[tip:x86/asm] x86/asm: Optimize memcpy_flushcache()

[tip-bot for Mikulas Patocka]

Commit-ID:  02101c45ec5b19d607af7372680f5259050b4e9c
Gitweb:     https://git.kernel.org/tip/02101c45ec5b19d607af7372680f5259050b4e9c
Author:     Mikulas Patocka <mpatocka@xxxxxxxxxx>
AuthorDate: Wed, 8 Aug 2018 17:22:16 -0400
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Mon, 10 Sep 2018 15:17:12 +0200

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@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mike Snitzer <snitzer@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: device-mapper development <dm-devel@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/alpine.LRH.2.02.1808081720460.24747@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/include/asm/string_64.h | 20 +++++++++++++++++++-
 arch/x86/lib/usercopy_64.c       |  4 ++--
 2 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index d33f92b9fa22..7ad41bfcc16c 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/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__ */
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 9c5606d88f61..c50a1d815a37 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/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)