Introduce memcpy_nontemporal() for write-once copy sites that want a
named non-temporal copy primitive.

On x86_64, override the helper in arch/x86/include/asm/string_64.h using
the usual self-macro pattern, next to the existing memcpy_flushcache()
backend that memcpy_nontemporal() wraps.

include/linux/string.h provides the generic memcpy_nontemporal()
fallback as

  #define memcpy_nontemporal(dst, src, len) \
	((void)memcpy(dst, src, len))

instead of an inline wrapper, so architectures without a specialized
backend keep the usual memcpy() FORTIFY coverage when the compiler can
still see object sizes at the original call site. It also makes the
memcpy_nontemporal() API uniformly void, matching memcpy_flushcache()
and the x86 backend, so callers cannot accidentally depend on a return
value on fallback architectures.

memcpy_nontemporal() is only a copy primitive. It does not imply a drain
or a publication barrier. Callers that use it before a producer-consumer
or device-visible handoff must provide the required ordering at that
handoff point.

The immediate user is the ZONE_DEVICE template-copy path. It populates
struct page descriptors in a write-once pattern, so a regular cached
memcpy() can incur avoidable write-allocate traffic and cache pollution
for data with little near-term reuse.

Signed-off-by: Li Zhe <lizhe.67@bytedance.com>
---
 arch/x86/include/asm/string_64.h | 12 ++++++++++++
 include/linux/string.h           | 13 +++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 4635616863f5..21ae515ae35a 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -100,6 +100,18 @@ static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t
 	}
 	__memcpy_flushcache(dst, src, cnt);
 }
+
+#define memcpy_nontemporal memcpy_nontemporal
+/*
+ * Reuse the existing x86 flushcache backend as the non-temporal copy
+ * primitive.
+ */
+static __always_inline void memcpy_nontemporal(void *dst, const void *src,
+		size_t cnt)
+{
+	memcpy_flushcache(dst, src, cnt);
+}
+
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/string.h b/include/linux/string.h
index 5702daca4326..6cb5cdd01158 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -278,6 +278,19 @@ static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
 }
 #endif
 
+#ifndef memcpy_nontemporal
+/*
+ * memcpy_nontemporal() requests a non-temporal copy when the
+ * architecture has a suitable backend. Architectures without a
+ * specialized backend fall back to memcpy(). Keep this as a
+ * function-like macro so the compiler can still see the original
+ * memcpy() call site and preserve the usual FORTIFY coverage when
+ * object sizes remain visible there, while keeping the API void.
+ */
+#define memcpy_nontemporal(dst, src, len) \
+	((void)memcpy(dst, src, len))
+#endif
+
 void *memchr_inv(const void *s, int c, size_t n);
 char *strreplace(char *str, char old, char new);
 
-- 
2.20.1