x86: Stop using weak symbols for __iowrite32_copy()

Start switching iomap_copy routines over to use #define and arch provided
inline/macro functions instead of weak symbols.

Inline functions allow more compiler optimization and this is often a
driver hot path.

x86 has the only weak implementation for __iowrite32_copy(), so replace it
with a static inline containing the same single instruction inline
assembly. The compiler will generate the "mov edx,ecx" in a more optimal
way.

Remove iomap_copy_64.S

Link: https://lore.kernel.org/r/1-v3-1893cd8b9369+1925-mlx5_arm_wc_jgg@nvidia.com
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

arch/x86/include/asm/io.h

@@ -209,6 +209,23 @@ void memset_io(volatile void __iomem *, int, size_t);
 #define memcpy_toio memcpy_toio
 #define memset_io memset_io
 
+#ifdef CONFIG_X86_64
+/*
+ * Commit 0f07496144c2 ("[PATCH] Add faster __iowrite32_copy routine for
+ * x86_64") says that circa 2006 rep movsl is noticeably faster than a copy
+ * loop.
+ */
+static inline void __iowrite32_copy(void __iomem *to, const void *from,
+				    size_t count)
+{
+	asm volatile("rep ; movsl"
+		     : "=&c"(count), "=&D"(to), "=&S"(from)
+		     : "0"(count), "1"(to), "2"(from)
+		     : "memory");
+}
+#define __iowrite32_copy __iowrite32_copy
+#endif
+
 /*
  * ISA space is 'always mapped' on a typical x86 system, no need to
  * explicitly ioremap() it. The fact that the ISA IO space is mapped

arch/x86/lib/Makefile

@@ -53,7 +53,6 @@ ifneq ($(CONFIG_X86_CMPXCHG64),y)
         lib-y += atomic64_386_32.o
 endif
 else
-        obj-y += iomap_copy_64.o
 ifneq ($(CONFIG_GENERIC_CSUM),y)
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
 endif

arch/x86/lib/iomap_copy_64.S

@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright 2006 PathScale, Inc.  All Rights Reserved.
- */
-
-#include <linux/linkage.h>
-
-/*
- * override generic version in lib/iomap_copy.c
- */
-SYM_FUNC_START(__iowrite32_copy)
-	movl %edx,%ecx
-	rep movsl
-	RET
-SYM_FUNC_END(__iowrite32_copy)

include/linux/io.h

@@ -16,7 +16,10 @@
 struct device;
 struct resource;
 
-__visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count);
+#ifndef __iowrite32_copy
+void __iowrite32_copy(void __iomem *to, const void *from, size_t count);
+#endif
+
 void __ioread32_copy(void *to, const void __iomem *from, size_t count);
 void __iowrite64_copy(void __iomem *to, const void *from, size_t count);
 

lib/iomap_copy.c

@@ -16,9 +16,8 @@
  * time.  Order of access is not guaranteed, nor is a memory barrier
  * performed afterwards.
  */
-void __attribute__((weak)) __iowrite32_copy(void __iomem *to,
-					    const void *from,
-					    size_t count)
+#ifndef __iowrite32_copy
+void __iowrite32_copy(void __iomem *to, const void *from, size_t count)
 {
 	u32 __iomem *dst = to;
 	const u32 *src = from;
@@ -28,6 +27,7 @@ void __attribute__((weak)) __iowrite32_copy(void __iomem *to,
 		__raw_writel(*src++, dst++);
 }
 EXPORT_SYMBOL_GPL(__iowrite32_copy);
+#endif
 
 /**
  * __ioread32_copy - copy data from MMIO space, in 32-bit units