Merge tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:

 - Refactor VFP code and convert to C code (Ard Biesheuvel)

 - Fix hardware breakpoint single-stepping using bpf_overflow_handler

 - Make SMP stop calls asynchronous allowing panic from irq context to
   work

 - Fix for kernel-doc warnings for locomo

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm:
  Revert part of ae1f8d793a19 ("ARM: 9304/1: add prototype for function called only from asm")
  ARM: 9318/1: locomo: move kernel-doc to prevent warnings
  ARM: 9317/1: kexec: Make smp stop calls asynchronous
  ARM: 9316/1: hw_breakpoint: fix single-stepping when using bpf_overflow_handler
  ARM: entry: Make asm coproc dispatch code NWFPE only
  ARM: iwmmxt: Use undef hook to enable coprocessor for task
  ARM: entry: Disregard Thumb undef exception in coproc dispatch
  ARM: vfp: Use undef hook for handling VFP exceptions
  ARM: kernel: Get rid of thread_info::used_cp[] array
  ARM: vfp: Reimplement VFP exception entry in C code
  ARM: vfp: Remove workaround for Feroceon CPUs
  ARM: vfp: Record VFP bounces as perf emulation faults

1 files changed, 13 insertions, 1 deletions

diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 46364b699cc3..5d07cf9e0044 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -94,16 +94,28 @@ static void machine_crash_nonpanic_core(void *unused)
 	}
 }
 
+static DEFINE_PER_CPU(call_single_data_t, cpu_stop_csd) =
+	CSD_INIT(machine_crash_nonpanic_core, NULL);
+
 void crash_smp_send_stop(void)
 {
 	static int cpus_stopped;
 	unsigned long msecs;
+	call_single_data_t *csd;
+	int cpu, this_cpu = raw_smp_processor_id();
 
 	if (cpus_stopped)
 		return;
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	smp_call_function(machine_crash_nonpanic_core, NULL, false);
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+
+		csd = &per_cpu(cpu_stop_csd, cpu);
+		smp_call_function_single_async(cpu, csd);
+	}
+
 	msecs = 1000; /* Wait at most a second for the other cpus to stop */
 	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
 		mdelay(1);