drm/amd/display: Simplify the per-CPU usage.

The fpu_recursion_depth counter is used to ensure that dc_fpu_begin()
can be invoked multiple times while the FPU-disable function itself is
only invoked once. Also the counter part (dc_fpu_end()) is ballanced
properly.

Instead of using the get_cpu_ptr() dance around the inc it is simpler to
increment the per-CPU variable directly. Also the per-CPU variable has
to be incremented and decremented on the same CPU. This is ensured by
the inner-part which disables preemption. This is kind of not obvious,
works and the preempt-counter is touched a few times for no reason.

Disable preemption before incrementing fpu_recursion_depth for the first
time. Keep preemption disabled until dc_fpu_end() where the counter is
decremented making it obvious that the preemption has to stay disabled
while the counter is non-zero.
Use simple inc/dec functions.
Remove the nested preempt_disable/enable functions which are now not
needed.

Acked-by: Harry Wentland <[e-mail]>
Reviewed-by: Rodrigo Siqueira <[e-mail]>
Signed-off-by: Sebastian Andrzej Siewior <[e-mail]>
Signed-off-by: Hamza Mahfooz <[e-mail]>
Signed-off-by: Alex Deucher <[e-mail]>

drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c

···
  */
 inline void dc_assert_fp_enabled(void)
 {
-	int *pcpu, depth = 0;
+	int depth;
 
-	pcpu = get_cpu_ptr(&fpu_recursion_depth);
-	depth = *pcpu;
-	put_cpu_ptr(&fpu_recursion_depth);
+	depth = __this_cpu_read(fpu_recursion_depth);
 
 	ASSERT(depth >= 1);
 }
···
  */
 void dc_fpu_begin(const char *function_name, const int line)
 {
-	int *pcpu;
+	int depth;
 
-	pcpu = get_cpu_ptr(&fpu_recursion_depth);
-	*pcpu += 1;
+	preempt_disable();
+	depth = __this_cpu_inc_return(fpu_recursion_depth);
 
-	if (*pcpu == 1) {
+	if (depth == 1) {
 #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH)
 		kernel_fpu_begin();
 #elif defined(CONFIG_PPC64)
-		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
-			preempt_disable();
+		if (cpu_has_feature(CPU_FTR_VSX_COMP))
 			enable_kernel_vsx();
-		} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) {
-			preempt_disable();
+		else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP))
 			enable_kernel_altivec();
-		} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) {
-			preempt_disable();
+		else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE))
 			enable_kernel_fp();
-		}
 #elif defined(CONFIG_ARM64)
 		kernel_neon_begin();
 #endif
 	}
 
-	TRACE_DCN_FPU(true, function_name, line, *pcpu);
-	put_cpu_ptr(&fpu_recursion_depth);
+	TRACE_DCN_FPU(true, function_name, line, depth);
 }
 
 /**
···
  */
 void dc_fpu_end(const char *function_name, const int line)
 {
-	int *pcpu;
+	int depth;
 
-	pcpu = get_cpu_ptr(&fpu_recursion_depth);
-	*pcpu -= 1;
-	if (*pcpu <= 0) {
+	depth = __this_cpu_dec_return(fpu_recursion_depth);
+	if (depth == 0) {
 #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH)
 		kernel_fpu_end();
 #elif defined(CONFIG_PPC64)
-		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
+		if (cpu_has_feature(CPU_FTR_VSX_COMP))
 			disable_kernel_vsx();
-			preempt_enable();
-		} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) {
+		else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP))
 			disable_kernel_altivec();
-			preempt_enable();
-		} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) {
+		else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE))
 			disable_kernel_fp();
-			preempt_enable();
-		}
 #elif defined(CONFIG_ARM64)
 		kernel_neon_end();
 #endif
+	} else {
+		WARN_ON_ONCE(depth < 0);
 	}
 
-	TRACE_DCN_FPU(false, function_name, line, *pcpu);
-	put_cpu_ptr(&fpu_recursion_depth);
+	TRACE_DCN_FPU(false, function_name, line, depth);
+	preempt_enable();
 }