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

From: Jason Gunthorpe <jgg@nvidia.com>
To: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Christian Borntraeger <borntraeger@linux.ibm.com>,
	Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Gerald Schaefer <gerald.schaefer@linux.ibm.com>,
	Vasily Gorbik <gor@linux.ibm.com>,
	Heiko Carstens <hca@linux.ibm.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Justin Stitt <justinstitt@google.com>,
	Jakub Kicinski <kuba@kernel.org>,
	Leon Romanovsky <leon@kernel.org>,
	linux-rdma@vger.kernel.org, linux-s390@vger.kernel.org,
	llvm@lists.linux.dev, Ingo Molnar <mingo@redhat.com>,
	Bill Wendling <morbo@google.com>,
	Nathan Chancellor <nathan@kernel.org>,
	Nick Desaulniers <ndesaulniers@google.com>,
	netdev@vger.kernel.org, Paolo Abeni <pabeni@redhat.com>,
	Salil Mehta <salil.mehta@huawei.com>,
	Jijie Shao <shaojijie@huawei.com>,
	Sven Schnelle <svens@linux.ibm.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	x86@kernel.org, Yisen Zhuang <yisen.zhuang@huawei.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Leon Romanovsky <leonro@mellanox.com>,
	linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
	Mark Rutland <mark.rutland@arm.com>,
	Michael Guralnik <michaelgur@mellanox.com>,
	patches@lists.linux.dev, Niklas Schnelle <schnelle@linux.ibm.com>,
	Will Deacon <will@kernel.org>
Subject: Re: [PATCH 4/6] arm64/io: Provide a WC friendly __iowriteXX_copy()
Date: Wed, 28 Feb 2024 19:06:16 -0400	[thread overview]
Message-ID: <20240228230616.GS13330@nvidia.com> (raw)
In-Reply-To: <Zd27XtDg_NDzLXg-@arm.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

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel