powerpc, bpf: Inline bpf_get_smp_processor_id()

Inline the calls to bpf_get_smp_processor_id() in the powerpc bpf jit.

powerpc saves the Logical processor number (paca_index) in paca.

Here is how the powerpc JITed assembly changes after this commit:

Before:

cpu = bpf_get_smp_processor_id();

addis 12, 2, -517
addi 12, 12, -29456
mtctr 12
bctrl
mr	8, 3

After:

cpu = bpf_get_smp_processor_id();

lhz 8, 8(13)

To evaluate the performance improvements introduced by this change,
the benchmark described in [1] was employed.

+---------------+-------------------+-------------------+--------------+
|      Name     |      Before       |        After      |   % change   |
|---------------+-------------------+-------------------+--------------|
| glob-arr-inc  | 41.580 ± 0.034M/s | 54.137 ± 0.019M/s |   + 30.20%   |
| arr-inc       | 39.592 ± 0.055M/s | 54.000 ± 0.026M/s |   + 36.39%   |
| hash-inc      | 25.873 ± 0.012M/s | 26.334 ± 0.058M/s |   + 1.78%    |
+---------------+-------------------+-------------------+--------------+

[1] anakryiko/linux@8dec900975ef

Signed-off-by: Saket Kumar Bhaskar <[email protected]>

Author: Saket Kumar Bhaskar

arch/powerpc/net/bpf_jit_comp.c

@@ -445,6 +445,16 @@ bool bpf_jit_supports_percpu_insn(void)
 	return true;
 }
 
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+	switch (imm) {
+	case BPF_FUNC_get_smp_processor_id:
+		return true;
+	default:
+		return false;
+	}
+}
+
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
 	return bpf_prog_pack_alloc(size, bpf_jit_fill_ill_insns);

arch/powerpc/net/bpf_jit_comp64.c

@@ -1087,6 +1087,11 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 		case BPF_JMP | BPF_CALL:
 			ctx->seen |= SEEN_FUNC;
 
+			if (insn[i].src_reg == 0 && imm == BPF_FUNC_get_smp_processor_id) {
+				EMIT(PPC_RAW_LHZ(bpf_to_ppc(BPF_REG_0), _R13, offsetof(struct paca_struct, paca_index)));
+				break;
+			}
+
 			ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
 						    &func_addr, &func_addr_fixed);
 			if (ret < 0)