riscv: optimized memcpy

Write a C version of memcpy() which uses the biggest data size allowed,
without generating unaligned accesses.

The procedure is made of three steps:
First copy data one byte at time until the destination buffer is aligned
to a long boundary.
Then copy the data one long at time shifting the current and the next u8
to compose a long at every cycle.
Finally, copy the remainder one byte at time.

On a BeagleV, the TCP RX throughput increased by 45%:

before:

$ iperf3 -c beaglev
Connecting to host beaglev, port 5201
[  5] local 192.168.85.6 port 44840 connected to 192.168.85.48 port 5201
[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-1.00   sec  76.4 MBytes   641 Mbits/sec   27    624 KBytes
[  5]   1.00-2.00   sec  72.5 MBytes   608 Mbits/sec    0    708 KBytes
[  5]   2.00-3.00   sec  73.8 MBytes   619 Mbits/sec   10    451 KBytes
[  5]   3.00-4.00   sec  72.5 MBytes   608 Mbits/sec    0    564 KBytes
[  5]   4.00-5.00   sec  73.8 MBytes   619 Mbits/sec    0    658 KBytes
[  5]   5.00-6.00   sec  73.8 MBytes   619 Mbits/sec   14    522 KBytes
[  5]   6.00-7.00   sec  73.8 MBytes   619 Mbits/sec    0    621 KBytes
[  5]   7.00-8.00   sec  72.5 MBytes   608 Mbits/sec    0    706 KBytes
[  5]   8.00-9.00   sec  73.8 MBytes   619 Mbits/sec   20    580 KBytes
[  5]   9.00-10.00  sec  73.8 MBytes   619 Mbits/sec    0    672 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec   736 MBytes   618 Mbits/sec   71             sender
[  5]   0.00-10.01  sec   733 MBytes   615 Mbits/sec                  receiver

after:

$ iperf3 -c beaglev
Connecting to host beaglev, port 5201
[  5] local 192.168.85.6 port 44864 connected to 192.168.85.48 port 5201
[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-1.00   sec   109 MBytes   912 Mbits/sec   48    559 KBytes
[  5]   1.00-2.00   sec   108 MBytes   902 Mbits/sec    0    690 KBytes
[  5]   2.00-3.00   sec   106 MBytes   891 Mbits/sec   36    396 KBytes
[  5]   3.00-4.00   sec   108 MBytes   902 Mbits/sec    0    567 KBytes
[  5]   4.00-5.00   sec   106 MBytes   891 Mbits/sec    0    699 KBytes
[  5]   5.00-6.00   sec   106 MBytes   891 Mbits/sec   32    414 KBytes
[  5]   6.00-7.00   sec   106 MBytes   891 Mbits/sec    0    583 KBytes
[  5]   7.00-8.00   sec   106 MBytes   891 Mbits/sec    0    708 KBytes
[  5]   8.00-9.00   sec   106 MBytes   891 Mbits/sec   28    433 KBytes
[  5]   9.00-10.00  sec   108 MBytes   902 Mbits/sec    0    591 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec  1.04 GBytes   897 Mbits/sec  144             sender
[  5]   0.00-10.01  sec  1.04 GBytes   894 Mbits/sec                  receiver

And the decreased CPU time of the memcpy() is observable with perf top.
This is the `perf top -Ue task-clock` output when doing the test:

before:

Overhead  Shared O  Symbol
  42.22%  [kernel]  [k] memcpy
  35.00%  [kernel]  [k] __asm_copy_to_user
   3.50%  [kernel]  [k] sifive_l2_flush64_range
   2.30%  [kernel]  [k] stmmac_napi_poll_rx
   1.11%  [kernel]  [k] memset

after:

Overhead  Shared O  Symbol
  45.69%  [kernel]  [k] __asm_copy_to_user
  29.06%  [kernel]  [k] memcpy
   4.09%  [kernel]  [k] sifive_l2_flush64_range
   2.77%  [kernel]  [k] stmmac_napi_poll_rx
   1.24%  [kernel]  [k] memset

Signed-off-by: Matteo Croce <mcroce@microsoft.com>

arch/riscv/include/asm/string.h

@@ -12,9 +12,13 @@
 #define __HAVE_ARCH_MEMSET
 extern asmlinkage void *memset(void *, int, size_t);
 extern asmlinkage void *__memset(void *, int, size_t);
+
+#ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
 #define __HAVE_ARCH_MEMCPY
-extern asmlinkage void *memcpy(void *, const void *, size_t);
-extern asmlinkage void *__memcpy(void *, const void *, size_t);
+extern void *memcpy(void *dest, const void *src, size_t count);
+extern void *__memcpy(void *dest, const void *src, size_t count);
+#endif
+
 #define __HAVE_ARCH_MEMMOVE
 extern asmlinkage void *memmove(void *, const void *, size_t);
 extern asmlinkage void *__memmove(void *, const void *, size_t);

arch/riscv/kernel/riscv_ksyms.c

@@ -10,8 +10,6 @@
  * Assembly functions that may be used (directly or indirectly) by modules
  */
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(__memcpy);
 EXPORT_SYMBOL(__memmove);

arch/riscv/lib/Makefile

@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0-only
 lib-y			+= delay.o
-lib-y			+= memcpy.o
 lib-y			+= memset.o
 lib-y			+= memmove.o
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
+lib-$(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) += string.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o

arch/riscv/lib/string.c

@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * String functions optimized for hardware which doesn't
+ * handle unaligned memory accesses efficiently.
+ *
+ * Copyright (C) 2021 Matteo Croce
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+
+/* Minimum size for a word copy to be convenient */
+#define MIN_THRESHOLD (BITS_PER_LONG / 8 * 2)
+
+/* convenience union to avoid cast between different pointer types */
+union types {
+	u8 *u8;
+	unsigned long *ulong;
+	uintptr_t uptr;
+};
+
+union const_types {
+	const u8 *u8;
+	unsigned long *ulong;
+};
+
+void *__memcpy(void *dest, const void *src, size_t count)
+{
+	const int bytes_long = BITS_PER_LONG / 8;
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	const int mask = bytes_long - 1;
+	const int distance = (src - dest) & mask;
+#endif
+	union const_types s = { .u8 = src };
+	union types d = { .u8 = dest };
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (count < MIN_THRESHOLD)
+		goto copy_remainder;
+
+	/* copy a byte at time until destination is aligned */
+	for (; count && d.uptr & mask; count--)
+		*d.u8++ = *s.u8++;
+
+	if (distance) {
+		unsigned long last, next;
+
+		/* move s backward to the previous alignment boundary */
+		s.u8 -= distance;
+
+		/* 32/64 bit wide copy from s to d.
+		 * d is aligned now but s is not, so read s alignment wise,
+		 * and do proper shift to get the right value.
+		 * Works only on Little Endian machines.
+		 */
+		for (next = s.ulong[0]; count >= bytes_long + mask; count -= bytes_long) {
+			last = next;
+			next = s.ulong[1];
+
+			d.ulong[0] = last >> (distance * 8) |
+				     next << ((bytes_long - distance) * 8);
+
+			d.ulong++;
+			s.ulong++;
+		}
+
+		/* restore s with the original offset */
+		s.u8 += distance;
+	} else
+#endif
+	{
+		/* if the source and dest lower bits are the same, do a simple
+		 * 32/64 bit wide copy.
+		 */
+		for (; count >= bytes_long; count -= bytes_long)
+			*d.ulong++ = *s.ulong++;
+	}
+
+	/* suppress warning when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y */
+	goto copy_remainder;
+
+copy_remainder:
+	while (count--)
+		*d.u8++ = *s.u8++;
+
+	return dest;
+}
+EXPORT_SYMBOL(__memcpy);
+
+void *memcpy(void *dest, const void *src, size_t count) __weak __alias(__memcpy);
+EXPORT_SYMBOL(memcpy);