[PATCH v3 7/8] x86/string: extend memcpy_flushcache() fixed-size fastpaths

[Li Zhe]

Small constant-sized flushcache copies currently fall back to
__memcpy_flushcache() unless they are exactly 4, 8, or 16 bytes.

Factor the existing inline movnti sequences into small helpers and
extend the fixed-size fastpath coverage to 24..96 bytes for naturally
aligned transfers. This keeps common struct-page-sized copies on the
inline path for the upcoming memcpy_streaming() user, while still
falling back to __memcpy_flushcache() for unaligned or uncommon sizes.
Zero-length copies return immediately.

Issue the fixed-size stores in ascending address order so
write-combining sees a forward stream.

Signed-off-by: Li Zhe <lizhe.67@xxxxxxxxxxxxx>
---
 arch/x86/include/asm/string_64.h | 125 ++++++++++++++++++++++++++-----
 1 file changed, 107 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 0b57e9e6f3db..8e6fca0185ee 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -82,24 +82,6 @@ int strcmp(const char *cs, const char *ct);
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
 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);
-}
 
 /*
  * Only reuse memcpy_flushcache() for transfers that can stay entirely
@@ -123,6 +105,113 @@ static __always_inline int memcpy_flushcache_nt_safe(const void *dst,
 	return cnt == 4 && !(d & 3) && !(s & 3);
 }
 
+static __always_inline void memcpy_flushcache_4(void *dst, const void *src)
+{
+	asm volatile("movntil %1, %0"
+		     : "=m"(*(u32 *)dst)
+		     : "r"(*(const u32 *)src)
+		     : "memory");
+}
+
+static __always_inline void memcpy_flushcache_8(void *dst, const void *src)
+{
+	asm volatile("movntiq %1, %0"
+		     : "=m"(*(u64 *)dst)
+		     : "r"(*(const u64 *)src)
+		     : "memory");
+}
+
+static __always_inline void memcpy_flushcache_16(void *dst,
+						 const void *src)
+{
+	memcpy_flushcache_8(dst, src);
+	memcpy_flushcache_8(dst + 8, src + 8);
+}
+
+static __always_inline void memcpy_flushcache_32(void *dst,
+						 const void *src)
+{
+	memcpy_flushcache_16(dst, src);
+	memcpy_flushcache_16(dst + 16, src + 16);
+}
+
+static __always_inline void memcpy_flushcache_64(void *dst,
+						 const void *src)
+{
+	memcpy_flushcache_32(dst, src);
+	memcpy_flushcache_32(dst + 32, src + 32);
+}
+
+/*
+ * Keep common fixed-size copies on the inline movnti path when they can
+ * stay entirely on aligned non-temporal stores. Issue the stores in
+ * ascending address order so write-combining sees a forward stream.
+ */
+static __always_inline int memcpy_flushcache_small(void *dst,
+						   const void *src,
+						   size_t cnt)
+{
+	char *d = dst;
+	const char *s = src;
+
+	if (!memcpy_flushcache_nt_safe(dst, src, cnt))
+		return 0;
+
+	switch (cnt) {
+	case 4:
+		memcpy_flushcache_4(d, s);
+		return 1;
+	case 8:
+		memcpy_flushcache_8(d, s);
+		return 1;
+	}
+
+	if (cnt & 8) {
+		memcpy_flushcache_8(d, s);
+		d += 8;
+		s += 8;
+		cnt -= 8;
+	}
+
+	switch (cnt) {
+	case 16:
+		memcpy_flushcache_16(d, s);
+		return 1;
+	case 32:
+		memcpy_flushcache_32(d, s);
+		return 1;
+	case 48:
+		memcpy_flushcache_32(d, s);
+		memcpy_flushcache_16(d + 32, s + 32);
+		return 1;
+	case 64:
+		memcpy_flushcache_64(d, s);
+		return 1;
+	case 80:
+		memcpy_flushcache_64(d, s);
+		memcpy_flushcache_16(d + 64, s + 64);
+		return 1;
+	case 96:
+		memcpy_flushcache_64(d, s);
+		memcpy_flushcache_32(d + 64, s + 64);
+		return 1;
+	}
+
+	return 0;
+}
+
+static __always_inline void memcpy_flushcache(void *dst, const void *src,
+					      size_t cnt)
+{
+	if (!cnt)
+		return;
+
+	if (__builtin_constant_p(cnt) && memcpy_flushcache_small(dst, src, cnt))
+		return;
+
+	__memcpy_flushcache(dst, src, cnt);
+}
+
 #define __HAVE_ARCH_MEMCPY_STREAMING 1
 static __always_inline void memcpy_streaming(void *dst, const void *src,
 					     size_t cnt)
-- 
2.20.1