@@ -180,9 +180,6 @@ static void panic_print_sys_info(bool console_flush)
return;
}
- if (panic_print & PANIC_PRINT_ALL_CPU_BT)
- trigger_all_cpu_backtrace();
-
if (panic_print & PANIC_PRINT_TASK_INFO)
show_state();
@@ -199,6 +196,30 @@ static void panic_print_sys_info(bool console_flush)
ftrace_dump(DUMP_ALL);
}
+/*
+ * 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(void)
+{
+ 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_post_notifiers)
+ smp_send_stop();
+ else
+ crash_smp_send_stop();
+}
+
/**
* panic - halt the system
* @fmt: The text string to print
@@ -214,7 +235,6 @@ void panic(const char *fmt, ...)
long i, i_next = 0, len;
int state = 0;
int old_cpu, this_cpu;
- bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;
if (panic_on_warn) {
/*
@@ -289,23 +309,10 @@ void panic(const char *fmt, ...)
*
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
- if (!_crash_kexec_post_notifiers) {
+ 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();
/*
* Run any panic handlers, including those that might need to
@@ -326,7 +333,7 @@ void panic(const char *fmt, ...)
*
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
- if (_crash_kexec_post_notifiers)
+ if (crash_kexec_post_notifiers)
__crash_kexec(NULL);
#ifdef CONFIG_VT
Commit 8d470a45d1a6 ("panic: add option to dump all CPUs backtraces in panic_print") introduced a setting for the "panic_print" kernel parameter to allow users to request a NMI backtrace on panic. Problem is that the panic_print handling happens after the secondary CPUs are already disabled, hence this option ended-up being kind of a no-op - kernel skips the NMI trace in idling CPUs, which is the case of offline CPUs. Fix it by checking the NMI backtrace bit in the panic_print prior to the CPU disabling function. Fixes: 8d470a45d1a6 ("panic: add option to dump all CPUs backtraces in panic_print") Cc: Feng Tang <feng.tang@intel.com> Cc: Petr Mladek <pmladek@suse.com> Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com> --- V2: - new patch, there was no V1 of this one. Hi folks, thanks upfront for reviews. This is a new patch, fixing an issue I found in my tests, so I shoved it into this fixes series. Notice that while at it, I got rid of the "crash_kexec_post_notifiers" local copy in panic(). This was introduced by commit b26e27ddfd2a ("kexec: use core_param for crash_kexec_post_notifiers boot option"), but it is not clear from comments or commit message why this local copy is required. My understanding is that it's a mechanism to prevent some concurrency, in case some other CPU modify this variable while panic() is running. I find it very unlikely, hence I removed it - but if people consider this copy needed, I can respin this patch and keep it, even providing a comment about that, in order to be explict about its need. Let me know your thoughts! Cheers, Guilherme kernel/panic.c | 47 +++++++++++++++++++++++++++-------------------- 1 file changed, 27 insertions(+), 20 deletions(-)