crypto: x86/aesni - Use RIP-relative addressing

Prefer RIP-relative addressing where possible, which removes the need
for boot time relocation fixups. In the GCM case, we can get rid of the
oversized permutation array entirely while at it.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Author: ardbiesheuvel

arch/x86/crypto/aesni-intel_asm.S

@@ -2717,7 +2717,7 @@ SYM_FUNC_END(aesni_cts_cbc_dec)
  *	BSWAP_MASK == endian swapping mask
  */
 SYM_FUNC_START_LOCAL(_aesni_inc_init)
-	movaps .Lbswap_mask, BSWAP_MASK
+	movaps .Lbswap_mask(%rip), BSWAP_MASK
 	movaps IV, CTR
 	pshufb BSWAP_MASK, CTR
 	mov $1, TCTR_LOW

arch/x86/crypto/aesni-intel_avx-x86_64.S

@@ -154,30 +154,6 @@ SHIFT_MASK:      .octa     0x0f0e0d0c0b0a09080706050403020100
 ALL_F:           .octa     0xffffffffffffffffffffffffffffffff
                  .octa     0x00000000000000000000000000000000
 
-.section .rodata
-.align 16
-.type aad_shift_arr, @object
-.size aad_shift_arr, 272
-aad_shift_arr:
-        .octa     0xffffffffffffffffffffffffffffffff
-        .octa     0xffffffffffffffffffffffffffffff0C
-        .octa     0xffffffffffffffffffffffffffff0D0C
-        .octa     0xffffffffffffffffffffffffff0E0D0C
-        .octa     0xffffffffffffffffffffffff0F0E0D0C
-        .octa     0xffffffffffffffffffffff0C0B0A0908
-        .octa     0xffffffffffffffffffff0D0C0B0A0908
-        .octa     0xffffffffffffffffff0E0D0C0B0A0908
-        .octa     0xffffffffffffffff0F0E0D0C0B0A0908
-        .octa     0xffffffffffffff0C0B0A090807060504
-        .octa     0xffffffffffff0D0C0B0A090807060504
-        .octa     0xffffffffff0E0D0C0B0A090807060504
-        .octa     0xffffffff0F0E0D0C0B0A090807060504
-        .octa     0xffffff0C0B0A09080706050403020100
-        .octa     0xffff0D0C0B0A09080706050403020100
-        .octa     0xff0E0D0C0B0A09080706050403020100
-        .octa     0x0F0E0D0C0B0A09080706050403020100
-
-
 .text
 
 
@@ -646,11 +622,13 @@ _get_AAD_rest4\@:
 _get_AAD_rest0\@:
 	/* finalize: shift out the extra bytes we read, and align
 	left. since pslldq can only shift by an immediate, we use
-	vpshufb and an array of shuffle masks */
-	movq    %r12, %r11
-	salq    $4, %r11
-	vmovdqu  aad_shift_arr(%r11), \T1
-	vpshufb \T1, \T7, \T7
+	vpshufb and a pair of shuffle masks */
+	leaq	ALL_F(%rip), %r11
+	subq	%r12, %r11
+	vmovdqu	16(%r11), \T1
+	andq	$~3, %r11
+	vpshufb (%r11), \T7, \T7
+	vpand	\T1, \T7, \T7
 _get_AAD_rest_final\@:
 	vpshufb SHUF_MASK(%rip), \T7, \T7
 	vpxor   \T8, \T7, \T7