crypto: x86/chacha20 - Avoid spurious jumps to other functions

The chacha_Nblock_xor_avx512vl() functions all have their own,
identical, .LdoneN label, however in one particular spot {2,4} jump to
the 8 version instead of their own. Resulting in:

  arch/x86/crypto/chacha-x86_64.o: warning: objtool: chacha_2block_xor_avx512vl() falls through to next function chacha_8block_xor_avx512vl()
  arch/x86/crypto/chacha-x86_64.o: warning: objtool: chacha_4block_xor_avx512vl() falls through to next function chacha_8block_xor_avx512vl()

Make each function consistently use its own done label.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S
index 946f74dd6fbaa6bbd53480a3b8a087d2113219cd..259383e1ad4409bbaa119c87358a4f83860c239b 100644 (file)
--- a/arch/x86/crypto/chacha-avx512vl-x86_64.S
+++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S
@@ -172,7 +172,7 @@ SYM_FUNC_START(chacha_2block_xor_avx512vl)
        # xor remaining bytes from partial register into output
        mov             %rcx,%rax
        and             $0xf,%rcx
-       jz              .Ldone8
+       jz              .Ldone2
        mov             %rax,%r9
        and             $~0xf,%r9
 
@@ -438,7 +438,7 @@ SYM_FUNC_START(chacha_4block_xor_avx512vl)
        # xor remaining bytes from partial register into output
        mov             %rcx,%rax
        and             $0xf,%rcx
-       jz              .Ldone8
+       jz              .Ldone4
        mov             %rax,%r9
        and             $~0xf,%r9