diff --git a/arch/arm64/crypto/poly1305-armv8.pl b/arch/arm64/crypto/poly1305-armv8.pl
index 6e5576d19af8..cbc980fb02e3 100644
--- a/arch/arm64/crypto/poly1305-armv8.pl
+++ b/arch/arm64/crypto/poly1305-armv8.pl
@@ -840,7 +840,6 @@ poly1305_blocks_neon:
 	 ldp	d14,d15,[sp,#64]
 	addp	$ACC2,$ACC2,$ACC2
 	 ldr	x30,[sp,#8]
-	 .inst	0xd50323bf		// autiasp
 
 	////////////////////////////////////////////////////////////////
 	// lazy reduction, but without narrowing
@@ -882,6 +881,7 @@ poly1305_blocks_neon:
 	str	x4,[$ctx,#8]		// set is_base2_26
 
 	ldr	x29,[sp],#80
+	 .inst	0xd50323bf		// autiasp
 	ret
 .size	poly1305_blocks_neon,.-poly1305_blocks_neon
 
diff --git a/arch/arm64/crypto/poly1305-core.S_shipped b/arch/arm64/crypto/poly1305-core.S_shipped
index 8d1c4e420ccd..fb2822abf63a 100644
--- a/arch/arm64/crypto/poly1305-core.S_shipped
+++ b/arch/arm64/crypto/poly1305-core.S_shipped
@@ -779,7 +779,6 @@ poly1305_blocks_neon:
 	 ldp	d14,d15,[sp,#64]
 	addp	v21.2d,v21.2d,v21.2d
 	 ldr	x30,[sp,#8]
-	 .inst	0xd50323bf		// autiasp
 
 	////////////////////////////////////////////////////////////////
 	// lazy reduction, but without narrowing
@@ -821,6 +820,7 @@ poly1305_blocks_neon:
 	str	x4,[x0,#8]		// set is_base2_26
 
 	ldr	x29,[sp],#80
+	 .inst	0xd50323bf		// autiasp
 	ret
 .size	poly1305_blocks_neon,.-poly1305_blocks_neon