RE: [PATCH v2 3/3] x86: remove unneeded flush in arch_copy_from_iter_pmem()

[Boylston, Brian]

Boaz Harrosh wrote on 2016-10-26:
> On 10/26/2016 06:50 PM, Brian Boylston wrote:
>> copy_from_iter_nocache() now uses nocache copies for all types of iovecs
>> on x86, so the flush in arch_copy_from_iter_pmem() is no longer needed.
>> 
>> Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
>> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
>> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
>> Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
>> Cc: <x86@xxxxxxxxxx>
>> Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
>> Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
>> Signed-off-by: Brian Boylston <brian.boylston@xxxxxxx>
>> Reviewed-by: Toshi Kani <toshi.kani@xxxxxxx>
>> Reported-by: Oliver Moreno <oliver.moreno@xxxxxxx>
>> ---
>>  arch/x86/include/asm/pmem.h | 19 +------------------
>>  1 file changed, 1 insertion(+), 18 deletions(-)
>> diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
>> index 643eba4..2fbf4ae 100644
>> --- a/arch/x86/include/asm/pmem.h
>> +++ b/arch/x86/include/asm/pmem.h
>> @@ -72,15 +72,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size)
>>  		clwb(p);
>>  }
>> -/*
>> - * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
>> - * iterators, so for other types (bvec & kvec) we must do a cache write-back.
>> - */
>> -static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
>> -{
>> -	return iter_is_iovec(i) == false;
>> -}
>> -
>>  /**
>>   * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
>>   * @addr:	PMEM destination address
>> @@ -92,15 +83,7 @@ static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
>>  static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
>>  		struct iov_iter *i)
>>  {
>> -	size_t len;
>> -
>> -	/* TODO: skip the write-back by always using non-temporal stores */
>> -	len = copy_from_iter_nocache(addr, bytes, i);
>> -
>> -	if (__iter_needs_pmem_wb(i))
>> -		arch_wb_cache_pmem(addr, bytes);
>> -
>> -	return len;
>> +	return copy_from_iter_nocache(addr, bytes, i);
> 
> I wish you would remove all this completely. Don't see the point for it anymore
> 

At first, I was just targeting bvecs for the splice() case, so I had left the
check and the flush in there for kvecs.  When doing this v2 of the patch set,
I made kvecs nocache as well, so removed the check and flush, but didn't follow
through completely as you suggest.  Will revisit.

Thanks!
Brian

> Thanks a lot for doing this. I have this patch for ages in my trees and was too
> lasy to fight them through. Yes it is a big boost for many workloads.
> 
> Lots of gratitude
> Boaz
> 
>>  }
>>  /**