LoongArch: BPF: Inline bpf_get_smp_processor_id() helper

The pointer to thread_info is always available in the $tp register,
the call to bpf_get_smp_processor_id() can be inlined into a single
load instruction.

(1) Here is the sample test.c:

  #include <linux/bpf.h>
  #include <bpf/bpf_helpers.h>

  SEC("raw_tp/sys_enter")
  int test_cpuid(void *ctx)
  {
	  return bpf_get_smp_processor_id();
  }
  char _license[] SEC("license") = "GPL";

(2) Here are the test steps:

  sudo yum install libbpf-devel kernel-devel bpftool
  clang -target bpf -O2 -c test.c -o test.o
  sudo sysctl -w net.core.bpf_jit_enable=1
  sudo bpftool prog show name test_cpuid
  sudo rm -f /sys/fs/bpf/test_cpuid
  sudo bpftool prog load test.o /sys/fs/bpf/test_cpuid
  ID=$(sudo bpftool prog show pinned /sys/fs/bpf/test_cpuid | grep -oE '^[0-9]+')
  sudo bpftool prog dump jited id $ID

(3) Here are the test results:

Before: 6 instructions

  ...
  64:	lu12i.w	$t1, 1213
  68:	ori	$t1, $t1, 1680
  6c:	lu32i.d	$t1, 0
  70:	lu52i.d	$t1, $t1, -1792
  74:	jirl	$ra, $t1, 0
  78:	move	$a5, $a0
  ...

After: 1 instruction

  ...
  64:	ld.wu	$a5, $tp, 16
  ...

This is similar with commit 2ddec2c ("riscv, bpf: inline
bpf_get_smp_processor_id()").

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>

Author: seehearfeel

arch/loongarch/net/bpf_jit.c

@@ -5,6 +5,7 @@
  * Copyright (C) 2022 Loongson Technology Corporation Limited
  */
 #include <linux/memory.h>
+#include <asm/asm-offsets.h>
 #include "bpf_jit.h"
 
 #define LOONGARCH_MAX_REG_ARGS 8
@@ -1154,6 +1155,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 			break;
 		}
 
+		/* Implement helper call to bpf_get_smp_processor_id() inline */
+		if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
+			emit_insn(ctx, ldwu, regmap[BPF_REG_0], LOONGARCH_GPR_TP, TI_CPU);
+			break;
+		}
+
 		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
 					    &func_addr, &func_addr_fixed);
 		if (ret < 0)
@@ -2384,6 +2391,7 @@ bool bpf_jit_inlines_helper_call(s32 imm)
 	switch (imm) {
 	case BPF_FUNC_get_current_task:
 	case BPF_FUNC_get_current_task_btf:
+	case BPF_FUNC_get_smp_processor_id:
 		return true;
 	default:
 		return false;