update_handler,
.extra1 = &min_wakeup_granularity_ns,
.extra2 = &max_wakeup_granularity_ns,
},
#ifdef CONFIG_SMP
{
.procname = "sched_tunable_scaling",
.data = &sysctl_sched_tunable_scaling,
.maxlen = sizeof(enum sched_tunable_scaling),
.mode = 0644,
.proc_handler = sched_proc_update_handler,
.extra1 = &min_sched_tunable_scaling,
.extra2 = &max_sched_tunable_scaling,
},
{
.procname = "sched_migration_cost_ns",
.data = &sysctl_sched_migration_cost,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "sched_nr_migrate",
.data = &sysctl_sched_nr_migrate,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "sched_time_avg_ms",
.data = &sysctl_sched_time_avg,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "sched_shares_window_ns",
.data = &sysctl_sched_shares_window,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif /* CONFIG_SMP */
#ifdef CONFIG_NUMA_BALANCING
mm: sched: numa: Implement slow start for working set sampling Add a 1 second delay before starting to scan the working set of a task and starting to balance it amongst nodes. [ note that before the constant per task WSS sampling rate patch the initial scan would happen much later still, in effect that patch caused this regression. ] The theory is that short-run tasks benefit very little from NUMA placement: they come and go, and they better stick to the node they were started on. As tasks mature and rebalance to other CPUs and nodes, so does their NUMA placement have to change and so does it start to matter more and more. In practice this change fixes an observable kbuild regression: # [ a perf stat --null --repeat 10 test of ten bzImage builds to /dev/shm ] !NUMA: 45.291088843 seconds time elapsed ( +- 0.40% ) 45.154231752 seconds time elapsed ( +- 0.36% ) +NUMA, no slow start: 46.172308123 seconds time elapsed ( +- 0.30% ) 46.343168745 seconds time elapsed ( +- 0.25% ) +NUMA, 1 sec slow start: 45.224189155 seconds time elapsed ( +- 0.25% ) 45.160866532 seconds time elapsed ( +- 0.17% ) and it also fixes an observable perf bench (hackbench) regression: # perf stat --null --repeat 10 perf bench sched messaging -NUMA: -NUMA: 0.246225691 seconds time elapsed ( +- 1.31% ) +NUMA no slow start: 0.252620063 seconds time elapsed ( +- 1.13% ) +NUMA 1sec delay: 0.248076230 seconds time elapsed ( +- 1.35% ) The implementation is simple and straightforward, most of the patch deals with adding the /proc/sys/kernel/numa_balancing_scan_delay_ms tunable knob. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote the changelog, ran measurements, tuned the default. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:47 +00:00
{
.procname = "numa_balancing_scan_delay_ms",
.data = &sysctl_numa_balancing_scan_delay,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "numa_balancing_scan_period_min_ms",
.data = &sysctl_numa_balancing_scan_period_min,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "numa_balancing_scan_period_max_ms",
.data = &sysctl_numa_balancing_scan_period_max,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
{
.procname = "numa_balancing_scan_size_mb",
.data = &sysctl_numa_balancing_scan_size,
.maxlen = sizeof(unsigned int),
.mode = 0644,
sched/fair: Fix division by zero sysctl_numa_balancing_scan_size File /proc/sys/kernel/numa_balancing_scan_size_mb allows writing of zero. This bash command reproduces problem: $ while :; do echo 0 > /proc/sys/kernel/numa_balancing_scan_size_mb; \ echo 256 > /proc/sys/kernel/numa_balancing_scan_size_mb; done divide error: 0000 [#1] SMP Modules linked in: CPU: 0 PID: 24112 Comm: bash Not tainted 3.17.0+ #8 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88013c852600 ti: ffff880037a68000 task.ti: ffff880037a68000 RIP: 0010:[<ffffffff81074191>] [<ffffffff81074191>] task_scan_min+0x21/0x50 RSP: 0000:ffff880037a6bce0 EFLAGS: 00010246 RAX: 0000000000000a00 RBX: 00000000000003e8 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88013c852600 RBP: ffff880037a6bcf0 R08: 0000000000000001 R09: 0000000000015c90 R10: ffff880239bf6c00 R11: 0000000000000016 R12: 0000000000003fff R13: ffff88013c852600 R14: ffffea0008d1b000 R15: 0000000000000003 FS: 00007f12bb048700(0000) GS:ffff88007da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000001505678 CR3: 0000000234770000 CR4: 00000000000006f0 Stack: ffff88013c852600 0000000000003fff ffff880037a6bd18 ffffffff810741d1 ffff88013c852600 0000000000003fff 000000000002bfff ffff880037a6bda8 ffffffff81077ef7 ffffea0008a56d40 0000000000000001 0000000000000001 Call Trace: [<ffffffff810741d1>] task_scan_max+0x11/0x40 [<ffffffff81077ef7>] task_numa_fault+0x1f7/0xae0 [<ffffffff8115a896>] ? migrate_misplaced_page+0x276/0x300 [<ffffffff81134a4d>] handle_mm_fault+0x62d/0xba0 [<ffffffff8103e2f1>] __do_page_fault+0x191/0x510 [<ffffffff81030122>] ? native_smp_send_reschedule+0x42/0x60 [<ffffffff8106dc00>] ? check_preempt_curr+0x80/0xa0 [<ffffffff8107092c>] ? wake_up_new_task+0x11c/0x1a0 [<ffffffff8104887d>] ? do_fork+0x14d/0x340 [<ffffffff811799bb>] ? get_unused_fd_flags+0x2b/0x30 [<ffffffff811799df>] ? __fd_install+0x1f/0x60 [<ffffffff8103e67c>] do_page_fault+0xc/0x10 [<ffffffff8150d322>] page_fault+0x22/0x30 RIP [<ffffffff81074191>] task_scan_min+0x21/0x50 RSP <ffff880037a6bce0> ---[ end trace 9a826d16936c04de ]--- Also fix race in task_scan_min (it depends on compiler behaviour). Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dario Faggioli <raistlin@linux.it> Cc: David Rientjes <rientjes@google.com> Cc: Jens Axboe <axboe@fb.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Link: http://lkml.kernel.org/r/1413455977.24793.78.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-16 10:39:37 +00:00
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
},
{
.procname = "numa_balancing",
.data = NULL, /* filled in by handler */
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = sysctl_numa_balancing,
.extra1 = &zero,
.extra2 = &one,
},
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
{
.procname = "sched_rt_period_us",
.data = &sysctl_sched_rt_period,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = sched_rt_handler,
},
{
.procname = "sched_rt_runtime_us",
.data = &sysctl_sched_rt_runtime,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = sched_rt_handler,
},
{
.procname = "sched_rr_timeslice_ms",
.data = &sched_rr_timeslice,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = sched_rr_handler,
},
sched: Add 'autogroup' scheduling feature: automated per session task groups A recurring complaint from CFS users is that parallel kbuild has a negative impact on desktop interactivity. This patch implements an idea from Linus, to automatically create task groups. Currently, only per session autogroups are implemented, but the patch leaves the way open for enhancement. Implementation: each task's signal struct contains an inherited pointer to a refcounted autogroup struct containing a task group pointer, the default for all tasks pointing to the init_task_group. When a task calls setsid(), a new task group is created, the process is moved into the new task group, and a reference to the preveious task group is dropped. Child processes inherit this task group thereafter, and increase it's refcount. When the last thread of a process exits, the process's reference is dropped, such that when the last process referencing an autogroup exits, the autogroup is destroyed. At runqueue selection time, IFF a task has no cgroup assignment, its current autogroup is used. Autogroup bandwidth is controllable via setting it's nice level through the proc filesystem: cat /proc/<pid>/autogroup Displays the task's group and the group's nice level. echo <nice level> > /proc/<pid>/autogroup Sets the task group's shares to the weight of nice <level> task. Setting nice level is rate limited for !admin users due to the abuse risk of task group locking. The feature is enabled from boot by default if CONFIG_SCHED_AUTOGROUP=y is selected, but can be disabled via the boot option noautogroup, and can also be turned on/off on the fly via: echo [01] > /proc/sys/kernel/sched_autogroup_enabled ... which will automatically move tasks to/from the root task group. Signed-off-by: Mike Galbraith <efault@gmx.de> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Paul Turner <pjt@google.com> Cc: Oleg Nesterov <oleg@redhat.com> [ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> LKML-Reference: <1290281700.28711.9.camel@maggy.simson.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-30 13:18:03 +00:00
#ifdef CONFIG_SCHED_AUTOGROUP
{
.procname = "sched_autogroup_enabled",
.data = &sysctl_sched_autogroup_enabled,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
sched: Add 'autogroup' scheduling feature: automated per session task groups A recurring complaint from CFS users is that parallel kbuild has a negative impact on desktop interactivity. This patch implements an idea from Linus, to automatically create task groups. Currently, only per session autogroups are implemented, but the patch leaves the way open for enhancement. Implementation: each task's signal struct contains an inherited pointer to a refcounted autogroup struct containing a task group pointer, the default for all tasks pointing to the init_task_group. When a task calls setsid(), a new task group is created, the process is moved into the new task group, and a reference to the preveious task group is dropped. Child processes inherit this task group thereafter, and increase it's refcount. When the last thread of a process exits, the process's reference is dropped, such that when the last process referencing an autogroup exits, the autogroup is destroyed. At runqueue selection time, IFF a task has no cgroup assignment, its current autogroup is used. Autogroup bandwidth is controllable via setting it's nice level through the proc filesystem: cat /proc/<pid>/autogroup Displays the task's group and the group's nice level. echo <nice level> > /proc/<pid>/autogroup Sets the task group's shares to the weight of nice <level> task. Setting nice level is rate limited for !admin users due to the abuse risk of task group locking. The feature is enabled from boot by default if CONFIG_SCHED_AUTOGROUP=y is selected, but can be disabled via the boot option noautogroup, and can also be turned on/off on the fly via: echo [01] > /proc/sys/kernel/sched_autogroup_enabled ... which will automatically move tasks to/from the root task group. Signed-off-by: Mike Galbraith <efault@gmx.de> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Paul Turner <pjt@google.com> Cc: Oleg Nesterov <oleg@redhat.com> [ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> LKML-Reference: <1290281700.28711.9.camel@maggy.simson.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-30 13:18:03 +00:00
.extra1 = &zero,
.extra2 = &one,
},
#endif
#ifdef CONFIG_CFS_BANDWIDTH
{
.procname = "sched_cfs_bandwidth_slice_us",
.data = &sysctl_sched_cfs_bandwidth_slice,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
},
#endif
lockstat: core infrastructure Introduce the core lock statistics code. Lock statistics provides lock wait-time and hold-time (as well as the count of corresponding contention and acquisitions events). Also, the first few call-sites that encounter contention are tracked. Lock wait-time is the time spent waiting on the lock. This provides insight into the locking scheme, that is, a heavily contended lock is indicative of a too coarse locking scheme. Lock hold-time is the duration the lock was held, this provides a reference for the wait-time numbers, so they can be put into perspective. 1) lock 2) ... do stuff .. unlock 3) The time between 1 and 2 is the wait-time. The time between 2 and 3 is the hold-time. The lockdep held-lock tracking code is reused, because it already collects locks into meaningful groups (classes), and because it is an existing infrastructure for lock instrumentation. Currently lockdep tracks lock acquisition with two hooks: lock() lock_acquire() _lock() ... code protected by lock ... unlock() lock_release() _unlock() We need to extend this with two more hooks, in order to measure contention. lock_contended() - used to measure contention events lock_acquired() - completion of the contention These are then placed the following way: lock() lock_acquire() if (!_try_lock()) lock_contended() _lock() lock_acquired() ... do locked stuff ... unlock() lock_release() _unlock() (Note: the try_lock() 'trick' is used to avoid instrumenting all platform dependent lock primitive implementations.) It is also possible to toggle the two lockdep features at runtime using: /proc/sys/kernel/prove_locking /proc/sys/kernel/lock_stat (esp. turning off the O(n^2) prove_locking functionaliy can help) [akpm@linux-foundation.org: build fixes] [akpm@linux-foundation.org: nuke unneeded ifdefs] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:48:56 +00:00
#ifdef CONFIG_PROVE_LOCKING
{
.procname = "prove_locking",
.data = &prove_locking,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
lockstat: core infrastructure Introduce the core lock statistics code. Lock statistics provides lock wait-time and hold-time (as well as the count of corresponding contention and acquisitions events). Also, the first few call-sites that encounter contention are tracked. Lock wait-time is the time spent waiting on the lock. This provides insight into the locking scheme, that is, a heavily contended lock is indicative of a too coarse locking scheme. Lock hold-time is the duration the lock was held, this provides a reference for the wait-time numbers, so they can be put into perspective. 1) lock 2) ... do stuff .. unlock 3) The time between 1 and 2 is the wait-time. The time between 2 and 3 is the hold-time. The lockdep held-lock tracking code is reused, because it already collects locks into meaningful groups (classes), and because it is an existing infrastructure for lock instrumentation. Currently lockdep tracks lock acquisition with two hooks: lock() lock_acquire() _lock() ... code protected by lock ... unlock() lock_release() _unlock() We need to extend this with two more hooks, in order to measure contention. lock_contended() - used to measure contention events lock_acquired() - completion of the contention These are then placed the following way: lock() lock_acquire() if (!_try_lock()) lock_contended() _lock() lock_acquired() ... do locked stuff ... unlock() lock_release() _unlock() (Note: the try_lock() 'trick' is used to avoid instrumenting all platform dependent lock primitive implementations.) It is also possible to toggle the two lockdep features at runtime using: /proc/sys/kernel/prove_locking /proc/sys/kernel/lock_stat (esp. turning off the O(n^2) prove_locking functionaliy can help) [akpm@linux-foundation.org: build fixes] [akpm@linux-foundation.org: nuke unneeded ifdefs] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:48:56 +00:00
},
#endif
#ifdef CONFIG_LOCK_STAT
{
.procname = "lock_stat",
.data = &lock_stat,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
lockstat: core infrastructure Introduce the core lock statistics code. Lock statistics provides lock wait-time and hold-time (as well as the count of corresponding contention and acquisitions events). Also, the first few call-sites that encounter contention are tracked. Lock wait-time is the time spent waiting on the lock. This provides insight into the locking scheme, that is, a heavily contended lock is indicative of a too coarse locking scheme. Lock hold-time is the duration the lock was held, this provides a reference for the wait-time numbers, so they can be put into perspective. 1) lock 2) ... do stuff .. unlock 3) The time between 1 and 2 is the wait-time. The time between 2 and 3 is the hold-time. The lockdep held-lock tracking code is reused, because it already collects locks into meaningful groups (classes), and because it is an existing infrastructure for lock instrumentation. Currently lockdep tracks lock acquisition with two hooks: lock() lock_acquire() _lock() ... code protected by lock ... unlock() lock_release() _unlock() We need to extend this with two more hooks, in order to measure contention. lock_contended() - used to measure contention events lock_acquired() - completion of the contention These are then placed the following way: lock() lock_acquire() if (!_try_lock()) lock_contended() _lock() lock_acquired() ... do locked stuff ... unlock() lock_release() _unlock() (Note: the try_lock() 'trick' is used to avoid instrumenting all platform dependent lock primitive implementations.) It is also possible to toggle the two lockdep features at runtime using: /proc/sys/kernel/prove_locking /proc/sys/kernel/lock_stat (esp. turning off the O(n^2) prove_locking functionaliy can help) [akpm@linux-foundation.org: build fixes] [akpm@linux-foundation.org: nuke unneeded ifdefs] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:48:56 +00:00
},
#endif
{
.procname = "panic",
.data = &panic_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_COREDUMP
{
.procname = "core_uses_pid",
.data = &core_uses_pid,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "core_pattern",
.data = core_pattern,
.maxlen = CORENAME_MAX_SIZE,
.mode = 0644,
.proc_handler = proc_dostring_coredump,
},
{
.procname = "core_pipe_limit",
.data = &core_pipe_limit,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_PROC_SYSCTL
{
.procname = "tainted",
.maxlen = sizeof(long),
.mode = 0644,
.proc_handler = proc_taint,
},
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
{
.procname = "sysctl_writes_strict",
.data = &sysctl_writes_strict,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &neg_one,
.extra2 = &one,
},
#endif
#ifdef CONFIG_LATENCYTOP
{
.procname = "latencytop",
.data = &latencytop_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_BLK_DEV_INITRD
{
.procname = "real-root-dev",
.data = &real_root_dev,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
{
.procname = "print-fatal-signals",
.data = &print_fatal_signals,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_SPARC
{
.procname = "reboot-cmd",
.data = reboot_command,
.maxlen = 256,
.mode = 0644,
.proc_handler = proc_dostring,
},
{
.procname = "stop-a",
.data = &stop_a_enabled,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "scons-poweroff",
.data = &scons_pwroff,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_SPARC64
{
.procname = "tsb-ratio",
.data = &sysctl_tsb_ratio,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef __hppa__
{
.procname = "soft-power",
.data = &pwrsw_enabled,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
{
.procname = "unaligned-trap",
.data = &unaligned_enabled,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
{
.procname = "ctrl-alt-del",
.data = &C_A_D,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_FUNCTION_TRACER
{
.procname = "ftrace_enabled",
.data = &ftrace_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = ftrace_enable_sysctl,
},
#endif
#ifdef CONFIG_STACK_TRACER
{
.procname = "stack_tracer_enabled",
.data = &stack_tracer_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = stack_trace_sysctl,
},
#endif
#ifdef CONFIG_TRACING
{
.procname = "ftrace_dump_on_oops",
.data = &ftrace_dump_on_oops,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "traceoff_on_warning",
.data = &__disable_trace_on_warning,
.maxlen = sizeof(__disable_trace_on_warning),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tracepoint_printk",
.data = &tracepoint_printk,
.maxlen = sizeof(tracepoint_printk),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
2015-09-09 22:38:55 +00:00
#ifdef CONFIG_KEXEC_CORE
kexec: add sysctl to disable kexec_load For general-purpose (i.e. distro) kernel builds it makes sense to build with CONFIG_KEXEC to allow end users to choose what kind of things they want to do with kexec. However, in the face of trying to lock down a system with such a kernel, there needs to be a way to disable kexec_load (much like module loading can be disabled). Without this, it is too easy for the root user to modify kernel memory even when CONFIG_STRICT_DEVMEM and modules_disabled are set. With this change, it is still possible to load an image for use later, then disable kexec_load so the image (or lack of image) can't be altered. The intention is for using this in environments where "perfect" enforcement is hard. Without a verified boot, along with verified modules, and along with verified kexec, this is trying to give a system a better chance to defend itself (or at least grow the window of discoverability) against attack in the face of a privilege escalation. In my mind, I consider several boot scenarios: 1) Verified boot of read-only verified root fs loading fd-based verification of kexec images. 2) Secure boot of writable root fs loading signed kexec images. 3) Regular boot loading kexec (e.g. kcrash) image early and locking it. 4) Regular boot with no control of kexec image at all. 1 and 2 don't exist yet, but will soon once the verified kexec series has landed. 4 is the state of things now. The gap between 2 and 4 is too large, so this change creates scenario 3, a middle-ground above 4 when 2 and 1 are not possible for a system. Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Rik van Riel <riel@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-23 23:55:59 +00:00
{
.procname = "kexec_load_disabled",
.data = &kexec_load_disabled,
.maxlen = sizeof(int),
.mode = 0644,
/* only handle a transition from default "0" to "1" */
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
.extra2 = &one,
},
#endif
#ifdef CONFIG_MODULES
{
.procname = "modprobe",
.data = &modprobe_path,
.maxlen = KMOD_PATH_LEN,
.mode = 0644,
.proc_handler = proc_dostring,
},
{
.procname = "modules_disabled",
.data = &modules_disabled,
.maxlen = sizeof(int),
.mode = 0644,
/* only handle a transition from default "0" to "1" */
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
.extra2 = &one,
},
#endif
#ifdef CONFIG_UEVENT_HELPER
{
.procname = "hotplug",
.data = &uevent_helper,
.maxlen = UEVENT_HELPER_PATH_LEN,
.mode = 0644,
.proc_handler = proc_dostring,
},
#endif
#ifdef CONFIG_CHR_DEV_SG
{
.procname = "sg-big-buff",
.data = &sg_big_buff,
.maxlen = sizeof (int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
{
.procname = "acct",
.data = &acct_parm,
.maxlen = 3*sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_MAGIC_SYSRQ
{
.procname = "sysrq",
.data = &__sysrq_enabled,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = sysrq_sysctl_handler,
},
#endif
#ifdef CONFIG_PROC_SYSCTL
{
.procname = "cad_pid",
.data = NULL,
.maxlen = sizeof (int),
.mode = 0600,
.proc_handler = proc_do_cad_pid,
},
#endif
{
.procname = "threads-max",
.data = NULL,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = sysctl_max_threads,
},
{
.procname = "random",
.mode = 0555,
.child = random_table,
},
{
.procname = "usermodehelper",
.mode = 0555,
.child = usermodehelper_table,
},
{
.procname = "overflowuid",
.data = &overflowuid,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
{
.procname = "overflowgid",
.data = &overflowgid,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
#ifdef CONFIG_S390
#ifdef CONFIG_MATHEMU
{
.procname = "ieee_emulation_warnings",
.data = &sysctl_ieee_emulation_warnings,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
{
.procname = "userprocess_debug",
.data = &show_unhandled_signals,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
{
.procname = "pid_max",
.data = &pid_max,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &pid_max_min,
.extra2 = &pid_max_max,
},
{
.procname = "panic_on_oops",
.data = &panic_on_oops,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#if defined CONFIG_PRINTK
{
.procname = "printk",
.data = &console_loglevel,
.maxlen = 4*sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "printk_ratelimit",
.data = &printk_ratelimit_state.interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "printk_ratelimit_burst",
.data = &printk_ratelimit_state.burst,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "printk_delay",
.data = &printk_delay_msec,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &ten_thousand,
},
{
.procname = "dmesg_restrict",
.data = &dmesg_restrict,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax_sysadmin,
.extra1 = &zero,
.extra2 = &one,
},
kptr_restrict for hiding kernel pointers from unprivileged users Add the %pK printk format specifier and the /proc/sys/kernel/kptr_restrict sysctl. The %pK format specifier is designed to hide exposed kernel pointers, specifically via /proc interfaces. Exposing these pointers provides an easy target for kernel write vulnerabilities, since they reveal the locations of writable structures containing easily triggerable function pointers. The behavior of %pK depends on the kptr_restrict sysctl. If kptr_restrict is set to 0, no deviation from the standard %p behavior occurs. If kptr_restrict is set to 1, the default, if the current user (intended to be a reader via seq_printf(), etc.) does not have CAP_SYSLOG (currently in the LSM tree), kernel pointers using %pK are printed as 0's. If kptr_restrict is set to 2, kernel pointers using %pK are printed as 0's regardless of privileges. Replacing with 0's was chosen over the default "(null)", which cannot be parsed by userland %p, which expects "(nil)". [akpm@linux-foundation.org: check for IRQ context when !kptr_restrict, save an indent level, s/WARN/WARN_ONCE/] [akpm@linux-foundation.org: coding-style fixup] [randy.dunlap@oracle.com: fix kernel/sysctl.c warning] Signed-off-by: Dan Rosenberg <drosenberg@vsecurity.com> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: James Morris <jmorris@namei.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Thomas Graf <tgraf@infradead.org> Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Kees Cook <kees.cook@canonical.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: David S. Miller <davem@davemloft.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Eric Paris <eparis@parisplace.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-13 00:59:41 +00:00
{
.procname = "kptr_restrict",
.data = &kptr_restrict,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax_sysadmin,
kptr_restrict for hiding kernel pointers from unprivileged users Add the %pK printk format specifier and the /proc/sys/kernel/kptr_restrict sysctl. The %pK format specifier is designed to hide exposed kernel pointers, specifically via /proc interfaces. Exposing these pointers provides an easy target for kernel write vulnerabilities, since they reveal the locations of writable structures containing easily triggerable function pointers. The behavior of %pK depends on the kptr_restrict sysctl. If kptr_restrict is set to 0, no deviation from the standard %p behavior occurs. If kptr_restrict is set to 1, the default, if the current user (intended to be a reader via seq_printf(), etc.) does not have CAP_SYSLOG (currently in the LSM tree), kernel pointers using %pK are printed as 0's. If kptr_restrict is set to 2, kernel pointers using %pK are printed as 0's regardless of privileges. Replacing with 0's was chosen over the default "(null)", which cannot be parsed by userland %p, which expects "(nil)". [akpm@linux-foundation.org: check for IRQ context when !kptr_restrict, save an indent level, s/WARN/WARN_ONCE/] [akpm@linux-foundation.org: coding-style fixup] [randy.dunlap@oracle.com: fix kernel/sysctl.c warning] Signed-off-by: Dan Rosenberg <drosenberg@vsecurity.com> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: James Morris <jmorris@namei.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Thomas Graf <tgraf@infradead.org> Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Kees Cook <kees.cook@canonical.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: David S. Miller <davem@davemloft.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Eric Paris <eparis@parisplace.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-13 00:59:41 +00:00
.extra1 = &zero,
.extra2 = &two,
},
#endif
{
.procname = "ngroups_max",
.data = &ngroups_max,
.maxlen = sizeof (int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
{
.procname = "cap_last_cap",
.data = (void *)&cap_last_cap,
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Eric Paris <eparis@redhat.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2010-05-07 21:11:44 +00:00
#if defined(CONFIG_LOCKUP_DETECTOR)
{
lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Eric Paris <eparis@redhat.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2010-05-07 21:11:44 +00:00
.procname = "watchdog",
.data = &watchdog_user_enabled,
.maxlen = sizeof (int),
.mode = 0644,
watchdog: enable the new user interface of the watchdog mechanism With the current user interface of the watchdog mechanism it is only possible to disable or enable both lockup detectors at the same time. This series introduces new kernel parameters and changes the semantics of some existing kernel parameters, so that the hard lockup detector and the soft lockup detector can be disabled or enabled individually. With this series applied, the user interface is as follows. - parameters in /proc/sys/kernel . soft_watchdog This is a new parameter to control and examine the run state of the soft lockup detector. . nmi_watchdog The semantics of this parameter have changed. It can now be used to control and examine the run state of the hard lockup detector. . watchdog This parameter is still available to control the run state of both lockup detectors at the same time. If this parameter is examined, it shows the logical OR of soft_watchdog and nmi_watchdog. . watchdog_thresh The semantics of this parameter are not affected by the patch. - kernel command line parameters . nosoftlockup The semantics of this parameter have changed. It can now be used to disable the soft lockup detector at boot time. . nmi_watchdog=0 or nmi_watchdog=1 Disable or enable the hard lockup detector at boot time. The patch introduces '=1' as a new option. . nowatchdog The semantics of this parameter are not affected by the patch. It is still available to disable both lockup detectors at boot time. Also, remove the proc_dowatchdog() function which is no longer needed. [dzickus@redhat.com: wrote changelog] [dzickus@redhat.com: update documentation for kernel params and sysctl] Signed-off-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-14 22:44:13 +00:00
.proc_handler = proc_watchdog,
.extra1 = &zero,
.extra2 = &one,
lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Eric Paris <eparis@redhat.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2010-05-07 21:11:44 +00:00
},
{
.procname = "watchdog_thresh",
.data = &watchdog_thresh,
lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Eric Paris <eparis@redhat.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2010-05-07 21:11:44 +00:00
.maxlen = sizeof(int),
.mode = 0644,
watchdog: enable the new user interface of the watchdog mechanism With the current user interface of the watchdog mechanism it is only possible to disable or enable both lockup detectors at the same time. This series introduces new kernel parameters and changes the semantics of some existing kernel parameters, so that the hard lockup detector and the soft lockup detector can be disabled or enabled individually. With this series applied, the user interface is as follows. - parameters in /proc/sys/kernel . soft_watchdog This is a new parameter to control and examine the run state of the soft lockup detector. . nmi_watchdog The semantics of this parameter have changed. It can now be used to control and examine the run state of the hard lockup detector. . watchdog This parameter is still available to control the run state of both lockup detectors at the same time. If this parameter is examined, it shows the logical OR of soft_watchdog and nmi_watchdog. . watchdog_thresh The semantics of this parameter are not affected by the patch. - kernel command line parameters . nosoftlockup The semantics of this parameter have changed. It can now be used to disable the soft lockup detector at boot time. . nmi_watchdog=0 or nmi_watchdog=1 Disable or enable the hard lockup detector at boot time. The patch introduces '=1' as a new option. . nowatchdog The semantics of this parameter are not affected by the patch. It is still available to disable both lockup detectors at boot time. Also, remove the proc_dowatchdog() function which is no longer needed. [dzickus@redhat.com: wrote changelog] [dzickus@redhat.com: update documentation for kernel params and sysctl] Signed-off-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-14 22:44:13 +00:00
.proc_handler = proc_watchdog_thresh,
.extra1 = &zero,
lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Eric Paris <eparis@redhat.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2010-05-07 21:11:44 +00:00
.extra2 = &sixty,
},
watchdog: enable the new user interface of the watchdog mechanism With the current user interface of the watchdog mechanism it is only possible to disable or enable both lockup detectors at the same time. This series introduces new kernel parameters and changes the semantics of some existing kernel parameters, so that the hard lockup detector and the soft lockup detector can be disabled or enabled individually. With this series applied, the user interface is as follows. - parameters in /proc/sys/kernel . soft_watchdog This is a new parameter to control and examine the run state of the soft lockup detector. . nmi_watchdog The semantics of this parameter have changed. It can now be used to control and examine the run state of the hard lockup detector. . watchdog This parameter is still available to control the run state of both lockup detectors at the same time. If this parameter is examined, it shows the logical OR of soft_watchdog and nmi_watchdog. . watchdog_thresh The semantics of this parameter are not affected by the patch. - kernel command line parameters . nosoftlockup The semantics of this parameter have changed. It can now be used to disable the soft lockup detector at boot time. . nmi_watchdog=0 or nmi_watchdog=1 Disable or enable the hard lockup detector at boot time. The patch introduces '=1' as a new option. . nowatchdog The semantics of this parameter are not affected by the patch. It is still available to disable both lockup detectors at boot time. Also, remove the proc_dowatchdog() function which is no longer needed. [dzickus@redhat.com: wrote changelog] [dzickus@redhat.com: update documentation for kernel params and sysctl] Signed-off-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-14 22:44:13 +00:00
{
.procname = "nmi_watchdog",
.data = &nmi_watchdog_enabled,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_nmi_watchdog,
.extra1 = &zero,
#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
.extra2 = &one,
#else
.extra2 = &zero,
#endif
},
{
.procname = "soft_watchdog",
.data = &soft_watchdog_enabled,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_soft_watchdog,
.extra1 = &zero,
.extra2 = &one,
},
watchdog: add watchdog_cpumask sysctl to assist nohz Change the default behavior of watchdog so it only runs on the housekeeping cores when nohz_full is enabled at build and boot time. Allow modifying the set of cores the watchdog is currently running on with a new kernel.watchdog_cpumask sysctl. In the current system, the watchdog subsystem runs a periodic timer that schedules the watchdog kthread to run. However, nohz_full cores are designed to allow userspace application code running on those cores to have 100% access to the CPU. So the watchdog system prevents the nohz_full application code from being able to run the way it wants to, thus the motivation to suppress the watchdog on nohz_full cores, which this patchset provides by default. However, if we disable the watchdog globally, then the housekeeping cores can't benefit from the watchdog functionality. So we allow disabling it only on some cores. See Documentation/lockup-watchdogs.txt for more information. [jhubbard@nvidia.com: fix a watchdog crash in some configurations] Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Acked-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-24 23:55:45 +00:00
{
.procname = "watchdog_cpumask",
.data = &watchdog_cpumask_bits,
.maxlen = NR_CPUS,
.mode = 0644,
.proc_handler = proc_watchdog_cpumask,
},
{
.procname = "softlockup_panic",
.data = &softlockup_panic,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#ifdef CONFIG_HARDLOCKUP_DETECTOR
{
.procname = "hardlockup_panic",
.data = &hardlockup_panic,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#endif
kernel/watchdog.c: print traces for all cpus on lockup detection A 'softlockup' is defined as a bug that causes the kernel to loop in kernel mode for more than a predefined period to time, without giving other tasks a chance to run. Currently, upon detection of this condition by the per-cpu watchdog task, debug information (including a stack trace) is sent to the system log. On some occasions, we have observed that the "victim" rather than the actual "culprit" (i.e. the owner/holder of the contended resource) is reported to the user. Often this information has proven to be insufficient to assist debugging efforts. To avoid loss of useful debug information, for architectures which support NMI, this patch makes it possible to improve soft lockup reporting. This is accomplished by issuing an NMI to each cpu to obtain a stack trace. If NMI is not supported we just revert back to the old method. A sysctl and boot-time parameter is available to toggle this feature. [dzickus@redhat.com: add CONFIG_SMP in certain areas] [akpm@linux-foundation.org: additional CONFIG_SMP=n optimisations] [mq@suse.cz: fix warning] Signed-off-by: Aaron Tomlin <atomlin@redhat.com> Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: David S. Miller <davem@davemloft.net> Cc: Mateusz Guzik <mguzik@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Jan Moskyto Matejka <mq@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-23 20:22:05 +00:00
#ifdef CONFIG_SMP
{
.procname = "softlockup_all_cpu_backtrace",
.data = &sysctl_softlockup_all_cpu_backtrace,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "hardlockup_all_cpu_backtrace",
.data = &sysctl_hardlockup_all_cpu_backtrace,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
kernel/watchdog.c: print traces for all cpus on lockup detection A 'softlockup' is defined as a bug that causes the kernel to loop in kernel mode for more than a predefined period to time, without giving other tasks a chance to run. Currently, upon detection of this condition by the per-cpu watchdog task, debug information (including a stack trace) is sent to the system log. On some occasions, we have observed that the "victim" rather than the actual "culprit" (i.e. the owner/holder of the contended resource) is reported to the user. Often this information has proven to be insufficient to assist debugging efforts. To avoid loss of useful debug information, for architectures which support NMI, this patch makes it possible to improve soft lockup reporting. This is accomplished by issuing an NMI to each cpu to obtain a stack trace. If NMI is not supported we just revert back to the old method. A sysctl and boot-time parameter is available to toggle this feature. [dzickus@redhat.com: add CONFIG_SMP in certain areas] [akpm@linux-foundation.org: additional CONFIG_SMP=n optimisations] [mq@suse.cz: fix warning] Signed-off-by: Aaron Tomlin <atomlin@redhat.com> Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: David S. Miller <davem@davemloft.net> Cc: Mateusz Guzik <mguzik@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Jan Moskyto Matejka <mq@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-23 20:22:05 +00:00
#endif /* CONFIG_SMP */
#endif
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
{
.procname = "unknown_nmi_panic",
.data = &unknown_nmi_panic,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_X86)
{
.procname = "panic_on_unrecovered_nmi",
.data = &panic_on_unrecovered_nmi,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "panic_on_io_nmi",
.data = &panic_on_io_nmi,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_DEBUG_STACKOVERFLOW
{
.procname = "panic_on_stackoverflow",
.data = &sysctl_panic_on_stackoverflow,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
{
.procname = "bootloader_type",
.data = &bootloader_type,
.maxlen = sizeof (int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
{
.procname = "bootloader_version",
.data = &bootloader_version,
.maxlen = sizeof (int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
{
.procname = "kstack_depth_to_print",
.data = &kstack_depth_to_print,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "io_delay_type",
.data = &io_delay_type,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_MMU)
{
.procname = "randomize_va_space",
.data = &randomize_va_space,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_S390) && defined(CONFIG_SMP)
{
.procname = "spin_retry",
.data = &spin_retry,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86)
{
.procname = "acpi_video_flags",
.data = &acpi_realmode_flags,
.maxlen = sizeof (unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
#endif
#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
{
.procname = "ignore-unaligned-usertrap",
.data = &no_unaligned_warning,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_IA64
{
.procname = "unaligned-dump-stack",
.data = &unaligned_dump_stack,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
{
.procname = "hung_task_panic",
.data = &sysctl_hung_task_panic,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-25 20:08:02 +00:00
{
.procname = "hung_task_check_count",
.data = &sysctl_hung_task_check_count,
.maxlen = sizeof(int),
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-25 20:08:02 +00:00
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-25 20:08:02 +00:00
},
{
.procname = "hung_task_timeout_secs",
.data = &sysctl_hung_task_timeout_secs,
.maxlen = sizeof(unsigned long),
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-25 20:08:02 +00:00
.mode = 0644,
.proc_handler = proc_dohung_task_timeout_secs,
.extra2 = &hung_task_timeout_max,
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-25 20:08:02 +00:00
},
{
.procname = "hung_task_warnings",
.data = &sysctl_hung_task_warnings,
.maxlen = sizeof(int),
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-25 20:08:02 +00:00
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &neg_one,
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-25 20:08:02 +00:00
},
#endif
#ifdef CONFIG_COMPAT
{
.procname = "compat-log",
.data = &compat_log,
.maxlen = sizeof (int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_RT_MUTEXES
{
.procname = "max_lock_depth",
.data = &max_lock_depth,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
{
.procname = "poweroff_cmd",
.data = &poweroff_cmd,
.maxlen = POWEROFF_CMD_PATH_LEN,
.mode = 0644,
.proc_handler = proc_dostring,
},
#ifdef CONFIG_KEYS
{
.procname = "keys",
.mode = 0555,
.child = key_sysctls,
},
#endif
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
#ifdef CONFIG_PERF_EVENTS
/*
* User-space scripts rely on the existence of this file
* as a feature check for perf_events being enabled.
*
* So it's an ABI, do not remove!
*/
{
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
.procname = "perf_event_paranoid",
.data = &sysctl_perf_event_paranoid,
.maxlen = sizeof(sysctl_perf_event_paranoid),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
.procname = "perf_event_mlock_kb",
.data = &sysctl_perf_event_mlock,
.maxlen = sizeof(sysctl_perf_event_mlock),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
.procname = "perf_event_max_sample_rate",
.data = &sysctl_perf_event_sample_rate,
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
.proc_handler = perf_proc_update_handler,
.extra1 = &one,
},
{
.procname = "perf_cpu_time_max_percent",
.data = &sysctl_perf_cpu_time_max_percent,
.maxlen = sizeof(sysctl_perf_cpu_time_max_percent),
.mode = 0644,
.proc_handler = perf_cpu_time_max_percent_handler,
.extra1 = &zero,
.extra2 = &one_hundred,
},
#endif
#ifdef CONFIG_KMEMCHECK
{
.procname = "kmemcheck",
.data = &kmemcheck_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
kernel: add panic_on_warn There have been several times where I have had to rebuild a kernel to cause a panic when hitting a WARN() in the code in order to get a crash dump from a system. Sometimes this is easy to do, other times (such as in the case of a remote admin) it is not trivial to send new images to the user. A much easier method would be a switch to change the WARN() over to a panic. This makes debugging easier in that I can now test the actual image the WARN() was seen on and I do not have to engage in remote debugging. This patch adds a panic_on_warn kernel parameter and /proc/sys/kernel/panic_on_warn calls panic() in the warn_slowpath_common() path. The function will still print out the location of the warning. An example of the panic_on_warn output: The first line below is from the WARN_ON() to output the WARN_ON()'s location. After that the panic() output is displayed. WARNING: CPU: 30 PID: 11698 at /home/prarit/dummy_module/dummy-module.c:25 init_dummy+0x1f/0x30 [dummy_module]() Kernel panic - not syncing: panic_on_warn set ... CPU: 30 PID: 11698 Comm: insmod Tainted: G W OE 3.17.0+ #57 Hardware name: Intel Corporation S2600CP/S2600CP, BIOS RMLSDP.86I.00.29.D696.1311111329 11/11/2013 0000000000000000 000000008e3f87df ffff88080f093c38 ffffffff81665190 0000000000000000 ffffffff818aea3d ffff88080f093cb8 ffffffff8165e2ec ffffffff00000008 ffff88080f093cc8 ffff88080f093c68 000000008e3f87df Call Trace: [<ffffffff81665190>] dump_stack+0x46/0x58 [<ffffffff8165e2ec>] panic+0xd0/0x204 [<ffffffffa038e05f>] ? init_dummy+0x1f/0x30 [dummy_module] [<ffffffff81076b90>] warn_slowpath_common+0xd0/0xd0 [<ffffffffa038e040>] ? dummy_greetings+0x40/0x40 [dummy_module] [<ffffffff81076c8a>] warn_slowpath_null+0x1a/0x20 [<ffffffffa038e05f>] init_dummy+0x1f/0x30 [dummy_module] [<ffffffff81002144>] do_one_initcall+0xd4/0x210 [<ffffffff811b52c2>] ? __vunmap+0xc2/0x110 [<ffffffff810f8889>] load_module+0x16a9/0x1b30 [<ffffffff810f3d30>] ? store_uevent+0x70/0x70 [<ffffffff810f49b9>] ? copy_module_from_fd.isra.44+0x129/0x180 [<ffffffff810f8ec6>] SyS_finit_module+0xa6/0xd0 [<ffffffff8166cf29>] system_call_fastpath+0x12/0x17 Successfully tested by me. hpa said: There is another very valid use for this: many operators would rather a machine shuts down than being potentially compromised either functionally or security-wise. Signed-off-by: Prarit Bhargava <prarit@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Acked-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Fabian Frederick <fabf@skynet.be> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-10 23:45:50 +00:00
{
.procname = "panic_on_warn",
.data = &panic_on_warn,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
timer: Reduce timer migration overhead if disabled Eric reported that the timer_migration sysctl is not really nice performance wise as it needs to check at every timer insertion whether the feature is enabled or not. Further the check does not live in the timer code, so we have an extra function call which checks an extra cache line to figure out that it is disabled. We can do better and store that information in the per cpu (hr)timer bases. I pondered to use a static key, but that's a nightmare to update from the nohz code and the timer base cache line is hot anyway when we select a timer base. The old logic enabled the timer migration unconditionally if CONFIG_NO_HZ was set even if nohz was disabled on the kernel command line. With this modification, we start off with migration disabled. The user visible sysctl is still set to enabled. If the kernel switches to NOHZ migration is enabled, if the user did not disable it via the sysctl prior to the switch. If nohz=off is on the kernel command line, migration stays disabled no matter what. Before: 47.76% hog [.] main 14.84% [kernel] [k] _raw_spin_lock_irqsave 9.55% [kernel] [k] _raw_spin_unlock_irqrestore 6.71% [kernel] [k] mod_timer 6.24% [kernel] [k] lock_timer_base.isra.38 3.76% [kernel] [k] detach_if_pending 3.71% [kernel] [k] del_timer 2.50% [kernel] [k] internal_add_timer 1.51% [kernel] [k] get_nohz_timer_target 1.28% [kernel] [k] __internal_add_timer 0.78% [kernel] [k] timerfn 0.48% [kernel] [k] wake_up_nohz_cpu After: 48.10% hog [.] main 15.25% [kernel] [k] _raw_spin_lock_irqsave 9.76% [kernel] [k] _raw_spin_unlock_irqrestore 6.50% [kernel] [k] mod_timer 6.44% [kernel] [k] lock_timer_base.isra.38 3.87% [kernel] [k] detach_if_pending 3.80% [kernel] [k] del_timer 2.67% [kernel] [k] internal_add_timer 1.33% [kernel] [k] __internal_add_timer 0.73% [kernel] [k] timerfn 0.54% [kernel] [k] wake_up_nohz_cpu Reported-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Joonwoo Park <joonwoop@codeaurora.org> Cc: Wenbo Wang <wenbo.wang@memblaze.com> Link: http://lkml.kernel.org/r/20150526224512.127050787@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-26 22:50:33 +00:00
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
{
.procname = "timer_migration",
.data = &sysctl_timer_migration,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = timer_migration_handler,
},
bpf: enable non-root eBPF programs In order to let unprivileged users load and execute eBPF programs teach verifier to prevent pointer leaks. Verifier will prevent - any arithmetic on pointers (except R10+Imm which is used to compute stack addresses) - comparison of pointers (except if (map_value_ptr == 0) ... ) - passing pointers to helper functions - indirectly passing pointers in stack to helper functions - returning pointer from bpf program - storing pointers into ctx or maps Spill/fill of pointers into stack is allowed, but mangling of pointers stored in the stack or reading them byte by byte is not. Within bpf programs the pointers do exist, since programs need to be able to access maps, pass skb pointer to LD_ABS insns, etc but programs cannot pass such pointer values to the outside or obfuscate them. Only allow BPF_PROG_TYPE_SOCKET_FILTER unprivileged programs, so that socket filters (tcpdump), af_packet (quic acceleration) and future kcm can use it. tracing and tc cls/act program types still require root permissions, since tracing actually needs to be able to see all kernel pointers and tc is for root only. For example, the following unprivileged socket filter program is allowed: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += skb->len; return 0; } but the following program is not: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += (u64) skb; return 0; } since it would leak the kernel address into the map. Unprivileged socket filter bpf programs have access to the following helper functions: - map lookup/update/delete (but they cannot store kernel pointers into them) - get_random (it's already exposed to unprivileged user space) - get_smp_processor_id - tail_call into another socket filter program - ktime_get_ns The feature is controlled by sysctl kernel.unprivileged_bpf_disabled. This toggle defaults to off (0), but can be set true (1). Once true, bpf programs and maps cannot be accessed from unprivileged process, and the toggle cannot be set back to false. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-08 05:23:21 +00:00
#endif
#ifdef CONFIG_BPF_SYSCALL
{
.procname = "unprivileged_bpf_disabled",
.data = &sysctl_unprivileged_bpf_disabled,
.maxlen = sizeof(sysctl_unprivileged_bpf_disabled),
.mode = 0644,
/* only handle a transition from default "0" to "1" */
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
.extra2 = &one,
},
timer: Reduce timer migration overhead if disabled Eric reported that the timer_migration sysctl is not really nice performance wise as it needs to check at every timer insertion whether the feature is enabled or not. Further the check does not live in the timer code, so we have an extra function call which checks an extra cache line to figure out that it is disabled. We can do better and store that information in the per cpu (hr)timer bases. I pondered to use a static key, but that's a nightmare to update from the nohz code and the timer base cache line is hot anyway when we select a timer base. The old logic enabled the timer migration unconditionally if CONFIG_NO_HZ was set even if nohz was disabled on the kernel command line. With this modification, we start off with migration disabled. The user visible sysctl is still set to enabled. If the kernel switches to NOHZ migration is enabled, if the user did not disable it via the sysctl prior to the switch. If nohz=off is on the kernel command line, migration stays disabled no matter what. Before: 47.76% hog [.] main 14.84% [kernel] [k] _raw_spin_lock_irqsave 9.55% [kernel] [k] _raw_spin_unlock_irqrestore 6.71% [kernel] [k] mod_timer 6.24% [kernel] [k] lock_timer_base.isra.38 3.76% [kernel] [k] detach_if_pending 3.71% [kernel] [k] del_timer 2.50% [kernel] [k] internal_add_timer 1.51% [kernel] [k] get_nohz_timer_target 1.28% [kernel] [k] __internal_add_timer 0.78% [kernel] [k] timerfn 0.48% [kernel] [k] wake_up_nohz_cpu After: 48.10% hog [.] main 15.25% [kernel] [k] _raw_spin_lock_irqsave 9.76% [kernel] [k] _raw_spin_unlock_irqrestore 6.50% [kernel] [k] mod_timer 6.44% [kernel] [k] lock_timer_base.isra.38 3.87% [kernel] [k] detach_if_pending 3.80% [kernel] [k] del_timer 2.67% [kernel] [k] internal_add_timer 1.33% [kernel] [k] __internal_add_timer 0.73% [kernel] [k] timerfn 0.54% [kernel] [k] wake_up_nohz_cpu Reported-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Joonwoo Park <joonwoop@codeaurora.org> Cc: Wenbo Wang <wenbo.wang@memblaze.com> Link: http://lkml.kernel.org/r/20150526224512.127050787@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-26 22:50:33 +00:00
#endif
{ }
};
static struct ctl_table vm_table[] = {
{
.procname = "overcommit_memory",
.data = &sysctl_overcommit_memory,
.maxlen = sizeof(sysctl_overcommit_memory),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &two,
},
{
.procname = "panic_on_oom",
.data = &sysctl_panic_on_oom,
.maxlen = sizeof(sysctl_panic_on_oom),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &two,
},
{
.procname = "oom_kill_allocating_task",
.data = &sysctl_oom_kill_allocating_task,
.maxlen = sizeof(sysctl_oom_kill_allocating_task),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "oom_dump_tasks",
.data = &sysctl_oom_dump_tasks,
.maxlen = sizeof(sysctl_oom_dump_tasks),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "overcommit_ratio",
.data = &sysctl_overcommit_ratio,
.maxlen = sizeof(sysctl_overcommit_ratio),
.mode = 0644,
.proc_handler = overcommit_ratio_handler,
},
{
.procname = "overcommit_kbytes",
.data = &sysctl_overcommit_kbytes,
.maxlen = sizeof(sysctl_overcommit_kbytes),
.mode = 0644,
.proc_handler = overcommit_kbytes_handler,
},
{
.procname = "page-cluster",
.data = &page_cluster,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
{
.procname = "dirty_background_ratio",
.data = &dirty_background_ratio,
.maxlen = sizeof(dirty_background_ratio),
.mode = 0644,
.proc_handler = dirty_background_ratio_handler,
.extra1 = &zero,
.extra2 = &one_hundred,
},
mm: add dirty_background_bytes and dirty_bytes sysctls This change introduces two new sysctls to /proc/sys/vm: dirty_background_bytes and dirty_bytes. dirty_background_bytes is the counterpart to dirty_background_ratio and dirty_bytes is the counterpart to dirty_ratio. With growing memory capacities of individual machines, it's no longer sufficient to specify dirty thresholds as a percentage of the amount of dirtyable memory over the entire system. dirty_background_bytes and dirty_bytes specify quantities of memory, in bytes, that represent the dirty limits for the entire system. If either of these values is set, its value represents the amount of dirty memory that is needed to commence either background or direct writeback. When a `bytes' or `ratio' file is written, its counterpart becomes a function of the written value. For example, if dirty_bytes is written to be 8096, 8K of memory is required to commence direct writeback. dirty_ratio is then functionally equivalent to 8K / the amount of dirtyable memory: dirtyable_memory = free pages + mapped pages + file cache dirty_background_bytes = dirty_background_ratio * dirtyable_memory -or- dirty_background_ratio = dirty_background_bytes / dirtyable_memory AND dirty_bytes = dirty_ratio * dirtyable_memory -or- dirty_ratio = dirty_bytes / dirtyable_memory Only one of dirty_background_bytes and dirty_background_ratio may be specified at a time, and only one of dirty_bytes and dirty_ratio may be specified. When one sysctl is written, the other appears as 0 when read. The `bytes' files operate on a page size granularity since dirty limits are compared with ZVC values, which are in page units. Prior to this change, the minimum dirty_ratio was 5 as implemented by get_dirty_limits() although /proc/sys/vm/dirty_ratio would show any user written value between 0 and 100. This restriction is maintained, but dirty_bytes has a lower limit of only one page. Also prior to this change, the dirty_background_ratio could not equal or exceed dirty_ratio. This restriction is maintained in addition to restricting dirty_background_bytes. If either background threshold equals or exceeds that of the dirty threshold, it is implicitly set to half the dirty threshold. Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andrea Righi <righi.andrea@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:31 +00:00
{
.procname = "dirty_background_bytes",
.data = &dirty_background_bytes,
.maxlen = sizeof(dirty_background_bytes),
.mode = 0644,
.proc_handler = dirty_background_bytes_handler,
.extra1 = &one_ul,
mm: add dirty_background_bytes and dirty_bytes sysctls This change introduces two new sysctls to /proc/sys/vm: dirty_background_bytes and dirty_bytes. dirty_background_bytes is the counterpart to dirty_background_ratio and dirty_bytes is the counterpart to dirty_ratio. With growing memory capacities of individual machines, it's no longer sufficient to specify dirty thresholds as a percentage of the amount of dirtyable memory over the entire system. dirty_background_bytes and dirty_bytes specify quantities of memory, in bytes, that represent the dirty limits for the entire system. If either of these values is set, its value represents the amount of dirty memory that is needed to commence either background or direct writeback. When a `bytes' or `ratio' file is written, its counterpart becomes a function of the written value. For example, if dirty_bytes is written to be 8096, 8K of memory is required to commence direct writeback. dirty_ratio is then functionally equivalent to 8K / the amount of dirtyable memory: dirtyable_memory = free pages + mapped pages + file cache dirty_background_bytes = dirty_background_ratio * dirtyable_memory -or- dirty_background_ratio = dirty_background_bytes / dirtyable_memory AND dirty_bytes = dirty_ratio * dirtyable_memory -or- dirty_ratio = dirty_bytes / dirtyable_memory Only one of dirty_background_bytes and dirty_background_ratio may be specified at a time, and only one of dirty_bytes and dirty_ratio may be specified. When one sysctl is written, the other appears as 0 when read. The `bytes' files operate on a page size granularity since dirty limits are compared with ZVC values, which are in page units. Prior to this change, the minimum dirty_ratio was 5 as implemented by get_dirty_limits() although /proc/sys/vm/dirty_ratio would show any user written value between 0 and 100. This restriction is maintained, but dirty_bytes has a lower limit of only one page. Also prior to this change, the dirty_background_ratio could not equal or exceed dirty_ratio. This restriction is maintained in addition to restricting dirty_background_bytes. If either background threshold equals or exceeds that of the dirty threshold, it is implicitly set to half the dirty threshold. Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andrea Righi <righi.andrea@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:31 +00:00
},
{
.procname = "dirty_ratio",
.data = &vm_dirty_ratio,
.maxlen = sizeof(vm_dirty_ratio),
.mode = 0644,
.proc_handler = dirty_ratio_handler,
.extra1 = &zero,
.extra2 = &one_hundred,
},
mm: add dirty_background_bytes and dirty_bytes sysctls This change introduces two new sysctls to /proc/sys/vm: dirty_background_bytes and dirty_bytes. dirty_background_bytes is the counterpart to dirty_background_ratio and dirty_bytes is the counterpart to dirty_ratio. With growing memory capacities of individual machines, it's no longer sufficient to specify dirty thresholds as a percentage of the amount of dirtyable memory over the entire system. dirty_background_bytes and dirty_bytes specify quantities of memory, in bytes, that represent the dirty limits for the entire system. If either of these values is set, its value represents the amount of dirty memory that is needed to commence either background or direct writeback. When a `bytes' or `ratio' file is written, its counterpart becomes a function of the written value. For example, if dirty_bytes is written to be 8096, 8K of memory is required to commence direct writeback. dirty_ratio is then functionally equivalent to 8K / the amount of dirtyable memory: dirtyable_memory = free pages + mapped pages + file cache dirty_background_bytes = dirty_background_ratio * dirtyable_memory -or- dirty_background_ratio = dirty_background_bytes / dirtyable_memory AND dirty_bytes = dirty_ratio * dirtyable_memory -or- dirty_ratio = dirty_bytes / dirtyable_memory Only one of dirty_background_bytes and dirty_background_ratio may be specified at a time, and only one of dirty_bytes and dirty_ratio may be specified. When one sysctl is written, the other appears as 0 when read. The `bytes' files operate on a page size granularity since dirty limits are compared with ZVC values, which are in page units. Prior to this change, the minimum dirty_ratio was 5 as implemented by get_dirty_limits() although /proc/sys/vm/dirty_ratio would show any user written value between 0 and 100. This restriction is maintained, but dirty_bytes has a lower limit of only one page. Also prior to this change, the dirty_background_ratio could not equal or exceed dirty_ratio. This restriction is maintained in addition to restricting dirty_background_bytes. If either background threshold equals or exceeds that of the dirty threshold, it is implicitly set to half the dirty threshold. Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andrea Righi <righi.andrea@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:31 +00:00
{
.procname = "dirty_bytes",
.data = &vm_dirty_bytes,
.maxlen = sizeof(vm_dirty_bytes),
.mode = 0644,
.proc_handler = dirty_bytes_handler,
mm: prevent divide error for small values of vm_dirty_bytes Avoid setting less than two pages for vm_dirty_bytes: this is necessary to avoid potential division by 0 (like the following) in get_dirty_limits(). [ 49.951610] divide error: 0000 [#1] PREEMPT SMP [ 49.952195] last sysfs file: /sys/devices/pci0000:00/0000:00:01.1/host0/target0:0:0/0:0:0:0/block/sda/uevent [ 49.952195] CPU 1 [ 49.952195] Modules linked in: pcspkr [ 49.952195] Pid: 3064, comm: dd Not tainted 2.6.30-rc3 #1 [ 49.952195] RIP: 0010:[<ffffffff802d39a9>] [<ffffffff802d39a9>] get_dirty_limits+0xe9/0x2c0 [ 49.952195] RSP: 0018:ffff88001de03a98 EFLAGS: 00010202 [ 49.952195] RAX: 00000000000000c0 RBX: ffff88001de03b80 RCX: 28f5c28f5c28f5c3 [ 49.952195] RDX: 0000000000000000 RSI: 00000000000000c0 RDI: 0000000000000000 [ 49.952195] RBP: ffff88001de03ae8 R08: 0000000000000000 R09: 0000000000000000 [ 49.952195] R10: ffff88001ddda9a0 R11: 0000000000000001 R12: 0000000000000001 [ 49.952195] R13: ffff88001fbc8218 R14: ffff88001de03b70 R15: ffff88001de03b78 [ 49.952195] FS: 00007fe9a435b6f0(0000) GS:ffff8800025d9000(0000) knlGS:0000000000000000 [ 49.952195] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 49.952195] CR2: 00007fe9a39ab000 CR3: 000000001de38000 CR4: 00000000000006e0 [ 49.952195] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 49.952195] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 49.952195] Process dd (pid: 3064, threadinfo ffff88001de02000, task ffff88001ddda250) [ 49.952195] Stack: [ 49.952195] ffff88001fa0de00 ffff88001f2dbd70 ffff88001f9fe800 000080b900000000 [ 49.952195] 00000000000000c0 ffff8800027a6100 0000000000000400 ffff88001fbc8218 [ 49.952195] 0000000000000000 0000000000000600 ffff88001de03bb8 ffffffff802d3ed7 [ 49.952195] Call Trace: [ 49.952195] [<ffffffff802d3ed7>] balance_dirty_pages_ratelimited_nr+0x1d7/0x3f0 [ 49.952195] [<ffffffff80368f8e>] ? ext3_writeback_write_end+0x9e/0x120 [ 49.952195] [<ffffffff802cc7df>] generic_file_buffered_write+0x12f/0x330 [ 49.952195] [<ffffffff802cce8d>] __generic_file_aio_write_nolock+0x26d/0x460 [ 49.952195] [<ffffffff802cda32>] ? generic_file_aio_write+0x52/0xd0 [ 49.952195] [<ffffffff802cda49>] generic_file_aio_write+0x69/0xd0 [ 49.952195] [<ffffffff80365fa6>] ext3_file_write+0x26/0xc0 [ 49.952195] [<ffffffff803034d1>] do_sync_write+0xf1/0x140 [ 49.952195] [<ffffffff80290d1a>] ? get_lock_stats+0x2a/0x60 [ 49.952195] [<ffffffff80280730>] ? autoremove_wake_function+0x0/0x40 [ 49.952195] [<ffffffff8030411b>] vfs_write+0xcb/0x190 [ 49.952195] [<ffffffff803042d0>] sys_write+0x50/0x90 [ 49.952195] [<ffffffff8022ff6b>] system_call_fastpath+0x16/0x1b [ 49.952195] Code: 00 00 00 2b 05 09 1c 17 01 48 89 c6 49 0f af f4 48 c1 ee 02 48 89 f0 48 f7 e1 48 89 d6 31 d2 48 c1 ee 02 48 0f af 75 d0 48 89 f0 <48> f7 f7 41 8b 95 ac 01 00 00 48 89 c7 49 0f af d4 48 c1 ea 02 [ 49.952195] RIP [<ffffffff802d39a9>] get_dirty_limits+0xe9/0x2c0 [ 49.952195] RSP <ffff88001de03a98> [ 50.096523] ---[ end trace 008d7aa02f244d7b ]--- Signed-off-by: Andrea Righi <righi.andrea@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-30 22:08:57 +00:00
.extra1 = &dirty_bytes_min,
mm: add dirty_background_bytes and dirty_bytes sysctls This change introduces two new sysctls to /proc/sys/vm: dirty_background_bytes and dirty_bytes. dirty_background_bytes is the counterpart to dirty_background_ratio and dirty_bytes is the counterpart to dirty_ratio. With growing memory capacities of individual machines, it's no longer sufficient to specify dirty thresholds as a percentage of the amount of dirtyable memory over the entire system. dirty_background_bytes and dirty_bytes specify quantities of memory, in bytes, that represent the dirty limits for the entire system. If either of these values is set, its value represents the amount of dirty memory that is needed to commence either background or direct writeback. When a `bytes' or `ratio' file is written, its counterpart becomes a function of the written value. For example, if dirty_bytes is written to be 8096, 8K of memory is required to commence direct writeback. dirty_ratio is then functionally equivalent to 8K / the amount of dirtyable memory: dirtyable_memory = free pages + mapped pages + file cache dirty_background_bytes = dirty_background_ratio * dirtyable_memory -or- dirty_background_ratio = dirty_background_bytes / dirtyable_memory AND dirty_bytes = dirty_ratio * dirtyable_memory -or- dirty_ratio = dirty_bytes / dirtyable_memory Only one of dirty_background_bytes and dirty_background_ratio may be specified at a time, and only one of dirty_bytes and dirty_ratio may be specified. When one sysctl is written, the other appears as 0 when read. The `bytes' files operate on a page size granularity since dirty limits are compared with ZVC values, which are in page units. Prior to this change, the minimum dirty_ratio was 5 as implemented by get_dirty_limits() although /proc/sys/vm/dirty_ratio would show any user written value between 0 and 100. This restriction is maintained, but dirty_bytes has a lower limit of only one page. Also prior to this change, the dirty_background_ratio could not equal or exceed dirty_ratio. This restriction is maintained in addition to restricting dirty_background_bytes. If either background threshold equals or exceeds that of the dirty threshold, it is implicitly set to half the dirty threshold. Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andrea Righi <righi.andrea@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:31 +00:00
},
{
.procname = "dirty_writeback_centisecs",
.data = &dirty_writeback_interval,
.maxlen = sizeof(dirty_writeback_interval),
.mode = 0644,
.proc_handler = dirty_writeback_centisecs_handler,
},
{
.procname = "dirty_expire_centisecs",
.data = &dirty_expire_interval,
.maxlen = sizeof(dirty_expire_interval),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
{
.procname = "dirtytime_expire_seconds",
.data = &dirtytime_expire_interval,
.maxlen = sizeof(dirty_expire_interval),
.mode = 0644,
.proc_handler = dirtytime_interval_handler,
.extra1 = &zero,
},
{
.procname = "nr_pdflush_threads",
.mode = 0444 /* read-only */,
.proc_handler = pdflush_proc_obsolete,
},
{
.procname = "swappiness",
.data = &vm_swappiness,
.maxlen = sizeof(vm_swappiness),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one_hundred,
},
#ifdef CONFIG_HUGETLB_PAGE
hugetlb: derive huge pages nodes allowed from task mempolicy This patch derives a "nodes_allowed" node mask from the numa mempolicy of the task modifying the number of persistent huge pages to control the allocation, freeing and adjusting of surplus huge pages when the pool page count is modified via the new sysctl or sysfs attribute "nr_hugepages_mempolicy". The nodes_allowed mask is derived as follows: * For "default" [NULL] task mempolicy, a NULL nodemask_t pointer is produced. This will cause the hugetlb subsystem to use node_online_map as the "nodes_allowed". This preserves the behavior before this patch. * For "preferred" mempolicy, including explicit local allocation, a nodemask with the single preferred node will be produced. "local" policy will NOT track any internode migrations of the task adjusting nr_hugepages. * For "bind" and "interleave" policy, the mempolicy's nodemask will be used. * Other than to inform the construction of the nodes_allowed node mask, the actual mempolicy mode is ignored. That is, all modes behave like interleave over the resulting nodes_allowed mask with no "fallback". See the updated documentation [next patch] for more information about the implications of this patch. Examples: Starting with: Node 0 HugePages_Total: 0 Node 1 HugePages_Total: 0 Node 2 HugePages_Total: 0 Node 3 HugePages_Total: 0 Default behavior [with or without this patch] balances persistent hugepage allocation across nodes [with sufficient contiguous memory]: sysctl vm.nr_hugepages[_mempolicy]=32 yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 8 Node 3 HugePages_Total: 8 Of course, we only have nr_hugepages_mempolicy with the patch, but with default mempolicy, nr_hugepages_mempolicy behaves the same as nr_hugepages. Applying mempolicy--e.g., with numactl [using '-m' a.k.a. '--membind' because it allows multiple nodes to be specified and it's easy to type]--we can allocate huge pages on individual nodes or sets of nodes. So, starting from the condition above, with 8 huge pages per node, add 8 more to node 2 using: numactl -m 2 sysctl vm.nr_hugepages_mempolicy=40 This yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The incremental 8 huge pages were restricted to node 2 by the specified mempolicy. Similarly, we can use mempolicy to free persistent huge pages from specified nodes: numactl -m 0,1 sysctl vm.nr_hugepages_mempolicy=32 yields: Node 0 HugePages_Total: 4 Node 1 HugePages_Total: 4 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The 8 huge pages freed were balanced over nodes 0 and 1. [rientjes@google.com: accomodate reworked NODEMASK_ALLOC] Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Nishanth Aravamudan <nacc@us.ibm.com> Cc: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@canonical.com> Cc: Eric Whitney <eric.whitney@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:21 +00:00
{
.procname = "nr_hugepages",
.data = NULL,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = hugetlb_sysctl_handler,
hugetlb: derive huge pages nodes allowed from task mempolicy This patch derives a "nodes_allowed" node mask from the numa mempolicy of the task modifying the number of persistent huge pages to control the allocation, freeing and adjusting of surplus huge pages when the pool page count is modified via the new sysctl or sysfs attribute "nr_hugepages_mempolicy". The nodes_allowed mask is derived as follows: * For "default" [NULL] task mempolicy, a NULL nodemask_t pointer is produced. This will cause the hugetlb subsystem to use node_online_map as the "nodes_allowed". This preserves the behavior before this patch. * For "preferred" mempolicy, including explicit local allocation, a nodemask with the single preferred node will be produced. "local" policy will NOT track any internode migrations of the task adjusting nr_hugepages. * For "bind" and "interleave" policy, the mempolicy's nodemask will be used. * Other than to inform the construction of the nodes_allowed node mask, the actual mempolicy mode is ignored. That is, all modes behave like interleave over the resulting nodes_allowed mask with no "fallback". See the updated documentation [next patch] for more information about the implications of this patch. Examples: Starting with: Node 0 HugePages_Total: 0 Node 1 HugePages_Total: 0 Node 2 HugePages_Total: 0 Node 3 HugePages_Total: 0 Default behavior [with or without this patch] balances persistent hugepage allocation across nodes [with sufficient contiguous memory]: sysctl vm.nr_hugepages[_mempolicy]=32 yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 8 Node 3 HugePages_Total: 8 Of course, we only have nr_hugepages_mempolicy with the patch, but with default mempolicy, nr_hugepages_mempolicy behaves the same as nr_hugepages. Applying mempolicy--e.g., with numactl [using '-m' a.k.a. '--membind' because it allows multiple nodes to be specified and it's easy to type]--we can allocate huge pages on individual nodes or sets of nodes. So, starting from the condition above, with 8 huge pages per node, add 8 more to node 2 using: numactl -m 2 sysctl vm.nr_hugepages_mempolicy=40 This yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The incremental 8 huge pages were restricted to node 2 by the specified mempolicy. Similarly, we can use mempolicy to free persistent huge pages from specified nodes: numactl -m 0,1 sysctl vm.nr_hugepages_mempolicy=32 yields: Node 0 HugePages_Total: 4 Node 1 HugePages_Total: 4 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The 8 huge pages freed were balanced over nodes 0 and 1. [rientjes@google.com: accomodate reworked NODEMASK_ALLOC] Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Nishanth Aravamudan <nacc@us.ibm.com> Cc: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@canonical.com> Cc: Eric Whitney <eric.whitney@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:21 +00:00
},
#ifdef CONFIG_NUMA
{
.procname = "nr_hugepages_mempolicy",
.data = NULL,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = &hugetlb_mempolicy_sysctl_handler,
},
#endif
{
.procname = "hugetlb_shm_group",
.data = &sysctl_hugetlb_shm_group,
.maxlen = sizeof(gid_t),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "hugepages_treat_as_movable",
.data = &hugepages_treat_as_movable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
hugetlb: introduce nr_overcommit_hugepages sysctl hugetlb: introduce nr_overcommit_hugepages sysctl While examining the code to support /proc/sys/vm/hugetlb_dynamic_pool, I became convinced that having a boolean sysctl was insufficient: 1) To support per-node control of hugepages, I have previously submitted patches to add a sysfs attribute related to nr_hugepages. However, with a boolean global value and per-mount quota enforcement constraining the dynamic pool, adding corresponding control of the dynamic pool on a per-node basis seems inconsistent to me. 2) Administration of the hugetlb dynamic pool with multiple hugetlbfs mount points is, arguably, more arduous than it needs to be. Each quota would need to be set separately, and the sum would need to be monitored. To ease the administration, and to help make the way for per-node control of the static & dynamic hugepage pool, I added a separate sysctl, nr_overcommit_hugepages. This value serves as a high watermark for the overall hugepage pool, while nr_hugepages serves as a low watermark. The boolean sysctl can then be removed, as the condition nr_overcommit_hugepages > 0 indicates the same administrative setting as hugetlb_dynamic_pool == 1 Quotas still serve as local enforcement of the size of the pool on a per-mount basis. A few caveats: 1) There is a race whereby the global surplus huge page counter is incremented before a hugepage has allocated. Another process could then try grow the pool, and fail to convert a surplus huge page to a normal huge page and instead allocate a fresh huge page. I believe this is benign, as no memory is leaked (the actual pages are still tracked correctly) and the counters won't go out of sync. 2) Shrinking the static pool while a surplus is in effect will allow the number of surplus huge pages to exceed the overcommit value. As long as this condition holds, however, no more surplus huge pages will be allowed on the system until one of the two sysctls are increased sufficiently, or the surplus huge pages go out of use and are freed. Successfully tested on x86_64 with the current libhugetlbfs snapshot, modified to use the new sysctl. Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Acked-by: Adam Litke <agl@us.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-12-18 00:20:12 +00:00
{
.procname = "nr_overcommit_hugepages",
.data = NULL,
.maxlen = sizeof(unsigned long),
hugetlb: introduce nr_overcommit_hugepages sysctl hugetlb: introduce nr_overcommit_hugepages sysctl While examining the code to support /proc/sys/vm/hugetlb_dynamic_pool, I became convinced that having a boolean sysctl was insufficient: 1) To support per-node control of hugepages, I have previously submitted patches to add a sysfs attribute related to nr_hugepages. However, with a boolean global value and per-mount quota enforcement constraining the dynamic pool, adding corresponding control of the dynamic pool on a per-node basis seems inconsistent to me. 2) Administration of the hugetlb dynamic pool with multiple hugetlbfs mount points is, arguably, more arduous than it needs to be. Each quota would need to be set separately, and the sum would need to be monitored. To ease the administration, and to help make the way for per-node control of the static & dynamic hugepage pool, I added a separate sysctl, nr_overcommit_hugepages. This value serves as a high watermark for the overall hugepage pool, while nr_hugepages serves as a low watermark. The boolean sysctl can then be removed, as the condition nr_overcommit_hugepages > 0 indicates the same administrative setting as hugetlb_dynamic_pool == 1 Quotas still serve as local enforcement of the size of the pool on a per-mount basis. A few caveats: 1) There is a race whereby the global surplus huge page counter is incremented before a hugepage has allocated. Another process could then try grow the pool, and fail to convert a surplus huge page to a normal huge page and instead allocate a fresh huge page. I believe this is benign, as no memory is leaked (the actual pages are still tracked correctly) and the counters won't go out of sync. 2) Shrinking the static pool while a surplus is in effect will allow the number of surplus huge pages to exceed the overcommit value. As long as this condition holds, however, no more surplus huge pages will be allowed on the system until one of the two sysctls are increased sufficiently, or the surplus huge pages go out of use and are freed. Successfully tested on x86_64 with the current libhugetlbfs snapshot, modified to use the new sysctl. Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Acked-by: Adam Litke <agl@us.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-12-18 00:20:12 +00:00
.mode = 0644,
.proc_handler = hugetlb_overcommit_handler,
hugetlb: introduce nr_overcommit_hugepages sysctl hugetlb: introduce nr_overcommit_hugepages sysctl While examining the code to support /proc/sys/vm/hugetlb_dynamic_pool, I became convinced that having a boolean sysctl was insufficient: 1) To support per-node control of hugepages, I have previously submitted patches to add a sysfs attribute related to nr_hugepages. However, with a boolean global value and per-mount quota enforcement constraining the dynamic pool, adding corresponding control of the dynamic pool on a per-node basis seems inconsistent to me. 2) Administration of the hugetlb dynamic pool with multiple hugetlbfs mount points is, arguably, more arduous than it needs to be. Each quota would need to be set separately, and the sum would need to be monitored. To ease the administration, and to help make the way for per-node control of the static & dynamic hugepage pool, I added a separate sysctl, nr_overcommit_hugepages. This value serves as a high watermark for the overall hugepage pool, while nr_hugepages serves as a low watermark. The boolean sysctl can then be removed, as the condition nr_overcommit_hugepages > 0 indicates the same administrative setting as hugetlb_dynamic_pool == 1 Quotas still serve as local enforcement of the size of the pool on a per-mount basis. A few caveats: 1) There is a race whereby the global surplus huge page counter is incremented before a hugepage has allocated. Another process could then try grow the pool, and fail to convert a surplus huge page to a normal huge page and instead allocate a fresh huge page. I believe this is benign, as no memory is leaked (the actual pages are still tracked correctly) and the counters won't go out of sync. 2) Shrinking the static pool while a surplus is in effect will allow the number of surplus huge pages to exceed the overcommit value. As long as this condition holds, however, no more surplus huge pages will be allowed on the system until one of the two sysctls are increased sufficiently, or the surplus huge pages go out of use and are freed. Successfully tested on x86_64 with the current libhugetlbfs snapshot, modified to use the new sysctl. Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Acked-by: Adam Litke <agl@us.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-12-18 00:20:12 +00:00
},
#endif
{
.procname = "lowmem_reserve_ratio",
.data = &sysctl_lowmem_reserve_ratio,
.maxlen = sizeof(sysctl_lowmem_reserve_ratio),
.mode = 0644,
.proc_handler = lowmem_reserve_ratio_sysctl_handler,
},
{
.procname = "drop_caches",
.data = &sysctl_drop_caches,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = drop_caches_sysctl_handler,
.extra1 = &one,
2014-04-03 21:48:19 +00:00
.extra2 = &four,
},
#ifdef CONFIG_COMPACTION
{
.procname = "compact_memory",
.data = &sysctl_compact_memory,
.maxlen = sizeof(int),
.mode = 0200,
.proc_handler = sysctl_compaction_handler,
},
{
.procname = "extfrag_threshold",
.data = &sysctl_extfrag_threshold,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = sysctl_extfrag_handler,
.extra1 = &min_extfrag_threshold,
.extra2 = &max_extfrag_threshold,
},
mm: allow compaction of unevictable pages Currently, pages which are marked as unevictable are protected from compaction, but not from other types of migration. The POSIX real time extension explicitly states that mlock() will prevent a major page fault, but the spirit of this is that mlock() should give a process the ability to control sources of latency, including minor page faults. However, the mlock manpage only explicitly says that a locked page will not be written to swap and this can cause some confusion. The compaction code today does not give a developer who wants to avoid swap but wants to have large contiguous areas available any method to achieve this state. This patch introduces a sysctl for controlling compaction behavior with respect to the unevictable lru. Users who demand no page faults after a page is present can set compact_unevictable_allowed to 0 and users who need the large contiguous areas can enable compaction on locked memory by leaving the default value of 1. To illustrate this problem I wrote a quick test program that mmaps a large number of 1MB files filled with random data. These maps are created locked and read only. Then every other mmap is unmapped and I attempt to allocate huge pages to the static huge page pool. When the compact_unevictable_allowed sysctl is 0, I cannot allocate hugepages after fragmenting memory. When the value is set to 1, allocations succeed. Signed-off-by: Eric B Munson <emunson@akamai.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Christoph Lameter <cl@linux.com> Acked-by: David Rientjes <rientjes@google.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Christoph Lameter <cl@linux.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 23:13:20 +00:00
{
.procname = "compact_unevictable_allowed",
.data = &sysctl_compact_unevictable_allowed,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = &zero,
.extra2 = &one,
},
#endif /* CONFIG_COMPACTION */
{
.procname = "min_free_kbytes",
.data = &min_free_kbytes,
.maxlen = sizeof(min_free_kbytes),
.mode = 0644,
.proc_handler = min_free_kbytes_sysctl_handler,
.extra1 = &zero,
},
{
.procname = "percpu_pagelist_fraction",
.data = &percpu_pagelist_fraction,
.maxlen = sizeof(percpu_pagelist_fraction),
.mode = 0644,
.proc_handler = percpu_pagelist_fraction_sysctl_handler,
mm, pcp: allow restoring percpu_pagelist_fraction default Oleg reports a division by zero error on zero-length write() to the percpu_pagelist_fraction sysctl: divide error: 0000 [#1] SMP DEBUG_PAGEALLOC CPU: 1 PID: 9142 Comm: badarea_io Not tainted 3.15.0-rc2-vm-nfs+ #19 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff8800d5aeb6e0 ti: ffff8800d87a2000 task.ti: ffff8800d87a2000 RIP: 0010: percpu_pagelist_fraction_sysctl_handler+0x84/0x120 RSP: 0018:ffff8800d87a3e78 EFLAGS: 00010246 RAX: 0000000000000f89 RBX: ffff88011f7fd000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000010 RBP: ffff8800d87a3e98 R08: ffffffff81d002c8 R09: ffff8800d87a3f50 R10: 000000000000000b R11: 0000000000000246 R12: 0000000000000060 R13: ffffffff81c3c3e0 R14: ffffffff81cfddf8 R15: ffff8801193b0800 FS: 00007f614f1e9740(0000) GS:ffff88011f440000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007f614f1fa000 CR3: 00000000d9291000 CR4: 00000000000006e0 Call Trace: proc_sys_call_handler+0xb3/0xc0 proc_sys_write+0x14/0x20 vfs_write+0xba/0x1e0 SyS_write+0x46/0xb0 tracesys+0xe1/0xe6 However, if the percpu_pagelist_fraction sysctl is set by the user, it is also impossible to restore it to the kernel default since the user cannot write 0 to the sysctl. This patch allows the user to write 0 to restore the default behavior. It still requires a fraction equal to or larger than 8, however, as stated by the documentation for sanity. If a value in the range [1, 7] is written, the sysctl will return EINVAL. This successfully solves the divide by zero issue at the same time. Signed-off-by: David Rientjes <rientjes@google.com> Reported-by: Oleg Drokin <green@linuxhacker.ru> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-23 20:22:04 +00:00
.extra1 = &zero,
},
#ifdef CONFIG_MMU
{
.procname = "max_map_count",
.data = &sysctl_max_map_count,
.maxlen = sizeof(sysctl_max_map_count),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
#else
{
.procname = "nr_trim_pages",
.data = &sysctl_nr_trim_pages,
.maxlen = sizeof(sysctl_nr_trim_pages),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
#endif
{
.procname = "laptop_mode",
.data = &laptop_mode,
.maxlen = sizeof(laptop_mode),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "block_dump",
.data = &block_dump,
.maxlen = sizeof(block_dump),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = &zero,
},
{
.procname = "vfs_cache_pressure",
.data = &sysctl_vfs_cache_pressure,
.maxlen = sizeof(sysctl_vfs_cache_pressure),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = &zero,
},
#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
{
.procname = "legacy_va_layout",
.data = &sysctl_legacy_va_layout,
.maxlen = sizeof(sysctl_legacy_va_layout),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = &zero,
},
#endif
#ifdef CONFIG_NUMA
{
.procname = "zone_reclaim_mode",
.data = &zone_reclaim_mode,
.maxlen = sizeof(zone_reclaim_mode),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = &zero,
},
{
.procname = "min_unmapped_ratio",
.data = &sysctl_min_unmapped_ratio,
.maxlen = sizeof(sysctl_min_unmapped_ratio),
.mode = 0644,
.proc_handler = sysctl_min_unmapped_ratio_sysctl_handler,
.extra1 = &zero,
.extra2 = &one_hundred,
},
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 06:31:52 +00:00
{
.procname = "min_slab_ratio",
.data = &sysctl_min_slab_ratio,
.maxlen = sizeof(sysctl_min_slab_ratio),
.mode = 0644,
.proc_handler = sysctl_min_slab_ratio_sysctl_handler,
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 06:31:52 +00:00
.extra1 = &zero,
.extra2 = &one_hundred,
},
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma Move the i386 VDSO down into a vma and thus randomize it. Besides the security implications, this feature also helps debuggers, which can COW a vma-backed VDSO just like a normal DSO and can thus do single-stepping and other debugging features. It's good for hypervisors (Xen, VMWare) too, which typically live in the same high-mapped address space as the VDSO, hence whenever the VDSO is used, they get lots of guest pagefaults and have to fix such guest accesses up - which slows things down instead of speeding things up (the primary purpose of the VDSO). There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support for older glibcs that still rely on a prelinked high-mapped VDSO. Newer distributions (using glibc 2.3.3 or later) can turn this option off. Turning it off is also recommended for security reasons: attackers cannot use the predictable high-mapped VDSO page as syscall trampoline anymore. There is a new vdso=[0|1] boot option as well, and a runtime /proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned on/off. (This version of the VDSO-randomization patch also has working ELF coredumping, the previous patch crashed in the coredumping code.) This code is a combined work of the exec-shield VDSO randomization code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell started this patch and i completed it. [akpm@osdl.org: cleanups] [akpm@osdl.org: compile fix] [akpm@osdl.org: compile fix 2] [akpm@osdl.org: compile fix 3] [akpm@osdl.org: revernt MAXMEM change] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@infradead.org> Cc: Gerd Hoffmann <kraxel@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Zachary Amsden <zach@vmware.com> Cc: Andi Kleen <ak@muc.de> Cc: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:50 +00:00
#endif
#ifdef CONFIG_SMP
{
.procname = "stat_interval",
.data = &sysctl_stat_interval,
.maxlen = sizeof(sysctl_stat_interval),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
#endif
#ifdef CONFIG_MMU
{
.procname = "mmap_min_addr",
.data = &dac_mmap_min_addr,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = mmap_min_addr_handler,
},
#endif
change zonelist order: zonelist order selection logic Make zonelist creation policy selectable from sysctl/boot option v6. This patch makes NUMA's zonelist (of pgdat) order selectable. Available order are Default(automatic)/ Node-based / Zone-based. [Default Order] The kernel selects Node-based or Zone-based order automatically. [Node-based Order] This policy treats the locality of memory as the most important parameter. Zonelist order is created by each zone's locality. This means lower zones (ex. ZONE_DMA) can be used before higher zone (ex. ZONE_NORMAL) exhausion. IOW. ZONE_DMA will be in the middle of zonelist. current 2.6.21 kernel uses this. Pros. * A user can expect local memory as much as possible. Cons. * lower zone will be exhansted before higher zone. This may cause OOM_KILL. Maybe suitable if ZONE_DMA is relatively big and you never see OOM_KILL because of ZONE_DMA exhaution and you need the best locality. (example) assume 2 node NUMA. node(0) has ZONE_DMA/ZONE_NORMAL, node(1) has ZONE_NORMAL. *node(0)'s memory allocation order: node(0)'s NORMAL -> node(0)'s DMA -> node(1)'s NORMAL. *node(1)'s memory allocation order: node(1)'s NORMAL -> node(0)'s NORMAL -> node(0)'s DMA. [Zone-based order] This policy treats the zone type as the most important parameter. Zonelist order is created by zone-type order. This means lower zone never be used bofere higher zone exhaustion. IOW. ZONE_DMA will be always at the tail of zonelist. Pros. * OOM_KILL(bacause of lower zone) occurs only if the whole zones are exhausted. Cons. * memory locality may not be best. (example) assume 2 node NUMA. node(0) has ZONE_DMA/ZONE_NORMAL, node(1) has ZONE_NORMAL. *node(0)'s memory allocation order: node(0)'s NORMAL -> node(1)'s NORMAL -> node(0)'s DMA. *node(1)'s memory allocation order: node(1)'s NORMAL -> node(0)'s NORMAL -> node(0)'s DMA. bootoption "numa_zonelist_order=" and proc/sysctl is supporetd. command: %echo N > /proc/sys/vm/numa_zonelist_order Will rebuild zonelist in Node-based order. command: %echo Z > /proc/sys/vm/numa_zonelist_order Will rebuild zonelist in Zone-based order. Thanks to Lee Schermerhorn, he gives me much help and codes. [Lee.Schermerhorn@hp.com: add check_highest_zone to build_zonelists_in_zone_order] [akpm@linux-foundation.org: build fix] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: "jesse.barnes@intel.com" <jesse.barnes@intel.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16 06:38:01 +00:00
#ifdef CONFIG_NUMA
{
.procname = "numa_zonelist_order",
.data = &numa_zonelist_order,
.maxlen = NUMA_ZONELIST_ORDER_LEN,
.mode = 0644,
.proc_handler = numa_zonelist_order_handler,
change zonelist order: zonelist order selection logic Make zonelist creation policy selectable from sysctl/boot option v6. This patch makes NUMA's zonelist (of pgdat) order selectable. Available order are Default(automatic)/ Node-based / Zone-based. [Default Order] The kernel selects Node-based or Zone-based order automatically. [Node-based Order] This policy treats the locality of memory as the most important parameter. Zonelist order is created by each zone's locality. This means lower zones (ex. ZONE_DMA) can be used before higher zone (ex. ZONE_NORMAL) exhausion. IOW. ZONE_DMA will be in the middle of zonelist. current 2.6.21 kernel uses this. Pros. * A user can expect local memory as much as possible. Cons. * lower zone will be exhansted before higher zone. This may cause OOM_KILL. Maybe suitable if ZONE_DMA is relatively big and you never see OOM_KILL because of ZONE_DMA exhaution and you need the best locality. (example) assume 2 node NUMA. node(0) has ZONE_DMA/ZONE_NORMAL, node(1) has ZONE_NORMAL. *node(0)'s memory allocation order: node(0)'s NORMAL -> node(0)'s DMA -> node(1)'s NORMAL. *node(1)'s memory allocation order: node(1)'s NORMAL -> node(0)'s NORMAL -> node(0)'s DMA. [Zone-based order] This policy treats the zone type as the most important parameter. Zonelist order is created by zone-type order. This means lower zone never be used bofere higher zone exhaustion. IOW. ZONE_DMA will be always at the tail of zonelist. Pros. * OOM_KILL(bacause of lower zone) occurs only if the whole zones are exhausted. Cons. * memory locality may not be best. (example) assume 2 node NUMA. node(0) has ZONE_DMA/ZONE_NORMAL, node(1) has ZONE_NORMAL. *node(0)'s memory allocation order: node(0)'s NORMAL -> node(1)'s NORMAL -> node(0)'s DMA. *node(1)'s memory allocation order: node(1)'s NORMAL -> node(0)'s NORMAL -> node(0)'s DMA. bootoption "numa_zonelist_order=" and proc/sysctl is supporetd. command: %echo N > /proc/sys/vm/numa_zonelist_order Will rebuild zonelist in Node-based order. command: %echo Z > /proc/sys/vm/numa_zonelist_order Will rebuild zonelist in Zone-based order. Thanks to Lee Schermerhorn, he gives me much help and codes. [Lee.Schermerhorn@hp.com: add check_highest_zone to build_zonelists_in_zone_order] [akpm@linux-foundation.org: build fix] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: "jesse.barnes@intel.com" <jesse.barnes@intel.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16 06:38:01 +00:00
},
#endif
#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
(defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma Move the i386 VDSO down into a vma and thus randomize it. Besides the security implications, this feature also helps debuggers, which can COW a vma-backed VDSO just like a normal DSO and can thus do single-stepping and other debugging features. It's good for hypervisors (Xen, VMWare) too, which typically live in the same high-mapped address space as the VDSO, hence whenever the VDSO is used, they get lots of guest pagefaults and have to fix such guest accesses up - which slows things down instead of speeding things up (the primary purpose of the VDSO). There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support for older glibcs that still rely on a prelinked high-mapped VDSO. Newer distributions (using glibc 2.3.3 or later) can turn this option off. Turning it off is also recommended for security reasons: attackers cannot use the predictable high-mapped VDSO page as syscall trampoline anymore. There is a new vdso=[0|1] boot option as well, and a runtime /proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned on/off. (This version of the VDSO-randomization patch also has working ELF coredumping, the previous patch crashed in the coredumping code.) This code is a combined work of the exec-shield VDSO randomization code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell started this patch and i completed it. [akpm@osdl.org: cleanups] [akpm@osdl.org: compile fix] [akpm@osdl.org: compile fix 2] [akpm@osdl.org: compile fix 3] [akpm@osdl.org: revernt MAXMEM change] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@infradead.org> Cc: Gerd Hoffmann <kraxel@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Zachary Amsden <zach@vmware.com> Cc: Andi Kleen <ak@muc.de> Cc: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:50 +00:00
{
.procname = "vdso_enabled",
#ifdef CONFIG_X86_32
.data = &vdso32_enabled,
.maxlen = sizeof(vdso32_enabled),
#else
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma Move the i386 VDSO down into a vma and thus randomize it. Besides the security implications, this feature also helps debuggers, which can COW a vma-backed VDSO just like a normal DSO and can thus do single-stepping and other debugging features. It's good for hypervisors (Xen, VMWare) too, which typically live in the same high-mapped address space as the VDSO, hence whenever the VDSO is used, they get lots of guest pagefaults and have to fix such guest accesses up - which slows things down instead of speeding things up (the primary purpose of the VDSO). There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support for older glibcs that still rely on a prelinked high-mapped VDSO. Newer distributions (using glibc 2.3.3 or later) can turn this option off. Turning it off is also recommended for security reasons: attackers cannot use the predictable high-mapped VDSO page as syscall trampoline anymore. There is a new vdso=[0|1] boot option as well, and a runtime /proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned on/off. (This version of the VDSO-randomization patch also has working ELF coredumping, the previous patch crashed in the coredumping code.) This code is a combined work of the exec-shield VDSO randomization code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell started this patch and i completed it. [akpm@osdl.org: cleanups] [akpm@osdl.org: compile fix] [akpm@osdl.org: compile fix 2] [akpm@osdl.org: compile fix 3] [akpm@osdl.org: revernt MAXMEM change] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@infradead.org> Cc: Gerd Hoffmann <kraxel@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Zachary Amsden <zach@vmware.com> Cc: Andi Kleen <ak@muc.de> Cc: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:50 +00:00
.data = &vdso_enabled,
.maxlen = sizeof(vdso_enabled),
#endif
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma Move the i386 VDSO down into a vma and thus randomize it. Besides the security implications, this feature also helps debuggers, which can COW a vma-backed VDSO just like a normal DSO and can thus do single-stepping and other debugging features. It's good for hypervisors (Xen, VMWare) too, which typically live in the same high-mapped address space as the VDSO, hence whenever the VDSO is used, they get lots of guest pagefaults and have to fix such guest accesses up - which slows things down instead of speeding things up (the primary purpose of the VDSO). There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support for older glibcs that still rely on a prelinked high-mapped VDSO. Newer distributions (using glibc 2.3.3 or later) can turn this option off. Turning it off is also recommended for security reasons: attackers cannot use the predictable high-mapped VDSO page as syscall trampoline anymore. There is a new vdso=[0|1] boot option as well, and a runtime /proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned on/off. (This version of the VDSO-randomization patch also has working ELF coredumping, the previous patch crashed in the coredumping code.) This code is a combined work of the exec-shield VDSO randomization code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell started this patch and i completed it. [akpm@osdl.org: cleanups] [akpm@osdl.org: compile fix] [akpm@osdl.org: compile fix 2] [akpm@osdl.org: compile fix 3] [akpm@osdl.org: revernt MAXMEM change] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@infradead.org> Cc: Gerd Hoffmann <kraxel@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Zachary Amsden <zach@vmware.com> Cc: Andi Kleen <ak@muc.de> Cc: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:50 +00:00
.mode = 0644,
.proc_handler = proc_dointvec,
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma Move the i386 VDSO down into a vma and thus randomize it. Besides the security implications, this feature also helps debuggers, which can COW a vma-backed VDSO just like a normal DSO and can thus do single-stepping and other debugging features. It's good for hypervisors (Xen, VMWare) too, which typically live in the same high-mapped address space as the VDSO, hence whenever the VDSO is used, they get lots of guest pagefaults and have to fix such guest accesses up - which slows things down instead of speeding things up (the primary purpose of the VDSO). There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support for older glibcs that still rely on a prelinked high-mapped VDSO. Newer distributions (using glibc 2.3.3 or later) can turn this option off. Turning it off is also recommended for security reasons: attackers cannot use the predictable high-mapped VDSO page as syscall trampoline anymore. There is a new vdso=[0|1] boot option as well, and a runtime /proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned on/off. (This version of the VDSO-randomization patch also has working ELF coredumping, the previous patch crashed in the coredumping code.) This code is a combined work of the exec-shield VDSO randomization code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell started this patch and i completed it. [akpm@osdl.org: cleanups] [akpm@osdl.org: compile fix] [akpm@osdl.org: compile fix 2] [akpm@osdl.org: compile fix 3] [akpm@osdl.org: revernt MAXMEM change] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@infradead.org> Cc: Gerd Hoffmann <kraxel@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Zachary Amsden <zach@vmware.com> Cc: Andi Kleen <ak@muc.de> Cc: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:50 +00:00
.extra1 = &zero,
},
#endif
#ifdef CONFIG_HIGHMEM
{
.procname = "highmem_is_dirtyable",
.data = &vm_highmem_is_dirtyable,
.maxlen = sizeof(vm_highmem_is_dirtyable),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#endif
HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 09:50:15 +00:00
#ifdef CONFIG_MEMORY_FAILURE
{
.procname = "memory_failure_early_kill",
.data = &sysctl_memory_failure_early_kill,
.maxlen = sizeof(sysctl_memory_failure_early_kill),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 09:50:15 +00:00
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "memory_failure_recovery",
.data = &sysctl_memory_failure_recovery,
.maxlen = sizeof(sysctl_memory_failure_recovery),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 09:50:15 +00:00
.extra1 = &zero,
.extra2 = &one,
},
#endif
mm: limit growth of 3% hardcoded other user reserve Add user_reserve_kbytes knob. Limit the growth of the memory reserved for other user processes to min(3% current process size, user_reserve_pages). Only about 8MB is necessary to enable recovery in the default mode, and only a few hundred MB are required even when overcommit is disabled. user_reserve_pages defaults to min(3% free pages, 128MB) I arrived at 128MB by taking the max VSZ of sshd, login, bash, and top ... then adding the RSS of each. This only affects OVERCOMMIT_NEVER mode. Background 1. user reserve __vm_enough_memory reserves a hardcoded 3% of the current process size for other applications when overcommit is disabled. This was done so that a user could recover if they launched a memory hogging process. Without the reserve, a user would easily run into a message such as: bash: fork: Cannot allocate memory 2. admin reserve Additionally, a hardcoded 3% of free memory is reserved for root in both overcommit 'guess' and 'never' modes. This was intended to prevent a scenario where root-cant-log-in and perform recovery operations. Note that this reserve shrinks, and doesn't guarantee a useful reserve. Motivation The two hardcoded memory reserves should be updated to account for current memory sizes. Also, the admin reserve would be more useful if it didn't shrink too much. When the current code was originally written, 1GB was considered "enterprise". Now the 3% reserve can grow to multiple GB on large memory systems, and it only needs to be a few hundred MB at most to enable a user or admin to recover a system with an unwanted memory hogging process. I've found that reducing these reserves is especially beneficial for a specific type of application load: * single application system * one or few processes (e.g. one per core) * allocating all available memory * not initializing every page immediately * long running I've run scientific clusters with this sort of load. A long running job sometimes failed many hours (weeks of CPU time) into a calculation. They weren't initializing all of their memory immediately, and they weren't using calloc, so I put systems into overcommit 'never' mode. These clusters run diskless and have no swap. However, with the current reserves, a user wishing to allocate as much memory as possible to one process may be prevented from using, for example, almost 2GB out of 32GB. The effect is less, but still significant when a user starts a job with one process per core. I have repeatedly seen a set of processes requesting the same amount of memory fail because one of them could not allocate the amount of memory a user would expect to be able to allocate. For example, Message Passing Interfce (MPI) processes, one per core. And it is similar for other parallel programming frameworks. Changing this reserve code will make the overcommit never mode more useful by allowing applications to allocate nearly all of the available memory. Also, the new admin_reserve_kbytes will be safer than the current behavior since the hardcoded 3% of available memory reserve can shrink to something useless in the case where applications have grabbed all available memory. Risks * "bash: fork: Cannot allocate memory" The downside of the first patch-- which creates a tunable user reserve that is only used in overcommit 'never' mode--is that an admin can set it so low that a user may not be able to kill their process, even if they already have a shell prompt. Of course, a user can get in the same predicament with the current 3% reserve--they just have to launch processes until 3% becomes negligible. * root-cant-log-in problem The second patch, adding the tunable rootuser_reserve_pages, allows the admin to shoot themselves in the foot by setting it too small. They can easily get the system into a state where root-can't-log-in. However, the new admin_reserve_kbytes will be safer than the current behavior since the hardcoded 3% of available memory reserve can shrink to something useless in the case where applications have grabbed all available memory. Alternatives * Memory cgroups provide a more flexible way to limit application memory. Not everyone wants to set up cgroups or deal with their overhead. * We could create a fourth overcommit mode which provides smaller reserves. The size of useful reserves may be drastically different depending on the whether the system is embedded or enterprise. * Force users to initialize all of their memory or use calloc. Some users don't want/expect the system to overcommit when they malloc. Overcommit 'never' mode is for this scenario, and it should work well. The new user and admin reserve tunables are simple to use, with low overhead compared to cgroups. The patches preserve current behavior where 3% of memory is less than 128MB, except that the admin reserve doesn't shrink to an unusable size under pressure. The code allows admins to tune for embedded and enterprise usage. FAQ * How is the root-cant-login problem addressed? What happens if admin_reserve_pages is set to 0? Root is free to shoot themselves in the foot by setting admin_reserve_kbytes too low. On x86_64, the minimum useful reserve is: 8MB for overcommit 'guess' 128MB for overcommit 'never' admin_reserve_pages defaults to min(3% free memory, 8MB) So, anyone switching to 'never' mode needs to adjust admin_reserve_pages. * How do you calculate a minimum useful reserve? A user or the admin needs enough memory to login and perform recovery operations, which includes, at a minimum: sshd or login + bash (or some other shell) + top (or ps, kill, etc.) For overcommit 'guess', we can sum resident set sizes (RSS) because we only need enough memory to handle what the recovery programs will typically use. On x86_64 this is about 8MB. For overcommit 'never', we can take the max of their virtual sizes (VSZ) and add the sum of their RSS. We use VSZ instead of RSS because mode forces us to ensure we can fulfill all of the requested memory allocations-- even if the programs only use a fraction of what they ask for. On x86_64 this is about 128MB. When swap is enabled, reserves are useful even when they are as small as 10MB, regardless of overcommit mode. When both swap and overcommit are disabled, then the admin should tune the reserves higher to be absolutley safe. Over 230MB each was safest in my testing. * What happens if user_reserve_pages is set to 0? Note, this only affects overcomitt 'never' mode. Then a user will be able to allocate all available memory minus admin_reserve_kbytes. However, they will easily see a message such as: "bash: fork: Cannot allocate memory" And they won't be able to recover/kill their application. The admin should be able to recover the system if admin_reserve_kbytes is set appropriately. * What's the difference between overcommit 'guess' and 'never'? "Guess" allows an allocation if there are enough free + reclaimable pages. It has a hardcoded 3% of free pages reserved for root. "Never" allows an allocation if there is enough swap + a configurable percentage (default is 50) of physical RAM. It has a hardcoded 3% of free pages reserved for root, like "Guess" mode. It also has a hardcoded 3% of the current process size reserved for additional applications. * Why is overcommit 'guess' not suitable even when an app eventually writes to every page? It takes free pages, file pages, available swap pages, reclaimable slab pages into consideration. In other words, these are all pages available, then why isn't overcommit suitable? Because it only looks at the present state of the system. It does not take into account the memory that other applications have malloced, but haven't initialized yet. It overcommits the system. Test Summary There was little change in behavior in the default overcommit 'guess' mode with swap enabled before and after the patch. This was expected. Systems run most predictably (i.e. no oom kills) in overcommit 'never' mode with swap enabled. This also allowed the most memory to be allocated to a user application. Overcommit 'guess' mode without swap is a bad idea. It is easy to crash the system. None of the other tested combinations crashed. This matches my experience on the Roadrunner supercomputer. Without the tunable user reserve, a system in overcommit 'never' mode and without swap does not allow the admin to recover, although the admin can. With the new tunable reserves, a system in overcommit 'never' mode and without swap can be configured to: 1. maximize user-allocatable memory, running close to the edge of recoverability 2. maximize recoverability, sacrificing allocatable memory to ensure that a user cannot take down a system Test Description Fedora 18 VM - 4 x86_64 cores, 5725MB RAM, 4GB Swap System is booted into multiuser console mode, with unnecessary services turned off. Caches were dropped before each test. Hogs are user memtester processes that attempt to allocate all free memory as reported by /proc/meminfo In overcommit 'never' mode, memory_ratio=100 Test Results 3.9.0-rc1-mm1 Overcommit | Swap | Hogs | MB Got/Wanted | OOMs | User Recovery | Admin Recovery ---------- ---- ---- ------------- ---- ------------- -------------- guess yes 1 5432/5432 no yes yes guess yes 4 5444/5444 1 yes yes guess no 1 5302/5449 no yes yes guess no 4 - crash no no never yes 1 5460/5460 1 yes yes never yes 4 5460/5460 1 yes yes never no 1 5218/5432 no no yes never no 4 5203/5448 no no yes 3.9.0-rc1-mm1-tunablereserves User and Admin Recovery show their respective reserves, if applicable. Overcommit | Swap | Hogs | MB Got/Wanted | OOMs | User Recovery | Admin Recovery ---------- ---- ---- ------------- ---- ------------- -------------- guess yes 1 5419/5419 no - yes 8MB yes guess yes 4 5436/5436 1 - yes 8MB yes guess no 1 5440/5440 * - yes 8MB yes guess no 4 - crash - no 8MB no * process would successfully mlock, then the oom killer would pick it never yes 1 5446/5446 no 10MB yes 20MB yes never yes 4 5456/5456 no 10MB yes 20MB yes never no 1 5387/5429 no 128MB no 8MB barely never no 1 5323/5428 no 226MB barely 8MB barely never no 1 5323/5428 no 226MB barely 8MB barely never no 1 5359/5448 no 10MB no 10MB barely never no 1 5323/5428 no 0MB no 10MB barely never no 1 5332/5428 no 0MB no 50MB yes never no 1 5293/5429 no 0MB no 90MB yes never no 1 5001/5427 no 230MB yes 338MB yes never no 4* 4998/5424 no 230MB yes 338MB yes * more memtesters were launched, able to allocate approximately another 100MB Future Work - Test larger memory systems. - Test an embedded image. - Test other architectures. - Time malloc microbenchmarks. - Would it be useful to be able to set overcommit policy for each memory cgroup? - Some lines are slightly above 80 chars. Perhaps define a macro to convert between pages and kb? Other places in the kernel do this. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: make init_user_reserve() static] Signed-off-by: Andrew Shewmaker <agshew@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-29 22:08:10 +00:00
{
.procname = "user_reserve_kbytes",
.data = &sysctl_user_reserve_kbytes,
.maxlen = sizeof(sysctl_user_reserve_kbytes),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "admin_reserve_kbytes",
.data = &sysctl_admin_reserve_kbytes,
.maxlen = sizeof(sysctl_admin_reserve_kbytes),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
mm: mmap: add new /proc tunable for mmap_base ASLR Address Space Layout Randomization (ASLR) provides a barrier to exploitation of user-space processes in the presence of security vulnerabilities by making it more difficult to find desired code/data which could help an attack. This is done by adding a random offset to the location of regions in the process address space, with a greater range of potential offset values corresponding to better protection/a larger search-space for brute force, but also to greater potential for fragmentation. The offset added to the mmap_base address, which provides the basis for the majority of the mappings for a process, is set once on process exec in arch_pick_mmap_layout() and is done via hard-coded per-arch values, which reflect, hopefully, the best compromise for all systems. The trade-off between increased entropy in the offset value generation and the corresponding increased variability in address space fragmentation is not absolute, however, and some platforms may tolerate higher amounts of entropy. This patch introduces both new Kconfig values and a sysctl interface which may be used to change the amount of entropy used for offset generation on a system. The direct motivation for this change was in response to the libstagefright vulnerabilities that affected Android, specifically to information provided by Google's project zero at: http://googleprojectzero.blogspot.com/2015/09/stagefrightened.html The attack presented therein, by Google's project zero, specifically targeted the limited randomness used to generate the offset added to the mmap_base address in order to craft a brute-force-based attack. Concretely, the attack was against the mediaserver process, which was limited to respawning every 5 seconds, on an arm device. The hard-coded 8 bits used resulted in an average expected success rate of defeating the mmap ASLR after just over 10 minutes (128 tries at 5 seconds a piece). With this patch, and an accompanying increase in the entropy value to 16 bits, the same attack would take an average expected time of over 45 hours (32768 tries), which makes it both less feasible and more likely to be noticed. The introduced Kconfig and sysctl options are limited by per-arch minimum and maximum values, the minimum of which was chosen to match the current hard-coded value and the maximum of which was chosen so as to give the greatest flexibility without generating an invalid mmap_base address, generally a 3-4 bits less than the number of bits in the user-space accessible virtual address space. When decided whether or not to change the default value, a system developer should consider that mmap_base address could be placed anywhere up to 2^(value) bits away from the non-randomized location, which would introduce variable-sized areas above and below the mmap_base address such that the maximum vm_area_struct size may be reduced, preventing very large allocations. This patch (of 4): ASLR only uses as few as 8 bits to generate the random offset for the mmap base address on 32 bit architectures. This value was chosen to prevent a poorly chosen value from dividing the address space in such a way as to prevent large allocations. This may not be an issue on all platforms. Allow the specification of a minimum number of bits so that platforms desiring greater ASLR protection may determine where to place the trade-off. Signed-off-by: Daniel Cashman <dcashman@google.com> Cc: Russell King <linux@arm.linux.org.uk> Acked-by: Kees Cook <keescook@chromium.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Don Zickus <dzickus@redhat.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Heinrich Schuchardt <xypron.glpk@gmx.de> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Rientjes <rientjes@google.com> Cc: Mark Salyzyn <salyzyn@android.com> Cc: Jeff Vander Stoep <jeffv@google.com> Cc: Nick Kralevich <nnk@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hector Marco-Gisbert <hecmargi@upv.es> Cc: Borislav Petkov <bp@suse.de> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:19:53 +00:00
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
{
.procname = "mmap_rnd_bits",
.data = &mmap_rnd_bits,
.maxlen = sizeof(mmap_rnd_bits),
.mode = 0600,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&mmap_rnd_bits_min,
.extra2 = (void *)&mmap_rnd_bits_max,
},
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
{
.procname = "mmap_rnd_compat_bits",
.data = &mmap_rnd_compat_bits,
.maxlen = sizeof(mmap_rnd_compat_bits),
.mode = 0600,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&mmap_rnd_compat_bits_min,
.extra2 = (void *)&mmap_rnd_compat_bits_max,
},
#endif
{ }
};
static struct ctl_table fs_table[] = {
{
.procname = "inode-nr",
.data = &inodes_stat,
fs: bump inode and dentry counters to long This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Dave Chinner <dchinner@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 00:17:53 +00:00
.maxlen = 2*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_inodes,
},
{
.procname = "inode-state",
.data = &inodes_stat,
fs: bump inode and dentry counters to long This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Dave Chinner <dchinner@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 00:17:53 +00:00
.maxlen = 7*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_inodes,
},
{
.procname = "file-nr",
.data = &files_stat,
fs: allow for more than 2^31 files Robin Holt tried to boot a 16TB system and found af_unix was overflowing a 32bit value : <quote> We were seeing a failure which prevented boot. The kernel was incapable of creating either a named pipe or unix domain socket. This comes down to a common kernel function called unix_create1() which does: atomic_inc(&unix_nr_socks); if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; The function get_max_files() is a simple return of files_stat.max_files. files_stat.max_files is a signed integer and is computed in fs/file_table.c's files_init(). n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; In our case, mempages (total_ram_pages) is approx 3,758,096,384 (0xe0000000). That leaves max_files at approximately 1,503,238,553. This causes 2 * get_max_files() to integer overflow. </quote> Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long integers, and change af_unix to use an atomic_long_t instead of atomic_t. get_max_files() is changed to return an unsigned long. get_nr_files() is changed to return a long. unix_nr_socks is changed from atomic_t to atomic_long_t, while not strictly needed to address Robin problem. Before patch (on a 64bit kernel) : # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max -18446744071562067968 After patch: # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648 Reported-by: Robin Holt <holt@sgi.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: David Miller <davem@davemloft.net> Reviewed-by: Robin Holt <holt@sgi.com> Tested-by: Robin Holt <holt@sgi.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:22:44 +00:00
.maxlen = sizeof(files_stat),
.mode = 0444,
.proc_handler = proc_nr_files,
},
{
.procname = "file-max",
.data = &files_stat.max_files,
fs: allow for more than 2^31 files Robin Holt tried to boot a 16TB system and found af_unix was overflowing a 32bit value : <quote> We were seeing a failure which prevented boot. The kernel was incapable of creating either a named pipe or unix domain socket. This comes down to a common kernel function called unix_create1() which does: atomic_inc(&unix_nr_socks); if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; The function get_max_files() is a simple return of files_stat.max_files. files_stat.max_files is a signed integer and is computed in fs/file_table.c's files_init(). n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; In our case, mempages (total_ram_pages) is approx 3,758,096,384 (0xe0000000). That leaves max_files at approximately 1,503,238,553. This causes 2 * get_max_files() to integer overflow. </quote> Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long integers, and change af_unix to use an atomic_long_t instead of atomic_t. get_max_files() is changed to return an unsigned long. get_nr_files() is changed to return a long. unix_nr_socks is changed from atomic_t to atomic_long_t, while not strictly needed to address Robin problem. Before patch (on a 64bit kernel) : # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max -18446744071562067968 After patch: # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648 Reported-by: Robin Holt <holt@sgi.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: David Miller <davem@davemloft.net> Reviewed-by: Robin Holt <holt@sgi.com> Tested-by: Robin Holt <holt@sgi.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:22:44 +00:00
.maxlen = sizeof(files_stat.max_files),
.mode = 0644,
fs: allow for more than 2^31 files Robin Holt tried to boot a 16TB system and found af_unix was overflowing a 32bit value : <quote> We were seeing a failure which prevented boot. The kernel was incapable of creating either a named pipe or unix domain socket. This comes down to a common kernel function called unix_create1() which does: atomic_inc(&unix_nr_socks); if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; The function get_max_files() is a simple return of files_stat.max_files. files_stat.max_files is a signed integer and is computed in fs/file_table.c's files_init(). n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; In our case, mempages (total_ram_pages) is approx 3,758,096,384 (0xe0000000). That leaves max_files at approximately 1,503,238,553. This causes 2 * get_max_files() to integer overflow. </quote> Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long integers, and change af_unix to use an atomic_long_t instead of atomic_t. get_max_files() is changed to return an unsigned long. get_nr_files() is changed to return a long. unix_nr_socks is changed from atomic_t to atomic_long_t, while not strictly needed to address Robin problem. Before patch (on a 64bit kernel) : # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max -18446744071562067968 After patch: # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648 Reported-by: Robin Holt <holt@sgi.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: David Miller <davem@davemloft.net> Reviewed-by: Robin Holt <holt@sgi.com> Tested-by: Robin Holt <holt@sgi.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:22:44 +00:00
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "nr_open",
.data = &sysctl_nr_open,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &sysctl_nr_open_min,
.extra2 = &sysctl_nr_open_max,
},
{
.procname = "dentry-state",
.data = &dentry_stat,
fs: bump inode and dentry counters to long This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Dave Chinner <dchinner@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 00:17:53 +00:00
.maxlen = 6*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_dentry,
},
{
.procname = "overflowuid",
.data = &fs_overflowuid,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
{
.procname = "overflowgid",
.data = &fs_overflowgid,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
#ifdef CONFIG_FILE_LOCKING
{
.procname = "leases-enable",
.data = &leases_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_DNOTIFY
{
.procname = "dir-notify-enable",
.data = &dir_notify_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_MMU
#ifdef CONFIG_FILE_LOCKING
{
.procname = "lease-break-time",
.data = &lease_break_time,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_AIO
{
.procname = "aio-nr",
.data = &aio_nr,
.maxlen = sizeof(aio_nr),
.mode = 0444,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "aio-max-nr",
.data = &aio_max_nr,
.maxlen = sizeof(aio_max_nr),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
#endif /* CONFIG_AIO */
#ifdef CONFIG_INOTIFY_USER
{
.procname = "inotify",
.mode = 0555,
.child = inotify_table,
},
#endif
epoll: introduce resource usage limits It has been thought that the per-user file descriptors limit would also limit the resources that a normal user can request via the epoll interface. Vegard Nossum reported a very simple program (a modified version attached) that can make a normal user to request a pretty large amount of kernel memory, well within the its maximum number of fds. To solve such problem, default limits are now imposed, and /proc based configuration has been introduced. A new directory has been created, named /proc/sys/fs/epoll/ and inside there, there are two configuration points: max_user_instances = Maximum number of devices - per user max_user_watches = Maximum number of "watched" fds - per user The current default for "max_user_watches" limits the memory used by epoll to store "watches", to 1/32 of the amount of the low RAM. As example, a 256MB 32bit machine, will have "max_user_watches" set to roughly 90000. That should be enough to not break existing heavy epoll users. The default value for "max_user_instances" is set to 128, that should be enough too. This also changes the userspace, because a new error code can now come out from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already listed, so that should be ok. [akpm@linux-foundation.org: use get_current_user()] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: <stable@kernel.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Reported-by: Vegard Nossum <vegardno@ifi.uio.no> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 21:13:55 +00:00
#ifdef CONFIG_EPOLL
{
.procname = "epoll",
.mode = 0555,
.child = epoll_table,
},
#endif
#endif
fs: add link restrictions This adds symlink and hardlink restrictions to the Linux VFS. Symlinks: A long-standing class of security issues is the symlink-based time-of-check-time-of-use race, most commonly seen in world-writable directories like /tmp. The common method of exploitation of this flaw is to cross privilege boundaries when following a given symlink (i.e. a root process follows a symlink belonging to another user). For a likely incomplete list of hundreds of examples across the years, please see: http://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=/tmp The solution is to permit symlinks to only be followed when outside a sticky world-writable directory, or when the uid of the symlink and follower match, or when the directory owner matches the symlink's owner. Some pointers to the history of earlier discussion that I could find: 1996 Aug, Zygo Blaxell http://marc.info/?l=bugtraq&m=87602167419830&w=2 1996 Oct, Andrew Tridgell http://lkml.indiana.edu/hypermail/linux/kernel/9610.2/0086.html 1997 Dec, Albert D Cahalan http://lkml.org/lkml/1997/12/16/4 2005 Feb, Lorenzo Hernández García-Hierro http://lkml.indiana.edu/hypermail/linux/kernel/0502.0/1896.html 2010 May, Kees Cook https://lkml.org/lkml/2010/5/30/144 Past objections and rebuttals could be summarized as: - Violates POSIX. - POSIX didn't consider this situation and it's not useful to follow a broken specification at the cost of security. - Might break unknown applications that use this feature. - Applications that break because of the change are easy to spot and fix. Applications that are vulnerable to symlink ToCToU by not having the change aren't. Additionally, no applications have yet been found that rely on this behavior. - Applications should just use mkstemp() or O_CREATE|O_EXCL. - True, but applications are not perfect, and new software is written all the time that makes these mistakes; blocking this flaw at the kernel is a single solution to the entire class of vulnerability. - This should live in the core VFS. - This should live in an LSM. (https://lkml.org/lkml/2010/5/31/135) - This should live in an LSM. - This should live in the core VFS. (https://lkml.org/lkml/2010/8/2/188) Hardlinks: On systems that have user-writable directories on the same partition as system files, a long-standing class of security issues is the hardlink-based time-of-check-time-of-use race, most commonly seen in world-writable directories like /tmp. The common method of exploitation of this flaw is to cross privilege boundaries when following a given hardlink (i.e. a root process follows a hardlink created by another user). Additionally, an issue exists where users can "pin" a potentially vulnerable setuid/setgid file so that an administrator will not actually upgrade a system fully. The solution is to permit hardlinks to only be created when the user is already the existing file's owner, or if they already have read/write access to the existing file. Many Linux users are surprised when they learn they can link to files they have no access to, so this change appears to follow the doctrine of "least surprise". Additionally, this change does not violate POSIX, which states "the implementation may require that the calling process has permission to access the existing file"[1]. This change is known to break some implementations of the "at" daemon, though the version used by Fedora and Ubuntu has been fixed[2] for a while. Otherwise, the change has been undisruptive while in use in Ubuntu for the last 1.5 years. [1] http://pubs.opengroup.org/onlinepubs/9699919799/functions/linkat.html [2] http://anonscm.debian.org/gitweb/?p=collab-maint/at.git;a=commitdiff;h=f4114656c3a6c6f6070e315ffdf940a49eda3279 This patch is based on the patches in Openwall and grsecurity, along with suggestions from Al Viro. I have added a sysctl to enable the protected behavior, and documentation. Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-07-26 00:29:07 +00:00
{
.procname = "protected_symlinks",
.data = &sysctl_protected_symlinks,
.maxlen = sizeof(int),
.mode = 0600,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "protected_hardlinks",
.data = &sysctl_protected_hardlinks,
.maxlen = sizeof(int),
.mode = 0600,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
[PATCH] setuid core dump Add a new `suid_dumpable' sysctl: This value can be used to query and set the core dump mode for setuid or otherwise protected/tainted binaries. The modes are 0 - (default) - traditional behaviour. Any process which has changed privilege levels or is execute only will not be dumped 1 - (debug) - all processes dump core when possible. The core dump is owned by the current user and no security is applied. This is intended for system debugging situations only. Ptrace is unchecked. 2 - (suidsafe) - any binary which normally would not be dumped is dumped readable by root only. This allows the end user to remove such a dump but not access it directly. For security reasons core dumps in this mode will not overwrite one another or other files. This mode is appropriate when adminstrators are attempting to debug problems in a normal environment. (akpm: > > +EXPORT_SYMBOL(suid_dumpable); > > EXPORT_SYMBOL_GPL? No problem to me. > > if (current->euid == current->uid && current->egid == current->gid) > > current->mm->dumpable = 1; > > Should this be SUID_DUMP_USER? Actually the feedback I had from last time was that the SUID_ defines should go because its clearer to follow the numbers. They can go everywhere (and there are lots of places where dumpable is tested/used as a bool in untouched code) > Maybe this should be renamed to `dump_policy' or something. Doing that > would help us catch any code which isn't using the #defines, too. Fair comment. The patch was designed to be easy to maintain for Red Hat rather than for merging. Changing that field would create a gigantic diff because it is used all over the place. ) Signed-off-by: Alan Cox <alan@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 07:09:43 +00:00
{
.procname = "suid_dumpable",
.data = &suid_dumpable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax_coredump,
.extra1 = &zero,
.extra2 = &two,
[PATCH] setuid core dump Add a new `suid_dumpable' sysctl: This value can be used to query and set the core dump mode for setuid or otherwise protected/tainted binaries. The modes are 0 - (default) - traditional behaviour. Any process which has changed privilege levels or is execute only will not be dumped 1 - (debug) - all processes dump core when possible. The core dump is owned by the current user and no security is applied. This is intended for system debugging situations only. Ptrace is unchecked. 2 - (suidsafe) - any binary which normally would not be dumped is dumped readable by root only. This allows the end user to remove such a dump but not access it directly. For security reasons core dumps in this mode will not overwrite one another or other files. This mode is appropriate when adminstrators are attempting to debug problems in a normal environment. (akpm: > > +EXPORT_SYMBOL(suid_dumpable); > > EXPORT_SYMBOL_GPL? No problem to me. > > if (current->euid == current->uid && current->egid == current->gid) > > current->mm->dumpable = 1; > > Should this be SUID_DUMP_USER? Actually the feedback I had from last time was that the SUID_ defines should go because its clearer to follow the numbers. They can go everywhere (and there are lots of places where dumpable is tested/used as a bool in untouched code) > Maybe this should be renamed to `dump_policy' or something. Doing that > would help us catch any code which isn't using the #defines, too. Fair comment. The patch was designed to be easy to maintain for Red Hat rather than for merging. Changing that field would create a gigantic diff because it is used all over the place. ) Signed-off-by: Alan Cox <alan@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 07:09:43 +00:00
},
#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
{
.procname = "binfmt_misc",
.mode = 0555,
.child = sysctl_mount_point,
},
#endif
{
.procname = "pipe-max-size",
.data = &pipe_max_size,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &pipe_proc_fn,
.extra1 = &pipe_min_size,
},
pipe: limit the per-user amount of pages allocated in pipes On no-so-small systems, it is possible for a single process to cause an OOM condition by filling large pipes with data that are never read. A typical process filling 4000 pipes with 1 MB of data will use 4 GB of memory. On small systems it may be tricky to set the pipe max size to prevent this from happening. This patch makes it possible to enforce a per-user soft limit above which new pipes will be limited to a single page, effectively limiting them to 4 kB each, as well as a hard limit above which no new pipes may be created for this user. This has the effect of protecting the system against memory abuse without hurting other users, and still allowing pipes to work correctly though with less data at once. The limit are controlled by two new sysctls : pipe-user-pages-soft, and pipe-user-pages-hard. Both may be disabled by setting them to zero. The default soft limit allows the default number of FDs per process (1024) to create pipes of the default size (64kB), thus reaching a limit of 64MB before starting to create only smaller pipes. With 256 processes limited to 1024 FDs each, this results in 1024*64kB + (256*1024 - 1024) * 4kB = 1084 MB of memory allocated for a user. The hard limit is disabled by default to avoid breaking existing applications that make intensive use of pipes (eg: for splicing). Reported-by: socketpair@gmail.com Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Mitigates: CVE-2013-4312 (Linux 2.0+) Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Willy Tarreau <w@1wt.eu> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-01-18 15:36:09 +00:00
{
.procname = "pipe-user-pages-hard",
.data = &pipe_user_pages_hard,
.maxlen = sizeof(pipe_user_pages_hard),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "pipe-user-pages-soft",
.data = &pipe_user_pages_soft,
.maxlen = sizeof(pipe_user_pages_soft),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{ }
};
static struct ctl_table debug_table[] = {
#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE
{
.procname = "exception-trace",
.data = &show_unhandled_signals,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#endif
#if defined(CONFIG_OPTPROBES)
{
.procname = "kprobes-optimization",
.data = &sysctl_kprobes_optimization,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_kprobes_optimization_handler,
.extra1 = &zero,
.extra2 = &one,
},
#endif
{ }
};
static struct ctl_table dev_table[] = {
{ }
};
int __init sysctl_init(void)
{
sysctl: suppress kmemleak messages register_sysctl_table() is a strange function, as it makes internal allocations (a header) to register a sysctl_table. This header is a handle to the table that is created, and can be used to unregister the table. But if the table is permanent and never unregistered, the header acts the same as a static variable. Unfortunately, this allocation of memory that is never expected to be freed fools kmemleak in thinking that we have leaked memory. For those sysctl tables that are never unregistered, and have no pointer referencing them, kmemleak will think that these are memory leaks: unreferenced object 0xffff880079fb9d40 (size 192): comm "swapper/0", pid 0, jiffies 4294667316 (age 12614.152s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8146b590>] kmemleak_alloc+0x73/0x98 [<ffffffff8110a935>] kmemleak_alloc_recursive.constprop.42+0x16/0x18 [<ffffffff8110b852>] __kmalloc+0x107/0x153 [<ffffffff8116fa72>] kzalloc.constprop.8+0xe/0x10 [<ffffffff811703c9>] __register_sysctl_paths+0xe1/0x160 [<ffffffff81170463>] register_sysctl_paths+0x1b/0x1d [<ffffffff8117047d>] register_sysctl_table+0x18/0x1a [<ffffffff81afb0a1>] sysctl_init+0x10/0x14 [<ffffffff81b05a6f>] proc_sys_init+0x2f/0x31 [<ffffffff81b0584c>] proc_root_init+0xa5/0xa7 [<ffffffff81ae5b7e>] start_kernel+0x3d0/0x40a [<ffffffff81ae52a7>] x86_64_start_reservations+0xae/0xb2 [<ffffffff81ae53ad>] x86_64_start_kernel+0x102/0x111 [<ffffffffffffffff>] 0xffffffffffffffff The sysctl_base_table used by sysctl itself is one such instance that registers the table to never be unregistered. Use kmemleak_not_leak() to suppress the kmemleak false positive. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-30 21:42:48 +00:00
struct ctl_table_header *hdr;
hdr = register_sysctl_table(sysctl_base_table);
kmemleak_not_leak(hdr);
return 0;
}
#endif /* CONFIG_SYSCTL */
/*
* /proc/sys support
*/
#ifdef CONFIG_PROC_SYSCTL
static int _proc_do_string(char *data, int maxlen, int write,
char __user *buffer,
size_t *lenp, loff_t *ppos)
{
size_t len;
char __user *p;
char c;
if (!data || !maxlen || !*lenp) {
*lenp = 0;
return 0;
}
if (write) {
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) {
/* Only continue writes not past the end of buffer. */
len = strlen(data);
if (len > maxlen - 1)
len = maxlen - 1;
if (*ppos > len)
return 0;
len = *ppos;
} else {
/* Start writing from beginning of buffer. */
len = 0;
}
*ppos += *lenp;
p = buffer;
while ((p - buffer) < *lenp && len < maxlen - 1) {
if (get_user(c, p++))
return -EFAULT;
if (c == 0 || c == '\n')
break;
data[len++] = c;
}
data[len] = 0;
} else {
len = strlen(data);
if (len > maxlen)
len = maxlen;
if (*ppos > len) {
*lenp = 0;
return 0;
}
data += *ppos;
len -= *ppos;
if (len > *lenp)
len = *lenp;
if (len)
if (copy_to_user(buffer, data, len))
return -EFAULT;
if (len < *lenp) {
if (put_user('\n', buffer + len))
return -EFAULT;
len++;
}
*lenp = len;
*ppos += len;
}
return 0;
}
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
static void warn_sysctl_write(struct ctl_table *table)
{
pr_warn_once("%s wrote to %s when file position was not 0!\n"
"This will not be supported in the future. To silence this\n"
"warning, set kernel.sysctl_writes_strict = -1\n",
current->comm, table->procname);
}
/**
* proc_dostring - read a string sysctl
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Reads/writes a string from/to the user buffer. If the kernel
* buffer provided is not large enough to hold the string, the
* string is truncated. The copied string is %NULL-terminated.
* If the string is being read by the user process, it is copied
* and a newline '\n' is added. It is truncated if the buffer is
* not large enough.
*
* Returns 0 on success.
*/
int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN)
warn_sysctl_write(table);
return _proc_do_string((char *)(table->data), table->maxlen, write,
(char __user *)buffer, lenp, ppos);
}
static size_t proc_skip_spaces(char **buf)
{
size_t ret;
char *tmp = skip_spaces(*buf);
ret = tmp - *buf;
*buf = tmp;
return ret;
}
static void proc_skip_char(char **buf, size_t *size, const char v)
{
while (*size) {
if (**buf != v)
break;
(*size)--;
(*buf)++;
}
}
#define TMPBUFLEN 22
/**
* proc_get_long - reads an ASCII formatted integer from a user buffer
*
* @buf: a kernel buffer
* @size: size of the kernel buffer
* @val: this is where the number will be stored
* @neg: set to %TRUE if number is negative
* @perm_tr: a vector which contains the allowed trailers
* @perm_tr_len: size of the perm_tr vector
* @tr: pointer to store the trailer character
*
* In case of success %0 is returned and @buf and @size are updated with
* the amount of bytes read. If @tr is non-NULL and a trailing
* character exists (size is non-zero after returning from this
* function), @tr is updated with the trailing character.
*/
static int proc_get_long(char **buf, size_t *size,
unsigned long *val, bool *neg,
const char *perm_tr, unsigned perm_tr_len, char *tr)
{
int len;
char *p, tmp[TMPBUFLEN];
if (!*size)
return -EINVAL;
len = *size;
if (len > TMPBUFLEN - 1)
len = TMPBUFLEN - 1;
memcpy(tmp, *buf, len);
tmp[len] = 0;
p = tmp;
if (*p == '-' && *size > 1) {
*neg = true;
p++;
} else
*neg = false;
if (!isdigit(*p))
return -EINVAL;
*val = simple_strtoul(p, &p, 0);
len = p - tmp;
/* We don't know if the next char is whitespace thus we may accept
* invalid integers (e.g. 1234...a) or two integers instead of one
* (e.g. 123...1). So lets not allow such large numbers. */
if (len == TMPBUFLEN - 1)
return -EINVAL;
if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len))
return -EINVAL;
if (tr && (len < *size))
*tr = *p;
*buf += len;
*size -= len;
return 0;
}
/**
* proc_put_long - converts an integer to a decimal ASCII formatted string
*
* @buf: the user buffer
* @size: the size of the user buffer
* @val: the integer to be converted
* @neg: sign of the number, %TRUE for negative
*
* In case of success %0 is returned and @buf and @size are updated with
* the amount of bytes written.
*/
static int proc_put_long(void __user **buf, size_t *size, unsigned long val,
bool neg)
{
int len;
char tmp[TMPBUFLEN], *p = tmp;
sprintf(p, "%s%lu", neg ? "-" : "", val);
len = strlen(tmp);
if (len > *size)
len = *size;
if (copy_to_user(*buf, tmp, len))
return -EFAULT;
*size -= len;
*buf += len;
return 0;
}
#undef TMPBUFLEN
static int proc_put_char(void __user **buf, size_t *size, char c)
{
if (*size) {
char __user **buffer = (char __user **)buf;
if (put_user(c, *buffer))
return -EFAULT;
(*size)--, (*buffer)++;
*buf = *buffer;
}
return 0;
}
static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
if (write) {
if (*negp) {
if (*lvalp > (unsigned long) INT_MAX + 1)
return -EINVAL;
*valp = -*lvalp;
} else {
if (*lvalp > (unsigned long) INT_MAX)
return -EINVAL;
*valp = *lvalp;
}
} else {
int val = *valp;
if (val < 0) {
*negp = true;
*lvalp = -(unsigned long)val;
} else {
*negp = false;
*lvalp = (unsigned long)val;
}
}
return 0;
}
static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
int write, void __user *buffer,
size_t *lenp, loff_t *ppos,
int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
int write, void *data),
void *data)
{
int *i, vleft, first = 1, err = 0;
size_t left;
char *kbuf = NULL, *p;
if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
*lenp = 0;
return 0;
}
i = (int *) tbl_data;
vleft = table->maxlen / sizeof(*i);
left = *lenp;
if (!conv)
conv = do_proc_dointvec_conv;
if (write) {
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
if (*ppos) {
switch (sysctl_writes_strict) {
case SYSCTL_WRITES_STRICT:
goto out;
case SYSCTL_WRITES_WARN:
warn_sysctl_write(table);
break;
default:
break;
}
}
if (left > PAGE_SIZE - 1)
left = PAGE_SIZE - 1;
p = kbuf = memdup_user_nul(buffer, left);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
}
for (; left && vleft--; i++, first=0) {
unsigned long lval;
bool neg;
if (write) {
left -= proc_skip_spaces(&p);
if (!left)
break;
err = proc_get_long(&p, &left, &lval, &neg,
proc_wspace_sep,
sizeof(proc_wspace_sep), NULL);
if (err)
break;
if (conv(&neg, &lval, i, 1, data)) {
err = -EINVAL;
break;
}
} else {
if (conv(&neg, &lval, i, 0, data)) {
err = -EINVAL;
break;
}
if (!first)
err = proc_put_char(&buffer, &left, '\t');
if (err)
break;
err = proc_put_long(&buffer, &left, lval, neg);
if (err)
break;
}
}
if (!write && !first && left && !err)
err = proc_put_char(&buffer, &left, '\n');
if (write && !err && left)
left -= proc_skip_spaces(&p);
if (write) {
kfree(kbuf);
if (first)
return err ? : -EINVAL;
}
*lenp -= left;
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
out:
*ppos += *lenp;
return err;
}
static int do_proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos,
int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
int write, void *data),
void *data)
{
return __do_proc_dointvec(table->data, table, write,
buffer, lenp, ppos, conv, data);
}
/**
* proc_dointvec - read a vector of integers
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Reads/writes up to table->maxlen/sizeof(unsigned int) integer
* values from/to the user buffer, treated as an ASCII string.
*
* Returns 0 on success.
*/
int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return do_proc_dointvec(table,write,buffer,lenp,ppos,
NULL,NULL);
}
/*
* Taint values can only be increased
* This means we can safely use a temporary.
*/
static int proc_taint(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
unsigned long tmptaint = get_taint();
int err;
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
t = *table;
t.data = &tmptaint;
err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
if (err < 0)
return err;
if (write) {
/*
* Poor man's atomic or. Not worth adding a primitive
* to everyone's atomic.h for this
*/
int i;
for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) {
if ((tmptaint >> i) & 1)
add_taint(i, LOCKDEP_STILL_OK);
}
}
return err;
}
#ifdef CONFIG_PRINTK
static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
#endif
struct do_proc_dointvec_minmax_conv_param {
int *min;
int *max;
};
static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
struct do_proc_dointvec_minmax_conv_param *param = data;
if (write) {
int val = *negp ? -*lvalp : *lvalp;
if ((param->min && *param->min > val) ||
(param->max && *param->max < val))
return -EINVAL;
*valp = val;
} else {
int val = *valp;
if (val < 0) {
*negp = true;
*lvalp = -(unsigned long)val;
} else {
*negp = false;
*lvalp = (unsigned long)val;
}
}
return 0;
}
/**
* proc_dointvec_minmax - read a vector of integers with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Reads/writes up to table->maxlen/sizeof(unsigned int) integer
* values from/to the user buffer, treated as an ASCII string.
*
* This routine will ensure the values are within the range specified by
* table->extra1 (min) and table->extra2 (max).
*
* Returns 0 on success.
*/
int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct do_proc_dointvec_minmax_conv_param param = {
.min = (int *) table->extra1,
.max = (int *) table->extra2,
};
return do_proc_dointvec(table, write, buffer, lenp, ppos,
do_proc_dointvec_minmax_conv, &param);
}
static void validate_coredump_safety(void)
{
#ifdef CONFIG_COREDUMP
if (suid_dumpable == SUID_DUMP_ROOT &&
core_pattern[0] != '/' && core_pattern[0] != '|') {
printk(KERN_WARNING "Unsafe core_pattern used with "\
"suid_dumpable=2. Pipe handler or fully qualified "\
"core dump path required.\n");
}
#endif
}
static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!error)
validate_coredump_safety();
return error;
}
#ifdef CONFIG_COREDUMP
static int proc_dostring_coredump(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int error = proc_dostring(table, write, buffer, lenp, ppos);
if (!error)
validate_coredump_safety();
return error;
}
#endif
static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos,
unsigned long convmul,
unsigned long convdiv)
{
unsigned long *i, *min, *max;
int vleft, first = 1, err = 0;
size_t left;
char *kbuf = NULL, *p;
if (!data || !table->maxlen || !*lenp || (*ppos && !write)) {
*lenp = 0;
return 0;
}
i = (unsigned long *) data;
min = (unsigned long *) table->extra1;
max = (unsigned long *) table->extra2;
vleft = table->maxlen / sizeof(unsigned long);
left = *lenp;
if (write) {
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
if (*ppos) {
switch (sysctl_writes_strict) {
case SYSCTL_WRITES_STRICT:
goto out;
case SYSCTL_WRITES_WARN:
warn_sysctl_write(table);
break;
default:
break;
}
}
if (left > PAGE_SIZE - 1)
left = PAGE_SIZE - 1;
p = kbuf = memdup_user_nul(buffer, left);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
}
for (; left && vleft--; i++, first = 0) {
unsigned long val;
if (write) {
bool neg;
left -= proc_skip_spaces(&p);
err = proc_get_long(&p, &left, &val, &neg,
proc_wspace_sep,
sizeof(proc_wspace_sep), NULL);
if (err)
break;
if (neg)
continue;
if ((min && val < *min) || (max && val > *max))
continue;
*i = val;
} else {
val = convdiv * (*i) / convmul;
if (!first) {
err = proc_put_char(&buffer, &left, '\t');
if (err)
break;
}
err = proc_put_long(&buffer, &left, val, false);
if (err)
break;
}
}
if (!write && !first && left && !err)
err = proc_put_char(&buffer, &left, '\n');
if (write && !err)
left -= proc_skip_spaces(&p);
if (write) {
kfree(kbuf);
if (first)
return err ? : -EINVAL;
}
*lenp -= left;
sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-06 21:37:19 +00:00
out:
*ppos += *lenp;
return err;
}
static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos,
unsigned long convmul,
unsigned long convdiv)
{
return __do_proc_doulongvec_minmax(table->data, table, write,
buffer, lenp, ppos, convmul, convdiv);
}
/**
* proc_doulongvec_minmax - read a vector of long integers with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
* values from/to the user buffer, treated as an ASCII string.
*
* This routine will ensure the values are within the range specified by
* table->extra1 (min) and table->extra2 (max).
*
* Returns 0 on success.
*/
int proc_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
}
/**
* proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
* values from/to the user buffer, treated as an ASCII string. The values
* are treated as milliseconds, and converted to jiffies when they are stored.
*
* This routine will ensure the values are within the range specified by
* table->extra1 (min) and table->extra2 (max).
*
* Returns 0 on success.
*/
int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
return do_proc_doulongvec_minmax(table, write, buffer,
lenp, ppos, HZ, 1000l);
}
static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
if (write) {
if (*lvalp > LONG_MAX / HZ)
return 1;
*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
} else {
int val = *valp;
unsigned long lval;
if (val < 0) {
*negp = true;
lval = -(unsigned long)val;
} else {
*negp = false;
lval = (unsigned long)val;
}
*lvalp = lval / HZ;
}
return 0;
}
static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
if (write) {
if (USER_HZ < HZ && *lvalp > (LONG_MAX / HZ) * USER_HZ)
return 1;
*valp = clock_t_to_jiffies(*negp ? -*lvalp : *lvalp);
} else {
int val = *valp;
unsigned long lval;
if (val < 0) {
*negp = true;
lval = -(unsigned long)val;
} else {
*negp = false;
lval = (unsigned long)val;
}
*lvalp = jiffies_to_clock_t(lval);
}
return 0;
}
static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
if (write) {
unsigned long jif = msecs_to_jiffies(*negp ? -*lvalp : *lvalp);
if (jif > INT_MAX)
return 1;
*valp = (int)jif;
} else {
int val = *valp;
unsigned long lval;
if (val < 0) {
*negp = true;
lval = -(unsigned long)val;
} else {
*negp = false;
lval = (unsigned long)val;
}
*lvalp = jiffies_to_msecs(lval);
}
return 0;
}
/**
* proc_dointvec_jiffies - read a vector of integers as seconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Reads/writes up to table->maxlen/sizeof(unsigned int) integer
* values from/to the user buffer, treated as an ASCII string.
* The values read are assumed to be in seconds, and are converted into
* jiffies.
*
* Returns 0 on success.
*/
int proc_dointvec_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return do_proc_dointvec(table,write,buffer,lenp,ppos,
do_proc_dointvec_jiffies_conv,NULL);
}
/**
* proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: pointer to the file position
*
* Reads/writes up to table->maxlen/sizeof(unsigned int) integer
* values from/to the user buffer, treated as an ASCII string.
* The values read are assumed to be in 1/USER_HZ seconds, and
* are converted into jiffies.
*
* Returns 0 on success.
*/
int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return do_proc_dointvec(table,write,buffer,lenp,ppos,
do_proc_dointvec_userhz_jiffies_conv,NULL);
}
/**
* proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
* @ppos: the current position in the file
*
* Reads/writes up to table->maxlen/sizeof(unsigned int) integer
* values from/to the user buffer, treated as an ASCII string.
* The values read are assumed to be in 1/1000 seconds, and
* are converted into jiffies.
*
* Returns 0 on success.
*/
int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return do_proc_dointvec(table, write, buffer, lenp, ppos,
do_proc_dointvec_ms_jiffies_conv, NULL);
}
static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct pid *new_pid;
pid_t tmp;
int r;
tmp = pid_vnr(cad_pid);
r = __do_proc_dointvec(&tmp, table, write, buffer,
lenp, ppos, NULL, NULL);
if (r || !write)
return r;
new_pid = find_get_pid(tmp);
if (!new_pid)
return -ESRCH;
put_pid(xchg(&cad_pid, new_pid));
return 0;
}
/**
* proc_do_large_bitmap - read/write from/to a large bitmap
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* The bitmap is stored at table->data and the bitmap length (in bits)
* in table->maxlen.
*
* We use a range comma separated format (e.g. 1,3-4,10-10) so that
* large bitmaps may be represented in a compact manner. Writing into
* the file will clear the bitmap then update it with the given input.
*
* Returns 0 on success.
*/
int proc_do_large_bitmap(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int err = 0;
bool first = 1;
size_t left = *lenp;
unsigned long bitmap_len = table->maxlen;
unsigned long *bitmap = *(unsigned long **) table->data;
unsigned long *tmp_bitmap = NULL;
char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
if (!bitmap || !bitmap_len || !left || (*ppos && !write)) {
*lenp = 0;
return 0;
}
if (write) {
char *kbuf, *p;
if (left > PAGE_SIZE - 1)
left = PAGE_SIZE - 1;
p = kbuf = memdup_user_nul(buffer, left);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
tmp_bitmap = kzalloc(BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long),
GFP_KERNEL);
if (!tmp_bitmap) {
kfree(kbuf);
return -ENOMEM;
}
proc_skip_char(&p, &left, '\n');
while (!err && left) {
unsigned long val_a, val_b;
bool neg;
err = proc_get_long(&p, &left, &val_a, &neg, tr_a,
sizeof(tr_a), &c);
if (err)
break;
if (val_a >= bitmap_len || neg) {
err = -EINVAL;
break;
}
val_b = val_a;
if (left) {
p++;
left--;
}
if (c == '-') {
err = proc_get_long(&p, &left, &val_b,
&neg, tr_b, sizeof(tr_b),
&c);
if (err)
break;
if (val_b >= bitmap_len || neg ||
val_a > val_b) {
err = -EINVAL;
break;
}
if (left) {
p++;
left--;
}
}
bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1);
first = 0;
proc_skip_char(&p, &left, '\n');
}
kfree(kbuf);
} else {
unsigned long bit_a, bit_b = 0;
while (left) {
bit_a = find_next_bit(bitmap, bitmap_len, bit_b);
if (bit_a >= bitmap_len)
break;
bit_b = find_next_zero_bit(bitmap, bitmap_len,
bit_a + 1) - 1;
if (!first) {
err = proc_put_char(&buffer, &left, ',');
if (err)
break;
}
err = proc_put_long(&buffer, &left, bit_a, false);
if (err)
break;
if (bit_a != bit_b) {
err = proc_put_char(&buffer, &left, '-');
if (err)
break;
err = proc_put_long(&buffer, &left, bit_b, false);
if (err)
break;
}
first = 0; bit_b++;
}
if (!err)
err = proc_put_char(&buffer, &left, '\n');
}
if (!err) {
if (write) {
if (*ppos)
bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len);
else
bitmap_copy(bitmap, tmp_bitmap, bitmap_len);
}
kfree(tmp_bitmap);
*lenp -= left;
*ppos += *lenp;
return 0;
} else {
kfree(tmp_bitmap);
return err;
}
}
#else /* CONFIG_PROC_SYSCTL */
int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_dointvec_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
#endif /* CONFIG_PROC_SYSCTL */
/*
* No sense putting this after each symbol definition, twice,
* exception granted :-)
*/
EXPORT_SYMBOL(proc_dointvec);
EXPORT_SYMBOL(proc_dointvec_jiffies);
EXPORT_SYMBOL(proc_dointvec_minmax);
EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
EXPORT_SYMBOL(proc_dostring);
EXPORT_SYMBOL(proc_doulongvec_minmax);
EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);