lkdtm/bugs: add test for hung smp_call_function_single()

The CONFIG_CSD_LOCK_WAIT_DEBUG option enables debugging of hung
smp_call_function*() calls (e.g. when the target CPU gets stuck within
the callback function). Testing this option requires triggering such
hangs.

This patch adds an lkdtm test with a hung smp_call_function_single()
callback, which can be used to test CONFIG_CSD_LOCK_WAIT_DEBUG and NMI
backtraces (as CONFIG_CSD_LOCK_WAIT_DEBUG will attempt an NMI backtrace
of the hung target CPU).

On arm64 using pseudo-NMI, this looks like:

| # mount -t debugfs none /sys/kernel/debug/
| # echo SMP_CALL_LOCKUP > /sys/kernel/debug/provoke-crash/DIRECT
| lkdtm: Performing direct entry SMP_CALL_LOCKUP
| smp: csd: Detected non-responsive CSD lock (#1) on CPU#1, waiting 5000000176 ns for CPU#00 __lkdtm_SMP_CALL_LOCKUP+0x0/0x8(0x0).
| smp:     csd: CSD lock (#1) handling this request.
| Sending NMI from CPU 1 to CPUs 0:
| NMI backtrace for cpu 0
| CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.9.0-rc4-00001-gfdfd281212ec #1
| Hardware name: linux,dummy-virt (DT)
| pstate: 60401005 (nZCv daif +PAN -UAO -TCO -DIT +SSBS BTYPE=--)
| pc : __lkdtm_SMP_CALL_LOCKUP+0x0/0x8
| lr : __flush_smp_call_function_queue+0x1b0/0x290
| sp : ffff800080003f30
| pmr_save: 00000060
| x29: ffff800080003f30 x28: ffffa4ce961a4900 x27: 0000000000000000
| x26: fff000003fcfa0c0 x25: ffffa4ce961a4900 x24: ffffa4ce959aa140
| x23: ffffa4ce959aa140 x22: 0000000000000000 x21: ffff800080523c40
| x20: 0000000000000000 x19: 0000000000000000 x18: fff05b31aa323000
| x17: fff05b31aa323000 x16: ffff800080000000 x15: 0000330fc3fe6b2c
| x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000279
| x11: 0000000000000040 x10: fff000000302d0a8 x9 : fff000000302d0a0
| x8 : fff0000003400270 x7 : 0000000000000000 x6 : ffffa4ce9451b810
| x5 : 0000000000000000 x4 : fff05b31aa323000 x3 : ffff800080003f30
| x2 : fff05b31aa323000 x1 : ffffa4ce959aa140 x0 : 0000000000000000
| Call trace:
|  __lkdtm_SMP_CALL_LOCKUP+0x0/0x8
|  generic_smp_call_function_single_interrupt+0x14/0x20
|  ipi_handler+0xb8/0x178
|  handle_percpu_devid_irq+0x84/0x130
|  generic_handle_domain_irq+0x2c/0x44
|  gic_handle_irq+0x118/0x240
|  call_on_irq_stack+0x24/0x4c
|  do_interrupt_handler+0x80/0x84
|  el1_interrupt+0x44/0xc0
|  el1h_64_irq_handler+0x18/0x24
|  el1h_64_irq+0x78/0x7c
|  default_idle_call+0x40/0x60
|  do_idle+0x23c/0x2d0
|  cpu_startup_entry+0x38/0x3c
|  kernel_init+0x0/0x1d8
|  start_kernel+0x51c/0x608
|  __primary_switched+0x80/0x88
| CPU: 1 PID: 128 Comm: sh Not tainted 6.9.0-rc4-00001-gfdfd281212ec #1
| Hardware name: linux,dummy-virt (DT)
| Call trace:
|  dump_backtrace+0x90/0xe8
|  show_stack+0x18/0x24
|  dump_stack_lvl+0xac/0xe8
|  dump_stack+0x18/0x24
|  csd_lock_wait_toolong+0x268/0x338
|  smp_call_function_single+0x1dc/0x2f0
|  lkdtm_SMP_CALL_LOCKUP+0xcc/0xfc
|  lkdtm_do_action+0x1c/0x38
|  direct_entry+0xbc/0x14c
|  full_proxy_write+0x60/0xb4
|  vfs_write+0xd0/0x35c
|  ksys_write+0x70/0x104
|  __arm64_sys_write+0x1c/0x28
|  invoke_syscall+0x48/0x114
|  el0_svc_common.constprop.0+0x40/0xe0
|  do_el0_svc+0x1c/0x28
|  el0_svc+0x38/0x108
|  el0t_64_sync_handler+0x120/0x12c
|  el0t_64_sync+0x1a4/0x1a8
| smp: csd: Continued non-responsive CSD lock (#1) on CPU#1, waiting 10000064272 ns for CPU#00 __lkdtm_SMP_CALL_LOCKUP+0x0/0x8(0x0).
| smp:     csd: CSD lock (#1) handling this request.
| smp: csd: Continued non-responsive CSD lock (#1) on CPU#1, waiting 15000064384 ns for CPU#00 __lkdtm_SMP_CALL_LOCKUP+0x0/0x8(0x0).
| smp:     csd: CSD lock (#1) handling this request.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20240515120828.375585-1-mark.rutland@arm.com
Signed-off-by: Kees Cook <kees@kernel.org>

1 files changed, 30 insertions, 0 deletions

diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c
index 5178c02b21eb..62ba01525479 100644
--- a/drivers/misc/lkdtm/bugs.c
+++ b/drivers/misc/lkdtm/bugs.c
@@ -286,6 +286,35 @@ static void lkdtm_HARDLOCKUP(void)
 		cpu_relax();
 }
 
+static void __lkdtm_SMP_CALL_LOCKUP(void *unused)
+{
+	for (;;)
+		cpu_relax();
+}
+
+static void lkdtm_SMP_CALL_LOCKUP(void)
+{
+	unsigned int cpu, target;
+
+	cpus_read_lock();
+
+	cpu = get_cpu();
+	target = cpumask_any_but(cpu_online_mask, cpu);
+
+	if (target >= nr_cpu_ids) {
+		pr_err("FAIL: no other online CPUs\n");
+		goto out_put_cpus;
+	}
+
+	smp_call_function_single(target, __lkdtm_SMP_CALL_LOCKUP, NULL, 1);
+
+	pr_err("FAIL: did not hang\n");
+
+out_put_cpus:
+	put_cpu();
+	cpus_read_unlock();
+}
+
 static void lkdtm_SPINLOCKUP(void)
 {
 	/* Must be called twice to trigger. */
@@ -680,6 +709,7 @@ static struct crashtype crashtypes[] = {
 	CRASHTYPE(UNALIGNED_LOAD_STORE_WRITE),
 	CRASHTYPE(SOFTLOCKUP),
 	CRASHTYPE(HARDLOCKUP),
+	CRASHTYPE(SMP_CALL_LOCKUP),
 	CRASHTYPE(SPINLOCKUP),
 	CRASHTYPE(HUNG_TASK),
 	CRASHTYPE(OVERFLOW_SIGNED),