riscv: Disable preemption while handling PR_RISCV_CTX_SW_FENCEI_OFF

The icache will be flushed in switch_to() if force_icache_flush is true,
or in flush_icache_deferred() if icache_stale_mask is set. Between
setting force_icache_flush to false and calculating the new
icache_stale_mask, preemption needs to be disabled. There are two
reasons for this:

1. If CPU migration happens between force_icache_flush = false, and the
   icache_stale_mask is set, an icache flush will not be emitted.
2. smp_processor_id() is used in set_icache_stale_mask() to mark the
   current CPU as not needing another flush since a flush will have
   happened either by userspace or by the kernel when performing the
   migration. smp_processor_id() is currently called twice with preemption
   enabled which causes a race condition. It allows
   icache_stale_mask to be populated with inconsistent CPU ids.

Resolve these two issues by setting the icache_stale_mask before setting
force_icache_flush to false, and using get_cpu()/put_cpu() to obtain the
smp_processor_id().

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Fixes: 6b9391b581 ("riscv: Include riscv_set_icache_flush_ctx prctl")
Link: https://lore.kernel.org/r/20240903-fix_fencei_optimization-v2-1-8025f20171fc@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/mm/cacheflush.c

@@ -158,6 +158,7 @@ void __init riscv_init_cbo_blocksizes(void)
 #ifdef CONFIG_SMP
 static void set_icache_stale_mask(void)
 {
+	int cpu = get_cpu();
 	cpumask_t *mask;
 	bool stale_cpu;
 
@@ -168,10 +169,11 @@ static void set_icache_stale_mask(void)
 	 * concurrently on different harts.
 	 */
 	mask = &current->mm->context.icache_stale_mask;
-	stale_cpu = cpumask_test_cpu(smp_processor_id(), mask);
+	stale_cpu = cpumask_test_cpu(cpu, mask);
 
 	cpumask_setall(mask);
-	cpumask_assign_cpu(smp_processor_id(), mask, stale_cpu);
+	cpumask_assign_cpu(cpu, mask, stale_cpu);
+	put_cpu();
 }
 #endif
 
@@ -239,14 +241,12 @@ int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long scope)
 	case PR_RISCV_CTX_SW_FENCEI_OFF:
 		switch (scope) {
 		case PR_RISCV_SCOPE_PER_PROCESS:
-			current->mm->context.force_icache_flush = false;
-
 			set_icache_stale_mask();
+			current->mm->context.force_icache_flush = false;
 			break;
 		case PR_RISCV_SCOPE_PER_THREAD:
-			current->thread.force_icache_flush = false;
-
 			set_icache_stale_mask();
+			current->thread.force_icache_flush = false;
 			break;
 		default:
 			return -EINVAL;