Thread (31 messages) 31 messages, 6 authors, 2024-03-01

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

From: Jason Gunthorpe <jgg@nvidia.com>
Date: 2024-02-28 23:06:47
Also in: linux-arch, linux-patches, linux-rdma, linux-s390, llvm, netdev

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:
quoted
+/*
+ * 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
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help