Commit dabe5167 authored by Josh Poimboeuf's avatar Josh Poimboeuf
Browse files

x86/crypto/camellia-aesni-avx2: Unconditionally allocate stack buffer 



A conditional stack allocation violates traditional unwinding
requirements when a single instruction can have differing stack layouts.

There's no benefit in allocating the stack buffer conditionally.  Just
do it unconditionally.

Signed-off-by: default avatarJosh Poimboeuf <jpoimboe@redhat.com>
Tested-by: default avatarArd Biesheuvel <ardb@kernel.org>
Acked-by: default avatarArd Biesheuvel <ardb@kernel.org>
Tested-by: default avatarSami Tolvanen <samitolvanen@google.com>
Acked-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: default avatarHerbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/r/85ac96613ee5784b6239c18d3f68b1f3c509caa3.1614182415.git.jpoimboe@redhat.com
parent e163be86

arch/x86/crypto/camellia-aesni-avx2-asm_64.S

+2 −3
Original line number Original line Diff line number Diff line
@@ -990,6 +990,7 @@ SYM_FUNC_START(camellia_cbc_dec_32way) 
	 *	%rdx: src (32 blocks)

	 *	%rdx: src (32 blocks)

	 */

	 */

	FRAME_BEGIN

	FRAME_BEGIN

	subq $(16 * 32), %rsp;





	vzeroupper;

	vzeroupper;
@@ -1002,7 +1003,6 @@ SYM_FUNC_START(camellia_cbc_dec_32way) 
		     %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14,

		     %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14,

		     %ymm15, %rdx, (key_table)(CTX, %r8, 8));

		     %ymm15, %rdx, (key_table)(CTX, %r8, 8));





	movq %rsp, %r10;

	cmpq %rsi, %rdx;

	cmpq %rsi, %rdx;

	je .Lcbc_dec_use_stack;

	je .Lcbc_dec_use_stack;
@@ -1015,7 +1015,6 @@ SYM_FUNC_START(camellia_cbc_dec_32way) 
	 * dst still in-use (because dst == src), so use stack for temporary

	 * dst still in-use (because dst == src), so use stack for temporary

	 * storage.

	 * storage.

	 */

	 */

	subq $(16 * 32), %rsp;

	movq %rsp, %rax;

	movq %rsp, %rax;





.Lcbc_dec_continue:

.Lcbc_dec_continue:
@@ -1025,7 +1024,6 @@ SYM_FUNC_START(camellia_cbc_dec_32way) 
	vpxor %ymm7, %ymm7, %ymm7;

	vpxor %ymm7, %ymm7, %ymm7;

	vinserti128 $1, (%rdx), %ymm7, %ymm7;

	vinserti128 $1, (%rdx), %ymm7, %ymm7;

	vpxor (%rax), %ymm7, %ymm7;

	vpxor (%rax), %ymm7, %ymm7;

	movq %r10, %rsp;

	vpxor (0 * 32 + 16)(%rdx), %ymm6, %ymm6;

	vpxor (0 * 32 + 16)(%rdx), %ymm6, %ymm6;

	vpxor (1 * 32 + 16)(%rdx), %ymm5, %ymm5;

	vpxor (1 * 32 + 16)(%rdx), %ymm5, %ymm5;

	vpxor (2 * 32 + 16)(%rdx), %ymm4, %ymm4;

	vpxor (2 * 32 + 16)(%rdx), %ymm4, %ymm4;
@@ -1047,6 +1045,7 @@ SYM_FUNC_START(camellia_cbc_dec_32way) 




	vzeroupper;

	vzeroupper;





	addq $(16 * 32), %rsp;

	FRAME_END

	FRAME_END

	ret;

	ret;

SYM_FUNC_END(camellia_cbc_dec_32way)
 
SYM_FUNC_END(camellia_cbc_dec_32way)