bpf, arm: Optimize ALU64 ARSH X using orrpl conditional instruction

This patch optimizes the code generated by emit_a32_arsh_r64, which
handles the BPF_ALU64 BPF_ARSH BPF_X instruction.

The original code uses a conditional B followed by an unconditional ORR.
The optimization saves one instruction by removing the B instruction
and using a conditional ORR (with an inverted condition).

Example of the code generated for BPF_ALU64_REG(BPF_ARSH, BPF_REG_0,
BPF_REG_1), before optimization:

  34:  rsb    ip, r2, #32
  38:  subs   r9, r2, #32
  3c:  lsr    lr, r0, r2
  40:  orr    lr, lr, r1, lsl ip
  44:  bmi    0x4c
  48:  orr    lr, lr, r1, asr r9
  4c:  asr    ip, r1, r2
  50:  mov    r0, lr
  54:  mov    r1, ip

and after optimization:

  34:  rsb    ip, r2, #32
  38:  subs   r9, r2, #32
  3c:  lsr    lr, r0, r2
  40:  orr    lr, lr, r1, lsl ip
  44:  orrpl  lr, lr, r1, asr r9
  48:  asr    ip, r1, r2
  4c:  mov    r0, lr
  50:  mov    r1, ip

Tested on QEMU using lib/test_bpf and test_verifier.
Co-developed-by: NXi Wang <xi.wang@gmail.com>
Signed-off-by: NXi Wang <xi.wang@gmail.com>
Signed-off-by: NLuke Nelson <luke.r.nels@gmail.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200501020210.32294-2-luke.r.nels@gmail.com

arch/arm/net/bpf_jit_32.c

@@ -860,8 +860,8 @@ static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[],
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
 	emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx);
-	_emit(ARM_COND_MI, ARM_B(0), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASR, tmp2[0]), ctx);
+	_emit(ARM_COND_PL,
+	      ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASR, tmp2[0]), ctx);
 	emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_ASR, rt), ctx);
 
 	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);