diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S
index fe0d84a7ced1..9243f6289d34 100644
--- a/arch/x86/crypto/aria-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S
@@ -267,35 +267,44 @@
 
 #define aria_ark_8way(x0, x1, x2, x3,			\
 		      x4, x5, x6, x7,			\
-		      t0, rk, idx, round)		\
+		      t0, t1, t2, rk,			\
+		      idx, round)			\
 	/* AddRoundKey */                               \
-	vpbroadcastb ((round * 16) + idx + 3)(rk), t0;	\
-	vpxor t0, x0, x0;				\
-	vpbroadcastb ((round * 16) + idx + 2)(rk), t0;	\
-	vpxor t0, x1, x1;				\
-	vpbroadcastb ((round * 16) + idx + 1)(rk), t0;	\
-	vpxor t0, x2, x2;				\
-	vpbroadcastb ((round * 16) + idx + 0)(rk), t0;	\
-	vpxor t0, x3, x3;				\
-	vpbroadcastb ((round * 16) + idx + 7)(rk), t0;	\
-	vpxor t0, x4, x4;				\
-	vpbroadcastb ((round * 16) + idx + 6)(rk), t0;	\
-	vpxor t0, x5, x5;				\
-	vpbroadcastb ((round * 16) + idx + 5)(rk), t0;	\
-	vpxor t0, x6, x6;				\
-	vpbroadcastb ((round * 16) + idx + 4)(rk), t0;	\
-	vpxor t0, x7, x7;
+	vbroadcastss ((round * 16) + idx + 0)(rk), t0;	\
+	vpsrld $24, t0, t2;				\
+	vpshufb t1, t2, t2;				\
+	vpxor t2, x0, x0;				\
+	vpsrld $16, t0, t2;				\
+	vpshufb t1, t2, t2;				\
+	vpxor t2, x1, x1;				\
+	vpsrld $8, t0, t2;				\
+	vpshufb t1, t2, t2;				\
+	vpxor t2, x2, x2;				\
+	vpshufb t1, t0, t2;				\
+	vpxor t2, x3, x3;				\
+	vbroadcastss ((round * 16) + idx + 4)(rk), t0;	\
+	vpsrld $24, t0, t2;				\
+	vpshufb t1, t2, t2;				\
+	vpxor t2, x4, x4;				\
+	vpsrld $16, t0, t2;				\
+	vpshufb t1, t2, t2;				\
+	vpxor t2, x5, x5;				\
+	vpsrld $8, t0, t2;				\
+	vpshufb t1, t2, t2;				\
+	vpxor t2, x6, x6;				\
+	vpshufb t1, t0, t2;				\
+	vpxor t2, x7, x7;
 
 #ifdef CONFIG_AS_GFNI
 #define aria_sbox_8way_gfni(x0, x1, x2, x3,		\
 			    x4, x5, x6, x7,		\
 			    t0, t1, t2, t3,		\
 			    t4, t5, t6, t7)		\
-	vpbroadcastq .Ltf_s2_bitmatrix, t0;		\
-	vpbroadcastq .Ltf_inv_bitmatrix, t1;		\
-	vpbroadcastq .Ltf_id_bitmatrix, t2;		\
-	vpbroadcastq .Ltf_aff_bitmatrix, t3;		\
-	vpbroadcastq .Ltf_x2_bitmatrix, t4;		\
+	vmovdqa .Ltf_s2_bitmatrix, t0;			\
+	vmovdqa .Ltf_inv_bitmatrix, t1;			\
+	vmovdqa .Ltf_id_bitmatrix, t2;			\
+	vmovdqa .Ltf_aff_bitmatrix, t3;			\
+	vmovdqa .Ltf_x2_bitmatrix, t4;			\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1;	\
 	vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5;	\
 	vgf2p8affineqb $(tf_inv_const), t1, x2, x2;	\
@@ -315,10 +324,9 @@
 		       x4, x5, x6, x7,			\
 		       t0, t1, t2, t3,			\
 		       t4, t5, t6, t7)			\
-	vpxor t7, t7, t7;				\
 	vmovdqa .Linv_shift_row, t0;			\
 	vmovdqa .Lshift_row, t1;			\
-	vpbroadcastd .L0f0f0f0f, t6;			\
+	vbroadcastss .L0f0f0f0f, t6;			\
 	vmovdqa .Ltf_lo__inv_aff__and__s2, t2;		\
 	vmovdqa .Ltf_hi__inv_aff__and__s2, t3;		\
 	vmovdqa .Ltf_lo__x2__and__fwd_aff, t4;		\
@@ -413,8 +421,9 @@
 		y0, y1, y2, y3,				\
 		y4, y5, y6, y7,				\
 		mem_tmp, rk, round)			\
+	vpxor y7, y7, y7;				\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 8, round);		\
+		      y0, y7, y2, rk, 8, round);	\
 							\
 	aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5,	\
 		       y0, y1, y2, y3, y4, y5, y6, y7);	\
@@ -429,7 +438,7 @@
 			     x4, x5, x6, x7,		\
 			     mem_tmp, 0);		\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 0, round);		\
+		      y0, y7, y2, rk, 0, round);	\
 							\
 	aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5,	\
 		       y0, y1, y2, y3, y4, y5, y6, y7);	\
@@ -467,8 +476,9 @@
 		y0, y1, y2, y3,				\
 		y4, y5, y6, y7,				\
 		mem_tmp, rk, round)			\
+	vpxor y7, y7, y7;				\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 8, round);		\
+		      y0, y7, y2, rk, 8, round);	\
 							\
 	aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
 		       y0, y1, y2, y3, y4, y5, y6, y7);	\
@@ -483,7 +493,7 @@
 			     x4, x5, x6, x7,		\
 			     mem_tmp, 0);		\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 0, round);		\
+		      y0, y7, y2, rk, 0, round);	\
 							\
 	aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
 		       y0, y1, y2, y3, y4, y5, y6, y7);	\
@@ -521,14 +531,15 @@
 		y0, y1, y2, y3,				\
 		y4, y5, y6, y7,				\
 		mem_tmp, rk, round, last_round)		\
+	vpxor y7, y7, y7;				\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 8, round);		\
+		      y0, y7, y2, rk, 8, round);	\
 							\
 	aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5,	\
 		       y0, y1, y2, y3, y4, y5, y6, y7);	\
 							\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 8, last_round);		\
+		      y0, y7, y2, rk, 8, last_round);	\
 							\
 	aria_store_state_8way(x0, x1, x2, x3,		\
 			      x4, x5, x6, x7,		\
@@ -538,13 +549,13 @@
 			     x4, x5, x6, x7,		\
 			     mem_tmp, 0);		\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 0, round);		\
+		      y0, y7, y2, rk, 0, round);	\
 							\
 	aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5,	\
 		       y0, y1, y2, y3, y4, y5, y6, y7);	\
 							\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 0, last_round);		\
+		      y0, y7, y2, rk, 0, last_round);	\
 							\
 	aria_load_state_8way(y0, y1, y2, y3,		\
 			     y4, y5, y6, y7,		\
@@ -556,8 +567,9 @@
 		     y0, y1, y2, y3,			\
 		     y4, y5, y6, y7,			\
 		     mem_tmp, rk, round)		\
+	vpxor y7, y7, y7;				\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 8, round);		\
+		      y0, y7, y2, rk, 8, round);	\
 							\
 	aria_sbox_8way_gfni(x2, x3, x0, x1, 		\
 			    x6, x7, x4, x5,		\
@@ -574,7 +586,7 @@
 			     x4, x5, x6, x7,		\
 			     mem_tmp, 0);		\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 0, round);		\
+		      y0, y7, y2, rk, 0, round);	\
 							\
 	aria_sbox_8way_gfni(x2, x3, x0, x1, 		\
 			    x6, x7, x4, x5,		\
@@ -614,8 +626,9 @@
 		     y0, y1, y2, y3,			\
 		     y4, y5, y6, y7,			\
 		     mem_tmp, rk, round)		\
+	vpxor y7, y7, y7;				\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 8, round);		\
+		      y0, y7, y2, rk, 8, round);	\
 							\
 	aria_sbox_8way_gfni(x0, x1, x2, x3, 		\
 			    x4, x5, x6, x7,		\
@@ -632,7 +645,7 @@
 			     x4, x5, x6, x7,		\
 			     mem_tmp, 0);		\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 0, round);		\
+		      y0, y7, y2, rk, 0, round);	\
 							\
 	aria_sbox_8way_gfni(x0, x1, x2, x3, 		\
 			    x4, x5, x6, x7,		\
@@ -672,8 +685,9 @@
 		y0, y1, y2, y3,				\
 		y4, y5, y6, y7,				\
 		mem_tmp, rk, round, last_round)		\
+	vpxor y7, y7, y7;				\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 8, round);		\
+		      y0, y7, y2, rk, 8, round);	\
 							\
 	aria_sbox_8way_gfni(x2, x3, x0, x1, 		\
 			    x6, x7, x4, x5,		\
@@ -681,7 +695,7 @@
 			    y4, y5, y6, y7);		\
 							\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 8, last_round);		\
+		      y0, y7, y2, rk, 8, last_round);	\
 							\
 	aria_store_state_8way(x0, x1, x2, x3,		\
 			      x4, x5, x6, x7,		\
@@ -691,7 +705,7 @@
 			     x4, x5, x6, x7,		\
 			     mem_tmp, 0);		\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 0, round);		\
+		      y0, y7, y2, rk, 0, round);	\
 							\
 	aria_sbox_8way_gfni(x2, x3, x0, x1, 		\
 			    x6, x7, x4, x5,		\
@@ -699,7 +713,7 @@
 			    y4, y5, y6, y7);		\
 							\
 	aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7,	\
-		      y0, rk, 0, last_round);		\
+		      y0, y7, y2, rk, 0, last_round);	\
 							\
 	aria_load_state_8way(y0, y1, y2, y3,		\
 			     y4, y5, y6, y7,		\
@@ -772,6 +786,14 @@
 		    BV8(0, 1, 1, 1, 1, 1, 0, 0),
 		    BV8(0, 0, 1, 1, 1, 1, 1, 0),
 		    BV8(0, 0, 0, 1, 1, 1, 1, 1))
+	.quad BM8X8(BV8(1, 0, 0, 0, 1, 1, 1, 1),
+		    BV8(1, 1, 0, 0, 0, 1, 1, 1),
+		    BV8(1, 1, 1, 0, 0, 0, 1, 1),
+		    BV8(1, 1, 1, 1, 0, 0, 0, 1),
+		    BV8(1, 1, 1, 1, 1, 0, 0, 0),
+		    BV8(0, 1, 1, 1, 1, 1, 0, 0),
+		    BV8(0, 0, 1, 1, 1, 1, 1, 0),
+		    BV8(0, 0, 0, 1, 1, 1, 1, 1))
 
 /* AES inverse affine: */
 #define tf_inv_const BV8(1, 0, 1, 0, 0, 0, 0, 0)
@@ -784,6 +806,14 @@
 		    BV8(0, 0, 1, 0, 1, 0, 0, 1),
 		    BV8(1, 0, 0, 1, 0, 1, 0, 0),
 		    BV8(0, 1, 0, 0, 1, 0, 1, 0))
+	.quad BM8X8(BV8(0, 0, 1, 0, 0, 1, 0, 1),
+		    BV8(1, 0, 0, 1, 0, 0, 1, 0),
+		    BV8(0, 1, 0, 0, 1, 0, 0, 1),
+		    BV8(1, 0, 1, 0, 0, 1, 0, 0),
+		    BV8(0, 1, 0, 1, 0, 0, 1, 0),
+		    BV8(0, 0, 1, 0, 1, 0, 0, 1),
+		    BV8(1, 0, 0, 1, 0, 1, 0, 0),
+		    BV8(0, 1, 0, 0, 1, 0, 1, 0))
 
 /* S2: */
 #define tf_s2_const BV8(0, 1, 0, 0, 0, 1, 1, 1)
@@ -796,6 +826,14 @@
 		    BV8(1, 1, 0, 0, 1, 1, 1, 0),
 		    BV8(0, 1, 1, 0, 0, 0, 1, 1),
 		    BV8(1, 1, 1, 1, 0, 1, 1, 0))
+	.quad BM8X8(BV8(0, 1, 0, 1, 0, 1, 1, 1),
+		    BV8(0, 0, 1, 1, 1, 1, 1, 1),
+		    BV8(1, 1, 1, 0, 1, 1, 0, 1),
+		    BV8(1, 1, 0, 0, 0, 0, 1, 1),
+		    BV8(0, 1, 0, 0, 0, 0, 1, 1),
+		    BV8(1, 1, 0, 0, 1, 1, 1, 0),
+		    BV8(0, 1, 1, 0, 0, 0, 1, 1),
+		    BV8(1, 1, 1, 1, 0, 1, 1, 0))
 
 /* X2: */
 #define tf_x2_const BV8(0, 0, 1, 1, 0, 1, 0, 0)
@@ -808,6 +846,14 @@
 		    BV8(0, 1, 1, 0, 1, 0, 1, 1),
 		    BV8(1, 0, 1, 1, 1, 1, 0, 1),
 		    BV8(1, 0, 0, 1, 0, 0, 1, 1))
+	.quad BM8X8(BV8(0, 0, 0, 1, 1, 0, 0, 0),
+		    BV8(0, 0, 1, 0, 0, 1, 1, 0),
+		    BV8(0, 0, 0, 0, 1, 0, 1, 0),
+		    BV8(1, 1, 1, 0, 0, 0, 1, 1),
+		    BV8(1, 1, 1, 0, 1, 1, 0, 0),
+		    BV8(0, 1, 1, 0, 1, 0, 1, 1),
+		    BV8(1, 0, 1, 1, 1, 1, 0, 1),
+		    BV8(1, 0, 0, 1, 0, 0, 1, 1))
 
 /* Identity matrix: */
 .Ltf_id_bitmatrix:
@@ -819,6 +865,14 @@
 		    BV8(0, 0, 0, 0, 0, 1, 0, 0),
 		    BV8(0, 0, 0, 0, 0, 0, 1, 0),
 		    BV8(0, 0, 0, 0, 0, 0, 0, 1))
+	.quad BM8X8(BV8(1, 0, 0, 0, 0, 0, 0, 0),
+		    BV8(0, 1, 0, 0, 0, 0, 0, 0),
+		    BV8(0, 0, 1, 0, 0, 0, 0, 0),
+		    BV8(0, 0, 0, 1, 0, 0, 0, 0),
+		    BV8(0, 0, 0, 0, 1, 0, 0, 0),
+		    BV8(0, 0, 0, 0, 0, 1, 0, 0),
+		    BV8(0, 0, 0, 0, 0, 0, 1, 0),
+		    BV8(0, 0, 0, 0, 0, 0, 0, 1))
 #endif /* CONFIG_AS_GFNI */
 
 /* 4-bit mask */