android_kernel_sony_msm8994/kernel/panic.c

503 lines
12 KiB
C
Raw Normal View History

/*
* linux/kernel/panic.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
2016-04-09 14:46:03 +00:00
/*
* NOTE: This file has been modified by Sony Mobile Communications Inc.
* Modifications are Copyright (c) 2014 Sony Mobile Communications Inc,
* and licensed under the license of the file.
*/
/*
* This function is used through-out the kernel (including mm and fs)
* to indicate a major problem.
*/
#include <linux/debug_locks.h>
#include <linux/interrupt.h>
#include <linux/kmsg_dump.h>
#include <linux/kallsyms.h>
#include <linux/notifier.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/kexec.h>
#include <linux/sched.h>
#include <linux/sysrq.h>
#include <linux/init.h>
#include <linux/nmi.h>
2016-04-09 14:46:03 +00:00
#include <linux/crash_notes.h>
#define CREATE_TRACE_POINTS
#include <trace/events/exception.h>
#define PANIC_TIMER_STEP 100
#define PANIC_BLINK_SPD 18
/* Machine specific panic information string */
char *mach_panic_string;
int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
static unsigned long tainted_mask;
static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
#ifndef CONFIG_PANIC_TIMEOUT
#define CONFIG_PANIC_TIMEOUT 0
#endif
int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
[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 09:16:30 +00:00
ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
EXPORT_SYMBOL(panic_notifier_list);
static long no_blink(int state)
{
return 0;
}
/* Returns how long it waited in ms */
long (*panic_blink)(int state);
EXPORT_SYMBOL(panic_blink);
/*
* Stop ourself in panic -- architecture code may override this
*/
void __weak panic_smp_self_stop(void)
{
while (1)
cpu_relax();
}
/**
* panic - halt the system
* @fmt: The text string to print
*
* Display a message, then perform cleanups.
*
* This function never returns.
*/
void panic(const char *fmt, ...)
{
static DEFINE_SPINLOCK(panic_lock);
static char buf[1024];
va_list args;
long i, i_next = 0;
int state = 0;
trace_kernel_panic(0);
/*
* 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
* after the panic_lock is acquired) from invoking panic again.
*/
local_irq_disable();
/*
* It's possible to come here directly from a panic-assertion and
* not have preempt disabled. Some functions called from here want
* preempt to be disabled. No point enabling it later though...
*
* 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().
*/
if (!spin_trylock(&panic_lock))
panic_smp_self_stop();
console_verbose();
bust_spinlocks(1);
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
#ifdef CONFIG_DEBUG_BUGVERBOSE
/*
* Avoid nested stack-dumping if a panic occurs during oops processing
*/
if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
dump_stack();
#endif
/*
* If we have crashed and we have a crash kernel loaded let it handle
* everything else.
* Do we want to call this before we try to display a message?
*/
crash_kexec(NULL);
2016-04-09 14:46:03 +00:00
/* Store crash context for all other no panic cpus */
crash_notes_save_cpus();
/*
* 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();
kmsg_dump(KMSG_DUMP_PANIC);
[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 09:16:30 +00:00
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
bust_spinlocks(0);
if (!panic_blink)
panic_blink = no_blink;
if (panic_timeout > 0) {
/*
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked.
*/
printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout);
for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
touch_nmi_watchdog();
if (i >= i_next) {
i += panic_blink(state ^= 1);
i_next = i + 3600 / PANIC_BLINK_SPD;
}
mdelay(PANIC_TIMER_STEP);
}
}
trace_kernel_panic_late(0);
if (panic_timeout != 0) {
/*
* 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.
*/
emergency_restart();
}
#ifdef __sparc__
{
extern int stop_a_enabled;
/* Make sure the user can actually press Stop-A (L1-A) */
stop_a_enabled = 1;
printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n");
}
#endif
#if defined(CONFIG_S390)
{
unsigned long caller;
caller = (unsigned long)__builtin_return_address(0);
disabled_wait(caller);
}
#endif
local_irq_enable();
for (i = 0; ; i += PANIC_TIMER_STEP) {
touch_softlockup_watchdog();
if (i >= i_next) {
i += panic_blink(state ^= 1);
i_next = i + 3600 / PANIC_BLINK_SPD;
}
mdelay(PANIC_TIMER_STEP);
}
}
EXPORT_SYMBOL(panic);
struct tnt {
u8 bit;
char true;
char false;
};
static const struct tnt tnts[] = {
{ TAINT_PROPRIETARY_MODULE, 'P', 'G' },
{ TAINT_FORCED_MODULE, 'F', ' ' },
{ TAINT_UNSAFE_SMP, 'S', ' ' },
{ TAINT_FORCED_RMMOD, 'R', ' ' },
{ TAINT_MACHINE_CHECK, 'M', ' ' },
{ TAINT_BAD_PAGE, 'B', ' ' },
{ TAINT_USER, 'U', ' ' },
{ TAINT_DIE, 'D', ' ' },
{ TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' },
{ TAINT_WARN, 'W', ' ' },
{ TAINT_CRAP, 'C', ' ' },
{ TAINT_FIRMWARE_WORKAROUND, 'I', ' ' },
{ TAINT_OOT_MODULE, 'O', ' ' },
};
/**
* print_tainted - return a string to represent the kernel taint state.
*
* 'P' - Proprietary module has been loaded.
* 'F' - Module has been forcibly loaded.
* 'S' - SMP with CPUs not designed for SMP.
* 'R' - User forced a module unload.
* 'M' - System experienced a machine check exception.
* 'B' - System has hit bad_page.
* 'U' - Userspace-defined naughtiness.
* 'D' - Kernel has oopsed before
* 'A' - ACPI table overridden.
* 'W' - Taint on warning.
* 'C' - modules from drivers/staging are loaded.
* 'I' - Working around severe firmware bug.
* 'O' - Out-of-tree module has been loaded.
*
* The string is overwritten by the next call to print_tainted().
*/
const char *print_tainted(void)
{
static char buf[ARRAY_SIZE(tnts) + sizeof("Tainted: ") + 1];
if (tainted_mask) {
char *s;
int i;
s = buf + sprintf(buf, "Tainted: ");
for (i = 0; i < ARRAY_SIZE(tnts); i++) {
const struct tnt *t = &tnts[i];
*s++ = test_bit(t->bit, &tainted_mask) ?
t->true : t->false;
}
*s = 0;
} else
snprintf(buf, sizeof(buf), "Not tainted");
return buf;
}
int test_taint(unsigned flag)
{
return test_bit(flag, &tainted_mask);
}
EXPORT_SYMBOL(test_taint);
unsigned long get_taint(void)
{
return tainted_mask;
}
/**
* 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)
{
if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off())
printk(KERN_WARNING
"Disabling lock debugging due to kernel taint\n");
set_bit(flag, &tainted_mask);
}
EXPORT_SYMBOL(add_taint);
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);
}
/*
* Return true if the calling CPU is allowed to print oops-related info.
* This is a bit racy..
*/
int oops_may_print(void)
{
return pause_on_oops_flag == 0;
}
/*
* Called when the architecture enters its oops handler, before it prints
* anything. If this is the first CPU to oops, and it's oopsing the first
* time then let it proceed.
*
* 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.
*
* 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().
*/
void oops_enter(void)
{
tracing_off();
/* can't trust the integrity of the kernel anymore: */
debug_locks_off();
printk: introduce printk oops log buffer The initial kernel oops message often contains informative log messages to help root cause issues. However, because of a limited log buffer size, it is possible that important information is lost due to log buffer wrap-around. Introduce oops log buffer which preserves kernel messages from the point when kernel oops happened by saving messages from regular log buffer when the initial oops messages wrap arounds. This guarantees to obtain initial oops and onward messages up to configured buffer size by running dmesg, /dev/kmsg, /proc/kmsg, kmsg_dumper and other debugging tools. Below is a dmesg output example with CONFIG_OOPS_LOG_BUFFER=y after kernel oops that shows the kernel oops and onward messages up to oops log buffer while regular log buffer still shows the newest messages with distinguishing line '---end of oops log buffer---'. Internal error: Oops: a07 [#1] PREEMPT SMP ARM Modules linked in: CPU: 0 PID: 192 Comm: sh Tainted: G W 3.10.0-gd727407-00072-g7c16272-dirty #87 task: c457ca80 ti: c45dc000 task.ti: c45dc000 PC is at sysrq_handle_crash+0xc/0x14 LR is at write_sysrq_trigger+0x40/0x50 pc : [<c05420ec>] lr : [<c0542a00>] psr: 40000013 sp : c45ddf30 ip : fffff100 fp : 0015ab14 r10: 00000000 r9 : 00000002 r8 : 0015bc68 r7 : 00000000 r6 : 00000001 r5 : 0015bc68 r4 : 00000002 r3 : 00000000 r2 : 00000001 r1 : 60000013 r0 : 00000063 Flags: nZcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user Control: 30c5787d Table: 045673c0 DAC: fffffffd <snip> LR: 0xc0542980: 2980 1a000004 e1a00006 e2841034 ebfd8a4d e2707001 33a07000 e1a00007 e28dd004 29a0 e8bd8ff0 c0c41220 c14bfda8 c162a004 c162a008 c146a450 c162a034 c14640c0 29c0 e92d4070 e2524000 0a00000c e1a05001 ebf7b96c e1a0200d e1a00005 e3c23d7f ---end of oops log buffer--- lowmem_reserve[]: 0 9968 9968 HighMem free:1256224kB min:512kB low:2044kB high:3580kB active_anon:132kB inactive_anon:0kB active_file:508kB io lowmem_reserve[]: 0 0 0 Normal: 9*4kB (UM) 10*8kB (UEM) 6*16kB (UEM) 6*32kB (UEM) 6*64kB (UM) 9*128kB (UEM) 7*256kB (UM) 8*512kB (UM) 7B HighMem: 0*4kB 2*8kB (UM) 1*16kB (U) 2*32kB (UC) 1*64kB (C) 1*128kB (C) 2*256kB (MC) 2*512kB (MC) 3*1024kB (UMCB 364 total pagecache pages <snip> CRs-fixed: 561659 Change-Id: I587961931bfea3aba64a40790598020a4d5b9b36 Signed-off-by: Joonwoo Park <joonwoop@codeaurora.org>
2014-02-21 20:20:50 +00:00
oops_printk_start();
do_oops_enter_exit();
}
debug: add end-of-oops marker Right now it's nearly impossible for parsers that collect kernel crashes from logs or emails (such as www.kerneloops.org) to detect the end-of-oops condition. In addition, it's not currently possible to detect whether or not 2 oopses that look alike are actually the same oops reported twice, or are truly two unique oopses. This patch adds an end-of-oops marker, and makes the end marker include a very simple 64-bit random ID to be able to detect duplicate reports. Normally, this ID is calculated as a late_initcall() (in the hope that at that time there is enough entropy to get a unique enough ID); however for early oopses the oops_exit() function needs to generate the ID on the fly. We do this all at the _end_ of an oops printout, so this does not impact our ability to get the most important portions of a crash out to the console first. [ Sidenote: the already existing oopses-since-bootup counter we print during crashes serves as the differentiator between multiple oopses that trigger during the same bootup. ] Tested on 32-bit and 64-bit x86. Artificially injected very early crashes as well, as expected they result in this constant ID after multiple bootups: ---[ end trace ca143223eefdc828 ]--- ---[ end trace ca143223eefdc828 ]--- because the random pools are still all zero. But it all still works fine and causes no additional problems (which is the main goal of instrumentation code). Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-20 14:01:17 +00:00
/*
* 64-bit random ID for oopses:
*/
static u64 oops_id;
static int init_oops_id(void)
{
if (!oops_id)
get_random_bytes(&oops_id, sizeof(oops_id));
else
oops_id++;
debug: add end-of-oops marker Right now it's nearly impossible for parsers that collect kernel crashes from logs or emails (such as www.kerneloops.org) to detect the end-of-oops condition. In addition, it's not currently possible to detect whether or not 2 oopses that look alike are actually the same oops reported twice, or are truly two unique oopses. This patch adds an end-of-oops marker, and makes the end marker include a very simple 64-bit random ID to be able to detect duplicate reports. Normally, this ID is calculated as a late_initcall() (in the hope that at that time there is enough entropy to get a unique enough ID); however for early oopses the oops_exit() function needs to generate the ID on the fly. We do this all at the _end_ of an oops printout, so this does not impact our ability to get the most important portions of a crash out to the console first. [ Sidenote: the already existing oopses-since-bootup counter we print during crashes serves as the differentiator between multiple oopses that trigger during the same bootup. ] Tested on 32-bit and 64-bit x86. Artificially injected very early crashes as well, as expected they result in this constant ID after multiple bootups: ---[ end trace ca143223eefdc828 ]--- ---[ end trace ca143223eefdc828 ]--- because the random pools are still all zero. But it all still works fine and causes no additional problems (which is the main goal of instrumentation code). Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-20 14:01:17 +00:00
return 0;
}
late_initcall(init_oops_id);
void print_oops_end_marker(void)
{
init_oops_id();
if (mach_panic_string)
printk(KERN_WARNING "Board Information: %s\n",
mach_panic_string);
printk(KERN_WARNING "---[ end trace %016llx ]---\n",
(unsigned long long)oops_id);
}
/*
* Called when the architecture exits its oops handler, after printing
* everything.
*/
void oops_exit(void)
{
do_oops_enter_exit();
print_oops_end_marker();
kmsg_dump(KMSG_DUMP_OOPS);
}
#ifdef WANT_WARN_ON_SLOWPATH
struct slowpath_args {
const char *fmt;
va_list args;
};
static void warn_slowpath_common(const char *file, int line, void *caller,
unsigned taint, struct slowpath_args *args)
{
printk(KERN_WARNING "------------[ cut here ]------------\n");
printk(KERN_WARNING "WARNING: at %s:%d %pS()\n", file, line, caller);
if (args)
vprintk(args->fmt, args->args);
print_modules();
dump_stack();
print_oops_end_marker();
/* Just a warning, don't kill lockdep. */
add_taint(taint, LOCKDEP_STILL_OK);
}
void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...)
{
struct slowpath_args args;
args.fmt = fmt;
va_start(args.args, fmt);
warn_slowpath_common(file, line, __builtin_return_address(0),
TAINT_WARN, &args);
va_end(args.args);
}
EXPORT_SYMBOL(warn_slowpath_fmt);
void warn_slowpath_fmt_taint(const char *file, int line,
unsigned taint, const char *fmt, ...)
{
struct slowpath_args args;
args.fmt = fmt;
va_start(args.args, fmt);
warn_slowpath_common(file, line, __builtin_return_address(0),
taint, &args);
va_end(args.args);
}
EXPORT_SYMBOL(warn_slowpath_fmt_taint);
void warn_slowpath_null(const char *file, int line)
{
warn_slowpath_common(file, line, __builtin_return_address(0),
TAINT_WARN, NULL);
}
EXPORT_SYMBOL(warn_slowpath_null);
#endif
#ifdef CONFIG_CC_STACKPROTECTOR
/*
* Called when gcc's -fstack-protector feature is used, and
* gcc detects corruption of the on-stack canary value
*/
void __stack_chk_fail(void)
{
panic("stack-protector: Kernel stack is corrupted in: %p\n",
__builtin_return_address(0));
}
EXPORT_SYMBOL(__stack_chk_fail);
#endif
core_param(panic, panic_timeout, int, 0644);
core_param(pause_on_oops, pause_on_oops, int, 0644);
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);