Re: [PATCH] util/cacheflush: Avoid flushing dcache twice when not necessary

["Philippe Mathieu-Daudé" <philmd@linaro.org>]

On 5/6/23 23:56, BALATON Zoltan wrote:
> On Mon, 5 Jun 2023, Philippe Mathieu-Daudé wrote:
>> <libkern/OSCacheControl.h> describes sys_icache_invalidate() as
>> "equivalent to sys_cache_control(kCacheFunctionPrepareForExecution)",
>> having kCacheFunctionPrepareForExecution defined as:
>>
>>  /* Prepare memory for execution.  This should be called
>>   * after writing machine instructions to memory, before
>>   * executing them.  It syncs the dcache and icache. [...]
>>   */
>>
>> Since the dcache is also sync'd, we can avoid the sys_dcache_flush()
>> call when both rx/rw pointers are equal.
>>
>> Suggested-by: Richard Henderson <richard.henderson@linaro.org>
>> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
>> ---
>> Based-on: <20230605175647.88395-2-philmd@linaro.org>
>> ---
>> util/cacheflush.c | 9 ++++++++-
>> 1 file changed, 8 insertions(+), 1 deletion(-)
>>
>> diff --git a/util/cacheflush.c b/util/cacheflush.c
>> index de35616718..a08906155a 100644
>> --- a/util/cacheflush.c
>> +++ b/util/cacheflush.c
>> @@ -241,7 +241,14 @@ static void __attribute__((constructor)) 
>> init_cache_info(void)
>>
>> void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
>> {
>> -    sys_dcache_flush((void *)rw, len);
>> +    if (rx == rw) {
> 
> Isn't it more straight forward to use rx != rw and drop the else branch 
> than having an empty if branch? You can still keep the comment above the 
> if to explain it if needed.

I tried that first but found it was not obvious, so chose this
form because it seemed clearer to me.