arm64: Prevent offlining first CPU with 32-bit EL0 on mismatched system

If we want to support 32-bit applications, then when we identify a CPU
with mismatched 32-bit EL0 support we must ensure that we will always
have an active 32-bit CPU available to us from then on. This is important
for the scheduler, because is_cpu_allowed() will be constrained to 32-bit
CPUs for compat tasks and forced migration due to a hotplug event will
hang if no 32-bit CPUs are available.

On detecting a mismatch, prevent offlining of either the mismatching CPU
if it is 32-bit capable, or find the first active 32-bit capable CPU
otherwise.

Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Catalin Marinas <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: willdeacon

arch/arm64/kernel/cpufeature.c

@@ -2901,15 +2901,38 @@ void __init setup_cpu_features(void)
 
 static int enable_mismatched_32bit_el0(unsigned int cpu)
 {
+	/*
+	 * The first 32-bit-capable CPU we detected and so can no longer
+	 * be offlined by userspace. -1 indicates we haven't yet onlined
+	 * a 32-bit-capable CPU.
+	 */
+	static int lucky_winner = -1;
+
 	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
 	bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0);
 
 	if (cpu_32bit) {
 		cpumask_set_cpu(cpu, cpu_32bit_el0_mask);
 		static_branch_enable_cpuslocked(&arm64_mismatched_32bit_el0);
-		setup_elf_hwcaps(compat_elf_hwcaps);
 	}
 
+	if (cpumask_test_cpu(0, cpu_32bit_el0_mask) == cpu_32bit)
+		return 0;
+
+	if (lucky_winner >= 0)
+		return 0;
+
+	/*
+	 * We've detected a mismatch. We need to keep one of our CPUs with
+	 * 32-bit EL0 online so that is_cpu_allowed() doesn't end up rejecting
+	 * every CPU in the system for a 32-bit task.
+	 */
+	lucky_winner = cpu_32bit ? cpu : cpumask_any_and(cpu_32bit_el0_mask,
+							 cpu_active_mask);
+	get_cpu_device(lucky_winner)->offline_disabled = true;
+	setup_elf_hwcaps(compat_elf_hwcaps);
+	pr_info("Asymmetric 32-bit EL0 support detected on CPU %u; CPU hot-unplug disabled on CPU %u\n",
+		cpu, lucky_winner);
 	return 0;
 }