diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 9d05572370ed..84b0078272d1 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -14,8 +14,6 @@
  * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
  */
 
-.weak memcpy
-
 /*
  * memcpy - Copy a memory block.
  *
@@ -28,7 +26,9 @@
  * rax original destination
  */
 ENTRY(__memcpy)
-ENTRY(memcpy)
+.weak memcpy
+.p2align 4, 0x90
+memcpy:
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index bbec69d8223b..e1cfc880f42d 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -25,8 +25,8 @@
  * rax: dest
  */
 .weak memmove
-
-ENTRY(memmove)
+.p2align 4, 0x90
+memmove:
 ENTRY(__memmove)
 
 	/* Handle more 32 bytes in loop */
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 9bc861c71e75..084189acdcd0 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -6,8 +6,6 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
-.weak memset
-
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
  * string to get better performance than the original function. The code is
@@ -19,7 +17,9 @@
  *
  * rax   original destination
  */
-ENTRY(memset)
+.weak memset
+.p2align 4, 0x90
+memset:
 ENTRY(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended