x86/asm: Optimize memcpy_flushcache()

I use memcpy_flushcache() in my persistent memory driver for metadata
updates, there are many 8-byte and 16-byte updates and it turns out that
the overhead of memcpy_flushcache causes 2% performance degradation
compared to "movnti" instruction explicitly coded using inline assembler.

The tests were done on a Skylake processor with persistent memory emulated
using the "memmap" kernel parameter. dd was used to copy data to the
dm-writecache target.

This patch recognizes memcpy_flushcache calls with constant short length
and turns them into inline assembler - so that I don't have to use inline
assembler in the driver.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: device-mapper development <dm-devel@redhat.com>
Link: http://lkml.kernel.org/r/alpine.LRH.2.02.1808081720460.24747@file01.intranet.prod.int.rdu2.redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/string_64.h

@@ -149,7 +149,25 @@ memcpy_mcsafe(void *dst, const void *src, size_t cnt)
 
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
-void memcpy_flushcache(void *dst, const void *src, size_t cnt);
+void __memcpy_flushcache(void *dst, const void *src, size_t cnt);
+static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
+{
+	if (__builtin_constant_p(cnt)) {
+		switch (cnt) {
+			case 4:
+				asm ("movntil %1, %0" : "=m"(*(u32 *)dst) : "r"(*(u32 *)src));
+				return;
+			case 8:
+				asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src));
+				return;
+			case 16:
+				asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src));
+				asm ("movntiq %1, %0" : "=m"(*(u64 *)(dst + 8)) : "r"(*(u64 *)(src + 8)));
+				return;
+		}
+	}
+	__memcpy_flushcache(dst, src, cnt);
+}
 #endif
 
 #endif /* __KERNEL__ */

arch/x86/lib/usercopy_64.c

@@ -153,7 +153,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
 	return rc;
 }
 
-void memcpy_flushcache(void *_dst, const void *_src, size_t size)
+void __memcpy_flushcache(void *_dst, const void *_src, size_t size)
 {
 	unsigned long dest = (unsigned long) _dst;
 	unsigned long source = (unsigned long) _src;
@@ -216,7 +216,7 @@ void memcpy_flushcache(void *_dst, const void *_src, size_t size)
 		clean_cache_range((void *) dest, size);
 	}
 }
-EXPORT_SYMBOL_GPL(memcpy_flushcache);
+EXPORT_SYMBOL_GPL(__memcpy_flushcache);
 
 void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
 		size_t len)