ARM: net: bpf: use ldr instructions with shifted rm register

Rather than pre-shifting the rm register for the ldr in the tail call,
shift it in the load instruction.  This eliminates one unnecessary
instruction.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

arch/arm/net/bpf_jit_32.c

@@ -1096,8 +1096,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	r_array = arm_bpf_get_reg32(r2[1], tmp2[1], ctx);
 	emit(ARM_ADD_I(tmp[1], r_array, off), ctx);
 	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
-	emit(ARM_MOV_SI(tmp[0], r_index, SRTYPE_ASL, 2), ctx);
-	emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx);
+	emit(ARM_LDR_R_SI(tmp[1], tmp[1], r_index, SRTYPE_ASL, 2), ctx);
 	emit(ARM_CMP_I(tmp[1], 0), ctx);
 	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
 

arch/arm/net/bpf_jit_32.h

@@ -188,6 +188,10 @@
 #define ARM_LDR_R(rt, rn, rm)	(ARM_INST_LDR_R | ARM_INST_LDST__U \
 				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))
+#define ARM_LDR_R_SI(rt, rn, rm, type, imm) \
+				(ARM_INST_LDR_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
+				 | (imm) << 7 | (type) << 5 | (rm))
 #define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | ARM_INST_LDST__U \
 				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))