+static void (*xcall_deliver_impl)(struct trap_per_cpu *, int);
+
+static void xcall_deliver(u64 data0, u64 data1, u64 data2, const cpumask_t *mask)
+{
+ struct trap_per_cpu *tb;
+ int this_cpu, i, cnt;
+ unsigned long flags;
+ u16 *cpu_list;
+ u64 *mondo;
+
+ /* We have to do this whole thing with interrupts fully disabled.
+ * Otherwise if we send an xcall from interrupt context it will
+ * corrupt both our mondo block and cpu list state.
+ *
+ * One consequence of this is that we cannot use timeout mechanisms
+ * that depend upon interrupts being delivered locally. So, for
+ * example, we cannot sample jiffies and expect it to advance.
+ *
+ * Fortunately, udelay() uses %stick/%tick so we can use that.
+ */
+ local_irq_save(flags);
+
+ this_cpu = smp_processor_id();
+ tb = &trap_block[this_cpu];
+
+ mondo = __va(tb->cpu_mondo_block_pa);
+ mondo[0] = data0;
+ mondo[1] = data1;
+ mondo[2] = data2;
+ wmb();
+
+ cpu_list = __va(tb->cpu_list_pa);
+
+ /* Setup the initial cpu list. */
+ cnt = 0;
+ for_each_cpu_mask_nr(i, *mask) {
+ if (i == this_cpu || !cpu_online(i))
+ continue;
+ cpu_list[cnt++] = i;
+ }
+
+ if (cnt)
+ xcall_deliver_impl(tb, cnt);
+
+ local_irq_restore(flags);
+}
+
+/* Send cross call to all processors mentioned in MASK_P
+ * except self. Really, there are only two cases currently,
+ * "&cpu_online_map" and "&mm->cpu_vm_mask".