diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 791accb89cf8aa10220d7704e80a489091c7d3f1..185d20c371a3cb52899778c19bb53dc14546709a 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -592,17 +592,21 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 				PPC_MR(dst_reg, b2p[TMP_REG_1]);
 				break;
 			case 64:
-				/*
-				 * Way easier and faster(?) to store the value
-				 * into stack and then use ldbrx
-				 *
-				 * ctx->seen will be reliable in pass2, but
-				 * the instructions generated will remain the
-				 * same across all passes
-				 */
+				/* Store the value to stack and then use byte-reverse loads */
 				PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx));
-				PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx));
-				PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]);
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx)));
+				if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+					EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1]));
+				} else {
+					EMIT(PPC_RAW_LWBRX(dst_reg, 0, b2p[TMP_REG_1]));
+					if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
+						EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, 32));
+					EMIT(PPC_RAW_LI(b2p[TMP_REG_2], 4));
+					EMIT(PPC_RAW_LWBRX(b2p[TMP_REG_2], b2p[TMP_REG_2], b2p[TMP_REG_1]));
+					if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+						EMIT(PPC_RAW_SLDI(b2p[TMP_REG_2], b2p[TMP_REG_2], 32));
+					EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_2]));
+				}
 				break;
 			}
 			break;