ARM: 7769/1: Cortex-A15: fix erratum 798181 implementation

Looking into the active_asids array is not enough, as we also need
to look into the reserved_asids array (they both represent processes
that are currently running).

Also, not holding the ASID allocator lock is racy, as another CPU
could schedule that process and trigger a rollover, making the erratum
workaround miss an IPI.

Exposing this outside of context.c is a little ugly on the side, so
let's define a new entry point that the erratum workaround can call
to obtain the cpumask.

Cc: <stable@vger.kernel.org> # 3.9
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 83e0905..eeab06e 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -45,10 +45,37 @@
 static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
 static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);
 
-DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(atomic64_t, active_asids);
 static DEFINE_PER_CPU(u64, reserved_asids);
 static cpumask_t tlb_flush_pending;
 
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+			     cpumask_t *mask)
+{
+	int cpu;
+	unsigned long flags;
+	u64 context_id, asid;
+
+	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+	context_id = mm->context.id.counter;
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+		/*
+		 * We only need to send an IPI if the other CPUs are
+		 * running the same ASID as the one being invalidated.
+		 */
+		asid = per_cpu(active_asids, cpu).counter;
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, cpu);
+		if (context_id == asid)
+			cpumask_set_cpu(cpu, mask);
+	}
+	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+}
+#endif
+
 #ifdef CONFIG_ARM_LPAE
 static void cpu_set_reserved_ttbr0(void)
 {