Re: [PATCH 4/6] arm64/io: Provide a WC friendly __iowriteXX_copy()

[Jason Gunthorpe <jgg@nvidia.com>]

On Tue, Feb 27, 2024 at 10:37:18AM +0000, Catalin Marinas wrote:
> On Tue, Feb 20, 2024 at 09:17:08PM -0400, Jason Gunthorpe wrote:
> > +/*
> > + * This generates a memcpy that works on a from/to address which is aligned to
> > + * bits. Count is in terms of the number of bits sized quantities to copy. It
> > + * optimizes to use the STR groupings when possible so that it is WC friendly.
> > + */
> > +#define memcpy_toio_aligned(to, from, count, bits)                        \
> > +	({                                                                \
> > +		volatile u##bits __iomem *_to = to;                       \
> > +		const u##bits *_from = from;                              \
> > +		size_t _count = count;                                    \
> > +		const u##bits *_end_from = _from + ALIGN_DOWN(_count, 8); \
> > +                                                                          \
> > +		for (; _from < _end_from; _from += 8, _to += 8)           \
> > +			__const_memcpy_toio_aligned##bits(_to, _from, 8); \
> > +		if ((_count % 8) >= 4) {                                  \
> > +			__const_memcpy_toio_aligned##bits(_to, _from, 4); \
> > +			_from += 4;                                       \
> > +			_to += 4;                                         \
> > +		}                                                         \
> > +		if ((_count % 4) >= 2) {                                  \
> > +			__const_memcpy_toio_aligned##bits(_to, _from, 2); \
> > +			_from += 2;                                       \
> > +			_to += 2;                                         \
> > +		}                                                         \
> > +		if (_count % 2)                                           \
> > +			__const_memcpy_toio_aligned##bits(_to, _from, 1); \
> > +	})
> 
> Do we actually need all this if count is not constant? If it's not
> performance critical anywhere, I'd rather copy the generic
> implementation, it's easier to read.

Which generic version?

The point is to maximize WC effects with non-constant values, so I
think we do need something like this. ie we can't just fall back to
looping over 64 bit stores one at a time.

If we don't use the large block stores we know we get very poor WC
behavior. So at least the 8 and 4 constant value sections are
needed. At that point you may as well just do 4 and 2 instead of
another loop.

Most places I know about using this are performance paths, the entire
iocopy infrastructure was introduced as an x86 performance
optimization..

Jason