+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/panic.c
*
#include <linux/debug_locks.h>
#include <linux/sched/debug.h>
#include <linux/interrupt.h>
+#include <linux/kgdb.h>
#include <linux/kmsg_dump.h>
#include <linux/kallsyms.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/kexec.h>
+#include <linux/panic_notifier.h>
#include <linux/sched.h>
+#include <linux/string_helpers.h>
#include <linux/sysrq.h>
#include <linux/init.h>
#include <linux/nmi.h>
#include <linux/bug.h>
#include <linux/ratelimit.h>
#include <linux/debugfs.h>
+#include <linux/sysfs.h>
+#include <linux/context_tracking.h>
+#include <trace/events/error_report.h>
#include <asm/sections.h>
#define PANIC_TIMER_STEP 100
#define PANIC_BLINK_SPD 18
+#ifdef CONFIG_SMP
+/*
+ * Should we dump all CPUs backtraces in an oops event?
+ * Defaults to 0, can be changed via sysctl.
+ */
+static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace;
+#else
+#define sysctl_oops_all_cpu_backtrace 0
+#endif /* CONFIG_SMP */
+
int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
static unsigned long tainted_mask =
- IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
+ IS_ENABLED(CONFIG_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
bool crash_kexec_post_notifiers;
int panic_on_warn __read_mostly;
+unsigned long panic_on_taint;
+bool panic_on_taint_nousertaint = false;
+static unsigned int warn_limit __read_mostly;
int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
#define PANIC_PRINT_TIMER_INFO 0x00000004
#define PANIC_PRINT_LOCK_INFO 0x00000008
#define PANIC_PRINT_FTRACE_INFO 0x00000010
+#define PANIC_PRINT_ALL_PRINTK_MSG 0x00000020
+#define PANIC_PRINT_ALL_CPU_BT 0x00000040
+#define PANIC_PRINT_BLOCKED_TASKS 0x00000080
unsigned long panic_print;
ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
EXPORT_SYMBOL(panic_notifier_list);
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kern_panic_table[] = {
+#ifdef CONFIG_SMP
+ {
+ .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,
+ },
+#endif
+ {
+ .procname = "warn_limit",
+ .data = &warn_limit,
+ .maxlen = sizeof(warn_limit),
+ .mode = 0644,
+ .proc_handler = proc_douintvec,
+ },
+ { }
+};
+
+static __init int kernel_panic_sysctls_init(void)
+{
+ register_sysctl_init("kernel", kern_panic_table);
+ return 0;
+}
+late_initcall(kernel_panic_sysctls_init);
+#endif
+
+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
+
static long no_blink(int state)
{
return 0;
/*
* Stop ourself in panic -- architecture code may override this
*/
-void __weak panic_smp_self_stop(void)
+void __weak __noreturn panic_smp_self_stop(void)
{
while (1)
cpu_relax();
* 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.
*/
-void __weak nmi_panic_self_stop(struct pt_regs *regs)
+void __weak __noreturn nmi_panic_self_stop(struct pt_regs *regs)
{
panic_smp_self_stop();
}
*/
void nmi_panic(struct pt_regs *regs, const char *msg)
{
- int old_cpu, cpu;
+ int old_cpu, this_cpu;
- cpu = raw_smp_processor_id();
- old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu);
+ old_cpu = PANIC_CPU_INVALID;
+ this_cpu = raw_smp_processor_id();
- if (old_cpu == PANIC_CPU_INVALID)
+ /* atomic_try_cmpxchg updates old_cpu on failure */
+ if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu))
panic("%s", msg);
- else if (old_cpu != cpu)
+ else if (old_cpu != this_cpu)
nmi_panic_self_stop(regs);
}
EXPORT_SYMBOL(nmi_panic);
-static void panic_print_sys_info(void)
+static void panic_print_sys_info(bool console_flush)
{
+ if (console_flush) {
+ if (panic_print & PANIC_PRINT_ALL_PRINTK_MSG)
+ console_flush_on_panic(CONSOLE_REPLAY_ALL);
+ return;
+ }
+
if (panic_print & PANIC_PRINT_TASK_INFO)
show_state();
if (panic_print & PANIC_PRINT_MEM_INFO)
- show_mem(0, NULL);
+ show_mem();
if (panic_print & PANIC_PRINT_TIMER_INFO)
sysrq_timer_list_show();
if (panic_print & PANIC_PRINT_FTRACE_INFO)
ftrace_dump(DUMP_ALL);
+
+ if (panic_print & PANIC_PRINT_BLOCKED_TASKS)
+ show_state_filter(TASK_UNINTERRUPTIBLE);
+}
+
+void check_panic_on_warn(const char *origin)
+{
+ unsigned int limit;
+
+ if (panic_on_warn)
+ panic("%s: panic_on_warn set ...\n", origin);
+
+ limit = READ_ONCE(warn_limit);
+ if (atomic_inc_return(&warn_count) >= limit && limit)
+ panic("%s: system warned too often (kernel.warn_limit is %d)",
+ origin, limit);
+}
+
+/*
+ * 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();
}
/**
int old_cpu, this_cpu;
bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;
+ 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;
+ }
+
/*
* Disable local interrupts. This will prevent panic_smp_self_stop
* from deadlocking the first cpu that invokes the panic, since
* after setting panic_cpu) from invoking panic() again.
*/
local_irq_disable();
+ preempt_disable_notrace();
/*
* It's possible to come here directly from a panic-assertion and
* stop themself or will wait until they are stopped by the 1st CPU
* with smp_send_stop().
*
- * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which
- * comes here, so go ahead.
+ * cmpxchg success 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.
*/
+ old_cpu = PANIC_CPU_INVALID;
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)
+ /* atomic_try_cmpxchg updates old_cpu on failure */
+ if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) {
+ /* go ahead */
+ } else if (old_cpu != this_cpu)
panic_smp_self_stop();
console_verbose();
dump_stack();
#endif
+ /*
+ * 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);
+
/*
* If we have crashed and we have a crash kernel loaded let it handle
* everything else.
*
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
- if (!_crash_kexec_post_notifiers) {
- printk_safe_flush_on_panic();
+ if (!_crash_kexec_post_notifiers)
__crash_kexec(NULL);
- /*
- * 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();
- } else {
- /*
- * If we want to do crash dump after notifier calls and
- * kmsg_dump, we will need architecture dependent extra
- * works in addition to stopping other CPUs.
- */
- crash_smp_send_stop();
- }
+ panic_other_cpus_shutdown(_crash_kexec_post_notifiers);
/*
* Run any panic handlers, including those that might need to
*/
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
- /* Call flush even twice. It tries harder with a single online CPU */
- printk_safe_flush_on_panic();
+ panic_print_sys_info(false);
+
kmsg_dump(KMSG_DUMP_PANIC);
/*
if (_crash_kexec_post_notifiers)
__crash_kexec(NULL);
-#ifdef CONFIG_VT
- unblank_screen();
-#endif
console_unblank();
/*
* panic() is not being callled from OOPS.
*/
debug_locks_off();
- console_flush_on_panic();
+ console_flush_on_panic(CONSOLE_FLUSH_PENDING);
- panic_print_sys_info();
+ panic_print_sys_info(true);
if (!panic_blink)
panic_blink = no_blink;
/* Do not scroll important messages printed above */
suppress_printk = 1;
+
+ /*
+ * 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);
+
local_irq_enable();
for (i = 0; ; i += PANIC_TIMER_STEP) {
touch_softlockup_watchdog();
[ TAINT_LIVEPATCH ] = { 'K', ' ', true },
[ TAINT_AUX ] = { 'X', ' ', true },
[ TAINT_RANDSTRUCT ] = { 'T', ' ', true },
+ [ TAINT_TEST ] = { 'N', ' ', true },
};
/**
* print_tainted - return a string to represent the kernel taint state.
*
- * For individual taint flag meanings, see Documentation/sysctl/kernel.txt
+ * For individual taint flag meanings, see Documentation/admin-guide/sysctl/kernel.rst
*
* The string is overwritten by the next call to print_tainted(),
* but is always NULL terminated.
pr_warn("Disabling lock debugging due to kernel taint\n");
set_bit(flag, &tainted_mask);
+
+ if (tainted_mask & panic_on_taint) {
+ panic_on_taint = 0;
+ panic("panic_on_taint set ...");
+ }
}
EXPORT_SYMBOL(add_taint);
* Return true if the calling CPU is allowed to print oops-related info.
* This is a bit racy..
*/
-int oops_may_print(void)
+bool oops_may_print(void)
{
return pause_on_oops_flag == 0;
}
/* can't trust the integrity of the kernel anymore: */
debug_locks_off();
do_oops_enter_exit();
-}
-/*
- * 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++;
-
- return 0;
+ if (sysctl_oops_all_cpu_backtrace)
+ trigger_all_cpu_backtrace();
}
-late_initcall(init_oops_id);
-void print_oops_end_marker(void)
+static void print_oops_end_marker(void)
{
- init_oops_id();
- pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);
+ pr_warn("---[ end trace %016llx ]---\n", 0ULL);
}
/*
{
disable_trace_on_warning();
- if (args)
- pr_warn(CUT_HERE);
-
if (file)
pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n",
raw_smp_processor_id(), current->pid, file, line,
pr_warn("WARNING: CPU: %d PID: %d at %pS\n",
raw_smp_processor_id(), current->pid, caller);
+#pragma GCC diagnostic push
+#ifndef __clang__
+#pragma GCC diagnostic ignored "-Wsuggest-attribute=format"
+#endif
if (args)
vprintk(args->fmt, args->args);
-
- 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;
- panic("panic_on_warn set ...\n");
- }
+#pragma GCC diagnostic pop
print_modules();
if (regs)
show_regs(regs);
- else
+
+ check_panic_on_warn("kernel");
+
+ if (!regs)
dump_stack();
print_irqtrace_events(current);
print_oops_end_marker();
+ trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller);
/* Just a warning, don't kill lockdep. */
add_taint(taint, LOCKDEP_STILL_OK);
}
-#ifdef WANT_WARN_ON_SLOWPATH
-void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...)
+#ifdef CONFIG_BUG
+#ifndef __WARN_FLAGS
+void warn_slowpath_fmt(const char *file, int line, unsigned taint,
+ const char *fmt, ...)
{
+ bool rcu = warn_rcu_enter();
struct warn_args args;
- args.fmt = fmt;
- va_start(args.args, fmt);
- __warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL,
- &args);
- va_end(args.args);
-}
-EXPORT_SYMBOL(warn_slowpath_fmt);
+ pr_warn(CUT_HERE);
-void warn_slowpath_fmt_taint(const char *file, int line,
- unsigned taint, const char *fmt, ...)
-{
- struct warn_args args;
+ if (!fmt) {
+ __warn(file, line, __builtin_return_address(0), taint,
+ NULL, NULL);
+ warn_rcu_exit(rcu);
+ return;
+ }
args.fmt = fmt;
va_start(args.args, fmt);
__warn(file, line, __builtin_return_address(0), taint, NULL, &args);
va_end(args.args);
+ warn_rcu_exit(rcu);
}
-EXPORT_SYMBOL(warn_slowpath_fmt_taint);
-
-void warn_slowpath_null(const char *file, int line)
-{
- pr_warn(CUT_HERE);
- __warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, NULL);
-}
-EXPORT_SYMBOL(warn_slowpath_null);
+EXPORT_SYMBOL(warn_slowpath_fmt);
#else
void __warn_printk(const char *fmt, ...)
{
+ bool rcu = warn_rcu_enter();
va_list args;
pr_warn(CUT_HERE);
va_start(args, fmt);
vprintk(fmt, args);
va_end(args);
+ warn_rcu_exit(rcu);
}
EXPORT_SYMBOL(__warn_printk);
#endif
-#ifdef CONFIG_BUG
-
/* Support resetting WARN*_ONCE state */
static int clear_warn_once_set(void *data, u64 val)
* Called when gcc's -fstack-protector feature is used, and
* gcc detects corruption of the on-stack canary value
*/
-__visible void __stack_chk_fail(void)
+__visible noinstr void __stack_chk_fail(void)
{
+ instrumentation_begin();
panic("stack-protector: Kernel stack is corrupted in: %pB",
__builtin_return_address(0));
+ instrumentation_end();
}
EXPORT_SYMBOL(__stack_chk_fail);
#endif
-#ifdef CONFIG_ARCH_HAS_REFCOUNT
-void refcount_error_report(struct pt_regs *regs, const char *err)
-{
- WARN_RATELIMIT(1, "refcount_t %s at %pB in %s[%d], uid/euid: %u/%u\n",
- err, (void *)instruction_pointer(regs),
- current->comm, task_pid_nr(current),
- from_kuid_munged(&init_user_ns, current_uid()),
- from_kuid_munged(&init_user_ns, current_euid()));
-}
-#endif
-
core_param(panic, panic_timeout, int, 0644);
core_param(panic_print, panic_print, ulong, 0644);
core_param(pause_on_oops, pause_on_oops, int, 0644);
return 0;
}
early_param("oops", oops_setup);
+
+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;
+
+ pr_info("panic_on_taint: bitmask=0x%lx nousertaint_mode=%s\n",
+ panic_on_taint, str_enabled_disabled(panic_on_taint_nousertaint));
+
+ return 0;
+}
+early_param("panic_on_taint", panic_on_taint_setup);