bpf, riscv: inline bpf_get_current_task() and bpf_get_current_task_btf()

On RISC-V, the current task pointer is stored in the thread pointer
register (tp). Emit a single `mv a5, tp` instead of a full helper
call for BPF_FUNC_get_current_task and BPF_FUNC_get_current_task_btf.

Register bpf_jit_inlines_helper_call() entries for both helpers so the
verifier treats them as inlined, and add the expected `mv a5, tp`
annotation to the riscv64 selftests.

The following show changes before and after this patch.

Before patch:

      auipc  t1,0x817a    # load upper PC-relative address
      jalr   -2004(t1)    # call bpf_get_current_task helper
      mv     a5,a0        # move return value to BPF_REG_0

After patch:

      mv     a5,tp        # directly: a5 = current (tp = thread pointer)

Benchmark (bpf_prog_test_run wrapping bpf_get_current_task in loop,
batch=100, 10s, QEMU RISC-V):

              | runs/sec  | helper-calls/sec | ns/call
 -------------+-----------+------------------+---------
 Before patch |   173,490 |       17,349,090 |      57
 After patch  |   320,497 |       32,049,780 |      31
 -------------+-----------+------------------+---------
 Improvement  |   +84.7%  |          +84.7%  |  -45.6%

Signed-off-by: Varun R Mallya <varunrmallya@gmail.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/r/20260602205847.102825-3-varunrmallya@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 2f1109dbf105b78e6f63a995bb42de5bc3cee1b1..e2c70c70cca8d48c0751a1db6ef52f081d45d942 100644 (file)
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1808,6 +1808,13 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
                        break;
                }
 
+               /* Implement helper call to bpf_get_current_task/_btf() inline */
+               if (insn->src_reg == 0 && (insn->imm == BPF_FUNC_get_current_task ||
+                                          insn->imm == BPF_FUNC_get_current_task_btf)) {
+                       emit_mv(bpf_to_rv_reg(BPF_REG_0, ctx), RV_REG_TP, ctx);
+                       break;
+               }
+
                mark_call(ctx);
                ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
                                            &addr, &fixed_addr);
@@ -2138,6 +2145,8 @@ bool bpf_jit_inlines_helper_call(s32 imm)
 {
        switch (imm) {
        case BPF_FUNC_get_smp_processor_id:
+       case BPF_FUNC_get_current_task:
+       case BPF_FUNC_get_current_task_btf:
                return true;
        default:
                return false;

diff --git a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c
index 885ff69a3a620428550e785263ce427a476735fe..76d80605ec7fd03b763af2be0f892e089ab84c4d 100644 (file)
--- a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c
+++ b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c
@@ -10,6 +10,8 @@ __arch_x86_64
 __jited("      addq    %gs:{{.*}}, %rax")
 __arch_arm64
 __jited("      mrs     x8, SP_EL0")
+__arch_riscv64
+__jited("      mv      a5, tp")
 int inline_bpf_get_current_task(void)
 {
        bpf_get_current_task();