LoongArch: Prevent cond_resched() occurring within kernel-fpu

When CONFIG_PREEMPT_COUNT is not configured (i.e. CONFIG_PREEMPT_NONE/
CONFIG_PREEMPT_VOLUNTARY), preempt_disable() / preempt_enable() merely
acts as a barrier(). However, in these cases cond_resched() can still
trigger a context switch and modify the CSR.EUEN, resulting in do_fpu()
exception being activated within the kernel-fpu critical sections, as
demonstrated in the following path:

dcn32_calculate_wm_and_dlg()
    DC_FP_START()
	dcn32_calculate_wm_and_dlg_fpu()
	    dcn32_find_dummy_latency_index_for_fw_based_mclk_switch()
		dcn32_internal_validate_bw()
		    dcn32_enable_phantom_stream()
			dc_create_stream_for_sink()
			   kzalloc(GFP_KERNEL)
				__kmem_cache_alloc_node()
				    __cond_resched()
    DC_FP_END()

This patch is similar to commit d021985 (x86/fpu: Improve crypto
performance by making kernel-mode FPU reliably usable in softirqs).  It
uses local_bh_disable() instead of preempt_disable() for non-RT kernels
so it can avoid the cond_resched() issue, and also extend the kernel-fpu
application scenarios to the softirq context.

Cc: stable@vger.kernel.org
Signed-off-by: Tianyang Zhang <zhangtianyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

Author: zhangtianyang-zty

arch/loongarch/kernel/kfpu.c

@@ -18,11 +18,28 @@ static unsigned int euen_mask = CSR_EUEN_FPEN;
 static DEFINE_PER_CPU(bool, in_kernel_fpu);
 static DEFINE_PER_CPU(unsigned int, euen_current);
 
+static inline void fpregs_lock(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_disable();
+	else
+		local_bh_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_enable();
+	else
+		local_bh_enable();
+}
+
 void kernel_fpu_begin(void)
 {
 	unsigned int *euen_curr;
 
-	preempt_disable();
+	if (!irqs_disabled())
+		fpregs_lock();
 
 	WARN_ON(this_cpu_read(in_kernel_fpu));
 
@@ -73,7 +90,8 @@ void kernel_fpu_end(void)
 
 	this_cpu_write(in_kernel_fpu, false);
 
-	preempt_enable();
+	if (!irqs_disabled())
+		fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);