2019-05-19 20:08:55 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* linux/kernel/panic.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function is used through-out the kernel (including mm and fs)
|
|
|
|
* to indicate a major problem.
|
|
|
|
*/
|
2009-03-13 18:14:06 +08:00
|
|
|
#include <linux/debug_locks.h>
|
2017-02-09 01:51:35 +08:00
|
|
|
#include <linux/sched/debug.h>
|
2009-03-13 18:14:06 +08:00
|
|
|
#include <linux/interrupt.h>
|
2019-09-26 07:47:45 +08:00
|
|
|
#include <linux/kgdb.h>
|
2009-10-16 20:09:18 +08:00
|
|
|
#include <linux/kmsg_dump.h>
|
2009-03-13 18:14:06 +08:00
|
|
|
#include <linux/kallsyms.h>
|
|
|
|
#include <linux/notifier.h>
|
panic: avoid deadlocks in re-entrant console drivers
From printk()/serial console point of view panic() is special, because
it may force CPU to re-enter printk() or/and serial console driver.
Therefore, some of serial consoles drivers are re-entrant. E.g. 8250:
serial8250_console_write()
{
if (port->sysrq)
locked = 0;
else if (oops_in_progress)
locked = spin_trylock_irqsave(&port->lock, flags);
else
spin_lock_irqsave(&port->lock, flags);
...
}
panic() does set oops_in_progress via bust_spinlocks(1), so in theory
we should be able to re-enter serial console driver from panic():
CPU0
<NMI>
uart_console_write()
serial8250_console_write() // if (oops_in_progress)
// spin_trylock_irqsave()
call_console_drivers()
console_unlock()
console_flush_on_panic()
bust_spinlocks(1) // oops_in_progress++
panic()
<NMI/>
spin_lock_irqsave(&port->lock, flags) // spin_lock_irqsave()
serial8250_console_write()
call_console_drivers()
console_unlock()
printk()
...
However, this does not happen and we deadlock in serial console on
port->lock spinlock. And the problem is that console_flush_on_panic()
called after bust_spinlocks(0):
void panic(const char *fmt, ...)
{
bust_spinlocks(1);
...
bust_spinlocks(0);
console_flush_on_panic();
...
}
bust_spinlocks(0) decrements oops_in_progress, so oops_in_progress
can go back to zero. Thus even re-entrant console drivers will simply
spin on port->lock spinlock. Given that port->lock may already be
locked either by a stopped CPU, or by the very same CPU we execute
panic() on (for instance, NMI panic() on printing CPU) the system
deadlocks and does not reboot.
Fix this by removing bust_spinlocks(0), so oops_in_progress is always
set in panic() now and, thus, re-entrant console drivers will trylock
the port->lock instead of spinning on it forever, when we call them
from console_flush_on_panic().
Link: http://lkml.kernel.org/r/20181025101036.6823-1-sergey.senozhatsky@gmail.com
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Daniel Wang <wonderfly@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk>
Cc: Jiri Slaby <jslaby@suse.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: linux-serial@vger.kernel.org
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-10-25 18:10:36 +08:00
|
|
|
#include <linux/vt_kern.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/module.h>
|
2009-03-13 18:14:06 +08:00
|
|
|
#include <linux/random.h>
|
2013-06-15 04:21:43 +08:00
|
|
|
#include <linux/ftrace.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/reboot.h>
|
2009-03-13 18:14:06 +08:00
|
|
|
#include <linux/delay.h>
|
|
|
|
#include <linux/kexec.h>
|
2021-07-01 09:54:59 +08:00
|
|
|
#include <linux/panic_notifier.h>
|
2009-03-13 18:14:06 +08:00
|
|
|
#include <linux/sched.h>
|
2022-10-09 03:59:14 +08:00
|
|
|
#include <linux/string_helpers.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/sysrq.h>
|
2009-03-13 18:14:06 +08:00
|
|
|
#include <linux/init.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/nmi.h>
|
2015-11-07 08:32:58 +08:00
|
|
|
#include <linux/console.h>
|
2016-03-18 05:23:04 +08:00
|
|
|
#include <linux/bug.h>
|
locking/refcounts, x86/asm: Implement fast refcount overflow protection
This implements refcount_t overflow protection on x86 without a noticeable
performance impact, though without the fuller checking of REFCOUNT_FULL.
This is done by duplicating the existing atomic_t refcount implementation
but with normally a single instruction added to detect if the refcount
has gone negative (e.g. wrapped past INT_MAX or below zero). When detected,
the handler saturates the refcount_t to INT_MIN / 2. With this overflow
protection, the erroneous reference release that would follow a wrap back
to zero is blocked from happening, avoiding the class of refcount-overflow
use-after-free vulnerabilities entirely.
Only the overflow case of refcounting can be perfectly protected, since
it can be detected and stopped before the reference is freed and left to
be abused by an attacker. There isn't a way to block early decrements,
and while REFCOUNT_FULL stops increment-from-zero cases (which would
be the state _after_ an early decrement and stops potential double-free
conditions), this fast implementation does not, since it would require
the more expensive cmpxchg loops. Since the overflow case is much more
common (e.g. missing a "put" during an error path), this protection
provides real-world protection. For example, the two public refcount
overflow use-after-free exploits published in 2016 would have been
rendered unexploitable:
http://perception-point.io/2016/01/14/analysis-and-exploitation-of-a-linux-kernel-vulnerability-cve-2016-0728/
http://cyseclabs.com/page?n=02012016
This implementation does, however, notice an unchecked decrement to zero
(i.e. caller used refcount_dec() instead of refcount_dec_and_test() and it
resulted in a zero). Decrements under zero are noticed (since they will
have resulted in a negative value), though this only indicates that a
use-after-free may have already happened. Such notifications are likely
avoidable by an attacker that has already exploited a use-after-free
vulnerability, but it's better to have them reported than allow such
conditions to remain universally silent.
On first overflow detection, the refcount value is reset to INT_MIN / 2
(which serves as a saturation value) and a report and stack trace are
produced. When operations detect only negative value results (such as
changing an already saturated value), saturation still happens but no
notification is performed (since the value was already saturated).
On the matter of races, since the entire range beyond INT_MAX but before
0 is negative, every operation at INT_MIN / 2 will trap, leaving no
overflow-only race condition.
As for performance, this implementation adds a single "js" instruction
to the regular execution flow of a copy of the standard atomic_t refcount
operations. (The non-"and_test" refcount_dec() function, which is uncommon
in regular refcount design patterns, has an additional "jz" instruction
to detect reaching exactly zero.) Since this is a forward jump, it is by
default the non-predicted path, which will be reinforced by dynamic branch
prediction. The result is this protection having virtually no measurable
change in performance over standard atomic_t operations. The error path,
located in .text.unlikely, saves the refcount location and then uses UD0
to fire a refcount exception handler, which resets the refcount, handles
reporting, and returns to regular execution. This keeps the changes to
.text size minimal, avoiding return jumps and open-coded calls to the
error reporting routine.
Example assembly comparison:
refcount_inc() before:
.text:
ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp)
refcount_inc() after:
.text:
ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp)
ffffffff8154614d: 0f 88 80 d5 17 00 js ffffffff816c36d3
...
.text.unlikely:
ffffffff816c36d3: 48 8d 4d f4 lea -0xc(%rbp),%rcx
ffffffff816c36d7: 0f ff (bad)
These are the cycle counts comparing a loop of refcount_inc() from 1
to INT_MAX and back down to 0 (via refcount_dec_and_test()), between
unprotected refcount_t (atomic_t), fully protected REFCOUNT_FULL
(refcount_t-full), and this overflow-protected refcount (refcount_t-fast):
2147483646 refcount_inc()s and 2147483647 refcount_dec_and_test()s:
cycles protections
atomic_t 82249267387 none
refcount_t-fast 82211446892 overflow, untested dec-to-zero
refcount_t-full 144814735193 overflow, untested dec-to-zero, inc-from-zero
This code is a modified version of the x86 PAX_REFCOUNT atomic_t
overflow defense from the last public patch of PaX/grsecurity, based
on my understanding of the code. Changes or omissions from the original
code are mine and don't reflect the original grsecurity/PaX code. Thanks
to PaX Team for various suggestions for improvement for repurposing this
code to be a refcount-only protection.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Elena Reshetova <elena.reshetova@intel.com>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Hans Liljestrand <ishkamiel@gmail.com>
Cc: James Bottomley <James.Bottomley@hansenpartnership.com>
Cc: Jann Horn <jannh@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Serge E. Hallyn <serge@hallyn.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: arozansk@redhat.com
Cc: axboe@kernel.dk
Cc: kernel-hardening@lists.openwall.com
Cc: linux-arch <linux-arch@vger.kernel.org>
Link: http://lkml.kernel.org/r/20170815161924.GA133115@beast
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-16 00:19:24 +08:00
|
|
|
#include <linux/ratelimit.h>
|
2017-11-18 07:27:03 +08:00
|
|
|
#include <linux/debugfs.h>
|
2022-11-18 07:43:26 +08:00
|
|
|
#include <linux/sysfs.h>
|
2023-01-26 23:08:31 +08:00
|
|
|
#include <linux/context_tracking.h>
|
2022-01-20 10:09:56 +08:00
|
|
|
#include <trace/events/error_report.h>
|
2017-11-18 07:27:03 +08:00
|
|
|
#include <asm/sections.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-11 09:03:28 +08:00
|
|
|
#define PANIC_TIMER_STEP 100
|
|
|
|
#define PANIC_BLINK_SPD 18
|
|
|
|
|
2020-06-08 12:40:48 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/*
|
|
|
|
* Should we dump all CPUs backtraces in an oops event?
|
|
|
|
* Defaults to 0, can be changed via sysctl.
|
|
|
|
*/
|
2022-02-18 18:59:12 +08:00
|
|
|
static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace;
|
|
|
|
#else
|
|
|
|
#define sysctl_oops_all_cpu_backtrace 0
|
2020-06-08 12:40:48 +08:00
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
|
2012-04-11 20:15:29 +08:00
|
|
|
int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
|
2018-04-11 07:32:33 +08:00
|
|
|
static unsigned long tainted_mask =
|
2022-05-04 04:55:00 +08:00
|
|
|
IS_ENABLED(CONFIG_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
|
2006-03-23 19:00:57 +08:00
|
|
|
static int pause_on_oops;
|
|
|
|
static int pause_on_oops_flag;
|
|
|
|
static DEFINE_SPINLOCK(pause_on_oops_lock);
|
2015-07-01 05:57:46 +08:00
|
|
|
bool crash_kexec_post_notifiers;
|
2014-12-11 07:45:50 +08:00
|
|
|
int panic_on_warn __read_mostly;
|
2020-06-08 12:40:17 +08:00
|
|
|
unsigned long panic_on_taint;
|
|
|
|
bool panic_on_taint_nousertaint = false;
|
2022-11-18 07:43:25 +08:00
|
|
|
static unsigned int warn_limit __read_mostly;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-11-26 07:23:04 +08:00
|
|
|
int panic_timeout = CONFIG_PANIC_TIMEOUT;
|
ACPI, APEI, Generic Hardware Error Source POLL/IRQ/NMI notification type support
Generic Hardware Error Source provides a way to report platform
hardware errors (such as that from chipset). It works in so called
"Firmware First" mode, that is, hardware errors are reported to
firmware firstly, then reported to Linux by firmware. This way, some
non-standard hardware error registers or non-standard hardware link
can be checked by firmware to produce more valuable hardware error
information for Linux.
This patch adds POLL/IRQ/NMI notification types support.
Because the memory area used to transfer hardware error information
from BIOS to Linux can be determined only in NMI, IRQ or timer
handler, but general ioremap can not be used in atomic context, so a
special version of atomic ioremap is implemented for that.
Known issue:
- Error information can not be printed for recoverable errors notified
via NMI, because printk is not NMI-safe. Will fix this via delay
printing to IRQ context via irq_work or make printk NMI-safe.
v2:
- adjust printk format per comments.
Signed-off-by: Huang Ying <ying.huang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
2011-01-12 14:44:55 +08:00
|
|
|
EXPORT_SYMBOL_GPL(panic_timeout);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2019-01-04 07:28:17 +08:00
|
|
|
#define PANIC_PRINT_TASK_INFO 0x00000001
|
|
|
|
#define PANIC_PRINT_MEM_INFO 0x00000002
|
|
|
|
#define PANIC_PRINT_TIMER_INFO 0x00000004
|
|
|
|
#define PANIC_PRINT_LOCK_INFO 0x00000008
|
|
|
|
#define PANIC_PRINT_FTRACE_INFO 0x00000010
|
2019-05-18 05:31:50 +08:00
|
|
|
#define PANIC_PRINT_ALL_PRINTK_MSG 0x00000020
|
2022-03-24 07:07:06 +08:00
|
|
|
#define PANIC_PRINT_ALL_CPU_BT 0x00000040
|
2019-01-04 07:28:20 +08:00
|
|
|
unsigned long panic_print;
|
2019-01-04 07:28:17 +08:00
|
|
|
|
[PATCH] Notifier chain update: API changes
The kernel's implementation of notifier chains is unsafe. There is no
protection against entries being added to or removed from a chain while the
chain is in use. The issues were discussed in this thread:
http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2
We noticed that notifier chains in the kernel fall into two basic usage
classes:
"Blocking" chains are always called from a process context
and the callout routines are allowed to sleep;
"Atomic" chains can be called from an atomic context and
the callout routines are not allowed to sleep.
We decided to codify this distinction and make it part of the API. Therefore
this set of patches introduces three new, parallel APIs: one for blocking
notifiers, one for atomic notifiers, and one for "raw" notifiers (which is
really just the old API under a new name). New kinds of data structures are
used for the heads of the chains, and new routines are defined for
registration, unregistration, and calling a chain. The three APIs are
explained in include/linux/notifier.h and their implementation is in
kernel/sys.c.
With atomic and blocking chains, the implementation guarantees that the chain
links will not be corrupted and that chain callers will not get messed up by
entries being added or removed. For raw chains the implementation provides no
guarantees at all; users of this API must provide their own protections. (The
idea was that situations may come up where the assumptions of the atomic and
blocking APIs are not appropriate, so it should be possible for users to
handle these things in their own way.)
There are some limitations, which should not be too hard to live with. For
atomic/blocking chains, registration and unregistration must always be done in
a process context since the chain is protected by a mutex/rwsem. Also, a
callout routine for a non-raw chain must not try to register or unregister
entries on its own chain. (This did happen in a couple of places and the code
had to be changed to avoid it.)
Since atomic chains may be called from within an NMI handler, they cannot use
spinlocks for synchronization. Instead we use RCU. The overhead falls almost
entirely in the unregister routine, which is okay since unregistration is much
less frequent that calling a chain.
Here is the list of chains that we adjusted and their classifications. None
of them use the raw API, so for the moment it is only a placeholder.
ATOMIC CHAINS
-------------
arch/i386/kernel/traps.c: i386die_chain
arch/ia64/kernel/traps.c: ia64die_chain
arch/powerpc/kernel/traps.c: powerpc_die_chain
arch/sparc64/kernel/traps.c: sparc64die_chain
arch/x86_64/kernel/traps.c: die_chain
drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list
kernel/panic.c: panic_notifier_list
kernel/profile.c: task_free_notifier
net/bluetooth/hci_core.c: hci_notifier
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain
net/ipv6/addrconf.c: inet6addr_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain
net/netlink/af_netlink.c: netlink_chain
BLOCKING CHAINS
---------------
arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain
arch/s390/kernel/process.c: idle_chain
arch/x86_64/kernel/process.c idle_notifier
drivers/base/memory.c: memory_chain
drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list
drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list
drivers/macintosh/adb.c: adb_client_list
drivers/macintosh/via-pmu.c sleep_notifier_list
drivers/macintosh/via-pmu68k.c sleep_notifier_list
drivers/macintosh/windfarm_core.c wf_client_list
drivers/usb/core/notify.c usb_notifier_list
drivers/video/fbmem.c fb_notifier_list
kernel/cpu.c cpu_chain
kernel/module.c module_notify_list
kernel/profile.c munmap_notifier
kernel/profile.c task_exit_notifier
kernel/sys.c reboot_notifier_list
net/core/dev.c netdev_chain
net/decnet/dn_dev.c: dnaddr_chain
net/ipv4/devinet.c: inetaddr_chain
It's possible that some of these classifications are wrong. If they are,
please let us know or submit a patch to fix them. Note that any chain that
gets called very frequently should be atomic, because the rwsem read-locking
used for blocking chains is very likely to incur cache misses on SMP systems.
(However, if the chain's callout routines may sleep then the chain cannot be
atomic.)
The patch set was written by Alan Stern and Chandra Seetharaman, incorporating
material written by Keith Owens and suggestions from Paul McKenney and Andrew
Morton.
[jes@sgi.com: restructure the notifier chain initialization macros]
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Jes Sorensen <jes@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
|
|
|
ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
EXPORT_SYMBOL(panic_notifier_list);
|
|
|
|
|
2022-11-18 07:43:21 +08:00
|
|
|
#ifdef CONFIG_SYSCTL
|
2022-02-18 18:59:12 +08:00
|
|
|
static struct ctl_table kern_panic_table[] = {
|
2022-11-18 07:43:21 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2022-02-18 18:59:12 +08:00
|
|
|
{
|
|
|
|
.procname = "oops_all_cpu_backtrace",
|
|
|
|
.data = &sysctl_oops_all_cpu_backtrace,
|
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec_minmax,
|
|
|
|
.extra1 = SYSCTL_ZERO,
|
|
|
|
.extra2 = SYSCTL_ONE,
|
|
|
|
},
|
2022-11-18 07:43:21 +08:00
|
|
|
#endif
|
2022-11-18 07:43:25 +08:00
|
|
|
{
|
|
|
|
.procname = "warn_limit",
|
|
|
|
.data = &warn_limit,
|
|
|
|
.maxlen = sizeof(warn_limit),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_douintvec,
|
|
|
|
},
|
2022-02-18 18:59:12 +08:00
|
|
|
{ }
|
|
|
|
};
|
|
|
|
|
|
|
|
static __init int kernel_panic_sysctls_init(void)
|
|
|
|
{
|
|
|
|
register_sysctl_init("kernel", kern_panic_table);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
late_initcall(kernel_panic_sysctls_init);
|
|
|
|
#endif
|
|
|
|
|
2022-11-18 07:43:26 +08:00
|
|
|
static atomic_t warn_count = ATOMIC_INIT(0);
|
|
|
|
|
|
|
|
#ifdef CONFIG_SYSFS
|
|
|
|
static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr,
|
|
|
|
char *page)
|
|
|
|
{
|
|
|
|
return sysfs_emit(page, "%d\n", atomic_read(&warn_count));
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count);
|
|
|
|
|
|
|
|
static __init int kernel_panic_sysfs_init(void)
|
|
|
|
{
|
|
|
|
sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
late_initcall(kernel_panic_sysfs_init);
|
|
|
|
#endif
|
|
|
|
|
2010-08-11 09:03:28 +08:00
|
|
|
static long no_blink(int state)
|
2010-03-06 05:42:55 +08:00
|
|
|
{
|
2010-08-11 09:03:28 +08:00
|
|
|
return 0;
|
2010-03-06 05:42:55 +08:00
|
|
|
}
|
|
|
|
|
2010-08-11 09:03:28 +08:00
|
|
|
/* Returns how long it waited in ms */
|
|
|
|
long (*panic_blink)(int state);
|
|
|
|
EXPORT_SYMBOL(panic_blink);
|
|
|
|
|
2012-01-13 09:20:18 +08:00
|
|
|
/*
|
|
|
|
* Stop ourself in panic -- architecture code may override this
|
|
|
|
*/
|
2023-04-13 07:49:35 +08:00
|
|
|
void __weak __noreturn panic_smp_self_stop(void)
|
2012-01-13 09:20:18 +08:00
|
|
|
{
|
|
|
|
while (1)
|
|
|
|
cpu_relax();
|
|
|
|
}
|
|
|
|
|
panic, x86: Allow CPUs to save registers even if looping in NMI context
Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(),
sends an NMI IPI to CPUs which haven't called panic() to stop them,
save their register information and do some cleanups for crash dumping.
However, if such a CPU is infinitely looping in NMI context, we fail to
save its register information into the crash dump.
For example, this can happen when unknown NMIs are broadcast to all
CPUs as follows:
CPU 0 CPU 1
=========================== ==========================
receive an unknown NMI
unknown_nmi_error()
panic() receive an unknown NMI
spin_trylock(&panic_lock) unknown_nmi_error()
crash_kexec() panic()
spin_trylock(&panic_lock)
panic_smp_self_stop()
infinite loop
kdump_nmi_shootdown_cpus()
issue NMI IPI -----------> blocked until IRET
infinite loop...
Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is
blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET,
so the NMI is not handled and the callback function to save registers is
never called.
In practice, this can happen on some servers which broadcast NMIs to all
CPUs when the NMI button is pushed.
To save registers in this case, we need to:
a) Return from NMI handler instead of looping infinitely
or
b) Call the callback function directly from the infinite loop
Inherently, a) is risky because NMI is also used to prevent corrupted
data from being propagated to devices. So, we chose b).
This patch does the following:
1. Move the infinite looping of CPUs which haven't called panic() in NMI
context (actually done by panic_smp_self_stop()) outside of panic() to
enable us to refer pt_regs. Please note that panic_smp_self_stop() is
still used for normal context.
2. Call a callback of kdump_nmi_shootdown_cpus() directly to save
registers and do some cleanups after setting waiting_for_crash_ipi which
is used for counting down the number of CPUs which handled the callback
Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Aaron Tomlin <atomlin@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: David Hildenbrand <dahi@linux.vnet.ibm.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Javi Merino <javi.merino@arm.com>
Cc: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: kexec@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: lkml <linux-kernel@vger.kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs
[ Cleanup comments, fixup formatting. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:10 +08:00
|
|
|
/*
|
|
|
|
* Stop ourselves in NMI context if another CPU has already panicked. Arch code
|
|
|
|
* may override this to prepare for crash dumping, e.g. save regs info.
|
|
|
|
*/
|
2023-04-13 07:49:36 +08:00
|
|
|
void __weak __noreturn nmi_panic_self_stop(struct pt_regs *regs)
|
panic, x86: Allow CPUs to save registers even if looping in NMI context
Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(),
sends an NMI IPI to CPUs which haven't called panic() to stop them,
save their register information and do some cleanups for crash dumping.
However, if such a CPU is infinitely looping in NMI context, we fail to
save its register information into the crash dump.
For example, this can happen when unknown NMIs are broadcast to all
CPUs as follows:
CPU 0 CPU 1
=========================== ==========================
receive an unknown NMI
unknown_nmi_error()
panic() receive an unknown NMI
spin_trylock(&panic_lock) unknown_nmi_error()
crash_kexec() panic()
spin_trylock(&panic_lock)
panic_smp_self_stop()
infinite loop
kdump_nmi_shootdown_cpus()
issue NMI IPI -----------> blocked until IRET
infinite loop...
Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is
blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET,
so the NMI is not handled and the callback function to save registers is
never called.
In practice, this can happen on some servers which broadcast NMIs to all
CPUs when the NMI button is pushed.
To save registers in this case, we need to:
a) Return from NMI handler instead of looping infinitely
or
b) Call the callback function directly from the infinite loop
Inherently, a) is risky because NMI is also used to prevent corrupted
data from being propagated to devices. So, we chose b).
This patch does the following:
1. Move the infinite looping of CPUs which haven't called panic() in NMI
context (actually done by panic_smp_self_stop()) outside of panic() to
enable us to refer pt_regs. Please note that panic_smp_self_stop() is
still used for normal context.
2. Call a callback of kdump_nmi_shootdown_cpus() directly to save
registers and do some cleanups after setting waiting_for_crash_ipi which
is used for counting down the number of CPUs which handled the callback
Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Aaron Tomlin <atomlin@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: David Hildenbrand <dahi@linux.vnet.ibm.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Javi Merino <javi.merino@arm.com>
Cc: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: kexec@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: lkml <linux-kernel@vger.kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs
[ Cleanup comments, fixup formatting. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:10 +08:00
|
|
|
{
|
|
|
|
panic_smp_self_stop();
|
|
|
|
}
|
|
|
|
|
2016-10-12 04:54:23 +08:00
|
|
|
/*
|
|
|
|
* Stop other CPUs in panic. Architecture dependent code may override this
|
|
|
|
* with more suitable version. For example, if the architecture supports
|
|
|
|
* crash dump, it should save registers of each stopped CPU and disable
|
|
|
|
* per-CPU features such as virtualization extensions.
|
|
|
|
*/
|
|
|
|
void __weak crash_smp_send_stop(void)
|
|
|
|
{
|
|
|
|
static int cpus_stopped;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function can be called twice in panic path, but obviously
|
|
|
|
* we execute this only once.
|
|
|
|
*/
|
|
|
|
if (cpus_stopped)
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Note smp_send_stop is the usual smp shutdown function, which
|
|
|
|
* unfortunately means it may not be hardened to work in a panic
|
|
|
|
* situation.
|
|
|
|
*/
|
|
|
|
smp_send_stop();
|
|
|
|
cpus_stopped = 1;
|
|
|
|
}
|
|
|
|
|
2015-12-14 18:19:09 +08:00
|
|
|
atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID);
|
|
|
|
|
2016-03-23 05:27:17 +08:00
|
|
|
/*
|
|
|
|
* A variant of panic() called from NMI context. We return if we've already
|
|
|
|
* panicked on this CPU. If another CPU already panicked, loop in
|
|
|
|
* nmi_panic_self_stop() which can provide architecture dependent code such
|
|
|
|
* as saving register state for crash dump.
|
|
|
|
*/
|
|
|
|
void nmi_panic(struct pt_regs *regs, const char *msg)
|
|
|
|
{
|
|
|
|
int old_cpu, cpu;
|
|
|
|
|
|
|
|
cpu = raw_smp_processor_id();
|
|
|
|
old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu);
|
|
|
|
|
|
|
|
if (old_cpu == PANIC_CPU_INVALID)
|
|
|
|
panic("%s", msg);
|
|
|
|
else if (old_cpu != cpu)
|
|
|
|
nmi_panic_self_stop(regs);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(nmi_panic);
|
|
|
|
|
panic: move panic_print before kmsg dumpers
The panic_print setting allows users to collect more information in a
panic event, like memory stats, tasks, CPUs backtraces, etc. This is an
interesting debug mechanism, but currently the print event happens *after*
kmsg_dump(), meaning that pstore, for example, cannot collect a dmesg with
the panic_print extra information.
This patch changes that in 2 steps:
(a) The panic_print setting allows to replay the existing kernel log
buffer to the console (bit 5), besides the extra information dump.
This functionality makes sense only at the end of the panic()
function. So, we hereby allow to distinguish the two situations by a
new boolean parameter in the function panic_print_sys_info().
(b) With the above change, we can safely call panic_print_sys_info()
before kmsg_dump(), allowing to dump the extra information when using
pstore or other kmsg dumpers.
The additional messages from panic_print could overwrite the oldest
messages when the buffer is full. The only reasonable solution is to use
a large enough log buffer, hence we added an advice into the kernel
parameters documentation about that.
Link: https://lkml.kernel.org/r/20220214141308.841525-1-gpiccoli@igalia.com
Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Acked-by: Baoquan He <bhe@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Feng Tang <feng.tang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-24 07:07:09 +08:00
|
|
|
static void panic_print_sys_info(bool console_flush)
|
2019-01-04 07:28:17 +08:00
|
|
|
{
|
panic: move panic_print before kmsg dumpers
The panic_print setting allows users to collect more information in a
panic event, like memory stats, tasks, CPUs backtraces, etc. This is an
interesting debug mechanism, but currently the print event happens *after*
kmsg_dump(), meaning that pstore, for example, cannot collect a dmesg with
the panic_print extra information.
This patch changes that in 2 steps:
(a) The panic_print setting allows to replay the existing kernel log
buffer to the console (bit 5), besides the extra information dump.
This functionality makes sense only at the end of the panic()
function. So, we hereby allow to distinguish the two situations by a
new boolean parameter in the function panic_print_sys_info().
(b) With the above change, we can safely call panic_print_sys_info()
before kmsg_dump(), allowing to dump the extra information when using
pstore or other kmsg dumpers.
The additional messages from panic_print could overwrite the oldest
messages when the buffer is full. The only reasonable solution is to use
a large enough log buffer, hence we added an advice into the kernel
parameters documentation about that.
Link: https://lkml.kernel.org/r/20220214141308.841525-1-gpiccoli@igalia.com
Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Acked-by: Baoquan He <bhe@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Feng Tang <feng.tang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-24 07:07:09 +08:00
|
|
|
if (console_flush) {
|
|
|
|
if (panic_print & PANIC_PRINT_ALL_PRINTK_MSG)
|
|
|
|
console_flush_on_panic(CONSOLE_REPLAY_ALL);
|
|
|
|
return;
|
|
|
|
}
|
2019-05-18 05:31:50 +08:00
|
|
|
|
2019-01-04 07:28:17 +08:00
|
|
|
if (panic_print & PANIC_PRINT_TASK_INFO)
|
|
|
|
show_state();
|
|
|
|
|
|
|
|
if (panic_print & PANIC_PRINT_MEM_INFO)
|
2023-06-30 14:22:52 +08:00
|
|
|
show_mem();
|
2019-01-04 07:28:17 +08:00
|
|
|
|
|
|
|
if (panic_print & PANIC_PRINT_TIMER_INFO)
|
|
|
|
sysrq_timer_list_show();
|
|
|
|
|
|
|
|
if (panic_print & PANIC_PRINT_LOCK_INFO)
|
|
|
|
debug_show_all_locks();
|
|
|
|
|
|
|
|
if (panic_print & PANIC_PRINT_FTRACE_INFO)
|
|
|
|
ftrace_dump(DUMP_ALL);
|
|
|
|
}
|
|
|
|
|
2022-11-18 07:43:24 +08:00
|
|
|
void check_panic_on_warn(const char *origin)
|
|
|
|
{
|
2022-12-17 04:26:57 +08:00
|
|
|
unsigned int limit;
|
|
|
|
|
2022-11-18 07:43:24 +08:00
|
|
|
if (panic_on_warn)
|
|
|
|
panic("%s: panic_on_warn set ...\n", origin);
|
2022-11-18 07:43:25 +08:00
|
|
|
|
2022-12-17 04:26:57 +08:00
|
|
|
limit = READ_ONCE(warn_limit);
|
|
|
|
if (atomic_inc_return(&warn_count) >= limit && limit)
|
2022-11-18 07:43:25 +08:00
|
|
|
panic("%s: system warned too often (kernel.warn_limit is %d)",
|
2022-12-17 04:26:57 +08:00
|
|
|
origin, limit);
|
2022-11-18 07:43:24 +08:00
|
|
|
}
|
|
|
|
|
2023-02-27 00:08:38 +08:00
|
|
|
/*
|
|
|
|
* Helper that triggers the NMI backtrace (if set in panic_print)
|
|
|
|
* and then performs the secondary CPUs shutdown - we cannot have
|
|
|
|
* the NMI backtrace after the CPUs are off!
|
|
|
|
*/
|
|
|
|
static void panic_other_cpus_shutdown(bool crash_kexec)
|
|
|
|
{
|
|
|
|
if (panic_print & PANIC_PRINT_ALL_CPU_BT)
|
|
|
|
trigger_all_cpu_backtrace();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Note that smp_send_stop() is the usual SMP shutdown function,
|
|
|
|
* which unfortunately may not be hardened to work in a panic
|
|
|
|
* situation. If we want to do crash dump after notifier calls
|
|
|
|
* and kmsg_dump, we will need architecture dependent extra
|
|
|
|
* bits in addition to stopping other CPUs, hence we rely on
|
|
|
|
* crash_smp_send_stop() for that.
|
|
|
|
*/
|
|
|
|
if (!crash_kexec)
|
|
|
|
smp_send_stop();
|
|
|
|
else
|
|
|
|
crash_smp_send_stop();
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
|
|
|
* panic - halt the system
|
|
|
|
* @fmt: The text string to print
|
|
|
|
*
|
|
|
|
* Display a message, then perform cleanups.
|
|
|
|
*
|
|
|
|
* This function never returns.
|
|
|
|
*/
|
2012-01-13 09:17:17 +08:00
|
|
|
void panic(const char *fmt, ...)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
static char buf[1024];
|
|
|
|
va_list args;
|
2018-10-31 06:07:17 +08:00
|
|
|
long i, i_next = 0, len;
|
2010-08-11 09:03:28 +08:00
|
|
|
int state = 0;
|
2015-12-14 18:19:09 +08:00
|
|
|
int old_cpu, this_cpu;
|
2016-08-03 05:06:13 +08:00
|
|
|
bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2022-03-24 07:06:51 +08:00
|
|
|
if (panic_on_warn) {
|
|
|
|
/*
|
|
|
|
* This thread may hit another WARN() in the panic path.
|
|
|
|
* Resetting this prevents additional WARN() from panicking the
|
|
|
|
* system on this thread. Other threads are blocked by the
|
|
|
|
* panic_mutex in panic().
|
|
|
|
*/
|
|
|
|
panic_on_warn = 0;
|
|
|
|
}
|
|
|
|
|
2012-07-31 05:39:58 +08:00
|
|
|
/*
|
|
|
|
* Disable local interrupts. This will prevent panic_smp_self_stop
|
|
|
|
* from deadlocking the first cpu that invokes the panic, since
|
|
|
|
* there is nothing to prevent an interrupt handler (that runs
|
2015-12-14 18:19:09 +08:00
|
|
|
* after setting panic_cpu) from invoking panic() again.
|
2012-07-31 05:39:58 +08:00
|
|
|
*/
|
|
|
|
local_irq_disable();
|
2019-10-07 08:58:00 +08:00
|
|
|
preempt_disable_notrace();
|
2012-07-31 05:39:58 +08:00
|
|
|
|
2005-06-26 05:57:52 +08:00
|
|
|
/*
|
2009-03-13 18:14:06 +08:00
|
|
|
* It's possible to come here directly from a panic-assertion and
|
|
|
|
* not have preempt disabled. Some functions called from here want
|
2005-06-26 05:57:52 +08:00
|
|
|
* preempt to be disabled. No point enabling it later though...
|
2012-01-13 09:20:18 +08:00
|
|
|
*
|
|
|
|
* Only one CPU is allowed to execute the panic code from here. For
|
|
|
|
* multiple parallel invocations of panic, all other CPUs either
|
|
|
|
* stop themself or will wait until they are stopped by the 1st CPU
|
|
|
|
* with smp_send_stop().
|
2015-12-14 18:19:09 +08:00
|
|
|
*
|
|
|
|
* `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which
|
|
|
|
* comes here, so go ahead.
|
|
|
|
* `old_cpu == this_cpu' means we came from nmi_panic() which sets
|
|
|
|
* panic_cpu to this CPU. In this case, this is also the 1st CPU.
|
2005-06-26 05:57:52 +08:00
|
|
|
*/
|
2015-12-14 18:19:09 +08:00
|
|
|
this_cpu = raw_smp_processor_id();
|
|
|
|
old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
|
|
|
|
|
|
|
|
if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu)
|
2012-01-13 09:20:18 +08:00
|
|
|
panic_smp_self_stop();
|
2005-06-26 05:57:52 +08:00
|
|
|
|
2010-05-27 05:44:24 +08:00
|
|
|
console_verbose();
|
2005-04-17 06:20:36 +08:00
|
|
|
bust_spinlocks(1);
|
|
|
|
va_start(args, fmt);
|
2018-10-31 06:07:17 +08:00
|
|
|
len = vscnprintf(buf, sizeof(buf), fmt, args);
|
2005-04-17 06:20:36 +08:00
|
|
|
va_end(args);
|
2018-10-31 06:07:17 +08:00
|
|
|
|
|
|
|
if (len && buf[len - 1] == '\n')
|
|
|
|
buf[len - 1] = '\0';
|
|
|
|
|
2014-04-08 06:39:03 +08:00
|
|
|
pr_emerg("Kernel panic - not syncing: %s\n", buf);
|
2008-02-14 16:07:01 +08:00
|
|
|
#ifdef CONFIG_DEBUG_BUGVERBOSE
|
2012-01-13 09:20:30 +08:00
|
|
|
/*
|
|
|
|
* Avoid nested stack-dumping if a panic occurs during oops processing
|
|
|
|
*/
|
2012-04-13 03:49:17 +08:00
|
|
|
if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
|
2012-01-13 09:20:30 +08:00
|
|
|
dump_stack();
|
2008-02-14 16:07:01 +08:00
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2019-09-26 07:47:45 +08:00
|
|
|
/*
|
|
|
|
* If kgdb is enabled, give it a chance to run before we stop all
|
|
|
|
* the other CPUs or else we won't be able to debug processes left
|
|
|
|
* running on them.
|
|
|
|
*/
|
|
|
|
kgdb_panic(buf);
|
|
|
|
|
2005-06-26 05:57:52 +08:00
|
|
|
/*
|
|
|
|
* If we have crashed and we have a crash kernel loaded let it handle
|
|
|
|
* everything else.
|
2014-06-07 05:37:07 +08:00
|
|
|
* If we want to run this after calling panic_notifiers, pass
|
|
|
|
* the "crash_kexec_post_notifiers" option to the kernel.
|
2015-12-14 18:19:11 +08:00
|
|
|
*
|
|
|
|
* Bypass the panic_cpu check and call __crash_kexec directly.
|
2005-06-26 05:57:52 +08:00
|
|
|
*/
|
2023-02-27 00:08:38 +08:00
|
|
|
if (!_crash_kexec_post_notifiers)
|
2015-12-14 18:19:11 +08:00
|
|
|
__crash_kexec(NULL);
|
2005-06-26 05:57:52 +08:00
|
|
|
|
2023-02-27 00:08:38 +08:00
|
|
|
panic_other_cpus_shutdown(_crash_kexec_post_notifiers);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-09-12 05:25:49 +08:00
|
|
|
/*
|
|
|
|
* Run any panic handlers, including those that might need to
|
|
|
|
* add information to the kmsg dump output.
|
|
|
|
*/
|
[PATCH] Notifier chain update: API changes
The kernel's implementation of notifier chains is unsafe. There is no
protection against entries being added to or removed from a chain while the
chain is in use. The issues were discussed in this thread:
http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2
We noticed that notifier chains in the kernel fall into two basic usage
classes:
"Blocking" chains are always called from a process context
and the callout routines are allowed to sleep;
"Atomic" chains can be called from an atomic context and
the callout routines are not allowed to sleep.
We decided to codify this distinction and make it part of the API. Therefore
this set of patches introduces three new, parallel APIs: one for blocking
notifiers, one for atomic notifiers, and one for "raw" notifiers (which is
really just the old API under a new name). New kinds of data structures are
used for the heads of the chains, and new routines are defined for
registration, unregistration, and calling a chain. The three APIs are
explained in include/linux/notifier.h and their implementation is in
kernel/sys.c.
With atomic and blocking chains, the implementation guarantees that the chain
links will not be corrupted and that chain callers will not get messed up by
entries being added or removed. For raw chains the implementation provides no
guarantees at all; users of this API must provide their own protections. (The
idea was that situations may come up where the assumptions of the atomic and
blocking APIs are not appropriate, so it should be possible for users to
handle these things in their own way.)
There are some limitations, which should not be too hard to live with. For
atomic/blocking chains, registration and unregistration must always be done in
a process context since the chain is protected by a mutex/rwsem. Also, a
callout routine for a non-raw chain must not try to register or unregister
entries on its own chain. (This did happen in a couple of places and the code
had to be changed to avoid it.)
Since atomic chains may be called from within an NMI handler, they cannot use
spinlocks for synchronization. Instead we use RCU. The overhead falls almost
entirely in the unregister routine, which is okay since unregistration is much
less frequent that calling a chain.
Here is the list of chains that we adjusted and their classifications. None
of them use the raw API, so for the moment it is only a placeholder.
ATOMIC CHAINS
-------------
arch/i386/kernel/traps.c: i386die_chain
arch/ia64/kernel/traps.c: ia64die_chain
arch/powerpc/kernel/traps.c: powerpc_die_chain
arch/sparc64/kernel/traps.c: sparc64die_chain
arch/x86_64/kernel/traps.c: die_chain
drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list
kernel/panic.c: panic_notifier_list
kernel/profile.c: task_free_notifier
net/bluetooth/hci_core.c: hci_notifier
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain
net/ipv6/addrconf.c: inet6addr_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain
net/netlink/af_netlink.c: netlink_chain
BLOCKING CHAINS
---------------
arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain
arch/s390/kernel/process.c: idle_chain
arch/x86_64/kernel/process.c idle_notifier
drivers/base/memory.c: memory_chain
drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list
drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list
drivers/macintosh/adb.c: adb_client_list
drivers/macintosh/via-pmu.c sleep_notifier_list
drivers/macintosh/via-pmu68k.c sleep_notifier_list
drivers/macintosh/windfarm_core.c wf_client_list
drivers/usb/core/notify.c usb_notifier_list
drivers/video/fbmem.c fb_notifier_list
kernel/cpu.c cpu_chain
kernel/module.c module_notify_list
kernel/profile.c munmap_notifier
kernel/profile.c task_exit_notifier
kernel/sys.c reboot_notifier_list
net/core/dev.c netdev_chain
net/decnet/dn_dev.c: dnaddr_chain
net/ipv4/devinet.c: inetaddr_chain
It's possible that some of these classifications are wrong. If they are,
please let us know or submit a patch to fix them. Note that any chain that
gets called very frequently should be atomic, because the rwsem read-locking
used for blocking chains is very likely to incur cache misses on SMP systems.
(However, if the chain's callout routines may sleep then the chain cannot be
atomic.)
The patch set was written by Alan Stern and Chandra Seetharaman, incorporating
material written by Keith Owens and suggestions from Paul McKenney and Andrew
Morton.
[jes@sgi.com: restructure the notifier chain initialization macros]
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Jes Sorensen <jes@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
|
|
|
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
panic: move panic_print before kmsg dumpers
The panic_print setting allows users to collect more information in a
panic event, like memory stats, tasks, CPUs backtraces, etc. This is an
interesting debug mechanism, but currently the print event happens *after*
kmsg_dump(), meaning that pstore, for example, cannot collect a dmesg with
the panic_print extra information.
This patch changes that in 2 steps:
(a) The panic_print setting allows to replay the existing kernel log
buffer to the console (bit 5), besides the extra information dump.
This functionality makes sense only at the end of the panic()
function. So, we hereby allow to distinguish the two situations by a
new boolean parameter in the function panic_print_sys_info().
(b) With the above change, we can safely call panic_print_sys_info()
before kmsg_dump(), allowing to dump the extra information when using
pstore or other kmsg dumpers.
The additional messages from panic_print could overwrite the oldest
messages when the buffer is full. The only reasonable solution is to use
a large enough log buffer, hence we added an advice into the kernel
parameters documentation about that.
Link: https://lkml.kernel.org/r/20220214141308.841525-1-gpiccoli@igalia.com
Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Acked-by: Baoquan He <bhe@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Feng Tang <feng.tang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-24 07:07:09 +08:00
|
|
|
panic_print_sys_info(false);
|
|
|
|
|
2013-09-12 05:25:49 +08:00
|
|
|
kmsg_dump(KMSG_DUMP_PANIC);
|
|
|
|
|
2014-06-07 05:37:07 +08:00
|
|
|
/*
|
|
|
|
* If you doubt kdump always works fine in any situation,
|
|
|
|
* "crash_kexec_post_notifiers" offers you a chance to run
|
|
|
|
* panic_notifiers and dumping kmsg before kdump.
|
|
|
|
* Note: since some panic_notifiers can make crashed kernel
|
|
|
|
* more unstable, it can increase risks of the kdump failure too.
|
2015-12-14 18:19:11 +08:00
|
|
|
*
|
|
|
|
* Bypass the panic_cpu check and call __crash_kexec directly.
|
2014-06-07 05:37:07 +08:00
|
|
|
*/
|
2016-08-03 05:06:13 +08:00
|
|
|
if (_crash_kexec_post_notifiers)
|
2015-12-14 18:19:11 +08:00
|
|
|
__crash_kexec(NULL);
|
2014-06-07 05:37:07 +08:00
|
|
|
|
panic: avoid deadlocks in re-entrant console drivers
From printk()/serial console point of view panic() is special, because
it may force CPU to re-enter printk() or/and serial console driver.
Therefore, some of serial consoles drivers are re-entrant. E.g. 8250:
serial8250_console_write()
{
if (port->sysrq)
locked = 0;
else if (oops_in_progress)
locked = spin_trylock_irqsave(&port->lock, flags);
else
spin_lock_irqsave(&port->lock, flags);
...
}
panic() does set oops_in_progress via bust_spinlocks(1), so in theory
we should be able to re-enter serial console driver from panic():
CPU0
<NMI>
uart_console_write()
serial8250_console_write() // if (oops_in_progress)
// spin_trylock_irqsave()
call_console_drivers()
console_unlock()
console_flush_on_panic()
bust_spinlocks(1) // oops_in_progress++
panic()
<NMI/>
spin_lock_irqsave(&port->lock, flags) // spin_lock_irqsave()
serial8250_console_write()
call_console_drivers()
console_unlock()
printk()
...
However, this does not happen and we deadlock in serial console on
port->lock spinlock. And the problem is that console_flush_on_panic()
called after bust_spinlocks(0):
void panic(const char *fmt, ...)
{
bust_spinlocks(1);
...
bust_spinlocks(0);
console_flush_on_panic();
...
}
bust_spinlocks(0) decrements oops_in_progress, so oops_in_progress
can go back to zero. Thus even re-entrant console drivers will simply
spin on port->lock spinlock. Given that port->lock may already be
locked either by a stopped CPU, or by the very same CPU we execute
panic() on (for instance, NMI panic() on printing CPU) the system
deadlocks and does not reboot.
Fix this by removing bust_spinlocks(0), so oops_in_progress is always
set in panic() now and, thus, re-entrant console drivers will trylock
the port->lock instead of spinning on it forever, when we call them
from console_flush_on_panic().
Link: http://lkml.kernel.org/r/20181025101036.6823-1-sergey.senozhatsky@gmail.com
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Daniel Wang <wonderfly@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk>
Cc: Jiri Slaby <jslaby@suse.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: linux-serial@vger.kernel.org
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-10-25 18:10:36 +08:00
|
|
|
console_unblank();
|
2009-10-02 19:41:20 +08:00
|
|
|
|
2015-11-07 08:32:58 +08:00
|
|
|
/*
|
|
|
|
* We may have ended up stopping the CPU holding the lock (in
|
|
|
|
* smp_send_stop()) while still having some valuable data in the console
|
|
|
|
* buffer. Try to acquire the lock then release it regardless of the
|
2015-11-21 07:57:24 +08:00
|
|
|
* result. The release will also print the buffers out. Locks debug
|
|
|
|
* should be disabled to avoid reporting bad unlock balance when
|
|
|
|
* panic() is not being callled from OOPS.
|
2015-11-07 08:32:58 +08:00
|
|
|
*/
|
2015-11-21 07:57:24 +08:00
|
|
|
debug_locks_off();
|
2019-05-18 05:31:50 +08:00
|
|
|
console_flush_on_panic(CONSOLE_FLUSH_PENDING);
|
2015-11-07 08:32:58 +08:00
|
|
|
|
panic: move panic_print before kmsg dumpers
The panic_print setting allows users to collect more information in a
panic event, like memory stats, tasks, CPUs backtraces, etc. This is an
interesting debug mechanism, but currently the print event happens *after*
kmsg_dump(), meaning that pstore, for example, cannot collect a dmesg with
the panic_print extra information.
This patch changes that in 2 steps:
(a) The panic_print setting allows to replay the existing kernel log
buffer to the console (bit 5), besides the extra information dump.
This functionality makes sense only at the end of the panic()
function. So, we hereby allow to distinguish the two situations by a
new boolean parameter in the function panic_print_sys_info().
(b) With the above change, we can safely call panic_print_sys_info()
before kmsg_dump(), allowing to dump the extra information when using
pstore or other kmsg dumpers.
The additional messages from panic_print could overwrite the oldest
messages when the buffer is full. The only reasonable solution is to use
a large enough log buffer, hence we added an advice into the kernel
parameters documentation about that.
Link: https://lkml.kernel.org/r/20220214141308.841525-1-gpiccoli@igalia.com
Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Acked-by: Baoquan He <bhe@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Feng Tang <feng.tang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-24 07:07:09 +08:00
|
|
|
panic_print_sys_info(true);
|
2019-01-04 07:28:17 +08:00
|
|
|
|
2010-08-11 09:03:28 +08:00
|
|
|
if (!panic_blink)
|
|
|
|
panic_blink = no_blink;
|
|
|
|
|
2005-06-26 05:57:52 +08:00
|
|
|
if (panic_timeout > 0) {
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2009-03-13 18:14:06 +08:00
|
|
|
* Delay timeout seconds before rebooting the machine.
|
|
|
|
* We can't use the "normal" timers since we just panicked.
|
|
|
|
*/
|
2017-01-25 07:18:29 +08:00
|
|
|
pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
|
2009-03-13 18:14:06 +08:00
|
|
|
|
2010-08-11 09:03:28 +08:00
|
|
|
for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
|
2005-04-17 06:20:36 +08:00
|
|
|
touch_nmi_watchdog();
|
2010-08-11 09:03:28 +08:00
|
|
|
if (i >= i_next) {
|
|
|
|
i += panic_blink(state ^= 1);
|
|
|
|
i_next = i + 3600 / PANIC_BLINK_SPD;
|
|
|
|
}
|
|
|
|
mdelay(PANIC_TIMER_STEP);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2011-07-27 07:08:52 +08:00
|
|
|
}
|
|
|
|
if (panic_timeout != 0) {
|
2009-03-13 18:14:06 +08:00
|
|
|
/*
|
|
|
|
* This will not be a clean reboot, with everything
|
|
|
|
* shutting down. But if there is a chance of
|
|
|
|
* rebooting the system it will be rebooted.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2019-05-15 06:45:37 +08:00
|
|
|
if (panic_reboot_mode != REBOOT_UNDEFINED)
|
|
|
|
reboot_mode = panic_reboot_mode;
|
2005-07-27 01:49:23 +08:00
|
|
|
emergency_restart();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
#ifdef __sparc__
|
|
|
|
{
|
|
|
|
extern int stop_a_enabled;
|
2005-04-25 11:38:02 +08:00
|
|
|
/* Make sure the user can actually press Stop-A (L1-A) */
|
2005-04-17 06:20:36 +08:00
|
|
|
stop_a_enabled = 1;
|
2017-02-02 03:34:39 +08:00
|
|
|
pr_emerg("Press Stop-A (L1-A) from sun keyboard or send break\n"
|
|
|
|
"twice on console to return to the boot prom\n");
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
#endif
|
2006-01-06 16:19:28 +08:00
|
|
|
#if defined(CONFIG_S390)
|
2019-04-30 18:33:45 +08:00
|
|
|
disabled_wait();
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
2018-03-06 17:49:12 +08:00
|
|
|
pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf);
|
panic: avoid the extra noise dmesg
When kernel panic happens, it will first print the panic call stack,
then the ending msg like:
[ 35.743249] ---[ end Kernel panic - not syncing: Fatal exception
[ 35.749975] ------------[ cut here ]------------
The above message are very useful for debugging.
But if system is configured to not reboot on panic, say the
"panic_timeout" parameter equals 0, it will likely print out many noisy
message like WARN() call stack for each and every CPU except the panic
one, messages like below:
WARNING: CPU: 1 PID: 280 at kernel/sched/core.c:1198 set_task_cpu+0x183/0x190
Call Trace:
<IRQ>
try_to_wake_up
default_wake_function
autoremove_wake_function
__wake_up_common
__wake_up_common_lock
__wake_up
wake_up_klogd_work_func
irq_work_run_list
irq_work_tick
update_process_times
tick_sched_timer
__hrtimer_run_queues
hrtimer_interrupt
smp_apic_timer_interrupt
apic_timer_interrupt
For people working in console mode, the screen will first show the panic
call stack, but immediately overridden by these noisy extra messages,
which makes debugging much more difficult, as the original context gets
lost on screen.
Also these noisy messages will confuse some users, as I have seen many bug
reporters posted the noisy message into bugzilla, instead of the real
panic call stack and context.
Adding a flag "suppress_printk" which gets set in panic() to avoid those
noisy messages, without changing current kernel behavior that both panic
blinking and sysrq magic key can work as is, suggested by Petr Mladek.
To verify this, make sure kernel is not configured to reboot on panic and
in console
# echo c > /proc/sysrq-trigger
to see if console only prints out the panic call stack.
Link: http://lkml.kernel.org/r/1551430186-24169-1-git-send-email-feng.tang@intel.com
Signed-off-by: Feng Tang <feng.tang@intel.com>
Suggested-by: Petr Mladek <pmladek@suse.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Kees Cook <keescook@chromium.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jslaby@suse.com>
Cc: Sasha Levin <sashal@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-15 06:45:34 +08:00
|
|
|
|
|
|
|
/* Do not scroll important messages printed above */
|
|
|
|
suppress_printk = 1;
|
2024-02-07 21:41:02 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The final messages may not have been printed if in a context that
|
|
|
|
* defers printing (such as NMI) and irq_work is not available.
|
|
|
|
* Explicitly flush the kernel log buffer one last time.
|
|
|
|
*/
|
|
|
|
console_flush_on_panic(CONSOLE_FLUSH_PENDING);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
local_irq_enable();
|
2010-08-11 09:03:28 +08:00
|
|
|
for (i = 0; ; i += PANIC_TIMER_STEP) {
|
2006-02-10 17:51:11 +08:00
|
|
|
touch_softlockup_watchdog();
|
2010-08-11 09:03:28 +08:00
|
|
|
if (i >= i_next) {
|
|
|
|
i += panic_blink(state ^= 1);
|
|
|
|
i_next = i + 3600 / PANIC_BLINK_SPD;
|
|
|
|
}
|
|
|
|
mdelay(PANIC_TIMER_STEP);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(panic);
|
|
|
|
|
2016-09-21 19:47:22 +08:00
|
|
|
/*
|
|
|
|
* TAINT_FORCED_RMMOD could be a per-module flag but the module
|
|
|
|
* is being removed anyway.
|
|
|
|
*/
|
|
|
|
const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = {
|
2018-04-11 07:32:26 +08:00
|
|
|
[ TAINT_PROPRIETARY_MODULE ] = { 'P', 'G', true },
|
|
|
|
[ TAINT_FORCED_MODULE ] = { 'F', ' ', true },
|
|
|
|
[ TAINT_CPU_OUT_OF_SPEC ] = { 'S', ' ', false },
|
|
|
|
[ TAINT_FORCED_RMMOD ] = { 'R', ' ', false },
|
|
|
|
[ TAINT_MACHINE_CHECK ] = { 'M', ' ', false },
|
|
|
|
[ TAINT_BAD_PAGE ] = { 'B', ' ', false },
|
|
|
|
[ TAINT_USER ] = { 'U', ' ', false },
|
|
|
|
[ TAINT_DIE ] = { 'D', ' ', false },
|
|
|
|
[ TAINT_OVERRIDDEN_ACPI_TABLE ] = { 'A', ' ', false },
|
|
|
|
[ TAINT_WARN ] = { 'W', ' ', false },
|
|
|
|
[ TAINT_CRAP ] = { 'C', ' ', true },
|
|
|
|
[ TAINT_FIRMWARE_WORKAROUND ] = { 'I', ' ', false },
|
|
|
|
[ TAINT_OOT_MODULE ] = { 'O', ' ', true },
|
|
|
|
[ TAINT_UNSIGNED_MODULE ] = { 'E', ' ', true },
|
|
|
|
[ TAINT_SOFTLOCKUP ] = { 'L', ' ', false },
|
|
|
|
[ TAINT_LIVEPATCH ] = { 'K', ' ', true },
|
|
|
|
[ TAINT_AUX ] = { 'X', ' ', true },
|
2018-04-11 07:32:33 +08:00
|
|
|
[ TAINT_RANDSTRUCT ] = { 'T', ' ', true },
|
2022-07-01 16:47:41 +08:00
|
|
|
[ TAINT_TEST ] = { 'N', ' ', true },
|
2008-10-16 13:01:41 +08:00
|
|
|
};
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
2018-04-11 07:32:29 +08:00
|
|
|
* print_tainted - return a string to represent the kernel taint state.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2019-04-23 03:48:00 +08:00
|
|
|
* For individual taint flag meanings, see Documentation/admin-guide/sysctl/kernel.rst
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2018-04-11 07:32:29 +08:00
|
|
|
* The string is overwritten by the next call to print_tainted(),
|
|
|
|
* but is always NULL terminated.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
const char *print_tainted(void)
|
|
|
|
{
|
2016-09-21 19:47:22 +08:00
|
|
|
static char buf[TAINT_FLAGS_COUNT + sizeof("Tainted: ")];
|
2008-10-16 13:01:41 +08:00
|
|
|
|
2018-04-11 07:32:26 +08:00
|
|
|
BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT);
|
|
|
|
|
2008-10-16 13:01:41 +08:00
|
|
|
if (tainted_mask) {
|
|
|
|
char *s;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
s = buf + sprintf(buf, "Tainted: ");
|
2016-09-21 19:47:22 +08:00
|
|
|
for (i = 0; i < TAINT_FLAGS_COUNT; i++) {
|
|
|
|
const struct taint_flag *t = &taint_flags[i];
|
|
|
|
*s++ = test_bit(i, &tainted_mask) ?
|
2017-01-02 10:25:25 +08:00
|
|
|
t->c_true : t->c_false;
|
2008-10-16 13:01:41 +08:00
|
|
|
}
|
|
|
|
*s = 0;
|
|
|
|
} else
|
2005-04-17 06:20:36 +08:00
|
|
|
snprintf(buf, sizeof(buf), "Not tainted");
|
2009-03-13 18:14:06 +08:00
|
|
|
|
|
|
|
return buf;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2008-10-16 13:01:41 +08:00
|
|
|
int test_taint(unsigned flag)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-10-16 13:01:41 +08:00
|
|
|
return test_bit(flag, &tainted_mask);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(test_taint);
|
|
|
|
|
|
|
|
unsigned long get_taint(void)
|
|
|
|
{
|
|
|
|
return tainted_mask;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2006-03-23 19:00:57 +08:00
|
|
|
|
2013-01-21 14:47:39 +08:00
|
|
|
/**
|
|
|
|
* add_taint: add a taint flag if not already set.
|
|
|
|
* @flag: one of the TAINT_* constants.
|
|
|
|
* @lockdep_ok: whether lock debugging is still OK.
|
|
|
|
*
|
|
|
|
* If something bad has gone wrong, you'll want @lockdebug_ok = false, but for
|
|
|
|
* some notewortht-but-not-corrupting cases, it can be set to true.
|
|
|
|
*/
|
|
|
|
void add_taint(unsigned flag, enum lockdep_ok lockdep_ok)
|
2006-03-23 19:00:57 +08:00
|
|
|
{
|
2013-01-21 14:47:39 +08:00
|
|
|
if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off())
|
2014-04-08 06:39:03 +08:00
|
|
|
pr_warn("Disabling lock debugging due to kernel taint\n");
|
2009-04-11 09:17:17 +08:00
|
|
|
|
2008-10-16 13:01:41 +08:00
|
|
|
set_bit(flag, &tainted_mask);
|
2020-06-08 12:40:17 +08:00
|
|
|
|
|
|
|
if (tainted_mask & panic_on_taint) {
|
|
|
|
panic_on_taint = 0;
|
|
|
|
panic("panic_on_taint set ...");
|
|
|
|
}
|
2006-03-23 19:00:57 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
EXPORT_SYMBOL(add_taint);
|
2006-03-23 19:00:57 +08:00
|
|
|
|
|
|
|
static void spin_msec(int msecs)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < msecs; i++) {
|
|
|
|
touch_nmi_watchdog();
|
|
|
|
mdelay(1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* It just happens that oops_enter() and oops_exit() are identically
|
|
|
|
* implemented...
|
|
|
|
*/
|
|
|
|
static void do_oops_enter_exit(void)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
static int spin_counter;
|
|
|
|
|
|
|
|
if (!pause_on_oops)
|
|
|
|
return;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&pause_on_oops_lock, flags);
|
|
|
|
if (pause_on_oops_flag == 0) {
|
|
|
|
/* This CPU may now print the oops message */
|
|
|
|
pause_on_oops_flag = 1;
|
|
|
|
} else {
|
|
|
|
/* We need to stall this CPU */
|
|
|
|
if (!spin_counter) {
|
|
|
|
/* This CPU gets to do the counting */
|
|
|
|
spin_counter = pause_on_oops;
|
|
|
|
do {
|
|
|
|
spin_unlock(&pause_on_oops_lock);
|
|
|
|
spin_msec(MSEC_PER_SEC);
|
|
|
|
spin_lock(&pause_on_oops_lock);
|
|
|
|
} while (--spin_counter);
|
|
|
|
pause_on_oops_flag = 0;
|
|
|
|
} else {
|
|
|
|
/* This CPU waits for a different one */
|
|
|
|
while (spin_counter) {
|
|
|
|
spin_unlock(&pause_on_oops_lock);
|
|
|
|
spin_msec(1);
|
|
|
|
spin_lock(&pause_on_oops_lock);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
spin_unlock_irqrestore(&pause_on_oops_lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2009-03-13 18:14:06 +08:00
|
|
|
* Return true if the calling CPU is allowed to print oops-related info.
|
|
|
|
* This is a bit racy..
|
2006-03-23 19:00:57 +08:00
|
|
|
*/
|
2020-08-12 09:36:46 +08:00
|
|
|
bool oops_may_print(void)
|
2006-03-23 19:00:57 +08:00
|
|
|
{
|
|
|
|
return pause_on_oops_flag == 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Called when the architecture enters its oops handler, before it prints
|
2009-03-13 18:14:06 +08:00
|
|
|
* anything. If this is the first CPU to oops, and it's oopsing the first
|
|
|
|
* time then let it proceed.
|
2006-03-23 19:00:57 +08:00
|
|
|
*
|
2009-03-13 18:14:06 +08:00
|
|
|
* This is all enabled by the pause_on_oops kernel boot option. We do all
|
|
|
|
* this to ensure that oopses don't scroll off the screen. It has the
|
|
|
|
* side-effect of preventing later-oopsing CPUs from mucking up the display,
|
|
|
|
* too.
|
2006-03-23 19:00:57 +08:00
|
|
|
*
|
2009-03-13 18:14:06 +08:00
|
|
|
* It turns out that the CPU which is allowed to print ends up pausing for
|
|
|
|
* the right duration, whereas all the other CPUs pause for twice as long:
|
|
|
|
* once in oops_enter(), once in oops_exit().
|
2006-03-23 19:00:57 +08:00
|
|
|
*/
|
|
|
|
void oops_enter(void)
|
|
|
|
{
|
2009-07-25 03:30:45 +08:00
|
|
|
tracing_off();
|
2009-03-13 18:14:06 +08:00
|
|
|
/* can't trust the integrity of the kernel anymore: */
|
|
|
|
debug_locks_off();
|
2006-03-23 19:00:57 +08:00
|
|
|
do_oops_enter_exit();
|
2020-06-08 12:40:48 +08:00
|
|
|
|
|
|
|
if (sysctl_oops_all_cpu_backtrace)
|
|
|
|
trigger_all_cpu_backtrace();
|
2006-03-23 19:00:57 +08:00
|
|
|
}
|
|
|
|
|
2020-08-12 09:36:53 +08:00
|
|
|
static void print_oops_end_marker(void)
|
2008-01-30 20:32:50 +08:00
|
|
|
{
|
2022-01-20 10:09:59 +08:00
|
|
|
pr_warn("---[ end trace %016llx ]---\n", 0ULL);
|
2008-01-30 20:32:50 +08:00
|
|
|
}
|
|
|
|
|
2006-03-23 19:00:57 +08:00
|
|
|
/*
|
|
|
|
* Called when the architecture exits its oops handler, after printing
|
|
|
|
* everything.
|
|
|
|
*/
|
|
|
|
void oops_exit(void)
|
|
|
|
{
|
|
|
|
do_oops_enter_exit();
|
2008-01-30 20:32:50 +08:00
|
|
|
print_oops_end_marker();
|
2009-10-16 20:09:18 +08:00
|
|
|
kmsg_dump(KMSG_DUMP_OOPS);
|
2006-03-23 19:00:57 +08:00
|
|
|
}
|
2006-09-26 16:52:39 +08:00
|
|
|
|
2016-03-18 05:23:04 +08:00
|
|
|
struct warn_args {
|
2009-05-17 04:41:28 +08:00
|
|
|
const char *fmt;
|
2008-07-25 16:45:53 +08:00
|
|
|
va_list args;
|
2009-05-17 04:41:28 +08:00
|
|
|
};
|
2008-11-29 00:36:09 +08:00
|
|
|
|
2016-03-18 05:23:04 +08:00
|
|
|
void __warn(const char *file, int line, void *caller, unsigned taint,
|
|
|
|
struct pt_regs *regs, struct warn_args *args)
|
2009-05-17 04:41:28 +08:00
|
|
|
{
|
2013-06-15 04:21:43 +08:00
|
|
|
disable_trace_on_warning();
|
|
|
|
|
2016-03-18 05:23:04 +08:00
|
|
|
if (file)
|
|
|
|
pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n",
|
|
|
|
raw_smp_processor_id(), current->pid, file, line,
|
|
|
|
caller);
|
|
|
|
else
|
|
|
|
pr_warn("WARNING: CPU: %d PID: %d at %pS\n",
|
|
|
|
raw_smp_processor_id(), current->pid, caller);
|
2008-11-29 00:35:25 +08:00
|
|
|
|
2009-05-17 04:41:28 +08:00
|
|
|
if (args)
|
|
|
|
vprintk(args->fmt, args->args);
|
2008-07-25 16:45:53 +08:00
|
|
|
|
2020-10-16 11:13:22 +08:00
|
|
|
print_modules();
|
|
|
|
|
|
|
|
if (regs)
|
|
|
|
show_regs(regs);
|
|
|
|
|
2022-11-18 07:43:24 +08:00
|
|
|
check_panic_on_warn("kernel");
|
2014-12-11 07:45:50 +08:00
|
|
|
|
2020-11-14 14:52:20 +08:00
|
|
|
if (!regs)
|
|
|
|
dump_stack();
|
2016-03-18 05:23:04 +08:00
|
|
|
|
2018-04-03 22:31:47 +08:00
|
|
|
print_irqtrace_events(current);
|
|
|
|
|
2008-07-25 16:45:53 +08:00
|
|
|
print_oops_end_marker();
|
2022-01-20 10:09:56 +08:00
|
|
|
trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller);
|
2016-03-18 05:23:04 +08:00
|
|
|
|
2013-01-21 14:47:39 +08:00
|
|
|
/* Just a warning, don't kill lockdep. */
|
|
|
|
add_taint(taint, LOCKDEP_STILL_OK);
|
2008-07-25 16:45:53 +08:00
|
|
|
}
|
2009-05-17 04:41:28 +08:00
|
|
|
|
2023-05-17 21:10:55 +08:00
|
|
|
#ifdef CONFIG_BUG
|
2019-09-26 07:48:08 +08:00
|
|
|
#ifndef __WARN_FLAGS
|
2019-09-26 07:47:52 +08:00
|
|
|
void warn_slowpath_fmt(const char *file, int line, unsigned taint,
|
|
|
|
const char *fmt, ...)
|
2010-04-04 02:34:56 +08:00
|
|
|
{
|
2023-01-26 23:08:31 +08:00
|
|
|
bool rcu = warn_rcu_enter();
|
2016-03-18 05:23:04 +08:00
|
|
|
struct warn_args args;
|
2010-04-04 02:34:56 +08:00
|
|
|
|
2019-09-26 07:48:01 +08:00
|
|
|
pr_warn(CUT_HERE);
|
|
|
|
|
2019-09-26 07:47:58 +08:00
|
|
|
if (!fmt) {
|
|
|
|
__warn(file, line, __builtin_return_address(0), taint,
|
|
|
|
NULL, NULL);
|
2023-09-15 15:55:39 +08:00
|
|
|
warn_rcu_exit(rcu);
|
2019-09-26 07:47:58 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2010-04-04 02:34:56 +08:00
|
|
|
args.fmt = fmt;
|
|
|
|
va_start(args.args, fmt);
|
2016-03-18 05:23:04 +08:00
|
|
|
__warn(file, line, __builtin_return_address(0), taint, NULL, &args);
|
2010-04-04 02:34:56 +08:00
|
|
|
va_end(args.args);
|
2023-01-26 23:08:31 +08:00
|
|
|
warn_rcu_exit(rcu);
|
2010-04-04 02:34:56 +08:00
|
|
|
}
|
2019-09-26 07:47:52 +08:00
|
|
|
EXPORT_SYMBOL(warn_slowpath_fmt);
|
2017-11-18 07:27:24 +08:00
|
|
|
#else
|
|
|
|
void __warn_printk(const char *fmt, ...)
|
|
|
|
{
|
2023-01-26 23:08:31 +08:00
|
|
|
bool rcu = warn_rcu_enter();
|
2017-11-18 07:27:24 +08:00
|
|
|
va_list args;
|
|
|
|
|
|
|
|
pr_warn(CUT_HERE);
|
|
|
|
|
|
|
|
va_start(args, fmt);
|
|
|
|
vprintk(fmt, args);
|
|
|
|
va_end(args);
|
2023-01-26 23:08:31 +08:00
|
|
|
warn_rcu_exit(rcu);
|
2017-11-18 07:27:24 +08:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(__warn_printk);
|
2008-01-30 20:32:50 +08:00
|
|
|
#endif
|
|
|
|
|
2017-11-18 07:27:03 +08:00
|
|
|
/* Support resetting WARN*_ONCE state */
|
|
|
|
|
|
|
|
static int clear_warn_once_set(void *data, u64 val)
|
|
|
|
{
|
2017-11-18 07:27:06 +08:00
|
|
|
generic_bug_clear_once();
|
2017-11-18 07:27:03 +08:00
|
|
|
memset(__start_once, 0, __end_once - __start_once);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-03-08 08:26:36 +08:00
|
|
|
DEFINE_DEBUGFS_ATTRIBUTE(clear_warn_once_fops, NULL, clear_warn_once_set,
|
|
|
|
"%lld\n");
|
2017-11-18 07:27:03 +08:00
|
|
|
|
|
|
|
static __init int register_warn_debugfs(void)
|
|
|
|
{
|
|
|
|
/* Don't care about failure */
|
2019-03-08 08:26:36 +08:00
|
|
|
debugfs_create_file_unsafe("clear_warn_once", 0200, NULL, NULL,
|
|
|
|
&clear_warn_once_fops);
|
2017-11-18 07:27:03 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
device_initcall(register_warn_debugfs);
|
|
|
|
#endif
|
|
|
|
|
Kbuild: rename CC_STACKPROTECTOR[_STRONG] config variables
The changes to automatically test for working stack protector compiler
support in the Kconfig files removed the special STACKPROTECTOR_AUTO
option that picked the strongest stack protector that the compiler
supported.
That was all a nice cleanup - it makes no sense to have the AUTO case
now that the Kconfig phase can just determine the compiler support
directly.
HOWEVER.
It also meant that doing "make oldconfig" would now _disable_ the strong
stackprotector if you had AUTO enabled, because in a legacy config file,
the sane stack protector configuration would look like
CONFIG_HAVE_CC_STACKPROTECTOR=y
# CONFIG_CC_STACKPROTECTOR_NONE is not set
# CONFIG_CC_STACKPROTECTOR_REGULAR is not set
# CONFIG_CC_STACKPROTECTOR_STRONG is not set
CONFIG_CC_STACKPROTECTOR_AUTO=y
and when you ran this through "make oldconfig" with the Kbuild changes,
it would ask you about the regular CONFIG_CC_STACKPROTECTOR (that had
been renamed from CONFIG_CC_STACKPROTECTOR_REGULAR to just
CONFIG_CC_STACKPROTECTOR), but it would think that the STRONG version
used to be disabled (because it was really enabled by AUTO), and would
disable it in the new config, resulting in:
CONFIG_HAVE_CC_STACKPROTECTOR=y
CONFIG_CC_HAS_STACKPROTECTOR_NONE=y
CONFIG_CC_STACKPROTECTOR=y
# CONFIG_CC_STACKPROTECTOR_STRONG is not set
CONFIG_CC_HAS_SANE_STACKPROTECTOR=y
That's dangerously subtle - people could suddenly find themselves with
the weaker stack protector setup without even realizing.
The solution here is to just rename not just the old RECULAR stack
protector option, but also the strong one. This does that by just
removing the CC_ prefix entirely for the user choices, because it really
is not about the compiler support (the compiler support now instead
automatially impacts _visibility_ of the options to users).
This results in "make oldconfig" actually asking the user for their
choice, so that we don't have any silent subtle security model changes.
The end result would generally look like this:
CONFIG_HAVE_CC_STACKPROTECTOR=y
CONFIG_CC_HAS_STACKPROTECTOR_NONE=y
CONFIG_STACKPROTECTOR=y
CONFIG_STACKPROTECTOR_STRONG=y
CONFIG_CC_HAS_SANE_STACKPROTECTOR=y
where the "CC_" versions really are about internal compiler
infrastructure, not the user selections.
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-14 11:21:18 +08:00
|
|
|
#ifdef CONFIG_STACKPROTECTOR
|
2008-02-16 07:33:12 +08:00
|
|
|
|
2006-09-26 16:52:39 +08:00
|
|
|
/*
|
|
|
|
* Called when gcc's -fstack-protector feature is used, and
|
|
|
|
* gcc detects corruption of the on-stack canary value
|
|
|
|
*/
|
2020-03-13 20:49:51 +08:00
|
|
|
__visible noinstr void __stack_chk_fail(void)
|
2006-09-26 16:52:39 +08:00
|
|
|
{
|
2020-03-13 20:49:51 +08:00
|
|
|
instrumentation_begin();
|
2018-10-31 06:07:13 +08:00
|
|
|
panic("stack-protector: Kernel stack is corrupted in: %pB",
|
2008-02-14 16:02:13 +08:00
|
|
|
__builtin_return_address(0));
|
2020-03-13 20:49:51 +08:00
|
|
|
instrumentation_end();
|
2006-09-26 16:52:39 +08:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(__stack_chk_fail);
|
2008-02-16 07:33:12 +08:00
|
|
|
|
2006-09-26 16:52:39 +08:00
|
|
|
#endif
|
2008-10-22 23:00:24 +08:00
|
|
|
|
|
|
|
core_param(panic, panic_timeout, int, 0644);
|
2019-01-04 07:28:17 +08:00
|
|
|
core_param(panic_print, panic_print, ulong, 0644);
|
2008-10-22 23:00:24 +08:00
|
|
|
core_param(pause_on_oops, pause_on_oops, int, 0644);
|
2014-12-11 07:45:50 +08:00
|
|
|
core_param(panic_on_warn, panic_on_warn, int, 0644);
|
2016-08-03 05:06:13 +08:00
|
|
|
core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644);
|
2014-06-07 05:37:07 +08:00
|
|
|
|
2011-03-23 07:34:04 +08:00
|
|
|
static int __init oops_setup(char *s)
|
|
|
|
{
|
|
|
|
if (!s)
|
|
|
|
return -EINVAL;
|
|
|
|
if (!strcmp(s, "panic"))
|
|
|
|
panic_on_oops = 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
early_param("oops", oops_setup);
|
2020-06-08 12:40:17 +08:00
|
|
|
|
|
|
|
static int __init panic_on_taint_setup(char *s)
|
|
|
|
{
|
|
|
|
char *taint_str;
|
|
|
|
|
|
|
|
if (!s)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
taint_str = strsep(&s, ",");
|
|
|
|
if (kstrtoul(taint_str, 16, &panic_on_taint))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
/* make sure panic_on_taint doesn't hold out-of-range TAINT flags */
|
|
|
|
panic_on_taint &= TAINT_FLAGS_MAX;
|
|
|
|
|
|
|
|
if (!panic_on_taint)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (s && !strcmp(s, "nousertaint"))
|
|
|
|
panic_on_taint_nousertaint = true;
|
|
|
|
|
2022-10-09 03:59:14 +08:00
|
|
|
pr_info("panic_on_taint: bitmask=0x%lx nousertaint_mode=%s\n",
|
|
|
|
panic_on_taint, str_enabled_disabled(panic_on_taint_nousertaint));
|
2020-06-08 12:40:17 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
early_param("panic_on_taint", panic_on_taint_setup);
|