lkdtm/bugs: add test for panic() with stuck secondary CPUs

Upon a panic() the kernel will use either smp_send_stop() or
crash_smp_send_stop() to attempt to stop secondary CPUs via an IPI,
which may or may not be an NMI. Generally it's preferable that this is an
NMI so that CPUs can be stopped in as many situations as possible, but
it's not always possible to provide an NMI, and there are cases where
CPUs may be unable to handle the NMI regardless.

This patch adds a test for panic() where all other CPUs are stuck with
interrupts disabled, which can be used to check whether the kernel
gracefully handles CPUs failing to respond to a stop, and whether NMIs
actually work to stop CPUs.

For example, on arm64 *without* an NMI, this results in:

| # echo PANIC_STOP_IRQOFF > /sys/kernel/debug/provoke-crash/DIRECT
| lkdtm: Performing direct entry PANIC_STOP_IRQOFF
| Kernel panic - not syncing: panic stop irqoff test
| CPU: 2 PID: 24 Comm: migration/2 Not tainted 6.5.0-rc3-00077-ge6c782389895-dirty #4
| Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
| Stopper: multi_cpu_stop+0x0/0x1a0 <- stop_machine_cpuslocked+0x158/0x1a4
| Call trace:
|  dump_backtrace+0x94/0xec
|  show_stack+0x18/0x24
|  dump_stack_lvl+0x74/0xc0
|  dump_stack+0x18/0x24
|  panic+0x358/0x3e8
|  lkdtm_PANIC+0x0/0x18
|  multi_cpu_stop+0x9c/0x1a0
|  cpu_stopper_thread+0x84/0x118
|  smpboot_thread_fn+0x224/0x248
|  kthread+0x114/0x118
|  ret_from_fork+0x10/0x20
| SMP: stopping secondary CPUs
| SMP: failed to stop secondary CPUs 0-3
| Kernel Offset: 0x401cf3490000 from 0xffff80008000000c0
| PHYS_OFFSET: 0x40000000
| CPU features: 0x00000000,68c167a1,cce6773f
| Memory Limit: none
| ---[ end Kernel panic - not syncing: panic stop irqoff test ]---

Note the "failed to stop secondary CPUs 0-3" message.

On arm64 *with* an NMI, this results in:

| # echo PANIC_STOP_IRQOFF > /sys/kernel/debug/provoke-crash/DIRECT
| lkdtm: Performing direct entry PANIC_STOP_IRQOFF
| Kernel panic - not syncing: panic stop irqoff test
| CPU: 1 PID: 19 Comm: migration/1 Not tainted 6.5.0-rc3-00077-ge6c782389895-dirty #4
| Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
| Stopper: multi_cpu_stop+0x0/0x1a0 <- stop_machine_cpuslocked+0x158/0x1a4
| Call trace:
|  dump_backtrace+0x94/0xec
|  show_stack+0x18/0x24
|  dump_stack_lvl+0x74/0xc0
|  dump_stack+0x18/0x24
|  panic+0x358/0x3e8
|  lkdtm_PANIC+0x0/0x18
|  multi_cpu_stop+0x9c/0x1a0
|  cpu_stopper_thread+0x84/0x118
|  smpboot_thread_fn+0x224/0x248
|  kthread+0x114/0x118
|  ret_from_fork+0x10/0x20
| SMP: stopping secondary CPUs
| Kernel Offset: 0x55a9c0bc0000 from 0xffff800080000000
| PHYS_OFFSET: 0x40000000
| CPU features: 0x00000000,68c167a1,fce6773f
| Memory Limit: none
| ---[ end Kernel panic - not syncing: panic stop irqoff test ]---

Note the absence of a "failed to stop secondary CPUs" message, since we
don't log anything when secondary CPUs are successfully stopped.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Douglas Anderson <dianders@chromium.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Stephen Boyd <swboyd@chromium.org>
Cc: Sumit Garg <sumit.garg@linaro.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Link: https://lore.kernel.org/r/20230921161634.4063233-1-mark.rutland@arm.com
Signed-off-by: Kees Cook <keescook@chromium.org>

2 files changed, 30 insertions, 1 deletions

diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c
index c66cc05a68c4..b080eb2335eb 100644
--- a/drivers/misc/lkdtm/bugs.c
+++ b/drivers/misc/lkdtm/bugs.c
@@ -6,12 +6,14 @@
  * test source files.
  */
 #include "lkdtm.h"
+#include <linux/cpu.h>
 #include <linux/list.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task_stack.h>
-#include <linux/uaccess.h>
 #include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <linux/uaccess.h>
 
 #if IS_ENABLED(CONFIG_X86_32) && !IS_ENABLED(CONFIG_UML)
 #include <asm/desc.h>
@@ -73,6 +75,31 @@ static void lkdtm_PANIC(void)
 	panic("dumptest");
 }
 
+static int panic_stop_irqoff_fn(void *arg)
+{
+	atomic_t *v = arg;
+
+	/*
+	 * As stop_machine() disables interrupts, all CPUs within this function
+	 * have interrupts disabled and cannot take a regular IPI.
+	 *
+	 * The last CPU which enters here will trigger a panic, and as all CPUs
+	 * cannot take a regular IPI, we'll only be able to stop secondaries if
+	 * smp_send_stop() or crash_smp_send_stop() uses an NMI.
+	 */
+	if (atomic_inc_return(v) == num_online_cpus())
+		panic("panic stop irqoff test");
+
+	for (;;)
+		cpu_relax();
+}
+
+static void lkdtm_PANIC_STOP_IRQOFF(void)
+{
+	atomic_t v = ATOMIC_INIT(0);
+	stop_machine(panic_stop_irqoff_fn, &v, cpu_online_mask);
+}
+
 static void lkdtm_BUG(void)
 {
 	BUG();
@@ -638,6 +665,7 @@ static noinline void lkdtm_CORRUPT_PAC(void)
 
 static struct crashtype crashtypes[] = {
 	CRASHTYPE(PANIC),
+	CRASHTYPE(PANIC_STOP_IRQOFF),
 	CRASHTYPE(BUG),
 	CRASHTYPE(WARNING),
 	CRASHTYPE(WARNING_MESSAGE),
diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt
index 607b8d7e3ea3..71a2990b48b1 100644
--- a/tools/testing/selftests/lkdtm/tests.txt
+++ b/tools/testing/selftests/lkdtm/tests.txt
@@ -1,4 +1,5 @@
 #PANIC
+#PANIC_STOP_IRQOFF Crashes entire system
 BUG kernel BUG at
 WARNING WARNING:
 WARNING_MESSAGE message trigger