[PATCH] lib/crypto: x86/aes-ctr: Remove some unreachable code

[Eric Biggers]

In the AES-CTR and AES-XCTR code that handles a remainder of '4*VL < LEN
< 8*VL', first 4 full vectors are processed, leaving 0 < LEN < 4*VL.
After that, five different cases are handled depending on whether there
are 0, 1, 2, 3, or 4 full vectors remaining.  But the case of 4 vectors
is never reached there, making the code handling it unused.  Remove it.

With that done, the '.Lxor_tail_partial_vec_3\@' block would be reached
only via an unconditional jump.  Therefore, relocate it to the only
place that jumps to it.  This allows removing the jump at the end of the
'.Lxor_tail_partial_vec_2\@' block and making it fall through.

Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx>
---
 lib/crypto/x86/aes-ctr-avx-x86_64.S | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/lib/crypto/x86/aes-ctr-avx-x86_64.S b/lib/crypto/x86/aes-ctr-avx-x86_64.S
index c232337899b6..13b3e2cfae37 100644
--- a/lib/crypto/x86/aes-ctr-avx-x86_64.S
+++ b/lib/crypto/x86/aes-ctr-avx-x86_64.S
@@ -419,10 +419,12 @@
 	cmp		$3*VL-1, LEN32
 	jle		.Lxor_tail_partial_vec_2\@
 	_xor_data	2
-	cmp		$4*VL-1, LEN32
-	jle		.Lxor_tail_partial_vec_3\@
-	_xor_data	3
-	jmp		.Ldone\@
+	add		$-3*VL, LEN32
+	jz		.Ldone\@
+	sub		$-3*VL, SRC
+	sub		$-3*VL, DST
+	_vmovdqa	AESDATA3, AESDATA0
+	jmp		.Lxor_tail_partial_vec_0\@
 
 .Lenc_tail_atmost4vecs\@:
 	cmp		$2*VL, LEN32
@@ -469,14 +471,6 @@
 	sub		$-2*VL, SRC
 	sub		$-2*VL, DST
 	_vmovdqa	AESDATA2, AESDATA0
-	jmp		.Lxor_tail_partial_vec_0\@
-
-.Lxor_tail_partial_vec_3\@:
-	add		$-3*VL, LEN32
-	jz		.Ldone\@
-	sub		$-3*VL, SRC
-	sub		$-3*VL, DST
-	_vmovdqa	AESDATA3, AESDATA0
 
 .Lxor_tail_partial_vec_0\@:
 	// XOR the remaining 1 <= LEN < VL bytes.  It's easy if masked

base-commit: 9ca77aa621027149c43551308112eba06b1de3af
-- 
2.56.0